Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@web.de>
Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@ascom.ch>
Mark Brown <broonie@sirena.org.uk>
+Martin Kepplinger <martink@posteo.de> <martin.kepplinger@theobroma-systems.com>
+Martin Kepplinger <martink@posteo.de> <martin.kepplinger@ginzinger.com>
Matthieu CASTET <castet.matthieu@free.fr>
Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@brturbo.com.br>
Mauro Carvalho Chehab <mchehab@kernel.org> <maurochehab@gmail.com>
Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@virtuozzo.com>
Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@parallels.com>
Takashi YOSHII <takashi.yoshii.zj@renesas.com>
+Yakir Yang <kuankuan.y@gmail.com> <ykk@rock-chips.com>
Yusuke Goda <goda.yusuke@renesas.com>
Gustavo Padovan <gustavo@las.ic.unicamp.br>
Gustavo Padovan <padovan@profusion.mobi>
S: Boulder, Colorado 80302
S: USA
+N: Hans-Christian Noren Egtvedt
+E: egtvedt@samfundet.no
+D: AVR32 architecture maintainer.
+
N: Heiko Eißfeldt
E: heiko@colossus.escape.de heiko@unifix.de
D: verify_area stuff, generic SCSI fixes
S: Markham, Ontario L3R 2Z6
S: Canada
+N: Haavard Skinnemoen
+M: Haavard Skinnemoen <hskinnemoen@gmail.com>
+D: AVR32 architecture port to Linux and maintainer.
+
N: Rick Sladkey
E: jrs@world.std.com
D: utility hacker: Emacs, NFS server, mount, kmem-ps, UPS debugger, strace, GDB
--- /dev/null
+What: /sys/firmware/acpi/hotplug/force_remove
+Date: Mar 2017
+Contact: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+Description:
+ Since the force_remove is inherently broken and dangerous to
+ use for some hotplugable resources like memory (because ignoring
+ the offline failure might lead to memory corruption and crashes)
+ enabling this knob is not safe and thus unsupported.
Date: May 2011
Contact: Martin K. Petersen <martin.petersen@oracle.com>
Description:
- Devices that support discard functionality may return
- stale or random data when a previously discarded block
- is read back. This can cause problems if the filesystem
- expects discarded blocks to be explicitly cleared. If a
- device reports that it deterministically returns zeroes
- when a discarded area is read the discard_zeroes_data
- parameter will be set to one. Otherwise it will be 0 and
- the result of reading a discarded area is undefined.
+ Will always return 0. Don't rely on any specific behavior
+ for discards, and don't read this file.
What: /sys/block/<disk>/queue/write_same_max_bytes
Date: January 2012
or 0 (unset). Attempts to write any other values to it will
cause -EINVAL to be returned.
-What: /sys/firmware/acpi/hotplug/force_remove
-Date: May 2013
-Contact: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
-Description:
- The number in this file (0 or 1) determines whether (1) or not
- (0) the ACPI subsystem will allow devices to be hot-removed even
- if they cannot be put offline gracefully (from the kernel's
- viewpoint). That number can be changed by writing a boolean
- value to this file.
-
What: /sys/firmware/acpi/interrupts/
Date: February 2008
Contact: Len Brown <lenb@kernel.org>
--- /dev/null
+Graphs
+
+
+_DSD
+----
+
+_DSD (Device Specific Data) [7] is a predefined ACPI device
+configuration object that can be used to convey information on
+hardware features which are not specifically covered by the ACPI
+specification [1][6]. There are two _DSD extensions that are relevant
+for graphs: property [4] and hierarchical data extensions [5]. The
+property extension provides generic key-value pairs whereas the
+hierarchical data extension supports nodes with references to other
+nodes, forming a tree. The nodes in the tree may contain properties as
+defined by the property extension. The two extensions together provide
+a tree-like structure with zero or more properties (key-value pairs)
+in each node of the tree.
+
+The data structure may be accessed at runtime by using the device_*
+and fwnode_* functions defined in include/linux/fwnode.h .
+
+Fwnode represents a generic firmware node object. It is independent on
+the firmware type. In ACPI, fwnodes are _DSD hierarchical data
+extensions objects. A device's _DSD object is represented by an
+fwnode.
+
+The data structure may be referenced to elsewhere in the ACPI tables
+by using a hard reference to the device itself and an index to the
+hierarchical data extension array on each depth.
+
+
+Ports and endpoints
+-------------------
+
+The port and endpoint concepts are very similar to those in Devicetree
+[3]. A port represents an interface in a device, and an endpoint
+represents a connection to that interface.
+
+All port nodes are located under the device's "_DSD" node in the
+hierarchical data extension tree. The property extension related to
+each port node must contain the key "port" and an integer value which
+is the number of the port. The object it refers to should be called "PRTX",
+where "X" is the number of the port.
+
+Further on, endpoints are located under the individual port nodes. The
+first hierarchical data extension package list entry of the endpoint
+nodes must begin with "endpoint" and must be followed by the number
+of the endpoint. The object it refers to should be called "EPXY", where
+"X" is the number of the port and "Y" is the number of the endpoint.
+
+Each port node contains a property extension key "port", the value of
+which is the number of the port node. The each endpoint is similarly numbered
+with a property extension key "endpoint". Port numbers must be unique within a
+device and endpoint numbers must be unique within a port.
+
+The endpoint reference uses property extension with "remote-endpoint" property
+name followed by a reference in the same package. Such references consist of the
+the remote device reference, number of the port in the device and finally the
+number of the endpoint in that port. Individual references thus appear as:
+
+ Package() { device, port_number, endpoint_number }
+
+The references to endpoints must be always done both ways, to the
+remote endpoint and back from the referred remote endpoint node.
+
+A simple example of this is show below:
+
+ Scope (\_SB.PCI0.I2C2)
+ {
+ Device (CAM0)
+ {
+ Name (_DSD, Package () {
+ ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+ Package () {
+ Package () { "compatible", Package () { "nokia,smia" } },
+ },
+ ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
+ Package () {
+ Package () { "port0", "PRT0" },
+ }
+ })
+ Name (PRT0, Package() {
+ ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+ Package () {
+ Package () { "port", 0 },
+ },
+ ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
+ Package () {
+ Package () { "endpoint0", "EP00" },
+ }
+ })
+ Name (EP00, Package() {
+ ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+ Package () {
+ Package () { "endpoint", 0 },
+ Package () { "remote-endpoint", Package() { \_SB.PCI0.ISP, 4, 0 } },
+ }
+ })
+ }
+ }
+
+ Scope (\_SB.PCI0)
+ {
+ Device (ISP)
+ {
+ Name (_DSD, Package () {
+ ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
+ Package () {
+ Package () { "port4", "PRT4" },
+ }
+ })
+
+ Name (PRT4, Package() {
+ ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+ Package () {
+ Package () { "port", 4 }, /* CSI-2 port number */
+ },
+ ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
+ Package () {
+ Package () { "endpoint0", "EP40" },
+ }
+ })
+
+ Name (EP40, Package() {
+ ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+ Package () {
+ Package () { "endpoint", 0 },
+ Package () { "remote-endpoint", Package () { \_SB.PCI0.I2C2.CAM0, 0, 0 } },
+ }
+ })
+ }
+ }
+
+Here, the port 0 of the "CAM0" device is connected to the port 4 of
+the "ISP" device and vice versa.
+
+
+References
+----------
+
+[1] _DSD (Device Specific Data) Implementation Guide.
+ <URL:http://www.uefi.org/sites/default/files/resources/_DSD-implementation-guide-toplevel-1_1.htm>,
+ referenced 2016-10-03.
+
+[2] Devicetree. <URL:http://www.devicetree.org>, referenced 2016-10-03.
+
+[3]Â Documentation/devicetree/bindings/graph.txt
+
+[4] Device Properties UUID For _DSD.
+ <URL:http://www.uefi.org/sites/default/files/resources/_DSD-device-properties-UUID.pdf>,
+ referenced 2016-10-04.
+
+[5] Hierarchical Data Extension UUID For _DSD.
+ <URL:http://www.uefi.org/sites/default/files/resources/_DSD-hierarchical-data-extension-UUID-v1.pdf>,
+ referenced 2016-10-04.
+
+[6] Advanced Configuration and Power Interface Specification.
+ <URL:http://www.uefi.org/sites/default/files/resources/ACPI_6_1.pdf>,
+ referenced 2016-10-04.
+
+[7] _DSD Device Properties Usage Rules.
+ Documentation/acpi/DSD-properties-rules.txt
The homepage of ACPICA project is: www.acpica.org, it is maintained and
supported by Intel Corporation.
- The following figure depicts the Linux ACPI subystem where the ACPICA
+ The following figure depicts the Linux ACPI subsystem where the ACPICA
adaptation is included:
+---------------------------------------------------------+
Linux patches. The patches generated by this process are referred to as
"linuxized ACPICA patches". The release process is carried out on a local
copy the ACPICA git repository. Each commit in the monthly release is
- converted into a linuxized ACPICA patch. Together, they form the montly
+ converted into a linuxized ACPICA patch. Together, they form the monthly
ACPICA release patchset for the Linux ACPI community. This process is
illustrated in the following figure:
<http://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git>.
Before the linuxized ACPICA patches are sent to the Linux ACPI community
- for review, there is a quality ensurance build test process to reduce
+ for review, there is a quality assurance build test process to reduce
porting issues. Currently this build process only takes care of the
following kernel configuration options:
CONFIG_ACPI/CONFIG_ACPI_DEBUG/CONFIG_ACPI_DEBUGGER
release utilities (please refer to Section 4 below for the details).
3. Linux specific features - Sometimes it's impossible to use the
current ACPICA APIs to implement features required by the Linux kernel,
- so Linux developers occasionaly have to change ACPICA code directly.
+ so Linux developers occasionally have to change ACPICA code directly.
Those changes may not be acceptable by ACPICA upstream and in such cases
they are left as committed ACPICA divergences unless the ACPICA side can
implement new mechanisms as replacements for them.
4. ACPICA release fixups - ACPICA only tests commits using a set of the
- user space simulation utilies, thus the linuxized ACPICA patches may
+ user space simulation utilities, thus the linuxized ACPICA patches may
break the Linux kernel, leaving us build/boot failures. In order to
avoid breaking Linux bisection, fixes are applied directly to the
linuxized ACPICA patches during the release process. When the release
today Linux also runs on (at least) the Compaq Alpha AXP, Sun SPARC and
UltraSPARC, Motorola 68000, PowerPC, PowerPC64, ARM, Hitachi SuperH, Cell,
IBM S/390, MIPS, HP PA-RISC, Intel IA-64, DEC VAX, AMD x86-64, AXIS CRIS,
- Xtensa, Tilera TILE, AVR32, ARC and Renesas M32R architectures.
+ Xtensa, Tilera TILE, ARC and Renesas M32R architectures.
Linux is easily portable to most general-purpose 32- or 64-bit architectures
as long as they have a paged memory management unit (PMMU) and a port of the
APIC APIC support is enabled.
APM Advanced Power Management support is enabled.
ARM ARM architecture is enabled.
- AVR32 AVR32 architecture is enabled.
AX25 Appropriate AX.25 support is enabled.
BLACKFIN Blackfin architecture is enabled.
CLK Common clock infrastructure is enabled.
[ACPI] acpi_pm
[ARM] imx_timer1,OSTS,netx_timer,mpu_timer2,
pxa_timer,timer3,32k_counter,timer0_1
- [AVR32] avr32
[X86-32] pit,hpet,tsc;
scx200_hrt on Geode; cyclone on IBM x440
[MIPS] MIPS
osd-targets. Please see:
Documentation/filesystems/pnfs.txt for more explanations
- nmi_debug= [KNL,AVR32,SH] Specify one or more actions to take
+ nmi_debug= [KNL,SH] Specify one or more actions to take
when a NMI is triggered.
Format: [state][,regs][,debounce][,die]
ramdisk_size= [RAM] Sizes of RAM disks in kilobytes
See Documentation/blockdev/ramdisk.txt.
+ ras=option[,option,...] [KNL] RAS-specific options
+
+ cec_disable [X86]
+ Disable the Correctable Errors Collector,
+ see CONFIG_RAS_CEC help text.
+
rcu_nocbs= [KNL]
The argument is a cpu list, as described above.
| ARM | Cortex-A57 | #852523 | N/A |
| ARM | Cortex-A57 | #834220 | ARM64_ERRATUM_834220 |
| ARM | Cortex-A72 | #853709 | N/A |
+| ARM | Cortex-A73 | #858921 | ARM64_ERRATUM_858921 |
| ARM | MMU-500 | #841119,#826419 | N/A |
| | | | |
| Cavium | ThunderX ITS | #22375, #24313 | CAVIUM_ERRATUM_22375 |
00-INDEX
- This file
+bfq-iosched.txt
+ - BFQ IO scheduler and its tunables
biodoc.txt
- Notes on the Generic Block Layer Rewrite in Linux 2.5
biovecs.txt
--- /dev/null
+BFQ (Budget Fair Queueing)
+==========================
+
+BFQ is a proportional-share I/O scheduler, with some extra
+low-latency capabilities. In addition to cgroups support (blkio or io
+controllers), BFQ's main features are:
+- BFQ guarantees a high system and application responsiveness, and a
+ low latency for time-sensitive applications, such as audio or video
+ players;
+- BFQ distributes bandwidth, and not just time, among processes or
+ groups (switching back to time distribution when needed to keep
+ throughput high).
+
+On average CPUs, the current version of BFQ can handle devices
+performing at most ~30K IOPS; at most ~50 KIOPS on faster CPUs. As a
+reference, 30-50 KIOPS correspond to very high bandwidths with
+sequential I/O (e.g., 8-12 GB/s if I/O requests are 256 KB large), and
+to 120-200 MB/s with 4KB random I/O. BFQ has not yet been tested on
+multi-queue devices.
+
+The table of contents follow. Impatients can just jump to Section 3.
+
+CONTENTS
+
+1. When may BFQ be useful?
+ 1-1 Personal systems
+ 1-2 Server systems
+2. How does BFQ work?
+3. What are BFQ's tunable?
+4. BFQ group scheduling
+ 4-1 Service guarantees provided
+ 4-2 Interface
+
+1. When may BFQ be useful?
+==========================
+
+BFQ provides the following benefits on personal and server systems.
+
+1-1 Personal systems
+--------------------
+
+Low latency for interactive applications
+
+Regardless of the actual background workload, BFQ guarantees that, for
+interactive tasks, the storage device is virtually as responsive as if
+it was idle. For example, even if one or more of the following
+background workloads are being executed:
+- one or more large files are being read, written or copied,
+- a tree of source files is being compiled,
+- one or more virtual machines are performing I/O,
+- a software update is in progress,
+- indexing daemons are scanning filesystems and updating their
+ databases,
+starting an application or loading a file from within an application
+takes about the same time as if the storage device was idle. As a
+comparison, with CFQ, NOOP or DEADLINE, and in the same conditions,
+applications experience high latencies, or even become unresponsive
+until the background workload terminates (also on SSDs).
+
+Low latency for soft real-time applications
+
+Also soft real-time applications, such as audio and video
+players/streamers, enjoy a low latency and a low drop rate, regardless
+of the background I/O workload. As a consequence, these applications
+do not suffer from almost any glitch due to the background workload.
+
+Higher speed for code-development tasks
+
+If some additional workload happens to be executed in parallel, then
+BFQ executes the I/O-related components of typical code-development
+tasks (compilation, checkout, merge, ...) much more quickly than CFQ,
+NOOP or DEADLINE.
+
+High throughput
+
+On hard disks, BFQ achieves up to 30% higher throughput than CFQ, and
+up to 150% higher throughput than DEADLINE and NOOP, with all the
+sequential workloads considered in our tests. With random workloads,
+and with all the workloads on flash-based devices, BFQ achieves,
+instead, about the same throughput as the other schedulers.
+
+Strong fairness, bandwidth and delay guarantees
+
+BFQ distributes the device throughput, and not just the device time,
+among I/O-bound applications in proportion their weights, with any
+workload and regardless of the device parameters. From these bandwidth
+guarantees, it is possible to compute tight per-I/O-request delay
+guarantees by a simple formula. If not configured for strict service
+guarantees, BFQ switches to time-based resource sharing (only) for
+applications that would otherwise cause a throughput loss.
+
+1-2 Server systems
+------------------
+
+Most benefits for server systems follow from the same service
+properties as above. In particular, regardless of whether additional,
+possibly heavy workloads are being served, BFQ guarantees:
+
+. audio and video-streaming with zero or very low jitter and drop
+ rate;
+
+. fast retrieval of WEB pages and embedded objects;
+
+. real-time recording of data in live-dumping applications (e.g.,
+ packet logging);
+
+. responsiveness in local and remote access to a server.
+
+
+2. How does BFQ work?
+=====================
+
+BFQ is a proportional-share I/O scheduler, whose general structure,
+plus a lot of code, are borrowed from CFQ.
+
+- Each process doing I/O on a device is associated with a weight and a
+ (bfq_)queue.
+
+- BFQ grants exclusive access to the device, for a while, to one queue
+ (process) at a time, and implements this service model by
+ associating every queue with a budget, measured in number of
+ sectors.
+
+ - After a queue is granted access to the device, the budget of the
+ queue is decremented, on each request dispatch, by the size of the
+ request.
+
+ - The in-service queue is expired, i.e., its service is suspended,
+ only if one of the following events occurs: 1) the queue finishes
+ its budget, 2) the queue empties, 3) a "budget timeout" fires.
+
+ - The budget timeout prevents processes doing random I/O from
+ holding the device for too long and dramatically reducing
+ throughput.
+
+ - Actually, as in CFQ, a queue associated with a process issuing
+ sync requests may not be expired immediately when it empties. In
+ contrast, BFQ may idle the device for a short time interval,
+ giving the process the chance to go on being served if it issues
+ a new request in time. Device idling typically boosts the
+ throughput on rotational devices, if processes do synchronous
+ and sequential I/O. In addition, under BFQ, device idling is
+ also instrumental in guaranteeing the desired throughput
+ fraction to processes issuing sync requests (see the description
+ of the slice_idle tunable in this document, or [1, 2], for more
+ details).
+
+ - With respect to idling for service guarantees, if several
+ processes are competing for the device at the same time, but
+ all processes (and groups, after the following commit) have
+ the same weight, then BFQ guarantees the expected throughput
+ distribution without ever idling the device. Throughput is
+ thus as high as possible in this common scenario.
+
+ - If low-latency mode is enabled (default configuration), BFQ
+ executes some special heuristics to detect interactive and soft
+ real-time applications (e.g., video or audio players/streamers),
+ and to reduce their latency. The most important action taken to
+ achieve this goal is to give to the queues associated with these
+ applications more than their fair share of the device
+ throughput. For brevity, we call just "weight-raising" the whole
+ sets of actions taken by BFQ to privilege these queues. In
+ particular, BFQ provides a milder form of weight-raising for
+ interactive applications, and a stronger form for soft real-time
+ applications.
+
+ - BFQ automatically deactivates idling for queues born in a burst of
+ queue creations. In fact, these queues are usually associated with
+ the processes of applications and services that benefit mostly
+ from a high throughput. Examples are systemd during boot, or git
+ grep.
+
+ - As CFQ, BFQ merges queues performing interleaved I/O, i.e.,
+ performing random I/O that becomes mostly sequential if
+ merged. Differently from CFQ, BFQ achieves this goal with a more
+ reactive mechanism, called Early Queue Merge (EQM). EQM is so
+ responsive in detecting interleaved I/O (cooperating processes),
+ that it enables BFQ to achieve a high throughput, by queue
+ merging, even for queues for which CFQ needs a different
+ mechanism, preemption, to get a high throughput. As such EQM is a
+ unified mechanism to achieve a high throughput with interleaved
+ I/O.
+
+ - Queues are scheduled according to a variant of WF2Q+, named
+ B-WF2Q+, and implemented using an augmented rb-tree to preserve an
+ O(log N) overall complexity. See [2] for more details. B-WF2Q+ is
+ also ready for hierarchical scheduling. However, for a cleaner
+ logical breakdown, the code that enables and completes
+ hierarchical support is provided in the next commit, which focuses
+ exactly on this feature.
+
+ - B-WF2Q+ guarantees a tight deviation with respect to an ideal,
+ perfectly fair, and smooth service. In particular, B-WF2Q+
+ guarantees that each queue receives a fraction of the device
+ throughput proportional to its weight, even if the throughput
+ fluctuates, and regardless of: the device parameters, the current
+ workload and the budgets assigned to the queue.
+
+ - The last, budget-independence, property (although probably
+ counterintuitive in the first place) is definitely beneficial, for
+ the following reasons:
+
+ - First, with any proportional-share scheduler, the maximum
+ deviation with respect to an ideal service is proportional to
+ the maximum budget (slice) assigned to queues. As a consequence,
+ BFQ can keep this deviation tight not only because of the
+ accurate service of B-WF2Q+, but also because BFQ *does not*
+ need to assign a larger budget to a queue to let the queue
+ receive a higher fraction of the device throughput.
+
+ - Second, BFQ is free to choose, for every process (queue), the
+ budget that best fits the needs of the process, or best
+ leverages the I/O pattern of the process. In particular, BFQ
+ updates queue budgets with a simple feedback-loop algorithm that
+ allows a high throughput to be achieved, while still providing
+ tight latency guarantees to time-sensitive applications. When
+ the in-service queue expires, this algorithm computes the next
+ budget of the queue so as to:
+
+ - Let large budgets be eventually assigned to the queues
+ associated with I/O-bound applications performing sequential
+ I/O: in fact, the longer these applications are served once
+ got access to the device, the higher the throughput is.
+
+ - Let small budgets be eventually assigned to the queues
+ associated with time-sensitive applications (which typically
+ perform sporadic and short I/O), because, the smaller the
+ budget assigned to a queue waiting for service is, the sooner
+ B-WF2Q+ will serve that queue (Subsec 3.3 in [2]).
+
+- If several processes are competing for the device at the same time,
+ but all processes and groups have the same weight, then BFQ
+ guarantees the expected throughput distribution without ever idling
+ the device. It uses preemption instead. Throughput is then much
+ higher in this common scenario.
+
+- ioprio classes are served in strict priority order, i.e.,
+ lower-priority queues are not served as long as there are
+ higher-priority queues. Among queues in the same class, the
+ bandwidth is distributed in proportion to the weight of each
+ queue. A very thin extra bandwidth is however guaranteed to
+ the Idle class, to prevent it from starving.
+
+
+3. What are BFQ's tunable?
+==========================
+
+The tunables back_seek-max, back_seek_penalty, fifo_expire_async and
+fifo_expire_sync below are the same as in CFQ. Their description is
+just copied from that for CFQ. Some considerations in the description
+of slice_idle are copied from CFQ too.
+
+per-process ioprio and weight
+-----------------------------
+
+Unless the cgroups interface is used (see "4. BFQ group scheduling"),
+weights can be assigned to processes only indirectly, through I/O
+priorities, and according to the relation:
+weight = (IOPRIO_BE_NR - ioprio) * 10.
+
+Beware that, if low-latency is set, then BFQ automatically raises the
+weight of the queues associated with interactive and soft real-time
+applications. Unset this tunable if you need/want to control weights.
+
+slice_idle
+----------
+
+This parameter specifies how long BFQ should idle for next I/O
+request, when certain sync BFQ queues become empty. By default
+slice_idle is a non-zero value. Idling has a double purpose: boosting
+throughput and making sure that the desired throughput distribution is
+respected (see the description of how BFQ works, and, if needed, the
+papers referred there).
+
+As for throughput, idling can be very helpful on highly seeky media
+like single spindle SATA/SAS disks where we can cut down on overall
+number of seeks and see improved throughput.
+
+Setting slice_idle to 0 will remove all the idling on queues and one
+should see an overall improved throughput on faster storage devices
+like multiple SATA/SAS disks in hardware RAID configuration.
+
+So depending on storage and workload, it might be useful to set
+slice_idle=0. In general for SATA/SAS disks and software RAID of
+SATA/SAS disks keeping slice_idle enabled should be useful. For any
+configurations where there are multiple spindles behind single LUN
+(Host based hardware RAID controller or for storage arrays), setting
+slice_idle=0 might end up in better throughput and acceptable
+latencies.
+
+Idling is however necessary to have service guarantees enforced in
+case of differentiated weights or differentiated I/O-request lengths.
+To see why, suppose that a given BFQ queue A must get several I/O
+requests served for each request served for another queue B. Idling
+ensures that, if A makes a new I/O request slightly after becoming
+empty, then no request of B is dispatched in the middle, and thus A
+does not lose the possibility to get more than one request dispatched
+before the next request of B is dispatched. Note that idling
+guarantees the desired differentiated treatment of queues only in
+terms of I/O-request dispatches. To guarantee that the actual service
+order then corresponds to the dispatch order, the strict_guarantees
+tunable must be set too.
+
+There is an important flipside for idling: apart from the above cases
+where it is beneficial also for throughput, idling can severely impact
+throughput. One important case is random workload. Because of this
+issue, BFQ tends to avoid idling as much as possible, when it is not
+beneficial also for throughput. As a consequence of this behavior, and
+of further issues described for the strict_guarantees tunable,
+short-term service guarantees may be occasionally violated. And, in
+some cases, these guarantees may be more important than guaranteeing
+maximum throughput. For example, in video playing/streaming, a very
+low drop rate may be more important than maximum throughput. In these
+cases, consider setting the strict_guarantees parameter.
+
+strict_guarantees
+-----------------
+
+If this parameter is set (default: unset), then BFQ
+
+- always performs idling when the in-service queue becomes empty;
+
+- forces the device to serve one I/O request at a time, by dispatching a
+ new request only if there is no outstanding request.
+
+In the presence of differentiated weights or I/O-request sizes, both
+the above conditions are needed to guarantee that every BFQ queue
+receives its allotted share of the bandwidth. The first condition is
+needed for the reasons explained in the description of the slice_idle
+tunable. The second condition is needed because all modern storage
+devices reorder internally-queued requests, which may trivially break
+the service guarantees enforced by the I/O scheduler.
+
+Setting strict_guarantees may evidently affect throughput.
+
+back_seek_max
+-------------
+
+This specifies, given in Kbytes, the maximum "distance" for backward seeking.
+The distance is the amount of space from the current head location to the
+sectors that are backward in terms of distance.
+
+This parameter allows the scheduler to anticipate requests in the "backward"
+direction and consider them as being the "next" if they are within this
+distance from the current head location.
+
+back_seek_penalty
+-----------------
+
+This parameter is used to compute the cost of backward seeking. If the
+backward distance of request is just 1/back_seek_penalty from a "front"
+request, then the seeking cost of two requests is considered equivalent.
+
+So scheduler will not bias toward one or the other request (otherwise scheduler
+will bias toward front request). Default value of back_seek_penalty is 2.
+
+fifo_expire_async
+-----------------
+
+This parameter is used to set the timeout of asynchronous requests. Default
+value of this is 248ms.
+
+fifo_expire_sync
+----------------
+
+This parameter is used to set the timeout of synchronous requests. Default
+value of this is 124ms. In case to favor synchronous requests over asynchronous
+one, this value should be decreased relative to fifo_expire_async.
+
+low_latency
+-----------
+
+This parameter is used to enable/disable BFQ's low latency mode. By
+default, low latency mode is enabled. If enabled, interactive and soft
+real-time applications are privileged and experience a lower latency,
+as explained in more detail in the description of how BFQ works.
+
+DO NOT enable this mode if you need full control on bandwidth
+distribution. In fact, if it is enabled, then BFQ automatically
+increases the bandwidth share of privileged applications, as the main
+means to guarantee a lower latency to them.
+
+timeout_sync
+------------
+
+Maximum amount of device time that can be given to a task (queue) once
+it has been selected for service. On devices with costly seeks,
+increasing this time usually increases maximum throughput. On the
+opposite end, increasing this time coarsens the granularity of the
+short-term bandwidth and latency guarantees, especially if the
+following parameter is set to zero.
+
+max_budget
+----------
+
+Maximum amount of service, measured in sectors, that can be provided
+to a BFQ queue once it is set in service (of course within the limits
+of the above timeout). According to what said in the description of
+the algorithm, larger values increase the throughput in proportion to
+the percentage of sequential I/O requests issued. The price of larger
+values is that they coarsen the granularity of short-term bandwidth
+and latency guarantees.
+
+The default value is 0, which enables auto-tuning: BFQ sets max_budget
+to the maximum number of sectors that can be served during
+timeout_sync, according to the estimated peak rate.
+
+weights
+-------
+
+Read-only parameter, used to show the weights of the currently active
+BFQ queues.
+
+
+wr_ tunables
+------------
+
+BFQ exports a few parameters to control/tune the behavior of
+low-latency heuristics.
+
+wr_coeff
+
+Factor by which the weight of a weight-raised queue is multiplied. If
+the queue is deemed soft real-time, then the weight is further
+multiplied by an additional, constant factor.
+
+wr_max_time
+
+Maximum duration of a weight-raising period for an interactive task
+(ms). If set to zero (default value), then this value is computed
+automatically, as a function of the peak rate of the device. In any
+case, when the value of this parameter is read, it always reports the
+current duration, regardless of whether it has been set manually or
+computed automatically.
+
+wr_max_softrt_rate
+
+Maximum service rate below which a queue is deemed to be associated
+with a soft real-time application, and is then weight-raised
+accordingly (sectors/sec).
+
+wr_min_idle_time
+
+Minimum idle period after which interactive weight-raising may be
+reactivated for a queue (in ms).
+
+wr_rt_max_time
+
+Maximum weight-raising duration for soft real-time queues (in ms). The
+start time from which this duration is considered is automatically
+moved forward if the queue is detected to be still soft real-time
+before the current soft real-time weight-raising period finishes.
+
+wr_min_inter_arr_async
+
+Minimum period between I/O request arrivals after which weight-raising
+may be reactivated for an already busy async queue (in ms).
+
+
+4. Group scheduling with BFQ
+============================
+
+BFQ supports both cgroups-v1 and cgroups-v2 io controllers, namely
+blkio and io. In particular, BFQ supports weight-based proportional
+share. To activate cgroups support, set BFQ_GROUP_IOSCHED.
+
+4-1 Service guarantees provided
+-------------------------------
+
+With BFQ, proportional share means true proportional share of the
+device bandwidth, according to group weights. For example, a group
+with weight 200 gets twice the bandwidth, and not just twice the time,
+of a group with weight 100.
+
+BFQ supports hierarchies (group trees) of any depth. Bandwidth is
+distributed among groups and processes in the expected way: for each
+group, the children of the group share the whole bandwidth of the
+group in proportion to their weights. In particular, this implies
+that, for each leaf group, every process of the group receives the
+same share of the whole group bandwidth, unless the ioprio of the
+process is modified.
+
+The resource-sharing guarantee for a group may partially or totally
+switch from bandwidth to time, if providing bandwidth guarantees to
+the group lowers the throughput too much. This switch occurs on a
+per-process basis: if a process of a leaf group causes throughput loss
+if served in such a way to receive its share of the bandwidth, then
+BFQ switches back to just time-based proportional share for that
+process.
+
+4-2 Interface
+-------------
+
+To get proportional sharing of bandwidth with BFQ for a given device,
+BFQ must of course be the active scheduler for that device.
+
+Within each group directory, the names of the files associated with
+BFQ-specific cgroup parameters and stats begin with the "bfq."
+prefix. So, with cgroups-v1 or cgroups-v2, the full prefix for
+BFQ-specific files is "blkio.bfq." or "io.bfq." For example, the group
+parameter to set the weight of a group with BFQ is blkio.bfq.weight
+or io.bfq.weight.
+
+Parameters to set
+-----------------
+
+For each group, there is only the following parameter to set.
+
+weight (namely blkio.bfq.weight or io.bfq-weight): the weight of the
+group inside its parent. Available values: 1..10000 (default 100). The
+linear mapping between ioprio and weights, described at the beginning
+of the tunable section, is still valid, but all weights higher than
+IOPRIO_BE_NR*10 are mapped to ioprio 0.
+
+Recall that, if low-latency is set, then BFQ automatically raises the
+weight of the queues associated with interactive and soft real-time
+applications. Unset this tunable if you need/want to control weights.
+
+
+[1] P. Valente, A. Avanzini, "Evolution of the BFQ Storage I/O
+ Scheduler", Proceedings of the First Workshop on Mobile System
+ Technologies (MST-2015), May 2015.
+ http://algogroup.unimore.it/people/paolo/disk_sched/mst-2015.pdf
+
+[2] P. Valente and M. Andreolini, "Improving Application
+ Responsiveness with the BFQ Disk I/O Scheduler", Proceedings of
+ the 5th Annual International Systems and Storage Conference
+ (SYSTOR '12), June 2012.
+ Slightly extended version:
+ http://algogroup.unimore.it/people/paolo/disk_sched/bfq-v1-suite-
+ results.pdf
--- /dev/null
+Kyber I/O scheduler tunables
+===========================
+
+The only two tunables for the Kyber scheduler are the target latencies for
+reads and synchronous writes. Kyber will throttle requests in order to meet
+these target latencies.
+
+read_lat_nsec
+-------------
+Target latency for reads (in nanoseconds).
+
+write_lat_nsec
+--------------
+Target latency for synchronous writes (in nanoseconds).
smaller discards and potentially help reduce latencies induced by large
discard operations.
-discard_zeroes_data (RO)
-------------------------
-When read, this file will show if the discarded block are zeroed by the
-device or not. If its value is '1' the blocks are zeroed otherwise not.
-
hw_sector_size (RO)
-------------------
This is the hardware sector size of the device, in bytes.
feature. Writing a value of '-1' to this file resets the value to the
default setting.
+throttle_sample_time (RW)
+-------------------------
+This is the time window that blk-throttle samples data, in millisecond.
+blk-throttle makes decision based on the samplings. Lower time means cgroups
+have more smooth throughput, but higher CPU overhead. This exists only when
+CONFIG_BLK_DEV_THROTTLING_LOW is enabled.
Jens Axboe <jens.axboe@oracle.com>, February 2009
+++ /dev/null
-This document describes m[g]flash support in linux.
-
-Contents
- 1. Overview
- 2. Reserved area configuration
- 3. Example of mflash platform driver registration
-
-1. Overview
-
-Mflash and gflash are embedded flash drive. The only difference is mflash is
-MCP(Multi Chip Package) device. These two device operate exactly same way.
-So the rest mflash repersents mflash and gflash altogether.
-
-Internally, mflash has nand flash and other hardware logics and supports
-2 different operation (ATA, IO) modes. ATA mode doesn't need any new
-driver and currently works well under standard IDE subsystem. Actually it's
-one chip SSD. IO mode is ATA-like custom mode for the host that doesn't have
-IDE interface.
-
-Following are brief descriptions about IO mode.
-A. IO mode based on ATA protocol and uses some custom command. (read confirm,
-write confirm)
-B. IO mode uses SRAM bus interface.
-C. IO mode supports 4kB boot area, so host can boot from mflash.
-
-2. Reserved area configuration
-If host boot from mflash, usually needs raw area for boot loader image. All of
-the mflash's block device operation will be taken this value as start offset.
-Note that boot loader's size of reserved area and kernel configuration value
-must be same.
-
-3. Example of mflash platform driver registration
-Working mflash is very straight forward. Adding platform device stuff to board
-configuration file is all. Here is some pseudo example.
-
-static struct mg_drv_data mflash_drv_data = {
- /* If you want to polling driver set to 1 */
- .use_polling = 0,
- /* device attribution */
- .dev_attr = MG_BOOT_DEV
-};
-
-static struct resource mg_mflash_rsc[] = {
- /* Base address of mflash */
- [0] = {
- .start = 0x08000000,
- .end = 0x08000000 + SZ_64K - 1,
- .flags = IORESOURCE_MEM
- },
- /* mflash interrupt pin */
- [1] = {
- .start = IRQ_GPIO(84),
- .end = IRQ_GPIO(84),
- .flags = IORESOURCE_IRQ
- },
- /* mflash reset pin */
- [2] = {
- .start = 43,
- .end = 43,
- .name = MG_RST_PIN,
- .flags = IORESOURCE_IO
- },
- /* mflash reset-out pin
- * If you use mflash as storage device (i.e. other than MG_BOOT_DEV),
- * should assign this */
- [3] = {
- .start = 51,
- .end = 51,
- .name = MG_RSTOUT_PIN,
- .flags = IORESOURCE_IO
- }
-};
-
-static struct platform_device mflash_dev = {
- .name = MG_DEV_NAME,
- .id = -1,
- .dev = {
- .platform_data = &mflash_drv_data,
- },
- .num_resources = ARRAY_SIZE(mg_mflash_rsc),
- .resource = mg_mflash_rsc
-};
-
-platform_device_register(&mflash_dev);
--- /dev/null
+Device tree binding for the TI DM816 AHCI SATA Controller
+---------------------------------------------------------
+
+Required properties:
+ - compatible: must be "ti,dm816-ahci"
+ - reg: physical base address and size of the register region used by
+ the controller (as defined by the AHCI 1.1 standard)
+ - interrupts: interrupt specifier (refer to the interrupt binding)
+ - clocks: list of phandle and clock specifier pairs (or only
+ phandles for clock providers with '0' defined for
+ #clock-cells); two clocks must be specified: the functional
+ clock and an external reference clock
+
+Example:
+
+ sata: sata@4a140000 {
+ compatible = "ti,dm816-ahci";
+ reg = <0x4a140000 0x10000>;
+ interrupts = <16>;
+ clocks = <&sysclk5_ck>, <&sata_refclk>;
+ };
--- /dev/null
+ads7828 properties
+
+Required properties:
+- compatible: Should be one of
+ ti,ads7828
+ ti,ads7830
+- reg: I2C address
+
+Optional properties:
+
+- ti,differential-input
+ Set to use the device in differential mode.
+- vref-supply
+ The external reference on the device is set to this regulators output. If it
+ does not exists the internal reference will be used and output by the ads78xx
+ on the "external vref" pin.
+
+ Example ADS7828 node:
+
+ ads7828: ads@48 {
+ comatible = "ti,ads7828";
+ reg = <0x48>;
+ vref-supply = <&vref>;
+ ti,differential-input;
+ };
--- /dev/null
+ASPEED AST2400/AST2500 PWM and Fan Tacho controller device driver
+
+The ASPEED PWM controller can support upto 8 PWM outputs. The ASPEED Fan Tacho
+controller can support upto 16 Fan tachometer inputs.
+
+There can be upto 8 fans supported. Each fan can have one PWM output and
+one/two Fan tach inputs.
+
+Required properties for pwm-tacho node:
+- #address-cells : should be 1.
+
+- #size-cells : should be 1.
+
+- reg : address and length of the register set for the device.
+
+- pinctrl-names : a pinctrl state named "default" must be defined.
+
+- pinctrl-0 : phandle referencing pin configuration of the PWM ports.
+
+- compatible : should be "aspeed,ast2400-pwm-tacho" for AST2400 and
+ "aspeed,ast2500-pwm-tacho" for AST2500.
+
+- clocks : a fixed clock providing input clock frequency(PWM
+ and Fan Tach clock)
+
+fan subnode format:
+===================
+Under fan subnode there can upto 8 child nodes, with each child node
+representing a fan. If there are 8 fans each fan can have one PWM port and
+one/two Fan tach inputs.
+
+Required properties for each child node:
+- reg : should specify PWM source port.
+ integer value in the range 0 to 7 with 0 indicating PWM port A and
+ 7 indicating PWM port H.
+
+- aspeed,fan-tach-ch : should specify the Fan tach input channel.
+ integer value in the range 0 through 15, with 0 indicating
+ Fan tach channel 0 and 15 indicating Fan tach channel 15.
+ Atleast one Fan tach input channel is required.
+
+Examples:
+
+pwm_tacho_fixed_clk: fixedclk {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <24000000>;
+};
+
+pwm_tacho: pwmtachocontroller@1e786000 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ reg = <0x1E786000 0x1000>;
+ compatible = "aspeed,ast2500-pwm-tacho";
+ clocks = <&pwm_tacho_fixed_clk>;
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_pwm0_default &pinctrl_pwm1_default>;
+
+ fan@0 {
+ reg = <0x00>;
+ aspeed,fan-tach-ch = /bits/ 8 <0x00>;
+ };
+
+ fan@1 {
+ reg = <0x01>;
+ aspeed,fan-tach-ch = /bits/ 8 <0x01 0x02>;
+ };
+};
--- /dev/null
+*LM87 hwmon sensor.
+
+Required properties:
+- compatible: Should be
+ "ti,lm87"
+
+- reg: I2C address
+
+optional properties:
+- has-temp3: This configures pins 18 and 19 to be used as a second
+ remote temperature sensing channel. By default the pins
+ are configured as voltage input pins in0 and in5.
+
+- has-in6: When set, pin 5 is configured to be used as voltage input
+ in6. Otherwise the pin is set as FAN1 input.
+
+- has-in7: When set, pin 6 is configured to be used as voltage input
+ in7. Otherwise the pin is set as FAN2 input.
+
+- vcc-supply: a Phandle for the regulator supplying power, can be
+ cofigured to measure 5.0V power supply. Default is 3.3V.
+
+Example:
+
+lm87@2e {
+ compatible = "ti,lm87";
+ reg = <0x2e>;
+ has-temp3;
+ vcc-supply = <®_5v0>;
+};
-* Cortina Systems Gemini interrupt controller
+* Faraday Technologt FTINTC010 interrupt controller
-This interrupt controller is found on the Gemini SoCs.
+This interrupt controller is a stock IP block from Faraday Technology found
+in the Gemini SoCs and other designs.
Required properties:
-- compatible: must be "cortina,gemini-interrupt-controller"
+- compatible: must be one of
+ "faraday,ftintc010"
+ "cortina,gemini-interrupt-controller" (deprecated)
- reg: The register bank for the interrupt controller.
- interrupt-controller: Identifies the node as an interrupt controller
- #interrupt-cells: The number of cells to define the interrupts.
Example:
interrupt-controller@48000000 {
- compatible = "cortina,gemini-interrupt-controller";
+ compatible = "faraday,ftintc010"
reg = <0x48000000 0x1000>;
interrupt-controller;
#interrupt-cells = <2>;
--- /dev/null
+* Mediatek 27xx cirq
+
+In Mediatek SOCs, the CIRQ is a low power interrupt controller designed to
+work outside MCUSYS which comprises with Cortex-Ax cores,CCI and GIC.
+The external interrupts (outside MCUSYS) will feed through CIRQ and connect
+to GIC in MCUSYS. When CIRQ is enabled, it will record the edge-sensitive
+interrupts and generate a pulse signal to parent interrupt controller when
+flush command is executed. With CIRQ, MCUSYS can be completely turned off
+to improve the system power consumption without losing interrupts.
+
+Required properties:
+- compatible: should be one of
+ - "mediatek,mt2701-cirq" for mt2701 CIRQ
+ - "mediatek,mt8135-cirq" for mt8135 CIRQ
+ - "mediatek,mt8173-cirq" for mt8173 CIRQ
+ and "mediatek,cirq" as a fallback.
+- interrupt-controller : Identifies the node as an interrupt controller.
+- #interrupt-cells : Use the same format as specified by GIC in arm,gic.txt.
+- interrupt-parent: phandle of irq parent for cirq. The parent must
+ use the same interrupt-cells format as GIC.
+- reg: Physical base address of the cirq registers and length of memory
+ mapped region.
+- mediatek,ext-irq-range: Identifies external irq number range in different
+ SOCs.
+
+Example:
+ cirq: interrupt-controller@10204000 {
+ compatible = "mediatek,mt2701-cirq",
+ "mediatek,mtk-cirq";
+ interrupt-controller;
+ #interrupt-cells = <3>;
+ interrupt-parent = <&sysirq>;
+ reg = <0 0x10204000 0 0x400>;
+ mediatek,ext-irq-start = <32 200>;
+ };
- interrupt-parent: phandle of irq parent for sysirq. The parent must
use the same interrupt-cells format as GIC.
- reg: Physical base address of the intpol registers and length of memory
- mapped region.
+ mapped region. Could be multiple bases here. Ex: mt6797 needs 2 reg, others
+ need 1.
Example:
- sysirq: interrupt-controller@10200100 {
- compatible = "mediatek,mt6589-sysirq", "mediatek,mt6577-sysirq";
+ sysirq: intpol-controller@10200620 {
+ compatible = "mediatek,mt6797-sysirq",
+ "mediatek,mt6577-sysirq";
interrupt-controller;
#interrupt-cells = <3>;
interrupt-parent = <&gic>;
- reg = <0 0x10200100 0 0x1c>;
+ reg = <0 0x10220620 0 0x20>,
+ <0 0x10220690 0 0x10>;
};
Required properties:
-- compatible : should be "aspeed,ast2400-ibt-bmc"
+- compatible : should be one of
+ "aspeed,ast2400-ibt-bmc"
+ "aspeed,ast2500-ibt-bmc"
- reg: physical address and size of the registers
Optional properties:
--- /dev/null
+Motorola CPCAP PMIC LEDs
+------------------------
+
+This module is part of the CPCAP. For more details about the whole
+chip see Documentation/devicetree/bindings/mfd/motorola-cpcap.txt.
+
+Requires node properties:
+- compatible: should be one of
+ * "motorola,cpcap-led-mdl" (Main Display Lighting)
+ * "motorola,cpcap-led-kl" (Keyboard Lighting)
+ * "motorola,cpcap-led-adl" (Aux Display Lighting)
+ * "motorola,cpcap-led-red" (Red Triode)
+ * "motorola,cpcap-led-green" (Green Triode)
+ * "motorola,cpcap-led-blue" (Blue Triode)
+ * "motorola,cpcap-led-cf" (Camera Flash)
+ * "motorola,cpcap-led-bt" (Bluetooth)
+ * "motorola,cpcap-led-cp" (Camera Privacy LED)
+- label: see Documentation/devicetree/bindings/leds/common.txt
+- vdd-supply: A phandle to the regulator powering the LED
+
+Example:
+
+&cpcap {
+ cpcap_led_red: red-led {
+ compatible = "motorola,cpcap-led-red";
+ label = "cpcap:red";
+ vdd-supply = <&sw5>;
+ };
+};
--- /dev/null
+Device Tree Bindings for LED support on MT6323 PMIC
+
+MT6323 LED controller is subfunction provided by MT6323 PMIC, so the LED
+controllers are defined as the subnode of the function node provided by MT6323
+PMIC controller that is being defined as one kind of Muti-Function Device (MFD)
+using shared bus called PMIC wrapper for each subfunction to access remote
+MT6323 PMIC hardware.
+
+For MT6323 MFD bindings see:
+Documentation/devicetree/bindings/mfd/mt6397.txt
+For MediaTek PMIC wrapper bindings see:
+Documentation/devicetree/bindings/soc/mediatek/pwrap.txt
+
+Required properties:
+- compatible : Must be "mediatek,mt6323-led"
+- address-cells : Must be 1
+- size-cells : Must be 0
+
+Each led is represented as a child node of the mediatek,mt6323-led that
+describes the initial behavior for each LED physically and currently only four
+LED child nodes can be supported.
+
+Required properties for the LED child node:
+- reg : LED channel number (0..3)
+
+Optional properties for the LED child node:
+- label : See Documentation/devicetree/bindings/leds/common.txt
+- linux,default-trigger : See Documentation/devicetree/bindings/leds/common.txt
+- default-state: See Documentation/devicetree/bindings/leds/common.txt
+
+Example:
+
+ mt6323: pmic {
+ compatible = "mediatek,mt6323";
+
+ ...
+
+ mt6323led: leds {
+ compatible = "mediatek,mt6323-led";
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ led@0 {
+ reg = <0>;
+ label = "LED0";
+ linux,default-trigger = "timer";
+ default-state = "on";
+ };
+ led@1 {
+ reg = <1>;
+ label = "LED1";
+ default-state = "off";
+ };
+ led@2 {
+ reg = <2>;
+ label = "LED2";
+ default-state = "on";
+ };
+ };
+ };
- label: see Documentation/devicetree/bindings/leds/common.txt
- type: Output configuration, see dt-bindings/leds/leds-pca9532.h (default NONE)
- linux,default-trigger: see Documentation/devicetree/bindings/leds/common.txt
+ - default-state: see Documentation/devicetree/bindings/leds/common.txt
+ This property is only valid for sub-nodes of type <PCA9532_TYPE_LED>.
Example:
#include <dt-bindings/leds/leds-pca9532.h>
label = "pca:green:power";
type = <PCA9532_TYPE_LED>;
};
+ kernel-booting {
+ type = <PCA9532_TYPE_LED>;
+ default-state = "on";
+ };
+ sys-stat {
+ type = <PCA9532_TYPE_LED>;
+ default-state = "keep"; // don't touch, was set by U-Boot
+ };
};
For more product information please see the link below:
--- /dev/null
+Broadcom FlexRM Ring Manager
+============================
+The Broadcom FlexRM ring manager provides a set of rings which can be
+used to submit work to offload engines. An SoC may have multiple FlexRM
+hardware blocks. There is one device tree entry per FlexRM block. The
+FlexRM driver will create a mailbox-controller instance for given FlexRM
+hardware block where each mailbox channel is a separate FlexRM ring.
+
+Required properties:
+--------------------
+- compatible: Should be "brcm,iproc-flexrm-mbox"
+- reg: Specifies base physical address and size of the FlexRM
+ ring registers
+- msi-parent: Phandles (and potential Device IDs) to MSI controllers
+ The FlexRM engine will send MSIs (instead of wired
+ interrupts) to CPU. There is one MSI for each FlexRM ring.
+ Refer devicetree/bindings/interrupt-controller/msi.txt
+- #mbox-cells: Specifies the number of cells needed to encode a mailbox
+ channel. This should be 3.
+
+ The 1st cell is the mailbox channel number.
+
+ The 2nd cell contains MSI completion threshold. This is the
+ number of completion messages for which FlexRM will inject
+ one MSI interrupt to CPU.
+
+ The 3nd cell contains MSI timer value representing time for
+ which FlexRM will wait to accumulate N completion messages
+ where N is the value specified by 2nd cell above. If FlexRM
+ does not get required number of completion messages in time
+ specified by this cell then it will inject one MSI interrupt
+ to CPU provided atleast one completion message is available.
+
+Optional properties:
+--------------------
+- dma-coherent: Present if DMA operations made by the FlexRM engine (such
+ as DMA descriptor access, access to buffers pointed by DMA
+ descriptors and read/write pointer updates to DDR) are
+ cache coherent with the CPU.
+
+Example:
+--------
+crypto_mbox: mbox@67000000 {
+ compatible = "brcm,iproc-flexrm-mbox";
+ reg = <0x67000000 0x200000>;
+ msi-parent = <&gic_its 0x7f00>;
+ #mbox-cells = <3>;
+};
+
+crypto@672c0000 {
+ compatible = "brcm,spu2-v2-crypto";
+ reg = <0x672c0000 0x1000>;
+ mboxes = <&crypto_mbox 0 0x1 0xffff>,
+ <&crypto_mbox 1 0x1 0xffff>,
+ <&crypto_mbox 16 0x1 0xffff>,
+ <&crypto_mbox 17 0x1 0xffff>,
+ <&crypto_mbox 30 0x1 0xffff>,
+ <&crypto_mbox 31 0x1 0xffff>;
+};
The PDC driver manages data transfer to and from various offload engines
on some Broadcom SoCs. An SoC may have multiple PDC hardware blocks. There is
-one device tree entry per block.
+one device tree entry per block. On some chips, the PDC functionality is
+handled by the FA2 (Northstar Plus).
Required properties:
-- compatible : Should be "brcm,iproc-pdc-mbox".
+- compatible : Should be "brcm,iproc-pdc-mbox" or "brcm,iproc-fa2-mbox" for
+ FA2/Northstar Plus.
- reg: Should contain PDC registers location and length.
- interrupts: Should contain the IRQ line for the PDC.
- #mbox-cells: 1
};
HiSilicon Hip06/Hip07 PCIe host bridge DT (almost-ECAM) description.
+
+Some BIOSes place the host controller in a mode where it is ECAM
+compliant for all devices other than the root complex. In such cases,
+the host controller should be described as below.
+
The properties and their meanings are identical to those described in
host-generic-pci.txt except as listed below.
Properties of the host controller node that differ from
host-generic-pci.txt:
-- compatible : Must be "hisilicon,pcie-almost-ecam"
+- compatible : Must be "hisilicon,hip06-pcie-ecam", or
+ "hisilicon,hip07-pcie-ecam"
- reg : Two entries: First the ECAM configuration space for any
other bus underneath the root bus. Second, the base
Example:
pcie0: pcie@a0090000 {
- compatible = "hisilicon,pcie-almost-ecam";
+ compatible = "hisilicon,hip06-pcie-ecam";
reg = <0 0xb0000000 0 0x2000000>, /* ECAM configuration space */
<0 0xa0090000 0 0x10000>; /* host bridge registers */
bus-range = <0 31>;
- domain-idle-states : A phandle of an idle-state that shall be soaked into a
generic domain power state. The idle state definitions are
- compatible with domain-idle-state specified in [1].
+ compatible with domain-idle-state specified in [1]. phandles
+ that are not compatible with domain-idle-state will be
+ ignored.
The domain-idle-state property reflects the idle state of this PM domain and
not the idle states of the devices or sub-domains in the PM domain. Devices
and sub-domains have their own idle-states independent of the parent
--- /dev/null
+* Device-Tree bindings for Cortina Systems Gemini Poweroff
+
+This is a special IP block in the Cortina Gemini SoC that only
+deals with different ways to power the system down.
+
+Required properties:
+- compatible: should be "cortina,gemini-power-controller"
+- reg: should contain the physical memory base and size
+- interrupts: should contain the power management interrupt
+
+Example:
+
+power-controller@4b000000 {
+ compatible = "cortina,gemini-power-controller";
+ reg = <0x4b000000 0x100>;
+ interrupts = <26 IRQ_TYPE_EDGE_FALLING>;
+};
This is a generic poweroff driver using syscon to map the poweroff register.
The poweroff is generally performed with a write to the poweroff register
defined by the register map pointed by syscon reference plus the offset
-with the mask defined in the poweroff node.
+with the value and mask defined in the poweroff node.
Required properties:
- compatible: should contain "syscon-poweroff"
- regmap: this is phandle to the register map node
- offset: offset in the register map for the poweroff register (in bytes)
-- mask: the poweroff value written to the poweroff register (32 bit access)
+- value: the poweroff value written to the poweroff register (32 bit access)
+
+Optional properties:
+- mask: update only the register bits defined by the mask (32 bit)
+
+Legacy usage:
+If a node doesn't contain a value property but contains a mask property, the
+mask property is used as the value.
Default will be little endian mode, 32 bit access only.
- compatible: should be one of:
- "rockchip,rk3188-io-voltage-domain" for rk3188
- "rockchip,rk3288-io-voltage-domain" for rk3288
+ - "rockchip,rk3328-io-voltage-domain" for rk3328
- "rockchip,rk3368-io-voltage-domain" for rk3368
- "rockchip,rk3368-pmu-io-voltage-domain" for rk3368 pmu-domains
- "rockchip,rk3399-io-voltage-domain" for rk3399
--- /dev/null
+Motorola CPCAP PMIC battery charger binding
+
+Required properties:
+- compatible: Shall be "motorola,mapphone-cpcap-charger"
+- interrupts: Interrupt specifier for each name in interrupt-names
+- interrupt-names: Should contain the following entries:
+ "chrg_det", "rvrs_chrg", "chrg_se1b", "se0conn",
+ "rvrs_mode", "chrgcurr1", "vbusvld", "battdetb"
+- io-channels: IIO ADC channel specifier for each name in io-channel-names
+- io-channel-names: Should contain the following entries:
+ "battdetb", "battp", "vbus", "chg_isense", "batti"
+
+Optional properties:
+- mode-gpios: Optionally CPCAP charger can have a companion wireless
+ charge controller that is controlled with two GPIOs
+ that are active low.
+
+Example:
+
+cpcap_charger: charger {
+ compatible = "motorola,mapphone-cpcap-charger";
+ interrupts-extended = <
+ &cpcap 13 0 &cpcap 12 0 &cpcap 29 0 &cpcap 28 0
+ &cpcap 22 0 &cpcap 20 0 &cpcap 19 0 &cpcap 54 0
+ >;
+ interrupt-names =
+ "chrg_det", "rvrs_chrg", "chrg_se1b", "se0conn",
+ "rvrs_mode", "chrgcurr1", "vbusvld", "battdetb";
+ mode-gpios = <&gpio3 29 GPIO_ACTIVE_LOW
+ &gpio3 23 GPIO_ACTIVE_LOW>;
+ io-channels = <&cpcap_adc 0 &cpcap_adc 1
+ &cpcap_adc 2 &cpcap_adc 5
+ &cpcap_adc 6>;
+ io-channel-names = "battdetb", "battp",
+ "vbus", "chg_isense",
+ "batti";
+};
--- /dev/null
+LEGO MINDSTORMS EV3 Battery
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+LEGO MINDSTORMS EV3 has some built-in capability for monitoring the battery.
+It uses 6 AA batteries or a special Li-ion rechargeable battery pack that is
+detected by a key switch in the battery compartment.
+
+Required properties:
+ - compatible: Must be "lego,ev3-battery"
+ - io-channels: phandles to analog inputs for reading voltage and current
+ - io-channel-names: Must be "voltage", "current"
+ - rechargeable-gpios: phandle to the rechargeable battery indication gpio
+
+Example:
+
+ battery {
+ compatible = "lego,ev3-battery";
+ io-channels = <&adc 4>, <&adc 3>;
+ io-channel-names = "voltage", "current";
+ rechargeable-gpios = <&gpio 136 GPIO_ACTIVE_LOW>;
+ };
formula for the charge counter.
Required properties:
-- compatible: Should contain "ltc2941" or "ltc2943" which also indicates the
- type of I2C chip attached.
+- compatible: Should contain "lltc,ltc2941" or "lltc,ltc2943" which also
+ indicates the type of I2C chip attached.
- reg: The 7-bit I2C address.
- lltc,resistor-sense: The sense resistor value in milli-ohms. Can be a 32-bit
negative value when the battery has been connected to the wrong end of the
Example from the Topic Miami Florida board:
fuelgauge: ltc2943@64 {
- compatible = "ltc2943";
+ compatible = "lltc,ltc2943";
reg = <0x64>;
lltc,resistor-sense = <15>;
lltc,prescaler-exponent = <5>; /* 2^(2*5) = 1024 */
+++ /dev/null
-Cortina Systems Gemini timer
-
-This timer is embedded in the Cortina Systems Gemini SoCs.
-
-Required properties:
-
-- compatible : Must be "cortina,gemini-timer"
-- reg : Should contain registers location and length
-- interrupts : Should contain the three timer interrupts with
- flags for rising edge
-- syscon : a phandle to the global Gemini system controller
-
-Example:
-
-timer@43000000 {
- compatible = "cortina,gemini-timer";
- reg = <0x43000000 0x1000>;
- interrupts = <14 IRQ_TYPE_EDGE_RISING>, /* Timer 1 */
- <15 IRQ_TYPE_EDGE_RISING>, /* Timer 2 */
- <16 IRQ_TYPE_EDGE_RISING>; /* Timer 3 */
- syscon = <&syscon>;
-};
--- /dev/null
+Faraday Technology timer
+
+This timer is a generic IP block from Faraday Technology, embedded in the
+Cortina Systems Gemini SoCs and other designs.
+
+Required properties:
+
+- compatible : Must be one of
+ "faraday,fttmr010"
+ "cortina,gemini-timer"
+- reg : Should contain registers location and length
+- interrupts : Should contain the three timer interrupts usually with
+ flags for falling edge
+
+Optionally required properties:
+
+- clocks : a clock to provide the tick rate for "faraday,fttmr010"
+- clock-names : should be "EXTCLK" and "PCLK" for the external tick timer
+ and peripheral clock respectively, for "faraday,fttmr010"
+- syscon : a phandle to the global Gemini system controller if the compatible
+ type is "cortina,gemini-timer"
+
+Example:
+
+timer@43000000 {
+ compatible = "faraday,fttmr010";
+ reg = <0x43000000 0x1000>;
+ interrupts = <14 IRQ_TYPE_EDGE_FALLING>, /* Timer 1 */
+ <15 IRQ_TYPE_EDGE_FALLING>, /* Timer 2 */
+ <16 IRQ_TYPE_EDGE_FALLING>; /* Timer 3 */
+ clocks = <&extclk>, <&pclk>;
+ clock-names = "EXTCLK", "PCLK";
+};
Rockchip rk timer
Required properties:
-- compatible: shall be one of:
- "rockchip,rk3288-timer" - for rk3066, rk3036, rk3188, rk322x, rk3288, rk3368
- "rockchip,rk3399-timer" - for rk3399
+- compatible: should be:
+ "rockchip,rk3036-timer", "rockchip,rk3288-timer": for Rockchip RK3036
+ "rockchip,rk3066-timer", "rockchip,rk3288-timer": for Rockchip RK3066
+ "rockchip,rk3188-timer", "rockchip,rk3288-timer": for Rockchip RK3188
+ "rockchip,rk3228-timer", "rockchip,rk3288-timer": for Rockchip RK3228
+ "rockchip,rk3229-timer", "rockchip,rk3288-timer": for Rockchip RK3229
+ "rockchip,rk3288-timer": for Rockchip RK3288
+ "rockchip,rk3368-timer", "rockchip,rk3288-timer": for Rockchip RK3368
+ "rockchip,rk3399-timer": for Rockchip RK3399
- reg: base address of the timer register starting with TIMERS CONTROL register
- interrupts: should contain the interrupts for Timer0
- clocks : must contain an entry for each entry in clock-names
schindler Schindler
seagate Seagate Technology PLC
semtech Semtech Corporation
+sensirion Sensirion AG
sgx SGX Sensortech
sharp Sharp Corporation
si-en Si-En Technology Ltd.
| arc: | TODO |
| arm: | ok |
| arm64: | ok |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | ok |
| arm: | ok |
| arm64: | ok |
- | avr32: | TODO |
| blackfin: | ok |
| c6x: | TODO |
| cris: | TODO |
| arc: | TODO |
| arm: | ok |
| arm64: | ok |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | ok |
| arm: | ok |
| arm64: | ok |
- | avr32: | TODO |
| blackfin: | ok |
| c6x: | ok |
| cris: | TODO |
| arc: | TODO |
| arm: | TODO |
| arm64: | ok |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | TODO |
| arm: | ok |
| arm64: | ok |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | ok |
| arm: | ok |
| arm64: | ok |
- | avr32: | TODO |
| blackfin: | ok |
| c6x: | TODO |
| cris: | TODO |
| arc: | TODO |
| arm: | TODO |
| arm64: | TODO |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | ok |
| arm: | ok |
| arm64: | TODO |
- | avr32: | ok |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | ok |
| arm: | ok |
| arm64: | TODO |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | TODO |
| arm: | ok |
| arm64: | TODO |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | TODO |
| arm: | ok |
| arm64: | ok |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | TODO |
| arm: | ok |
| arm64: | TODO |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | TODO |
| arm: | TODO |
| arm64: | TODO |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | TODO |
| arm: | ok |
| arm64: | ok |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | ok |
| cris: | TODO |
| arc: | TODO |
| arm: | ok |
| arm64: | ok |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | ok |
| arm: | ok |
| arm64: | ok |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | TODO |
| arm: | TODO |
| arm64: | TODO |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | TODO |
| arm: | TODO |
| arm64: | TODO |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | ok |
| arm: | ok |
| arm64: | ok |
- | avr32: | ok |
| blackfin: | ok |
| c6x: | TODO |
| cris: | TODO |
| arc: | TODO |
| arm: | TODO |
| arm64: | TODO |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | TODO |
| arm: | TODO |
| arm64: | TODO |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | TODO |
| arm: | TODO |
| arm64: | TODO |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | TODO |
| arm: | ok |
| arm64: | TODO |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | TODO |
| arm: | ok |
| arm64: | ok |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | TODO |
| arm: | ok |
| arm64: | ok |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | .. |
| arm: | .. |
| arm64: | .. |
- | avr32: | .. |
| blackfin: | .. |
| c6x: | .. |
| cris: | .. |
| arc: | TODO |
| arm: | ok |
| arm64: | ok |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | TODO |
| arm: | ok |
| arm64: | ok |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | ok |
| arm: | ok |
| arm64: | ok |
- | avr32: | ok |
| blackfin: | ok |
| c6x: | ok |
| cris: | ok |
| arc: | TODO |
| arm: | ok |
| arm64: | ok |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | TODO |
| arm: | ok |
| arm64: | ok |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | ok |
| arm: | TODO |
| arm64: | ok |
- | avr32: | ok |
| blackfin: | TODO |
| c6x: | ok |
| cris: | TODO |
| arc: | TODO |
| arm: | ok |
| arm64: | ok |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | TODO |
| arm: | ok |
| arm64: | ok |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | TODO |
| arm: | TODO |
| arm64: | TODO |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | ok |
| arm: | ok |
| arm64: | ok |
- | avr32: | .. |
| blackfin: | .. |
| c6x: | .. |
| cris: | .. |
| arc: | TODO |
| arm: | TODO |
| arm64: | TODO |
- | avr32: | .. |
| blackfin: | TODO |
| c6x: | .. |
| cris: | .. |
| arc: | TODO |
| arm: | TODO |
| arm64: | ok |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | ok |
| arm: | TODO |
| arm64: | TODO |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
| arc: | .. |
| arm: | .. |
| arm64: | .. |
- | avr32: | .. |
| blackfin: | .. |
| c6x: | .. |
| cris: | .. |
| arc: | ok |
| arm: | ok |
| arm64: | ok |
- | avr32: | TODO |
| blackfin: | TODO |
| c6x: | TODO |
| cris: | TODO |
int (*permission) (struct inode *, int, unsigned int);
int (*get_acl)(struct inode *, int);
int (*setattr) (struct dentry *, struct iattr *);
- int (*getattr) (const struct path *, struct dentry *, struct kstat *,
- u32, unsigned int);
+ int (*getattr) (const struct path *, struct kstat *, u32, unsigned int);
ssize_t (*listxattr) (struct dentry *, char *, size_t);
int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len);
void (*update_time)(struct inode *, struct timespec *, int);
[recommended]
->readlink is optional for symlinks. Don't set, unless filesystem needs
to fake something for readlink(2).
+--
+[mandatory]
+ ->getattr() is now passed a struct path rather than a vfsmount and
+ dentry separately, and it now has request_mask and query_flags arguments
+ to specify the fields and sync type requested by statx. Filesystems not
+ supporting any statx-specific features may ignore the new arguments.
int (*permission) (struct inode *, int);
int (*get_acl)(struct inode *, int);
int (*setattr) (struct dentry *, struct iattr *);
- int (*getattr) (const struct path *, struct dentry *, struct kstat *,
- u32, unsigned int);
+ int (*getattr) (const struct path *, struct kstat *, u32, unsigned int);
ssize_t (*listxattr) (struct dentry *, char *, size_t);
void (*update_time)(struct inode *, struct timespec *, int);
int (*atomic_open)(struct inode *, struct dentry *, struct file *,
--- /dev/null
+Kernel driver aspeed-pwm-tacho
+==============================
+
+Supported chips:
+ ASPEED AST2400/2500
+
+Authors:
+ <jaghu@google.com>
+
+Description:
+------------
+This driver implements support for ASPEED AST2400/2500 PWM and Fan Tacho
+controller. The PWM controller supports upto 8 PWM outputs. The Fan tacho
+controller supports up to 16 tachometer inputs.
+
+The driver provides the following sensor accesses in sysfs:
+
+fanX_input ro provide current fan rotation value in RPM as reported
+ by the fan to the device.
+
+pwmX rw get or set PWM fan control value. This is an integer
+ value between 0(off) and 255(full speed).
===================
Supported chips:
- * Microship TC654 and TC655
+ * Microchip TC654 and TC655
Prefix: 'tc654'
Datasheet: http://ww1.microchip.com/downloads/en/DeviceDoc/20001734C.pdf
--- /dev/null
+pblk: Physical Block Device Target
+==================================
+
+pblk implements a fully associative, host-based FTL that exposes a traditional
+block I/O interface. Its primary responsibilities are:
+
+ - Map logical addresses onto physical addresses (4KB granularity) in a
+ logical-to-physical (L2P) table.
+ - Maintain the integrity and consistency of the L2P table as well as its
+ recovery from normal tear down and power outage.
+ - Deal with controller- and media-specific constrains.
+ - Handle I/O errors.
+ - Implement garbage collection.
+ - Maintain consistency across the I/O stack during synchronization points.
+
+For more information please refer to:
+
+ http://lightnvm.io
+
+which maintains updated FAQs, manual pages, technical documentation, tools,
+contacts, etc.
control and configuration, and a parallel or a serial bus for data.
- camera host - an interface, to which a camera is connected. Typically a
specialised interface, present on many SoCs, e.g. PXA27x and PXA3xx, SuperH,
- AVR32, i.MX27, i.MX31.
+ i.MX27, i.MX31.
- camera host bus - a connection between a camera host and a camera. Can be
parallel or serial, consists of data and control lines, e.g. clock, vertical
and horizontal synchronization signals.
int __init foo_probe(void)
{
+ int error;
+
struct pinctrl_dev *pctl;
- return pinctrl_register_and_init(&foo_desc, <PARENT>, NULL, &pctl);
+ error = pinctrl_register_and_init(&foo_desc, <PARENT>, NULL, &pctl);
+ if (error)
+ return error;
+
+ return pinctrl_enable(pctl);
}
To enable the pinctrl subsystem and the subgroups for PINMUX and PINCONF and
- set the power.last_busy field to the current time
void pm_runtime_use_autosuspend(struct device *dev);
- - set the power.use_autosuspend flag, enabling autosuspend delays
+ - set the power.use_autosuspend flag, enabling autosuspend delays; call
+ pm_runtime_get_sync if the flag was previously cleared and
+ power.autosuspend_delay is negative
void pm_runtime_dont_use_autosuspend(struct device *dev);
- - clear the power.use_autosuspend flag, disabling autosuspend delays
+ - clear the power.use_autosuspend flag, disabling autosuspend delays;
+ decrement the device's usage counter if the flag was previously set and
+ power.autosuspend_delay is negative; call pm_runtime_idle
void pm_runtime_set_autosuspend_delay(struct device *dev, int delay);
- set the power.autosuspend_delay value to 'delay' (expressed in
milliseconds); if 'delay' is negative then runtime suspends are
- prevented
+ prevented; if power.use_autosuspend is set, pm_runtime_get_sync may be
+ called or the device's usage counter may be decremented and
+ pm_runtime_idle called depending on if power.autosuspend_delay is
+ changed to or from a negative value; if power.use_autosuspend is clear,
+ pm_runtime_idle is called
unsigned long pm_runtime_autosuspend_expiration(struct device *dev);
- calculate the time when the current autosuspend delay period will expire,
Instead of: pm_runtime_put_sync use: pm_runtime_put_sync_autosuspend.
Drivers may also continue to use the non-autosuspend helper functions; they
-will behave normally, not taking the autosuspend delay into account.
-Similarly, if the power.use_autosuspend field isn't set then the autosuspend
-helper functions will behave just like the non-autosuspend counterparts.
+will behave normally, which means sometimes taking the autosuspend delay into
+account (see pm_runtime_idle).
Under some circumstances a driver or subsystem may want to prevent a device
from autosuspending immediately, even though the usage counter is zero and the
.. code-block:: none
- Cc: <stable@vger.kernel.org> # 3.3.x-
+ Cc: <stable@vger.kernel.org> # 3.3.x
The tag has the meaning of:
--- /dev/null
+/*
+ * The following program is used to generate the constants for
+ * computing sched averages.
+ *
+ * ==============================================================
+ * C program (compile with -lm)
+ * ==============================================================
+ */
+
+#include <math.h>
+#include <stdio.h>
+
+#define HALFLIFE 32
+#define SHIFT 32
+
+double y;
+
+void calc_runnable_avg_yN_inv(void)
+{
+ int i;
+ unsigned int x;
+
+ printf("static const u32 runnable_avg_yN_inv[] = {");
+ for (i = 0; i < HALFLIFE; i++) {
+ x = ((1UL<<32)-1)*pow(y, i);
+
+ if (i % 6 == 0) printf("\n\t");
+ printf("0x%8x, ", x);
+ }
+ printf("\n};\n\n");
+}
+
+int sum = 1024;
+
+void calc_runnable_avg_yN_sum(void)
+{
+ int i;
+
+ printf("static const u32 runnable_avg_yN_sum[] = {\n\t 0,");
+ for (i = 1; i <= HALFLIFE; i++) {
+ if (i == 1)
+ sum *= y;
+ else
+ sum = sum*y + 1024*y;
+
+ if (i % 11 == 0)
+ printf("\n\t");
+
+ printf("%5d,", sum);
+ }
+ printf("\n};\n\n");
+}
+
+int n = -1;
+/* first period */
+long max = 1024;
+
+void calc_converged_max(void)
+{
+ long last = 0, y_inv = ((1UL<<32)-1)*y;
+
+ for (; ; n++) {
+ if (n > -1)
+ max = ((max*y_inv)>>SHIFT) + 1024;
+ /*
+ * This is the same as:
+ * max = max*y + 1024;
+ */
+
+ if (last == max)
+ break;
+
+ last = max;
+ }
+ n--;
+ printf("#define LOAD_AVG_PERIOD %d\n", HALFLIFE);
+ printf("#define LOAD_AVG_MAX %ld\n", max);
+// printf("#define LOAD_AVG_MAX_N %d\n\n", n);
+}
+
+void calc_accumulated_sum_32(void)
+{
+ int i, x = sum;
+
+ printf("static const u32 __accumulated_sum_N32[] = {\n\t 0,");
+ for (i = 1; i <= n/HALFLIFE+1; i++) {
+ if (i > 1)
+ x = x/2 + sum;
+
+ if (i % 6 == 0)
+ printf("\n\t");
+
+ printf("%6d,", x);
+ }
+ printf("\n};\n\n");
+}
+
+void main(void)
+{
+ printf("/* Generated by Documentation/scheduler/sched-pelt; do not modify. */\n\n");
+
+ y = pow(0.5, 1/(double)HALFLIFE);
+
+ calc_runnable_avg_yN_inv();
+// calc_runnable_avg_yN_sum();
+ calc_converged_max();
+// calc_accumulated_sum_32();
+}
--------
These events are similar to tracepoint based events. Instead of Tracepoint,
this is based on kprobes (kprobe and kretprobe). So it can probe wherever
-kprobes can probe (this means, all functions body except for __kprobes
-functions). Unlike the Tracepoint based event, this can be added and removed
+kprobes can probe (this means, all functions except those with
+__kprobes/nokprobe_inline annotation and those marked NOKPROBE_SYMBOL).
+Unlike the Tracepoint based event, this can be added and removed
dynamically, on the fly.
To enable this feature, build your kernel with CONFIG_KPROBE_EVENTS=y.
Bits for undefined preemption levels are RAZ/WI.
+ For historical reasons and to provide ABI compatibility with userspace we
+ export the GICC_PMR register in the format of the GICH_VMCR.VMPriMask
+ field in the lower 5 bits of a word, meaning that userspace must always
+ use the lower 5 bits to communicate with the KVM device and must shift the
+ value left by 3 places to obtain the actual priority mask level.
+
Limitations:
- Priorities are not implemented, and registers are RAZ/WI
- Currently only implemented for KVM_DEV_TYPE_ARM_VGIC_V2.
1C0/020 ALL efi_info EFI 32 information (struct efi_info)
1E0/004 ALL alk_mem_k Alternative mem check, in KB
1E4/004 ALL scratch Scratch field for the kernel setup code
-1E8/001 ALL e820_entries Number of entries in e820_map (below)
+1E8/001 ALL e820_entries Number of entries in e820_table (below)
1E9/001 ALL eddbuf_entries Number of entries in eddbuf (below)
1EA/001 ALL edd_mbr_sig_buf_entries Number of entries in edd_mbr_sig_buffer
(below)
1EC/001 ALL secure_boot Secure boot is enabled in the firmware
1EF/001 ALL sentinel Used to detect broken bootloaders
290/040 ALL edd_mbr_sig_buffer EDD MBR signatures
-2D0/A00 ALL e820_map E820 memory map table
- (array of struct e820entry)
+2D0/A00 ALL e820_table E820 memory map table
+ (array of struct e820_entry)
D00/1EC ALL eddbuf EDD data (array of struct edd_info)
F: drivers/auxdisplay/
F: include/linux/cfag12864b.h
-AVR32 ARCHITECTURE
-M: Haavard Skinnemoen <hskinnemoen@gmail.com>
-M: Hans-Christian Egtvedt <egtvedt@samfundet.no>
-W: http://www.atmel.com/products/AVR32/
-W: http://mirror.egtvedt.no/avr32linux.org/
-W: http://avrfreaks.net/
-S: Maintained
-F: arch/avr32/
-
-AVR32/AT32AP MACHINE SUPPORT
-M: Haavard Skinnemoen <hskinnemoen@gmail.com>
-M: Hans-Christian Egtvedt <egtvedt@samfundet.no>
-S: Maintained
-F: arch/avr32/mach-at32ap/
-
AX.25 NETWORK LAYER
M: Ralf Baechle <ralf@linux-mips.org>
L: linux-hams@vger.kernel.org
F: kernel/trace/blktrace.c
F: lib/sbitmap.c
+BFQ I/O SCHEDULER
+M: Paolo Valente <paolo.valente@linaro.org>
+M: Jens Axboe <axboe@kernel.dk>
+L: linux-block@vger.kernel.org
+S: Maintained
+F: block/bfq-*
+F: Documentation/block/bfq-iosched.txt
+
BLOCK2MTD DRIVER
M: Joern Engel <joern@lazybastard.org>
L: linux-mtd@lists.infradead.org
BPF (Safe dynamic programs and tools)
M: Alexei Starovoitov <ast@kernel.org>
+M: Daniel Borkmann <daniel@iogearbox.net>
L: netdev@vger.kernel.org
L: linux-kernel@vger.kernel.org
S: Supported
+F: arch/x86/net/bpf_jit*
+F: Documentation/networking/filter.txt
+F: include/linux/bpf*
+F: include/linux/filter.h
+F: include/uapi/linux/bpf*
+F: include/uapi/linux/filter.h
F: kernel/bpf/
-F: tools/testing/selftests/bpf/
+F: kernel/trace/bpf_trace.c
F: lib/test_bpf.c
+F: net/bpf/
+F: net/core/filter.c
+F: net/sched/act_bpf.c
+F: net/sched/cls_bpf.c
+F: samples/bpf/
+F: tools/net/bpf*
+F: tools/testing/selftests/bpf/
BROADCOM B44 10/100 ETHERNET DRIVER
M: Michael Chan <michael.chan@broadcom.com>
T: git git://git.linaro.org/people/vireshk/linux.git (For ARM Updates)
B: https://bugzilla.kernel.org
F: Documentation/cpu-freq/
+F: Documentation/devicetree/bindings/cpufreq/
F: drivers/cpufreq/
F: include/linux/cpufreq.h
F: tools/testing/selftests/cpufreq/
F: lib/lru_cache.c
F: Documentation/blockdev/drbd/
-DRIVER CORE, KOBJECTS, DEBUGFS, KERNFS AND SYSFS
+DRIVER CORE, KOBJECTS, DEBUGFS AND SYSFS
M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
S: Supported
F: Documentation/kobject.txt
F: drivers/base/
F: fs/debugfs/
-F: fs/kernfs/
F: fs/sysfs/
F: include/linux/debugfs.h
F: include/linux/kobj*
L: linux-mips@linux-mips.org
S: Supported
F: drivers/edac/octeon_edac*
+F: drivers/edac/thunderx_edac*
EDAC-E752X
M: Mark Gross <mark.gross@intel.com>
F: net/bridge/
ETHERNET PHY LIBRARY
+M: Andrew Lunn <andrew@lunn.ch>
M: Florian Fainelli <f.fainelli@gmail.com>
L: netdev@vger.kernel.org
S: Maintained
F: include/uapi/linux/fuse.h
F: Documentation/filesystems/fuse.txt
+FUTEX SUBSYSTEM
+M: Thomas Gleixner <tglx@linutronix.de>
+M: Ingo Molnar <mingo@redhat.com>
+R: Peter Zijlstra <peterz@infradead.org>
+R: Darren Hart <dvhart@infradead.org>
+L: linux-kernel@vger.kernel.org
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking/core
+S: Maintained
+F: kernel/futex.c
+F: kernel/futex_compat.c
+F: include/asm-generic/futex.h
+F: include/linux/futex.h
+F: include/uapi/linux/futex.h
+F: tools/testing/selftests/futex/
+F: tools/perf/bench/futex*
+F: Documentation/*futex*
+
FUTURE DOMAIN TMC-16x0 SCSI DRIVER (16-bit)
M: Rik Faith <faith@cs.unc.edu>
L: linux-scsi@vger.kernel.org
F: fs/autofs4/
KERNEL BUILD + files below scripts/ (unless maintained elsewhere)
+M: Masahiro Yamada <yamada.masahiro@socionext.com>
M: Michal Marek <mmarek@suse.com>
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild.git for-next
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild.git rc-fixes
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-kbuild.git
L: linux-kbuild@vger.kernel.org
S: Maintained
F: Documentation/kbuild/
F: arch/mips/include/asm/kvm*
F: arch/mips/kvm/
+KERNFS
+M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+M: Tejun Heo <tj@kernel.org>
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
+S: Supported
+F: include/linux/kernfs.h
+F: fs/kernfs/
+
KEXEC
M: Eric Biederman <ebiederm@xmission.com>
W: http://kernel.org/pub/linux/utils/kernel/kexec/
Q: http://patchwork.ozlabs.org/project/netdev/list/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git
T: git git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git
+B: mailto:netdev@vger.kernel.org
S: Maintained
F: net/
F: include/net/
F: block/partitions/ibm.c
S390 NETWORK DRIVERS
+M: Julian Wiedmann <jwi@linux.vnet.ibm.com>
M: Ursula Braun <ubraun@linux.vnet.ibm.com>
L: linux-s390@vger.kernel.org
W: http://www.ibm.com/developerworks/linux/linux390/
F: drivers/s390/scsi/zfcp_*
S390 IUCV NETWORK LAYER
+M: Julian Wiedmann <jwi@linux.vnet.ibm.com>
M: Ursula Braun <ubraun@linux.vnet.ibm.com>
L: linux-s390@vger.kernel.org
W: http://www.ibm.com/developerworks/linux/linux390/
TIMEKEEPING, CLOCKSOURCE CORE, NTP, ALARMTIMER
M: John Stultz <john.stultz@linaro.org>
M: Thomas Gleixner <tglx@linutronix.de>
+R: Stephen Boyd <sboyd@codeaurora.org>
L: linux-kernel@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/core
S: Supported
F: include/linux/clk/ti.h
TI ETHERNET SWITCH DRIVER (CPSW)
-M: Mugunthan V N <mugunthanvnm@ti.com>
R: Grygorii Strashko <grygorii.strashko@ti.com>
L: linux-omap@vger.kernel.org
L: netdev@vger.kernel.org
F: tools/virtio/
F: drivers/net/virtio_net.c
F: drivers/block/virtio_blk.c
-F: include/linux/virtio_*.h
+F: include/linux/virtio*.h
F: include/uapi/linux/virtio_*.h
F: drivers/crypto/virtio/
VERSION = 4
PATCHLEVEL = 11
SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION =
NAME = Fearless Coyote
# *DOCUMENTATION*
CFLAGS_KERNEL =
AFLAGS_KERNEL =
LDFLAGS_vmlinux =
-CFLAGS_GCOV = -fprofile-arcs -ftest-coverage -fno-tree-loop-im -Wno-maybe-uninitialized
+CFLAGS_GCOV := -fprofile-arcs -ftest-coverage -fno-tree-loop-im $(call cc-disable-warning,maybe-uninitialized,)
CFLAGS_KCOV := $(call cc-option,-fsanitize-coverage=trace-pc,)
# Tell gcc to never replace conditional load with a non-conditional one
KBUILD_CFLAGS += $(call cc-option,--param=allow-store-data-races=0)
+# check for 'asm goto'
+ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC) $(KBUILD_CFLAGS)), y)
+ KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO
+ KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO
+endif
+
include scripts/Makefile.gcc-plugins
ifdef CONFIG_READABLE_ASM
# use the deterministic mode of AR if available
KBUILD_ARFLAGS := $(call ar-option,D)
-# check for 'asm goto'
-ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC) $(KBUILD_CFLAGS)), y)
- KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO
- KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO
-endif
-
include scripts/Makefile.kasan
include scripts/Makefile.extrawarn
include scripts/Makefile.ubsan
--- /dev/null
+#ifndef _ASM_EXTABLE_H
+#define _ASM_EXTABLE_H
+
+/*
+ * About the exception table:
+ *
+ * - insn is a 32-bit pc-relative offset from the faulting insn.
+ * - nextinsn is a 16-bit offset off of the faulting instruction
+ * (not off of the *next* instruction as branches are).
+ * - errreg is the register in which to place -EFAULT.
+ * - valreg is the final target register for the load sequence
+ * and will be zeroed.
+ *
+ * Either errreg or valreg may be $31, in which case nothing happens.
+ *
+ * The exception fixup information "just so happens" to be arranged
+ * as in a MEM format instruction. This lets us emit our three
+ * values like so:
+ *
+ * lda valreg, nextinsn(errreg)
+ *
+ */
+
+struct exception_table_entry
+{
+ signed int insn;
+ union exception_fixup {
+ unsigned unit;
+ struct {
+ signed int nextinsn : 16;
+ unsigned int errreg : 5;
+ unsigned int valreg : 5;
+ } bits;
+ } fixup;
+};
+
+/* Returns the new pc */
+#define fixup_exception(map_reg, _fixup, pc) \
+({ \
+ if ((_fixup)->fixup.bits.valreg != 31) \
+ map_reg((_fixup)->fixup.bits.valreg) = 0; \
+ if ((_fixup)->fixup.bits.errreg != 31) \
+ map_reg((_fixup)->fixup.bits.errreg) = -EFAULT; \
+ (pc) + (_fixup)->fixup.bits.nextinsn; \
+})
+
+#define ARCH_HAS_RELATIVE_EXTABLE
+
+#define swap_ex_entry_fixup(a, b, tmp, delta) \
+ do { \
+ (a)->fixup.unit = (b)->fixup.unit; \
+ (b)->fixup.unit = (tmp).fixup.unit; \
+ } while (0)
+
+#endif
"3: .subsection 2\n" \
"4: br 1b\n" \
" .previous\n" \
- " .section __ex_table,\"a\"\n" \
- " .long 1b-.\n" \
- " lda $31,3b-1b(%1)\n" \
- " .long 2b-.\n" \
- " lda $31,3b-2b(%1)\n" \
- " .previous\n" \
+ EXC(1b,3b,%1,$31) \
+ EXC(2b,3b,%1,$31) \
: "=&r" (oldval), "=&r"(ret) \
: "r" (uaddr), "r"(oparg) \
: "memory")
"3: .subsection 2\n"
"4: br 1b\n"
" .previous\n"
- " .section __ex_table,\"a\"\n"
- " .long 1b-.\n"
- " lda $31,3b-1b(%0)\n"
- " .long 2b-.\n"
- " lda $31,3b-2b(%0)\n"
- " .previous\n"
+ EXC(1b,3b,%0,$31)
+ EXC(2b,3b,%0,$31)
: "+r"(ret), "=&r"(prev), "=&r"(cmp)
: "r"(uaddr), "r"((long)(int)oldval), "r"(newval)
: "memory");
#ifndef __ALPHA_UACCESS_H
#define __ALPHA_UACCESS_H
-#include <linux/errno.h>
-#include <linux/sched.h>
-
-
/*
* The fs value determines whether argument validity checking should be
* performed or not. If get_fs() == USER_DS, checking is performed, with
#define KERNEL_DS ((mm_segment_t) { 0UL })
#define USER_DS ((mm_segment_t) { -0x40000000000UL })
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
#define get_fs() (current_thread_info()->addr_limit)
#define get_ds() (KERNEL_DS)
#define set_fs(x) (current_thread_info()->addr_limit = (x))
* - AND "addr+size" doesn't have any high-bits set
* - OR we are in kernel mode.
*/
-#define __access_ok(addr, size, segment) \
- (((segment).seg & (addr | size | (addr+size))) == 0)
+#define __access_ok(addr, size) \
+ ((get_fs().seg & (addr | size | (addr+size))) == 0)
-#define access_ok(type, addr, size) \
-({ \
- __chk_user_ptr(addr); \
- __access_ok(((unsigned long)(addr)), (size), get_fs()); \
+#define access_ok(type, addr, size) \
+({ \
+ __chk_user_ptr(addr); \
+ __access_ok(((unsigned long)(addr)), (size)); \
})
/*
* (b) require any knowledge of processes at this stage
*/
#define put_user(x, ptr) \
- __put_user_check((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), get_fs())
+ __put_user_check((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
#define get_user(x, ptr) \
- __get_user_check((x), (ptr), sizeof(*(ptr)), get_fs())
+ __get_user_check((x), (ptr), sizeof(*(ptr)))
/*
* The "__xxx" versions do not do address space checking, useful when
* more extensive comments with fixup_inline_exception below for
* more information.
*/
+#define EXC(label,cont,res,err) \
+ ".section __ex_table,\"a\"\n" \
+ " .long "#label"-.\n" \
+ " lda "#res","#cont"-"#label"("#err")\n" \
+ ".previous\n"
extern void __get_user_unknown(void);
__gu_err; \
})
-#define __get_user_check(x, ptr, size, segment) \
-({ \
- long __gu_err = -EFAULT; \
- unsigned long __gu_val = 0; \
- const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \
- if (__access_ok((unsigned long)__gu_addr, size, segment)) { \
- __gu_err = 0; \
- switch (size) { \
- case 1: __get_user_8(__gu_addr); break; \
- case 2: __get_user_16(__gu_addr); break; \
- case 4: __get_user_32(__gu_addr); break; \
- case 8: __get_user_64(__gu_addr); break; \
- default: __get_user_unknown(); break; \
- } \
- } \
- (x) = (__force __typeof__(*(ptr))) __gu_val; \
- __gu_err; \
+#define __get_user_check(x, ptr, size) \
+({ \
+ long __gu_err = -EFAULT; \
+ unsigned long __gu_val = 0; \
+ const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \
+ if (__access_ok((unsigned long)__gu_addr, size)) { \
+ __gu_err = 0; \
+ switch (size) { \
+ case 1: __get_user_8(__gu_addr); break; \
+ case 2: __get_user_16(__gu_addr); break; \
+ case 4: __get_user_32(__gu_addr); break; \
+ case 8: __get_user_64(__gu_addr); break; \
+ default: __get_user_unknown(); break; \
+ } \
+ } \
+ (x) = (__force __typeof__(*(ptr))) __gu_val; \
+ __gu_err; \
})
struct __large_struct { unsigned long buf[100]; };
#define __get_user_64(addr) \
__asm__("1: ldq %0,%2\n" \
"2:\n" \
- ".section __ex_table,\"a\"\n" \
- " .long 1b - .\n" \
- " lda %0, 2b-1b(%1)\n" \
- ".previous" \
+ EXC(1b,2b,%0,%1) \
: "=r"(__gu_val), "=r"(__gu_err) \
: "m"(__m(addr)), "1"(__gu_err))
#define __get_user_32(addr) \
__asm__("1: ldl %0,%2\n" \
"2:\n" \
- ".section __ex_table,\"a\"\n" \
- " .long 1b - .\n" \
- " lda %0, 2b-1b(%1)\n" \
- ".previous" \
+ EXC(1b,2b,%0,%1) \
: "=r"(__gu_val), "=r"(__gu_err) \
: "m"(__m(addr)), "1"(__gu_err))
#define __get_user_16(addr) \
__asm__("1: ldwu %0,%2\n" \
"2:\n" \
- ".section __ex_table,\"a\"\n" \
- " .long 1b - .\n" \
- " lda %0, 2b-1b(%1)\n" \
- ".previous" \
+ EXC(1b,2b,%0,%1) \
: "=r"(__gu_val), "=r"(__gu_err) \
: "m"(__m(addr)), "1"(__gu_err))
#define __get_user_8(addr) \
__asm__("1: ldbu %0,%2\n" \
"2:\n" \
- ".section __ex_table,\"a\"\n" \
- " .long 1b - .\n" \
- " lda %0, 2b-1b(%1)\n" \
- ".previous" \
+ EXC(1b,2b,%0,%1) \
: "=r"(__gu_val), "=r"(__gu_err) \
: "m"(__m(addr)), "1"(__gu_err))
#else
" extwh %1,%3,%1\n" \
" or %0,%1,%0\n" \
"3:\n" \
- ".section __ex_table,\"a\"\n" \
- " .long 1b - .\n" \
- " lda %0, 3b-1b(%2)\n" \
- " .long 2b - .\n" \
- " lda %0, 3b-2b(%2)\n" \
- ".previous" \
+ EXC(1b,3b,%0,%2) \
+ EXC(2b,3b,%0,%2) \
: "=&r"(__gu_val), "=&r"(__gu_tmp), "=r"(__gu_err) \
: "r"(addr), "2"(__gu_err)); \
}
__asm__("1: ldq_u %0,0(%2)\n" \
" extbl %0,%2,%0\n" \
"2:\n" \
- ".section __ex_table,\"a\"\n" \
- " .long 1b - .\n" \
- " lda %0, 2b-1b(%1)\n" \
- ".previous" \
+ EXC(1b,2b,%0,%1) \
: "=&r"(__gu_val), "=r"(__gu_err) \
: "r"(addr), "1"(__gu_err))
#endif
__pu_err; \
})
-#define __put_user_check(x, ptr, size, segment) \
-({ \
- long __pu_err = -EFAULT; \
- __typeof__(*(ptr)) __user *__pu_addr = (ptr); \
- if (__access_ok((unsigned long)__pu_addr, size, segment)) { \
- __pu_err = 0; \
- switch (size) { \
- case 1: __put_user_8(x, __pu_addr); break; \
- case 2: __put_user_16(x, __pu_addr); break; \
- case 4: __put_user_32(x, __pu_addr); break; \
- case 8: __put_user_64(x, __pu_addr); break; \
- default: __put_user_unknown(); break; \
- } \
- } \
- __pu_err; \
+#define __put_user_check(x, ptr, size) \
+({ \
+ long __pu_err = -EFAULT; \
+ __typeof__(*(ptr)) __user *__pu_addr = (ptr); \
+ if (__access_ok((unsigned long)__pu_addr, size)) { \
+ __pu_err = 0; \
+ switch (size) { \
+ case 1: __put_user_8(x, __pu_addr); break; \
+ case 2: __put_user_16(x, __pu_addr); break; \
+ case 4: __put_user_32(x, __pu_addr); break; \
+ case 8: __put_user_64(x, __pu_addr); break; \
+ default: __put_user_unknown(); break; \
+ } \
+ } \
+ __pu_err; \
})
/*
#define __put_user_64(x, addr) \
__asm__ __volatile__("1: stq %r2,%1\n" \
"2:\n" \
- ".section __ex_table,\"a\"\n" \
- " .long 1b - .\n" \
- " lda $31,2b-1b(%0)\n" \
- ".previous" \
+ EXC(1b,2b,$31,%0) \
: "=r"(__pu_err) \
: "m" (__m(addr)), "rJ" (x), "0"(__pu_err))
#define __put_user_32(x, addr) \
__asm__ __volatile__("1: stl %r2,%1\n" \
"2:\n" \
- ".section __ex_table,\"a\"\n" \
- " .long 1b - .\n" \
- " lda $31,2b-1b(%0)\n" \
- ".previous" \
+ EXC(1b,2b,$31,%0) \
: "=r"(__pu_err) \
: "m"(__m(addr)), "rJ"(x), "0"(__pu_err))
#define __put_user_16(x, addr) \
__asm__ __volatile__("1: stw %r2,%1\n" \
"2:\n" \
- ".section __ex_table,\"a\"\n" \
- " .long 1b - .\n" \
- " lda $31,2b-1b(%0)\n" \
- ".previous" \
+ EXC(1b,2b,$31,%0) \
: "=r"(__pu_err) \
: "m"(__m(addr)), "rJ"(x), "0"(__pu_err))
#define __put_user_8(x, addr) \
__asm__ __volatile__("1: stb %r2,%1\n" \
"2:\n" \
- ".section __ex_table,\"a\"\n" \
- " .long 1b - .\n" \
- " lda $31,2b-1b(%0)\n" \
- ".previous" \
+ EXC(1b,2b,$31,%0) \
: "=r"(__pu_err) \
: "m"(__m(addr)), "rJ"(x), "0"(__pu_err))
#else
"3: stq_u %2,1(%5)\n" \
"4: stq_u %1,0(%5)\n" \
"5:\n" \
- ".section __ex_table,\"a\"\n" \
- " .long 1b - .\n" \
- " lda $31, 5b-1b(%0)\n" \
- " .long 2b - .\n" \
- " lda $31, 5b-2b(%0)\n" \
- " .long 3b - .\n" \
- " lda $31, 5b-3b(%0)\n" \
- " .long 4b - .\n" \
- " lda $31, 5b-4b(%0)\n" \
- ".previous" \
+ EXC(1b,5b,$31,%0) \
+ EXC(2b,5b,$31,%0) \
+ EXC(3b,5b,$31,%0) \
+ EXC(4b,5b,$31,%0) \
: "=r"(__pu_err), "=&r"(__pu_tmp1), \
"=&r"(__pu_tmp2), "=&r"(__pu_tmp3), \
"=&r"(__pu_tmp4) \
" or %1,%2,%1\n" \
"2: stq_u %1,0(%4)\n" \
"3:\n" \
- ".section __ex_table,\"a\"\n" \
- " .long 1b - .\n" \
- " lda $31, 3b-1b(%0)\n" \
- " .long 2b - .\n" \
- " lda $31, 3b-2b(%0)\n" \
- ".previous" \
+ EXC(1b,3b,$31,%0) \
+ EXC(2b,3b,$31,%0) \
: "=r"(__pu_err), \
"=&r"(__pu_tmp1), "=&r"(__pu_tmp2) \
: "r"((unsigned long)(x)), "r"(addr), "0"(__pu_err)); \
* Complex access routines
*/
-/* This little bit of silliness is to get the GP loaded for a function
- that ordinarily wouldn't. Otherwise we could have it done by the macro
- directly, which can be optimized the linker. */
-#ifdef MODULE
-#define __module_address(sym) "r"(sym),
-#define __module_call(ra, arg, sym) "jsr $" #ra ",(%" #arg ")," #sym
-#else
-#define __module_address(sym)
-#define __module_call(ra, arg, sym) "bsr $" #ra "," #sym " !samegp"
-#endif
-
-extern void __copy_user(void);
-
-extern inline long
-__copy_tofrom_user_nocheck(void *to, const void *from, long len)
-{
- register void * __cu_to __asm__("$6") = to;
- register const void * __cu_from __asm__("$7") = from;
- register long __cu_len __asm__("$0") = len;
-
- __asm__ __volatile__(
- __module_call(28, 3, __copy_user)
- : "=r" (__cu_len), "=r" (__cu_from), "=r" (__cu_to)
- : __module_address(__copy_user)
- "0" (__cu_len), "1" (__cu_from), "2" (__cu_to)
- : "$1", "$2", "$3", "$4", "$5", "$28", "memory");
-
- return __cu_len;
-}
-
-#define __copy_to_user(to, from, n) \
-({ \
- __chk_user_ptr(to); \
- __copy_tofrom_user_nocheck((__force void *)(to), (from), (n)); \
-})
-#define __copy_from_user(to, from, n) \
-({ \
- __chk_user_ptr(from); \
- __copy_tofrom_user_nocheck((to), (__force void *)(from), (n)); \
-})
-
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
+extern long __copy_user(void *to, const void *from, long len);
-extern inline long
-copy_to_user(void __user *to, const void *from, long n)
+static inline unsigned long
+raw_copy_from_user(void *to, const void __user *from, unsigned long len)
{
- if (likely(__access_ok((unsigned long)to, n, get_fs())))
- n = __copy_tofrom_user_nocheck((__force void *)to, from, n);
- return n;
+ return __copy_user(to, (__force const void *)from, len);
}
-extern inline long
-copy_from_user(void *to, const void __user *from, long n)
+static inline unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long len)
{
- long res = n;
- if (likely(__access_ok((unsigned long)from, n, get_fs())))
- res = __copy_from_user_inatomic(to, from, n);
- if (unlikely(res))
- memset(to + (n - res), 0, res);
- return res;
+ return __copy_user((__force void *)to, from, len);
}
-extern void __do_clear_user(void);
-
-extern inline long
-__clear_user(void __user *to, long len)
-{
- register void __user * __cl_to __asm__("$6") = to;
- register long __cl_len __asm__("$0") = len;
- __asm__ __volatile__(
- __module_call(28, 2, __do_clear_user)
- : "=r"(__cl_len), "=r"(__cl_to)
- : __module_address(__do_clear_user)
- "0"(__cl_len), "1"(__cl_to)
- : "$1", "$2", "$3", "$4", "$5", "$28", "memory");
- return __cl_len;
-}
+extern long __clear_user(void __user *to, long len);
extern inline long
clear_user(void __user *to, long len)
{
- if (__access_ok((unsigned long)to, len, get_fs()))
+ if (__access_ok((unsigned long)to, len))
len = __clear_user(to, len);
return len;
}
-#undef __module_address
-#undef __module_call
-
#define user_addr_max() \
- (segment_eq(get_fs(), USER_DS) ? TASK_SIZE : ~0UL)
+ (uaccess_kernel() ? ~0UL : TASK_SIZE)
extern long strncpy_from_user(char *dest, const char __user *src, long count);
extern __must_check long strlen_user(const char __user *str);
extern __must_check long strnlen_user(const char __user *str, long n);
-/*
- * About the exception table:
- *
- * - insn is a 32-bit pc-relative offset from the faulting insn.
- * - nextinsn is a 16-bit offset off of the faulting instruction
- * (not off of the *next* instruction as branches are).
- * - errreg is the register in which to place -EFAULT.
- * - valreg is the final target register for the load sequence
- * and will be zeroed.
- *
- * Either errreg or valreg may be $31, in which case nothing happens.
- *
- * The exception fixup information "just so happens" to be arranged
- * as in a MEM format instruction. This lets us emit our three
- * values like so:
- *
- * lda valreg, nextinsn(errreg)
- *
- */
-
-struct exception_table_entry
-{
- signed int insn;
- union exception_fixup {
- unsigned unit;
- struct {
- signed int nextinsn : 16;
- unsigned int errreg : 5;
- unsigned int valreg : 5;
- } bits;
- } fixup;
-};
-
-/* Returns the new pc */
-#define fixup_exception(map_reg, _fixup, pc) \
-({ \
- if ((_fixup)->fixup.bits.valreg != 31) \
- map_reg((_fixup)->fixup.bits.valreg) = 0; \
- if ((_fixup)->fixup.bits.errreg != 31) \
- map_reg((_fixup)->fixup.bits.errreg) = -EFAULT; \
- (pc) + (_fixup)->fixup.bits.nextinsn; \
-})
-
-#define ARCH_HAS_RELATIVE_EXTABLE
-
-#define swap_ex_entry_fixup(a, b, tmp, delta) \
- do { \
- (a)->fixup.unit = (b)->fixup.unit; \
- (b)->fixup.unit = (tmp).fixup.unit; \
- } while (0)
-
+#include <asm/extable.h>
#endif /* __ALPHA_UACCESS_H */
SYSCALL_DEFINE2(osf_settimeofday, struct timeval32 __user *, tv,
struct timezone __user *, tz)
{
+ struct timespec64 kts64;
struct timespec kts;
struct timezone ktz;
if (get_tv32((struct timeval *)&kts, tv))
return -EFAULT;
kts.tv_nsec *= 1000;
+ kts64 = timespec_to_timespec64(kts);
}
if (tz) {
if (copy_from_user(&ktz, tz, sizeof(*tz)))
return -EFAULT;
}
- return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL);
+ return do_sys_settimeofday64(tv ? &kts64 : NULL, tz ? &ktz : NULL);
}
asmlinkage long sys_ni_posix_timers(void);
/* copy relevant bits of struct timex. */
if (copy_from_user(&txc, txc_p, offsetof(struct timex32, time)) ||
copy_from_user(&txc.tick, &txc_p->tick, sizeof(struct timex32) -
- offsetof(struct timex32, time)))
+ offsetof(struct timex32, tick)))
return -EFAULT;
ret = do_adjtimex(&txc);
" extwl %1,%3,%1\n"
" extwh %2,%3,%2\n"
"3:\n"
- ".section __ex_table,\"a\"\n"
- " .long 1b - .\n"
- " lda %1,3b-1b(%0)\n"
- " .long 2b - .\n"
- " lda %2,3b-2b(%0)\n"
- ".previous"
+ EXC(1b,3b,%1,%0)
+ EXC(2b,3b,%2,%0)
: "=r"(error), "=&r"(tmp1), "=&r"(tmp2)
: "r"(va), "0"(0));
if (error)
" extll %1,%3,%1\n"
" extlh %2,%3,%2\n"
"3:\n"
- ".section __ex_table,\"a\"\n"
- " .long 1b - .\n"
- " lda %1,3b-1b(%0)\n"
- " .long 2b - .\n"
- " lda %2,3b-2b(%0)\n"
- ".previous"
+ EXC(1b,3b,%1,%0)
+ EXC(2b,3b,%2,%0)
: "=r"(error), "=&r"(tmp1), "=&r"(tmp2)
: "r"(va), "0"(0));
if (error)
" extql %1,%3,%1\n"
" extqh %2,%3,%2\n"
"3:\n"
- ".section __ex_table,\"a\"\n"
- " .long 1b - .\n"
- " lda %1,3b-1b(%0)\n"
- " .long 2b - .\n"
- " lda %2,3b-2b(%0)\n"
- ".previous"
+ EXC(1b,3b,%1,%0)
+ EXC(2b,3b,%2,%0)
: "=r"(error), "=&r"(tmp1), "=&r"(tmp2)
: "r"(va), "0"(0));
if (error)
"3: stq_u %2,1(%5)\n"
"4: stq_u %1,0(%5)\n"
"5:\n"
- ".section __ex_table,\"a\"\n"
- " .long 1b - .\n"
- " lda %2,5b-1b(%0)\n"
- " .long 2b - .\n"
- " lda %1,5b-2b(%0)\n"
- " .long 3b - .\n"
- " lda $31,5b-3b(%0)\n"
- " .long 4b - .\n"
- " lda $31,5b-4b(%0)\n"
- ".previous"
+ EXC(1b,5b,%2,%0)
+ EXC(2b,5b,%1,%0)
+ EXC(3b,5b,$31,%0)
+ EXC(4b,5b,$31,%0)
: "=r"(error), "=&r"(tmp1), "=&r"(tmp2),
"=&r"(tmp3), "=&r"(tmp4)
: "r"(va), "r"(una_reg(reg)), "0"(0));
"3: stq_u %2,3(%5)\n"
"4: stq_u %1,0(%5)\n"
"5:\n"
- ".section __ex_table,\"a\"\n"
- " .long 1b - .\n"
- " lda %2,5b-1b(%0)\n"
- " .long 2b - .\n"
- " lda %1,5b-2b(%0)\n"
- " .long 3b - .\n"
- " lda $31,5b-3b(%0)\n"
- " .long 4b - .\n"
- " lda $31,5b-4b(%0)\n"
- ".previous"
+ EXC(1b,5b,%2,%0)
+ EXC(2b,5b,%1,%0)
+ EXC(3b,5b,$31,%0)
+ EXC(4b,5b,$31,%0)
: "=r"(error), "=&r"(tmp1), "=&r"(tmp2),
"=&r"(tmp3), "=&r"(tmp4)
: "r"(va), "r"(una_reg(reg)), "0"(0));
"3: stq_u %2,7(%5)\n"
"4: stq_u %1,0(%5)\n"
"5:\n"
- ".section __ex_table,\"a\"\n\t"
- " .long 1b - .\n"
- " lda %2,5b-1b(%0)\n"
- " .long 2b - .\n"
- " lda %1,5b-2b(%0)\n"
- " .long 3b - .\n"
- " lda $31,5b-3b(%0)\n"
- " .long 4b - .\n"
- " lda $31,5b-4b(%0)\n"
- ".previous"
+ EXC(1b,5b,%2,%0)
+ EXC(2b,5b,%1,%0)
+ EXC(3b,5b,$31,%0)
+ EXC(4b,5b,$31,%0)
: "=r"(error), "=&r"(tmp1), "=&r"(tmp2),
"=&r"(tmp3), "=&r"(tmp4)
: "r"(va), "r"(una_reg(reg)), "0"(0));
/* Don't bother reading ds in the access check since we already
know that this came from the user. Also rely on the fact that
the page at TASK_SIZE is unmapped and so can't be touched anyway. */
- if (!__access_ok((unsigned long)va, 0, USER_DS))
+ if ((unsigned long)va >= TASK_SIZE)
goto give_sigsegv;
++unaligned[1].count;
" extwl %1,%3,%1\n"
" extwh %2,%3,%2\n"
"3:\n"
- ".section __ex_table,\"a\"\n"
- " .long 1b - .\n"
- " lda %1,3b-1b(%0)\n"
- " .long 2b - .\n"
- " lda %2,3b-2b(%0)\n"
- ".previous"
+ EXC(1b,3b,%1,%0)
+ EXC(2b,3b,%2,%0)
: "=r"(error), "=&r"(tmp1), "=&r"(tmp2)
: "r"(va), "0"(0));
if (error)
" extll %1,%3,%1\n"
" extlh %2,%3,%2\n"
"3:\n"
- ".section __ex_table,\"a\"\n"
- " .long 1b - .\n"
- " lda %1,3b-1b(%0)\n"
- " .long 2b - .\n"
- " lda %2,3b-2b(%0)\n"
- ".previous"
+ EXC(1b,3b,%1,%0)
+ EXC(2b,3b,%2,%0)
: "=r"(error), "=&r"(tmp1), "=&r"(tmp2)
: "r"(va), "0"(0));
if (error)
" extql %1,%3,%1\n"
" extqh %2,%3,%2\n"
"3:\n"
- ".section __ex_table,\"a\"\n"
- " .long 1b - .\n"
- " lda %1,3b-1b(%0)\n"
- " .long 2b - .\n"
- " lda %2,3b-2b(%0)\n"
- ".previous"
+ EXC(1b,3b,%1,%0)
+ EXC(2b,3b,%2,%0)
: "=r"(error), "=&r"(tmp1), "=&r"(tmp2)
: "r"(va), "0"(0));
if (error)
" extll %1,%3,%1\n"
" extlh %2,%3,%2\n"
"3:\n"
- ".section __ex_table,\"a\"\n"
- " .long 1b - .\n"
- " lda %1,3b-1b(%0)\n"
- " .long 2b - .\n"
- " lda %2,3b-2b(%0)\n"
- ".previous"
+ EXC(1b,3b,%1,%0)
+ EXC(2b,3b,%2,%0)
: "=r"(error), "=&r"(tmp1), "=&r"(tmp2)
: "r"(va), "0"(0));
if (error)
" extql %1,%3,%1\n"
" extqh %2,%3,%2\n"
"3:\n"
- ".section __ex_table,\"a\"\n"
- " .long 1b - .\n"
- " lda %1,3b-1b(%0)\n"
- " .long 2b - .\n"
- " lda %2,3b-2b(%0)\n"
- ".previous"
+ EXC(1b,3b,%1,%0)
+ EXC(2b,3b,%2,%0)
: "=r"(error), "=&r"(tmp1), "=&r"(tmp2)
: "r"(va), "0"(0));
if (error)
"3: stq_u %2,1(%5)\n"
"4: stq_u %1,0(%5)\n"
"5:\n"
- ".section __ex_table,\"a\"\n"
- " .long 1b - .\n"
- " lda %2,5b-1b(%0)\n"
- " .long 2b - .\n"
- " lda %1,5b-2b(%0)\n"
- " .long 3b - .\n"
- " lda $31,5b-3b(%0)\n"
- " .long 4b - .\n"
- " lda $31,5b-4b(%0)\n"
- ".previous"
+ EXC(1b,5b,%2,%0)
+ EXC(2b,5b,%1,%0)
+ EXC(3b,5b,$31,%0)
+ EXC(4b,5b,$31,%0)
: "=r"(error), "=&r"(tmp1), "=&r"(tmp2),
"=&r"(tmp3), "=&r"(tmp4)
: "r"(va), "r"(*reg_addr), "0"(0));
"3: stq_u %2,3(%5)\n"
"4: stq_u %1,0(%5)\n"
"5:\n"
- ".section __ex_table,\"a\"\n"
- " .long 1b - .\n"
- " lda %2,5b-1b(%0)\n"
- " .long 2b - .\n"
- " lda %1,5b-2b(%0)\n"
- " .long 3b - .\n"
- " lda $31,5b-3b(%0)\n"
- " .long 4b - .\n"
- " lda $31,5b-4b(%0)\n"
- ".previous"
+ EXC(1b,5b,%2,%0)
+ EXC(2b,5b,%1,%0)
+ EXC(3b,5b,$31,%0)
+ EXC(4b,5b,$31,%0)
: "=r"(error), "=&r"(tmp1), "=&r"(tmp2),
"=&r"(tmp3), "=&r"(tmp4)
: "r"(va), "r"(*reg_addr), "0"(0));
"3: stq_u %2,7(%5)\n"
"4: stq_u %1,0(%5)\n"
"5:\n"
- ".section __ex_table,\"a\"\n\t"
- " .long 1b - .\n"
- " lda %2,5b-1b(%0)\n"
- " .long 2b - .\n"
- " lda %1,5b-2b(%0)\n"
- " .long 3b - .\n"
- " lda $31,5b-3b(%0)\n"
- " .long 4b - .\n"
- " lda $31,5b-4b(%0)\n"
- ".previous"
+ EXC(1b,5b,%2,%0)
+ EXC(2b,5b,%1,%0)
+ EXC(3b,5b,$31,%0)
+ EXC(4b,5b,$31,%0)
: "=r"(error), "=&r"(tmp1), "=&r"(tmp2),
"=&r"(tmp3), "=&r"(tmp4)
: "r"(va), "r"(*reg_addr), "0"(0));
/* We need to replicate some of the logic in mm/fault.c,
since we don't have access to the fault code in the
exception handling return path. */
- if (!__access_ok((unsigned long)va, 0, USER_DS))
+ if ((unsigned long)va >= TASK_SIZE)
info.si_code = SEGV_ACCERR;
else {
struct mm_struct *mm = current->mm;
* right "bytes left to zero" value (and that it is updated only _after_
* a successful copy). There is also some rather minor exception setup
* stuff.
- *
- * NOTE! This is not directly C-callable, because the calling semantics
- * are different:
- *
- * Inputs:
- * length in $0
- * destination address in $6
- * exception pointer in $7
- * return address in $28 (exceptions expect it there)
- *
- * Outputs:
- * bytes left to copy in $0
- *
- * Clobbers:
- * $1,$2,$3,$4,$5,$6
*/
#include <asm/export.h>
.set noreorder
.align 4
- .globl __do_clear_user
- .ent __do_clear_user
- .frame $30, 0, $28
+ .globl __clear_user
+ .ent __clear_user
+ .frame $30, 0, $26
.prologue 0
$loop:
and $1, 3, $4 # e0 :
beq $4, 1f # .. e1 :
-0: EX( stq_u $31, 0($6) ) # e0 : zero one word
+0: EX( stq_u $31, 0($16) ) # e0 : zero one word
subq $0, 8, $0 # .. e1 :
subq $4, 1, $4 # e0 :
- addq $6, 8, $6 # .. e1 :
+ addq $16, 8, $16 # .. e1 :
bne $4, 0b # e1 :
unop # :
1: bic $1, 3, $1 # e0 :
beq $1, $tail # .. e1 :
-2: EX( stq_u $31, 0($6) ) # e0 : zero four words
+2: EX( stq_u $31, 0($16) ) # e0 : zero four words
subq $0, 8, $0 # .. e1 :
- EX( stq_u $31, 8($6) ) # e0 :
+ EX( stq_u $31, 8($16) ) # e0 :
subq $0, 8, $0 # .. e1 :
- EX( stq_u $31, 16($6) ) # e0 :
+ EX( stq_u $31, 16($16) ) # e0 :
subq $0, 8, $0 # .. e1 :
- EX( stq_u $31, 24($6) ) # e0 :
+ EX( stq_u $31, 24($16) ) # e0 :
subq $0, 8, $0 # .. e1 :
subq $1, 4, $1 # e0 :
- addq $6, 32, $6 # .. e1 :
+ addq $16, 32, $16 # .. e1 :
bne $1, 2b # e1 :
$tail:
bne $2, 1f # e1 : is there a tail to do?
- ret $31, ($28), 1 # .. e1 :
+ ret $31, ($26), 1 # .. e1 :
-1: EX( ldq_u $5, 0($6) ) # e0 :
+1: EX( ldq_u $5, 0($16) ) # e0 :
clr $0 # .. e1 :
nop # e1 :
mskqh $5, $0, $5 # e0 :
- EX( stq_u $5, 0($6) ) # e0 :
- ret $31, ($28), 1 # .. e1 :
+ EX( stq_u $5, 0($16) ) # e0 :
+ ret $31, ($26), 1 # .. e1 :
-__do_clear_user:
- and $6, 7, $4 # e0 : find dest misalignment
+__clear_user:
+ and $17, $17, $0
+ and $16, 7, $4 # e0 : find dest misalignment
beq $0, $zerolength # .. e1 :
addq $0, $4, $1 # e0 : bias counter
and $1, 7, $2 # e1 : number of bytes in tail
srl $1, 3, $1 # e0 :
beq $4, $loop # .. e1 :
- EX( ldq_u $5, 0($6) ) # e0 : load dst word to mask back in
+ EX( ldq_u $5, 0($16) ) # e0 : load dst word to mask back in
beq $1, $oneword # .. e1 : sub-word store?
- mskql $5, $6, $5 # e0 : take care of misaligned head
- addq $6, 8, $6 # .. e1 :
- EX( stq_u $5, -8($6) ) # e0 :
+ mskql $5, $16, $5 # e0 : take care of misaligned head
+ addq $16, 8, $16 # .. e1 :
+ EX( stq_u $5, -8($16) ) # e0 :
addq $0, $4, $0 # .. e1 : bytes left -= 8 - misalignment
subq $1, 1, $1 # e0 :
subq $0, 8, $0 # .. e1 :
unop # :
$oneword:
- mskql $5, $6, $4 # e0 :
+ mskql $5, $16, $4 # e0 :
mskqh $5, $2, $5 # e0 :
or $5, $4, $5 # e1 :
- EX( stq_u $5, 0($6) ) # e0 :
+ EX( stq_u $5, 0($16) ) # e0 :
clr $0 # .. e1 :
$zerolength:
$exception:
- ret $31, ($28), 1 # .. e1 :
+ ret $31, ($26), 1 # .. e1 :
- .end __do_clear_user
- EXPORT_SYMBOL(__do_clear_user)
+ .end __clear_user
+ EXPORT_SYMBOL(__clear_user)
* contains the right "bytes left to copy" value (and that it is updated
* only _after_ a successful copy). There is also some rather minor
* exception setup stuff..
- *
- * NOTE! This is not directly C-callable, because the calling semantics are
- * different:
- *
- * Inputs:
- * length in $0
- * destination address in $6
- * source address in $7
- * return address in $28
- *
- * Outputs:
- * bytes left to copy in $0
- *
- * Clobbers:
- * $1,$2,$3,$4,$5,$6,$7
*/
#include <asm/export.h>
.ent __copy_user
__copy_user:
.prologue 0
- and $6,7,$3
+ and $18,$18,$0
+ and $16,7,$3
beq $0,$35
beq $3,$36
subq $3,8,$3
.align 4
$37:
- EXI( ldq_u $1,0($7) )
- EXO( ldq_u $2,0($6) )
- extbl $1,$7,$1
- mskbl $2,$6,$2
- insbl $1,$6,$1
+ EXI( ldq_u $1,0($17) )
+ EXO( ldq_u $2,0($16) )
+ extbl $1,$17,$1
+ mskbl $2,$16,$2
+ insbl $1,$16,$1
addq $3,1,$3
bis $1,$2,$1
- EXO( stq_u $1,0($6) )
+ EXO( stq_u $1,0($16) )
subq $0,1,$0
- addq $6,1,$6
- addq $7,1,$7
+ addq $16,1,$16
+ addq $17,1,$17
beq $0,$41
bne $3,$37
$36:
- and $7,7,$1
+ and $17,7,$1
bic $0,7,$4
beq $1,$43
beq $4,$48
- EXI( ldq_u $3,0($7) )
+ EXI( ldq_u $3,0($17) )
.align 4
$50:
- EXI( ldq_u $2,8($7) )
+ EXI( ldq_u $2,8($17) )
subq $4,8,$4
- extql $3,$7,$3
- extqh $2,$7,$1
+ extql $3,$17,$3
+ extqh $2,$17,$1
bis $3,$1,$1
- EXO( stq $1,0($6) )
- addq $7,8,$7
+ EXO( stq $1,0($16) )
+ addq $17,8,$17
subq $0,8,$0
- addq $6,8,$6
+ addq $16,8,$16
bis $2,$2,$3
bne $4,$50
$48:
beq $0,$41
.align 4
$57:
- EXI( ldq_u $1,0($7) )
- EXO( ldq_u $2,0($6) )
- extbl $1,$7,$1
- mskbl $2,$6,$2
- insbl $1,$6,$1
+ EXI( ldq_u $1,0($17) )
+ EXO( ldq_u $2,0($16) )
+ extbl $1,$17,$1
+ mskbl $2,$16,$2
+ insbl $1,$16,$1
bis $1,$2,$1
- EXO( stq_u $1,0($6) )
+ EXO( stq_u $1,0($16) )
subq $0,1,$0
- addq $6,1,$6
- addq $7,1,$7
+ addq $16,1,$16
+ addq $17,1,$17
bne $0,$57
br $31,$41
.align 4
beq $4,$65
.align 4
$66:
- EXI( ldq $1,0($7) )
+ EXI( ldq $1,0($17) )
subq $4,8,$4
- EXO( stq $1,0($6) )
- addq $7,8,$7
+ EXO( stq $1,0($16) )
+ addq $17,8,$17
subq $0,8,$0
- addq $6,8,$6
+ addq $16,8,$16
bne $4,$66
$65:
beq $0,$41
- EXI( ldq $2,0($7) )
- EXO( ldq $1,0($6) )
+ EXI( ldq $2,0($17) )
+ EXO( ldq $1,0($16) )
mskql $2,$0,$2
mskqh $1,$0,$1
bis $2,$1,$2
- EXO( stq $2,0($6) )
+ EXO( stq $2,0($16) )
bis $31,$31,$0
$41:
$35:
$exitin:
$exitout:
- ret $31,($28),1
+ ret $31,($26),1
.end __copy_user
EXPORT_SYMBOL(__copy_user)
__asm__ __volatile__( \
"1: ldq_u %0,%2\n" \
"2:\n" \
- ".section __ex_table,\"a\"\n" \
- " .long 1b - .\n" \
- " lda %0,2b-1b(%1)\n" \
- ".previous" \
+ EXC(1b,2b,%0,%1) \
: "=r"(x), "=r"(__guu_err) \
: "m"(__m(ptr)), "1"(0)); \
__guu_err; \
__asm__ __volatile__( \
"1: stq_u %2,%1\n" \
"2:\n" \
- ".section __ex_table,\"a\"\n" \
- " .long 1b - ." \
- " lda $31,2b-1b(%0)\n" \
- ".previous" \
+ EXC(1b,2b,$31,%0) \
: "=r"(__puu_err) \
: "m"(__m(addr)), "rJ"(x), "0"(0)); \
__puu_err; \
* a successful copy). There is also some rather minor exception setup
* stuff.
*
- * NOTE! This is not directly C-callable, because the calling semantics
- * are different:
- *
- * Inputs:
- * length in $0
- * destination address in $6
- * exception pointer in $7
- * return address in $28 (exceptions expect it there)
- *
- * Outputs:
- * bytes left to copy in $0
- *
- * Clobbers:
- * $1,$2,$3,$4,$5,$6
- *
* Much of the information about 21264 scheduling/coding comes from:
* Compiler Writer's Guide for the Alpha 21264
* abbreviated as 'CWG' in other comments here
.set noreorder
.align 4
- .globl __do_clear_user
- .ent __do_clear_user
- .frame $30, 0, $28
+ .globl __clear_user
+ .ent __clear_user
+ .frame $30, 0, $26
.prologue 0
# Pipeline info : Slotting & Comments
-__do_clear_user:
- and $6, 7, $4 # .. E .. .. : find dest head misalignment
+__clear_user:
+ and $17, $17, $0
+ and $16, 7, $4 # .. E .. .. : find dest head misalignment
beq $0, $zerolength # U .. .. .. : U L U L
addq $0, $4, $1 # .. .. .. E : bias counter
/*
* Head is not aligned. Write (8 - $4) bytes to head of destination
- * This means $6 is known to be misaligned
+ * This means $16 is known to be misaligned
*/
- EX( ldq_u $5, 0($6) ) # .. .. .. L : load dst word to mask back in
+ EX( ldq_u $5, 0($16) ) # .. .. .. L : load dst word to mask back in
beq $1, $onebyte # .. .. U .. : sub-word store?
- mskql $5, $6, $5 # .. U .. .. : take care of misaligned head
- addq $6, 8, $6 # E .. .. .. : L U U L
+ mskql $5, $16, $5 # .. U .. .. : take care of misaligned head
+ addq $16, 8, $16 # E .. .. .. : L U U L
- EX( stq_u $5, -8($6) ) # .. .. .. L :
+ EX( stq_u $5, -8($16) ) # .. .. .. L :
subq $1, 1, $1 # .. .. E .. :
addq $0, $4, $0 # .. E .. .. : bytes left -= 8 - misalignment
subq $0, 8, $0 # E .. .. .. : U L U L
* values upon initial entry to the loop
* $1 is number of quadwords to clear (zero is a valid value)
* $2 is number of trailing bytes (0..7) ($2 never used...)
- * $6 is known to be aligned 0mod8
+ * $16 is known to be aligned 0mod8
*/
$headalign:
subq $1, 16, $4 # .. .. .. E : If < 16, we can not use the huge loop
- and $6, 0x3f, $2 # .. .. E .. : Forward work for huge loop
+ and $16, 0x3f, $2 # .. .. E .. : Forward work for huge loop
subq $2, 0x40, $3 # .. E .. .. : bias counter (huge loop)
blt $4, $trailquad # U .. .. .. : U L U L
beq $3, $bigalign # U .. .. .. : U L U L : Aligned 0mod64
$alignmod64:
- EX( stq_u $31, 0($6) ) # .. .. .. L
+ EX( stq_u $31, 0($16) ) # .. .. .. L
addq $3, 8, $3 # .. .. E ..
subq $0, 8, $0 # .. E .. ..
nop # E .. .. .. : U L U L
nop # .. .. .. E
subq $1, 1, $1 # .. .. E ..
- addq $6, 8, $6 # .. E .. ..
+ addq $16, 8, $16 # .. E .. ..
blt $3, $alignmod64 # U .. .. .. : U L U L
$bigalign:
/*
* $0 is the number of bytes left
* $1 is the number of quads left
- * $6 is aligned 0mod64
+ * $16 is aligned 0mod64
* we know that we'll be taking a minimum of one trip through
* CWG Section 3.7.6: do not expect a sustained store rate of > 1/cycle
* We are _not_ going to update $0 after every single store. That
nop # E :
nop # E :
nop # E :
- bis $6,$6,$3 # E : U L U L : Initial wh64 address is dest
+ bis $16,$16,$3 # E : U L U L : Initial wh64 address is dest
/* This might actually help for the current trip... */
$do_wh64:
wh64 ($3) # .. .. .. L1 : memory subsystem hint
subq $1, 16, $4 # .. .. E .. : Forward calculation - repeat the loop?
- EX( stq_u $31, 0($6) ) # .. L .. ..
+ EX( stq_u $31, 0($16) ) # .. L .. ..
subq $0, 8, $0 # E .. .. .. : U L U L
- addq $6, 128, $3 # E : Target address of wh64
- EX( stq_u $31, 8($6) ) # L :
- EX( stq_u $31, 16($6) ) # L :
+ addq $16, 128, $3 # E : Target address of wh64
+ EX( stq_u $31, 8($16) ) # L :
+ EX( stq_u $31, 16($16) ) # L :
subq $0, 16, $0 # E : U L L U
nop # E :
- EX( stq_u $31, 24($6) ) # L :
- EX( stq_u $31, 32($6) ) # L :
+ EX( stq_u $31, 24($16) ) # L :
+ EX( stq_u $31, 32($16) ) # L :
subq $0, 168, $5 # E : U L L U : two trips through the loop left?
/* 168 = 192 - 24, since we've already completed some stores */
subq $0, 16, $0 # E :
- EX( stq_u $31, 40($6) ) # L :
- EX( stq_u $31, 48($6) ) # L :
- cmovlt $5, $6, $3 # E : U L L U : Latency 2, extra mapping cycle
+ EX( stq_u $31, 40($16) ) # L :
+ EX( stq_u $31, 48($16) ) # L :
+ cmovlt $5, $16, $3 # E : U L L U : Latency 2, extra mapping cycle
subq $1, 8, $1 # E :
subq $0, 16, $0 # E :
- EX( stq_u $31, 56($6) ) # L :
+ EX( stq_u $31, 56($16) ) # L :
nop # E : U L U L
nop # E :
subq $0, 8, $0 # E :
- addq $6, 64, $6 # E :
+ addq $16, 64, $16 # E :
bge $4, $do_wh64 # U : U L U L
$trailquad:
beq $1, $trailbytes # U .. .. .. : U L U L : Only 0..7 bytes to go
$onequad:
- EX( stq_u $31, 0($6) ) # .. .. .. L
+ EX( stq_u $31, 0($16) ) # .. .. .. L
subq $1, 1, $1 # .. .. E ..
subq $0, 8, $0 # .. E .. ..
nop # E .. .. .. : U L U L
nop # .. .. .. E
nop # .. .. E ..
- addq $6, 8, $6 # .. E .. ..
+ addq $16, 8, $16 # .. E .. ..
bgt $1, $onequad # U .. .. .. : U L U L
# We have an unknown number of bytes left to go.
# so we will use $0 as the loop counter
# We know for a fact that $0 > 0 zero due to previous context
$onebyte:
- EX( stb $31, 0($6) ) # .. .. .. L
+ EX( stb $31, 0($16) ) # .. .. .. L
subq $0, 1, $0 # .. .. E .. :
- addq $6, 1, $6 # .. E .. .. :
+ addq $16, 1, $16 # .. E .. .. :
bgt $0, $onebyte # U .. .. .. : U L U L
$zerolength:
nop # .. .. .. E :
nop # .. .. E .. :
nop # .. E .. .. :
- ret $31, ($28), 1 # L0 .. .. .. : L U L U
- .end __do_clear_user
- EXPORT_SYMBOL(__do_clear_user)
+ ret $31, ($26), 1 # L0 .. .. .. : L U L U
+ .end __clear_user
+ EXPORT_SYMBOL(__clear_user)
* only _after_ a successful copy). There is also some rather minor
* exception setup stuff..
*
- * NOTE! This is not directly C-callable, because the calling semantics are
- * different:
- *
- * Inputs:
- * length in $0
- * destination address in $6
- * source address in $7
- * return address in $28
- *
- * Outputs:
- * bytes left to copy in $0
- *
- * Clobbers:
- * $1,$2,$3,$4,$5,$6,$7
- *
* Much of the information about 21264 scheduling/coding comes from:
* Compiler Writer's Guide for the Alpha 21264
* abbreviated as 'CWG' in other comments here
# Pipeline info: Slotting & Comments
__copy_user:
.prologue 0
- subq $0, 32, $1 # .. E .. .. : Is this going to be a small copy?
+ andq $18, $18, $0
+ subq $18, 32, $1 # .. E .. .. : Is this going to be a small copy?
beq $0, $zerolength # U .. .. .. : U L U L
- and $6,7,$3 # .. .. .. E : is leading dest misalignment
+ and $16,7,$3 # .. .. .. E : is leading dest misalignment
ble $1, $onebyteloop # .. .. U .. : 1st branch : small amount of data
beq $3, $destaligned # .. U .. .. : 2nd (one cycle fetcher stall)
subq $3, 8, $3 # E .. .. .. : L U U L : trip counter
* We know we have at least one trip through this loop
*/
$aligndest:
- EXI( ldbu $1,0($7) ) # .. .. .. L : Keep loads separate from stores
- addq $6,1,$6 # .. .. E .. : Section 3.8 in the CWG
+ EXI( ldbu $1,0($17) ) # .. .. .. L : Keep loads separate from stores
+ addq $16,1,$16 # .. .. E .. : Section 3.8 in the CWG
addq $3,1,$3 # .. E .. .. :
nop # E .. .. .. : U L U L
/*
- * the -1 is to compensate for the inc($6) done in a previous quadpack
+ * the -1 is to compensate for the inc($16) done in a previous quadpack
* which allows us zero dependencies within either quadpack in the loop
*/
- EXO( stb $1,-1($6) ) # .. .. .. L :
- addq $7,1,$7 # .. .. E .. : Section 3.8 in the CWG
+ EXO( stb $1,-1($16) ) # .. .. .. L :
+ addq $17,1,$17 # .. .. E .. : Section 3.8 in the CWG
subq $0,1,$0 # .. E .. .. :
bne $3, $aligndest # U .. .. .. : U L U L
* If we arrived via branch, we have a minimum of 32 bytes
*/
$destaligned:
- and $7,7,$1 # .. .. .. E : Check _current_ source alignment
+ and $17,7,$1 # .. .. .. E : Check _current_ source alignment
bic $0,7,$4 # .. .. E .. : number bytes as a quadword loop
- EXI( ldq_u $3,0($7) ) # .. L .. .. : Forward fetch for fallthrough code
+ EXI( ldq_u $3,0($17) ) # .. L .. .. : Forward fetch for fallthrough code
beq $1,$quadaligned # U .. .. .. : U L U L
/*
- * In the worst case, we've just executed an ldq_u here from 0($7)
+ * In the worst case, we've just executed an ldq_u here from 0($17)
* and we'll repeat it once if we take the branch
*/
/* Misaligned quadword loop - not unrolled. Leave it that way. */
$misquad:
- EXI( ldq_u $2,8($7) ) # .. .. .. L :
+ EXI( ldq_u $2,8($17) ) # .. .. .. L :
subq $4,8,$4 # .. .. E .. :
- extql $3,$7,$3 # .. U .. .. :
- extqh $2,$7,$1 # U .. .. .. : U U L L
+ extql $3,$17,$3 # .. U .. .. :
+ extqh $2,$17,$1 # U .. .. .. : U U L L
bis $3,$1,$1 # .. .. .. E :
- EXO( stq $1,0($6) ) # .. .. L .. :
- addq $7,8,$7 # .. E .. .. :
+ EXO( stq $1,0($16) ) # .. .. L .. :
+ addq $17,8,$17 # .. E .. .. :
subq $0,8,$0 # E .. .. .. : U L L U
- addq $6,8,$6 # .. .. .. E :
+ addq $16,8,$16 # .. .. .. E :
bis $2,$2,$3 # .. .. E .. :
nop # .. E .. .. :
bne $4,$misquad # U .. .. .. : U L U L
beq $0,$zerolength # U .. .. .. : U L U L
/* We know we have at least one trip through the byte loop */
- EXI ( ldbu $2,0($7) ) # .. .. .. L : No loads in the same quad
- addq $6,1,$6 # .. .. E .. : as the store (Section 3.8 in CWG)
+ EXI ( ldbu $2,0($17) ) # .. .. .. L : No loads in the same quad
+ addq $16,1,$16 # .. .. E .. : as the store (Section 3.8 in CWG)
nop # .. E .. .. :
br $31, $dirtyentry # L0 .. .. .. : L U U L
/* Do the trailing byte loop load, then hop into the store part of the loop */
* Based upon the usage context, it's worth the effort to unroll this loop
* $0 - number of bytes to be moved
* $4 - number of bytes to move as quadwords
- * $6 is current destination address
- * $7 is current source address
+ * $16 is current destination address
+ * $17 is current source address
*/
$quadaligned:
subq $4, 32, $2 # .. .. .. E : do not unroll for small stuff
* instruction memory hint instruction).
*/
$unroll4:
- EXI( ldq $1,0($7) ) # .. .. .. L
- EXI( ldq $2,8($7) ) # .. .. L ..
+ EXI( ldq $1,0($17) ) # .. .. .. L
+ EXI( ldq $2,8($17) ) # .. .. L ..
subq $4,32,$4 # .. E .. ..
nop # E .. .. .. : U U L L
- addq $7,16,$7 # .. .. .. E
- EXO( stq $1,0($6) ) # .. .. L ..
- EXO( stq $2,8($6) ) # .. L .. ..
+ addq $17,16,$17 # .. .. .. E
+ EXO( stq $1,0($16) ) # .. .. L ..
+ EXO( stq $2,8($16) ) # .. L .. ..
subq $0,16,$0 # E .. .. .. : U L L U
- addq $6,16,$6 # .. .. .. E
- EXI( ldq $1,0($7) ) # .. .. L ..
- EXI( ldq $2,8($7) ) # .. L .. ..
+ addq $16,16,$16 # .. .. .. E
+ EXI( ldq $1,0($17) ) # .. .. L ..
+ EXI( ldq $2,8($17) ) # .. L .. ..
subq $4, 32, $3 # E .. .. .. : U U L L : is there enough for another trip?
- EXO( stq $1,0($6) ) # .. .. .. L
- EXO( stq $2,8($6) ) # .. .. L ..
+ EXO( stq $1,0($16) ) # .. .. .. L
+ EXO( stq $2,8($16) ) # .. .. L ..
subq $0,16,$0 # .. E .. ..
- addq $7,16,$7 # E .. .. .. : U L L U
+ addq $17,16,$17 # E .. .. .. : U L L U
nop # .. .. .. E
nop # .. .. E ..
- addq $6,16,$6 # .. E .. ..
+ addq $16,16,$16 # .. E .. ..
bgt $3,$unroll4 # U .. .. .. : U L U L
nop
beq $4, $noquads
$onequad:
- EXI( ldq $1,0($7) )
+ EXI( ldq $1,0($17) )
subq $4,8,$4
- addq $7,8,$7
+ addq $17,8,$17
nop
- EXO( stq $1,0($6) )
+ EXO( stq $1,0($16) )
subq $0,8,$0
- addq $6,8,$6
+ addq $16,8,$16
bne $4,$onequad
$noquads:
* There's no point in doing a lot of complex alignment calculations to try to
* to quadword stuff for a small amount of data.
* $0 - remaining number of bytes left to copy
- * $6 - current dest addr
- * $7 - current source addr
+ * $16 - current dest addr
+ * $17 - current source addr
*/
$onebyteloop:
- EXI ( ldbu $2,0($7) ) # .. .. .. L : No loads in the same quad
- addq $6,1,$6 # .. .. E .. : as the store (Section 3.8 in CWG)
+ EXI ( ldbu $2,0($17) ) # .. .. .. L : No loads in the same quad
+ addq $16,1,$16 # .. .. E .. : as the store (Section 3.8 in CWG)
nop # .. E .. .. :
nop # E .. .. .. : U L U L
$dirtyentry:
/*
- * the -1 is to compensate for the inc($6) done in a previous quadpack
+ * the -1 is to compensate for the inc($16) done in a previous quadpack
* which allows us zero dependencies within either quadpack in the loop
*/
- EXO ( stb $2,-1($6) ) # .. .. .. L :
- addq $7,1,$7 # .. .. E .. : quadpack as the load
+ EXO ( stb $2,-1($16) ) # .. .. .. L :
+ addq $17,1,$17 # .. .. E .. : quadpack as the load
subq $0,1,$0 # .. E .. .. : change count _after_ copy
bgt $0,$onebyteloop # U .. .. .. : U L U L
nop # .. .. .. E
nop # .. .. E ..
nop # .. E .. ..
- ret $31,($28),1 # L0 .. .. .. : L U L U
+ ret $31,($26),1 # L0 .. .. .. : L U L U
.end __copy_user
EXPORT_SYMBOL(__copy_user)
bool "Insn: div, divu, rem, remu"
default y
+config ARC_HAS_ACCL_REGS
+ bool "Reg Pair ACCL:ACCH (FPU and/or MPY > 6)"
+ default n
+ help
+ Depending on the configuration, CPU can contain accumulator reg-pair
+ (also referred to as r58:r59). These can also be used by gcc as GPR so
+ kernel needs to save/restore per process
+
endif # ISA_ARCV2
endmenu # "ARC CPU Configuration"
generic-y += div64.h
generic-y += emergency-restart.h
generic-y += errno.h
+generic-y += extable.h
generic-y += fb.h
generic-y += fcntl.h
generic-y += ftrace.h
#include <asm/barrier.h>
#include <asm/smp.h>
+#define ATOMIC_INIT(i) { (i) }
+
#ifndef CONFIG_ARC_PLAT_EZNPS
#define atomic_read(v) READ_ONCE((v)->counter)
-#define ATOMIC_INIT(i) { (i) }
#ifdef CONFIG_ARC_HAS_LLSC
;
; Now manually save: r12, sp, fp, gp, r25
+#ifdef CONFIG_ARC_HAS_ACCL_REGS
+ PUSH r59
+ PUSH r58
+#endif
+
PUSH r30
PUSH r12
POP r12
POP r30
+#ifdef CONFIG_ARC_HAS_ACCL_REGS
+ POP r58
+ POP r59
+#endif
+
.endm
/*------------------------------------------------------------------------*/
unsigned long r12, r30;
+#ifdef CONFIG_ARC_HAS_ACCL_REGS
+ unsigned long r58, r59; /* ACCL/ACCH used by FPU / DSP MPY */
+#endif
+
/*------- Below list auto saved by h/w -----------*/
unsigned long r0, r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11;
#ifndef _ASM_ARC_UACCESS_H
#define _ASM_ARC_UACCESS_H
-#include <linux/sched.h>
-#include <asm/errno.h>
#include <linux/string.h> /* for generic string functions */
-#define __kernel_ok (segment_eq(get_fs(), KERNEL_DS))
+#define __kernel_ok (uaccess_kernel())
/*
* Algorithmically, for __user_ok() we want do:
static inline unsigned long
-__arc_copy_from_user(void *to, const void __user *from, unsigned long n)
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
{
long res = 0;
char val;
return res;
}
-extern unsigned long slowpath_copy_to_user(void __user *to, const void *from,
- unsigned long n);
-
static inline unsigned long
-__arc_copy_to_user(void __user *to, const void *from, unsigned long n)
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
{
long res = 0;
char val;
}
#ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE
-#define __copy_from_user(t, f, n) __arc_copy_from_user(t, f, n)
-#define __copy_to_user(t, f, n) __arc_copy_to_user(t, f, n)
+
+#define INLINE_COPY_TO_USER
+#define INLINE_COPY_FROM_USER
+
#define __clear_user(d, n) __arc_clear_user(d, n)
#define __strncpy_from_user(d, s, n) __arc_strncpy_from_user(d, s, n)
#define __strnlen_user(s, n) __arc_strnlen_user(s, n)
#else
-extern long arc_copy_from_user_noinline(void *to, const void __user * from,
- unsigned long n);
-extern long arc_copy_to_user_noinline(void __user *to, const void *from,
- unsigned long n);
extern unsigned long arc_clear_user_noinline(void __user *to,
unsigned long n);
extern long arc_strncpy_from_user_noinline (char *dst, const char __user *src,
long count);
extern long arc_strnlen_user_noinline(const char __user *src, long n);
-#define __copy_from_user(t, f, n) arc_copy_from_user_noinline(t, f, n)
-#define __copy_to_user(t, f, n) arc_copy_to_user_noinline(t, f, n)
#define __clear_user(d, n) arc_clear_user_noinline(d, n)
#define __strncpy_from_user(d, s, n) arc_strncpy_from_user_noinline(d, s, n)
#define __strnlen_user(s, n) arc_strnlen_user_noinline(s, n)
#include <asm-generic/uaccess.h>
-extern int fixup_exception(struct pt_regs *regs);
-
#endif
static void arc_chk_core_config(void)
{
struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
- int fpu_enabled;
+ int saved = 0, present = 0;
+ char *opt_nm = NULL;;
if (!cpu->extn.timer0)
panic("Timer0 is not present!\n");
/*
* FP hardware/software config sanity
- * -If hardware contains DPFP, kernel needs to save/restore FPU state
+ * -If hardware present, kernel needs to save/restore FPU state
* -If not, it will crash trying to save/restore the non-existant regs
- *
- * (only DPDP checked since SP has no arch visible regs)
*/
- fpu_enabled = IS_ENABLED(CONFIG_ARC_FPU_SAVE_RESTORE);
- if (cpu->extn.fpu_dp && !fpu_enabled)
- pr_warn("CONFIG_ARC_FPU_SAVE_RESTORE needed for working apps\n");
- else if (!cpu->extn.fpu_dp && fpu_enabled)
- panic("FPU non-existent, disable CONFIG_ARC_FPU_SAVE_RESTORE\n");
+ if (is_isa_arcompact()) {
+ opt_nm = "CONFIG_ARC_FPU_SAVE_RESTORE";
+ saved = IS_ENABLED(CONFIG_ARC_FPU_SAVE_RESTORE);
+
+ /* only DPDP checked since SP has no arch visible regs */
+ present = cpu->extn.fpu_dp;
+ } else {
+ opt_nm = "CONFIG_ARC_HAS_ACCL_REGS";
+ saved = IS_ENABLED(CONFIG_ARC_HAS_ACCL_REGS);
+
+ /* Accumulator Low:High pair (r58:59) present if DSP MPY or FPU */
+ present = cpu->extn_mpy.dsp | cpu->extn.fpu_sp | cpu->extn.fpu_dp;
+ }
+
+ if (present && !saved)
+ pr_warn("Enable %s for working apps\n", opt_nm);
+ else if (!present && saved)
+ panic("Disable %s, hardware NOT present\n", opt_nm);
}
/*
#ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
-long arc_copy_from_user_noinline(void *to, const void __user *from,
- unsigned long n)
-{
- return __arc_copy_from_user(to, from, n);
-}
-EXPORT_SYMBOL(arc_copy_from_user_noinline);
-
-long arc_copy_to_user_noinline(void __user *to, const void *from,
- unsigned long n)
-{
- return __arc_copy_to_user(to, from, n);
-}
-EXPORT_SYMBOL(arc_copy_to_user_noinline);
-
unsigned long arc_clear_user_noinline(void __user *to,
unsigned long n)
{
select HARDIRQS_SW_RESEND
select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
- select HAVE_ARCH_HARDENED_USERCOPY
select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
select HAVE_ARCH_MMAP_RND_BITS if MMU
phy1: ethernet-phy@1 {
reg = <7>;
+ eee-broken-100tx;
+ eee-broken-1000t;
};
};
ti,non-removable;
bus-width = <4>;
cap-power-off-card;
+ keep-power-in-suspend;
pinctrl-names = "default";
pinctrl-0 = <&mmc2_pins>;
device_type = "pci";
ranges = <0x81000000 0 0 0x03000 0 0x00010000
0x82000000 0 0x20013000 0x13000 0 0xffed000>;
+ bus-range = <0x00 0xff>;
#interrupt-cells = <1>;
num-lanes = <1>;
linux,pci-domain = <0>;
device_type = "pci";
ranges = <0x81000000 0 0 0x03000 0 0x00010000
0x82000000 0 0x30013000 0x13000 0 0xffed000>;
+ bus-range = <0x00 0xff>;
#interrupt-cells = <1>;
num-lanes = <1>;
linux,pci-domain = <1>;
&i2c3 {
clock-frequency = <400000>;
at24@50 {
- compatible = "at24,24c02";
+ compatible = "atmel,24c64";
readonly;
reg = <0x50>;
};
};
};
+ timer3: timer@2000e000 {
+ compatible = "rockchip,rk3188-timer", "rockchip,rk3288-timer";
+ reg = <0x2000e000 0x20>;
+ interrupts = <GIC_SPI 46 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&cru SCLK_TIMER3>, <&cru PCLK_TIMER3>;
+ clock-names = "timer", "pclk";
+ };
+
+ timer6: timer@200380a0 {
+ compatible = "rockchip,rk3188-timer", "rockchip,rk3288-timer";
+ reg = <0x200380a0 0x20>;
+ interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&cru SCLK_TIMER6>, <&cru PCLK_TIMER0>;
+ clock-names = "timer", "pclk";
+ };
+
i2s0: i2s@1011a000 {
compatible = "rockchip,rk3188-i2s", "rockchip,rk3066-i2s";
reg = <0x1011a000 0x2000>;
&global_timer {
interrupts = <GIC_PPI 11 0xf04>;
+ status = "disabled";
};
&local_timer {
};
timer: timer@110c0000 {
- compatible = "rockchip,rk3288-timer";
+ compatible = "rockchip,rk3228-timer", "rockchip,rk3288-timer";
reg = <0x110c0000 0x20>;
interrupts = <GIC_SPI 43 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&xin24m>, <&cru PCLK_TIMER>;
status = "disabled";
};
- cpufreq-cooling {
- compatible = "stericsson,db8500-cpufreq-cooling";
- status = "disabled";
- };
-
mcde@a0350000 {
compatible = "stericsson,mcde";
reg = <0xa0350000 0x1000>, /* MCDE */
opp-microvolt = <1200000>;
clock-latency-ns = <244144>; /* 8 32k periods */
};
-
- opp@1200000000 {
- opp-hz = /bits/ 64 <1200000000>;
- opp-microvolt = <1320000>;
- clock-latency-ns = <244144>; /* 8 32k periods */
- };
};
cpus {
operating-points-v2 = <&cpu0_opp_table>;
};
+ cpu@1 {
+ operating-points-v2 = <&cpu0_opp_table>;
+ };
+
cpu@2 {
compatible = "arm,cortex-a7";
device_type = "cpu";
reg = <2>;
+ operating-points-v2 = <&cpu0_opp_table>;
};
cpu@3 {
compatible = "arm,cortex-a7";
device_type = "cpu";
reg = <3>;
+ operating-points-v2 = <&cpu0_opp_table>;
};
};
CONFIG_LEDS_TRIGGER_TRANSIENT=y
CONFIG_LEDS_TRIGGER_CAMERA=y
CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
CONFIG_EDAC_HIGHBANK_MC=y
CONFIG_EDAC_HIGHBANK_L2=y
CONFIG_RTC_CLASS=y
CONFIG_LEDS_TRIGGER_DEFAULT_ON=m
CONFIG_LEDS_TRIGGER_TRANSIENT=m
CONFIG_LEDS_TRIGGER_CAMERA=m
-CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=m
+CONFIG_EDAC=m
CONFIG_RTC_CLASS=y
CONFIG_RTC_DEBUG=y
CONFIG_RTC_DRV_DS1307=m
generic-y += emergency-restart.h
generic-y += errno.h
generic-y += exec.h
+generic-y += extable.h
generic-y += ioctl.h
generic-y += ipcbuf.h
generic-y += irq_regs.h
*/
#define ZIMAGE_OFFSET_LIMIT SZ_128M
#define MIN_ZIMAGE_OFFSET MAX_UNCOMP_KERNEL_SIZE
-#define MAX_FDT_OFFSET ZIMAGE_OFFSET_LIMIT
+
+/* on ARM, the FDT should be located in the first 128 MB of RAM */
+static inline unsigned long efi_get_max_fdt_addr(unsigned long dram_base)
+{
+ return dram_base + ZIMAGE_OFFSET_LIMIT;
+}
+
+/* on ARM, the initrd should be loaded in a lowmem region */
+static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base,
+ unsigned long image_addr)
+{
+ return dram_base + SZ_512M;
+}
#endif /* _ASM_ARM_EFI_H */
* User space memory access functions
*/
#include <linux/string.h>
-#include <linux/thread_info.h>
-#include <asm/errno.h>
#include <asm/memory.h>
#include <asm/domain.h>
#include <asm/unified.h>
#define __put_user_unaligned __put_user
#endif
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue. No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path. This means when everything is well,
- * we don't even have to jump over them. Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry
-{
- unsigned long insn, fixup;
-};
-
-extern int fixup_exception(struct pt_regs *regs);
+#include <asm/extable.h>
/*
* These two functions allow hooking accesses to userspace to increase
#define access_ok(type, addr, size) (__range_ok(addr, size) == 0)
#define user_addr_max() \
- (segment_eq(get_fs(), KERNEL_DS) ? ~0UL : get_fs())
+ (uaccess_kernel() ? ~0UL : get_fs())
/*
* The "__xxx" versions of the user access functions do not verify the
arm_copy_from_user(void *to, const void __user *from, unsigned long n);
static inline unsigned long __must_check
-__arch_copy_from_user(void *to, const void __user *from, unsigned long n)
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
{
unsigned int __ua_flags;
__copy_to_user_std(void __user *to, const void *from, unsigned long n);
static inline unsigned long __must_check
-__arch_copy_to_user(void __user *to, const void *from, unsigned long n)
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
{
#ifndef CONFIG_UACCESS_WITH_MEMCPY
unsigned int __ua_flags;
}
#else
-#define __arch_copy_from_user(to, from, n) \
- (memcpy(to, (void __force *)from, n), 0)
-#define __arch_copy_to_user(to, from, n) \
- (memcpy((void __force *)to, from, n), 0)
-#define __clear_user(addr, n) (memset((void __force *)addr, 0, n), 0)
-#endif
-
-static inline unsigned long __must_check
-__copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- check_object_size(to, n, false);
- return __arch_copy_from_user(to, from, n);
-}
-
-static inline unsigned long __must_check
-copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- unsigned long res = n;
-
- check_object_size(to, n, false);
-
- if (likely(access_ok(VERIFY_READ, from, n)))
- res = __arch_copy_from_user(to, from, n);
- if (unlikely(res))
- memset(to + (n - res), 0, res);
- return res;
-}
-
-static inline unsigned long __must_check
-__copy_to_user(void __user *to, const void *from, unsigned long n)
+static inline unsigned long
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
{
- check_object_size(from, n, true);
-
- return __arch_copy_to_user(to, from, n);
+ memcpy(to, (const void __force *)from, n);
+ return 0;
}
-
-static inline unsigned long __must_check
-copy_to_user(void __user *to, const void *from, unsigned long n)
+static inline unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
{
- check_object_size(from, n, true);
-
- if (access_ok(VERIFY_WRITE, to, n))
- n = __arch_copy_to_user(to, from, n);
- return n;
+ memcpy((void __force *)to, from, n);
+ return 0;
}
-
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
+#define __clear_user(addr, n) (memset((void __force *)addr, 0, n), 0)
+#endif
+#define INLINE_COPY_TO_USER
+#define INLINE_COPY_FROM_USER
static inline unsigned long __must_check clear_user(void __user *to, unsigned long n)
{
if (__hyp_get_vectors() == hyp_default_vectors)
cpu_init_hyp_mode(NULL);
}
+
+ if (vgic_present)
+ kvm_vgic_init_cpu_hardware();
}
static void cpu_hyp_reset(void)
phys_addr_t addr = start, end = start + size;
phys_addr_t next;
+ assert_spin_locked(&kvm->mmu_lock);
pgd = kvm->arch.pgd + stage2_pgd_index(addr);
do {
next = stage2_pgd_addr_end(addr, end);
if (!stage2_pgd_none(*pgd))
unmap_stage2_puds(kvm, pgd, addr, next);
+ /*
+ * If the range is too large, release the kvm->mmu_lock
+ * to prevent starvation and lockup detector warnings.
+ */
+ if (next != end)
+ cond_resched_lock(&kvm->mmu_lock);
} while (pgd++, addr = next, addr != end);
}
int idx;
idx = srcu_read_lock(&kvm->srcu);
+ down_read(¤t->mm->mmap_sem);
spin_lock(&kvm->mmu_lock);
slots = kvm_memslots(kvm);
stage2_unmap_memslot(kvm, memslot);
spin_unlock(&kvm->mmu_lock);
+ up_read(¤t->mm->mmap_sem);
srcu_read_unlock(&kvm->srcu, idx);
}
if (kvm->arch.pgd == NULL)
return;
+ spin_lock(&kvm->mmu_lock);
unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
+ spin_unlock(&kvm->mmu_lock);
+
/* Free the HW pgd, one page at a time */
free_pages_exact(kvm->arch.pgd, S2_PGD_SIZE);
kvm->arch.pgd = NULL;
(KVM_PHYS_SIZE >> PAGE_SHIFT))
return -EFAULT;
+ down_read(¤t->mm->mmap_sem);
/*
* A memory region could potentially cover multiple VMAs, and any holes
* between them, so iterate over all of them to find out if we can map
pa += vm_start - vma->vm_start;
/* IO region dirty page logging not allowed */
- if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES)
- return -EINVAL;
+ if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) {
+ ret = -EINVAL;
+ goto out;
+ }
ret = kvm_phys_addr_ioremap(kvm, gpa, pa,
vm_end - vm_start,
} while (hva < reg_end);
if (change == KVM_MR_FLAGS_ONLY)
- return ret;
+ goto out;
spin_lock(&kvm->mmu_lock);
if (ret)
else
stage2_flush_memslot(kvm, memslot);
spin_unlock(&kvm->mmu_lock);
+out:
+ up_read(¤t->mm->mmap_sem);
return ret;
}
unsigned long ua_flags;
int atomic;
- if (unlikely(segment_eq(get_fs(), KERNEL_DS))) {
+ if (uaccess_kernel()) {
memcpy((void *)to, from, n);
return 0;
}
{
unsigned long ua_flags;
- if (unlikely(segment_eq(get_fs(), KERNEL_DS))) {
+ if (uaccess_kernel()) {
memset((void *)addr, 0, n);
return 0;
}
depends on ARCH_MULTI_V4
select CPU_FA526
select ARM_DMA_MEM_BUFFERABLE
+ select FARADAY_FTINTC010
select MOXART_TIMER
- select GENERIC_IRQ_CHIP
select GPIOLIB
select PHYLIB if NETDEVICES
help
extern int omap4_mpuss_init(void);
extern int omap4_enter_lowpower(unsigned int cpu, unsigned int power_state);
extern int omap4_hotplug_cpu(unsigned int cpu, unsigned int power_state);
+extern u32 omap4_get_cpu1_ns_pa_addr(void);
#else
static inline int omap4_enter_lowpower(unsigned int cpu,
unsigned int power_state)
omap4_hotplug_cpu(cpu, PWRDM_POWER_OFF);
if (omap_secure_apis_support())
- boot_cpu = omap_read_auxcoreboot0();
+ boot_cpu = omap_read_auxcoreboot0() >> 9;
else
boot_cpu =
readl_relaxed(base + OMAP_AUX_CORE_BOOT_0) >> 5;
#include "prm-regbits-44xx.h"
static void __iomem *sar_base;
+static u32 old_cpu1_ns_pa_addr;
#if defined(CONFIG_PM) && defined(CONFIG_SMP)
{}
#endif
+u32 omap4_get_cpu1_ns_pa_addr(void)
+{
+ return old_cpu1_ns_pa_addr;
+}
+
/**
* omap4_enter_lowpower: OMAP4 MPUSS Low Power Entry Function
* The purpose of this function is to manage low power programming
void __init omap4_mpuss_early_init(void)
{
unsigned long startup_pa;
+ void __iomem *ns_pa_addr;
- if (!(cpu_is_omap44xx() || soc_is_omap54xx()))
+ if (!(soc_is_omap44xx() || soc_is_omap54xx()))
return;
sar_base = omap4_get_sar_ram_base();
- if (cpu_is_omap443x())
+ /* Save old NS_PA_ADDR for validity checks later on */
+ if (soc_is_omap44xx())
+ ns_pa_addr = sar_base + CPU1_WAKEUP_NS_PA_ADDR_OFFSET;
+ else
+ ns_pa_addr = sar_base + OMAP5_CPU1_WAKEUP_NS_PA_ADDR_OFFSET;
+ old_cpu1_ns_pa_addr = readl_relaxed(ns_pa_addr);
+
+ if (soc_is_omap443x())
startup_pa = __pa_symbol(omap4_secondary_startup);
- else if (cpu_is_omap446x())
+ else if (soc_is_omap446x())
startup_pa = __pa_symbol(omap4460_secondary_startup);
else if ((__boot_cpu_mode & MODE_MASK) == HYP_MODE)
startup_pa = __pa_symbol(omap5_secondary_hyp_startup);
else
startup_pa = __pa_symbol(omap5_secondary_startup);
- if (cpu_is_omap44xx())
+ if (soc_is_omap44xx())
writel_relaxed(startup_pa, sar_base +
CPU1_WAKEUP_NS_PA_ADDR_OFFSET);
else
ldr r12, =0x103
dsb
smc #0
- mov r0, r0, lsr #9
ldmfd sp!, {r2-r12, pc}
ENDPROC(omap_read_auxcoreboot0)
#include <linux/io.h>
#include <linux/irqchip/arm-gic.h>
+#include <asm/sections.h>
#include <asm/smp_scu.h>
#include <asm/virt.h>
#define OMAP5_CORE_COUNT 0x2
+#define AUX_CORE_BOOT0_GP_RELEASE 0x020
+#define AUX_CORE_BOOT0_HS_RELEASE 0x200
+
struct omap_smp_config {
unsigned long cpu1_rstctrl_pa;
void __iomem *cpu1_rstctrl_va;
void __iomem *scu_base;
+ void __iomem *wakeupgen_base;
void *startup_addr;
};
static struct clockdomain *cpu1_clkdm;
static bool booted;
static struct powerdomain *cpu1_pwrdm;
- void __iomem *base = omap_get_wakeupgen_base();
/*
* Set synchronisation state between this boot processor
* A barrier is added to ensure that write buffer is drained
*/
if (omap_secure_apis_support())
- omap_modify_auxcoreboot0(0x200, 0xfffffdff);
+ omap_modify_auxcoreboot0(AUX_CORE_BOOT0_HS_RELEASE,
+ 0xfffffdff);
else
- writel_relaxed(0x20, base + OMAP_AUX_CORE_BOOT_0);
+ writel_relaxed(AUX_CORE_BOOT0_GP_RELEASE,
+ cfg.wakeupgen_base + OMAP_AUX_CORE_BOOT_0);
if (!cpu1_clkdm && !cpu1_pwrdm) {
cpu1_clkdm = clkdm_lookup("mpu1_clkdm");
set_cpu_possible(i, true);
}
+/*
+ * For now, just make sure the start-up address is not within the booting
+ * kernel space as that means we just overwrote whatever secondary_startup()
+ * code there was.
+ */
+static bool __init omap4_smp_cpu1_startup_valid(unsigned long addr)
+{
+ if ((addr >= __pa(PAGE_OFFSET)) && (addr <= __pa(__bss_start)))
+ return false;
+
+ return true;
+}
+
+/*
+ * We may need to reset CPU1 before configuring, otherwise kexec boot can end
+ * up trying to use old kernel startup address or suspend-resume will
+ * occasionally fail to bring up CPU1 on 4430 if CPU1 fails to enter deeper
+ * idle states.
+ */
+static void __init omap4_smp_maybe_reset_cpu1(struct omap_smp_config *c)
+{
+ unsigned long cpu1_startup_pa, cpu1_ns_pa_addr;
+ bool needs_reset = false;
+ u32 released;
+
+ if (omap_secure_apis_support())
+ released = omap_read_auxcoreboot0() & AUX_CORE_BOOT0_HS_RELEASE;
+ else
+ released = readl_relaxed(cfg.wakeupgen_base +
+ OMAP_AUX_CORE_BOOT_0) &
+ AUX_CORE_BOOT0_GP_RELEASE;
+ if (released) {
+ pr_warn("smp: CPU1 not parked?\n");
+
+ return;
+ }
+
+ cpu1_startup_pa = readl_relaxed(cfg.wakeupgen_base +
+ OMAP_AUX_CORE_BOOT_1);
+ cpu1_ns_pa_addr = omap4_get_cpu1_ns_pa_addr();
+
+ /* Did the configured secondary_startup() get overwritten? */
+ if (!omap4_smp_cpu1_startup_valid(cpu1_startup_pa))
+ needs_reset = true;
+
+ /*
+ * If omap4 or 5 has NS_PA_ADDR configured, CPU1 may be in a
+ * deeper idle state in WFI and will wake to an invalid address.
+ */
+ if ((soc_is_omap44xx() || soc_is_omap54xx()) &&
+ !omap4_smp_cpu1_startup_valid(cpu1_ns_pa_addr))
+ needs_reset = true;
+
+ if (!needs_reset || !c->cpu1_rstctrl_va)
+ return;
+
+ pr_info("smp: CPU1 parked within kernel, needs reset (0x%lx 0x%lx)\n",
+ cpu1_startup_pa, cpu1_ns_pa_addr);
+
+ writel_relaxed(1, c->cpu1_rstctrl_va);
+ readl_relaxed(c->cpu1_rstctrl_va);
+ writel_relaxed(0, c->cpu1_rstctrl_va);
+}
+
static void __init omap4_smp_prepare_cpus(unsigned int max_cpus)
{
- void __iomem *base = omap_get_wakeupgen_base();
const struct omap_smp_config *c = NULL;
if (soc_is_omap443x())
/* Must preserve cfg.scu_base set earlier */
cfg.cpu1_rstctrl_pa = c->cpu1_rstctrl_pa;
cfg.startup_addr = c->startup_addr;
+ cfg.wakeupgen_base = omap_get_wakeupgen_base();
if (soc_is_dra74x() || soc_is_omap54xx()) {
if ((__boot_cpu_mode & MODE_MASK) == HYP_MODE)
if (cfg.scu_base)
scu_enable(cfg.scu_base);
- /*
- * Reset CPU1 before configuring, otherwise kexec will
- * end up trying to use old kernel startup address.
- */
- if (cfg.cpu1_rstctrl_va) {
- writel_relaxed(1, cfg.cpu1_rstctrl_va);
- readl_relaxed(cfg.cpu1_rstctrl_va);
- writel_relaxed(0, cfg.cpu1_rstctrl_va);
- }
+ omap4_smp_maybe_reset_cpu1(&cfg);
/*
* Write the address of secondary startup routine into the
omap_auxcoreboot_addr(__pa_symbol(cfg.startup_addr));
else
writel_relaxed(__pa_symbol(cfg.startup_addr),
- base + OMAP_AUX_CORE_BOOT_1);
+ cfg.wakeupgen_base + OMAP_AUX_CORE_BOOT_1);
}
const struct smp_operations omap4_smp_ops __initconst = {
dev_err(dev, "failed to idle\n");
}
break;
+ case BUS_NOTIFY_BIND_DRIVER:
+ od = to_omap_device(pdev);
+ if (od && (od->_state == OMAP_DEVICE_STATE_ENABLED) &&
+ pm_runtime_status_suspended(dev)) {
+ od->_driver_status = BUS_NOTIFY_BIND_DRIVER;
+ pm_runtime_set_active(dev);
+ }
+ break;
case BUS_NOTIFY_ADD_DEVICE:
if (pdev->dev.of_node)
omap_device_build_from_dt(pdev);
select GPIOLIB
select MVEBU_MBUS
select PCI
+ select PHYLIB if NETDEVICES
select PLAT_ORION_LEGACY
help
Support for the following Marvell Orion 5x series SoCs:
__arm_dma_free(dev, size, cpu_addr, handle, attrs, true);
}
+/*
+ * The whole dma_get_sgtable() idea is fundamentally unsafe - it seems
+ * that the intention is to allow exporting memory allocated via the
+ * coherent DMA APIs through the dma_buf API, which only accepts a
+ * scattertable. This presents a couple of problems:
+ * 1. Not all memory allocated via the coherent DMA APIs is backed by
+ * a struct page
+ * 2. Passing coherent DMA memory into the streaming APIs is not allowed
+ * as we will try to flush the memory through a different alias to that
+ * actually being used (and the flushes are redundant.)
+ */
int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
void *cpu_addr, dma_addr_t handle, size_t size,
unsigned long attrs)
{
- struct page *page = pfn_to_page(dma_to_pfn(dev, handle));
+ unsigned long pfn = dma_to_pfn(dev, handle);
+ struct page *page;
int ret;
+ /* If the PFN is not valid, we do not have a struct page */
+ if (!pfn_valid(pfn))
+ return -ENXIO;
+
+ page = pfn_to_page(pfn);
+
ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
if (unlikely(ret))
return ret;
*/
static inline bool security_extensions_enabled(void)
{
- return !!cpuid_feature_extract(CPUID_EXT_PFR1, 4);
+ /* Check CPUID Identification Scheme before ID_PFR1 read */
+ if ((read_cpuid_id() & 0x000f0000) == 0x000f0000)
+ return !!cpuid_feature_extract(CPUID_EXT_PFR1, 4);
+ return 0;
}
static unsigned long __init setup_vectors_base(void)
eth_data, &orion_ge11);
}
+#ifdef CONFIG_ARCH_ORION5X
/*****************************************************************************
* Ethernet switch
****************************************************************************/
struct mdio_board_info *bd;
unsigned int i;
+ if (!IS_BUILTIN(CONFIG_PHYLIB))
+ return;
+
for (i = 0; i < ARRAY_SIZE(d->port_names); i++)
if (!strcmp(d->port_names[i], "cpu"))
break;
mdiobus_register_board_info(&orion_ge00_switch_board_info, 1);
}
+#endif
/*****************************************************************************
* I2C
#endif
if (p) {
- if (cur) {
+ if (!p->ainsn.insn_check_cc(regs->ARM_cpsr)) {
+ /*
+ * Probe hit but conditional execution check failed,
+ * so just skip the instruction and continue as if
+ * nothing had happened.
+ * In this case, we can skip recursing check too.
+ */
+ singlestep_skip(p, regs);
+ } else if (cur) {
/* Kprobe is pending, so we're recursing. */
switch (kcb->kprobe_status) {
case KPROBE_HIT_ACTIVE:
case KPROBE_HIT_SSDONE:
+ case KPROBE_HIT_SS:
/* A pre- or post-handler probe got us here. */
kprobes_inc_nmissed_count(p);
save_previous_kprobe(kcb);
singlestep(p, regs, kcb);
restore_previous_kprobe(kcb);
break;
+ case KPROBE_REENTER:
+ /* A nested probe was hit in FIQ, it is a BUG */
+ pr_warn("Unrecoverable kprobe detected at %p.\n",
+ p->addr);
+ /* fall through */
default:
/* impossible cases */
BUG();
}
- } else if (p->ainsn.insn_check_cc(regs->ARM_cpsr)) {
+ } else {
/* Probe hit and conditional execution check ok. */
set_current_kprobe(p);
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
}
reset_current_kprobe();
}
- } else {
- /*
- * Probe hit but conditional execution check failed,
- * so just skip the instruction and continue as if
- * nothing had happened.
- */
- singlestep_skip(p, regs);
}
} else if (cur) {
/* We probably hit a jprobe. Call its break handler. */
struct hlist_node *tmp;
unsigned long flags, orig_ret_address = 0;
unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
+ kprobe_opcode_t *correct_ret_addr = NULL;
INIT_HLIST_HEAD(&empty_rp);
kretprobe_hash_lock(current, &head, &flags);
/* another task is sharing our hash bucket */
continue;
+ orig_ret_address = (unsigned long)ri->ret_addr;
+
+ if (orig_ret_address != trampoline_address)
+ /*
+ * This is the real return address. Any other
+ * instances associated with this task are for
+ * other calls deeper on the call stack
+ */
+ break;
+ }
+
+ kretprobe_assert(ri, orig_ret_address, trampoline_address);
+
+ correct_ret_addr = ri->ret_addr;
+ hlist_for_each_entry_safe(ri, tmp, head, hlist) {
+ if (ri->task != current)
+ /* another task is sharing our hash bucket */
+ continue;
+
+ orig_ret_address = (unsigned long)ri->ret_addr;
if (ri->rp && ri->rp->handler) {
__this_cpu_write(current_kprobe, &ri->rp->kp);
get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
+ ri->ret_addr = correct_ret_addr;
ri->rp->handler(ri, regs);
__this_cpu_write(current_kprobe, NULL);
}
- orig_ret_address = (unsigned long)ri->ret_addr;
recycle_rp_inst(ri, &empty_rp);
if (orig_ret_address != trampoline_address)
break;
}
- kretprobe_assert(ri, orig_ret_address, trampoline_address);
kretprobe_hash_unlock(current, &flags);
hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
void __naked __kprobes_test_case_start(void)
{
__asm__ __volatile__ (
- "stmdb sp!, {r4-r11} \n\t"
+ "mov r2, sp \n\t"
+ "bic r3, r2, #7 \n\t"
+ "mov sp, r3 \n\t"
+ "stmdb sp!, {r2-r11} \n\t"
"sub sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t"
"bic r0, lr, #1 @ r0 = inline data \n\t"
"mov r1, sp \n\t"
"movne pc, r0 \n\t"
"mov r0, r4 \n\t"
"add sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t"
- "ldmia sp!, {r4-r11} \n\t"
+ "ldmia sp!, {r2-r11} \n\t"
+ "mov sp, r2 \n\t"
"mov pc, r0 \n\t"
);
}
"bxne r0 \n\t"
"mov r0, r4 \n\t"
"add sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t"
- "ldmia sp!, {r4-r11} \n\t"
+ "ldmia sp!, {r2-r11} \n\t"
+ "mov sp, r2 \n\t"
"bx r0 \n\t"
);
}
def_bool y
select ACPI_CCA_REQUIRED if ACPI
select ACPI_GENERIC_GSI if ACPI
+ select ACPI_GTDT if ACPI
select ACPI_REDUCED_HARDWARE_ONLY if ACPI
select ACPI_MCFG if ACPI
select ACPI_SPCR_TABLE if ACPI
select HAVE_ALIGNED_STRUCT_PAGE if SLUB
select HAVE_ARCH_AUDITSYSCALL
select HAVE_ARCH_BITREVERSE
- select HAVE_ARCH_HARDENED_USERCOPY
select HAVE_ARCH_HUGE_VMAP
select HAVE_ARCH_JUMP_LABEL
select HAVE_ARCH_KASAN if SPARSEMEM_VMEMMAP && !(ARM64_16K_PAGES && ARM64_VA_BITS_48)
usbphy: phy@01c19400 {
compatible = "allwinner,sun50i-a64-usb-phy";
reg = <0x01c19400 0x14>,
+ <0x01c1a800 0x4>,
<0x01c1b800 0x4>;
reg-names = "phy_ctrl",
+ "pmu0",
"pmu1";
clocks = <&ccu CLK_USB_PHY0>,
<&ccu CLK_USB_PHY1>;
#include <linux/bug.h>
#include <linux/init.h>
#include <linux/jump_label.h>
+#include <linux/smp.h>
#include <linux/types.h>
#include <clocksource/arm_arch_timer.h>
#define needs_unstable_timer_counter_workaround() false
#endif
+enum arch_timer_erratum_match_type {
+ ate_match_dt,
+ ate_match_local_cap_id,
+ ate_match_acpi_oem_info,
+};
+
+struct clock_event_device;
struct arch_timer_erratum_workaround {
- const char *id; /* Indicate the Erratum ID */
+ enum arch_timer_erratum_match_type match_type;
+ const void *id;
+ const char *desc;
u32 (*read_cntp_tval_el0)(void);
u32 (*read_cntv_tval_el0)(void);
u64 (*read_cntvct_el0)(void);
+ int (*set_next_event_phys)(unsigned long, struct clock_event_device *);
+ int (*set_next_event_virt)(unsigned long, struct clock_event_device *);
};
-extern const struct arch_timer_erratum_workaround *timer_unstable_counter_workaround;
-
-#define arch_timer_reg_read_stable(reg) \
-({ \
- u64 _val; \
- if (needs_unstable_timer_counter_workaround()) \
- _val = timer_unstable_counter_workaround->read_##reg();\
- else \
- _val = read_sysreg(reg); \
- _val; \
+DECLARE_PER_CPU(const struct arch_timer_erratum_workaround *,
+ timer_unstable_counter_workaround);
+
+#define arch_timer_reg_read_stable(reg) \
+({ \
+ u64 _val; \
+ if (needs_unstable_timer_counter_workaround()) { \
+ const struct arch_timer_erratum_workaround *wa; \
+ preempt_disable(); \
+ wa = __this_cpu_read(timer_unstable_counter_workaround); \
+ if (wa && wa->read_##reg) \
+ _val = wa->read_##reg(); \
+ else \
+ _val = read_sysreg(reg); \
+ preempt_enable(); \
+ } else { \
+ _val = read_sysreg(reg); \
+ } \
+ _val; \
})
/*
#define ARM64_HAS_NO_FPSIMD 16
#define ARM64_WORKAROUND_REPEAT_TLBI 17
#define ARM64_WORKAROUND_QCOM_FALKOR_E1003 18
+#define ARM64_WORKAROUND_858921 19
-#define ARM64_NCAPS 19
+#define ARM64_NCAPS 20
#endif /* __ASM_CPUCAPS_H */
#define ARM_CPU_PART_FOUNDATION 0xD00
#define ARM_CPU_PART_CORTEX_A57 0xD07
#define ARM_CPU_PART_CORTEX_A53 0xD03
+#define ARM_CPU_PART_CORTEX_A73 0xD09
#define APM_CPU_PART_POTENZA 0x000
#define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
#define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
+#define MIDR_CORTEX_A73 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A73)
#define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
#define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
#define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1)
#ifndef _ASM_EFI_H
#define _ASM_EFI_H
+#include <asm/boot.h>
#include <asm/cpufeature.h>
#include <asm/io.h>
#include <asm/mmu_context.h>
* 2MiB so we know it won't cross a 2MiB boundary.
*/
#define EFI_FDT_ALIGN SZ_2M /* used by allocate_new_fdt_and_exit_boot() */
-#define MAX_FDT_OFFSET SZ_512M
+
+/* on arm64, the FDT may be located anywhere in system RAM */
+static inline unsigned long efi_get_max_fdt_addr(unsigned long dram_base)
+{
+ return ULONG_MAX;
+}
+
+/*
+ * On arm64, we have to ensure that the initrd ends up in the linear region,
+ * which is a 1 GB aligned region of size '1UL << (VA_BITS - 1)' that is
+ * guaranteed to cover the kernel Image.
+ *
+ * Since the EFI stub is part of the kernel Image, we can relax the
+ * usual requirements in Documentation/arm64/booting.txt, which still
+ * apply to other bootloaders, and are required for some kernel
+ * configurations.
+ */
+static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base,
+ unsigned long image_addr)
+{
+ return (image_addr & ~(SZ_1G - 1UL)) + (1UL << (VA_BITS - 1));
+}
#define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__)
#define __efi_call_early(f, ...) f(__VA_ARGS__)
#define ESR_ELx_SYS64_ISS_SYS_CTR_READ (ESR_ELx_SYS64_ISS_SYS_CTR | \
ESR_ELx_SYS64_ISS_DIR_READ)
+#define ESR_ELx_SYS64_ISS_SYS_CNTVCT (ESR_ELx_SYS64_ISS_SYS_VAL(3, 3, 2, 14, 0) | \
+ ESR_ELx_SYS64_ISS_DIR_READ)
#ifndef __ASSEMBLY__
#include <asm/types.h>
--- /dev/null
+#ifndef __ASM_EXTABLE_H
+#define __ASM_EXTABLE_H
+
+/*
+ * The exception table consists of pairs of relative offsets: the first
+ * is the relative offset to an instruction that is allowed to fault,
+ * and the second is the relative offset at which the program should
+ * continue. No registers are modified, so it is entirely up to the
+ * continuation code to figure out what to do.
+ *
+ * All the routines below use bits of fixup code that are out of line
+ * with the main instruction path. This means when everything is well,
+ * we don't even have to jump over them. Further, they do not intrude
+ * on our cache or tlb entries.
+ */
+
+struct exception_table_entry
+{
+ int insn, fixup;
+};
+
+#define ARCH_HAS_RELATIVE_EXTABLE
+
+extern int fixup_exception(struct pt_regs *regs);
+#endif
#include <linux/bitops.h>
#include <linux/kasan-checks.h>
#include <linux/string.h>
-#include <linux/thread_info.h>
#include <asm/cpufeature.h>
#include <asm/ptrace.h>
-#include <asm/errno.h>
#include <asm/memory.h>
#include <asm/compiler.h>
-
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
-/*
- * The exception table consists of pairs of relative offsets: the first
- * is the relative offset to an instruction that is allowed to fault,
- * and the second is the relative offset at which the program should
- * continue. No registers are modified, so it is entirely up to the
- * continuation code to figure out what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path. This means when everything is well,
- * we don't even have to jump over them. Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry
-{
- int insn, fixup;
-};
-
-#define ARCH_HAS_RELATIVE_EXTABLE
-
-extern int fixup_exception(struct pt_regs *regs);
+#include <asm/extable.h>
#define KERNEL_DS (-1UL)
#define get_ds() (KERNEL_DS)
})
extern unsigned long __must_check __arch_copy_from_user(void *to, const void __user *from, unsigned long n);
+#define raw_copy_from_user __arch_copy_from_user
extern unsigned long __must_check __arch_copy_to_user(void __user *to, const void *from, unsigned long n);
-extern unsigned long __must_check __copy_in_user(void __user *to, const void __user *from, unsigned long n);
+#define raw_copy_to_user __arch_copy_to_user
+extern unsigned long __must_check raw_copy_in_user(void __user *to, const void __user *from, unsigned long n);
extern unsigned long __must_check __clear_user(void __user *addr, unsigned long n);
-
-static inline unsigned long __must_check __copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- kasan_check_write(to, n);
- check_object_size(to, n, false);
- return __arch_copy_from_user(to, from, n);
-}
-
-static inline unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n)
-{
- kasan_check_read(from, n);
- check_object_size(from, n, true);
- return __arch_copy_to_user(to, from, n);
-}
-
-static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- unsigned long res = n;
- kasan_check_write(to, n);
- check_object_size(to, n, false);
-
- if (access_ok(VERIFY_READ, from, n)) {
- res = __arch_copy_from_user(to, from, n);
- }
- if (unlikely(res))
- memset(to + (n - res), 0, res);
- return res;
-}
-
-static inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n)
-{
- kasan_check_read(from, n);
- check_object_size(from, n, true);
-
- if (access_ok(VERIFY_WRITE, to, n)) {
- n = __arch_copy_to_user(to, from, n);
- }
- return n;
-}
-
-static inline unsigned long __must_check copy_in_user(void __user *to, const void __user *from, unsigned long n)
-{
- if (access_ok(VERIFY_READ, from, n) && access_ok(VERIFY_WRITE, to, n))
- n = __copy_in_user(to, from, n);
- return n;
-}
-
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
+#define INLINE_COPY_TO_USER
+#define INLINE_COPY_FROM_USER
static inline unsigned long __must_check clear_user(void __user *to, unsigned long n)
{
#include <linux/acpi.h>
#include <linux/bootmem.h>
#include <linux/cpumask.h>
+#include <linux/efi-bgrt.h>
#include <linux/init.h>
#include <linux/irq.h>
#include <linux/irqdomain.h>
early_init_dt_scan_chosen_stdout();
} else {
parse_spcr(earlycon_init_is_deferred);
+ if (IS_ENABLED(CONFIG_ACPI_BGRT))
+ acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt);
}
}
EXPORT_SYMBOL(__arch_copy_from_user);
EXPORT_SYMBOL(__arch_copy_to_user);
EXPORT_SYMBOL(__clear_user);
-EXPORT_SYMBOL(__copy_in_user);
+EXPORT_SYMBOL(raw_copy_in_user);
/* physical memory */
EXPORT_SYMBOL(memstart_addr);
.midr_range_min = min, \
.midr_range_max = max
+#define MIDR_ALL_VERSIONS(model) \
+ .def_scope = SCOPE_LOCAL_CPU, \
+ .matches = is_affected_midr_range, \
+ .midr_model = model, \
+ .midr_range_min = 0, \
+ .midr_range_max = (MIDR_VARIANT_MASK | MIDR_REVISION_MASK)
+
const struct arm64_cpu_capabilities arm64_errata[] = {
#if defined(CONFIG_ARM64_ERRATUM_826319) || \
defined(CONFIG_ARM64_ERRATUM_827319) || \
MIDR_CPU_VAR_REV(0, 0)),
},
#endif
+#ifdef CONFIG_ARM64_ERRATUM_858921
+ {
+ /* Cortex-A73 all versions */
+ .desc = "ARM erratum 858921",
+ .capability = ARM64_WORKAROUND_858921,
+ MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
+ },
+#endif
{
}
};
* Check if the current CPU has a given feature capability.
* Should be called from non-preemptible context.
*/
-bool this_cpu_has_cap(unsigned int cap)
+static bool __this_cpu_has_cap(const struct arm64_cpu_capabilities *cap_array,
+ unsigned int cap)
{
const struct arm64_cpu_capabilities *caps;
if (WARN_ON(preemptible()))
return false;
- for (caps = arm64_features; caps->desc; caps++)
+ for (caps = cap_array; caps->desc; caps++)
if (caps->capability == cap && caps->matches)
return caps->matches(caps, SCOPE_LOCAL_CPU);
return false;
}
+extern const struct arm64_cpu_capabilities arm64_errata[];
+
+bool this_cpu_has_cap(unsigned int cap)
+{
+ return (__this_cpu_has_cap(arm64_features, cap) ||
+ __this_cpu_has_cap(arm64_errata, cap));
+}
+
void __init setup_cpu_features(void)
{
u32 cwg;
regs->pc += 4;
}
+static void cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
+{
+ int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+
+ pt_regs_write_reg(regs, rt, arch_counter_get_cntvct());
+ regs->pc += 4;
+}
+
struct sys64_hook {
unsigned int esr_mask;
unsigned int esr_val;
.esr_val = ESR_ELx_SYS64_ISS_SYS_CTR_READ,
.handler = ctr_read_handler,
},
+ {
+ /* Trap read access to CNTVCT_EL0 */
+ .esr_mask = ESR_ELx_SYS64_ISS_SYS_OP_MASK,
+ .esr_val = ESR_ELx_SYS64_ISS_SYS_CNTVCT,
+ .handler = cntvct_read_handler,
+ },
{},
};
.endm
end .req x5
-ENTRY(__copy_in_user)
+ENTRY(raw_copy_in_user)
uaccess_enable_not_uao x3, x4
add end, x0, x2
#include "copy_template.S"
uaccess_disable_not_uao x3
mov x0, #0
ret
-ENDPROC(__copy_in_user)
+ENDPROC(raw_copy_in_user)
.section .fixup,"ax"
.align 2
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
-static const char *fault_name(unsigned int esr);
+struct fault_info {
+ int (*fn)(unsigned long addr, unsigned int esr,
+ struct pt_regs *regs);
+ int sig;
+ int code;
+ const char *name;
+};
+
+static const struct fault_info fault_info[];
+
+static inline const struct fault_info *esr_to_fault_info(unsigned int esr)
+{
+ return fault_info + (esr & 63);
+}
#ifdef CONFIG_KPROBES
static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
struct pt_regs *regs)
{
struct siginfo si;
+ const struct fault_info *inf;
if (unhandled_signal(tsk, sig) && show_unhandled_signals_ratelimited()) {
+ inf = esr_to_fault_info(esr);
pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x\n",
- tsk->comm, task_pid_nr(tsk), fault_name(esr), sig,
+ tsk->comm, task_pid_nr(tsk), inf->name, sig,
addr, esr);
show_pte(tsk->mm, addr);
show_regs(regs);
{
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->active_mm;
+ const struct fault_info *inf;
/*
* If we are in kernel mode at this point, we have no context to
* handle this fault with.
*/
- if (user_mode(regs))
- __do_user_fault(tsk, addr, esr, SIGSEGV, SEGV_MAPERR, regs);
- else
+ if (user_mode(regs)) {
+ inf = esr_to_fault_info(esr);
+ __do_user_fault(tsk, addr, esr, inf->sig, inf->code, regs);
+ } else
__do_kernel_fault(mm, addr, esr, regs);
}
return 1;
}
-static const struct fault_info {
- int (*fn)(unsigned long addr, unsigned int esr, struct pt_regs *regs);
- int sig;
- int code;
- const char *name;
-} fault_info[] = {
+static const struct fault_info fault_info[] = {
{ do_bad, SIGBUS, 0, "ttbr address size fault" },
{ do_bad, SIGBUS, 0, "level 1 address size fault" },
{ do_bad, SIGBUS, 0, "level 2 address size fault" },
{ do_bad, SIGBUS, 0, "unknown 63" },
};
-static const char *fault_name(unsigned int esr)
-{
- const struct fault_info *inf = fault_info + (esr & 63);
- return inf->name;
-}
-
/*
* Dispatch a data abort to the relevant handler.
*/
asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
struct pt_regs *regs)
{
- const struct fault_info *inf = fault_info + (esr & 63);
+ const struct fault_info *inf = esr_to_fault_info(esr);
struct siginfo info;
if (!inf->fn(addr, esr, regs))
hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
} else if (ps == PUD_SIZE) {
hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
- } else if (ps == (PAGE_SIZE * CONT_PTES)) {
- hugetlb_add_hstate(CONT_PTE_SHIFT);
- } else if (ps == (PMD_SIZE * CONT_PMDS)) {
- hugetlb_add_hstate((PMD_SHIFT + CONT_PMD_SHIFT) - PAGE_SHIFT);
} else {
hugetlb_bad_size();
pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
return 1;
}
__setup("hugepagesz=", setup_hugepagesz);
-
-#ifdef CONFIG_ARM64_64K_PAGES
-static __init int add_default_hugepagesz(void)
-{
- if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL)
- hugetlb_add_hstate(CONT_PTE_SHIFT);
- return 0;
-}
-arch_initcall(add_default_hugepagesz);
-#endif
+++ /dev/null
-config AVR32
- def_bool y
- # With EXPERT=n, we get lots of stuff automatically selected
- # that we usually don't need on AVR32.
- select EXPERT
- select HAVE_CLK
- select HAVE_EXIT_THREAD
- select HAVE_OPROFILE
- select HAVE_KPROBES
- select VIRT_TO_BUS
- select GENERIC_IRQ_PROBE
- select GENERIC_ATOMIC64
- select HARDIRQS_SW_RESEND
- select GENERIC_IRQ_SHOW
- select ARCH_HAVE_CUSTOM_GPIO_H
- select ARCH_WANT_IPC_PARSE_VERSION
- select ARCH_HAVE_NMI_SAFE_CMPXCHG
- select GENERIC_CLOCKEVENTS
- select HAVE_MOD_ARCH_SPECIFIC
- select MODULES_USE_ELF_RELA
- select HAVE_NMI
- help
- AVR32 is a high-performance 32-bit RISC microprocessor core,
- designed for cost-sensitive embedded applications, with particular
- emphasis on low power consumption and high code density.
-
- There is an AVR32 Linux project with a web page at
- http://avr32linux.org/.
-
-config STACKTRACE_SUPPORT
- def_bool y
-
-config LOCKDEP_SUPPORT
- def_bool y
-
-config TRACE_IRQFLAGS_SUPPORT
- def_bool y
-
-config RWSEM_GENERIC_SPINLOCK
- def_bool y
-
-config RWSEM_XCHGADD_ALGORITHM
- def_bool n
-
-config ARCH_HAS_ILOG2_U32
- def_bool n
-
-config ARCH_HAS_ILOG2_U64
- def_bool n
-
-config GENERIC_HWEIGHT
- def_bool y
-
-config GENERIC_CALIBRATE_DELAY
- def_bool y
-
-config GENERIC_BUG
- def_bool y
- depends on BUG
-
-source "init/Kconfig"
-
-source "kernel/Kconfig.freezer"
-
-menu "System Type and features"
-
-config SUBARCH_AVR32B
- bool
-config MMU
- bool
-config PERFORMANCE_COUNTERS
- bool
-
-config PLATFORM_AT32AP
- bool
- select SUBARCH_AVR32B
- select MMU
- select PERFORMANCE_COUNTERS
- select GPIOLIB
- select GENERIC_ALLOCATOR
- select HAVE_FB_ATMEL
-
-#
-# CPU types
-#
-
-# AP7000 derivatives
-config CPU_AT32AP700X
- bool
- select PLATFORM_AT32AP
-config CPU_AT32AP7000
- bool
- select CPU_AT32AP700X
-config CPU_AT32AP7001
- bool
- select CPU_AT32AP700X
-config CPU_AT32AP7002
- bool
- select CPU_AT32AP700X
-
-# AP700X boards
-config BOARD_ATNGW100_COMMON
- bool
- select CPU_AT32AP7000
-
-choice
- prompt "AVR32 board type"
- default BOARD_ATSTK1000
-
-config BOARD_ATSTK1000
- bool "ATSTK1000 evaluation board"
-
-config BOARD_ATNGW100_MKI
- bool "ATNGW100 Network Gateway"
- select BOARD_ATNGW100_COMMON
-
-config BOARD_ATNGW100_MKII
- bool "ATNGW100 mkII Network Gateway"
- select BOARD_ATNGW100_COMMON
-
-config BOARD_HAMMERHEAD
- bool "Hammerhead board"
- select CPU_AT32AP7000
- select USB_ARCH_HAS_HCD
- help
- The Hammerhead platform is built around an AVR32 32-bit microcontroller from Atmel.
- It offers versatile peripherals, such as ethernet, usb device, usb host etc.
-
- The board also incorporates a power supply and is a Power over Ethernet (PoE) Powered
- Device (PD).
-
- Additionally, a Cyclone III FPGA from Altera is integrated on the board. The FPGA is
- mapped into the 32-bit AVR memory bus. The FPGA offers two DDR2 SDRAM interfaces, which
- will cover even the most exceptional need of memory bandwidth. Together with the onboard
- video decoder the board is ready for video processing.
-
- For more information see: http://www.miromico.ch/index.php/hammerhead.html
-
-config BOARD_FAVR_32
- bool "Favr-32 LCD-board"
- select CPU_AT32AP7000
-
-config BOARD_MERISC
- bool "Merisc board"
- select CPU_AT32AP7000
- help
- Merisc is the family name for a range of AVR32-based boards.
-
- The boards are designed to be used in a man-machine
- interfacing environment, utilizing a touch-based graphical
- user interface. They host a vast range of I/O peripherals as
- well as a large SDRAM & Flash memory bank.
-
- For more information see: http://www.martinsson.se/merisc
-
-config BOARD_MIMC200
- bool "MIMC200 CPU board"
- select CPU_AT32AP7000
-endchoice
-
-source "arch/avr32/boards/atstk1000/Kconfig"
-source "arch/avr32/boards/atngw100/Kconfig"
-source "arch/avr32/boards/hammerhead/Kconfig"
-source "arch/avr32/boards/favr-32/Kconfig"
-source "arch/avr32/boards/merisc/Kconfig"
-
-choice
- prompt "Boot loader type"
- default LOADER_U_BOOT
-
-config LOADER_U_BOOT
- bool "U-Boot (or similar) bootloader"
-endchoice
-
-source "arch/avr32/mach-at32ap/Kconfig"
-
-config LOAD_ADDRESS
- hex
- default 0x10000000 if LOADER_U_BOOT=y && CPU_AT32AP700X=y
-
-config ENTRY_ADDRESS
- hex
- default 0x90000000 if LOADER_U_BOOT=y && CPU_AT32AP700X=y
-
-config PHYS_OFFSET
- hex
- default 0x10000000 if CPU_AT32AP700X=y
-
-source "kernel/Kconfig.preempt"
-
-config QUICKLIST
- def_bool y
-
-config ARCH_HAVE_MEMORY_PRESENT
- def_bool n
-
-config NEED_NODE_MEMMAP_SIZE
- def_bool n
-
-config ARCH_FLATMEM_ENABLE
- def_bool y
-
-config ARCH_DISCONTIGMEM_ENABLE
- def_bool n
-
-config ARCH_SPARSEMEM_ENABLE
- def_bool n
-
-config NODES_SHIFT
- int
- default "2"
- depends on NEED_MULTIPLE_NODES
-
-source "mm/Kconfig"
-
-config OWNERSHIP_TRACE
- bool "Ownership trace support"
- default y
- help
- Say Y to generate an Ownership Trace message on every context switch,
- enabling Nexus-compliant debuggers to keep track of the PID of the
- currently executing task.
-
-config NMI_DEBUGGING
- bool "NMI Debugging"
- default n
- help
- Say Y here and pass the nmi_debug command-line parameter to
- the kernel to turn on NMI debugging. Depending on the value
- of the nmi_debug option, various pieces of information will
- be dumped to the console when a Non-Maskable Interrupt
- happens.
-
-# FPU emulation goes here
-
-source "kernel/Kconfig.hz"
-
-config CMDLINE
- string "Default kernel command line"
- default ""
- help
- If you don't have a boot loader capable of passing a command line string
- to the kernel, you may specify one here. As a minimum, you should specify
- the memory size and the root device (e.g., mem=8M, root=/dev/nfs).
-
-endmenu
-
-menu "Power management options"
-
-source "kernel/power/Kconfig"
-
-config ARCH_SUSPEND_POSSIBLE
- def_bool y
-
-menu "CPU Frequency scaling"
-source "drivers/cpufreq/Kconfig"
-endmenu
-
-endmenu
-
-menu "Bus options"
-
-config PCI
- bool
-
-source "drivers/pci/Kconfig"
-
-source "drivers/pcmcia/Kconfig"
-
-endmenu
-
-menu "Executable file formats"
-source "fs/Kconfig.binfmt"
-endmenu
-
-source "net/Kconfig"
-
-source "drivers/Kconfig"
-
-source "fs/Kconfig"
-
-source "arch/avr32/Kconfig.debug"
-
-source "security/Kconfig"
-
-source "crypto/Kconfig"
-
-source "lib/Kconfig"
+++ /dev/null
-menu "Kernel hacking"
-
-config TRACE_IRQFLAGS_SUPPORT
- bool
- default y
-
-source "lib/Kconfig.debug"
-
-endmenu
+++ /dev/null
-#
-# This file is subject to the terms and conditions of the GNU General Public
-# License. See the file "COPYING" in the main directory of this archive
-# for more details.
-#
-# Copyright (C) 2004-2006 Atmel Corporation.
-
-# Default target when executing plain make
-.PHONY: all
-all: uImage vmlinux.elf
-
-KBUILD_DEFCONFIG := atstk1002_defconfig
-
-KBUILD_CFLAGS += -pipe -fno-builtin -mno-pic -D__linux__
-KBUILD_AFLAGS += -mrelax -mno-pic
-KBUILD_CFLAGS_MODULE += -mno-relax
-LDFLAGS_vmlinux += --relax
-
-cpuflags-$(CONFIG_PLATFORM_AT32AP) += -march=ap
-
-KBUILD_CFLAGS += $(cpuflags-y)
-KBUILD_AFLAGS += $(cpuflags-y)
-
-CHECKFLAGS += -D__avr32__ -D__BIG_ENDIAN
-
-machine-$(CONFIG_PLATFORM_AT32AP) := at32ap
-machdirs := $(patsubst %,arch/avr32/mach-%/, $(machine-y))
-
-KBUILD_CPPFLAGS += $(patsubst %,-I$(srctree)/%include,$(machdirs))
-
-head-$(CONFIG_LOADER_U_BOOT) += arch/avr32/boot/u-boot/head.o
-head-y += arch/avr32/kernel/head.o
-core-y += $(machdirs)
-core-$(CONFIG_BOARD_ATSTK1000) += arch/avr32/boards/atstk1000/
-core-$(CONFIG_BOARD_ATNGW100_COMMON) += arch/avr32/boards/atngw100/
-core-$(CONFIG_BOARD_HAMMERHEAD) += arch/avr32/boards/hammerhead/
-core-$(CONFIG_BOARD_FAVR_32) += arch/avr32/boards/favr-32/
-core-$(CONFIG_BOARD_MERISC) += arch/avr32/boards/merisc/
-core-$(CONFIG_BOARD_MIMC200) += arch/avr32/boards/mimc200/
-core-$(CONFIG_LOADER_U_BOOT) += arch/avr32/boot/u-boot/
-core-y += arch/avr32/kernel/
-core-y += arch/avr32/mm/
-drivers-$(CONFIG_OPROFILE) += arch/avr32/oprofile/
-libs-y += arch/avr32/lib/
-
-BOOT_TARGETS := vmlinux.elf vmlinux.bin uImage uImage.srec
-
-.PHONY: $(BOOT_TARGETS) install
-
-boot := arch/$(ARCH)/boot/images
-
- KBUILD_IMAGE := $(boot)/uImage
-vmlinux.elf: KBUILD_IMAGE := $(boot)/vmlinux.elf
-vmlinux.cso: KBUILD_IMAGE := $(boot)/vmlinux.cso
-uImage.srec: KBUILD_IMAGE := $(boot)/uImage.srec
-uImage: KBUILD_IMAGE := $(boot)/uImage
-
-quiet_cmd_listing = LST $@
- cmd_listing = avr32-linux-objdump $(OBJDUMPFLAGS) -lS $< > $@
-quiet_cmd_disasm = DIS $@
- cmd_disasm = avr32-linux-objdump $(OBJDUMPFLAGS) -d $< > $@
-
-vmlinux.elf vmlinux.bin uImage.srec uImage vmlinux.cso: vmlinux
- $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
-
-install: vmlinux
- $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(KBUILD_IMAGE) $@
-
-vmlinux.s: vmlinux
- $(call if_changed,disasm)
-
-vmlinux.lst: vmlinux
- $(call if_changed,listing)
-
-CLEAN_FILES += vmlinux.s vmlinux.lst
-
-archclean:
- $(Q)$(MAKE) $(clean)=$(boot)
-
-define archhelp
- @echo '* vmlinux.elf - ELF image with load address 0'
- @echo ' vmlinux.cso - PathFinder CSO image'
- @echo '* uImage - Create a bootable image for U-Boot'
-endef
+++ /dev/null
-# NGW100 customization
-
-if BOARD_ATNGW100_COMMON
-
-config BOARD_ATNGW100_MKII_LCD
- bool "Enable ATNGW100 mkII LCD interface"
- depends on BOARD_ATNGW100_MKII
- help
- This enables the LCD controller (LCDC) in the AT32AP7000. Since the
- LCDC is multiplexed with MACB1 (LAN) Ethernet port, only one can be
- enabled at a time.
-
- This choice enables the LCDC and disables the MACB1 interface marked
- LAN on the PCB.
-
-choice
- prompt "Select an NGW100 add-on board to support"
- default BOARD_ATNGW100_ADDON_NONE
-
-config BOARD_ATNGW100_ADDON_NONE
- bool "None"
-
-config BOARD_ATNGW100_EVKLCD10X
- bool "EVKLCD10X addon board"
- depends on BOARD_ATNGW100_MKI || BOARD_ATNGW100_MKII_LCD
- help
- This enables support for the EVKLCD100 (QVGA) or EVKLCD101 (VGA)
- addon board for the NGW100 and NGW100 mkII. By enabling this the LCD
- controller and AC97 controller is added as platform devices.
-
-config BOARD_ATNGW100_MRMT
- bool "Mediama RMT1/2 add-on board"
- help
- This enables support for the Mediama RMT1 or RMT2 board.
- RMT provides LCD support, AC97 codec and other
- optional peripherals to the Atmel NGW100.
-
- This choice disables the detect pin and the write-protect pin for the
- MCI platform device, since it conflicts with the LCD platform device.
- The MCI pins can be reenabled by editing the "add device function" but
- this may break the setup for other displays that use these pins.
-
-endchoice
-
-choice
- prompt "LCD panel resolution on EVKLCD10X"
- depends on BOARD_ATNGW100_EVKLCD10X
- default BOARD_ATNGW100_EVKLCD10X_VGA
-
-config BOARD_ATNGW100_EVKLCD10X_QVGA
- bool "QVGA (320x240)"
-
-config BOARD_ATNGW100_EVKLCD10X_VGA
- bool "VGA (640x480)"
-
-config BOARD_ATNGW100_EVKLCD10X_POW_QVGA
- bool "Powertip QVGA (320x240)"
-
-endchoice
-
-if BOARD_ATNGW100_MRMT
-source "arch/avr32/boards/atngw100/Kconfig_mrmt"
-endif
-
-endif # BOARD_ATNGW100_COMMON
+++ /dev/null
-# RMT for NGW100 customization
-
-choice
- prompt "RMT Version"
- help
- Select the RMTx board version.
-
-config BOARD_MRMT_REV1
- bool "RMT1"
-config BOARD_MRMT_REV2
- bool "RMT2"
-
-endchoice
-
-config BOARD_MRMT_AC97
- bool "Enable AC97 CODEC"
- help
- Enable the UCB1400 AC97 CODEC driver.
-
-choice
- prompt "Touchscreen Driver"
- default BOARD_MRMT_ADS7846_TS
-
-config BOARD_MRMT_UCB1400_TS
- bool "Use UCB1400 Touchscreen"
-
-config BOARD_MRMT_ADS7846_TS
- bool "Use ADS7846 Touchscreen"
-
-endchoice
-
-choice
- prompt "RMTx LCD Selection"
- default BOARD_MRMT_LCD_DISABLE
-
-config BOARD_MRMT_LCD_DISABLE
- bool "LCD Disabled"
-
-config BOARD_MRMT_LCD_LQ043T3DX0X
- bool "Sharp LQ043T3DX0x or compatible"
- help
- If using RMT2, be sure to load the resistor pack selectors accordingly
-
-if BOARD_MRMT_REV2
-config BOARD_MRMT_LCD_KWH043GM08
- bool "Formike KWH043GM08 or compatible"
- help
- Be sure to load the RMT2 resistor pack selectors accordingly
-endif
-
-endchoice
-
-if !BOARD_MRMT_LCD_DISABLE
-config BOARD_MRMT_BL_PWM
- bool "Use PWM control for LCD Backlight"
- help
- Use PWM driver for controlling LCD Backlight.
- Otherwise, LCD Backlight is always on.
-endif
-
-config BOARD_MRMT_RTC_I2C
- bool "Use External RTC on I2C Bus"
- help
- RMT1 has an optional RTC device on the I2C bus.
- It is a SII S35390A. Be sure to select the
- matching RTC driver.
-
-choice
- prompt "Wireless Module on ttyS2"
- default BOARD_MRMT_WIRELESS_ZB
-
-config BOARD_MRMT_WIRELESS_ZB
- bool "Use ZigBee/802.15.4 Module"
-
-config BOARD_MRMT_WIRELESS_BT
- bool "Use Bluetooth (HCI) Module"
-
-config BOARD_MRMT_WIRELESS_NONE
- bool "Not Installed"
-endchoice
+++ /dev/null
-obj-y += setup.o flash.o
-obj-$(CONFIG_BOARD_ATNGW100_EVKLCD10X) += evklcd10x.o
-obj-$(CONFIG_BOARD_ATNGW100_MRMT) += mrmt.o
+++ /dev/null
-/*
- * Board-specific setup code for the ATEVKLCD10X addon board to the ATNGW100
- * Network Gateway
- *
- * Copyright (C) 2008 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- */
-
-#include <linux/init.h>
-#include <linux/linkage.h>
-#include <linux/gpio.h>
-#include <linux/fb.h>
-#include <linux/platform_device.h>
-
-#include <video/atmel_lcdc.h>
-
-#include <asm/setup.h>
-
-#include <mach/at32ap700x.h>
-#include <mach/portmux.h>
-#include <mach/board.h>
-
-#include <sound/atmel-ac97c.h>
-
-static struct ac97c_platform_data __initdata ac97c0_data = {
- .reset_pin = GPIO_PIN_PB(19),
-};
-
-#ifdef CONFIG_BOARD_ATNGW100_EVKLCD10X_VGA
-static struct fb_videomode __initdata tcg057vglad_modes[] = {
- {
- .name = "640x480 @ 50",
- .refresh = 50,
- .xres = 640, .yres = 480,
- .pixclock = KHZ2PICOS(25180),
-
- .left_margin = 64, .right_margin = 96,
- .upper_margin = 34, .lower_margin = 11,
- .hsync_len = 64, .vsync_len = 15,
-
- .sync = 0,
- .vmode = FB_VMODE_NONINTERLACED,
- },
-};
-
-static struct fb_monspecs __initdata atevklcd10x_default_monspecs = {
- .manufacturer = "KYO",
- .monitor = "TCG057VGLAD",
- .modedb = tcg057vglad_modes,
- .modedb_len = ARRAY_SIZE(tcg057vglad_modes),
- .hfmin = 19948,
- .hfmax = 31478,
- .vfmin = 50,
- .vfmax = 67,
- .dclkmax = 28330000,
-};
-
-static struct atmel_lcdfb_pdata __initdata atevklcd10x_lcdc_data = {
- .default_bpp = 16,
- .default_dmacon = ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
- .default_lcdcon2 = (ATMEL_LCDC_DISTYPE_TFT
- | ATMEL_LCDC_CLKMOD_ALWAYSACTIVE
- | ATMEL_LCDC_MEMOR_BIG),
- .default_monspecs = &atevklcd10x_default_monspecs,
- .guard_time = 2,
-};
-#elif CONFIG_BOARD_ATNGW100_EVKLCD10X_QVGA
-static struct fb_videomode __initdata tcg057qvlad_modes[] = {
- {
- .name = "320x240 @ 50",
- .refresh = 50,
- .xres = 320, .yres = 240,
- .pixclock = KHZ2PICOS(6300),
-
- .left_margin = 34, .right_margin = 46,
- .upper_margin = 7, .lower_margin = 15,
- .hsync_len = 64, .vsync_len = 12,
-
- .sync = 0,
- .vmode = FB_VMODE_NONINTERLACED,
- },
-};
-
-static struct fb_monspecs __initdata atevklcd10x_default_monspecs = {
- .manufacturer = "KYO",
- .monitor = "TCG057QVLAD",
- .modedb = tcg057qvlad_modes,
- .modedb_len = ARRAY_SIZE(tcg057qvlad_modes),
- .hfmin = 19948,
- .hfmax = 31478,
- .vfmin = 50,
- .vfmax = 67,
- .dclkmax = 7000000,
-};
-
-static struct atmel_lcdfb_pdata __initdata atevklcd10x_lcdc_data = {
- .default_bpp = 16,
- .default_dmacon = ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
- .default_lcdcon2 = (ATMEL_LCDC_DISTYPE_TFT
- | ATMEL_LCDC_CLKMOD_ALWAYSACTIVE
- | ATMEL_LCDC_MEMOR_BIG),
- .default_monspecs = &atevklcd10x_default_monspecs,
- .guard_time = 2,
-};
-#elif CONFIG_BOARD_ATNGW100_EVKLCD10X_POW_QVGA
-static struct fb_videomode __initdata ph320240t_modes[] = {
- {
- .name = "320x240 @ 60",
- .refresh = 60,
- .xres = 320, .yres = 240,
- .pixclock = KHZ2PICOS(6300),
-
- .left_margin = 38, .right_margin = 20,
- .upper_margin = 15, .lower_margin = 5,
- .hsync_len = 30, .vsync_len = 3,
-
- .sync = 0,
- .vmode = FB_VMODE_NONINTERLACED,
- },
-};
-
-static struct fb_monspecs __initdata atevklcd10x_default_monspecs = {
- .manufacturer = "POW",
- .monitor = "PH320240T",
- .modedb = ph320240t_modes,
- .modedb_len = ARRAY_SIZE(ph320240t_modes),
- .hfmin = 14400,
- .hfmax = 21600,
- .vfmin = 50,
- .vfmax = 90,
- .dclkmax = 6400000,
-};
-
-static struct atmel_lcdfb_pdata __initdata atevklcd10x_lcdc_data = {
- .default_bpp = 16,
- .default_dmacon = ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
- .default_lcdcon2 = (ATMEL_LCDC_DISTYPE_TFT
- | ATMEL_LCDC_CLKMOD_ALWAYSACTIVE
- | ATMEL_LCDC_MEMOR_BIG),
- .default_monspecs = &atevklcd10x_default_monspecs,
- .guard_time = 2,
-};
-#endif
-
-static void atevklcd10x_lcdc_power_control(struct atmel_lcdfb_pdata *pdata, int on)
-{
- gpio_set_value(GPIO_PIN_PB(15), on);
-}
-
-static int __init atevklcd10x_init(void)
-{
- /* PB15 is connected to the enable line on the boost regulator
- * controlling the backlight for the LCD panel.
- */
- at32_select_gpio(GPIO_PIN_PB(15), AT32_GPIOF_OUTPUT);
- gpio_request(GPIO_PIN_PB(15), "backlight");
- gpio_direction_output(GPIO_PIN_PB(15), 0);
-
- atevklcd10x_lcdc_data.atmel_lcdfb_power_control =
- atevklcd10x_lcdc_power_control;
-
- at32_add_device_lcdc(0, &atevklcd10x_lcdc_data,
- fbmem_start, fbmem_size,
-#ifdef CONFIG_BOARD_ATNGW100_MKII
- ATMEL_LCDC_PRI_18BIT | ATMEL_LCDC_PC_DVAL
-#else
- ATMEL_LCDC_ALT_18BIT | ATMEL_LCDC_PE_DVAL
-#endif
- );
-
- at32_add_device_ac97c(0, &ac97c0_data, AC97C_BOTH);
-
- return 0;
-}
-postcore_initcall(atevklcd10x_init);
+++ /dev/null
-/*
- * ATNGW100 board-specific flash initialization
- *
- * Copyright (C) 2005-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/mtd/mtd.h>
-#include <linux/mtd/partitions.h>
-#include <linux/mtd/physmap.h>
-
-#include <mach/smc.h>
-
-static struct smc_timing flash_timing __initdata = {
- .ncs_read_setup = 0,
- .nrd_setup = 40,
- .ncs_write_setup = 0,
- .nwe_setup = 10,
-
- .ncs_read_pulse = 80,
- .nrd_pulse = 40,
- .ncs_write_pulse = 65,
- .nwe_pulse = 55,
-
- .read_cycle = 120,
- .write_cycle = 120,
-};
-
-static struct smc_config flash_config __initdata = {
- .bus_width = 2,
- .nrd_controlled = 1,
- .nwe_controlled = 1,
- .byte_write = 1,
-};
-
-static struct mtd_partition flash_parts[] = {
- {
- .name = "u-boot",
- .offset = 0x00000000,
- .size = 0x00020000, /* 128 KiB */
- .mask_flags = MTD_WRITEABLE,
- },
- {
- .name = "root",
- .offset = 0x00020000,
- .size = 0x007d0000,
- },
- {
- .name = "env",
- .offset = 0x007f0000,
- .size = 0x00010000,
- .mask_flags = MTD_WRITEABLE,
- },
-};
-
-static struct physmap_flash_data flash_data = {
- .width = 2,
- .nr_parts = ARRAY_SIZE(flash_parts),
- .parts = flash_parts,
-};
-
-static struct resource flash_resource = {
- .start = 0x00000000,
- .end = 0x007fffff,
- .flags = IORESOURCE_MEM,
-};
-
-static struct platform_device flash_device = {
- .name = "physmap-flash",
- .id = 0,
- .resource = &flash_resource,
- .num_resources = 1,
- .dev = {
- .platform_data = &flash_data,
- },
-};
-
-/* This needs to be called after the SMC has been initialized */
-static int __init atngw100_flash_init(void)
-{
- int ret;
-
- smc_set_timing(&flash_config, &flash_timing);
- ret = smc_set_configuration(0, &flash_config);
- if (ret < 0) {
- printk(KERN_ERR "atngw100: failed to set NOR flash timing\n");
- return ret;
- }
-
- platform_device_register(&flash_device);
-
- return 0;
-}
-device_initcall(atngw100_flash_init);
+++ /dev/null
-/*
- * Board-specific setup code for Remote Media Terminal 1 (RMT1)
- * add-on board for the ATNGW100 Network Gateway
- *
- * Copyright (C) 2008 Mediama Technologies
- * Based on ATNGW100 Network Gateway (Copyright (C) Atmel)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/gpio.h>
-#include <linux/init.h>
-#include <linux/irq.h>
-#include <linux/linkage.h>
-#include <linux/platform_device.h>
-#include <linux/types.h>
-#include <linux/fb.h>
-#include <linux/leds.h>
-#include <linux/pwm.h>
-#include <linux/leds_pwm.h>
-#include <linux/input.h>
-#include <linux/gpio_keys.h>
-#include <linux/spi/spi.h>
-#include <linux/spi/ads7846.h>
-
-#include <video/atmel_lcdc.h>
-#include <sound/atmel-ac97c.h>
-
-#include <asm/delay.h>
-#include <asm/io.h>
-#include <asm/setup.h>
-
-#include <mach/at32ap700x.h>
-#include <mach/board.h>
-#include <mach/init.h>
-#include <mach/portmux.h>
-
-/* Define board-specifoic GPIO assignments */
-#define PIN_LCD_BL GPIO_PIN_PA(28)
-#define PWM_CH_BL 0 /* Must match with GPIO pin definition */
-#define PIN_LCD_DISP GPIO_PIN_PA(31)
-#define PIN_AC97_RST_N GPIO_PIN_PA(30)
-#define PB_EXTINT_BASE 25
-#define TS_IRQ 0
-#define PIN_TS_EXTINT GPIO_PIN_PB(PB_EXTINT_BASE+TS_IRQ)
-#define PIN_PB_LEFT GPIO_PIN_PB(11)
-#define PIN_PB_RIGHT GPIO_PIN_PB(12)
-#define PIN_PWR_SW_N GPIO_PIN_PB(14)
-#define PIN_PWR_ON GPIO_PIN_PB(13)
-#define PIN_ZB_RST_N GPIO_PIN_PA(21)
-#define PIN_BT_RST GPIO_PIN_PA(22)
-#define PIN_LED_SYS GPIO_PIN_PA(16)
-#define PIN_LED_A GPIO_PIN_PA(19)
-#define PIN_LED_B GPIO_PIN_PE(19)
-
-#ifdef CONFIG_BOARD_MRMT_LCD_LQ043T3DX0X
-/* Sharp LQ043T3DX0x (or compatible) panel */
-static struct fb_videomode __initdata lcd_fb_modes[] = {
- {
- .name = "480x272 @ 59.94Hz",
- .refresh = 59.94,
- .xres = 480, .yres = 272,
- .pixclock = KHZ2PICOS(9000),
-
- .left_margin = 2, .right_margin = 2,
- .upper_margin = 3, .lower_margin = 9,
- .hsync_len = 41, .vsync_len = 1,
-
- .sync = 0,
- .vmode = FB_VMODE_NONINTERLACED,
- },
-};
-
-static struct fb_monspecs __initdata lcd_fb_default_monspecs = {
- .manufacturer = "SHA",
- .monitor = "LQ043T3DX02",
- .modedb = lcd_fb_modes,
- .modedb_len = ARRAY_SIZE(lcd_fb_modes),
- .hfmin = 14915,
- .hfmax = 17638,
- .vfmin = 53,
- .vfmax = 61,
- .dclkmax = 9260000,
-};
-
-static struct atmel_lcdfb_pdata __initdata rmt_lcdc_data = {
- .default_bpp = 24,
- .default_dmacon = ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
- .default_lcdcon2 = (ATMEL_LCDC_DISTYPE_TFT
- | ATMEL_LCDC_CLKMOD_ALWAYSACTIVE
- | ATMEL_LCDC_INVCLK_NORMAL
- | ATMEL_LCDC_MEMOR_BIG),
- .lcd_wiring_mode = ATMEL_LCDC_WIRING_RGB,
- .default_monspecs = &lcd_fb_default_monspecs,
- .guard_time = 2,
-};
-#endif
-
-#ifdef CONFIG_BOARD_MRMT_LCD_KWH043GM08
-/* Sharp KWH043GM08-Fxx (or compatible) panel */
-static struct fb_videomode __initdata lcd_fb_modes[] = {
- {
- .name = "480x272 @ 59.94Hz",
- .refresh = 59.94,
- .xres = 480, .yres = 272,
- .pixclock = KHZ2PICOS(9000),
-
- .left_margin = 2, .right_margin = 2,
- .upper_margin = 3, .lower_margin = 9,
- .hsync_len = 41, .vsync_len = 1,
-
- .sync = 0,
- .vmode = FB_VMODE_NONINTERLACED,
- },
-};
-
-static struct fb_monspecs __initdata lcd_fb_default_monspecs = {
- .manufacturer = "FOR",
- .monitor = "KWH043GM08",
- .modedb = lcd_fb_modes,
- .modedb_len = ARRAY_SIZE(lcd_fb_modes),
- .hfmin = 14915,
- .hfmax = 17638,
- .vfmin = 53,
- .vfmax = 61,
- .dclkmax = 9260000,
-};
-
-static struct atmel_lcdfb_pdata __initdata rmt_lcdc_data = {
- .default_bpp = 24,
- .default_dmacon = ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
- .default_lcdcon2 = (ATMEL_LCDC_DISTYPE_TFT
- | ATMEL_LCDC_CLKMOD_ALWAYSACTIVE
- | ATMEL_LCDC_INVCLK_INVERTED
- | ATMEL_LCDC_MEMOR_BIG),
- .lcd_wiring_mode = ATMEL_LCDC_WIRING_RGB,
- .default_monspecs = &lcd_fb_default_monspecs,
- .guard_time = 2,
-};
-#endif
-
-#ifdef CONFIG_BOARD_MRMT_AC97
-static struct ac97c_platform_data __initdata ac97c0_data = {
- .reset_pin = PIN_AC97_RST_N,
-};
-#endif
-
-#ifdef CONFIG_BOARD_MRMT_UCB1400_TS
-/* NOTE: IRQ assignment relies on kernel module parameter */
-static struct platform_device rmt_ts_device = {
- .name = "ucb1400_ts",
- .id = -1,
-};
-#endif
-
-#ifdef CONFIG_BOARD_MRMT_BL_PWM
-/* PWM LEDs: LCD Backlight, etc */
-static struct pwm_lookup pwm_lookup[] = {
- PWM_LOOKUP("at91sam9rl-pwm", PWM_CH_BL, "leds_pwm", "ds1",
- 5000, PWM_POLARITY_INVERSED),
-};
-
-static struct led_pwm pwm_leds[] = {
- {
- .name = "backlight",
- .max_brightness = 255,
- },
-};
-
-static struct led_pwm_platform_data pwm_data = {
- .num_leds = ARRAY_SIZE(pwm_leds),
- .leds = pwm_leds,
-};
-
-static struct platform_device leds_pwm = {
- .name = "leds_pwm",
- .id = -1,
- .dev = {
- .platform_data = &pwm_data,
- },
-};
-#endif
-
-#ifdef CONFIG_BOARD_MRMT_ADS7846_TS
-static int ads7846_pendown_state(void)
-{
- return !gpio_get_value( PIN_TS_EXTINT ); /* PENIRQ.*/
-}
-
-static struct ads7846_platform_data ads_info = {
- .model = 7846,
- .keep_vref_on = 0, /* Use external VREF pin */
- .vref_delay_usecs = 0,
- .vref_mv = 3300, /* VREF = 3.3V */
- .settle_delay_usecs = 800,
- .penirq_recheck_delay_usecs = 800,
- .x_plate_ohms = 750,
- .y_plate_ohms = 300,
- .pressure_max = 4096,
- .debounce_max = 1,
- .debounce_rep = 0,
- .debounce_tol = (~0),
- .get_pendown_state = ads7846_pendown_state,
- .filter = NULL,
- .filter_init = NULL,
-};
-
-static struct spi_board_info spi01_board_info[] __initdata = {
- {
- .modalias = "ads7846",
- .max_speed_hz = 31250*26,
- .bus_num = 0,
- .chip_select = 1,
- .platform_data = &ads_info,
- .irq = AT32_EXTINT(TS_IRQ),
- },
-};
-#endif
-
-/* GPIO Keys: left, right, power, etc */
-static const struct gpio_keys_button rmt_gpio_keys_buttons[] = {
- [0] = {
- .type = EV_KEY,
- .code = KEY_POWER,
- .gpio = PIN_PWR_SW_N,
- .active_low = 1,
- .desc = "power button",
- },
- [1] = {
- .type = EV_KEY,
- .code = KEY_LEFT,
- .gpio = PIN_PB_LEFT,
- .active_low = 1,
- .desc = "left button",
- },
- [2] = {
- .type = EV_KEY,
- .code = KEY_RIGHT,
- .gpio = PIN_PB_RIGHT,
- .active_low = 1,
- .desc = "right button",
- },
-};
-
-static const struct gpio_keys_platform_data rmt_gpio_keys_data = {
- .nbuttons = ARRAY_SIZE(rmt_gpio_keys_buttons),
- .buttons = (void *) rmt_gpio_keys_buttons,
-};
-
-static struct platform_device rmt_gpio_keys = {
- .name = "gpio-keys",
- .id = -1,
- .dev = {
- .platform_data = (void *) &rmt_gpio_keys_data,
- }
-};
-
-#ifdef CONFIG_BOARD_MRMT_RTC_I2C
-static struct i2c_board_info __initdata mrmt1_i2c_rtc = {
- I2C_BOARD_INFO("s35390a", 0x30),
- .irq = 0,
-};
-#endif
-
-static void mrmt_power_off(void)
-{
- /* PWR_ON=0 will force power off */
- gpio_set_value( PIN_PWR_ON, 0 );
-}
-
-static int __init mrmt1_init(void)
-{
- gpio_set_value( PIN_PWR_ON, 1 ); /* Ensure PWR_ON is enabled */
-
- pm_power_off = mrmt_power_off;
-
- /* Setup USARTS (other than console) */
- at32_map_usart(2, 1, 0); /* USART 2: /dev/ttyS1, RMT1:DB9M */
- at32_map_usart(3, 2, ATMEL_USART_RTS | ATMEL_USART_CTS);
- /* USART 3: /dev/ttyS2, RMT1:Wireless, w/ RTS/CTS */
- at32_add_device_usart(1);
- at32_add_device_usart(2);
-
- /* Select GPIO Key pins */
- at32_select_gpio( PIN_PWR_SW_N, AT32_GPIOF_DEGLITCH);
- at32_select_gpio( PIN_PB_LEFT, AT32_GPIOF_DEGLITCH);
- at32_select_gpio( PIN_PB_RIGHT, AT32_GPIOF_DEGLITCH);
- platform_device_register(&rmt_gpio_keys);
-
-#ifdef CONFIG_BOARD_MRMT_RTC_I2C
- i2c_register_board_info(0, &mrmt1_i2c_rtc, 1);
-#endif
-
-#ifndef CONFIG_BOARD_MRMT_LCD_DISABLE
- /* User "alternate" LCDC inferface on Port E & D */
- /* NB: exclude LCDC_CC pin, as NGW100 reserves it for other use */
- at32_add_device_lcdc(0, &rmt_lcdc_data,
- fbmem_start, fbmem_size,
- (ATMEL_LCDC_ALT_24BIT | ATMEL_LCDC_PE_DVAL ) );
-#endif
-
-#ifdef CONFIG_BOARD_MRMT_AC97
- at32_add_device_ac97c(0, &ac97c0_data, AC97C_BOTH);
-#endif
-
-#ifdef CONFIG_BOARD_MRMT_ADS7846_TS
- /* Select the Touchscreen interrupt pin mode */
- at32_select_periph( GPIO_PIOB_BASE, 1 << (PB_EXTINT_BASE+TS_IRQ),
- GPIO_PERIPH_A, AT32_GPIOF_DEGLITCH);
- irq_set_irq_type(AT32_EXTINT(TS_IRQ), IRQ_TYPE_EDGE_FALLING);
- at32_spi_setup_slaves(0,spi01_board_info,ARRAY_SIZE(spi01_board_info));
- spi_register_board_info(spi01_board_info,ARRAY_SIZE(spi01_board_info));
-#endif
-
-#ifdef CONFIG_BOARD_MRMT_UCB1400_TS
- /* Select the Touchscreen interrupt pin mode */
- at32_select_periph( GPIO_PIOB_BASE, 1 << (PB_EXTINT_BASE+TS_IRQ),
- GPIO_PERIPH_A, AT32_GPIOF_DEGLITCH);
- platform_device_register(&rmt_ts_device);
-#endif
-
- at32_select_gpio( PIN_LCD_DISP, AT32_GPIOF_OUTPUT );
- gpio_request( PIN_LCD_DISP, "LCD_DISP" );
- gpio_direction_output( PIN_LCD_DISP, 0 ); /* LCD DISP */
-#ifdef CONFIG_BOARD_MRMT_LCD_DISABLE
- /* Keep Backlight and DISP off */
- at32_select_gpio( PIN_LCD_BL, AT32_GPIOF_OUTPUT );
- gpio_request( PIN_LCD_BL, "LCD_BL" );
- gpio_direction_output( PIN_LCD_BL, 0 ); /* Backlight */
-#else
- gpio_set_value( PIN_LCD_DISP, 1 ); /* DISP asserted first */
-#ifdef CONFIG_BOARD_MRMT_BL_PWM
- /* Use PWM for Backlight controls */
- at32_add_device_pwm(1 << PWM_CH_BL);
- pwm_add_table(pwm_lookup, ARRAY_SIZE(pwm_lookup));
- platform_device_register(&leds_pwm);
-#else
- /* Backlight always on */
- udelay( 1 );
- at32_select_gpio( PIN_LCD_BL, AT32_GPIOF_OUTPUT );
- gpio_request( PIN_LCD_BL, "LCD_BL" );
- gpio_direction_output( PIN_LCD_BL, 1 );
-#endif
-#endif
-
- /* Make sure BT and Zigbee modules in reset */
- at32_select_gpio( PIN_BT_RST, AT32_GPIOF_OUTPUT );
- gpio_request( PIN_BT_RST, "BT_RST" );
- gpio_direction_output( PIN_BT_RST, 1 );
- /* BT Module in Reset */
-
- at32_select_gpio( PIN_ZB_RST_N, AT32_GPIOF_OUTPUT );
- gpio_request( PIN_ZB_RST_N, "ZB_RST_N" );
- gpio_direction_output( PIN_ZB_RST_N, 0 );
- /* XBee Module in Reset */
-
-#ifdef CONFIG_BOARD_MRMT_WIRELESS_ZB
- udelay( 1000 );
- /* Unreset the XBee Module */
- gpio_set_value( PIN_ZB_RST_N, 1 );
-#endif
-#ifdef CONFIG_BOARD_MRMT_WIRELESS_BT
- udelay( 1000 );
- /* Unreset the BT Module */
- gpio_set_value( PIN_BT_RST, 0 );
-#endif
-
- return 0;
-}
-arch_initcall(mrmt1_init);
-
-static int __init mrmt1_early_init(void)
-{
- /* To maintain power-on signal in case boot loader did not already */
- at32_select_gpio( PIN_PWR_ON, AT32_GPIOF_OUTPUT );
- gpio_request( PIN_PWR_ON, "PIN_PWR_ON" );
- gpio_direction_output( PIN_PWR_ON, 1 );
-
- return 0;
-}
-core_initcall(mrmt1_early_init);
+++ /dev/null
-/*
- * Board-specific setup code for the ATNGW100 Network Gateway
- *
- * Copyright (C) 2005-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/clk.h>
-#include <linux/etherdevice.h>
-#include <linux/gpio.h>
-#include <linux/irq.h>
-#include <linux/i2c.h>
-#include <linux/i2c-gpio.h>
-#include <linux/init.h>
-#include <linux/linkage.h>
-#include <linux/platform_device.h>
-#include <linux/types.h>
-#include <linux/leds.h>
-#include <linux/spi/spi.h>
-#include <linux/atmel-mci.h>
-#include <linux/usb/atmel_usba_udc.h>
-
-#include <asm/io.h>
-#include <asm/setup.h>
-
-#include <mach/at32ap700x.h>
-#include <mach/board.h>
-#include <mach/init.h>
-#include <mach/portmux.h>
-
-/* Oscillator frequencies. These are board-specific */
-unsigned long at32_board_osc_rates[3] = {
- [0] = 32768, /* 32.768 kHz on RTC osc */
- [1] = 20000000, /* 20 MHz on osc0 */
- [2] = 12000000, /* 12 MHz on osc1 */
-};
-
-/*
- * The ATNGW100 mkII is very similar to the ATNGW100. Both have the AT32AP7000
- * chip on board; the difference is that the ATNGW100 mkII has 128 MB 32-bit
- * SDRAM (the ATNGW100 has 32 MB 16-bit SDRAM) and 256 MB 16-bit NAND flash
- * (the ATNGW100 has none.)
- *
- * The RAM difference is handled by the boot loader, so the only difference we
- * end up handling here is the NAND flash, EBI pin reservation and if LCDC or
- * MACB1 should be enabled.
- */
-#ifdef CONFIG_BOARD_ATNGW100_MKII
-#include <linux/mtd/partitions.h>
-#include <mach/smc.h>
-
-static struct smc_timing nand_timing __initdata = {
- .ncs_read_setup = 0,
- .nrd_setup = 10,
- .ncs_write_setup = 0,
- .nwe_setup = 10,
-
- .ncs_read_pulse = 30,
- .nrd_pulse = 15,
- .ncs_write_pulse = 30,
- .nwe_pulse = 15,
-
- .read_cycle = 30,
- .write_cycle = 30,
-
- .ncs_read_recover = 0,
- .nrd_recover = 15,
- .ncs_write_recover = 0,
- /* WE# high -> RE# low min 60 ns */
- .nwe_recover = 50,
-};
-
-static struct smc_config nand_config __initdata = {
- .bus_width = 2,
- .nrd_controlled = 1,
- .nwe_controlled = 1,
- .nwait_mode = 0,
- .byte_write = 0,
- .tdf_cycles = 2,
- .tdf_mode = 0,
-};
-
-static struct mtd_partition nand_partitions[] = {
- {
- .name = "main",
- .offset = 0x00000000,
- .size = MTDPART_SIZ_FULL,
- },
-};
-
-
-static struct atmel_nand_data atngw100mkii_nand_data __initdata = {
- .cle = 21,
- .ale = 22,
- .rdy_pin = GPIO_PIN_PB(28),
- .enable_pin = GPIO_PIN_PE(23),
- .bus_width_16 = true,
- .ecc_mode = NAND_ECC_SOFT,
- .parts = nand_partitions,
- .num_parts = ARRAY_SIZE(nand_partitions),
-};
-#endif
-
-/* Initialized by bootloader-specific startup code. */
-struct tag *bootloader_tags __initdata;
-
-struct eth_addr {
- u8 addr[6];
-};
-static struct eth_addr __initdata hw_addr[2];
-static struct macb_platform_data __initdata eth_data[2];
-
-static struct spi_board_info spi0_board_info[] __initdata = {
- {
- .modalias = "mtd_dataflash",
- .max_speed_hz = 8000000,
- .chip_select = 0,
- },
-};
-
-static struct mci_platform_data __initdata mci0_data = {
- .slot[0] = {
- .bus_width = 4,
-#if defined(CONFIG_BOARD_ATNGW100_MKII)
- .detect_pin = GPIO_PIN_PC(25),
- .wp_pin = GPIO_PIN_PE(22),
-#else
- .detect_pin = GPIO_PIN_PC(25),
- .wp_pin = GPIO_PIN_PE(0),
-#endif
- },
-};
-
-static struct usba_platform_data atngw100_usba_data __initdata = {
-#if defined(CONFIG_BOARD_ATNGW100_MKII)
- .vbus_pin = GPIO_PIN_PE(26),
-#else
- .vbus_pin = -ENODEV,
-#endif
-};
-
-/*
- * The next two functions should go away as the boot loader is
- * supposed to initialize the macb address registers with a valid
- * ethernet address. But we need to keep it around for a while until
- * we can be reasonably sure the boot loader does this.
- *
- * The phy_id is ignored as the driver will probe for it.
- */
-static int __init parse_tag_ethernet(struct tag *tag)
-{
- int i;
-
- i = tag->u.ethernet.mac_index;
- if (i < ARRAY_SIZE(hw_addr))
- memcpy(hw_addr[i].addr, tag->u.ethernet.hw_address,
- sizeof(hw_addr[i].addr));
-
- return 0;
-}
-__tagtable(ATAG_ETHERNET, parse_tag_ethernet);
-
-static void __init set_hw_addr(struct platform_device *pdev)
-{
- struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- const u8 *addr;
- void __iomem *regs;
- struct clk *pclk;
-
- if (!res)
- return;
- if (pdev->id >= ARRAY_SIZE(hw_addr))
- return;
-
- addr = hw_addr[pdev->id].addr;
- if (!is_valid_ether_addr(addr))
- return;
-
- /*
- * Since this is board-specific code, we'll cheat and use the
- * physical address directly as we happen to know that it's
- * the same as the virtual address.
- */
- regs = (void __iomem __force *)res->start;
- pclk = clk_get(&pdev->dev, "pclk");
- if (IS_ERR(pclk))
- return;
-
- clk_enable(pclk);
- __raw_writel((addr[3] << 24) | (addr[2] << 16)
- | (addr[1] << 8) | addr[0], regs + 0x98);
- __raw_writel((addr[5] << 8) | addr[4], regs + 0x9c);
- clk_disable(pclk);
- clk_put(pclk);
-}
-
-void __init setup_board(void)
-{
- at32_map_usart(1, 0, 0); /* USART 1: /dev/ttyS0, DB9 */
- at32_setup_serial_console(0);
-}
-
-static const struct gpio_led ngw_leds[] = {
- { .name = "sys", .gpio = GPIO_PIN_PA(16), .active_low = 1,
- .default_trigger = "heartbeat",
- },
- { .name = "a", .gpio = GPIO_PIN_PA(19), .active_low = 1, },
- { .name = "b", .gpio = GPIO_PIN_PE(19), .active_low = 1, },
-};
-
-static const struct gpio_led_platform_data ngw_led_data = {
- .num_leds = ARRAY_SIZE(ngw_leds),
- .leds = (void *) ngw_leds,
-};
-
-static struct platform_device ngw_gpio_leds = {
- .name = "leds-gpio",
- .id = -1,
- .dev = {
- .platform_data = (void *) &ngw_led_data,
- }
-};
-
-static struct i2c_gpio_platform_data i2c_gpio_data = {
- .sda_pin = GPIO_PIN_PA(6),
- .scl_pin = GPIO_PIN_PA(7),
- .sda_is_open_drain = 1,
- .scl_is_open_drain = 1,
- .udelay = 2, /* close to 100 kHz */
-};
-
-static struct platform_device i2c_gpio_device = {
- .name = "i2c-gpio",
- .id = 0,
- .dev = {
- .platform_data = &i2c_gpio_data,
- },
-};
-
-static struct i2c_board_info __initdata i2c_info[] = {
- /* NOTE: original ATtiny24 firmware is at address 0x0b */
-};
-
-static int __init atngw100_init(void)
-{
- unsigned i;
-
- /*
- * ATNGW100 mkII uses 32-bit SDRAM interface. Reserve the
- * SDRAM-specific pins so that nobody messes with them.
- */
-#ifdef CONFIG_BOARD_ATNGW100_MKII
- at32_reserve_pin(GPIO_PIOE_BASE, ATMEL_EBI_PE_DATA_ALL);
-
- smc_set_timing(&nand_config, &nand_timing);
- smc_set_configuration(3, &nand_config);
- at32_add_device_nand(0, &atngw100mkii_nand_data);
-#endif
-
- at32_add_device_usart(0);
-
- set_hw_addr(at32_add_device_eth(0, ð_data[0]));
-#ifndef CONFIG_BOARD_ATNGW100_MKII_LCD
- set_hw_addr(at32_add_device_eth(1, ð_data[1]));
-#endif
-
- at32_add_device_spi(0, spi0_board_info, ARRAY_SIZE(spi0_board_info));
- at32_add_device_mci(0, &mci0_data);
- at32_add_device_usba(0, &atngw100_usba_data);
-
- for (i = 0; i < ARRAY_SIZE(ngw_leds); i++) {
- at32_select_gpio(ngw_leds[i].gpio,
- AT32_GPIOF_OUTPUT | AT32_GPIOF_HIGH);
- }
- platform_device_register(&ngw_gpio_leds);
-
- /* all these i2c/smbus pins should have external pullups for
- * open-drain sharing among all I2C devices. SDA and SCL do;
- * PB28/EXTINT3 (ATNGW100) and PE21 (ATNGW100 mkII) doesn't; it should
- * be SMBALERT# (for PMBus), but it's not available off-board.
- */
-#ifdef CONFIG_BOARD_ATNGW100_MKII
- at32_select_periph(GPIO_PIOE_BASE, 1 << 21, 0, AT32_GPIOF_PULLUP);
-#else
- at32_select_periph(GPIO_PIOB_BASE, 1 << 28, 0, AT32_GPIOF_PULLUP);
-#endif
- at32_select_gpio(i2c_gpio_data.sda_pin,
- AT32_GPIOF_MULTIDRV | AT32_GPIOF_OUTPUT | AT32_GPIOF_HIGH);
- at32_select_gpio(i2c_gpio_data.scl_pin,
- AT32_GPIOF_MULTIDRV | AT32_GPIOF_OUTPUT | AT32_GPIOF_HIGH);
- platform_device_register(&i2c_gpio_device);
- i2c_register_board_info(0, i2c_info, ARRAY_SIZE(i2c_info));
-
- return 0;
-}
-postcore_initcall(atngw100_init);
-
-static int __init atngw100_arch_init(void)
-{
- /* PB30 (ATNGW100) and PE30 (ATNGW100 mkII) is the otherwise unused
- * jumper on the mainboard, with an external pullup; the jumper grounds
- * it. Use it however you like, including letting U-Boot or Linux tweak
- * boot sequences.
- */
-#ifdef CONFIG_BOARD_ATNGW100_MKII
- at32_select_gpio(GPIO_PIN_PE(30), 0);
- gpio_request(GPIO_PIN_PE(30), "j15");
- gpio_direction_input(GPIO_PIN_PE(30));
- gpio_export(GPIO_PIN_PE(30), false);
-#else
- at32_select_gpio(GPIO_PIN_PB(30), 0);
- gpio_request(GPIO_PIN_PB(30), "j15");
- gpio_direction_input(GPIO_PIN_PB(30));
- gpio_export(GPIO_PIN_PB(30), false);
-#endif
-
- /* set_irq_type() after the arch_initcall for EIC has run, and
- * before the I2C subsystem could try using this IRQ.
- */
- return irq_set_irq_type(AT32_EXTINT(3), IRQ_TYPE_EDGE_FALLING);
-}
-arch_initcall(atngw100_arch_init);
+++ /dev/null
-# STK1000 customization
-
-if BOARD_ATSTK1000
-
-choice
- prompt "ATSTK1000 CPU daughterboard type"
- default BOARD_ATSTK1002
-
-config BOARD_ATSTK1002
- bool "ATSTK1002"
- select CPU_AT32AP7000
-
-config BOARD_ATSTK1003
- bool "ATSTK1003"
- select CPU_AT32AP7001
-
-config BOARD_ATSTK1004
- bool "ATSTK1004"
- select CPU_AT32AP7002
-
-config BOARD_ATSTK1006
- bool "ATSTK1006"
- select CPU_AT32AP7000
-
-endchoice
-
-
-config BOARD_ATSTK100X_CUSTOM
- bool "Non-default STK1002/STK1003/STK1004 jumper settings"
- help
- You will normally leave the jumpers on the CPU card at their
- default settings. If you need to use certain peripherals,
- you will need to change some of those jumpers.
-
-if BOARD_ATSTK100X_CUSTOM
-
-config BOARD_ATSTK100X_SW1_CUSTOM
- bool "SW1: use SSC1 (not SPI0)"
- help
- This also prevents using the external DAC as an audio interface,
- and means you can't initialize the on-board QVGA display.
-
-config BOARD_ATSTK100X_SW2_CUSTOM
- bool "SW2: use IRDA or TIMER0 (not UART-A, MMC/SD, and PS2-A)"
- help
- If you change this you'll want an updated boot loader putting
- the console on UART-C not UART-A.
-
-config BOARD_ATSTK100X_SW3_CUSTOM
- bool "SW3: use TIMER1 (not SSC0 and GCLK)"
- help
- This also prevents using the external DAC as an audio interface.
-
-config BOARD_ATSTK100X_SW4_CUSTOM
- bool "SW4: use ISI/Camera (not GPIOs, SPI1, and PS2-B)"
- help
- To use the camera interface you'll need a custom card (on the
- PCI-format connector) connect a video sensor.
-
-config BOARD_ATSTK1002_SW5_CUSTOM
- bool "SW5: use MACB1 (not LCDC)"
- depends on BOARD_ATSTK1002
-
-config BOARD_ATSTK1002_SW6_CUSTOM
- bool "SW6: more GPIOs (not MACB0)"
- depends on BOARD_ATSTK1002
-
-endif # custom
-
-config BOARD_ATSTK100X_SPI1
- bool "Configure SPI1 controller"
- depends on !BOARD_ATSTK100X_SW4_CUSTOM
- help
- All the signals for the second SPI controller are available on
- GPIO lines and accessed through the J1 jumper block. Say "y"
- here to configure that SPI controller.
-
-config BOARD_ATSTK1000_J2_LED
- bool
- default BOARD_ATSTK1000_J2_LED8 || BOARD_ATSTK1000_J2_RGB
-
-choice
- prompt "LEDs connected to J2:"
- depends on LEDS_GPIO && !BOARD_ATSTK100X_SW4_CUSTOM
- optional
- help
- Select this if you have jumpered the J2 jumper block to the
- LED0..LED7 amber leds, or to the RGB leds, using a ten-pin
- IDC cable. A default "heartbeat" trigger is provided, but
- you can of course override this.
-
-config BOARD_ATSTK1000_J2_LED8
- bool "LED0..LED7"
- help
- Select this if J2 is jumpered to LED0..LED7 amber leds.
-
-config BOARD_ATSTK1000_J2_RGB
- bool "RGB leds"
- help
- Select this if J2 is jumpered to the RGB leds.
-
-endchoice
-
-config BOARD_ATSTK1000_EXTDAC
- bool
- depends on !BOARD_ATSTK100X_SW1_CUSTOM && !BOARD_ATSTK100X_SW3_CUSTOM
- default y
-
-endif # stk 1000
+++ /dev/null
-obj-y += setup.o flash.o
-obj-$(CONFIG_BOARD_ATSTK1002) += atstk1002.o
-obj-$(CONFIG_BOARD_ATSTK1003) += atstk1003.o
-obj-$(CONFIG_BOARD_ATSTK1004) += atstk1004.o
-obj-$(CONFIG_BOARD_ATSTK1006) += atstk1002.o
+++ /dev/null
-/*
- * ATSTK1000 setup code: Daughterboard interface
- *
- * Copyright (C) 2007 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ARCH_AVR32_BOARDS_ATSTK1000_ATSTK1000_H
-#define __ARCH_AVR32_BOARDS_ATSTK1000_ATSTK1000_H
-
-extern struct atmel_lcdfb_pdata atstk1000_lcdc_data;
-
-void atstk1000_setup_j2_leds(void);
-
-#endif /* __ARCH_AVR32_BOARDS_ATSTK1000_ATSTK1000_H */
+++ /dev/null
-/*
- * ATSTK1002/ATSTK1006 daughterboard-specific init code
- *
- * Copyright (C) 2005-2007 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/clk.h>
-#include <linux/etherdevice.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/platform_device.h>
-#include <linux/string.h>
-#include <linux/types.h>
-#include <linux/spi/spi.h>
-#include <linux/spi/at73c213.h>
-#include <linux/atmel-mci.h>
-
-#include <video/atmel_lcdc.h>
-
-#include <asm/io.h>
-#include <asm/setup.h>
-
-#include <mach/at32ap700x.h>
-#include <mach/board.h>
-#include <mach/init.h>
-#include <mach/portmux.h>
-
-#include "atstk1000.h"
-
-/* Oscillator frequencies. These are board specific */
-unsigned long at32_board_osc_rates[3] = {
- [0] = 32768, /* 32.768 kHz on RTC osc */
- [1] = 20000000, /* 20 MHz on osc0 */
- [2] = 12000000, /* 12 MHz on osc1 */
-};
-
-/*
- * The ATSTK1006 daughterboard is very similar to the ATSTK1002. Both
- * have the AT32AP7000 chip on board; the difference is that the
- * STK1006 has 128 MB SDRAM (the STK1002 uses the 8 MB SDRAM chip on
- * the STK1000 motherboard) and 256 MB NAND flash (the STK1002 has
- * none.)
- *
- * The RAM difference is handled by the boot loader, so the only
- * difference we end up handling here is the NAND flash.
- */
-#ifdef CONFIG_BOARD_ATSTK1006
-#include <linux/mtd/partitions.h>
-#include <mach/smc.h>
-
-static struct smc_timing nand_timing __initdata = {
- .ncs_read_setup = 0,
- .nrd_setup = 10,
- .ncs_write_setup = 0,
- .nwe_setup = 10,
-
- .ncs_read_pulse = 30,
- .nrd_pulse = 15,
- .ncs_write_pulse = 30,
- .nwe_pulse = 15,
-
- .read_cycle = 30,
- .write_cycle = 30,
-
- .ncs_read_recover = 0,
- .nrd_recover = 15,
- .ncs_write_recover = 0,
- /* WE# high -> RE# low min 60 ns */
- .nwe_recover = 50,
-};
-
-static struct smc_config nand_config __initdata = {
- .bus_width = 1,
- .nrd_controlled = 1,
- .nwe_controlled = 1,
- .nwait_mode = 0,
- .byte_write = 0,
- .tdf_cycles = 2,
- .tdf_mode = 0,
-};
-
-static struct mtd_partition nand_partitions[] = {
- {
- .name = "main",
- .offset = 0x00000000,
- .size = MTDPART_SIZ_FULL,
- },
-};
-
-static struct atmel_nand_data atstk1006_nand_data __initdata = {
- .cle = 21,
- .ale = 22,
- .rdy_pin = GPIO_PIN_PB(30),
- .enable_pin = GPIO_PIN_PB(29),
- .ecc_mode = NAND_ECC_SOFT,
- .parts = nand_partitions,
- .num_parts = ARRAY_SIZE(nand_partitions),
-};
-#endif
-
-struct eth_addr {
- u8 addr[6];
-};
-
-static struct eth_addr __initdata hw_addr[2];
-static struct macb_platform_data __initdata eth_data[2] = {
- {
- /*
- * The MDIO pullups on STK1000 are a bit too weak for
- * the autodetection to work properly, so we have to
- * mask out everything but the correct address.
- */
- .phy_mask = ~(1U << 16),
- },
- {
- .phy_mask = ~(1U << 17),
- },
-};
-
-#ifdef CONFIG_BOARD_ATSTK1000_EXTDAC
-static struct at73c213_board_info at73c213_data = {
- .ssc_id = 0,
- .shortname = "AVR32 STK1000 external DAC",
-};
-#endif
-
-#ifndef CONFIG_BOARD_ATSTK100X_SW1_CUSTOM
-static struct spi_board_info spi0_board_info[] __initdata = {
-#ifdef CONFIG_BOARD_ATSTK1000_EXTDAC
- {
- /* AT73C213 */
- .modalias = "at73c213",
- .max_speed_hz = 200000,
- .chip_select = 0,
- .mode = SPI_MODE_1,
- .platform_data = &at73c213_data,
- },
-#endif
- {
- /* QVGA display */
- .modalias = "ltv350qv",
- .max_speed_hz = 16000000,
- .chip_select = 1,
- .mode = SPI_MODE_3,
- },
-};
-#endif
-
-#ifdef CONFIG_BOARD_ATSTK100X_SPI1
-static struct spi_board_info spi1_board_info[] __initdata = { {
- /* patch in custom entries here */
-} };
-#endif
-
-/*
- * The next two functions should go away as the boot loader is
- * supposed to initialize the macb address registers with a valid
- * ethernet address. But we need to keep it around for a while until
- * we can be reasonably sure the boot loader does this.
- *
- * The phy_id is ignored as the driver will probe for it.
- */
-static int __init parse_tag_ethernet(struct tag *tag)
-{
- int i;
-
- i = tag->u.ethernet.mac_index;
- if (i < ARRAY_SIZE(hw_addr))
- memcpy(hw_addr[i].addr, tag->u.ethernet.hw_address,
- sizeof(hw_addr[i].addr));
-
- return 0;
-}
-__tagtable(ATAG_ETHERNET, parse_tag_ethernet);
-
-static void __init set_hw_addr(struct platform_device *pdev)
-{
- struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- const u8 *addr;
- void __iomem *regs;
- struct clk *pclk;
-
- if (!res)
- return;
- if (pdev->id >= ARRAY_SIZE(hw_addr))
- return;
-
- addr = hw_addr[pdev->id].addr;
- if (!is_valid_ether_addr(addr))
- return;
-
- /*
- * Since this is board-specific code, we'll cheat and use the
- * physical address directly as we happen to know that it's
- * the same as the virtual address.
- */
- regs = (void __iomem __force *)res->start;
- pclk = clk_get(&pdev->dev, "pclk");
- if (IS_ERR(pclk))
- return;
-
- clk_enable(pclk);
- __raw_writel((addr[3] << 24) | (addr[2] << 16)
- | (addr[1] << 8) | addr[0], regs + 0x98);
- __raw_writel((addr[5] << 8) | addr[4], regs + 0x9c);
- clk_disable(pclk);
- clk_put(pclk);
-}
-
-#ifdef CONFIG_BOARD_ATSTK1000_EXTDAC
-static void __init atstk1002_setup_extdac(void)
-{
- struct clk *gclk;
- struct clk *pll;
-
- gclk = clk_get(NULL, "gclk0");
- if (IS_ERR(gclk))
- goto err_gclk;
- pll = clk_get(NULL, "pll0");
- if (IS_ERR(pll))
- goto err_pll;
-
- if (clk_set_parent(gclk, pll)) {
- pr_debug("STK1000: failed to set pll0 as parent for DAC clock\n");
- goto err_set_clk;
- }
-
- at32_select_periph(GPIO_PIOA_BASE, (1 << 30), GPIO_PERIPH_A, 0);
- at73c213_data.dac_clk = gclk;
-
-err_set_clk:
- clk_put(pll);
-err_pll:
- clk_put(gclk);
-err_gclk:
- return;
-}
-#else
-static void __init atstk1002_setup_extdac(void)
-{
-
-}
-#endif /* CONFIG_BOARD_ATSTK1000_EXTDAC */
-
-void __init setup_board(void)
-{
-#ifdef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
- at32_map_usart(0, 1, 0); /* USART 0/B: /dev/ttyS1, IRDA */
-#else
- at32_map_usart(1, 0, 0); /* USART 1/A: /dev/ttyS0, DB9 */
-#endif
- /* USART 2/unused: expansion connector */
- at32_map_usart(3, 2, 0); /* USART 3/C: /dev/ttyS2, DB9 */
-
- at32_setup_serial_console(0);
-}
-
-#ifndef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
-
-static struct mci_platform_data __initdata mci0_data = {
- .slot[0] = {
- .bus_width = 4,
-
-/* MMC card detect requires MACB0 *NOT* be used */
-#ifdef CONFIG_BOARD_ATSTK1002_SW6_CUSTOM
- .detect_pin = GPIO_PIN_PC(14), /* gpio30/sdcd */
- .wp_pin = GPIO_PIN_PC(15), /* gpio31/sdwp */
-#else
- .detect_pin = -ENODEV,
- .wp_pin = -ENODEV,
-#endif /* SW6 for sd{cd,wp} routing */
- },
-};
-
-#endif /* SW2 for MMC signal routing */
-
-static int __init atstk1002_init(void)
-{
- /*
- * ATSTK1000 uses 32-bit SDRAM interface. Reserve the
- * SDRAM-specific pins so that nobody messes with them.
- */
- at32_reserve_pin(GPIO_PIOE_BASE, ATMEL_EBI_PE_DATA_ALL);
-
-#ifdef CONFIG_BOARD_ATSTK1006
- smc_set_timing(&nand_config, &nand_timing);
- smc_set_configuration(3, &nand_config);
- at32_add_device_nand(0, &atstk1006_nand_data);
-#endif
-
-#ifdef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
- at32_add_device_usart(1);
-#else
- at32_add_device_usart(0);
-#endif
- at32_add_device_usart(2);
-
-#ifndef CONFIG_BOARD_ATSTK1002_SW6_CUSTOM
- set_hw_addr(at32_add_device_eth(0, ð_data[0]));
-#endif
-#ifndef CONFIG_BOARD_ATSTK100X_SW1_CUSTOM
- at32_add_device_spi(0, spi0_board_info, ARRAY_SIZE(spi0_board_info));
-#endif
-#ifdef CONFIG_BOARD_ATSTK100X_SPI1
- at32_add_device_spi(1, spi1_board_info, ARRAY_SIZE(spi1_board_info));
-#endif
-#ifndef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
- at32_add_device_mci(0, &mci0_data);
-#endif
-#ifdef CONFIG_BOARD_ATSTK1002_SW5_CUSTOM
- set_hw_addr(at32_add_device_eth(1, ð_data[1]));
-#else
- at32_add_device_lcdc(0, &atstk1000_lcdc_data,
- fbmem_start, fbmem_size,
- ATMEL_LCDC_PRI_24BIT | ATMEL_LCDC_PRI_CONTROL);
-#endif
- at32_add_device_usba(0, NULL);
-#ifndef CONFIG_BOARD_ATSTK100X_SW3_CUSTOM
- at32_add_device_ssc(0, ATMEL_SSC_TX);
-#endif
-
- atstk1000_setup_j2_leds();
- atstk1002_setup_extdac();
-
- return 0;
-}
-postcore_initcall(atstk1002_init);
+++ /dev/null
-/*
- * ATSTK1003 daughterboard-specific init code
- *
- * Copyright (C) 2007 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/clk.h>
-#include <linux/err.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/platform_device.h>
-#include <linux/string.h>
-#include <linux/types.h>
-
-#include <linux/spi/at73c213.h>
-#include <linux/spi/spi.h>
-#include <linux/atmel-mci.h>
-
-#include <asm/setup.h>
-
-#include <mach/at32ap700x.h>
-#include <mach/board.h>
-#include <mach/init.h>
-#include <mach/portmux.h>
-
-#include "atstk1000.h"
-
-/* Oscillator frequencies. These are board specific */
-unsigned long at32_board_osc_rates[3] = {
- [0] = 32768, /* 32.768 kHz on RTC osc */
- [1] = 20000000, /* 20 MHz on osc0 */
- [2] = 12000000, /* 12 MHz on osc1 */
-};
-
-#ifdef CONFIG_BOARD_ATSTK1000_EXTDAC
-static struct at73c213_board_info at73c213_data = {
- .ssc_id = 0,
- .shortname = "AVR32 STK1000 external DAC",
-};
-#endif
-
-#ifndef CONFIG_BOARD_ATSTK100X_SW1_CUSTOM
-static struct spi_board_info spi0_board_info[] __initdata = {
-#ifdef CONFIG_BOARD_ATSTK1000_EXTDAC
- {
- /* AT73C213 */
- .modalias = "at73c213",
- .max_speed_hz = 200000,
- .chip_select = 0,
- .mode = SPI_MODE_1,
- .platform_data = &at73c213_data,
- },
-#endif
- /*
- * We can control the LTV350QV LCD panel, but it isn't much
- * point since we don't have an LCD controller...
- */
-};
-#endif
-
-#ifdef CONFIG_BOARD_ATSTK100X_SPI1
-static struct spi_board_info spi1_board_info[] __initdata = { {
- /* patch in custom entries here */
-} };
-#endif
-
-#ifndef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
-static struct mci_platform_data __initdata mci0_data = {
- .slot[0] = {
- .bus_width = 4,
- .detect_pin = -ENODEV,
- .wp_pin = -ENODEV,
- },
-};
-#endif
-
-#ifdef CONFIG_BOARD_ATSTK1000_EXTDAC
-static void __init atstk1003_setup_extdac(void)
-{
- struct clk *gclk;
- struct clk *pll;
-
- gclk = clk_get(NULL, "gclk0");
- if (IS_ERR(gclk))
- goto err_gclk;
- pll = clk_get(NULL, "pll0");
- if (IS_ERR(pll))
- goto err_pll;
-
- if (clk_set_parent(gclk, pll)) {
- pr_debug("STK1000: failed to set pll0 as parent for DAC clock\n");
- goto err_set_clk;
- }
-
- at32_select_periph(GPIO_PIOA_BASE, (1 << 30), GPIO_PERIPH_A, 0);
- at73c213_data.dac_clk = gclk;
-
-err_set_clk:
- clk_put(pll);
-err_pll:
- clk_put(gclk);
-err_gclk:
- return;
-}
-#else
-static void __init atstk1003_setup_extdac(void)
-{
-
-}
-#endif /* CONFIG_BOARD_ATSTK1000_EXTDAC */
-
-void __init setup_board(void)
-{
-#ifdef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
- at32_map_usart(0, 1, 0); /* USART 0/B: /dev/ttyS1, IRDA */
-#else
- at32_map_usart(1, 0, 0); /* USART 1/A: /dev/ttyS0, DB9 */
-#endif
- /* USART 2/unused: expansion connector */
- at32_map_usart(3, 2, 0); /* USART 3/C: /dev/ttyS2, DB9 */
-
- at32_setup_serial_console(0);
-}
-
-static int __init atstk1003_init(void)
-{
- /*
- * ATSTK1000 uses 32-bit SDRAM interface. Reserve the
- * SDRAM-specific pins so that nobody messes with them.
- */
- at32_reserve_pin(GPIO_PIOE_BASE, ATMEL_EBI_PE_DATA_ALL);
-
-#ifdef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
- at32_add_device_usart(1);
-#else
- at32_add_device_usart(0);
-#endif
- at32_add_device_usart(2);
-
-#ifndef CONFIG_BOARD_ATSTK100X_SW1_CUSTOM
- at32_add_device_spi(0, spi0_board_info, ARRAY_SIZE(spi0_board_info));
-#endif
-#ifdef CONFIG_BOARD_ATSTK100X_SPI1
- at32_add_device_spi(1, spi1_board_info, ARRAY_SIZE(spi1_board_info));
-#endif
-#ifndef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
- at32_add_device_mci(0, &mci0_data);
-#endif
- at32_add_device_usba(0, NULL);
-#ifndef CONFIG_BOARD_ATSTK100X_SW3_CUSTOM
- at32_add_device_ssc(0, ATMEL_SSC_TX);
-#endif
-
- atstk1000_setup_j2_leds();
- atstk1003_setup_extdac();
-
- return 0;
-}
-postcore_initcall(atstk1003_init);
+++ /dev/null
-/*
- * ATSTK1003 daughterboard-specific init code
- *
- * Copyright (C) 2007 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/clk.h>
-#include <linux/err.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/platform_device.h>
-#include <linux/string.h>
-#include <linux/types.h>
-
-#include <linux/spi/at73c213.h>
-#include <linux/spi/spi.h>
-#include <linux/atmel-mci.h>
-
-#include <video/atmel_lcdc.h>
-
-#include <asm/setup.h>
-
-#include <mach/at32ap700x.h>
-#include <mach/board.h>
-#include <mach/init.h>
-#include <mach/portmux.h>
-
-#include "atstk1000.h"
-
-/* Oscillator frequencies. These are board specific */
-unsigned long at32_board_osc_rates[3] = {
- [0] = 32768, /* 32.768 kHz on RTC osc */
- [1] = 20000000, /* 20 MHz on osc0 */
- [2] = 12000000, /* 12 MHz on osc1 */
-};
-
-#ifdef CONFIG_BOARD_ATSTK1000_EXTDAC
-static struct at73c213_board_info at73c213_data = {
- .ssc_id = 0,
- .shortname = "AVR32 STK1000 external DAC",
-};
-#endif
-
-#ifndef CONFIG_BOARD_ATSTK100X_SW1_CUSTOM
-static struct spi_board_info spi0_board_info[] __initdata = {
-#ifdef CONFIG_BOARD_ATSTK1000_EXTDAC
- {
- /* AT73C213 */
- .modalias = "at73c213",
- .max_speed_hz = 200000,
- .chip_select = 0,
- .mode = SPI_MODE_1,
- .platform_data = &at73c213_data,
- },
-#endif
- {
- /* QVGA display */
- .modalias = "ltv350qv",
- .max_speed_hz = 16000000,
- .chip_select = 1,
- .mode = SPI_MODE_3,
- },
-};
-#endif
-
-#ifdef CONFIG_BOARD_ATSTK100X_SPI1
-static struct spi_board_info spi1_board_info[] __initdata = { {
- /* patch in custom entries here */
-} };
-#endif
-
-#ifndef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
-static struct mci_platform_data __initdata mci0_data = {
- .slot[0] = {
- .bus_width = 4,
- .detect_pin = -ENODEV,
- .wp_pin = -ENODEV,
- },
-};
-#endif
-
-#ifdef CONFIG_BOARD_ATSTK1000_EXTDAC
-static void __init atstk1004_setup_extdac(void)
-{
- struct clk *gclk;
- struct clk *pll;
-
- gclk = clk_get(NULL, "gclk0");
- if (IS_ERR(gclk))
- goto err_gclk;
- pll = clk_get(NULL, "pll0");
- if (IS_ERR(pll))
- goto err_pll;
-
- if (clk_set_parent(gclk, pll)) {
- pr_debug("STK1000: failed to set pll0 as parent for DAC clock\n");
- goto err_set_clk;
- }
-
- at32_select_periph(GPIO_PIOA_BASE, (1 << 30), GPIO_PERIPH_A, 0);
- at73c213_data.dac_clk = gclk;
-
-err_set_clk:
- clk_put(pll);
-err_pll:
- clk_put(gclk);
-err_gclk:
- return;
-}
-#else
-static void __init atstk1004_setup_extdac(void)
-{
-
-}
-#endif /* CONFIG_BOARD_ATSTK1000_EXTDAC */
-
-void __init setup_board(void)
-{
-#ifdef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
- at32_map_usart(0, 1, 0); /* USART 0/B: /dev/ttyS1, IRDA */
-#else
- at32_map_usart(1, 0, 0); /* USART 1/A: /dev/ttyS0, DB9 */
-#endif
- /* USART 2/unused: expansion connector */
- at32_map_usart(3, 2, 0); /* USART 3/C: /dev/ttyS2, DB9 */
-
- at32_setup_serial_console(0);
-}
-
-static int __init atstk1004_init(void)
-{
-#ifdef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
- at32_add_device_usart(1);
-#else
- at32_add_device_usart(0);
-#endif
- at32_add_device_usart(2);
-
-#ifndef CONFIG_BOARD_ATSTK100X_SW1_CUSTOM
- at32_add_device_spi(0, spi0_board_info, ARRAY_SIZE(spi0_board_info));
-#endif
-#ifdef CONFIG_BOARD_ATSTK100X_SPI1
- at32_add_device_spi(1, spi1_board_info, ARRAY_SIZE(spi1_board_info));
-#endif
-#ifndef CONFIG_BOARD_ATSTK100X_SW2_CUSTOM
- at32_add_device_mci(0, &mci0_data);
-#endif
- at32_add_device_lcdc(0, &atstk1000_lcdc_data,
- fbmem_start, fbmem_size,
- ATMEL_LCDC_PRI_24BIT | ATMEL_LCDC_PRI_CONTROL);
- at32_add_device_usba(0, NULL);
-#ifndef CONFIG_BOARD_ATSTK100X_SW3_CUSTOM
- at32_add_device_ssc(0, ATMEL_SSC_TX);
-#endif
-
- atstk1000_setup_j2_leds();
- atstk1004_setup_extdac();
-
- return 0;
-}
-postcore_initcall(atstk1004_init);
+++ /dev/null
-/*
- * ATSTK1000 board-specific flash initialization
- *
- * Copyright (C) 2005-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/mtd/mtd.h>
-#include <linux/mtd/partitions.h>
-#include <linux/mtd/physmap.h>
-
-#include <mach/smc.h>
-
-static struct smc_timing flash_timing __initdata = {
- .ncs_read_setup = 0,
- .nrd_setup = 40,
- .ncs_write_setup = 0,
- .nwe_setup = 10,
-
- .ncs_read_pulse = 80,
- .nrd_pulse = 40,
- .ncs_write_pulse = 65,
- .nwe_pulse = 55,
-
- .read_cycle = 120,
- .write_cycle = 120,
-};
-
-static struct smc_config flash_config __initdata = {
- .bus_width = 2,
- .nrd_controlled = 1,
- .nwe_controlled = 1,
- .byte_write = 1,
-};
-
-static struct mtd_partition flash_parts[] = {
- {
- .name = "u-boot",
- .offset = 0x00000000,
- .size = 0x00020000, /* 128 KiB */
- .mask_flags = MTD_WRITEABLE,
- },
- {
- .name = "root",
- .offset = 0x00020000,
- .size = 0x007d0000,
- },
- {
- .name = "env",
- .offset = 0x007f0000,
- .size = 0x00010000,
- .mask_flags = MTD_WRITEABLE,
- },
-};
-
-static struct physmap_flash_data flash_data = {
- .width = 2,
- .nr_parts = ARRAY_SIZE(flash_parts),
- .parts = flash_parts,
-};
-
-static struct resource flash_resource = {
- .start = 0x00000000,
- .end = 0x007fffff,
- .flags = IORESOURCE_MEM,
-};
-
-static struct platform_device flash_device = {
- .name = "physmap-flash",
- .id = 0,
- .resource = &flash_resource,
- .num_resources = 1,
- .dev = {
- .platform_data = &flash_data,
- },
-};
-
-/* This needs to be called after the SMC has been initialized */
-static int __init atstk1000_flash_init(void)
-{
- int ret;
-
- smc_set_timing(&flash_config, &flash_timing);
- ret = smc_set_configuration(0, &flash_config);
- if (ret < 0) {
- printk(KERN_ERR "atstk1000: failed to set NOR flash timing\n");
- return ret;
- }
-
- platform_device_register(&flash_device);
-
- return 0;
-}
-device_initcall(atstk1000_flash_init);
+++ /dev/null
-/*
- * ATSTK1000 board-specific setup code.
- *
- * Copyright (C) 2005-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/bootmem.h>
-#include <linux/fb.h>
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/types.h>
-#include <linux/linkage.h>
-
-#include <video/atmel_lcdc.h>
-
-#include <asm/setup.h>
-
-#include <mach/at32ap700x.h>
-#include <mach/board.h>
-#include <mach/portmux.h>
-
-#include "atstk1000.h"
-
-/* Initialized by bootloader-specific startup code. */
-struct tag *bootloader_tags __initdata;
-
-static struct fb_videomode __initdata ltv350qv_modes[] = {
- {
- .name = "320x240 @ 75",
- .refresh = 75,
- .xres = 320, .yres = 240,
- .pixclock = KHZ2PICOS(6891),
-
- .left_margin = 17, .right_margin = 33,
- .upper_margin = 10, .lower_margin = 10,
- .hsync_len = 16, .vsync_len = 1,
-
- .sync = 0,
- .vmode = FB_VMODE_NONINTERLACED,
- },
-};
-
-static struct fb_monspecs __initdata atstk1000_default_monspecs = {
- .manufacturer = "SNG",
- .monitor = "LTV350QV",
- .modedb = ltv350qv_modes,
- .modedb_len = ARRAY_SIZE(ltv350qv_modes),
- .hfmin = 14820,
- .hfmax = 22230,
- .vfmin = 60,
- .vfmax = 90,
- .dclkmax = 30000000,
-};
-
-struct atmel_lcdfb_pdata __initdata atstk1000_lcdc_data = {
- .default_bpp = 24,
- .default_dmacon = ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
- .default_lcdcon2 = (ATMEL_LCDC_DISTYPE_TFT
- | ATMEL_LCDC_INVCLK
- | ATMEL_LCDC_CLKMOD_ALWAYSACTIVE
- | ATMEL_LCDC_MEMOR_BIG),
- .default_monspecs = &atstk1000_default_monspecs,
- .guard_time = 2,
-};
-
-#ifdef CONFIG_BOARD_ATSTK1000_J2_LED
-#include <linux/leds.h>
-
-static struct gpio_led stk1000_j2_led[] = {
-#ifdef CONFIG_BOARD_ATSTK1000_J2_LED8
-#define LEDSTRING "J2 jumpered to LED8"
- { .name = "led0:amber", .gpio = GPIO_PIN_PB( 8), },
- { .name = "led1:amber", .gpio = GPIO_PIN_PB( 9), },
- { .name = "led2:amber", .gpio = GPIO_PIN_PB(10), },
- { .name = "led3:amber", .gpio = GPIO_PIN_PB(13), },
- { .name = "led4:amber", .gpio = GPIO_PIN_PB(14), },
- { .name = "led5:amber", .gpio = GPIO_PIN_PB(15), },
- { .name = "led6:amber", .gpio = GPIO_PIN_PB(16), },
- { .name = "led7:amber", .gpio = GPIO_PIN_PB(30),
- .default_trigger = "heartbeat", },
-#else /* RGB */
-#define LEDSTRING "J2 jumpered to RGB LEDs"
- { .name = "r1:red", .gpio = GPIO_PIN_PB( 8), },
- { .name = "g1:green", .gpio = GPIO_PIN_PB(10), },
- { .name = "b1:blue", .gpio = GPIO_PIN_PB(14), },
-
- { .name = "r2:red", .gpio = GPIO_PIN_PB( 9),
- .default_trigger = "heartbeat", },
- { .name = "g2:green", .gpio = GPIO_PIN_PB(13), },
- { .name = "b2:blue", .gpio = GPIO_PIN_PB(15),
- .default_trigger = "heartbeat", },
- /* PB16, PB30 unused */
-#endif
-};
-
-static struct gpio_led_platform_data stk1000_j2_led_data = {
- .num_leds = ARRAY_SIZE(stk1000_j2_led),
- .leds = stk1000_j2_led,
-};
-
-static struct platform_device stk1000_j2_led_dev = {
- .name = "leds-gpio",
- .id = 2, /* gpio block J2 */
- .dev = {
- .platform_data = &stk1000_j2_led_data,
- },
-};
-
-void __init atstk1000_setup_j2_leds(void)
-{
- unsigned i;
-
- for (i = 0; i < ARRAY_SIZE(stk1000_j2_led); i++)
- at32_select_gpio(stk1000_j2_led[i].gpio, AT32_GPIOF_OUTPUT);
-
- printk("STK1000: " LEDSTRING "\n");
- platform_device_register(&stk1000_j2_led_dev);
-}
-#else /* CONFIG_BOARD_ATSTK1000_J2_LED */
-void __init atstk1000_setup_j2_leds(void)
-{
-
-}
-#endif /* CONFIG_BOARD_ATSTK1000_J2_LED */
+++ /dev/null
-# Favr-32 customization
-
-if BOARD_FAVR_32
-
-config BOARD_FAVR32_ABDAC_RATE
- int "DAC target rate"
- default 44100
- range 32000 50000
- help
- Specify the target rate the internal DAC should try to match. This
- will use PLL1 to generate a frequency as close as possible to this
- rate.
-
- Must be within the range 32000 to 50000, which should be suitable to
- generate most other frequencies in power of 2 steps.
-
- Ex:
- 48000 will also suit 24000 and 12000
- 44100 will also suit 22050 and 11025
- 32000 will also suit 16000 and 8000
-
-endif # BOARD_FAVR_32
+++ /dev/null
-obj-y += setup.o flash.o
+++ /dev/null
-/*
- * Favr-32 board-specific flash initialization
- *
- * Copyright (C) 2008 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/mtd/mtd.h>
-#include <linux/mtd/partitions.h>
-#include <linux/mtd/physmap.h>
-
-#include <mach/smc.h>
-
-static struct smc_timing flash_timing __initdata = {
- .ncs_read_setup = 0,
- .nrd_setup = 40,
- .ncs_write_setup = 0,
- .nwe_setup = 10,
-
- .ncs_read_pulse = 80,
- .nrd_pulse = 40,
- .ncs_write_pulse = 65,
- .nwe_pulse = 55,
-
- .read_cycle = 120,
- .write_cycle = 120,
-};
-
-static struct smc_config flash_config __initdata = {
- .bus_width = 2,
- .nrd_controlled = 1,
- .nwe_controlled = 1,
- .byte_write = 1,
-};
-
-static struct mtd_partition flash_parts[] = {
- {
- .name = "u-boot",
- .offset = 0x00000000,
- .size = 0x00020000, /* 128 KiB */
- .mask_flags = MTD_WRITEABLE,
- },
- {
- .name = "root",
- .offset = 0x00020000,
- .size = 0x007d0000,
- },
- {
- .name = "env",
- .offset = 0x007f0000,
- .size = 0x00010000,
- .mask_flags = MTD_WRITEABLE,
- },
-};
-
-static struct physmap_flash_data flash_data = {
- .width = 2,
- .nr_parts = ARRAY_SIZE(flash_parts),
- .parts = flash_parts,
-};
-
-static struct resource flash_resource = {
- .start = 0x00000000,
- .end = 0x007fffff,
- .flags = IORESOURCE_MEM,
-};
-
-static struct platform_device flash_device = {
- .name = "physmap-flash",
- .id = 0,
- .resource = &flash_resource,
- .num_resources = 1,
- .dev = {
- .platform_data = &flash_data,
- },
-};
-
-/* This needs to be called after the SMC has been initialized */
-static int __init favr32_flash_init(void)
-{
- int ret;
-
- smc_set_timing(&flash_config, &flash_timing);
- ret = smc_set_configuration(0, &flash_config);
- if (ret < 0) {
- printk(KERN_ERR "Favr-32: failed to set NOR flash timing\n");
- return ret;
- }
-
- platform_device_register(&flash_device);
-
- return 0;
-}
-device_initcall(favr32_flash_init);
+++ /dev/null
-/*
- * Favr-32 board-specific setup code.
- *
- * Copyright (C) 2008 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/clk.h>
-#include <linux/etherdevice.h>
-#include <linux/bootmem.h>
-#include <linux/fb.h>
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/types.h>
-#include <linux/linkage.h>
-#include <linux/gpio.h>
-#include <linux/leds.h>
-#include <linux/atmel-mci.h>
-#include <linux/pwm.h>
-#include <linux/pwm_backlight.h>
-#include <linux/regulator/fixed.h>
-#include <linux/regulator/machine.h>
-#include <linux/spi/spi.h>
-#include <linux/spi/ads7846.h>
-
-#include <sound/atmel-abdac.h>
-
-#include <video/atmel_lcdc.h>
-
-#include <asm/setup.h>
-
-#include <mach/at32ap700x.h>
-#include <mach/init.h>
-#include <mach/board.h>
-#include <mach/portmux.h>
-
-#define PWM_BL_CH 2
-
-/* Oscillator frequencies. These are board-specific */
-unsigned long at32_board_osc_rates[3] = {
- [0] = 32768, /* 32.768 kHz on RTC osc */
- [1] = 20000000, /* 20 MHz on osc0 */
- [2] = 12000000, /* 12 MHz on osc1 */
-};
-
-/* Initialized by bootloader-specific startup code. */
-struct tag *bootloader_tags __initdata;
-
-static struct atmel_abdac_pdata __initdata abdac0_data = {
-};
-
-struct eth_addr {
- u8 addr[6];
-};
-static struct eth_addr __initdata hw_addr[1];
-static struct macb_platform_data __initdata eth_data[1] = {
- {
- .phy_mask = ~(1U << 1),
- },
-};
-
-static int ads7843_get_pendown_state(void)
-{
- return !gpio_get_value(GPIO_PIN_PB(3));
-}
-
-static struct ads7846_platform_data ads7843_data = {
- .model = 7843,
- .get_pendown_state = ads7843_get_pendown_state,
- .pressure_max = 255,
- /*
- * Values below are for debounce filtering, these can be experimented
- * with further.
- */
- .debounce_max = 20,
- .debounce_rep = 4,
- .debounce_tol = 5,
-
- .keep_vref_on = true,
- .settle_delay_usecs = 500,
- .penirq_recheck_delay_usecs = 100,
-};
-
-static struct spi_board_info __initdata spi1_board_info[] = {
- {
- /* ADS7843 touch controller */
- .modalias = "ads7846",
- .max_speed_hz = 2000000,
- .chip_select = 0,
- .bus_num = 1,
- .platform_data = &ads7843_data,
- },
-};
-
-static struct mci_platform_data __initdata mci0_data = {
- .slot[0] = {
- .bus_width = 4,
- .detect_pin = -ENODEV,
- .wp_pin = -ENODEV,
- },
-};
-
-static struct fb_videomode __initdata lb104v03_modes[] = {
- {
- .name = "640x480 @ 50",
- .refresh = 50,
- .xres = 640, .yres = 480,
- .pixclock = KHZ2PICOS(25100),
-
- .left_margin = 90, .right_margin = 70,
- .upper_margin = 30, .lower_margin = 15,
- .hsync_len = 12, .vsync_len = 2,
-
- .sync = 0,
- .vmode = FB_VMODE_NONINTERLACED,
- },
-};
-
-static struct fb_monspecs __initdata favr32_default_monspecs = {
- .manufacturer = "LG",
- .monitor = "LB104V03",
- .modedb = lb104v03_modes,
- .modedb_len = ARRAY_SIZE(lb104v03_modes),
- .hfmin = 27273,
- .hfmax = 31111,
- .vfmin = 45,
- .vfmax = 60,
- .dclkmax = 28000000,
-};
-
-struct atmel_lcdfb_pdata __initdata favr32_lcdc_data = {
- .default_bpp = 16,
- .default_dmacon = ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
- .default_lcdcon2 = (ATMEL_LCDC_DISTYPE_TFT
- | ATMEL_LCDC_CLKMOD_ALWAYSACTIVE
- | ATMEL_LCDC_MEMOR_BIG),
- .default_monspecs = &favr32_default_monspecs,
- .guard_time = 2,
-};
-
-static struct gpio_led favr32_leds[] = {
- {
- .name = "green",
- .gpio = GPIO_PIN_PE(19),
- .default_trigger = "heartbeat",
- .active_low = 1,
- },
- {
- .name = "red",
- .gpio = GPIO_PIN_PE(20),
- .active_low = 1,
- },
-};
-
-static struct gpio_led_platform_data favr32_led_data = {
- .num_leds = ARRAY_SIZE(favr32_leds),
- .leds = favr32_leds,
-};
-
-static struct platform_device favr32_led_dev = {
- .name = "leds-gpio",
- .id = 0,
- .dev = {
- .platform_data = &favr32_led_data,
- },
-};
-
-/*
- * The next two functions should go away as the boot loader is
- * supposed to initialize the macb address registers with a valid
- * ethernet address. But we need to keep it around for a while until
- * we can be reasonably sure the boot loader does this.
- *
- * The phy_id is ignored as the driver will probe for it.
- */
-static int __init parse_tag_ethernet(struct tag *tag)
-{
- int i;
-
- i = tag->u.ethernet.mac_index;
- if (i < ARRAY_SIZE(hw_addr))
- memcpy(hw_addr[i].addr, tag->u.ethernet.hw_address,
- sizeof(hw_addr[i].addr));
-
- return 0;
-}
-__tagtable(ATAG_ETHERNET, parse_tag_ethernet);
-
-static void __init set_hw_addr(struct platform_device *pdev)
-{
- struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- const u8 *addr;
- void __iomem *regs;
- struct clk *pclk;
-
- if (!res)
- return;
- if (pdev->id >= ARRAY_SIZE(hw_addr))
- return;
-
- addr = hw_addr[pdev->id].addr;
- if (!is_valid_ether_addr(addr))
- return;
-
- /*
- * Since this is board-specific code, we'll cheat and use the
- * physical address directly as we happen to know that it's
- * the same as the virtual address.
- */
- regs = (void __iomem __force *)res->start;
- pclk = clk_get(&pdev->dev, "pclk");
- if (IS_ERR(pclk))
- return;
-
- clk_enable(pclk);
- __raw_writel((addr[3] << 24) | (addr[2] << 16)
- | (addr[1] << 8) | addr[0], regs + 0x98);
- __raw_writel((addr[5] << 8) | addr[4], regs + 0x9c);
- clk_disable(pclk);
- clk_put(pclk);
-}
-
-void __init favr32_setup_leds(void)
-{
- unsigned i;
-
- for (i = 0; i < ARRAY_SIZE(favr32_leds); i++)
- at32_select_gpio(favr32_leds[i].gpio, AT32_GPIOF_OUTPUT);
-
- platform_device_register(&favr32_led_dev);
-}
-
-static struct pwm_lookup pwm_lookup[] = {
- PWM_LOOKUP("at91sam9rl-pwm", PWM_BL_CH, "pwm-backlight.0", NULL,
- 5000, PWM_POLARITY_INVERSED),
-};
-
-static struct regulator_consumer_supply fixed_power_consumers[] = {
- REGULATOR_SUPPLY("power", "pwm-backlight.0"),
-};
-
-static struct platform_pwm_backlight_data pwm_bl_data = {
- .enable_gpio = GPIO_PIN_PA(28),
- .max_brightness = 255,
- .dft_brightness = 255,
- .lth_brightness = 50,
-};
-
-static struct platform_device pwm_bl_device = {
- .name = "pwm-backlight",
- .dev = {
- .platform_data = &pwm_bl_data,
- },
-};
-
-static void __init favr32_setup_atmel_pwm_bl(void)
-{
- pwm_add_table(pwm_lookup, ARRAY_SIZE(pwm_lookup));
- regulator_register_always_on(0, "fixed", fixed_power_consumers,
- ARRAY_SIZE(fixed_power_consumers), 3300000);
- platform_device_register(&pwm_bl_device);
- at32_select_gpio(pwm_bl_data.enable_gpio, 0);
-}
-
-void __init setup_board(void)
-{
- at32_map_usart(3, 0, 0); /* USART 3 => /dev/ttyS0 */
- at32_setup_serial_console(0);
-}
-
-static int __init set_abdac_rate(struct platform_device *pdev)
-{
- int retval;
- struct clk *osc1;
- struct clk *pll1;
- struct clk *abdac;
-
- if (pdev == NULL)
- return -ENXIO;
-
- osc1 = clk_get(NULL, "osc1");
- if (IS_ERR(osc1)) {
- retval = PTR_ERR(osc1);
- goto out;
- }
-
- pll1 = clk_get(NULL, "pll1");
- if (IS_ERR(pll1)) {
- retval = PTR_ERR(pll1);
- goto out_osc1;
- }
-
- abdac = clk_get(&pdev->dev, "sample_clk");
- if (IS_ERR(abdac)) {
- retval = PTR_ERR(abdac);
- goto out_pll1;
- }
-
- retval = clk_set_parent(pll1, osc1);
- if (retval != 0)
- goto out_abdac;
-
- /*
- * Rate is 32000 to 50000 and ABDAC oversamples 256x. Multiply, in
- * power of 2, to a value above 80 MHz. Power of 2 so it is possible
- * for the generic clock to divide it down again and 80 MHz is the
- * lowest frequency for the PLL.
- */
- retval = clk_round_rate(pll1,
- CONFIG_BOARD_FAVR32_ABDAC_RATE * 256 * 16);
- if (retval <= 0) {
- retval = -EINVAL;
- goto out_abdac;
- }
-
- retval = clk_set_rate(pll1, retval);
- if (retval != 0)
- goto out_abdac;
-
- retval = clk_set_parent(abdac, pll1);
- if (retval != 0)
- goto out_abdac;
-
-out_abdac:
- clk_put(abdac);
-out_pll1:
- clk_put(pll1);
-out_osc1:
- clk_put(osc1);
-out:
- return retval;
-}
-
-static int __init favr32_init(void)
-{
- /*
- * Favr-32 uses 32-bit SDRAM interface. Reserve the SDRAM-specific
- * pins so that nobody messes with them.
- */
- at32_reserve_pin(GPIO_PIOE_BASE, ATMEL_EBI_PE_DATA_ALL);
-
- at32_select_gpio(GPIO_PIN_PB(3), 0); /* IRQ from ADS7843 */
-
- at32_add_device_usart(0);
-
- set_hw_addr(at32_add_device_eth(0, ð_data[0]));
-
- spi1_board_info[0].irq = gpio_to_irq(GPIO_PIN_PB(3));
-
- set_abdac_rate(at32_add_device_abdac(0, &abdac0_data));
-
- at32_add_device_pwm(1 << PWM_BL_CH);
- at32_add_device_spi(1, spi1_board_info, ARRAY_SIZE(spi1_board_info));
- at32_add_device_mci(0, &mci0_data);
- at32_add_device_usba(0, NULL);
- at32_add_device_lcdc(0, &favr32_lcdc_data, fbmem_start, fbmem_size, 0);
-
- favr32_setup_leds();
-
- favr32_setup_atmel_pwm_bl();
-
- return 0;
-}
-postcore_initcall(favr32_init);
+++ /dev/null
-# Hammerhead customization
-
-if BOARD_HAMMERHEAD
-
-config BOARD_HAMMERHEAD_USB
- bool "Philips ISP116x-hcd USB support"
- help
- This enables USB support for Hammerheads internal ISP116x
- controller from Philips.
-
- Choose 'Y' here if you want to have your board USB driven.
-
-config BOARD_HAMMERHEAD_LCD
- bool "Atmel AT91/AT32 LCD support"
- help
- This enables LCD support for the Hammerhead board. You may
- also add support for framebuffer devices (AT91/AT32 LCD Controller)
- and framebuffer console support to get the most out of your LCD.
-
- Choose 'Y' here if you have ordered a Corona daugther board and
- want to have support for your Hantronix HDA-351T-LV LCD.
-
-config BOARD_HAMMERHEAD_SND
- bool "Atmel AC97 Sound support"
- help
- This enables Sound support for the Hammerhead board. You may
- also go through the ALSA settings to get it working.
-
- Choose 'Y' here if you have ordered a Corona daugther board and
- want to make your board funky.
-
-config BOARD_HAMMERHEAD_FPGA
- bool "Hammerhead FPGA Support"
- default y
- help
- This adds support for the Cyclone III FPGA from Altera
- found on Miromico's Hammerhead board.
-
- Choose 'Y' here if you want to have FPGA support enabled.
- You will have to choose the "Hammerhead FPGA Device Support" in
- Device Drivers->Misc to be able to use FPGA functionality.
-
-endif # BOARD_ATNGW100
+++ /dev/null
-obj-y += setup.o flash.o
+++ /dev/null
-/*
- * Hammerhead board-specific flash initialization
- *
- * Copyright (C) 2008 Miromico AG
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/mtd/mtd.h>
-#include <linux/mtd/partitions.h>
-#include <linux/mtd/physmap.h>
-#include <linux/usb/isp116x.h>
-#include <linux/dma-mapping.h>
-#include <linux/delay.h>
-
-#include <mach/portmux.h>
-#include <mach/at32ap700x.h>
-#include <mach/smc.h>
-
-#include "../../mach-at32ap/clock.h"
-#include "flash.h"
-
-
-#define HAMMERHEAD_USB_PERIPH_GCLK0 0x40000000
-#define HAMMERHEAD_USB_PERIPH_CS2 0x02000000
-#define HAMMERHEAD_USB_PERIPH_EXTINT0 0x02000000
-
-#define HAMMERHEAD_FPGA_PERIPH_MOSI 0x00000002
-#define HAMMERHEAD_FPGA_PERIPH_SCK 0x00000020
-#define HAMMERHEAD_FPGA_PERIPH_EXTINT3 0x10000000
-
-static struct smc_timing flash_timing __initdata = {
- .ncs_read_setup = 0,
- .nrd_setup = 40,
- .ncs_write_setup = 0,
- .nwe_setup = 10,
-
- .ncs_read_pulse = 80,
- .nrd_pulse = 40,
- .ncs_write_pulse = 65,
- .nwe_pulse = 55,
-
- .read_cycle = 120,
- .write_cycle = 120,
-};
-
-static struct smc_config flash_config __initdata = {
- .bus_width = 2,
- .nrd_controlled = 1,
- .nwe_controlled = 1,
- .byte_write = 1,
-};
-
-static struct mtd_partition flash_parts[] = {
- {
- .name = "u-boot",
- .offset = 0x00000000,
- .size = 0x00020000, /* 128 KiB */
- .mask_flags = MTD_WRITEABLE,
- },
- {
- .name = "root",
- .offset = 0x00020000,
- .size = 0x007d0000,
- },
- {
- .name = "env",
- .offset = 0x007f0000,
- .size = 0x00010000,
- .mask_flags = MTD_WRITEABLE,
- },
-};
-
-static struct physmap_flash_data flash_data = {
- .width = 2,
- .nr_parts = ARRAY_SIZE(flash_parts),
- .parts = flash_parts,
-};
-
-static struct resource flash_resource = {
- .start = 0x00000000,
- .end = 0x007fffff,
- .flags = IORESOURCE_MEM,
-};
-
-static struct platform_device flash_device = {
- .name = "physmap-flash",
- .id = 0,
- .resource = &flash_resource,
- .num_resources = 1,
- .dev = { .platform_data = &flash_data, },
-};
-
-#ifdef CONFIG_BOARD_HAMMERHEAD_USB
-
-static struct smc_timing isp1160_timing __initdata = {
- .ncs_read_setup = 75,
- .nrd_setup = 75,
- .ncs_write_setup = 75,
- .nwe_setup = 75,
-
-
- /* We use conservative timing settings, as the minimal settings aren't
- stable. There may be room for tweaking. */
- .ncs_read_pulse = 75, /* min. 33ns */
- .nrd_pulse = 75, /* min. 33ns */
- .ncs_write_pulse = 75, /* min. 26ns */
- .nwe_pulse = 75, /* min. 26ns */
-
- .read_cycle = 225, /* min. 143ns */
- .write_cycle = 225, /* min. 136ns */
-};
-
-static struct smc_config isp1160_config __initdata = {
- .bus_width = 2,
- .nrd_controlled = 1,
- .nwe_controlled = 1,
- .byte_write = 0,
-};
-
-/*
- * The platform delay function is only used to enforce the strange
- * read to write delay. This can not be configured in the SMC. All other
- * timings are controlled by the SMC (see timings obove)
- * So in isp116x-hcd.c we should comment out USE_PLATFORM_DELAY
- */
-void isp116x_delay(struct device *dev, int delay)
-{
- if (delay > 150)
- ndelay(delay - 150);
-}
-
-static struct isp116x_platform_data isp1160_data = {
- .sel15Kres = 1, /* use internal downstream resistors */
- .oc_enable = 0, /* external overcurrent detection */
- .int_edge_triggered = 0, /* interrupt is level triggered */
- .int_act_high = 0, /* interrupt is active low */
- .delay = isp116x_delay, /* platform delay function */
-};
-
-static struct resource isp1160_resource[] = {
- {
- .start = 0x08000000,
- .end = 0x08000001,
- .flags = IORESOURCE_MEM,
- },
- {
- .start = 0x08000002,
- .end = 0x08000003,
- .flags = IORESOURCE_MEM,
- },
- {
- .start = 64,
- .flags = IORESOURCE_IRQ,
- },
-};
-
-static struct platform_device isp1160_device = {
- .name = "isp116x-hcd",
- .id = 0,
- .resource = isp1160_resource,
- .num_resources = 3,
- .dev = {
- .platform_data = &isp1160_data,
- },
-};
-#endif
-
-#ifdef CONFIG_BOARD_HAMMERHEAD_USB
-static int __init hammerhead_usbh_init(void)
-{
- struct clk *gclk;
- struct clk *osc;
-
- int ret;
-
- /* setup smc for usbh */
- smc_set_timing(&isp1160_config, &isp1160_timing);
- ret = smc_set_configuration(2, &isp1160_config);
-
- if (ret < 0) {
- printk(KERN_ERR
- "hammerhead: failed to set ISP1160 USBH timing\n");
- return ret;
- }
-
- /* setup gclk0 to run from osc1 */
- gclk = clk_get(NULL, "gclk0");
- if (IS_ERR(gclk)) {
- ret = PTR_ERR(gclk);
- goto err_gclk;
- }
-
- osc = clk_get(NULL, "osc1");
- if (IS_ERR(osc)) {
- ret = PTR_ERR(osc);
- goto err_osc;
- }
-
- ret = clk_set_parent(gclk, osc);
- if (ret < 0) {
- pr_debug("hammerhead: failed to set osc1 for USBH clock\n");
- goto err_set_clk;
- }
-
- /* set clock to 6MHz */
- clk_set_rate(gclk, 6000000);
-
- /* and enable */
- clk_enable(gclk);
-
- /* select GCLK0 peripheral function */
- at32_select_periph(GPIO_PIOA_BASE, HAMMERHEAD_USB_PERIPH_GCLK0,
- GPIO_PERIPH_A, 0);
-
- /* enable CS2 peripheral function */
- at32_select_periph(GPIO_PIOE_BASE, HAMMERHEAD_USB_PERIPH_CS2,
- GPIO_PERIPH_A, 0);
-
- /* H_WAKEUP must be driven low */
- at32_select_gpio(GPIO_PIN_PA(8), AT32_GPIOF_OUTPUT);
-
- /* Select EXTINT0 for PB25 */
- at32_select_periph(GPIO_PIOB_BASE, HAMMERHEAD_USB_PERIPH_EXTINT0,
- GPIO_PERIPH_A, 0);
-
- /* register usbh device driver */
- platform_device_register(&isp1160_device);
-
- err_set_clk:
- clk_put(osc);
- err_osc:
- clk_put(gclk);
- err_gclk:
- return ret;
-}
-#endif
-
-#ifdef CONFIG_BOARD_HAMMERHEAD_FPGA
-static struct smc_timing fpga_timing __initdata = {
- .ncs_read_setup = 16,
- .nrd_setup = 32,
- .ncs_read_pulse = 48,
- .nrd_pulse = 32,
- .read_cycle = 64,
-
- .ncs_write_setup = 16,
- .nwe_setup = 16,
- .ncs_write_pulse = 32,
- .nwe_pulse = 32,
- .write_cycle = 64,
-};
-
-static struct smc_config fpga_config __initdata = {
- .bus_width = 4,
- .nrd_controlled = 1,
- .nwe_controlled = 1,
- .byte_write = 0,
-};
-
-static struct resource hh_fpga0_resource[] = {
- {
- .start = 0xffe00400,
- .end = 0xffe00400 + 0x3ff,
- .flags = IORESOURCE_MEM,
- },
- {
- .start = 4,
- .end = 4,
- .flags = IORESOURCE_IRQ,
- },
- {
- .start = 0x0c000000,
- .end = 0x0c000100,
- .flags = IORESOURCE_MEM,
- },
- {
- .start = 67,
- .end = 67,
- .flags = IORESOURCE_IRQ,
- },
-};
-
-static u64 hh_fpga0_dma_mask = DMA_BIT_MASK(32);
-static struct platform_device hh_fpga0_device = {
- .name = "hh_fpga",
- .id = 0,
- .dev = {
- .dma_mask = &hh_fpga0_dma_mask,
- .coherent_dma_mask = DMA_BIT_MASK(32),
- },
- .resource = hh_fpga0_resource,
- .num_resources = ARRAY_SIZE(hh_fpga0_resource),
-};
-
-static struct clk hh_fpga0_spi_clk = {
- .name = "spi_clk",
- .dev = &hh_fpga0_device.dev,
- .mode = pba_clk_mode,
- .get_rate = pba_clk_get_rate,
- .index = 1,
-};
-
-struct platform_device *__init at32_add_device_hh_fpga(void)
-{
- /* Select peripheral functionallity for SPI SCK and MOSI */
- at32_select_periph(GPIO_PIOB_BASE, HAMMERHEAD_FPGA_PERIPH_SCK,
- GPIO_PERIPH_B, 0);
- at32_select_periph(GPIO_PIOB_BASE, HAMMERHEAD_FPGA_PERIPH_MOSI,
- GPIO_PERIPH_B, 0);
-
- /* reserve all other needed gpio
- * We have on board pull ups, so there is no need
- * to enable gpio pull ups */
- /* INIT_DONE (input) */
- at32_select_gpio(GPIO_PIN_PB(0), 0);
-
- /* nSTATUS (input) */
- at32_select_gpio(GPIO_PIN_PB(2), 0);
-
- /* nCONFIG (output, low) */
- at32_select_gpio(GPIO_PIN_PB(3), AT32_GPIOF_OUTPUT);
-
- /* CONF_DONE (input) */
- at32_select_gpio(GPIO_PIN_PB(4), 0);
-
- /* Select EXTINT3 for PB28 (Interrupt from FPGA) */
- at32_select_periph(GPIO_PIOB_BASE, HAMMERHEAD_FPGA_PERIPH_EXTINT3,
- GPIO_PERIPH_A, 0);
-
- /* Get our parent clock */
- hh_fpga0_spi_clk.parent = clk_get(NULL, "pba");
- clk_put(hh_fpga0_spi_clk.parent);
-
- /* Register clock in at32 clock tree */
- at32_clk_register(&hh_fpga0_spi_clk);
-
- platform_device_register(&hh_fpga0_device);
- return &hh_fpga0_device;
-}
-#endif
-
-/* This needs to be called after the SMC has been initialized */
-static int __init hammerhead_flash_init(void)
-{
- int ret;
-
- smc_set_timing(&flash_config, &flash_timing);
- ret = smc_set_configuration(0, &flash_config);
-
- if (ret < 0) {
- printk(KERN_ERR "hammerhead: failed to set NOR flash timing\n");
- return ret;
- }
-
- platform_device_register(&flash_device);
-
-#ifdef CONFIG_BOARD_HAMMERHEAD_USB
- hammerhead_usbh_init();
-#endif
-
-#ifdef CONFIG_BOARD_HAMMERHEAD_FPGA
- /* Setup SMC for FPGA interface */
- smc_set_timing(&fpga_config, &fpga_timing);
- ret = smc_set_configuration(3, &fpga_config);
-#endif
-
-
- if (ret < 0) {
- printk(KERN_ERR "hammerhead: failed to set FPGA timing\n");
- return ret;
- }
-
- return 0;
-}
-
-device_initcall(hammerhead_flash_init);
+++ /dev/null
-#ifndef __BOARDS_HAMMERHEAD_FLASH_H
-#define __BOARDS_HAMMERHEAD_FLASH_H
-
-struct platform_device *at32_add_device_hh_fpga(void);
-
-#endif /* __BOARDS_HAMMERHEAD_FLASH_H */
+++ /dev/null
-/*
- * Board-specific setup code for the Miromico Hammerhead board
- *
- * Copyright (C) 2008 Miromico AG
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/atmel-mci.h>
-#include <linux/clk.h>
-#include <linux/fb.h>
-#include <linux/etherdevice.h>
-#include <linux/i2c.h>
-#include <linux/i2c-gpio.h>
-#include <linux/init.h>
-#include <linux/linkage.h>
-#include <linux/platform_device.h>
-#include <linux/types.h>
-#include <linux/spi/spi.h>
-
-#include <video/atmel_lcdc.h>
-
-#include <linux/io.h>
-#include <asm/setup.h>
-
-#include <mach/at32ap700x.h>
-#include <mach/board.h>
-#include <mach/init.h>
-#include <mach/portmux.h>
-
-#include <sound/atmel-ac97c.h>
-
-#include "../../mach-at32ap/clock.h"
-#include "flash.h"
-
-/* Oscillator frequencies. These are board-specific */
-unsigned long at32_board_osc_rates[3] = {
- [0] = 32768, /* 32.768 kHz on RTC osc */
- [1] = 25000000, /* 25MHz on osc0 */
- [2] = 12000000, /* 12 MHz on osc1 */
-};
-
-/* Initialized by bootloader-specific startup code. */
-struct tag *bootloader_tags __initdata;
-
-#ifdef CONFIG_BOARD_HAMMERHEAD_LCD
-static struct fb_videomode __initdata hda350tlv_modes[] = {
- {
- .name = "320x240 @ 75",
- .refresh = 75,
- .xres = 320,
- .yres = 240,
- .pixclock = KHZ2PICOS(6891),
-
- .left_margin = 48,
- .right_margin = 18,
- .upper_margin = 18,
- .lower_margin = 4,
- .hsync_len = 20,
- .vsync_len = 2,
-
- .sync = 0,
- .vmode = FB_VMODE_NONINTERLACED,
- },
-};
-
-static struct fb_monspecs __initdata hammerhead_hda350t_monspecs = {
- .manufacturer = "HAN",
- .monitor = "HDA350T-LV",
- .modedb = hda350tlv_modes,
- .modedb_len = ARRAY_SIZE(hda350tlv_modes),
- .hfmin = 14900,
- .hfmax = 22350,
- .vfmin = 60,
- .vfmax = 90,
- .dclkmax = 10000000,
-};
-
-struct atmel_lcdfb_pdata __initdata hammerhead_lcdc_data = {
- .default_bpp = 24,
- .default_dmacon = ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
- .default_lcdcon2 = (ATMEL_LCDC_DISTYPE_TFT
- | ATMEL_LCDC_INVCLK
- | ATMEL_LCDC_CLKMOD_ALWAYSACTIVE
- | ATMEL_LCDC_MEMOR_BIG),
- .default_monspecs = &hammerhead_hda350t_monspecs,
- .guard_time = 2,
-};
-#endif
-
-static struct mci_platform_data __initdata mci0_data = {
- .slot[0] = {
- .bus_width = 4,
- .detect_pin = -ENODEV,
- .wp_pin = -ENODEV,
- },
-};
-
-struct eth_addr {
- u8 addr[6];
-};
-
-static struct eth_addr __initdata hw_addr[1];
-static struct macb_platform_data __initdata eth_data[1];
-
-/*
- * The next two functions should go away as the boot loader is
- * supposed to initialize the macb address registers with a valid
- * ethernet address. But we need to keep it around for a while until
- * we can be reasonably sure the boot loader does this.
- *
- * The phy_id is ignored as the driver will probe for it.
- */
-static int __init parse_tag_ethernet(struct tag *tag)
-{
- int i = tag->u.ethernet.mac_index;
-
- if (i < ARRAY_SIZE(hw_addr))
- memcpy(hw_addr[i].addr, tag->u.ethernet.hw_address,
- sizeof(hw_addr[i].addr));
-
- return 0;
-}
-__tagtable(ATAG_ETHERNET, parse_tag_ethernet);
-
-static void __init set_hw_addr(struct platform_device *pdev)
-{
- struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- const u8 *addr;
- void __iomem *regs;
- struct clk *pclk;
-
- if (!res)
- return;
-
- if (pdev->id >= ARRAY_SIZE(hw_addr))
- return;
-
- addr = hw_addr[pdev->id].addr;
-
- if (!is_valid_ether_addr(addr))
- return;
-
- /*
- * Since this is board-specific code, we'll cheat and use the
- * physical address directly as we happen to know that it's
- * the same as the virtual address.
- */
- regs = (void __iomem __force *)res->start;
- pclk = clk_get(&pdev->dev, "pclk");
-
- if (IS_ERR(pclk))
- return;
-
- clk_enable(pclk);
-
- __raw_writel((addr[3] << 24) | (addr[2] << 16) | (addr[1] << 8) |
- addr[0], regs + 0x98);
- __raw_writel((addr[5] << 8) | addr[4], regs + 0x9c);
-
- clk_disable(pclk);
- clk_put(pclk);
-}
-
-void __init setup_board(void)
-{
- at32_map_usart(1, 0, 0); /* USART 1: /dev/ttyS0, DB9 */
- at32_setup_serial_console(0);
-}
-
-static struct i2c_gpio_platform_data i2c_gpio_data = {
- .sda_pin = GPIO_PIN_PA(6),
- .scl_pin = GPIO_PIN_PA(7),
- .sda_is_open_drain = 1,
- .scl_is_open_drain = 1,
- .udelay = 2, /* close to 100 kHz */
-};
-
-static struct platform_device i2c_gpio_device = {
- .name = "i2c-gpio",
- .id = 0,
- .dev = { .platform_data = &i2c_gpio_data, },
-};
-
-static struct i2c_board_info __initdata i2c_info[] = {};
-
-#ifdef CONFIG_BOARD_HAMMERHEAD_SND
-static struct ac97c_platform_data ac97c_data = {
- .reset_pin = GPIO_PIN_PA(16),
-};
-#endif
-
-static int __init hammerhead_init(void)
-{
- /*
- * Hammerhead uses 32-bit SDRAM interface. Reserve the
- * SDRAM-specific pins so that nobody messes with them.
- */
- at32_reserve_pin(GPIO_PIOE_BASE, ATMEL_EBI_PE_DATA_ALL);
-
- at32_add_device_usart(0);
-
- /* Reserve PB29 (GCLK3). This pin is used as clock source
- * for ETH PHY (25MHz). GCLK3 setup is done by U-Boot.
- */
- at32_reserve_pin(GPIO_PIOB_BASE, (1<<29));
-
- /*
- * Hammerhead uses only one ethernet port, so we don't set
- * address of second port
- */
- set_hw_addr(at32_add_device_eth(0, ð_data[0]));
-
-#ifdef CONFIG_BOARD_HAMMERHEAD_FPGA
- at32_add_device_hh_fpga();
-#endif
- at32_add_device_mci(0, &mci0_data);
-
-#ifdef CONFIG_BOARD_HAMMERHEAD_USB
- at32_add_device_usba(0, NULL);
-#endif
-#ifdef CONFIG_BOARD_HAMMERHEAD_LCD
- at32_add_device_lcdc(0, &hammerhead_lcdc_data, fbmem_start,
- fbmem_size, ATMEL_LCDC_PRI_24BIT);
-#endif
-
- at32_select_gpio(i2c_gpio_data.sda_pin,
- AT32_GPIOF_MULTIDRV | AT32_GPIOF_OUTPUT |
- AT32_GPIOF_HIGH);
- at32_select_gpio(i2c_gpio_data.scl_pin,
- AT32_GPIOF_MULTIDRV | AT32_GPIOF_OUTPUT |
- AT32_GPIOF_HIGH);
- platform_device_register(&i2c_gpio_device);
- i2c_register_board_info(0, i2c_info, ARRAY_SIZE(i2c_info));
-
-#ifdef CONFIG_BOARD_HAMMERHEAD_SND
- at32_add_device_ac97c(0, &ac97c_data, AC97C_BOTH);
-#endif
-
- /* Select the Touchscreen interrupt pin mode */
- at32_select_periph(GPIO_PIOB_BASE, 0x08000000, GPIO_PERIPH_A, 0);
-
- return 0;
-}
-
-postcore_initcall(hammerhead_init);
+++ /dev/null
-# Merisc customization
-
-if BOARD_MERISC
-
-endif # BOARD_MERISC
+++ /dev/null
-obj-y += setup.o flash.o display.o merisc_sysfs.o
+++ /dev/null
-/*
- * Display setup code for the Merisc board
- *
- * Copyright (C) 2008 Martinsson Elektronik AB
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/fb.h>
-#include <video/atmel_lcdc.h>
-#include <asm/setup.h>
-#include <mach/board.h>
-#include "merisc.h"
-
-static struct fb_videomode merisc_fb_videomode[] = {
- {
- .refresh = 44,
- .xres = 640,
- .yres = 480,
- .left_margin = 96,
- .right_margin = 96,
- .upper_margin = 34,
- .lower_margin = 8,
- .hsync_len = 64,
- .vsync_len = 64,
- .name = "640x480 @ 44",
- .pixclock = KHZ2PICOS(25180),
- .sync = 0,
- .vmode = FB_VMODE_NONINTERLACED,
- },
-};
-
-static struct fb_monspecs merisc_fb_monspecs = {
- .manufacturer = "Kyo",
- .monitor = "TCG075VG2AD",
- .modedb = merisc_fb_videomode,
- .modedb_len = ARRAY_SIZE(merisc_fb_videomode),
- .hfmin = 30000,
- .hfmax = 33333,
- .vfmin = 60,
- .vfmax = 90,
- .dclkmax = 30000000,
-};
-
-struct atmel_lcdfb_pdata merisc_lcdc_data = {
- .default_bpp = 24,
- .default_dmacon = ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
- .default_lcdcon2 = (ATMEL_LCDC_DISTYPE_TFT
- | ATMEL_LCDC_CLKMOD_ALWAYSACTIVE
- | ATMEL_LCDC_MEMOR_BIG),
- .default_monspecs = &merisc_fb_monspecs,
- .guard_time = 2,
-};
-
-static int __init merisc_display_init(void)
-{
- at32_add_device_lcdc(0, &merisc_lcdc_data, fbmem_start,
- fbmem_size, 0);
-
- return 0;
-}
-device_initcall(merisc_display_init);
+++ /dev/null
-/*
- * Merisc board-specific flash initialization
- *
- * Copyright (C) 2008 Martinsson Elektronik AB
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/mtd/mtd.h>
-#include <linux/mtd/partitions.h>
-#include <linux/mtd/physmap.h>
-#include <mach/smc.h>
-
-/* Will be translated to units of 14.3 ns, rounded up */
-static struct smc_timing flash_timing __initdata = {
- .ncs_read_setup = 1 * 14,
- .nrd_setup = 5 * 14,
- .ncs_write_setup = 1 * 14,
- .nwe_setup = 2 * 14,
-
- .ncs_read_pulse = 12 * 14,
- .nrd_pulse = 7 * 14,
- .ncs_write_pulse = 8 * 14,
- .nwe_pulse = 4 * 14,
-
- .read_cycle = 14 * 14,
- .write_cycle = 10 * 14,
-};
-
-static struct smc_config flash_config __initdata = {
- .bus_width = 2,
- .nrd_controlled = 1,
- .nwe_controlled = 1,
- .byte_write = 1,
- .tdf_cycles = 3,
-};
-
-static struct mtd_partition flash_0_parts[] = {
- {
- .name = "boot",
- .offset = 0x00000000,
- .size = 0x00060000,
- .mask_flags = 0,
- },
- {
- .name = "kernel",
- .offset = 0x00060000,
- .size = 0x00200000,
- .mask_flags = 0,
- },
- {
- .name = "root",
- .offset = 0x00260000,
- .size = MTDPART_SIZ_FULL,
- .mask_flags = 0,
- },
-};
-
-static struct mtd_partition flash_1_parts[] = {
- {
- .name = "2ndflash",
- .offset = 0x00000000,
- .size = MTDPART_SIZ_FULL,
- .mask_flags = 0,
- },
-};
-
-static struct physmap_flash_data flash_data[] = {
- {
- .width = 2,
- .nr_parts = ARRAY_SIZE(flash_0_parts),
- .parts = flash_0_parts,
- },
- {
- .width = 2,
- .nr_parts = ARRAY_SIZE(flash_1_parts),
- .parts = flash_1_parts,
- }
-};
-
-static struct resource flash_resource[] = {
- {
- .start = 0x00000000,
- .end = 0x03ffffff,
- .flags = IORESOURCE_MEM,
- },
- {
- .start = 0x04000000,
- .end = 0x07ffffff,
- .flags = IORESOURCE_MEM,
- },
-};
-
-static struct platform_device flash_device[] = {
- {
- .name = "physmap-flash",
- .id = 0,
- .resource = &flash_resource[0],
- .num_resources = 1,
- .dev = {
- .platform_data = &flash_data[0],
- },
- },
- {
- .name = "physmap-flash",
- .id = 1,
- .resource = &flash_resource[1],
- .num_resources = 1,
- .dev = {
- .platform_data = &flash_data[1],
- },
- },
-};
-
-static int __init merisc_flash_init(void)
-{
- int ret;
- smc_set_timing(&flash_config, &flash_timing);
-
- ret = smc_set_configuration(0, &flash_config);
- if (ret < 0) {
- printk(KERN_ERR "Merisc: failed to set NOR flash timing #0\n");
- return ret;
- }
-
- ret = smc_set_configuration(4, &flash_config);
- if (ret < 0) {
- printk(KERN_ERR "Merisc: failed to set NOR flash timing #1\n");
- return ret;
- }
-
- platform_device_register(&flash_device[0]);
- platform_device_register(&flash_device[1]);
- return 0;
-}
-device_initcall(merisc_flash_init);
+++ /dev/null
-/*
- * Merisc exports
- *
- * Copyright (C) 2008 Martinsson Elektronik AB
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ARCH_AVR32_BOARDS_MERISC_MERISC_H
-#define __ARCH_AVR32_BOARDS_MERISC_MERISC_H
-
-const char *merisc_revision(void);
-const char *merisc_model(void);
-
-extern struct class merisc_class;
-
-#endif /* __ARCH_AVR32_BOARDS_MERISC_MERISC_H */
+++ /dev/null
-/*
- * Merisc sysfs exports
- *
- * Copyright (C) 2008 Martinsson Elektronik AB
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/list.h>
-#include <linux/spinlock.h>
-#include <linux/device.h>
-#include <linux/timer.h>
-#include <linux/err.h>
-#include <linux/ctype.h>
-#include "merisc.h"
-
-static ssize_t merisc_model_show(struct class *class, char *buf)
-{
- ssize_t ret = 0;
-
- sprintf(buf, "%s\n", merisc_model());
- ret = strlen(buf) + 1;
-
- return ret;
-}
-
-static ssize_t merisc_revision_show(struct class *class, char *buf)
-{
- ssize_t ret = 0;
-
- sprintf(buf, "%s\n", merisc_revision());
- ret = strlen(buf) + 1;
-
- return ret;
-}
-
-static struct class_attribute merisc_class_attrs[] = {
- __ATTR(model, S_IRUGO, merisc_model_show, NULL),
- __ATTR(revision, S_IRUGO, merisc_revision_show, NULL),
- __ATTR_NULL,
-};
-
-struct class merisc_class = {
- .name = "merisc",
- .owner = THIS_MODULE,
- .class_attrs = merisc_class_attrs,
-};
-
-static int __init merisc_sysfs_init(void)
-{
- int status;
-
- status = class_register(&merisc_class);
- if (status < 0)
- return status;
-
- return 0;
-}
-
-postcore_initcall(merisc_sysfs_init);
+++ /dev/null
-/*
- * Board-specific setup code for the Merisc
- *
- * Copyright (C) 2008 Martinsson Elektronik AB
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/clk.h>
-#include <linux/etherdevice.h>
-#include <linux/i2c.h>
-#include <linux/i2c-gpio.h>
-#include <linux/gpio.h>
-#include <linux/init.h>
-#include <linux/linkage.h>
-#include <linux/platform_device.h>
-#include <linux/types.h>
-#include <linux/leds.h>
-#include <linux/spi/spi.h>
-#include <linux/spi/ads7846.h>
-#include <linux/irq.h>
-#include <linux/fb.h>
-#include <linux/atmel-mci.h>
-#include <linux/pwm.h>
-#include <linux/leds_pwm.h>
-
-#include <asm/io.h>
-#include <asm/setup.h>
-
-#include <mach/at32ap700x.h>
-#include <mach/board.h>
-#include <mach/init.h>
-#include <mach/portmux.h>
-
-#include "merisc.h"
-
-/* Holds the autodetected board model and revision */
-static int merisc_board_id;
-
-/* Initialized by bootloader-specific startup code. */
-struct tag *bootloader_tags __initdata;
-
-/* Oscillator frequencies. These are board specific */
-unsigned long at32_board_osc_rates[3] = {
- [0] = 32768, /* 32.768 kHz on RTC osc */
- [1] = 20000000, /* 20 MHz on osc0 */
- [2] = 12000000, /* 12 MHz on osc1 */
-};
-
-struct eth_addr {
- u8 addr[6];
-};
-
-static struct eth_addr __initdata hw_addr[2];
-static struct macb_platform_data __initdata eth_data[2];
-
-static int ads7846_get_pendown_state_PB26(void)
-{
- return !gpio_get_value(GPIO_PIN_PB(26));
-}
-
-static int ads7846_get_pendown_state_PB28(void)
-{
- return !gpio_get_value(GPIO_PIN_PB(28));
-}
-
-static struct ads7846_platform_data __initdata ads7846_data = {
- .model = 7846,
- .vref_delay_usecs = 100,
- .vref_mv = 0,
- .keep_vref_on = 0,
- .settle_delay_usecs = 150,
- .penirq_recheck_delay_usecs = 1,
- .x_plate_ohms = 800,
- .debounce_rep = 4,
- .debounce_max = 10,
- .debounce_tol = 50,
- .get_pendown_state = ads7846_get_pendown_state_PB26,
- .filter_init = NULL,
- .filter = NULL,
- .filter_cleanup = NULL,
-};
-
-static struct spi_board_info __initdata spi0_board_info[] = {
- {
- .modalias = "ads7846",
- .max_speed_hz = 3250000,
- .chip_select = 0,
- .bus_num = 0,
- .platform_data = &ads7846_data,
- .mode = SPI_MODE_0,
- },
-};
-
-static struct mci_platform_data __initdata mci0_data = {
- .slot[0] = {
- .bus_width = 4,
- .detect_pin = GPIO_PIN_PE(19),
- .wp_pin = GPIO_PIN_PE(20),
- .detect_is_active_high = true,
- },
-};
-
-static int __init parse_tag_ethernet(struct tag *tag)
-{
- int i;
-
- i = tag->u.ethernet.mac_index;
- if (i < ARRAY_SIZE(hw_addr)) {
- memcpy(hw_addr[i].addr, tag->u.ethernet.hw_address,
- sizeof(hw_addr[i].addr));
- }
-
- return 0;
-}
-__tagtable(ATAG_ETHERNET, parse_tag_ethernet);
-
-static void __init set_hw_addr(struct platform_device *pdev)
-{
- struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- const u8 *addr;
- void __iomem *regs;
- struct clk *pclk;
-
- if (!res)
- return;
-
- if (pdev->id >= ARRAY_SIZE(hw_addr))
- return;
-
- addr = hw_addr[pdev->id].addr;
- if (!is_valid_ether_addr(addr))
- return;
-
- regs = (void __iomem __force *)res->start;
- pclk = clk_get(&pdev->dev, "pclk");
- if (IS_ERR(pclk))
- return;
-
- clk_enable(pclk);
- __raw_writel((addr[3] << 24) | (addr[2] << 16)
- | (addr[1] << 8) | addr[0], regs + 0x98);
- __raw_writel((addr[5] << 8) | addr[4], regs + 0x9c);
- clk_disable(pclk);
- clk_put(pclk);
-}
-
-static struct i2c_gpio_platform_data i2c_gpio_data = {
- .sda_pin = GPIO_PIN_PA(6),
- .scl_pin = GPIO_PIN_PA(7),
- .sda_is_open_drain = 1,
- .scl_is_open_drain = 1,
- .udelay = 2,
-};
-
-static struct platform_device i2c_gpio_device = {
- .name = "i2c-gpio",
- .id = 0,
- .dev = {
- .platform_data = &i2c_gpio_data,
- },
-};
-
-static struct i2c_board_info __initdata i2c_info[] = {
- {
- I2C_BOARD_INFO("pcf8563", 0x51)
- },
-};
-
-#if IS_ENABLED(CONFIG_LEDS_PWM)
-static struct pwm_lookup pwm_lookup[] = {
- PWM_LOOKUP("at91sam9rl-pwm", 0, "leds_pwm", "backlight",
- 5000, PWM_POLARITY_NORMAL),
-};
-
-static struct led_pwm pwm_leds[] = {
- {
- .name = "backlight",
- .max_brightness = 255,
- },
-};
-
-static struct led_pwm_platform_data pwm_data = {
- .num_leds = ARRAY_SIZE(pwm_leds),
- .leds = pwm_leds,
-};
-
-static struct platform_device leds_pwm = {
- .name = "leds_pwm",
- .id = -1,
- .dev = {
- .platform_data = &pwm_data,
- },
-};
-#endif
-
-const char *merisc_model(void)
-{
- switch (merisc_board_id) {
- case 0:
- case 1:
- return "500-01";
- case 2:
- return "BT";
- default:
- return "Unknown";
- }
-}
-
-const char *merisc_revision(void)
-{
- switch (merisc_board_id) {
- case 0:
- return "B";
- case 1:
- return "D";
- case 2:
- return "A";
- default:
- return "Unknown";
- }
-}
-
-static void detect_merisc_board_id(void)
-{
- /* Board ID pins MUST be set as input or the board may be damaged */
- at32_select_gpio(GPIO_PIN_PA(24), AT32_GPIOF_PULLUP);
- at32_select_gpio(GPIO_PIN_PA(25), AT32_GPIOF_PULLUP);
- at32_select_gpio(GPIO_PIN_PA(26), AT32_GPIOF_PULLUP);
- at32_select_gpio(GPIO_PIN_PA(27), AT32_GPIOF_PULLUP);
-
- merisc_board_id = !gpio_get_value(GPIO_PIN_PA(24)) +
- !gpio_get_value(GPIO_PIN_PA(25)) * 2 +
- !gpio_get_value(GPIO_PIN_PA(26)) * 4 +
- !gpio_get_value(GPIO_PIN_PA(27)) * 8;
-}
-
-void __init setup_board(void)
-{
- at32_map_usart(0, 0, 0);
- at32_map_usart(1, 1, 0);
- at32_map_usart(3, 3, 0);
- at32_setup_serial_console(1);
-}
-
-static int __init merisc_init(void)
-{
- detect_merisc_board_id();
-
- printk(KERN_NOTICE "BOARD: Merisc %s revision %s\n", merisc_model(),
- merisc_revision());
-
- /* Reserve pins for SDRAM */
- at32_reserve_pin(GPIO_PIOE_BASE, ATMEL_EBI_PE_DATA_ALL | (1 << 26));
-
- if (merisc_board_id >= 1)
- at32_map_usart(2, 2, 0);
-
- at32_add_device_usart(0);
- at32_add_device_usart(1);
- if (merisc_board_id >= 1)
- at32_add_device_usart(2);
- at32_add_device_usart(3);
- set_hw_addr(at32_add_device_eth(0, ð_data[0]));
-
- /* ADS7846 PENIRQ */
- if (merisc_board_id == 0) {
- ads7846_data.get_pendown_state = ads7846_get_pendown_state_PB26;
- at32_select_periph(GPIO_PIOB_BASE, 1 << 26,
- GPIO_PERIPH_A, AT32_GPIOF_PULLUP);
- spi0_board_info[0].irq = AT32_EXTINT(1);
- } else {
- ads7846_data.get_pendown_state = ads7846_get_pendown_state_PB28;
- at32_select_periph(GPIO_PIOB_BASE, 1 << 28, GPIO_PERIPH_A,
- AT32_GPIOF_PULLUP);
- spi0_board_info[0].irq = AT32_EXTINT(3);
- }
-
- /* ADS7846 busy pin */
- at32_select_gpio(GPIO_PIN_PA(4), AT32_GPIOF_PULLUP);
-
- at32_add_device_spi(0, spi0_board_info, ARRAY_SIZE(spi0_board_info));
-
- at32_add_device_mci(0, &mci0_data);
-
-#if IS_ENABLED(CONFIG_LEDS_PWM)
- pwm_add_table(pwm_lookup, ARRAY_SIZE(pwm_lookup));
- at32_add_device_pwm((1 << 0) | (1 << 2));
- platform_device_register(&leds_pwm);
-#else
- at32_add_device_pwm((1 << 2));
-#endif
-
- at32_select_gpio(i2c_gpio_data.sda_pin,
- AT32_GPIOF_MULTIDRV | AT32_GPIOF_OUTPUT | AT32_GPIOF_HIGH);
- at32_select_gpio(i2c_gpio_data.scl_pin,
- AT32_GPIOF_MULTIDRV | AT32_GPIOF_OUTPUT | AT32_GPIOF_HIGH);
- platform_device_register(&i2c_gpio_device);
-
- i2c_register_board_info(0, i2c_info, ARRAY_SIZE(i2c_info));
-
- return 0;
-}
-postcore_initcall(merisc_init);
+++ /dev/null
-obj-y += setup.o flash.o
+++ /dev/null
-/*
- * MIMC200 board-specific flash initialization
- *
- * Copyright (C) 2008 Mercury IMC Ltd
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/mtd/mtd.h>
-#include <linux/mtd/partitions.h>
-#include <linux/mtd/physmap.h>
-
-#include <mach/smc.h>
-
-static struct smc_timing flash_timing __initdata = {
- .ncs_read_setup = 0,
- .nrd_setup = 15,
- .ncs_write_setup = 0,
- .nwe_setup = 0,
-
- .ncs_read_pulse = 115,
- .nrd_pulse = 110,
- .ncs_write_pulse = 60,
- .nwe_pulse = 60,
-
- .read_cycle = 115,
- .write_cycle = 100,
-};
-
-static struct smc_config flash_config __initdata = {
- .bus_width = 2,
- .nrd_controlled = 1,
- .nwe_controlled = 1,
- .byte_write = 1,
-};
-
-/* system flash definition */
-
-static struct mtd_partition flash_parts_system[] = {
- {
- .name = "u-boot",
- .offset = 0x00000000,
- .size = 0x00020000, /* 128 KiB */
- .mask_flags = MTD_WRITEABLE,
- },
- {
- .name = "root",
- .offset = 0x00020000,
- .size = 0x007c0000,
- },
- {
- .name = "splash",
- .offset = 0x007e0000,
- .size = 0x00010000, /* 64KiB */
- },
- {
- .name = "env",
- .offset = 0x007f0000,
- .size = 0x00010000,
- .mask_flags = MTD_WRITEABLE,
- },
-};
-
-static struct physmap_flash_data flash_system = {
- .width = 2,
- .nr_parts = ARRAY_SIZE(flash_parts_system),
- .parts = flash_parts_system,
-};
-
-static struct resource flash_resource_system = {
- .start = 0x00000000,
- .end = 0x007fffff,
- .flags = IORESOURCE_MEM,
-};
-
-static struct platform_device flash_device_system = {
- .name = "physmap-flash",
- .id = 0,
- .resource = &flash_resource_system,
- .num_resources = 1,
- .dev = {
- .platform_data = &flash_system,
- },
-};
-
-/* data flash definition */
-
-static struct mtd_partition flash_parts_data[] = {
- {
- .name = "data",
- .offset = 0x00000000,
- .size = 0x00800000,
- },
-};
-
-static struct physmap_flash_data flash_data = {
- .width = 2,
- .nr_parts = ARRAY_SIZE(flash_parts_data),
- .parts = flash_parts_data,
-};
-
-static struct resource flash_resource_data = {
- .start = 0x08000000,
- .end = 0x087fffff,
- .flags = IORESOURCE_MEM,
-};
-
-static struct platform_device flash_device_data = {
- .name = "physmap-flash",
- .id = 1,
- .resource = &flash_resource_data,
- .num_resources = 1,
- .dev = {
- .platform_data = &flash_data,
- },
-};
-
-/* This needs to be called after the SMC has been initialized */
-static int __init mimc200_flash_init(void)
-{
- int ret;
-
- smc_set_timing(&flash_config, &flash_timing);
- ret = smc_set_configuration(0, &flash_config);
- if (ret < 0) {
- printk(KERN_ERR "mimc200: failed to set 'System' NOR flash timing\n");
- return ret;
- }
- ret = smc_set_configuration(1, &flash_config);
- if (ret < 0) {
- printk(KERN_ERR "mimc200: failed to set 'Data' NOR flash timing\n");
- return ret;
- }
-
- platform_device_register(&flash_device_system);
- platform_device_register(&flash_device_data);
-
- return 0;
-}
-device_initcall(mimc200_flash_init);
+++ /dev/null
-/*
- * Board-specific setup code for the MIMC200
- *
- * Copyright (C) 2008 Mercury IMC Ltd
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-extern struct atmel_lcdfb_pdata mimc200_lcdc_data;
-
-#include <linux/clk.h>
-#include <linux/etherdevice.h>
-#include <linux/i2c-gpio.h>
-#include <linux/init.h>
-#include <linux/linkage.h>
-#include <linux/platform_device.h>
-#include <linux/types.h>
-#include <linux/leds.h>
-#include <linux/spi/spi.h>
-#include <linux/spi/eeprom.h>
-
-#include <video/atmel_lcdc.h>
-#include <linux/fb.h>
-
-#include <linux/atmel-mci.h>
-#include <linux/io.h>
-#include <asm/setup.h>
-
-#include <mach/at32ap700x.h>
-#include <mach/board.h>
-#include <mach/init.h>
-#include <mach/portmux.h>
-
-/* Oscillator frequencies. These are board-specific */
-unsigned long at32_board_osc_rates[3] = {
- [0] = 32768, /* 32.768 kHz on RTC osc */
- [1] = 10000000, /* 10 MHz on osc0 */
- [2] = 12000000, /* 12 MHz on osc1 */
-};
-
-/* Initialized by bootloader-specific startup code. */
-struct tag *bootloader_tags __initdata;
-
-static struct fb_videomode __initdata pt0434827_modes[] = {
- {
- .name = "480x272 @ 72",
- .refresh = 72,
- .xres = 480, .yres = 272,
- .pixclock = KHZ2PICOS(10000),
-
- .left_margin = 1, .right_margin = 1,
- .upper_margin = 12, .lower_margin = 1,
- .hsync_len = 42, .vsync_len = 1,
-
- .sync = 0,
- .vmode = FB_VMODE_NONINTERLACED,
- },
-};
-
-static struct fb_monspecs __initdata mimc200_default_monspecs = {
- .manufacturer = "PT",
- .monitor = "PT0434827-A401",
- .modedb = pt0434827_modes,
- .modedb_len = ARRAY_SIZE(pt0434827_modes),
- .hfmin = 14820,
- .hfmax = 22230,
- .vfmin = 60,
- .vfmax = 85,
- .dclkmax = 25200000,
-};
-
-struct atmel_lcdfb_pdata __initdata mimc200_lcdc_data = {
- .default_bpp = 16,
- .default_dmacon = ATMEL_LCDC_DMAEN | ATMEL_LCDC_DMA2DEN,
- .default_lcdcon2 = (ATMEL_LCDC_DISTYPE_TFT
- | ATMEL_LCDC_INVCLK
- | ATMEL_LCDC_CLKMOD_ALWAYSACTIVE
- | ATMEL_LCDC_MEMOR_BIG),
- .default_monspecs = &mimc200_default_monspecs,
- .guard_time = 2,
-};
-
-struct eth_addr {
- u8 addr[6];
-};
-static struct eth_addr __initdata hw_addr[2];
-static struct macb_platform_data __initdata eth_data[2];
-
-static struct spi_eeprom eeprom_25lc010 = {
- .name = "25lc010",
- .byte_len = 128,
- .page_size = 16,
- .flags = EE_ADDR1,
-};
-
-static struct spi_board_info spi0_board_info[] __initdata = {
- {
- .modalias = "rtc-ds1390",
- .max_speed_hz = 4000000,
- .chip_select = 2,
- },
- {
- .modalias = "at25",
- .max_speed_hz = 1000000,
- .chip_select = 1,
- .mode = SPI_MODE_3,
- .platform_data = &eeprom_25lc010,
- },
-};
-
-static struct mci_platform_data __initdata mci0_data = {
- .slot[0] = {
- .bus_width = 4,
- .detect_pin = GPIO_PIN_PA(26),
- .wp_pin = GPIO_PIN_PA(27),
- },
-};
-
-/*
- * The next two functions should go away as the boot loader is
- * supposed to initialize the macb address registers with a valid
- * ethernet address. But we need to keep it around for a while until
- * we can be reasonably sure the boot loader does this.
- *
- * The phy_id is ignored as the driver will probe for it.
- */
-static int __init parse_tag_ethernet(struct tag *tag)
-{
- int i;
-
- i = tag->u.ethernet.mac_index;
- if (i < ARRAY_SIZE(hw_addr))
- memcpy(hw_addr[i].addr, tag->u.ethernet.hw_address,
- sizeof(hw_addr[i].addr));
-
- return 0;
-}
-__tagtable(ATAG_ETHERNET, parse_tag_ethernet);
-
-static void __init set_hw_addr(struct platform_device *pdev)
-{
- struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- const u8 *addr;
- void __iomem *regs;
- struct clk *pclk;
-
- if (!res)
- return;
- if (pdev->id >= ARRAY_SIZE(hw_addr))
- return;
-
- addr = hw_addr[pdev->id].addr;
- if (!is_valid_ether_addr(addr))
- return;
-
- /*
- * Since this is board-specific code, we'll cheat and use the
- * physical address directly as we happen to know that it's
- * the same as the virtual address.
- */
- regs = (void __iomem __force *)res->start;
- pclk = clk_get(&pdev->dev, "pclk");
- if (IS_ERR(pclk))
- return;
-
- clk_enable(pclk);
- __raw_writel((addr[3] << 24) | (addr[2] << 16)
- | (addr[1] << 8) | addr[0], regs + 0x98);
- __raw_writel((addr[5] << 8) | addr[4], regs + 0x9c);
- clk_disable(pclk);
- clk_put(pclk);
-}
-
-void __init setup_board(void)
-{
- at32_map_usart(0, 0, 0); /* USART 0: /dev/ttyS0 (TTL --> Altera) */
- at32_map_usart(1, 1, 0); /* USART 1: /dev/ttyS1 (RS232) */
- at32_map_usart(2, 2, 0); /* USART 2: /dev/ttyS2 (RS485) */
- at32_map_usart(3, 3, 0); /* USART 3: /dev/ttyS3 (RS422 Multidrop) */
-}
-
-static struct i2c_gpio_platform_data i2c_gpio_data = {
- .sda_pin = GPIO_PIN_PA(6),
- .scl_pin = GPIO_PIN_PA(7),
- .sda_is_open_drain = 1,
- .scl_is_open_drain = 1,
- .udelay = 2, /* close to 100 kHz */
-};
-
-static struct platform_device i2c_gpio_device = {
- .name = "i2c-gpio",
- .id = 0,
- .dev = {
- .platform_data = &i2c_gpio_data,
- },
-};
-
-static struct i2c_board_info __initdata i2c_info[] = {
-};
-
-static int __init mimc200_init(void)
-{
- /*
- * MIMC200 uses 16-bit SDRAM interface, so we don't need to
- * reserve any pins for it.
- */
-
- at32_add_device_usart(0);
- at32_add_device_usart(1);
- at32_add_device_usart(2);
- at32_add_device_usart(3);
-
- set_hw_addr(at32_add_device_eth(0, ð_data[0]));
- set_hw_addr(at32_add_device_eth(1, ð_data[1]));
-
- at32_add_device_spi(0, spi0_board_info, ARRAY_SIZE(spi0_board_info));
- at32_add_device_mci(0, &mci0_data);
- at32_add_device_usba(0, NULL);
-
- at32_select_periph(GPIO_PIOB_BASE, 1 << 28, 0, AT32_GPIOF_PULLUP);
- at32_select_gpio(i2c_gpio_data.sda_pin,
- AT32_GPIOF_MULTIDRV | AT32_GPIOF_OUTPUT | AT32_GPIOF_HIGH);
- at32_select_gpio(i2c_gpio_data.scl_pin,
- AT32_GPIOF_MULTIDRV | AT32_GPIOF_OUTPUT | AT32_GPIOF_HIGH);
- platform_device_register(&i2c_gpio_device);
- i2c_register_board_info(0, i2c_info, ARRAY_SIZE(i2c_info));
-
- at32_add_device_lcdc(0, &mimc200_lcdc_data,
- fbmem_start, fbmem_size,
- ATMEL_LCDC_CONTROL | ATMEL_LCDC_ALT_CONTROL | ATMEL_LCDC_ALT_24B_DATA);
-
- return 0;
-}
-postcore_initcall(mimc200_init);
+++ /dev/null
-uImage
-uImage.srec
-vmlinux.cso
-sfdwarf.log
+++ /dev/null
-#
-# Copyright (C) 2004-2006 Atmel Corporation
-#
-# This file is subject to the terms and conditions of the GNU General Public
-# License. See the file "COPYING" in the main directory of this archive
-# for more details.
-#
-
-extra-y := vmlinux.bin vmlinux.gz
-
-OBJCOPYFLAGS_vmlinux.bin := -O binary -R .note.gnu.build-id
-$(obj)/vmlinux.bin: vmlinux FORCE
- $(call if_changed,objcopy)
-
-$(obj)/vmlinux.gz: $(obj)/vmlinux.bin FORCE
- $(call if_changed,gzip)
-
-UIMAGE_LOADADDR = $(CONFIG_LOAD_ADDRESS)
-UIMAGE_ENTRYADDR = $(CONFIG_ENTRY_ADDRESS)
-UIMAGE_COMPRESSION = gzip
-
-targets += uImage uImage.srec
-$(obj)/uImage: $(obj)/vmlinux.gz
- $(call if_changed,uimage)
- @echo ' Image $@ is ready'
-
-OBJCOPYFLAGS_uImage.srec := -I binary -O srec
-$(obj)/uImage.srec: $(obj)/uImage
- $(call if_changed,objcopy)
-
-OBJCOPYFLAGS_vmlinux.elf := --change-section-lma .text-0x80000000 \
- --change-section-lma __ex_table-0x80000000 \
- --change-section-lma .rodata-0x80000000 \
- --change-section-lma .data-0x80000000 \
- --change-section-lma .init-0x80000000 \
- --change-section-lma .bss-0x80000000 \
- --change-section-lma __param-0x80000000 \
- --change-section-lma __ksymtab-0x80000000 \
- --change-section-lma __ksymtab_gpl-0x80000000 \
- --change-section-lma __kcrctab-0x80000000 \
- --change-section-lma __kcrctab_gpl-0x80000000 \
- --change-section-lma __ksymtab_strings-0x80000000 \
- --set-start 0xa0000000
-$(obj)/vmlinux.elf: vmlinux FORCE
- $(call if_changed,objcopy)
-
-quiet_cmd_sfdwarf = SFDWARF $@
- cmd_sfdwarf = sfdwarf $< TO $@ GNUAVR IW $(SFDWARF_FLAGS) > $(obj)/sfdwarf.log
-
-$(obj)/vmlinux.cso: $(obj)/vmlinux.elf FORCE
- $(call if_changed,sfdwarf)
-
-install: $(BOOTIMAGE)
- sh $(srctree)/install-kernel.sh $<
-
-# Generated files to be removed upon make clean
-clean-files := vmlinux.elf vmlinux.bin vmlinux.gz uImage uImage.srec
+++ /dev/null
-extra-y := head.o
-
-obj-y := empty.o
+++ /dev/null
-/* Empty file */
+++ /dev/null
-/*
- * Startup code for use with the u-boot bootloader.
- *
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <asm/setup.h>
-#include <asm/thread_info.h>
-#include <asm/sysreg.h>
-
- /*
- * The kernel is loaded where we want it to be and all caches
- * have just been flushed. We get two parameters from u-boot:
- *
- * r12 contains a magic number (ATAG_MAGIC)
- * r11 points to a tag table providing information about
- * the system.
- */
- .section .init.text,"ax"
- .global _start
-_start:
- /* Initialize .bss */
- lddpc r2, bss_start_addr
- lddpc r3, end_addr
- mov r0, 0
- mov r1, 0
-1: st.d r2++, r0
- cp r2, r3
- brlo 1b
-
- /* Initialize status register */
- lddpc r0, init_sr
- mtsr SYSREG_SR, r0
-
- /* Set initial stack pointer */
- lddpc sp, stack_addr
- sub sp, -THREAD_SIZE
-
-#ifdef CONFIG_FRAME_POINTER
- /* Mark last stack frame */
- mov lr, 0
- mov r7, 0
-#endif
-
- /* Check if the boot loader actually provided a tag table */
- lddpc r0, magic_number
- cp.w r12, r0
- brne no_tag_table
-
- /*
- * Save the tag table address for later use. This must be done
- * _after_ .bss has been initialized...
- */
- lddpc r0, tag_table_addr
- st.w r0[0], r11
-
- /* Jump to loader-independent setup code */
- rjmp kernel_entry
-
- .align 2
-magic_number:
- .long ATAG_MAGIC
-tag_table_addr:
- .long bootloader_tags
-bss_start_addr:
- .long __bss_start
-end_addr:
- .long _end
-init_sr:
- .long 0x007f0000 /* Supervisor mode, everything masked */
-stack_addr:
- .long init_thread_union
-panic_addr:
- .long panic
-
-no_tag_table:
- sub r12, pc, (. - 2f)
- /* branch to panic() which can be far away with that construct */
- lddpc pc, panic_addr
-2: .asciz "Boot loader didn't provide correct magic number\n"
+++ /dev/null
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_RELAY=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-CONFIG_BOARD_ATNGW100_MKI=y
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_NMI_DEBUGGING=y
-CONFIG_CPU_FREQ=y
-# CONFIG_CPU_FREQ_STAT is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=y
-CONFIG_NET_KEY=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_MROUTE=y
-CONFIG_IP_PIMSM_V1=y
-CONFIG_SYN_COOKIES=y
-CONFIG_INET_AH=y
-CONFIG_INET_ESP=y
-CONFIG_INET_IPCOMP=y
-# CONFIG_INET_LRO is not set
-CONFIG_IPV6=y
-CONFIG_INET6_AH=y
-CONFIG_INET6_ESP=y
-CONFIG_INET6_IPCOMP=y
-CONFIG_NETFILTER=y
-# CONFIG_NETFILTER_ADVANCED is not set
-CONFIG_NETFILTER_XTABLES=y
-CONFIG_BRIDGE=m
-CONFIG_VLAN_8021Q=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_DATAFLASH=y
-CONFIG_MTD_UBI=y
-CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=m
-CONFIG_ATMEL_TCLIB=y
-CONFIG_NETDEVICES=y
-CONFIG_TUN=m
-CONFIG_MACB=y
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_FILTER=y
-CONFIG_PPP_MPPE=m
-CONFIG_PPPOE=m
-CONFIG_PPP_ASYNC=m
-# CONFIG_INPUT is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-# CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-CONFIG_I2C_GPIO=m
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=m
-CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_USB_GADGET=y
-CONFIG_USB_GADGET_VBUS_DRAW=350
-CONFIG_USB_ZERO=m
-CONFIG_USB_ETH=m
-CONFIG_USB_GADGETFS=m
-CONFIG_USB_MASS_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_USB_CDC_COMPOSITE=m
-CONFIG_MMC=y
-CONFIG_MMC_TEST=m
-CONFIG_MMC_ATMELMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_AT32AP700X=y
-CONFIG_DMADEVICES=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
-CONFIG_EXT4_FS=y
-# CONFIG_DNOTIFY is not set
-CONFIG_FUSE_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_FAT_DEFAULT_CODEPAGE=850
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_UBIFS_FS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NFSD=m
-CONFIG_NFSD_V3=y
-CONFIG_CIFS=m
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_UTF8=m
-CONFIG_DEBUG_FS=y
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
+++ /dev/null
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_RELAY=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-CONFIG_BOARD_ATNGW100_MKI=y
-CONFIG_BOARD_ATNGW100_EVKLCD10X=y
-CONFIG_BOARD_ATNGW100_EVKLCD10X_QVGA=y
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_NMI_DEBUGGING=y
-CONFIG_CPU_FREQ=y
-# CONFIG_CPU_FREQ_STAT is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=y
-CONFIG_NET_KEY=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_MROUTE=y
-CONFIG_IP_PIMSM_V1=y
-CONFIG_SYN_COOKIES=y
-CONFIG_INET_AH=y
-CONFIG_INET_ESP=y
-CONFIG_INET_IPCOMP=y
-# CONFIG_INET_LRO is not set
-CONFIG_IPV6=y
-CONFIG_INET6_AH=y
-CONFIG_INET6_ESP=y
-CONFIG_INET6_IPCOMP=y
-CONFIG_NETFILTER=y
-# CONFIG_NETFILTER_ADVANCED is not set
-CONFIG_NETFILTER_XTABLES=y
-CONFIG_BRIDGE=m
-CONFIG_VLAN_8021Q=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_DATAFLASH=y
-CONFIG_MTD_UBI=y
-CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=m
-CONFIG_ATMEL_TCLIB=y
-CONFIG_NETDEVICES=y
-CONFIG_TUN=m
-CONFIG_MACB=y
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_FILTER=y
-CONFIG_PPP_MPPE=m
-CONFIG_PPPOE=m
-CONFIG_PPP_ASYNC=m
-# CONFIG_INPUT_MOUSEDEV is not set
-CONFIG_INPUT_EVDEV=m
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-CONFIG_INPUT_TOUCHSCREEN=y
-CONFIG_TOUCHSCREEN_WM97XX=m
-# CONFIG_SERIO is not set
-# CONFIG_LEGACY_PTYS is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-CONFIG_I2C_GPIO=m
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=m
-CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_FB=y
-CONFIG_FB_ATMEL=y
-CONFIG_SOUND=y
-CONFIG_SND=y
-CONFIG_SND_MIXER_OSS=m
-CONFIG_SND_PCM_OSS=m
-CONFIG_SND_HRTIMER=y
-# CONFIG_SND_SUPPORT_OLD_API is not set
-# CONFIG_SND_DRIVERS is not set
-CONFIG_SND_ATMEL_AC97C=m
-# CONFIG_SND_SPI is not set
-CONFIG_USB_GADGET=y
-CONFIG_USB_GADGET_VBUS_DRAW=350
-CONFIG_USB_ZERO=m
-CONFIG_USB_ETH=m
-CONFIG_USB_GADGETFS=m
-CONFIG_USB_MASS_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_USB_CDC_COMPOSITE=m
-CONFIG_MMC=y
-CONFIG_MMC_TEST=m
-CONFIG_MMC_ATMELMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_AT32AP700X=y
-CONFIG_DMADEVICES=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
-CONFIG_EXT4_FS=y
-# CONFIG_DNOTIFY is not set
-CONFIG_FUSE_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_FAT_DEFAULT_CODEPAGE=850
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_UBIFS_FS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NFSD=m
-CONFIG_NFSD_V3=y
-CONFIG_CIFS=m
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_UTF8=m
-CONFIG_DEBUG_FS=y
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
+++ /dev/null
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_RELAY=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-CONFIG_BOARD_ATNGW100_MKI=y
-CONFIG_BOARD_ATNGW100_EVKLCD10X=y
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_NMI_DEBUGGING=y
-CONFIG_CPU_FREQ=y
-# CONFIG_CPU_FREQ_STAT is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=y
-CONFIG_NET_KEY=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_MROUTE=y
-CONFIG_IP_PIMSM_V1=y
-CONFIG_SYN_COOKIES=y
-CONFIG_INET_AH=y
-CONFIG_INET_ESP=y
-CONFIG_INET_IPCOMP=y
-# CONFIG_INET_LRO is not set
-CONFIG_IPV6=y
-CONFIG_INET6_AH=y
-CONFIG_INET6_ESP=y
-CONFIG_INET6_IPCOMP=y
-CONFIG_NETFILTER=y
-# CONFIG_NETFILTER_ADVANCED is not set
-CONFIG_NETFILTER_XTABLES=y
-CONFIG_BRIDGE=m
-CONFIG_VLAN_8021Q=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_DATAFLASH=y
-CONFIG_MTD_UBI=y
-CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=m
-CONFIG_ATMEL_TCLIB=y
-CONFIG_NETDEVICES=y
-CONFIG_TUN=m
-CONFIG_MACB=y
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_FILTER=y
-CONFIG_PPP_MPPE=m
-CONFIG_PPPOE=m
-CONFIG_PPP_ASYNC=m
-# CONFIG_INPUT_MOUSEDEV is not set
-CONFIG_INPUT_EVDEV=m
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-CONFIG_INPUT_TOUCHSCREEN=y
-CONFIG_TOUCHSCREEN_WM97XX=m
-# CONFIG_SERIO is not set
-# CONFIG_LEGACY_PTYS is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-CONFIG_I2C_GPIO=m
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=m
-CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_FB=y
-CONFIG_FB_ATMEL=y
-CONFIG_SOUND=y
-CONFIG_SND=y
-CONFIG_SND_MIXER_OSS=m
-CONFIG_SND_PCM_OSS=m
-CONFIG_SND_HRTIMER=y
-# CONFIG_SND_SUPPORT_OLD_API is not set
-# CONFIG_SND_DRIVERS is not set
-CONFIG_SND_ATMEL_AC97C=m
-# CONFIG_SND_SPI is not set
-CONFIG_USB_GADGET=y
-CONFIG_USB_GADGET_VBUS_DRAW=350
-CONFIG_USB_ZERO=m
-CONFIG_USB_ETH=m
-CONFIG_USB_GADGETFS=m
-CONFIG_USB_MASS_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_USB_CDC_COMPOSITE=m
-CONFIG_MMC=y
-CONFIG_MMC_TEST=m
-CONFIG_MMC_ATMELMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_AT32AP700X=y
-CONFIG_DMADEVICES=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
-CONFIG_EXT4_FS=y
-# CONFIG_DNOTIFY is not set
-CONFIG_FUSE_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_FAT_DEFAULT_CODEPAGE=850
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_UBIFS_FS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NFSD=m
-CONFIG_NFSD_V3=y
-CONFIG_CIFS=m
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_UTF8=m
-CONFIG_DEBUG_FS=y
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
+++ /dev/null
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_BSD_PROCESS_ACCT=y
-CONFIG_BSD_PROCESS_ACCT_V3=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_SLUB_DEBUG is not set
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODULE_FORCE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_OWNERSHIP_TRACE is not set
-# CONFIG_SUSPEND is not set
-CONFIG_PM=y
-CONFIG_CPU_FREQ=y
-CONFIG_CPU_FREQ_GOV_POWERSAVE=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_CPU_FREQ_GOV_ONDEMAND=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_SYN_COOKIES=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
-# CONFIG_IPV6 is not set
-CONFIG_BT=m
-CONFIG_BT_RFCOMM=m
-CONFIG_BT_RFCOMM_TTY=y
-CONFIG_BT_HIDP=m
-CONFIG_BT_HCIUART=m
-CONFIG_BT_HCIUART_H4=y
-CONFIG_BT_HCIUART_BCSP=y
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_DATAFLASH=y
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_NETDEVICES=y
-CONFIG_MACB=y
-# CONFIG_INPUT_MOUSEDEV is not set
-CONFIG_INPUT_EVDEV=y
-# CONFIG_KEYBOARD_ATKBD is not set
-CONFIG_KEYBOARD_GPIO=y
-# CONFIG_INPUT_MOUSE is not set
-CONFIG_INPUT_TOUCHSCREEN=y
-CONFIG_TOUCHSCREEN_ADS7846=m
-# CONFIG_SERIO is not set
-CONFIG_VT_HW_CONSOLE_BINDING=y
-# CONFIG_LEGACY_PTYS is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=y
-CONFIG_I2C_CHARDEV=y
-CONFIG_I2C_GPIO=y
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=y
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_FB=y
-CONFIG_FB_ATMEL=y
-CONFIG_LCD_CLASS_DEVICE=y
-CONFIG_SOUND=m
-CONFIG_SND=m
-CONFIG_SND_MIXER_OSS=m
-CONFIG_SND_PCM_OSS=m
-# CONFIG_SND_SUPPORT_OLD_API is not set
-# CONFIG_SND_VERBOSE_PROCFS is not set
-CONFIG_SND_ATMEL_AC97C=m
-# CONFIG_SND_SPI is not set
-CONFIG_USB_GADGET=m
-CONFIG_USB_GADGET_DEBUG_FILES=y
-CONFIG_USB_MASS_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_MMC=y
-CONFIG_MMC_ATMELMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=y
-CONFIG_LEDS_PWM=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_S35390A=m
-CONFIG_RTC_DRV_AT32AP700X=m
-CONFIG_DMADEVICES=y
-CONFIG_UIO=y
-CONFIG_PWM=y
-CONFIG_PWM_ATMEL=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT2_FS_XATTR=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_DNOTIFY is not set
-CONFIG_MSDOS_FS=y
-CONFIG_VFAT_FS=y
-CONFIG_FAT_DEFAULT_CODEPAGE=850
-CONFIG_NTFS_FS=m
-CONFIG_NTFS_RW=y
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_CIFS=m
-CONFIG_CIFS_STATS=y
-CONFIG_CIFS_WEAK_PW_HASH=y
-CONFIG_CIFS_XATTR=y
-CONFIG_CIFS_POSIX=y
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_CODEPAGE_850=y
-CONFIG_NLS_ISO8859_1=y
-CONFIG_NLS_UTF8=y
-CONFIG_DEBUG_FS=y
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_CRC_CCITT=y
+++ /dev/null
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_RELAY=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-CONFIG_BOARD_ATNGW100_MKII=y
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_NMI_DEBUGGING=y
-CONFIG_CPU_FREQ=y
-# CONFIG_CPU_FREQ_STAT is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=y
-CONFIG_NET_KEY=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_MROUTE=y
-CONFIG_IP_PIMSM_V1=y
-CONFIG_SYN_COOKIES=y
-CONFIG_INET_AH=y
-CONFIG_INET_ESP=y
-CONFIG_INET_IPCOMP=y
-# CONFIG_INET_LRO is not set
-CONFIG_IPV6=y
-CONFIG_INET6_AH=y
-CONFIG_INET6_ESP=y
-CONFIG_INET6_IPCOMP=y
-CONFIG_NETFILTER=y
-# CONFIG_NETFILTER_ADVANCED is not set
-CONFIG_NETFILTER_XTABLES=y
-CONFIG_BRIDGE=m
-CONFIG_VLAN_8021Q=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_INTELEXT=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_DATAFLASH=y
-CONFIG_MTD_NAND=y
-CONFIG_MTD_NAND_ATMEL=y
-CONFIG_MTD_UBI=y
-CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=m
-CONFIG_ATMEL_TCLIB=y
-CONFIG_NETDEVICES=y
-CONFIG_TUN=m
-CONFIG_MACB=y
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_FILTER=y
-CONFIG_PPP_MPPE=m
-CONFIG_PPPOE=m
-CONFIG_PPP_ASYNC=m
-# CONFIG_INPUT is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-# CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-CONFIG_I2C_GPIO=m
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=m
-CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_USB_GADGET=y
-CONFIG_USB_GADGET_VBUS_DRAW=350
-CONFIG_USB_ZERO=m
-CONFIG_USB_ETH=m
-CONFIG_USB_GADGETFS=m
-CONFIG_USB_MASS_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_USB_CDC_COMPOSITE=m
-CONFIG_MMC=y
-CONFIG_MMC_TEST=m
-CONFIG_MMC_ATMELMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_AT32AP700X=y
-CONFIG_DMADEVICES=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
-CONFIG_EXT4_FS=y
-# CONFIG_DNOTIFY is not set
-CONFIG_FUSE_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_FAT_DEFAULT_CODEPAGE=850
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_UBIFS_FS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NFSD=m
-CONFIG_NFSD_V3=y
-CONFIG_CIFS=m
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_UTF8=m
-CONFIG_DEBUG_FS=y
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
+++ /dev/null
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_RELAY=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-CONFIG_BOARD_ATNGW100_MKII=y
-CONFIG_BOARD_ATNGW100_MKII_LCD=y
-CONFIG_BOARD_ATNGW100_EVKLCD10X=y
-CONFIG_BOARD_ATNGW100_EVKLCD10X_QVGA=y
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_NMI_DEBUGGING=y
-CONFIG_CPU_FREQ=y
-# CONFIG_CPU_FREQ_STAT is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=y
-CONFIG_NET_KEY=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_MROUTE=y
-CONFIG_IP_PIMSM_V1=y
-CONFIG_SYN_COOKIES=y
-CONFIG_INET_AH=y
-CONFIG_INET_ESP=y
-CONFIG_INET_IPCOMP=y
-# CONFIG_INET_LRO is not set
-CONFIG_IPV6=y
-CONFIG_INET6_AH=y
-CONFIG_INET6_ESP=y
-CONFIG_INET6_IPCOMP=y
-CONFIG_NETFILTER=y
-# CONFIG_NETFILTER_ADVANCED is not set
-CONFIG_NETFILTER_XTABLES=y
-CONFIG_BRIDGE=m
-CONFIG_VLAN_8021Q=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_INTELEXT=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_DATAFLASH=y
-CONFIG_MTD_NAND=y
-CONFIG_MTD_NAND_ATMEL=y
-CONFIG_MTD_UBI=y
-CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=m
-CONFIG_ATMEL_TCLIB=y
-CONFIG_NETDEVICES=y
-CONFIG_TUN=m
-CONFIG_MACB=y
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_FILTER=y
-CONFIG_PPP_MPPE=m
-CONFIG_PPPOE=m
-CONFIG_PPP_ASYNC=m
-# CONFIG_INPUT_MOUSEDEV is not set
-CONFIG_INPUT_EVDEV=m
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-CONFIG_INPUT_TOUCHSCREEN=y
-CONFIG_TOUCHSCREEN_WM97XX=m
-# CONFIG_SERIO is not set
-# CONFIG_LEGACY_PTYS is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-CONFIG_I2C_GPIO=m
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=m
-CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_FB=y
-CONFIG_FB_ATMEL=y
-CONFIG_SOUND=y
-CONFIG_SND=y
-CONFIG_SND_MIXER_OSS=m
-CONFIG_SND_PCM_OSS=m
-CONFIG_SND_HRTIMER=y
-# CONFIG_SND_SUPPORT_OLD_API is not set
-# CONFIG_SND_DRIVERS is not set
-CONFIG_SND_ATMEL_AC97C=m
-# CONFIG_SND_SPI is not set
-CONFIG_USB_GADGET=y
-CONFIG_USB_GADGET_VBUS_DRAW=350
-CONFIG_USB_ZERO=m
-CONFIG_USB_ETH=m
-CONFIG_USB_GADGETFS=m
-CONFIG_USB_MASS_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_USB_CDC_COMPOSITE=m
-CONFIG_MMC=y
-CONFIG_MMC_TEST=m
-CONFIG_MMC_ATMELMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_AT32AP700X=y
-CONFIG_DMADEVICES=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
-CONFIG_EXT4_FS=y
-# CONFIG_DNOTIFY is not set
-CONFIG_FUSE_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_FAT_DEFAULT_CODEPAGE=850
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_UBIFS_FS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NFSD=m
-CONFIG_NFSD_V3=y
-CONFIG_CIFS=m
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_UTF8=m
-CONFIG_DEBUG_FS=y
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
+++ /dev/null
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_RELAY=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-CONFIG_BOARD_ATNGW100_MKII=y
-CONFIG_BOARD_ATNGW100_MKII_LCD=y
-CONFIG_BOARD_ATNGW100_EVKLCD10X=y
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_NMI_DEBUGGING=y
-CONFIG_CPU_FREQ=y
-# CONFIG_CPU_FREQ_STAT is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=y
-CONFIG_NET_KEY=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_MROUTE=y
-CONFIG_IP_PIMSM_V1=y
-CONFIG_SYN_COOKIES=y
-CONFIG_INET_AH=y
-CONFIG_INET_ESP=y
-CONFIG_INET_IPCOMP=y
-# CONFIG_INET_LRO is not set
-CONFIG_IPV6=y
-CONFIG_INET6_AH=y
-CONFIG_INET6_ESP=y
-CONFIG_INET6_IPCOMP=y
-CONFIG_NETFILTER=y
-# CONFIG_NETFILTER_ADVANCED is not set
-CONFIG_NETFILTER_XTABLES=y
-CONFIG_BRIDGE=m
-CONFIG_VLAN_8021Q=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_INTELEXT=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_DATAFLASH=y
-CONFIG_MTD_NAND=y
-CONFIG_MTD_NAND_ATMEL=y
-CONFIG_MTD_UBI=y
-CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=m
-CONFIG_ATMEL_TCLIB=y
-CONFIG_NETDEVICES=y
-CONFIG_TUN=m
-CONFIG_MACB=y
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_FILTER=y
-CONFIG_PPP_MPPE=m
-CONFIG_PPPOE=m
-CONFIG_PPP_ASYNC=m
-# CONFIG_INPUT_MOUSEDEV is not set
-CONFIG_INPUT_EVDEV=m
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-CONFIG_INPUT_TOUCHSCREEN=y
-CONFIG_TOUCHSCREEN_WM97XX=m
-# CONFIG_SERIO is not set
-# CONFIG_LEGACY_PTYS is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-CONFIG_I2C_GPIO=m
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=m
-CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_FB=y
-CONFIG_FB_ATMEL=y
-CONFIG_SOUND=y
-CONFIG_SND=y
-CONFIG_SND_MIXER_OSS=m
-CONFIG_SND_PCM_OSS=m
-CONFIG_SND_HRTIMER=y
-# CONFIG_SND_SUPPORT_OLD_API is not set
-# CONFIG_SND_DRIVERS is not set
-CONFIG_SND_ATMEL_AC97C=m
-# CONFIG_SND_SPI is not set
-CONFIG_USB_GADGET=y
-CONFIG_USB_GADGET_VBUS_DRAW=350
-CONFIG_USB_ZERO=m
-CONFIG_USB_ETH=m
-CONFIG_USB_GADGETFS=m
-CONFIG_USB_MASS_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_USB_CDC_COMPOSITE=m
-CONFIG_MMC=y
-CONFIG_MMC_TEST=m
-CONFIG_MMC_ATMELMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_AT32AP700X=y
-CONFIG_DMADEVICES=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
-CONFIG_EXT4_FS=y
-# CONFIG_DNOTIFY is not set
-CONFIG_FUSE_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_FAT_DEFAULT_CODEPAGE=850
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_UBIFS_FS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NFSD=m
-CONFIG_NFSD_V3=y
-CONFIG_CIFS=m
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_UTF8=m
-CONFIG_DEBUG_FS=y
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
+++ /dev/null
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_RELAY=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_NMI_DEBUGGING=y
-CONFIG_CPU_FREQ=y
-# CONFIG_CPU_FREQ_STAT is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=m
-CONFIG_NET_KEY=m
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_NET_IPIP=m
-CONFIG_NET_IPGRE_DEMUX=m
-CONFIG_NET_IPGRE=m
-CONFIG_INET_AH=m
-CONFIG_INET_ESP=m
-CONFIG_INET_XFRM_MODE_TRANSPORT=m
-CONFIG_INET_XFRM_MODE_TUNNEL=m
-CONFIG_INET_XFRM_MODE_BEET=m
-# CONFIG_INET_LRO is not set
-CONFIG_INET6_AH=m
-CONFIG_INET6_ESP=m
-CONFIG_INET6_IPCOMP=m
-CONFIG_IPV6_TUNNEL=m
-CONFIG_BRIDGE=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_UBI=y
-CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=m
-CONFIG_ATMEL_TCLIB=y
-CONFIG_ATMEL_SSC=m
-# CONFIG_SCSI_PROC_FS is not set
-CONFIG_BLK_DEV_SD=m
-CONFIG_BLK_DEV_SR=m
-# CONFIG_SCSI_LOWLEVEL is not set
-CONFIG_ATA=m
-# CONFIG_SATA_PMP is not set
-CONFIG_PATA_AT32=m
-CONFIG_NETDEVICES=y
-CONFIG_TUN=m
-CONFIG_MACB=y
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_ASYNC=m
-CONFIG_INPUT=m
-CONFIG_INPUT_EVDEV=m
-# CONFIG_KEYBOARD_ATKBD is not set
-CONFIG_KEYBOARD_GPIO=m
-# CONFIG_MOUSE_PS2 is not set
-CONFIG_MOUSE_GPIO=m
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-# CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-CONFIG_I2C_GPIO=m
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=m
-CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_FB=y
-CONFIG_FB_ATMEL=y
-CONFIG_LCD_CLASS_DEVICE=y
-CONFIG_LCD_LTV350QV=y
-CONFIG_SOUND=m
-CONFIG_SND=m
-CONFIG_SND_MIXER_OSS=m
-CONFIG_SND_PCM_OSS=m
-# CONFIG_SND_SUPPORT_OLD_API is not set
-# CONFIG_SND_VERBOSE_PROCFS is not set
-CONFIG_SND_AT73C213=m
-CONFIG_USB_GADGET=y
-CONFIG_USB_ZERO=m
-CONFIG_USB_ETH=m
-CONFIG_USB_GADGETFS=m
-CONFIG_USB_MASS_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_USB_CDC_COMPOSITE=m
-CONFIG_MMC=y
-CONFIG_MMC_TEST=m
-CONFIG_MMC_ATMELMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=m
-CONFIG_LEDS_PWM=m
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=m
-CONFIG_LEDS_TRIGGER_HEARTBEAT=m
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_AT32AP700X=y
-CONFIG_DMADEVICES=y
-CONFIG_PWM=y
-CONFIG_PWM_ATMEL=m
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
-CONFIG_EXT4_FS=y
-# CONFIG_DNOTIFY is not set
-CONFIG_FUSE_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_FAT_DEFAULT_CODEPAGE=850
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_UBIFS_FS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_CIFS=m
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_UTF8=m
-CONFIG_DEBUG_FS=y
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
+++ /dev/null
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_RELAY=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-CONFIG_BOARD_ATSTK1003=y
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_NMI_DEBUGGING=y
-CONFIG_CPU_FREQ=y
-# CONFIG_CPU_FREQ_STAT is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
-# CONFIG_INET_DIAG is not set
-# CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_UBI=y
-CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=m
-CONFIG_ATMEL_TCLIB=y
-CONFIG_ATMEL_SSC=m
-# CONFIG_SCSI_PROC_FS is not set
-CONFIG_BLK_DEV_SD=m
-CONFIG_BLK_DEV_SR=m
-# CONFIG_SCSI_LOWLEVEL is not set
-CONFIG_ATA=m
-# CONFIG_SATA_PMP is not set
-CONFIG_PATA_AT32=m
-CONFIG_NETDEVICES=y
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_ASYNC=m
-CONFIG_INPUT=m
-CONFIG_INPUT_EVDEV=m
-# CONFIG_KEYBOARD_ATKBD is not set
-CONFIG_KEYBOARD_GPIO=m
-# CONFIG_MOUSE_PS2 is not set
-CONFIG_MOUSE_GPIO=m
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-# CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-CONFIG_I2C_GPIO=m
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=m
-CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_SOUND=m
-CONFIG_SND=m
-CONFIG_SND_MIXER_OSS=m
-CONFIG_SND_PCM_OSS=m
-# CONFIG_SND_DRIVERS is not set
-CONFIG_SND_AT73C213=m
-CONFIG_USB_GADGET=y
-CONFIG_USB_ZERO=m
-CONFIG_USB_ETH=m
-CONFIG_USB_GADGETFS=m
-CONFIG_USB_MASS_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_USB_CDC_COMPOSITE=m
-CONFIG_MMC=y
-CONFIG_MMC_TEST=m
-CONFIG_MMC_ATMELMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=m
-CONFIG_LEDS_PWM=m
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=m
-CONFIG_LEDS_TRIGGER_HEARTBEAT=m
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_AT32AP700X=y
-CONFIG_DMADEVICES=y
-CONFIG_PWM=y
-CONFIG_PWM_ATMEL=m
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
-CONFIG_EXT4_FS=y
-# CONFIG_DNOTIFY is not set
-CONFIG_FUSE_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_FAT_DEFAULT_CODEPAGE=850
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_UBIFS_FS=y
-# CONFIG_NETWORK_FILESYSTEMS is not set
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_UTF8=m
-CONFIG_DEBUG_FS=y
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
+++ /dev/null
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_RELAY=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-CONFIG_BOARD_ATSTK1004=y
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_NMI_DEBUGGING=y
-CONFIG_CPU_FREQ=y
-# CONFIG_CPU_FREQ_STAT is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
-# CONFIG_INET_DIAG is not set
-# CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_UBI=y
-CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=m
-CONFIG_ATMEL_TCLIB=y
-CONFIG_ATMEL_SSC=m
-# CONFIG_SCSI_PROC_FS is not set
-CONFIG_BLK_DEV_SD=m
-CONFIG_BLK_DEV_SR=m
-# CONFIG_SCSI_LOWLEVEL is not set
-CONFIG_ATA=m
-# CONFIG_SATA_PMP is not set
-CONFIG_PATA_AT32=m
-CONFIG_NETDEVICES=y
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_ASYNC=m
-CONFIG_INPUT=m
-CONFIG_INPUT_EVDEV=m
-# CONFIG_KEYBOARD_ATKBD is not set
-CONFIG_KEYBOARD_GPIO=m
-# CONFIG_MOUSE_PS2 is not set
-CONFIG_MOUSE_GPIO=m
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-# CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-CONFIG_I2C_GPIO=m
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=m
-CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_FB=y
-CONFIG_FB_ATMEL=y
-CONFIG_LCD_CLASS_DEVICE=y
-CONFIG_LCD_LTV350QV=y
-CONFIG_USB_GADGET=y
-CONFIG_USB_ZERO=m
-CONFIG_USB_ETH=m
-CONFIG_USB_GADGETFS=m
-CONFIG_USB_MASS_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_USB_CDC_COMPOSITE=m
-CONFIG_MMC=y
-CONFIG_MMC_TEST=m
-CONFIG_MMC_ATMELMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=m
-CONFIG_LEDS_PWM=m
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=m
-CONFIG_LEDS_TRIGGER_HEARTBEAT=m
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_AT32AP700X=y
-CONFIG_DMADEVICES=y
-CONFIG_PWM=y
-CONFIG_PWM_ATMEL=m
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
-CONFIG_EXT4_FS=y
-# CONFIG_DNOTIFY is not set
-CONFIG_FUSE_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_FAT_DEFAULT_CODEPAGE=850
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_UBIFS_FS=y
-# CONFIG_NETWORK_FILESYSTEMS is not set
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_UTF8=m
-CONFIG_DEBUG_FS=y
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
+++ /dev/null
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_RELAY=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-CONFIG_BOARD_ATSTK1006=y
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_NMI_DEBUGGING=y
-CONFIG_CPU_FREQ=y
-# CONFIG_CPU_FREQ_STAT is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=m
-CONFIG_NET_KEY=m
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_NET_IPIP=m
-CONFIG_NET_IPGRE_DEMUX=m
-CONFIG_NET_IPGRE=m
-CONFIG_INET_AH=m
-CONFIG_INET_ESP=m
-CONFIG_INET_XFRM_MODE_TRANSPORT=m
-CONFIG_INET_XFRM_MODE_TUNNEL=m
-CONFIG_INET_XFRM_MODE_BEET=m
-# CONFIG_INET_LRO is not set
-CONFIG_INET6_AH=m
-CONFIG_INET6_ESP=m
-CONFIG_INET6_IPCOMP=m
-CONFIG_IPV6_TUNNEL=m
-CONFIG_BRIDGE=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_NAND=y
-CONFIG_MTD_NAND_ATMEL=y
-CONFIG_MTD_UBI=y
-CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=m
-CONFIG_ATMEL_TCLIB=y
-CONFIG_ATMEL_SSC=m
-# CONFIG_SCSI_PROC_FS is not set
-CONFIG_BLK_DEV_SD=m
-CONFIG_BLK_DEV_SR=m
-# CONFIG_SCSI_LOWLEVEL is not set
-CONFIG_ATA=m
-# CONFIG_SATA_PMP is not set
-CONFIG_PATA_AT32=m
-CONFIG_NETDEVICES=y
-CONFIG_TUN=m
-CONFIG_MACB=y
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_ASYNC=m
-CONFIG_INPUT=m
-CONFIG_INPUT_EVDEV=m
-# CONFIG_KEYBOARD_ATKBD is not set
-CONFIG_KEYBOARD_GPIO=m
-# CONFIG_MOUSE_PS2 is not set
-CONFIG_MOUSE_GPIO=m
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-# CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-CONFIG_I2C_GPIO=m
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=m
-CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_FB=y
-CONFIG_FB_ATMEL=y
-CONFIG_LCD_CLASS_DEVICE=y
-CONFIG_LCD_LTV350QV=y
-CONFIG_SOUND=m
-CONFIG_SND=m
-CONFIG_SND_MIXER_OSS=m
-CONFIG_SND_PCM_OSS=m
-# CONFIG_SND_SUPPORT_OLD_API is not set
-# CONFIG_SND_VERBOSE_PROCFS is not set
-CONFIG_SND_AT73C213=m
-CONFIG_USB_GADGET=y
-CONFIG_USB_ZERO=m
-CONFIG_USB_ETH=m
-CONFIG_USB_GADGETFS=m
-CONFIG_USB_MASS_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_USB_CDC_COMPOSITE=m
-CONFIG_MMC=y
-CONFIG_MMC_TEST=m
-CONFIG_MMC_ATMELMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=m
-CONFIG_LEDS_PWM=m
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=m
-CONFIG_LEDS_TRIGGER_HEARTBEAT=m
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_AT32AP700X=y
-CONFIG_DMADEVICES=y
-CONFIG_PWM=y
-CONFIG_PWM_ATMEL=m
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
-CONFIG_EXT4_FS=y
-# CONFIG_DNOTIFY is not set
-CONFIG_FUSE_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_FAT_DEFAULT_CODEPAGE=850
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_UBIFS_FS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_CIFS=m
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_UTF8=m
-CONFIG_DEBUG_FS=y
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DETECT_HUNG_TASK=y
+++ /dev/null
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_RELAY=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-CONFIG_BOARD_FAVR_32=y
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_NMI_DEBUGGING=y
-CONFIG_CPU_FREQ=y
-# CONFIG_CPU_FREQ_STAT is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=m
-CONFIG_NET_KEY=m
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_NET_IPIP=m
-CONFIG_INET_AH=m
-CONFIG_INET_ESP=m
-CONFIG_INET_XFRM_MODE_TRANSPORT=m
-CONFIG_INET_XFRM_MODE_TUNNEL=m
-CONFIG_INET_XFRM_MODE_BEET=m
-# CONFIG_INET_LRO is not set
-CONFIG_IPV6=y
-CONFIG_INET6_AH=m
-CONFIG_INET6_ESP=m
-CONFIG_INET6_IPCOMP=m
-CONFIG_INET6_XFRM_MODE_TRANSPORT=m
-CONFIG_INET6_XFRM_MODE_TUNNEL=m
-CONFIG_INET6_XFRM_MODE_BEET=m
-CONFIG_IPV6_SIT=m
-CONFIG_IPV6_TUNNEL=m
-CONFIG_BRIDGE=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=m
-CONFIG_ATMEL_TCLIB=y
-CONFIG_ATMEL_SSC=m
-CONFIG_NETDEVICES=y
-CONFIG_MACB=y
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_ASYNC=m
-CONFIG_INPUT_MOUSEDEV=m
-CONFIG_INPUT_EVDEV=m
-# CONFIG_KEYBOARD_ATKBD is not set
-CONFIG_KEYBOARD_GPIO=m
-# CONFIG_MOUSE_PS2 is not set
-CONFIG_MOUSE_GPIO=m
-CONFIG_INPUT_TOUCHSCREEN=y
-CONFIG_TOUCHSCREEN_ADS7846=m
-# CONFIG_SERIO is not set
-# CONFIG_CONSOLE_TRANSLATIONS is not set
-# CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-CONFIG_I2C_GPIO=m
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=m
-CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_FB=y
-CONFIG_FB_ATMEL=y
-# CONFIG_LCD_CLASS_DEVICE is not set
-CONFIG_BACKLIGHT_PWM=m
-CONFIG_SOUND=m
-CONFIG_SOUND_PRIME=m
-CONFIG_USB_GADGET=y
-CONFIG_USB_ZERO=m
-CONFIG_USB_ETH=m
-CONFIG_USB_GADGETFS=m
-CONFIG_USB_MASS_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_USB_CDC_COMPOSITE=m
-CONFIG_MMC=y
-CONFIG_MMC_ATMELMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_AT32AP700X=y
-CONFIG_DMADEVICES=y
-CONFIG_PWM=y
-CONFIG_PWM_ATMEL=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_FS_XATTR is not set
-# CONFIG_DNOTIFY is not set
-CONFIG_FUSE_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-# CONFIG_JFFS2_FS_WRITEBUFFER is not set
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_UTF8=m
-CONFIG_DEBUG_FS=y
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-# CONFIG_CRYPTO_HW is not set
+++ /dev/null
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_BSD_PROCESS_ACCT=y
-CONFIG_BSD_PROCESS_ACCT_V3=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODULE_FORCE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-CONFIG_BOARD_HAMMERHEAD=y
-CONFIG_BOARD_HAMMERHEAD_USB=y
-CONFIG_BOARD_HAMMERHEAD_LCD=y
-CONFIG_BOARD_HAMMERHEAD_SND=y
-# CONFIG_BOARD_HAMMERHEAD_FPGA is not set
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_CPU_FREQ=y
-# CONFIG_CPU_FREQ_STAT is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=y
-CONFIG_NET_KEY=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_MROUTE=y
-CONFIG_IP_PIMSM_V1=y
-CONFIG_SYN_COOKIES=y
-CONFIG_INET_AH=y
-CONFIG_INET_ESP=y
-CONFIG_INET_IPCOMP=y
-# CONFIG_INET_LRO is not set
-# CONFIG_IPV6 is not set
-CONFIG_NETFILTER=y
-# CONFIG_NETFILTER_ADVANCED is not set
-CONFIG_NETFILTER_XTABLES=y
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_DATAFLASH=y
-CONFIG_BLK_DEV_RAM=m
-CONFIG_ATMEL_TCLIB=y
-CONFIG_SCSI=m
-CONFIG_BLK_DEV_SD=m
-CONFIG_NETDEVICES=y
-CONFIG_MACB=y
-CONFIG_INPUT_FF_MEMLESS=m
-CONFIG_INPUT_EVDEV=m
-CONFIG_INPUT_TOUCHSCREEN=y
-# CONFIG_LEGACY_PTYS is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=m
-CONFIG_I2C_CHARDEV=m
-CONFIG_I2C_GPIO=m
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=m
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_FB=y
-CONFIG_FB_ATMEL=y
-CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_SOUND=m
-CONFIG_SND=m
-CONFIG_SND_SEQUENCER=m
-CONFIG_SND_MIXER_OSS=m
-CONFIG_SND_PCM_OSS=m
-CONFIG_SND_SEQUENCER_OSS=y
-# CONFIG_SND_SUPPORT_OLD_API is not set
-CONFIG_HID_A4TECH=m
-CONFIG_HID_APPLE=m
-CONFIG_HID_BELKIN=m
-CONFIG_HID_CHERRY=m
-CONFIG_HID_CHICONY=m
-CONFIG_HID_CYPRESS=m
-CONFIG_HID_EZKEY=m
-CONFIG_HID_GYRATION=m
-CONFIG_HID_LOGITECH=m
-CONFIG_HID_MICROSOFT=m
-CONFIG_HID_MONTEREY=m
-CONFIG_HID_PANTHERLORD=m
-CONFIG_HID_PETALYNX=m
-CONFIG_HID_SAMSUNG=m
-CONFIG_HID_SUNPLUS=m
-CONFIG_USB=m
-CONFIG_USB_MON=m
-CONFIG_USB_ISP116X_HCD=m
-CONFIG_USB_STORAGE=m
-CONFIG_USB_GADGET=y
-CONFIG_USB_ZERO=m
-CONFIG_USB_ETH=m
-CONFIG_USB_GADGETFS=m
-CONFIG_USB_MASS_STORAGE=m
-CONFIG_USB_G_SERIAL=m
-CONFIG_MMC=m
-CONFIG_MMC_ATMELMCI=m
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_AT32AP700X=y
-CONFIG_EXT2_FS=m
-# CONFIG_DNOTIFY is not set
-CONFIG_MSDOS_FS=y
-CONFIG_VFAT_FS=m
-CONFIG_FAT_DEFAULT_CODEPAGE=850
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_UTF8=m
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_CRYPTO_ECB=m
-CONFIG_CRYPTO_PCBC=m
-CONFIG_CRYPTO_ARC4=m
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_CCITT=m
-CONFIG_CRC_ITU_T=m
-CONFIG_CRC7=m
+++ /dev/null
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_BSD_PROCESS_ACCT=y
-CONFIG_BSD_PROCESS_ACCT_V3=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODULE_FORCE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-CONFIG_BOARD_MERISC=y
-CONFIG_AP700X_32_BIT_SMC=y
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=y
-CONFIG_NET_KEY=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_MROUTE=y
-CONFIG_IP_PIMSM_V1=y
-CONFIG_SYN_COOKIES=y
-CONFIG_INET_AH=y
-CONFIG_INET_ESP=y
-CONFIG_INET_IPCOMP=y
-# CONFIG_INET_LRO is not set
-# CONFIG_IPV6 is not set
-CONFIG_CAN=y
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_JEDECPROBE=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_ABSENT=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_BLOCK2MTD=y
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_ATMEL_SSC=y
-CONFIG_SCSI=y
-CONFIG_BLK_DEV_SD=y
-# CONFIG_SCSI_LOWLEVEL is not set
-CONFIG_NETDEVICES=y
-CONFIG_MACB=y
-# CONFIG_INPUT_MOUSEDEV is not set
-CONFIG_INPUT_EVDEV=y
-# CONFIG_KEYBOARD_ATKBD is not set
-# CONFIG_INPUT_MOUSE is not set
-CONFIG_INPUT_TOUCHSCREEN=y
-CONFIG_TOUCHSCREEN_ADS7846=y
-CONFIG_INPUT_MISC=y
-CONFIG_INPUT_UINPUT=y
-# CONFIG_SERIO is not set
-# CONFIG_CONSOLE_TRANSLATIONS is not set
-# CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=y
-CONFIG_I2C_CHARDEV=y
-CONFIG_I2C_GPIO=y
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_SPI_SPIDEV=y
-CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_FB=y
-CONFIG_FB_ATMEL=y
-# CONFIG_LCD_CLASS_DEVICE is not set
-CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_LOGO=y
-CONFIG_MMC=y
-CONFIG_MMC_ATMELMCI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_PWM=y
-CONFIG_RTC_CLASS=y
-# CONFIG_RTC_HCTOSYS is not set
-CONFIG_RTC_DRV_PCF8563=y
-CONFIG_DMADEVICES=y
-CONFIG_UIO=y
-CONFIG_PWM=y
-CONFIG_PWM_ATMEL=m
-CONFIG_EXT2_FS=y
-# CONFIG_DNOTIFY is not set
-CONFIG_FUSE_FS=y
-CONFIG_MSDOS_FS=y
-CONFIG_VFAT_FS=y
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_JFFS2_FS_WBUF_VERIFY=y
-CONFIG_CRAMFS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_CODEPAGE_850=y
-CONFIG_NLS_ISO8859_1=y
-CONFIG_NLS_UTF8=y
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-# CONFIG_CRYPTO_HW is not set
+++ /dev/null
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_BSD_PROCESS_ACCT=y
-CONFIG_BSD_PROCESS_ACCT_V3=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
-# CONFIG_BASE_FULL is not set
-# CONFIG_COMPAT_BRK is not set
-CONFIG_PROFILING=y
-# CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-CONFIG_BOARD_MIMC200=y
-# CONFIG_OWNERSHIP_TRACE is not set
-CONFIG_NMI_DEBUGGING=y
-CONFIG_CPU_FREQ=y
-# CONFIG_CPU_FREQ_STAT is not set
-CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
-CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_AVR32_AT32AP_CPUFREQ=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=y
-CONFIG_NET_KEY=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_MROUTE=y
-CONFIG_IP_PIMSM_V1=y
-CONFIG_SYN_COOKIES=y
-CONFIG_INET_AH=y
-CONFIG_INET_ESP=y
-CONFIG_INET_IPCOMP=y
-# CONFIG_INET_LRO is not set
-CONFIG_INET6_AH=y
-CONFIG_INET6_ESP=y
-CONFIG_INET6_IPCOMP=y
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_FW_LOADER is not set
-CONFIG_MTD=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP=y
-CONFIG_MTD_DATAFLASH=y
-CONFIG_ATMEL_TCLIB=y
-CONFIG_EEPROM_AT24=y
-CONFIG_EEPROM_AT25=y
-CONFIG_NETDEVICES=y
-CONFIG_MACB=y
-# CONFIG_INPUT is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-# CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
-CONFIG_SERIAL_ATMEL=y
-CONFIG_SERIAL_ATMEL_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_I2C=y
-CONFIG_I2C_CHARDEV=y
-CONFIG_I2C_GPIO=y
-CONFIG_SPI=y
-CONFIG_SPI_ATMEL=y
-CONFIG_GPIO_SYSFS=y
-# CONFIG_HWMON is not set
-CONFIG_WATCHDOG=y
-CONFIG_AT32AP700X_WDT=y
-CONFIG_FB=y
-CONFIG_FB_ATMEL=y
-# CONFIG_USB_SUPPORT is not set
-CONFIG_MMC=y
-CONFIG_MMC_TEST=y
-CONFIG_MMC_ATMELMCI=y
-CONFIG_MMC_SPI=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_GPIO=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_DS1390=y
-CONFIG_DMADEVICES=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_FS_XATTR is not set
-# CONFIG_DNOTIFY is not set
-CONFIG_MSDOS_FS=y
-CONFIG_VFAT_FS=y
-CONFIG_FAT_DEFAULT_CODEPAGE=850
-CONFIG_TMPFS=y
-CONFIG_CONFIGFS_FS=y
-CONFIG_JFFS2_FS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_CODEPAGE_850=y
-CONFIG_NLS_ISO8859_1=y
-CONFIG_NLS_UTF8=y
-CONFIG_FRAME_POINTER=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_CRYPTO_ECB=y
-CONFIG_CRYPTO_PCBC=y
-CONFIG_CRYPTO_ARC4=y
-CONFIG_CRC_CCITT=y
+++ /dev/null
-
-generic-y += clkdev.h
-generic-y += delay.h
-generic-y += device.h
-generic-y += div64.h
-generic-y += emergency-restart.h
-generic-y += exec.h
-generic-y += futex.h
-generic-y += irq_regs.h
-generic-y += irq_work.h
-generic-y += local.h
-generic-y += local64.h
-generic-y += mcs_spinlock.h
-generic-y += mm-arch-hooks.h
-generic-y += param.h
-generic-y += percpu.h
-generic-y += preempt.h
-generic-y += sections.h
-generic-y += topology.h
-generic-y += trace_clock.h
-generic-y += vga.h
-generic-y += word-at-a-time.h
-generic-y += xor.h
+++ /dev/null
-/*
- * Definitions for the address spaces of the AVR32 CPUs. Heavily based on
- * include/asm-sh/addrspace.h
- *
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_ADDRSPACE_H
-#define __ASM_AVR32_ADDRSPACE_H
-
-#ifdef CONFIG_MMU
-
-/* Memory segments when segmentation is enabled */
-#define P0SEG 0x00000000
-#define P1SEG 0x80000000
-#define P2SEG 0xa0000000
-#define P3SEG 0xc0000000
-#define P4SEG 0xe0000000
-
-/* Returns the privileged segment base of a given address */
-#define PXSEG(a) (((unsigned long)(a)) & 0xe0000000)
-
-/* Returns the physical address of a PnSEG (n=1,2) address */
-#define PHYSADDR(a) (((unsigned long)(a)) & 0x1fffffff)
-
-/*
- * Map an address to a certain privileged segment
- */
-#define P1SEGADDR(a) ((__typeof__(a))(((unsigned long)(a) & 0x1fffffff) \
- | P1SEG))
-#define P2SEGADDR(a) ((__typeof__(a))(((unsigned long)(a) & 0x1fffffff) \
- | P2SEG))
-#define P3SEGADDR(a) ((__typeof__(a))(((unsigned long)(a) & 0x1fffffff) \
- | P3SEG))
-#define P4SEGADDR(a) ((__typeof__(a))(((unsigned long)(a) & 0x1fffffff) \
- | P4SEG))
-
-#endif /* CONFIG_MMU */
-
-#endif /* __ASM_AVR32_ADDRSPACE_H */
+++ /dev/null
-#include <generated/asm-offsets.h>
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_ASM_H__
-#define __ASM_AVR32_ASM_H__
-
-#include <asm/sysreg.h>
-#include <asm/asm-offsets.h>
-#include <asm/thread_info.h>
-
-#define mask_interrupts ssrf SYSREG_GM_OFFSET
-#define mask_exceptions ssrf SYSREG_EM_OFFSET
-#define unmask_interrupts csrf SYSREG_GM_OFFSET
-#define unmask_exceptions csrf SYSREG_EM_OFFSET
-
-#ifdef CONFIG_FRAME_POINTER
- .macro save_fp
- st.w --sp, r7
- .endm
- .macro restore_fp
- ld.w r7, sp++
- .endm
- .macro zero_fp
- mov r7, 0
- .endm
-#else
- .macro save_fp
- .endm
- .macro restore_fp
- .endm
- .macro zero_fp
- .endm
-#endif
- .macro get_thread_info reg
- mov \reg, sp
- andl \reg, ~(THREAD_SIZE - 1) & 0xffff
- .endm
-
- /* Save and restore registers */
- .macro save_min sr, tmp=lr
- pushm lr
- mfsr \tmp, \sr
- zero_fp
- st.w --sp, \tmp
- .endm
-
- .macro restore_min sr, tmp=lr
- ld.w \tmp, sp++
- mtsr \sr, \tmp
- popm lr
- .endm
-
- .macro save_half sr, tmp=lr
- save_fp
- pushm r8-r9,r10,r11,r12,lr
- zero_fp
- mfsr \tmp, \sr
- st.w --sp, \tmp
- .endm
-
- .macro restore_half sr, tmp=lr
- ld.w \tmp, sp++
- mtsr \sr, \tmp
- popm r8-r9,r10,r11,r12,lr
- restore_fp
- .endm
-
- .macro save_full_user sr, tmp=lr
- stmts --sp, r0,r1,r2,r3,r4,r5,r6,r7,r8,r9,r10,r11,r12,sp,lr
- st.w --sp, lr
- zero_fp
- mfsr \tmp, \sr
- st.w --sp, \tmp
- .endm
-
- .macro restore_full_user sr, tmp=lr
- ld.w \tmp, sp++
- mtsr \sr, \tmp
- ld.w lr, sp++
- ldmts sp++, r0,r1,r2,r3,r4,r5,r6,r7,r8,r9,r10,r11,r12,sp,lr
- .endm
-
- /* uaccess macros */
- .macro branch_if_kernel scratch, label
- get_thread_info \scratch
- ld.w \scratch, \scratch[TI_flags]
- bld \scratch, TIF_USERSPACE
- brcc \label
- .endm
-
- .macro ret_if_privileged scratch, addr, size, ret
- sub \scratch, \size, 1
- add \scratch, \addr
- retcs \ret
- retmi \ret
- .endm
-
-#endif /* __ASM_AVR32_ASM_H__ */
+++ /dev/null
-/*
- * Atomic operations that C can't guarantee us. Useful for
- * resource counting etc.
- *
- * But use these as seldom as possible since they are slower than
- * regular operations.
- *
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_ATOMIC_H
-#define __ASM_AVR32_ATOMIC_H
-
-#include <linux/types.h>
-#include <asm/cmpxchg.h>
-
-#define ATOMIC_INIT(i) { (i) }
-
-#define atomic_read(v) READ_ONCE((v)->counter)
-#define atomic_set(v, i) WRITE_ONCE(((v)->counter), (i))
-
-#define ATOMIC_OP_RETURN(op, asm_op, asm_con) \
-static inline int __atomic_##op##_return(int i, atomic_t *v) \
-{ \
- int result; \
- \
- asm volatile( \
- "/* atomic_" #op "_return */\n" \
- "1: ssrf 5\n" \
- " ld.w %0, %2\n" \
- " " #asm_op " %0, %3\n" \
- " stcond %1, %0\n" \
- " brne 1b" \
- : "=&r" (result), "=o" (v->counter) \
- : "m" (v->counter), #asm_con (i) \
- : "cc"); \
- \
- return result; \
-}
-
-#define ATOMIC_FETCH_OP(op, asm_op, asm_con) \
-static inline int __atomic_fetch_##op(int i, atomic_t *v) \
-{ \
- int result, val; \
- \
- asm volatile( \
- "/* atomic_fetch_" #op " */\n" \
- "1: ssrf 5\n" \
- " ld.w %0, %3\n" \
- " mov %1, %0\n" \
- " " #asm_op " %1, %4\n" \
- " stcond %2, %1\n" \
- " brne 1b" \
- : "=&r" (result), "=&r" (val), "=o" (v->counter) \
- : "m" (v->counter), #asm_con (i) \
- : "cc"); \
- \
- return result; \
-}
-
-ATOMIC_OP_RETURN(sub, sub, rKs21)
-ATOMIC_OP_RETURN(add, add, r)
-ATOMIC_FETCH_OP (sub, sub, rKs21)
-ATOMIC_FETCH_OP (add, add, r)
-
-#define ATOMIC_OPS(op, asm_op) \
-ATOMIC_OP_RETURN(op, asm_op, r) \
-static inline void atomic_##op(int i, atomic_t *v) \
-{ \
- (void)__atomic_##op##_return(i, v); \
-} \
-ATOMIC_FETCH_OP(op, asm_op, r) \
-static inline int atomic_fetch_##op(int i, atomic_t *v) \
-{ \
- return __atomic_fetch_##op(i, v); \
-}
-
-ATOMIC_OPS(and, and)
-ATOMIC_OPS(or, or)
-ATOMIC_OPS(xor, eor)
-
-#undef ATOMIC_OPS
-#undef ATOMIC_FETCH_OP
-#undef ATOMIC_OP_RETURN
-
-/*
- * Probably found the reason why we want to use sub with the signed 21-bit
- * limit, it uses one less register than the add instruction that can add up to
- * 32-bit values.
- *
- * Both instructions are 32-bit, to use a 16-bit instruction the immediate is
- * very small; 4 bit.
- *
- * sub 32-bit, type IV, takes a register and subtracts a 21-bit immediate.
- * add 32-bit, type II, adds two register values together.
- */
-#define IS_21BIT_CONST(i) \
- (__builtin_constant_p(i) && ((i) >= -1048575) && ((i) <= 1048576))
-
-/*
- * atomic_add_return - add integer to atomic variable
- * @i: integer value to add
- * @v: pointer of type atomic_t
- *
- * Atomically adds @i to @v. Returns the resulting value.
- */
-static inline int atomic_add_return(int i, atomic_t *v)
-{
- if (IS_21BIT_CONST(i))
- return __atomic_sub_return(-i, v);
-
- return __atomic_add_return(i, v);
-}
-
-static inline int atomic_fetch_add(int i, atomic_t *v)
-{
- if (IS_21BIT_CONST(i))
- return __atomic_fetch_sub(-i, v);
-
- return __atomic_fetch_add(i, v);
-}
-
-/*
- * atomic_sub_return - subtract the atomic variable
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v. Returns the resulting value.
- */
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
- if (IS_21BIT_CONST(i))
- return __atomic_sub_return(i, v);
-
- return __atomic_add_return(-i, v);
-}
-
-static inline int atomic_fetch_sub(int i, atomic_t *v)
-{
- if (IS_21BIT_CONST(i))
- return __atomic_fetch_sub(i, v);
-
- return __atomic_fetch_add(-i, v);
-}
-
-/*
- * __atomic_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
-*/
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
-{
- int tmp, old = atomic_read(v);
-
- if (IS_21BIT_CONST(a)) {
- asm volatile(
- "/* __atomic_sub_unless */\n"
- "1: ssrf 5\n"
- " ld.w %0, %2\n"
- " cp.w %0, %4\n"
- " breq 1f\n"
- " sub %0, %3\n"
- " stcond %1, %0\n"
- " brne 1b\n"
- "1:"
- : "=&r"(tmp), "=o"(v->counter)
- : "m"(v->counter), "rKs21"(-a), "rKs21"(u)
- : "cc", "memory");
- } else {
- asm volatile(
- "/* __atomic_add_unless */\n"
- "1: ssrf 5\n"
- " ld.w %0, %2\n"
- " cp.w %0, %4\n"
- " breq 1f\n"
- " add %0, %3\n"
- " stcond %1, %0\n"
- " brne 1b\n"
- "1:"
- : "=&r"(tmp), "=o"(v->counter)
- : "m"(v->counter), "r"(a), "ir"(u)
- : "cc", "memory");
- }
-
- return old;
-}
-
-#undef IS_21BIT_CONST
-
-/*
- * atomic_sub_if_positive - conditionally subtract integer from atomic variable
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically test @v and subtract @i if @v is greater or equal than @i.
- * The function returns the old value of @v minus @i.
- */
-static inline int atomic_sub_if_positive(int i, atomic_t *v)
-{
- int result;
-
- asm volatile(
- "/* atomic_sub_if_positive */\n"
- "1: ssrf 5\n"
- " ld.w %0, %2\n"
- " sub %0, %3\n"
- " brlt 1f\n"
- " stcond %1, %0\n"
- " brne 1b\n"
- "1:"
- : "=&r"(result), "=o"(v->counter)
- : "m"(v->counter), "ir"(i)
- : "cc", "memory");
-
- return result;
-}
-
-#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
-#define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
-
-#define atomic_sub(i, v) (void)atomic_sub_return(i, v)
-#define atomic_add(i, v) (void)atomic_add_return(i, v)
-#define atomic_dec(v) atomic_sub(1, (v))
-#define atomic_inc(v) atomic_add(1, (v))
-
-#define atomic_dec_return(v) atomic_sub_return(1, v)
-#define atomic_inc_return(v) atomic_add_return(1, v)
-
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
-#define atomic_inc_and_test(v) (atomic_add_return(1, v) == 0)
-#define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0)
-#define atomic_add_negative(i, v) (atomic_add_return(i, v) < 0)
-
-#define atomic_dec_if_positive(v) atomic_sub_if_positive(1, v)
-
-#endif /* __ASM_AVR32_ATOMIC_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_BARRIER_H
-#define __ASM_AVR32_BARRIER_H
-
-/*
- * Weirdest thing ever.. no full barrier, but it has a write barrier!
- */
-#define wmb() asm volatile("sync 0" : : : "memory")
-
-#ifdef CONFIG_SMP
-# error "The AVR32 port does not support SMP"
-#endif
-
-#include <asm-generic/barrier.h>
-
-#endif /* __ASM_AVR32_BARRIER_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_BITOPS_H
-#define __ASM_AVR32_BITOPS_H
-
-#ifndef _LINUX_BITOPS_H
-#error only <linux/bitops.h> can be included directly
-#endif
-
-#include <asm/byteorder.h>
-#include <asm/barrier.h>
-
-/*
- * set_bit - Atomically set a bit in memory
- * @nr: the bit to set
- * @addr: the address to start counting from
- *
- * This function is atomic and may not be reordered. See __set_bit()
- * if you do not require the atomic guarantees.
- *
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static inline void set_bit(int nr, volatile void * addr)
-{
- unsigned long *p = ((unsigned long *)addr) + nr / BITS_PER_LONG;
- unsigned long tmp;
-
- if (__builtin_constant_p(nr)) {
- asm volatile(
- "1: ssrf 5\n"
- " ld.w %0, %2\n"
- " sbr %0, %3\n"
- " stcond %1, %0\n"
- " brne 1b"
- : "=&r"(tmp), "=o"(*p)
- : "m"(*p), "i"(nr)
- : "cc");
- } else {
- unsigned long mask = 1UL << (nr % BITS_PER_LONG);
- asm volatile(
- "1: ssrf 5\n"
- " ld.w %0, %2\n"
- " or %0, %3\n"
- " stcond %1, %0\n"
- " brne 1b"
- : "=&r"(tmp), "=o"(*p)
- : "m"(*p), "r"(mask)
- : "cc");
- }
-}
-
-/*
- * clear_bit - Clears a bit in memory
- * @nr: Bit to clear
- * @addr: Address to start counting from
- *
- * clear_bit() is atomic and may not be reordered. However, it does
- * not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
- * in order to ensure changes are visible on other processors.
- */
-static inline void clear_bit(int nr, volatile void * addr)
-{
- unsigned long *p = ((unsigned long *)addr) + nr / BITS_PER_LONG;
- unsigned long tmp;
-
- if (__builtin_constant_p(nr)) {
- asm volatile(
- "1: ssrf 5\n"
- " ld.w %0, %2\n"
- " cbr %0, %3\n"
- " stcond %1, %0\n"
- " brne 1b"
- : "=&r"(tmp), "=o"(*p)
- : "m"(*p), "i"(nr)
- : "cc");
- } else {
- unsigned long mask = 1UL << (nr % BITS_PER_LONG);
- asm volatile(
- "1: ssrf 5\n"
- " ld.w %0, %2\n"
- " andn %0, %3\n"
- " stcond %1, %0\n"
- " brne 1b"
- : "=&r"(tmp), "=o"(*p)
- : "m"(*p), "r"(mask)
- : "cc");
- }
-}
-
-/*
- * change_bit - Toggle a bit in memory
- * @nr: Bit to change
- * @addr: Address to start counting from
- *
- * change_bit() is atomic and may not be reordered.
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static inline void change_bit(int nr, volatile void * addr)
-{
- unsigned long *p = ((unsigned long *)addr) + nr / BITS_PER_LONG;
- unsigned long mask = 1UL << (nr % BITS_PER_LONG);
- unsigned long tmp;
-
- asm volatile(
- "1: ssrf 5\n"
- " ld.w %0, %2\n"
- " eor %0, %3\n"
- " stcond %1, %0\n"
- " brne 1b"
- : "=&r"(tmp), "=o"(*p)
- : "m"(*p), "r"(mask)
- : "cc");
-}
-
-/*
- * test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It also implies a memory barrier.
- */
-static inline int test_and_set_bit(int nr, volatile void * addr)
-{
- unsigned long *p = ((unsigned long *)addr) + nr / BITS_PER_LONG;
- unsigned long mask = 1UL << (nr % BITS_PER_LONG);
- unsigned long tmp, old;
-
- if (__builtin_constant_p(nr)) {
- asm volatile(
- "1: ssrf 5\n"
- " ld.w %0, %3\n"
- " mov %2, %0\n"
- " sbr %0, %4\n"
- " stcond %1, %0\n"
- " brne 1b"
- : "=&r"(tmp), "=o"(*p), "=&r"(old)
- : "m"(*p), "i"(nr)
- : "memory", "cc");
- } else {
- asm volatile(
- "1: ssrf 5\n"
- " ld.w %2, %3\n"
- " or %0, %2, %4\n"
- " stcond %1, %0\n"
- " brne 1b"
- : "=&r"(tmp), "=o"(*p), "=&r"(old)
- : "m"(*p), "r"(mask)
- : "memory", "cc");
- }
-
- return (old & mask) != 0;
-}
-
-/*
- * test_and_clear_bit - Clear a bit and return its old value
- * @nr: Bit to clear
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It also implies a memory barrier.
- */
-static inline int test_and_clear_bit(int nr, volatile void * addr)
-{
- unsigned long *p = ((unsigned long *)addr) + nr / BITS_PER_LONG;
- unsigned long mask = 1UL << (nr % BITS_PER_LONG);
- unsigned long tmp, old;
-
- if (__builtin_constant_p(nr)) {
- asm volatile(
- "1: ssrf 5\n"
- " ld.w %0, %3\n"
- " mov %2, %0\n"
- " cbr %0, %4\n"
- " stcond %1, %0\n"
- " brne 1b"
- : "=&r"(tmp), "=o"(*p), "=&r"(old)
- : "m"(*p), "i"(nr)
- : "memory", "cc");
- } else {
- asm volatile(
- "1: ssrf 5\n"
- " ld.w %0, %3\n"
- " mov %2, %0\n"
- " andn %0, %4\n"
- " stcond %1, %0\n"
- " brne 1b"
- : "=&r"(tmp), "=o"(*p), "=&r"(old)
- : "m"(*p), "r"(mask)
- : "memory", "cc");
- }
-
- return (old & mask) != 0;
-}
-
-/*
- * test_and_change_bit - Change a bit and return its old value
- * @nr: Bit to change
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It also implies a memory barrier.
- */
-static inline int test_and_change_bit(int nr, volatile void * addr)
-{
- unsigned long *p = ((unsigned long *)addr) + nr / BITS_PER_LONG;
- unsigned long mask = 1UL << (nr % BITS_PER_LONG);
- unsigned long tmp, old;
-
- asm volatile(
- "1: ssrf 5\n"
- " ld.w %2, %3\n"
- " eor %0, %2, %4\n"
- " stcond %1, %0\n"
- " brne 1b"
- : "=&r"(tmp), "=o"(*p), "=&r"(old)
- : "m"(*p), "r"(mask)
- : "memory", "cc");
-
- return (old & mask) != 0;
-}
-
-#include <asm-generic/bitops/non-atomic.h>
-
-/* Find First bit Set */
-static inline unsigned long __ffs(unsigned long word)
-{
- unsigned long result;
-
- asm("brev %1\n\t"
- "clz %0,%1"
- : "=r"(result), "=&r"(word)
- : "1"(word));
- return result;
-}
-
-/* Find First Zero */
-static inline unsigned long ffz(unsigned long word)
-{
- return __ffs(~word);
-}
-
-/* Find Last bit Set */
-static inline int fls(unsigned long word)
-{
- unsigned long result;
-
- asm("clz %0,%1" : "=r"(result) : "r"(word));
- return 32 - result;
-}
-
-static inline int __fls(unsigned long word)
-{
- return fls(word) - 1;
-}
-
-unsigned long find_first_zero_bit(const unsigned long *addr,
- unsigned long size);
-#define find_first_zero_bit find_first_zero_bit
-
-unsigned long find_next_zero_bit(const unsigned long *addr,
- unsigned long size,
- unsigned long offset);
-#define find_next_zero_bit find_next_zero_bit
-
-unsigned long find_first_bit(const unsigned long *addr,
- unsigned long size);
-#define find_first_bit find_first_bit
-
-unsigned long find_next_bit(const unsigned long *addr,
- unsigned long size,
- unsigned long offset);
-#define find_next_bit find_next_bit
-
-/*
- * ffs: find first bit set. This is defined the same way as
- * the libc and compiler builtin ffs routines, therefore
- * differs in spirit from the above ffz (man ffs).
- *
- * The difference is that bit numbering starts at 1, and if no bit is set,
- * the function returns 0.
- */
-static inline int ffs(unsigned long word)
-{
- if(word == 0)
- return 0;
- return __ffs(word) + 1;
-}
-
-#include <asm-generic/bitops/fls64.h>
-#include <asm-generic/bitops/sched.h>
-#include <asm-generic/bitops/hweight.h>
-#include <asm-generic/bitops/lock.h>
-
-extern unsigned long find_next_zero_bit_le(const void *addr,
- unsigned long size, unsigned long offset);
-#define find_next_zero_bit_le find_next_zero_bit_le
-
-extern unsigned long find_next_bit_le(const void *addr,
- unsigned long size, unsigned long offset);
-#define find_next_bit_le find_next_bit_le
-
-#include <asm-generic/bitops/le.h>
-#include <asm-generic/bitops/ext2-atomic.h>
-
-#endif /* __ASM_AVR32_BITOPS_H */
+++ /dev/null
-/*
- * Copyright (C) 2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_BUG_H
-#define __ASM_AVR32_BUG_H
-
-#ifdef CONFIG_BUG
-
-/*
- * According to our Chief Architect, this compact opcode is very
- * unlikely to ever be implemented.
- */
-#define AVR32_BUG_OPCODE 0x5df0
-
-#ifdef CONFIG_DEBUG_BUGVERBOSE
-
-#define _BUG_OR_WARN(flags) \
- asm volatile( \
- "1: .hword %0\n" \
- " .section __bug_table,\"a\",@progbits\n" \
- "2: .long 1b\n" \
- " .long %1\n" \
- " .short %2\n" \
- " .short %3\n" \
- " .org 2b + %4\n" \
- " .previous" \
- : \
- : "i"(AVR32_BUG_OPCODE), "i"(__FILE__), \
- "i"(__LINE__), "i"(flags), \
- "i"(sizeof(struct bug_entry)))
-
-#else
-
-#define _BUG_OR_WARN(flags) \
- asm volatile( \
- "1: .hword %0\n" \
- " .section __bug_table,\"a\",@progbits\n" \
- "2: .long 1b\n" \
- " .short %1\n" \
- " .org 2b + %2\n" \
- " .previous" \
- : \
- : "i"(AVR32_BUG_OPCODE), "i"(flags), \
- "i"(sizeof(struct bug_entry)))
-
-#endif /* CONFIG_DEBUG_BUGVERBOSE */
-
-#define BUG() \
- do { \
- _BUG_OR_WARN(0); \
- unreachable(); \
- } while (0)
-
-#define WARN_ON(condition) \
- ({ \
- int __ret_warn_on = !!(condition); \
- if (unlikely(__ret_warn_on)) \
- _BUG_OR_WARN(BUGFLAG_WARNING); \
- unlikely(__ret_warn_on); \
- })
-
-#define HAVE_ARCH_BUG
-#define HAVE_ARCH_WARN_ON
-
-#endif /* CONFIG_BUG */
-
-#include <asm-generic/bug.h>
-
-struct pt_regs;
-void die(const char *str, struct pt_regs *regs, long err);
-void _exception(long signr, struct pt_regs *regs, int code,
- unsigned long addr);
-
-#endif /* __ASM_AVR32_BUG_H */
+++ /dev/null
-/*
- * This is included by init/main.c to check for architecture-dependent bugs.
- *
- * Needs:
- * void check_bugs(void);
- */
-#ifndef __ASM_AVR32_BUGS_H
-#define __ASM_AVR32_BUGS_H
-
-static void __init check_bugs(void)
-{
- boot_cpu_data.loops_per_jiffy = loops_per_jiffy;
-}
-
-#endif /* __ASM_AVR32_BUGS_H */
+++ /dev/null
-#ifndef __ASM_AVR32_CACHE_H
-#define __ASM_AVR32_CACHE_H
-
-#define L1_CACHE_SHIFT 5
-#define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT)
-
-/*
- * Memory returned by kmalloc() may be used for DMA, so we must make
- * sure that all such allocations are cache aligned. Otherwise,
- * unrelated code may cause parts of the buffer to be read into the
- * cache before the transfer is done, causing old data to be seen by
- * the CPU.
- */
-#define ARCH_DMA_MINALIGN L1_CACHE_BYTES
-
-#ifndef __ASSEMBLER__
-struct cache_info {
- unsigned int ways;
- unsigned int sets;
- unsigned int linesz;
-};
-#endif /* __ASSEMBLER */
-
-/* Cache operation constants */
-#define ICACHE_FLUSH 0x00
-#define ICACHE_INVALIDATE 0x01
-#define ICACHE_LOCK 0x02
-#define ICACHE_UNLOCK 0x03
-#define ICACHE_PREFETCH 0x04
-
-#define DCACHE_FLUSH 0x08
-#define DCACHE_LOCK 0x09
-#define DCACHE_UNLOCK 0x0a
-#define DCACHE_INVALIDATE 0x0b
-#define DCACHE_CLEAN 0x0c
-#define DCACHE_CLEAN_INVAL 0x0d
-
-#endif /* __ASM_AVR32_CACHE_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_CACHEFLUSH_H
-#define __ASM_AVR32_CACHEFLUSH_H
-
-/* Keep includes the same across arches. */
-#include <linux/mm.h>
-
-#define CACHE_OP_ICACHE_INVALIDATE 0x01
-#define CACHE_OP_DCACHE_INVALIDATE 0x0b
-#define CACHE_OP_DCACHE_CLEAN 0x0c
-#define CACHE_OP_DCACHE_CLEAN_INVAL 0x0d
-
-/*
- * Invalidate any cacheline containing virtual address vaddr without
- * writing anything back to memory.
- *
- * Note that this function may corrupt unrelated data structures when
- * applied on buffers that are not cacheline aligned in both ends.
- */
-static inline void invalidate_dcache_line(void *vaddr)
-{
- asm volatile("cache %0[0], %1"
- :
- : "r"(vaddr), "n"(CACHE_OP_DCACHE_INVALIDATE)
- : "memory");
-}
-
-/*
- * Make sure any cacheline containing virtual address vaddr is written
- * to memory.
- */
-static inline void clean_dcache_line(void *vaddr)
-{
- asm volatile("cache %0[0], %1"
- :
- : "r"(vaddr), "n"(CACHE_OP_DCACHE_CLEAN)
- : "memory");
-}
-
-/*
- * Make sure any cacheline containing virtual address vaddr is written
- * to memory and then invalidate it.
- */
-static inline void flush_dcache_line(void *vaddr)
-{
- asm volatile("cache %0[0], %1"
- :
- : "r"(vaddr), "n"(CACHE_OP_DCACHE_CLEAN_INVAL)
- : "memory");
-}
-
-/*
- * Invalidate any instruction cacheline containing virtual address
- * vaddr.
- */
-static inline void invalidate_icache_line(void *vaddr)
-{
- asm volatile("cache %0[0], %1"
- :
- : "r"(vaddr), "n"(CACHE_OP_ICACHE_INVALIDATE)
- : "memory");
-}
-
-/*
- * Applies the above functions on all lines that are touched by the
- * specified virtual address range.
- */
-void invalidate_dcache_region(void *start, size_t len);
-void clean_dcache_region(void *start, size_t len);
-void flush_dcache_region(void *start, size_t len);
-void invalidate_icache_region(void *start, size_t len);
-
-/*
- * Make sure any pending writes are completed before continuing.
- */
-#define flush_write_buffer() asm volatile("sync 0" : : : "memory")
-
-/*
- * The following functions are called when a virtual mapping changes.
- * We do not need to flush anything in this case.
- */
-#define flush_cache_all() do { } while (0)
-#define flush_cache_mm(mm) do { } while (0)
-#define flush_cache_dup_mm(mm) do { } while (0)
-#define flush_cache_range(vma, start, end) do { } while (0)
-#define flush_cache_page(vma, vmaddr, pfn) do { } while (0)
-#define flush_cache_vmap(start, end) do { } while (0)
-#define flush_cache_vunmap(start, end) do { } while (0)
-
-/*
- * I think we need to implement this one to be able to reliably
- * execute pages from RAMDISK. However, if we implement the
- * flush_dcache_*() functions, it might not be needed anymore.
- *
- * #define flush_icache_page(vma, page) do { } while (0)
- */
-extern void flush_icache_page(struct vm_area_struct *vma, struct page *page);
-
-/*
- * These are (I think) related to D-cache aliasing. We might need to
- * do something here, but only for certain configurations. No such
- * configurations exist at this time.
- */
-#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
-#define flush_dcache_page(page) do { } while (0)
-#define flush_dcache_mmap_lock(page) do { } while (0)
-#define flush_dcache_mmap_unlock(page) do { } while (0)
-
-/*
- * These are for I/D cache coherency. In this case, we do need to
- * flush with all configurations.
- */
-extern void flush_icache_range(unsigned long start, unsigned long end);
-
-extern void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
- unsigned long vaddr, void *dst, const void *src,
- unsigned long len);
-
-static inline void copy_from_user_page(struct vm_area_struct *vma,
- struct page *page, unsigned long vaddr, void *dst,
- const void *src, unsigned long len)
-{
- memcpy(dst, src, len);
-}
-
-#endif /* __ASM_AVR32_CACHEFLUSH_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_CHECKSUM_H
-#define __ASM_AVR32_CHECKSUM_H
-
-/*
- * computes the checksum of a memory block at buff, length len,
- * and adds in "sum" (32-bit)
- *
- * returns a 32-bit number suitable for feeding into itself
- * or csum_tcpudp_magic
- *
- * this function must be called with even lengths, except
- * for the last fragment, which may be odd
- *
- * it's best to have buff aligned on a 32-bit boundary
- */
-__wsum csum_partial(const void *buff, int len, __wsum sum);
-
-/*
- * the same as csum_partial, but copies from src while it
- * checksums, and handles user-space pointer exceptions correctly, when needed.
- *
- * here even more important to align src and dst on a 32-bit (or even
- * better 64-bit) boundary
- */
-__wsum csum_partial_copy_generic(const void *src, void *dst, int len,
- __wsum sum, int *src_err_ptr,
- int *dst_err_ptr);
-
-/*
- * Note: when you get a NULL pointer exception here this means someone
- * passed in an incorrect kernel address to one of these functions.
- *
- * If you use these functions directly please don't forget the
- * access_ok().
- */
-static inline
-__wsum csum_partial_copy_nocheck(const void *src, void *dst,
- int len, __wsum sum)
-{
- return csum_partial_copy_generic(src, dst, len, sum, NULL, NULL);
-}
-
-static inline
-__wsum csum_partial_copy_from_user(const void __user *src, void *dst,
- int len, __wsum sum, int *err_ptr)
-{
- return csum_partial_copy_generic((const void __force *)src, dst, len,
- sum, err_ptr, NULL);
-}
-
-/*
- * This is a version of ip_compute_csum() optimized for IP headers,
- * which always checksum on 4 octet boundaries.
- */
-static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
-{
- unsigned int sum, tmp;
-
- __asm__ __volatile__(
- " ld.w %0, %1++\n"
- " ld.w %3, %1++\n"
- " sub %2, 4\n"
- " add %0, %3\n"
- " ld.w %3, %1++\n"
- " adc %0, %0, %3\n"
- " ld.w %3, %1++\n"
- " adc %0, %0, %3\n"
- " acr %0\n"
- "1: ld.w %3, %1++\n"
- " add %0, %3\n"
- " acr %0\n"
- " sub %2, 1\n"
- " brne 1b\n"
- " lsl %3, %0, 16\n"
- " andl %0, 0\n"
- " mov %2, 0xffff\n"
- " add %0, %3\n"
- " adc %0, %0, %2\n"
- " com %0\n"
- " lsr %0, 16\n"
- : "=r"(sum), "=r"(iph), "=r"(ihl), "=r"(tmp)
- : "1"(iph), "2"(ihl)
- : "memory", "cc");
- return (__force __sum16)sum;
-}
-
-/*
- * Fold a partial checksum
- */
-
-static inline __sum16 csum_fold(__wsum sum)
-{
- unsigned int tmp;
-
- asm(" bfextu %1, %0, 0, 16\n"
- " lsr %0, 16\n"
- " add %0, %1\n"
- " bfextu %1, %0, 16, 16\n"
- " add %0, %1"
- : "=&r"(sum), "=&r"(tmp)
- : "0"(sum));
-
- return (__force __sum16)~sum;
-}
-
-static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
- __u32 len, __u8 proto,
- __wsum sum)
-{
- asm(" add %0, %1\n"
- " adc %0, %0, %2\n"
- " adc %0, %0, %3\n"
- " acr %0"
- : "=r"(sum)
- : "r"(daddr), "r"(saddr), "r"(len + proto),
- "0"(sum)
- : "cc");
-
- return sum;
-}
-
-/*
- * computes the checksum of the TCP/UDP pseudo-header
- * returns a 16-bit checksum, already complemented
- */
-static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
- __u32 len, __u8 proto,
- __wsum sum)
-{
- return csum_fold(csum_tcpudp_nofold(saddr,daddr,len,proto,sum));
-}
-
-/*
- * this routine is used for miscellaneous IP-like checksums, mainly
- * in icmp.c
- */
-
-static inline __sum16 ip_compute_csum(const void *buff, int len)
-{
- return csum_fold(csum_partial(buff, len, 0));
-}
-
-#endif /* __ASM_AVR32_CHECKSUM_H */
+++ /dev/null
-/*
- * Atomic operations that C can't guarantee us. Useful for
- * resource counting etc.
- *
- * But use these as seldom as possible since they are slower than
- * regular operations.
- *
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_CMPXCHG_H
-#define __ASM_AVR32_CMPXCHG_H
-
-#define xchg(ptr,x) \
- ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
-
-extern void __xchg_called_with_bad_pointer(void);
-
-static inline unsigned long xchg_u32(u32 val, volatile u32 *m)
-{
- u32 ret;
-
- asm volatile("xchg %[ret], %[m], %[val]"
- : [ret] "=&r"(ret), "=m"(*m)
- : "m"(*m), [m] "r"(m), [val] "r"(val)
- : "memory");
- return ret;
-}
-
-static inline unsigned long __xchg(unsigned long x,
- volatile void *ptr,
- int size)
-{
- switch(size) {
- case 4:
- return xchg_u32(x, ptr);
- default:
- __xchg_called_with_bad_pointer();
- return x;
- }
-}
-
-static inline unsigned long __cmpxchg_u32(volatile int *m, unsigned long old,
- unsigned long new)
-{
- __u32 ret;
-
- asm volatile(
- "1: ssrf 5\n"
- " ld.w %[ret], %[m]\n"
- " cp.w %[ret], %[old]\n"
- " brne 2f\n"
- " stcond %[m], %[new]\n"
- " brne 1b\n"
- "2:\n"
- : [ret] "=&r"(ret), [m] "=m"(*m)
- : "m"(m), [old] "Ks21r"(old), [new] "r"(new)
- : "memory", "cc");
- return ret;
-}
-
-extern unsigned long __cmpxchg_u64_unsupported_on_32bit_kernels(
- volatile int * m, unsigned long old, unsigned long new);
-#define __cmpxchg_u64 __cmpxchg_u64_unsupported_on_32bit_kernels
-
-/* This function doesn't exist, so you'll get a linker error
- if something tries to do an invalid cmpxchg(). */
-extern void __cmpxchg_called_with_bad_pointer(void);
-
-static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
- unsigned long new, int size)
-{
- switch (size) {
- case 4:
- return __cmpxchg_u32(ptr, old, new);
- case 8:
- return __cmpxchg_u64(ptr, old, new);
- }
-
- __cmpxchg_called_with_bad_pointer();
- return old;
-}
-
-#define cmpxchg(ptr, old, new) \
- ((typeof(*(ptr)))__cmpxchg((ptr), (unsigned long)(old), \
- (unsigned long)(new), \
- sizeof(*(ptr))))
-
-#include <asm-generic/cmpxchg-local.h>
-
-static inline unsigned long __cmpxchg_local(volatile void *ptr,
- unsigned long old,
- unsigned long new, int size)
-{
- switch (size) {
- case 4:
- return __cmpxchg_u32(ptr, old, new);
- default:
- return __cmpxchg_local_generic(ptr, old, new, size);
- }
-
- return old;
-}
-
-#define cmpxchg_local(ptr, old, new) \
- ((typeof(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(old), \
- (unsigned long)(new), \
- sizeof(*(ptr))))
-
-#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
-
-#endif /* __ASM_AVR32_CMPXCHG_H */
+++ /dev/null
-#ifndef __ASM_AVR32_CURRENT_H
-#define __ASM_AVR32_CURRENT_H
-
-#include <linux/thread_info.h>
-
-struct task_struct;
-
-inline static struct task_struct * get_current(void)
-{
- return current_thread_info()->task;
-}
-
-#define current get_current()
-
-#endif /* __ASM_AVR32_CURRENT_H */
+++ /dev/null
-#ifndef __ASM_AVR32_DMA_MAPPING_H
-#define __ASM_AVR32_DMA_MAPPING_H
-
-extern void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
- int direction);
-
-extern const struct dma_map_ops avr32_dma_ops;
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
- return &avr32_dma_ops;
-}
-
-#endif /* __ASM_AVR32_DMA_MAPPING_H */
+++ /dev/null
-#ifndef __ASM_AVR32_DMA_H
-#define __ASM_AVR32_DMA_H
-
-/* The maximum address that we can perform a DMA transfer to on this platform.
- * Not really applicable to AVR32, but some functions need it. */
-#define MAX_DMA_ADDRESS 0xffffffff
-
-#endif /* __ASM_AVR32_DMA_H */
+++ /dev/null
-#ifndef __ASM_AVR32_ELF_H
-#define __ASM_AVR32_ELF_H
-
-/* AVR32 relocation numbers */
-#define R_AVR32_NONE 0
-#define R_AVR32_32 1
-#define R_AVR32_16 2
-#define R_AVR32_8 3
-#define R_AVR32_32_PCREL 4
-#define R_AVR32_16_PCREL 5
-#define R_AVR32_8_PCREL 6
-#define R_AVR32_DIFF32 7
-#define R_AVR32_DIFF16 8
-#define R_AVR32_DIFF8 9
-#define R_AVR32_GOT32 10
-#define R_AVR32_GOT16 11
-#define R_AVR32_GOT8 12
-#define R_AVR32_21S 13
-#define R_AVR32_16U 14
-#define R_AVR32_16S 15
-#define R_AVR32_8S 16
-#define R_AVR32_8S_EXT 17
-#define R_AVR32_22H_PCREL 18
-#define R_AVR32_18W_PCREL 19
-#define R_AVR32_16B_PCREL 20
-#define R_AVR32_16N_PCREL 21
-#define R_AVR32_14UW_PCREL 22
-#define R_AVR32_11H_PCREL 23
-#define R_AVR32_10UW_PCREL 24
-#define R_AVR32_9H_PCREL 25
-#define R_AVR32_9UW_PCREL 26
-#define R_AVR32_HI16 27
-#define R_AVR32_LO16 28
-#define R_AVR32_GOTPC 29
-#define R_AVR32_GOTCALL 30
-#define R_AVR32_LDA_GOT 31
-#define R_AVR32_GOT21S 32
-#define R_AVR32_GOT18SW 33
-#define R_AVR32_GOT16S 34
-#define R_AVR32_GOT7UW 35
-#define R_AVR32_32_CPENT 36
-#define R_AVR32_CPCALL 37
-#define R_AVR32_16_CP 38
-#define R_AVR32_9W_CP 39
-#define R_AVR32_RELATIVE 40
-#define R_AVR32_GLOB_DAT 41
-#define R_AVR32_JMP_SLOT 42
-#define R_AVR32_ALIGN 43
-
-/*
- * ELF register definitions..
- */
-
-#include <asm/ptrace.h>
-#include <asm/user.h>
-
-typedef unsigned long elf_greg_t;
-
-#define ELF_NGREG (sizeof (struct pt_regs) / sizeof (elf_greg_t))
-typedef elf_greg_t elf_gregset_t[ELF_NGREG];
-
-typedef struct user_fpu_struct elf_fpregset_t;
-
-/*
- * This is used to ensure we don't load something for the wrong architecture.
- */
-#define elf_check_arch(x) ( (x)->e_machine == EM_AVR32 )
-
-/*
- * These are used to set parameters in the core dumps.
- */
-#define ELF_CLASS ELFCLASS32
-#ifdef __LITTLE_ENDIAN__
-#define ELF_DATA ELFDATA2LSB
-#else
-#define ELF_DATA ELFDATA2MSB
-#endif
-#define ELF_ARCH EM_AVR32
-
-#define ELF_EXEC_PAGESIZE 4096
-
-/* This is the location that an ET_DYN program is loaded if exec'ed. Typical
- use of this is to invoke "./ld.so someprog" to test out a new version of
- the loader. We need to make sure that it is out of the way of the program
- that it will "exec", and that there is sufficient room for the brk. */
-
-#define ELF_ET_DYN_BASE (TASK_SIZE / 3 * 2)
-
-
-/* This yields a mask that user programs can use to figure out what
- instruction set this CPU supports. This could be done in user space,
- but it's not easy, and we've already done it here. */
-
-#define ELF_HWCAP (0)
-
-/* This yields a string that ld.so will use to load implementation
- specific libraries for optimization. This is more specific in
- intent than poking at uname or /proc/cpuinfo.
-
- For the moment, we have only optimizations for the Intel generations,
- but that could change... */
-
-#define ELF_PLATFORM (NULL)
-
-#endif /* __ASM_AVR32_ELF_H */
+++ /dev/null
-#ifndef _ASM_FB_H_
-#define _ASM_FB_H_
-
-#include <linux/fb.h>
-#include <linux/fs.h>
-#include <asm/page.h>
-
-static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
- unsigned long off)
-{
- vma->vm_page_prot = __pgprot((pgprot_val(vma->vm_page_prot)
- & ~_PAGE_CACHABLE)
- | (_PAGE_BUFFER | _PAGE_DIRTY));
-}
-
-static inline int fb_is_primary_device(struct fb_info *info)
-{
- return 0;
-}
-
-#endif /* _ASM_FB_H_ */
+++ /dev/null
-/* empty */
+++ /dev/null
-#ifndef __ASM_AVR32_GPIO_H
-#define __ASM_AVR32_GPIO_H
-
-#include <mach/gpio.h>
-
-#endif /* __ASM_AVR32_GPIO_H */
+++ /dev/null
-#ifndef __ASM_AVR32_HARDIRQ_H
-#define __ASM_AVR32_HARDIRQ_H
-#ifndef __ASSEMBLY__
-#include <asm-generic/hardirq.h>
-#endif /* __ASSEMBLY__ */
-#endif /* __ASM_AVR32_HARDIRQ_H */
+++ /dev/null
-#ifndef __ASM_AVR32_HW_IRQ_H
-#define __ASM_AVR32_HW_IRQ_H
-
-static inline void hw_resend_irq(struct irq_chip *h, unsigned int i)
-{
- /* Nothing to do */
-}
-
-#endif /* __ASM_AVR32_HW_IRQ_H */
+++ /dev/null
-#ifndef __ASM_AVR32_IO_H
-#define __ASM_AVR32_IO_H
-
-#include <linux/bug.h>
-#include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/types.h>
-
-#include <asm/addrspace.h>
-#include <asm/byteorder.h>
-
-#include <mach/io.h>
-
-/* virt_to_phys will only work when address is in P1 or P2 */
-static __inline__ unsigned long virt_to_phys(volatile void *address)
-{
- return PHYSADDR(address);
-}
-
-static __inline__ void * phys_to_virt(unsigned long address)
-{
- return (void *)P1SEGADDR(address);
-}
-
-#define cached_to_phys(addr) ((unsigned long)PHYSADDR(addr))
-#define uncached_to_phys(addr) ((unsigned long)PHYSADDR(addr))
-#define phys_to_cached(addr) ((void *)P1SEGADDR(addr))
-#define phys_to_uncached(addr) ((void *)P2SEGADDR(addr))
-
-/*
- * Generic IO read/write. These perform native-endian accesses. Note
- * that some architectures will want to re-define __raw_{read,write}w.
- */
-extern void __raw_writesb(void __iomem *addr, const void *data, int bytelen);
-extern void __raw_writesw(void __iomem *addr, const void *data, int wordlen);
-extern void __raw_writesl(void __iomem *addr, const void *data, int longlen);
-
-extern void __raw_readsb(const void __iomem *addr, void *data, int bytelen);
-extern void __raw_readsw(const void __iomem *addr, void *data, int wordlen);
-extern void __raw_readsl(const void __iomem *addr, void *data, int longlen);
-
-static inline void __raw_writeb(u8 v, volatile void __iomem *addr)
-{
- *(volatile u8 __force *)addr = v;
-}
-static inline void __raw_writew(u16 v, volatile void __iomem *addr)
-{
- *(volatile u16 __force *)addr = v;
-}
-static inline void __raw_writel(u32 v, volatile void __iomem *addr)
-{
- *(volatile u32 __force *)addr = v;
-}
-
-static inline u8 __raw_readb(const volatile void __iomem *addr)
-{
- return *(const volatile u8 __force *)addr;
-}
-static inline u16 __raw_readw(const volatile void __iomem *addr)
-{
- return *(const volatile u16 __force *)addr;
-}
-static inline u32 __raw_readl(const volatile void __iomem *addr)
-{
- return *(const volatile u32 __force *)addr;
-}
-
-/* Convert I/O port address to virtual address */
-#ifndef __io
-# define __io(p) ((void *)phys_to_uncached(p))
-#endif
-
-/*
- * Not really sure about the best way to slow down I/O on
- * AVR32. Defining it as a no-op until we have an actual test case.
- */
-#define SLOW_DOWN_IO do { } while (0)
-
-#define __BUILD_MEMORY_SINGLE(pfx, bwl, type) \
-static inline void \
-pfx##write##bwl(type val, volatile void __iomem *addr) \
-{ \
- volatile type *__addr; \
- type __val; \
- \
- __addr = (void *)__swizzle_addr_##bwl((unsigned long)(addr)); \
- __val = pfx##ioswab##bwl(__addr, val); \
- \
- BUILD_BUG_ON(sizeof(type) > sizeof(unsigned long)); \
- \
- *__addr = __val; \
-} \
- \
-static inline type pfx##read##bwl(const volatile void __iomem *addr) \
-{ \
- volatile type *__addr; \
- type __val; \
- \
- __addr = (void *)__swizzle_addr_##bwl((unsigned long)(addr)); \
- \
- BUILD_BUG_ON(sizeof(type) > sizeof(unsigned long)); \
- \
- __val = *__addr; \
- return pfx##ioswab##bwl(__addr, __val); \
-}
-
-#define __BUILD_IOPORT_SINGLE(pfx, bwl, type, p, slow) \
-static inline void pfx##out##bwl##p(type val, unsigned long port) \
-{ \
- volatile type *__addr; \
- type __val; \
- \
- __addr = __io(__swizzle_addr_##bwl(port)); \
- __val = pfx##ioswab##bwl(__addr, val); \
- \
- BUILD_BUG_ON(sizeof(type) > sizeof(unsigned long)); \
- \
- *__addr = __val; \
- slow; \
-} \
- \
-static inline type pfx##in##bwl##p(unsigned long port) \
-{ \
- volatile type *__addr; \
- type __val; \
- \
- __addr = __io(__swizzle_addr_##bwl(port)); \
- \
- BUILD_BUG_ON(sizeof(type) > sizeof(unsigned long)); \
- \
- __val = *__addr; \
- slow; \
- \
- return pfx##ioswab##bwl(__addr, __val); \
-}
-
-#define __BUILD_MEMORY_PFX(bus, bwl, type) \
- __BUILD_MEMORY_SINGLE(bus, bwl, type)
-
-#define BUILDIO_MEM(bwl, type) \
- __BUILD_MEMORY_PFX(, bwl, type) \
- __BUILD_MEMORY_PFX(__mem_, bwl, type)
-
-#define __BUILD_IOPORT_PFX(bus, bwl, type) \
- __BUILD_IOPORT_SINGLE(bus, bwl, type, ,) \
- __BUILD_IOPORT_SINGLE(bus, bwl, type, _p, SLOW_DOWN_IO)
-
-#define BUILDIO_IOPORT(bwl, type) \
- __BUILD_IOPORT_PFX(, bwl, type) \
- __BUILD_IOPORT_PFX(__mem_, bwl, type)
-
-BUILDIO_MEM(b, u8)
-BUILDIO_MEM(w, u16)
-BUILDIO_MEM(l, u32)
-
-BUILDIO_IOPORT(b, u8)
-BUILDIO_IOPORT(w, u16)
-BUILDIO_IOPORT(l, u32)
-
-#define readb_relaxed readb
-#define readw_relaxed readw
-#define readl_relaxed readl
-
-#define readb_be __raw_readb
-#define readw_be __raw_readw
-#define readl_be __raw_readl
-
-#define writeb_relaxed writeb
-#define writew_relaxed writew
-#define writel_relaxed writel
-
-#define writeb_be __raw_writeb
-#define writew_be __raw_writew
-#define writel_be __raw_writel
-
-#define __BUILD_MEMORY_STRING(bwl, type) \
-static inline void writes##bwl(volatile void __iomem *addr, \
- const void *data, unsigned int count) \
-{ \
- const type *__data = data; \
- \
- while (count--) \
- __mem_write##bwl(*__data++, addr); \
-} \
- \
-static inline void reads##bwl(const volatile void __iomem *addr, \
- void *data, unsigned int count) \
-{ \
- type *__data = data; \
- \
- while (count--) \
- *__data++ = __mem_read##bwl(addr); \
-}
-
-#define __BUILD_IOPORT_STRING(bwl, type) \
-static inline void outs##bwl(unsigned long port, const void *data, \
- unsigned int count) \
-{ \
- const type *__data = data; \
- \
- while (count--) \
- __mem_out##bwl(*__data++, port); \
-} \
- \
-static inline void ins##bwl(unsigned long port, void *data, \
- unsigned int count) \
-{ \
- type *__data = data; \
- \
- while (count--) \
- *__data++ = __mem_in##bwl(port); \
-}
-
-#define BUILDSTRING(bwl, type) \
- __BUILD_MEMORY_STRING(bwl, type) \
- __BUILD_IOPORT_STRING(bwl, type)
-
-BUILDSTRING(b, u8)
-BUILDSTRING(w, u16)
-BUILDSTRING(l, u32)
-
-/*
- * io{read,write}{8,16,32} macros in both le (for PCI style consumers) and native be
- */
-#ifndef ioread8
-
-#define ioread8(p) ((unsigned int)readb(p))
-
-#define ioread16(p) ((unsigned int)readw(p))
-#define ioread16be(p) ((unsigned int)__raw_readw(p))
-
-#define ioread32(p) ((unsigned int)readl(p))
-#define ioread32be(p) ((unsigned int)__raw_readl(p))
-
-#define iowrite8(v,p) writeb(v, p)
-
-#define iowrite16(v,p) writew(v, p)
-#define iowrite16be(v,p) __raw_writew(v, p)
-
-#define iowrite32(v,p) writel(v, p)
-#define iowrite32be(v,p) __raw_writel(v, p)
-
-#define ioread8_rep(p,d,c) readsb(p,d,c)
-#define ioread16_rep(p,d,c) readsw(p,d,c)
-#define ioread32_rep(p,d,c) readsl(p,d,c)
-
-#define iowrite8_rep(p,s,c) writesb(p,s,c)
-#define iowrite16_rep(p,s,c) writesw(p,s,c)
-#define iowrite32_rep(p,s,c) writesl(p,s,c)
-
-#endif
-
-static inline void memcpy_fromio(void * to, const volatile void __iomem *from,
- unsigned long count)
-{
- memcpy(to, (const void __force *)from, count);
-}
-
-static inline void memcpy_toio(volatile void __iomem *to, const void * from,
- unsigned long count)
-{
- memcpy((void __force *)to, from, count);
-}
-
-static inline void memset_io(volatile void __iomem *addr, unsigned char val,
- unsigned long count)
-{
- memset((void __force *)addr, val, count);
-}
-
-#define mmiowb()
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-extern void __iomem *__ioremap(unsigned long offset, size_t size,
- unsigned long flags);
-extern void __iounmap(void __iomem *addr);
-
-/*
- * ioremap - map bus memory into CPU space
- * @offset bus address of the memory
- * @size size of the resource to map
- *
- * ioremap performs a platform specific sequence of operations to make
- * bus memory CPU accessible via the readb/.../writel functions and
- * the other mmio helpers. The returned address is not guaranteed to
- * be usable directly as a virtual address.
- */
-#define ioremap(offset, size) \
- __ioremap((offset), (size), 0)
-
-#define ioremap_nocache(offset, size) \
- __ioremap((offset), (size), 0)
-
-#define iounmap(addr) \
- __iounmap(addr)
-
-#define ioremap_wc ioremap_nocache
-#define ioremap_wt ioremap_nocache
-#define ioremap_uc ioremap_nocache
-
-#define cached(addr) P1SEGADDR(addr)
-#define uncached(addr) P2SEGADDR(addr)
-
-#define virt_to_bus virt_to_phys
-#define bus_to_virt phys_to_virt
-#define page_to_bus page_to_phys
-#define bus_to_page phys_to_page
-
-/*
- * Create a virtual mapping cookie for an IO port range. There exists
- * no such thing as port-based I/O on AVR32, so a regular ioremap()
- * should do what we need.
- */
-#define ioport_map(port, nr) ioremap(port, nr)
-#define ioport_unmap(port) iounmap(port)
-
-/*
- * Convert a physical pointer to a virtual kernel pointer for /dev/mem
- * access
- */
-#define xlate_dev_mem_ptr(p) __va(p)
-
-/*
- * Convert a virtual cached pointer to an uncached pointer
- */
-#define xlate_dev_kmem_ptr(p) p
-
-#endif /* __ASM_AVR32_IO_H */
+++ /dev/null
-#ifndef __ASM_AVR32_IRQ_H
-#define __ASM_AVR32_IRQ_H
-
-#define NR_INTERNAL_IRQS 64
-
-#include <mach/irq.h>
-
-#ifndef NR_IRQS
-#define NR_IRQS (NR_INTERNAL_IRQS)
-#endif
-
-#define irq_canonicalize(i) (i)
-
-#ifndef __ASSEMBLER__
-int nmi_enable(void);
-void nmi_disable(void);
-
-/*
- * Returns a bitmask of pending interrupts in a group.
- */
-extern unsigned long intc_get_pending(unsigned int group);
-#endif
-
-#endif /* __ASM_AVR32_IOCTLS_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_IRQFLAGS_H
-#define __ASM_AVR32_IRQFLAGS_H
-
-#include <linux/types.h>
-#include <asm/sysreg.h>
-
-static inline unsigned long arch_local_save_flags(void)
-{
- return sysreg_read(SR);
-}
-
-/*
- * This will restore ALL status register flags, not only the interrupt
- * mask flag.
- *
- * The empty asm statement informs the compiler of this fact while
- * also serving as a barrier.
- */
-static inline void arch_local_irq_restore(unsigned long flags)
-{
- sysreg_write(SR, flags);
- asm volatile("" : : : "memory", "cc");
-}
-
-static inline void arch_local_irq_disable(void)
-{
- asm volatile("ssrf %0" : : "n"(SYSREG_GM_OFFSET) : "memory");
-}
-
-static inline void arch_local_irq_enable(void)
-{
- asm volatile("csrf %0" : : "n"(SYSREG_GM_OFFSET) : "memory");
-}
-
-static inline bool arch_irqs_disabled_flags(unsigned long flags)
-{
- return (flags & SYSREG_BIT(GM)) != 0;
-}
-
-static inline bool arch_irqs_disabled(void)
-{
- return arch_irqs_disabled_flags(arch_local_save_flags());
-}
-
-static inline unsigned long arch_local_irq_save(void)
-{
- unsigned long flags = arch_local_save_flags();
-
- arch_local_irq_disable();
-
- return flags;
-}
-
-#endif /* __ASM_AVR32_IRQFLAGS_H */
+++ /dev/null
-#ifndef __ASM_AVR32_KDEBUG_H
-#define __ASM_AVR32_KDEBUG_H
-
-/* Grossly misnamed. */
-enum die_val {
- DIE_BREAKPOINT,
- DIE_SSTEP,
- DIE_NMI,
- DIE_OOPS,
-};
-
-#endif /* __ASM_AVR32_KDEBUG_H */
+++ /dev/null
-#ifndef __ASM_AVR32_KMAP_TYPES_H
-#define __ASM_AVR32_KMAP_TYPES_H
-
-#ifdef CONFIG_DEBUG_HIGHMEM
-# define KM_TYPE_NR 29
-#else
-# define KM_TYPE_NR 14
-#endif
-
-#endif /* __ASM_AVR32_KMAP_TYPES_H */
+++ /dev/null
-/*
- * Kernel Probes (KProbes)
- *
- * Copyright (C) 2005-2006 Atmel Corporation
- * Copyright (C) IBM Corporation, 2002, 2004
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_KPROBES_H
-#define __ASM_AVR32_KPROBES_H
-
-#include <asm-generic/kprobes.h>
-
-#define BREAKPOINT_INSTRUCTION 0xd673 /* breakpoint */
-
-#ifdef CONFIG_KPROBES
-#include <linux/types.h>
-
-typedef u16 kprobe_opcode_t;
-#define MAX_INSN_SIZE 2
-#define MAX_STACK_SIZE 64 /* 32 would probably be OK */
-
-#define kretprobe_blacklist_size 0
-
-#define arch_remove_kprobe(p) do { } while (0)
-
-/* Architecture specific copy of original instruction */
-struct arch_specific_insn {
- kprobe_opcode_t insn[MAX_INSN_SIZE];
-};
-
-struct prev_kprobe {
- struct kprobe *kp;
- unsigned int status;
-};
-
-/* per-cpu kprobe control block */
-struct kprobe_ctlblk {
- unsigned int kprobe_status;
- struct prev_kprobe prev_kprobe;
- struct pt_regs jprobe_saved_regs;
- char jprobes_stack[MAX_STACK_SIZE];
-};
-
-extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
-extern int kprobe_exceptions_notify(struct notifier_block *self,
- unsigned long val, void *data);
-
-#define flush_insn_slot(p) do { } while (0)
-
-#endif /* CONFIG_KPROBES */
-#endif /* __ASM_AVR32_KPROBES_H */
+++ /dev/null
-#ifndef __ASM_LINKAGE_H
-#define __ASM_LINKAGE_H
-
-#define __ALIGN .balign 2
-#define __ALIGN_STR ".balign 2"
-
-#endif /* __ASM_LINKAGE_H */
+++ /dev/null
-#ifndef __ASM_AVR32_MMU_H
-#define __ASM_AVR32_MMU_H
-
-/* Default "unsigned long" context */
-typedef unsigned long mm_context_t;
-
-#define MMU_ITLB_ENTRIES 64
-#define MMU_DTLB_ENTRIES 64
-
-#endif /* __ASM_AVR32_MMU_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * ASID handling taken from SH implementation.
- * Copyright (C) 1999 Niibe Yutaka
- * Copyright (C) 2003 Paul Mundt
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_MMU_CONTEXT_H
-#define __ASM_AVR32_MMU_CONTEXT_H
-
-#include <linux/mm_types.h>
-
-#include <asm/tlbflush.h>
-#include <asm/sysreg.h>
-#include <asm-generic/mm_hooks.h>
-
-/*
- * The MMU "context" consists of two things:
- * (a) TLB cache version
- * (b) ASID (Address Space IDentifier)
- */
-#define MMU_CONTEXT_ASID_MASK 0x000000ff
-#define MMU_CONTEXT_VERSION_MASK 0xffffff00
-#define MMU_CONTEXT_FIRST_VERSION 0x00000100
-#define NO_CONTEXT 0
-
-#define MMU_NO_ASID 0x100
-
-/* Virtual Page Number mask */
-#define MMU_VPN_MASK 0xfffff000
-
-/* Cache of MMU context last used */
-extern unsigned long mmu_context_cache;
-
-/*
- * Get MMU context if needed
- */
-static inline void
-get_mmu_context(struct mm_struct *mm)
-{
- unsigned long mc = mmu_context_cache;
-
- if (((mm->context ^ mc) & MMU_CONTEXT_VERSION_MASK) == 0)
- /* It's up to date, do nothing */
- return;
-
- /* It's old, we need to get new context with new version */
- mc = ++mmu_context_cache;
- if (!(mc & MMU_CONTEXT_ASID_MASK)) {
- /*
- * We have exhausted all ASIDs of this version.
- * Flush the TLB and start new cycle.
- */
- flush_tlb_all();
- /*
- * Fix version. Note that we avoid version #0
- * to distinguish NO_CONTEXT.
- */
- if (!mc)
- mmu_context_cache = mc = MMU_CONTEXT_FIRST_VERSION;
- }
- mm->context = mc;
-}
-
-/*
- * Initialize the context related info for a new mm_struct
- * instance.
- */
-static inline int init_new_context(struct task_struct *tsk,
- struct mm_struct *mm)
-{
- mm->context = NO_CONTEXT;
- return 0;
-}
-
-/*
- * Destroy context related info for an mm_struct that is about
- * to be put to rest.
- */
-static inline void destroy_context(struct mm_struct *mm)
-{
- /* Do nothing */
-}
-
-static inline void set_asid(unsigned long asid)
-{
- /* XXX: We're destroying TLBEHI[8:31] */
- sysreg_write(TLBEHI, asid & MMU_CONTEXT_ASID_MASK);
- cpu_sync_pipeline();
-}
-
-static inline unsigned long get_asid(void)
-{
- unsigned long asid;
-
- asid = sysreg_read(TLBEHI);
- return asid & MMU_CONTEXT_ASID_MASK;
-}
-
-static inline void activate_context(struct mm_struct *mm)
-{
- get_mmu_context(mm);
- set_asid(mm->context & MMU_CONTEXT_ASID_MASK);
-}
-
-static inline void switch_mm(struct mm_struct *prev,
- struct mm_struct *next,
- struct task_struct *tsk)
-{
- if (likely(prev != next)) {
- unsigned long __pgdir = (unsigned long)next->pgd;
-
- sysreg_write(PTBR, __pgdir);
- activate_context(next);
- }
-}
-
-#define deactivate_mm(tsk,mm) do { } while(0)
-
-#define activate_mm(prev, next) switch_mm((prev), (next), NULL)
-
-static inline void
-enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
-{
-}
-
-
-static inline void enable_mmu(void)
-{
- sysreg_write(MMUCR, (SYSREG_BIT(MMUCR_S)
- | SYSREG_BIT(E)
- | SYSREG_BIT(MMUCR_I)));
- nop(); nop(); nop(); nop(); nop(); nop(); nop(); nop();
-
- if (mmu_context_cache == NO_CONTEXT)
- mmu_context_cache = MMU_CONTEXT_FIRST_VERSION;
-
- set_asid(mmu_context_cache & MMU_CONTEXT_ASID_MASK);
-}
-
-static inline void disable_mmu(void)
-{
- sysreg_write(MMUCR, SYSREG_BIT(MMUCR_S));
-}
-
-#endif /* __ASM_AVR32_MMU_CONTEXT_H */
+++ /dev/null
-#ifndef __ASM_AVR32_MODULE_H
-#define __ASM_AVR32_MODULE_H
-
-#include <asm-generic/module.h>
-
-struct mod_arch_syminfo {
- unsigned long got_offset;
- int got_initialized;
-};
-
-struct mod_arch_specific {
- /* Starting offset of got in the module core memory. */
- unsigned long got_offset;
- /* Size of the got. */
- unsigned long got_size;
- /* Number of symbols in syminfo. */
- int nsyms;
- /* Additional symbol information (got offsets). */
- struct mod_arch_syminfo *syminfo;
-};
-
-#define MODULE_PROC_FAMILY "AVR32v1"
-
-#define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY
-
-#endif /* __ASM_AVR32_MODULE_H */
+++ /dev/null
-/*
- * AVR32 OCD Interface and register definitions
- *
- * Copyright (C) 2004-2007 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_OCD_H
-#define __ASM_AVR32_OCD_H
-
-/* OCD Register offsets. Abbreviations used below:
- *
- * BP Breakpoint
- * Comm Communication
- * DT Data Trace
- * PC Program Counter
- * PID Process ID
- * R/W Read/Write
- * WP Watchpoint
- */
-#define OCD_DID 0x0000 /* Device ID */
-#define OCD_DC 0x0008 /* Development Control */
-#define OCD_DS 0x0010 /* Development Status */
-#define OCD_RWCS 0x001c /* R/W Access Control */
-#define OCD_RWA 0x0024 /* R/W Access Address */
-#define OCD_RWD 0x0028 /* R/W Access Data */
-#define OCD_WT 0x002c /* Watchpoint Trigger */
-#define OCD_DTC 0x0034 /* Data Trace Control */
-#define OCD_DTSA0 0x0038 /* DT Start Addr Channel 0 */
-#define OCD_DTSA1 0x003c /* DT Start Addr Channel 1 */
-#define OCD_DTEA0 0x0048 /* DT End Addr Channel 0 */
-#define OCD_DTEA1 0x004c /* DT End Addr Channel 1 */
-#define OCD_BWC0A 0x0058 /* PC BP/WP Control 0A */
-#define OCD_BWC0B 0x005c /* PC BP/WP Control 0B */
-#define OCD_BWC1A 0x0060 /* PC BP/WP Control 1A */
-#define OCD_BWC1B 0x0064 /* PC BP/WP Control 1B */
-#define OCD_BWC2A 0x0068 /* PC BP/WP Control 2A */
-#define OCD_BWC2B 0x006c /* PC BP/WP Control 2B */
-#define OCD_BWC3A 0x0070 /* Data BP/WP Control 3A */
-#define OCD_BWC3B 0x0074 /* Data BP/WP Control 3B */
-#define OCD_BWA0A 0x0078 /* PC BP/WP Address 0A */
-#define OCD_BWA0B 0x007c /* PC BP/WP Address 0B */
-#define OCD_BWA1A 0x0080 /* PC BP/WP Address 1A */
-#define OCD_BWA1B 0x0084 /* PC BP/WP Address 1B */
-#define OCD_BWA2A 0x0088 /* PC BP/WP Address 2A */
-#define OCD_BWA2B 0x008c /* PC BP/WP Address 2B */
-#define OCD_BWA3A 0x0090 /* Data BP/WP Address 3A */
-#define OCD_BWA3B 0x0094 /* Data BP/WP Address 3B */
-#define OCD_NXCFG 0x0100 /* Nexus Configuration */
-#define OCD_DINST 0x0104 /* Debug Instruction */
-#define OCD_DPC 0x0108 /* Debug Program Counter */
-#define OCD_CPUCM 0x010c /* CPU Control Mask */
-#define OCD_DCCPU 0x0110 /* Debug Comm CPU */
-#define OCD_DCEMU 0x0114 /* Debug Comm Emulator */
-#define OCD_DCSR 0x0118 /* Debug Comm Status */
-#define OCD_PID 0x011c /* Ownership Trace PID */
-#define OCD_EPC0 0x0120 /* Event Pair Control 0 */
-#define OCD_EPC1 0x0124 /* Event Pair Control 1 */
-#define OCD_EPC2 0x0128 /* Event Pair Control 2 */
-#define OCD_EPC3 0x012c /* Event Pair Control 3 */
-#define OCD_AXC 0x0130 /* AUX port Control */
-
-/* Bits in DID */
-#define OCD_DID_MID_START 1
-#define OCD_DID_MID_SIZE 11
-#define OCD_DID_PN_START 12
-#define OCD_DID_PN_SIZE 16
-#define OCD_DID_RN_START 28
-#define OCD_DID_RN_SIZE 4
-
-/* Bits in DC */
-#define OCD_DC_TM_START 0
-#define OCD_DC_TM_SIZE 2
-#define OCD_DC_EIC_START 3
-#define OCD_DC_EIC_SIZE 2
-#define OCD_DC_OVC_START 5
-#define OCD_DC_OVC_SIZE 3
-#define OCD_DC_SS_BIT 8
-#define OCD_DC_DBR_BIT 12
-#define OCD_DC_DBE_BIT 13
-#define OCD_DC_EOS_START 20
-#define OCD_DC_EOS_SIZE 2
-#define OCD_DC_SQA_BIT 22
-#define OCD_DC_IRP_BIT 23
-#define OCD_DC_IFM_BIT 24
-#define OCD_DC_TOZ_BIT 25
-#define OCD_DC_TSR_BIT 26
-#define OCD_DC_RID_BIT 27
-#define OCD_DC_ORP_BIT 28
-#define OCD_DC_MM_BIT 29
-#define OCD_DC_RES_BIT 30
-#define OCD_DC_ABORT_BIT 31
-
-/* Bits in DS */
-#define OCD_DS_SSS_BIT 0
-#define OCD_DS_SWB_BIT 1
-#define OCD_DS_HWB_BIT 2
-#define OCD_DS_HWE_BIT 3
-#define OCD_DS_STP_BIT 4
-#define OCD_DS_DBS_BIT 5
-#define OCD_DS_BP_START 8
-#define OCD_DS_BP_SIZE 8
-#define OCD_DS_INC_BIT 24
-#define OCD_DS_BOZ_BIT 25
-#define OCD_DS_DBA_BIT 26
-#define OCD_DS_EXB_BIT 27
-#define OCD_DS_NTBF_BIT 28
-
-/* Bits in RWCS */
-#define OCD_RWCS_DV_BIT 0
-#define OCD_RWCS_ERR_BIT 1
-#define OCD_RWCS_CNT_START 2
-#define OCD_RWCS_CNT_SIZE 14
-#define OCD_RWCS_CRC_BIT 19
-#define OCD_RWCS_NTBC_START 20
-#define OCD_RWCS_NTBC_SIZE 2
-#define OCD_RWCS_NTE_BIT 22
-#define OCD_RWCS_NTAP_BIT 23
-#define OCD_RWCS_WRAPPED_BIT 24
-#define OCD_RWCS_CCTRL_START 25
-#define OCD_RWCS_CCTRL_SIZE 2
-#define OCD_RWCS_SZ_START 27
-#define OCD_RWCS_SZ_SIZE 3
-#define OCD_RWCS_RW_BIT 30
-#define OCD_RWCS_AC_BIT 31
-
-/* Bits in RWA */
-#define OCD_RWA_RWA_START 0
-#define OCD_RWA_RWA_SIZE 32
-
-/* Bits in RWD */
-#define OCD_RWD_RWD_START 0
-#define OCD_RWD_RWD_SIZE 32
-
-/* Bits in WT */
-#define OCD_WT_DTE_START 20
-#define OCD_WT_DTE_SIZE 3
-#define OCD_WT_DTS_START 23
-#define OCD_WT_DTS_SIZE 3
-#define OCD_WT_PTE_START 26
-#define OCD_WT_PTE_SIZE 3
-#define OCD_WT_PTS_START 29
-#define OCD_WT_PTS_SIZE 3
-
-/* Bits in DTC */
-#define OCD_DTC_T0WP_BIT 0
-#define OCD_DTC_T1WP_BIT 1
-#define OCD_DTC_ASID0EN_BIT 2
-#define OCD_DTC_ASID0_START 3
-#define OCD_DTC_ASID0_SIZE 8
-#define OCD_DTC_ASID1EN_BIT 11
-#define OCD_DTC_ASID1_START 12
-#define OCD_DTC_ASID1_SIZE 8
-#define OCD_DTC_RWT1_START 28
-#define OCD_DTC_RWT1_SIZE 2
-#define OCD_DTC_RWT0_START 30
-#define OCD_DTC_RWT0_SIZE 2
-
-/* Bits in DTSA0 */
-#define OCD_DTSA0_DTSA_START 0
-#define OCD_DTSA0_DTSA_SIZE 32
-
-/* Bits in DTSA1 */
-#define OCD_DTSA1_DTSA_START 0
-#define OCD_DTSA1_DTSA_SIZE 32
-
-/* Bits in DTEA0 */
-#define OCD_DTEA0_DTEA_START 0
-#define OCD_DTEA0_DTEA_SIZE 32
-
-/* Bits in DTEA1 */
-#define OCD_DTEA1_DTEA_START 0
-#define OCD_DTEA1_DTEA_SIZE 32
-
-/* Bits in BWC0A */
-#define OCD_BWC0A_ASIDEN_BIT 0
-#define OCD_BWC0A_ASID_START 1
-#define OCD_BWC0A_ASID_SIZE 8
-#define OCD_BWC0A_EOC_BIT 14
-#define OCD_BWC0A_AME_BIT 25
-#define OCD_BWC0A_BWE_START 30
-#define OCD_BWC0A_BWE_SIZE 2
-
-/* Bits in BWC0B */
-#define OCD_BWC0B_ASIDEN_BIT 0
-#define OCD_BWC0B_ASID_START 1
-#define OCD_BWC0B_ASID_SIZE 8
-#define OCD_BWC0B_EOC_BIT 14
-#define OCD_BWC0B_AME_BIT 25
-#define OCD_BWC0B_BWE_START 30
-#define OCD_BWC0B_BWE_SIZE 2
-
-/* Bits in BWC1A */
-#define OCD_BWC1A_ASIDEN_BIT 0
-#define OCD_BWC1A_ASID_START 1
-#define OCD_BWC1A_ASID_SIZE 8
-#define OCD_BWC1A_EOC_BIT 14
-#define OCD_BWC1A_AME_BIT 25
-#define OCD_BWC1A_BWE_START 30
-#define OCD_BWC1A_BWE_SIZE 2
-
-/* Bits in BWC1B */
-#define OCD_BWC1B_ASIDEN_BIT 0
-#define OCD_BWC1B_ASID_START 1
-#define OCD_BWC1B_ASID_SIZE 8
-#define OCD_BWC1B_EOC_BIT 14
-#define OCD_BWC1B_AME_BIT 25
-#define OCD_BWC1B_BWE_START 30
-#define OCD_BWC1B_BWE_SIZE 2
-
-/* Bits in BWC2A */
-#define OCD_BWC2A_ASIDEN_BIT 0
-#define OCD_BWC2A_ASID_START 1
-#define OCD_BWC2A_ASID_SIZE 8
-#define OCD_BWC2A_EOC_BIT 14
-#define OCD_BWC2A_AMB_START 20
-#define OCD_BWC2A_AMB_SIZE 5
-#define OCD_BWC2A_AME_BIT 25
-#define OCD_BWC2A_BWE_START 30
-#define OCD_BWC2A_BWE_SIZE 2
-
-/* Bits in BWC2B */
-#define OCD_BWC2B_ASIDEN_BIT 0
-#define OCD_BWC2B_ASID_START 1
-#define OCD_BWC2B_ASID_SIZE 8
-#define OCD_BWC2B_EOC_BIT 14
-#define OCD_BWC2B_AME_BIT 25
-#define OCD_BWC2B_BWE_START 30
-#define OCD_BWC2B_BWE_SIZE 2
-
-/* Bits in BWC3A */
-#define OCD_BWC3A_ASIDEN_BIT 0
-#define OCD_BWC3A_ASID_START 1
-#define OCD_BWC3A_ASID_SIZE 8
-#define OCD_BWC3A_SIZE_START 9
-#define OCD_BWC3A_SIZE_SIZE 3
-#define OCD_BWC3A_EOC_BIT 14
-#define OCD_BWC3A_BWO_START 16
-#define OCD_BWC3A_BWO_SIZE 2
-#define OCD_BWC3A_BME_START 20
-#define OCD_BWC3A_BME_SIZE 4
-#define OCD_BWC3A_BRW_START 28
-#define OCD_BWC3A_BRW_SIZE 2
-#define OCD_BWC3A_BWE_START 30
-#define OCD_BWC3A_BWE_SIZE 2
-
-/* Bits in BWC3B */
-#define OCD_BWC3B_ASIDEN_BIT 0
-#define OCD_BWC3B_ASID_START 1
-#define OCD_BWC3B_ASID_SIZE 8
-#define OCD_BWC3B_SIZE_START 9
-#define OCD_BWC3B_SIZE_SIZE 3
-#define OCD_BWC3B_EOC_BIT 14
-#define OCD_BWC3B_BWO_START 16
-#define OCD_BWC3B_BWO_SIZE 2
-#define OCD_BWC3B_BME_START 20
-#define OCD_BWC3B_BME_SIZE 4
-#define OCD_BWC3B_BRW_START 28
-#define OCD_BWC3B_BRW_SIZE 2
-#define OCD_BWC3B_BWE_START 30
-#define OCD_BWC3B_BWE_SIZE 2
-
-/* Bits in BWA0A */
-#define OCD_BWA0A_BWA_START 0
-#define OCD_BWA0A_BWA_SIZE 32
-
-/* Bits in BWA0B */
-#define OCD_BWA0B_BWA_START 0
-#define OCD_BWA0B_BWA_SIZE 32
-
-/* Bits in BWA1A */
-#define OCD_BWA1A_BWA_START 0
-#define OCD_BWA1A_BWA_SIZE 32
-
-/* Bits in BWA1B */
-#define OCD_BWA1B_BWA_START 0
-#define OCD_BWA1B_BWA_SIZE 32
-
-/* Bits in BWA2A */
-#define OCD_BWA2A_BWA_START 0
-#define OCD_BWA2A_BWA_SIZE 32
-
-/* Bits in BWA2B */
-#define OCD_BWA2B_BWA_START 0
-#define OCD_BWA2B_BWA_SIZE 32
-
-/* Bits in BWA3A */
-#define OCD_BWA3A_BWA_START 0
-#define OCD_BWA3A_BWA_SIZE 32
-
-/* Bits in BWA3B */
-#define OCD_BWA3B_BWA_START 0
-#define OCD_BWA3B_BWA_SIZE 32
-
-/* Bits in NXCFG */
-#define OCD_NXCFG_NXARCH_START 0
-#define OCD_NXCFG_NXARCH_SIZE 4
-#define OCD_NXCFG_NXOCD_START 4
-#define OCD_NXCFG_NXOCD_SIZE 4
-#define OCD_NXCFG_NXPCB_START 8
-#define OCD_NXCFG_NXPCB_SIZE 4
-#define OCD_NXCFG_NXDB_START 12
-#define OCD_NXCFG_NXDB_SIZE 4
-#define OCD_NXCFG_MXMSEO_BIT 16
-#define OCD_NXCFG_NXMDO_START 17
-#define OCD_NXCFG_NXMDO_SIZE 4
-#define OCD_NXCFG_NXPT_BIT 21
-#define OCD_NXCFG_NXOT_BIT 22
-#define OCD_NXCFG_NXDWT_BIT 23
-#define OCD_NXCFG_NXDRT_BIT 24
-#define OCD_NXCFG_NXDTC_START 25
-#define OCD_NXCFG_NXDTC_SIZE 3
-#define OCD_NXCFG_NXDMA_BIT 28
-
-/* Bits in DINST */
-#define OCD_DINST_DINST_START 0
-#define OCD_DINST_DINST_SIZE 32
-
-/* Bits in CPUCM */
-#define OCD_CPUCM_BEM_BIT 1
-#define OCD_CPUCM_FEM_BIT 2
-#define OCD_CPUCM_REM_BIT 3
-#define OCD_CPUCM_IBEM_BIT 4
-#define OCD_CPUCM_IEEM_BIT 5
-
-/* Bits in DCCPU */
-#define OCD_DCCPU_DATA_START 0
-#define OCD_DCCPU_DATA_SIZE 32
-
-/* Bits in DCEMU */
-#define OCD_DCEMU_DATA_START 0
-#define OCD_DCEMU_DATA_SIZE 32
-
-/* Bits in DCSR */
-#define OCD_DCSR_CPUD_BIT 0
-#define OCD_DCSR_EMUD_BIT 1
-
-/* Bits in PID */
-#define OCD_PID_PROCESS_START 0
-#define OCD_PID_PROCESS_SIZE 32
-
-/* Bits in EPC0 */
-#define OCD_EPC0_RNG_START 0
-#define OCD_EPC0_RNG_SIZE 2
-#define OCD_EPC0_CE_BIT 4
-#define OCD_EPC0_ECNT_START 16
-#define OCD_EPC0_ECNT_SIZE 16
-
-/* Bits in EPC1 */
-#define OCD_EPC1_RNG_START 0
-#define OCD_EPC1_RNG_SIZE 2
-#define OCD_EPC1_ATB_BIT 5
-#define OCD_EPC1_AM_BIT 6
-
-/* Bits in EPC2 */
-#define OCD_EPC2_RNG_START 0
-#define OCD_EPC2_RNG_SIZE 2
-#define OCD_EPC2_DB_START 2
-#define OCD_EPC2_DB_SIZE 2
-
-/* Bits in EPC3 */
-#define OCD_EPC3_RNG_START 0
-#define OCD_EPC3_RNG_SIZE 2
-#define OCD_EPC3_DWE_BIT 2
-
-/* Bits in AXC */
-#define OCD_AXC_DIV_START 0
-#define OCD_AXC_DIV_SIZE 4
-#define OCD_AXC_AXE_BIT 8
-#define OCD_AXC_AXS_BIT 9
-#define OCD_AXC_DDR_BIT 10
-#define OCD_AXC_LS_BIT 11
-#define OCD_AXC_REX_BIT 12
-#define OCD_AXC_REXTEN_BIT 13
-
-/* Constants for DC:EIC */
-#define OCD_EIC_PROGRAM_AND_DATA_TRACE 0
-#define OCD_EIC_BREAKPOINT 1
-#define OCD_EIC_NOP 2
-
-/* Constants for DC:OVC */
-#define OCD_OVC_OVERRUN 0
-#define OCD_OVC_DELAY_CPU_BTM 1
-#define OCD_OVC_DELAY_CPU_DTM 2
-#define OCD_OVC_DELAY_CPU_BTM_DTM 3
-
-/* Constants for DC:EOS */
-#define OCD_EOS_NOP 0
-#define OCD_EOS_DEBUG_MODE 1
-#define OCD_EOS_BREAKPOINT_WATCHPOINT 2
-#define OCD_EOS_THQ 3
-
-/* Constants for RWCS:NTBC */
-#define OCD_NTBC_OVERWRITE 0
-#define OCD_NTBC_DISABLE 1
-#define OCD_NTBC_BREAKPOINT 2
-
-/* Constants for RWCS:CCTRL */
-#define OCD_CCTRL_AUTO 0
-#define OCD_CCTRL_CACHED 1
-#define OCD_CCTRL_UNCACHED 2
-
-/* Constants for RWCS:SZ */
-#define OCD_SZ_BYTE 0
-#define OCD_SZ_HALFWORD 1
-#define OCD_SZ_WORD 2
-
-/* Constants for WT:PTS */
-#define OCD_PTS_DISABLED 0
-#define OCD_PTS_PROGRAM_0B 1
-#define OCD_PTS_PROGRAM_1A 2
-#define OCD_PTS_PROGRAM_1B 3
-#define OCD_PTS_PROGRAM_2A 4
-#define OCD_PTS_PROGRAM_2B 5
-#define OCD_PTS_DATA_3A 6
-#define OCD_PTS_DATA_3B 7
-
-/* Constants for DTC:RWT1 */
-#define OCD_RWT1_NO_TRACE 0
-#define OCD_RWT1_DATA_READ 1
-#define OCD_RWT1_DATA_WRITE 2
-#define OCD_RWT1_DATA_READ_WRITE 3
-
-/* Constants for DTC:RWT0 */
-#define OCD_RWT0_NO_TRACE 0
-#define OCD_RWT0_DATA_READ 1
-#define OCD_RWT0_DATA_WRITE 2
-#define OCD_RWT0_DATA_READ_WRITE 3
-
-/* Constants for BWC0A:BWE */
-#define OCD_BWE_DISABLED 0
-#define OCD_BWE_BREAKPOINT_ENABLED 1
-#define OCD_BWE_WATCHPOINT_ENABLED 3
-
-/* Constants for BWC0B:BWE */
-#define OCD_BWE_DISABLED 0
-#define OCD_BWE_BREAKPOINT_ENABLED 1
-#define OCD_BWE_WATCHPOINT_ENABLED 3
-
-/* Constants for BWC1A:BWE */
-#define OCD_BWE_DISABLED 0
-#define OCD_BWE_BREAKPOINT_ENABLED 1
-#define OCD_BWE_WATCHPOINT_ENABLED 3
-
-/* Constants for BWC1B:BWE */
-#define OCD_BWE_DISABLED 0
-#define OCD_BWE_BREAKPOINT_ENABLED 1
-#define OCD_BWE_WATCHPOINT_ENABLED 3
-
-/* Constants for BWC2A:BWE */
-#define OCD_BWE_DISABLED 0
-#define OCD_BWE_BREAKPOINT_ENABLED 1
-#define OCD_BWE_WATCHPOINT_ENABLED 3
-
-/* Constants for BWC2B:BWE */
-#define OCD_BWE_DISABLED 0
-#define OCD_BWE_BREAKPOINT_ENABLED 1
-#define OCD_BWE_WATCHPOINT_ENABLED 3
-
-/* Constants for BWC3A:SIZE */
-#define OCD_SIZE_BYTE_ACCESS 4
-#define OCD_SIZE_HALFWORD_ACCESS 5
-#define OCD_SIZE_WORD_ACCESS 6
-#define OCD_SIZE_DOUBLE_WORD_ACCESS 7
-
-/* Constants for BWC3A:BRW */
-#define OCD_BRW_READ_BREAK 0
-#define OCD_BRW_WRITE_BREAK 1
-#define OCD_BRW_ANY_ACCES_BREAK 2
-
-/* Constants for BWC3A:BWE */
-#define OCD_BWE_DISABLED 0
-#define OCD_BWE_BREAKPOINT_ENABLED 1
-#define OCD_BWE_WATCHPOINT_ENABLED 3
-
-/* Constants for BWC3B:SIZE */
-#define OCD_SIZE_BYTE_ACCESS 4
-#define OCD_SIZE_HALFWORD_ACCESS 5
-#define OCD_SIZE_WORD_ACCESS 6
-#define OCD_SIZE_DOUBLE_WORD_ACCESS 7
-
-/* Constants for BWC3B:BRW */
-#define OCD_BRW_READ_BREAK 0
-#define OCD_BRW_WRITE_BREAK 1
-#define OCD_BRW_ANY_ACCES_BREAK 2
-
-/* Constants for BWC3B:BWE */
-#define OCD_BWE_DISABLED 0
-#define OCD_BWE_BREAKPOINT_ENABLED 1
-#define OCD_BWE_WATCHPOINT_ENABLED 3
-
-/* Constants for EPC0:RNG */
-#define OCD_RNG_DISABLED 0
-#define OCD_RNG_EXCLUSIVE 1
-#define OCD_RNG_INCLUSIVE 2
-
-/* Constants for EPC1:RNG */
-#define OCD_RNG_DISABLED 0
-#define OCD_RNG_EXCLUSIVE 1
-#define OCD_RNG_INCLUSIVE 2
-
-/* Constants for EPC2:RNG */
-#define OCD_RNG_DISABLED 0
-#define OCD_RNG_EXCLUSIVE 1
-#define OCD_RNG_INCLUSIVE 2
-
-/* Constants for EPC2:DB */
-#define OCD_DB_DISABLED 0
-#define OCD_DB_CHAINED_B 1
-#define OCD_DB_CHAINED_A 2
-#define OCD_DB_AHAINED_A_AND_B 3
-
-/* Constants for EPC3:RNG */
-#define OCD_RNG_DISABLED 0
-#define OCD_RNG_EXCLUSIVE 1
-#define OCD_RNG_INCLUSIVE 2
-
-#ifndef __ASSEMBLER__
-
-/* Register access macros */
-static inline unsigned long __ocd_read(unsigned int reg)
-{
- return __builtin_mfdr(reg);
-}
-
-static inline void __ocd_write(unsigned int reg, unsigned long value)
-{
- __builtin_mtdr(reg, value);
-}
-
-#define ocd_read(reg) __ocd_read(OCD_##reg)
-#define ocd_write(reg, value) __ocd_write(OCD_##reg, value)
-
-struct task_struct;
-
-void ocd_enable(struct task_struct *child);
-void ocd_disable(struct task_struct *child);
-
-#endif /* !__ASSEMBLER__ */
-
-#endif /* __ASM_AVR32_OCD_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_PAGE_H
-#define __ASM_AVR32_PAGE_H
-
-#include <linux/const.h>
-
-/* PAGE_SHIFT determines the page size */
-#define PAGE_SHIFT 12
-#define PAGE_SIZE (_AC(1, UL) << PAGE_SHIFT)
-#define PAGE_MASK (~(PAGE_SIZE-1))
-#define PTE_MASK PAGE_MASK
-
-#ifndef __ASSEMBLY__
-
-#include <asm/addrspace.h>
-
-extern void clear_page(void *to);
-extern void copy_page(void *to, void *from);
-
-#define clear_user_page(page, vaddr, pg) clear_page(page)
-#define copy_user_page(to, from, vaddr, pg) copy_page(to, from)
-
-/*
- * These are used to make use of C type-checking..
- */
-typedef struct { unsigned long pte; } pte_t;
-typedef struct { unsigned long pgd; } pgd_t;
-typedef struct { unsigned long pgprot; } pgprot_t;
-typedef struct page *pgtable_t;
-
-#define pte_val(x) ((x).pte)
-#define pgd_val(x) ((x).pgd)
-#define pgprot_val(x) ((x).pgprot)
-
-#define __pte(x) ((pte_t) { (x) })
-#define __pgd(x) ((pgd_t) { (x) })
-#define __pgprot(x) ((pgprot_t) { (x) })
-
-/* FIXME: These should be removed soon */
-extern unsigned long memory_start, memory_end;
-
-/* Pure 2^n version of get_order */
-static inline int get_order(unsigned long size)
-{
- unsigned lz;
-
- size = (size - 1) >> PAGE_SHIFT;
- asm("clz %0, %1" : "=r"(lz) : "r"(size));
- return 32 - lz;
-}
-
-#endif /* !__ASSEMBLY__ */
-
-/*
- * The hardware maps the virtual addresses 0x80000000 -> 0x9fffffff
- * permanently to the physical addresses 0x00000000 -> 0x1fffffff when
- * segmentation is enabled. We want to make use of this in order to
- * minimize TLB pressure.
- */
-#define PAGE_OFFSET (0x80000000UL)
-
-/*
- * ALSA uses virt_to_page() on DMA pages, which I'm not entirely sure
- * is a good idea. Anyway, we can't simply subtract PAGE_OFFSET here
- * in that case, so we'll have to mask out the three most significant
- * bits of the address instead...
- *
- * What's the difference between __pa() and virt_to_phys() anyway?
- */
-#define __pa(x) PHYSADDR(x)
-#define __va(x) ((void *)(P1SEGADDR(x)))
-
-#define MAP_NR(addr) (((unsigned long)(addr) - PAGE_OFFSET) >> PAGE_SHIFT)
-
-#define phys_to_page(phys) (pfn_to_page(phys >> PAGE_SHIFT))
-#define page_to_phys(page) (page_to_pfn(page) << PAGE_SHIFT)
-
-#ifndef CONFIG_NEED_MULTIPLE_NODES
-
-#define ARCH_PFN_OFFSET (CONFIG_PHYS_OFFSET >> PAGE_SHIFT)
-
-#define pfn_valid(pfn) ((pfn) >= ARCH_PFN_OFFSET && (pfn) < (ARCH_PFN_OFFSET + max_mapnr))
-#endif /* CONFIG_NEED_MULTIPLE_NODES */
-
-#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
-#define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
-
-#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | \
- VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
-
-/*
- * Memory above this physical address will be considered highmem.
- */
-#define HIGHMEM_START 0x20000000UL
-
-#include <asm-generic/memory_model.h>
-
-#endif /* __ASM_AVR32_PAGE_H */
+++ /dev/null
-#ifndef __ASM_AVR32_PCI_H__
-#define __ASM_AVR32_PCI_H__
-
-/* We don't support PCI yet, but some drivers require this file anyway */
-
-#define PCI_DMA_BUS_IS_PHYS (1)
-
-#endif /* __ASM_AVR32_PCI_H__ */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_PGALLOC_H
-#define __ASM_AVR32_PGALLOC_H
-
-#include <linux/mm.h>
-#include <linux/quicklist.h>
-#include <asm/page.h>
-#include <asm/pgtable.h>
-
-#define QUICK_PGD 0 /* Preserve kernel mappings over free */
-#define QUICK_PT 1 /* Zero on free */
-
-static inline void pmd_populate_kernel(struct mm_struct *mm,
- pmd_t *pmd, pte_t *pte)
-{
- set_pmd(pmd, __pmd((unsigned long)pte));
-}
-
-static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
- pgtable_t pte)
-{
- set_pmd(pmd, __pmd((unsigned long)page_address(pte)));
-}
-#define pmd_pgtable(pmd) pmd_page(pmd)
-
-static inline void pgd_ctor(void *x)
-{
- pgd_t *pgd = x;
-
- memcpy(pgd + USER_PTRS_PER_PGD,
- swapper_pg_dir + USER_PTRS_PER_PGD,
- (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
-}
-
-/*
- * Allocate and free page tables
- */
-static inline pgd_t *pgd_alloc(struct mm_struct *mm)
-{
- return quicklist_alloc(QUICK_PGD, GFP_KERNEL, pgd_ctor);
-}
-
-static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
-{
- quicklist_free(QUICK_PGD, NULL, pgd);
-}
-
-static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
- unsigned long address)
-{
- return quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL);
-}
-
-static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
- unsigned long address)
-{
- struct page *page;
- void *pg;
-
- pg = quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL);
- if (!pg)
- return NULL;
-
- page = virt_to_page(pg);
- if (!pgtable_page_ctor(page)) {
- quicklist_free(QUICK_PT, NULL, pg);
- return NULL;
- }
-
- return page;
-}
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
- quicklist_free(QUICK_PT, NULL, pte);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
-{
- pgtable_page_dtor(pte);
- quicklist_free_page(QUICK_PT, NULL, pte);
-}
-
-#define __pte_free_tlb(tlb,pte,addr) \
-do { \
- pgtable_page_dtor(pte); \
- tlb_remove_page((tlb), pte); \
-} while (0)
-
-static inline void check_pgt_cache(void)
-{
- quicklist_trim(QUICK_PGD, NULL, 25, 16);
- quicklist_trim(QUICK_PT, NULL, 25, 16);
-}
-
-#endif /* __ASM_AVR32_PGALLOC_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_PGTABLE_2LEVEL_H
-#define __ASM_AVR32_PGTABLE_2LEVEL_H
-
-#define __ARCH_USE_5LEVEL_HACK
-#include <asm-generic/pgtable-nopmd.h>
-
-/*
- * Traditional 2-level paging structure
- */
-#define PGDIR_SHIFT 22
-#define PTRS_PER_PGD 1024
-
-#define PTRS_PER_PTE 1024
-
-#ifndef __ASSEMBLY__
-#define pte_ERROR(e) \
- printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
-#define pgd_ERROR(e) \
- printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
-
-/*
- * Certain architectures need to do special things when PTEs
- * within a page table are directly modified. Thus, the following
- * hook is made available.
- */
-#define set_pte(pteptr, pteval) (*(pteptr) = pteval)
-#define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep, pteval)
-
-/*
- * (pmds are folded into pgds so this doesn't get actually called,
- * but the define is needed for a generic inline function.)
- */
-#define set_pmd(pmdptr, pmdval) (*(pmdptr) = pmdval)
-
-#define pte_pfn(x) ((unsigned long)(((x).pte >> PAGE_SHIFT)))
-#define pfn_pte(pfn, prot) __pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot))
-#define pfn_pmd(pfn, prot) __pmd(((pfn) << PAGE_SHIFT) | pgprot_val(prot))
-
-#endif /* !__ASSEMBLY__ */
-
-#endif /* __ASM_AVR32_PGTABLE_2LEVEL_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_PGTABLE_H
-#define __ASM_AVR32_PGTABLE_H
-
-#include <asm/addrspace.h>
-
-#ifndef __ASSEMBLY__
-#include <linux/sched.h>
-
-#endif /* !__ASSEMBLY__ */
-
-/*
- * Use two-level page tables just as the i386 (without PAE)
- */
-#include <asm/pgtable-2level.h>
-
-/*
- * The following code might need some cleanup when the values are
- * final...
- */
-#define PMD_SIZE (1UL << PMD_SHIFT)
-#define PMD_MASK (~(PMD_SIZE-1))
-#define PGDIR_SIZE (1UL << PGDIR_SHIFT)
-#define PGDIR_MASK (~(PGDIR_SIZE-1))
-
-#define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE)
-#define FIRST_USER_ADDRESS 0UL
-
-#ifndef __ASSEMBLY__
-extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
-extern void paging_init(void);
-
-/*
- * ZERO_PAGE is a global shared page that is always zero: used for
- * zero-mapped memory areas etc.
- */
-extern struct page *empty_zero_page;
-#define ZERO_PAGE(vaddr) (empty_zero_page)
-
-/*
- * Just any arbitrary offset to the start of the vmalloc VM area: the
- * current 8 MiB value just means that there will be a 8 MiB "hole"
- * after the uncached physical memory (P2 segment) until the vmalloc
- * area starts. That means that any out-of-bounds memory accesses will
- * hopefully be caught; we don't know if the end of the P1/P2 segments
- * are actually used for anything, but it is anyway safer to let the
- * MMU catch these kinds of errors than to rely on the memory bus.
- *
- * A "hole" of the same size is added to the end of the P3 segment as
- * well. It might seem wasteful to use 16 MiB of virtual address space
- * on this, but we do have 512 MiB of it...
- *
- * The vmalloc() routines leave a hole of 4 KiB between each vmalloced
- * area for the same reason.
- */
-#define VMALLOC_OFFSET (8 * 1024 * 1024)
-#define VMALLOC_START (P3SEG + VMALLOC_OFFSET)
-#define VMALLOC_END (P4SEG - VMALLOC_OFFSET)
-#endif /* !__ASSEMBLY__ */
-
-/*
- * Page flags. Some of these flags are not directly supported by
- * hardware, so we have to emulate them.
- */
-#define _TLBEHI_BIT_VALID 9
-#define _TLBEHI_VALID (1 << _TLBEHI_BIT_VALID)
-
-#define _PAGE_BIT_WT 0 /* W-bit : write-through */
-#define _PAGE_BIT_DIRTY 1 /* D-bit : page changed */
-#define _PAGE_BIT_SZ0 2 /* SZ0-bit : Size of page */
-#define _PAGE_BIT_SZ1 3 /* SZ1-bit : Size of page */
-#define _PAGE_BIT_EXECUTE 4 /* X-bit : execute access allowed */
-#define _PAGE_BIT_RW 5 /* AP0-bit : write access allowed */
-#define _PAGE_BIT_USER 6 /* AP1-bit : user space access allowed */
-#define _PAGE_BIT_BUFFER 7 /* B-bit : bufferable */
-#define _PAGE_BIT_GLOBAL 8 /* G-bit : global (ignore ASID) */
-#define _PAGE_BIT_CACHABLE 9 /* C-bit : cachable */
-
-/* If we drop support for 1K pages, we get two extra bits */
-#define _PAGE_BIT_PRESENT 10
-#define _PAGE_BIT_ACCESSED 11 /* software: page was accessed */
-
-#define _PAGE_WT (1 << _PAGE_BIT_WT)
-#define _PAGE_DIRTY (1 << _PAGE_BIT_DIRTY)
-#define _PAGE_EXECUTE (1 << _PAGE_BIT_EXECUTE)
-#define _PAGE_RW (1 << _PAGE_BIT_RW)
-#define _PAGE_USER (1 << _PAGE_BIT_USER)
-#define _PAGE_BUFFER (1 << _PAGE_BIT_BUFFER)
-#define _PAGE_GLOBAL (1 << _PAGE_BIT_GLOBAL)
-#define _PAGE_CACHABLE (1 << _PAGE_BIT_CACHABLE)
-
-/* Software flags */
-#define _PAGE_ACCESSED (1 << _PAGE_BIT_ACCESSED)
-#define _PAGE_PRESENT (1 << _PAGE_BIT_PRESENT)
-
-/*
- * Page types, i.e. sizes. _PAGE_TYPE_NONE corresponds to what is
- * usually called _PAGE_PROTNONE on other architectures.
- *
- * XXX: Find out if _PAGE_PROTNONE is equivalent with !_PAGE_USER. If
- * so, we can encode all possible page sizes (although we can't really
- * support 1K pages anyway due to the _PAGE_PRESENT and _PAGE_ACCESSED
- * bits)
- *
- */
-#define _PAGE_TYPE_MASK ((1 << _PAGE_BIT_SZ0) | (1 << _PAGE_BIT_SZ1))
-#define _PAGE_TYPE_NONE (0 << _PAGE_BIT_SZ0)
-#define _PAGE_TYPE_SMALL (1 << _PAGE_BIT_SZ0)
-#define _PAGE_TYPE_MEDIUM (2 << _PAGE_BIT_SZ0)
-#define _PAGE_TYPE_LARGE (3 << _PAGE_BIT_SZ0)
-
-/*
- * Mask which drop software flags. We currently can't handle more than
- * 512 MiB of physical memory, so we can use bits 29-31 for other
- * stuff. With a fixed 4K page size, we can use bits 10-11 as well as
- * bits 2-3 (SZ)
- */
-#define _PAGE_FLAGS_HARDWARE_MASK 0xfffff3ff
-
-#define _PAGE_FLAGS_CACHE_MASK (_PAGE_CACHABLE | _PAGE_BUFFER | _PAGE_WT)
-
-/* Flags that may be modified by software */
-#define _PAGE_CHG_MASK (PTE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY \
- | _PAGE_FLAGS_CACHE_MASK)
-
-#define _PAGE_FLAGS_READ (_PAGE_CACHABLE | _PAGE_BUFFER)
-#define _PAGE_FLAGS_WRITE (_PAGE_FLAGS_READ | _PAGE_RW | _PAGE_DIRTY)
-
-#define _PAGE_NORMAL(x) __pgprot((x) | _PAGE_PRESENT | _PAGE_TYPE_SMALL \
- | _PAGE_ACCESSED)
-
-#define PAGE_NONE (_PAGE_ACCESSED | _PAGE_TYPE_NONE)
-#define PAGE_READ (_PAGE_FLAGS_READ | _PAGE_USER)
-#define PAGE_EXEC (_PAGE_FLAGS_READ | _PAGE_EXECUTE | _PAGE_USER)
-#define PAGE_WRITE (_PAGE_FLAGS_WRITE | _PAGE_USER)
-#define PAGE_KERNEL _PAGE_NORMAL(_PAGE_FLAGS_WRITE | _PAGE_EXECUTE | _PAGE_GLOBAL)
-#define PAGE_KERNEL_RO _PAGE_NORMAL(_PAGE_FLAGS_READ | _PAGE_EXECUTE | _PAGE_GLOBAL)
-
-#define _PAGE_P(x) _PAGE_NORMAL((x) & ~(_PAGE_RW | _PAGE_DIRTY))
-#define _PAGE_S(x) _PAGE_NORMAL(x)
-
-#define PAGE_COPY _PAGE_P(PAGE_WRITE | PAGE_READ)
-#define PAGE_SHARED _PAGE_S(PAGE_WRITE | PAGE_READ)
-
-#ifndef __ASSEMBLY__
-/*
- * The hardware supports flags for write- and execute access. Read is
- * always allowed if the page is loaded into the TLB, so the "-w-",
- * "--x" and "-wx" mappings are implemented as "rw-", "r-x" and "rwx",
- * respectively.
- *
- * The "---" case is handled by software; the page will simply not be
- * loaded into the TLB if the page type is _PAGE_TYPE_NONE.
- */
-
-#define __P000 __pgprot(PAGE_NONE)
-#define __P001 _PAGE_P(PAGE_READ)
-#define __P010 _PAGE_P(PAGE_WRITE)
-#define __P011 _PAGE_P(PAGE_WRITE | PAGE_READ)
-#define __P100 _PAGE_P(PAGE_EXEC)
-#define __P101 _PAGE_P(PAGE_EXEC | PAGE_READ)
-#define __P110 _PAGE_P(PAGE_EXEC | PAGE_WRITE)
-#define __P111 _PAGE_P(PAGE_EXEC | PAGE_WRITE | PAGE_READ)
-
-#define __S000 __pgprot(PAGE_NONE)
-#define __S001 _PAGE_S(PAGE_READ)
-#define __S010 _PAGE_S(PAGE_WRITE)
-#define __S011 _PAGE_S(PAGE_WRITE | PAGE_READ)
-#define __S100 _PAGE_S(PAGE_EXEC)
-#define __S101 _PAGE_S(PAGE_EXEC | PAGE_READ)
-#define __S110 _PAGE_S(PAGE_EXEC | PAGE_WRITE)
-#define __S111 _PAGE_S(PAGE_EXEC | PAGE_WRITE | PAGE_READ)
-
-#define pte_none(x) (!pte_val(x))
-#define pte_present(x) (pte_val(x) & _PAGE_PRESENT)
-
-#define pte_clear(mm,addr,xp) \
- do { \
- set_pte_at(mm, addr, xp, __pte(0)); \
- } while (0)
-
-/*
- * The following only work if pte_present() is true.
- * Undefined behaviour if not..
- */
-static inline int pte_write(pte_t pte)
-{
- return pte_val(pte) & _PAGE_RW;
-}
-static inline int pte_dirty(pte_t pte)
-{
- return pte_val(pte) & _PAGE_DIRTY;
-}
-static inline int pte_young(pte_t pte)
-{
- return pte_val(pte) & _PAGE_ACCESSED;
-}
-static inline int pte_special(pte_t pte)
-{
- return 0;
-}
-
-/* Mutator functions for PTE bits */
-static inline pte_t pte_wrprotect(pte_t pte)
-{
- set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_RW));
- return pte;
-}
-static inline pte_t pte_mkclean(pte_t pte)
-{
- set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_DIRTY));
- return pte;
-}
-static inline pte_t pte_mkold(pte_t pte)
-{
- set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_ACCESSED));
- return pte;
-}
-static inline pte_t pte_mkwrite(pte_t pte)
-{
- set_pte(&pte, __pte(pte_val(pte) | _PAGE_RW));
- return pte;
-}
-static inline pte_t pte_mkdirty(pte_t pte)
-{
- set_pte(&pte, __pte(pte_val(pte) | _PAGE_DIRTY));
- return pte;
-}
-static inline pte_t pte_mkyoung(pte_t pte)
-{
- set_pte(&pte, __pte(pte_val(pte) | _PAGE_ACCESSED));
- return pte;
-}
-static inline pte_t pte_mkspecial(pte_t pte)
-{
- return pte;
-}
-
-#define pmd_none(x) (!pmd_val(x))
-#define pmd_present(x) (pmd_val(x))
-
-static inline void pmd_clear(pmd_t *pmdp)
-{
- set_pmd(pmdp, __pmd(0));
-}
-
-#define pmd_bad(x) (pmd_val(x) & ~PAGE_MASK)
-
-/*
- * Permanent address of a page. We don't support highmem, so this is
- * trivial.
- */
-#define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT))
-#define pte_page(x) (pfn_to_page(pte_pfn(x)))
-
-/*
- * Mark the prot value as uncacheable and unbufferable
- */
-#define pgprot_noncached(prot) \
- __pgprot(pgprot_val(prot) & ~(_PAGE_BUFFER | _PAGE_CACHABLE))
-
-/*
- * Mark the prot value as uncacheable but bufferable
- */
-#define pgprot_writecombine(prot) \
- __pgprot((pgprot_val(prot) & ~_PAGE_CACHABLE) | _PAGE_BUFFER)
-
-/*
- * Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- *
- * extern pte_t mk_pte(struct page *page, pgprot_t pgprot)
- */
-#define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot))
-
-static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
-{
- set_pte(&pte, __pte((pte_val(pte) & _PAGE_CHG_MASK)
- | pgprot_val(newprot)));
- return pte;
-}
-
-#define page_pte(page) page_pte_prot(page, __pgprot(0))
-
-#define pmd_page_vaddr(pmd) pmd_val(pmd)
-#define pmd_page(pmd) (virt_to_page(pmd_val(pmd)))
-
-/* to find an entry in a page-table-directory. */
-#define pgd_index(address) (((address) >> PGDIR_SHIFT) \
- & (PTRS_PER_PGD - 1))
-#define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address))
-
-/* to find an entry in a kernel page-table-directory */
-#define pgd_offset_k(address) pgd_offset(&init_mm, address)
-
-/* Find an entry in the third-level page table.. */
-#define pte_index(address) \
- ((address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
-#define pte_offset(dir, address) \
- ((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(address))
-#define pte_offset_kernel(dir, address) \
- ((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(address))
-#define pte_offset_map(dir, address) pte_offset_kernel(dir, address)
-#define pte_unmap(pte) do { } while (0)
-
-struct vm_area_struct;
-extern void update_mmu_cache(struct vm_area_struct * vma,
- unsigned long address, pte_t *ptep);
-
-/*
- * Encode and decode a swap entry
- *
- * Constraints:
- * _PAGE_TYPE_* at bits 2-3 (for emulating _PAGE_PROTNONE)
- * _PAGE_PRESENT at bit 10
- *
- * We encode the type into bits 4-9 and offset into bits 11-31. This
- * gives us a 21 bits offset, or 2**21 * 4K = 8G usable swap space per
- * device, and 64 possible types.
- *
- * NOTE: We should set ZEROs at the position of _PAGE_PRESENT
- * and _PAGE_PROTNONE bits
- */
-#define __swp_type(x) (((x).val >> 4) & 0x3f)
-#define __swp_offset(x) ((x).val >> 11)
-#define __swp_entry(type, offset) ((swp_entry_t) { ((type) << 4) | ((offset) << 11) })
-#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
-#define __swp_entry_to_pte(x) ((pte_t) { (x).val })
-
-typedef pte_t *pte_addr_t;
-
-#define kern_addr_valid(addr) (1)
-
-/* No page table caches to initialize (?) */
-#define pgtable_cache_init() do { } while(0)
-
-#include <asm-generic/pgtable.h>
-
-#endif /* !__ASSEMBLY__ */
-
-#endif /* __ASM_AVR32_PGTABLE_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_PROCESSOR_H
-#define __ASM_AVR32_PROCESSOR_H
-
-#include <asm/page.h>
-#include <asm/cache.h>
-
-#define TASK_SIZE 0x80000000
-
-#ifdef __KERNEL__
-#define STACK_TOP TASK_SIZE
-#define STACK_TOP_MAX STACK_TOP
-#endif
-
-#ifndef __ASSEMBLY__
-
-static inline void *current_text_addr(void)
-{
- register void *pc asm("pc");
- return pc;
-}
-
-enum arch_type {
- ARCH_AVR32A,
- ARCH_AVR32B,
- ARCH_MAX
-};
-
-enum cpu_type {
- CPU_MORGAN,
- CPU_AT32AP,
- CPU_MAX
-};
-
-enum tlb_config {
- TLB_NONE,
- TLB_SPLIT,
- TLB_UNIFIED,
- TLB_INVALID
-};
-
-#define AVR32_FEATURE_RMW (1 << 0)
-#define AVR32_FEATURE_DSP (1 << 1)
-#define AVR32_FEATURE_SIMD (1 << 2)
-#define AVR32_FEATURE_OCD (1 << 3)
-#define AVR32_FEATURE_PCTR (1 << 4)
-#define AVR32_FEATURE_JAVA (1 << 5)
-#define AVR32_FEATURE_FPU (1 << 6)
-
-struct avr32_cpuinfo {
- struct clk *clk;
- unsigned long loops_per_jiffy;
- enum arch_type arch_type;
- enum cpu_type cpu_type;
- unsigned short arch_revision;
- unsigned short cpu_revision;
- enum tlb_config tlb_config;
- unsigned long features;
- u32 device_id;
-
- struct cache_info icache;
- struct cache_info dcache;
-};
-
-static inline unsigned int avr32_get_manufacturer_id(struct avr32_cpuinfo *cpu)
-{
- return (cpu->device_id >> 1) & 0x7f;
-}
-static inline unsigned int avr32_get_product_number(struct avr32_cpuinfo *cpu)
-{
- return (cpu->device_id >> 12) & 0xffff;
-}
-static inline unsigned int avr32_get_chip_revision(struct avr32_cpuinfo *cpu)
-{
- return (cpu->device_id >> 28) & 0x0f;
-}
-
-extern struct avr32_cpuinfo boot_cpu_data;
-
-/* No SMP support so far */
-#define current_cpu_data boot_cpu_data
-
-/* This decides where the kernel will search for a free chunk of vm
- * space during mmap's
- */
-#define TASK_UNMAPPED_BASE (PAGE_ALIGN(TASK_SIZE / 3))
-
-#define cpu_relax() barrier()
-#define cpu_sync_pipeline() asm volatile("sub pc, -2" : : : "memory")
-
-struct cpu_context {
- unsigned long sr;
- unsigned long pc;
- unsigned long ksp; /* Kernel stack pointer */
- unsigned long r7;
- unsigned long r6;
- unsigned long r5;
- unsigned long r4;
- unsigned long r3;
- unsigned long r2;
- unsigned long r1;
- unsigned long r0;
-};
-
-/* This struct contains the CPU context as stored by switch_to() */
-struct thread_struct {
- struct cpu_context cpu_context;
- unsigned long single_step_addr;
- u16 single_step_insn;
-};
-
-#define INIT_THREAD { \
- .cpu_context = { \
- .ksp = sizeof(init_stack) + (long)&init_stack, \
- }, \
-}
-
-/*
- * Do necessary setup to start up a newly executed thread.
- */
-#define start_thread(regs, new_pc, new_sp) \
- do { \
- memset(regs, 0, sizeof(*regs)); \
- regs->sr = MODE_USER; \
- regs->pc = new_pc & ~1; \
- regs->sp = new_sp; \
- } while(0)
-
-struct task_struct;
-
-/* Free all resources held by a thread */
-extern void release_thread(struct task_struct *);
-
-/* Return saved PC of a blocked thread */
-#define thread_saved_pc(tsk) ((tsk)->thread.cpu_context.pc)
-
-struct pt_regs;
-extern unsigned long get_wchan(struct task_struct *p);
-extern void show_regs_log_lvl(struct pt_regs *regs, const char *log_lvl);
-extern void show_stack_log_lvl(struct task_struct *tsk, unsigned long sp,
- struct pt_regs *regs, const char *log_lvl);
-
-#define task_pt_regs(p) \
- ((struct pt_regs *)(THREAD_SIZE + task_stack_page(p)) - 1)
-
-#define KSTK_EIP(tsk) ((tsk)->thread.cpu_context.pc)
-#define KSTK_ESP(tsk) ((tsk)->thread.cpu_context.ksp)
-
-#define ARCH_HAS_PREFETCH
-
-static inline void prefetch(const void *x)
-{
- const char *c = x;
- asm volatile("pref %0" : : "r"(c));
-}
-#define PREFETCH_STRIDE L1_CACHE_BYTES
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* __ASM_AVR32_PROCESSOR_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_PTRACE_H
-#define __ASM_AVR32_PTRACE_H
-
-#include <uapi/asm/ptrace.h>
-
-#ifndef __ASSEMBLY__
-
-#include <asm/ocd.h>
-
-#define arch_has_single_step() (1)
-
-#define arch_ptrace_attach(child) ocd_enable(child)
-
-#define user_mode(regs) (((regs)->sr & MODE_MASK) == MODE_USER)
-#define instruction_pointer(regs) ((regs)->pc)
-#define profile_pc(regs) instruction_pointer(regs)
-#define user_stack_pointer(regs) ((regs)->sp)
-
-static __inline__ int valid_user_regs(struct pt_regs *regs)
-{
- /*
- * Some of the Java bits might be acceptable if/when we
- * implement some support for that stuff...
- */
- if ((regs->sr & 0xffff0000) == 0)
- return 1;
-
- /*
- * Force status register flags to be sane and report this
- * illegal behaviour...
- */
- regs->sr &= 0x0000ffff;
- return 0;
-}
-
-
-#endif /* ! __ASSEMBLY__ */
-#endif /* __ASM_AVR32_PTRACE_H */
+++ /dev/null
-#ifndef _ASM_SERIAL_H
-#define _ASM_SERIAL_H
-
-/*
- * This assumes you have a 1.8432 MHz clock for your UART.
- *
- * It'd be nice if someone built a serial card with a 24.576 MHz
- * clock, since the 16550A is capable of handling a top speed of 1.5
- * megabits/second; but this requires the faster clock.
- */
-#define BASE_BAUD (1843200 / 16)
-
-#endif /* _ASM_SERIAL_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * Based on linux/include/asm-arm/setup.h
- * Copyright (C) 1997-1999 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_SETUP_H__
-#define __ASM_AVR32_SETUP_H__
-
-#include <uapi/asm/setup.h>
-
-
-/* Magic number indicating that a tag table is present */
-#define ATAG_MAGIC 0xa2a25441
-
-#ifndef __ASSEMBLY__
-
-/*
- * Generic memory range, used by several tags.
- *
- * addr is always physical.
- * size is measured in bytes.
- * next is for use by the OS, e.g. for grouping regions into
- * linked lists.
- */
-struct tag_mem_range {
- u32 addr;
- u32 size;
- struct tag_mem_range * next;
-};
-
-/* The list ends with an ATAG_NONE node. */
-#define ATAG_NONE 0x00000000
-
-struct tag_header {
- u32 size;
- u32 tag;
-};
-
-/* The list must start with an ATAG_CORE node */
-#define ATAG_CORE 0x54410001
-
-struct tag_core {
- u32 flags;
- u32 pagesize;
- u32 rootdev;
-};
-
-/* it is allowed to have multiple ATAG_MEM nodes */
-#define ATAG_MEM 0x54410002
-/* ATAG_MEM uses tag_mem_range */
-
-/* command line: \0 terminated string */
-#define ATAG_CMDLINE 0x54410003
-
-struct tag_cmdline {
- char cmdline[1]; /* this is the minimum size */
-};
-
-/* Ramdisk image (may be compressed) */
-#define ATAG_RDIMG 0x54410004
-/* ATAG_RDIMG uses tag_mem_range */
-
-/* Information about various clocks present in the system */
-#define ATAG_CLOCK 0x54410005
-
-struct tag_clock {
- u32 clock_id; /* Which clock are we talking about? */
- u32 clock_flags; /* Special features */
- u64 clock_hz; /* Clock speed in Hz */
-};
-
-/* The clock types we know about */
-#define CLOCK_BOOTCPU 0
-
-/* Memory reserved for the system (e.g. the bootloader) */
-#define ATAG_RSVD_MEM 0x54410006
-/* ATAG_RSVD_MEM uses tag_mem_range */
-
-/* Ethernet information */
-
-#define ATAG_ETHERNET 0x54410007
-
-struct tag_ethernet {
- u8 mac_index;
- u8 mii_phy_addr;
- u8 hw_address[6];
-};
-
-#define ETH_INVALID_PHY 0xff
-
-/* board information */
-#define ATAG_BOARDINFO 0x54410008
-
-struct tag_boardinfo {
- u32 board_number;
-};
-
-struct tag {
- struct tag_header hdr;
- union {
- struct tag_core core;
- struct tag_mem_range mem_range;
- struct tag_cmdline cmdline;
- struct tag_clock clock;
- struct tag_ethernet ethernet;
- struct tag_boardinfo boardinfo;
- } u;
-};
-
-struct tagtable {
- u32 tag;
- int (*parse)(struct tag *);
-};
-
-#define __tag __used __attribute__((__section__(".taglist.init")))
-#define __tagtable(tag, fn) \
- static struct tagtable __tagtable_##fn __tag = { tag, fn }
-
-#define tag_member_present(tag,member) \
- ((unsigned long)(&((struct tag *)0L)->member + 1) \
- <= (tag)->hdr.size * 4)
-
-#define tag_next(t) ((struct tag *)((u32 *)(t) + (t)->hdr.size))
-#define tag_size(type) ((sizeof(struct tag_header) + sizeof(struct type)) >> 2)
-
-#define for_each_tag(t,base) \
- for (t = base; t->hdr.size; t = tag_next(t))
-
-extern struct tag *bootloader_tags;
-
-extern resource_size_t fbmem_start;
-extern resource_size_t fbmem_size;
-extern u32 board_number;
-
-void setup_processor(void);
-
-#endif /* !__ASSEMBLY__ */
-
-#endif /* __ASM_AVR32_SETUP_H__ */
+++ /dev/null
-#ifndef __ASM_AVR32_SHMPARAM_H
-#define __ASM_AVR32_SHMPARAM_H
-
-#define SHMLBA PAGE_SIZE /* attach addr a multiple of this */
-
-#endif /* __ASM_AVR32_SHMPARAM_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_SIGNAL_H
-#define __ASM_AVR32_SIGNAL_H
-
-#include <uapi/asm/signal.h>
-
-/* Most things should be clean enough to redefine this at will, if care
- is taken to make libc match. */
-
-#define _NSIG 64
-#define _NSIG_BPW 32
-#define _NSIG_WORDS (_NSIG / _NSIG_BPW)
-
-typedef unsigned long old_sigset_t; /* at least 32 bits */
-
-typedef struct {
- unsigned long sig[_NSIG_WORDS];
-} sigset_t;
-
-#define __ARCH_HAS_SA_RESTORER
-
-#include <asm/sigcontext.h>
-#undef __HAVE_ARCH_SIG_BITOPS
-
-#endif
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_STRING_H
-#define __ASM_AVR32_STRING_H
-
-#define __HAVE_ARCH_MEMSET
-extern void *memset(void *b, int c, size_t len);
-
-#define __HAVE_ARCH_MEMCPY
-extern void *memcpy(void *to, const void *from, size_t len);
-
-#endif /* __ASM_AVR32_STRING_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_SWITCH_TO_H
-#define __ASM_AVR32_SWITCH_TO_H
-
-/*
- * Help PathFinder and other Nexus-compliant debuggers keep track of
- * the current PID by emitting an Ownership Trace Message each time we
- * switch task.
- */
-#ifdef CONFIG_OWNERSHIP_TRACE
-#include <asm/ocd.h>
-#define ocd_switch(prev, next) \
- do { \
- ocd_write(PID, prev->pid); \
- ocd_write(PID, next->pid); \
- } while(0)
-#else
-#define ocd_switch(prev, next)
-#endif
-
-/*
- * switch_to(prev, next, last) should switch from task `prev' to task
- * `next'. `prev' will never be the same as `next'.
- *
- * We just delegate everything to the __switch_to assembly function,
- * which is implemented in arch/avr32/kernel/switch_to.S
- *
- * mb() tells GCC not to cache `current' across this call.
- */
-struct cpu_context;
-struct task_struct;
-extern struct task_struct *__switch_to(struct task_struct *,
- struct cpu_context *,
- struct cpu_context *);
-#define switch_to(prev, next, last) \
- do { \
- ocd_switch(prev, next); \
- last = __switch_to(prev, &prev->thread.cpu_context + 1, \
- &next->thread.cpu_context); \
- } while (0)
-
-
-#endif /* __ASM_AVR32_SWITCH_TO_H */
+++ /dev/null
-/*
- * syscalls.h - Linux syscall interfaces (arch-specific)
- *
- * Copyright (c) 2008 Jaswinder Singh
- *
- * This file is released under the GPLv2.
- * See the file COPYING for more details.
- */
-
-#ifndef _ASM_AVR32_SYSCALLS_H
-#define _ASM_AVR32_SYSCALLS_H
-
-#include <linux/compiler.h>
-#include <linux/linkage.h>
-#include <linux/types.h>
-#include <linux/signal.h>
-
-/* mm/cache.c */
-asmlinkage int sys_cacheflush(int, void __user *, size_t);
-
-#endif /* _ASM_AVR32_SYSCALLS_H */
+++ /dev/null
-/*
- * AVR32 System Registers
- *
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_SYSREG_H
-#define __ASM_AVR32_SYSREG_H
-
-/* sysreg register offsets */
-#define SYSREG_SR 0x0000
-#define SYSREG_EVBA 0x0004
-#define SYSREG_ACBA 0x0008
-#define SYSREG_CPUCR 0x000c
-#define SYSREG_ECR 0x0010
-#define SYSREG_RSR_SUP 0x0014
-#define SYSREG_RSR_INT0 0x0018
-#define SYSREG_RSR_INT1 0x001c
-#define SYSREG_RSR_INT2 0x0020
-#define SYSREG_RSR_INT3 0x0024
-#define SYSREG_RSR_EX 0x0028
-#define SYSREG_RSR_NMI 0x002c
-#define SYSREG_RSR_DBG 0x0030
-#define SYSREG_RAR_SUP 0x0034
-#define SYSREG_RAR_INT0 0x0038
-#define SYSREG_RAR_INT1 0x003c
-#define SYSREG_RAR_INT2 0x0040
-#define SYSREG_RAR_INT3 0x0044
-#define SYSREG_RAR_EX 0x0048
-#define SYSREG_RAR_NMI 0x004c
-#define SYSREG_RAR_DBG 0x0050
-#define SYSREG_JECR 0x0054
-#define SYSREG_JOSP 0x0058
-#define SYSREG_JAVA_LV0 0x005c
-#define SYSREG_JAVA_LV1 0x0060
-#define SYSREG_JAVA_LV2 0x0064
-#define SYSREG_JAVA_LV3 0x0068
-#define SYSREG_JAVA_LV4 0x006c
-#define SYSREG_JAVA_LV5 0x0070
-#define SYSREG_JAVA_LV6 0x0074
-#define SYSREG_JAVA_LV7 0x0078
-#define SYSREG_JTBA 0x007c
-#define SYSREG_JBCR 0x0080
-#define SYSREG_CONFIG0 0x0100
-#define SYSREG_CONFIG1 0x0104
-#define SYSREG_COUNT 0x0108
-#define SYSREG_COMPARE 0x010c
-#define SYSREG_TLBEHI 0x0110
-#define SYSREG_TLBELO 0x0114
-#define SYSREG_PTBR 0x0118
-#define SYSREG_TLBEAR 0x011c
-#define SYSREG_MMUCR 0x0120
-#define SYSREG_TLBARLO 0x0124
-#define SYSREG_TLBARHI 0x0128
-#define SYSREG_PCCNT 0x012c
-#define SYSREG_PCNT0 0x0130
-#define SYSREG_PCNT1 0x0134
-#define SYSREG_PCCR 0x0138
-#define SYSREG_BEAR 0x013c
-#define SYSREG_SABAL 0x0300
-#define SYSREG_SABAH 0x0304
-#define SYSREG_SABD 0x0308
-
-/* Bitfields in SR */
-#define SYSREG_SR_C_OFFSET 0
-#define SYSREG_SR_C_SIZE 1
-#define SYSREG_Z_OFFSET 1
-#define SYSREG_Z_SIZE 1
-#define SYSREG_SR_N_OFFSET 2
-#define SYSREG_SR_N_SIZE 1
-#define SYSREG_SR_V_OFFSET 3
-#define SYSREG_SR_V_SIZE 1
-#define SYSREG_Q_OFFSET 4
-#define SYSREG_Q_SIZE 1
-#define SYSREG_L_OFFSET 5
-#define SYSREG_L_SIZE 1
-#define SYSREG_T_OFFSET 14
-#define SYSREG_T_SIZE 1
-#define SYSREG_SR_R_OFFSET 15
-#define SYSREG_SR_R_SIZE 1
-#define SYSREG_GM_OFFSET 16
-#define SYSREG_GM_SIZE 1
-#define SYSREG_I0M_OFFSET 17
-#define SYSREG_I0M_SIZE 1
-#define SYSREG_I1M_OFFSET 18
-#define SYSREG_I1M_SIZE 1
-#define SYSREG_I2M_OFFSET 19
-#define SYSREG_I2M_SIZE 1
-#define SYSREG_I3M_OFFSET 20
-#define SYSREG_I3M_SIZE 1
-#define SYSREG_EM_OFFSET 21
-#define SYSREG_EM_SIZE 1
-#define SYSREG_MODE_OFFSET 22
-#define SYSREG_MODE_SIZE 3
-#define SYSREG_M0_OFFSET 22
-#define SYSREG_M0_SIZE 1
-#define SYSREG_M1_OFFSET 23
-#define SYSREG_M1_SIZE 1
-#define SYSREG_M2_OFFSET 24
-#define SYSREG_M2_SIZE 1
-#define SYSREG_SR_D_OFFSET 26
-#define SYSREG_SR_D_SIZE 1
-#define SYSREG_DM_OFFSET 27
-#define SYSREG_DM_SIZE 1
-#define SYSREG_SR_J_OFFSET 28
-#define SYSREG_SR_J_SIZE 1
-#define SYSREG_H_OFFSET 29
-#define SYSREG_H_SIZE 1
-
-/* Bitfields in CPUCR */
-#define SYSREG_BI_OFFSET 0
-#define SYSREG_BI_SIZE 1
-#define SYSREG_BE_OFFSET 1
-#define SYSREG_BE_SIZE 1
-#define SYSREG_FE_OFFSET 2
-#define SYSREG_FE_SIZE 1
-#define SYSREG_RE_OFFSET 3
-#define SYSREG_RE_SIZE 1
-#define SYSREG_IBE_OFFSET 4
-#define SYSREG_IBE_SIZE 1
-#define SYSREG_IEE_OFFSET 5
-#define SYSREG_IEE_SIZE 1
-
-/* Bitfields in CONFIG0 */
-#define SYSREG_CONFIG0_R_OFFSET 0
-#define SYSREG_CONFIG0_R_SIZE 1
-#define SYSREG_CONFIG0_D_OFFSET 1
-#define SYSREG_CONFIG0_D_SIZE 1
-#define SYSREG_CONFIG0_S_OFFSET 2
-#define SYSREG_CONFIG0_S_SIZE 1
-#define SYSREG_CONFIG0_O_OFFSET 3
-#define SYSREG_CONFIG0_O_SIZE 1
-#define SYSREG_CONFIG0_P_OFFSET 4
-#define SYSREG_CONFIG0_P_SIZE 1
-#define SYSREG_CONFIG0_J_OFFSET 5
-#define SYSREG_CONFIG0_J_SIZE 1
-#define SYSREG_CONFIG0_F_OFFSET 6
-#define SYSREG_CONFIG0_F_SIZE 1
-#define SYSREG_MMUT_OFFSET 7
-#define SYSREG_MMUT_SIZE 3
-#define SYSREG_AR_OFFSET 10
-#define SYSREG_AR_SIZE 3
-#define SYSREG_AT_OFFSET 13
-#define SYSREG_AT_SIZE 3
-#define SYSREG_PROCESSORREVISION_OFFSET 16
-#define SYSREG_PROCESSORREVISION_SIZE 8
-#define SYSREG_PROCESSORID_OFFSET 24
-#define SYSREG_PROCESSORID_SIZE 8
-
-/* Bitfields in CONFIG1 */
-#define SYSREG_DASS_OFFSET 0
-#define SYSREG_DASS_SIZE 3
-#define SYSREG_DLSZ_OFFSET 3
-#define SYSREG_DLSZ_SIZE 3
-#define SYSREG_DSET_OFFSET 6
-#define SYSREG_DSET_SIZE 4
-#define SYSREG_IASS_OFFSET 10
-#define SYSREG_IASS_SIZE 3
-#define SYSREG_ILSZ_OFFSET 13
-#define SYSREG_ILSZ_SIZE 3
-#define SYSREG_ISET_OFFSET 16
-#define SYSREG_ISET_SIZE 4
-#define SYSREG_DMMUSZ_OFFSET 20
-#define SYSREG_DMMUSZ_SIZE 6
-#define SYSREG_IMMUSZ_OFFSET 26
-#define SYSREG_IMMUSZ_SIZE 6
-
-/* Bitfields in TLBEHI */
-#define SYSREG_ASID_OFFSET 0
-#define SYSREG_ASID_SIZE 8
-#define SYSREG_TLBEHI_I_OFFSET 8
-#define SYSREG_TLBEHI_I_SIZE 1
-#define SYSREG_TLBEHI_V_OFFSET 9
-#define SYSREG_TLBEHI_V_SIZE 1
-#define SYSREG_VPN_OFFSET 10
-#define SYSREG_VPN_SIZE 22
-
-/* Bitfields in TLBELO */
-#define SYSREG_W_OFFSET 0
-#define SYSREG_W_SIZE 1
-#define SYSREG_TLBELO_D_OFFSET 1
-#define SYSREG_TLBELO_D_SIZE 1
-#define SYSREG_SZ_OFFSET 2
-#define SYSREG_SZ_SIZE 2
-#define SYSREG_AP_OFFSET 4
-#define SYSREG_AP_SIZE 3
-#define SYSREG_B_OFFSET 7
-#define SYSREG_B_SIZE 1
-#define SYSREG_G_OFFSET 8
-#define SYSREG_G_SIZE 1
-#define SYSREG_TLBELO_C_OFFSET 9
-#define SYSREG_TLBELO_C_SIZE 1
-#define SYSREG_PFN_OFFSET 10
-#define SYSREG_PFN_SIZE 22
-
-/* Bitfields in MMUCR */
-#define SYSREG_E_OFFSET 0
-#define SYSREG_E_SIZE 1
-#define SYSREG_M_OFFSET 1
-#define SYSREG_M_SIZE 1
-#define SYSREG_MMUCR_I_OFFSET 2
-#define SYSREG_MMUCR_I_SIZE 1
-#define SYSREG_MMUCR_N_OFFSET 3
-#define SYSREG_MMUCR_N_SIZE 1
-#define SYSREG_MMUCR_S_OFFSET 4
-#define SYSREG_MMUCR_S_SIZE 1
-#define SYSREG_DLA_OFFSET 8
-#define SYSREG_DLA_SIZE 6
-#define SYSREG_DRP_OFFSET 14
-#define SYSREG_DRP_SIZE 6
-#define SYSREG_ILA_OFFSET 20
-#define SYSREG_ILA_SIZE 6
-#define SYSREG_IRP_OFFSET 26
-#define SYSREG_IRP_SIZE 6
-
-/* Bitfields in PCCR */
-#define SYSREG_PCCR_E_OFFSET 0
-#define SYSREG_PCCR_E_SIZE 1
-#define SYSREG_PCCR_R_OFFSET 1
-#define SYSREG_PCCR_R_SIZE 1
-#define SYSREG_PCCR_C_OFFSET 2
-#define SYSREG_PCCR_C_SIZE 1
-#define SYSREG_PCCR_S_OFFSET 3
-#define SYSREG_PCCR_S_SIZE 1
-#define SYSREG_IEC_OFFSET 4
-#define SYSREG_IEC_SIZE 1
-#define SYSREG_IE0_OFFSET 5
-#define SYSREG_IE0_SIZE 1
-#define SYSREG_IE1_OFFSET 6
-#define SYSREG_IE1_SIZE 1
-#define SYSREG_FC_OFFSET 8
-#define SYSREG_FC_SIZE 1
-#define SYSREG_F0_OFFSET 9
-#define SYSREG_F0_SIZE 1
-#define SYSREG_F1_OFFSET 10
-#define SYSREG_F1_SIZE 1
-#define SYSREG_CONF0_OFFSET 12
-#define SYSREG_CONF0_SIZE 6
-#define SYSREG_CONF1_OFFSET 18
-#define SYSREG_CONF1_SIZE 6
-
-/* Constants for ECR */
-#define ECR_UNRECOVERABLE 0
-#define ECR_TLB_MULTIPLE 1
-#define ECR_BUS_ERROR_WRITE 2
-#define ECR_BUS_ERROR_READ 3
-#define ECR_NMI 4
-#define ECR_ADDR_ALIGN_X 5
-#define ECR_PROTECTION_X 6
-#define ECR_DEBUG 7
-#define ECR_ILLEGAL_OPCODE 8
-#define ECR_UNIMPL_INSTRUCTION 9
-#define ECR_PRIVILEGE_VIOLATION 10
-#define ECR_FPE 11
-#define ECR_COPROC_ABSENT 12
-#define ECR_ADDR_ALIGN_R 13
-#define ECR_ADDR_ALIGN_W 14
-#define ECR_PROTECTION_R 15
-#define ECR_PROTECTION_W 16
-#define ECR_DTLB_MODIFIED 17
-#define ECR_TLB_MISS_X 20
-#define ECR_TLB_MISS_R 24
-#define ECR_TLB_MISS_W 28
-
-/* Bit manipulation macros */
-#define SYSREG_BIT(name) \
- (1 << SYSREG_##name##_OFFSET)
-#define SYSREG_BF(name,value) \
- (((value) & ((1 << SYSREG_##name##_SIZE) - 1)) \
- << SYSREG_##name##_OFFSET)
-#define SYSREG_BFEXT(name,value)\
- (((value) >> SYSREG_##name##_OFFSET) \
- & ((1 << SYSREG_##name##_SIZE) - 1))
-#define SYSREG_BFINS(name,value,old) \
- (((old) & ~(((1 << SYSREG_##name##_SIZE) - 1) \
- << SYSREG_##name##_OFFSET)) \
- | SYSREG_BF(name,value))
-
-/* Register access macros */
-#ifdef __CHECKER__
-extern unsigned long __builtin_mfsr(unsigned long reg);
-extern void __builtin_mtsr(unsigned long reg, unsigned long value);
-#endif
-
-#define sysreg_read(reg) __builtin_mfsr(SYSREG_##reg)
-#define sysreg_write(reg, value) __builtin_mtsr(SYSREG_##reg, value)
-
-#endif /* __ASM_AVR32_SYSREG_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_TERMIOS_H
-#define __ASM_AVR32_TERMIOS_H
-
-#include <uapi/asm/termios.h>
-
-/* intr=^C quit=^\ erase=del kill=^U
- eof=^D vtime=\0 vmin=\1 sxtc=\0
- start=^Q stop=^S susp=^Z eol=\0
- reprint=^R discard=^U werase=^W lnext=^V
- eol2=\0
-*/
-#define INIT_C_CC "\003\034\177\025\004\0\1\0\021\023\032\0\022\017\027\026\0"
-
-#include <asm-generic/termios-base.h>
-
-#endif /* __ASM_AVR32_TERMIOS_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_THREAD_INFO_H
-#define __ASM_AVR32_THREAD_INFO_H
-
-#include <asm/page.h>
-
-#define THREAD_SIZE_ORDER 1
-#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER)
-
-#ifndef __ASSEMBLY__
-#include <asm/types.h>
-
-struct task_struct;
-
-struct thread_info {
- struct task_struct *task; /* main task structure */
- unsigned long flags; /* low level flags */
- __u32 cpu;
- __s32 preempt_count; /* 0 => preemptable, <0 => BUG */
- __u32 rar_saved; /* return address... */
- __u32 rsr_saved; /* ...and status register
- saved by debug handler
- when setting up
- trampoline */
- __u8 supervisor_stack[0];
-};
-
-#define INIT_THREAD_INFO(tsk) \
-{ \
- .task = &tsk, \
- .flags = 0, \
- .cpu = 0, \
- .preempt_count = INIT_PREEMPT_COUNT, \
-}
-
-#define init_thread_info (init_thread_union.thread_info)
-#define init_stack (init_thread_union.stack)
-
-/*
- * Get the thread information struct from C.
- * We do the usual trick and use the lower end of the stack for this
- */
-static inline struct thread_info *current_thread_info(void)
-{
- unsigned long addr = ~(THREAD_SIZE - 1);
-
- asm("and %0, sp" : "=r"(addr) : "0"(addr));
- return (struct thread_info *)addr;
-}
-
-#define get_thread_info(ti) get_task_struct((ti)->task)
-#define put_thread_info(ti) put_task_struct((ti)->task)
-
-#endif /* !__ASSEMBLY__ */
-
-/*
- * Thread information flags
- * - these are process state flags that various assembly files may need to access
- * - pending work-to-be-done flags are in LSW
- * - other flags in MSW
- */
-#define TIF_SYSCALL_TRACE 0 /* syscall trace active */
-#define TIF_SIGPENDING 1 /* signal pending */
-#define TIF_NEED_RESCHED 2 /* rescheduling necessary */
-#define TIF_BREAKPOINT 4 /* enter monitor mode on return */
-#define TIF_SINGLE_STEP 5 /* single step in progress */
-#define TIF_MEMDIE 6 /* is terminating due to OOM killer */
-#define TIF_RESTORE_SIGMASK 7 /* restore signal mask in do_signal */
-#define TIF_CPU_GOING_TO_SLEEP 8 /* CPU is entering sleep 0 mode */
-#define TIF_NOTIFY_RESUME 9 /* callback before returning to user */
-#define TIF_DEBUG 30 /* debugging enabled */
-#define TIF_USERSPACE 31 /* true if FS sets userspace */
-
-#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE)
-#define _TIF_SIGPENDING (1 << TIF_SIGPENDING)
-#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
-#define _TIF_BREAKPOINT (1 << TIF_BREAKPOINT)
-#define _TIF_SINGLE_STEP (1 << TIF_SINGLE_STEP)
-#define _TIF_MEMDIE (1 << TIF_MEMDIE)
-#define _TIF_CPU_GOING_TO_SLEEP (1 << TIF_CPU_GOING_TO_SLEEP)
-#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
-
-/* Note: The masks below must never span more than 16 bits! */
-
-/* work to do on interrupt/exception return */
-#define _TIF_WORK_MASK \
- (_TIF_SIGPENDING \
- | _TIF_NOTIFY_RESUME \
- | _TIF_NEED_RESCHED \
- | _TIF_BREAKPOINT)
-
-/* work to do on any return to userspace */
-#define _TIF_ALLWORK_MASK (_TIF_WORK_MASK | _TIF_SYSCALL_TRACE)
-/* work to do on return from debug mode */
-#define _TIF_DBGWORK_MASK (_TIF_WORK_MASK & ~_TIF_BREAKPOINT)
-
-#endif /* __ASM_AVR32_THREAD_INFO_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_TIMEX_H
-#define __ASM_AVR32_TIMEX_H
-
-/*
- * This is the frequency of the timer used for Linux's timer interrupt.
- * The value should be defined as accurate as possible or under certain
- * circumstances Linux timekeeping might become inaccurate or fail.
- *
- * For many system the exact clockrate of the timer isn't known but due to
- * the way this value is used we can get away with a wrong value as long
- * as this value is:
- *
- * - a multiple of HZ
- * - a divisor of the actual rate
- *
- * 500000 is a good such cheat value.
- *
- * The obscure number 1193182 is the same as used by the original i8254
- * time in legacy PC hardware; the chip is never found in AVR32 systems.
- */
-#define CLOCK_TICK_RATE 500000 /* Underlying HZ */
-
-typedef unsigned long cycles_t;
-
-static inline cycles_t get_cycles (void)
-{
- return 0;
-}
-
-#define ARCH_HAS_READ_CURRENT_TIMER
-
-#endif /* __ASM_AVR32_TIMEX_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_TLB_H
-#define __ASM_AVR32_TLB_H
-
-#define tlb_start_vma(tlb, vma) \
- flush_cache_range(vma, vma->vm_start, vma->vm_end)
-
-#define tlb_end_vma(tlb, vma) \
- flush_tlb_range(vma, vma->vm_start, vma->vm_end)
-
-#define __tlb_remove_tlb_entry(tlb, pte, address) do { } while(0)
-
-/*
- * Flush whole TLB for MM
- */
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
-
-#include <asm-generic/tlb.h>
-
-/*
- * For debugging purposes
- */
-extern void show_dtlb_entry(unsigned int index);
-extern void dump_dtlb(void);
-
-#endif /* __ASM_AVR32_TLB_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_TLBFLUSH_H
-#define __ASM_AVR32_TLBFLUSH_H
-
-#include <asm/mmu.h>
-
-/*
- * TLB flushing:
- *
- * - flush_tlb() flushes the current mm struct TLBs
- * - flush_tlb_all() flushes all processes' TLB entries
- * - flush_tlb_mm(mm) flushes the specified mm context TLBs
- * - flush_tlb_page(vma, vmaddr) flushes one page
- * - flush_tlb_range(vma, start, end) flushes a range of pages
- * - flush_tlb_kernel_range(start, end) flushes a range of kernel pages
- */
-extern void flush_tlb(void);
-extern void flush_tlb_all(void);
-extern void flush_tlb_mm(struct mm_struct *mm);
-extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
- unsigned long end);
-extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long page);
-
-extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
-
-#endif /* __ASM_AVR32_TLBFLUSH_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_TRAPS_H
-#define __ASM_AVR32_TRAPS_H
-
-#include <linux/list.h>
-
-struct undef_hook {
- struct list_head node;
- u32 insn_mask;
- u32 insn_val;
- int (*fn)(struct pt_regs *regs, u32 insn);
-};
-
-void register_undef_hook(struct undef_hook *hook);
-void unregister_undef_hook(struct undef_hook *hook);
-
-#endif /* __ASM_AVR32_TRAPS_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_TYPES_H
-#define __ASM_AVR32_TYPES_H
-
-#include <uapi/asm/types.h>
-
-/*
- * These aren't exported outside the kernel to avoid name space clashes
- */
-
-#define BITS_PER_LONG 32
-
-#endif /* __ASM_AVR32_TYPES_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_UACCESS_H
-#define __ASM_AVR32_UACCESS_H
-
-#include <linux/errno.h>
-#include <linux/sched.h>
-
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
-typedef struct {
- unsigned int is_user_space;
-} mm_segment_t;
-
-/*
- * The fs value determines whether argument validity checking should be
- * performed or not. If get_fs() == USER_DS, checking is performed, with
- * get_fs() == KERNEL_DS, checking is bypassed.
- *
- * For historical reasons (Data Segment Register?), these macros are misnamed.
- */
-#define MAKE_MM_SEG(s) ((mm_segment_t) { (s) })
-#define segment_eq(a, b) ((a).is_user_space == (b).is_user_space)
-
-#define USER_ADDR_LIMIT 0x80000000
-
-#define KERNEL_DS MAKE_MM_SEG(0)
-#define USER_DS MAKE_MM_SEG(1)
-
-#define get_ds() (KERNEL_DS)
-
-static inline mm_segment_t get_fs(void)
-{
- return MAKE_MM_SEG(test_thread_flag(TIF_USERSPACE));
-}
-
-static inline void set_fs(mm_segment_t s)
-{
- if (s.is_user_space)
- set_thread_flag(TIF_USERSPACE);
- else
- clear_thread_flag(TIF_USERSPACE);
-}
-
-/*
- * Test whether a block of memory is a valid user space address.
- * Returns 0 if the range is valid, nonzero otherwise.
- *
- * We do the following checks:
- * 1. Is the access from kernel space?
- * 2. Does (addr + size) set the carry bit?
- * 3. Is (addr + size) a negative number (i.e. >= 0x80000000)?
- *
- * If yes on the first check, access is granted.
- * If no on any of the others, access is denied.
- */
-#define __range_ok(addr, size) \
- (test_thread_flag(TIF_USERSPACE) \
- && (((unsigned long)(addr) >= 0x80000000) \
- || ((unsigned long)(size) > 0x80000000) \
- || (((unsigned long)(addr) + (unsigned long)(size)) > 0x80000000)))
-
-#define access_ok(type, addr, size) (likely(__range_ok(addr, size) == 0))
-
-/* Generic arbitrary sized copy. Return the number of bytes NOT copied */
-extern __kernel_size_t __copy_user(void *to, const void *from,
- __kernel_size_t n);
-
-extern __kernel_size_t copy_to_user(void __user *to, const void *from,
- __kernel_size_t n);
-extern __kernel_size_t ___copy_from_user(void *to, const void __user *from,
- __kernel_size_t n);
-
-static inline __kernel_size_t __copy_to_user(void __user *to, const void *from,
- __kernel_size_t n)
-{
- return __copy_user((void __force *)to, from, n);
-}
-static inline __kernel_size_t __copy_from_user(void *to,
- const void __user *from,
- __kernel_size_t n)
-{
- return __copy_user(to, (const void __force *)from, n);
-}
-static inline __kernel_size_t copy_from_user(void *to,
- const void __user *from,
- __kernel_size_t n)
-{
- size_t res = ___copy_from_user(to, from, n);
- if (unlikely(res))
- memset(to + (n - res), 0, res);
- return res;
-}
-
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
-
-/*
- * put_user: - Write a simple value into user space.
- * @x: Value to copy to user space.
- * @ptr: Destination address, in user space.
- *
- * Context: User context only. This function may sleep if pagefaults are
- * enabled.
- *
- * This macro copies a single simple value from kernel space to user
- * space. It supports simple types like char and int, but not larger
- * data types like structures or arrays.
- *
- * @ptr must have pointer-to-simple-variable type, and @x must be assignable
- * to the result of dereferencing @ptr.
- *
- * Returns zero on success, or -EFAULT on error.
- */
-#define put_user(x, ptr) \
- __put_user_check((x), (ptr), sizeof(*(ptr)))
-
-/*
- * get_user: - Get a simple variable from user space.
- * @x: Variable to store result.
- * @ptr: Source address, in user space.
- *
- * Context: User context only. This function may sleep if pagefaults are
- * enabled.
- *
- * This macro copies a single simple variable from user space to kernel
- * space. It supports simple types like char and int, but not larger
- * data types like structures or arrays.
- *
- * @ptr must have pointer-to-simple-variable type, and the result of
- * dereferencing @ptr must be assignable to @x without a cast.
- *
- * Returns zero on success, or -EFAULT on error.
- * On error, the variable @x is set to zero.
- */
-#define get_user(x, ptr) \
- __get_user_check((x), (ptr), sizeof(*(ptr)))
-
-/*
- * __put_user: - Write a simple value into user space, with less checking.
- * @x: Value to copy to user space.
- * @ptr: Destination address, in user space.
- *
- * Context: User context only. This function may sleep if pagefaults are
- * enabled.
- *
- * This macro copies a single simple value from kernel space to user
- * space. It supports simple types like char and int, but not larger
- * data types like structures or arrays.
- *
- * @ptr must have pointer-to-simple-variable type, and @x must be assignable
- * to the result of dereferencing @ptr.
- *
- * Caller must check the pointer with access_ok() before calling this
- * function.
- *
- * Returns zero on success, or -EFAULT on error.
- */
-#define __put_user(x, ptr) \
- __put_user_nocheck((x), (ptr), sizeof(*(ptr)))
-
-/*
- * __get_user: - Get a simple variable from user space, with less checking.
- * @x: Variable to store result.
- * @ptr: Source address, in user space.
- *
- * Context: User context only. This function may sleep if pagefaults are
- * enabled.
- *
- * This macro copies a single simple variable from user space to kernel
- * space. It supports simple types like char and int, but not larger
- * data types like structures or arrays.
- *
- * @ptr must have pointer-to-simple-variable type, and the result of
- * dereferencing @ptr must be assignable to @x without a cast.
- *
- * Caller must check the pointer with access_ok() before calling this
- * function.
- *
- * Returns zero on success, or -EFAULT on error.
- * On error, the variable @x is set to zero.
- */
-#define __get_user(x, ptr) \
- __get_user_nocheck((x), (ptr), sizeof(*(ptr)))
-
-extern int __get_user_bad(void);
-extern int __put_user_bad(void);
-
-#define __get_user_nocheck(x, ptr, size) \
-({ \
- unsigned long __gu_val = 0; \
- int __gu_err = 0; \
- \
- switch (size) { \
- case 1: __get_user_asm("ub", __gu_val, ptr, __gu_err); break; \
- case 2: __get_user_asm("uh", __gu_val, ptr, __gu_err); break; \
- case 4: __get_user_asm("w", __gu_val, ptr, __gu_err); break; \
- default: __gu_err = __get_user_bad(); break; \
- } \
- \
- x = (__force typeof(*(ptr)))__gu_val; \
- __gu_err; \
-})
-
-#define __get_user_check(x, ptr, size) \
-({ \
- unsigned long __gu_val = 0; \
- const typeof(*(ptr)) __user * __gu_addr = (ptr); \
- int __gu_err = 0; \
- \
- if (access_ok(VERIFY_READ, __gu_addr, size)) { \
- switch (size) { \
- case 1: \
- __get_user_asm("ub", __gu_val, __gu_addr, \
- __gu_err); \
- break; \
- case 2: \
- __get_user_asm("uh", __gu_val, __gu_addr, \
- __gu_err); \
- break; \
- case 4: \
- __get_user_asm("w", __gu_val, __gu_addr, \
- __gu_err); \
- break; \
- default: \
- __gu_err = __get_user_bad(); \
- break; \
- } \
- } else { \
- __gu_err = -EFAULT; \
- } \
- x = (__force typeof(*(ptr)))__gu_val; \
- __gu_err; \
-})
-
-#define __get_user_asm(suffix, __gu_val, ptr, __gu_err) \
- asm volatile( \
- "1: ld." suffix " %1, %3 \n" \
- "2: \n" \
- " .subsection 1 \n" \
- "3: mov %0, %4 \n" \
- " rjmp 2b \n" \
- " .subsection 0 \n" \
- " .section __ex_table, \"a\" \n" \
- " .long 1b, 3b \n" \
- " .previous \n" \
- : "=r"(__gu_err), "=r"(__gu_val) \
- : "0"(__gu_err), "m"(*(ptr)), "i"(-EFAULT))
-
-#define __put_user_nocheck(x, ptr, size) \
-({ \
- typeof(*(ptr)) __pu_val; \
- int __pu_err = 0; \
- \
- __pu_val = (x); \
- switch (size) { \
- case 1: __put_user_asm("b", ptr, __pu_val, __pu_err); break; \
- case 2: __put_user_asm("h", ptr, __pu_val, __pu_err); break; \
- case 4: __put_user_asm("w", ptr, __pu_val, __pu_err); break; \
- case 8: __put_user_asm("d", ptr, __pu_val, __pu_err); break; \
- default: __pu_err = __put_user_bad(); break; \
- } \
- __pu_err; \
-})
-
-#define __put_user_check(x, ptr, size) \
-({ \
- typeof(*(ptr)) __pu_val; \
- typeof(*(ptr)) __user *__pu_addr = (ptr); \
- int __pu_err = 0; \
- \
- __pu_val = (x); \
- if (access_ok(VERIFY_WRITE, __pu_addr, size)) { \
- switch (size) { \
- case 1: \
- __put_user_asm("b", __pu_addr, __pu_val, \
- __pu_err); \
- break; \
- case 2: \
- __put_user_asm("h", __pu_addr, __pu_val, \
- __pu_err); \
- break; \
- case 4: \
- __put_user_asm("w", __pu_addr, __pu_val, \
- __pu_err); \
- break; \
- case 8: \
- __put_user_asm("d", __pu_addr, __pu_val, \
- __pu_err); \
- break; \
- default: \
- __pu_err = __put_user_bad(); \
- break; \
- } \
- } else { \
- __pu_err = -EFAULT; \
- } \
- __pu_err; \
-})
-
-#define __put_user_asm(suffix, ptr, __pu_val, __gu_err) \
- asm volatile( \
- "1: st." suffix " %1, %3 \n" \
- "2: \n" \
- " .subsection 1 \n" \
- "3: mov %0, %4 \n" \
- " rjmp 2b \n" \
- " .subsection 0 \n" \
- " .section __ex_table, \"a\" \n" \
- " .long 1b, 3b \n" \
- " .previous \n" \
- : "=r"(__gu_err), "=m"(*(ptr)) \
- : "0"(__gu_err), "r"(__pu_val), "i"(-EFAULT))
-
-extern __kernel_size_t clear_user(void __user *addr, __kernel_size_t size);
-extern __kernel_size_t __clear_user(void __user *addr, __kernel_size_t size);
-
-extern long strncpy_from_user(char *dst, const char __user *src, long count);
-extern long __strncpy_from_user(char *dst, const char __user *src, long count);
-
-extern long strnlen_user(const char __user *__s, long __n);
-extern long __strnlen_user(const char __user *__s, long __n);
-
-#define strlen_user(s) strnlen_user(s, ~0UL >> 1)
-
-struct exception_table_entry
-{
- unsigned long insn, fixup;
-};
-
-#endif /* __ASM_AVR32_UACCESS_H */
+++ /dev/null
-#ifndef __ASM_AVR32_UCONTEXT_H
-#define __ASM_AVR32_UCONTEXT_H
-
-struct ucontext {
- unsigned long uc_flags;
- struct ucontext * uc_link;
- stack_t uc_stack;
- struct sigcontext uc_mcontext;
- sigset_t uc_sigmask;
-};
-
-#endif /* __ASM_AVR32_UCONTEXT_H */
+++ /dev/null
-#ifndef _ASM_AVR32_UNALIGNED_H
-#define _ASM_AVR32_UNALIGNED_H
-
-/*
- * AVR32 can handle some unaligned accesses, depending on the
- * implementation. The AVR32 AP implementation can handle unaligned
- * words, but halfwords must be halfword-aligned, and doublewords must
- * be word-aligned.
- *
- * However, swapped word loads must be word-aligned so we can't
- * optimize word loads in general.
- */
-
-#include <linux/unaligned/be_struct.h>
-#include <linux/unaligned/le_byteshift.h>
-#include <linux/unaligned/generic.h>
-
-#define get_unaligned __get_unaligned_be
-#define put_unaligned __put_unaligned_be
-
-#endif /* _ASM_AVR32_UNALIGNED_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_UNISTD_H
-#define __ASM_AVR32_UNISTD_H
-
-#include <uapi/asm/unistd.h>
-
-#define NR_syscalls 321
-
-/* Old stuff */
-#define __IGNORE_uselib
-#define __IGNORE_mmap
-
-/* NUMA stuff */
-#define __IGNORE_mbind
-#define __IGNORE_get_mempolicy
-#define __IGNORE_set_mempolicy
-#define __IGNORE_migrate_pages
-#define __IGNORE_move_pages
-
-/* SMP stuff */
-#define __IGNORE_getcpu
-
-#define __ARCH_WANT_STAT64
-#define __ARCH_WANT_SYS_ALARM
-#define __ARCH_WANT_SYS_GETHOSTNAME
-#define __ARCH_WANT_SYS_PAUSE
-#define __ARCH_WANT_SYS_TIME
-#define __ARCH_WANT_SYS_UTIME
-#define __ARCH_WANT_SYS_WAITPID
-#define __ARCH_WANT_SYS_FADVISE64
-#define __ARCH_WANT_SYS_GETPGRP
-#define __ARCH_WANT_SYS_LLSEEK
-#define __ARCH_WANT_SYS_GETPGRP
-#define __ARCH_WANT_SYS_FORK
-#define __ARCH_WANT_SYS_VFORK
-#define __ARCH_WANT_SYS_CLONE
-
-#endif /* __ASM_AVR32_UNISTD_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Note: We may not need these definitions for AVR32, as we don't
- * support a.out.
- */
-#ifndef __ASM_AVR32_USER_H
-#define __ASM_AVR32_USER_H
-
-#include <linux/types.h>
-#include <asm/ptrace.h>
-#include <asm/page.h>
-
-/*
- * Core file format: The core file is written in such a way that gdb
- * can understand it and provide useful information to the user (under
- * linux we use the `trad-core' bfd). The file contents are as follows:
- *
- * upage: 1 page consisting of a user struct that tells gdb
- * what is present in the file. Directly after this is a
- * copy of the task_struct, which is currently not used by gdb,
- * but it may come in handy at some point. All of the registers
- * are stored as part of the upage. The upage should always be
- * only one page long.
- * data: The data segment follows next. We use current->end_text to
- * current->brk to pick up all of the user variables, plus any memory
- * that may have been sbrk'ed. No attempt is made to determine if a
- * page is demand-zero or if a page is totally unused, we just cover
- * the entire range. All of the addresses are rounded in such a way
- * that an integral number of pages is written.
- * stack: We need the stack information in order to get a meaningful
- * backtrace. We need to write the data from usp to
- * current->start_stack, so we round each of these in order to be able
- * to write an integer number of pages.
- */
-
-struct user_fpu_struct {
- /* We have no FPU (yet) */
-};
-
-struct user {
- struct pt_regs regs; /* entire machine state */
- size_t u_tsize; /* text size (pages) */
- size_t u_dsize; /* data size (pages) */
- size_t u_ssize; /* stack size (pages) */
- unsigned long start_code; /* text starting address */
- unsigned long start_data; /* data starting address */
- unsigned long start_stack; /* stack starting address */
- long int signal; /* signal causing core dump */
- unsigned long u_ar0; /* help gdb find registers */
- unsigned long magic; /* identifies a core file */
- char u_comm[32]; /* user command name */
-};
-
-#define NBPG PAGE_SIZE
-#define UPAGES 1
-#define HOST_TEXT_START_ADDR (u.start_code)
-#define HOST_DATA_START_ADDR (u.start_data)
-#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG)
-
-#endif /* __ASM_AVR32_USER_H */
+++ /dev/null
-# UAPI Header export list
-include include/uapi/asm-generic/Kbuild.asm
-
-header-y += auxvec.h
-header-y += byteorder.h
-header-y += cachectl.h
-header-y += msgbuf.h
-header-y += param.h
-header-y += posix_types.h
-header-y += ptrace.h
-header-y += sembuf.h
-header-y += setup.h
-header-y += shmbuf.h
-header-y += sigcontext.h
-header-y += signal.h
-header-y += socket.h
-header-y += sockios.h
-header-y += stat.h
-header-y += swab.h
-header-y += termbits.h
-header-y += termios.h
-header-y += types.h
-header-y += unistd.h
-generic-y += bitsperlong.h
-generic-y += errno.h
-generic-y += fcntl.h
-generic-y += ioctl.h
-generic-y += ioctls.h
-generic-y += ipcbuf.h
-generic-y += kvm_para.h
-generic-y += mman.h
-generic-y += param.h
-generic-y += poll.h
-generic-y += resource.h
-generic-y += siginfo.h
-generic-y += statfs.h
+++ /dev/null
-#ifndef _UAPI__ASM_AVR32_AUXVEC_H
-#define _UAPI__ASM_AVR32_AUXVEC_H
-
-#endif /* _UAPI__ASM_AVR32_AUXVEC_H */
+++ /dev/null
-/*
- * AVR32 endian-conversion functions.
- */
-#ifndef _UAPI__ASM_AVR32_BYTEORDER_H
-#define _UAPI__ASM_AVR32_BYTEORDER_H
-
-#include <linux/byteorder/big_endian.h>
-
-#endif /* _UAPI__ASM_AVR32_BYTEORDER_H */
+++ /dev/null
-#ifndef _UAPI__ASM_AVR32_CACHECTL_H
-#define _UAPI__ASM_AVR32_CACHECTL_H
-
-/*
- * Operations that can be performed through the cacheflush system call
- */
-
-/* Clean the data cache, then invalidate the icache */
-#define CACHE_IFLUSH 0
-
-#endif /* _UAPI__ASM_AVR32_CACHECTL_H */
+++ /dev/null
-#ifndef _UAPI__ASM_AVR32_MSGBUF_H
-#define _UAPI__ASM_AVR32_MSGBUF_H
-
-/*
- * The msqid64_ds structure for i386 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
- */
-
-struct msqid64_ds {
- struct ipc64_perm msg_perm;
- __kernel_time_t msg_stime; /* last msgsnd time */
- unsigned long __unused1;
- __kernel_time_t msg_rtime; /* last msgrcv time */
- unsigned long __unused2;
- __kernel_time_t msg_ctime; /* last change time */
- unsigned long __unused3;
- unsigned long msg_cbytes; /* current number of bytes on queue */
- unsigned long msg_qnum; /* number of messages in queue */
- unsigned long msg_qbytes; /* max number of bytes on queue */
- __kernel_pid_t msg_lspid; /* pid of last msgsnd */
- __kernel_pid_t msg_lrpid; /* last receive pid */
- unsigned long __unused4;
- unsigned long __unused5;
-};
-
-#endif /* _UAPI__ASM_AVR32_MSGBUF_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef _UAPI__ASM_AVR32_POSIX_TYPES_H
-#define _UAPI__ASM_AVR32_POSIX_TYPES_H
-
-/*
- * This file is generally used by user-level software, so you need to
- * be a little careful about namespace pollution etc. Also, we cannot
- * assume GCC is being used.
- */
-
-typedef unsigned short __kernel_mode_t;
-#define __kernel_mode_t __kernel_mode_t
-
-typedef unsigned short __kernel_ipc_pid_t;
-#define __kernel_ipc_pid_t __kernel_ipc_pid_t
-
-typedef unsigned long __kernel_size_t;
-typedef long __kernel_ssize_t;
-typedef int __kernel_ptrdiff_t;
-#define __kernel_size_t __kernel_size_t
-
-typedef unsigned short __kernel_old_uid_t;
-typedef unsigned short __kernel_old_gid_t;
-#define __kernel_old_uid_t __kernel_old_uid_t
-
-typedef unsigned short __kernel_old_dev_t;
-#define __kernel_old_dev_t __kernel_old_dev_t
-
-#include <asm-generic/posix_types.h>
-
-#endif /* _UAPI__ASM_AVR32_POSIX_TYPES_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef _UAPI__ASM_AVR32_PTRACE_H
-#define _UAPI__ASM_AVR32_PTRACE_H
-
-#define PTRACE_GETREGS 12
-#define PTRACE_SETREGS 13
-
-/*
- * Status Register bits
- */
-#define SR_H 0x20000000
-#define SR_J 0x10000000
-#define SR_DM 0x08000000
-#define SR_D 0x04000000
-#define MODE_NMI 0x01c00000
-#define MODE_EXCEPTION 0x01800000
-#define MODE_INT3 0x01400000
-#define MODE_INT2 0x01000000
-#define MODE_INT1 0x00c00000
-#define MODE_INT0 0x00800000
-#define MODE_SUPERVISOR 0x00400000
-#define MODE_USER 0x00000000
-#define MODE_MASK 0x01c00000
-#define SR_EM 0x00200000
-#define SR_I3M 0x00100000
-#define SR_I2M 0x00080000
-#define SR_I1M 0x00040000
-#define SR_I0M 0x00020000
-#define SR_GM 0x00010000
-
-#define SR_H_BIT 29
-#define SR_J_BIT 28
-#define SR_DM_BIT 27
-#define SR_D_BIT 26
-#define MODE_SHIFT 22
-#define SR_EM_BIT 21
-#define SR_I3M_BIT 20
-#define SR_I2M_BIT 19
-#define SR_I1M_BIT 18
-#define SR_I0M_BIT 17
-#define SR_GM_BIT 16
-
-/* The user-visible part */
-#define SR_L 0x00000020
-#define SR_Q 0x00000010
-#define SR_V 0x00000008
-#define SR_N 0x00000004
-#define SR_Z 0x00000002
-#define SR_C 0x00000001
-
-#define SR_L_BIT 5
-#define SR_Q_BIT 4
-#define SR_V_BIT 3
-#define SR_N_BIT 2
-#define SR_Z_BIT 1
-#define SR_C_BIT 0
-
-/*
- * The order is defined by the stmts instruction. r0 is stored first,
- * so it gets the highest address.
- *
- * Registers 0-12 are general-purpose registers (r12 is normally used for
- * the function return value).
- * Register 13 is the stack pointer
- * Register 14 is the link register
- * Register 15 is the program counter (retrieved from the RAR sysreg)
- */
-#define FRAME_SIZE_FULL 72
-#define REG_R12_ORIG 68
-#define REG_R0 64
-#define REG_R1 60
-#define REG_R2 56
-#define REG_R3 52
-#define REG_R4 48
-#define REG_R5 44
-#define REG_R6 40
-#define REG_R7 36
-#define REG_R8 32
-#define REG_R9 28
-#define REG_R10 24
-#define REG_R11 20
-#define REG_R12 16
-#define REG_SP 12
-#define REG_LR 8
-
-#define FRAME_SIZE_MIN 8
-#define REG_PC 4
-#define REG_SR 0
-
-#ifndef __ASSEMBLY__
-struct pt_regs {
- /* These are always saved */
- unsigned long sr;
- unsigned long pc;
-
- /* These are sometimes saved */
- unsigned long lr;
- unsigned long sp;
- unsigned long r12;
- unsigned long r11;
- unsigned long r10;
- unsigned long r9;
- unsigned long r8;
- unsigned long r7;
- unsigned long r6;
- unsigned long r5;
- unsigned long r4;
- unsigned long r3;
- unsigned long r2;
- unsigned long r1;
- unsigned long r0;
-
- /* Only saved on system call */
- unsigned long r12_orig;
-};
-
-
-#endif /* ! __ASSEMBLY__ */
-
-#endif /* _UAPI__ASM_AVR32_PTRACE_H */
+++ /dev/null
-#ifndef _UAPI__ASM_AVR32_SEMBUF_H
-#define _UAPI__ASM_AVR32_SEMBUF_H
-
-/*
-* The semid64_ds structure for AVR32 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
- */
-
-struct semid64_ds {
- struct ipc64_perm sem_perm; /* permissions .. see ipc.h */
- __kernel_time_t sem_otime; /* last semop time */
- unsigned long __unused1;
- __kernel_time_t sem_ctime; /* last change time */
- unsigned long __unused2;
- unsigned long sem_nsems; /* no. of semaphores in array */
- unsigned long __unused3;
- unsigned long __unused4;
-};
-
-#endif /* _UAPI__ASM_AVR32_SEMBUF_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * Based on linux/include/asm-arm/setup.h
- * Copyright (C) 1997-1999 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef _UAPI__ASM_AVR32_SETUP_H__
-#define _UAPI__ASM_AVR32_SETUP_H__
-
-#define COMMAND_LINE_SIZE 256
-
-#endif /* _UAPI__ASM_AVR32_SETUP_H__ */
+++ /dev/null
-#ifndef _UAPI__ASM_AVR32_SHMBUF_H
-#define _UAPI__ASM_AVR32_SHMBUF_H
-
-/*
- * The shmid64_ds structure for i386 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
- */
-
-struct shmid64_ds {
- struct ipc64_perm shm_perm; /* operation perms */
- size_t shm_segsz; /* size of segment (bytes) */
- __kernel_time_t shm_atime; /* last attach time */
- unsigned long __unused1;
- __kernel_time_t shm_dtime; /* last detach time */
- unsigned long __unused2;
- __kernel_time_t shm_ctime; /* last change time */
- unsigned long __unused3;
- __kernel_pid_t shm_cpid; /* pid of creator */
- __kernel_pid_t shm_lpid; /* pid of last operator */
- unsigned long shm_nattch; /* no. of current attaches */
- unsigned long __unused4;
- unsigned long __unused5;
-};
-
-struct shminfo64 {
- unsigned long shmmax;
- unsigned long shmmin;
- unsigned long shmmni;
- unsigned long shmseg;
- unsigned long shmall;
- unsigned long __unused1;
- unsigned long __unused2;
- unsigned long __unused3;
- unsigned long __unused4;
-};
-
-#endif /* _UAPI__ASM_AVR32_SHMBUF_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef _UAPI__ASM_AVR32_SIGCONTEXT_H
-#define _UAPI__ASM_AVR32_SIGCONTEXT_H
-
-struct sigcontext {
- unsigned long oldmask;
-
- /* CPU registers */
- unsigned long sr;
- unsigned long pc;
- unsigned long lr;
- unsigned long sp;
- unsigned long r12;
- unsigned long r11;
- unsigned long r10;
- unsigned long r9;
- unsigned long r8;
- unsigned long r7;
- unsigned long r6;
- unsigned long r5;
- unsigned long r4;
- unsigned long r3;
- unsigned long r2;
- unsigned long r1;
- unsigned long r0;
-};
-
-#endif /* _UAPI__ASM_AVR32_SIGCONTEXT_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef _UAPI__ASM_AVR32_SIGNAL_H
-#define _UAPI__ASM_AVR32_SIGNAL_H
-
-#include <linux/types.h>
-
-/* Avoid too many header ordering problems. */
-struct siginfo;
-
-#ifndef __KERNEL__
-/* Here we must cater to libcs that poke about in kernel headers. */
-
-#define NSIG 32
-typedef unsigned long sigset_t;
-
-#endif /* __KERNEL__ */
-
-#define SIGHUP 1
-#define SIGINT 2
-#define SIGQUIT 3
-#define SIGILL 4
-#define SIGTRAP 5
-#define SIGABRT 6
-#define SIGIOT 6
-#define SIGBUS 7
-#define SIGFPE 8
-#define SIGKILL 9
-#define SIGUSR1 10
-#define SIGSEGV 11
-#define SIGUSR2 12
-#define SIGPIPE 13
-#define SIGALRM 14
-#define SIGTERM 15
-#define SIGSTKFLT 16
-#define SIGCHLD 17
-#define SIGCONT 18
-#define SIGSTOP 19
-#define SIGTSTP 20
-#define SIGTTIN 21
-#define SIGTTOU 22
-#define SIGURG 23
-#define SIGXCPU 24
-#define SIGXFSZ 25
-#define SIGVTALRM 26
-#define SIGPROF 27
-#define SIGWINCH 28
-#define SIGIO 29
-#define SIGPOLL SIGIO
-/*
-#define SIGLOST 29
-*/
-#define SIGPWR 30
-#define SIGSYS 31
-#define SIGUNUSED 31
-
-/* These should not be considered constants from userland. */
-#define SIGRTMIN 32
-#define SIGRTMAX (_NSIG-1)
-
-/*
- * SA_FLAGS values:
- *
- * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop.
- * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies.
- * SA_SIGINFO deliver the signal with SIGINFO structs
- * SA_ONSTACK indicates that a registered stack_t will be used.
- * SA_RESTART flag to get restarting signals (which were the default long ago)
- * SA_NODEFER prevents the current signal from being masked in the handler.
- * SA_RESETHAND clears the handler when the signal is delivered.
- *
- * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single
- * Unix names RESETHAND and NODEFER respectively.
- */
-#define SA_NOCLDSTOP 0x00000001
-#define SA_NOCLDWAIT 0x00000002
-#define SA_SIGINFO 0x00000004
-#define SA_RESTORER 0x04000000
-#define SA_ONSTACK 0x08000000
-#define SA_RESTART 0x10000000
-#define SA_NODEFER 0x40000000
-#define SA_RESETHAND 0x80000000
-
-#define SA_NOMASK SA_NODEFER
-#define SA_ONESHOT SA_RESETHAND
-
-#define MINSIGSTKSZ 2048
-#define SIGSTKSZ 8192
-
-#include <asm-generic/signal-defs.h>
-
-#ifndef __KERNEL__
-/* Here we must cater to libcs that poke about in kernel headers. */
-
-struct sigaction {
- union {
- __sighandler_t _sa_handler;
- void (*_sa_sigaction)(int, struct siginfo *, void *);
- } _u;
- sigset_t sa_mask;
- unsigned long sa_flags;
- void (*sa_restorer)(void);
-};
-
-#define sa_handler _u._sa_handler
-#define sa_sigaction _u._sa_sigaction
-
-#endif /* __KERNEL__ */
-
-typedef struct sigaltstack {
- void __user *ss_sp;
- int ss_flags;
- size_t ss_size;
-} stack_t;
-
-#endif /* _UAPI__ASM_AVR32_SIGNAL_H */
+++ /dev/null
-#ifndef _UAPI__ASM_AVR32_SOCKET_H
-#define _UAPI__ASM_AVR32_SOCKET_H
-
-#include <asm/sockios.h>
-
-/* For setsockopt(2) */
-#define SOL_SOCKET 1
-
-#define SO_DEBUG 1
-#define SO_REUSEADDR 2
-#define SO_TYPE 3
-#define SO_ERROR 4
-#define SO_DONTROUTE 5
-#define SO_BROADCAST 6
-#define SO_SNDBUF 7
-#define SO_RCVBUF 8
-#define SO_SNDBUFFORCE 32
-#define SO_RCVBUFFORCE 33
-#define SO_KEEPALIVE 9
-#define SO_OOBINLINE 10
-#define SO_NO_CHECK 11
-#define SO_PRIORITY 12
-#define SO_LINGER 13
-#define SO_BSDCOMPAT 14
-#define SO_REUSEPORT 15
-#define SO_PASSCRED 16
-#define SO_PEERCRED 17
-#define SO_RCVLOWAT 18
-#define SO_SNDLOWAT 19
-#define SO_RCVTIMEO 20
-#define SO_SNDTIMEO 21
-
-/* Security levels - as per NRL IPv6 - don't actually do anything */
-#define SO_SECURITY_AUTHENTICATION 22
-#define SO_SECURITY_ENCRYPTION_TRANSPORT 23
-#define SO_SECURITY_ENCRYPTION_NETWORK 24
-
-#define SO_BINDTODEVICE 25
-
-/* Socket filtering */
-#define SO_ATTACH_FILTER 26
-#define SO_DETACH_FILTER 27
-#define SO_GET_FILTER SO_ATTACH_FILTER
-
-#define SO_PEERNAME 28
-#define SO_TIMESTAMP 29
-#define SCM_TIMESTAMP SO_TIMESTAMP
-
-#define SO_ACCEPTCONN 30
-
-#define SO_PEERSEC 31
-#define SO_PASSSEC 34
-#define SO_TIMESTAMPNS 35
-#define SCM_TIMESTAMPNS SO_TIMESTAMPNS
-
-#define SO_MARK 36
-
-#define SO_TIMESTAMPING 37
-#define SCM_TIMESTAMPING SO_TIMESTAMPING
-
-#define SO_PROTOCOL 38
-#define SO_DOMAIN 39
-
-#define SO_RXQ_OVFL 40
-
-#define SO_WIFI_STATUS 41
-#define SCM_WIFI_STATUS SO_WIFI_STATUS
-#define SO_PEEK_OFF 42
-
-/* Instruct lower device to use last 4-bytes of skb data as FCS */
-#define SO_NOFCS 43
-
-#define SO_LOCK_FILTER 44
-
-#define SO_SELECT_ERR_QUEUE 45
-
-#define SO_BUSY_POLL 46
-
-#define SO_MAX_PACING_RATE 47
-
-#define SO_BPF_EXTENSIONS 48
-
-#define SO_INCOMING_CPU 49
-
-#define SO_ATTACH_BPF 50
-#define SO_DETACH_BPF SO_DETACH_FILTER
-
-#define SO_ATTACH_REUSEPORT_CBPF 51
-#define SO_ATTACH_REUSEPORT_EBPF 52
-
-#define SO_CNX_ADVICE 53
-
-#define SCM_TIMESTAMPING_OPT_STATS 54
-
-#endif /* _UAPI__ASM_AVR32_SOCKET_H */
+++ /dev/null
-#ifndef _UAPI__ASM_AVR32_SOCKIOS_H
-#define _UAPI__ASM_AVR32_SOCKIOS_H
-
-/* Socket-level I/O control calls. */
-#define FIOSETOWN 0x8901
-#define SIOCSPGRP 0x8902
-#define FIOGETOWN 0x8903
-#define SIOCGPGRP 0x8904
-#define SIOCATMARK 0x8905
-#define SIOCGSTAMP 0x8906 /* Get stamp (timeval) */
-#define SIOCGSTAMPNS 0x8907 /* Get stamp (timespec) */
-
-#endif /* _UAPI__ASM_AVR32_SOCKIOS_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef _UAPI__ASM_AVR32_STAT_H
-#define _UAPI__ASM_AVR32_STAT_H
-
-struct __old_kernel_stat {
- unsigned short st_dev;
- unsigned short st_ino;
- unsigned short st_mode;
- unsigned short st_nlink;
- unsigned short st_uid;
- unsigned short st_gid;
- unsigned short st_rdev;
- unsigned long st_size;
- unsigned long st_atime;
- unsigned long st_mtime;
- unsigned long st_ctime;
-};
-
-struct stat {
- unsigned long st_dev;
- unsigned long st_ino;
- unsigned short st_mode;
- unsigned short st_nlink;
- unsigned short st_uid;
- unsigned short st_gid;
- unsigned long st_rdev;
- unsigned long st_size;
- unsigned long st_blksize;
- unsigned long st_blocks;
- unsigned long st_atime;
- unsigned long st_atime_nsec;
- unsigned long st_mtime;
- unsigned long st_mtime_nsec;
- unsigned long st_ctime;
- unsigned long st_ctime_nsec;
- unsigned long __unused4;
- unsigned long __unused5;
-};
-
-#define STAT_HAVE_NSEC 1
-
-struct stat64 {
- unsigned long long st_dev;
-
- unsigned long long st_ino;
- unsigned int st_mode;
- unsigned int st_nlink;
-
- unsigned long st_uid;
- unsigned long st_gid;
-
- unsigned long long st_rdev;
-
- long long st_size;
- unsigned long __pad1; /* align 64-bit st_blocks */
- unsigned long st_blksize;
-
- unsigned long long st_blocks; /* Number 512-byte blocks allocated. */
-
- unsigned long st_atime;
- unsigned long st_atime_nsec;
-
- unsigned long st_mtime;
- unsigned long st_mtime_nsec;
-
- unsigned long st_ctime;
- unsigned long st_ctime_nsec;
-
- unsigned long __unused1;
- unsigned long __unused2;
-};
-
-#endif /* _UAPI__ASM_AVR32_STAT_H */
+++ /dev/null
-/*
- * AVR32 byteswapping functions.
- */
-#ifndef _UAPI__ASM_AVR32_SWAB_H
-#define _UAPI__ASM_AVR32_SWAB_H
-
-#include <linux/types.h>
-#include <linux/compiler.h>
-
-#define __SWAB_64_THRU_32__
-
-#ifdef __CHECKER__
-extern unsigned long __builtin_bswap_32(unsigned long x);
-extern unsigned short __builtin_bswap_16(unsigned short x);
-#endif
-
-/*
- * avr32-linux-gcc versions earlier than 4.2 improperly sign-extends
- * the result.
- */
-#if !(__GNUC__ == 4 && __GNUC_MINOR__ < 2)
-static inline __attribute_const__ __u16 __arch_swab16(__u16 val)
-{
- return __builtin_bswap_16(val);
-}
-#define __arch_swab16 __arch_swab16
-
-static inline __attribute_const__ __u32 __arch_swab32(__u32 val)
-{
- return __builtin_bswap_32(val);
-}
-#define __arch_swab32 __arch_swab32
-#endif
-
-#endif /* _UAPI__ASM_AVR32_SWAB_H */
+++ /dev/null
-#ifndef _UAPI__ASM_AVR32_TERMBITS_H
-#define _UAPI__ASM_AVR32_TERMBITS_H
-
-#include <linux/posix_types.h>
-
-typedef unsigned char cc_t;
-typedef unsigned int speed_t;
-typedef unsigned int tcflag_t;
-
-#define NCCS 19
-struct termios {
- tcflag_t c_iflag; /* input mode flags */
- tcflag_t c_oflag; /* output mode flags */
- tcflag_t c_cflag; /* control mode flags */
- tcflag_t c_lflag; /* local mode flags */
- cc_t c_line; /* line discipline */
- cc_t c_cc[NCCS]; /* control characters */
-};
-
-struct termios2 {
- tcflag_t c_iflag; /* input mode flags */
- tcflag_t c_oflag; /* output mode flags */
- tcflag_t c_cflag; /* control mode flags */
- tcflag_t c_lflag; /* local mode flags */
- cc_t c_line; /* line discipline */
- cc_t c_cc[NCCS]; /* control characters */
- speed_t c_ispeed; /* input speed */
- speed_t c_ospeed; /* output speed */
-};
-
-struct ktermios {
- tcflag_t c_iflag; /* input mode flags */
- tcflag_t c_oflag; /* output mode flags */
- tcflag_t c_cflag; /* control mode flags */
- tcflag_t c_lflag; /* local mode flags */
- cc_t c_line; /* line discipline */
- cc_t c_cc[NCCS]; /* control characters */
- speed_t c_ispeed; /* input speed */
- speed_t c_ospeed; /* output speed */
-};
-
-/* c_cc characters */
-#define VINTR 0
-#define VQUIT 1
-#define VERASE 2
-#define VKILL 3
-#define VEOF 4
-#define VTIME 5
-#define VMIN 6
-#define VSWTC 7
-#define VSTART 8
-#define VSTOP 9
-#define VSUSP 10
-#define VEOL 11
-#define VREPRINT 12
-#define VDISCARD 13
-#define VWERASE 14
-#define VLNEXT 15
-#define VEOL2 16
-
-/* c_iflag bits */
-#define IGNBRK 0000001
-#define BRKINT 0000002
-#define IGNPAR 0000004
-#define PARMRK 0000010
-#define INPCK 0000020
-#define ISTRIP 0000040
-#define INLCR 0000100
-#define IGNCR 0000200
-#define ICRNL 0000400
-#define IUCLC 0001000
-#define IXON 0002000
-#define IXANY 0004000
-#define IXOFF 0010000
-#define IMAXBEL 0020000
-#define IUTF8 0040000
-
-/* c_oflag bits */
-#define OPOST 0000001
-#define OLCUC 0000002
-#define ONLCR 0000004
-#define OCRNL 0000010
-#define ONOCR 0000020
-#define ONLRET 0000040
-#define OFILL 0000100
-#define OFDEL 0000200
-#define NLDLY 0000400
-#define NL0 0000000
-#define NL1 0000400
-#define CRDLY 0003000
-#define CR0 0000000
-#define CR1 0001000
-#define CR2 0002000
-#define CR3 0003000
-#define TABDLY 0014000
-#define TAB0 0000000
-#define TAB1 0004000
-#define TAB2 0010000
-#define TAB3 0014000
-#define XTABS 0014000
-#define BSDLY 0020000
-#define BS0 0000000
-#define BS1 0020000
-#define VTDLY 0040000
-#define VT0 0000000
-#define VT1 0040000
-#define FFDLY 0100000
-#define FF0 0000000
-#define FF1 0100000
-
-/* c_cflag bit meaning */
-#define CBAUD 0010017
-#define B0 0000000 /* hang up */
-#define B50 0000001
-#define B75 0000002
-#define B110 0000003
-#define B134 0000004
-#define B150 0000005
-#define B200 0000006
-#define B300 0000007
-#define B600 0000010
-#define B1200 0000011
-#define B1800 0000012
-#define B2400 0000013
-#define B4800 0000014
-#define B9600 0000015
-#define B19200 0000016
-#define B38400 0000017
-#define EXTA B19200
-#define EXTB B38400
-#define CSIZE 0000060
-#define CS5 0000000
-#define CS6 0000020
-#define CS7 0000040
-#define CS8 0000060
-#define CSTOPB 0000100
-#define CREAD 0000200
-#define PARENB 0000400
-#define PARODD 0001000
-#define HUPCL 0002000
-#define CLOCAL 0004000
-#define CBAUDEX 0010000
-#define B57600 0010001
-#define B115200 0010002
-#define B230400 0010003
-#define B460800 0010004
-#define B500000 0010005
-#define B576000 0010006
-#define B921600 0010007
-#define B1000000 0010010
-#define B1152000 0010011
-#define B1500000 0010012
-#define B2000000 0010013
-#define B2500000 0010014
-#define B3000000 0010015
-#define B3500000 0010016
-#define B4000000 0010017
-#define CIBAUD 002003600000 /* input baud rate (not used) */
-#define CMSPAR 010000000000 /* mark or space (stick) parity */
-#define CRTSCTS 020000000000 /* flow control */
-
-/* c_lflag bits */
-#define ISIG 0000001
-#define ICANON 0000002
-#define XCASE 0000004
-#define ECHO 0000010
-#define ECHOE 0000020
-#define ECHOK 0000040
-#define ECHONL 0000100
-#define NOFLSH 0000200
-#define TOSTOP 0000400
-#define ECHOCTL 0001000
-#define ECHOPRT 0002000
-#define ECHOKE 0004000
-#define FLUSHO 0010000
-#define PENDIN 0040000
-#define IEXTEN 0100000
-#define EXTPROC 0200000
-
-/* tcflow() and TCXONC use these */
-#define TCOOFF 0
-#define TCOON 1
-#define TCIOFF 2
-#define TCION 3
-
-/* tcflush() and TCFLSH use these */
-#define TCIFLUSH 0
-#define TCOFLUSH 1
-#define TCIOFLUSH 2
-
-/* tcsetattr uses these */
-#define TCSANOW 0
-#define TCSADRAIN 1
-#define TCSAFLUSH 2
-
-#endif /* _UAPI__ASM_AVR32_TERMBITS_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef _UAPI__ASM_AVR32_TERMIOS_H
-#define _UAPI__ASM_AVR32_TERMIOS_H
-
-#include <asm/termbits.h>
-#include <asm/ioctls.h>
-
-struct winsize {
- unsigned short ws_row;
- unsigned short ws_col;
- unsigned short ws_xpixel;
- unsigned short ws_ypixel;
-};
-
-#define NCC 8
-struct termio {
- unsigned short c_iflag; /* input mode flags */
- unsigned short c_oflag; /* output mode flags */
- unsigned short c_cflag; /* control mode flags */
- unsigned short c_lflag; /* local mode flags */
- unsigned char c_line; /* line discipline */
- unsigned char c_cc[NCC]; /* control characters */
-};
-
-/* modem lines */
-#define TIOCM_LE 0x001
-#define TIOCM_DTR 0x002
-#define TIOCM_RTS 0x004
-#define TIOCM_ST 0x008
-#define TIOCM_SR 0x010
-#define TIOCM_CTS 0x020
-#define TIOCM_CAR 0x040
-#define TIOCM_RNG 0x080
-#define TIOCM_DSR 0x100
-#define TIOCM_CD TIOCM_CAR
-#define TIOCM_RI TIOCM_RNG
-#define TIOCM_OUT1 0x2000
-#define TIOCM_OUT2 0x4000
-#define TIOCM_LOOP 0x8000
-
-/* ioctl (fd, TIOCSERGETLSR, &result) where result may be as below */
-
-#endif /* _UAPI__ASM_AVR32_TERMIOS_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef _UAPI__ASM_AVR32_TYPES_H
-#define _UAPI__ASM_AVR32_TYPES_H
-
-#include <asm-generic/int-ll64.h>
-
-#endif /* _UAPI__ASM_AVR32_TYPES_H */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef _UAPI__ASM_AVR32_UNISTD_H
-#define _UAPI__ASM_AVR32_UNISTD_H
-
-/*
- * This file contains the system call numbers.
- */
-
-#define __NR_restart_syscall 0
-#define __NR_exit 1
-#define __NR_fork 2
-#define __NR_read 3
-#define __NR_write 4
-#define __NR_open 5
-#define __NR_close 6
-#define __NR_umask 7
-#define __NR_creat 8
-#define __NR_link 9
-#define __NR_unlink 10
-#define __NR_execve 11
-#define __NR_chdir 12
-#define __NR_time 13
-#define __NR_mknod 14
-#define __NR_chmod 15
-#define __NR_chown 16
-#define __NR_lchown 17
-#define __NR_lseek 18
-#define __NR__llseek 19
-#define __NR_getpid 20
-#define __NR_mount 21
-#define __NR_umount2 22
-#define __NR_setuid 23
-#define __NR_getuid 24
-#define __NR_stime 25
-#define __NR_ptrace 26
-#define __NR_alarm 27
-#define __NR_pause 28
-#define __NR_utime 29
-#define __NR_stat 30
-#define __NR_fstat 31
-#define __NR_lstat 32
-#define __NR_access 33
-#define __NR_chroot 34
-#define __NR_sync 35
-#define __NR_fsync 36
-#define __NR_kill 37
-#define __NR_rename 38
-#define __NR_mkdir 39
-#define __NR_rmdir 40
-#define __NR_dup 41
-#define __NR_pipe 42
-#define __NR_times 43
-#define __NR_clone 44
-#define __NR_brk 45
-#define __NR_setgid 46
-#define __NR_getgid 47
-#define __NR_getcwd 48
-#define __NR_geteuid 49
-#define __NR_getegid 50
-#define __NR_acct 51
-#define __NR_setfsuid 52
-#define __NR_setfsgid 53
-#define __NR_ioctl 54
-#define __NR_fcntl 55
-#define __NR_setpgid 56
-#define __NR_mremap 57
-#define __NR_setresuid 58
-#define __NR_getresuid 59
-#define __NR_setreuid 60
-#define __NR_setregid 61
-#define __NR_ustat 62
-#define __NR_dup2 63
-#define __NR_getppid 64
-#define __NR_getpgrp 65
-#define __NR_setsid 66
-#define __NR_rt_sigaction 67
-#define __NR_rt_sigreturn 68
-#define __NR_rt_sigprocmask 69
-#define __NR_rt_sigpending 70
-#define __NR_rt_sigtimedwait 71
-#define __NR_rt_sigqueueinfo 72
-#define __NR_rt_sigsuspend 73
-#define __NR_sethostname 74
-#define __NR_setrlimit 75
-#define __NR_getrlimit 76 /* SuS compliant getrlimit */
-#define __NR_getrusage 77
-#define __NR_gettimeofday 78
-#define __NR_settimeofday 79
-#define __NR_getgroups 80
-#define __NR_setgroups 81
-#define __NR_select 82
-#define __NR_symlink 83
-#define __NR_fchdir 84
-#define __NR_readlink 85
-#define __NR_pread 86
-#define __NR_pwrite 87
-#define __NR_swapon 88
-#define __NR_reboot 89
-#define __NR_mmap2 90
-#define __NR_munmap 91
-#define __NR_truncate 92
-#define __NR_ftruncate 93
-#define __NR_fchmod 94
-#define __NR_fchown 95
-#define __NR_getpriority 96
-#define __NR_setpriority 97
-#define __NR_wait4 98
-#define __NR_statfs 99
-#define __NR_fstatfs 100
-#define __NR_vhangup 101
-#define __NR_sigaltstack 102
-#define __NR_syslog 103
-#define __NR_setitimer 104
-#define __NR_getitimer 105
-#define __NR_swapoff 106
-#define __NR_sysinfo 107
-/* 108 was __NR_ipc for a little while */
-#define __NR_sendfile 109
-#define __NR_setdomainname 110
-#define __NR_uname 111
-#define __NR_adjtimex 112
-#define __NR_mprotect 113
-#define __NR_vfork 114
-#define __NR_init_module 115
-#define __NR_delete_module 116
-#define __NR_quotactl 117
-#define __NR_getpgid 118
-#define __NR_bdflush 119
-#define __NR_sysfs 120
-#define __NR_personality 121
-#define __NR_afs_syscall 122 /* Syscall for Andrew File System */
-#define __NR_getdents 123
-#define __NR_flock 124
-#define __NR_msync 125
-#define __NR_readv 126
-#define __NR_writev 127
-#define __NR_getsid 128
-#define __NR_fdatasync 129
-#define __NR__sysctl 130
-#define __NR_mlock 131
-#define __NR_munlock 132
-#define __NR_mlockall 133
-#define __NR_munlockall 134
-#define __NR_sched_setparam 135
-#define __NR_sched_getparam 136
-#define __NR_sched_setscheduler 137
-#define __NR_sched_getscheduler 138
-#define __NR_sched_yield 139
-#define __NR_sched_get_priority_max 140
-#define __NR_sched_get_priority_min 141
-#define __NR_sched_rr_get_interval 142
-#define __NR_nanosleep 143
-#define __NR_poll 144
-#define __NR_nfsservctl 145
-#define __NR_setresgid 146
-#define __NR_getresgid 147
-#define __NR_prctl 148
-#define __NR_socket 149
-#define __NR_bind 150
-#define __NR_connect 151
-#define __NR_listen 152
-#define __NR_accept 153
-#define __NR_getsockname 154
-#define __NR_getpeername 155
-#define __NR_socketpair 156
-#define __NR_send 157
-#define __NR_recv 158
-#define __NR_sendto 159
-#define __NR_recvfrom 160
-#define __NR_shutdown 161
-#define __NR_setsockopt 162
-#define __NR_getsockopt 163
-#define __NR_sendmsg 164
-#define __NR_recvmsg 165
-#define __NR_truncate64 166
-#define __NR_ftruncate64 167
-#define __NR_stat64 168
-#define __NR_lstat64 169
-#define __NR_fstat64 170
-#define __NR_pivot_root 171
-#define __NR_mincore 172
-#define __NR_madvise 173
-#define __NR_getdents64 174
-#define __NR_fcntl64 175
-#define __NR_gettid 176
-#define __NR_readahead 177
-#define __NR_setxattr 178
-#define __NR_lsetxattr 179
-#define __NR_fsetxattr 180
-#define __NR_getxattr 181
-#define __NR_lgetxattr 182
-#define __NR_fgetxattr 183
-#define __NR_listxattr 184
-#define __NR_llistxattr 185
-#define __NR_flistxattr 186
-#define __NR_removexattr 187
-#define __NR_lremovexattr 188
-#define __NR_fremovexattr 189
-#define __NR_tkill 190
-#define __NR_sendfile64 191
-#define __NR_futex 192
-#define __NR_sched_setaffinity 193
-#define __NR_sched_getaffinity 194
-#define __NR_capget 195
-#define __NR_capset 196
-#define __NR_io_setup 197
-#define __NR_io_destroy 198
-#define __NR_io_getevents 199
-#define __NR_io_submit 200
-#define __NR_io_cancel 201
-#define __NR_fadvise64 202
-#define __NR_exit_group 203
-#define __NR_lookup_dcookie 204
-#define __NR_epoll_create 205
-#define __NR_epoll_ctl 206
-#define __NR_epoll_wait 207
-#define __NR_remap_file_pages 208
-#define __NR_set_tid_address 209
-#define __NR_timer_create 210
-#define __NR_timer_settime 211
-#define __NR_timer_gettime 212
-#define __NR_timer_getoverrun 213
-#define __NR_timer_delete 214
-#define __NR_clock_settime 215
-#define __NR_clock_gettime 216
-#define __NR_clock_getres 217
-#define __NR_clock_nanosleep 218
-#define __NR_statfs64 219
-#define __NR_fstatfs64 220
-#define __NR_tgkill 221
-/* 222 reserved for tux */
-#define __NR_utimes 223
-#define __NR_fadvise64_64 224
-#define __NR_cacheflush 225
-#define __NR_vserver 226
-#define __NR_mq_open 227
-#define __NR_mq_unlink 228
-#define __NR_mq_timedsend 229
-#define __NR_mq_timedreceive 230
-#define __NR_mq_notify 231
-#define __NR_mq_getsetattr 232
-#define __NR_kexec_load 233
-#define __NR_waitid 234
-#define __NR_add_key 235
-#define __NR_request_key 236
-#define __NR_keyctl 237
-#define __NR_ioprio_set 238
-#define __NR_ioprio_get 239
-#define __NR_inotify_init 240
-#define __NR_inotify_add_watch 241
-#define __NR_inotify_rm_watch 242
-#define __NR_openat 243
-#define __NR_mkdirat 244
-#define __NR_mknodat 245
-#define __NR_fchownat 246
-#define __NR_futimesat 247
-#define __NR_fstatat64 248
-#define __NR_unlinkat 249
-#define __NR_renameat 250
-#define __NR_linkat 251
-#define __NR_symlinkat 252
-#define __NR_readlinkat 253
-#define __NR_fchmodat 254
-#define __NR_faccessat 255
-#define __NR_pselect6 256
-#define __NR_ppoll 257
-#define __NR_unshare 258
-#define __NR_set_robust_list 259
-#define __NR_get_robust_list 260
-#define __NR_splice 261
-#define __NR_sync_file_range 262
-#define __NR_tee 263
-#define __NR_vmsplice 264
-#define __NR_epoll_pwait 265
-#define __NR_msgget 266
-#define __NR_msgsnd 267
-#define __NR_msgrcv 268
-#define __NR_msgctl 269
-#define __NR_semget 270
-#define __NR_semop 271
-#define __NR_semctl 272
-#define __NR_semtimedop 273
-#define __NR_shmat 274
-#define __NR_shmget 275
-#define __NR_shmdt 276
-#define __NR_shmctl 277
-#define __NR_utimensat 278
-#define __NR_signalfd 279
-/* 280 was __NR_timerfd */
-#define __NR_eventfd 281
-/* 282 was half-implemented __NR_recvmmsg */
-#define __NR_setns 283
-#define __NR_pread64 284
-#define __NR_pwrite64 285
-#define __NR_timerfd_create 286
-#define __NR_fallocate 287
-#define __NR_timerfd_settime 288
-#define __NR_timerfd_gettime 289
-#define __NR_signalfd4 290
-#define __NR_eventfd2 291
-#define __NR_epoll_create1 292
-#define __NR_dup3 293
-#define __NR_pipe2 294
-#define __NR_inotify_init1 295
-#define __NR_preadv 296
-#define __NR_pwritev 297
-#define __NR_rt_tgsigqueueinfo 298
-#define __NR_perf_event_open 299
-#define __NR_recvmmsg 300
-#define __NR_fanotify_init 301
-#define __NR_fanotify_mark 302
-#define __NR_prlimit64 303
-#define __NR_name_to_handle_at 304
-#define __NR_open_by_handle_at 305
-#define __NR_clock_adjtime 306
-#define __NR_syncfs 307
-#define __NR_sendmmsg 308
-#define __NR_process_vm_readv 309
-#define __NR_process_vm_writev 310
-#define __NR_kcmp 311
-#define __NR_finit_module 312
-#define __NR_sched_setattr 313
-#define __NR_sched_getattr 314
-#define __NR_renameat2 315
-#define __NR_seccomp 316
-#define __NR_getrandom 317
-#define __NR_memfd_create 318
-#define __NR_bpf 319
-#define __NR_execveat 320
-#define __NR_accept4 321
-#define __NR_userfaultfd 322
-#define __NR_membarrier 323
-#define __NR_mlock2 324
-#define __NR_copy_file_range 325
-#define __NR_preadv2 326
-#define __NR_pwritev2 327
-#define __NR_pkey_mprotect 328
-#define __NR_pkey_alloc 329
-#define __NR_pkey_free 330
-
-#endif /* _UAPI__ASM_AVR32_UNISTD_H */
+++ /dev/null
-vmlinux.lds
+++ /dev/null
-#
-# Makefile for the Linux/AVR32 kernel.
-#
-
-extra-y := head.o vmlinux.lds
-
-obj-$(CONFIG_SUBARCH_AVR32B) += entry-avr32b.o
-obj-y += syscall_table.o syscall-stubs.o irq.o
-obj-y += setup.o traps.o ocd.o ptrace.o
-obj-y += signal.o process.o time.o
-obj-y += switch_to.o cpu.o
-obj-$(CONFIG_MODULES) += module.o avr32_ksyms.o
-obj-$(CONFIG_KPROBES) += kprobes.o
-obj-$(CONFIG_STACKTRACE) += stacktrace.o
-obj-$(CONFIG_NMI_DEBUGGING) += nmi_debug.o
+++ /dev/null
-/*
- * Generate definitions needed by assembly language modules.
- * This code generates raw asm output which is post-processed
- * to extract and format the required data.
- */
-
-#include <linux/mm.h>
-#include <linux/sched.h>
-#include <linux/thread_info.h>
-#include <linux/kbuild.h>
-
-void foo(void)
-{
- OFFSET(TI_task, thread_info, task);
- OFFSET(TI_flags, thread_info, flags);
- OFFSET(TI_cpu, thread_info, cpu);
- OFFSET(TI_preempt_count, thread_info, preempt_count);
- OFFSET(TI_rar_saved, thread_info, rar_saved);
- OFFSET(TI_rsr_saved, thread_info, rsr_saved);
- BLANK();
- OFFSET(TSK_active_mm, task_struct, active_mm);
- BLANK();
- OFFSET(MM_pgd, mm_struct, pgd);
-}
+++ /dev/null
-/*
- * Export AVR32-specific functions for loadable modules.
- *
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/delay.h>
-#include <linux/io.h>
-#include <linux/module.h>
-
-#include <asm/checksum.h>
-#include <linux/uaccess.h>
-
-/*
- * GCC functions
- */
-extern unsigned long long __avr32_lsl64(unsigned long long u, unsigned long b);
-extern unsigned long long __avr32_lsr64(unsigned long long u, unsigned long b);
-extern unsigned long long __avr32_asr64(unsigned long long u, unsigned long b);
-EXPORT_SYMBOL(__avr32_lsl64);
-EXPORT_SYMBOL(__avr32_lsr64);
-EXPORT_SYMBOL(__avr32_asr64);
-
-/*
- * String functions
- */
-EXPORT_SYMBOL(memset);
-EXPORT_SYMBOL(memcpy);
-
-EXPORT_SYMBOL(clear_page);
-EXPORT_SYMBOL(copy_page);
-
-/*
- * Userspace access stuff.
- */
-EXPORT_SYMBOL(___copy_from_user);
-EXPORT_SYMBOL(copy_to_user);
-EXPORT_SYMBOL(__copy_user);
-EXPORT_SYMBOL(strncpy_from_user);
-EXPORT_SYMBOL(__strncpy_from_user);
-EXPORT_SYMBOL(clear_user);
-EXPORT_SYMBOL(__clear_user);
-EXPORT_SYMBOL(strnlen_user);
-
-EXPORT_SYMBOL(csum_partial);
-EXPORT_SYMBOL(csum_partial_copy_generic);
-
-/* Delay loops (lib/delay.S) */
-EXPORT_SYMBOL(__ndelay);
-EXPORT_SYMBOL(__udelay);
-EXPORT_SYMBOL(__const_udelay);
-
-/* Bit operations (lib/findbit.S) */
-EXPORT_SYMBOL(find_first_zero_bit);
-EXPORT_SYMBOL(find_next_zero_bit);
-EXPORT_SYMBOL(find_first_bit);
-EXPORT_SYMBOL(find_next_bit);
-EXPORT_SYMBOL(find_next_bit_le);
-EXPORT_SYMBOL(find_next_zero_bit_le);
-
-/* I/O primitives (lib/io-*.S) */
-EXPORT_SYMBOL(__raw_readsb);
-EXPORT_SYMBOL(__raw_readsw);
-EXPORT_SYMBOL(__raw_readsl);
-EXPORT_SYMBOL(__raw_writesb);
-EXPORT_SYMBOL(__raw_writesw);
-EXPORT_SYMBOL(__raw_writesl);
+++ /dev/null
-/*
- * Copyright (C) 2005-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/init.h>
-#include <linux/device.h>
-#include <linux/seq_file.h>
-#include <linux/cpu.h>
-#include <linux/module.h>
-#include <linux/percpu.h>
-#include <linux/param.h>
-#include <linux/errno.h>
-#include <linux/clk.h>
-
-#include <asm/setup.h>
-#include <asm/sysreg.h>
-
-static DEFINE_PER_CPU(struct cpu, cpu_devices);
-
-#ifdef CONFIG_PERFORMANCE_COUNTERS
-
-/*
- * XXX: If/when a SMP-capable implementation of AVR32 will ever be
- * made, we must make sure that the code executes on the correct CPU.
- */
-static ssize_t show_pc0event(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- unsigned long pccr;
-
- pccr = sysreg_read(PCCR);
- return sprintf(buf, "0x%lx\n", (pccr >> 12) & 0x3f);
-}
-static ssize_t store_pc0event(struct device *dev,
- struct device_attribute *attr, const char *buf,
- size_t count)
-{
- unsigned long val;
- int ret;
-
- ret = kstrtoul(buf, 0, &val);
- if (ret)
- return ret;
- if (val > 0x3f)
- return -EINVAL;
- val = (val << 12) | (sysreg_read(PCCR) & 0xfffc0fff);
- sysreg_write(PCCR, val);
- return count;
-}
-static ssize_t show_pc0count(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- unsigned long pcnt0;
-
- pcnt0 = sysreg_read(PCNT0);
- return sprintf(buf, "%lu\n", pcnt0);
-}
-static ssize_t store_pc0count(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
-{
- unsigned long val;
- int ret;
-
- ret = kstrtoul(buf, 0, &val);
- if (ret)
- return ret;
- sysreg_write(PCNT0, val);
-
- return count;
-}
-
-static ssize_t show_pc1event(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- unsigned long pccr;
-
- pccr = sysreg_read(PCCR);
- return sprintf(buf, "0x%lx\n", (pccr >> 18) & 0x3f);
-}
-static ssize_t store_pc1event(struct device *dev,
- struct device_attribute *attr, const char *buf,
- size_t count)
-{
- unsigned long val;
- int ret;
-
- ret = kstrtoul(buf, 0, &val);
- if (ret)
- return ret;
- if (val > 0x3f)
- return -EINVAL;
- val = (val << 18) | (sysreg_read(PCCR) & 0xff03ffff);
- sysreg_write(PCCR, val);
- return count;
-}
-static ssize_t show_pc1count(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- unsigned long pcnt1;
-
- pcnt1 = sysreg_read(PCNT1);
- return sprintf(buf, "%lu\n", pcnt1);
-}
-static ssize_t store_pc1count(struct device *dev,
- struct device_attribute *attr, const char *buf,
- size_t count)
-{
- unsigned long val;
- int ret;
-
- ret = kstrtoul(buf, 0, &val);
- if (ret)
- return ret;
- sysreg_write(PCNT1, val);
-
- return count;
-}
-
-static ssize_t show_pccycles(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- unsigned long pccnt;
-
- pccnt = sysreg_read(PCCNT);
- return sprintf(buf, "%lu\n", pccnt);
-}
-static ssize_t store_pccycles(struct device *dev,
- struct device_attribute *attr, const char *buf,
- size_t count)
-{
- unsigned long val;
- int ret;
-
- ret = kstrtoul(buf, 0, &val);
- if (ret)
- return ret;
- sysreg_write(PCCNT, val);
-
- return count;
-}
-
-static ssize_t show_pcenable(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- unsigned long pccr;
-
- pccr = sysreg_read(PCCR);
- return sprintf(buf, "%c\n", (pccr & 1)?'1':'0');
-}
-static ssize_t store_pcenable(struct device *dev,
- struct device_attribute *attr, const char *buf,
- size_t count)
-{
- unsigned long pccr, val;
- int ret;
-
- ret = kstrtoul(buf, 0, &val);
- if (ret)
- return ret;
- if (val)
- val = 1;
-
- pccr = sysreg_read(PCCR);
- pccr = (pccr & ~1UL) | val;
- sysreg_write(PCCR, pccr);
-
- return count;
-}
-
-static DEVICE_ATTR(pc0event, 0600, show_pc0event, store_pc0event);
-static DEVICE_ATTR(pc0count, 0600, show_pc0count, store_pc0count);
-static DEVICE_ATTR(pc1event, 0600, show_pc1event, store_pc1event);
-static DEVICE_ATTR(pc1count, 0600, show_pc1count, store_pc1count);
-static DEVICE_ATTR(pccycles, 0600, show_pccycles, store_pccycles);
-static DEVICE_ATTR(pcenable, 0600, show_pcenable, store_pcenable);
-
-#endif /* CONFIG_PERFORMANCE_COUNTERS */
-
-static int __init topology_init(void)
-{
- int cpu;
-
- for_each_possible_cpu(cpu) {
- struct cpu *c = &per_cpu(cpu_devices, cpu);
-
- register_cpu(c, cpu);
-
-#ifdef CONFIG_PERFORMANCE_COUNTERS
- device_create_file(&c->dev, &dev_attr_pc0event);
- device_create_file(&c->dev, &dev_attr_pc0count);
- device_create_file(&c->dev, &dev_attr_pc1event);
- device_create_file(&c->dev, &dev_attr_pc1count);
- device_create_file(&c->dev, &dev_attr_pccycles);
- device_create_file(&c->dev, &dev_attr_pcenable);
-#endif
- }
-
- return 0;
-}
-
-subsys_initcall(topology_init);
-
-struct chip_id_map {
- u16 mid;
- u16 pn;
- const char *name;
-};
-
-static const struct chip_id_map chip_names[] = {
- { .mid = 0x1f, .pn = 0x1e82, .name = "AT32AP700x" },
-};
-#define NR_CHIP_NAMES ARRAY_SIZE(chip_names)
-
-static const char *cpu_names[] = {
- "Morgan",
- "AP7",
-};
-#define NR_CPU_NAMES ARRAY_SIZE(cpu_names)
-
-static const char *arch_names[] = {
- "AVR32A",
- "AVR32B",
-};
-#define NR_ARCH_NAMES ARRAY_SIZE(arch_names)
-
-static const char *mmu_types[] = {
- "No MMU",
- "ITLB and DTLB",
- "Shared TLB",
- "MPU"
-};
-
-static const char *cpu_feature_flags[] = {
- "rmw", "dsp", "simd", "ocd", "perfctr", "java", "fpu",
-};
-
-static const char *get_chip_name(struct avr32_cpuinfo *cpu)
-{
- unsigned int i;
- unsigned int mid = avr32_get_manufacturer_id(cpu);
- unsigned int pn = avr32_get_product_number(cpu);
-
- for (i = 0; i < NR_CHIP_NAMES; i++) {
- if (chip_names[i].mid == mid && chip_names[i].pn == pn)
- return chip_names[i].name;
- }
-
- return "(unknown)";
-}
-
-void __init setup_processor(void)
-{
- unsigned long config0, config1;
- unsigned long features;
- unsigned cpu_id, cpu_rev, arch_id, arch_rev, mmu_type;
- unsigned device_id;
- unsigned tmp;
- unsigned i;
-
- config0 = sysreg_read(CONFIG0);
- config1 = sysreg_read(CONFIG1);
- cpu_id = SYSREG_BFEXT(PROCESSORID, config0);
- cpu_rev = SYSREG_BFEXT(PROCESSORREVISION, config0);
- arch_id = SYSREG_BFEXT(AT, config0);
- arch_rev = SYSREG_BFEXT(AR, config0);
- mmu_type = SYSREG_BFEXT(MMUT, config0);
-
- device_id = ocd_read(DID);
-
- boot_cpu_data.arch_type = arch_id;
- boot_cpu_data.cpu_type = cpu_id;
- boot_cpu_data.arch_revision = arch_rev;
- boot_cpu_data.cpu_revision = cpu_rev;
- boot_cpu_data.tlb_config = mmu_type;
- boot_cpu_data.device_id = device_id;
-
- tmp = SYSREG_BFEXT(ILSZ, config1);
- if (tmp) {
- boot_cpu_data.icache.ways = 1 << SYSREG_BFEXT(IASS, config1);
- boot_cpu_data.icache.sets = 1 << SYSREG_BFEXT(ISET, config1);
- boot_cpu_data.icache.linesz = 1 << (tmp + 1);
- }
- tmp = SYSREG_BFEXT(DLSZ, config1);
- if (tmp) {
- boot_cpu_data.dcache.ways = 1 << SYSREG_BFEXT(DASS, config1);
- boot_cpu_data.dcache.sets = 1 << SYSREG_BFEXT(DSET, config1);
- boot_cpu_data.dcache.linesz = 1 << (tmp + 1);
- }
-
- if ((cpu_id >= NR_CPU_NAMES) || (arch_id >= NR_ARCH_NAMES)) {
- printk ("Unknown CPU configuration (ID %02x, arch %02x), "
- "continuing anyway...\n",
- cpu_id, arch_id);
- return;
- }
-
- printk ("CPU: %s chip revision %c\n", get_chip_name(&boot_cpu_data),
- avr32_get_chip_revision(&boot_cpu_data) + 'A');
- printk ("CPU: %s [%02x] core revision %d (%s arch revision %d)\n",
- cpu_names[cpu_id], cpu_id, cpu_rev,
- arch_names[arch_id], arch_rev);
- printk ("CPU: MMU configuration: %s\n", mmu_types[mmu_type]);
-
- printk ("CPU: features:");
- features = 0;
- if (config0 & SYSREG_BIT(CONFIG0_R))
- features |= AVR32_FEATURE_RMW;
- if (config0 & SYSREG_BIT(CONFIG0_D))
- features |= AVR32_FEATURE_DSP;
- if (config0 & SYSREG_BIT(CONFIG0_S))
- features |= AVR32_FEATURE_SIMD;
- if (config0 & SYSREG_BIT(CONFIG0_O))
- features |= AVR32_FEATURE_OCD;
- if (config0 & SYSREG_BIT(CONFIG0_P))
- features |= AVR32_FEATURE_PCTR;
- if (config0 & SYSREG_BIT(CONFIG0_J))
- features |= AVR32_FEATURE_JAVA;
- if (config0 & SYSREG_BIT(CONFIG0_F))
- features |= AVR32_FEATURE_FPU;
-
- for (i = 0; i < ARRAY_SIZE(cpu_feature_flags); i++)
- if (features & (1 << i))
- printk(" %s", cpu_feature_flags[i]);
-
- printk("\n");
- boot_cpu_data.features = features;
-}
-
-#ifdef CONFIG_PROC_FS
-static int c_show(struct seq_file *m, void *v)
-{
- unsigned int icache_size, dcache_size;
- unsigned int cpu = smp_processor_id();
- unsigned int freq;
- unsigned int i;
-
- icache_size = boot_cpu_data.icache.ways *
- boot_cpu_data.icache.sets *
- boot_cpu_data.icache.linesz;
- dcache_size = boot_cpu_data.dcache.ways *
- boot_cpu_data.dcache.sets *
- boot_cpu_data.dcache.linesz;
-
- seq_printf(m, "processor\t: %d\n", cpu);
-
- seq_printf(m, "chip type\t: %s revision %c\n",
- get_chip_name(&boot_cpu_data),
- avr32_get_chip_revision(&boot_cpu_data) + 'A');
- if (boot_cpu_data.arch_type < NR_ARCH_NAMES)
- seq_printf(m, "cpu arch\t: %s revision %d\n",
- arch_names[boot_cpu_data.arch_type],
- boot_cpu_data.arch_revision);
- if (boot_cpu_data.cpu_type < NR_CPU_NAMES)
- seq_printf(m, "cpu core\t: %s revision %d\n",
- cpu_names[boot_cpu_data.cpu_type],
- boot_cpu_data.cpu_revision);
-
- freq = (clk_get_rate(boot_cpu_data.clk) + 500) / 1000;
- seq_printf(m, "cpu MHz\t\t: %u.%03u\n", freq / 1000, freq % 1000);
-
- seq_printf(m, "i-cache\t\t: %dK (%u ways x %u sets x %u)\n",
- icache_size >> 10,
- boot_cpu_data.icache.ways,
- boot_cpu_data.icache.sets,
- boot_cpu_data.icache.linesz);
- seq_printf(m, "d-cache\t\t: %dK (%u ways x %u sets x %u)\n",
- dcache_size >> 10,
- boot_cpu_data.dcache.ways,
- boot_cpu_data.dcache.sets,
- boot_cpu_data.dcache.linesz);
-
- seq_printf(m, "features\t:");
- for (i = 0; i < ARRAY_SIZE(cpu_feature_flags); i++)
- if (boot_cpu_data.features & (1 << i))
- seq_printf(m, " %s", cpu_feature_flags[i]);
-
- seq_printf(m, "\nbogomips\t: %lu.%02lu\n",
- boot_cpu_data.loops_per_jiffy / (500000/HZ),
- (boot_cpu_data.loops_per_jiffy / (5000/HZ)) % 100);
-
- return 0;
-}
-
-static void *c_start(struct seq_file *m, loff_t *pos)
-{
- return *pos < 1 ? (void *)1 : NULL;
-}
-
-static void *c_next(struct seq_file *m, void *v, loff_t *pos)
-{
- ++*pos;
- return NULL;
-}
-
-static void c_stop(struct seq_file *m, void *v)
-{
-
-}
-
-const struct seq_operations cpuinfo_op = {
- .start = c_start,
- .next = c_next,
- .stop = c_stop,
- .show = c_show
-};
-#endif /* CONFIG_PROC_FS */
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-/*
- * This file contains the low-level entry-points into the kernel, that is,
- * exception handlers, debug trap handlers, interrupt handlers and the
- * system call handler.
- */
-#include <linux/errno.h>
-
-#include <asm/asm.h>
-#include <asm/hardirq.h>
-#include <asm/irq.h>
-#include <asm/ocd.h>
-#include <asm/page.h>
-#include <asm/pgtable.h>
-#include <asm/ptrace.h>
-#include <asm/sysreg.h>
-#include <asm/thread_info.h>
-#include <asm/unistd.h>
-
-#ifdef CONFIG_PREEMPT
-# define preempt_stop mask_interrupts
-#else
-# define preempt_stop
-# define fault_resume_kernel fault_restore_all
-#endif
-
-#define __MASK(x) ((1 << (x)) - 1)
-#define IRQ_MASK ((__MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT) | \
- (__MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT))
-
- .section .ex.text,"ax",@progbits
- .align 2
-exception_vectors:
- bral handle_critical
- .align 2
- bral handle_critical
- .align 2
- bral do_bus_error_write
- .align 2
- bral do_bus_error_read
- .align 2
- bral do_nmi_ll
- .align 2
- bral handle_address_fault
- .align 2
- bral handle_protection_fault
- .align 2
- bral handle_debug
- .align 2
- bral do_illegal_opcode_ll
- .align 2
- bral do_illegal_opcode_ll
- .align 2
- bral do_illegal_opcode_ll
- .align 2
- bral do_fpe_ll
- .align 2
- bral do_illegal_opcode_ll
- .align 2
- bral handle_address_fault
- .align 2
- bral handle_address_fault
- .align 2
- bral handle_protection_fault
- .align 2
- bral handle_protection_fault
- .align 2
- bral do_dtlb_modified
-
-#define tlbmiss_save pushm r0-r3
-#define tlbmiss_restore popm r0-r3
-
- .org 0x50
- .global itlb_miss
-itlb_miss:
- tlbmiss_save
- rjmp tlb_miss_common
-
- .org 0x60
-dtlb_miss_read:
- tlbmiss_save
- rjmp tlb_miss_common
-
- .org 0x70
-dtlb_miss_write:
- tlbmiss_save
-
- .global tlb_miss_common
- .align 2
-tlb_miss_common:
- mfsr r0, SYSREG_TLBEAR
- mfsr r1, SYSREG_PTBR
-
- /*
- * First level lookup: The PGD contains virtual pointers to
- * the second-level page tables, but they may be NULL if not
- * present.
- */
-pgtbl_lookup:
- lsr r2, r0, PGDIR_SHIFT
- ld.w r3, r1[r2 << 2]
- bfextu r1, r0, PAGE_SHIFT, PGDIR_SHIFT - PAGE_SHIFT
- cp.w r3, 0
- breq page_table_not_present
-
- /* Second level lookup */
- ld.w r2, r3[r1 << 2]
- mfsr r0, SYSREG_TLBARLO
- bld r2, _PAGE_BIT_PRESENT
- brcc page_not_present
-
- /* Mark the page as accessed */
- sbr r2, _PAGE_BIT_ACCESSED
- st.w r3[r1 << 2], r2
-
- /* Drop software flags */
- andl r2, _PAGE_FLAGS_HARDWARE_MASK & 0xffff
- mtsr SYSREG_TLBELO, r2
-
- /* Figure out which entry we want to replace */
- mfsr r1, SYSREG_MMUCR
- clz r2, r0
- brcc 1f
- mov r3, -1 /* All entries have been accessed, */
- mov r2, 0 /* so start at 0 */
- mtsr SYSREG_TLBARLO, r3 /* and reset TLBAR */
-
-1: bfins r1, r2, SYSREG_DRP_OFFSET, SYSREG_DRP_SIZE
- mtsr SYSREG_MMUCR, r1
- tlbw
-
- tlbmiss_restore
- rete
-
- /* The slow path of the TLB miss handler */
- .align 2
-page_table_not_present:
- /* Do we need to synchronize with swapper_pg_dir? */
- bld r0, 31
- brcs sync_with_swapper_pg_dir
-
-page_not_present:
- tlbmiss_restore
- sub sp, 4
- stmts --sp, r0-lr
- call save_full_context_ex
- mfsr r12, SYSREG_ECR
- mov r11, sp
- call do_page_fault
- rjmp ret_from_exception
-
- .align 2
-sync_with_swapper_pg_dir:
- /*
- * If swapper_pg_dir contains a non-NULL second-level page
- * table pointer, copy it into the current PGD. If not, we
- * must handle it as a full-blown page fault.
- *
- * Jumping back to pgtbl_lookup causes an unnecessary lookup,
- * but it is guaranteed to be a cache hit, it won't happen
- * very often, and we absolutely do not want to sacrifice any
- * performance in the fast path in order to improve this.
- */
- mov r1, lo(swapper_pg_dir)
- orh r1, hi(swapper_pg_dir)
- ld.w r3, r1[r2 << 2]
- cp.w r3, 0
- breq page_not_present
- mfsr r1, SYSREG_PTBR
- st.w r1[r2 << 2], r3
- rjmp pgtbl_lookup
-
- /*
- * We currently have two bytes left at this point until we
- * crash into the system call handler...
- *
- * Don't worry, the assembler will let us know.
- */
-
-
- /* --- System Call --- */
-
- .org 0x100
-system_call:
-#ifdef CONFIG_PREEMPT
- mask_interrupts
-#endif
- pushm r12 /* r12_orig */
- stmts --sp, r0-lr
-
- mfsr r0, SYSREG_RAR_SUP
- mfsr r1, SYSREG_RSR_SUP
-#ifdef CONFIG_PREEMPT
- unmask_interrupts
-#endif
- zero_fp
- stm --sp, r0-r1
-
- /* check for syscall tracing */
- get_thread_info r0
- ld.w r1, r0[TI_flags]
- bld r1, TIF_SYSCALL_TRACE
- brcs syscall_trace_enter
-
-syscall_trace_cont:
- cp.w r8, NR_syscalls
- brhs syscall_badsys
-
- lddpc lr, syscall_table_addr
- ld.w lr, lr[r8 << 2]
- mov r8, r5 /* 5th argument (6th is pushed by stub) */
- icall lr
-
- .global syscall_return
-syscall_return:
- get_thread_info r0
- mask_interrupts /* make sure we don't miss an interrupt
- setting need_resched or sigpending
- between sampling and the rets */
-
- /* Store the return value so that the correct value is loaded below */
- stdsp sp[REG_R12], r12
-
- ld.w r1, r0[TI_flags]
- andl r1, _TIF_ALLWORK_MASK, COH
- brne syscall_exit_work
-
-syscall_exit_cont:
- popm r8-r9
- mtsr SYSREG_RAR_SUP, r8
- mtsr SYSREG_RSR_SUP, r9
- ldmts sp++, r0-lr
- sub sp, -4 /* r12_orig */
- rets
-
- .align 2
-syscall_table_addr:
- .long sys_call_table
-
-syscall_badsys:
- mov r12, -ENOSYS
- rjmp syscall_return
-
- .global ret_from_fork
-ret_from_fork:
- call schedule_tail
- mov r12, 0
- rjmp syscall_return
-
- .global ret_from_kernel_thread
-ret_from_kernel_thread:
- call schedule_tail
- mov r12, r0
- mov lr, r2 /* syscall_return */
- mov pc, r1
-
-syscall_trace_enter:
- pushm r8-r12
- call syscall_trace
- popm r8-r12
- rjmp syscall_trace_cont
-
-syscall_exit_work:
- bld r1, TIF_SYSCALL_TRACE
- brcc 1f
- unmask_interrupts
- call syscall_trace
- mask_interrupts
- ld.w r1, r0[TI_flags]
-
-1: bld r1, TIF_NEED_RESCHED
- brcc 2f
- unmask_interrupts
- call schedule
- mask_interrupts
- ld.w r1, r0[TI_flags]
- rjmp 1b
-
-2: mov r2, _TIF_SIGPENDING | _TIF_NOTIFY_RESUME
- tst r1, r2
- breq 3f
- unmask_interrupts
- mov r12, sp
- mov r11, r0
- call do_notify_resume
- mask_interrupts
- ld.w r1, r0[TI_flags]
- rjmp 1b
-
-3: bld r1, TIF_BREAKPOINT
- brcc syscall_exit_cont
- rjmp enter_monitor_mode
-
- /* This function expects to find offending PC in SYSREG_RAR_EX */
- .type save_full_context_ex, @function
- .align 2
-save_full_context_ex:
- mfsr r11, SYSREG_RAR_EX
- sub r9, pc, . - debug_trampoline
- mfsr r8, SYSREG_RSR_EX
- cp.w r9, r11
- breq 3f
- mov r12, r8
- andh r8, (MODE_MASK >> 16), COH
- brne 2f
-
-1: pushm r11, r12 /* PC and SR */
- unmask_exceptions
- ret r12
-
-2: sub r10, sp, -(FRAME_SIZE_FULL - REG_LR)
- stdsp sp[4], r10 /* replace saved SP */
- rjmp 1b
-
- /*
- * The debug handler set up a trampoline to make us
- * automatically enter monitor mode upon return, but since
- * we're saving the full context, we must assume that the
- * exception handler might want to alter the return address
- * and/or status register. So we need to restore the original
- * context and enter monitor mode manually after the exception
- * has been handled.
- */
-3: get_thread_info r8
- ld.w r11, r8[TI_rar_saved]
- ld.w r12, r8[TI_rsr_saved]
- rjmp 1b
- .size save_full_context_ex, . - save_full_context_ex
-
- /* Low-level exception handlers */
-handle_critical:
- /*
- * AT32AP700x errata:
- *
- * After a Java stack overflow or underflow trap, any CPU
- * memory access may cause erratic behavior. This will happen
- * when the four least significant bits of the JOSP system
- * register contains any value between 9 and 15 (inclusive).
- *
- * Possible workarounds:
- * - Don't use the Java Extension Module
- * - Ensure that the stack overflow and underflow trap
- * handlers do not do any memory access or trigger any
- * exceptions before the overflow/underflow condition is
- * cleared (by incrementing or decrementing the JOSP)
- * - Make sure that JOSP does not contain any problematic
- * value before doing any exception or interrupt
- * processing.
- * - Set up a critical exception handler which writes a
- * known-to-be-safe value, e.g. 4, to JOSP before doing
- * any further processing.
- *
- * We'll use the last workaround for now since we cannot
- * guarantee that user space processes don't use Java mode.
- * Non-well-behaving userland will be terminated with extreme
- * prejudice.
- */
-#ifdef CONFIG_CPU_AT32AP700X
- /*
- * There's a chance we can't touch memory, so temporarily
- * borrow PTBR to save the stack pointer while we fix things
- * up...
- */
- mtsr SYSREG_PTBR, sp
- mov sp, 4
- mtsr SYSREG_JOSP, sp
- mfsr sp, SYSREG_PTBR
- sub pc, -2
-
- /* Push most of pt_regs on stack. We'll do the rest later */
- sub sp, 4
- pushm r0-r12
-
- /* PTBR mirrors current_thread_info()->task->active_mm->pgd */
- get_thread_info r0
- ld.w r1, r0[TI_task]
- ld.w r2, r1[TSK_active_mm]
- ld.w r3, r2[MM_pgd]
- mtsr SYSREG_PTBR, r3
-#else
- sub sp, 4
- pushm r0-r12
-#endif
- sub r0, sp, -(14 * 4)
- mov r1, lr
- mfsr r2, SYSREG_RAR_EX
- mfsr r3, SYSREG_RSR_EX
- pushm r0-r3
-
- mfsr r12, SYSREG_ECR
- mov r11, sp
- call do_critical_exception
-
- /* We should never get here... */
-bad_return:
- sub r12, pc, (. - 1f)
- lddpc pc, 2f
- .align 2
-1: .asciz "Return from critical exception!"
-2: .long panic
-
- .align 1
-do_bus_error_write:
- sub sp, 4
- stmts --sp, r0-lr
- call save_full_context_ex
- mov r11, 1
- rjmp 1f
-
-do_bus_error_read:
- sub sp, 4
- stmts --sp, r0-lr
- call save_full_context_ex
- mov r11, 0
-1: mfsr r12, SYSREG_BEAR
- mov r10, sp
- call do_bus_error
- rjmp ret_from_exception
-
- .align 1
-do_nmi_ll:
- sub sp, 4
- stmts --sp, r0-lr
- mfsr r9, SYSREG_RSR_NMI
- mfsr r8, SYSREG_RAR_NMI
- bfextu r0, r9, MODE_SHIFT, 3
- brne 2f
-
-1: pushm r8, r9 /* PC and SR */
- mfsr r12, SYSREG_ECR
- mov r11, sp
- call do_nmi
- popm r8-r9
- mtsr SYSREG_RAR_NMI, r8
- tst r0, r0
- mtsr SYSREG_RSR_NMI, r9
- brne 3f
-
- ldmts sp++, r0-lr
- sub sp, -4 /* skip r12_orig */
- rete
-
-2: sub r10, sp, -(FRAME_SIZE_FULL - REG_LR)
- stdsp sp[4], r10 /* replace saved SP */
- rjmp 1b
-
-3: popm lr
- sub sp, -4 /* skip sp */
- popm r0-r12
- sub sp, -4 /* skip r12_orig */
- rete
-
-handle_address_fault:
- sub sp, 4
- stmts --sp, r0-lr
- call save_full_context_ex
- mfsr r12, SYSREG_ECR
- mov r11, sp
- call do_address_exception
- rjmp ret_from_exception
-
-handle_protection_fault:
- sub sp, 4
- stmts --sp, r0-lr
- call save_full_context_ex
- mfsr r12, SYSREG_ECR
- mov r11, sp
- call do_page_fault
- rjmp ret_from_exception
-
- .align 1
-do_illegal_opcode_ll:
- sub sp, 4
- stmts --sp, r0-lr
- call save_full_context_ex
- mfsr r12, SYSREG_ECR
- mov r11, sp
- call do_illegal_opcode
- rjmp ret_from_exception
-
-do_dtlb_modified:
- pushm r0-r3
- mfsr r1, SYSREG_TLBEAR
- mfsr r0, SYSREG_PTBR
- lsr r2, r1, PGDIR_SHIFT
- ld.w r0, r0[r2 << 2]
- lsl r1, (32 - PGDIR_SHIFT)
- lsr r1, (32 - PGDIR_SHIFT) + PAGE_SHIFT
-
- /* Translate to virtual address in P1 */
- andl r0, 0xf000
- sbr r0, 31
- add r2, r0, r1 << 2
- ld.w r3, r2[0]
- sbr r3, _PAGE_BIT_DIRTY
- mov r0, r3
- st.w r2[0], r3
-
- /* The page table is up-to-date. Update the TLB entry as well */
- andl r0, lo(_PAGE_FLAGS_HARDWARE_MASK)
- mtsr SYSREG_TLBELO, r0
-
- /* MMUCR[DRP] is updated automatically, so let's go... */
- tlbw
-
- popm r0-r3
- rete
-
-do_fpe_ll:
- sub sp, 4
- stmts --sp, r0-lr
- call save_full_context_ex
- unmask_interrupts
- mov r12, 26
- mov r11, sp
- call do_fpe
- rjmp ret_from_exception
-
-ret_from_exception:
- mask_interrupts
- lddsp r4, sp[REG_SR]
-
- andh r4, (MODE_MASK >> 16), COH
- brne fault_resume_kernel
-
- get_thread_info r0
- ld.w r1, r0[TI_flags]
- andl r1, _TIF_WORK_MASK, COH
- brne fault_exit_work
-
-fault_resume_user:
- popm r8-r9
- mask_exceptions
- mtsr SYSREG_RAR_EX, r8
- mtsr SYSREG_RSR_EX, r9
- ldmts sp++, r0-lr
- sub sp, -4
- rete
-
-fault_resume_kernel:
-#ifdef CONFIG_PREEMPT
- get_thread_info r0
- ld.w r2, r0[TI_preempt_count]
- cp.w r2, 0
- brne 1f
- ld.w r1, r0[TI_flags]
- bld r1, TIF_NEED_RESCHED
- brcc 1f
- lddsp r4, sp[REG_SR]
- bld r4, SYSREG_GM_OFFSET
- brcs 1f
- call preempt_schedule_irq
-1:
-#endif
-
- popm r8-r9
- mask_exceptions
- mfsr r1, SYSREG_SR
- mtsr SYSREG_RAR_EX, r8
- mtsr SYSREG_RSR_EX, r9
- popm lr
- sub sp, -4 /* ignore SP */
- popm r0-r12
- sub sp, -4 /* ignore r12_orig */
- rete
-
-irq_exit_work:
- /* Switch to exception mode so that we can share the same code. */
- mfsr r8, SYSREG_SR
- cbr r8, SYSREG_M0_OFFSET
- orh r8, hi(SYSREG_BIT(M1) | SYSREG_BIT(M2))
- mtsr SYSREG_SR, r8
- sub pc, -2
- get_thread_info r0
- ld.w r1, r0[TI_flags]
-
-fault_exit_work:
- bld r1, TIF_NEED_RESCHED
- brcc 1f
- unmask_interrupts
- call schedule
- mask_interrupts
- ld.w r1, r0[TI_flags]
- rjmp fault_exit_work
-
-1: mov r2, _TIF_SIGPENDING | _TIF_NOTIFY_RESUME
- tst r1, r2
- breq 2f
- unmask_interrupts
- mov r12, sp
- mov r11, r0
- call do_notify_resume
- mask_interrupts
- ld.w r1, r0[TI_flags]
- rjmp fault_exit_work
-
-2: bld r1, TIF_BREAKPOINT
- brcc fault_resume_user
- rjmp enter_monitor_mode
-
- .section .kprobes.text, "ax", @progbits
- .type handle_debug, @function
-handle_debug:
- sub sp, 4 /* r12_orig */
- stmts --sp, r0-lr
- mfsr r8, SYSREG_RAR_DBG
- mfsr r9, SYSREG_RSR_DBG
- unmask_exceptions
- pushm r8-r9
- bfextu r9, r9, SYSREG_MODE_OFFSET, SYSREG_MODE_SIZE
- brne debug_fixup_regs
-
-.Ldebug_fixup_cont:
-#ifdef CONFIG_TRACE_IRQFLAGS
- call trace_hardirqs_off
-#endif
- mov r12, sp
- call do_debug
- mov sp, r12
-
- lddsp r2, sp[REG_SR]
- bfextu r3, r2, SYSREG_MODE_OFFSET, SYSREG_MODE_SIZE
- brne debug_resume_kernel
-
- get_thread_info r0
- ld.w r1, r0[TI_flags]
- mov r2, _TIF_DBGWORK_MASK
- tst r1, r2
- brne debug_exit_work
-
- bld r1, TIF_SINGLE_STEP
- brcc 1f
- mfdr r4, OCD_DC
- sbr r4, OCD_DC_SS_BIT
- mtdr OCD_DC, r4
-
-1: popm r10,r11
- mask_exceptions
- mtsr SYSREG_RSR_DBG, r11
- mtsr SYSREG_RAR_DBG, r10
-#ifdef CONFIG_TRACE_IRQFLAGS
- call trace_hardirqs_on
-1:
-#endif
- ldmts sp++, r0-lr
- sub sp, -4
- retd
- .size handle_debug, . - handle_debug
-
- /* Mode of the trapped context is in r9 */
- .type debug_fixup_regs, @function
-debug_fixup_regs:
- mfsr r8, SYSREG_SR
- mov r10, r8
- bfins r8, r9, SYSREG_MODE_OFFSET, SYSREG_MODE_SIZE
- mtsr SYSREG_SR, r8
- sub pc, -2
- stdsp sp[REG_LR], lr
- mtsr SYSREG_SR, r10
- sub pc, -2
- sub r8, sp, -FRAME_SIZE_FULL
- stdsp sp[REG_SP], r8
- rjmp .Ldebug_fixup_cont
- .size debug_fixup_regs, . - debug_fixup_regs
-
- .type debug_resume_kernel, @function
-debug_resume_kernel:
- mask_exceptions
- popm r10, r11
- mtsr SYSREG_RAR_DBG, r10
- mtsr SYSREG_RSR_DBG, r11
-#ifdef CONFIG_TRACE_IRQFLAGS
- bld r11, SYSREG_GM_OFFSET
- brcc 1f
- call trace_hardirqs_on
-1:
-#endif
- mfsr r2, SYSREG_SR
- mov r1, r2
- bfins r2, r3, SYSREG_MODE_OFFSET, SYSREG_MODE_SIZE
- mtsr SYSREG_SR, r2
- sub pc, -2
- popm lr
- mtsr SYSREG_SR, r1
- sub pc, -2
- sub sp, -4 /* skip SP */
- popm r0-r12
- sub sp, -4
- retd
- .size debug_resume_kernel, . - debug_resume_kernel
-
- .type debug_exit_work, @function
-debug_exit_work:
- /*
- * We must return from Monitor Mode using a retd, and we must
- * not schedule since that involves the D bit in SR getting
- * cleared by something other than the debug hardware. This
- * may cause undefined behaviour according to the Architecture
- * manual.
- *
- * So we fix up the return address and status and return to a
- * stub below in Exception mode. From there, we can follow the
- * normal exception return path.
- *
- * The real return address and status registers are stored on
- * the stack in the way the exception return path understands,
- * so no need to fix anything up there.
- */
- sub r8, pc, . - fault_exit_work
- mtsr SYSREG_RAR_DBG, r8
- mov r9, 0
- orh r9, hi(SR_EM | SR_GM | MODE_EXCEPTION)
- mtsr SYSREG_RSR_DBG, r9
- sub pc, -2
- retd
- .size debug_exit_work, . - debug_exit_work
-
- .set rsr_int0, SYSREG_RSR_INT0
- .set rsr_int1, SYSREG_RSR_INT1
- .set rsr_int2, SYSREG_RSR_INT2
- .set rsr_int3, SYSREG_RSR_INT3
- .set rar_int0, SYSREG_RAR_INT0
- .set rar_int1, SYSREG_RAR_INT1
- .set rar_int2, SYSREG_RAR_INT2
- .set rar_int3, SYSREG_RAR_INT3
-
- .macro IRQ_LEVEL level
- .type irq_level\level, @function
-irq_level\level:
- sub sp, 4 /* r12_orig */
- stmts --sp,r0-lr
- mfsr r8, rar_int\level
- mfsr r9, rsr_int\level
-
-#ifdef CONFIG_PREEMPT
- sub r11, pc, (. - system_call)
- cp.w r11, r8
- breq 4f
-#endif
-
- pushm r8-r9
-
- mov r11, sp
- mov r12, \level
-
- call do_IRQ
-
- lddsp r4, sp[REG_SR]
- bfextu r4, r4, SYSREG_M0_OFFSET, 3
- cp.w r4, MODE_SUPERVISOR >> SYSREG_M0_OFFSET
- breq 2f
- cp.w r4, MODE_USER >> SYSREG_M0_OFFSET
-#ifdef CONFIG_PREEMPT
- brne 3f
-#else
- brne 1f
-#endif
-
- get_thread_info r0
- ld.w r1, r0[TI_flags]
- andl r1, _TIF_WORK_MASK, COH
- brne irq_exit_work
-
-1:
-#ifdef CONFIG_TRACE_IRQFLAGS
- call trace_hardirqs_on
-#endif
- popm r8-r9
- mtsr rar_int\level, r8
- mtsr rsr_int\level, r9
- ldmts sp++,r0-lr
- sub sp, -4 /* ignore r12_orig */
- rete
-
-#ifdef CONFIG_PREEMPT
-4: mask_interrupts
- mfsr r8, rsr_int\level
- sbr r8, 16
- mtsr rsr_int\level, r8
- ldmts sp++, r0-lr
- sub sp, -4 /* ignore r12_orig */
- rete
-#endif
-
-2: get_thread_info r0
- ld.w r1, r0[TI_flags]
- bld r1, TIF_CPU_GOING_TO_SLEEP
-#ifdef CONFIG_PREEMPT
- brcc 3f
-#else
- brcc 1b
-#endif
- sub r1, pc, . - cpu_idle_skip_sleep
- stdsp sp[REG_PC], r1
-#ifdef CONFIG_PREEMPT
-3: get_thread_info r0
- ld.w r2, r0[TI_preempt_count]
- cp.w r2, 0
- brne 1b
- ld.w r1, r0[TI_flags]
- bld r1, TIF_NEED_RESCHED
- brcc 1b
- lddsp r4, sp[REG_SR]
- bld r4, SYSREG_GM_OFFSET
- brcs 1b
- call preempt_schedule_irq
-#endif
- rjmp 1b
- .endm
-
- .section .irq.text,"ax",@progbits
-
- .global irq_level0
- .global irq_level1
- .global irq_level2
- .global irq_level3
- IRQ_LEVEL 0
- IRQ_LEVEL 1
- IRQ_LEVEL 2
- IRQ_LEVEL 3
-
- .section .kprobes.text, "ax", @progbits
- .type enter_monitor_mode, @function
-enter_monitor_mode:
- /*
- * We need to enter monitor mode to do a single step. The
- * monitor code will alter the return address so that we
- * return directly to the user instead of returning here.
- */
- breakpoint
- rjmp breakpoint_failed
-
- .size enter_monitor_mode, . - enter_monitor_mode
-
- .type debug_trampoline, @function
- .global debug_trampoline
-debug_trampoline:
- /*
- * Save the registers on the stack so that the monitor code
- * can find them easily.
- */
- sub sp, 4 /* r12_orig */
- stmts --sp, r0-lr
- get_thread_info r0
- ld.w r8, r0[TI_rar_saved]
- ld.w r9, r0[TI_rsr_saved]
- pushm r8-r9
-
- /*
- * The monitor code will alter the return address so we don't
- * return here.
- */
- breakpoint
- rjmp breakpoint_failed
- .size debug_trampoline, . - debug_trampoline
-
- .type breakpoint_failed, @function
-breakpoint_failed:
- /*
- * Something went wrong. Perhaps the debug hardware isn't
- * enabled?
- */
- lda.w r12, msg_breakpoint_failed
- mov r11, sp
- mov r10, 9 /* SIGKILL */
- call die
-1: rjmp 1b
-
-msg_breakpoint_failed:
- .asciz "Failed to enter Debug Mode"
+++ /dev/null
-/*
- * Non-board-specific low-level startup code
- *
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/linkage.h>
-
-#include <asm/page.h>
-
- .section .init.text,"ax"
- .global kernel_entry
-kernel_entry:
- /* Start the show */
- lddpc pc, kernel_start_addr
-
- .align 2
-kernel_start_addr:
- .long start_kernel
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * Based on arch/i386/kernel/irq.c
- * Copyright (C) 1992, 1998 Linus Torvalds, Ingo Molnar
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/kernel_stat.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <linux/device.h>
-
-/* May be overridden by platform code */
-int __weak nmi_enable(void)
-{
- return -ENOSYS;
-}
-
-void __weak nmi_disable(void)
-{
-
-}
+++ /dev/null
-/*
- * Kernel Probes (KProbes)
- *
- * Copyright (C) 2005-2006 Atmel Corporation
- *
- * Based on arch/ppc64/kernel/kprobes.c
- * Copyright (C) IBM Corporation, 2002, 2004
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/kprobes.h>
-#include <linux/ptrace.h>
-
-#include <asm/cacheflush.h>
-#include <linux/kdebug.h>
-#include <asm/ocd.h>
-
-DEFINE_PER_CPU(struct kprobe *, current_kprobe);
-static unsigned long kprobe_status;
-static struct pt_regs jprobe_saved_regs;
-
-struct kretprobe_blackpoint kretprobe_blacklist[] = {{NULL, NULL}};
-
-int __kprobes arch_prepare_kprobe(struct kprobe *p)
-{
- int ret = 0;
-
- if ((unsigned long)p->addr & 0x01) {
- printk("Attempt to register kprobe at an unaligned address\n");
- ret = -EINVAL;
- }
-
- /* XXX: Might be a good idea to check if p->addr is a valid
- * kernel address as well... */
-
- if (!ret) {
- pr_debug("copy kprobe at %p\n", p->addr);
- memcpy(p->ainsn.insn, p->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
- p->opcode = *p->addr;
- }
-
- return ret;
-}
-
-void __kprobes arch_arm_kprobe(struct kprobe *p)
-{
- pr_debug("arming kprobe at %p\n", p->addr);
- ocd_enable(NULL);
- *p->addr = BREAKPOINT_INSTRUCTION;
- flush_icache_range((unsigned long)p->addr,
- (unsigned long)p->addr + sizeof(kprobe_opcode_t));
-}
-
-void __kprobes arch_disarm_kprobe(struct kprobe *p)
-{
- pr_debug("disarming kprobe at %p\n", p->addr);
- ocd_disable(NULL);
- *p->addr = p->opcode;
- flush_icache_range((unsigned long)p->addr,
- (unsigned long)p->addr + sizeof(kprobe_opcode_t));
-}
-
-static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
-{
- unsigned long dc;
-
- pr_debug("preparing to singlestep over %p (PC=%08lx)\n",
- p->addr, regs->pc);
-
- BUG_ON(!(sysreg_read(SR) & SYSREG_BIT(SR_D)));
-
- dc = ocd_read(DC);
- dc |= 1 << OCD_DC_SS_BIT;
- ocd_write(DC, dc);
-
- /*
- * We must run the instruction from its original location
- * since it may actually reference PC.
- *
- * TODO: Do the instruction replacement directly in icache.
- */
- *p->addr = p->opcode;
- flush_icache_range((unsigned long)p->addr,
- (unsigned long)p->addr + sizeof(kprobe_opcode_t));
-}
-
-static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs)
-{
- unsigned long dc;
-
- pr_debug("resuming execution at PC=%08lx\n", regs->pc);
-
- dc = ocd_read(DC);
- dc &= ~(1 << OCD_DC_SS_BIT);
- ocd_write(DC, dc);
-
- *p->addr = BREAKPOINT_INSTRUCTION;
- flush_icache_range((unsigned long)p->addr,
- (unsigned long)p->addr + sizeof(kprobe_opcode_t));
-}
-
-static void __kprobes set_current_kprobe(struct kprobe *p)
-{
- __this_cpu_write(current_kprobe, p);
-}
-
-static int __kprobes kprobe_handler(struct pt_regs *regs)
-{
- struct kprobe *p;
- void *addr = (void *)regs->pc;
- int ret = 0;
-
- pr_debug("kprobe_handler: kprobe_running=%p\n",
- kprobe_running());
-
- /*
- * We don't want to be preempted for the entire
- * duration of kprobe processing
- */
- preempt_disable();
-
- /* Check that we're not recursing */
- if (kprobe_running()) {
- p = get_kprobe(addr);
- if (p) {
- if (kprobe_status == KPROBE_HIT_SS) {
- printk("FIXME: kprobe hit while single-stepping!\n");
- goto no_kprobe;
- }
-
- printk("FIXME: kprobe hit while handling another kprobe\n");
- goto no_kprobe;
- } else {
- p = kprobe_running();
- if (p->break_handler && p->break_handler(p, regs))
- goto ss_probe;
- }
- /* If it's not ours, can't be delete race, (we hold lock). */
- goto no_kprobe;
- }
-
- p = get_kprobe(addr);
- if (!p)
- goto no_kprobe;
-
- kprobe_status = KPROBE_HIT_ACTIVE;
- set_current_kprobe(p);
- if (p->pre_handler && p->pre_handler(p, regs))
- /* handler has already set things up, so skip ss setup */
- return 1;
-
-ss_probe:
- prepare_singlestep(p, regs);
- kprobe_status = KPROBE_HIT_SS;
- return 1;
-
-no_kprobe:
- preempt_enable_no_resched();
- return ret;
-}
-
-static int __kprobes post_kprobe_handler(struct pt_regs *regs)
-{
- struct kprobe *cur = kprobe_running();
-
- pr_debug("post_kprobe_handler, cur=%p\n", cur);
-
- if (!cur)
- return 0;
-
- if (cur->post_handler) {
- kprobe_status = KPROBE_HIT_SSDONE;
- cur->post_handler(cur, regs, 0);
- }
-
- resume_execution(cur, regs);
- reset_current_kprobe();
- preempt_enable_no_resched();
-
- return 1;
-}
-
-int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
-{
- struct kprobe *cur = kprobe_running();
-
- pr_debug("kprobe_fault_handler: trapnr=%d\n", trapnr);
-
- if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
- return 1;
-
- if (kprobe_status & KPROBE_HIT_SS) {
- resume_execution(cur, regs);
- preempt_enable_no_resched();
- }
- return 0;
-}
-
-/*
- * Wrapper routine to for handling exceptions.
- */
-int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
- unsigned long val, void *data)
-{
- struct die_args *args = (struct die_args *)data;
- int ret = NOTIFY_DONE;
-
- pr_debug("kprobe_exceptions_notify: val=%lu, data=%p\n",
- val, data);
-
- switch (val) {
- case DIE_BREAKPOINT:
- if (kprobe_handler(args->regs))
- ret = NOTIFY_STOP;
- break;
- case DIE_SSTEP:
- if (post_kprobe_handler(args->regs))
- ret = NOTIFY_STOP;
- break;
- default:
- break;
- }
-
- return ret;
-}
-
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
- struct jprobe *jp = container_of(p, struct jprobe, kp);
-
- memcpy(&jprobe_saved_regs, regs, sizeof(struct pt_regs));
-
- /*
- * TODO: We should probably save some of the stack here as
- * well, since gcc may pass arguments on the stack for certain
- * functions (lots of arguments, large aggregates, varargs)
- */
-
- /* setup return addr to the jprobe handler routine */
- regs->pc = (unsigned long)jp->entry;
- return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
- asm volatile("breakpoint" ::: "memory");
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
- /*
- * FIXME - we should ideally be validating that we got here 'cos
- * of the "trap" in jprobe_return() above, before restoring the
- * saved regs...
- */
- memcpy(regs, &jprobe_saved_regs, sizeof(struct pt_regs));
- return 1;
-}
-
-int __init arch_init_kprobes(void)
-{
- /* TODO: Register kretprobe trampoline */
- return 0;
-}
+++ /dev/null
-/*
- * AVR32-specific kernel module loader
- *
- * Copyright (C) 2005-2006 Atmel Corporation
- *
- * GOT initialization parts are based on the s390 version
- * Copyright (C) 2002, 2003 IBM Deutschland Entwicklung GmbH,
- * IBM Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/bug.h>
-#include <linux/elf.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/moduleloader.h>
-#include <linux/vmalloc.h>
-
-void module_arch_freeing_init(struct module *mod)
-{
- vfree(mod->arch.syminfo);
- mod->arch.syminfo = NULL;
-}
-
-static inline int check_rela(Elf32_Rela *rela, struct module *module,
- char *strings, Elf32_Sym *symbols)
-{
- struct mod_arch_syminfo *info;
-
- info = module->arch.syminfo + ELF32_R_SYM(rela->r_info);
- switch (ELF32_R_TYPE(rela->r_info)) {
- case R_AVR32_GOT32:
- case R_AVR32_GOT16:
- case R_AVR32_GOT8:
- case R_AVR32_GOT21S:
- case R_AVR32_GOT18SW: /* mcall */
- case R_AVR32_GOT16S: /* ld.w */
- if (rela->r_addend != 0) {
- printk(KERN_ERR
- "GOT relocation against %s at offset %u with addend\n",
- strings + symbols[ELF32_R_SYM(rela->r_info)].st_name,
- rela->r_offset);
- return -ENOEXEC;
- }
- if (info->got_offset == -1UL) {
- info->got_offset = module->arch.got_size;
- module->arch.got_size += sizeof(void *);
- }
- pr_debug("GOT[%3lu] %s\n", info->got_offset,
- strings + symbols[ELF32_R_SYM(rela->r_info)].st_name);
- break;
- }
-
- return 0;
-}
-
-int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
- char *secstrings, struct module *module)
-{
- Elf32_Shdr *symtab;
- Elf32_Sym *symbols;
- Elf32_Rela *rela;
- char *strings;
- int nrela, i, j;
- int ret;
-
- /* Find the symbol table */
- symtab = NULL;
- for (i = 0; i < hdr->e_shnum; i++)
- switch (sechdrs[i].sh_type) {
- case SHT_SYMTAB:
- symtab = &sechdrs[i];
- break;
- }
- if (!symtab) {
- printk(KERN_ERR "module %s: no symbol table\n", module->name);
- return -ENOEXEC;
- }
-
- /* Allocate room for one syminfo structure per symbol. */
- module->arch.nsyms = symtab->sh_size / sizeof(Elf_Sym);
- module->arch.syminfo = vmalloc(module->arch.nsyms
- * sizeof(struct mod_arch_syminfo));
- if (!module->arch.syminfo)
- return -ENOMEM;
-
- symbols = (void *)hdr + symtab->sh_offset;
- strings = (void *)hdr + sechdrs[symtab->sh_link].sh_offset;
- for (i = 0; i < module->arch.nsyms; i++) {
- if (symbols[i].st_shndx == SHN_UNDEF &&
- strcmp(strings + symbols[i].st_name,
- "_GLOBAL_OFFSET_TABLE_") == 0)
- /* "Define" it as absolute. */
- symbols[i].st_shndx = SHN_ABS;
- module->arch.syminfo[i].got_offset = -1UL;
- module->arch.syminfo[i].got_initialized = 0;
- }
-
- /* Allocate GOT entries for symbols that need it. */
- module->arch.got_size = 0;
- for (i = 0; i < hdr->e_shnum; i++) {
- if (sechdrs[i].sh_type != SHT_RELA)
- continue;
- nrela = sechdrs[i].sh_size / sizeof(Elf32_Rela);
- rela = (void *)hdr + sechdrs[i].sh_offset;
- for (j = 0; j < nrela; j++) {
- ret = check_rela(rela + j, module,
- strings, symbols);
- if (ret)
- goto out_free_syminfo;
- }
- }
-
- /*
- * Increase core size to make room for GOT and set start
- * offset for GOT.
- */
- module->core_layout.size = ALIGN(module->core_layout.size, 4);
- module->arch.got_offset = module->core_layout.size;
- module->core_layout.size += module->arch.got_size;
-
- return 0;
-
-out_free_syminfo:
- vfree(module->arch.syminfo);
- module->arch.syminfo = NULL;
-
- return ret;
-}
-
-static inline int reloc_overflow(struct module *module, const char *reloc_name,
- Elf32_Addr relocation)
-{
- printk(KERN_ERR "module %s: Value %lx does not fit relocation %s\n",
- module->name, (unsigned long)relocation, reloc_name);
- return -ENOEXEC;
-}
-
-#define get_u16(loc) (*((uint16_t *)loc))
-#define put_u16(loc, val) (*((uint16_t *)loc) = (val))
-
-int apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab,
- unsigned int symindex, unsigned int relindex,
- struct module *module)
-{
- Elf32_Shdr *symsec = sechdrs + symindex;
- Elf32_Shdr *relsec = sechdrs + relindex;
- Elf32_Shdr *dstsec = sechdrs + relsec->sh_info;
- Elf32_Rela *rel = (void *)relsec->sh_addr;
- unsigned int i;
- int ret = 0;
-
- for (i = 0; i < relsec->sh_size / sizeof(Elf32_Rela); i++, rel++) {
- struct mod_arch_syminfo *info;
- Elf32_Sym *sym;
- Elf32_Addr relocation;
- uint32_t *location;
- uint32_t value;
-
- location = (void *)dstsec->sh_addr + rel->r_offset;
- sym = (Elf32_Sym *)symsec->sh_addr + ELF32_R_SYM(rel->r_info);
- relocation = sym->st_value + rel->r_addend;
-
- info = module->arch.syminfo + ELF32_R_SYM(rel->r_info);
-
- /* Initialize GOT entry if necessary */
- switch (ELF32_R_TYPE(rel->r_info)) {
- case R_AVR32_GOT32:
- case R_AVR32_GOT16:
- case R_AVR32_GOT8:
- case R_AVR32_GOT21S:
- case R_AVR32_GOT18SW:
- case R_AVR32_GOT16S:
- if (!info->got_initialized) {
- Elf32_Addr *gotent;
-
- gotent = (module->core_layout.base
- + module->arch.got_offset
- + info->got_offset);
- *gotent = relocation;
- info->got_initialized = 1;
- }
-
- relocation = info->got_offset;
- break;
- }
-
- switch (ELF32_R_TYPE(rel->r_info)) {
- case R_AVR32_32:
- case R_AVR32_32_CPENT:
- *location = relocation;
- break;
- case R_AVR32_22H_PCREL:
- relocation -= (Elf32_Addr)location;
- if ((relocation & 0xffe00001) != 0
- && (relocation & 0xffc00001) != 0xffc00000)
- return reloc_overflow(module,
- "R_AVR32_22H_PCREL",
- relocation);
- relocation >>= 1;
-
- value = *location;
- value = ((value & 0xe1ef0000)
- | (relocation & 0xffff)
- | ((relocation & 0x10000) << 4)
- | ((relocation & 0x1e0000) << 8));
- *location = value;
- break;
- case R_AVR32_11H_PCREL:
- relocation -= (Elf32_Addr)location;
- if ((relocation & 0xfffffc01) != 0
- && (relocation & 0xfffff801) != 0xfffff800)
- return reloc_overflow(module,
- "R_AVR32_11H_PCREL",
- relocation);
- value = get_u16(location);
- value = ((value & 0xf00c)
- | ((relocation & 0x1fe) << 3)
- | ((relocation & 0x600) >> 9));
- put_u16(location, value);
- break;
- case R_AVR32_9H_PCREL:
- relocation -= (Elf32_Addr)location;
- if ((relocation & 0xffffff01) != 0
- && (relocation & 0xfffffe01) != 0xfffffe00)
- return reloc_overflow(module,
- "R_AVR32_9H_PCREL",
- relocation);
- value = get_u16(location);
- value = ((value & 0xf00f)
- | ((relocation & 0x1fe) << 3));
- put_u16(location, value);
- break;
- case R_AVR32_9UW_PCREL:
- relocation -= ((Elf32_Addr)location) & 0xfffffffc;
- if ((relocation & 0xfffffc03) != 0)
- return reloc_overflow(module,
- "R_AVR32_9UW_PCREL",
- relocation);
- value = get_u16(location);
- value = ((value & 0xf80f)
- | ((relocation & 0x1fc) << 2));
- put_u16(location, value);
- break;
- case R_AVR32_GOTPC:
- /*
- * R6 = PC - (PC - GOT)
- *
- * At this point, relocation contains the
- * value of PC. Just subtract the value of
- * GOT, and we're done.
- */
- pr_debug("GOTPC: PC=0x%x, got_offset=0x%lx, core=0x%p\n",
- relocation, module->arch.got_offset,
- module->core_layout.base);
- relocation -= ((unsigned long)module->core_layout.base
- + module->arch.got_offset);
- *location = relocation;
- break;
- case R_AVR32_GOT18SW:
- if ((relocation & 0xfffe0003) != 0
- && (relocation & 0xfffc0000) != 0xfffc0000)
- return reloc_overflow(module, "R_AVR32_GOT18SW",
- relocation);
- relocation >>= 2;
- /* fall through */
- case R_AVR32_GOT16S:
- if ((relocation & 0xffff8000) != 0
- && (relocation & 0xffff0000) != 0xffff0000)
- return reloc_overflow(module, "R_AVR32_GOT16S",
- relocation);
- pr_debug("GOT reloc @ 0x%x -> %u\n",
- rel->r_offset, relocation);
- value = *location;
- value = ((value & 0xffff0000)
- | (relocation & 0xffff));
- *location = value;
- break;
-
- default:
- printk(KERN_ERR "module %s: Unknown relocation: %u\n",
- module->name, ELF32_R_TYPE(rel->r_info));
- return -ENOEXEC;
- }
- }
-
- return ret;
-}
+++ /dev/null
-/*
- * Copyright (C) 2007 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/delay.h>
-#include <linux/kdebug.h>
-#include <linux/notifier.h>
-#include <linux/sched.h>
-#include <linux/sched/debug.h>
-
-#include <asm/irq.h>
-
-enum nmi_action {
- NMI_SHOW_STATE = 1 << 0,
- NMI_SHOW_REGS = 1 << 1,
- NMI_DIE = 1 << 2,
- NMI_DEBOUNCE = 1 << 3,
-};
-
-static unsigned long nmi_actions;
-
-static int nmi_debug_notify(struct notifier_block *self,
- unsigned long val, void *data)
-{
- struct die_args *args = data;
-
- if (likely(val != DIE_NMI))
- return NOTIFY_DONE;
-
- if (nmi_actions & NMI_SHOW_STATE)
- show_state();
- if (nmi_actions & NMI_SHOW_REGS)
- show_regs(args->regs);
- if (nmi_actions & NMI_DEBOUNCE)
- mdelay(10);
- if (nmi_actions & NMI_DIE)
- return NOTIFY_BAD;
-
- return NOTIFY_OK;
-}
-
-static struct notifier_block nmi_debug_nb = {
- .notifier_call = nmi_debug_notify,
-};
-
-static int __init nmi_debug_setup(char *str)
-{
- char *p, *sep;
-
- register_die_notifier(&nmi_debug_nb);
- if (nmi_enable()) {
- printk(KERN_WARNING "Unable to enable NMI.\n");
- return 0;
- }
-
- if (*str != '=')
- return 0;
-
- for (p = str + 1; *p; p = sep + 1) {
- sep = strchr(p, ',');
- if (sep)
- *sep = 0;
- if (strcmp(p, "state") == 0)
- nmi_actions |= NMI_SHOW_STATE;
- else if (strcmp(p, "regs") == 0)
- nmi_actions |= NMI_SHOW_REGS;
- else if (strcmp(p, "debounce") == 0)
- nmi_actions |= NMI_DEBOUNCE;
- else if (strcmp(p, "die") == 0)
- nmi_actions |= NMI_DIE;
- else
- printk(KERN_WARNING "NMI: Unrecognized action `%s'\n",
- p);
- if (!sep)
- break;
- }
-
- return 0;
-}
-__setup("nmi_debug", nmi_debug_setup);
+++ /dev/null
-/*
- * Copyright (C) 2007 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/spinlock.h>
-
-#include <asm/ocd.h>
-
-static long ocd_count;
-static spinlock_t ocd_lock;
-
-/**
- * ocd_enable - enable on-chip debugging
- * @child: task to be debugged
- *
- * If @child is non-NULL, ocd_enable() first checks if debugging has
- * already been enabled for @child, and if it has, does nothing.
- *
- * If @child is NULL (e.g. when debugging the kernel), or debugging
- * has not already been enabled for it, ocd_enable() increments the
- * reference count and enables the debugging hardware.
- */
-void ocd_enable(struct task_struct *child)
-{
- u32 dc;
-
- if (child)
- pr_debug("ocd_enable: child=%s [%u]\n",
- child->comm, child->pid);
- else
- pr_debug("ocd_enable (no child)\n");
-
- if (!child || !test_and_set_tsk_thread_flag(child, TIF_DEBUG)) {
- spin_lock(&ocd_lock);
- ocd_count++;
- dc = ocd_read(DC);
- dc |= (1 << OCD_DC_MM_BIT) | (1 << OCD_DC_DBE_BIT);
- ocd_write(DC, dc);
- spin_unlock(&ocd_lock);
- }
-}
-
-/**
- * ocd_disable - disable on-chip debugging
- * @child: task that was being debugged, but isn't anymore
- *
- * If @child is non-NULL, ocd_disable() checks if debugging is enabled
- * for @child, and if it isn't, does nothing.
- *
- * If @child is NULL (e.g. when debugging the kernel), or debugging is
- * enabled, ocd_disable() decrements the reference count, and if it
- * reaches zero, disables the debugging hardware.
- */
-void ocd_disable(struct task_struct *child)
-{
- u32 dc;
-
- if (!child)
- pr_debug("ocd_disable (no child)\n");
- else if (test_tsk_thread_flag(child, TIF_DEBUG))
- pr_debug("ocd_disable: child=%s [%u]\n",
- child->comm, child->pid);
-
- if (!child || test_and_clear_tsk_thread_flag(child, TIF_DEBUG)) {
- spin_lock(&ocd_lock);
- ocd_count--;
-
- WARN_ON(ocd_count < 0);
-
- if (ocd_count <= 0) {
- dc = ocd_read(DC);
- dc &= ~((1 << OCD_DC_MM_BIT) | (1 << OCD_DC_DBE_BIT));
- ocd_write(DC, dc);
- }
- spin_unlock(&ocd_lock);
- }
-}
-
-#ifdef CONFIG_DEBUG_FS
-#include <linux/debugfs.h>
-#include <linux/module.h>
-
-static struct dentry *ocd_debugfs_root;
-static struct dentry *ocd_debugfs_DC;
-static struct dentry *ocd_debugfs_DS;
-static struct dentry *ocd_debugfs_count;
-
-static int ocd_DC_get(void *data, u64 *val)
-{
- *val = ocd_read(DC);
- return 0;
-}
-static int ocd_DC_set(void *data, u64 val)
-{
- ocd_write(DC, val);
- return 0;
-}
-DEFINE_SIMPLE_ATTRIBUTE(fops_DC, ocd_DC_get, ocd_DC_set, "0x%08llx\n");
-
-static int ocd_DS_get(void *data, u64 *val)
-{
- *val = ocd_read(DS);
- return 0;
-}
-DEFINE_SIMPLE_ATTRIBUTE(fops_DS, ocd_DS_get, NULL, "0x%08llx\n");
-
-static int ocd_count_get(void *data, u64 *val)
-{
- *val = ocd_count;
- return 0;
-}
-DEFINE_SIMPLE_ATTRIBUTE(fops_count, ocd_count_get, NULL, "%lld\n");
-
-static void ocd_debugfs_init(void)
-{
- struct dentry *root;
-
- root = debugfs_create_dir("ocd", NULL);
- if (IS_ERR(root) || !root)
- goto err_root;
- ocd_debugfs_root = root;
-
- ocd_debugfs_DC = debugfs_create_file("DC", S_IRUSR | S_IWUSR,
- root, NULL, &fops_DC);
- if (!ocd_debugfs_DC)
- goto err_DC;
-
- ocd_debugfs_DS = debugfs_create_file("DS", S_IRUSR, root,
- NULL, &fops_DS);
- if (!ocd_debugfs_DS)
- goto err_DS;
-
- ocd_debugfs_count = debugfs_create_file("count", S_IRUSR, root,
- NULL, &fops_count);
- if (!ocd_debugfs_count)
- goto err_count;
-
- return;
-
-err_count:
- debugfs_remove(ocd_debugfs_DS);
-err_DS:
- debugfs_remove(ocd_debugfs_DC);
-err_DC:
- debugfs_remove(ocd_debugfs_root);
-err_root:
- printk(KERN_WARNING "OCD: Failed to create debugfs entries\n");
-}
-#else
-static inline void ocd_debugfs_init(void)
-{
-
-}
-#endif
-
-static int __init ocd_init(void)
-{
- spin_lock_init(&ocd_lock);
- ocd_debugfs_init();
- return 0;
-}
-arch_initcall(ocd_init);
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/sched.h>
-#include <linux/sched/debug.h>
-#include <linux/sched/task.h>
-#include <linux/sched/task_stack.h>
-#include <linux/module.h>
-#include <linux/kallsyms.h>
-#include <linux/fs.h>
-#include <linux/pm.h>
-#include <linux/ptrace.h>
-#include <linux/slab.h>
-#include <linux/reboot.h>
-#include <linux/tick.h>
-#include <linux/uaccess.h>
-#include <linux/unistd.h>
-
-#include <asm/sysreg.h>
-#include <asm/ocd.h>
-#include <asm/syscalls.h>
-
-#include <mach/pm.h>
-
-void (*pm_power_off)(void);
-EXPORT_SYMBOL(pm_power_off);
-
-/*
- * This file handles the architecture-dependent parts of process handling..
- */
-
-void arch_cpu_idle(void)
-{
- cpu_enter_idle();
-}
-
-void machine_halt(void)
-{
- /*
- * Enter Stop mode. The 32 kHz oscillator will keep running so
- * the RTC will keep the time properly and the system will
- * boot quickly.
- */
- asm volatile("sleep 3\n\t"
- "sub pc, -2");
-}
-
-void machine_power_off(void)
-{
- if (pm_power_off)
- pm_power_off();
-}
-
-void machine_restart(char *cmd)
-{
- ocd_write(DC, (1 << OCD_DC_DBE_BIT));
- ocd_write(DC, (1 << OCD_DC_RES_BIT));
- while (1) ;
-}
-
-/*
- * Free current thread data structures etc
- */
-void exit_thread(struct task_struct *tsk)
-{
- ocd_disable(tsk);
-}
-
-void flush_thread(void)
-{
- /* nothing to do */
-}
-
-void release_thread(struct task_struct *dead_task)
-{
- /* do nothing */
-}
-
-static void dump_mem(const char *str, const char *log_lvl,
- unsigned long bottom, unsigned long top)
-{
- unsigned long p;
- int i;
-
- printk("%s%s(0x%08lx to 0x%08lx)\n", log_lvl, str, bottom, top);
-
- for (p = bottom & ~31; p < top; ) {
- printk("%s%04lx: ", log_lvl, p & 0xffff);
-
- for (i = 0; i < 8; i++, p += 4) {
- unsigned int val;
-
- if (p < bottom || p >= top)
- printk(" ");
- else {
- if (__get_user(val, (unsigned int __user *)p)) {
- printk("\n");
- goto out;
- }
- printk("%08x ", val);
- }
- }
- printk("\n");
- }
-
-out:
- return;
-}
-
-static inline int valid_stack_ptr(struct thread_info *tinfo, unsigned long p)
-{
- return (p > (unsigned long)tinfo)
- && (p < (unsigned long)tinfo + THREAD_SIZE - 3);
-}
-
-#ifdef CONFIG_FRAME_POINTER
-static void show_trace_log_lvl(struct task_struct *tsk, unsigned long *sp,
- struct pt_regs *regs, const char *log_lvl)
-{
- unsigned long lr, fp;
- struct thread_info *tinfo;
-
- if (regs)
- fp = regs->r7;
- else if (tsk == current)
- asm("mov %0, r7" : "=r"(fp));
- else
- fp = tsk->thread.cpu_context.r7;
-
- /*
- * Walk the stack as long as the frame pointer (a) is within
- * the kernel stack of the task, and (b) it doesn't move
- * downwards.
- */
- tinfo = task_thread_info(tsk);
- printk("%sCall trace:\n", log_lvl);
- while (valid_stack_ptr(tinfo, fp)) {
- unsigned long new_fp;
-
- lr = *(unsigned long *)fp;
-#ifdef CONFIG_KALLSYMS
- printk("%s [<%08lx>] ", log_lvl, lr);
-#else
- printk(" [<%08lx>] ", lr);
-#endif
- print_symbol("%s\n", lr);
-
- new_fp = *(unsigned long *)(fp + 4);
- if (new_fp <= fp)
- break;
- fp = new_fp;
- }
- printk("\n");
-}
-#else
-static void show_trace_log_lvl(struct task_struct *tsk, unsigned long *sp,
- struct pt_regs *regs, const char *log_lvl)
-{
- unsigned long addr;
-
- printk("%sCall trace:\n", log_lvl);
-
- while (!kstack_end(sp)) {
- addr = *sp++;
- if (kernel_text_address(addr)) {
-#ifdef CONFIG_KALLSYMS
- printk("%s [<%08lx>] ", log_lvl, addr);
-#else
- printk(" [<%08lx>] ", addr);
-#endif
- print_symbol("%s\n", addr);
- }
- }
- printk("\n");
-}
-#endif
-
-void show_stack_log_lvl(struct task_struct *tsk, unsigned long sp,
- struct pt_regs *regs, const char *log_lvl)
-{
- struct thread_info *tinfo;
-
- if (sp == 0) {
- if (tsk)
- sp = tsk->thread.cpu_context.ksp;
- else
- sp = (unsigned long)&tinfo;
- }
- if (!tsk)
- tsk = current;
-
- tinfo = task_thread_info(tsk);
-
- if (valid_stack_ptr(tinfo, sp)) {
- dump_mem("Stack: ", log_lvl, sp,
- THREAD_SIZE + (unsigned long)tinfo);
- show_trace_log_lvl(tsk, (unsigned long *)sp, regs, log_lvl);
- }
-}
-
-void show_stack(struct task_struct *tsk, unsigned long *stack)
-{
- show_stack_log_lvl(tsk, (unsigned long)stack, NULL, "");
-}
-
-static const char *cpu_modes[] = {
- "Application", "Supervisor", "Interrupt level 0", "Interrupt level 1",
- "Interrupt level 2", "Interrupt level 3", "Exception", "NMI"
-};
-
-void show_regs_log_lvl(struct pt_regs *regs, const char *log_lvl)
-{
- unsigned long sp = regs->sp;
- unsigned long lr = regs->lr;
- unsigned long mode = (regs->sr & MODE_MASK) >> MODE_SHIFT;
-
- show_regs_print_info(log_lvl);
-
- if (!user_mode(regs)) {
- sp = (unsigned long)regs + FRAME_SIZE_FULL;
-
- printk("%s", log_lvl);
- print_symbol("PC is at %s\n", instruction_pointer(regs));
- printk("%s", log_lvl);
- print_symbol("LR is at %s\n", lr);
- }
-
- printk("%spc : [<%08lx>] lr : [<%08lx>] %s\n"
- "%ssp : %08lx r12: %08lx r11: %08lx\n",
- log_lvl, instruction_pointer(regs), lr, print_tainted(),
- log_lvl, sp, regs->r12, regs->r11);
- printk("%sr10: %08lx r9 : %08lx r8 : %08lx\n",
- log_lvl, regs->r10, regs->r9, regs->r8);
- printk("%sr7 : %08lx r6 : %08lx r5 : %08lx r4 : %08lx\n",
- log_lvl, regs->r7, regs->r6, regs->r5, regs->r4);
- printk("%sr3 : %08lx r2 : %08lx r1 : %08lx r0 : %08lx\n",
- log_lvl, regs->r3, regs->r2, regs->r1, regs->r0);
- printk("%sFlags: %c%c%c%c%c\n", log_lvl,
- regs->sr & SR_Q ? 'Q' : 'q',
- regs->sr & SR_V ? 'V' : 'v',
- regs->sr & SR_N ? 'N' : 'n',
- regs->sr & SR_Z ? 'Z' : 'z',
- regs->sr & SR_C ? 'C' : 'c');
- printk("%sMode bits: %c%c%c%c%c%c%c%c%c%c\n", log_lvl,
- regs->sr & SR_H ? 'H' : 'h',
- regs->sr & SR_J ? 'J' : 'j',
- regs->sr & SR_DM ? 'M' : 'm',
- regs->sr & SR_D ? 'D' : 'd',
- regs->sr & SR_EM ? 'E' : 'e',
- regs->sr & SR_I3M ? '3' : '.',
- regs->sr & SR_I2M ? '2' : '.',
- regs->sr & SR_I1M ? '1' : '.',
- regs->sr & SR_I0M ? '0' : '.',
- regs->sr & SR_GM ? 'G' : 'g');
- printk("%sCPU Mode: %s\n", log_lvl, cpu_modes[mode]);
-}
-
-void show_regs(struct pt_regs *regs)
-{
- unsigned long sp = regs->sp;
-
- if (!user_mode(regs))
- sp = (unsigned long)regs + FRAME_SIZE_FULL;
-
- show_regs_log_lvl(regs, "");
- show_trace_log_lvl(current, (unsigned long *)sp, regs, "");
-}
-EXPORT_SYMBOL(show_regs);
-
-/* Fill in the fpu structure for a core dump. This is easy -- we don't have any */
-int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu)
-{
- /* Not valid */
- return 0;
-}
-
-asmlinkage void ret_from_fork(void);
-asmlinkage void ret_from_kernel_thread(void);
-asmlinkage void syscall_return(void);
-
-int copy_thread(unsigned long clone_flags, unsigned long usp,
- unsigned long arg,
- struct task_struct *p)
-{
- struct pt_regs *childregs = task_pt_regs(p);
-
- if (unlikely(p->flags & PF_KTHREAD)) {
- memset(childregs, 0, sizeof(struct pt_regs));
- p->thread.cpu_context.r0 = arg;
- p->thread.cpu_context.r1 = usp; /* fn */
- p->thread.cpu_context.r2 = (unsigned long)syscall_return;
- p->thread.cpu_context.pc = (unsigned long)ret_from_kernel_thread;
- childregs->sr = MODE_SUPERVISOR;
- } else {
- *childregs = *current_pt_regs();
- if (usp)
- childregs->sp = usp;
- childregs->r12 = 0; /* Set return value for child */
- p->thread.cpu_context.pc = (unsigned long)ret_from_fork;
- }
-
- p->thread.cpu_context.sr = MODE_SUPERVISOR | SR_GM;
- p->thread.cpu_context.ksp = (unsigned long)childregs;
-
- clear_tsk_thread_flag(p, TIF_DEBUG);
- if ((clone_flags & CLONE_PTRACE) && test_thread_flag(TIF_DEBUG))
- ocd_enable(p);
-
- return 0;
-}
-
-/*
- * This function is supposed to answer the question "who called
- * schedule()?"
- */
-unsigned long get_wchan(struct task_struct *p)
-{
- unsigned long pc;
- unsigned long stack_page;
-
- if (!p || p == current || p->state == TASK_RUNNING)
- return 0;
-
- stack_page = (unsigned long)task_stack_page(p);
- BUG_ON(!stack_page);
-
- /*
- * The stored value of PC is either the address right after
- * the call to __switch_to() or ret_from_fork.
- */
- pc = thread_saved_pc(p);
- if (in_sched_functions(pc)) {
-#ifdef CONFIG_FRAME_POINTER
- unsigned long fp = p->thread.cpu_context.r7;
- BUG_ON(fp < stack_page || fp > (THREAD_SIZE + stack_page));
- pc = *(unsigned long *)fp;
-#else
- /*
- * We depend on the frame size of schedule here, which
- * is actually quite ugly. It might be possible to
- * determine the frame size automatically at build
- * time by doing this:
- * - compile sched/core.c
- * - disassemble the resulting sched.o
- * - look for 'sub sp,??' shortly after '<schedule>:'
- */
- unsigned long sp = p->thread.cpu_context.ksp + 16;
- BUG_ON(sp < stack_page || sp > (THREAD_SIZE + stack_page));
- pc = *(unsigned long *)sp;
-#endif
- }
-
- return pc;
-}
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#undef DEBUG
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/sched/task_stack.h>
-#include <linux/mm.h>
-#include <linux/ptrace.h>
-#include <linux/errno.h>
-#include <linux/user.h>
-#include <linux/security.h>
-#include <linux/unistd.h>
-#include <linux/notifier.h>
-
-#include <asm/traps.h>
-#include <linux/uaccess.h>
-#include <asm/ocd.h>
-#include <asm/mmu_context.h>
-#include <linux/kdebug.h>
-
-static struct pt_regs *get_user_regs(struct task_struct *tsk)
-{
- return (struct pt_regs *)((unsigned long)task_stack_page(tsk) +
- THREAD_SIZE - sizeof(struct pt_regs));
-}
-
-void user_enable_single_step(struct task_struct *tsk)
-{
- pr_debug("user_enable_single_step: pid=%u, PC=0x%08lx, SR=0x%08lx\n",
- tsk->pid, task_pt_regs(tsk)->pc, task_pt_regs(tsk)->sr);
-
- /*
- * We can't schedule in Debug mode, so when TIF_BREAKPOINT is
- * set, the system call or exception handler will do a
- * breakpoint to enter monitor mode before returning to
- * userspace.
- *
- * The monitor code will then notice that TIF_SINGLE_STEP is
- * set and return to userspace with single stepping enabled.
- * The CPU will then enter monitor mode again after exactly
- * one instruction has been executed, and the monitor code
- * will then send a SIGTRAP to the process.
- */
- set_tsk_thread_flag(tsk, TIF_BREAKPOINT);
- set_tsk_thread_flag(tsk, TIF_SINGLE_STEP);
-}
-
-void user_disable_single_step(struct task_struct *child)
-{
- /* XXX(hch): a no-op here seems wrong.. */
-}
-
-/*
- * Called by kernel/ptrace.c when detaching
- *
- * Make sure any single step bits, etc. are not set
- */
-void ptrace_disable(struct task_struct *child)
-{
- clear_tsk_thread_flag(child, TIF_SINGLE_STEP);
- clear_tsk_thread_flag(child, TIF_BREAKPOINT);
- ocd_disable(child);
-}
-
-/*
- * Read the word at offset "offset" into the task's "struct user". We
- * actually access the pt_regs struct stored on the kernel stack.
- */
-static int ptrace_read_user(struct task_struct *tsk, unsigned long offset,
- unsigned long __user *data)
-{
- unsigned long *regs;
- unsigned long value;
-
- if (offset & 3 || offset >= sizeof(struct user)) {
- printk("ptrace_read_user: invalid offset 0x%08lx\n", offset);
- return -EIO;
- }
-
- regs = (unsigned long *)get_user_regs(tsk);
-
- value = 0;
- if (offset < sizeof(struct pt_regs))
- value = regs[offset / sizeof(regs[0])];
-
- pr_debug("ptrace_read_user(%s[%u], %#lx, %p) -> %#lx\n",
- tsk->comm, tsk->pid, offset, data, value);
-
- return put_user(value, data);
-}
-
-/*
- * Write the word "value" to offset "offset" into the task's "struct
- * user". We actually access the pt_regs struct stored on the kernel
- * stack.
- */
-static int ptrace_write_user(struct task_struct *tsk, unsigned long offset,
- unsigned long value)
-{
- unsigned long *regs;
-
- pr_debug("ptrace_write_user(%s[%u], %#lx, %#lx)\n",
- tsk->comm, tsk->pid, offset, value);
-
- if (offset & 3 || offset >= sizeof(struct user)) {
- pr_debug(" invalid offset 0x%08lx\n", offset);
- return -EIO;
- }
-
- if (offset >= sizeof(struct pt_regs))
- return 0;
-
- regs = (unsigned long *)get_user_regs(tsk);
- regs[offset / sizeof(regs[0])] = value;
-
- return 0;
-}
-
-static int ptrace_getregs(struct task_struct *tsk, void __user *uregs)
-{
- struct pt_regs *regs = get_user_regs(tsk);
-
- return copy_to_user(uregs, regs, sizeof(*regs)) ? -EFAULT : 0;
-}
-
-static int ptrace_setregs(struct task_struct *tsk, const void __user *uregs)
-{
- struct pt_regs newregs;
- int ret;
-
- ret = -EFAULT;
- if (copy_from_user(&newregs, uregs, sizeof(newregs)) == 0) {
- struct pt_regs *regs = get_user_regs(tsk);
-
- ret = -EINVAL;
- if (valid_user_regs(&newregs)) {
- *regs = newregs;
- ret = 0;
- }
- }
-
- return ret;
-}
-
-long arch_ptrace(struct task_struct *child, long request,
- unsigned long addr, unsigned long data)
-{
- int ret;
- void __user *datap = (void __user *) data;
-
- switch (request) {
- /* Read the word at location addr in the child process */
- case PTRACE_PEEKTEXT:
- case PTRACE_PEEKDATA:
- ret = generic_ptrace_peekdata(child, addr, data);
- break;
-
- case PTRACE_PEEKUSR:
- ret = ptrace_read_user(child, addr, datap);
- break;
-
- /* Write the word in data at location addr */
- case PTRACE_POKETEXT:
- case PTRACE_POKEDATA:
- ret = generic_ptrace_pokedata(child, addr, data);
- break;
-
- case PTRACE_POKEUSR:
- ret = ptrace_write_user(child, addr, data);
- break;
-
- case PTRACE_GETREGS:
- ret = ptrace_getregs(child, datap);
- break;
-
- case PTRACE_SETREGS:
- ret = ptrace_setregs(child, datap);
- break;
-
- default:
- ret = ptrace_request(child, request, addr, data);
- break;
- }
-
- return ret;
-}
-
-asmlinkage void syscall_trace(void)
-{
- if (!test_thread_flag(TIF_SYSCALL_TRACE))
- return;
- if (!(current->ptrace & PT_PTRACED))
- return;
-
- /* The 0x80 provides a way for the tracing parent to
- * distinguish between a syscall stop and SIGTRAP delivery */
- ptrace_notify(SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
- ? 0x80 : 0));
-
- /*
- * this isn't the same as continuing with a signal, but it
- * will do for normal use. strace only continues with a
- * signal if the stopping signal is not SIGTRAP. -brl
- */
- if (current->exit_code) {
- pr_debug("syscall_trace: sending signal %d to PID %u\n",
- current->exit_code, current->pid);
- send_sig(current->exit_code, current, 1);
- current->exit_code = 0;
- }
-}
-
-/*
- * debug_trampoline() is an assembly stub which will store all user
- * registers on the stack and execute a breakpoint instruction.
- *
- * If we single-step into an exception handler which runs with
- * interrupts disabled the whole time so it doesn't have to check for
- * pending work, its return address will be modified so that it ends
- * up returning to debug_trampoline.
- *
- * If the exception handler decides to store the user context and
- * enable interrupts after all, it will restore the original return
- * address and status register value. Before it returns, it will
- * notice that TIF_BREAKPOINT is set and execute a breakpoint
- * instruction.
- */
-extern void debug_trampoline(void);
-
-asmlinkage struct pt_regs *do_debug(struct pt_regs *regs)
-{
- struct thread_info *ti;
- unsigned long trampoline_addr;
- u32 status;
- u32 ctrl;
- int code;
-
- status = ocd_read(DS);
- ti = current_thread_info();
- code = TRAP_BRKPT;
-
- pr_debug("do_debug: status=0x%08x PC=0x%08lx SR=0x%08lx tif=0x%08lx\n",
- status, regs->pc, regs->sr, ti->flags);
-
- if (!user_mode(regs)) {
- unsigned long die_val = DIE_BREAKPOINT;
-
- if (status & (1 << OCD_DS_SSS_BIT))
- die_val = DIE_SSTEP;
-
- if (notify_die(die_val, "ptrace", regs, 0, 0, SIGTRAP)
- == NOTIFY_STOP)
- return regs;
-
- if ((status & (1 << OCD_DS_SWB_BIT))
- && test_and_clear_ti_thread_flag(
- ti, TIF_BREAKPOINT)) {
- /*
- * Explicit breakpoint from trampoline or
- * exception/syscall/interrupt handler.
- *
- * The real saved regs are on the stack right
- * after the ones we saved on entry.
- */
- regs++;
- pr_debug(" -> TIF_BREAKPOINT done, adjusted regs:"
- "PC=0x%08lx SR=0x%08lx\n",
- regs->pc, regs->sr);
- BUG_ON(!user_mode(regs));
-
- if (test_thread_flag(TIF_SINGLE_STEP)) {
- pr_debug("Going to do single step...\n");
- return regs;
- }
-
- /*
- * No TIF_SINGLE_STEP means we're done
- * stepping over a syscall. Do the trap now.
- */
- code = TRAP_TRACE;
- } else if ((status & (1 << OCD_DS_SSS_BIT))
- && test_ti_thread_flag(ti, TIF_SINGLE_STEP)) {
-
- pr_debug("Stepped into something, "
- "setting TIF_BREAKPOINT...\n");
- set_ti_thread_flag(ti, TIF_BREAKPOINT);
-
- /*
- * We stepped into an exception, interrupt or
- * syscall handler. Some exception handlers
- * don't check for pending work, so we need to
- * set up a trampoline just in case.
- *
- * The exception entry code will undo the
- * trampoline stuff if it does a full context
- * save (which also means that it'll check for
- * pending work later.)
- */
- if ((regs->sr & MODE_MASK) == MODE_EXCEPTION) {
- trampoline_addr
- = (unsigned long)&debug_trampoline;
-
- pr_debug("Setting up trampoline...\n");
- ti->rar_saved = sysreg_read(RAR_EX);
- ti->rsr_saved = sysreg_read(RSR_EX);
- sysreg_write(RAR_EX, trampoline_addr);
- sysreg_write(RSR_EX, (MODE_EXCEPTION
- | SR_EM | SR_GM));
- BUG_ON(ti->rsr_saved & MODE_MASK);
- }
-
- /*
- * If we stepped into a system call, we
- * shouldn't do a single step after we return
- * since the return address is right after the
- * "scall" instruction we were told to step
- * over.
- */
- if ((regs->sr & MODE_MASK) == MODE_SUPERVISOR) {
- pr_debug("Supervisor; no single step\n");
- clear_ti_thread_flag(ti, TIF_SINGLE_STEP);
- }
-
- ctrl = ocd_read(DC);
- ctrl &= ~(1 << OCD_DC_SS_BIT);
- ocd_write(DC, ctrl);
-
- return regs;
- } else {
- printk(KERN_ERR "Unexpected OCD_DS value: 0x%08x\n",
- status);
- printk(KERN_ERR "Thread flags: 0x%08lx\n", ti->flags);
- die("Unhandled debug trap in kernel mode",
- regs, SIGTRAP);
- }
- } else if (status & (1 << OCD_DS_SSS_BIT)) {
- /* Single step in user mode */
- code = TRAP_TRACE;
-
- ctrl = ocd_read(DC);
- ctrl &= ~(1 << OCD_DC_SS_BIT);
- ocd_write(DC, ctrl);
- }
-
- pr_debug("Sending SIGTRAP: code=%d PC=0x%08lx SR=0x%08lx\n",
- code, regs->pc, regs->sr);
-
- clear_thread_flag(TIF_SINGLE_STEP);
- _exception(SIGTRAP, regs, code, instruction_pointer(regs));
-
- return regs;
-}
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/clk.h>
-#include <linux/init.h>
-#include <linux/initrd.h>
-#include <linux/sched.h>
-#include <linux/console.h>
-#include <linux/ioport.h>
-#include <linux/bootmem.h>
-#include <linux/fs.h>
-#include <linux/module.h>
-#include <linux/pfn.h>
-#include <linux/root_dev.h>
-#include <linux/cpu.h>
-#include <linux/kernel.h>
-
-#include <asm/sections.h>
-#include <asm/processor.h>
-#include <asm/pgtable.h>
-#include <asm/setup.h>
-#include <asm/sysreg.h>
-
-#include <mach/board.h>
-#include <mach/init.h>
-
-extern int root_mountflags;
-
-/*
- * Initialize loops_per_jiffy as 5000000 (500MIPS).
- * Better make it too large than too small...
- */
-struct avr32_cpuinfo boot_cpu_data = {
- .loops_per_jiffy = 5000000
-};
-EXPORT_SYMBOL(boot_cpu_data);
-
-static char __initdata command_line[COMMAND_LINE_SIZE];
-
-/*
- * Standard memory resources
- */
-static struct resource __initdata kernel_data = {
- .name = "Kernel data",
- .start = 0,
- .end = 0,
- .flags = IORESOURCE_SYSTEM_RAM,
-};
-static struct resource __initdata kernel_code = {
- .name = "Kernel code",
- .start = 0,
- .end = 0,
- .flags = IORESOURCE_SYSTEM_RAM,
- .sibling = &kernel_data,
-};
-
-/*
- * Available system RAM and reserved regions as singly linked
- * lists. These lists are traversed using the sibling pointer in
- * struct resource and are kept sorted at all times.
- */
-static struct resource *__initdata system_ram;
-static struct resource *__initdata reserved = &kernel_code;
-
-/*
- * We need to allocate these before the bootmem allocator is up and
- * running, so we need this "cache". 32 entries are probably enough
- * for all but the most insanely complex systems.
- */
-static struct resource __initdata res_cache[32];
-static unsigned int __initdata res_cache_next_free;
-
-static void __init resource_init(void)
-{
- struct resource *mem, *res;
- struct resource *new;
-
- kernel_code.start = __pa(init_mm.start_code);
-
- for (mem = system_ram; mem; mem = mem->sibling) {
- new = alloc_bootmem_low(sizeof(struct resource));
- memcpy(new, mem, sizeof(struct resource));
-
- new->sibling = NULL;
- if (request_resource(&iomem_resource, new))
- printk(KERN_WARNING "Bad RAM resource %08x-%08x\n",
- mem->start, mem->end);
- }
-
- for (res = reserved; res; res = res->sibling) {
- new = alloc_bootmem_low(sizeof(struct resource));
- memcpy(new, res, sizeof(struct resource));
-
- new->sibling = NULL;
- if (insert_resource(&iomem_resource, new))
- printk(KERN_WARNING
- "Bad reserved resource %s (%08x-%08x)\n",
- res->name, res->start, res->end);
- }
-}
-
-static void __init
-add_physical_memory(resource_size_t start, resource_size_t end)
-{
- struct resource *new, *next, **pprev;
-
- for (pprev = &system_ram, next = system_ram; next;
- pprev = &next->sibling, next = next->sibling) {
- if (end < next->start)
- break;
- if (start <= next->end) {
- printk(KERN_WARNING
- "Warning: Physical memory map is broken\n");
- printk(KERN_WARNING
- "Warning: %08x-%08x overlaps %08x-%08x\n",
- start, end, next->start, next->end);
- return;
- }
- }
-
- if (res_cache_next_free >= ARRAY_SIZE(res_cache)) {
- printk(KERN_WARNING
- "Warning: Failed to add physical memory %08x-%08x\n",
- start, end);
- return;
- }
-
- new = &res_cache[res_cache_next_free++];
- new->start = start;
- new->end = end;
- new->name = "System RAM";
- new->flags = IORESOURCE_SYSTEM_RAM;
-
- *pprev = new;
-}
-
-static int __init
-add_reserved_region(resource_size_t start, resource_size_t end,
- const char *name)
-{
- struct resource *new, *next, **pprev;
-
- if (end < start)
- return -EINVAL;
-
- if (res_cache_next_free >= ARRAY_SIZE(res_cache))
- return -ENOMEM;
-
- for (pprev = &reserved, next = reserved; next;
- pprev = &next->sibling, next = next->sibling) {
- if (end < next->start)
- break;
- if (start <= next->end)
- return -EBUSY;
- }
-
- new = &res_cache[res_cache_next_free++];
- new->start = start;
- new->end = end;
- new->name = name;
- new->sibling = next;
- new->flags = IORESOURCE_MEM;
-
- *pprev = new;
-
- return 0;
-}
-
-static unsigned long __init
-find_free_region(const struct resource *mem, resource_size_t size,
- resource_size_t align)
-{
- struct resource *res;
- unsigned long target;
-
- target = ALIGN(mem->start, align);
- for (res = reserved; res; res = res->sibling) {
- if ((target + size) <= res->start)
- break;
- if (target <= res->end)
- target = ALIGN(res->end + 1, align);
- }
-
- if ((target + size) > (mem->end + 1))
- return mem->end + 1;
-
- return target;
-}
-
-static int __init
-alloc_reserved_region(resource_size_t *start, resource_size_t size,
- resource_size_t align, const char *name)
-{
- struct resource *mem;
- resource_size_t target;
- int ret;
-
- for (mem = system_ram; mem; mem = mem->sibling) {
- target = find_free_region(mem, size, align);
- if (target <= mem->end) {
- ret = add_reserved_region(target, target + size - 1,
- name);
- if (!ret)
- *start = target;
- return ret;
- }
- }
-
- return -ENOMEM;
-}
-
-/*
- * Early framebuffer allocation. Works as follows:
- * - If fbmem_size is zero, nothing will be allocated or reserved.
- * - If fbmem_start is zero when setup_bootmem() is called,
- * a block of fbmem_size bytes will be reserved before bootmem
- * initialization. It will be aligned to the largest page size
- * that fbmem_size is a multiple of.
- * - If fbmem_start is nonzero, an area of size fbmem_size will be
- * reserved at the physical address fbmem_start if possible. If
- * it collides with other reserved memory, a different block of
- * same size will be allocated, just as if fbmem_start was zero.
- *
- * Board-specific code may use these variables to set up platform data
- * for the framebuffer driver if fbmem_size is nonzero.
- */
-resource_size_t __initdata fbmem_start;
-resource_size_t __initdata fbmem_size;
-
-/*
- * "fbmem=xxx[kKmM]" allocates the specified amount of boot memory for
- * use as framebuffer.
- *
- * "fbmem=xxx[kKmM]@yyy[kKmM]" defines a memory region of size xxx and
- * starting at yyy to be reserved for use as framebuffer.
- *
- * The kernel won't verify that the memory region starting at yyy
- * actually contains usable RAM.
- */
-static int __init early_parse_fbmem(char *p)
-{
- int ret;
- unsigned long align;
-
- fbmem_size = memparse(p, &p);
- if (*p == '@') {
- fbmem_start = memparse(p + 1, &p);
- ret = add_reserved_region(fbmem_start,
- fbmem_start + fbmem_size - 1,
- "Framebuffer");
- if (ret) {
- printk(KERN_WARNING
- "Failed to reserve framebuffer memory\n");
- fbmem_start = 0;
- }
- }
-
- if (!fbmem_start) {
- if ((fbmem_size & 0x000fffffUL) == 0)
- align = 0x100000; /* 1 MiB */
- else if ((fbmem_size & 0x0000ffffUL) == 0)
- align = 0x10000; /* 64 KiB */
- else
- align = 0x1000; /* 4 KiB */
-
- ret = alloc_reserved_region(&fbmem_start, fbmem_size,
- align, "Framebuffer");
- if (ret) {
- printk(KERN_WARNING
- "Failed to allocate framebuffer memory\n");
- fbmem_size = 0;
- } else {
- memset(__va(fbmem_start), 0, fbmem_size);
- }
- }
-
- return 0;
-}
-early_param("fbmem", early_parse_fbmem);
-
-/*
- * Pick out the memory size. We look for mem=size@start,
- * where start and size are "size[KkMmGg]"
- */
-static int __init early_mem(char *p)
-{
- resource_size_t size, start;
-
- start = system_ram->start;
- size = memparse(p, &p);
- if (*p == '@')
- start = memparse(p + 1, &p);
-
- system_ram->start = start;
- system_ram->end = system_ram->start + size - 1;
- return 0;
-}
-early_param("mem", early_mem);
-
-static int __init parse_tag_core(struct tag *tag)
-{
- if (tag->hdr.size > 2) {
- if ((tag->u.core.flags & 1) == 0)
- root_mountflags &= ~MS_RDONLY;
- ROOT_DEV = new_decode_dev(tag->u.core.rootdev);
- }
- return 0;
-}
-__tagtable(ATAG_CORE, parse_tag_core);
-
-static int __init parse_tag_mem(struct tag *tag)
-{
- unsigned long start, end;
-
- /*
- * Ignore zero-sized entries. If we're running standalone, the
- * SDRAM code may emit such entries if something goes
- * wrong...
- */
- if (tag->u.mem_range.size == 0)
- return 0;
-
- start = tag->u.mem_range.addr;
- end = tag->u.mem_range.addr + tag->u.mem_range.size - 1;
-
- add_physical_memory(start, end);
- return 0;
-}
-__tagtable(ATAG_MEM, parse_tag_mem);
-
-static int __init parse_tag_rdimg(struct tag *tag)
-{
-#ifdef CONFIG_BLK_DEV_INITRD
- struct tag_mem_range *mem = &tag->u.mem_range;
- int ret;
-
- if (initrd_start) {
- printk(KERN_WARNING
- "Warning: Only the first initrd image will be used\n");
- return 0;
- }
-
- ret = add_reserved_region(mem->addr, mem->addr + mem->size - 1,
- "initrd");
- if (ret) {
- printk(KERN_WARNING
- "Warning: Failed to reserve initrd memory\n");
- return ret;
- }
-
- initrd_start = (unsigned long)__va(mem->addr);
- initrd_end = initrd_start + mem->size;
-#else
- printk(KERN_WARNING "RAM disk image present, but "
- "no initrd support in kernel, ignoring\n");
-#endif
-
- return 0;
-}
-__tagtable(ATAG_RDIMG, parse_tag_rdimg);
-
-static int __init parse_tag_rsvd_mem(struct tag *tag)
-{
- struct tag_mem_range *mem = &tag->u.mem_range;
-
- return add_reserved_region(mem->addr, mem->addr + mem->size - 1,
- "Reserved");
-}
-__tagtable(ATAG_RSVD_MEM, parse_tag_rsvd_mem);
-
-static int __init parse_tag_cmdline(struct tag *tag)
-{
- strlcpy(boot_command_line, tag->u.cmdline.cmdline, COMMAND_LINE_SIZE);
- return 0;
-}
-__tagtable(ATAG_CMDLINE, parse_tag_cmdline);
-
-static int __init parse_tag_clock(struct tag *tag)
-{
- /*
- * We'll figure out the clocks by peeking at the system
- * manager regs directly.
- */
- return 0;
-}
-__tagtable(ATAG_CLOCK, parse_tag_clock);
-
-/*
- * The board_number correspond to the bd->bi_board_number in U-Boot. This
- * parameter is only available during initialisation and can be used in some
- * kind of board identification.
- */
-u32 __initdata board_number;
-
-static int __init parse_tag_boardinfo(struct tag *tag)
-{
- board_number = tag->u.boardinfo.board_number;
-
- return 0;
-}
-__tagtable(ATAG_BOARDINFO, parse_tag_boardinfo);
-
-/*
- * Scan the tag table for this tag, and call its parse function. The
- * tag table is built by the linker from all the __tagtable
- * declarations.
- */
-static int __init parse_tag(struct tag *tag)
-{
- extern struct tagtable __tagtable_begin, __tagtable_end;
- struct tagtable *t;
-
- for (t = &__tagtable_begin; t < &__tagtable_end; t++)
- if (tag->hdr.tag == t->tag) {
- t->parse(tag);
- break;
- }
-
- return t < &__tagtable_end;
-}
-
-/*
- * Parse all tags in the list we got from the boot loader
- */
-static void __init parse_tags(struct tag *t)
-{
- for (; t->hdr.tag != ATAG_NONE; t = tag_next(t))
- if (!parse_tag(t))
- printk(KERN_WARNING
- "Ignoring unrecognised tag 0x%08x\n",
- t->hdr.tag);
-}
-
-/*
- * Find a free memory region large enough for storing the
- * bootmem bitmap.
- */
-static unsigned long __init
-find_bootmap_pfn(const struct resource *mem)
-{
- unsigned long bootmap_pages, bootmap_len;
- unsigned long node_pages = PFN_UP(resource_size(mem));
- unsigned long bootmap_start;
-
- bootmap_pages = bootmem_bootmap_pages(node_pages);
- bootmap_len = bootmap_pages << PAGE_SHIFT;
-
- /*
- * Find a large enough region without reserved pages for
- * storing the bootmem bitmap. We can take advantage of the
- * fact that all lists have been sorted.
- *
- * We have to check that we don't collide with any reserved
- * regions, which includes the kernel image and any RAMDISK
- * images.
- */
- bootmap_start = find_free_region(mem, bootmap_len, PAGE_SIZE);
-
- return bootmap_start >> PAGE_SHIFT;
-}
-
-#define MAX_LOWMEM HIGHMEM_START
-#define MAX_LOWMEM_PFN PFN_DOWN(MAX_LOWMEM)
-
-static void __init setup_bootmem(void)
-{
- unsigned bootmap_size;
- unsigned long first_pfn, bootmap_pfn, pages;
- unsigned long max_pfn, max_low_pfn;
- unsigned node = 0;
- struct resource *res;
-
- printk(KERN_INFO "Physical memory:\n");
- for (res = system_ram; res; res = res->sibling)
- printk(" %08x-%08x\n", res->start, res->end);
- printk(KERN_INFO "Reserved memory:\n");
- for (res = reserved; res; res = res->sibling)
- printk(" %08x-%08x: %s\n",
- res->start, res->end, res->name);
-
- nodes_clear(node_online_map);
-
- if (system_ram->sibling)
- printk(KERN_WARNING "Only using first memory bank\n");
-
- for (res = system_ram; res; res = NULL) {
- first_pfn = PFN_UP(res->start);
- max_low_pfn = max_pfn = PFN_DOWN(res->end + 1);
- bootmap_pfn = find_bootmap_pfn(res);
- if (bootmap_pfn > max_pfn)
- panic("No space for bootmem bitmap!\n");
-
- if (max_low_pfn > MAX_LOWMEM_PFN) {
- max_low_pfn = MAX_LOWMEM_PFN;
-#ifndef CONFIG_HIGHMEM
- /*
- * Lowmem is memory that can be addressed
- * directly through P1/P2
- */
- printk(KERN_WARNING
- "Node %u: Only %ld MiB of memory will be used.\n",
- node, MAX_LOWMEM >> 20);
- printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
-#else
-#error HIGHMEM is not supported by AVR32 yet
-#endif
- }
-
- /* Initialize the boot-time allocator with low memory only. */
- bootmap_size = init_bootmem_node(NODE_DATA(node), bootmap_pfn,
- first_pfn, max_low_pfn);
-
- /*
- * Register fully available RAM pages with the bootmem
- * allocator.
- */
- pages = max_low_pfn - first_pfn;
- free_bootmem_node (NODE_DATA(node), PFN_PHYS(first_pfn),
- PFN_PHYS(pages));
-
- /* Reserve space for the bootmem bitmap... */
- reserve_bootmem_node(NODE_DATA(node),
- PFN_PHYS(bootmap_pfn),
- bootmap_size,
- BOOTMEM_DEFAULT);
-
- /* ...and any other reserved regions. */
- for (res = reserved; res; res = res->sibling) {
- if (res->start > PFN_PHYS(max_pfn))
- break;
-
- /*
- * resource_init will complain about partial
- * overlaps, so we'll just ignore such
- * resources for now.
- */
- if (res->start >= PFN_PHYS(first_pfn)
- && res->end < PFN_PHYS(max_pfn))
- reserve_bootmem_node(NODE_DATA(node),
- res->start,
- resource_size(res),
- BOOTMEM_DEFAULT);
- }
-
- node_set_online(node);
- }
-}
-
-void __init setup_arch (char **cmdline_p)
-{
- struct clk *cpu_clk;
-
- init_mm.start_code = (unsigned long)_stext;
- init_mm.end_code = (unsigned long)_etext;
- init_mm.end_data = (unsigned long)_edata;
- init_mm.brk = (unsigned long)_end;
-
- /*
- * Include .init section to make allocations easier. It will
- * be removed before the resource is actually requested.
- */
- kernel_code.start = __pa(__init_begin);
- kernel_code.end = __pa(init_mm.end_code - 1);
- kernel_data.start = __pa(init_mm.end_code);
- kernel_data.end = __pa(init_mm.brk - 1);
-
- parse_tags(bootloader_tags);
-
- setup_processor();
- setup_platform();
- setup_board();
-
- cpu_clk = clk_get(NULL, "cpu");
- if (IS_ERR(cpu_clk)) {
- printk(KERN_WARNING "Warning: Unable to get CPU clock\n");
- } else {
- unsigned long cpu_hz = clk_get_rate(cpu_clk);
-
- /*
- * Well, duh, but it's probably a good idea to
- * increment the use count.
- */
- clk_enable(cpu_clk);
-
- boot_cpu_data.clk = cpu_clk;
- boot_cpu_data.loops_per_jiffy = cpu_hz * 4;
- printk("CPU: Running at %lu.%03lu MHz\n",
- ((cpu_hz + 500) / 1000) / 1000,
- ((cpu_hz + 500) / 1000) % 1000);
- }
-
- strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
- *cmdline_p = command_line;
- parse_early_param();
-
- setup_bootmem();
-
-#ifdef CONFIG_VT
- conswitchp = &dummy_con;
-#endif
-
- paging_init();
- resource_init();
-}
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * Based on linux/arch/sh/kernel/signal.c
- * Copyright (C) 1999, 2000 Niibe Yutaka & Kaz Kojima
- * Copyright (C) 1991, 1992 Linus Torvalds
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/errno.h>
-#include <linux/ptrace.h>
-#include <linux/unistd.h>
-#include <linux/tracehook.h>
-
-#include <linux/uaccess.h>
-#include <asm/ucontext.h>
-#include <asm/syscalls.h>
-
-struct rt_sigframe
-{
- struct siginfo info;
- struct ucontext uc;
- unsigned long retcode;
-};
-
-static int
-restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
-{
- int err = 0;
-
-#define COPY(x) err |= __get_user(regs->x, &sc->x)
- COPY(sr);
- COPY(pc);
- COPY(lr);
- COPY(sp);
- COPY(r12);
- COPY(r11);
- COPY(r10);
- COPY(r9);
- COPY(r8);
- COPY(r7);
- COPY(r6);
- COPY(r5);
- COPY(r4);
- COPY(r3);
- COPY(r2);
- COPY(r1);
- COPY(r0);
-#undef COPY
-
- /*
- * Don't allow anyone to pretend they're running in supervisor
- * mode or something...
- */
- err |= !valid_user_regs(regs);
-
- return err;
-}
-
-
-asmlinkage int sys_rt_sigreturn(struct pt_regs *regs)
-{
- struct rt_sigframe __user *frame;
- sigset_t set;
-
- /* Always make any pending restarted system calls return -EINTR */
- current->restart_block.fn = do_no_restart_syscall;
-
- frame = (struct rt_sigframe __user *)regs->sp;
- pr_debug("SIG return: frame = %p\n", frame);
-
- if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
- goto badframe;
-
- if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
- goto badframe;
-
- set_current_blocked(&set);
-
- if (restore_sigcontext(regs, &frame->uc.uc_mcontext))
- goto badframe;
-
- if (restore_altstack(&frame->uc.uc_stack))
- goto badframe;
-
- pr_debug("Context restored: pc = %08lx, lr = %08lx, sp = %08lx\n",
- regs->pc, regs->lr, regs->sp);
-
- return regs->r12;
-
-badframe:
- force_sig(SIGSEGV, current);
- return 0;
-}
-
-static int
-setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs)
-{
- int err = 0;
-
-#define COPY(x) err |= __put_user(regs->x, &sc->x)
- COPY(sr);
- COPY(pc);
- COPY(lr);
- COPY(sp);
- COPY(r12);
- COPY(r11);
- COPY(r10);
- COPY(r9);
- COPY(r8);
- COPY(r7);
- COPY(r6);
- COPY(r5);
- COPY(r4);
- COPY(r3);
- COPY(r2);
- COPY(r1);
- COPY(r0);
-#undef COPY
-
- return err;
-}
-
-static inline void __user *
-get_sigframe(struct ksignal *ksig, struct pt_regs *regs, int framesize)
-{
- unsigned long sp = sigsp(regs->sp, ksig);
-
- return (void __user *)((sp - framesize) & ~3);
-}
-
-static int
-setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs)
-{
- struct rt_sigframe __user *frame;
- int err = 0;
-
- frame = get_sigframe(ksig, regs, sizeof(*frame));
- err = -EFAULT;
- if (!access_ok(VERIFY_WRITE, frame, sizeof (*frame)))
- goto out;
-
- /*
- * Set up the return code:
- *
- * mov r8, __NR_rt_sigreturn
- * scall
- *
- * Note: This will blow up since we're using a non-executable
- * stack. Better use SA_RESTORER.
- */
-#if __NR_rt_sigreturn > 127
-# error __NR_rt_sigreturn must be < 127 to fit in a short mov
-#endif
- err = __put_user(0x3008d733 | (__NR_rt_sigreturn << 20),
- &frame->retcode);
-
- err |= copy_siginfo_to_user(&frame->info, &ksig->info);
-
- /* Set up the ucontext */
- err |= __put_user(0, &frame->uc.uc_flags);
- err |= __put_user(NULL, &frame->uc.uc_link);
- err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
- err |= setup_sigcontext(&frame->uc.uc_mcontext, regs);
- err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
-
- if (err)
- goto out;
-
- regs->r12 = ksig->sig;
- regs->r11 = (unsigned long) &frame->info;
- regs->r10 = (unsigned long) &frame->uc;
- regs->sp = (unsigned long) frame;
- if (ksig->ka.sa.sa_flags & SA_RESTORER)
- regs->lr = (unsigned long)ksig->ka.sa.sa_restorer;
- else {
- printk(KERN_NOTICE "[%s:%d] did not set SA_RESTORER\n",
- current->comm, current->pid);
- regs->lr = (unsigned long) &frame->retcode;
- }
-
- pr_debug("SIG deliver [%s:%d]: sig=%d sp=0x%lx pc=0x%lx->0x%p lr=0x%lx\n",
- current->comm, current->pid, ksig->sig, regs->sp,
- regs->pc, ksig->ka.sa.sa_handler, regs->lr);
-
- regs->pc = (unsigned long)ksig->ka.sa.sa_handler;
-
-out:
- return err;
-}
-
-static inline void setup_syscall_restart(struct pt_regs *regs)
-{
- if (regs->r12 == -ERESTART_RESTARTBLOCK)
- regs->r8 = __NR_restart_syscall;
- else
- regs->r12 = regs->r12_orig;
- regs->pc -= 2;
-}
-
-static inline void
-handle_signal(struct ksignal *ksig, struct pt_regs *regs, int syscall)
-{
- int ret;
-
- /*
- * Set up the stack frame
- */
- ret = setup_rt_frame(ksig, sigmask_to_save(), regs);
-
- /*
- * Check that the resulting registers are sane
- */
- ret |= !valid_user_regs(regs);
-
- /*
- * Block the signal if we were successful.
- */
- signal_setup_done(ret, ksig, 0);
-}
-
-/*
- * Note that 'init' is a special process: it doesn't get signals it
- * doesn't want to handle. Thus you cannot kill init even with a
- * SIGKILL even by mistake.
- */
-static void do_signal(struct pt_regs *regs, int syscall)
-{
- struct ksignal ksig;
-
- /*
- * We want the common case to go fast, which is why we may in
- * certain cases get here from kernel mode. Just return
- * without doing anything if so.
- */
- if (!user_mode(regs))
- return;
-
- get_signal(&ksig);
- if (syscall) {
- switch (regs->r12) {
- case -ERESTART_RESTARTBLOCK:
- case -ERESTARTNOHAND:
- if (ksig.sig > 0) {
- regs->r12 = -EINTR;
- break;
- }
- /* fall through */
- case -ERESTARTSYS:
- if (ksig.sig > 0 && !(ksig.ka.sa.sa_flags & SA_RESTART)) {
- regs->r12 = -EINTR;
- break;
- }
- /* fall through */
- case -ERESTARTNOINTR:
- setup_syscall_restart(regs);
- }
- }
-
- if (!ksig.sig) {
- /* No signal to deliver -- put the saved sigmask back */
- restore_saved_sigmask();
- return;
- }
-
- handle_signal(&ksig, regs, syscall);
-}
-
-asmlinkage void do_notify_resume(struct pt_regs *regs, struct thread_info *ti)
-{
- int syscall = 0;
-
- if ((sysreg_read(SR) & MODE_MASK) == MODE_SUPERVISOR)
- syscall = 1;
-
- if (ti->flags & _TIF_SIGPENDING)
- do_signal(regs, syscall);
-
- if (ti->flags & _TIF_NOTIFY_RESUME) {
- clear_thread_flag(TIF_NOTIFY_RESUME);
- tracehook_notify_resume(regs);
- }
-}
+++ /dev/null
-/*
- * Stack trace management functions
- *
- * Copyright (C) 2007 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/sched.h>
-#include <linux/sched/task_stack.h>
-#include <linux/stacktrace.h>
-#include <linux/thread_info.h>
-#include <linux/module.h>
-
-register unsigned long current_frame_pointer asm("r7");
-
-struct stackframe {
- unsigned long lr;
- unsigned long fp;
-};
-
-/*
- * Save stack-backtrace addresses into a stack_trace buffer.
- */
-void save_stack_trace(struct stack_trace *trace)
-{
- unsigned long low, high;
- unsigned long fp;
- struct stackframe *frame;
- int skip = trace->skip;
-
- low = (unsigned long)task_stack_page(current);
- high = low + THREAD_SIZE;
- fp = current_frame_pointer;
-
- while (fp >= low && fp <= (high - 8)) {
- frame = (struct stackframe *)fp;
-
- if (skip) {
- skip--;
- } else {
- trace->entries[trace->nr_entries++] = frame->lr;
- if (trace->nr_entries >= trace->max_entries)
- break;
- }
-
- /*
- * The next frame must be at a higher address than the
- * current frame.
- */
- low = fp + 8;
- fp = frame->fp;
- }
-}
-EXPORT_SYMBOL_GPL(save_stack_trace);
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <asm/sysreg.h>
-
- .text
- .global __switch_to
- .type __switch_to, @function
-
- /* Switch thread context from "prev" to "next", returning "last"
- * r12 : prev
- * r11 : &prev->thread + 1
- * r10 : &next->thread
- */
-__switch_to:
- stm --r11, r0,r1,r2,r3,r4,r5,r6,r7,sp,lr
- mfsr r9, SYSREG_SR
- st.w --r11, r9
- ld.w r8, r10++
- /*
- * schedule() may have been called from a mode with a different
- * set of registers. Make sure we don't lose anything here.
- */
- pushm r10,r12
- mtsr SYSREG_SR, r8
- frs /* flush the return stack */
- sub pc, -2 /* flush the pipeline */
- popm r10,r12
- ldm r10++, r0,r1,r2,r3,r4,r5,r6,r7,sp,pc
- .size __switch_to, . - __switch_to
+++ /dev/null
-/*
- * Copyright (C) 2005-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-/*
- * Stubs for syscalls that require access to pt_regs or that take more
- * than five parameters.
- */
-
-#define ARG6 r3
-
- .text
- .global __sys_rt_sigsuspend
- .type __sys_rt_sigsuspend,@function
-__sys_rt_sigsuspend:
- mov r10, sp
- rjmp sys_rt_sigsuspend
-
- .global __sys_rt_sigreturn
- .type __sys_rt_sigreturn,@function
-__sys_rt_sigreturn:
- mov r12, sp
- rjmp sys_rt_sigreturn
-
- .global __sys_mmap2
- .type __sys_mmap2,@function
-__sys_mmap2:
- pushm lr
- st.w --sp, ARG6
- call sys_mmap_pgoff
- sub sp, -4
- popm pc
-
- .global __sys_sendto
- .type __sys_sendto,@function
-__sys_sendto:
- pushm lr
- st.w --sp, ARG6
- call sys_sendto
- sub sp, -4
- popm pc
-
- .global __sys_recvfrom
- .type __sys_recvfrom,@function
-__sys_recvfrom:
- pushm lr
- st.w --sp, ARG6
- call sys_recvfrom
- sub sp, -4
- popm pc
-
- .global __sys_pselect6
- .type __sys_pselect6,@function
-__sys_pselect6:
- pushm lr
- st.w --sp, ARG6
- call sys_pselect6
- sub sp, -4
- popm pc
-
- .global __sys_splice
- .type __sys_splice,@function
-__sys_splice:
- pushm lr
- st.w --sp, ARG6
- call sys_splice
- sub sp, -4
- popm pc
-
- .global __sys_epoll_pwait
- .type __sys_epoll_pwait,@function
-__sys_epoll_pwait:
- pushm lr
- st.w --sp, ARG6
- call sys_epoll_pwait
- sub sp, -4
- popm pc
-
- .global __sys_sync_file_range
- .type __sys_sync_file_range,@function
-__sys_sync_file_range:
- pushm lr
- st.w --sp, ARG6
- call sys_sync_file_range
- sub sp, -4
- popm pc
-
- .global __sys_fallocate
- .type __sys_fallocate,@function
-__sys_fallocate:
- pushm lr
- st.w --sp, ARG6
- call sys_fallocate
- sub sp, -4
- popm pc
-
- .global __sys_fanotify_mark
- .type __sys_fanotify_mark,@function
-__sys_fanotify_mark:
- pushm lr
- st.w --sp, ARG6
- call sys_fanotify_mark
- sub sp, -4
- popm pc
-
- .global __sys_process_vm_readv
- .type __sys_process_vm_readv,@function
-__sys_process_vm_readv:
- pushm lr
- st.w --sp, ARG6
- call sys_process_vm_readv
- sub sp, -4
- popm pc
-
- .global __sys_process_vm_writev
- .type __sys_process_vm_writev,@function
-__sys_process_vm_writev:
- pushm lr
- st.w --sp, ARG6
- call sys_process_vm_writev
- sub sp, -4
- popm pc
-
- .global __sys_copy_file_range
- .type __sys_copy_file_range,@function
-__sys_copy_file_range:
- pushm lr
- st.w --sp, ARG6
- call sys_copy_file_range
- sub sp, -4
- popm pc
-
- .global __sys_preadv2
- .type __sys_preadv2,@function
-__sys_preadv2:
- pushm lr
- st.w --sp, ARG6
- call sys_preadv2
- sub sp, -4
- popm pc
-
- .global __sys_pwritev2
- .type __sys_pwritev2,@function
-__sys_pwritev2:
- pushm lr
- st.w --sp, ARG6
- call sys_pwritev2
- sub sp, -4
- popm pc
+++ /dev/null
-/*
- * AVR32 system call table
- *
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
- .section .rodata,"a",@progbits
- .type sys_call_table,@object
- .global sys_call_table
- .align 2
-sys_call_table:
- .long sys_restart_syscall
- .long sys_exit
- .long sys_fork
- .long sys_read
- .long sys_write
- .long sys_open
- .long sys_close
- .long sys_umask
- .long sys_creat
- .long sys_link
- .long sys_unlink /* 10 */
- .long sys_execve
- .long sys_chdir
- .long sys_time
- .long sys_mknod
- .long sys_chmod
- .long sys_chown
- .long sys_lchown
- .long sys_lseek
- .long sys_llseek
- .long sys_getpid /* 20 */
- .long sys_mount
- .long sys_umount
- .long sys_setuid
- .long sys_getuid
- .long sys_stime
- .long sys_ptrace
- .long sys_alarm
- .long sys_pause
- .long sys_utime
- .long sys_newstat /* 30 */
- .long sys_newfstat
- .long sys_newlstat
- .long sys_access
- .long sys_chroot
- .long sys_sync
- .long sys_fsync
- .long sys_kill
- .long sys_rename
- .long sys_mkdir
- .long sys_rmdir /* 40 */
- .long sys_dup
- .long sys_pipe
- .long sys_times
- .long sys_clone
- .long sys_brk
- .long sys_setgid
- .long sys_getgid
- .long sys_getcwd
- .long sys_geteuid
- .long sys_getegid /* 50 */
- .long sys_acct
- .long sys_setfsuid
- .long sys_setfsgid
- .long sys_ioctl
- .long sys_fcntl
- .long sys_setpgid
- .long sys_mremap
- .long sys_setresuid
- .long sys_getresuid
- .long sys_setreuid /* 60 */
- .long sys_setregid
- .long sys_ustat
- .long sys_dup2
- .long sys_getppid
- .long sys_getpgrp
- .long sys_setsid
- .long sys_rt_sigaction
- .long __sys_rt_sigreturn
- .long sys_rt_sigprocmask
- .long sys_rt_sigpending /* 70 */
- .long sys_rt_sigtimedwait
- .long sys_rt_sigqueueinfo
- .long __sys_rt_sigsuspend
- .long sys_sethostname
- .long sys_setrlimit
- .long sys_getrlimit
- .long sys_getrusage
- .long sys_gettimeofday
- .long sys_settimeofday
- .long sys_getgroups /* 80 */
- .long sys_setgroups
- .long sys_select
- .long sys_symlink
- .long sys_fchdir
- .long sys_readlink
- .long sys_pread64
- .long sys_pwrite64
- .long sys_swapon
- .long sys_reboot
- .long __sys_mmap2 /* 90 */
- .long sys_munmap
- .long sys_truncate
- .long sys_ftruncate
- .long sys_fchmod
- .long sys_fchown
- .long sys_getpriority
- .long sys_setpriority
- .long sys_wait4
- .long sys_statfs
- .long sys_fstatfs /* 100 */
- .long sys_vhangup
- .long sys_sigaltstack
- .long sys_syslog
- .long sys_setitimer
- .long sys_getitimer
- .long sys_swapoff
- .long sys_sysinfo
- .long sys_ni_syscall /* was sys_ipc briefly */
- .long sys_sendfile
- .long sys_setdomainname /* 110 */
- .long sys_newuname
- .long sys_adjtimex
- .long sys_mprotect
- .long sys_vfork
- .long sys_init_module
- .long sys_delete_module
- .long sys_quotactl
- .long sys_getpgid
- .long sys_bdflush
- .long sys_sysfs /* 120 */
- .long sys_personality
- .long sys_ni_syscall /* reserved for afs_syscall */
- .long sys_getdents
- .long sys_flock
- .long sys_msync
- .long sys_readv
- .long sys_writev
- .long sys_getsid
- .long sys_fdatasync
- .long sys_sysctl /* 130 */
- .long sys_mlock
- .long sys_munlock
- .long sys_mlockall
- .long sys_munlockall
- .long sys_sched_setparam
- .long sys_sched_getparam
- .long sys_sched_setscheduler
- .long sys_sched_getscheduler
- .long sys_sched_yield
- .long sys_sched_get_priority_max /* 140 */
- .long sys_sched_get_priority_min
- .long sys_sched_rr_get_interval
- .long sys_nanosleep
- .long sys_poll
- .long sys_ni_syscall /* 145 was nfsservctl */
- .long sys_setresgid
- .long sys_getresgid
- .long sys_prctl
- .long sys_socket
- .long sys_bind /* 150 */
- .long sys_connect
- .long sys_listen
- .long sys_accept
- .long sys_getsockname
- .long sys_getpeername
- .long sys_socketpair
- .long sys_send
- .long sys_recv
- .long __sys_sendto
- .long __sys_recvfrom /* 160 */
- .long sys_shutdown
- .long sys_setsockopt
- .long sys_getsockopt
- .long sys_sendmsg
- .long sys_recvmsg
- .long sys_truncate64
- .long sys_ftruncate64
- .long sys_stat64
- .long sys_lstat64
- .long sys_fstat64 /* 170 */
- .long sys_pivot_root
- .long sys_mincore
- .long sys_madvise
- .long sys_getdents64
- .long sys_fcntl64
- .long sys_gettid
- .long sys_readahead
- .long sys_setxattr
- .long sys_lsetxattr
- .long sys_fsetxattr /* 180 */
- .long sys_getxattr
- .long sys_lgetxattr
- .long sys_fgetxattr
- .long sys_listxattr
- .long sys_llistxattr
- .long sys_flistxattr
- .long sys_removexattr
- .long sys_lremovexattr
- .long sys_fremovexattr
- .long sys_tkill /* 190 */
- .long sys_sendfile64
- .long sys_futex
- .long sys_sched_setaffinity
- .long sys_sched_getaffinity
- .long sys_capget
- .long sys_capset
- .long sys_io_setup
- .long sys_io_destroy
- .long sys_io_getevents
- .long sys_io_submit /* 200 */
- .long sys_io_cancel
- .long sys_fadvise64
- .long sys_exit_group
- .long sys_lookup_dcookie
- .long sys_epoll_create
- .long sys_epoll_ctl
- .long sys_epoll_wait
- .long sys_remap_file_pages
- .long sys_set_tid_address
- .long sys_timer_create /* 210 */
- .long sys_timer_settime
- .long sys_timer_gettime
- .long sys_timer_getoverrun
- .long sys_timer_delete
- .long sys_clock_settime
- .long sys_clock_gettime
- .long sys_clock_getres
- .long sys_clock_nanosleep
- .long sys_statfs64
- .long sys_fstatfs64 /* 220 */
- .long sys_tgkill
- .long sys_ni_syscall /* reserved for TUX */
- .long sys_utimes
- .long sys_fadvise64_64
- .long sys_cacheflush
- .long sys_ni_syscall /* sys_vserver */
- .long sys_mq_open
- .long sys_mq_unlink
- .long sys_mq_timedsend
- .long sys_mq_timedreceive /* 230 */
- .long sys_mq_notify
- .long sys_mq_getsetattr
- .long sys_kexec_load
- .long sys_waitid
- .long sys_add_key
- .long sys_request_key
- .long sys_keyctl
- .long sys_ioprio_set
- .long sys_ioprio_get
- .long sys_inotify_init /* 240 */
- .long sys_inotify_add_watch
- .long sys_inotify_rm_watch
- .long sys_openat
- .long sys_mkdirat
- .long sys_mknodat
- .long sys_fchownat
- .long sys_futimesat
- .long sys_fstatat64
- .long sys_unlinkat
- .long sys_renameat /* 250 */
- .long sys_linkat
- .long sys_symlinkat
- .long sys_readlinkat
- .long sys_fchmodat
- .long sys_faccessat
- .long __sys_pselect6
- .long sys_ppoll
- .long sys_unshare
- .long sys_set_robust_list
- .long sys_get_robust_list /* 260 */
- .long __sys_splice
- .long __sys_sync_file_range
- .long sys_tee
- .long sys_vmsplice
- .long __sys_epoll_pwait
- .long sys_msgget
- .long sys_msgsnd
- .long sys_msgrcv
- .long sys_msgctl
- .long sys_semget /* 270 */
- .long sys_semop
- .long sys_semctl
- .long sys_semtimedop
- .long sys_shmat
- .long sys_shmget
- .long sys_shmdt
- .long sys_shmctl
- .long sys_utimensat
- .long sys_signalfd
- .long sys_ni_syscall /* 280, was sys_timerfd */
- .long sys_eventfd
- .long sys_ni_syscall /* 282, was half-implemented recvmmsg */
- .long sys_setns
- .long sys_pread64
- .long sys_pwrite64
- .long sys_timerfd_create
- .long __sys_fallocate
- .long sys_timerfd_settime
- .long sys_timerfd_gettime
- .long sys_signalfd4 /* 290 */
- .long sys_eventfd2
- .long sys_epoll_create1
- .long sys_dup3
- .long sys_pipe2
- .long sys_inotify_init1
- .long sys_preadv
- .long sys_pwritev
- .long sys_rt_tgsigqueueinfo
- .long sys_perf_event_open
- .long sys_recvmmsg /* 300 */
- .long sys_fanotify_init
- .long __sys_fanotify_mark
- .long sys_prlimit64
- .long sys_name_to_handle_at
- .long sys_open_by_handle_at
- .long sys_clock_adjtime
- .long sys_syncfs
- .long sys_sendmmsg
- .long __sys_process_vm_readv
- .long __sys_process_vm_writev /* 310 */
- .long sys_kcmp
- .long sys_finit_module
- .long sys_sched_setattr
- .long sys_sched_getattr
- .long sys_renameat2
- .long sys_seccomp
- .long sys_getrandom
- .long sys_memfd_create
- .long sys_bpf
- .long sys_execveat /* 320 */
- .long sys_accept4
- .long sys_userfaultfd
- .long sys_membarrier
- .long sys_mlock2
- .long __sys_copy_file_range
- .long __sys_preadv2
- .long __sys_pwritev2
- .long sys_pkey_mprotect
- .long sys_pkey_alloc
- .long sys_pkey_free /* 330 */
- .long sys_ni_syscall /* r8 is saturated at nr_syscalls */
+++ /dev/null
-/*
- * Copyright (C) 2004-2007 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/clk.h>
-#include <linux/clockchips.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/kernel.h>
-#include <linux/time.h>
-#include <linux/cpu.h>
-
-#include <asm/sysreg.h>
-
-#include <mach/pm.h>
-
-static bool disable_cpu_idle_poll;
-
-static u64 read_cycle_count(struct clocksource *cs)
-{
- return (u64)sysreg_read(COUNT);
-}
-
-/*
- * The architectural cycle count registers are a fine clocksource unless
- * the system idle loop use sleep states like "idle": the CPU cycles
- * measured by COUNT (and COMPARE) don't happen during sleep states.
- * Their duration also changes if cpufreq changes the CPU clock rate.
- * So we rate the clocksource using COUNT as very low quality.
- */
-static struct clocksource counter = {
- .name = "avr32_counter",
- .rating = 50,
- .read = read_cycle_count,
- .mask = CLOCKSOURCE_MASK(32),
- .flags = CLOCK_SOURCE_IS_CONTINUOUS,
-};
-
-static irqreturn_t timer_interrupt(int irq, void *dev_id)
-{
- struct clock_event_device *evdev = dev_id;
-
- if (unlikely(!(intc_get_pending(0) & 1)))
- return IRQ_NONE;
-
- /*
- * Disable the interrupt until the clockevent subsystem
- * reprograms it.
- */
- sysreg_write(COMPARE, 0);
-
- evdev->event_handler(evdev);
- return IRQ_HANDLED;
-}
-
-static struct irqaction timer_irqaction = {
- .handler = timer_interrupt,
- /* Oprofile uses the same irq as the timer, so allow it to be shared */
- .flags = IRQF_TIMER | IRQF_SHARED,
- .name = "avr32_comparator",
-};
-
-static int comparator_next_event(unsigned long delta,
- struct clock_event_device *evdev)
-{
- unsigned long flags;
-
- raw_local_irq_save(flags);
-
- /* The time to read COUNT then update COMPARE must be less
- * than the min_delta_ns value for this clockevent source.
- */
- sysreg_write(COMPARE, (sysreg_read(COUNT) + delta) ? : 1);
-
- raw_local_irq_restore(flags);
-
- return 0;
-}
-
-static int comparator_shutdown(struct clock_event_device *evdev)
-{
- pr_debug("%s: %s\n", __func__, evdev->name);
- sysreg_write(COMPARE, 0);
-
- if (disable_cpu_idle_poll) {
- disable_cpu_idle_poll = false;
- /*
- * Only disable idle poll if we have forced that
- * in a previous call.
- */
- cpu_idle_poll_ctrl(false);
- }
- return 0;
-}
-
-static int comparator_set_oneshot(struct clock_event_device *evdev)
-{
- pr_debug("%s: %s\n", __func__, evdev->name);
-
- disable_cpu_idle_poll = true;
- /*
- * If we're using the COUNT and COMPARE registers we
- * need to force idle poll.
- */
- cpu_idle_poll_ctrl(true);
-
- return 0;
-}
-
-static struct clock_event_device comparator = {
- .name = "avr32_comparator",
- .features = CLOCK_EVT_FEAT_ONESHOT,
- .shift = 16,
- .rating = 50,
- .set_next_event = comparator_next_event,
- .set_state_shutdown = comparator_shutdown,
- .set_state_oneshot = comparator_set_oneshot,
- .tick_resume = comparator_set_oneshot,
-};
-
-void read_persistent_clock(struct timespec *ts)
-{
- ts->tv_sec = mktime(2007, 1, 1, 0, 0, 0);
- ts->tv_nsec = 0;
-}
-
-void __init time_init(void)
-{
- unsigned long counter_hz;
- int ret;
-
- /* figure rate for counter */
- counter_hz = clk_get_rate(boot_cpu_data.clk);
- ret = clocksource_register_hz(&counter, counter_hz);
- if (ret)
- pr_debug("timer: could not register clocksource: %d\n", ret);
-
- /* setup COMPARE clockevent */
- comparator.mult = div_sc(counter_hz, NSEC_PER_SEC, comparator.shift);
- comparator.max_delta_ns = clockevent_delta2ns((u32)~0, &comparator);
- comparator.min_delta_ns = clockevent_delta2ns(50, &comparator) + 1;
- comparator.cpumask = cpumask_of(0);
-
- sysreg_write(COMPARE, 0);
- timer_irqaction.dev_id = &comparator;
-
- ret = setup_irq(0, &timer_irqaction);
- if (ret)
- pr_debug("timer: could not request IRQ 0: %d\n", ret);
- else {
- clockevents_register_device(&comparator);
-
- pr_info("%s: irq 0, %lu.%03lu MHz\n", comparator.name,
- ((counter_hz + 500) / 1000) / 1000,
- ((counter_hz + 500) / 1000) % 1000);
- }
-}
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/bug.h>
-#include <linux/hardirq.h>
-#include <linux/init.h>
-#include <linux/kallsyms.h>
-#include <linux/kdebug.h>
-#include <linux/extable.h>
-#include <linux/module.h> /* print_modules */
-#include <linux/notifier.h>
-#include <linux/sched/signal.h>
-#include <linux/uaccess.h>
-
-#include <asm/addrspace.h>
-#include <asm/mmu_context.h>
-#include <asm/ocd.h>
-#include <asm/sysreg.h>
-#include <asm/traps.h>
-
-static DEFINE_SPINLOCK(die_lock);
-
-void die(const char *str, struct pt_regs *regs, long err)
-{
- static int die_counter;
-
- console_verbose();
- spin_lock_irq(&die_lock);
- bust_spinlocks(1);
-
- printk(KERN_ALERT "Oops: %s, sig: %ld [#%d]\n",
- str, err, ++die_counter);
-
- printk(KERN_EMERG);
-
-#ifdef CONFIG_PREEMPT
- printk(KERN_CONT "PREEMPT ");
-#endif
-#ifdef CONFIG_FRAME_POINTER
- printk(KERN_CONT "FRAME_POINTER ");
-#endif
- if (current_cpu_data.features & AVR32_FEATURE_OCD) {
- unsigned long did = ocd_read(DID);
- printk(KERN_CONT "chip: 0x%03lx:0x%04lx rev %lu\n",
- (did >> 1) & 0x7ff,
- (did >> 12) & 0x7fff,
- (did >> 28) & 0xf);
- } else {
- printk(KERN_CONT "cpu: arch %u r%u / core %u r%u\n",
- current_cpu_data.arch_type,
- current_cpu_data.arch_revision,
- current_cpu_data.cpu_type,
- current_cpu_data.cpu_revision);
- }
-
- print_modules();
- show_regs_log_lvl(regs, KERN_EMERG);
- show_stack_log_lvl(current, regs->sp, regs, KERN_EMERG);
- bust_spinlocks(0);
- add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
- spin_unlock_irq(&die_lock);
-
- if (in_interrupt())
- panic("Fatal exception in interrupt");
-
- if (panic_on_oops)
- panic("Fatal exception");
-
- do_exit(err);
-}
-
-void _exception(long signr, struct pt_regs *regs, int code,
- unsigned long addr)
-{
- siginfo_t info;
-
- if (!user_mode(regs)) {
- const struct exception_table_entry *fixup;
-
- /* Are we prepared to handle this kernel fault? */
- fixup = search_exception_tables(regs->pc);
- if (fixup) {
- regs->pc = fixup->fixup;
- return;
- }
- die("Unhandled exception in kernel mode", regs, signr);
- }
-
- memset(&info, 0, sizeof(info));
- info.si_signo = signr;
- info.si_code = code;
- info.si_addr = (void __user *)addr;
- force_sig_info(signr, &info, current);
-}
-
-asmlinkage void do_nmi(unsigned long ecr, struct pt_regs *regs)
-{
- int ret;
-
- nmi_enter();
-
- ret = notify_die(DIE_NMI, "NMI", regs, 0, ecr, SIGINT);
- switch (ret) {
- case NOTIFY_OK:
- case NOTIFY_STOP:
- break;
- case NOTIFY_BAD:
- die("Fatal Non-Maskable Interrupt", regs, SIGINT);
- default:
- printk(KERN_ALERT "Got NMI, but nobody cared. Disabling...\n");
- nmi_disable();
- break;
- }
- nmi_exit();
-}
-
-asmlinkage void do_critical_exception(unsigned long ecr, struct pt_regs *regs)
-{
- die("Critical exception", regs, SIGKILL);
-}
-
-asmlinkage void do_address_exception(unsigned long ecr, struct pt_regs *regs)
-{
- _exception(SIGBUS, regs, BUS_ADRALN, regs->pc);
-}
-
-/* This way of handling undefined instructions is stolen from ARM */
-static LIST_HEAD(undef_hook);
-static DEFINE_SPINLOCK(undef_lock);
-
-void register_undef_hook(struct undef_hook *hook)
-{
- spin_lock_irq(&undef_lock);
- list_add(&hook->node, &undef_hook);
- spin_unlock_irq(&undef_lock);
-}
-
-void unregister_undef_hook(struct undef_hook *hook)
-{
- spin_lock_irq(&undef_lock);
- list_del(&hook->node);
- spin_unlock_irq(&undef_lock);
-}
-
-static int do_cop_absent(u32 insn)
-{
- int cop_nr;
- u32 cpucr;
-
- if ((insn & 0xfdf00000) == 0xf1900000)
- /* LDC0 */
- cop_nr = 0;
- else
- cop_nr = (insn >> 13) & 0x7;
-
- /* Try enabling the coprocessor */
- cpucr = sysreg_read(CPUCR);
- cpucr |= (1 << (24 + cop_nr));
- sysreg_write(CPUCR, cpucr);
-
- cpucr = sysreg_read(CPUCR);
- if (!(cpucr & (1 << (24 + cop_nr))))
- return -ENODEV;
-
- return 0;
-}
-
-#ifdef CONFIG_BUG
-int is_valid_bugaddr(unsigned long pc)
-{
- unsigned short opcode;
-
- if (pc < PAGE_OFFSET)
- return 0;
- if (probe_kernel_address((u16 *)pc, opcode))
- return 0;
-
- return opcode == AVR32_BUG_OPCODE;
-}
-#endif
-
-asmlinkage void do_illegal_opcode(unsigned long ecr, struct pt_regs *regs)
-{
- u32 insn;
- struct undef_hook *hook;
- void __user *pc;
- long code;
-
-#ifdef CONFIG_BUG
- if (!user_mode(regs) && (ecr == ECR_ILLEGAL_OPCODE)) {
- enum bug_trap_type type;
-
- type = report_bug(regs->pc, regs);
- switch (type) {
- case BUG_TRAP_TYPE_NONE:
- break;
- case BUG_TRAP_TYPE_WARN:
- regs->pc += 2;
- return;
- case BUG_TRAP_TYPE_BUG:
- die("Kernel BUG", regs, SIGKILL);
- }
- }
-#endif
-
- local_irq_enable();
-
- if (user_mode(regs)) {
- pc = (void __user *)instruction_pointer(regs);
- if (get_user(insn, (u32 __user *)pc))
- goto invalid_area;
-
- if (ecr == ECR_COPROC_ABSENT && !do_cop_absent(insn))
- return;
-
- spin_lock_irq(&undef_lock);
- list_for_each_entry(hook, &undef_hook, node) {
- if ((insn & hook->insn_mask) == hook->insn_val) {
- if (hook->fn(regs, insn) == 0) {
- spin_unlock_irq(&undef_lock);
- return;
- }
- }
- }
- spin_unlock_irq(&undef_lock);
- }
-
- switch (ecr) {
- case ECR_PRIVILEGE_VIOLATION:
- code = ILL_PRVOPC;
- break;
- case ECR_COPROC_ABSENT:
- code = ILL_COPROC;
- break;
- default:
- code = ILL_ILLOPC;
- break;
- }
-
- _exception(SIGILL, regs, code, regs->pc);
- return;
-
-invalid_area:
- _exception(SIGSEGV, regs, SEGV_MAPERR, regs->pc);
-}
-
-asmlinkage void do_fpe(unsigned long ecr, struct pt_regs *regs)
-{
- /* We have no FPU yet */
- _exception(SIGILL, regs, ILL_COPROC, regs->pc);
-}
-
-
-void __init trap_init(void)
-{
-
-}
+++ /dev/null
-/*
- * AVR32 linker script for the Linux kernel
- *
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#define LOAD_OFFSET 0x00000000
-#include <asm-generic/vmlinux.lds.h>
-#include <asm/cache.h>
-#include <asm/thread_info.h>
-
-OUTPUT_FORMAT("elf32-avr32", "elf32-avr32", "elf32-avr32")
-OUTPUT_ARCH(avr32)
-ENTRY(_start)
-
-/* Big endian */
-jiffies = jiffies_64 + 4;
-
-SECTIONS
-{
- . = CONFIG_ENTRY_ADDRESS;
- .init : AT(ADDR(.init) - LOAD_OFFSET) {
- _text = .;
- __init_begin = .;
- _sinittext = .;
- *(.text.reset)
- INIT_TEXT
- /*
- * .exit.text is discarded at runtime, not
- * link time, to deal with references from
- * __bug_table
- */
- EXIT_TEXT
- _einittext = .;
- . = ALIGN(4);
- __tagtable_begin = .;
- *(.taglist.init)
- __tagtable_end = .;
- }
- INIT_DATA_SECTION(16)
- . = ALIGN(PAGE_SIZE);
- __init_end = .;
-
- .text : AT(ADDR(.text) - LOAD_OFFSET) {
- _evba = .;
- _stext = .;
- *(.ex.text)
- *(.irq.text)
- KPROBES_TEXT
- TEXT_TEXT
- SCHED_TEXT
- CPUIDLE_TEXT
- LOCK_TEXT
- *(.fixup)
- *(.gnu.warning)
- _etext = .;
- } = 0xd703d703
-
- EXCEPTION_TABLE(4)
- RODATA
-
- .data : AT(ADDR(.data) - LOAD_OFFSET) {
- _data = .;
- _sdata = .;
-
- INIT_TASK_DATA(THREAD_SIZE)
- PAGE_ALIGNED_DATA(PAGE_SIZE);
- CACHELINE_ALIGNED_DATA(L1_CACHE_BYTES)
- *(.data.rel*)
- DATA_DATA
- CONSTRUCTORS
-
- _edata = .;
- }
-
- BSS_SECTION(0, 8, 8)
- _end = .;
-
- DWARF_DEBUG
-
- /* When something in the kernel is NOT compiled as a module, the module
- * cleanup code and data are put into these segments. Both can then be
- * thrown away, as cleanup code is never called unless it's a module.
- */
- DISCARDS
-}
+++ /dev/null
-#
-# Makefile for AVR32-specific library files
-#
-
-lib-y := copy_user.o clear_user.o
-lib-y += strncpy_from_user.o strnlen_user.o
-lib-y += delay.o memset.o memcpy.o findbit.o
-lib-y += csum_partial.o csum_partial_copy_generic.o
-lib-y += io-readsw.o io-readsl.o io-writesw.o io-writesl.o
-lib-y += io-readsb.o io-writesb.o
-lib-y += __avr32_lsl64.o __avr32_lsr64.o __avr32_asr64.o
+++ /dev/null
-/*
- * Copyright (C) 2005-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
- /*
- * DWtype __avr32_asr64(DWtype u, word_type b)
- */
- .text
- .global __avr32_asr64
- .type __avr32_asr64,@function
-__avr32_asr64:
- cp.w r12, 0
- reteq r12
-
- rsub r9, r12, 32
- brle 1f
-
- lsl r8, r11, r9
- lsr r10, r10, r12
- asr r11, r11, r12
- or r10, r8
- retal r12
-
-1: neg r9
- asr r10, r11, r9
- asr r11, 31
- retal r12
+++ /dev/null
-/*
- * Copyright (C) 2005-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
- /*
- * DWtype __avr32_lsl64(DWtype u, word_type b)
- */
- .text
- .global __avr32_lsl64
- .type __avr32_lsl64,@function
-__avr32_lsl64:
- cp.w r12, 0
- reteq r12
-
- rsub r9, r12, 32
- brle 1f
-
- lsr r8, r10, r9
- lsl r10, r10, r12
- lsl r11, r11, r12
- or r11, r8
- retal r12
-
-1: neg r9
- lsl r11, r10, r9
- mov r10, 0
- retal r12
+++ /dev/null
-/*
- * Copyright (C) 2005-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
- /*
- * DWtype __avr32_lsr64(DWtype u, word_type b)
- */
- .text
- .global __avr32_lsr64
- .type __avr32_lsr64,@function
-__avr32_lsr64:
- cp.w r12, 0
- reteq r12
-
- rsub r9, r12, 32
- brle 1f
-
- lsl r8, r11, r9
- lsr r11, r11, r12
- lsr r10, r10, r12
- or r10, r8
- retal r12
-
-1: neg r9
- lsr r10, r11, r9
- mov r11, 0
- retal r12
+++ /dev/null
-/*
- * Copyright 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <asm/page.h>
-#include <asm/thread_info.h>
-#include <asm/asm.h>
-
- .text
- .align 1
- .global clear_user
- .type clear_user, "function"
-clear_user:
- branch_if_kernel r8, __clear_user
- ret_if_privileged r8, r12, r11, r11
-
- .global __clear_user
- .type __clear_user, "function"
-__clear_user:
- mov r9, r12
- mov r8, 0
- andl r9, 3, COH
- brne 5f
-
-1: sub r11, 4
- brlt 2f
-
-10: st.w r12++, r8
- sub r11, 4
- brge 10b
-
-2: sub r11, -4
- reteq 0
-
- /* Unaligned count or address */
- bld r11, 1
- brcc 12f
-11: st.h r12++, r8
- sub r11, 2
- reteq 0
-12: st.b r12++, r8
- retal 0
-
- /* Unaligned address */
-5: cp.w r11, 4
- brlt 2b
-
- lsl r9, 2
- add pc, pc, r9
-13: st.b r12++, r8
- sub r11, 1
-14: st.b r12++, r8
- sub r11, 1
-15: st.b r12++, r8
- sub r11, 1
- rjmp 1b
-
- .size clear_user, . - clear_user
- .size __clear_user, . - __clear_user
-
- .section .fixup, "ax"
- .align 1
-18: sub r11, -4
-19: retal r11
-
- .section __ex_table, "a"
- .align 2
- .long 10b, 18b
- .long 11b, 19b
- .long 12b, 19b
- .long 13b, 19b
- .long 14b, 19b
- .long 15b, 19b
+++ /dev/null
-/*
- * Copy to/from userspace with optional address space checking.
- *
- * Copyright 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <asm/page.h>
-#include <asm/thread_info.h>
-#include <asm/asm.h>
-
- /*
- * __kernel_size_t
- * __copy_user(void *to, const void *from, __kernel_size_t n)
- *
- * Returns the number of bytes not copied. Might be off by
- * max 3 bytes if we get a fault in the main loop.
- *
- * The address-space checking functions simply fall through to
- * the non-checking version.
- */
- .text
- .align 1
- .global ___copy_from_user
- .type ___copy_from_user, @function
-___copy_from_user:
- branch_if_kernel r8, __copy_user
- ret_if_privileged r8, r11, r10, r10
- rjmp __copy_user
- .size ___copy_from_user, . - ___copy_from_user
-
- .global copy_to_user
- .type copy_to_user, @function
-copy_to_user:
- branch_if_kernel r8, __copy_user
- ret_if_privileged r8, r12, r10, r10
- .size copy_to_user, . - copy_to_user
-
- .global __copy_user
- .type __copy_user, @function
-__copy_user:
- mov r9, r11
- andl r9, 3, COH
- brne 6f
-
- /* At this point, from is word-aligned */
-1: sub r10, 4
- brlt 3f
-
-2:
-10: ld.w r8, r11++
-11: st.w r12++, r8
- sub r10, 4
- brge 2b
-
-3: sub r10, -4
- reteq 0
-
- /*
- * Handle unaligned count. Need to be careful with r10 here so
- * that we return the correct value even if we get a fault
- */
-4:
-20: ld.ub r8, r11++
-21: st.b r12++, r8
- sub r10, 1
- reteq 0
-22: ld.ub r8, r11++
-23: st.b r12++, r8
- sub r10, 1
- reteq 0
-24: ld.ub r8, r11++
-25: st.b r12++, r8
- retal 0
-
- /* Handle unaligned from-pointer */
-6: cp.w r10, 4
- brlt 4b
- rsub r9, r9, 4
-
-30: ld.ub r8, r11++
-31: st.b r12++, r8
- sub r10, 1
- sub r9, 1
- breq 1b
-32: ld.ub r8, r11++
-33: st.b r12++, r8
- sub r10, 1
- sub r9, 1
- breq 1b
-34: ld.ub r8, r11++
-35: st.b r12++, r8
- sub r10, 1
- rjmp 1b
- .size __copy_user, . - __copy_user
-
- .section .fixup,"ax"
- .align 1
-19: sub r10, -4
-29: retal r10
-
- .section __ex_table,"a"
- .align 2
- .long 10b, 19b
- .long 11b, 19b
- .long 20b, 29b
- .long 21b, 29b
- .long 22b, 29b
- .long 23b, 29b
- .long 24b, 29b
- .long 25b, 29b
- .long 30b, 29b
- .long 31b, 29b
- .long 32b, 29b
- .long 33b, 29b
- .long 34b, 29b
- .long 35b, 29b
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
- /*
- * unsigned int csum_partial(const unsigned char *buff,
- * int len, unsigned int sum)
- */
- .text
- .global csum_partial
- .type csum_partial,"function"
- .align 1
-csum_partial:
- /* checksum complete words, aligned or not */
-3: sub r11, 4
- brlt 5f
-4: ld.w r9, r12++
- add r10, r9
- acr r10
- sub r11, 4
- brge 4b
-
- /* return if we had a whole number of words */
-5: sub r11, -4
- reteq r10
-
- /* checksum any remaining bytes at the end */
- mov r9, 0
- mov r8, 0
- cp r11, 2
- brlt 6f
- ld.uh r9, r12++
- sub r11, 2
- breq 7f
- lsl r9, 16
-6: ld.ub r8, r12++
- lsl r8, 8
-7: or r9, r8
- add r10, r9
- acr r10
-
- retal r10
- .size csum_partial, . - csum_partial
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <asm/errno.h>
-#include <asm/asm.h>
-
- /*
- * unsigned int csum_partial_copy_generic(const char *src, char *dst, int len
- * int sum, int *src_err_ptr,
- * int *dst_err_ptr)
- *
- * Copy src to dst while checksumming, otherwise like csum_partial.
- */
-
- .macro ld_src size, reg, ptr
-9999: ld.\size \reg, \ptr
- .section __ex_table, "a"
- .long 9999b, fixup_ld_src
- .previous
- .endm
-
- .macro st_dst size, ptr, reg
-9999: st.\size \ptr, \reg
- .section __ex_table, "a"
- .long 9999b, fixup_st_dst
- .previous
- .endm
-
- .text
- .global csum_partial_copy_generic
- .type csum_partial_copy_generic,"function"
- .align 1
-csum_partial_copy_generic:
- pushm r4-r7,lr
-
- /* The inner loop */
-1: sub r10, 4
- brlt 5f
-2: ld_src w, r5, r12++
- st_dst w, r11++, r5
- add r9, r5
- acr r9
- sub r10, 4
- brge 2b
-
- /* return if we had a whole number of words */
-5: sub r10, -4
- brne 7f
-
-6: mov r12, r9
- popm r4-r7,pc
-
- /* handle additional bytes at the tail */
-7: mov r5, 0
- mov r4, 32
-8: ld_src ub, r6, r12++
- st_dst b, r11++, r6
- lsl r5, 8
- sub r4, 8
- bfins r5, r6, 0, 8
- sub r10, 1
- brne 8b
-
- lsl r5, r5, r4
- add r9, r5
- acr r9
- rjmp 6b
-
- /* Exception handler */
- .section .fixup,"ax"
- .align 1
-fixup_ld_src:
- mov r9, -EFAULT
- cp.w r8, 0
- breq 1f
- st.w r8[0], r9
-
-1: /*
- * TODO: zero the complete destination - computing the rest
- * is too much work
- */
-
- mov r9, 0
- rjmp 6b
-
-fixup_st_dst:
- mov r9, -EFAULT
- lddsp r8, sp[20]
- cp.w r8, 0
- breq 1f
- st.w r8[0], r9
-1: mov r9, 0
- rjmp 6b
-
- .previous
+++ /dev/null
-/*
- * Precise Delay Loops for avr32
- *
- * Copyright (C) 1993 Linus Torvalds
- * Copyright (C) 1997 Martin Mares <mj@atrey.karlin.mff.cuni.cz>
- * Copyright (C) 2005-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/delay.h>
-#include <linux/module.h>
-#include <linux/timex.h>
-#include <linux/param.h>
-#include <linux/types.h>
-#include <linux/init.h>
-
-#include <asm/processor.h>
-#include <asm/sysreg.h>
-
-int read_current_timer(unsigned long *timer_value)
-{
- *timer_value = sysreg_read(COUNT);
- return 0;
-}
-
-void __delay(unsigned long loops)
-{
- unsigned bclock, now;
-
- bclock = sysreg_read(COUNT);
- do {
- now = sysreg_read(COUNT);
- } while ((now - bclock) < loops);
-}
-
-inline void __const_udelay(unsigned long xloops)
-{
- unsigned long long loops;
-
- asm("mulu.d %0, %1, %2"
- : "=r"(loops)
- : "r"(current_cpu_data.loops_per_jiffy * HZ), "r"(xloops));
- __delay(loops >> 32);
-}
-
-void __udelay(unsigned long usecs)
-{
- __const_udelay(usecs * 0x000010c7); /* 2**32 / 1000000 (rounded up) */
-}
-
-void __ndelay(unsigned long nsecs)
-{
- __const_udelay(nsecs * 0x00005); /* 2**32 / 1000000000 (rounded up) */
-}
+++ /dev/null
-/*
- * Copyright (C) 2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/linkage.h>
-
- .text
- /*
- * unsigned long find_first_zero_bit(const unsigned long *addr,
- * unsigned long size)
- */
-ENTRY(find_first_zero_bit)
- cp.w r11, 0
- reteq r11
- mov r9, r11
-1: ld.w r8, r12[0]
- com r8
- brne .L_found
- sub r12, -4
- sub r9, 32
- brgt 1b
- retal r11
-
- /*
- * unsigned long find_next_zero_bit(const unsigned long *addr,
- * unsigned long size,
- * unsigned long offset)
- */
-ENTRY(find_next_zero_bit)
- lsr r8, r10, 5
- sub r9, r11, r10
- retle r11
-
- lsl r8, 2
- add r12, r8
- andl r10, 31, COH
- breq 1f
-
- /* offset is not word-aligned. Handle the first (32 - r10) bits */
- ld.w r8, r12[0]
- com r8
- sub r12, -4
- lsr r8, r8, r10
- brne .L_found
-
- /* r9 = r9 - (32 - r10) = r9 + r10 - 32 */
- add r9, r10
- sub r9, 32
- retle r11
-
- /* Main loop. offset must be word-aligned */
-1: ld.w r8, r12[0]
- com r8
- brne .L_found
- sub r12, -4
- sub r9, 32
- brgt 1b
- retal r11
-
- /* Common return path for when a bit is actually found. */
-.L_found:
- brev r8
- clz r10, r8
- rsub r9, r11
- add r10, r9
-
- /* XXX: If we don't have to return exactly "size" when the bit
- is not found, we may drop this "min" thing */
- min r12, r11, r10
- retal r12
-
- /*
- * unsigned long find_first_bit(const unsigned long *addr,
- * unsigned long size)
- */
-ENTRY(find_first_bit)
- cp.w r11, 0
- reteq r11
- mov r9, r11
-1: ld.w r8, r12[0]
- cp.w r8, 0
- brne .L_found
- sub r12, -4
- sub r9, 32
- brgt 1b
- retal r11
-
- /*
- * unsigned long find_next_bit(const unsigned long *addr,
- * unsigned long size,
- * unsigned long offset)
- */
-ENTRY(find_next_bit)
- lsr r8, r10, 5
- sub r9, r11, r10
- retle r11
-
- lsl r8, 2
- add r12, r8
- andl r10, 31, COH
- breq 1f
-
- /* offset is not word-aligned. Handle the first (32 - r10) bits */
- ld.w r8, r12[0]
- sub r12, -4
- lsr r8, r8, r10
- brne .L_found
-
- /* r9 = r9 - (32 - r10) = r9 + r10 - 32 */
- add r9, r10
- sub r9, 32
- retle r11
-
- /* Main loop. offset must be word-aligned */
-1: ld.w r8, r12[0]
- cp.w r8, 0
- brne .L_found
- sub r12, -4
- sub r9, 32
- brgt 1b
- retal r11
-
-ENTRY(find_next_bit_le)
- lsr r8, r10, 5
- sub r9, r11, r10
- retle r11
-
- lsl r8, 2
- add r12, r8
- andl r10, 31, COH
- breq 1f
-
- /* offset is not word-aligned. Handle the first (32 - r10) bits */
- ldswp.w r8, r12[0]
- sub r12, -4
- lsr r8, r8, r10
- brne .L_found
-
- /* r9 = r9 - (32 - r10) = r9 + r10 - 32 */
- add r9, r10
- sub r9, 32
- retle r11
-
- /* Main loop. offset must be word-aligned */
-1: ldswp.w r8, r12[0]
- cp.w r8, 0
- brne .L_found
- sub r12, -4
- sub r9, 32
- brgt 1b
- retal r11
-
-ENTRY(find_next_zero_bit_le)
- lsr r8, r10, 5
- sub r9, r11, r10
- retle r11
-
- lsl r8, 2
- add r12, r8
- andl r10, 31, COH
- breq 1f
-
- /* offset is not word-aligned. Handle the first (32 - r10) bits */
- ldswp.w r8, r12[0]
- sub r12, -4
- com r8
- lsr r8, r8, r10
- brne .L_found
-
- /* r9 = r9 - (32 - r10) = r9 + r10 - 32 */
- add r9, r10
- sub r9, 32
- retle r11
-
- /* Main loop. offset must be word-aligned */
-1: ldswp.w r8, r12[0]
- com r8
- brne .L_found
- sub r12, -4
- sub r9, 32
- brgt 1b
- retal r11
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
- .text
-.Lnot_word_aligned:
-1: ld.ub r8, r12[0]
- sub r10, 1
- st.b r11++, r8
- reteq r12
- tst r11, r9
- brne 1b
-
- /* fall through */
-
- .global __raw_readsb
- .type __raw_readsb,@function
-__raw_readsb:
- cp.w r10, 0
- mov r9, 3
- reteq r12
-
- tst r11, r9
- brne .Lnot_word_aligned
-
- sub r10, 4
- brlt 2f
-
-1: ldins.b r8:t, r12[0]
- ldins.b r8:u, r12[0]
- ldins.b r8:l, r12[0]
- ldins.b r8:b, r12[0]
- st.w r11++, r8
- sub r10, 4
- brge 1b
-
-2: sub r10, -4
- reteq r12
-
-3: ld.ub r8, r12[0]
- sub r10, 1
- st.b r11++, r8
- brne 3b
-
- retal r12
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
- .global __raw_readsl
- .type __raw_readsl,@function
-__raw_readsl:
- cp.w r10, 0
- reteq r12
-
- /*
- * If r11 isn't properly aligned, we might get an exception on
- * some implementations. But there's not much we can do about it.
- */
-1: ld.w r8, r12[0]
- sub r10, 1
- st.w r11++, r8
- brne 1b
-
- retal r12
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-.Lnot_word_aligned:
- /*
- * Bad alignment will cause a hardware exception, which is as
- * good as anything. No need for us to check for proper alignment.
- */
- ld.uh r8, r12[0]
- sub r10, 1
- st.h r11++, r8
-
- /* fall through */
-
- .global __raw_readsw
- .type __raw_readsw,@function
-__raw_readsw:
- cp.w r10, 0
- reteq r12
- mov r9, 3
- tst r11, r9
- brne .Lnot_word_aligned
-
- sub r10, 2
- brlt 2f
-
-1: ldins.h r8:t, r12[0]
- ldins.h r8:b, r12[0]
- st.w r11++, r8
- sub r10, 2
- brge 1b
-
-2: sub r10, -2
- reteq r12
-
- ld.uh r8, r12[0]
- st.h r11++, r8
- retal r12
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
- .text
-.Lnot_word_aligned:
-1: ld.ub r8, r11++
- sub r10, 1
- st.b r12[0], r8
- reteq r12
- tst r11, r9
- brne 1b
-
- /* fall through */
-
- .global __raw_writesb
- .type __raw_writesb,@function
-__raw_writesb:
- cp.w r10, 0
- mov r9, 3
- reteq r12
-
- tst r11, r9
- brne .Lnot_word_aligned
-
- sub r10, 4
- brlt 2f
-
-1: ld.w r8, r11++
- bfextu r9, r8, 24, 8
- st.b r12[0], r9
- bfextu r9, r8, 16, 8
- st.b r12[0], r9
- bfextu r9, r8, 8, 8
- st.b r12[0], r9
- st.b r12[0], r8
- sub r10, 4
- brge 1b
-
-2: sub r10, -4
- reteq r12
-
-3: ld.ub r8, r11++
- sub r10, 1
- st.b r12[0], r8
- brne 3b
-
- retal r12
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
- .global __raw_writesl
- .type __raw_writesl,@function
-__raw_writesl:
- cp.w r10, 0
- reteq r12
-
-1: ld.w r8, r11++
- sub r10, 1
- st.w r12[0], r8
- brne 1b
-
- retal r12
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-.Lnot_word_aligned:
- ld.uh r8, r11++
- sub r10, 1
- st.h r12[0], r8
-
- .global __raw_writesw
- .type __raw_writesw,@function
-__raw_writesw:
- cp.w r10, 0
- mov r9, 3
- reteq r12
- tst r11, r9
- brne .Lnot_word_aligned
-
- sub r10, 2
- brlt 2f
-
-1: ld.w r8, r11++
- bfextu r9, r8, 16, 16
- st.h r12[0], r9
- st.h r12[0], r8
- sub r10, 2
- brge 1b
-
-2: sub r10, -2
- reteq r12
-
- ld.uh r8, r11++
- st.h r12[0], r8
- retal r12
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
- /*
- * void *memcpy(void *to, const void *from, unsigned long n)
- *
- * This implementation does word-aligned loads in the main loop,
- * possibly sacrificing alignment of stores.
- *
- * Hopefully, in most cases, both "to" and "from" will be
- * word-aligned to begin with.
- */
- .text
- .global memcpy
- .type memcpy, @function
-memcpy:
- mov r9, r11
- andl r9, 3, COH
- brne 1f
-
- /* At this point, "from" is word-aligned */
-2: mov r9, r12
-5: sub r10, 4
- brlt 4f
-
-3: ld.w r8, r11++
- sub r10, 4
- st.w r12++, r8
- brge 3b
-
-4: neg r10
- reteq r9
-
- /* Handle unaligned count */
- lsl r10, 2
- add pc, pc, r10
- ld.ub r8, r11++
- st.b r12++, r8
- ld.ub r8, r11++
- st.b r12++, r8
- ld.ub r8, r11++
- st.b r12++, r8
- retal r9
-
- /* Handle unaligned "from" pointer */
-1: sub r10, 4
- movlt r9, r12
- brlt 4b
- add r10, r9
- lsl r9, 2
- add pc, pc, r9
- ld.ub r8, r11++
- st.b r12++, r8
- ld.ub r8, r11++
- st.b r12++, r8
- ld.ub r8, r11++
- st.b r12++, r8
- mov r8, r12
- add pc, pc, r9
- sub r8, 1
- nop
- sub r8, 1
- nop
- sub r8, 1
- nop
- mov r9, r8
- rjmp 5b
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * Based on linux/arch/arm/lib/memset.S
- * Copyright (C) 1995-2000 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * ASM optimised string functions
- */
-#include <asm/asm.h>
-
- /*
- * r12: void *b
- * r11: int c
- * r10: size_t len
- *
- * Returns b in r12
- */
- .text
- .global memset
- .type memset, @function
- .align 5
-memset:
- mov r9, r12
- mov r8, r12
- or r11, r11, r11 << 8
- andl r9, 3, COH
- brne 1f
-
-2: or r11, r11, r11 << 16
- sub r10, 4
- brlt 5f
-
- /* Let's do some real work */
-4: st.w r8++, r11
- sub r10, 4
- brge 4b
-
- /*
- * When we get here, we've got less than 4 bytes to set. r10
- * might be negative.
- */
-5: sub r10, -4
- reteq r12
-
- /* Fastpath ends here, exactly 32 bytes from memset */
-
- /* Handle unaligned count or pointer */
- bld r10, 1
- brcc 6f
- st.b r8++, r11
- st.b r8++, r11
- bld r10, 0
- retcc r12
-6: st.b r8++, r11
- retal r12
-
- /* Handle unaligned pointer */
-1: sub r10, 4
- brlt 5b
- add r10, r9
- lsl r9, 1
- add pc, r9
- st.b r8++, r11
- st.b r8++, r11
- st.b r8++, r11
- rjmp 2b
-
- .size memset, . - memset
+++ /dev/null
-/*
- * Copy to/from userspace with optional address space checking.
- *
- * Copyright 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/errno.h>
-
-#include <asm/page.h>
-#include <asm/thread_info.h>
-#include <asm/asm.h>
-
- /*
- * long strncpy_from_user(char *dst, const char *src, long count)
- *
- * On success, returns the length of the string, not including
- * the terminating NUL.
- *
- * If the string is longer than count, returns count
- *
- * If userspace access fails, returns -EFAULT
- */
- .text
- .align 1
- .global strncpy_from_user
- .type strncpy_from_user, "function"
-strncpy_from_user:
- mov r9, -EFAULT
- branch_if_kernel r8, __strncpy_from_user
- ret_if_privileged r8, r11, r10, r9
-
- .global __strncpy_from_user
- .type __strncpy_from_user, "function"
-__strncpy_from_user:
- cp.w r10, 0
- reteq 0
-
- mov r9, r10
-
-1: ld.ub r8, r11++
- st.b r12++, r8
- cp.w r8, 0
- breq 2f
- sub r9, 1
- brne 1b
-
-2: sub r10, r9
- retal r10
-
- .section .fixup, "ax"
- .align 1
-3: mov r12, -EFAULT
- retal r12
-
- .section __ex_table, "a"
- .align 2
- .long 1b, 3b
+++ /dev/null
-/*
- * Copy to/from userspace with optional address space checking.
- *
- * Copyright 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <asm/page.h>
-#include <asm/thread_info.h>
-#include <asm/processor.h>
-#include <asm/asm.h>
-
- .text
- .align 1
- .global strnlen_user
- .type strnlen_user, "function"
-strnlen_user:
- branch_if_kernel r8, __strnlen_user
- sub r8, r11, 1
- add r8, r12
- retcs 0
- brmi adjust_length /* do a closer inspection */
-
- .global __strnlen_user
- .type __strnlen_user, "function"
-__strnlen_user:
- mov r10, r12
-
-10: ld.ub r8, r12++
- cp.w r8, 0
- breq 2f
- sub r11, 1
- brne 10b
-
- sub r12, -1
-2: sub r12, r10
- retal r12
-
-
- .type adjust_length, "function"
-adjust_length:
- cp.w r12, 0 /* addr must always be < TASK_SIZE */
- retmi 0
-
- pushm lr
- lddpc lr, _task_size
- sub r11, lr, r12
- mov r9, r11
- call __strnlen_user
- cp.w r12, r9
- brgt 1f
- popm pc
-1: popm pc, r12=0
-
- .align 2
-_task_size:
- .long TASK_SIZE
-
- .section .fixup, "ax"
- .align 1
-19: retal 0
-
- .section __ex_table, "a"
- .align 2
- .long 10b, 19b
+++ /dev/null
-if PLATFORM_AT32AP
-
-menu "Atmel AVR32 AP options"
-
-choice
- prompt "AT32AP700x static memory bus width"
- depends on CPU_AT32AP700X
- default AP700X_16_BIT_SMC
- help
- Define the width of the AP7000 external static memory interface.
- This is used to determine how to mangle the address and/or data
- when doing little-endian port access.
-
- The current code can only support a single external memory bus
- width for all chip selects, excluding the flash (which is using
- raw access and is thus not affected by any of this.)
-
-config AP700X_32_BIT_SMC
- bool "32 bit"
-
-config AP700X_16_BIT_SMC
- bool "16 bit"
-
-config AP700X_8_BIT_SMC
- bool "8 bit"
-
-endchoice
-
-endmenu
-
-endif # PLATFORM_AT32AP
+++ /dev/null
-obj-y += pdc.o clock.o intc.o extint.o pio.o hsmc.o
-obj-y += hmatrix.o
-obj-$(CONFIG_CPU_AT32AP700X) += at32ap700x.o pm-at32ap700x.o
-obj-$(CONFIG_PM) += pm.o
-
-ifeq ($(CONFIG_PM_DEBUG),y)
-CFLAGS_pm.o += -DDEBUG
-endif
+++ /dev/null
-/*
- * Copyright (C) 2005-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/clk.h>
-#include <linux/delay.h>
-#include <linux/platform_data/dma-dw.h>
-#include <linux/fb.h>
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/dma-mapping.h>
-#include <linux/slab.h>
-#include <linux/gpio.h>
-#include <linux/spi/spi.h>
-#include <linux/usb/atmel_usba_udc.h>
-
-#include <linux/atmel-mci.h>
-
-#include <asm/io.h>
-#include <asm/irq.h>
-
-#include <mach/at32ap700x.h>
-#include <mach/board.h>
-#include <mach/hmatrix.h>
-#include <mach/portmux.h>
-#include <mach/sram.h>
-
-#include <sound/atmel-abdac.h>
-#include <sound/atmel-ac97c.h>
-
-#include <video/atmel_lcdc.h>
-
-#include "clock.h"
-#include "pio.h"
-#include "pm.h"
-
-
-#define PBMEM(base) \
- { \
- .start = base, \
- .end = base + 0x3ff, \
- .flags = IORESOURCE_MEM, \
- }
-#define IRQ(num) \
- { \
- .start = num, \
- .end = num, \
- .flags = IORESOURCE_IRQ, \
- }
-#define NAMED_IRQ(num, _name) \
- { \
- .start = num, \
- .end = num, \
- .name = _name, \
- .flags = IORESOURCE_IRQ, \
- }
-
-/* REVISIT these assume *every* device supports DMA, but several
- * don't ... tc, smc, pio, rtc, watchdog, pwm, ps2, and more.
- */
-#define DEFINE_DEV(_name, _id) \
-static u64 _name##_id##_dma_mask = DMA_BIT_MASK(32); \
-static struct platform_device _name##_id##_device = { \
- .name = #_name, \
- .id = _id, \
- .dev = { \
- .dma_mask = &_name##_id##_dma_mask, \
- .coherent_dma_mask = DMA_BIT_MASK(32), \
- }, \
- .resource = _name##_id##_resource, \
- .num_resources = ARRAY_SIZE(_name##_id##_resource), \
-}
-#define DEFINE_DEV_DATA(_name, _id) \
-static u64 _name##_id##_dma_mask = DMA_BIT_MASK(32); \
-static struct platform_device _name##_id##_device = { \
- .name = #_name, \
- .id = _id, \
- .dev = { \
- .dma_mask = &_name##_id##_dma_mask, \
- .platform_data = &_name##_id##_data, \
- .coherent_dma_mask = DMA_BIT_MASK(32), \
- }, \
- .resource = _name##_id##_resource, \
- .num_resources = ARRAY_SIZE(_name##_id##_resource), \
-}
-
-#define select_peripheral(port, pin_mask, periph, flags) \
- at32_select_periph(GPIO_##port##_BASE, pin_mask, \
- GPIO_##periph, flags)
-
-#define DEV_CLK(_name, devname, bus, _index) \
-static struct clk devname##_##_name = { \
- .name = #_name, \
- .dev = &devname##_device.dev, \
- .parent = &bus##_clk, \
- .mode = bus##_clk_mode, \
- .get_rate = bus##_clk_get_rate, \
- .index = _index, \
-}
-
-static DEFINE_SPINLOCK(pm_lock);
-
-static struct clk osc0;
-static struct clk osc1;
-
-static unsigned long osc_get_rate(struct clk *clk)
-{
- return at32_board_osc_rates[clk->index];
-}
-
-static unsigned long pll_get_rate(struct clk *clk, unsigned long control)
-{
- unsigned long div, mul, rate;
-
- div = PM_BFEXT(PLLDIV, control) + 1;
- mul = PM_BFEXT(PLLMUL, control) + 1;
-
- rate = clk->parent->get_rate(clk->parent);
- rate = (rate + div / 2) / div;
- rate *= mul;
-
- return rate;
-}
-
-static long pll_set_rate(struct clk *clk, unsigned long rate,
- u32 *pll_ctrl)
-{
- unsigned long mul;
- unsigned long mul_best_fit = 0;
- unsigned long div;
- unsigned long div_min;
- unsigned long div_max;
- unsigned long div_best_fit = 0;
- unsigned long base;
- unsigned long pll_in;
- unsigned long actual = 0;
- unsigned long rate_error;
- unsigned long rate_error_prev = ~0UL;
- u32 ctrl;
-
- /* Rate must be between 80 MHz and 200 Mhz. */
- if (rate < 80000000UL || rate > 200000000UL)
- return -EINVAL;
-
- ctrl = PM_BF(PLLOPT, 4);
- base = clk->parent->get_rate(clk->parent);
-
- /* PLL input frequency must be between 6 MHz and 32 MHz. */
- div_min = DIV_ROUND_UP(base, 32000000UL);
- div_max = base / 6000000UL;
-
- if (div_max < div_min)
- return -EINVAL;
-
- for (div = div_min; div <= div_max; div++) {
- pll_in = (base + div / 2) / div;
- mul = (rate + pll_in / 2) / pll_in;
-
- if (mul == 0)
- continue;
-
- actual = pll_in * mul;
- rate_error = abs(actual - rate);
-
- if (rate_error < rate_error_prev) {
- mul_best_fit = mul;
- div_best_fit = div;
- rate_error_prev = rate_error;
- }
-
- if (rate_error == 0)
- break;
- }
-
- if (div_best_fit == 0)
- return -EINVAL;
-
- ctrl |= PM_BF(PLLMUL, mul_best_fit - 1);
- ctrl |= PM_BF(PLLDIV, div_best_fit - 1);
- ctrl |= PM_BF(PLLCOUNT, 16);
-
- if (clk->parent == &osc1)
- ctrl |= PM_BIT(PLLOSC);
-
- *pll_ctrl = ctrl;
-
- return actual;
-}
-
-static unsigned long pll0_get_rate(struct clk *clk)
-{
- u32 control;
-
- control = pm_readl(PLL0);
-
- return pll_get_rate(clk, control);
-}
-
-static void pll1_mode(struct clk *clk, int enabled)
-{
- unsigned long timeout;
- u32 status;
- u32 ctrl;
-
- ctrl = pm_readl(PLL1);
-
- if (enabled) {
- if (!PM_BFEXT(PLLMUL, ctrl) && !PM_BFEXT(PLLDIV, ctrl)) {
- pr_debug("clk %s: failed to enable, rate not set\n",
- clk->name);
- return;
- }
-
- ctrl |= PM_BIT(PLLEN);
- pm_writel(PLL1, ctrl);
-
- /* Wait for PLL lock. */
- for (timeout = 10000; timeout; timeout--) {
- status = pm_readl(ISR);
- if (status & PM_BIT(LOCK1))
- break;
- udelay(10);
- }
-
- if (!(status & PM_BIT(LOCK1)))
- printk(KERN_ERR "clk %s: timeout waiting for lock\n",
- clk->name);
- } else {
- ctrl &= ~PM_BIT(PLLEN);
- pm_writel(PLL1, ctrl);
- }
-}
-
-static unsigned long pll1_get_rate(struct clk *clk)
-{
- u32 control;
-
- control = pm_readl(PLL1);
-
- return pll_get_rate(clk, control);
-}
-
-static long pll1_set_rate(struct clk *clk, unsigned long rate, int apply)
-{
- u32 ctrl = 0;
- unsigned long actual_rate;
-
- actual_rate = pll_set_rate(clk, rate, &ctrl);
-
- if (apply) {
- if (actual_rate != rate)
- return -EINVAL;
- if (clk->users > 0)
- return -EBUSY;
- pr_debug(KERN_INFO "clk %s: new rate %lu (actual rate %lu)\n",
- clk->name, rate, actual_rate);
- pm_writel(PLL1, ctrl);
- }
-
- return actual_rate;
-}
-
-static int pll1_set_parent(struct clk *clk, struct clk *parent)
-{
- u32 ctrl;
-
- if (clk->users > 0)
- return -EBUSY;
-
- ctrl = pm_readl(PLL1);
- WARN_ON(ctrl & PM_BIT(PLLEN));
-
- if (parent == &osc0)
- ctrl &= ~PM_BIT(PLLOSC);
- else if (parent == &osc1)
- ctrl |= PM_BIT(PLLOSC);
- else
- return -EINVAL;
-
- pm_writel(PLL1, ctrl);
- clk->parent = parent;
-
- return 0;
-}
-
-/*
- * The AT32AP7000 has five primary clock sources: One 32kHz
- * oscillator, two crystal oscillators and two PLLs.
- */
-static struct clk osc32k = {
- .name = "osc32k",
- .get_rate = osc_get_rate,
- .users = 1,
- .index = 0,
-};
-static struct clk osc0 = {
- .name = "osc0",
- .get_rate = osc_get_rate,
- .users = 1,
- .index = 1,
-};
-static struct clk osc1 = {
- .name = "osc1",
- .get_rate = osc_get_rate,
- .index = 2,
-};
-static struct clk pll0 = {
- .name = "pll0",
- .get_rate = pll0_get_rate,
- .parent = &osc0,
-};
-static struct clk pll1 = {
- .name = "pll1",
- .mode = pll1_mode,
- .get_rate = pll1_get_rate,
- .set_rate = pll1_set_rate,
- .set_parent = pll1_set_parent,
- .parent = &osc0,
-};
-
-/*
- * The main clock can be either osc0 or pll0. The boot loader may
- * have chosen one for us, so we don't really know which one until we
- * have a look at the SM.
- */
-static struct clk *main_clock;
-
-/*
- * Synchronous clocks are generated from the main clock. The clocks
- * must satisfy the constraint
- * fCPU >= fHSB >= fPB
- * i.e. each clock must not be faster than its parent.
- */
-static unsigned long bus_clk_get_rate(struct clk *clk, unsigned int shift)
-{
- return main_clock->get_rate(main_clock) >> shift;
-};
-
-static void cpu_clk_mode(struct clk *clk, int enabled)
-{
- unsigned long flags;
- u32 mask;
-
- spin_lock_irqsave(&pm_lock, flags);
- mask = pm_readl(CPU_MASK);
- if (enabled)
- mask |= 1 << clk->index;
- else
- mask &= ~(1 << clk->index);
- pm_writel(CPU_MASK, mask);
- spin_unlock_irqrestore(&pm_lock, flags);
-}
-
-static unsigned long cpu_clk_get_rate(struct clk *clk)
-{
- unsigned long cksel, shift = 0;
-
- cksel = pm_readl(CKSEL);
- if (cksel & PM_BIT(CPUDIV))
- shift = PM_BFEXT(CPUSEL, cksel) + 1;
-
- return bus_clk_get_rate(clk, shift);
-}
-
-static long cpu_clk_set_rate(struct clk *clk, unsigned long rate, int apply)
-{
- u32 control;
- unsigned long parent_rate, child_div, actual_rate, div;
-
- parent_rate = clk->parent->get_rate(clk->parent);
- control = pm_readl(CKSEL);
-
- if (control & PM_BIT(HSBDIV))
- child_div = 1 << (PM_BFEXT(HSBSEL, control) + 1);
- else
- child_div = 1;
-
- if (rate > 3 * (parent_rate / 4) || child_div == 1) {
- actual_rate = parent_rate;
- control &= ~PM_BIT(CPUDIV);
- } else {
- unsigned int cpusel;
- div = (parent_rate + rate / 2) / rate;
- if (div > child_div)
- div = child_div;
- cpusel = (div > 1) ? (fls(div) - 2) : 0;
- control = PM_BIT(CPUDIV) | PM_BFINS(CPUSEL, cpusel, control);
- actual_rate = parent_rate / (1 << (cpusel + 1));
- }
-
- pr_debug("clk %s: new rate %lu (actual rate %lu)\n",
- clk->name, rate, actual_rate);
-
- if (apply)
- pm_writel(CKSEL, control);
-
- return actual_rate;
-}
-
-static void hsb_clk_mode(struct clk *clk, int enabled)
-{
- unsigned long flags;
- u32 mask;
-
- spin_lock_irqsave(&pm_lock, flags);
- mask = pm_readl(HSB_MASK);
- if (enabled)
- mask |= 1 << clk->index;
- else
- mask &= ~(1 << clk->index);
- pm_writel(HSB_MASK, mask);
- spin_unlock_irqrestore(&pm_lock, flags);
-}
-
-static unsigned long hsb_clk_get_rate(struct clk *clk)
-{
- unsigned long cksel, shift = 0;
-
- cksel = pm_readl(CKSEL);
- if (cksel & PM_BIT(HSBDIV))
- shift = PM_BFEXT(HSBSEL, cksel) + 1;
-
- return bus_clk_get_rate(clk, shift);
-}
-
-void pba_clk_mode(struct clk *clk, int enabled)
-{
- unsigned long flags;
- u32 mask;
-
- spin_lock_irqsave(&pm_lock, flags);
- mask = pm_readl(PBA_MASK);
- if (enabled)
- mask |= 1 << clk->index;
- else
- mask &= ~(1 << clk->index);
- pm_writel(PBA_MASK, mask);
- spin_unlock_irqrestore(&pm_lock, flags);
-}
-
-unsigned long pba_clk_get_rate(struct clk *clk)
-{
- unsigned long cksel, shift = 0;
-
- cksel = pm_readl(CKSEL);
- if (cksel & PM_BIT(PBADIV))
- shift = PM_BFEXT(PBASEL, cksel) + 1;
-
- return bus_clk_get_rate(clk, shift);
-}
-
-static void pbb_clk_mode(struct clk *clk, int enabled)
-{
- unsigned long flags;
- u32 mask;
-
- spin_lock_irqsave(&pm_lock, flags);
- mask = pm_readl(PBB_MASK);
- if (enabled)
- mask |= 1 << clk->index;
- else
- mask &= ~(1 << clk->index);
- pm_writel(PBB_MASK, mask);
- spin_unlock_irqrestore(&pm_lock, flags);
-}
-
-static unsigned long pbb_clk_get_rate(struct clk *clk)
-{
- unsigned long cksel, shift = 0;
-
- cksel = pm_readl(CKSEL);
- if (cksel & PM_BIT(PBBDIV))
- shift = PM_BFEXT(PBBSEL, cksel) + 1;
-
- return bus_clk_get_rate(clk, shift);
-}
-
-static struct clk cpu_clk = {
- .name = "cpu",
- .get_rate = cpu_clk_get_rate,
- .set_rate = cpu_clk_set_rate,
- .users = 1,
-};
-static struct clk hsb_clk = {
- .name = "hsb",
- .parent = &cpu_clk,
- .get_rate = hsb_clk_get_rate,
-};
-static struct clk pba_clk = {
- .name = "pba",
- .parent = &hsb_clk,
- .mode = hsb_clk_mode,
- .get_rate = pba_clk_get_rate,
- .index = 1,
-};
-static struct clk pbb_clk = {
- .name = "pbb",
- .parent = &hsb_clk,
- .mode = hsb_clk_mode,
- .get_rate = pbb_clk_get_rate,
- .users = 1,
- .index = 2,
-};
-
-/* --------------------------------------------------------------------
- * Generic Clock operations
- * -------------------------------------------------------------------- */
-
-static void genclk_mode(struct clk *clk, int enabled)
-{
- u32 control;
-
- control = pm_readl(GCCTRL(clk->index));
- if (enabled)
- control |= PM_BIT(CEN);
- else
- control &= ~PM_BIT(CEN);
- pm_writel(GCCTRL(clk->index), control);
-}
-
-static unsigned long genclk_get_rate(struct clk *clk)
-{
- u32 control;
- unsigned long div = 1;
-
- control = pm_readl(GCCTRL(clk->index));
- if (control & PM_BIT(DIVEN))
- div = 2 * (PM_BFEXT(DIV, control) + 1);
-
- return clk->parent->get_rate(clk->parent) / div;
-}
-
-static long genclk_set_rate(struct clk *clk, unsigned long rate, int apply)
-{
- u32 control;
- unsigned long parent_rate, actual_rate, div;
-
- parent_rate = clk->parent->get_rate(clk->parent);
- control = pm_readl(GCCTRL(clk->index));
-
- if (rate > 3 * parent_rate / 4) {
- actual_rate = parent_rate;
- control &= ~PM_BIT(DIVEN);
- } else {
- div = (parent_rate + rate) / (2 * rate) - 1;
- control = PM_BFINS(DIV, div, control) | PM_BIT(DIVEN);
- actual_rate = parent_rate / (2 * (div + 1));
- }
-
- dev_dbg(clk->dev, "clk %s: new rate %lu (actual rate %lu)\n",
- clk->name, rate, actual_rate);
-
- if (apply)
- pm_writel(GCCTRL(clk->index), control);
-
- return actual_rate;
-}
-
-int genclk_set_parent(struct clk *clk, struct clk *parent)
-{
- u32 control;
-
- dev_dbg(clk->dev, "clk %s: new parent %s (was %s)\n",
- clk->name, parent->name, clk->parent->name);
-
- control = pm_readl(GCCTRL(clk->index));
-
- if (parent == &osc1 || parent == &pll1)
- control |= PM_BIT(OSCSEL);
- else if (parent == &osc0 || parent == &pll0)
- control &= ~PM_BIT(OSCSEL);
- else
- return -EINVAL;
-
- if (parent == &pll0 || parent == &pll1)
- control |= PM_BIT(PLLSEL);
- else
- control &= ~PM_BIT(PLLSEL);
-
- pm_writel(GCCTRL(clk->index), control);
- clk->parent = parent;
-
- return 0;
-}
-
-static void __init genclk_init_parent(struct clk *clk)
-{
- u32 control;
- struct clk *parent;
-
- BUG_ON(clk->index > 7);
-
- control = pm_readl(GCCTRL(clk->index));
- if (control & PM_BIT(OSCSEL))
- parent = (control & PM_BIT(PLLSEL)) ? &pll1 : &osc1;
- else
- parent = (control & PM_BIT(PLLSEL)) ? &pll0 : &osc0;
-
- clk->parent = parent;
-}
-
-static struct resource dw_dmac0_resource[] = {
- PBMEM(0xff200000),
- IRQ(2),
-};
-DEFINE_DEV(dw_dmac, 0);
-DEV_CLK(hclk, dw_dmac0, hsb, 10);
-
-/* --------------------------------------------------------------------
- * System peripherals
- * -------------------------------------------------------------------- */
-static struct resource at32_pm0_resource[] = {
- {
- .start = 0xfff00000,
- .end = 0xfff0007f,
- .flags = IORESOURCE_MEM,
- },
- IRQ(20),
-};
-
-static struct resource at32ap700x_rtc0_resource[] = {
- {
- .start = 0xfff00080,
- .end = 0xfff000af,
- .flags = IORESOURCE_MEM,
- },
- IRQ(21),
-};
-
-static struct resource at32_wdt0_resource[] = {
- {
- .start = 0xfff000b0,
- .end = 0xfff000cf,
- .flags = IORESOURCE_MEM,
- },
-};
-
-static struct resource at32_eic0_resource[] = {
- {
- .start = 0xfff00100,
- .end = 0xfff0013f,
- .flags = IORESOURCE_MEM,
- },
- IRQ(19),
-};
-
-DEFINE_DEV(at32_pm, 0);
-DEFINE_DEV(at32ap700x_rtc, 0);
-DEFINE_DEV(at32_wdt, 0);
-DEFINE_DEV(at32_eic, 0);
-
-/*
- * Peripheral clock for PM, RTC, WDT and EIC. PM will ensure that this
- * is always running.
- */
-static struct clk at32_pm_pclk = {
- .name = "pclk",
- .dev = &at32_pm0_device.dev,
- .parent = &pbb_clk,
- .mode = pbb_clk_mode,
- .get_rate = pbb_clk_get_rate,
- .users = 1,
- .index = 0,
-};
-
-static struct resource intc0_resource[] = {
- PBMEM(0xfff00400),
-};
-struct platform_device at32_intc0_device = {
- .name = "intc",
- .id = 0,
- .resource = intc0_resource,
- .num_resources = ARRAY_SIZE(intc0_resource),
-};
-DEV_CLK(pclk, at32_intc0, pbb, 1);
-
-static struct clk ebi_clk = {
- .name = "ebi",
- .parent = &hsb_clk,
- .mode = hsb_clk_mode,
- .get_rate = hsb_clk_get_rate,
- .users = 1,
-};
-static struct clk hramc_clk = {
- .name = "hramc",
- .parent = &hsb_clk,
- .mode = hsb_clk_mode,
- .get_rate = hsb_clk_get_rate,
- .users = 1,
- .index = 3,
-};
-static struct clk sdramc_clk = {
- .name = "sdramc_clk",
- .parent = &pbb_clk,
- .mode = pbb_clk_mode,
- .get_rate = pbb_clk_get_rate,
- .users = 1,
- .index = 14,
-};
-
-static struct resource smc0_resource[] = {
- PBMEM(0xfff03400),
-};
-DEFINE_DEV(smc, 0);
-DEV_CLK(pclk, smc0, pbb, 13);
-DEV_CLK(mck, smc0, hsb, 0);
-
-static struct platform_device pdc_device = {
- .name = "pdc",
- .id = 0,
-};
-DEV_CLK(hclk, pdc, hsb, 4);
-DEV_CLK(pclk, pdc, pba, 16);
-
-static struct clk pico_clk = {
- .name = "pico",
- .parent = &cpu_clk,
- .mode = cpu_clk_mode,
- .get_rate = cpu_clk_get_rate,
- .users = 1,
-};
-
-/* --------------------------------------------------------------------
- * HMATRIX
- * -------------------------------------------------------------------- */
-
-struct clk at32_hmatrix_clk = {
- .name = "hmatrix_clk",
- .parent = &pbb_clk,
- .mode = pbb_clk_mode,
- .get_rate = pbb_clk_get_rate,
- .index = 2,
- .users = 1,
-};
-
-/*
- * Set bits in the HMATRIX Special Function Register (SFR) used by the
- * External Bus Interface (EBI). This can be used to enable special
- * features like CompactFlash support, NAND Flash support, etc. on
- * certain chipselects.
- */
-static inline void set_ebi_sfr_bits(u32 mask)
-{
- hmatrix_sfr_set_bits(HMATRIX_SLAVE_EBI, mask);
-}
-
-/* --------------------------------------------------------------------
- * Timer/Counter (TC)
- * -------------------------------------------------------------------- */
-
-static struct resource at32_tcb0_resource[] = {
- PBMEM(0xfff00c00),
- IRQ(22),
-};
-static struct platform_device at32_tcb0_device = {
- .name = "atmel_tcb",
- .id = 0,
- .resource = at32_tcb0_resource,
- .num_resources = ARRAY_SIZE(at32_tcb0_resource),
-};
-DEV_CLK(t0_clk, at32_tcb0, pbb, 3);
-
-static struct resource at32_tcb1_resource[] = {
- PBMEM(0xfff01000),
- IRQ(23),
-};
-static struct platform_device at32_tcb1_device = {
- .name = "atmel_tcb",
- .id = 1,
- .resource = at32_tcb1_resource,
- .num_resources = ARRAY_SIZE(at32_tcb1_resource),
-};
-DEV_CLK(t0_clk, at32_tcb1, pbb, 4);
-
-/* --------------------------------------------------------------------
- * PIO
- * -------------------------------------------------------------------- */
-
-static struct resource pio0_resource[] = {
- PBMEM(0xffe02800),
- IRQ(13),
-};
-DEFINE_DEV(pio, 0);
-DEV_CLK(mck, pio0, pba, 10);
-
-static struct resource pio1_resource[] = {
- PBMEM(0xffe02c00),
- IRQ(14),
-};
-DEFINE_DEV(pio, 1);
-DEV_CLK(mck, pio1, pba, 11);
-
-static struct resource pio2_resource[] = {
- PBMEM(0xffe03000),
- IRQ(15),
-};
-DEFINE_DEV(pio, 2);
-DEV_CLK(mck, pio2, pba, 12);
-
-static struct resource pio3_resource[] = {
- PBMEM(0xffe03400),
- IRQ(16),
-};
-DEFINE_DEV(pio, 3);
-DEV_CLK(mck, pio3, pba, 13);
-
-static struct resource pio4_resource[] = {
- PBMEM(0xffe03800),
- IRQ(17),
-};
-DEFINE_DEV(pio, 4);
-DEV_CLK(mck, pio4, pba, 14);
-
-static int __init system_device_init(void)
-{
- platform_device_register(&at32_pm0_device);
- platform_device_register(&at32_intc0_device);
- platform_device_register(&at32ap700x_rtc0_device);
- platform_device_register(&at32_wdt0_device);
- platform_device_register(&at32_eic0_device);
- platform_device_register(&smc0_device);
- platform_device_register(&pdc_device);
- platform_device_register(&dw_dmac0_device);
-
- platform_device_register(&at32_tcb0_device);
- platform_device_register(&at32_tcb1_device);
-
- platform_device_register(&pio0_device);
- platform_device_register(&pio1_device);
- platform_device_register(&pio2_device);
- platform_device_register(&pio3_device);
- platform_device_register(&pio4_device);
-
- return 0;
-}
-core_initcall(system_device_init);
-
-/* --------------------------------------------------------------------
- * PSIF
- * -------------------------------------------------------------------- */
-static struct resource atmel_psif0_resource[] __initdata = {
- {
- .start = 0xffe03c00,
- .end = 0xffe03cff,
- .flags = IORESOURCE_MEM,
- },
- IRQ(18),
-};
-static struct clk atmel_psif0_pclk = {
- .name = "pclk",
- .parent = &pba_clk,
- .mode = pba_clk_mode,
- .get_rate = pba_clk_get_rate,
- .index = 15,
-};
-
-static struct resource atmel_psif1_resource[] __initdata = {
- {
- .start = 0xffe03d00,
- .end = 0xffe03dff,
- .flags = IORESOURCE_MEM,
- },
- IRQ(18),
-};
-static struct clk atmel_psif1_pclk = {
- .name = "pclk",
- .parent = &pba_clk,
- .mode = pba_clk_mode,
- .get_rate = pba_clk_get_rate,
- .index = 15,
-};
-
-struct platform_device *__init at32_add_device_psif(unsigned int id)
-{
- struct platform_device *pdev;
- u32 pin_mask;
-
- if (!(id == 0 || id == 1))
- return NULL;
-
- pdev = platform_device_alloc("atmel_psif", id);
- if (!pdev)
- return NULL;
-
- switch (id) {
- case 0:
- pin_mask = (1 << 8) | (1 << 9); /* CLOCK & DATA */
-
- if (platform_device_add_resources(pdev, atmel_psif0_resource,
- ARRAY_SIZE(atmel_psif0_resource)))
- goto err_add_resources;
- atmel_psif0_pclk.dev = &pdev->dev;
- select_peripheral(PIOA, pin_mask, PERIPH_A, 0);
- break;
- case 1:
- pin_mask = (1 << 11) | (1 << 12); /* CLOCK & DATA */
-
- if (platform_device_add_resources(pdev, atmel_psif1_resource,
- ARRAY_SIZE(atmel_psif1_resource)))
- goto err_add_resources;
- atmel_psif1_pclk.dev = &pdev->dev;
- select_peripheral(PIOB, pin_mask, PERIPH_A, 0);
- break;
- default:
- return NULL;
- }
-
- platform_device_add(pdev);
- return pdev;
-
-err_add_resources:
- platform_device_put(pdev);
- return NULL;
-}
-
-/* --------------------------------------------------------------------
- * USART
- * -------------------------------------------------------------------- */
-
-static struct atmel_uart_data atmel_usart0_data = {
- .use_dma_tx = 1,
- .use_dma_rx = 1,
-};
-static struct resource atmel_usart0_resource[] = {
- PBMEM(0xffe00c00),
- IRQ(6),
-};
-DEFINE_DEV_DATA(atmel_usart, 0);
-DEV_CLK(usart, atmel_usart0, pba, 3);
-
-static struct atmel_uart_data atmel_usart1_data = {
- .use_dma_tx = 1,
- .use_dma_rx = 1,
-};
-static struct resource atmel_usart1_resource[] = {
- PBMEM(0xffe01000),
- IRQ(7),
-};
-DEFINE_DEV_DATA(atmel_usart, 1);
-DEV_CLK(usart, atmel_usart1, pba, 4);
-
-static struct atmel_uart_data atmel_usart2_data = {
- .use_dma_tx = 1,
- .use_dma_rx = 1,
-};
-static struct resource atmel_usart2_resource[] = {
- PBMEM(0xffe01400),
- IRQ(8),
-};
-DEFINE_DEV_DATA(atmel_usart, 2);
-DEV_CLK(usart, atmel_usart2, pba, 5);
-
-static struct atmel_uart_data atmel_usart3_data = {
- .use_dma_tx = 1,
- .use_dma_rx = 1,
-};
-static struct resource atmel_usart3_resource[] = {
- PBMEM(0xffe01800),
- IRQ(9),
-};
-DEFINE_DEV_DATA(atmel_usart, 3);
-DEV_CLK(usart, atmel_usart3, pba, 6);
-
-static inline void configure_usart0_pins(int flags)
-{
- u32 pin_mask = (1 << 8) | (1 << 9); /* RXD & TXD */
- if (flags & ATMEL_USART_RTS) pin_mask |= (1 << 6);
- if (flags & ATMEL_USART_CTS) pin_mask |= (1 << 7);
- if (flags & ATMEL_USART_CLK) pin_mask |= (1 << 10);
-
- select_peripheral(PIOA, pin_mask, PERIPH_B, AT32_GPIOF_PULLUP);
-}
-
-static inline void configure_usart1_pins(int flags)
-{
- u32 pin_mask = (1 << 17) | (1 << 18); /* RXD & TXD */
- if (flags & ATMEL_USART_RTS) pin_mask |= (1 << 19);
- if (flags & ATMEL_USART_CTS) pin_mask |= (1 << 20);
- if (flags & ATMEL_USART_CLK) pin_mask |= (1 << 16);
-
- select_peripheral(PIOA, pin_mask, PERIPH_A, AT32_GPIOF_PULLUP);
-}
-
-static inline void configure_usart2_pins(int flags)
-{
- u32 pin_mask = (1 << 26) | (1 << 27); /* RXD & TXD */
- if (flags & ATMEL_USART_RTS) pin_mask |= (1 << 30);
- if (flags & ATMEL_USART_CTS) pin_mask |= (1 << 29);
- if (flags & ATMEL_USART_CLK) pin_mask |= (1 << 28);
-
- select_peripheral(PIOB, pin_mask, PERIPH_B, AT32_GPIOF_PULLUP);
-}
-
-static inline void configure_usart3_pins(int flags)
-{
- u32 pin_mask = (1 << 18) | (1 << 17); /* RXD & TXD */
- if (flags & ATMEL_USART_RTS) pin_mask |= (1 << 16);
- if (flags & ATMEL_USART_CTS) pin_mask |= (1 << 15);
- if (flags & ATMEL_USART_CLK) pin_mask |= (1 << 19);
-
- select_peripheral(PIOB, pin_mask, PERIPH_B, AT32_GPIOF_PULLUP);
-}
-
-static struct platform_device *__initdata at32_usarts[4];
-
-void __init at32_map_usart(unsigned int hw_id, unsigned int line, int flags)
-{
- struct platform_device *pdev;
- struct atmel_uart_data *pdata;
-
- switch (hw_id) {
- case 0:
- pdev = &atmel_usart0_device;
- configure_usart0_pins(flags);
- break;
- case 1:
- pdev = &atmel_usart1_device;
- configure_usart1_pins(flags);
- break;
- case 2:
- pdev = &atmel_usart2_device;
- configure_usart2_pins(flags);
- break;
- case 3:
- pdev = &atmel_usart3_device;
- configure_usart3_pins(flags);
- break;
- default:
- return;
- }
-
- if (PXSEG(pdev->resource[0].start) == P4SEG) {
- /* Addresses in the P4 segment are permanently mapped 1:1 */
- struct atmel_uart_data *data = pdev->dev.platform_data;
- data->regs = (void __iomem *)pdev->resource[0].start;
- }
-
- pdev->id = line;
- pdata = pdev->dev.platform_data;
- pdata->num = line;
- at32_usarts[line] = pdev;
-}
-
-struct platform_device *__init at32_add_device_usart(unsigned int id)
-{
- platform_device_register(at32_usarts[id]);
- return at32_usarts[id];
-}
-
-void __init at32_setup_serial_console(unsigned int usart_id)
-{
-#ifdef CONFIG_SERIAL_ATMEL
- atmel_default_console_device = at32_usarts[usart_id];
-#endif
-}
-
-/* --------------------------------------------------------------------
- * Ethernet
- * -------------------------------------------------------------------- */
-
-#ifdef CONFIG_CPU_AT32AP7000
-static struct macb_platform_data macb0_data;
-static struct resource macb0_resource[] = {
- PBMEM(0xfff01800),
- IRQ(25),
-};
-DEFINE_DEV_DATA(macb, 0);
-DEV_CLK(hclk, macb0, hsb, 8);
-DEV_CLK(pclk, macb0, pbb, 6);
-
-static struct macb_platform_data macb1_data;
-static struct resource macb1_resource[] = {
- PBMEM(0xfff01c00),
- IRQ(26),
-};
-DEFINE_DEV_DATA(macb, 1);
-DEV_CLK(hclk, macb1, hsb, 9);
-DEV_CLK(pclk, macb1, pbb, 7);
-
-struct platform_device *__init
-at32_add_device_eth(unsigned int id, struct macb_platform_data *data)
-{
- struct platform_device *pdev;
- u32 pin_mask;
-
- switch (id) {
- case 0:
- pdev = &macb0_device;
-
- pin_mask = (1 << 3); /* TXD0 */
- pin_mask |= (1 << 4); /* TXD1 */
- pin_mask |= (1 << 7); /* TXEN */
- pin_mask |= (1 << 8); /* TXCK */
- pin_mask |= (1 << 9); /* RXD0 */
- pin_mask |= (1 << 10); /* RXD1 */
- pin_mask |= (1 << 13); /* RXER */
- pin_mask |= (1 << 15); /* RXDV */
- pin_mask |= (1 << 16); /* MDC */
- pin_mask |= (1 << 17); /* MDIO */
-
- if (!data->is_rmii) {
- pin_mask |= (1 << 0); /* COL */
- pin_mask |= (1 << 1); /* CRS */
- pin_mask |= (1 << 2); /* TXER */
- pin_mask |= (1 << 5); /* TXD2 */
- pin_mask |= (1 << 6); /* TXD3 */
- pin_mask |= (1 << 11); /* RXD2 */
- pin_mask |= (1 << 12); /* RXD3 */
- pin_mask |= (1 << 14); /* RXCK */
-#ifndef CONFIG_BOARD_MIMC200
- pin_mask |= (1 << 18); /* SPD */
-#endif
- }
-
- select_peripheral(PIOC, pin_mask, PERIPH_A, 0);
-
- break;
-
- case 1:
- pdev = &macb1_device;
-
- pin_mask = (1 << 13); /* TXD0 */
- pin_mask |= (1 << 14); /* TXD1 */
- pin_mask |= (1 << 11); /* TXEN */
- pin_mask |= (1 << 12); /* TXCK */
- pin_mask |= (1 << 10); /* RXD0 */
- pin_mask |= (1 << 6); /* RXD1 */
- pin_mask |= (1 << 5); /* RXER */
- pin_mask |= (1 << 4); /* RXDV */
- pin_mask |= (1 << 3); /* MDC */
- pin_mask |= (1 << 2); /* MDIO */
-
-#ifndef CONFIG_BOARD_MIMC200
- if (!data->is_rmii)
- pin_mask |= (1 << 15); /* SPD */
-#endif
-
- select_peripheral(PIOD, pin_mask, PERIPH_B, 0);
-
- if (!data->is_rmii) {
- pin_mask = (1 << 19); /* COL */
- pin_mask |= (1 << 23); /* CRS */
- pin_mask |= (1 << 26); /* TXER */
- pin_mask |= (1 << 27); /* TXD2 */
- pin_mask |= (1 << 28); /* TXD3 */
- pin_mask |= (1 << 29); /* RXD2 */
- pin_mask |= (1 << 30); /* RXD3 */
- pin_mask |= (1 << 24); /* RXCK */
-
- select_peripheral(PIOC, pin_mask, PERIPH_B, 0);
- }
- break;
-
- default:
- return NULL;
- }
-
- memcpy(pdev->dev.platform_data, data, sizeof(struct macb_platform_data));
- platform_device_register(pdev);
-
- return pdev;
-}
-#endif
-
-/* --------------------------------------------------------------------
- * SPI
- * -------------------------------------------------------------------- */
-static struct resource atmel_spi0_resource[] = {
- PBMEM(0xffe00000),
- IRQ(3),
-};
-DEFINE_DEV(atmel_spi, 0);
-DEV_CLK(spi_clk, atmel_spi0, pba, 0);
-
-static struct resource atmel_spi1_resource[] = {
- PBMEM(0xffe00400),
- IRQ(4),
-};
-DEFINE_DEV(atmel_spi, 1);
-DEV_CLK(spi_clk, atmel_spi1, pba, 1);
-
-void __init
-at32_spi_setup_slaves(unsigned int bus_num, struct spi_board_info *b, unsigned int n)
-{
- /*
- * Manage the chipselects as GPIOs, normally using the same pins
- * the SPI controller expects; but boards can use other pins.
- */
- static u8 __initdata spi_pins[][4] = {
- { GPIO_PIN_PA(3), GPIO_PIN_PA(4),
- GPIO_PIN_PA(5), GPIO_PIN_PA(20) },
- { GPIO_PIN_PB(2), GPIO_PIN_PB(3),
- GPIO_PIN_PB(4), GPIO_PIN_PA(27) },
- };
- unsigned int pin, mode;
-
- /* There are only 2 SPI controllers */
- if (bus_num > 1)
- return;
-
- for (; n; n--, b++) {
- b->bus_num = bus_num;
- if (b->chip_select >= 4)
- continue;
- pin = (unsigned)b->controller_data;
- if (!pin) {
- pin = spi_pins[bus_num][b->chip_select];
- b->controller_data = (void *)pin;
- }
- mode = AT32_GPIOF_OUTPUT;
- if (!(b->mode & SPI_CS_HIGH))
- mode |= AT32_GPIOF_HIGH;
- at32_select_gpio(pin, mode);
- }
-}
-
-struct platform_device *__init
-at32_add_device_spi(unsigned int id, struct spi_board_info *b, unsigned int n)
-{
- struct platform_device *pdev;
- u32 pin_mask;
-
- switch (id) {
- case 0:
- pdev = &atmel_spi0_device;
- pin_mask = (1 << 1) | (1 << 2); /* MOSI & SCK */
-
- /* pullup MISO so a level is always defined */
- select_peripheral(PIOA, (1 << 0), PERIPH_A, AT32_GPIOF_PULLUP);
- select_peripheral(PIOA, pin_mask, PERIPH_A, 0);
-
- at32_spi_setup_slaves(0, b, n);
- break;
-
- case 1:
- pdev = &atmel_spi1_device;
- pin_mask = (1 << 1) | (1 << 5); /* MOSI */
-
- /* pullup MISO so a level is always defined */
- select_peripheral(PIOB, (1 << 0), PERIPH_B, AT32_GPIOF_PULLUP);
- select_peripheral(PIOB, pin_mask, PERIPH_B, 0);
-
- at32_spi_setup_slaves(1, b, n);
- break;
-
- default:
- return NULL;
- }
-
- spi_register_board_info(b, n);
- platform_device_register(pdev);
- return pdev;
-}
-
-/* --------------------------------------------------------------------
- * TWI
- * -------------------------------------------------------------------- */
-static struct resource atmel_twi0_resource[] __initdata = {
- PBMEM(0xffe00800),
- IRQ(5),
-};
-static struct clk atmel_twi0_pclk = {
- .name = "twi_pclk",
- .parent = &pba_clk,
- .mode = pba_clk_mode,
- .get_rate = pba_clk_get_rate,
- .index = 2,
-};
-
-struct platform_device *__init at32_add_device_twi(unsigned int id,
- struct i2c_board_info *b,
- unsigned int n)
-{
- struct platform_device *pdev;
- u32 pin_mask;
-
- if (id != 0)
- return NULL;
-
- pdev = platform_device_alloc("atmel_twi", id);
- if (!pdev)
- return NULL;
-
- if (platform_device_add_resources(pdev, atmel_twi0_resource,
- ARRAY_SIZE(atmel_twi0_resource)))
- goto err_add_resources;
-
- pin_mask = (1 << 6) | (1 << 7); /* SDA & SDL */
-
- select_peripheral(PIOA, pin_mask, PERIPH_A, 0);
-
- atmel_twi0_pclk.dev = &pdev->dev;
-
- if (b)
- i2c_register_board_info(id, b, n);
-
- platform_device_add(pdev);
- return pdev;
-
-err_add_resources:
- platform_device_put(pdev);
- return NULL;
-}
-
-/* --------------------------------------------------------------------
- * MMC
- * -------------------------------------------------------------------- */
-static struct resource atmel_mci0_resource[] __initdata = {
- PBMEM(0xfff02400),
- IRQ(28),
-};
-static struct clk atmel_mci0_pclk = {
- .name = "mci_clk",
- .parent = &pbb_clk,
- .mode = pbb_clk_mode,
- .get_rate = pbb_clk_get_rate,
- .index = 9,
-};
-
-static bool at32_mci_dma_filter(struct dma_chan *chan, void *pdata)
-{
- struct dw_dma_slave *sl = pdata;
-
- if (!sl)
- return false;
-
- if (sl->dma_dev == chan->device->dev) {
- chan->private = sl;
- return true;
- }
-
- return false;
-}
-
-struct platform_device *__init
-at32_add_device_mci(unsigned int id, struct mci_platform_data *data)
-{
- struct platform_device *pdev;
- struct dw_dma_slave *slave;
- u32 pioa_mask;
- u32 piob_mask;
-
- if (id != 0 || !data)
- return NULL;
-
- /* Must have at least one usable slot */
- if (!data->slot[0].bus_width && !data->slot[1].bus_width)
- return NULL;
-
- pdev = platform_device_alloc("atmel_mci", id);
- if (!pdev)
- goto fail;
-
- if (platform_device_add_resources(pdev, atmel_mci0_resource,
- ARRAY_SIZE(atmel_mci0_resource)))
- goto fail;
-
- slave = kzalloc(sizeof(*slave), GFP_KERNEL);
- if (!slave)
- goto fail;
-
- slave->dma_dev = &dw_dmac0_device.dev;
- slave->src_id = 0;
- slave->dst_id = 1;
- slave->m_master = 1;
- slave->p_master = 0;
-
- data->dma_slave = slave;
- data->dma_filter = at32_mci_dma_filter;
-
- if (platform_device_add_data(pdev, data,
- sizeof(struct mci_platform_data)))
- goto fail_free;
-
- /* CLK line is common to both slots */
- pioa_mask = 1 << 10;
-
- switch (data->slot[0].bus_width) {
- case 4:
- pioa_mask |= 1 << 13; /* DATA1 */
- pioa_mask |= 1 << 14; /* DATA2 */
- pioa_mask |= 1 << 15; /* DATA3 */
- /* fall through */
- case 1:
- pioa_mask |= 1 << 11; /* CMD */
- pioa_mask |= 1 << 12; /* DATA0 */
-
- if (gpio_is_valid(data->slot[0].detect_pin))
- at32_select_gpio(data->slot[0].detect_pin, 0);
- if (gpio_is_valid(data->slot[0].wp_pin))
- at32_select_gpio(data->slot[0].wp_pin, 0);
- break;
- case 0:
- /* Slot is unused */
- break;
- default:
- goto fail_free;
- }
-
- select_peripheral(PIOA, pioa_mask, PERIPH_A, 0);
- piob_mask = 0;
-
- switch (data->slot[1].bus_width) {
- case 4:
- piob_mask |= 1 << 8; /* DATA1 */
- piob_mask |= 1 << 9; /* DATA2 */
- piob_mask |= 1 << 10; /* DATA3 */
- /* fall through */
- case 1:
- piob_mask |= 1 << 6; /* CMD */
- piob_mask |= 1 << 7; /* DATA0 */
- select_peripheral(PIOB, piob_mask, PERIPH_B, 0);
-
- if (gpio_is_valid(data->slot[1].detect_pin))
- at32_select_gpio(data->slot[1].detect_pin, 0);
- if (gpio_is_valid(data->slot[1].wp_pin))
- at32_select_gpio(data->slot[1].wp_pin, 0);
- break;
- case 0:
- /* Slot is unused */
- break;
- default:
- if (!data->slot[0].bus_width)
- goto fail_free;
-
- data->slot[1].bus_width = 0;
- break;
- }
-
- atmel_mci0_pclk.dev = &pdev->dev;
-
- platform_device_add(pdev);
- return pdev;
-
-fail_free:
- kfree(slave);
-fail:
- data->dma_slave = NULL;
- platform_device_put(pdev);
- return NULL;
-}
-
-/* --------------------------------------------------------------------
- * LCDC
- * -------------------------------------------------------------------- */
-#if defined(CONFIG_CPU_AT32AP7000) || defined(CONFIG_CPU_AT32AP7002)
-static struct atmel_lcdfb_pdata atmel_lcdfb0_data;
-static struct resource atmel_lcdfb0_resource[] = {
- {
- .start = 0xff000000,
- .end = 0xff000fff,
- .flags = IORESOURCE_MEM,
- },
- IRQ(1),
- {
- /* Placeholder for pre-allocated fb memory */
- .start = 0x00000000,
- .end = 0x00000000,
- .flags = 0,
- },
-};
-DEFINE_DEV_DATA(atmel_lcdfb, 0);
-DEV_CLK(hclk, atmel_lcdfb0, hsb, 7);
-static struct clk atmel_lcdfb0_pixclk = {
- .name = "lcdc_clk",
- .dev = &atmel_lcdfb0_device.dev,
- .mode = genclk_mode,
- .get_rate = genclk_get_rate,
- .set_rate = genclk_set_rate,
- .set_parent = genclk_set_parent,
- .index = 7,
-};
-
-struct platform_device *__init
-at32_add_device_lcdc(unsigned int id, struct atmel_lcdfb_pdata *data,
- unsigned long fbmem_start, unsigned long fbmem_len,
- u64 pin_mask)
-{
- struct platform_device *pdev;
- struct atmel_lcdfb_pdata *info;
- struct fb_monspecs *monspecs;
- struct fb_videomode *modedb;
- unsigned int modedb_size;
- u32 portc_mask, portd_mask, porte_mask;
-
- /*
- * Do a deep copy of the fb data, monspecs and modedb. Make
- * sure all allocations are done before setting up the
- * portmux.
- */
- monspecs = kmemdup(data->default_monspecs,
- sizeof(struct fb_monspecs), GFP_KERNEL);
- if (!monspecs)
- return NULL;
-
- modedb_size = sizeof(struct fb_videomode) * monspecs->modedb_len;
- modedb = kmemdup(monspecs->modedb, modedb_size, GFP_KERNEL);
- if (!modedb)
- goto err_dup_modedb;
- monspecs->modedb = modedb;
-
- switch (id) {
- case 0:
- pdev = &atmel_lcdfb0_device;
-
- if (pin_mask == 0ULL)
- /* Default to "full" lcdc control signals and 24bit */
- pin_mask = ATMEL_LCDC_PRI_24BIT | ATMEL_LCDC_PRI_CONTROL;
-
- /* LCDC on port C */
- portc_mask = pin_mask & 0xfff80000;
- select_peripheral(PIOC, portc_mask, PERIPH_A, 0);
-
- /* LCDC on port D */
- portd_mask = pin_mask & 0x0003ffff;
- select_peripheral(PIOD, portd_mask, PERIPH_A, 0);
-
- /* LCDC on port E */
- porte_mask = (pin_mask >> 32) & 0x0007ffff;
- select_peripheral(PIOE, porte_mask, PERIPH_B, 0);
-
- clk_set_parent(&atmel_lcdfb0_pixclk, &pll0);
- clk_set_rate(&atmel_lcdfb0_pixclk, clk_get_rate(&pll0));
- break;
-
- default:
- goto err_invalid_id;
- }
-
- if (fbmem_len) {
- pdev->resource[2].start = fbmem_start;
- pdev->resource[2].end = fbmem_start + fbmem_len - 1;
- pdev->resource[2].flags = IORESOURCE_MEM;
- }
-
- info = pdev->dev.platform_data;
- memcpy(info, data, sizeof(struct atmel_lcdfb_pdata));
- info->default_monspecs = monspecs;
-
- pdev->name = "at32ap-lcdfb";
-
- platform_device_register(pdev);
- return pdev;
-
-err_invalid_id:
- kfree(modedb);
-err_dup_modedb:
- kfree(monspecs);
- return NULL;
-}
-#endif
-
-/* --------------------------------------------------------------------
- * PWM
- * -------------------------------------------------------------------- */
-static struct resource atmel_pwm0_resource[] __initdata = {
- PBMEM(0xfff01400),
- IRQ(24),
-};
-static struct clk atmel_pwm0_mck = {
- .name = "at91sam9rl-pwm",
- .parent = &pbb_clk,
- .mode = pbb_clk_mode,
- .get_rate = pbb_clk_get_rate,
- .index = 5,
-};
-
-struct platform_device *__init at32_add_device_pwm(u32 mask)
-{
- struct platform_device *pdev;
- u32 pin_mask;
-
- if (!mask)
- return NULL;
-
- pdev = platform_device_alloc("at91sam9rl-pwm", 0);
- if (!pdev)
- return NULL;
-
- if (platform_device_add_resources(pdev, atmel_pwm0_resource,
- ARRAY_SIZE(atmel_pwm0_resource)))
- goto out_free_pdev;
-
- pin_mask = 0;
- if (mask & (1 << 0))
- pin_mask |= (1 << 28);
- if (mask & (1 << 1))
- pin_mask |= (1 << 29);
- if (pin_mask > 0)
- select_peripheral(PIOA, pin_mask, PERIPH_A, 0);
-
- pin_mask = 0;
- if (mask & (1 << 2))
- pin_mask |= (1 << 21);
- if (mask & (1 << 3))
- pin_mask |= (1 << 22);
- if (pin_mask > 0)
- select_peripheral(PIOA, pin_mask, PERIPH_B, 0);
-
- atmel_pwm0_mck.dev = &pdev->dev;
-
- platform_device_add(pdev);
-
- return pdev;
-
-out_free_pdev:
- platform_device_put(pdev);
- return NULL;
-}
-
-/* --------------------------------------------------------------------
- * SSC
- * -------------------------------------------------------------------- */
-static struct resource ssc0_resource[] = {
- PBMEM(0xffe01c00),
- IRQ(10),
-};
-DEFINE_DEV(ssc, 0);
-DEV_CLK(pclk, ssc0, pba, 7);
-
-static struct resource ssc1_resource[] = {
- PBMEM(0xffe02000),
- IRQ(11),
-};
-DEFINE_DEV(ssc, 1);
-DEV_CLK(pclk, ssc1, pba, 8);
-
-static struct resource ssc2_resource[] = {
- PBMEM(0xffe02400),
- IRQ(12),
-};
-DEFINE_DEV(ssc, 2);
-DEV_CLK(pclk, ssc2, pba, 9);
-
-struct platform_device *__init
-at32_add_device_ssc(unsigned int id, unsigned int flags)
-{
- struct platform_device *pdev;
- u32 pin_mask = 0;
-
- switch (id) {
- case 0:
- pdev = &ssc0_device;
- if (flags & ATMEL_SSC_RF)
- pin_mask |= (1 << 21); /* RF */
- if (flags & ATMEL_SSC_RK)
- pin_mask |= (1 << 22); /* RK */
- if (flags & ATMEL_SSC_TK)
- pin_mask |= (1 << 23); /* TK */
- if (flags & ATMEL_SSC_TF)
- pin_mask |= (1 << 24); /* TF */
- if (flags & ATMEL_SSC_TD)
- pin_mask |= (1 << 25); /* TD */
- if (flags & ATMEL_SSC_RD)
- pin_mask |= (1 << 26); /* RD */
-
- if (pin_mask > 0)
- select_peripheral(PIOA, pin_mask, PERIPH_A, 0);
-
- break;
- case 1:
- pdev = &ssc1_device;
- if (flags & ATMEL_SSC_RF)
- pin_mask |= (1 << 0); /* RF */
- if (flags & ATMEL_SSC_RK)
- pin_mask |= (1 << 1); /* RK */
- if (flags & ATMEL_SSC_TK)
- pin_mask |= (1 << 2); /* TK */
- if (flags & ATMEL_SSC_TF)
- pin_mask |= (1 << 3); /* TF */
- if (flags & ATMEL_SSC_TD)
- pin_mask |= (1 << 4); /* TD */
- if (flags & ATMEL_SSC_RD)
- pin_mask |= (1 << 5); /* RD */
-
- if (pin_mask > 0)
- select_peripheral(PIOA, pin_mask, PERIPH_B, 0);
-
- break;
- case 2:
- pdev = &ssc2_device;
- if (flags & ATMEL_SSC_TD)
- pin_mask |= (1 << 13); /* TD */
- if (flags & ATMEL_SSC_RD)
- pin_mask |= (1 << 14); /* RD */
- if (flags & ATMEL_SSC_TK)
- pin_mask |= (1 << 15); /* TK */
- if (flags & ATMEL_SSC_TF)
- pin_mask |= (1 << 16); /* TF */
- if (flags & ATMEL_SSC_RF)
- pin_mask |= (1 << 17); /* RF */
- if (flags & ATMEL_SSC_RK)
- pin_mask |= (1 << 18); /* RK */
-
- if (pin_mask > 0)
- select_peripheral(PIOB, pin_mask, PERIPH_A, 0);
-
- break;
- default:
- return NULL;
- }
-
- platform_device_register(pdev);
- return pdev;
-}
-
-/* --------------------------------------------------------------------
- * USB Device Controller
- * -------------------------------------------------------------------- */
-static struct resource usba0_resource[] __initdata = {
- {
- .start = 0xff300000,
- .end = 0xff3fffff,
- .flags = IORESOURCE_MEM,
- }, {
- .start = 0xfff03000,
- .end = 0xfff033ff,
- .flags = IORESOURCE_MEM,
- },
- IRQ(31),
-};
-static struct clk usba0_pclk = {
- .name = "pclk",
- .parent = &pbb_clk,
- .mode = pbb_clk_mode,
- .get_rate = pbb_clk_get_rate,
- .index = 12,
-};
-static struct clk usba0_hclk = {
- .name = "hclk",
- .parent = &hsb_clk,
- .mode = hsb_clk_mode,
- .get_rate = hsb_clk_get_rate,
- .index = 6,
-};
-
-#define EP(nam, idx, maxpkt, maxbk, dma, isoc) \
- [idx] = { \
- .name = nam, \
- .index = idx, \
- .fifo_size = maxpkt, \
- .nr_banks = maxbk, \
- .can_dma = dma, \
- .can_isoc = isoc, \
- }
-
-static struct usba_ep_data at32_usba_ep[] __initdata = {
- EP("ep0", 0, 64, 1, 0, 0),
- EP("ep1", 1, 512, 2, 1, 1),
- EP("ep2", 2, 512, 2, 1, 1),
- EP("ep3-int", 3, 64, 3, 1, 0),
- EP("ep4-int", 4, 64, 3, 1, 0),
- EP("ep5", 5, 1024, 3, 1, 1),
- EP("ep6", 6, 1024, 3, 1, 1),
-};
-
-#undef EP
-
-struct platform_device *__init
-at32_add_device_usba(unsigned int id, struct usba_platform_data *data)
-{
- /*
- * pdata doesn't have room for any endpoints, so we need to
- * append room for the ones we need right after it.
- */
- struct {
- struct usba_platform_data pdata;
- struct usba_ep_data ep[7];
- } usba_data;
- struct platform_device *pdev;
-
- if (id != 0)
- return NULL;
-
- pdev = platform_device_alloc("atmel_usba_udc", 0);
- if (!pdev)
- return NULL;
-
- if (platform_device_add_resources(pdev, usba0_resource,
- ARRAY_SIZE(usba0_resource)))
- goto out_free_pdev;
-
- if (data) {
- usba_data.pdata.vbus_pin = data->vbus_pin;
- usba_data.pdata.vbus_pin_inverted = data->vbus_pin_inverted;
- } else {
- usba_data.pdata.vbus_pin = -EINVAL;
- usba_data.pdata.vbus_pin_inverted = -EINVAL;
- }
-
- data = &usba_data.pdata;
- data->num_ep = ARRAY_SIZE(at32_usba_ep);
- memcpy(data->ep, at32_usba_ep, sizeof(at32_usba_ep));
-
- if (platform_device_add_data(pdev, data, sizeof(usba_data)))
- goto out_free_pdev;
-
- if (gpio_is_valid(data->vbus_pin))
- at32_select_gpio(data->vbus_pin, 0);
-
- usba0_pclk.dev = &pdev->dev;
- usba0_hclk.dev = &pdev->dev;
-
- platform_device_add(pdev);
-
- return pdev;
-
-out_free_pdev:
- platform_device_put(pdev);
- return NULL;
-}
-
-/* --------------------------------------------------------------------
- * IDE / CompactFlash
- * -------------------------------------------------------------------- */
-#if defined(CONFIG_CPU_AT32AP7000) || defined(CONFIG_CPU_AT32AP7001)
-static struct resource at32_smc_cs4_resource[] __initdata = {
- {
- .start = 0x04000000,
- .end = 0x07ffffff,
- .flags = IORESOURCE_MEM,
- },
- IRQ(~0UL), /* Magic IRQ will be overridden */
-};
-static struct resource at32_smc_cs5_resource[] __initdata = {
- {
- .start = 0x20000000,
- .end = 0x23ffffff,
- .flags = IORESOURCE_MEM,
- },
- IRQ(~0UL), /* Magic IRQ will be overridden */
-};
-
-static int __init at32_init_ide_or_cf(struct platform_device *pdev,
- unsigned int cs, unsigned int extint)
-{
- static unsigned int extint_pin_map[4] __initdata = {
- (1 << 25),
- (1 << 26),
- (1 << 27),
- (1 << 28),
- };
- static bool common_pins_initialized __initdata = false;
- unsigned int extint_pin;
- int ret;
- u32 pin_mask;
-
- if (extint >= ARRAY_SIZE(extint_pin_map))
- return -EINVAL;
- extint_pin = extint_pin_map[extint];
-
- switch (cs) {
- case 4:
- ret = platform_device_add_resources(pdev,
- at32_smc_cs4_resource,
- ARRAY_SIZE(at32_smc_cs4_resource));
- if (ret)
- return ret;
-
- /* NCS4 -> OE_N */
- select_peripheral(PIOE, (1 << 21), PERIPH_A, 0);
- hmatrix_sfr_set_bits(HMATRIX_SLAVE_EBI, HMATRIX_EBI_CF0_ENABLE);
- break;
- case 5:
- ret = platform_device_add_resources(pdev,
- at32_smc_cs5_resource,
- ARRAY_SIZE(at32_smc_cs5_resource));
- if (ret)
- return ret;
-
- /* NCS5 -> OE_N */
- select_peripheral(PIOE, (1 << 22), PERIPH_A, 0);
- hmatrix_sfr_set_bits(HMATRIX_SLAVE_EBI, HMATRIX_EBI_CF1_ENABLE);
- break;
- default:
- return -EINVAL;
- }
-
- if (!common_pins_initialized) {
- pin_mask = (1 << 19); /* CFCE1 -> CS0_N */
- pin_mask |= (1 << 20); /* CFCE2 -> CS1_N */
- pin_mask |= (1 << 23); /* CFRNW -> DIR */
- pin_mask |= (1 << 24); /* NWAIT <- IORDY */
-
- select_peripheral(PIOE, pin_mask, PERIPH_A, 0);
-
- common_pins_initialized = true;
- }
-
- select_peripheral(PIOB, extint_pin, PERIPH_A, AT32_GPIOF_DEGLITCH);
-
- pdev->resource[1].start = EIM_IRQ_BASE + extint;
- pdev->resource[1].end = pdev->resource[1].start;
-
- return 0;
-}
-
-struct platform_device *__init
-at32_add_device_ide(unsigned int id, unsigned int extint,
- struct ide_platform_data *data)
-{
- struct platform_device *pdev;
-
- pdev = platform_device_alloc("at32_ide", id);
- if (!pdev)
- goto fail;
-
- if (platform_device_add_data(pdev, data,
- sizeof(struct ide_platform_data)))
- goto fail;
-
- if (at32_init_ide_or_cf(pdev, data->cs, extint))
- goto fail;
-
- platform_device_add(pdev);
- return pdev;
-
-fail:
- platform_device_put(pdev);
- return NULL;
-}
-
-struct platform_device *__init
-at32_add_device_cf(unsigned int id, unsigned int extint,
- struct cf_platform_data *data)
-{
- struct platform_device *pdev;
-
- pdev = platform_device_alloc("at32_cf", id);
- if (!pdev)
- goto fail;
-
- if (platform_device_add_data(pdev, data,
- sizeof(struct cf_platform_data)))
- goto fail;
-
- if (at32_init_ide_or_cf(pdev, data->cs, extint))
- goto fail;
-
- if (gpio_is_valid(data->detect_pin))
- at32_select_gpio(data->detect_pin, AT32_GPIOF_DEGLITCH);
- if (gpio_is_valid(data->reset_pin))
- at32_select_gpio(data->reset_pin, 0);
- if (gpio_is_valid(data->vcc_pin))
- at32_select_gpio(data->vcc_pin, 0);
- /* READY is used as extint, so we can't select it as gpio */
-
- platform_device_add(pdev);
- return pdev;
-
-fail:
- platform_device_put(pdev);
- return NULL;
-}
-#endif
-
-/* --------------------------------------------------------------------
- * NAND Flash / SmartMedia
- * -------------------------------------------------------------------- */
-static struct resource smc_cs3_resource[] __initdata = {
- {
- .start = 0x0c000000,
- .end = 0x0fffffff,
- .flags = IORESOURCE_MEM,
- }, {
- .start = 0xfff03c00,
- .end = 0xfff03fff,
- .flags = IORESOURCE_MEM,
- },
-};
-
-struct platform_device *__init
-at32_add_device_nand(unsigned int id, struct atmel_nand_data *data)
-{
- struct platform_device *pdev;
-
- if (id != 0 || !data)
- return NULL;
-
- pdev = platform_device_alloc("atmel_nand", id);
- if (!pdev)
- goto fail;
-
- if (platform_device_add_resources(pdev, smc_cs3_resource,
- ARRAY_SIZE(smc_cs3_resource)))
- goto fail;
-
- /* For at32ap7000, we use the reset workaround for nand driver */
- data->need_reset_workaround = true;
-
- if (platform_device_add_data(pdev, data,
- sizeof(struct atmel_nand_data)))
- goto fail;
-
- hmatrix_sfr_set_bits(HMATRIX_SLAVE_EBI, HMATRIX_EBI_NAND_ENABLE);
- if (data->enable_pin)
- at32_select_gpio(data->enable_pin,
- AT32_GPIOF_OUTPUT | AT32_GPIOF_HIGH);
- if (data->rdy_pin)
- at32_select_gpio(data->rdy_pin, 0);
- if (data->det_pin)
- at32_select_gpio(data->det_pin, 0);
-
- platform_device_add(pdev);
- return pdev;
-
-fail:
- platform_device_put(pdev);
- return NULL;
-}
-
-/* --------------------------------------------------------------------
- * AC97C
- * -------------------------------------------------------------------- */
-static struct resource atmel_ac97c0_resource[] __initdata = {
- PBMEM(0xfff02800),
- IRQ(29),
-};
-static struct clk atmel_ac97c0_pclk = {
- .name = "pclk",
- .parent = &pbb_clk,
- .mode = pbb_clk_mode,
- .get_rate = pbb_clk_get_rate,
- .index = 10,
-};
-
-struct platform_device *__init
-at32_add_device_ac97c(unsigned int id, struct ac97c_platform_data *data,
- unsigned int flags)
-{
- struct platform_device *pdev;
- struct dw_dma_slave *rx_dws;
- struct dw_dma_slave *tx_dws;
- struct ac97c_platform_data _data;
- u32 pin_mask;
-
- if (id != 0)
- return NULL;
-
- pdev = platform_device_alloc("atmel_ac97c", id);
- if (!pdev)
- return NULL;
-
- if (platform_device_add_resources(pdev, atmel_ac97c0_resource,
- ARRAY_SIZE(atmel_ac97c0_resource)))
- goto out_free_resources;
-
- if (!data) {
- data = &_data;
- memset(data, 0, sizeof(struct ac97c_platform_data));
- data->reset_pin = -ENODEV;
- }
-
- rx_dws = &data->rx_dws;
- tx_dws = &data->tx_dws;
-
- /* Check if DMA slave interface for capture should be configured. */
- if (flags & AC97C_CAPTURE) {
- rx_dws->dma_dev = &dw_dmac0_device.dev;
- rx_dws->src_id = 3;
- rx_dws->m_master = 0;
- rx_dws->p_master = 1;
- }
-
- /* Check if DMA slave interface for playback should be configured. */
- if (flags & AC97C_PLAYBACK) {
- tx_dws->dma_dev = &dw_dmac0_device.dev;
- tx_dws->dst_id = 4;
- tx_dws->m_master = 0;
- tx_dws->p_master = 1;
- }
-
- if (platform_device_add_data(pdev, data,
- sizeof(struct ac97c_platform_data)))
- goto out_free_resources;
-
- /* SDO | SYNC | SCLK | SDI */
- pin_mask = (1 << 20) | (1 << 21) | (1 << 22) | (1 << 23);
-
- select_peripheral(PIOB, pin_mask, PERIPH_B, 0);
-
- if (gpio_is_valid(data->reset_pin))
- at32_select_gpio(data->reset_pin, AT32_GPIOF_OUTPUT
- | AT32_GPIOF_HIGH);
-
- atmel_ac97c0_pclk.dev = &pdev->dev;
-
- platform_device_add(pdev);
- return pdev;
-
-out_free_resources:
- platform_device_put(pdev);
- return NULL;
-}
-
-/* --------------------------------------------------------------------
- * ABDAC
- * -------------------------------------------------------------------- */
-static struct resource abdac0_resource[] __initdata = {
- PBMEM(0xfff02000),
- IRQ(27),
-};
-static struct clk abdac0_pclk = {
- .name = "pclk",
- .parent = &pbb_clk,
- .mode = pbb_clk_mode,
- .get_rate = pbb_clk_get_rate,
- .index = 8,
-};
-static struct clk abdac0_sample_clk = {
- .name = "sample_clk",
- .mode = genclk_mode,
- .get_rate = genclk_get_rate,
- .set_rate = genclk_set_rate,
- .set_parent = genclk_set_parent,
- .index = 6,
-};
-
-struct platform_device *__init
-at32_add_device_abdac(unsigned int id, struct atmel_abdac_pdata *data)
-{
- struct platform_device *pdev;
- struct dw_dma_slave *dws;
- u32 pin_mask;
-
- if (id != 0 || !data)
- return NULL;
-
- pdev = platform_device_alloc("atmel_abdac", id);
- if (!pdev)
- return NULL;
-
- if (platform_device_add_resources(pdev, abdac0_resource,
- ARRAY_SIZE(abdac0_resource)))
- goto out_free_resources;
-
- dws = &data->dws;
-
- dws->dma_dev = &dw_dmac0_device.dev;
- dws->dst_id = 2;
- dws->m_master = 0;
- dws->p_master = 1;
-
- if (platform_device_add_data(pdev, data,
- sizeof(struct atmel_abdac_pdata)))
- goto out_free_resources;
-
- pin_mask = (1 << 20) | (1 << 22); /* DATA1 & DATAN1 */
- pin_mask |= (1 << 21) | (1 << 23); /* DATA0 & DATAN0 */
-
- select_peripheral(PIOB, pin_mask, PERIPH_A, 0);
-
- abdac0_pclk.dev = &pdev->dev;
- abdac0_sample_clk.dev = &pdev->dev;
-
- platform_device_add(pdev);
- return pdev;
-
-out_free_resources:
- platform_device_put(pdev);
- return NULL;
-}
-
-/* --------------------------------------------------------------------
- * GCLK
- * -------------------------------------------------------------------- */
-static struct clk gclk0 = {
- .name = "gclk0",
- .mode = genclk_mode,
- .get_rate = genclk_get_rate,
- .set_rate = genclk_set_rate,
- .set_parent = genclk_set_parent,
- .index = 0,
-};
-static struct clk gclk1 = {
- .name = "gclk1",
- .mode = genclk_mode,
- .get_rate = genclk_get_rate,
- .set_rate = genclk_set_rate,
- .set_parent = genclk_set_parent,
- .index = 1,
-};
-static struct clk gclk2 = {
- .name = "gclk2",
- .mode = genclk_mode,
- .get_rate = genclk_get_rate,
- .set_rate = genclk_set_rate,
- .set_parent = genclk_set_parent,
- .index = 2,
-};
-static struct clk gclk3 = {
- .name = "gclk3",
- .mode = genclk_mode,
- .get_rate = genclk_get_rate,
- .set_rate = genclk_set_rate,
- .set_parent = genclk_set_parent,
- .index = 3,
-};
-static struct clk gclk4 = {
- .name = "gclk4",
- .mode = genclk_mode,
- .get_rate = genclk_get_rate,
- .set_rate = genclk_set_rate,
- .set_parent = genclk_set_parent,
- .index = 4,
-};
-
-static __initdata struct clk *init_clocks[] = {
- &osc32k,
- &osc0,
- &osc1,
- &pll0,
- &pll1,
- &cpu_clk,
- &hsb_clk,
- &pba_clk,
- &pbb_clk,
- &at32_pm_pclk,
- &at32_intc0_pclk,
- &at32_hmatrix_clk,
- &ebi_clk,
- &hramc_clk,
- &sdramc_clk,
- &smc0_pclk,
- &smc0_mck,
- &pdc_hclk,
- &pdc_pclk,
- &dw_dmac0_hclk,
- &pico_clk,
- &pio0_mck,
- &pio1_mck,
- &pio2_mck,
- &pio3_mck,
- &pio4_mck,
- &at32_tcb0_t0_clk,
- &at32_tcb1_t0_clk,
- &atmel_psif0_pclk,
- &atmel_psif1_pclk,
- &atmel_usart0_usart,
- &atmel_usart1_usart,
- &atmel_usart2_usart,
- &atmel_usart3_usart,
- &atmel_pwm0_mck,
-#if defined(CONFIG_CPU_AT32AP7000)
- &macb0_hclk,
- &macb0_pclk,
- &macb1_hclk,
- &macb1_pclk,
-#endif
- &atmel_spi0_spi_clk,
- &atmel_spi1_spi_clk,
- &atmel_twi0_pclk,
- &atmel_mci0_pclk,
-#if defined(CONFIG_CPU_AT32AP7000) || defined(CONFIG_CPU_AT32AP7002)
- &atmel_lcdfb0_hclk,
- &atmel_lcdfb0_pixclk,
-#endif
- &ssc0_pclk,
- &ssc1_pclk,
- &ssc2_pclk,
- &usba0_hclk,
- &usba0_pclk,
- &atmel_ac97c0_pclk,
- &abdac0_pclk,
- &abdac0_sample_clk,
- &gclk0,
- &gclk1,
- &gclk2,
- &gclk3,
- &gclk4,
-};
-
-void __init setup_platform(void)
-{
- u32 cpu_mask = 0, hsb_mask = 0, pba_mask = 0, pbb_mask = 0;
- int i;
-
- if (pm_readl(MCCTRL) & PM_BIT(PLLSEL)) {
- main_clock = &pll0;
- cpu_clk.parent = &pll0;
- } else {
- main_clock = &osc0;
- cpu_clk.parent = &osc0;
- }
-
- if (pm_readl(PLL0) & PM_BIT(PLLOSC))
- pll0.parent = &osc1;
- if (pm_readl(PLL1) & PM_BIT(PLLOSC))
- pll1.parent = &osc1;
-
- genclk_init_parent(&gclk0);
- genclk_init_parent(&gclk1);
- genclk_init_parent(&gclk2);
- genclk_init_parent(&gclk3);
- genclk_init_parent(&gclk4);
-#if defined(CONFIG_CPU_AT32AP7000) || defined(CONFIG_CPU_AT32AP7002)
- genclk_init_parent(&atmel_lcdfb0_pixclk);
-#endif
- genclk_init_parent(&abdac0_sample_clk);
-
- /*
- * Build initial dynamic clock list by registering all clocks
- * from the array.
- * At the same time, turn on all clocks that have at least one
- * user already, and turn off everything else. We only do this
- * for module clocks, and even though it isn't particularly
- * pretty to check the address of the mode function, it should
- * do the trick...
- */
- for (i = 0; i < ARRAY_SIZE(init_clocks); i++) {
- struct clk *clk = init_clocks[i];
-
- /* first, register clock */
- at32_clk_register(clk);
-
- if (clk->users == 0)
- continue;
-
- if (clk->mode == &cpu_clk_mode)
- cpu_mask |= 1 << clk->index;
- else if (clk->mode == &hsb_clk_mode)
- hsb_mask |= 1 << clk->index;
- else if (clk->mode == &pba_clk_mode)
- pba_mask |= 1 << clk->index;
- else if (clk->mode == &pbb_clk_mode)
- pbb_mask |= 1 << clk->index;
- }
-
- pm_writel(CPU_MASK, cpu_mask);
- pm_writel(HSB_MASK, hsb_mask);
- pm_writel(PBA_MASK, pba_mask);
- pm_writel(PBB_MASK, pbb_mask);
-
- /* Initialize the port muxes */
- at32_init_pio(&pio0_device);
- at32_init_pio(&pio1_device);
- at32_init_pio(&pio2_device);
- at32_init_pio(&pio3_device);
- at32_init_pio(&pio4_device);
-}
-
-struct gen_pool *sram_pool;
-
-static int __init sram_init(void)
-{
- struct gen_pool *pool;
-
- /* 1KiB granularity */
- pool = gen_pool_create(10, -1);
- if (!pool)
- goto fail;
-
- if (gen_pool_add(pool, 0x24000000, 0x8000, -1))
- goto err_pool_add;
-
- sram_pool = pool;
- return 0;
-
-err_pool_add:
- gen_pool_destroy(pool);
-fail:
- pr_err("Failed to create SRAM pool\n");
- return -ENOMEM;
-}
-core_initcall(sram_init);
+++ /dev/null
-/*
- * Clock management for AT32AP CPUs
- *
- * Copyright (C) 2006 Atmel Corporation
- *
- * Based on arch/arm/mach-at91/clock.c
- * Copyright (C) 2005 David Brownell
- * Copyright (C) 2005 Ivan Kokshaysky
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/clk.h>
-#include <linux/err.h>
-#include <linux/export.h>
-#include <linux/device.h>
-#include <linux/string.h>
-#include <linux/list.h>
-
-#include <mach/chip.h>
-
-#include "clock.h"
-
-/* at32 clock list */
-static LIST_HEAD(at32_clock_list);
-
-static DEFINE_SPINLOCK(clk_lock);
-static DEFINE_SPINLOCK(clk_list_lock);
-
-void at32_clk_register(struct clk *clk)
-{
- spin_lock(&clk_list_lock);
- /* add the new item to the end of the list */
- list_add_tail(&clk->list, &at32_clock_list);
- spin_unlock(&clk_list_lock);
-}
-
-static struct clk *__clk_get(struct device *dev, const char *id)
-{
- struct clk *clk;
-
- list_for_each_entry(clk, &at32_clock_list, list) {
- if (clk->dev == dev && strcmp(id, clk->name) == 0) {
- return clk;
- }
- }
-
- return ERR_PTR(-ENOENT);
-}
-
-struct clk *clk_get(struct device *dev, const char *id)
-{
- struct clk *clk;
-
- spin_lock(&clk_list_lock);
- clk = __clk_get(dev, id);
- spin_unlock(&clk_list_lock);
-
- return clk;
-}
-
-EXPORT_SYMBOL(clk_get);
-
-void clk_put(struct clk *clk)
-{
- /* clocks are static for now, we can't free them */
-}
-EXPORT_SYMBOL(clk_put);
-
-static void __clk_enable(struct clk *clk)
-{
- if (clk->parent)
- __clk_enable(clk->parent);
- if (clk->users++ == 0 && clk->mode)
- clk->mode(clk, 1);
-}
-
-int clk_enable(struct clk *clk)
-{
- unsigned long flags;
-
- if (!clk)
- return 0;
-
- spin_lock_irqsave(&clk_lock, flags);
- __clk_enable(clk);
- spin_unlock_irqrestore(&clk_lock, flags);
-
- return 0;
-}
-EXPORT_SYMBOL(clk_enable);
-
-static void __clk_disable(struct clk *clk)
-{
- if (clk->users == 0) {
- printk(KERN_ERR "%s: mismatched disable\n", clk->name);
- WARN_ON(1);
- return;
- }
-
- if (--clk->users == 0 && clk->mode)
- clk->mode(clk, 0);
- if (clk->parent)
- __clk_disable(clk->parent);
-}
-
-void clk_disable(struct clk *clk)
-{
- unsigned long flags;
-
- if (IS_ERR_OR_NULL(clk))
- return;
-
- spin_lock_irqsave(&clk_lock, flags);
- __clk_disable(clk);
- spin_unlock_irqrestore(&clk_lock, flags);
-}
-EXPORT_SYMBOL(clk_disable);
-
-unsigned long clk_get_rate(struct clk *clk)
-{
- unsigned long flags;
- unsigned long rate;
-
- if (!clk)
- return 0;
-
- spin_lock_irqsave(&clk_lock, flags);
- rate = clk->get_rate(clk);
- spin_unlock_irqrestore(&clk_lock, flags);
-
- return rate;
-}
-EXPORT_SYMBOL(clk_get_rate);
-
-long clk_round_rate(struct clk *clk, unsigned long rate)
-{
- unsigned long flags, actual_rate;
-
- if (!clk)
- return 0;
-
- if (!clk->set_rate)
- return -ENOSYS;
-
- spin_lock_irqsave(&clk_lock, flags);
- actual_rate = clk->set_rate(clk, rate, 0);
- spin_unlock_irqrestore(&clk_lock, flags);
-
- return actual_rate;
-}
-EXPORT_SYMBOL(clk_round_rate);
-
-int clk_set_rate(struct clk *clk, unsigned long rate)
-{
- unsigned long flags;
- long ret;
-
- if (!clk)
- return 0;
-
- if (!clk->set_rate)
- return -ENOSYS;
-
- spin_lock_irqsave(&clk_lock, flags);
- ret = clk->set_rate(clk, rate, 1);
- spin_unlock_irqrestore(&clk_lock, flags);
-
- return (ret < 0) ? ret : 0;
-}
-EXPORT_SYMBOL(clk_set_rate);
-
-int clk_set_parent(struct clk *clk, struct clk *parent)
-{
- unsigned long flags;
- int ret;
-
- if (!clk)
- return 0;
-
- if (!clk->set_parent)
- return -ENOSYS;
-
- spin_lock_irqsave(&clk_lock, flags);
- ret = clk->set_parent(clk, parent);
- spin_unlock_irqrestore(&clk_lock, flags);
-
- return ret;
-}
-EXPORT_SYMBOL(clk_set_parent);
-
-struct clk *clk_get_parent(struct clk *clk)
-{
- return !clk ? NULL : clk->parent;
-}
-EXPORT_SYMBOL(clk_get_parent);
-
-
-
-#ifdef CONFIG_DEBUG_FS
-
-/* /sys/kernel/debug/at32ap_clk */
-
-#include <linux/io.h>
-#include <linux/debugfs.h>
-#include <linux/seq_file.h>
-#include "pm.h"
-
-
-#define NEST_DELTA 2
-#define NEST_MAX 6
-
-struct clkinf {
- struct seq_file *s;
- unsigned nest;
-};
-
-static void
-dump_clock(struct clk *parent, struct clkinf *r)
-{
- unsigned nest = r->nest;
- char buf[16 + NEST_MAX];
- struct clk *clk;
- unsigned i;
-
- /* skip clocks coupled to devices that aren't registered */
- if (parent->dev && !dev_name(parent->dev) && !parent->users)
- return;
-
- /* <nest spaces> name <pad to end> */
- memset(buf, ' ', sizeof(buf) - 1);
- buf[sizeof(buf) - 1] = 0;
- i = strlen(parent->name);
- memcpy(buf + nest, parent->name,
- min(i, (unsigned)(sizeof(buf) - 1 - nest)));
-
- seq_printf(r->s, "%s%c users=%2d %-3s %9ld Hz",
- buf, parent->set_parent ? '*' : ' ',
- parent->users,
- parent->users ? "on" : "off", /* NOTE: not-paranoid!! */
- clk_get_rate(parent));
- if (parent->dev)
- seq_printf(r->s, ", for %s", dev_name(parent->dev));
- seq_putc(r->s, '\n');
-
- /* cost of this scan is small, but not linear... */
- r->nest = nest + NEST_DELTA;
-
- list_for_each_entry(clk, &at32_clock_list, list) {
- if (clk->parent == parent)
- dump_clock(clk, r);
- }
- r->nest = nest;
-}
-
-static int clk_show(struct seq_file *s, void *unused)
-{
- struct clkinf r;
- int i;
- struct clk *clk;
-
- /* show all the power manager registers */
- seq_printf(s,
- "MCCTRL = %8x\n"
- "CKSEL = %8x\n"
- "CPUMASK = %8x\n"
- "HSBMASK = %8x\n"
- "PBAMASK = %8x\n"
- "PBBMASK = %8x\n"
- "PLL0 = %8x\n"
- "PLL1 = %8x\n"
- "IMR = %8x\n",
- pm_readl(MCCTRL),
- pm_readl(CKSEL),
- pm_readl(CPU_MASK),
- pm_readl(HSB_MASK),
- pm_readl(PBA_MASK),
- pm_readl(PBB_MASK),
- pm_readl(PLL0),
- pm_readl(PLL1),
- pm_readl(IMR));
- for (i = 0; i < 8; i++) {
- if (i == 5)
- continue;
- seq_printf(s, "GCCTRL%d = %8x\n", i, pm_readl(GCCTRL(i)));
- }
-
- seq_putc(s, '\n');
- r.s = s;
- r.nest = 0;
- /* protected from changes on the list while dumping */
- spin_lock(&clk_list_lock);
-
- /* show clock tree as derived from the three oscillators */
- clk = __clk_get(NULL, "osc32k");
- dump_clock(clk, &r);
- clk_put(clk);
-
- clk = __clk_get(NULL, "osc0");
- dump_clock(clk, &r);
- clk_put(clk);
-
- clk = __clk_get(NULL, "osc1");
- dump_clock(clk, &r);
- clk_put(clk);
-
- spin_unlock(&clk_list_lock);
-
- return 0;
-}
-
-static int clk_open(struct inode *inode, struct file *file)
-{
- return single_open(file, clk_show, NULL);
-}
-
-static const struct file_operations clk_operations = {
- .open = clk_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
-static int __init clk_debugfs_init(void)
-{
- (void) debugfs_create_file("at32ap_clk", S_IFREG | S_IRUGO,
- NULL, NULL, &clk_operations);
-
- return 0;
-}
-postcore_initcall(clk_debugfs_init);
-
-#endif
+++ /dev/null
-/*
- * Clock management for AT32AP CPUs
- *
- * Copyright (C) 2006 Atmel Corporation
- *
- * Based on arch/arm/mach-at91/clock.c
- * Copyright (C) 2005 David Brownell
- * Copyright (C) 2005 Ivan Kokshaysky
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/clk.h>
-#include <linux/list.h>
-
-
-void at32_clk_register(struct clk *clk);
-
-struct clk {
- struct list_head list; /* linking element */
- const char *name; /* Clock name/function */
- struct device *dev; /* Device the clock is used by */
- struct clk *parent; /* Parent clock, if any */
- void (*mode)(struct clk *clk, int enabled);
- unsigned long (*get_rate)(struct clk *clk);
- long (*set_rate)(struct clk *clk, unsigned long rate,
- int apply);
- int (*set_parent)(struct clk *clk, struct clk *parent);
- u16 users; /* Enabled if non-zero */
- u16 index; /* Sibling index */
-};
-
-unsigned long pba_clk_get_rate(struct clk *clk);
-void pba_clk_mode(struct clk *clk, int enabled);
+++ /dev/null
-/*
- * External interrupt handling for AT32AP CPUs
- *
- * Copyright (C) 2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/errno.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/platform_device.h>
-#include <linux/random.h>
-#include <linux/slab.h>
-
-#include <asm/io.h>
-
-/* EIC register offsets */
-#define EIC_IER 0x0000
-#define EIC_IDR 0x0004
-#define EIC_IMR 0x0008
-#define EIC_ISR 0x000c
-#define EIC_ICR 0x0010
-#define EIC_MODE 0x0014
-#define EIC_EDGE 0x0018
-#define EIC_LEVEL 0x001c
-#define EIC_NMIC 0x0024
-
-/* Bitfields in NMIC */
-#define EIC_NMIC_ENABLE (1 << 0)
-
-/* Bit manipulation macros */
-#define EIC_BIT(name) \
- (1 << EIC_##name##_OFFSET)
-#define EIC_BF(name,value) \
- (((value) & ((1 << EIC_##name##_SIZE) - 1)) \
- << EIC_##name##_OFFSET)
-#define EIC_BFEXT(name,value) \
- (((value) >> EIC_##name##_OFFSET) \
- & ((1 << EIC_##name##_SIZE) - 1))
-#define EIC_BFINS(name,value,old) \
- (((old) & ~(((1 << EIC_##name##_SIZE) - 1) \
- << EIC_##name##_OFFSET)) \
- | EIC_BF(name,value))
-
-/* Register access macros */
-#define eic_readl(port,reg) \
- __raw_readl((port)->regs + EIC_##reg)
-#define eic_writel(port,reg,value) \
- __raw_writel((value), (port)->regs + EIC_##reg)
-
-struct eic {
- void __iomem *regs;
- struct irq_chip *chip;
- unsigned int first_irq;
-};
-
-static struct eic *nmi_eic;
-static bool nmi_enabled;
-
-static void eic_ack_irq(struct irq_data *d)
-{
- struct eic *eic = irq_data_get_irq_chip_data(d);
- eic_writel(eic, ICR, 1 << (d->irq - eic->first_irq));
-}
-
-static void eic_mask_irq(struct irq_data *d)
-{
- struct eic *eic = irq_data_get_irq_chip_data(d);
- eic_writel(eic, IDR, 1 << (d->irq - eic->first_irq));
-}
-
-static void eic_mask_ack_irq(struct irq_data *d)
-{
- struct eic *eic = irq_data_get_irq_chip_data(d);
- eic_writel(eic, ICR, 1 << (d->irq - eic->first_irq));
- eic_writel(eic, IDR, 1 << (d->irq - eic->first_irq));
-}
-
-static void eic_unmask_irq(struct irq_data *d)
-{
- struct eic *eic = irq_data_get_irq_chip_data(d);
- eic_writel(eic, IER, 1 << (d->irq - eic->first_irq));
-}
-
-static int eic_set_irq_type(struct irq_data *d, unsigned int flow_type)
-{
- struct eic *eic = irq_data_get_irq_chip_data(d);
- unsigned int irq = d->irq;
- unsigned int i = irq - eic->first_irq;
- u32 mode, edge, level;
-
- flow_type &= IRQ_TYPE_SENSE_MASK;
- if (flow_type == IRQ_TYPE_NONE)
- flow_type = IRQ_TYPE_LEVEL_LOW;
-
- mode = eic_readl(eic, MODE);
- edge = eic_readl(eic, EDGE);
- level = eic_readl(eic, LEVEL);
-
- switch (flow_type) {
- case IRQ_TYPE_LEVEL_LOW:
- mode |= 1 << i;
- level &= ~(1 << i);
- break;
- case IRQ_TYPE_LEVEL_HIGH:
- mode |= 1 << i;
- level |= 1 << i;
- break;
- case IRQ_TYPE_EDGE_RISING:
- mode &= ~(1 << i);
- edge |= 1 << i;
- break;
- case IRQ_TYPE_EDGE_FALLING:
- mode &= ~(1 << i);
- edge &= ~(1 << i);
- break;
- default:
- return -EINVAL;
- }
-
- eic_writel(eic, MODE, mode);
- eic_writel(eic, EDGE, edge);
- eic_writel(eic, LEVEL, level);
-
- irqd_set_trigger_type(d, flow_type);
- if (flow_type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
- irq_set_handler_locked(d, handle_level_irq);
- else
- irq_set_handler_locked(d, handle_edge_irq);
-
- return IRQ_SET_MASK_OK_NOCOPY;
-}
-
-static struct irq_chip eic_chip = {
- .name = "eic",
- .irq_ack = eic_ack_irq,
- .irq_mask = eic_mask_irq,
- .irq_mask_ack = eic_mask_ack_irq,
- .irq_unmask = eic_unmask_irq,
- .irq_set_type = eic_set_irq_type,
-};
-
-static void demux_eic_irq(struct irq_desc *desc)
-{
- struct eic *eic = irq_desc_get_handler_data(desc);
- unsigned long status, pending;
- unsigned int i;
-
- status = eic_readl(eic, ISR);
- pending = status & eic_readl(eic, IMR);
-
- while (pending) {
- i = fls(pending) - 1;
- pending &= ~(1 << i);
-
- generic_handle_irq(i + eic->first_irq);
- }
-}
-
-int nmi_enable(void)
-{
- nmi_enabled = true;
-
- if (nmi_eic)
- eic_writel(nmi_eic, NMIC, EIC_NMIC_ENABLE);
-
- return 0;
-}
-
-void nmi_disable(void)
-{
- if (nmi_eic)
- eic_writel(nmi_eic, NMIC, 0);
-
- nmi_enabled = false;
-}
-
-static int __init eic_probe(struct platform_device *pdev)
-{
- struct eic *eic;
- struct resource *regs;
- unsigned int i;
- unsigned int nr_of_irqs;
- unsigned int int_irq;
- int ret;
- u32 pattern;
-
- regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- int_irq = platform_get_irq(pdev, 0);
- if (!regs || (int)int_irq <= 0) {
- dev_dbg(&pdev->dev, "missing regs and/or irq resource\n");
- return -ENXIO;
- }
-
- ret = -ENOMEM;
- eic = kzalloc(sizeof(struct eic), GFP_KERNEL);
- if (!eic) {
- dev_dbg(&pdev->dev, "no memory for eic structure\n");
- goto err_kzalloc;
- }
-
- eic->first_irq = EIM_IRQ_BASE + 32 * pdev->id;
- eic->regs = ioremap(regs->start, resource_size(regs));
- if (!eic->regs) {
- dev_dbg(&pdev->dev, "failed to map regs\n");
- goto err_ioremap;
- }
-
- /*
- * Find out how many interrupt lines that are actually
- * implemented in hardware.
- */
- eic_writel(eic, IDR, ~0UL);
- eic_writel(eic, MODE, ~0UL);
- pattern = eic_readl(eic, MODE);
- nr_of_irqs = fls(pattern);
-
- /* Trigger on low level unless overridden by driver */
- eic_writel(eic, EDGE, 0UL);
- eic_writel(eic, LEVEL, 0UL);
-
- eic->chip = &eic_chip;
-
- for (i = 0; i < nr_of_irqs; i++) {
- irq_set_chip_and_handler(eic->first_irq + i, &eic_chip,
- handle_level_irq);
- irq_set_chip_data(eic->first_irq + i, eic);
- }
-
- irq_set_chained_handler_and_data(int_irq, demux_eic_irq, eic);
-
- if (pdev->id == 0) {
- nmi_eic = eic;
- if (nmi_enabled)
- /*
- * Someone tried to enable NMI before we were
- * ready. Do it now.
- */
- nmi_enable();
- }
-
- dev_info(&pdev->dev,
- "External Interrupt Controller at 0x%p, IRQ %u\n",
- eic->regs, int_irq);
- dev_info(&pdev->dev,
- "Handling %u external IRQs, starting with IRQ %u\n",
- nr_of_irqs, eic->first_irq);
-
- return 0;
-
-err_ioremap:
- kfree(eic);
-err_kzalloc:
- return ret;
-}
-
-static struct platform_driver eic_driver = {
- .driver = {
- .name = "at32_eic",
- },
-};
-
-static int __init eic_init(void)
-{
- return platform_driver_probe(&eic_driver, eic_probe);
-}
-arch_initcall(eic_init);
+++ /dev/null
-/*
- * High-Speed Bus Matrix helper functions
- *
- * Copyright (C) 2008 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/clk.h>
-#include <linux/io.h>
-
-#include <mach/chip.h>
-#include <mach/hmatrix.h>
-
-static inline void __hmatrix_write_reg(unsigned long offset, u32 value)
-{
- __raw_writel(value, (void __iomem __force *)(HMATRIX_BASE + offset));
-}
-
-static inline u32 __hmatrix_read_reg(unsigned long offset)
-{
- return __raw_readl((void __iomem __force *)(HMATRIX_BASE + offset));
-}
-
-/**
- * hmatrix_write_reg - write HMATRIX configuration register
- * @offset: register offset
- * @value: value to be written to the register at @offset
- */
-void hmatrix_write_reg(unsigned long offset, u32 value)
-{
- clk_enable(&at32_hmatrix_clk);
- __hmatrix_write_reg(offset, value);
- __hmatrix_read_reg(offset);
- clk_disable(&at32_hmatrix_clk);
-}
-
-/**
- * hmatrix_read_reg - read HMATRIX configuration register
- * @offset: register offset
- *
- * Returns the value of the register at @offset.
- */
-u32 hmatrix_read_reg(unsigned long offset)
-{
- u32 value;
-
- clk_enable(&at32_hmatrix_clk);
- value = __hmatrix_read_reg(offset);
- clk_disable(&at32_hmatrix_clk);
-
- return value;
-}
-
-/**
- * hmatrix_sfr_set_bits - set bits in a slave's Special Function Register
- * @slave_id: operate on the SFR belonging to this slave
- * @mask: mask of bits to be set in the SFR
- */
-void hmatrix_sfr_set_bits(unsigned int slave_id, u32 mask)
-{
- u32 value;
-
- clk_enable(&at32_hmatrix_clk);
- value = __hmatrix_read_reg(HMATRIX_SFR(slave_id));
- value |= mask;
- __hmatrix_write_reg(HMATRIX_SFR(slave_id), value);
- __hmatrix_read_reg(HMATRIX_SFR(slave_id));
- clk_disable(&at32_hmatrix_clk);
-}
-
-/**
- * hmatrix_sfr_set_bits - clear bits in a slave's Special Function Register
- * @slave_id: operate on the SFR belonging to this slave
- * @mask: mask of bits to be cleared in the SFR
- */
-void hmatrix_sfr_clear_bits(unsigned int slave_id, u32 mask)
-{
- u32 value;
-
- clk_enable(&at32_hmatrix_clk);
- value = __hmatrix_read_reg(HMATRIX_SFR(slave_id));
- value &= ~mask;
- __hmatrix_write_reg(HMATRIX_SFR(slave_id), value);
- __hmatrix_read_reg(HMATRIX_SFR(slave_id));
- clk_disable(&at32_hmatrix_clk);
-}
+++ /dev/null
-/*
- * Static Memory Controller for AT32 chips
- *
- * Copyright (C) 2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/clk.h>
-#include <linux/err.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/slab.h>
-
-#include <asm/io.h>
-#include <mach/smc.h>
-
-#include "hsmc.h"
-
-#define NR_CHIP_SELECTS 6
-
-struct hsmc {
- void __iomem *regs;
- struct clk *pclk;
- struct clk *mck;
-};
-
-static struct hsmc *hsmc;
-
-void smc_set_timing(struct smc_config *config,
- const struct smc_timing *timing)
-{
- int recover;
- int cycle;
-
- unsigned long mul;
-
- /* Reset all SMC timings */
- config->ncs_read_setup = 0;
- config->nrd_setup = 0;
- config->ncs_write_setup = 0;
- config->nwe_setup = 0;
- config->ncs_read_pulse = 0;
- config->nrd_pulse = 0;
- config->ncs_write_pulse = 0;
- config->nwe_pulse = 0;
- config->read_cycle = 0;
- config->write_cycle = 0;
-
- /*
- * cycles = x / T = x * f
- * = ((x * 1000000000) * ((f * 65536) / 1000000000)) / 65536
- * = ((x * 1000000000) * (((f / 10000) * 65536) / 100000)) / 65536
- */
- mul = (clk_get_rate(hsmc->mck) / 10000) << 16;
- mul /= 100000;
-
-#define ns2cyc(x) ((((x) * mul) + 65535) >> 16)
-
- if (timing->ncs_read_setup > 0)
- config->ncs_read_setup = ns2cyc(timing->ncs_read_setup);
-
- if (timing->nrd_setup > 0)
- config->nrd_setup = ns2cyc(timing->nrd_setup);
-
- if (timing->ncs_write_setup > 0)
- config->ncs_write_setup = ns2cyc(timing->ncs_write_setup);
-
- if (timing->nwe_setup > 0)
- config->nwe_setup = ns2cyc(timing->nwe_setup);
-
- if (timing->ncs_read_pulse > 0)
- config->ncs_read_pulse = ns2cyc(timing->ncs_read_pulse);
-
- if (timing->nrd_pulse > 0)
- config->nrd_pulse = ns2cyc(timing->nrd_pulse);
-
- if (timing->ncs_write_pulse > 0)
- config->ncs_write_pulse = ns2cyc(timing->ncs_write_pulse);
-
- if (timing->nwe_pulse > 0)
- config->nwe_pulse = ns2cyc(timing->nwe_pulse);
-
- if (timing->read_cycle > 0)
- config->read_cycle = ns2cyc(timing->read_cycle);
-
- if (timing->write_cycle > 0)
- config->write_cycle = ns2cyc(timing->write_cycle);
-
- /* Extend read cycle in needed */
- if (timing->ncs_read_recover > 0)
- recover = ns2cyc(timing->ncs_read_recover);
- else
- recover = 1;
-
- cycle = config->ncs_read_setup + config->ncs_read_pulse + recover;
-
- if (config->read_cycle < cycle)
- config->read_cycle = cycle;
-
- /* Extend read cycle in needed */
- if (timing->nrd_recover > 0)
- recover = ns2cyc(timing->nrd_recover);
- else
- recover = 1;
-
- cycle = config->nrd_setup + config->nrd_pulse + recover;
-
- if (config->read_cycle < cycle)
- config->read_cycle = cycle;
-
- /* Extend write cycle in needed */
- if (timing->ncs_write_recover > 0)
- recover = ns2cyc(timing->ncs_write_recover);
- else
- recover = 1;
-
- cycle = config->ncs_write_setup + config->ncs_write_pulse + recover;
-
- if (config->write_cycle < cycle)
- config->write_cycle = cycle;
-
- /* Extend write cycle in needed */
- if (timing->nwe_recover > 0)
- recover = ns2cyc(timing->nwe_recover);
- else
- recover = 1;
-
- cycle = config->nwe_setup + config->nwe_pulse + recover;
-
- if (config->write_cycle < cycle)
- config->write_cycle = cycle;
-}
-EXPORT_SYMBOL(smc_set_timing);
-
-int smc_set_configuration(int cs, const struct smc_config *config)
-{
- unsigned long offset;
- u32 setup, pulse, cycle, mode;
-
- if (!hsmc)
- return -ENODEV;
- if (cs >= NR_CHIP_SELECTS)
- return -EINVAL;
-
- setup = (HSMC_BF(NWE_SETUP, config->nwe_setup)
- | HSMC_BF(NCS_WR_SETUP, config->ncs_write_setup)
- | HSMC_BF(NRD_SETUP, config->nrd_setup)
- | HSMC_BF(NCS_RD_SETUP, config->ncs_read_setup));
- pulse = (HSMC_BF(NWE_PULSE, config->nwe_pulse)
- | HSMC_BF(NCS_WR_PULSE, config->ncs_write_pulse)
- | HSMC_BF(NRD_PULSE, config->nrd_pulse)
- | HSMC_BF(NCS_RD_PULSE, config->ncs_read_pulse));
- cycle = (HSMC_BF(NWE_CYCLE, config->write_cycle)
- | HSMC_BF(NRD_CYCLE, config->read_cycle));
-
- switch (config->bus_width) {
- case 1:
- mode = HSMC_BF(DBW, HSMC_DBW_8_BITS);
- break;
- case 2:
- mode = HSMC_BF(DBW, HSMC_DBW_16_BITS);
- break;
- case 4:
- mode = HSMC_BF(DBW, HSMC_DBW_32_BITS);
- break;
- default:
- return -EINVAL;
- }
-
- switch (config->nwait_mode) {
- case 0:
- mode |= HSMC_BF(EXNW_MODE, HSMC_EXNW_MODE_DISABLED);
- break;
- case 1:
- mode |= HSMC_BF(EXNW_MODE, HSMC_EXNW_MODE_RESERVED);
- break;
- case 2:
- mode |= HSMC_BF(EXNW_MODE, HSMC_EXNW_MODE_FROZEN);
- break;
- case 3:
- mode |= HSMC_BF(EXNW_MODE, HSMC_EXNW_MODE_READY);
- break;
- default:
- return -EINVAL;
- }
-
- if (config->tdf_cycles) {
- mode |= HSMC_BF(TDF_CYCLES, config->tdf_cycles);
- }
-
- if (config->nrd_controlled)
- mode |= HSMC_BIT(READ_MODE);
- if (config->nwe_controlled)
- mode |= HSMC_BIT(WRITE_MODE);
- if (config->byte_write)
- mode |= HSMC_BIT(BAT);
- if (config->tdf_mode)
- mode |= HSMC_BIT(TDF_MODE);
-
- pr_debug("smc cs%d: setup/%08x pulse/%08x cycle/%08x mode/%08x\n",
- cs, setup, pulse, cycle, mode);
-
- offset = cs * 0x10;
- hsmc_writel(hsmc, SETUP0 + offset, setup);
- hsmc_writel(hsmc, PULSE0 + offset, pulse);
- hsmc_writel(hsmc, CYCLE0 + offset, cycle);
- hsmc_writel(hsmc, MODE0 + offset, mode);
- hsmc_readl(hsmc, MODE0); /* I/O barrier */
-
- return 0;
-}
-EXPORT_SYMBOL(smc_set_configuration);
-
-static int hsmc_probe(struct platform_device *pdev)
-{
- struct resource *regs;
- struct clk *pclk, *mck;
- int ret;
-
- if (hsmc)
- return -EBUSY;
-
- regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!regs)
- return -ENXIO;
- pclk = clk_get(&pdev->dev, "pclk");
- if (IS_ERR(pclk))
- return PTR_ERR(pclk);
- mck = clk_get(&pdev->dev, "mck");
- if (IS_ERR(mck)) {
- ret = PTR_ERR(mck);
- goto out_put_pclk;
- }
-
- ret = -ENOMEM;
- hsmc = kzalloc(sizeof(struct hsmc), GFP_KERNEL);
- if (!hsmc)
- goto out_put_clocks;
-
- clk_enable(pclk);
- clk_enable(mck);
-
- hsmc->pclk = pclk;
- hsmc->mck = mck;
- hsmc->regs = ioremap(regs->start, resource_size(regs));
- if (!hsmc->regs)
- goto out_disable_clocks;
-
- dev_info(&pdev->dev, "Atmel Static Memory Controller at 0x%08lx\n",
- (unsigned long)regs->start);
-
- platform_set_drvdata(pdev, hsmc);
-
- return 0;
-
-out_disable_clocks:
- clk_disable(mck);
- clk_disable(pclk);
- kfree(hsmc);
-out_put_clocks:
- clk_put(mck);
-out_put_pclk:
- clk_put(pclk);
- hsmc = NULL;
- return ret;
-}
-
-static struct platform_driver hsmc_driver = {
- .probe = hsmc_probe,
- .driver = {
- .name = "smc",
- },
-};
-
-static int __init hsmc_init(void)
-{
- return platform_driver_register(&hsmc_driver);
-}
-core_initcall(hsmc_init);
+++ /dev/null
-/*
- * Register definitions for Atmel Static Memory Controller (SMC)
- *
- * Copyright (C) 2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_HSMC_H__
-#define __ASM_AVR32_HSMC_H__
-
-/* HSMC register offsets */
-#define HSMC_SETUP0 0x0000
-#define HSMC_PULSE0 0x0004
-#define HSMC_CYCLE0 0x0008
-#define HSMC_MODE0 0x000c
-#define HSMC_SETUP1 0x0010
-#define HSMC_PULSE1 0x0014
-#define HSMC_CYCLE1 0x0018
-#define HSMC_MODE1 0x001c
-#define HSMC_SETUP2 0x0020
-#define HSMC_PULSE2 0x0024
-#define HSMC_CYCLE2 0x0028
-#define HSMC_MODE2 0x002c
-#define HSMC_SETUP3 0x0030
-#define HSMC_PULSE3 0x0034
-#define HSMC_CYCLE3 0x0038
-#define HSMC_MODE3 0x003c
-#define HSMC_SETUP4 0x0040
-#define HSMC_PULSE4 0x0044
-#define HSMC_CYCLE4 0x0048
-#define HSMC_MODE4 0x004c
-#define HSMC_SETUP5 0x0050
-#define HSMC_PULSE5 0x0054
-#define HSMC_CYCLE5 0x0058
-#define HSMC_MODE5 0x005c
-
-/* Bitfields in SETUP0 */
-#define HSMC_NWE_SETUP_OFFSET 0
-#define HSMC_NWE_SETUP_SIZE 6
-#define HSMC_NCS_WR_SETUP_OFFSET 8
-#define HSMC_NCS_WR_SETUP_SIZE 6
-#define HSMC_NRD_SETUP_OFFSET 16
-#define HSMC_NRD_SETUP_SIZE 6
-#define HSMC_NCS_RD_SETUP_OFFSET 24
-#define HSMC_NCS_RD_SETUP_SIZE 6
-
-/* Bitfields in PULSE0 */
-#define HSMC_NWE_PULSE_OFFSET 0
-#define HSMC_NWE_PULSE_SIZE 7
-#define HSMC_NCS_WR_PULSE_OFFSET 8
-#define HSMC_NCS_WR_PULSE_SIZE 7
-#define HSMC_NRD_PULSE_OFFSET 16
-#define HSMC_NRD_PULSE_SIZE 7
-#define HSMC_NCS_RD_PULSE_OFFSET 24
-#define HSMC_NCS_RD_PULSE_SIZE 7
-
-/* Bitfields in CYCLE0 */
-#define HSMC_NWE_CYCLE_OFFSET 0
-#define HSMC_NWE_CYCLE_SIZE 9
-#define HSMC_NRD_CYCLE_OFFSET 16
-#define HSMC_NRD_CYCLE_SIZE 9
-
-/* Bitfields in MODE0 */
-#define HSMC_READ_MODE_OFFSET 0
-#define HSMC_READ_MODE_SIZE 1
-#define HSMC_WRITE_MODE_OFFSET 1
-#define HSMC_WRITE_MODE_SIZE 1
-#define HSMC_EXNW_MODE_OFFSET 4
-#define HSMC_EXNW_MODE_SIZE 2
-#define HSMC_BAT_OFFSET 8
-#define HSMC_BAT_SIZE 1
-#define HSMC_DBW_OFFSET 12
-#define HSMC_DBW_SIZE 2
-#define HSMC_TDF_CYCLES_OFFSET 16
-#define HSMC_TDF_CYCLES_SIZE 4
-#define HSMC_TDF_MODE_OFFSET 20
-#define HSMC_TDF_MODE_SIZE 1
-#define HSMC_PMEN_OFFSET 24
-#define HSMC_PMEN_SIZE 1
-#define HSMC_PS_OFFSET 28
-#define HSMC_PS_SIZE 2
-
-/* Constants for READ_MODE */
-#define HSMC_READ_MODE_NCS_CONTROLLED 0
-#define HSMC_READ_MODE_NRD_CONTROLLED 1
-
-/* Constants for WRITE_MODE */
-#define HSMC_WRITE_MODE_NCS_CONTROLLED 0
-#define HSMC_WRITE_MODE_NWE_CONTROLLED 1
-
-/* Constants for EXNW_MODE */
-#define HSMC_EXNW_MODE_DISABLED 0
-#define HSMC_EXNW_MODE_RESERVED 1
-#define HSMC_EXNW_MODE_FROZEN 2
-#define HSMC_EXNW_MODE_READY 3
-
-/* Constants for BAT */
-#define HSMC_BAT_BYTE_SELECT 0
-#define HSMC_BAT_BYTE_WRITE 1
-
-/* Constants for DBW */
-#define HSMC_DBW_8_BITS 0
-#define HSMC_DBW_16_BITS 1
-#define HSMC_DBW_32_BITS 2
-
-/* Bit manipulation macros */
-#define HSMC_BIT(name) \
- (1 << HSMC_##name##_OFFSET)
-#define HSMC_BF(name,value) \
- (((value) & ((1 << HSMC_##name##_SIZE) - 1)) \
- << HSMC_##name##_OFFSET)
-#define HSMC_BFEXT(name,value) \
- (((value) >> HSMC_##name##_OFFSET) \
- & ((1 << HSMC_##name##_SIZE) - 1))
-#define HSMC_BFINS(name,value,old) \
- (((old) & ~(((1 << HSMC_##name##_SIZE) - 1) \
- << HSMC_##name##_OFFSET)) | HSMC_BF(name,value))
-
-/* Register access macros */
-#define hsmc_readl(port,reg) \
- __raw_readl((port)->regs + HSMC_##reg)
-#define hsmc_writel(port,reg,value) \
- __raw_writel((value), (port)->regs + HSMC_##reg)
-
-#endif /* __ASM_AVR32_HSMC_H__ */
+++ /dev/null
-/*
- * Pin definitions for AT32AP7000.
- *
- * Copyright (C) 2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_ARCH_AT32AP700X_H__
-#define __ASM_ARCH_AT32AP700X_H__
-
-#define GPIO_PERIPH_A 0
-#define GPIO_PERIPH_B 1
-
-/*
- * Pin numbers identifying specific GPIO pins on the chip. They can
- * also be converted to IRQ numbers by passing them through
- * gpio_to_irq().
- */
-#define GPIO_PIOA_BASE (0)
-#define GPIO_PIOB_BASE (GPIO_PIOA_BASE + 32)
-#define GPIO_PIOC_BASE (GPIO_PIOB_BASE + 32)
-#define GPIO_PIOD_BASE (GPIO_PIOC_BASE + 32)
-#define GPIO_PIOE_BASE (GPIO_PIOD_BASE + 32)
-
-#define GPIO_PIN_PA(N) (GPIO_PIOA_BASE + (N))
-#define GPIO_PIN_PB(N) (GPIO_PIOB_BASE + (N))
-#define GPIO_PIN_PC(N) (GPIO_PIOC_BASE + (N))
-#define GPIO_PIN_PD(N) (GPIO_PIOD_BASE + (N))
-#define GPIO_PIN_PE(N) (GPIO_PIOE_BASE + (N))
-
-
-/*
- * DMAC peripheral hardware handshaking interfaces, used with dw_dmac
- */
-#define DMAC_MCI_RX 0
-#define DMAC_MCI_TX 1
-#define DMAC_DAC_TX 2
-#define DMAC_AC97_A_RX 3
-#define DMAC_AC97_A_TX 4
-#define DMAC_AC97_B_RX 5
-#define DMAC_AC97_B_TX 6
-#define DMAC_DMAREQ_0 7
-#define DMAC_DMAREQ_1 8
-#define DMAC_DMAREQ_2 9
-#define DMAC_DMAREQ_3 10
-
-/* HSB master IDs */
-#define HMATRIX_MASTER_CPU_DCACHE 0
-#define HMATRIX_MASTER_CPU_ICACHE 1
-#define HMATRIX_MASTER_PDC 2
-#define HMATRIX_MASTER_ISI 3
-#define HMATRIX_MASTER_USBA 4
-#define HMATRIX_MASTER_LCDC 5
-#define HMATRIX_MASTER_MACB0 6
-#define HMATRIX_MASTER_MACB1 7
-#define HMATRIX_MASTER_DMACA_M0 8
-#define HMATRIX_MASTER_DMACA_M1 9
-
-/* HSB slave IDs */
-#define HMATRIX_SLAVE_SRAM0 0
-#define HMATRIX_SLAVE_SRAM1 1
-#define HMATRIX_SLAVE_PBA 2
-#define HMATRIX_SLAVE_PBB 3
-#define HMATRIX_SLAVE_EBI 4
-#define HMATRIX_SLAVE_USBA 5
-#define HMATRIX_SLAVE_LCDC 6
-#define HMATRIX_SLAVE_DMACA 7
-
-/* Bits in HMATRIX SFR4 (EBI) */
-#define HMATRIX_EBI_SDRAM_ENABLE (1 << 1)
-#define HMATRIX_EBI_NAND_ENABLE (1 << 3)
-#define HMATRIX_EBI_CF0_ENABLE (1 << 4)
-#define HMATRIX_EBI_CF1_ENABLE (1 << 5)
-#define HMATRIX_EBI_PULLUP_DISABLE (1 << 8)
-
-/*
- * Base addresses of controllers that may be accessed early by
- * platform code.
- */
-#define PM_BASE 0xfff00000
-#define HMATRIX_BASE 0xfff00800
-#define SDRAMC_BASE 0xfff03800
-
-/* LCDC on port C */
-#define ATMEL_LCDC_PC_CC (1ULL << 19)
-#define ATMEL_LCDC_PC_HSYNC (1ULL << 20)
-#define ATMEL_LCDC_PC_PCLK (1ULL << 21)
-#define ATMEL_LCDC_PC_VSYNC (1ULL << 22)
-#define ATMEL_LCDC_PC_DVAL (1ULL << 23)
-#define ATMEL_LCDC_PC_MODE (1ULL << 24)
-#define ATMEL_LCDC_PC_PWR (1ULL << 25)
-#define ATMEL_LCDC_PC_DATA0 (1ULL << 26)
-#define ATMEL_LCDC_PC_DATA1 (1ULL << 27)
-#define ATMEL_LCDC_PC_DATA2 (1ULL << 28)
-#define ATMEL_LCDC_PC_DATA3 (1ULL << 29)
-#define ATMEL_LCDC_PC_DATA4 (1ULL << 30)
-#define ATMEL_LCDC_PC_DATA5 (1ULL << 31)
-
-/* LCDC on port D */
-#define ATMEL_LCDC_PD_DATA6 (1ULL << 0)
-#define ATMEL_LCDC_PD_DATA7 (1ULL << 1)
-#define ATMEL_LCDC_PD_DATA8 (1ULL << 2)
-#define ATMEL_LCDC_PD_DATA9 (1ULL << 3)
-#define ATMEL_LCDC_PD_DATA10 (1ULL << 4)
-#define ATMEL_LCDC_PD_DATA11 (1ULL << 5)
-#define ATMEL_LCDC_PD_DATA12 (1ULL << 6)
-#define ATMEL_LCDC_PD_DATA13 (1ULL << 7)
-#define ATMEL_LCDC_PD_DATA14 (1ULL << 8)
-#define ATMEL_LCDC_PD_DATA15 (1ULL << 9)
-#define ATMEL_LCDC_PD_DATA16 (1ULL << 10)
-#define ATMEL_LCDC_PD_DATA17 (1ULL << 11)
-#define ATMEL_LCDC_PD_DATA18 (1ULL << 12)
-#define ATMEL_LCDC_PD_DATA19 (1ULL << 13)
-#define ATMEL_LCDC_PD_DATA20 (1ULL << 14)
-#define ATMEL_LCDC_PD_DATA21 (1ULL << 15)
-#define ATMEL_LCDC_PD_DATA22 (1ULL << 16)
-#define ATMEL_LCDC_PD_DATA23 (1ULL << 17)
-
-/* LCDC on port E */
-#define ATMEL_LCDC_PE_CC (1ULL << (32 + 0))
-#define ATMEL_LCDC_PE_DVAL (1ULL << (32 + 1))
-#define ATMEL_LCDC_PE_MODE (1ULL << (32 + 2))
-#define ATMEL_LCDC_PE_DATA0 (1ULL << (32 + 3))
-#define ATMEL_LCDC_PE_DATA1 (1ULL << (32 + 4))
-#define ATMEL_LCDC_PE_DATA2 (1ULL << (32 + 5))
-#define ATMEL_LCDC_PE_DATA3 (1ULL << (32 + 6))
-#define ATMEL_LCDC_PE_DATA4 (1ULL << (32 + 7))
-#define ATMEL_LCDC_PE_DATA8 (1ULL << (32 + 8))
-#define ATMEL_LCDC_PE_DATA9 (1ULL << (32 + 9))
-#define ATMEL_LCDC_PE_DATA10 (1ULL << (32 + 10))
-#define ATMEL_LCDC_PE_DATA11 (1ULL << (32 + 11))
-#define ATMEL_LCDC_PE_DATA12 (1ULL << (32 + 12))
-#define ATMEL_LCDC_PE_DATA16 (1ULL << (32 + 13))
-#define ATMEL_LCDC_PE_DATA17 (1ULL << (32 + 14))
-#define ATMEL_LCDC_PE_DATA18 (1ULL << (32 + 15))
-#define ATMEL_LCDC_PE_DATA19 (1ULL << (32 + 16))
-#define ATMEL_LCDC_PE_DATA20 (1ULL << (32 + 17))
-#define ATMEL_LCDC_PE_DATA21 (1ULL << (32 + 18))
-
-
-#define ATMEL_LCDC(PORT, PIN) (ATMEL_LCDC_##PORT##_##PIN)
-
-
-#define ATMEL_LCDC_PRI_24B_DATA ( \
- ATMEL_LCDC(PC, DATA0) | ATMEL_LCDC(PC, DATA1) | \
- ATMEL_LCDC(PC, DATA2) | ATMEL_LCDC(PC, DATA3) | \
- ATMEL_LCDC(PC, DATA4) | ATMEL_LCDC(PC, DATA5) | \
- ATMEL_LCDC(PD, DATA6) | ATMEL_LCDC(PD, DATA7) | \
- ATMEL_LCDC(PD, DATA8) | ATMEL_LCDC(PD, DATA9) | \
- ATMEL_LCDC(PD, DATA10) | ATMEL_LCDC(PD, DATA11) | \
- ATMEL_LCDC(PD, DATA12) | ATMEL_LCDC(PD, DATA13) | \
- ATMEL_LCDC(PD, DATA14) | ATMEL_LCDC(PD, DATA15) | \
- ATMEL_LCDC(PD, DATA16) | ATMEL_LCDC(PD, DATA17) | \
- ATMEL_LCDC(PD, DATA18) | ATMEL_LCDC(PD, DATA19) | \
- ATMEL_LCDC(PD, DATA20) | ATMEL_LCDC(PD, DATA21) | \
- ATMEL_LCDC(PD, DATA22) | ATMEL_LCDC(PD, DATA23))
-
-#define ATMEL_LCDC_ALT_24B_DATA ( \
- ATMEL_LCDC(PE, DATA0) | ATMEL_LCDC(PE, DATA1) | \
- ATMEL_LCDC(PE, DATA2) | ATMEL_LCDC(PE, DATA3) | \
- ATMEL_LCDC(PE, DATA4) | ATMEL_LCDC(PC, DATA5) | \
- ATMEL_LCDC(PD, DATA6) | ATMEL_LCDC(PD, DATA7) | \
- ATMEL_LCDC(PE, DATA8) | ATMEL_LCDC(PE, DATA9) | \
- ATMEL_LCDC(PE, DATA10) | ATMEL_LCDC(PE, DATA11) | \
- ATMEL_LCDC(PE, DATA12) | ATMEL_LCDC(PD, DATA13) | \
- ATMEL_LCDC(PD, DATA14) | ATMEL_LCDC(PD, DATA15) | \
- ATMEL_LCDC(PE, DATA16) | ATMEL_LCDC(PE, DATA17) | \
- ATMEL_LCDC(PE, DATA18) | ATMEL_LCDC(PE, DATA19) | \
- ATMEL_LCDC(PE, DATA20) | ATMEL_LCDC(PE, DATA21) | \
- ATMEL_LCDC(PD, DATA22) | ATMEL_LCDC(PD, DATA23))
-
-#define ATMEL_LCDC_PRI_18B_DATA ( \
- ATMEL_LCDC(PC, DATA2) | ATMEL_LCDC(PC, DATA3) | \
- ATMEL_LCDC(PC, DATA4) | ATMEL_LCDC(PC, DATA5) | \
- ATMEL_LCDC(PD, DATA6) | ATMEL_LCDC(PD, DATA7) | \
- ATMEL_LCDC(PD, DATA10) | ATMEL_LCDC(PD, DATA11) | \
- ATMEL_LCDC(PD, DATA12) | ATMEL_LCDC(PD, DATA13) | \
- ATMEL_LCDC(PD, DATA14) | ATMEL_LCDC(PD, DATA15) | \
- ATMEL_LCDC(PD, DATA18) | ATMEL_LCDC(PD, DATA19) | \
- ATMEL_LCDC(PD, DATA20) | ATMEL_LCDC(PD, DATA21) | \
- ATMEL_LCDC(PD, DATA22) | ATMEL_LCDC(PD, DATA23))
-
-#define ATMEL_LCDC_ALT_18B_DATA ( \
- ATMEL_LCDC(PE, DATA2) | ATMEL_LCDC(PE, DATA3) | \
- ATMEL_LCDC(PE, DATA4) | ATMEL_LCDC(PC, DATA5) | \
- ATMEL_LCDC(PD, DATA6) | ATMEL_LCDC(PD, DATA7) | \
- ATMEL_LCDC(PE, DATA10) | ATMEL_LCDC(PE, DATA11) | \
- ATMEL_LCDC(PE, DATA12) | ATMEL_LCDC(PD, DATA13) | \
- ATMEL_LCDC(PD, DATA14) | ATMEL_LCDC(PD, DATA15) | \
- ATMEL_LCDC(PE, DATA18) | ATMEL_LCDC(PE, DATA19) | \
- ATMEL_LCDC(PE, DATA20) | ATMEL_LCDC(PE, DATA21) | \
- ATMEL_LCDC(PD, DATA22) | ATMEL_LCDC(PD, DATA23))
-
-#define ATMEL_LCDC_PRI_15B_DATA ( \
- ATMEL_LCDC(PC, DATA3) | ATMEL_LCDC(PC, DATA4) | \
- ATMEL_LCDC(PC, DATA5) | ATMEL_LCDC(PD, DATA6) | \
- ATMEL_LCDC(PD, DATA7) | \
- ATMEL_LCDC(PD, DATA11) | ATMEL_LCDC(PD, DATA12) | \
- ATMEL_LCDC(PD, DATA13) | ATMEL_LCDC(PD, DATA14) | \
- ATMEL_LCDC(PD, DATA15) | \
- ATMEL_LCDC(PD, DATA19) | ATMEL_LCDC(PD, DATA20) | \
- ATMEL_LCDC(PD, DATA21) | ATMEL_LCDC(PD, DATA22) | \
- ATMEL_LCDC(PD, DATA23))
-
-#define ATMEL_LCDC_ALT_15B_DATA ( \
- ATMEL_LCDC(PE, DATA3) | ATMEL_LCDC(PE, DATA4) | \
- ATMEL_LCDC(PC, DATA5) | ATMEL_LCDC(PD, DATA6) | \
- ATMEL_LCDC(PD, DATA7) | \
- ATMEL_LCDC(PE, DATA11) | ATMEL_LCDC(PE, DATA12) | \
- ATMEL_LCDC(PD, DATA13) | ATMEL_LCDC(PD, DATA14) | \
- ATMEL_LCDC(PD, DATA15) | \
- ATMEL_LCDC(PE, DATA19) | ATMEL_LCDC(PE, DATA20) | \
- ATMEL_LCDC(PE, DATA21) | ATMEL_LCDC(PD, DATA22) | \
- ATMEL_LCDC(PD, DATA23))
-
-#define ATMEL_LCDC_PRI_CONTROL ( \
- ATMEL_LCDC(PC, CC) | ATMEL_LCDC(PC, DVAL) | \
- ATMEL_LCDC(PC, MODE) | ATMEL_LCDC(PC, PWR))
-
-#define ATMEL_LCDC_ALT_CONTROL ( \
- ATMEL_LCDC(PE, CC) | ATMEL_LCDC(PE, DVAL) | \
- ATMEL_LCDC(PE, MODE) | ATMEL_LCDC(PC, PWR))
-
-#define ATMEL_LCDC_CONTROL ( \
- ATMEL_LCDC(PC, HSYNC) | ATMEL_LCDC(PC, VSYNC) | \
- ATMEL_LCDC(PC, PCLK))
-
-#define ATMEL_LCDC_PRI_24BIT (ATMEL_LCDC_CONTROL | ATMEL_LCDC_PRI_24B_DATA)
-
-#define ATMEL_LCDC_ALT_24BIT (ATMEL_LCDC_CONTROL | ATMEL_LCDC_ALT_24B_DATA)
-
-#define ATMEL_LCDC_PRI_18BIT (ATMEL_LCDC_CONTROL | ATMEL_LCDC_PRI_18B_DATA)
-
-#define ATMEL_LCDC_ALT_18BIT (ATMEL_LCDC_CONTROL | ATMEL_LCDC_ALT_18B_DATA)
-
-#define ATMEL_LCDC_PRI_15BIT (ATMEL_LCDC_CONTROL | ATMEL_LCDC_PRI_15B_DATA)
-
-#define ATMEL_LCDC_ALT_15BIT (ATMEL_LCDC_CONTROL | ATMEL_LCDC_ALT_15B_DATA)
-
-/* Bitmask for all EBI data (D16..D31) pins on port E */
-#define ATMEL_EBI_PE_DATA_ALL (0x0000FFFF)
-
-#endif /* __ASM_ARCH_AT32AP700X_H__ */
+++ /dev/null
-/*
- * Platform data definitions.
- */
-#ifndef __ASM_ARCH_BOARD_H
-#define __ASM_ARCH_BOARD_H
-
-#include <linux/types.h>
-#include <linux/serial.h>
-#include <linux/platform_data/macb.h>
-#include <linux/platform_data/atmel.h>
-
-#define GPIO_PIN_NONE (-1)
-
-/*
- * Clock rates for various on-board oscillators. The number of entries
- * in this array is chip-dependent.
- */
-extern unsigned long at32_board_osc_rates[];
-
-/*
- * This used to add essential system devices, but this is now done
- * automatically. Please don't use it in new board code.
- */
-static inline void __deprecated at32_add_system_devices(void)
-{
-
-}
-
-extern struct platform_device *atmel_default_console_device;
-
-/* Flags for selecting USART extra pins */
-#define ATMEL_USART_RTS 0x01
-#define ATMEL_USART_CTS 0x02
-#define ATMEL_USART_CLK 0x04
-
-void at32_map_usart(unsigned int hw_id, unsigned int line, int flags);
-struct platform_device *at32_add_device_usart(unsigned int id);
-
-struct platform_device *
-at32_add_device_eth(unsigned int id, struct macb_platform_data *data);
-
-struct spi_board_info;
-struct platform_device *
-at32_add_device_spi(unsigned int id, struct spi_board_info *b, unsigned int n);
-void at32_spi_setup_slaves(unsigned int bus_num, struct spi_board_info *b, unsigned int n);
-
-struct atmel_lcdfb_pdata;
-struct platform_device *
-at32_add_device_lcdc(unsigned int id, struct atmel_lcdfb_pdata *data,
- unsigned long fbmem_start, unsigned long fbmem_len,
- u64 pin_mask);
-
-struct usba_platform_data;
-struct platform_device *
-at32_add_device_usba(unsigned int id, struct usba_platform_data *data);
-
-struct ide_platform_data {
- u8 cs;
-};
-struct platform_device *
-at32_add_device_ide(unsigned int id, unsigned int extint,
- struct ide_platform_data *data);
-
-/* mask says which PWM channels to mux */
-struct platform_device *at32_add_device_pwm(u32 mask);
-
-/* depending on what's hooked up, not all SSC pins will be used */
-#define ATMEL_SSC_TK 0x01
-#define ATMEL_SSC_TF 0x02
-#define ATMEL_SSC_TD 0x04
-#define ATMEL_SSC_TX (ATMEL_SSC_TK | ATMEL_SSC_TF | ATMEL_SSC_TD)
-
-#define ATMEL_SSC_RK 0x10
-#define ATMEL_SSC_RF 0x20
-#define ATMEL_SSC_RD 0x40
-#define ATMEL_SSC_RX (ATMEL_SSC_RK | ATMEL_SSC_RF | ATMEL_SSC_RD)
-
-struct platform_device *
-at32_add_device_ssc(unsigned int id, unsigned int flags);
-
-struct i2c_board_info;
-struct platform_device *at32_add_device_twi(unsigned int id,
- struct i2c_board_info *b,
- unsigned int n);
-
-struct mci_platform_data;
-struct platform_device *
-at32_add_device_mci(unsigned int id, struct mci_platform_data *data);
-
-struct ac97c_platform_data;
-struct platform_device *
-at32_add_device_ac97c(unsigned int id, struct ac97c_platform_data *data,
- unsigned int flags);
-
-struct atmel_abdac_pdata;
-struct platform_device *
-at32_add_device_abdac(unsigned int id, struct atmel_abdac_pdata *data);
-
-struct platform_device *at32_add_device_psif(unsigned int id);
-
-struct cf_platform_data {
- int detect_pin;
- int reset_pin;
- int vcc_pin;
- int ready_pin;
- u8 cs;
-};
-struct platform_device *
-at32_add_device_cf(unsigned int id, unsigned int extint,
- struct cf_platform_data *data);
-
-struct platform_device *
-at32_add_device_nand(unsigned int id, struct atmel_nand_data *data);
-
-#endif /* __ASM_ARCH_BOARD_H */
+++ /dev/null
-/*
- * AVR32 chip-specific definitions
- *
- * Copyright (C) 2008 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_ARCH_CHIP_H__
-#define __ASM_AVR32_ARCH_CHIP_H__
-
-#if defined(CONFIG_CPU_AT32AP700X)
-# include <mach/at32ap700x.h>
-#else
-# error Unknown chip type selected
-#endif
-
-#endif /* __ASM_AVR32_ARCH_CHIP_H__ */
+++ /dev/null
-/*
- * AVR32 CPU identification
- *
- * Copyright (C) 2007 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_ARCH_CPU_H
-#define __ASM_ARCH_CPU_H
-
-/*
- * Only AT32AP7000 is defined for now. We can identify the specific
- * chip at runtime, but I'm not sure if it's really worth it.
- */
-#ifdef CONFIG_CPU_AT32AP700X
-# define cpu_is_at32ap7000() (1)
-#else
-# define cpu_is_at32ap7000() (0)
-#endif
-
-#endif /* __ASM_ARCH_CPU_H */
+++ /dev/null
-#ifndef __ASM_AVR32_ARCH_GPIO_H
-#define __ASM_AVR32_ARCH_GPIO_H
-
-#include <linux/compiler.h>
-#include <asm/irq.h>
-
-
-/* Some GPIO chips can manage IRQs; some can't. The exact numbers can
- * be changed if needed, but for the moment they're not configurable.
- */
-#define ARCH_NR_GPIOS (NR_GPIO_IRQS + 2 * 32)
-
-
-/* Arch-neutral GPIO API, supporting both "native" and external GPIOs. */
-#include <asm-generic/gpio.h>
-
-static inline int gpio_get_value(unsigned int gpio)
-{
- return __gpio_get_value(gpio);
-}
-
-static inline void gpio_set_value(unsigned int gpio, int value)
-{
- __gpio_set_value(gpio, value);
-}
-
-static inline int gpio_cansleep(unsigned int gpio)
-{
- return __gpio_cansleep(gpio);
-}
-
-
-static inline int gpio_to_irq(unsigned int gpio)
-{
- if (gpio < NR_GPIO_IRQS)
- return gpio + GPIO_IRQ_BASE;
- return -EINVAL;
-}
-
-static inline int irq_to_gpio(unsigned int irq)
-{
- return irq - GPIO_IRQ_BASE;
-}
-
-#endif /* __ASM_AVR32_ARCH_GPIO_H */
+++ /dev/null
-/*
- * High-Speed Bus Matrix configuration registers
- *
- * Copyright (C) 2008 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __HMATRIX_H
-#define __HMATRIX_H
-
-extern struct clk at32_hmatrix_clk;
-
-void hmatrix_write_reg(unsigned long offset, u32 value);
-u32 hmatrix_read_reg(unsigned long offset);
-
-void hmatrix_sfr_set_bits(unsigned int slave_id, u32 mask);
-void hmatrix_sfr_clear_bits(unsigned int slave_id, u32 mask);
-
-/* Master Configuration register */
-#define HMATRIX_MCFG(m) (0x0000 + 4 * (m))
-/* Undefined length burst limit */
-# define HMATRIX_MCFG_ULBT_INFINITE 0 /* Infinite length */
-# define HMATRIX_MCFG_ULBT_SINGLE 1 /* Single Access */
-# define HMATRIX_MCFG_ULBT_FOUR_BEAT 2 /* Four beat */
-# define HMATRIX_MCFG_ULBT_EIGHT_BEAT 3 /* Eight beat */
-# define HMATRIX_MCFG_ULBT_SIXTEEN_BEAT 4 /* Sixteen beat */
-
-/* Slave Configuration register */
-#define HMATRIX_SCFG(s) (0x0040 + 4 * (s))
-# define HMATRIX_SCFG_SLOT_CYCLE(x) ((x) << 0) /* Max burst cycles */
-# define HMATRIX_SCFG_DEFMSTR_NONE ( 0 << 16) /* No default master */
-# define HMATRIX_SCFG_DEFMSTR_LAST ( 1 << 16) /* Last def master */
-# define HMATRIX_SCFG_DEFMSTR_FIXED ( 2 << 16) /* Fixed def master */
-# define HMATRIX_SCFG_FIXED_DEFMSTR(m) ((m) << 18) /* Fixed master ID */
-# define HMATRIX_SCFG_ARBT_ROUND_ROBIN ( 0 << 24) /* RR arbitration */
-# define HMATRIX_SCFG_ARBT_FIXED_PRIO ( 1 << 24) /* Fixed priority */
-
-/* Slave Priority register A (master 0..7) */
-#define HMATRIX_PRAS(s) (0x0080 + 8 * (s))
-# define HMATRIX_PRAS_PRIO(m, p) ((p) << ((m) * 4))
-
-/* Slave Priority register A (master 8..15) */
-#define HMATRIX_PRBS(s) (0x0084 + 8 * (s))
-# define HMATRIX_PRBS_PRIO(m, p) ((p) << (((m) - 8) * 4))
-
-/* Master Remap Control Register */
-#define HMATRIX_MRCR 0x0100
-# define HMATRIX_MRCR_REMAP(m) ( 1 << (m)) /* Remap master m */
-
-/* Special Function Register. Bit definitions are chip-specific */
-#define HMATRIX_SFR(s) (0x0110 + 4 * (s))
-
-#endif /* __HMATRIX_H */
+++ /dev/null
-/*
- * AT32AP platform initialization calls.
- *
- * Copyright (C) 2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_AT32AP_INIT_H__
-#define __ASM_AVR32_AT32AP_INIT_H__
-
-void setup_platform(void);
-void setup_board(void);
-
-void at32_setup_serial_console(unsigned int usart_id);
-
-#endif /* __ASM_AVR32_AT32AP_INIT_H__ */
+++ /dev/null
-#ifndef __ASM_AVR32_ARCH_AT32AP_IO_H
-#define __ASM_AVR32_ARCH_AT32AP_IO_H
-
-#include <linux/swab.h>
-
-#if defined(CONFIG_AP700X_32_BIT_SMC)
-# define __swizzle_addr_b(addr) (addr ^ 3UL)
-# define __swizzle_addr_w(addr) (addr ^ 2UL)
-# define __swizzle_addr_l(addr) (addr)
-# define ioswabb(a, x) (x)
-# define ioswabw(a, x) (x)
-# define ioswabl(a, x) (x)
-# define __mem_ioswabb(a, x) (x)
-# define __mem_ioswabw(a, x) swab16(x)
-# define __mem_ioswabl(a, x) swab32(x)
-#elif defined(CONFIG_AP700X_16_BIT_SMC)
-# define __swizzle_addr_b(addr) (addr ^ 1UL)
-# define __swizzle_addr_w(addr) (addr)
-# define __swizzle_addr_l(addr) (addr)
-# define ioswabb(a, x) (x)
-# define ioswabw(a, x) (x)
-# define ioswabl(a, x) swahw32(x)
-# define __mem_ioswabb(a, x) (x)
-# define __mem_ioswabw(a, x) swab16(x)
-# define __mem_ioswabl(a, x) swahb32(x)
-#else
-# define __swizzle_addr_b(addr) (addr)
-# define __swizzle_addr_w(addr) (addr)
-# define __swizzle_addr_l(addr) (addr)
-# define ioswabb(a, x) (x)
-# define ioswabw(a, x) swab16(x)
-# define ioswabl(a, x) swab32(x)
-# define __mem_ioswabb(a, x) (x)
-# define __mem_ioswabw(a, x) (x)
-# define __mem_ioswabl(a, x) (x)
-#endif
-
-#endif /* __ASM_AVR32_ARCH_AT32AP_IO_H */
+++ /dev/null
-#ifndef __ASM_AVR32_ARCH_IRQ_H
-#define __ASM_AVR32_ARCH_IRQ_H
-
-#define EIM_IRQ_BASE NR_INTERNAL_IRQS
-#define NR_EIM_IRQS 32
-#define AT32_EXTINT(n) (EIM_IRQ_BASE + (n))
-
-#define GPIO_IRQ_BASE (EIM_IRQ_BASE + NR_EIM_IRQS)
-#define NR_GPIO_CTLR (5 /*internal*/ + 1 /*external*/)
-#define NR_GPIO_IRQS (NR_GPIO_CTLR * 32)
-
-#define NR_IRQS (GPIO_IRQ_BASE + NR_GPIO_IRQS)
-
-#endif /* __ASM_AVR32_ARCH_IRQ_H */
+++ /dev/null
-/*
- * AVR32 AP Power Management.
- *
- * Copyright (C) 2008 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_ARCH_PM_H
-#define __ASM_AVR32_ARCH_PM_H
-
-/* Possible arguments to the "sleep" instruction */
-#define CPU_SLEEP_IDLE 0
-#define CPU_SLEEP_FROZEN 1
-#define CPU_SLEEP_STANDBY 2
-#define CPU_SLEEP_STOP 3
-#define CPU_SLEEP_STATIC 5
-
-#ifndef __ASSEMBLY__
-extern void cpu_enter_idle(void);
-extern void cpu_enter_standby(unsigned long sdramc_base);
-
-void intc_set_suspend_handler(unsigned long offset);
-#endif
-
-#endif /* __ASM_AVR32_ARCH_PM_H */
+++ /dev/null
-/*
- * AT32 portmux interface.
- *
- * Copyright (C) 2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_ARCH_PORTMUX_H__
-#define __ASM_ARCH_PORTMUX_H__
-
-/*
- * Set up pin multiplexing, called from board init only.
- *
- * The following flags determine the initial state of the pin.
- */
-#define AT32_GPIOF_PULLUP 0x00000001 /* (not-OUT) Enable pull-up */
-#define AT32_GPIOF_OUTPUT 0x00000002 /* (OUT) Enable output driver */
-#define AT32_GPIOF_HIGH 0x00000004 /* (OUT) Set output high */
-#define AT32_GPIOF_DEGLITCH 0x00000008 /* (IN) Filter glitches */
-#define AT32_GPIOF_MULTIDRV 0x00000010 /* Enable multidriver option */
-
-void at32_select_periph(unsigned int port, unsigned int pin,
- unsigned int periph, unsigned long flags);
-void at32_select_gpio(unsigned int pin, unsigned long flags);
-void at32_deselect_pin(unsigned int pin);
-void at32_reserve_pin(unsigned int port, u32 pin_mask);
-
-#endif /* __ASM_ARCH_PORTMUX_H__ */
+++ /dev/null
-/*
- * Static Memory Controller for AT32 chips
- *
- * Copyright (C) 2006 Atmel Corporation
- *
- * Inspired by the OMAP2 General-Purpose Memory Controller interface
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ARCH_AT32AP_SMC_H
-#define __ARCH_AT32AP_SMC_H
-
-/*
- * All timing parameters are in nanoseconds.
- */
-struct smc_timing {
- /* Delay from address valid to assertion of given strobe */
- int ncs_read_setup;
- int nrd_setup;
- int ncs_write_setup;
- int nwe_setup;
-
- /* Pulse length of given strobe */
- int ncs_read_pulse;
- int nrd_pulse;
- int ncs_write_pulse;
- int nwe_pulse;
-
- /* Total cycle length of given operation */
- int read_cycle;
- int write_cycle;
-
- /* Minimal recovery times, will extend cycle if needed */
- int ncs_read_recover;
- int nrd_recover;
- int ncs_write_recover;
- int nwe_recover;
-};
-
-/*
- * All timing parameters are in clock cycles.
- */
-struct smc_config {
-
- /* Delay from address valid to assertion of given strobe */
- u8 ncs_read_setup;
- u8 nrd_setup;
- u8 ncs_write_setup;
- u8 nwe_setup;
-
- /* Pulse length of given strobe */
- u8 ncs_read_pulse;
- u8 nrd_pulse;
- u8 ncs_write_pulse;
- u8 nwe_pulse;
-
- /* Total cycle length of given operation */
- u8 read_cycle;
- u8 write_cycle;
-
- /* Bus width in bytes */
- u8 bus_width;
-
- /*
- * 0: Data is sampled on rising edge of NCS
- * 1: Data is sampled on rising edge of NRD
- */
- unsigned int nrd_controlled:1;
-
- /*
- * 0: Data is driven on falling edge of NCS
- * 1: Data is driven on falling edge of NWR
- */
- unsigned int nwe_controlled:1;
-
- /*
- * 0: NWAIT is disabled
- * 1: Reserved
- * 2: NWAIT is frozen mode
- * 3: NWAIT in ready mode
- */
- unsigned int nwait_mode:2;
-
- /*
- * 0: Byte select access type
- * 1: Byte write access type
- */
- unsigned int byte_write:1;
-
- /*
- * Number of clock cycles before data is released after
- * the rising edge of the read controlling signal
- *
- * Total cycles from SMC is tdf_cycles + 1
- */
- unsigned int tdf_cycles:4;
-
- /*
- * 0: TDF optimization disabled
- * 1: TDF optimization enabled
- */
- unsigned int tdf_mode:1;
-};
-
-extern void smc_set_timing(struct smc_config *config,
- const struct smc_timing *timing);
-
-extern int smc_set_configuration(int cs, const struct smc_config *config);
-extern struct smc_config *smc_get_configuration(int cs);
-
-#endif /* __ARCH_AT32AP_SMC_H */
+++ /dev/null
-/*
- * Simple SRAM allocator
- *
- * Copyright (C) 2008 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ASM_AVR32_ARCH_SRAM_H
-#define __ASM_AVR32_ARCH_SRAM_H
-
-#include <linux/genalloc.h>
-
-extern struct gen_pool *sram_pool;
-
-static inline unsigned long sram_alloc(size_t len)
-{
- if (!sram_pool)
- return 0UL;
-
- return gen_pool_alloc(sram_pool, len);
-}
-
-static inline void sram_free(unsigned long addr, size_t len)
-{
- return gen_pool_free(sram_pool, addr, len);
-}
-
-#endif /* __ASM_AVR32_ARCH_SRAM_H */
+++ /dev/null
-/*
- * Copyright (C) 2006, 2008 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/clk.h>
-#include <linux/err.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/platform_device.h>
-#include <linux/syscore_ops.h>
-#include <linux/export.h>
-
-#include <asm/io.h>
-
-#include "intc.h"
-
-struct intc {
- void __iomem *regs;
- struct irq_chip chip;
-#ifdef CONFIG_PM
- unsigned long suspend_ipr;
- unsigned long saved_ipr[64];
-#endif
-};
-
-extern struct platform_device at32_intc0_device;
-
-/*
- * TODO: We may be able to implement mask/unmask by setting IxM flags
- * in the status register.
- */
-static void intc_mask_irq(struct irq_data *d)
-{
-
-}
-
-static void intc_unmask_irq(struct irq_data *d)
-{
-
-}
-
-static struct intc intc0 = {
- .chip = {
- .name = "intc",
- .irq_mask = intc_mask_irq,
- .irq_unmask = intc_unmask_irq,
- },
-};
-
-/*
- * All interrupts go via intc at some point.
- */
-asmlinkage void do_IRQ(int level, struct pt_regs *regs)
-{
- struct pt_regs *old_regs;
- unsigned int irq;
- unsigned long status_reg;
-
- local_irq_disable();
-
- old_regs = set_irq_regs(regs);
-
- irq_enter();
-
- irq = intc_readl(&intc0, INTCAUSE0 - 4 * level);
- generic_handle_irq(irq);
-
- /*
- * Clear all interrupt level masks so that we may handle
- * interrupts during softirq processing. If this is a nested
- * interrupt, interrupts must stay globally disabled until we
- * return.
- */
- status_reg = sysreg_read(SR);
- status_reg &= ~(SYSREG_BIT(I0M) | SYSREG_BIT(I1M)
- | SYSREG_BIT(I2M) | SYSREG_BIT(I3M));
- sysreg_write(SR, status_reg);
-
- irq_exit();
-
- set_irq_regs(old_regs);
-}
-
-void __init init_IRQ(void)
-{
- extern void _evba(void);
- extern void irq_level0(void);
- struct resource *regs;
- struct clk *pclk;
- unsigned int i;
- u32 offset, readback;
-
- regs = platform_get_resource(&at32_intc0_device, IORESOURCE_MEM, 0);
- if (!regs) {
- printk(KERN_EMERG "intc: no mmio resource defined\n");
- goto fail;
- }
- pclk = clk_get(&at32_intc0_device.dev, "pclk");
- if (IS_ERR(pclk)) {
- printk(KERN_EMERG "intc: no clock defined\n");
- goto fail;
- }
-
- clk_enable(pclk);
-
- intc0.regs = ioremap(regs->start, resource_size(regs));
- if (!intc0.regs) {
- printk(KERN_EMERG "intc: failed to map registers (0x%08lx)\n",
- (unsigned long)regs->start);
- goto fail;
- }
-
- /*
- * Initialize all interrupts to level 0 (lowest priority). The
- * priority level may be changed by calling
- * irq_set_priority().
- *
- */
- offset = (unsigned long)&irq_level0 - (unsigned long)&_evba;
- for (i = 0; i < NR_INTERNAL_IRQS; i++) {
- intc_writel(&intc0, INTPR0 + 4 * i, offset);
- readback = intc_readl(&intc0, INTPR0 + 4 * i);
- if (readback == offset)
- irq_set_chip_and_handler(i, &intc0.chip,
- handle_simple_irq);
- }
-
- /* Unmask all interrupt levels */
- sysreg_write(SR, (sysreg_read(SR)
- & ~(SR_I3M | SR_I2M | SR_I1M | SR_I0M)));
-
- return;
-
-fail:
- panic("Interrupt controller initialization failed!\n");
-}
-
-#ifdef CONFIG_PM
-void intc_set_suspend_handler(unsigned long offset)
-{
- intc0.suspend_ipr = offset;
-}
-
-static int intc_suspend(void)
-{
- int i;
-
- if (unlikely(!irqs_disabled())) {
- pr_err("intc_suspend: called with interrupts enabled\n");
- return -EINVAL;
- }
-
- if (unlikely(!intc0.suspend_ipr)) {
- pr_err("intc_suspend: suspend_ipr not initialized\n");
- return -EINVAL;
- }
-
- for (i = 0; i < 64; i++) {
- intc0.saved_ipr[i] = intc_readl(&intc0, INTPR0 + 4 * i);
- intc_writel(&intc0, INTPR0 + 4 * i, intc0.suspend_ipr);
- }
-
- return 0;
-}
-
-static void intc_resume(void)
-{
- int i;
-
- for (i = 0; i < 64; i++)
- intc_writel(&intc0, INTPR0 + 4 * i, intc0.saved_ipr[i]);
-}
-#else
-#define intc_suspend NULL
-#define intc_resume NULL
-#endif
-
-static struct syscore_ops intc_syscore_ops = {
- .suspend = intc_suspend,
- .resume = intc_resume,
-};
-
-static int __init intc_init_syscore(void)
-{
- register_syscore_ops(&intc_syscore_ops);
-
- return 0;
-}
-device_initcall(intc_init_syscore);
-
-unsigned long intc_get_pending(unsigned int group)
-{
- return intc_readl(&intc0, INTREQ0 + 4 * group);
-}
-EXPORT_SYMBOL_GPL(intc_get_pending);
+++ /dev/null
-/*
- * Automatically generated by gen-header.xsl
- */
-#ifndef __ASM_AVR32_PERIHP_INTC_H__
-#define __ASM_AVR32_PERIHP_INTC_H__
-
-#define INTC_NUM_INT_GRPS 33
-
-#define INTC_INTPR0 0x0
-# define INTC_INTPR0_INTLEV_OFFSET 30
-# define INTC_INTPR0_INTLEV_SIZE 2
-# define INTC_INTPR0_OFFSET_OFFSET 0
-# define INTC_INTPR0_OFFSET_SIZE 24
-#define INTC_INTREQ0 0x100
-# define INTC_INTREQ0_IREQUEST0_OFFSET 0
-# define INTC_INTREQ0_IREQUEST0_SIZE 1
-# define INTC_INTREQ0_IREQUEST1_OFFSET 1
-# define INTC_INTREQ0_IREQUEST1_SIZE 1
-#define INTC_INTPR1 0x4
-# define INTC_INTPR1_INTLEV_OFFSET 30
-# define INTC_INTPR1_INTLEV_SIZE 2
-# define INTC_INTPR1_OFFSET_OFFSET 0
-# define INTC_INTPR1_OFFSET_SIZE 24
-#define INTC_INTREQ1 0x104
-# define INTC_INTREQ1_IREQUEST32_OFFSET 0
-# define INTC_INTREQ1_IREQUEST32_SIZE 1
-# define INTC_INTREQ1_IREQUEST33_OFFSET 1
-# define INTC_INTREQ1_IREQUEST33_SIZE 1
-# define INTC_INTREQ1_IREQUEST34_OFFSET 2
-# define INTC_INTREQ1_IREQUEST34_SIZE 1
-# define INTC_INTREQ1_IREQUEST35_OFFSET 3
-# define INTC_INTREQ1_IREQUEST35_SIZE 1
-# define INTC_INTREQ1_IREQUEST36_OFFSET 4
-# define INTC_INTREQ1_IREQUEST36_SIZE 1
-# define INTC_INTREQ1_IREQUEST37_OFFSET 5
-# define INTC_INTREQ1_IREQUEST37_SIZE 1
-#define INTC_INTPR2 0x8
-# define INTC_INTPR2_INTLEV_OFFSET 30
-# define INTC_INTPR2_INTLEV_SIZE 2
-# define INTC_INTPR2_OFFSET_OFFSET 0
-# define INTC_INTPR2_OFFSET_SIZE 24
-#define INTC_INTREQ2 0x108
-# define INTC_INTREQ2_IREQUEST64_OFFSET 0
-# define INTC_INTREQ2_IREQUEST64_SIZE 1
-# define INTC_INTREQ2_IREQUEST65_OFFSET 1
-# define INTC_INTREQ2_IREQUEST65_SIZE 1
-# define INTC_INTREQ2_IREQUEST66_OFFSET 2
-# define INTC_INTREQ2_IREQUEST66_SIZE 1
-# define INTC_INTREQ2_IREQUEST67_OFFSET 3
-# define INTC_INTREQ2_IREQUEST67_SIZE 1
-# define INTC_INTREQ2_IREQUEST68_OFFSET 4
-# define INTC_INTREQ2_IREQUEST68_SIZE 1
-#define INTC_INTPR3 0xc
-# define INTC_INTPR3_INTLEV_OFFSET 30
-# define INTC_INTPR3_INTLEV_SIZE 2
-# define INTC_INTPR3_OFFSET_OFFSET 0
-# define INTC_INTPR3_OFFSET_SIZE 24
-#define INTC_INTREQ3 0x10c
-# define INTC_INTREQ3_IREQUEST96_OFFSET 0
-# define INTC_INTREQ3_IREQUEST96_SIZE 1
-#define INTC_INTPR4 0x10
-# define INTC_INTPR4_INTLEV_OFFSET 30
-# define INTC_INTPR4_INTLEV_SIZE 2
-# define INTC_INTPR4_OFFSET_OFFSET 0
-# define INTC_INTPR4_OFFSET_SIZE 24
-#define INTC_INTREQ4 0x110
-# define INTC_INTREQ4_IREQUEST128_OFFSET 0
-# define INTC_INTREQ4_IREQUEST128_SIZE 1
-#define INTC_INTPR5 0x14
-# define INTC_INTPR5_INTLEV_OFFSET 30
-# define INTC_INTPR5_INTLEV_SIZE 2
-# define INTC_INTPR5_OFFSET_OFFSET 0
-# define INTC_INTPR5_OFFSET_SIZE 24
-#define INTC_INTREQ5 0x114
-# define INTC_INTREQ5_IREQUEST160_OFFSET 0
-# define INTC_INTREQ5_IREQUEST160_SIZE 1
-#define INTC_INTPR6 0x18
-# define INTC_INTPR6_INTLEV_OFFSET 30
-# define INTC_INTPR6_INTLEV_SIZE 2
-# define INTC_INTPR6_OFFSET_OFFSET 0
-# define INTC_INTPR6_OFFSET_SIZE 24
-#define INTC_INTREQ6 0x118
-# define INTC_INTREQ6_IREQUEST192_OFFSET 0
-# define INTC_INTREQ6_IREQUEST192_SIZE 1
-#define INTC_INTPR7 0x1c
-# define INTC_INTPR7_INTLEV_OFFSET 30
-# define INTC_INTPR7_INTLEV_SIZE 2
-# define INTC_INTPR7_OFFSET_OFFSET 0
-# define INTC_INTPR7_OFFSET_SIZE 24
-#define INTC_INTREQ7 0x11c
-# define INTC_INTREQ7_IREQUEST224_OFFSET 0
-# define INTC_INTREQ7_IREQUEST224_SIZE 1
-#define INTC_INTPR8 0x20
-# define INTC_INTPR8_INTLEV_OFFSET 30
-# define INTC_INTPR8_INTLEV_SIZE 2
-# define INTC_INTPR8_OFFSET_OFFSET 0
-# define INTC_INTPR8_OFFSET_SIZE 24
-#define INTC_INTREQ8 0x120
-# define INTC_INTREQ8_IREQUEST256_OFFSET 0
-# define INTC_INTREQ8_IREQUEST256_SIZE 1
-#define INTC_INTPR9 0x24
-# define INTC_INTPR9_INTLEV_OFFSET 30
-# define INTC_INTPR9_INTLEV_SIZE 2
-# define INTC_INTPR9_OFFSET_OFFSET 0
-# define INTC_INTPR9_OFFSET_SIZE 24
-#define INTC_INTREQ9 0x124
-# define INTC_INTREQ9_IREQUEST288_OFFSET 0
-# define INTC_INTREQ9_IREQUEST288_SIZE 1
-#define INTC_INTPR10 0x28
-# define INTC_INTPR10_INTLEV_OFFSET 30
-# define INTC_INTPR10_INTLEV_SIZE 2
-# define INTC_INTPR10_OFFSET_OFFSET 0
-# define INTC_INTPR10_OFFSET_SIZE 24
-#define INTC_INTREQ10 0x128
-# define INTC_INTREQ10_IREQUEST320_OFFSET 0
-# define INTC_INTREQ10_IREQUEST320_SIZE 1
-#define INTC_INTPR11 0x2c
-# define INTC_INTPR11_INTLEV_OFFSET 30
-# define INTC_INTPR11_INTLEV_SIZE 2
-# define INTC_INTPR11_OFFSET_OFFSET 0
-# define INTC_INTPR11_OFFSET_SIZE 24
-#define INTC_INTREQ11 0x12c
-# define INTC_INTREQ11_IREQUEST352_OFFSET 0
-# define INTC_INTREQ11_IREQUEST352_SIZE 1
-#define INTC_INTPR12 0x30
-# define INTC_INTPR12_INTLEV_OFFSET 30
-# define INTC_INTPR12_INTLEV_SIZE 2
-# define INTC_INTPR12_OFFSET_OFFSET 0
-# define INTC_INTPR12_OFFSET_SIZE 24
-#define INTC_INTREQ12 0x130
-# define INTC_INTREQ12_IREQUEST384_OFFSET 0
-# define INTC_INTREQ12_IREQUEST384_SIZE 1
-#define INTC_INTPR13 0x34
-# define INTC_INTPR13_INTLEV_OFFSET 30
-# define INTC_INTPR13_INTLEV_SIZE 2
-# define INTC_INTPR13_OFFSET_OFFSET 0
-# define INTC_INTPR13_OFFSET_SIZE 24
-#define INTC_INTREQ13 0x134
-# define INTC_INTREQ13_IREQUEST416_OFFSET 0
-# define INTC_INTREQ13_IREQUEST416_SIZE 1
-#define INTC_INTPR14 0x38
-# define INTC_INTPR14_INTLEV_OFFSET 30
-# define INTC_INTPR14_INTLEV_SIZE 2
-# define INTC_INTPR14_OFFSET_OFFSET 0
-# define INTC_INTPR14_OFFSET_SIZE 24
-#define INTC_INTREQ14 0x138
-# define INTC_INTREQ14_IREQUEST448_OFFSET 0
-# define INTC_INTREQ14_IREQUEST448_SIZE 1
-#define INTC_INTPR15 0x3c
-# define INTC_INTPR15_INTLEV_OFFSET 30
-# define INTC_INTPR15_INTLEV_SIZE 2
-# define INTC_INTPR15_OFFSET_OFFSET 0
-# define INTC_INTPR15_OFFSET_SIZE 24
-#define INTC_INTREQ15 0x13c
-# define INTC_INTREQ15_IREQUEST480_OFFSET 0
-# define INTC_INTREQ15_IREQUEST480_SIZE 1
-#define INTC_INTPR16 0x40
-# define INTC_INTPR16_INTLEV_OFFSET 30
-# define INTC_INTPR16_INTLEV_SIZE 2
-# define INTC_INTPR16_OFFSET_OFFSET 0
-# define INTC_INTPR16_OFFSET_SIZE 24
-#define INTC_INTREQ16 0x140
-# define INTC_INTREQ16_IREQUEST512_OFFSET 0
-# define INTC_INTREQ16_IREQUEST512_SIZE 1
-#define INTC_INTPR17 0x44
-# define INTC_INTPR17_INTLEV_OFFSET 30
-# define INTC_INTPR17_INTLEV_SIZE 2
-# define INTC_INTPR17_OFFSET_OFFSET 0
-# define INTC_INTPR17_OFFSET_SIZE 24
-#define INTC_INTREQ17 0x144
-# define INTC_INTREQ17_IREQUEST544_OFFSET 0
-# define INTC_INTREQ17_IREQUEST544_SIZE 1
-#define INTC_INTPR18 0x48
-# define INTC_INTPR18_INTLEV_OFFSET 30
-# define INTC_INTPR18_INTLEV_SIZE 2
-# define INTC_INTPR18_OFFSET_OFFSET 0
-# define INTC_INTPR18_OFFSET_SIZE 24
-#define INTC_INTREQ18 0x148
-# define INTC_INTREQ18_IREQUEST576_OFFSET 0
-# define INTC_INTREQ18_IREQUEST576_SIZE 1
-#define INTC_INTPR19 0x4c
-# define INTC_INTPR19_INTLEV_OFFSET 30
-# define INTC_INTPR19_INTLEV_SIZE 2
-# define INTC_INTPR19_OFFSET_OFFSET 0
-# define INTC_INTPR19_OFFSET_SIZE 24
-#define INTC_INTREQ19 0x14c
-# define INTC_INTREQ19_IREQUEST608_OFFSET 0
-# define INTC_INTREQ19_IREQUEST608_SIZE 1
-# define INTC_INTREQ19_IREQUEST609_OFFSET 1
-# define INTC_INTREQ19_IREQUEST609_SIZE 1
-# define INTC_INTREQ19_IREQUEST610_OFFSET 2
-# define INTC_INTREQ19_IREQUEST610_SIZE 1
-# define INTC_INTREQ19_IREQUEST611_OFFSET 3
-# define INTC_INTREQ19_IREQUEST611_SIZE 1
-#define INTC_INTPR20 0x50
-# define INTC_INTPR20_INTLEV_OFFSET 30
-# define INTC_INTPR20_INTLEV_SIZE 2
-# define INTC_INTPR20_OFFSET_OFFSET 0
-# define INTC_INTPR20_OFFSET_SIZE 24
-#define INTC_INTREQ20 0x150
-# define INTC_INTREQ20_IREQUEST640_OFFSET 0
-# define INTC_INTREQ20_IREQUEST640_SIZE 1
-#define INTC_INTPR21 0x54
-# define INTC_INTPR21_INTLEV_OFFSET 30
-# define INTC_INTPR21_INTLEV_SIZE 2
-# define INTC_INTPR21_OFFSET_OFFSET 0
-# define INTC_INTPR21_OFFSET_SIZE 24
-#define INTC_INTREQ21 0x154
-# define INTC_INTREQ21_IREQUEST672_OFFSET 0
-# define INTC_INTREQ21_IREQUEST672_SIZE 1
-#define INTC_INTPR22 0x58
-# define INTC_INTPR22_INTLEV_OFFSET 30
-# define INTC_INTPR22_INTLEV_SIZE 2
-# define INTC_INTPR22_OFFSET_OFFSET 0
-# define INTC_INTPR22_OFFSET_SIZE 24
-#define INTC_INTREQ22 0x158
-# define INTC_INTREQ22_IREQUEST704_OFFSET 0
-# define INTC_INTREQ22_IREQUEST704_SIZE 1
-# define INTC_INTREQ22_IREQUEST705_OFFSET 1
-# define INTC_INTREQ22_IREQUEST705_SIZE 1
-# define INTC_INTREQ22_IREQUEST706_OFFSET 2
-# define INTC_INTREQ22_IREQUEST706_SIZE 1
-#define INTC_INTPR23 0x5c
-# define INTC_INTPR23_INTLEV_OFFSET 30
-# define INTC_INTPR23_INTLEV_SIZE 2
-# define INTC_INTPR23_OFFSET_OFFSET 0
-# define INTC_INTPR23_OFFSET_SIZE 24
-#define INTC_INTREQ23 0x15c
-# define INTC_INTREQ23_IREQUEST736_OFFSET 0
-# define INTC_INTREQ23_IREQUEST736_SIZE 1
-# define INTC_INTREQ23_IREQUEST737_OFFSET 1
-# define INTC_INTREQ23_IREQUEST737_SIZE 1
-# define INTC_INTREQ23_IREQUEST738_OFFSET 2
-# define INTC_INTREQ23_IREQUEST738_SIZE 1
-#define INTC_INTPR24 0x60
-# define INTC_INTPR24_INTLEV_OFFSET 30
-# define INTC_INTPR24_INTLEV_SIZE 2
-# define INTC_INTPR24_OFFSET_OFFSET 0
-# define INTC_INTPR24_OFFSET_SIZE 24
-#define INTC_INTREQ24 0x160
-# define INTC_INTREQ24_IREQUEST768_OFFSET 0
-# define INTC_INTREQ24_IREQUEST768_SIZE 1
-#define INTC_INTPR25 0x64
-# define INTC_INTPR25_INTLEV_OFFSET 30
-# define INTC_INTPR25_INTLEV_SIZE 2
-# define INTC_INTPR25_OFFSET_OFFSET 0
-# define INTC_INTPR25_OFFSET_SIZE 24
-#define INTC_INTREQ25 0x164
-# define INTC_INTREQ25_IREQUEST800_OFFSET 0
-# define INTC_INTREQ25_IREQUEST800_SIZE 1
-#define INTC_INTPR26 0x68
-# define INTC_INTPR26_INTLEV_OFFSET 30
-# define INTC_INTPR26_INTLEV_SIZE 2
-# define INTC_INTPR26_OFFSET_OFFSET 0
-# define INTC_INTPR26_OFFSET_SIZE 24
-#define INTC_INTREQ26 0x168
-# define INTC_INTREQ26_IREQUEST832_OFFSET 0
-# define INTC_INTREQ26_IREQUEST832_SIZE 1
-#define INTC_INTPR27 0x6c
-# define INTC_INTPR27_INTLEV_OFFSET 30
-# define INTC_INTPR27_INTLEV_SIZE 2
-# define INTC_INTPR27_OFFSET_OFFSET 0
-# define INTC_INTPR27_OFFSET_SIZE 24
-#define INTC_INTREQ27 0x16c
-# define INTC_INTREQ27_IREQUEST864_OFFSET 0
-# define INTC_INTREQ27_IREQUEST864_SIZE 1
-#define INTC_INTPR28 0x70
-# define INTC_INTPR28_INTLEV_OFFSET 30
-# define INTC_INTPR28_INTLEV_SIZE 2
-# define INTC_INTPR28_OFFSET_OFFSET 0
-# define INTC_INTPR28_OFFSET_SIZE 24
-#define INTC_INTREQ28 0x170
-# define INTC_INTREQ28_IREQUEST896_OFFSET 0
-# define INTC_INTREQ28_IREQUEST896_SIZE 1
-#define INTC_INTPR29 0x74
-# define INTC_INTPR29_INTLEV_OFFSET 30
-# define INTC_INTPR29_INTLEV_SIZE 2
-# define INTC_INTPR29_OFFSET_OFFSET 0
-# define INTC_INTPR29_OFFSET_SIZE 24
-#define INTC_INTREQ29 0x174
-# define INTC_INTREQ29_IREQUEST928_OFFSET 0
-# define INTC_INTREQ29_IREQUEST928_SIZE 1
-#define INTC_INTPR30 0x78
-# define INTC_INTPR30_INTLEV_OFFSET 30
-# define INTC_INTPR30_INTLEV_SIZE 2
-# define INTC_INTPR30_OFFSET_OFFSET 0
-# define INTC_INTPR30_OFFSET_SIZE 24
-#define INTC_INTREQ30 0x178
-# define INTC_INTREQ30_IREQUEST960_OFFSET 0
-# define INTC_INTREQ30_IREQUEST960_SIZE 1
-#define INTC_INTPR31 0x7c
-# define INTC_INTPR31_INTLEV_OFFSET 30
-# define INTC_INTPR31_INTLEV_SIZE 2
-# define INTC_INTPR31_OFFSET_OFFSET 0
-# define INTC_INTPR31_OFFSET_SIZE 24
-#define INTC_INTREQ31 0x17c
-# define INTC_INTREQ31_IREQUEST992_OFFSET 0
-# define INTC_INTREQ31_IREQUEST992_SIZE 1
-#define INTC_INTPR32 0x80
-# define INTC_INTPR32_INTLEV_OFFSET 30
-# define INTC_INTPR32_INTLEV_SIZE 2
-# define INTC_INTPR32_OFFSET_OFFSET 0
-# define INTC_INTPR32_OFFSET_SIZE 24
-#define INTC_INTREQ32 0x180
-# define INTC_INTREQ32_IREQUEST1024_OFFSET 0
-# define INTC_INTREQ32_IREQUEST1024_SIZE 1
-#define INTC_INTCAUSE0 0x20c
-# define INTC_INTCAUSE0_CAUSEGRP_OFFSET 0
-# define INTC_INTCAUSE0_CAUSEGRP_SIZE 6
-#define INTC_INTCAUSE1 0x208
-# define INTC_INTCAUSE1_CAUSEGRP_OFFSET 0
-# define INTC_INTCAUSE1_CAUSEGRP_SIZE 6
-#define INTC_INTCAUSE2 0x204
-# define INTC_INTCAUSE2_CAUSEGRP_OFFSET 0
-# define INTC_INTCAUSE2_CAUSEGRP_SIZE 6
-#define INTC_INTCAUSE3 0x200
-# define INTC_INTCAUSE3_CAUSEGRP_OFFSET 0
-# define INTC_INTCAUSE3_CAUSEGRP_SIZE 6
-
-#define INTC_BIT(name) (1 << INTC_##name##_OFFSET)
-#define INTC_MKBF(name, value) (((value) & ((1 << INTC_##name##_SIZE) - 1)) << INTC_##name##_OFFSET)
-#define INTC_GETBF(name, value) (((value) >> INTC_##name##_OFFSET) & ((1 << INTC_##name##_SIZE) - 1))
-
-#define intc_readl(port,reg) \
- __raw_readl((port)->regs + INTC_##reg)
-#define intc_writel(port,reg,value) \
- __raw_writel((value), (port)->regs + INTC_##reg)
-
-#endif /* __ASM_AVR32_PERIHP_INTC_H__ */
+++ /dev/null
-/*
- * Copyright (C) 2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/clk.h>
-#include <linux/err.h>
-#include <linux/init.h>
-#include <linux/platform_device.h>
-
-static int __init pdc_probe(struct platform_device *pdev)
-{
- struct clk *pclk, *hclk;
-
- pclk = clk_get(&pdev->dev, "pclk");
- if (IS_ERR(pclk)) {
- dev_err(&pdev->dev, "no pclk defined\n");
- return PTR_ERR(pclk);
- }
- hclk = clk_get(&pdev->dev, "hclk");
- if (IS_ERR(hclk)) {
- dev_err(&pdev->dev, "no hclk defined\n");
- clk_put(pclk);
- return PTR_ERR(hclk);
- }
-
- clk_enable(pclk);
- clk_enable(hclk);
-
- dev_info(&pdev->dev, "Atmel Peripheral DMA Controller enabled\n");
- return 0;
-}
-
-static struct platform_driver pdc_driver = {
- .driver = {
- .name = "pdc",
- },
-};
-
-static int __init pdc_init(void)
-{
- return platform_driver_probe(&pdc_driver, pdc_probe);
-}
-arch_initcall(pdc_init);
+++ /dev/null
-/*
- * Atmel PIO2 Port Multiplexer support
- *
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/clk.h>
-#include <linux/debugfs.h>
-#include <linux/export.h>
-#include <linux/fs.h>
-#include <linux/platform_device.h>
-#include <linux/irq.h>
-#include <linux/gpio.h>
-
-#include <asm/io.h>
-
-#include <mach/portmux.h>
-
-#include "pio.h"
-
-#define MAX_NR_PIO_DEVICES 8
-
-struct pio_device {
- struct gpio_chip chip;
- void __iomem *regs;
- const struct platform_device *pdev;
- struct clk *clk;
- u32 pinmux_mask;
- char name[8];
-};
-
-static struct pio_device pio_dev[MAX_NR_PIO_DEVICES];
-
-static struct pio_device *gpio_to_pio(unsigned int gpio)
-{
- struct pio_device *pio;
- unsigned int index;
-
- index = gpio >> 5;
- if (index >= MAX_NR_PIO_DEVICES)
- return NULL;
- pio = &pio_dev[index];
- if (!pio->regs)
- return NULL;
-
- return pio;
-}
-
-/* Pin multiplexing API */
-static DEFINE_SPINLOCK(pio_lock);
-
-void __init at32_select_periph(unsigned int port, u32 pin_mask,
- unsigned int periph, unsigned long flags)
-{
- struct pio_device *pio;
-
- /* assign and verify pio */
- pio = gpio_to_pio(port);
- if (unlikely(!pio)) {
- printk(KERN_WARNING "pio: invalid port %u\n", port);
- goto fail;
- }
-
- /* Test if any of the requested pins is already muxed */
- spin_lock(&pio_lock);
- if (unlikely(pio->pinmux_mask & pin_mask)) {
- printk(KERN_WARNING "%s: pin(s) busy (requested 0x%x, busy 0x%x)\n",
- pio->name, pin_mask, pio->pinmux_mask & pin_mask);
- spin_unlock(&pio_lock);
- goto fail;
- }
-
- pio->pinmux_mask |= pin_mask;
-
- /* enable pull ups */
- pio_writel(pio, PUER, pin_mask);
-
- /* select either peripheral A or B */
- if (periph)
- pio_writel(pio, BSR, pin_mask);
- else
- pio_writel(pio, ASR, pin_mask);
-
- /* enable peripheral control */
- pio_writel(pio, PDR, pin_mask);
-
- /* Disable pull ups if not requested. */
- if (!(flags & AT32_GPIOF_PULLUP))
- pio_writel(pio, PUDR, pin_mask);
-
- spin_unlock(&pio_lock);
-
- return;
-
-fail:
- dump_stack();
-}
-
-void __init at32_select_gpio(unsigned int pin, unsigned long flags)
-{
- struct pio_device *pio;
- unsigned int pin_index = pin & 0x1f;
- u32 mask = 1 << pin_index;
-
- pio = gpio_to_pio(pin);
- if (unlikely(!pio)) {
- printk("pio: invalid pin %u\n", pin);
- goto fail;
- }
-
- if (unlikely(test_and_set_bit(pin_index, &pio->pinmux_mask))) {
- printk("%s: pin %u is busy\n", pio->name, pin_index);
- goto fail;
- }
-
- if (flags & AT32_GPIOF_OUTPUT) {
- if (flags & AT32_GPIOF_HIGH)
- pio_writel(pio, SODR, mask);
- else
- pio_writel(pio, CODR, mask);
- if (flags & AT32_GPIOF_MULTIDRV)
- pio_writel(pio, MDER, mask);
- else
- pio_writel(pio, MDDR, mask);
- pio_writel(pio, PUDR, mask);
- pio_writel(pio, OER, mask);
- } else {
- if (flags & AT32_GPIOF_PULLUP)
- pio_writel(pio, PUER, mask);
- else
- pio_writel(pio, PUDR, mask);
- if (flags & AT32_GPIOF_DEGLITCH)
- pio_writel(pio, IFER, mask);
- else
- pio_writel(pio, IFDR, mask);
- pio_writel(pio, ODR, mask);
- }
-
- pio_writel(pio, PER, mask);
-
- return;
-
-fail:
- dump_stack();
-}
-
-/*
- * Undo a previous pin reservation. Will not affect the hardware
- * configuration.
- */
-void at32_deselect_pin(unsigned int pin)
-{
- struct pio_device *pio;
- unsigned int pin_index = pin & 0x1f;
-
- pio = gpio_to_pio(pin);
- if (unlikely(!pio)) {
- printk("pio: invalid pin %u\n", pin);
- dump_stack();
- return;
- }
-
- clear_bit(pin_index, &pio->pinmux_mask);
-}
-
-/* Reserve a pin, preventing anyone else from changing its configuration. */
-void __init at32_reserve_pin(unsigned int port, u32 pin_mask)
-{
- struct pio_device *pio;
-
- /* assign and verify pio */
- pio = gpio_to_pio(port);
- if (unlikely(!pio)) {
- printk(KERN_WARNING "pio: invalid port %u\n", port);
- goto fail;
- }
-
- /* Test if any of the requested pins is already muxed */
- spin_lock(&pio_lock);
- if (unlikely(pio->pinmux_mask & pin_mask)) {
- printk(KERN_WARNING "%s: pin(s) busy (req. 0x%x, busy 0x%x)\n",
- pio->name, pin_mask, pio->pinmux_mask & pin_mask);
- spin_unlock(&pio_lock);
- goto fail;
- }
-
- /* Reserve pins */
- pio->pinmux_mask |= pin_mask;
- spin_unlock(&pio_lock);
- return;
-
-fail:
- dump_stack();
-}
-
-/*--------------------------------------------------------------------------*/
-
-/* GPIO API */
-
-static int direction_input(struct gpio_chip *chip, unsigned offset)
-{
- struct pio_device *pio = gpiochip_get_data(chip);
- u32 mask = 1 << offset;
-
- if (!(pio_readl(pio, PSR) & mask))
- return -EINVAL;
-
- pio_writel(pio, ODR, mask);
- return 0;
-}
-
-static int gpio_get(struct gpio_chip *chip, unsigned offset)
-{
- struct pio_device *pio = gpiochip_get_data(chip);
-
- return (pio_readl(pio, PDSR) >> offset) & 1;
-}
-
-static void gpio_set(struct gpio_chip *chip, unsigned offset, int value);
-
-static int direction_output(struct gpio_chip *chip, unsigned offset, int value)
-{
- struct pio_device *pio = gpiochip_get_data(chip);
- u32 mask = 1 << offset;
-
- if (!(pio_readl(pio, PSR) & mask))
- return -EINVAL;
-
- gpio_set(chip, offset, value);
- pio_writel(pio, OER, mask);
- return 0;
-}
-
-static void gpio_set(struct gpio_chip *chip, unsigned offset, int value)
-{
- struct pio_device *pio = gpiochip_get_data(chip);
- u32 mask = 1 << offset;
-
- if (value)
- pio_writel(pio, SODR, mask);
- else
- pio_writel(pio, CODR, mask);
-}
-
-/*--------------------------------------------------------------------------*/
-
-/* GPIO IRQ support */
-
-static void gpio_irq_mask(struct irq_data *d)
-{
- unsigned gpio = irq_to_gpio(d->irq);
- struct pio_device *pio = &pio_dev[gpio >> 5];
-
- pio_writel(pio, IDR, 1 << (gpio & 0x1f));
-}
-
-static void gpio_irq_unmask(struct irq_data *d)
-{
- unsigned gpio = irq_to_gpio(d->irq);
- struct pio_device *pio = &pio_dev[gpio >> 5];
-
- pio_writel(pio, IER, 1 << (gpio & 0x1f));
-}
-
-static int gpio_irq_type(struct irq_data *d, unsigned type)
-{
- if (type != IRQ_TYPE_EDGE_BOTH && type != IRQ_TYPE_NONE)
- return -EINVAL;
-
- return 0;
-}
-
-static struct irq_chip gpio_irqchip = {
- .name = "gpio",
- .irq_mask = gpio_irq_mask,
- .irq_unmask = gpio_irq_unmask,
- .irq_set_type = gpio_irq_type,
-};
-
-static void gpio_irq_handler(struct irq_desc *desc)
-{
- struct pio_device *pio = irq_desc_get_chip_data(desc);
- unsigned gpio_irq;
-
- gpio_irq = (unsigned) irq_desc_get_handler_data(desc);
- for (;;) {
- u32 isr;
-
- /* ack pending GPIO interrupts */
- isr = pio_readl(pio, ISR) & pio_readl(pio, IMR);
- if (!isr)
- break;
- do {
- int i;
-
- i = ffs(isr) - 1;
- isr &= ~(1 << i);
-
- i += gpio_irq;
- generic_handle_irq(i);
- } while (isr);
- }
-}
-
-static void __init
-gpio_irq_setup(struct pio_device *pio, int irq, int gpio_irq)
-{
- unsigned i;
-
- irq_set_chip_data(irq, pio);
-
- for (i = 0; i < 32; i++, gpio_irq++) {
- irq_set_chip_data(gpio_irq, pio);
- irq_set_chip_and_handler(gpio_irq, &gpio_irqchip,
- handle_simple_irq);
- }
-
- irq_set_chained_handler_and_data(irq, gpio_irq_handler,
- (void *)gpio_irq);
-}
-
-/*--------------------------------------------------------------------------*/
-
-#ifdef CONFIG_DEBUG_FS
-
-#include <linux/seq_file.h>
-
-/*
- * This shows more info than the generic gpio dump code:
- * pullups, deglitching, open drain drive.
- */
-static void pio_bank_show(struct seq_file *s, struct gpio_chip *chip)
-{
- struct pio_device *pio = gpiochip_get_data(chip);
- u32 psr, osr, imr, pdsr, pusr, ifsr, mdsr;
- unsigned i;
- u32 mask;
- char bank;
-
- psr = pio_readl(pio, PSR);
- osr = pio_readl(pio, OSR);
- imr = pio_readl(pio, IMR);
- pdsr = pio_readl(pio, PDSR);
- pusr = pio_readl(pio, PUSR);
- ifsr = pio_readl(pio, IFSR);
- mdsr = pio_readl(pio, MDSR);
-
- bank = 'A' + pio->pdev->id;
-
- for (i = 0, mask = 1; i < 32; i++, mask <<= 1) {
- const char *label;
-
- label = gpiochip_is_requested(chip, i);
- if (!label && (imr & mask))
- label = "[irq]";
- if (!label)
- continue;
-
- seq_printf(s, " gpio-%-3d P%c%-2d (%-12s) %s %s %s",
- chip->base + i, bank, i,
- label,
- (osr & mask) ? "out" : "in ",
- (mask & pdsr) ? "hi" : "lo",
- (mask & pusr) ? " " : "up");
- if (ifsr & mask)
- seq_puts(s, " deglitch");
- if ((osr & mdsr) & mask)
- seq_puts(s, " open-drain");
- if (imr & mask)
- seq_printf(s, " irq-%d edge-both",
- gpio_to_irq(chip->base + i));
- seq_putc(s, '\n');
- }
-}
-
-#else
-#define pio_bank_show NULL
-#endif
-
-
-/*--------------------------------------------------------------------------*/
-
-static int __init pio_probe(struct platform_device *pdev)
-{
- struct pio_device *pio = NULL;
- int irq = platform_get_irq(pdev, 0);
- int gpio_irq_base = GPIO_IRQ_BASE + pdev->id * 32;
-
- BUG_ON(pdev->id >= MAX_NR_PIO_DEVICES);
- pio = &pio_dev[pdev->id];
- BUG_ON(!pio->regs);
-
- pio->chip.label = pio->name;
- pio->chip.base = pdev->id * 32;
- pio->chip.ngpio = 32;
- pio->chip.parent = &pdev->dev;
- pio->chip.owner = THIS_MODULE;
-
- pio->chip.direction_input = direction_input;
- pio->chip.get = gpio_get;
- pio->chip.direction_output = direction_output;
- pio->chip.set = gpio_set;
- pio->chip.dbg_show = pio_bank_show;
-
- gpiochip_add_data(&pio->chip, pio);
-
- gpio_irq_setup(pio, irq, gpio_irq_base);
-
- platform_set_drvdata(pdev, pio);
-
- printk(KERN_DEBUG "%s: base 0x%p, irq %d chains %d..%d\n",
- pio->name, pio->regs, irq, gpio_irq_base, gpio_irq_base + 31);
-
- return 0;
-}
-
-static struct platform_driver pio_driver = {
- .driver = {
- .name = "pio",
- },
-};
-
-static int __init pio_init(void)
-{
- return platform_driver_probe(&pio_driver, pio_probe);
-}
-postcore_initcall(pio_init);
-
-void __init at32_init_pio(struct platform_device *pdev)
-{
- struct resource *regs;
- struct pio_device *pio;
-
- if (pdev->id >= MAX_NR_PIO_DEVICES) {
- dev_err(&pdev->dev, "only %d PIO devices supported\n",
- MAX_NR_PIO_DEVICES);
- return;
- }
-
- pio = &pio_dev[pdev->id];
- snprintf(pio->name, sizeof(pio->name), "pio%d", pdev->id);
-
- regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!regs) {
- dev_err(&pdev->dev, "no mmio resource defined\n");
- return;
- }
-
- pio->clk = clk_get(&pdev->dev, "mck");
- if (IS_ERR(pio->clk))
- /*
- * This is a fatal error, but if we continue we might
- * be so lucky that we manage to initialize the
- * console and display this message...
- */
- dev_err(&pdev->dev, "no mck clock defined\n");
- else
- clk_enable(pio->clk);
-
- pio->pdev = pdev;
- pio->regs = ioremap(regs->start, resource_size(regs));
-
- /* start with irqs disabled and acked */
- pio_writel(pio, IDR, ~0UL);
- (void) pio_readl(pio, ISR);
-}
+++ /dev/null
-/*
- * Atmel PIO2 Port Multiplexer support
- *
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __ARCH_AVR32_AT32AP_PIO_H__
-#define __ARCH_AVR32_AT32AP_PIO_H__
-
-/* PIO register offsets */
-#define PIO_PER 0x0000
-#define PIO_PDR 0x0004
-#define PIO_PSR 0x0008
-#define PIO_OER 0x0010
-#define PIO_ODR 0x0014
-#define PIO_OSR 0x0018
-#define PIO_IFER 0x0020
-#define PIO_IFDR 0x0024
-#define PIO_IFSR 0x0028
-#define PIO_SODR 0x0030
-#define PIO_CODR 0x0034
-#define PIO_ODSR 0x0038
-#define PIO_PDSR 0x003c
-#define PIO_IER 0x0040
-#define PIO_IDR 0x0044
-#define PIO_IMR 0x0048
-#define PIO_ISR 0x004c
-#define PIO_MDER 0x0050
-#define PIO_MDDR 0x0054
-#define PIO_MDSR 0x0058
-#define PIO_PUDR 0x0060
-#define PIO_PUER 0x0064
-#define PIO_PUSR 0x0068
-#define PIO_ASR 0x0070
-#define PIO_BSR 0x0074
-#define PIO_ABSR 0x0078
-#define PIO_OWER 0x00a0
-#define PIO_OWDR 0x00a4
-#define PIO_OWSR 0x00a8
-
-/* Bitfields in PER */
-
-/* Bitfields in PDR */
-
-/* Bitfields in PSR */
-
-/* Bitfields in OER */
-
-/* Bitfields in ODR */
-
-/* Bitfields in OSR */
-
-/* Bitfields in IFER */
-
-/* Bitfields in IFDR */
-
-/* Bitfields in IFSR */
-
-/* Bitfields in SODR */
-
-/* Bitfields in CODR */
-
-/* Bitfields in ODSR */
-
-/* Bitfields in PDSR */
-
-/* Bitfields in IER */
-
-/* Bitfields in IDR */
-
-/* Bitfields in IMR */
-
-/* Bitfields in ISR */
-
-/* Bitfields in MDER */
-
-/* Bitfields in MDDR */
-
-/* Bitfields in MDSR */
-
-/* Bitfields in PUDR */
-
-/* Bitfields in PUER */
-
-/* Bitfields in PUSR */
-
-/* Bitfields in ASR */
-
-/* Bitfields in BSR */
-
-/* Bitfields in ABSR */
-#define PIO_P0_OFFSET 0
-#define PIO_P0_SIZE 1
-#define PIO_P1_OFFSET 1
-#define PIO_P1_SIZE 1
-#define PIO_P2_OFFSET 2
-#define PIO_P2_SIZE 1
-#define PIO_P3_OFFSET 3
-#define PIO_P3_SIZE 1
-#define PIO_P4_OFFSET 4
-#define PIO_P4_SIZE 1
-#define PIO_P5_OFFSET 5
-#define PIO_P5_SIZE 1
-#define PIO_P6_OFFSET 6
-#define PIO_P6_SIZE 1
-#define PIO_P7_OFFSET 7
-#define PIO_P7_SIZE 1
-#define PIO_P8_OFFSET 8
-#define PIO_P8_SIZE 1
-#define PIO_P9_OFFSET 9
-#define PIO_P9_SIZE 1
-#define PIO_P10_OFFSET 10
-#define PIO_P10_SIZE 1
-#define PIO_P11_OFFSET 11
-#define PIO_P11_SIZE 1
-#define PIO_P12_OFFSET 12
-#define PIO_P12_SIZE 1
-#define PIO_P13_OFFSET 13
-#define PIO_P13_SIZE 1
-#define PIO_P14_OFFSET 14
-#define PIO_P14_SIZE 1
-#define PIO_P15_OFFSET 15
-#define PIO_P15_SIZE 1
-#define PIO_P16_OFFSET 16
-#define PIO_P16_SIZE 1
-#define PIO_P17_OFFSET 17
-#define PIO_P17_SIZE 1
-#define PIO_P18_OFFSET 18
-#define PIO_P18_SIZE 1
-#define PIO_P19_OFFSET 19
-#define PIO_P19_SIZE 1
-#define PIO_P20_OFFSET 20
-#define PIO_P20_SIZE 1
-#define PIO_P21_OFFSET 21
-#define PIO_P21_SIZE 1
-#define PIO_P22_OFFSET 22
-#define PIO_P22_SIZE 1
-#define PIO_P23_OFFSET 23
-#define PIO_P23_SIZE 1
-#define PIO_P24_OFFSET 24
-#define PIO_P24_SIZE 1
-#define PIO_P25_OFFSET 25
-#define PIO_P25_SIZE 1
-#define PIO_P26_OFFSET 26
-#define PIO_P26_SIZE 1
-#define PIO_P27_OFFSET 27
-#define PIO_P27_SIZE 1
-#define PIO_P28_OFFSET 28
-#define PIO_P28_SIZE 1
-#define PIO_P29_OFFSET 29
-#define PIO_P29_SIZE 1
-#define PIO_P30_OFFSET 30
-#define PIO_P30_SIZE 1
-#define PIO_P31_OFFSET 31
-#define PIO_P31_SIZE 1
-
-/* Bitfields in OWER */
-
-/* Bitfields in OWDR */
-
-/* Bitfields in OWSR */
-
-/* Bit manipulation macros */
-#define PIO_BIT(name) (1 << PIO_##name##_OFFSET)
-#define PIO_BF(name,value) (((value) & ((1 << PIO_##name##_SIZE) - 1)) << PIO_##name##_OFFSET)
-#define PIO_BFEXT(name,value) (((value) >> PIO_##name##_OFFSET) & ((1 << PIO_##name##_SIZE) - 1))
-#define PIO_BFINS(name,value,old) (((old) & ~(((1 << PIO_##name##_SIZE) - 1) << PIO_##name##_OFFSET)) | PIO_BF(name,value))
-
-/* Register access macros */
-#define pio_readl(port,reg) \
- __raw_readl((port)->regs + PIO_##reg)
-#define pio_writel(port,reg,value) \
- __raw_writel((value), (port)->regs + PIO_##reg)
-
-void at32_init_pio(struct platform_device *pdev);
-
-#endif /* __ARCH_AVR32_AT32AP_PIO_H__ */
+++ /dev/null
-/*
- * Low-level Power Management code.
- *
- * Copyright (C) 2008 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <asm/asm.h>
-#include <asm/asm-offsets.h>
-#include <asm/thread_info.h>
-#include <mach/pm.h>
-
-#include "pm.h"
-#include "sdramc.h"
-
-/* Same as 0xfff00000 but fits in a 21 bit signed immediate */
-#define PM_BASE -0x100000
-
- /* Keep this close to the irq handlers */
- .section .irq.text, "ax", @progbits
-
- /*
- * void cpu_enter_idle(void)
- *
- * Put the CPU into "idle" mode, in which it will consume
- * significantly less power.
- *
- * If an interrupt comes along in the window between
- * unmask_interrupts and the sleep instruction below, the
- * interrupt code will adjust the return address so that we
- * never execute the sleep instruction. This is required
- * because the AP7000 doesn't unmask interrupts when entering
- * sleep modes; later CPUs may not need this workaround.
- */
- .global cpu_enter_idle
- .type cpu_enter_idle, @function
-cpu_enter_idle:
- mask_interrupts
- get_thread_info r8
- ld.w r9, r8[TI_flags]
- bld r9, TIF_NEED_RESCHED
- brcs .Lret_from_sleep
- sbr r9, TIF_CPU_GOING_TO_SLEEP
- st.w r8[TI_flags], r9
- unmask_interrupts
- sleep CPU_SLEEP_IDLE
- .size cpu_enter_idle, . - cpu_enter_idle
-
- /*
- * Common return path for PM functions that don't run from
- * SRAM.
- */
- .global cpu_idle_skip_sleep
- .type cpu_idle_skip_sleep, @function
-cpu_idle_skip_sleep:
- mask_interrupts
- ld.w r9, r8[TI_flags]
- cbr r9, TIF_CPU_GOING_TO_SLEEP
- st.w r8[TI_flags], r9
-.Lret_from_sleep:
- unmask_interrupts
- retal r12
- .size cpu_idle_skip_sleep, . - cpu_idle_skip_sleep
-
-#ifdef CONFIG_PM
- .section .init.text, "ax", @progbits
-
- .global pm_exception
- .type pm_exception, @function
-pm_exception:
- /*
- * Exceptions are masked when we switch to this handler, so
- * we'll only get "unrecoverable" exceptions (offset 0.)
- */
- sub r12, pc, . - .Lpanic_msg
- lddpc pc, .Lpanic_addr
-
- .align 2
-.Lpanic_addr:
- .long panic
-.Lpanic_msg:
- .asciz "Unrecoverable exception during suspend\n"
- .size pm_exception, . - pm_exception
-
- .global pm_irq0
- .type pm_irq0, @function
-pm_irq0:
- /* Disable interrupts and return after the sleep instruction */
- mfsr r9, SYSREG_RSR_INT0
- mtsr SYSREG_RAR_INT0, r8
- sbr r9, SYSREG_GM_OFFSET
- mtsr SYSREG_RSR_INT0, r9
- rete
-
- /*
- * void cpu_enter_standby(unsigned long sdramc_base)
- *
- * Enter PM_SUSPEND_STANDBY mode. At this point, all drivers
- * are suspended and interrupts are disabled. Interrupts
- * marked as 'wakeup' event sources may still come along and
- * get us out of here.
- *
- * The SDRAM will be put into self-refresh mode (which does
- * not require a clock from the CPU), and the CPU will be put
- * into "frozen" mode (HSB bus stopped). The SDRAM controller
- * will automatically bring the SDRAM into normal mode on the
- * first access, and the power manager will automatically
- * start the HSB and CPU clocks upon a wakeup event.
- *
- * This code uses the same "skip sleep" technique as above.
- * It is very important that we jump directly to
- * cpu_after_sleep after the sleep instruction since that's
- * where we'll end up if the interrupt handler decides that we
- * need to skip the sleep instruction.
- */
- .global pm_standby
- .type pm_standby, @function
-pm_standby:
- /*
- * interrupts are already masked at this point, and EVBA
- * points to pm_exception above.
- */
- ld.w r10, r12[SDRAMC_LPR]
- sub r8, pc, . - 1f /* return address for irq handler */
- mov r11, SDRAMC_LPR_LPCB_SELF_RFR
- bfins r10, r11, 0, 2 /* LPCB <- self Refresh */
- sync 0 /* flush write buffer */
- st.w r12[SDRAMC_LPR], r10 /* put SDRAM in self-refresh mode */
- ld.w r11, r12[SDRAMC_LPR]
- unmask_interrupts
- sleep CPU_SLEEP_FROZEN
-1: mask_interrupts
- retal r12
- .size pm_standby, . - pm_standby
-
- .global pm_suspend_to_ram
- .type pm_suspend_to_ram, @function
-pm_suspend_to_ram:
- /*
- * interrupts are already masked at this point, and EVBA
- * points to pm_exception above.
- */
- mov r11, 0
- cache r11[2], 8 /* clean all dcache lines */
- sync 0 /* flush write buffer */
- ld.w r10, r12[SDRAMC_LPR]
- sub r8, pc, . - 1f /* return address for irq handler */
- mov r11, SDRAMC_LPR_LPCB_SELF_RFR
- bfins r10, r11, 0, 2 /* LPCB <- self refresh */
- st.w r12[SDRAMC_LPR], r10 /* put SDRAM in self-refresh mode */
- ld.w r11, r12[SDRAMC_LPR]
-
- unmask_interrupts
- sleep CPU_SLEEP_STOP
-1: mask_interrupts
-
- retal r12
- .size pm_suspend_to_ram, . - pm_suspend_to_ram
-
- .global pm_sram_end
- .type pm_sram_end, @function
-pm_sram_end:
- .size pm_sram_end, 0
-
-#endif /* CONFIG_PM */
+++ /dev/null
-/*
- * AVR32 AP Power Management
- *
- * Copyright (C) 2008 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
- */
-#include <linux/io.h>
-#include <linux/suspend.h>
-#include <linux/vmalloc.h>
-
-#include <asm/cacheflush.h>
-#include <asm/sysreg.h>
-
-#include <mach/chip.h>
-#include <mach/pm.h>
-#include <mach/sram.h>
-
-#include "sdramc.h"
-
-#define SRAM_PAGE_FLAGS (SYSREG_BIT(TLBELO_D) | SYSREG_BF(SZ, 1) \
- | SYSREG_BF(AP, 3) | SYSREG_BIT(G))
-
-
-static unsigned long pm_sram_start;
-static size_t pm_sram_size;
-static struct vm_struct *pm_sram_area;
-
-static void (*avr32_pm_enter_standby)(unsigned long sdramc_base);
-static void (*avr32_pm_enter_str)(unsigned long sdramc_base);
-
-/*
- * Must be called with interrupts disabled. Exceptions will be masked
- * on return (i.e. all exceptions will be "unrecoverable".)
- */
-static void *avr32_pm_map_sram(void)
-{
- unsigned long vaddr;
- unsigned long page_addr;
- u32 tlbehi;
- u32 mmucr;
-
- vaddr = (unsigned long)pm_sram_area->addr;
- page_addr = pm_sram_start & PAGE_MASK;
-
- /*
- * Mask exceptions and grab the first TLB entry. We won't be
- * needing it while sleeping.
- */
- asm volatile("ssrf %0" : : "i"(SYSREG_EM_OFFSET) : "memory");
-
- mmucr = sysreg_read(MMUCR);
- tlbehi = sysreg_read(TLBEHI);
- sysreg_write(MMUCR, SYSREG_BFINS(DRP, 0, mmucr));
-
- tlbehi = SYSREG_BF(ASID, SYSREG_BFEXT(ASID, tlbehi));
- tlbehi |= vaddr & PAGE_MASK;
- tlbehi |= SYSREG_BIT(TLBEHI_V);
-
- sysreg_write(TLBELO, page_addr | SRAM_PAGE_FLAGS);
- sysreg_write(TLBEHI, tlbehi);
- __builtin_tlbw();
-
- return (void *)(vaddr + pm_sram_start - page_addr);
-}
-
-/*
- * Must be called with interrupts disabled. Exceptions will be
- * unmasked on return.
- */
-static void avr32_pm_unmap_sram(void)
-{
- u32 mmucr;
- u32 tlbehi;
- u32 tlbarlo;
-
- /* Going to update TLB entry at index 0 */
- mmucr = sysreg_read(MMUCR);
- tlbehi = sysreg_read(TLBEHI);
- sysreg_write(MMUCR, SYSREG_BFINS(DRP, 0, mmucr));
-
- /* Clear the "valid" bit */
- tlbehi = SYSREG_BF(ASID, SYSREG_BFEXT(ASID, tlbehi));
- sysreg_write(TLBEHI, tlbehi);
-
- /* Mark it as "not accessed" */
- tlbarlo = sysreg_read(TLBARLO);
- sysreg_write(TLBARLO, tlbarlo | 0x80000000U);
-
- /* Update the TLB */
- __builtin_tlbw();
-
- /* Unmask exceptions */
- asm volatile("csrf %0" : : "i"(SYSREG_EM_OFFSET) : "memory");
-}
-
-static int avr32_pm_valid_state(suspend_state_t state)
-{
- switch (state) {
- case PM_SUSPEND_ON:
- case PM_SUSPEND_STANDBY:
- case PM_SUSPEND_MEM:
- return 1;
-
- default:
- return 0;
- }
-}
-
-static int avr32_pm_enter(suspend_state_t state)
-{
- u32 lpr_saved;
- u32 evba_saved;
- void *sram;
-
- switch (state) {
- case PM_SUSPEND_STANDBY:
- sram = avr32_pm_map_sram();
-
- /* Switch to in-sram exception handlers */
- evba_saved = sysreg_read(EVBA);
- sysreg_write(EVBA, (unsigned long)sram);
-
- /*
- * Save the LPR register so that we can re-enable
- * SDRAM Low Power mode on resume.
- */
- lpr_saved = sdramc_readl(LPR);
- pr_debug("%s: Entering standby...\n", __func__);
- avr32_pm_enter_standby(SDRAMC_BASE);
- sdramc_writel(LPR, lpr_saved);
-
- /* Switch back to regular exception handlers */
- sysreg_write(EVBA, evba_saved);
-
- avr32_pm_unmap_sram();
- break;
-
- case PM_SUSPEND_MEM:
- sram = avr32_pm_map_sram();
-
- /* Switch to in-sram exception handlers */
- evba_saved = sysreg_read(EVBA);
- sysreg_write(EVBA, (unsigned long)sram);
-
- /*
- * Save the LPR register so that we can re-enable
- * SDRAM Low Power mode on resume.
- */
- lpr_saved = sdramc_readl(LPR);
- pr_debug("%s: Entering suspend-to-ram...\n", __func__);
- avr32_pm_enter_str(SDRAMC_BASE);
- sdramc_writel(LPR, lpr_saved);
-
- /* Switch back to regular exception handlers */
- sysreg_write(EVBA, evba_saved);
-
- avr32_pm_unmap_sram();
- break;
-
- case PM_SUSPEND_ON:
- pr_debug("%s: Entering idle...\n", __func__);
- cpu_enter_idle();
- break;
-
- default:
- pr_debug("%s: Invalid suspend state %d\n", __func__, state);
- goto out;
- }
-
- pr_debug("%s: wakeup\n", __func__);
-
-out:
- return 0;
-}
-
-static const struct platform_suspend_ops avr32_pm_ops = {
- .valid = avr32_pm_valid_state,
- .enter = avr32_pm_enter,
-};
-
-static unsigned long __init avr32_pm_offset(void *symbol)
-{
- extern u8 pm_exception[];
-
- return (unsigned long)symbol - (unsigned long)pm_exception;
-}
-
-static int __init avr32_pm_init(void)
-{
- extern u8 pm_exception[];
- extern u8 pm_irq0[];
- extern u8 pm_standby[];
- extern u8 pm_suspend_to_ram[];
- extern u8 pm_sram_end[];
- void *dst;
-
- /*
- * To keep things simple, we depend on not needing more than a
- * single page.
- */
- pm_sram_size = avr32_pm_offset(pm_sram_end);
- if (pm_sram_size > PAGE_SIZE)
- goto err;
-
- pm_sram_start = sram_alloc(pm_sram_size);
- if (!pm_sram_start)
- goto err_alloc_sram;
-
- /* Grab a virtual area we can use later on. */
- pm_sram_area = get_vm_area(pm_sram_size, VM_IOREMAP);
- if (!pm_sram_area)
- goto err_vm_area;
- pm_sram_area->phys_addr = pm_sram_start;
-
- local_irq_disable();
- dst = avr32_pm_map_sram();
- memcpy(dst, pm_exception, pm_sram_size);
- flush_dcache_region(dst, pm_sram_size);
- invalidate_icache_region(dst, pm_sram_size);
- avr32_pm_unmap_sram();
- local_irq_enable();
-
- avr32_pm_enter_standby = dst + avr32_pm_offset(pm_standby);
- avr32_pm_enter_str = dst + avr32_pm_offset(pm_suspend_to_ram);
- intc_set_suspend_handler(avr32_pm_offset(pm_irq0));
-
- suspend_set_ops(&avr32_pm_ops);
-
- printk("AVR32 AP Power Management enabled\n");
-
- return 0;
-
-err_vm_area:
- sram_free(pm_sram_start, pm_sram_size);
-err_alloc_sram:
-err:
- pr_err("AVR32 Power Management initialization failed\n");
- return -ENOMEM;
-}
-arch_initcall(avr32_pm_init);
+++ /dev/null
-/*
- * Register definitions for the Power Manager (PM)
- */
-#ifndef __ARCH_AVR32_MACH_AT32AP_PM_H__
-#define __ARCH_AVR32_MACH_AT32AP_PM_H__
-
-/* PM register offsets */
-#define PM_MCCTRL 0x0000
-#define PM_CKSEL 0x0004
-#define PM_CPU_MASK 0x0008
-#define PM_HSB_MASK 0x000c
-#define PM_PBA_MASK 0x0010
-#define PM_PBB_MASK 0x0014
-#define PM_PLL0 0x0020
-#define PM_PLL1 0x0024
-#define PM_IER 0x0040
-#define PM_IDR 0x0044
-#define PM_IMR 0x0048
-#define PM_ISR 0x004c
-#define PM_ICR 0x0050
-#define PM_GCCTRL(x) (0x0060 + 4 * (x))
-#define PM_RCAUSE 0x00c0
-
-/* Bitfields in CKSEL */
-#define PM_CPUSEL_OFFSET 0
-#define PM_CPUSEL_SIZE 3
-#define PM_CPUDIV_OFFSET 7
-#define PM_CPUDIV_SIZE 1
-#define PM_HSBSEL_OFFSET 8
-#define PM_HSBSEL_SIZE 3
-#define PM_HSBDIV_OFFSET 15
-#define PM_HSBDIV_SIZE 1
-#define PM_PBASEL_OFFSET 16
-#define PM_PBASEL_SIZE 3
-#define PM_PBADIV_OFFSET 23
-#define PM_PBADIV_SIZE 1
-#define PM_PBBSEL_OFFSET 24
-#define PM_PBBSEL_SIZE 3
-#define PM_PBBDIV_OFFSET 31
-#define PM_PBBDIV_SIZE 1
-
-/* Bitfields in PLL0 */
-#define PM_PLLEN_OFFSET 0
-#define PM_PLLEN_SIZE 1
-#define PM_PLLOSC_OFFSET 1
-#define PM_PLLOSC_SIZE 1
-#define PM_PLLOPT_OFFSET 2
-#define PM_PLLOPT_SIZE 3
-#define PM_PLLDIV_OFFSET 8
-#define PM_PLLDIV_SIZE 8
-#define PM_PLLMUL_OFFSET 16
-#define PM_PLLMUL_SIZE 8
-#define PM_PLLCOUNT_OFFSET 24
-#define PM_PLLCOUNT_SIZE 6
-#define PM_PLLTEST_OFFSET 31
-#define PM_PLLTEST_SIZE 1
-
-/* Bitfields in ICR */
-#define PM_LOCK0_OFFSET 0
-#define PM_LOCK0_SIZE 1
-#define PM_LOCK1_OFFSET 1
-#define PM_LOCK1_SIZE 1
-#define PM_WAKE_OFFSET 2
-#define PM_WAKE_SIZE 1
-#define PM_CKRDY_OFFSET 5
-#define PM_CKRDY_SIZE 1
-#define PM_MSKRDY_OFFSET 6
-#define PM_MSKRDY_SIZE 1
-
-/* Bitfields in GCCTRL0 */
-#define PM_OSCSEL_OFFSET 0
-#define PM_OSCSEL_SIZE 1
-#define PM_PLLSEL_OFFSET 1
-#define PM_PLLSEL_SIZE 1
-#define PM_CEN_OFFSET 2
-#define PM_CEN_SIZE 1
-#define PM_DIVEN_OFFSET 4
-#define PM_DIVEN_SIZE 1
-#define PM_DIV_OFFSET 8
-#define PM_DIV_SIZE 8
-
-/* Bitfields in RCAUSE */
-#define PM_POR_OFFSET 0
-#define PM_POR_SIZE 1
-#define PM_EXT_OFFSET 2
-#define PM_EXT_SIZE 1
-#define PM_WDT_OFFSET 3
-#define PM_WDT_SIZE 1
-#define PM_NTAE_OFFSET 4
-#define PM_NTAE_SIZE 1
-
-/* Bit manipulation macros */
-#define PM_BIT(name) \
- (1 << PM_##name##_OFFSET)
-#define PM_BF(name,value) \
- (((value) & ((1 << PM_##name##_SIZE) - 1)) \
- << PM_##name##_OFFSET)
-#define PM_BFEXT(name,value) \
- (((value) >> PM_##name##_OFFSET) \
- & ((1 << PM_##name##_SIZE) - 1))
-#define PM_BFINS(name,value,old)\
- (((old) & ~(((1 << PM_##name##_SIZE) - 1) \
- << PM_##name##_OFFSET)) \
- | PM_BF(name,value))
-
-/* Register access macros */
-#define pm_readl(reg) \
- __raw_readl((void __iomem __force *)PM_BASE + PM_##reg)
-#define pm_writel(reg,value) \
- __raw_writel((value), (void __iomem __force *)PM_BASE + PM_##reg)
-
-#endif /* __ARCH_AVR32_MACH_AT32AP_PM_H__ */
+++ /dev/null
-/*
- * Register definitions for the AT32AP SDRAM Controller
- *
- * Copyright (C) 2008 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
- */
-
-/* Register offsets */
-#define SDRAMC_MR 0x0000
-#define SDRAMC_TR 0x0004
-#define SDRAMC_CR 0x0008
-#define SDRAMC_HSR 0x000c
-#define SDRAMC_LPR 0x0010
-#define SDRAMC_IER 0x0014
-#define SDRAMC_IDR 0x0018
-#define SDRAMC_IMR 0x001c
-#define SDRAMC_ISR 0x0020
-#define SDRAMC_MDR 0x0024
-
-/* MR - Mode Register */
-#define SDRAMC_MR_MODE_NORMAL ( 0 << 0)
-#define SDRAMC_MR_MODE_NOP ( 1 << 0)
-#define SDRAMC_MR_MODE_BANKS_PRECHARGE ( 2 << 0)
-#define SDRAMC_MR_MODE_LOAD_MODE ( 3 << 0)
-#define SDRAMC_MR_MODE_AUTO_REFRESH ( 4 << 0)
-#define SDRAMC_MR_MODE_EXT_LOAD_MODE ( 5 << 0)
-#define SDRAMC_MR_MODE_POWER_DOWN ( 6 << 0)
-
-/* CR - Configuration Register */
-#define SDRAMC_CR_NC_8_BITS ( 0 << 0)
-#define SDRAMC_CR_NC_9_BITS ( 1 << 0)
-#define SDRAMC_CR_NC_10_BITS ( 2 << 0)
-#define SDRAMC_CR_NC_11_BITS ( 3 << 0)
-#define SDRAMC_CR_NR_11_BITS ( 0 << 2)
-#define SDRAMC_CR_NR_12_BITS ( 1 << 2)
-#define SDRAMC_CR_NR_13_BITS ( 2 << 2)
-#define SDRAMC_CR_NB_2_BANKS ( 0 << 4)
-#define SDRAMC_CR_NB_4_BANKS ( 1 << 4)
-#define SDRAMC_CR_CAS(x) ((x) << 5)
-#define SDRAMC_CR_DBW_32_BITS ( 0 << 7)
-#define SDRAMC_CR_DBW_16_BITS ( 1 << 7)
-#define SDRAMC_CR_TWR(x) ((x) << 8)
-#define SDRAMC_CR_TRC(x) ((x) << 12)
-#define SDRAMC_CR_TRP(x) ((x) << 16)
-#define SDRAMC_CR_TRCD(x) ((x) << 20)
-#define SDRAMC_CR_TRAS(x) ((x) << 24)
-#define SDRAMC_CR_TXSR(x) ((x) << 28)
-
-/* HSR - High Speed Register */
-#define SDRAMC_HSR_DA ( 1 << 0)
-
-/* LPR - Low Power Register */
-#define SDRAMC_LPR_LPCB_INHIBIT ( 0 << 0)
-#define SDRAMC_LPR_LPCB_SELF_RFR ( 1 << 0)
-#define SDRAMC_LPR_LPCB_PDOWN ( 2 << 0)
-#define SDRAMC_LPR_LPCB_DEEP_PDOWN ( 3 << 0)
-#define SDRAMC_LPR_PASR(x) ((x) << 4)
-#define SDRAMC_LPR_TCSR(x) ((x) << 8)
-#define SDRAMC_LPR_DS(x) ((x) << 10)
-#define SDRAMC_LPR_TIMEOUT(x) ((x) << 12)
-
-/* IER/IDR/IMR/ISR - Interrupt Enable/Disable/Mask/Status Register */
-#define SDRAMC_ISR_RES ( 1 << 0)
-
-/* MDR - Memory Device Register */
-#define SDRAMC_MDR_MD_SDRAM ( 0 << 0)
-#define SDRAMC_MDR_MD_LOW_PWR_SDRAM ( 1 << 0)
-
-/* Register access macros */
-#define sdramc_readl(reg) \
- __raw_readl((void __iomem __force *)SDRAMC_BASE + SDRAMC_##reg)
-#define sdramc_writel(reg, value) \
- __raw_writel(value, (void __iomem __force *)SDRAMC_BASE + SDRAMC_##reg)
+++ /dev/null
-#
-# Makefile for the Linux/AVR32 kernel.
-#
-
-obj-y += init.o clear_page.o copy_page.o dma-coherent.o
-obj-y += ioremap.o cache.o fault.o tlb.o
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/highmem.h>
-#include <linux/unistd.h>
-
-#include <asm/cacheflush.h>
-#include <asm/cachectl.h>
-#include <asm/processor.h>
-#include <linux/uaccess.h>
-#include <asm/syscalls.h>
-
-/*
- * If you attempt to flush anything more than this, you need superuser
- * privileges. The value is completely arbitrary.
- */
-#define CACHEFLUSH_MAX_LEN 1024
-
-void invalidate_dcache_region(void *start, size_t size)
-{
- unsigned long v, begin, end, linesz, mask;
-
- linesz = boot_cpu_data.dcache.linesz;
- mask = linesz - 1;
-
- /* when first and/or last cachelines are shared, flush them
- * instead of invalidating ... never discard valid data!
- */
- begin = (unsigned long)start;
- end = begin + size;
-
- if (begin & mask) {
- flush_dcache_line(start);
- begin += linesz;
- }
- if (end & mask) {
- flush_dcache_line((void *)end);
- end &= ~mask;
- }
-
- /* remaining cachelines only need invalidation */
- for (v = begin; v < end; v += linesz)
- invalidate_dcache_line((void *)v);
- flush_write_buffer();
-}
-
-void clean_dcache_region(void *start, size_t size)
-{
- unsigned long v, begin, end, linesz;
-
- linesz = boot_cpu_data.dcache.linesz;
- begin = (unsigned long)start & ~(linesz - 1);
- end = ((unsigned long)start + size + linesz - 1) & ~(linesz - 1);
-
- for (v = begin; v < end; v += linesz)
- clean_dcache_line((void *)v);
- flush_write_buffer();
-}
-
-void flush_dcache_region(void *start, size_t size)
-{
- unsigned long v, begin, end, linesz;
-
- linesz = boot_cpu_data.dcache.linesz;
- begin = (unsigned long)start & ~(linesz - 1);
- end = ((unsigned long)start + size + linesz - 1) & ~(linesz - 1);
-
- for (v = begin; v < end; v += linesz)
- flush_dcache_line((void *)v);
- flush_write_buffer();
-}
-
-void invalidate_icache_region(void *start, size_t size)
-{
- unsigned long v, begin, end, linesz;
-
- linesz = boot_cpu_data.icache.linesz;
- begin = (unsigned long)start & ~(linesz - 1);
- end = ((unsigned long)start + size + linesz - 1) & ~(linesz - 1);
-
- for (v = begin; v < end; v += linesz)
- invalidate_icache_line((void *)v);
-}
-
-static inline void __flush_icache_range(unsigned long start, unsigned long end)
-{
- unsigned long v, linesz;
-
- linesz = boot_cpu_data.dcache.linesz;
- for (v = start; v < end; v += linesz) {
- clean_dcache_line((void *)v);
- invalidate_icache_line((void *)v);
- }
-
- flush_write_buffer();
-}
-
-/*
- * This one is called after a module has been loaded.
- */
-void flush_icache_range(unsigned long start, unsigned long end)
-{
- unsigned long linesz;
-
- linesz = boot_cpu_data.dcache.linesz;
- __flush_icache_range(start & ~(linesz - 1),
- (end + linesz - 1) & ~(linesz - 1));
-}
-EXPORT_SYMBOL(flush_icache_range);
-
-/*
- * This one is called from __do_fault() and do_swap_page().
- */
-void flush_icache_page(struct vm_area_struct *vma, struct page *page)
-{
- if (vma->vm_flags & VM_EXEC) {
- void *v = page_address(page);
- __flush_icache_range((unsigned long)v, (unsigned long)v + PAGE_SIZE);
- }
-}
-
-asmlinkage int sys_cacheflush(int operation, void __user *addr, size_t len)
-{
- int ret;
-
- if (len > CACHEFLUSH_MAX_LEN) {
- ret = -EPERM;
- if (!capable(CAP_SYS_ADMIN))
- goto out;
- }
-
- ret = -EFAULT;
- if (!access_ok(VERIFY_WRITE, addr, len))
- goto out;
-
- switch (operation) {
- case CACHE_IFLUSH:
- flush_icache_range((unsigned long)addr,
- (unsigned long)addr + len);
- ret = 0;
- break;
- default:
- ret = -EINVAL;
- }
-
-out:
- return ret;
-}
-
-void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
- unsigned long vaddr, void *dst, const void *src,
- unsigned long len)
-{
- memcpy(dst, src, len);
- if (vma->vm_flags & VM_EXEC)
- flush_icache_range((unsigned long)dst,
- (unsigned long)dst + len);
-}
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/linkage.h>
-#include <asm/page.h>
-
-/*
- * clear_page
- * r12: P1 address (to)
- */
- .text
- .global clear_page
-clear_page:
- sub r9, r12, -PAGE_SIZE
- mov r10, 0
- mov r11, 0
-0: st.d r12++, r10
- cp r12, r9
- brne 0b
- mov pc, lr
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/linkage.h>
-#include <asm/page.h>
-
-/*
- * copy_page
- *
- * r12 to (P1 address)
- * r11 from (P1 address)
- * r8-r10 scratch
- */
- .text
- .global copy_page
-copy_page:
- sub r10, r11, -(1 << PAGE_SHIFT)
- /* pref r11[0] */
-1: /* pref r11[8] */
- ld.d r8, r11++
- st.d r12++, r8
- cp r11, r10
- brlo 1b
- mov pc, lr
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/dma-mapping.h>
-#include <linux/gfp.h>
-#include <linux/export.h>
-#include <linux/mm.h>
-#include <linux/device.h>
-#include <linux/scatterlist.h>
-
-#include <asm/processor.h>
-#include <asm/cacheflush.h>
-#include <asm/io.h>
-#include <asm/addrspace.h>
-
-void dma_cache_sync(struct device *dev, void *vaddr, size_t size, int direction)
-{
- /*
- * No need to sync an uncached area
- */
- if (PXSEG(vaddr) == P2SEG)
- return;
-
- switch (direction) {
- case DMA_FROM_DEVICE: /* invalidate only */
- invalidate_dcache_region(vaddr, size);
- break;
- case DMA_TO_DEVICE: /* writeback only */
- clean_dcache_region(vaddr, size);
- break;
- case DMA_BIDIRECTIONAL: /* writeback and invalidate */
- flush_dcache_region(vaddr, size);
- break;
- default:
- BUG();
- }
-}
-EXPORT_SYMBOL(dma_cache_sync);
-
-static struct page *__dma_alloc(struct device *dev, size_t size,
- dma_addr_t *handle, gfp_t gfp)
-{
- struct page *page, *free, *end;
- int order;
-
- /* Following is a work-around (a.k.a. hack) to prevent pages
- * with __GFP_COMP being passed to split_page() which cannot
- * handle them. The real problem is that this flag probably
- * should be 0 on AVR32 as it is not supported on this
- * platform--see CONFIG_HUGETLB_PAGE. */
- gfp &= ~(__GFP_COMP);
-
- size = PAGE_ALIGN(size);
- order = get_order(size);
-
- page = alloc_pages(gfp, order);
- if (!page)
- return NULL;
- split_page(page, order);
-
- /*
- * When accessing physical memory with valid cache data, we
- * get a cache hit even if the virtual memory region is marked
- * as uncached.
- *
- * Since the memory is newly allocated, there is no point in
- * doing a writeback. If the previous owner cares, he should
- * have flushed the cache before releasing the memory.
- */
- invalidate_dcache_region(phys_to_virt(page_to_phys(page)), size);
-
- *handle = page_to_bus(page);
- free = page + (size >> PAGE_SHIFT);
- end = page + (1 << order);
-
- /*
- * Free any unused pages
- */
- while (free < end) {
- __free_page(free);
- free++;
- }
-
- return page;
-}
-
-static void __dma_free(struct device *dev, size_t size,
- struct page *page, dma_addr_t handle)
-{
- struct page *end = page + (PAGE_ALIGN(size) >> PAGE_SHIFT);
-
- while (page < end)
- __free_page(page++);
-}
-
-static void *avr32_dma_alloc(struct device *dev, size_t size,
- dma_addr_t *handle, gfp_t gfp, unsigned long attrs)
-{
- struct page *page;
- dma_addr_t phys;
-
- page = __dma_alloc(dev, size, handle, gfp);
- if (!page)
- return NULL;
- phys = page_to_phys(page);
-
- if (attrs & DMA_ATTR_WRITE_COMBINE) {
- /* Now, map the page into P3 with write-combining turned on */
- *handle = phys;
- return __ioremap(phys, size, _PAGE_BUFFER);
- } else {
- return phys_to_uncached(phys);
- }
-}
-
-static void avr32_dma_free(struct device *dev, size_t size,
- void *cpu_addr, dma_addr_t handle, unsigned long attrs)
-{
- struct page *page;
-
- if (attrs & DMA_ATTR_WRITE_COMBINE) {
- iounmap(cpu_addr);
-
- page = phys_to_page(handle);
- } else {
- void *addr = phys_to_cached(uncached_to_phys(cpu_addr));
-
- pr_debug("avr32_dma_free addr %p (phys %08lx) size %u\n",
- cpu_addr, (unsigned long)handle, (unsigned)size);
-
- BUG_ON(!virt_addr_valid(addr));
- page = virt_to_page(addr);
- }
-
- __dma_free(dev, size, page, handle);
-}
-
-static dma_addr_t avr32_dma_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction direction, unsigned long attrs)
-{
- void *cpu_addr = page_address(page) + offset;
-
- if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
- dma_cache_sync(dev, cpu_addr, size, direction);
- return virt_to_bus(cpu_addr);
-}
-
-static int avr32_dma_map_sg(struct device *dev, struct scatterlist *sglist,
- int nents, enum dma_data_direction direction,
- unsigned long attrs)
-{
- int i;
- struct scatterlist *sg;
-
- for_each_sg(sglist, sg, nents, i) {
- char *virt;
-
- sg->dma_address = page_to_bus(sg_page(sg)) + sg->offset;
- virt = sg_virt(sg);
-
- if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
- continue;
-
- dma_cache_sync(dev, virt, sg->length, direction);
- }
-
- return nents;
-}
-
-static void avr32_dma_sync_single_for_device(struct device *dev,
- dma_addr_t dma_handle, size_t size,
- enum dma_data_direction direction)
-{
- dma_cache_sync(dev, bus_to_virt(dma_handle), size, direction);
-}
-
-static void avr32_dma_sync_sg_for_device(struct device *dev,
- struct scatterlist *sglist, int nents,
- enum dma_data_direction direction)
-{
- int i;
- struct scatterlist *sg;
-
- for_each_sg(sglist, sg, nents, i)
- dma_cache_sync(dev, sg_virt(sg), sg->length, direction);
-}
-
-const struct dma_map_ops avr32_dma_ops = {
- .alloc = avr32_dma_alloc,
- .free = avr32_dma_free,
- .map_page = avr32_dma_map_page,
- .map_sg = avr32_dma_map_sg,
- .sync_single_for_device = avr32_dma_sync_single_for_device,
- .sync_sg_for_device = avr32_dma_sync_sg_for_device,
-};
-EXPORT_SYMBOL(avr32_dma_ops);
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * Based on linux/arch/sh/mm/fault.c:
- * Copyright (C) 1999 Niibe Yutaka
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/mm.h>
-#include <linux/extable.h>
-#include <linux/pagemap.h>
-#include <linux/kdebug.h>
-#include <linux/kprobes.h>
-#include <linux/uaccess.h>
-
-#include <asm/mmu_context.h>
-#include <asm/sysreg.h>
-#include <asm/tlb.h>
-
-#ifdef CONFIG_KPROBES
-static inline int notify_page_fault(struct pt_regs *regs, int trap)
-{
- int ret = 0;
-
- if (!user_mode(regs)) {
- if (kprobe_running() && kprobe_fault_handler(regs, trap))
- ret = 1;
- }
-
- return ret;
-}
-#else
-static inline int notify_page_fault(struct pt_regs *regs, int trap)
-{
- return 0;
-}
-#endif
-
-int exception_trace = 1;
-
-/*
- * This routine handles page faults. It determines the address and the
- * problem, and then passes it off to one of the appropriate routines.
- *
- * ecr is the Exception Cause Register. Possible values are:
- * 6: Protection fault (instruction access)
- * 15: Protection fault (read access)
- * 16: Protection fault (write access)
- * 20: Page not found (instruction access)
- * 24: Page not found (read access)
- * 28: Page not found (write access)
- */
-asmlinkage void do_page_fault(unsigned long ecr, struct pt_regs *regs)
-{
- struct task_struct *tsk;
- struct mm_struct *mm;
- struct vm_area_struct *vma;
- const struct exception_table_entry *fixup;
- unsigned long address;
- unsigned long page;
- long signr;
- int code;
- int fault;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
-
- if (notify_page_fault(regs, ecr))
- return;
-
- address = sysreg_read(TLBEAR);
-
- tsk = current;
- mm = tsk->mm;
-
- signr = SIGSEGV;
- code = SEGV_MAPERR;
-
- /*
- * If we're in an interrupt or have no user context, we must
- * not take the fault...
- */
- if (faulthandler_disabled() || !mm || regs->sr & SYSREG_BIT(GM))
- goto no_context;
-
- local_irq_enable();
-
- if (user_mode(regs))
- flags |= FAULT_FLAG_USER;
-retry:
- down_read(&mm->mmap_sem);
-
- vma = find_vma(mm, address);
- if (!vma)
- goto bad_area;
- if (vma->vm_start <= address)
- goto good_area;
- if (!(vma->vm_flags & VM_GROWSDOWN))
- goto bad_area;
- if (expand_stack(vma, address))
- goto bad_area;
-
- /*
- * Ok, we have a good vm_area for this memory access, so we
- * can handle it...
- */
-good_area:
- code = SEGV_ACCERR;
-
- switch (ecr) {
- case ECR_PROTECTION_X:
- case ECR_TLB_MISS_X:
- if (!(vma->vm_flags & VM_EXEC))
- goto bad_area;
- break;
- case ECR_PROTECTION_R:
- case ECR_TLB_MISS_R:
- if (!(vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)))
- goto bad_area;
- break;
- case ECR_PROTECTION_W:
- case ECR_TLB_MISS_W:
- if (!(vma->vm_flags & VM_WRITE))
- goto bad_area;
- flags |= FAULT_FLAG_WRITE;
- break;
- default:
- panic("Unhandled case %lu in do_page_fault!", ecr);
- }
-
- /*
- * If for any reason at all we couldn't handle the fault, make
- * sure we exit gracefully rather than endlessly redo the
- * fault.
- */
- fault = handle_mm_fault(vma, address, flags);
-
- if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
- return;
-
- if (unlikely(fault & VM_FAULT_ERROR)) {
- if (fault & VM_FAULT_OOM)
- goto out_of_memory;
- else if (fault & VM_FAULT_SIGSEGV)
- goto bad_area;
- else if (fault & VM_FAULT_SIGBUS)
- goto do_sigbus;
- BUG();
- }
-
- if (flags & FAULT_FLAG_ALLOW_RETRY) {
- if (fault & VM_FAULT_MAJOR)
- tsk->maj_flt++;
- else
- tsk->min_flt++;
- if (fault & VM_FAULT_RETRY) {
- flags &= ~FAULT_FLAG_ALLOW_RETRY;
- flags |= FAULT_FLAG_TRIED;
-
- /*
- * No need to up_read(&mm->mmap_sem) as we would have
- * already released it in __lock_page_or_retry() in
- * mm/filemap.c.
- */
- goto retry;
- }
- }
-
- up_read(&mm->mmap_sem);
- return;
-
- /*
- * Something tried to access memory that isn't in our memory
- * map. Fix it, but check if it's kernel or user first...
- */
-bad_area:
- up_read(&mm->mmap_sem);
-
- if (user_mode(regs)) {
- if (exception_trace && printk_ratelimit())
- printk("%s%s[%d]: segfault at %08lx pc %08lx "
- "sp %08lx ecr %lu\n",
- is_global_init(tsk) ? KERN_EMERG : KERN_INFO,
- tsk->comm, tsk->pid, address, regs->pc,
- regs->sp, ecr);
- _exception(SIGSEGV, regs, code, address);
- return;
- }
-
-no_context:
- /* Are we prepared to handle this kernel fault? */
- fixup = search_exception_tables(regs->pc);
- if (fixup) {
- regs->pc = fixup->fixup;
- return;
- }
-
- /*
- * Oops. The kernel tried to access some bad page. We'll have
- * to terminate things with extreme prejudice.
- */
- if (address < PAGE_SIZE)
- printk(KERN_ALERT
- "Unable to handle kernel NULL pointer dereference");
- else
- printk(KERN_ALERT
- "Unable to handle kernel paging request");
- printk(" at virtual address %08lx\n", address);
-
- page = sysreg_read(PTBR);
- printk(KERN_ALERT "ptbr = %08lx", page);
- if (address >= TASK_SIZE)
- page = (unsigned long)swapper_pg_dir;
- if (page) {
- page = ((unsigned long *)page)[address >> 22];
- printk(" pgd = %08lx", page);
- if (page & _PAGE_PRESENT) {
- page &= PAGE_MASK;
- address &= 0x003ff000;
- page = ((unsigned long *)__va(page))[address >> PAGE_SHIFT];
- printk(" pte = %08lx", page);
- }
- }
- printk("\n");
- die("Kernel access of bad area", regs, signr);
- return;
-
- /*
- * We ran out of memory, or some other thing happened to us
- * that made us unable to handle the page fault gracefully.
- */
-out_of_memory:
- up_read(&mm->mmap_sem);
- if (!user_mode(regs))
- goto no_context;
- pagefault_out_of_memory();
- return;
-
-do_sigbus:
- up_read(&mm->mmap_sem);
-
- /* Kernel mode? Handle exceptions or die */
- signr = SIGBUS;
- code = BUS_ADRERR;
- if (!user_mode(regs))
- goto no_context;
-
- if (exception_trace)
- printk("%s%s[%d]: bus error at %08lx pc %08lx "
- "sp %08lx ecr %lu\n",
- is_global_init(tsk) ? KERN_EMERG : KERN_INFO,
- tsk->comm, tsk->pid, address, regs->pc,
- regs->sp, ecr);
-
- _exception(SIGBUS, regs, BUS_ADRERR, address);
-}
-
-asmlinkage void do_bus_error(unsigned long addr, int write_access,
- struct pt_regs *regs)
-{
- printk(KERN_ALERT
- "Bus error at physical address 0x%08lx (%s access)\n",
- addr, write_access ? "write" : "read");
- printk(KERN_INFO "DTLB dump:\n");
- dump_dtlb();
- die("Bus Error", regs, SIGKILL);
-}
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/kernel.h>
-#include <linux/gfp.h>
-#include <linux/mm.h>
-#include <linux/swap.h>
-#include <linux/init.h>
-#include <linux/mmzone.h>
-#include <linux/module.h>
-#include <linux/bootmem.h>
-#include <linux/pagemap.h>
-#include <linux/nodemask.h>
-
-#include <asm/page.h>
-#include <asm/mmu_context.h>
-#include <asm/tlb.h>
-#include <asm/io.h>
-#include <asm/dma.h>
-#include <asm/setup.h>
-#include <asm/sections.h>
-
-pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_data;
-
-struct page *empty_zero_page;
-EXPORT_SYMBOL(empty_zero_page);
-
-/*
- * Cache of MMU context last used.
- */
-unsigned long mmu_context_cache = NO_CONTEXT;
-
-/*
- * paging_init() sets up the page tables
- *
- * This routine also unmaps the page at virtual kernel address 0, so
- * that we can trap those pesky NULL-reference errors in the kernel.
- */
-void __init paging_init(void)
-{
- extern unsigned long _evba;
- void *zero_page;
- int nid;
-
- /*
- * Make sure we can handle exceptions before enabling
- * paging. Not that we should ever _get_ any exceptions this
- * early, but you never know...
- */
- printk("Exception vectors start at %p\n", &_evba);
- sysreg_write(EVBA, (unsigned long)&_evba);
-
- /*
- * Since we are ready to handle exceptions now, we should let
- * the CPU generate them...
- */
- __asm__ __volatile__ ("csrf %0" : : "i"(SR_EM_BIT));
-
- /*
- * Allocate the zero page. The allocator will panic if it
- * can't satisfy the request, so no need to check.
- */
- zero_page = alloc_bootmem_low_pages_node(NODE_DATA(0),
- PAGE_SIZE);
-
- sysreg_write(PTBR, (unsigned long)swapper_pg_dir);
- enable_mmu();
- printk ("CPU: Paging enabled\n");
-
- for_each_online_node(nid) {
- pg_data_t *pgdat = NODE_DATA(nid);
- unsigned long zones_size[MAX_NR_ZONES];
- unsigned long low, start_pfn;
-
- start_pfn = pgdat->bdata->node_min_pfn;
- low = pgdat->bdata->node_low_pfn;
-
- memset(zones_size, 0, sizeof(zones_size));
- zones_size[ZONE_NORMAL] = low - start_pfn;
-
- printk("Node %u: start_pfn = 0x%lx, low = 0x%lx\n",
- nid, start_pfn, low);
-
- free_area_init_node(nid, zones_size, start_pfn, NULL);
-
- printk("Node %u: mem_map starts at %p\n",
- pgdat->node_id, pgdat->node_mem_map);
- }
-
- mem_map = NODE_DATA(0)->node_mem_map;
-
- empty_zero_page = virt_to_page(zero_page);
- flush_dcache_page(empty_zero_page);
-}
-
-void __init mem_init(void)
-{
- pg_data_t *pgdat;
-
- high_memory = NULL;
- for_each_online_pgdat(pgdat)
- high_memory = max_t(void *, high_memory,
- __va(pgdat_end_pfn(pgdat) << PAGE_SHIFT));
-
- set_max_mapnr(MAP_NR(high_memory));
- free_all_bootmem();
- mem_init_print_info(NULL);
-}
-
-void free_initmem(void)
-{
- free_initmem_default(-1);
-}
-
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
- free_reserved_area((void *)start, (void *)end, -1, "initrd");
-}
-#endif
+++ /dev/null
-/*
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/vmalloc.h>
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/io.h>
-#include <linux/slab.h>
-
-#include <asm/pgtable.h>
-#include <asm/addrspace.h>
-
-/*
- * Re-map an arbitrary physical address space into the kernel virtual
- * address space. Needed when the kernel wants to access physical
- * memory directly.
- */
-void __iomem *__ioremap(unsigned long phys_addr, size_t size,
- unsigned long flags)
-{
- unsigned long addr;
- struct vm_struct *area;
- unsigned long offset, last_addr;
- pgprot_t prot;
-
- /*
- * Check if we can simply use the P4 segment. This area is
- * uncacheable, so if caching/buffering is requested, we can't
- * use it.
- */
- if ((phys_addr >= P4SEG) && (flags == 0))
- return (void __iomem *)phys_addr;
-
- /* Don't allow wraparound or zero size */
- last_addr = phys_addr + size - 1;
- if (!size || last_addr < phys_addr)
- return NULL;
-
- /*
- * XXX: When mapping regular RAM, we'd better make damn sure
- * it's never used for anything else. But this is really the
- * caller's responsibility...
- */
- if (PHYSADDR(P2SEGADDR(phys_addr)) == phys_addr)
- return (void __iomem *)P2SEGADDR(phys_addr);
-
- /* Mappings have to be page-aligned */
- offset = phys_addr & ~PAGE_MASK;
- phys_addr &= PAGE_MASK;
- size = PAGE_ALIGN(last_addr + 1) - phys_addr;
-
- prot = __pgprot(_PAGE_PRESENT | _PAGE_GLOBAL | _PAGE_RW | _PAGE_DIRTY
- | _PAGE_ACCESSED | _PAGE_TYPE_SMALL | flags);
-
- /*
- * Ok, go for it..
- */
- area = get_vm_area(size, VM_IOREMAP);
- if (!area)
- return NULL;
- area->phys_addr = phys_addr;
- addr = (unsigned long )area->addr;
- if (ioremap_page_range(addr, addr + size, phys_addr, prot)) {
- vunmap((void *)addr);
- return NULL;
- }
-
- return (void __iomem *)(offset + (char *)addr);
-}
-EXPORT_SYMBOL(__ioremap);
-
-void __iounmap(void __iomem *addr)
-{
- struct vm_struct *p;
-
- if ((unsigned long)addr >= P4SEG)
- return;
- if (PXSEG(addr) == P2SEG)
- return;
-
- p = remove_vm_area((void *)(PAGE_MASK & (unsigned long __force)addr));
- if (unlikely(!p)) {
- printk (KERN_ERR "iounmap: bad address %p\n", addr);
- return;
- }
-
- kfree (p);
-}
-EXPORT_SYMBOL(__iounmap);
+++ /dev/null
-/*
- * AVR32 TLB operations
- *
- * Copyright (C) 2004-2006 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/mm.h>
-
-#include <asm/mmu_context.h>
-
-/* TODO: Get the correct number from the CONFIG1 system register */
-#define NR_TLB_ENTRIES 32
-
-static void show_dtlb_entry(unsigned int index)
-{
- u32 tlbehi, tlbehi_save, tlbelo, mmucr, mmucr_save;
- unsigned long flags;
-
- local_irq_save(flags);
- mmucr_save = sysreg_read(MMUCR);
- tlbehi_save = sysreg_read(TLBEHI);
- mmucr = SYSREG_BFINS(DRP, index, mmucr_save);
- sysreg_write(MMUCR, mmucr);
-
- __builtin_tlbr();
- cpu_sync_pipeline();
-
- tlbehi = sysreg_read(TLBEHI);
- tlbelo = sysreg_read(TLBELO);
-
- printk("%2u: %c %c %02x %05x %05x %o %o %c %c %c %c\n",
- index,
- SYSREG_BFEXT(TLBEHI_V, tlbehi) ? '1' : '0',
- SYSREG_BFEXT(G, tlbelo) ? '1' : '0',
- SYSREG_BFEXT(ASID, tlbehi),
- SYSREG_BFEXT(VPN, tlbehi) >> 2,
- SYSREG_BFEXT(PFN, tlbelo) >> 2,
- SYSREG_BFEXT(AP, tlbelo),
- SYSREG_BFEXT(SZ, tlbelo),
- SYSREG_BFEXT(TLBELO_C, tlbelo) ? 'C' : ' ',
- SYSREG_BFEXT(B, tlbelo) ? 'B' : ' ',
- SYSREG_BFEXT(W, tlbelo) ? 'W' : ' ',
- SYSREG_BFEXT(TLBELO_D, tlbelo) ? 'D' : ' ');
-
- sysreg_write(MMUCR, mmucr_save);
- sysreg_write(TLBEHI, tlbehi_save);
- cpu_sync_pipeline();
- local_irq_restore(flags);
-}
-
-void dump_dtlb(void)
-{
- unsigned int i;
-
- printk("ID V G ASID VPN PFN AP SZ C B W D\n");
- for (i = 0; i < NR_TLB_ENTRIES; i++)
- show_dtlb_entry(i);
-}
-
-static void update_dtlb(unsigned long address, pte_t pte)
-{
- u32 tlbehi;
- u32 mmucr;
-
- /*
- * We're not changing the ASID here, so no need to flush the
- * pipeline.
- */
- tlbehi = sysreg_read(TLBEHI);
- tlbehi = SYSREG_BF(ASID, SYSREG_BFEXT(ASID, tlbehi));
- tlbehi |= address & MMU_VPN_MASK;
- tlbehi |= SYSREG_BIT(TLBEHI_V);
- sysreg_write(TLBEHI, tlbehi);
-
- /* Does this mapping already exist? */
- __builtin_tlbs();
- mmucr = sysreg_read(MMUCR);
-
- if (mmucr & SYSREG_BIT(MMUCR_N)) {
- /* Not found -- pick a not-recently-accessed entry */
- unsigned int rp;
- u32 tlbar = sysreg_read(TLBARLO);
-
- rp = 32 - fls(tlbar);
- if (rp == 32) {
- rp = 0;
- sysreg_write(TLBARLO, -1L);
- }
-
- mmucr = SYSREG_BFINS(DRP, rp, mmucr);
- sysreg_write(MMUCR, mmucr);
- }
-
- sysreg_write(TLBELO, pte_val(pte) & _PAGE_FLAGS_HARDWARE_MASK);
-
- /* Let's go */
- __builtin_tlbw();
-}
-
-void update_mmu_cache(struct vm_area_struct *vma,
- unsigned long address, pte_t *ptep)
-{
- unsigned long flags;
-
- /* ptrace may call this routine */
- if (vma && current->active_mm != vma->vm_mm)
- return;
-
- local_irq_save(flags);
- update_dtlb(address, *ptep);
- local_irq_restore(flags);
-}
-
-static void __flush_tlb_page(unsigned long asid, unsigned long page)
-{
- u32 mmucr, tlbehi;
-
- /*
- * Caller is responsible for masking out non-PFN bits in page
- * and changing the current ASID if necessary. This means that
- * we don't need to flush the pipeline after writing TLBEHI.
- */
- tlbehi = page | asid;
- sysreg_write(TLBEHI, tlbehi);
-
- __builtin_tlbs();
- mmucr = sysreg_read(MMUCR);
-
- if (!(mmucr & SYSREG_BIT(MMUCR_N))) {
- unsigned int entry;
- u32 tlbarlo;
-
- /* Clear the "valid" bit */
- sysreg_write(TLBEHI, tlbehi);
-
- /* mark the entry as "not accessed" */
- entry = SYSREG_BFEXT(DRP, mmucr);
- tlbarlo = sysreg_read(TLBARLO);
- tlbarlo |= (0x80000000UL >> entry);
- sysreg_write(TLBARLO, tlbarlo);
-
- /* update the entry with valid bit clear */
- __builtin_tlbw();
- }
-}
-
-void flush_tlb_page(struct vm_area_struct *vma, unsigned long page)
-{
- if (vma->vm_mm && vma->vm_mm->context != NO_CONTEXT) {
- unsigned long flags, asid;
- unsigned long saved_asid = MMU_NO_ASID;
-
- asid = vma->vm_mm->context & MMU_CONTEXT_ASID_MASK;
- page &= PAGE_MASK;
-
- local_irq_save(flags);
- if (vma->vm_mm != current->mm) {
- saved_asid = get_asid();
- set_asid(asid);
- }
-
- __flush_tlb_page(asid, page);
-
- if (saved_asid != MMU_NO_ASID)
- set_asid(saved_asid);
- local_irq_restore(flags);
- }
-}
-
-void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
- unsigned long end)
-{
- struct mm_struct *mm = vma->vm_mm;
-
- if (mm->context != NO_CONTEXT) {
- unsigned long flags;
- int size;
-
- local_irq_save(flags);
- size = (end - start + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
-
- if (size > (MMU_DTLB_ENTRIES / 4)) { /* Too many entries to flush */
- mm->context = NO_CONTEXT;
- if (mm == current->mm)
- activate_context(mm);
- } else {
- unsigned long asid;
- unsigned long saved_asid;
-
- asid = mm->context & MMU_CONTEXT_ASID_MASK;
- saved_asid = MMU_NO_ASID;
-
- start &= PAGE_MASK;
- end += (PAGE_SIZE - 1);
- end &= PAGE_MASK;
-
- if (mm != current->mm) {
- saved_asid = get_asid();
- set_asid(asid);
- }
-
- while (start < end) {
- __flush_tlb_page(asid, start);
- start += PAGE_SIZE;
- }
- if (saved_asid != MMU_NO_ASID)
- set_asid(saved_asid);
- }
- local_irq_restore(flags);
- }
-}
-
-/*
- * This function depends on the pages to be flushed having the G
- * (global) bit set in their pte. This is true for all
- * PAGE_KERNEL(_RO) pages.
- */
-void flush_tlb_kernel_range(unsigned long start, unsigned long end)
-{
- unsigned long flags;
- int size;
-
- size = (end - start + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
- if (size > (MMU_DTLB_ENTRIES / 4)) { /* Too many entries to flush */
- flush_tlb_all();
- } else {
- unsigned long asid;
-
- local_irq_save(flags);
- asid = get_asid();
-
- start &= PAGE_MASK;
- end += (PAGE_SIZE - 1);
- end &= PAGE_MASK;
-
- while (start < end) {
- __flush_tlb_page(asid, start);
- start += PAGE_SIZE;
- }
- local_irq_restore(flags);
- }
-}
-
-void flush_tlb_mm(struct mm_struct *mm)
-{
- /* Invalidate all TLB entries of this process by getting a new ASID */
- if (mm->context != NO_CONTEXT) {
- unsigned long flags;
-
- local_irq_save(flags);
- mm->context = NO_CONTEXT;
- if (mm == current->mm)
- activate_context(mm);
- local_irq_restore(flags);
- }
-}
-
-void flush_tlb_all(void)
-{
- unsigned long flags;
-
- local_irq_save(flags);
- sysreg_write(MMUCR, sysreg_read(MMUCR) | SYSREG_BIT(MMUCR_I));
- local_irq_restore(flags);
-}
-
-#ifdef CONFIG_PROC_FS
-
-#include <linux/seq_file.h>
-#include <linux/proc_fs.h>
-#include <linux/init.h>
-
-static void *tlb_start(struct seq_file *tlb, loff_t *pos)
-{
- static unsigned long tlb_index;
-
- if (*pos >= NR_TLB_ENTRIES)
- return NULL;
-
- tlb_index = 0;
- return &tlb_index;
-}
-
-static void *tlb_next(struct seq_file *tlb, void *v, loff_t *pos)
-{
- unsigned long *index = v;
-
- if (*index >= NR_TLB_ENTRIES - 1)
- return NULL;
-
- ++*pos;
- ++*index;
- return index;
-}
-
-static void tlb_stop(struct seq_file *tlb, void *v)
-{
-
-}
-
-static int tlb_show(struct seq_file *tlb, void *v)
-{
- unsigned int tlbehi, tlbehi_save, tlbelo, mmucr, mmucr_save;
- unsigned long flags;
- unsigned long *index = v;
-
- if (*index == 0)
- seq_puts(tlb, "ID V G ASID VPN PFN AP SZ C B W D\n");
-
- BUG_ON(*index >= NR_TLB_ENTRIES);
-
- local_irq_save(flags);
- mmucr_save = sysreg_read(MMUCR);
- tlbehi_save = sysreg_read(TLBEHI);
- mmucr = SYSREG_BFINS(DRP, *index, mmucr_save);
- sysreg_write(MMUCR, mmucr);
-
- /* TLBR might change the ASID */
- __builtin_tlbr();
- cpu_sync_pipeline();
-
- tlbehi = sysreg_read(TLBEHI);
- tlbelo = sysreg_read(TLBELO);
-
- sysreg_write(MMUCR, mmucr_save);
- sysreg_write(TLBEHI, tlbehi_save);
- cpu_sync_pipeline();
- local_irq_restore(flags);
-
- seq_printf(tlb, "%2lu: %c %c %02x %05x %05x %o %o %c %c %c %c\n",
- *index,
- SYSREG_BFEXT(TLBEHI_V, tlbehi) ? '1' : '0',
- SYSREG_BFEXT(G, tlbelo) ? '1' : '0',
- SYSREG_BFEXT(ASID, tlbehi),
- SYSREG_BFEXT(VPN, tlbehi) >> 2,
- SYSREG_BFEXT(PFN, tlbelo) >> 2,
- SYSREG_BFEXT(AP, tlbelo),
- SYSREG_BFEXT(SZ, tlbelo),
- SYSREG_BFEXT(TLBELO_C, tlbelo) ? '1' : '0',
- SYSREG_BFEXT(B, tlbelo) ? '1' : '0',
- SYSREG_BFEXT(W, tlbelo) ? '1' : '0',
- SYSREG_BFEXT(TLBELO_D, tlbelo) ? '1' : '0');
-
- return 0;
-}
-
-static const struct seq_operations tlb_ops = {
- .start = tlb_start,
- .next = tlb_next,
- .stop = tlb_stop,
- .show = tlb_show,
-};
-
-static int tlb_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &tlb_ops);
-}
-
-static const struct file_operations proc_tlb_operations = {
- .open = tlb_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
-static int __init proctlb_init(void)
-{
- proc_create("tlb", 0, NULL, &proc_tlb_operations);
- return 0;
-}
-late_initcall(proctlb_init);
-#endif /* CONFIG_PROC_FS */
+++ /dev/null
-obj-$(CONFIG_OPROFILE) += oprofile.o
-
-oprofile-y := $(addprefix ../../../drivers/oprofile/, \
- oprof.o cpu_buffer.o buffer_sync.o \
- event_buffer.o oprofile_files.o \
- oprofilefs.o oprofile_stats.o \
- timer_int.o)
-oprofile-y += op_model_avr32.o backtrace.o
+++ /dev/null
-/*
- * AVR32 specific backtracing code for oprofile
- *
- * Copyright 2008 Weinmann GmbH
- *
- * Author: Nikolaus Voss <n.voss@weinmann.de>
- *
- * Based on i386 oprofile backtrace code by John Levon and David Smith
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- */
-
-#include <linux/oprofile.h>
-#include <linux/ptrace.h>
-#include <linux/uaccess.h>
-
-/* The first two words of each frame on the stack look like this if we have
- * frame pointers */
-struct frame_head {
- unsigned long lr;
- struct frame_head *fp;
-};
-
-/* copied from arch/avr32/kernel/process.c */
-static inline int valid_stack_ptr(struct thread_info *tinfo, unsigned long p)
-{
- return (p > (unsigned long)tinfo)
- && (p < (unsigned long)tinfo + THREAD_SIZE - 3);
-}
-
-/* copied from arch/x86/oprofile/backtrace.c */
-static struct frame_head *dump_user_backtrace(struct frame_head *head)
-{
- struct frame_head bufhead[2];
-
- /* Also check accessibility of one struct frame_head beyond */
- if (!access_ok(VERIFY_READ, head, sizeof(bufhead)))
- return NULL;
- if (__copy_from_user_inatomic(bufhead, head, sizeof(bufhead)))
- return NULL;
-
- oprofile_add_trace(bufhead[0].lr);
-
- /* frame pointers should strictly progress back up the stack
- * (towards higher addresses) */
- if (bufhead[0].fp <= head)
- return NULL;
-
- return bufhead[0].fp;
-}
-
-void avr32_backtrace(struct pt_regs * const regs, unsigned int depth)
-{
- /* Get first frame pointer */
- struct frame_head *head = (struct frame_head *)(regs->r7);
-
- if (!user_mode(regs)) {
-#ifdef CONFIG_FRAME_POINTER
- /*
- * Traverse the kernel stack from frame to frame up to
- * "depth" steps.
- */
- while (depth-- && valid_stack_ptr(task_thread_info(current),
- (unsigned long)head)) {
- oprofile_add_trace(head->lr);
- if (head->fp <= head)
- break;
- head = head->fp;
- }
-#endif
- } else {
- /* Assume we have frame pointers in user mode process */
- while (depth-- && head)
- head = dump_user_backtrace(head);
- }
-}
-
-
+++ /dev/null
-/*
- * AVR32 Performance Counter Driver
- *
- * Copyright (C) 2005-2007 Atmel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Author: Ronny Pedersen
- */
-#include <linux/errno.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/oprofile.h>
-#include <linux/sched.h>
-#include <linux/types.h>
-
-#include <asm/sysreg.h>
-
-#define AVR32_PERFCTR_IRQ_GROUP 0
-#define AVR32_PERFCTR_IRQ_LINE 1
-
-void avr32_backtrace(struct pt_regs * const regs, unsigned int depth);
-
-enum { PCCNT, PCNT0, PCNT1, NR_counter };
-
-struct avr32_perf_counter {
- unsigned long enabled;
- unsigned long event;
- unsigned long count;
- unsigned long unit_mask;
- unsigned long kernel;
- unsigned long user;
-
- u32 ie_mask;
- u32 flag_mask;
-};
-
-static struct avr32_perf_counter counter[NR_counter] = {
- {
- .ie_mask = SYSREG_BIT(IEC),
- .flag_mask = SYSREG_BIT(FC),
- }, {
- .ie_mask = SYSREG_BIT(IE0),
- .flag_mask = SYSREG_BIT(F0),
- }, {
- .ie_mask = SYSREG_BIT(IE1),
- .flag_mask = SYSREG_BIT(F1),
- },
-};
-
-static void avr32_perf_counter_reset(void)
-{
- /* Reset all counter and disable/clear all interrupts */
- sysreg_write(PCCR, (SYSREG_BIT(PCCR_R)
- | SYSREG_BIT(PCCR_C)
- | SYSREG_BIT(FC)
- | SYSREG_BIT(F0)
- | SYSREG_BIT(F1)));
-}
-
-static irqreturn_t avr32_perf_counter_interrupt(int irq, void *dev_id)
-{
- struct avr32_perf_counter *ctr = dev_id;
- struct pt_regs *regs;
- u32 pccr;
-
- if (likely(!(intc_get_pending(AVR32_PERFCTR_IRQ_GROUP)
- & (1 << AVR32_PERFCTR_IRQ_LINE))))
- return IRQ_NONE;
-
- regs = get_irq_regs();
- pccr = sysreg_read(PCCR);
-
- /* Clear the interrupt flags we're about to handle */
- sysreg_write(PCCR, pccr);
-
- /* PCCNT */
- if (ctr->enabled && (pccr & ctr->flag_mask)) {
- sysreg_write(PCCNT, -ctr->count);
- oprofile_add_sample(regs, PCCNT);
- }
- ctr++;
- /* PCNT0 */
- if (ctr->enabled && (pccr & ctr->flag_mask)) {
- sysreg_write(PCNT0, -ctr->count);
- oprofile_add_sample(regs, PCNT0);
- }
- ctr++;
- /* PCNT1 */
- if (ctr->enabled && (pccr & ctr->flag_mask)) {
- sysreg_write(PCNT1, -ctr->count);
- oprofile_add_sample(regs, PCNT1);
- }
-
- return IRQ_HANDLED;
-}
-
-static int avr32_perf_counter_create_files(struct dentry *root)
-{
- struct dentry *dir;
- unsigned int i;
- char filename[4];
-
- for (i = 0; i < NR_counter; i++) {
- snprintf(filename, sizeof(filename), "%u", i);
- dir = oprofilefs_mkdir(root, filename);
-
- oprofilefs_create_ulong(dir, "enabled",
- &counter[i].enabled);
- oprofilefs_create_ulong(dir, "event",
- &counter[i].event);
- oprofilefs_create_ulong(dir, "count",
- &counter[i].count);
-
- /* Dummy entries */
- oprofilefs_create_ulong(dir, "kernel",
- &counter[i].kernel);
- oprofilefs_create_ulong(dir, "user",
- &counter[i].user);
- oprofilefs_create_ulong(dir, "unit_mask",
- &counter[i].unit_mask);
- }
-
- return 0;
-}
-
-static int avr32_perf_counter_setup(void)
-{
- struct avr32_perf_counter *ctr;
- u32 pccr;
- int ret;
- int i;
-
- pr_debug("avr32_perf_counter_setup\n");
-
- if (sysreg_read(PCCR) & SYSREG_BIT(PCCR_E)) {
- printk(KERN_ERR
- "oprofile: setup: perf counter already enabled\n");
- return -EBUSY;
- }
-
- ret = request_irq(AVR32_PERFCTR_IRQ_GROUP,
- avr32_perf_counter_interrupt, IRQF_SHARED,
- "oprofile", counter);
- if (ret)
- return ret;
-
- avr32_perf_counter_reset();
-
- pccr = 0;
- for (i = PCCNT; i < NR_counter; i++) {
- ctr = &counter[i];
- if (!ctr->enabled)
- continue;
-
- pr_debug("enabling counter %d...\n", i);
-
- pccr |= ctr->ie_mask;
-
- switch (i) {
- case PCCNT:
- /* PCCNT always counts cycles, so no events */
- sysreg_write(PCCNT, -ctr->count);
- break;
- case PCNT0:
- pccr |= SYSREG_BF(CONF0, ctr->event);
- sysreg_write(PCNT0, -ctr->count);
- break;
- case PCNT1:
- pccr |= SYSREG_BF(CONF1, ctr->event);
- sysreg_write(PCNT1, -ctr->count);
- break;
- }
- }
-
- pr_debug("oprofile: writing 0x%x to PCCR...\n", pccr);
-
- sysreg_write(PCCR, pccr);
-
- return 0;
-}
-
-static void avr32_perf_counter_shutdown(void)
-{
- pr_debug("avr32_perf_counter_shutdown\n");
-
- avr32_perf_counter_reset();
- free_irq(AVR32_PERFCTR_IRQ_GROUP, counter);
-}
-
-static int avr32_perf_counter_start(void)
-{
- pr_debug("avr32_perf_counter_start\n");
-
- sysreg_write(PCCR, sysreg_read(PCCR) | SYSREG_BIT(PCCR_E));
-
- return 0;
-}
-
-static void avr32_perf_counter_stop(void)
-{
- pr_debug("avr32_perf_counter_stop\n");
-
- sysreg_write(PCCR, sysreg_read(PCCR) & ~SYSREG_BIT(PCCR_E));
-}
-
-static struct oprofile_operations avr32_perf_counter_ops __initdata = {
- .create_files = avr32_perf_counter_create_files,
- .setup = avr32_perf_counter_setup,
- .shutdown = avr32_perf_counter_shutdown,
- .start = avr32_perf_counter_start,
- .stop = avr32_perf_counter_stop,
- .cpu_type = "avr32",
-};
-
-int __init oprofile_arch_init(struct oprofile_operations *ops)
-{
- if (!(current_cpu_data.features & AVR32_FEATURE_PCTR))
- return -ENODEV;
-
- memcpy(ops, &avr32_perf_counter_ops,
- sizeof(struct oprofile_operations));
-
- ops->backtrace = avr32_backtrace;
-
- printk(KERN_INFO "oprofile: using AVR32 performance monitoring.\n");
-
- return 0;
-}
-
-void oprofile_arch_exit(void)
-{
-
-}
generic-y += div64.h
generic-y += emergency-restart.h
generic-y += errno.h
+generic-y += extable.h
generic-y += fb.h
generic-y += futex.h
generic-y += hw_irq.h
/*
* User space memory access functions
*/
-#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/string.h>
#define segment_eq(a, b) ((a) == (b))
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
#define access_ok(type, addr, size) _access_ok((unsigned long)(addr), (size))
/*
extern int _access_ok(unsigned long addr, unsigned long size);
#endif
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue. No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path. This means when everything is well,
- * we don't even have to jump over them. Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry {
- unsigned long insn, fixup;
-};
+#include <asm/extable.h>
/*
* These are the main single-value transfer routines. They automatically
: "a" (__ptr(ptr))); \
})
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
-
static inline unsigned long __must_check
-__copy_from_user(void *to, const void __user *from, unsigned long n)
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
{
memcpy(to, (const void __force *)from, n);
return 0;
}
static inline unsigned long __must_check
-__copy_to_user(void __user *to, const void *from, unsigned long n)
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
{
memcpy((void __force *)to, from, n);
SSYNC();
return 0;
}
-static inline unsigned long __must_check
-copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- if (likely(access_ok(VERIFY_READ, from, n)))
- return __copy_from_user(to, from, n);
- memset(to, 0, n);
- return n;
-}
-
-static inline unsigned long __must_check
-copy_to_user(void __user *to, const void *from, unsigned long n)
-{
- if (likely(access_ok(VERIFY_WRITE, to, n)))
- return __copy_to_user(to, from, n);
- return n;
-}
-
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
/*
* Copy a null terminated string from userspace.
*/
/* Check that things do not wrap around */
if (addr > ULONG_MAX - size)
return 0;
- if (segment_eq(get_fs(), KERNEL_DS))
+ if (uaccess_kernel())
return 1;
#ifdef CONFIG_MTD_UCLINUX
if (1)
clock_tick = get_sclk();
evt->mult = div_sc(clock_tick, NSEC_PER_SEC, evt->shift);
evt->max_delta_ns = clockevent_delta2ns(-1, evt);
+ evt->max_delta_ticks = (unsigned long)-1;
evt->min_delta_ns = clockevent_delta2ns(100, evt);
+ evt->min_delta_ticks = 100;
evt->cpumask = cpumask_of(0);
clock_tick = get_cclk() / TIME_SCALE;
evt->mult = div_sc(clock_tick, NSEC_PER_SEC, evt->shift);
evt->max_delta_ns = clockevent_delta2ns(-1, evt);
+ evt->max_delta_ticks = (unsigned long)-1;
evt->min_delta_ns = clockevent_delta2ns(100, evt);
+ evt->min_delta_ticks = 100;
evt->cpumask = cpumask_of(cpu);
generic-y += emergency-restart.h
generic-y += errno.h
generic-y += exec.h
+generic-y += extable.h
generic-y += fb.h
generic-y += fcntl.h
generic-y += futex.h
#include <linux/compiler.h>
#include <linux/string.h>
-#ifdef CONFIG_ACCESS_CHECK
-#define __access_ok _access_ok
-#endif
-
/*
- * __copy_from_user/copy_to_user are based on ones in asm-generic/uaccess.h
- *
* C6X supports unaligned 32 and 64 bit loads and stores.
*/
-static inline __must_check long __copy_from_user(void *to,
- const void __user *from, unsigned long n)
+static inline __must_check unsigned long
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
{
u32 tmp32;
u64 tmp64;
return 0;
}
-static inline __must_check long __copy_to_user(void __user *to,
- const void *from, unsigned long n)
+static inline __must_check unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
{
u32 tmp32;
u64 tmp64;
memcpy((void __force *)to, from, n);
return 0;
}
-
-#define __copy_to_user __copy_to_user
-#define __copy_from_user __copy_from_user
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
extern int _access_ok(unsigned long addr, unsigned long size);
#ifdef CONFIG_ACCESS_CHECK
if (!addr || addr > (0xffffffffUL - (size - 1)))
goto _bad_access;
- if (segment_eq(get_fs(), KERNEL_DS))
+ if (uaccess_kernel())
return 1;
if (memory_start <= addr && (addr + size - 1) < memory_end)
clockevents_calc_mult_shift(cd, c6x_core_freq / TIMER_DIVISOR, 5);
cd->max_delta_ns = clockevent_delta2ns(0x7fffffff, cd);
+ cd->max_delta_ticks = 0x7fffffff;
cd->min_delta_ns = clockevent_delta2ns(250, cd);
+ cd->min_delta_ticks = 250;
cd->cpumask = cpumask_of(smp_processor_id());
}
EXPORT_SYMBOL(__copy_user);
-/* Copy from user to kernel, zeroing the bytes that were inaccessible in
- userland. The return-value is the number of bytes that were
+/* Copy from user to kernel. The return-value is the number of bytes that were
inaccessible. */
-unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
+unsigned long __copy_user_in(void *pdst, const void __user *psrc,
unsigned long pn)
{
/* We want the parameters put in special registers.
{
__asm_copy_from_user_1 (dst, src, retn);
n--;
+ if (retn)
+ goto exception;
}
if (((unsigned long) src & 2) && n >= 2)
{
__asm_copy_from_user_2 (dst, src, retn);
n -= 2;
+ if (retn)
+ goto exception;
}
-
- /* We only need one check after the unalignment-adjustments, because
- if both adjustments were done, either both or neither reference
- had an exception. */
- if (retn != 0)
- goto copy_exception_bytes;
}
/* Decide which copying method to use. */
n -= 4;
if (retn)
- goto copy_exception_bytes;
+ goto exception;
}
/* If we get here, there were no memory read faults. */
bytes. */
return retn;
-copy_exception_bytes:
- /* We already have "retn" bytes cleared, and need to clear the
- remaining "n" bytes. A non-optimized simple byte-for-byte in-line
- memset is preferred here, since this isn't speed-critical code and
- we'd rather have this a leaf-function than calling memset. */
- {
- char *endp;
- for (endp = dst + n; dst < endp; dst++)
- *dst = 0;
- }
-
+exception:
return retn + n;
}
-EXPORT_SYMBOL(__copy_user_zeroing);
+EXPORT_SYMBOL(__copy_user_in);
/* Zero userspace. */
unsigned long __do_clear_user(void __user *pto, unsigned long pn)
}
EXPORT_SYMBOL(__copy_user);
-/* Copy from user to kernel, zeroing the bytes that were inaccessible in
- userland. The return-value is the number of bytes that were
+/* Copy from user to kernel. The return-value is the number of bytes that were
inaccessible. */
-unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
+unsigned long __copy_user_in(void *pdst, const void __user *psrc,
unsigned long pn)
{
/* We want the parameters put in special registers.
{
__asm_copy_from_user_1 (dst, src, retn);
n--;
+ if (retn != 0)
+ goto exception;
}
if (((unsigned long) src & 2) && n >= 2)
{
__asm_copy_from_user_2 (dst, src, retn);
n -= 2;
+ if (retn != 0)
+ goto exception;
}
- /* We only need one check after the unalignment-adjustments, because
- if both adjustments were done, either both or neither reference
- had an exception. */
- if (retn != 0)
- goto copy_exception_bytes;
}
/* Movem is dirt cheap. The overheap is low enough to always use the
n -= 4;
if (retn)
- goto copy_exception_bytes;
+ goto exception;
}
/* If we get here, there were no memory read faults. */
bytes. */
return retn;
-copy_exception_bytes:
- /* We already have "retn" bytes cleared, and need to clear the
- remaining "n" bytes. A non-optimized simple byte-for-byte in-line
- memset is preferred here, since this isn't speed-critical code and
- we'd rather have this a leaf-function than calling memset. */
- {
- char *endp;
- for (endp = dst + n; dst < endp; dst++)
- *dst = 0;
- }
-
+exception:
return retn + n;
}
-EXPORT_SYMBOL(__copy_user_zeroing);
+EXPORT_SYMBOL(__copy_user_in);
/* Zero userspace. */
unsigned long __do_clear_user(void __user *pto, unsigned long pn)
__asm_copy_user_cont(to, from, ret, \
" move.b [%1+],$r9\n" \
"2: move.b $r9,[%0+]\n", \
- "3: addq 1,%2\n" \
- " clear.b [%0+]\n", \
+ "3: addq 1,%2\n", \
" .dword 2b,3b\n")
#define __asm_copy_from_user_2x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
__asm_copy_user_cont(to, from, ret, \
" move.w [%1+],$r9\n" \
"2: move.w $r9,[%0+]\n" COPY, \
- "3: addq 2,%2\n" \
- " clear.w [%0+]\n" FIXUP, \
+ "3: addq 2,%2\n" FIXUP, \
" .dword 2b,3b\n" TENTRY)
#define __asm_copy_from_user_2(to, from, ret) \
__asm_copy_from_user_2x_cont(to, from, ret, \
" move.b [%1+],$r9\n" \
"4: move.b $r9,[%0+]\n", \
- "5: addq 1,%2\n" \
- " clear.b [%0+]\n", \
+ "5: addq 1,%2\n", \
" .dword 4b,5b\n")
#define __asm_copy_from_user_4x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
__asm_copy_user_cont(to, from, ret, \
" move.d [%1+],$r9\n" \
"2: move.d $r9,[%0+]\n" COPY, \
- "3: addq 4,%2\n" \
- " clear.d [%0+]\n" FIXUP, \
+ "3: addq 4,%2\n" FIXUP, \
" .dword 2b,3b\n" TENTRY)
#define __asm_copy_from_user_4(to, from, ret) \
__asm_copy_from_user_4x_cont(to, from, ret, \
" move.b [%1+],$r9\n" \
"4: move.b $r9,[%0+]\n", \
- "5: addq 1,%2\n" \
- " clear.b [%0+]\n", \
+ "5: addq 1,%2\n", \
" .dword 4b,5b\n")
#define __asm_copy_from_user_6x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
" move.w [%1+],$r9\n" \
"4: move.w $r9,[%0+]\n" COPY, \
"5: addq 2,%2\n" \
- " clear.w [%0+]\n" FIXUP, \
+ FIXUP, \
" .dword 4b,5b\n" TENTRY)
#define __asm_copy_from_user_6(to, from, ret) \
__asm_copy_from_user_6x_cont(to, from, ret, \
" move.b [%1+],$r9\n" \
"6: move.b $r9,[%0+]\n", \
- "7: addq 1,%2\n" \
- " clear.b [%0+]\n", \
+ "7: addq 1,%2\n", \
" .dword 6b,7b\n")
#define __asm_copy_from_user_8x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
" move.d [%1+],$r9\n" \
"4: move.d $r9,[%0+]\n" COPY, \
"5: addq 4,%2\n" \
- " clear.d [%0+]\n" FIXUP, \
+ FIXUP, \
" .dword 4b,5b\n" TENTRY)
#define __asm_copy_from_user_8(to, from, ret) \
__asm_copy_from_user_8x_cont(to, from, ret, \
" move.b [%1+],$r9\n" \
"6: move.b $r9,[%0+]\n", \
- "7: addq 1,%2\n" \
- " clear.b [%0+]\n", \
+ "7: addq 1,%2\n", \
" .dword 6b,7b\n")
#define __asm_copy_from_user_10x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
" move.w [%1+],$r9\n" \
"6: move.w $r9,[%0+]\n" COPY, \
"7: addq 2,%2\n" \
- " clear.w [%0+]\n" FIXUP, \
+ FIXUP, \
" .dword 6b,7b\n" TENTRY)
#define __asm_copy_from_user_10(to, from, ret) \
__asm_copy_from_user_10x_cont(to, from, ret, \
" move.b [%1+],$r9\n" \
"8: move.b $r9,[%0+]\n", \
- "9: addq 1,%2\n" \
- " clear.b [%0+]\n", \
+ "9: addq 1,%2\n", \
" .dword 8b,9b\n")
#define __asm_copy_from_user_12x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
" move.d [%1+],$r9\n" \
"6: move.d $r9,[%0+]\n" COPY, \
"7: addq 4,%2\n" \
- " clear.d [%0+]\n" FIXUP, \
+ FIXUP, \
" .dword 6b,7b\n" TENTRY)
#define __asm_copy_from_user_12(to, from, ret) \
__asm_copy_from_user_12x_cont(to, from, ret, \
" move.b [%1+],$r9\n" \
"8: move.b $r9,[%0+]\n", \
- "9: addq 1,%2\n" \
- " clear.b [%0+]\n", \
+ "9: addq 1,%2\n", \
" .dword 8b,9b\n")
#define __asm_copy_from_user_14x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
" move.w [%1+],$r9\n" \
"8: move.w $r9,[%0+]\n" COPY, \
"9: addq 2,%2\n" \
- " clear.w [%0+]\n" FIXUP, \
+ FIXUP, \
" .dword 8b,9b\n" TENTRY)
#define __asm_copy_from_user_14(to, from, ret) \
__asm_copy_from_user_14x_cont(to, from, ret, \
" move.b [%1+],$r9\n" \
"10: move.b $r9,[%0+]\n", \
- "11: addq 1,%2\n" \
- " clear.b [%0+]\n", \
+ "11: addq 1,%2\n", \
" .dword 10b,11b\n")
#define __asm_copy_from_user_16x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
" move.d [%1+],$r9\n" \
"8: move.d $r9,[%0+]\n" COPY, \
"9: addq 4,%2\n" \
- " clear.d [%0+]\n" FIXUP, \
+ FIXUP, \
" .dword 8b,9b\n" TENTRY)
#define __asm_copy_from_user_16(to, from, ret) \
" move.d [%1+],$r9\n" \
"10: move.d $r9,[%0+]\n" COPY, \
"11: addq 4,%2\n" \
- " clear.d [%0+]\n" FIXUP, \
+ FIXUP, \
" .dword 10b,11b\n" TENTRY)
#define __asm_copy_from_user_20(to, from, ret) \
" move.d [%1+],$r9\n" \
"12: move.d $r9,[%0+]\n" COPY, \
"13: addq 4,%2\n" \
- " clear.d [%0+]\n" FIXUP, \
+ FIXUP, \
" .dword 12b,13b\n" TENTRY)
#define __asm_copy_from_user_24(to, from, ret) \
"2: move.b [%1+],$acr\n" \
" move.b $acr,[%0+]\n", \
"3: addq 1,%2\n" \
- " jump 1b\n" \
- " clear.b [%0+]\n", \
+ " jump 1b\n", \
" .dword 2b,3b\n")
#define __asm_copy_from_user_2x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
" move.w $acr,[%0+]\n", \
FIXUP \
"3: addq 2,%2\n" \
- " jump 1b\n" \
- " clear.w [%0+]\n", \
+ " jump 1b\n", \
TENTRY \
" .dword 2b,3b\n")
__asm_copy_from_user_2x_cont(to, from, ret, \
"4: move.b [%1+],$acr\n" \
" move.b $acr,[%0+]\n", \
- "5: addq 1,%2\n" \
- " clear.b [%0+]\n", \
+ "5: addq 1,%2\n", \
" .dword 4b,5b\n")
#define __asm_copy_from_user_4x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
" move.d $acr,[%0+]\n", \
FIXUP \
"3: addq 4,%2\n" \
- " jump 1b\n" \
- " clear.d [%0+]\n", \
+ " jump 1b\n", \
TENTRY \
" .dword 2b,3b\n")
__asm_copy_from_user_4x_cont(to, from, ret, \
"4: move.b [%1+],$acr\n" \
" move.b $acr,[%0+]\n", \
- "5: addq 1,%2\n" \
- " clear.b [%0+]\n", \
+ "5: addq 1,%2\n", \
" .dword 4b,5b\n")
#define __asm_copy_from_user_6x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
"4: move.w [%1+],$acr\n" \
" move.w $acr,[%0+]\n", \
FIXUP \
- "5: addq 2,%2\n" \
- " clear.w [%0+]\n", \
+ "5: addq 2,%2\n", \
TENTRY \
" .dword 4b,5b\n")
__asm_copy_from_user_6x_cont(to, from, ret, \
"6: move.b [%1+],$acr\n" \
" move.b $acr,[%0+]\n", \
- "7: addq 1,%2\n" \
- " clear.b [%0+]\n", \
+ "7: addq 1,%2\n", \
" .dword 6b,7b\n")
#define __asm_copy_from_user_8x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
"4: move.d [%1+],$acr\n" \
" move.d $acr,[%0+]\n", \
FIXUP \
- "5: addq 4,%2\n" \
- " clear.d [%0+]\n", \
+ "5: addq 4,%2\n", \
TENTRY \
" .dword 4b,5b\n")
__asm_copy_from_user_8x_cont(to, from, ret, \
"6: move.b [%1+],$acr\n" \
" move.b $acr,[%0+]\n", \
- "7: addq 1,%2\n" \
- " clear.b [%0+]\n", \
+ "7: addq 1,%2\n", \
" .dword 6b,7b\n")
#define __asm_copy_from_user_10x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
"6: move.w [%1+],$acr\n" \
" move.w $acr,[%0+]\n", \
FIXUP \
- "7: addq 2,%2\n" \
- " clear.w [%0+]\n", \
+ "7: addq 2,%2\n", \
TENTRY \
" .dword 6b,7b\n")
__asm_copy_from_user_10x_cont(to, from, ret, \
"8: move.b [%1+],$acr\n" \
" move.b $acr,[%0+]\n", \
- "9: addq 1,%2\n" \
- " clear.b [%0+]\n", \
+ "9: addq 1,%2\n", \
" .dword 8b,9b\n")
#define __asm_copy_from_user_12x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
"6: move.d [%1+],$acr\n" \
" move.d $acr,[%0+]\n", \
FIXUP \
- "7: addq 4,%2\n" \
- " clear.d [%0+]\n", \
+ "7: addq 4,%2\n", \
TENTRY \
" .dword 6b,7b\n")
__asm_copy_from_user_12x_cont(to, from, ret, \
"8: move.b [%1+],$acr\n" \
" move.b $acr,[%0+]\n", \
- "9: addq 1,%2\n" \
- " clear.b [%0+]\n", \
+ "9: addq 1,%2\n", \
" .dword 8b,9b\n")
#define __asm_copy_from_user_14x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
"8: move.w [%1+],$acr\n" \
" move.w $acr,[%0+]\n", \
FIXUP \
- "9: addq 2,%2\n" \
- " clear.w [%0+]\n", \
+ "9: addq 2,%2\n", \
TENTRY \
" .dword 8b,9b\n")
__asm_copy_from_user_14x_cont(to, from, ret, \
"10: move.b [%1+],$acr\n" \
" move.b $acr,[%0+]\n", \
- "11: addq 1,%2\n" \
- " clear.b [%0+]\n", \
+ "11: addq 1,%2\n", \
" .dword 10b,11b\n")
#define __asm_copy_from_user_16x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
"8: move.d [%1+],$acr\n" \
" move.d $acr,[%0+]\n", \
FIXUP \
- "9: addq 4,%2\n" \
- " clear.d [%0+]\n", \
+ "9: addq 4,%2\n", \
TENTRY \
" .dword 8b,9b\n")
"10: move.d [%1+],$acr\n" \
" move.d $acr,[%0+]\n", \
FIXUP \
- "11: addq 4,%2\n" \
- " clear.d [%0+]\n", \
+ "11: addq 4,%2\n", \
TENTRY \
" .dword 10b,11b\n")
"12: move.d [%1+],$acr\n" \
" move.d $acr,[%0+]\n", \
FIXUP \
- "13: addq 4,%2\n" \
- " clear.d [%0+]\n", \
+ "13: addq 4,%2\n", \
TENTRY \
" .dword 12b,13b\n")
generic-y += div64.h
generic-y += errno.h
generic-y += exec.h
+generic-y += extable.h
generic-y += emergency-restart.h
generic-y += fcntl.h
generic-y += futex.h
#ifndef _CRIS_UACCESS_H
#define _CRIS_UACCESS_H
-#ifndef __ASSEMBLY__
-#include <linux/sched.h>
-#include <linux/errno.h>
#include <asm/processor.h>
#include <asm/page.h>
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
/*
* The fs value determines whether argument validity checking should be
* performed or not. If get_fs() == USER_DS, checking is performed, with
#define segment_eq(a, b) ((a).seg == (b).seg)
-#define __kernel_ok (segment_eq(get_fs(), KERNEL_DS))
+#define __kernel_ok (uaccess_kernel())
#define __user_ok(addr, size) \
(((size) <= TASK_SIZE) && ((addr) <= TASK_SIZE-(size)))
#define __access_ok(addr, size) (__kernel_ok || __user_ok((addr), (size)))
#define access_ok(type, addr, size) __access_ok((unsigned long)(addr), (size))
#include <arch/uaccess.h>
-
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue. No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path. This means when everything is well,
- * we don't even have to jump over them. Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry {
- unsigned long insn, fixup;
-};
+#include <asm/extable.h>
/*
* These are the main single-value transfer routines. They automatically
live in lib/usercopy.c */
extern unsigned long __copy_user(void __user *to, const void *from, unsigned long n);
-extern unsigned long __copy_user_zeroing(void *to, const void __user *from, unsigned long n);
+extern unsigned long __copy_user_in(void *to, const void __user *from, unsigned long n);
extern unsigned long __do_clear_user(void __user *to, unsigned long n);
static inline long
else if (n == 24)
__asm_copy_from_user_24(to, from, ret);
else
- ret = __copy_user_zeroing(to, from, n);
+ ret = __copy_user_in(to, from, n);
return ret;
}
return __do_clear_user(to, n);
}
-static inline size_t copy_from_user(void *to, const void __user *from, size_t n)
+static inline unsigned long
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
{
- if (unlikely(!access_ok(VERIFY_READ, from, n))) {
- memset(to, 0, n);
- return n;
- }
if (__builtin_constant_p(n))
return __constant_copy_from_user(to, from, n);
else
- return __copy_user_zeroing(to, from, n);
+ return __copy_user_in(to, from, n);
}
-static inline size_t copy_to_user(void __user *to, const void *from, size_t n)
+static inline unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
{
- if (unlikely(!access_ok(VERIFY_WRITE, to, n)))
- return n;
if (__builtin_constant_p(n))
return __constant_copy_to_user(to, from, n);
else
return __copy_user(to, from, n);
}
-/* We let the __ versions of copy_from/to_user inline, because they're often
- * used in fast paths and have only a small space overhead.
- */
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
static inline unsigned long
-__generic_copy_from_user_nocheck(void *to, const void __user *from,
- unsigned long n)
-{
- return __copy_user_zeroing(to, from, n);
-}
-
-static inline unsigned long
-__generic_copy_to_user_nocheck(void __user *to, const void *from,
- unsigned long n)
-{
- return __copy_user(to, from, n);
-}
-
-static inline unsigned long
-__generic_clear_user_nocheck(void __user *to, unsigned long n)
+__clear_user(void __user *to, unsigned long n)
{
return __do_clear_user(to, n);
}
-/* without checking */
-
-#define __copy_to_user(to, from, n) \
- __generic_copy_to_user_nocheck((to), (from), (n))
-#define __copy_from_user(to, from, n) \
- __generic_copy_from_user_nocheck((to), (from), (n))
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
-#define __clear_user(to, n) __generic_clear_user_nocheck((to), (n))
-
#define strlen_user(str) strnlen_user((str), 0x7ffffffe)
-#endif /* __ASSEMBLY__ */
-
#endif /* _CRIS_UACCESS_H */
generic-y += clkdev.h
generic-y += exec.h
+generic-y += extable.h
generic-y += irq_work.h
generic-y += mcs_spinlock.h
generic-y += mm-arch-hooks.h
/*
* User space memory access functions
*/
-#include <linux/sched.h>
#include <linux/mm.h>
#include <asm/segment.h>
#include <asm/sections.h>
+#include <asm/extable.h>
#define __ptr(x) ((unsigned long __force *)(x))
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
/*
* check that a range of addresses falls within the current address limit
*/
#define access_ok(type,addr,size) (__range_ok((void __user *)(addr), (size)) == 0)
#define __access_ok(addr,size) (__range_ok((addr), (size)) == 0)
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue. No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path. This means when everything is well,
- * we don't even have to jump over them. Further, they do not intrude
- * on our cache or tlb entries.
- */
-struct exception_table_entry
-{
- unsigned long insn, fixup;
-};
-
-/* Returns 0 if exception not found and fixup otherwise. */
-extern unsigned long search_exception_table(unsigned long);
-
/*
* These are the main single-value transfer routines. They automatically
/*
*
*/
+
#define ____force(x) (__force void *)(void __user *)(x)
#ifdef CONFIG_MMU
extern long __memset_user(void *dst, unsigned long count);
extern long __memcpy_user(void *dst, const void *src, unsigned long count);
#define __clear_user(dst,count) __memset_user(____force(dst), (count))
-#define __copy_from_user_inatomic(to, from, n) __memcpy_user((to), ____force(from), (n))
-#define __copy_to_user_inatomic(to, from, n) __memcpy_user(____force(to), (from), (n))
#else
#define __clear_user(dst,count) (memset(____force(dst), 0, (count)), 0)
-#define __copy_from_user_inatomic(to, from, n) (memcpy((to), ____force(from), (n)), 0)
-#define __copy_to_user_inatomic(to, from, n) (memcpy(____force(to), (from), (n)), 0)
#endif
-static inline unsigned long __must_check
-clear_user(void __user *to, unsigned long n)
-{
- if (likely(__access_ok(to, n)))
- n = __clear_user(to, n);
- return n;
-}
-
-static inline unsigned long __must_check
-__copy_to_user(void __user *to, const void *from, unsigned long n)
-{
- might_fault();
- return __copy_to_user_inatomic(to, from, n);
-}
-
static inline unsigned long
-__copy_from_user(void *to, const void __user *from, unsigned long n)
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
{
- might_fault();
- return __copy_from_user_inatomic(to, from, n);
+#ifdef CONFIG_MMU
+ return __memcpy_user(to, (__force const void *)from, n);
+#else
+ memcpy(to, (__force const void *)from, n);
+ return 0;
+#endif
}
-static inline long copy_from_user(void *to, const void __user *from, unsigned long n)
+static inline unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
{
- unsigned long ret = n;
-
- if (likely(__access_ok(from, n)))
- ret = __copy_from_user(to, from, n);
-
- if (unlikely(ret != 0))
- memset(to + (n - ret), 0, ret);
-
- return ret;
+#ifdef CONFIG_MMU
+ return __memcpy_user((__force void *)to, from, n);
+#else
+ memcpy((__force void *)to, from, n);
+ return 0;
+#endif
}
+#define INLINE_COPY_TO_USER
+#define INLINE_COPY_FROM_USER
-static inline long copy_to_user(void __user *to, const void *from, unsigned long n)
+static inline unsigned long __must_check
+clear_user(void __user *to, unsigned long n)
{
- return likely(__access_ok(to, n)) ? __copy_to_user(to, from, n) : n;
+ if (likely(__access_ok(to, n)))
+ n = __clear_user(to, n);
+ return n;
}
extern long strncpy_from_user(char *dst, const char __user *src, long count);
#define strlen_user(str) strnlen_user(str, 32767)
-extern unsigned long search_exception_table(unsigned long addr);
-
#endif /* _ASM_UACCESS_H */
siginfo_t info;
#ifdef CONFIG_MMU
- unsigned long fixup;
-
- fixup = search_exception_table(__frame->pc);
- if (fixup) {
- __frame->pc = fixup;
+ if (fixup_exception(__frame))
return;
- }
#endif
die_if_kernel("-- Memory Access Exception --\n"
extern const void __memcpy_end, __memcpy_user_error_lr, __memcpy_user_error_handler;
extern spinlock_t modlist_lock;
-
-/*****************************************************************************/
-/*
- * see if there's a fixup handler available to deal with a kernel fault
- */
-unsigned long search_exception_table(unsigned long pc)
+int fixup_exception(struct pt_regs *regs)
{
const struct exception_table_entry *extab;
+ unsigned long pc = regs->pc;
/* determine if the fault lay during a memcpy_user or a memset_user */
- if (__frame->lr == (unsigned long) &__memset_user_error_lr &&
+ if (regs->lr == (unsigned long) &__memset_user_error_lr &&
(unsigned long) &memset <= pc && pc < (unsigned long) &__memset_end
) {
/* the fault occurred in a protected memset
* - we search for the return address (in LR) instead of the program counter
* - it was probably during a clear_user()
*/
- return (unsigned long) &__memset_user_error_handler;
+ regs->pc = (unsigned long) &__memset_user_error_handler;
+ return 1;
}
- if (__frame->lr == (unsigned long) &__memcpy_user_error_lr &&
+ if (regs->lr == (unsigned long) &__memcpy_user_error_lr &&
(unsigned long) &memcpy <= pc && pc < (unsigned long) &__memcpy_end
) {
/* the fault occurred in a protected memset
* - we search for the return address (in LR) instead of the program counter
* - it was probably during a copy_to/from_user()
*/
- return (unsigned long) &__memcpy_user_error_handler;
+ regs->pc = (unsigned long) &__memcpy_user_error_handler;
+ return 1;
}
extab = search_exception_tables(pc);
- if (extab)
- return extab->fixup;
+ if (extab) {
+ regs->pc = extab->fixup;
+ return 1;
+ }
return 0;
-
-} /* end search_exception_table() */
+}
{
struct vm_area_struct *vma;
struct mm_struct *mm;
- unsigned long _pme, lrai, lrad, fixup;
+ unsigned long _pme, lrai, lrad;
unsigned long flags = 0;
siginfo_t info;
pgd_t *pge;
no_context:
/* are we prepared to handle this kernel fault? */
- if ((fixup = search_exception_table(__frame->pc)) != 0) {
- __frame->pc = fixup;
+ if (fixup_exception(__frame))
return;
- }
/*
* Oops. The kernel tried to access some bad page. We'll have to
generic-y += emergency-restart.h
generic-y += errno.h
generic-y += exec.h
+generic-y += extable.h
generic-y += fb.h
generic-y += fcntl.h
generic-y += ftrace.h
generic-y += trace_clock.h
generic-y += topology.h
generic-y += types.h
-generic-y += uaccess.h
generic-y += ucontext.h
generic-y += unaligned.h
generic-y += vga.h
--- /dev/null
+#ifndef _ASM_UACCESS_H
+#define _ASM_UACCESS_H
+
+#include <linux/string.h>
+
+static inline __must_check unsigned long
+raw_copy_from_user(void *to, const void __user * from, unsigned long n)
+{
+ if (__builtin_constant_p(n)) {
+ switch(n) {
+ case 1:
+ *(u8 *)to = *(u8 __force *)from;
+ return 0;
+ case 2:
+ *(u16 *)to = *(u16 __force *)from;
+ return 0;
+ case 4:
+ *(u32 *)to = *(u32 __force *)from;
+ return 0;
+ }
+ }
+
+ memcpy(to, (const void __force *)from, n);
+ return 0;
+}
+
+static inline __must_check unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+ if (__builtin_constant_p(n)) {
+ switch(n) {
+ case 1:
+ *(u8 __force *)to = *(u8 *)from;
+ return 0;
+ case 2:
+ *(u16 __force *)to = *(u16 *)from;
+ return 0;
+ case 4:
+ *(u32 __force *)to = *(u32 *)from;
+ return 0;
+ default:
+ break;
+ }
+ }
+
+ memcpy((void __force *)to, from, n);
+ return 0;
+}
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
+
+#include <asm-generic/uaccess.h>
+
+#endif
generic-y += div64.h
generic-y += emergency-restart.h
generic-y += errno.h
+generic-y += extable.h
generic-y += fb.h
generic-y += fcntl.h
generic-y += ftrace.h
/*
* User space memory access functions
*/
-#include <linux/sched.h>
#include <linux/mm.h>
#include <asm/segment.h>
#include <asm/sections.h>
* reasonably simple and not *too* slow. After all, we've got the
* MMU for backup.
*/
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
#define __access_ok(addr, size) \
((get_fs().seg == KERNEL_DS.seg) || \
*/
/* Assembly somewhat optimized copy routines */
-unsigned long __copy_from_user_hexagon(void *to, const void __user *from,
+unsigned long raw_copy_from_user(void *to, const void __user *from,
unsigned long n);
-unsigned long __copy_to_user_hexagon(void __user *to, const void *from,
+unsigned long raw_copy_to_user(void __user *to, const void *from,
unsigned long n);
-
-#define __copy_from_user(to, from, n) __copy_from_user_hexagon(to, from, n)
-#define __copy_to_user(to, from, n) __copy_to_user_hexagon(to, from, n)
-
-/*
- * XXX todo: some additonal performance gain is possible by
- * implementing __copy_to/from_user_inatomic, which is much
- * like __copy_to/from_user, but performs slightly less checking.
- */
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
__kernel_size_t __clear_user_hexagon(void __user *dest, unsigned long count);
#define __clear_user(a, s) __clear_user_hexagon((a), (s))
return -EFAULT;
if (res > n) {
- copy_from_user(dst, src, n);
+ long left = raw_copy_from_user(dst, src, n);
+ if (unlikely(left))
+ memset(dst + (n - left), 0, left);
return n;
} else {
- copy_from_user(dst, src, res);
+ long left = raw_copy_from_user(dst, src, res);
+ if (unlikely(left))
+ memset(dst + (res - left), 0, left);
return res-1;
}
}
/* Additional functions */
EXPORT_SYMBOL(__clear_user_hexagon);
-EXPORT_SYMBOL(__copy_from_user_hexagon);
-EXPORT_SYMBOL(__copy_to_user_hexagon);
+EXPORT_SYMBOL(raw_copy_from_user);
+EXPORT_SYMBOL(raw_copy_to_user);
EXPORT_SYMBOL(__iounmap);
EXPORT_SYMBOL(__strnlen_user);
EXPORT_SYMBOL(__vmgetie);
clockevents_calc_mult_shift(ce_dev, sleep_clk_freq, 4);
ce_dev->max_delta_ns = clockevent_delta2ns(0x7fffffff, ce_dev);
+ ce_dev->max_delta_ticks = 0x7fffffff;
ce_dev->min_delta_ns = clockevent_delta2ns(0xf, ce_dev);
+ ce_dev->min_delta_ticks = 0xf;
#ifdef CONFIG_SMP
setup_percpu_clockdev();
#define bytes r2
#define loopcount r5
-#define FUNCNAME __copy_from_user_hexagon
+#define FUNCNAME raw_copy_from_user
#include "copy_user_template.S"
/* LOAD FAULTS from COPY_FROM_USER */
#define bytes r2
#define loopcount r5
-#define FUNCNAME __copy_to_user_hexagon
+#define FUNCNAME raw_copy_to_user
#include "copy_user_template.S"
/* STORE FAULTS from COPY_TO_USER */
select MODULES_USE_ELF_RELA
select ARCH_USE_CMPXCHG_LOCKREF
select HAVE_ARCH_AUDITSYSCALL
- select HAVE_ARCH_HARDENED_USERCOPY
default y
help
The Itanium Processor Family is Intel's 64-bit successor to
--- /dev/null
+#ifndef _ASM_IA64_ASM_PROTOTYPES_H
+#define _ASM_IA64_ASM_PROTOTYPES_H
+
+#include <asm/cacheflush.h>
+#include <asm/checksum.h>
+#include <asm/esi.h>
+#include <asm/ftrace.h>
+#include <asm/page.h>
+#include <asm/pal.h>
+#include <asm/string.h>
+#include <asm/uaccess.h>
+#include <asm/unwind.h>
+#include <asm/xor.h>
+
+extern const char ia64_ivt[];
+
+signed int __divsi3(signed int, unsigned int);
+signed int __modsi3(signed int, unsigned int);
+
+signed long long __divdi3(signed long long, unsigned long long);
+signed long long __moddi3(signed long long, unsigned long long);
+
+unsigned int __udivsi3(unsigned int, unsigned int);
+unsigned int __umodsi3(unsigned int, unsigned int);
+
+unsigned long long __udivdi3(unsigned long long, unsigned long long);
+unsigned long long __umoddi3(unsigned long long, unsigned long long);
+
+#endif /* _ASM_IA64_ASM_PROTOTYPES_H */
--- /dev/null
+#ifndef _ASM_IA64_EXTABLE_H
+#define _ASM_IA64_EXTABLE_H
+
+#define ARCH_HAS_RELATIVE_EXTABLE
+
+struct exception_table_entry {
+ int insn; /* location-relative address of insn this fixup is for */
+ int fixup; /* location-relative continuation addr.; if bit 2 is set, r9 is set to 0 */
+};
+
+#endif
*/
#include <linux/compiler.h>
-#include <linux/errno.h>
-#include <linux/sched.h>
#include <linux/page-flags.h>
#include <linux/mm.h>
#include <asm/intrinsics.h>
#include <asm/pgtable.h>
#include <asm/io.h>
+#include <asm/extable.h>
/*
* For historical reasons, the following macros are grossly misnamed:
#define KERNEL_DS ((mm_segment_t) { ~0UL }) /* cf. access_ok() */
#define USER_DS ((mm_segment_t) { TASK_SIZE-1 }) /* cf. access_ok() */
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
#define get_ds() (KERNEL_DS)
#define get_fs() (current_thread_info()->addr_limit)
#define set_fs(x) (current_thread_info()->addr_limit = (x))
* address TASK_SIZE is never valid. We also need to make sure that the address doesn't
* point inside the virtually mapped linear page table.
*/
-#define __access_ok(addr, size, segment) \
-({ \
- __chk_user_ptr(addr); \
- (likely((unsigned long) (addr) <= (segment).seg) \
- && ((segment).seg == KERNEL_DS.seg \
- || likely(REGION_OFFSET((unsigned long) (addr)) < RGN_MAP_LIMIT))); \
-})
-#define access_ok(type, addr, size) __access_ok((addr), (size), get_fs())
+static inline int __access_ok(const void __user *p, unsigned long size)
+{
+ unsigned long addr = (unsigned long)p;
+ unsigned long seg = get_fs().seg;
+ return likely(addr <= seg) &&
+ (seg == KERNEL_DS.seg || likely(REGION_OFFSET(addr) < RGN_MAP_LIMIT));
+}
+#define access_ok(type, addr, size) __access_ok((addr), (size))
/*
* These are the main single-value transfer routines. They automatically
* (a) re-use the arguments for side effects (sizeof/typeof is ok)
* (b) require any knowledge of processes at this stage
*/
-#define put_user(x, ptr) __put_user_check((__typeof__(*(ptr))) (x), (ptr), sizeof(*(ptr)), get_fs())
-#define get_user(x, ptr) __get_user_check((x), (ptr), sizeof(*(ptr)), get_fs())
+#define put_user(x, ptr) __put_user_check((__typeof__(*(ptr))) (x), (ptr), sizeof(*(ptr)))
+#define get_user(x, ptr) __get_user_check((x), (ptr), sizeof(*(ptr)))
/*
* The "__xxx" versions do not do address space checking, useful when
* could clobber r8 and r9 (among others). Thus, be careful not to evaluate it while
* using r8/r9.
*/
-#define __do_get_user(check, x, ptr, size, segment) \
+#define __do_get_user(check, x, ptr, size) \
({ \
const __typeof__(*(ptr)) __user *__gu_ptr = (ptr); \
__typeof__ (size) __gu_size = (size); \
long __gu_err = -EFAULT; \
unsigned long __gu_val = 0; \
- if (!check || __access_ok(__gu_ptr, size, segment)) \
+ if (!check || __access_ok(__gu_ptr, size)) \
switch (__gu_size) { \
case 1: __get_user_size(__gu_val, __gu_ptr, 1, __gu_err); break; \
case 2: __get_user_size(__gu_val, __gu_ptr, 2, __gu_err); break; \
__gu_err; \
})
-#define __get_user_nocheck(x, ptr, size) __do_get_user(0, x, ptr, size, KERNEL_DS)
-#define __get_user_check(x, ptr, size, segment) __do_get_user(1, x, ptr, size, segment)
+#define __get_user_nocheck(x, ptr, size) __do_get_user(0, x, ptr, size)
+#define __get_user_check(x, ptr, size) __do_get_user(1, x, ptr, size)
extern void __put_user_unknown (void);
* Evaluating arguments X, PTR, SIZE, and SEGMENT may involve subroutine-calls, which
* could clobber r8 (among others). Thus, be careful not to evaluate them while using r8.
*/
-#define __do_put_user(check, x, ptr, size, segment) \
+#define __do_put_user(check, x, ptr, size) \
({ \
__typeof__ (x) __pu_x = (x); \
__typeof__ (*(ptr)) __user *__pu_ptr = (ptr); \
__typeof__ (size) __pu_size = (size); \
long __pu_err = -EFAULT; \
\
- if (!check || __access_ok(__pu_ptr, __pu_size, segment)) \
+ if (!check || __access_ok(__pu_ptr, __pu_size)) \
switch (__pu_size) { \
case 1: __put_user_size(__pu_x, __pu_ptr, 1, __pu_err); break; \
case 2: __put_user_size(__pu_x, __pu_ptr, 2, __pu_err); break; \
__pu_err; \
})
-#define __put_user_nocheck(x, ptr, size) __do_put_user(0, x, ptr, size, KERNEL_DS)
-#define __put_user_check(x, ptr, size, segment) __do_put_user(1, x, ptr, size, segment)
+#define __put_user_nocheck(x, ptr, size) __do_put_user(0, x, ptr, size)
+#define __put_user_check(x, ptr, size) __do_put_user(1, x, ptr, size)
/*
* Complex access routines
unsigned long count);
static inline unsigned long
-__copy_to_user (void __user *to, const void *from, unsigned long count)
+raw_copy_to_user(void __user *to, const void *from, unsigned long count)
{
- check_object_size(from, count, true);
-
return __copy_user(to, (__force void __user *) from, count);
}
static inline unsigned long
-__copy_from_user (void *to, const void __user *from, unsigned long count)
+raw_copy_from_user(void *to, const void __user *from, unsigned long count)
{
- check_object_size(to, count, false);
-
return __copy_user((__force void __user *) to, from, count);
}
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
-#define copy_to_user(to, from, n) \
-({ \
- void __user *__cu_to = (to); \
- const void *__cu_from = (from); \
- long __cu_len = (n); \
- \
- if (__access_ok(__cu_to, __cu_len, get_fs())) { \
- check_object_size(__cu_from, __cu_len, true); \
- __cu_len = __copy_user(__cu_to, (__force void __user *) __cu_from, __cu_len); \
- } \
- __cu_len; \
-})
-
-static inline unsigned long
-copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- check_object_size(to, n, false);
- if (likely(__access_ok(from, n, get_fs())))
- n = __copy_user((__force void __user *) to, from, n);
- else
- memset(to, 0, n);
- return n;
-}
-
-#define __copy_in_user(to, from, size) __copy_user((to), (from), (size))
-
-static inline unsigned long
-copy_in_user (void __user *to, const void __user *from, unsigned long n)
-{
- if (likely(access_ok(VERIFY_READ, from, n) && access_ok(VERIFY_WRITE, to, n)))
- n = __copy_user(to, from, n);
- return n;
-}
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
extern unsigned long __do_clear_user (void __user *, unsigned long);
#define clear_user(to, n) \
({ \
unsigned long __cu_len = (n); \
- if (__access_ok(to, __cu_len, get_fs())) \
+ if (__access_ok(to, __cu_len)) \
__cu_len = __do_clear_user(to, __cu_len); \
__cu_len; \
})
({ \
const char __user * __sfu_from = (from); \
long __sfu_ret = -EFAULT; \
- if (__access_ok(__sfu_from, 0, get_fs())) \
+ if (__access_ok(__sfu_from, 0)) \
__sfu_ret = __strncpy_from_user((to), __sfu_from, (n)); \
__sfu_ret; \
})
({ \
const char __user *__su_str = (str); \
unsigned long __su_ret = 0; \
- if (__access_ok(__su_str, 0, get_fs())) \
+ if (__access_ok(__su_str, 0)) \
__su_ret = __strlen_user(__su_str); \
__su_ret; \
})
({ \
const char __user *__su_str = (str); \
unsigned long __su_ret = 0; \
- if (__access_ok(__su_str, 0, get_fs())) \
+ if (__access_ok(__su_str, 0)) \
__su_ret = __strnlen_user(__su_str, len); \
__su_ret; \
})
-#define ARCH_HAS_RELATIVE_EXTABLE
-
-struct exception_table_entry {
- int insn; /* location-relative address of insn this fixup is for */
- int fixup; /* location-relative continuation addr.; if bit 2 is set, r9 is set to 0 */
-};
-
#define ARCH_HAS_TRANSLATE_MEM_PTR 1
static __inline__ void *
xlate_dev_mem_ptr(phys_addr_t p)
static int
apply_imm64 (struct module *mod, struct insn *insn, uint64_t val)
{
- if (slot(insn) != 2) {
+ if (slot(insn) != 1 && slot(insn) != 2) {
printk(KERN_ERR "%s: invalid slot number %d for IMM64\n",
mod->name, slot(insn));
return 0;
static int
apply_imm60 (struct module *mod, struct insn *insn, uint64_t val)
{
- if (slot(insn) != 2) {
+ if (slot(insn) != 1 && slot(insn) != 2) {
printk(KERN_ERR "%s: invalid slot number %d for IMM60\n",
mod->name, slot(insn));
return 0;
const u8 *efi_guid;
u8 **oemdata;
u64 *oemdata_size;
- int ret;
};
-static void
+static long
salinfo_platform_oemdata_cpu(void *context)
{
struct salinfo_platform_oemdata_parms *parms = context;
- parms->ret = salinfo_platform_oemdata(parms->efi_guid, parms->oemdata, parms->oemdata_size);
+
+ return salinfo_platform_oemdata(parms->efi_guid, parms->oemdata, parms->oemdata_size);
}
static void
return 0;
}
-static void
-call_on_cpu(int cpu, void (*fn)(void *), void *arg)
-{
- cpumask_t save_cpus_allowed = current->cpus_allowed;
- set_cpus_allowed_ptr(current, cpumask_of(cpu));
- (*fn)(arg);
- set_cpus_allowed_ptr(current, &save_cpus_allowed);
-}
-
-static void
+static long
salinfo_log_read_cpu(void *context)
{
struct salinfo_data *data = context;
/* Clear corrected errors as they are read from SAL */
if (rh->severity == sal_log_severity_corrected)
ia64_sal_clear_state_info(data->type);
+ return 0;
}
static void
spin_unlock_irqrestore(&data_saved_lock, flags);
if (!data->saved_num)
- call_on_cpu(cpu, salinfo_log_read_cpu, data);
+ work_on_cpu_safe(cpu, salinfo_log_read_cpu, data);
if (!data->log_size) {
data->state = STATE_NO_DATA;
cpumask_clear_cpu(cpu, &data->cpu_event);
return simple_read_from_buffer(buffer, count, ppos, buf, bufsize);
}
-static void
+static long
salinfo_log_clear_cpu(void *context)
{
struct salinfo_data *data = context;
+
ia64_sal_clear_state_info(data->type);
+ return 0;
}
static int
rh = (sal_log_record_header_t *)(data->log_buffer);
/* Corrected errors have already been cleared from SAL */
if (rh->severity != sal_log_severity_corrected)
- call_on_cpu(cpu, salinfo_log_clear_cpu, data);
+ work_on_cpu_safe(cpu, salinfo_log_clear_cpu, data);
/* clearing a record may make a new record visible */
salinfo_log_new_read(cpu, data);
if (data->state == STATE_LOG_RECORD) {
.oemdata = &data->oemdata,
.oemdata_size = &data->oemdata_size
};
- call_on_cpu(cpu, salinfo_platform_oemdata_cpu, &parms);
- if (parms.ret)
- count = parms.ret;
+ count = work_on_cpu_safe(cpu, salinfo_platform_oemdata_cpu,
+ &parms);
} else
data->oemdata_size = 0;
} else
unsigned long i, j;
struct cache_info *this_object;
int retval = 0;
- cpumask_t oldmask;
if (all_cpu_cache_info[cpu].kobj.parent)
return 0;
- oldmask = current->cpus_allowed;
- retval = set_cpus_allowed_ptr(current, cpumask_of(cpu));
- if (unlikely(retval))
- return retval;
retval = cpu_cache_sysfs_init(cpu);
- set_cpus_allowed_ptr(current, &oldmask);
if (unlikely(retval < 0))
return retval;
AFLAGS___umodsi3.o = -DUNSIGNED -DMODULO
$(obj)/__divdi3.o: $(src)/idiv64.S FORCE
- $(call if_changed_dep,as_o_S)
+ $(call if_changed_rule,as_o_S)
$(obj)/__udivdi3.o: $(src)/idiv64.S FORCE
- $(call if_changed_dep,as_o_S)
+ $(call if_changed_rule,as_o_S)
$(obj)/__moddi3.o: $(src)/idiv64.S FORCE
- $(call if_changed_dep,as_o_S)
+ $(call if_changed_rule,as_o_S)
$(obj)/__umoddi3.o: $(src)/idiv64.S FORCE
- $(call if_changed_dep,as_o_S)
+ $(call if_changed_rule,as_o_S)
$(obj)/__divsi3.o: $(src)/idiv32.S FORCE
- $(call if_changed_dep,as_o_S)
+ $(call if_changed_rule,as_o_S)
$(obj)/__udivsi3.o: $(src)/idiv32.S FORCE
- $(call if_changed_dep,as_o_S)
+ $(call if_changed_rule,as_o_S)
$(obj)/__modsi3.o: $(src)/idiv32.S FORCE
- $(call if_changed_dep,as_o_S)
+ $(call if_changed_rule,as_o_S)
$(obj)/__umodsi3.o: $(src)/idiv32.S FORCE
- $(call if_changed_dep,as_o_S)
+ $(call if_changed_rule,as_o_S)
#define D r22
#define F r28
-#define memset_arg0 r32
-#define memset_arg2 r33
-
#define saved_retval loc0
#define saved_rtlink loc1
#define saved_pfs_stack loc2
* (faulting_addr - orig_dst) -> len to faulting st address
* B = (cur_dst - orig_dst) -> len copied so far
* C = A - B -> len need to be copied
- * D = orig_len - A -> len need to be zeroed
+ * D = orig_len - A -> len need to be left along
*/
(p6) sub A = F, saved_in0
(p7) sub A = F, saved_in1
sub D = saved_in2, A
;;
cmp.gt p8,p0=C,r0 // more than 1 byte?
- add memset_arg0=saved_in0, A
-(p6) mov memset_arg2=0 // copy_to_user should not call memset
-(p7) mov memset_arg2=D // copy_from_user need to have kbuf zeroed
mov r8=0
mov saved_retval = D
mov saved_rtlink = b0
;;
add saved_retval=saved_retval,r8 // above might return non-zero value
- cmp.gt p8,p0=memset_arg2,r0 // more than 1 byte?
- mov out0=memset_arg0 // *s
- mov out1=r0 // c
- mov out2=memset_arg2 // n
-(p8) br.call.sptk.few b0=memset
;;
mov retval=saved_retval
* David Mosberger-Tang <davidm@hpl.hp.com>
*/
-#include <linux/uaccess.h>
+#include <asm/ptrace.h>
+#include <asm/extable.h>
+#include <asm/errno.h>
+#include <asm/processor.h>
void
ia64_handle_exception (struct pt_regs *regs, const struct exception_table_entry *e)
op_info->ret = r;
}
+static long sn_hwperf_call_sal_work(void *info)
+{
+ sn_hwperf_call_sal(info);
+ return 0;
+}
+
static int sn_hwperf_op_cpu(struct sn_hwperf_op_info *op_info)
{
u32 cpu;
u32 use_ipi;
int r = 0;
- cpumask_t save_allowed;
cpu = (op_info->a->arg & SN_HWPERF_ARG_CPU_MASK) >> 32;
use_ipi = op_info->a->arg & SN_HWPERF_ARG_USE_IPI_MASK;
/* use an interprocessor interrupt to call SAL */
smp_call_function_single(cpu, sn_hwperf_call_sal,
op_info, 1);
- }
- else {
- /* migrate the task before calling SAL */
- save_allowed = current->cpus_allowed;
- set_cpus_allowed_ptr(current, cpumask_of(cpu));
- sn_hwperf_call_sal(op_info);
- set_cpus_allowed_ptr(current, &save_allowed);
+ } else {
+ /* Call on the target CPU */
+ work_on_cpu_safe(cpu, sn_hwperf_call_sal_work, op_info);
}
}
r = op_info->ret;
generic-y += clkdev.h
generic-y += current.h
generic-y += exec.h
+generic-y += extable.h
generic-y += irq_work.h
generic-y += kvm_para.h
generic-y += mcs_spinlock.h
/*
* User space memory access functions
*/
-#include <linux/errno.h>
-#include <linux/thread_info.h>
#include <asm/page.h>
#include <asm/setup.h>
-
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
+#include <linux/prefetch.h>
/*
* The fs value determines whether argument validity checking should be
}
#endif /* CONFIG_MMU */
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue. No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path. This means when everything is well,
- * we don't even have to jump over them. Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry
-{
- unsigned long insn, fixup;
-};
-
-extern int fixup_exception(struct pt_regs *regs);
+#include <asm/extable.h>
/*
* These are the main single-value transfer routines. They automatically
: "r14", "memory"); \
} while (0)
-#define __copy_user_zeroing(to, from, size) \
-do { \
- unsigned long __dst, __src, __c; \
- __asm__ __volatile__ ( \
- " mv r14, %0\n" \
- " or r14, %1\n" \
- " beq %0, %1, 9f\n" \
- " beqz %2, 9f\n" \
- " and3 r14, r14, #3\n" \
- " bnez r14, 2f\n" \
- " and3 %2, %2, #3\n" \
- " beqz %3, 2f\n" \
- " addi %0, #-4 ; word_copy \n" \
- " .fillinsn\n" \
- "0: ld r14, @%1+\n" \
- " addi %3, #-1\n" \
- " .fillinsn\n" \
- "1: st r14, @+%0\n" \
- " bnez %3, 0b\n" \
- " beqz %2, 9f\n" \
- " addi %0, #4\n" \
- " .fillinsn\n" \
- "2: ldb r14, @%1 ; byte_copy \n" \
- " .fillinsn\n" \
- "3: stb r14, @%0\n" \
- " addi %1, #1\n" \
- " addi %2, #-1\n" \
- " addi %0, #1\n" \
- " bnez %2, 2b\n" \
- " .fillinsn\n" \
- "9:\n" \
- ".section .fixup,\"ax\"\n" \
- " .balign 4\n" \
- "5: addi %3, #1\n" \
- " addi %1, #-4\n" \
- " .fillinsn\n" \
- "6: slli %3, #2\n" \
- " add %2, %3\n" \
- " addi %0, #4\n" \
- " .fillinsn\n" \
- "7: ldi r14, #0 ; store zero \n" \
- " .fillinsn\n" \
- "8: addi %2, #-1\n" \
- " stb r14, @%0 ; ACE? \n" \
- " addi %0, #1\n" \
- " bnez %2, 8b\n" \
- " seth r14, #high(9b)\n" \
- " or3 r14, r14, #low(9b)\n" \
- " jmp r14\n" \
- ".previous\n" \
- ".section __ex_table,\"a\"\n" \
- " .balign 4\n" \
- " .long 0b,6b\n" \
- " .long 1b,5b\n" \
- " .long 2b,7b\n" \
- " .long 3b,7b\n" \
- ".previous\n" \
- : "=&r" (__dst), "=&r" (__src), "=&r" (size), \
- "=&r" (__c) \
- : "0" (to), "1" (from), "2" (size), "3" (size / 4) \
- : "r14", "memory"); \
-} while (0)
-
-
/* We let the __ versions of copy_from/to_user inline, because they're often
* used in fast paths and have only a small space overhead.
*/
-static inline unsigned long __generic_copy_from_user_nocheck(void *to,
- const void __user *from, unsigned long n)
+static inline unsigned long
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
{
- __copy_user_zeroing(to, from, n);
+ prefetchw(to);
+ __copy_user(to, from, n);
return n;
}
-static inline unsigned long __generic_copy_to_user_nocheck(void __user *to,
- const void *from, unsigned long n)
+static inline unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
{
+ prefetch(from);
__copy_user(to, from, n);
return n;
}
-unsigned long __generic_copy_to_user(void __user *, const void *, unsigned long);
-unsigned long __generic_copy_from_user(void *, const void __user *, unsigned long);
-
-/**
- * __copy_to_user: - Copy a block of data into user space, with less checking.
- * @to: Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- * enabled.
- *
- * Copy data from kernel space to user space. Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- */
-#define __copy_to_user(to, from, n) \
- __generic_copy_to_user_nocheck((to), (from), (n))
-
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
-
-/**
- * copy_to_user: - Copy a block of data into user space.
- * @to: Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- * enabled.
- *
- * Copy data from kernel space to user space.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- */
-#define copy_to_user(to, from, n) \
-({ \
- might_fault(); \
- __generic_copy_to_user((to), (from), (n)); \
-})
-
-/**
- * __copy_from_user: - Copy a block of data from user space, with less checking. * @to: Destination address, in kernel space.
- * @from: Source address, in user space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- * enabled.
- *
- * Copy data from user space to kernel space. Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- *
- * If some data could not be copied, this function will pad the copied
- * data to the requested size using zero bytes.
- */
-#define __copy_from_user(to, from, n) \
- __generic_copy_from_user_nocheck((to), (from), (n))
-
-/**
- * copy_from_user: - Copy a block of data from user space.
- * @to: Destination address, in kernel space.
- * @from: Source address, in user space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- * enabled.
- *
- * Copy data from user space to kernel space.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- *
- * If some data could not be copied, this function will pad the copied
- * data to the requested size using zero bytes.
- */
-#define copy_from_user(to, from, n) \
-({ \
- might_fault(); \
- __generic_copy_from_user((to), (from), (n)); \
-})
-
long __must_check strncpy_from_user(char *dst, const char __user *src,
long count);
long __must_check __strncpy_from_user(char *dst,
EXPORT_SYMBOL(__strncpy_from_user);
EXPORT_SYMBOL(clear_user);
EXPORT_SYMBOL(__clear_user);
-EXPORT_SYMBOL(__generic_copy_from_user);
-EXPORT_SYMBOL(__generic_copy_to_user);
EXPORT_SYMBOL(strnlen_user);
#ifdef CONFIG_SMP
#include <linux/thread_info.h>
#include <linux/uaccess.h>
-unsigned long
-__generic_copy_to_user(void __user *to, const void *from, unsigned long n)
-{
- prefetch(from);
- if (access_ok(VERIFY_WRITE, to, n))
- __copy_user(to,from,n);
- return n;
-}
-
-unsigned long
-__generic_copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- prefetchw(to);
- if (access_ok(VERIFY_READ, from, n))
- __copy_user_zeroing(to,from,n);
- else
- memset(to, 0, n);
- return n;
-}
-
-
/*
* Copy a null terminated string from userspace.
*/
cf_pit_clockevent.mult = div_sc(FREQ, NSEC_PER_SEC, 32);
cf_pit_clockevent.max_delta_ns =
clockevent_delta2ns(0xFFFF, &cf_pit_clockevent);
+ cf_pit_clockevent.max_delta_ticks = 0xFFFF;
cf_pit_clockevent.min_delta_ns =
clockevent_delta2ns(0x3f, &cf_pit_clockevent);
+ cf_pit_clockevent.min_delta_ticks = 0x3f;
clockevents_register_device(&cf_pit_clockevent);
setup_irq(MCF_IRQ_PIT1, &pit_irq);
generic-y += emergency-restart.h
generic-y += errno.h
generic-y += exec.h
+generic-y += extable.h
generic-y += futex.h
generic-y += hw_irq.h
generic-y += ioctl.h
wrusp(usp);
}
-#ifdef CONFIG_MMU
-extern int handle_kernel_fault(struct pt_regs *regs);
-#else
-static inline int handle_kernel_fault(struct pt_regs *regs)
-{
- /* Any fault in kernel is fatal on non-mmu */
- return 0;
-}
-#endif
-
/* Forward declaration, a strange C thing */
struct task_struct;
#include <asm/uaccess_mm.h>
#endif
+#include <asm/extable.h>
#ifdef CONFIG_CPU_HAS_NO_UNALIGNED
#include <asm-generic/uaccess-unaligned.h>
#else
* User space memory access functions
*/
#include <linux/compiler.h>
-#include <linux/errno.h>
#include <linux/types.h>
-#include <linux/sched.h>
#include <asm/segment.h>
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
/* We let the MMU do all checking */
static inline int access_ok(int type, const void __user *addr,
unsigned long size)
#define MOVES "move"
#endif
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue. No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path. This means when everything is well,
- * we don't even have to jump over them. Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry
-{
- unsigned long insn, fixup;
-};
-
extern int __put_user_bad(void);
extern int __get_user_bad(void);
unsigned long __generic_copy_from_user(void *to, const void __user *from, unsigned long n);
unsigned long __generic_copy_to_user(void __user *to, const void *from, unsigned long n);
-#define __constant_copy_from_user_asm(res, to, from, tmp, n, s1, s2, s3)\
+#define __suffix0
+#define __suffix1 b
+#define __suffix2 w
+#define __suffix4 l
+
+#define ____constant_copy_from_user_asm(res, to, from, tmp, n1, n2, n3, s1, s2, s3)\
asm volatile ("\n" \
"1: "MOVES"."#s1" (%2)+,%3\n" \
" move."#s1" %3,(%1)+\n" \
+ " .ifnc \""#s2"\",\"\"\n" \
"2: "MOVES"."#s2" (%2)+,%3\n" \
" move."#s2" %3,(%1)+\n" \
" .ifnc \""#s3"\",\"\"\n" \
"3: "MOVES"."#s3" (%2)+,%3\n" \
" move."#s3" %3,(%1)+\n" \
" .endif\n" \
+ " .endif\n" \
"4:\n" \
" .section __ex_table,\"a\"\n" \
" .align 4\n" \
" .long 1b,10f\n" \
+ " .ifnc \""#s2"\",\"\"\n" \
" .long 2b,20f\n" \
" .ifnc \""#s3"\",\"\"\n" \
" .long 3b,30f\n" \
" .endif\n" \
+ " .endif\n" \
" .previous\n" \
"\n" \
" .section .fixup,\"ax\"\n" \
" .even\n" \
- "10: clr."#s1" (%1)+\n" \
- "20: clr."#s2" (%1)+\n" \
+ "10: addq.l #"#n1",%0\n" \
+ " .ifnc \""#s2"\",\"\"\n" \
+ "20: addq.l #"#n2",%0\n" \
" .ifnc \""#s3"\",\"\"\n" \
- "30: clr."#s3" (%1)+\n" \
+ "30: addq.l #"#n3",%0\n" \
+ " .endif\n" \
" .endif\n" \
- " moveq.l #"#n",%0\n" \
" jra 4b\n" \
" .previous\n" \
: "+d" (res), "+&a" (to), "+a" (from), "=&d" (tmp) \
: : "memory")
+#define ___constant_copy_from_user_asm(res, to, from, tmp, n1, n2, n3, s1, s2, s3)\
+ ____constant_copy_from_user_asm(res, to, from, tmp, n1, n2, n3, s1, s2, s3)
+#define __constant_copy_from_user_asm(res, to, from, tmp, n1, n2, n3) \
+ ___constant_copy_from_user_asm(res, to, from, tmp, n1, n2, n3, \
+ __suffix##n1, __suffix##n2, __suffix##n3)
+
static __always_inline unsigned long
__constant_copy_from_user(void *to, const void __user *from, unsigned long n)
{
switch (n) {
case 1:
- __get_user_asm(res, *(u8 *)to, (u8 __user *)from, u8, b, d, 1);
+ __constant_copy_from_user_asm(res, to, from, tmp, 1, 0, 0);
break;
case 2:
- __get_user_asm(res, *(u16 *)to, (u16 __user *)from, u16, w, r, 2);
+ __constant_copy_from_user_asm(res, to, from, tmp, 2, 0, 0);
break;
case 3:
- __constant_copy_from_user_asm(res, to, from, tmp, 3, w, b,);
+ __constant_copy_from_user_asm(res, to, from, tmp, 2, 1, 0);
break;
case 4:
- __get_user_asm(res, *(u32 *)to, (u32 __user *)from, u32, l, r, 4);
+ __constant_copy_from_user_asm(res, to, from, tmp, 4, 0, 0);
break;
case 5:
- __constant_copy_from_user_asm(res, to, from, tmp, 5, l, b,);
+ __constant_copy_from_user_asm(res, to, from, tmp, 4, 1, 0);
break;
case 6:
- __constant_copy_from_user_asm(res, to, from, tmp, 6, l, w,);
+ __constant_copy_from_user_asm(res, to, from, tmp, 4, 2, 0);
break;
case 7:
- __constant_copy_from_user_asm(res, to, from, tmp, 7, l, w, b);
+ __constant_copy_from_user_asm(res, to, from, tmp, 4, 2, 1);
break;
case 8:
- __constant_copy_from_user_asm(res, to, from, tmp, 8, l, l,);
+ __constant_copy_from_user_asm(res, to, from, tmp, 4, 4, 0);
break;
case 9:
- __constant_copy_from_user_asm(res, to, from, tmp, 9, l, l, b);
+ __constant_copy_from_user_asm(res, to, from, tmp, 4, 4, 1);
break;
case 10:
- __constant_copy_from_user_asm(res, to, from, tmp, 10, l, l, w);
+ __constant_copy_from_user_asm(res, to, from, tmp, 4, 4, 2);
break;
case 12:
- __constant_copy_from_user_asm(res, to, from, tmp, 12, l, l, l);
+ __constant_copy_from_user_asm(res, to, from, tmp, 4, 4, 4);
break;
default:
/* we limit the inlined version to 3 moves */
return res;
}
-#define __copy_from_user(to, from, n) \
-(__builtin_constant_p(n) ? \
- __constant_copy_from_user(to, from, n) : \
- __generic_copy_from_user(to, from, n))
-
-#define __copy_to_user(to, from, n) \
-(__builtin_constant_p(n) ? \
- __constant_copy_to_user(to, from, n) : \
- __generic_copy_to_user(to, from, n))
-
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
+static inline unsigned long
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+ if (__builtin_constant_p(n))
+ return __constant_copy_from_user(to, from, n);
+ return __generic_copy_from_user(to, from, n);
+}
-#define copy_from_user(to, from, n) __copy_from_user(to, from, n)
-#define copy_to_user(to, from, n) __copy_to_user(to, from, n)
+static inline unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+ if (__builtin_constant_p(n))
+ return __constant_copy_to_user(to, from, n);
+ return __generic_copy_to_user(to, from, n);
+}
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
#define user_addr_max() \
- (segment_eq(get_fs(), USER_DS) ? TASK_SIZE : ~0UL)
+ (uaccess_kernel() ? ~0UL : TASK_SIZE)
extern long strncpy_from_user(char *dst, const char __user *src, long count);
extern __must_check long strlen_user(const char __user *str);
/*
* User space memory access functions
*/
-#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <asm/segment.h>
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
#define access_ok(type,addr,size) _access_ok((unsigned long)(addr),(size))
/*
}
/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue. No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path. This means when everything is well,
- * we don't even have to jump over them. Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry
-{
- unsigned long insn, fixup;
-};
-
-
-/*
* These are the main single-value transfer routines. They automatically
* use the right size if we just have the right pointer type.
*/
: "=d" (x) \
: "m" (*__ptr(ptr)))
-#define copy_from_user(to, from, n) (memcpy(to, from, n), 0)
-#define copy_to_user(to, from, n) (memcpy(to, from, n), 0)
+static inline unsigned long
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+ memcpy(to, (__force const void *)from, n);
+ return 0;
+}
-#define __copy_from_user(to, from, n) copy_from_user(to, from, n)
-#define __copy_to_user(to, from, n) copy_to_user(to, from, n)
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
+static inline unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+ memcpy((__force void *)to, from, n);
+ return 0;
+}
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
/*
* Copy a null terminated string from userspace.
return frame_size_change[f];
}
-int handle_kernel_fault(struct pt_regs *regs)
+int fixup_exception(struct pt_regs *regs)
{
const struct exception_table_entry *fixup;
struct pt_regs *tregs;
/* traced a trapping instruction on a 68020/30,
* real exception will be executed afterwards.
*/
- } else if (!handle_kernel_fault(&fp->ptregs))
- bad_super_trap(fp);
+ return;
+ }
+#ifdef CONFIG_MMU
+ if (fixup_exception(&fp->ptregs))
+ return;
+#endif
+ bad_super_trap(fp);
return;
}
"6:\n"
" .section .fixup,\"ax\"\n"
" .even\n"
- "10: move.l %0,%3\n"
- "7: clr.l (%2)+\n"
- " subq.l #1,%3\n"
- " jne 7b\n"
- " lsl.l #2,%0\n"
+ "10: lsl.l #2,%0\n"
" btst #1,%5\n"
" jeq 8f\n"
- "30: clr.w (%2)+\n"
- " addq.l #2,%0\n"
+ "30: addq.l #2,%0\n"
"8: btst #0,%5\n"
" jeq 6b\n"
- "50: clr.b (%2)+\n"
- " addq.l #1,%0\n"
+ "50: addq.l #1,%0\n"
" jra 6b\n"
" .previous\n"
"\n"
force_sig_info(siginfo.si_signo,
&siginfo, current);
} else {
- if (handle_kernel_fault(regs))
+ if (fixup_exception(regs))
return -1;
//if (siginfo.si_signo == SIGBUS)
generic-y += emergency-restart.h
generic-y += errno.h
generic-y += exec.h
+generic-y += extable.h
generic-y += fb.h
generic-y += fcntl.h
generic-y += futex.h
/*
* User space memory access functions
*/
-#include <linux/sched.h>
-
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
/*
* The fs value determines whether argument validity checking should be
#define segment_eq(a, b) ((a).seg == (b).seg)
-#define __kernel_ok (segment_eq(get_fs(), KERNEL_DS))
+#define __kernel_ok (uaccess_kernel())
/*
* Explicitly allow NULL pointers here. Parts of the kernel such
* as readv/writev use access_ok to validate pointers, but want
#define access_ok(type, addr, size) __access_ok((unsigned long)(addr), \
(unsigned long)(size))
-static inline int verify_area(int type, const void *addr, unsigned long size)
-{
- return access_ok(type, addr, size) ? 0 : -EFAULT;
-}
-
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue. No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path. This means when everything is well,
- * we don't even have to jump over them. Further, they do not intrude
- * on our cache or tlb entries.
- */
-struct exception_table_entry {
- unsigned long insn, fixup;
-};
-
-extern int fixup_exception(struct pt_regs *regs);
+#include <asm/extable.h>
/*
* These are the main single-value transfer routines. They automatically
#define strlen_user(str) strnlen_user(str, 32767)
-extern unsigned long __must_check __copy_user_zeroing(void *to,
- const void __user *from,
- unsigned long n);
-
-static inline unsigned long
-copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- if (likely(access_ok(VERIFY_READ, from, n)))
- return __copy_user_zeroing(to, from, n);
- memset(to, 0, n);
- return n;
-}
-
-#define __copy_from_user(to, from, n) __copy_user_zeroing(to, from, n)
-#define __copy_from_user_inatomic __copy_from_user
-
-extern unsigned long __must_check __copy_user(void __user *to,
- const void *from,
- unsigned long n);
-
-static inline unsigned long copy_to_user(void __user *to, const void *from,
- unsigned long n)
-{
- if (access_ok(VERIFY_WRITE, to, n))
- return __copy_user(to, from, n);
- return n;
-}
-
-#define __copy_to_user(to, from, n) __copy_user(to, from, n)
-#define __copy_to_user_inatomic __copy_to_user
+extern unsigned long raw_copy_from_user(void *to, const void __user *from,
+ unsigned long n);
+extern unsigned long raw_copy_to_user(void __user *to, const void *from,
+ unsigned long n);
/*
* Zero Userspace
COPY \
"1:\n" \
" .section .fixup,\"ax\"\n" \
- " MOV D1Ar1,#0\n" \
FIXUP \
" MOVT D1Ar1,#HI(1b)\n" \
" JUMP D1Ar1,#LO(1b)\n" \
"MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
"22:\n" \
"MSETL [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
- "SUB %3, %3, #32\n" \
"23:\n" \
- "MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
+ "SUB %3, %3, #32\n" \
"24:\n" \
+ "MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
+ "25:\n" \
"MSETL [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "26:\n" \
"SUB %3, %3, #32\n" \
"DCACHE [%1+#-64], D0Ar6\n" \
"BR $Lloop"id"\n" \
\
"MOV RAPF, %1\n" \
- "25:\n" \
+ "27:\n" \
"MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "26:\n" \
+ "28:\n" \
"MSETL [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "29:\n" \
"SUB %3, %3, #32\n" \
- "27:\n" \
+ "30:\n" \
"MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "28:\n" \
+ "31:\n" \
"MSETL [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "32:\n" \
"SUB %0, %0, #8\n" \
- "29:\n" \
+ "33:\n" \
"SETL [%0++], D0.7, D1.7\n" \
"SUB %3, %3, #32\n" \
"1:" \
" .long 26b,3b\n" \
" .long 27b,3b\n" \
" .long 28b,3b\n" \
- " .long 29b,4b\n" \
+ " .long 29b,3b\n" \
+ " .long 30b,3b\n" \
+ " .long 31b,3b\n" \
+ " .long 32b,3b\n" \
+ " .long 33b,4b\n" \
" .previous\n" \
: "=r" (to), "=r" (from), "=r" (ret), "=d" (n) \
: "0" (to), "1" (from), "2" (ret), "3" (n) \
- : "D1Ar1", "D0Ar2", "memory")
+ : "D1Ar1", "D0Ar2", "cc", "memory")
/* rewind 'to' and 'from' pointers when a fault occurs
*
#define __asm_copy_to_user_64bit_rapf_loop(to, from, ret, n, id)\
__asm_copy_user_64bit_rapf_loop(to, from, ret, n, id, \
"LSR D0Ar2, D0Ar2, #8\n" \
- "AND D0Ar2, D0Ar2, #0x7\n" \
+ "ANDS D0Ar2, D0Ar2, #0x7\n" \
"ADDZ D0Ar2, D0Ar2, #4\n" \
"SUB D0Ar2, D0Ar2, #1\n" \
"MOV D1Ar1, #4\n" \
"MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
"22:\n" \
"MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
- "SUB %3, %3, #16\n" \
"23:\n" \
- "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "24:\n" \
- "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
"SUB %3, %3, #16\n" \
- "25:\n" \
+ "24:\n" \
"MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "26:\n" \
+ "25:\n" \
"MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "26:\n" \
"SUB %3, %3, #16\n" \
"27:\n" \
"MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
"28:\n" \
"MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "29:\n" \
+ "SUB %3, %3, #16\n" \
+ "30:\n" \
+ "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
+ "31:\n" \
+ "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "32:\n" \
"SUB %3, %3, #16\n" \
"DCACHE [%1+#-64], D0Ar6\n" \
"BR $Lloop"id"\n" \
\
"MOV RAPF, %1\n" \
- "29:\n" \
+ "33:\n" \
"MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "30:\n" \
+ "34:\n" \
"MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "35:\n" \
"SUB %3, %3, #16\n" \
- "31:\n" \
+ "36:\n" \
"MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "32:\n" \
+ "37:\n" \
"MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "38:\n" \
"SUB %3, %3, #16\n" \
- "33:\n" \
+ "39:\n" \
"MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "34:\n" \
+ "40:\n" \
"MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "41:\n" \
"SUB %3, %3, #16\n" \
- "35:\n" \
+ "42:\n" \
"MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "36:\n" \
+ "43:\n" \
"MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "44:\n" \
"SUB %0, %0, #4\n" \
- "37:\n" \
+ "45:\n" \
"SETD [%0++], D0.7\n" \
"SUB %3, %3, #16\n" \
"1:" \
" .long 34b,3b\n" \
" .long 35b,3b\n" \
" .long 36b,3b\n" \
- " .long 37b,4b\n" \
+ " .long 37b,3b\n" \
+ " .long 38b,3b\n" \
+ " .long 39b,3b\n" \
+ " .long 40b,3b\n" \
+ " .long 41b,3b\n" \
+ " .long 42b,3b\n" \
+ " .long 43b,3b\n" \
+ " .long 44b,3b\n" \
+ " .long 45b,4b\n" \
" .previous\n" \
: "=r" (to), "=r" (from), "=r" (ret), "=d" (n) \
: "0" (to), "1" (from), "2" (ret), "3" (n) \
- : "D1Ar1", "D0Ar2", "memory")
+ : "D1Ar1", "D0Ar2", "cc", "memory")
/* rewind 'to' and 'from' pointers when a fault occurs
*
#define __asm_copy_to_user_32bit_rapf_loop(to, from, ret, n, id)\
__asm_copy_user_32bit_rapf_loop(to, from, ret, n, id, \
"LSR D0Ar2, D0Ar2, #8\n" \
- "AND D0Ar2, D0Ar2, #0x7\n" \
+ "ANDS D0Ar2, D0Ar2, #0x7\n" \
"ADDZ D0Ar2, D0Ar2, #4\n" \
"SUB D0Ar2, D0Ar2, #1\n" \
"MOV D1Ar1, #4\n" \
"SUB %1, %1, D0Ar2\n" \
"SUB %3, %3, D1Ar1\n")
-unsigned long __copy_user(void __user *pdst, const void *psrc,
- unsigned long n)
+unsigned long raw_copy_to_user(void __user *pdst, const void *psrc,
+ unsigned long n)
{
register char __user *dst asm ("A0.2") = pdst;
register const char *src asm ("A1.2") = psrc;
if ((unsigned long) src & 1) {
__asm_copy_to_user_1(dst, src, retn);
n--;
+ if (retn)
+ return retn + n;
}
if ((unsigned long) dst & 1) {
/* Worst case - byte copy */
while (n > 0) {
__asm_copy_to_user_1(dst, src, retn);
n--;
+ if (retn)
+ return retn + n;
}
}
if (((unsigned long) src & 2) && n >= 2) {
__asm_copy_to_user_2(dst, src, retn);
n -= 2;
+ if (retn)
+ return retn + n;
}
if ((unsigned long) dst & 2) {
/* Second worst case - word copy */
while (n >= 2) {
__asm_copy_to_user_2(dst, src, retn);
n -= 2;
+ if (retn)
+ return retn + n;
}
}
while (n >= 8) {
__asm_copy_to_user_8x64(dst, src, retn);
n -= 8;
+ if (retn)
+ return retn + n;
}
}
if (n >= RAPF_MIN_BUF_SIZE) {
while (n >= 8) {
__asm_copy_to_user_8x64(dst, src, retn);
n -= 8;
+ if (retn)
+ return retn + n;
}
}
#endif
while (n >= 16) {
__asm_copy_to_user_16(dst, src, retn);
n -= 16;
+ if (retn)
+ return retn + n;
}
while (n >= 4) {
__asm_copy_to_user_4(dst, src, retn);
n -= 4;
+ if (retn)
+ return retn + n;
}
switch (n) {
break;
}
+ /*
+ * If we get here, retn correctly reflects the number of failing
+ * bytes.
+ */
return retn;
}
-EXPORT_SYMBOL(__copy_user);
+EXPORT_SYMBOL(raw_copy_to_user);
#define __asm_copy_from_user_1(to, from, ret) \
__asm_copy_user_cont(to, from, ret, \
" GETB D1Ar1,[%1++]\n" \
"2: SETB [%0++],D1Ar1\n", \
- "3: ADD %2,%2,#1\n" \
- " SETB [%0++],D1Ar1\n", \
+ "3: ADD %2,%2,#1\n", \
" .long 2b,3b\n")
#define __asm_copy_from_user_2x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
__asm_copy_user_cont(to, from, ret, \
" GETW D1Ar1,[%1++]\n" \
"2: SETW [%0++],D1Ar1\n" COPY, \
- "3: ADD %2,%2,#2\n" \
- " SETW [%0++],D1Ar1\n" FIXUP, \
+ "3: ADD %2,%2,#2\n" FIXUP, \
" .long 2b,3b\n" TENTRY)
#define __asm_copy_from_user_2(to, from, ret) \
__asm_copy_from_user_2x_cont(to, from, ret, \
" GETB D1Ar1,[%1++]\n" \
"4: SETB [%0++],D1Ar1\n", \
- "5: ADD %2,%2,#1\n" \
- " SETB [%0++],D1Ar1\n", \
+ "5: ADD %2,%2,#1\n", \
" .long 4b,5b\n")
#define __asm_copy_from_user_4x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
__asm_copy_user_cont(to, from, ret, \
" GETD D1Ar1,[%1++]\n" \
"2: SETD [%0++],D1Ar1\n" COPY, \
- "3: ADD %2,%2,#4\n" \
- " SETD [%0++],D1Ar1\n" FIXUP, \
+ "3: ADD %2,%2,#4\n" FIXUP, \
" .long 2b,3b\n" TENTRY)
#define __asm_copy_from_user_4(to, from, ret) \
__asm_copy_from_user_4x_cont(to, from, ret, "", "", "")
-#define __asm_copy_from_user_5(to, from, ret) \
- __asm_copy_from_user_4x_cont(to, from, ret, \
- " GETB D1Ar1,[%1++]\n" \
- "4: SETB [%0++],D1Ar1\n", \
- "5: ADD %2,%2,#1\n" \
- " SETB [%0++],D1Ar1\n", \
- " .long 4b,5b\n")
-
-#define __asm_copy_from_user_6x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
- __asm_copy_from_user_4x_cont(to, from, ret, \
- " GETW D1Ar1,[%1++]\n" \
- "4: SETW [%0++],D1Ar1\n" COPY, \
- "5: ADD %2,%2,#2\n" \
- " SETW [%0++],D1Ar1\n" FIXUP, \
- " .long 4b,5b\n" TENTRY)
-
-#define __asm_copy_from_user_6(to, from, ret) \
- __asm_copy_from_user_6x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_7(to, from, ret) \
- __asm_copy_from_user_6x_cont(to, from, ret, \
- " GETB D1Ar1,[%1++]\n" \
- "6: SETB [%0++],D1Ar1\n", \
- "7: ADD %2,%2,#1\n" \
- " SETB [%0++],D1Ar1\n", \
- " .long 6b,7b\n")
-
-#define __asm_copy_from_user_8x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
- __asm_copy_from_user_4x_cont(to, from, ret, \
- " GETD D1Ar1,[%1++]\n" \
- "4: SETD [%0++],D1Ar1\n" COPY, \
- "5: ADD %2,%2,#4\n" \
- " SETD [%0++],D1Ar1\n" FIXUP, \
- " .long 4b,5b\n" TENTRY)
-
-#define __asm_copy_from_user_8(to, from, ret) \
- __asm_copy_from_user_8x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_9(to, from, ret) \
- __asm_copy_from_user_8x_cont(to, from, ret, \
- " GETB D1Ar1,[%1++]\n" \
- "6: SETB [%0++],D1Ar1\n", \
- "7: ADD %2,%2,#1\n" \
- " SETB [%0++],D1Ar1\n", \
- " .long 6b,7b\n")
-
-#define __asm_copy_from_user_10x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
- __asm_copy_from_user_8x_cont(to, from, ret, \
- " GETW D1Ar1,[%1++]\n" \
- "6: SETW [%0++],D1Ar1\n" COPY, \
- "7: ADD %2,%2,#2\n" \
- " SETW [%0++],D1Ar1\n" FIXUP, \
- " .long 6b,7b\n" TENTRY)
-
-#define __asm_copy_from_user_10(to, from, ret) \
- __asm_copy_from_user_10x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_11(to, from, ret) \
- __asm_copy_from_user_10x_cont(to, from, ret, \
- " GETB D1Ar1,[%1++]\n" \
- "8: SETB [%0++],D1Ar1\n", \
- "9: ADD %2,%2,#1\n" \
- " SETB [%0++],D1Ar1\n", \
- " .long 8b,9b\n")
-
-#define __asm_copy_from_user_12x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
- __asm_copy_from_user_8x_cont(to, from, ret, \
- " GETD D1Ar1,[%1++]\n" \
- "6: SETD [%0++],D1Ar1\n" COPY, \
- "7: ADD %2,%2,#4\n" \
- " SETD [%0++],D1Ar1\n" FIXUP, \
- " .long 6b,7b\n" TENTRY)
-
-#define __asm_copy_from_user_12(to, from, ret) \
- __asm_copy_from_user_12x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_13(to, from, ret) \
- __asm_copy_from_user_12x_cont(to, from, ret, \
- " GETB D1Ar1,[%1++]\n" \
- "8: SETB [%0++],D1Ar1\n", \
- "9: ADD %2,%2,#1\n" \
- " SETB [%0++],D1Ar1\n", \
- " .long 8b,9b\n")
-
-#define __asm_copy_from_user_14x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
- __asm_copy_from_user_12x_cont(to, from, ret, \
- " GETW D1Ar1,[%1++]\n" \
- "8: SETW [%0++],D1Ar1\n" COPY, \
- "9: ADD %2,%2,#2\n" \
- " SETW [%0++],D1Ar1\n" FIXUP, \
- " .long 8b,9b\n" TENTRY)
-
-#define __asm_copy_from_user_14(to, from, ret) \
- __asm_copy_from_user_14x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_15(to, from, ret) \
- __asm_copy_from_user_14x_cont(to, from, ret, \
- " GETB D1Ar1,[%1++]\n" \
- "10: SETB [%0++],D1Ar1\n", \
- "11: ADD %2,%2,#1\n" \
- " SETB [%0++],D1Ar1\n", \
- " .long 10b,11b\n")
-
-#define __asm_copy_from_user_16x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
- __asm_copy_from_user_12x_cont(to, from, ret, \
- " GETD D1Ar1,[%1++]\n" \
- "8: SETD [%0++],D1Ar1\n" COPY, \
- "9: ADD %2,%2,#4\n" \
- " SETD [%0++],D1Ar1\n" FIXUP, \
- " .long 8b,9b\n" TENTRY)
-
-#define __asm_copy_from_user_16(to, from, ret) \
- __asm_copy_from_user_16x_cont(to, from, ret, "", "", "")
-
#define __asm_copy_from_user_8x64(to, from, ret) \
asm volatile ( \
" GETL D0Ar2,D1Ar1,[%1++]\n" \
"2: SETL [%0++],D0Ar2,D1Ar1\n" \
"1:\n" \
" .section .fixup,\"ax\"\n" \
- " MOV D1Ar1,#0\n" \
- " MOV D0Ar2,#0\n" \
"3: ADD %2,%2,#8\n" \
- " SETL [%0++],D0Ar2,D1Ar1\n" \
" MOVT D0Ar2,#HI(1b)\n" \
" JUMP D0Ar2,#LO(1b)\n" \
" .previous\n" \
*
* Rationale:
* A fault occurs while reading from user buffer, which is the
- * source. Since the fault is at a single address, we only
- * need to rewind by 8 bytes.
+ * source.
* Since we don't write to kernel buffer until we read first,
* the kernel buffer is at the right state and needn't be
- * corrected.
+ * corrected, but the source must be rewound to the beginning of
+ * the block, which is LSM_STEP*8 bytes.
+ * LSM_STEP is bits 10:8 in TXSTATUS which is already read
+ * and stored in D0Ar2
+ *
+ * NOTE: If a fault occurs at the last operation in M{G,S}ETL
+ * LSM_STEP will be 0. ie: we do 4 writes in our case, if
+ * a fault happens at the 4th write, LSM_STEP will be 0
+ * instead of 4. The code copes with that.
*/
#define __asm_copy_from_user_64bit_rapf_loop(to, from, ret, n, id) \
__asm_copy_user_64bit_rapf_loop(to, from, ret, n, id, \
- "SUB %1, %1, #8\n")
+ "LSR D0Ar2, D0Ar2, #5\n" \
+ "ANDS D0Ar2, D0Ar2, #0x38\n" \
+ "ADDZ D0Ar2, D0Ar2, #32\n" \
+ "SUB %1, %1, D0Ar2\n")
/* rewind 'from' pointer when a fault occurs
*
* Rationale:
* A fault occurs while reading from user buffer, which is the
- * source. Since the fault is at a single address, we only
- * need to rewind by 4 bytes.
+ * source.
* Since we don't write to kernel buffer until we read first,
* the kernel buffer is at the right state and needn't be
- * corrected.
+ * corrected, but the source must be rewound to the beginning of
+ * the block, which is LSM_STEP*4 bytes.
+ * LSM_STEP is bits 10:8 in TXSTATUS which is already read
+ * and stored in D0Ar2
+ *
+ * NOTE: If a fault occurs at the last operation in M{G,S}ETL
+ * LSM_STEP will be 0. ie: we do 4 writes in our case, if
+ * a fault happens at the 4th write, LSM_STEP will be 0
+ * instead of 4. The code copes with that.
*/
#define __asm_copy_from_user_32bit_rapf_loop(to, from, ret, n, id) \
__asm_copy_user_32bit_rapf_loop(to, from, ret, n, id, \
- "SUB %1, %1, #4\n")
+ "LSR D0Ar2, D0Ar2, #6\n" \
+ "ANDS D0Ar2, D0Ar2, #0x1c\n" \
+ "ADDZ D0Ar2, D0Ar2, #16\n" \
+ "SUB %1, %1, D0Ar2\n")
-/* Copy from user to kernel, zeroing the bytes that were inaccessible in
- userland. The return-value is the number of bytes that were
- inaccessible. */
-unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
- unsigned long n)
+/*
+ * Copy from user to kernel. The return-value is the number of bytes that were
+ * inaccessible.
+ */
+unsigned long raw_copy_from_user(void *pdst, const void __user *psrc,
+ unsigned long n)
{
register char *dst asm ("A0.2") = pdst;
register const char __user *src asm ("A1.2") = psrc;
if ((unsigned long) src & 1) {
__asm_copy_from_user_1(dst, src, retn);
n--;
+ if (retn)
+ return retn + n;
}
if ((unsigned long) dst & 1) {
/* Worst case - byte copy */
__asm_copy_from_user_1(dst, src, retn);
n--;
if (retn)
- goto copy_exception_bytes;
+ return retn + n;
}
}
if (((unsigned long) src & 2) && n >= 2) {
__asm_copy_from_user_2(dst, src, retn);
n -= 2;
+ if (retn)
+ return retn + n;
}
if ((unsigned long) dst & 2) {
/* Second worst case - word copy */
__asm_copy_from_user_2(dst, src, retn);
n -= 2;
if (retn)
- goto copy_exception_bytes;
+ return retn + n;
}
}
- /* We only need one check after the unalignment-adjustments,
- because if both adjustments were done, either both or
- neither reference had an exception. */
- if (retn != 0)
- goto copy_exception_bytes;
-
#ifdef USE_RAPF
/* 64 bit copy loop */
if (!(((unsigned long) src | (unsigned long) dst) & 7)) {
__asm_copy_from_user_8x64(dst, src, retn);
n -= 8;
if (retn)
- goto copy_exception_bytes;
+ return retn + n;
}
}
__asm_copy_from_user_8x64(dst, src, retn);
n -= 8;
if (retn)
- goto copy_exception_bytes;
+ return retn + n;
}
}
#endif
n -= 4;
if (retn)
- goto copy_exception_bytes;
+ return retn + n;
}
/* If we get here, there were no memory read faults. */
/* If we get here, retn correctly reflects the number of failing
bytes. */
return retn;
-
- copy_exception_bytes:
- /* We already have "retn" bytes cleared, and need to clear the
- remaining "n" bytes. A non-optimized simple byte-for-byte in-line
- memset is preferred here, since this isn't speed-critical code and
- we'd rather have this a leaf-function than calling memset. */
- {
- char *endp;
- for (endp = dst + n; dst < endp; dst++)
- *dst = 0;
- }
-
- return retn + n;
}
-EXPORT_SYMBOL(__copy_user_zeroing);
+EXPORT_SYMBOL(raw_copy_from_user);
#define __asm_clear_8x64(to, ret) \
asm volatile ( \
generic-y += clkdev.h
generic-y += device.h
generic-y += exec.h
+generic-y += extable.h
generic-y += irq_work.h
generic-y += mcs_spinlock.h
generic-y += mm-arch-hooks.h
#ifndef _ASM_MICROBLAZE_UACCESS_H
#define _ASM_MICROBLAZE_UACCESS_H
-#ifdef __KERNEL__
-#ifndef __ASSEMBLY__
-
#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/sched.h> /* RLIMIT_FSIZE */
#include <linux/mm.h>
#include <asm/mmu.h>
#include <asm/page.h>
#include <asm/pgtable.h>
+#include <asm/extable.h>
#include <linux/string.h>
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
/*
* On Microblaze the fs value is actually the top of the corresponding
* address space.
# define segment_eq(a, b) ((a).seg == (b).seg)
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue. No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path. This means when everything is well,
- * we don't even have to jump over them. Further, they do not intrude
- * on our cache or tlb entries.
- */
-struct exception_table_entry {
- unsigned long insn, fixup;
-};
-
#ifndef CONFIG_MMU
/* Check against bounds of physical memory */
__gu_err; \
})
-
-/* copy_to_from_user */
-#define __copy_from_user(to, from, n) \
- __copy_tofrom_user((__force void __user *)(to), \
- (void __user *)(from), (n))
-#define __copy_from_user_inatomic(to, from, n) \
- __copy_from_user((to), (from), (n))
-
-static inline long copy_from_user(void *to,
- const void __user *from, unsigned long n)
+static inline unsigned long
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
{
- unsigned long res = n;
- might_fault();
- if (likely(access_ok(VERIFY_READ, from, n)))
- res = __copy_from_user(to, from, n);
- if (unlikely(res))
- memset(to + (n - res), 0, res);
- return res;
+ return __copy_tofrom_user((__force void __user *)to, from, n);
}
-#define __copy_to_user(to, from, n) \
- __copy_tofrom_user((void __user *)(to), \
- (__force const void __user *)(from), (n))
-#define __copy_to_user_inatomic(to, from, n) __copy_to_user((to), (from), (n))
-
-static inline long copy_to_user(void __user *to,
- const void *from, unsigned long n)
+static inline unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
{
- might_fault();
- if (access_ok(VERIFY_WRITE, to, n))
- return __copy_to_user(to, from, n);
- return n;
+ return __copy_tofrom_user(to, (__force const void __user *)from, n);
}
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
/*
* Copy a null terminated string from userspace.
return __strnlen_user(src, n);
}
-#endif /* __ASSEMBLY__ */
-#endif /* __KERNEL__ */
-
#endif /* _ASM_MICROBLAZE_UACCESS_H */
select HANDLE_DOMAIN_IRQ
select HAVE_EXIT_THREAD
select HAVE_REGS_AND_STACK_ACCESS_API
- select HAVE_ARCH_HARDENED_USERCOPY
menu "Machine selection"
select CPU_SUPPORTS_HIGHMEM
select CPU_SUPPORTS_MSA
select GENERIC_CSUM
- select MIPS_O32_FP64_SUPPORT if MIPS32_O32
+ select MIPS_O32_FP64_SUPPORT if 32BIT || MIPS32_O32
select HAVE_KVM
help
Choose this option to build a kernel for release 6 or later of the
$(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh \
-m -O $(objtree) $(srctree)/arch/$(ARCH)/configs/generic_defconfig $^ \
$(foreach board,$(BOARDS),$(generic_config_dir)/board-$(board).config)
- $(Q)$(MAKE) olddefconfig
+ $(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig
#
# Prevent generic merge_config rules attempting to merge single fragments
#
.PHONY: sead3_defconfig
sead3_defconfig:
- $(Q)$(MAKE) 32r2el_defconfig BOARDS=sead-3
+ $(Q)$(MAKE) -f $(srctree)/Makefile 32r2el_defconfig BOARDS=sead-3
.PHONY: sead3micro_defconfig
sead3micro_defconfig:
- $(Q)$(MAKE) micro32r2el_defconfig BOARDS=sead-3
+ $(Q)$(MAKE) -f $(srctree)/Makefile micro32r2el_defconfig BOARDS=sead-3
cd->shift = 32;
cd->mult = div_sc(32768, NSEC_PER_SEC, cd->shift);
cd->max_delta_ns = clockevent_delta2ns(0xffffffff, cd);
- cd->min_delta_ns = clockevent_delta2ns(9, cd); /* ~0.28ms */
+ cd->max_delta_ticks = 0xffffffff;
+ cd->min_delta_ns = clockevent_delta2ns(9, cd);
+ cd->min_delta_ticks = 9; /* ~0.28ms */
clockevents_register_device(cd);
setup_irq(m2int, &au1x_rtcmatch2_irqaction);
.set noat
/*
- * t7 is used as a flag to note inatomic mode.
- */
-LEAF(__copy_user_inatomic)
-EXPORT_SYMBOL(__copy_user_inatomic)
- b __copy_user_common
- li t7, 1
- END(__copy_user_inatomic)
-
-/*
* A combined memcpy/__copy_user
* __copy_user sets len to 0 for success; else to an upper bound of
* the number of uncopied bytes.
__memcpy:
FEXPORT(__copy_user)
EXPORT_SYMBOL(__copy_user)
- li t7, 0 /* not inatomic */
-__copy_user_common:
/*
* Note: dst & src may be unaligned, len may be 0
* Temps
LOAD t0, TI_TASK($28)
LOAD t0, THREAD_BUADDR(t0) # t0 is just past last good address
SUB len, AT, t0 # len number of uncopied bytes
- bnez t7, 2f /* Skip the zeroing out part if inatomic */
- /*
- * Here's where we rely on src and dst being incremented in tandem,
- * See (3) above.
- * dst += (fault addr - src) to put dst at first byte to clear
- */
- ADD dst, t0 # compute start address in a1
- SUB dst, src
- /*
- * Clear len bytes starting at dst. Can't call __bzero because it
- * might modify len. An inefficient loop for these rare times...
- */
- beqz len, done
- SUB src, len, 1
-1: sb zero, 0(dst)
- ADD dst, dst, 1
- bnez src, 1b
- SUB src, src, 1
-2: jr ra
+ jr ra
nop
#include <asm/fpu.h>
#include <asm-generic/asm-prototypes.h>
#include <asm/uaccess.h>
+#include <asm/ftrace.h>
__wsum sum, int *err_ptr)
{
might_fault();
- if (segment_eq(get_fs(), get_ds()))
+ if (uaccess_kernel())
return __csum_partial_copy_kernel((__force void *)src, dst,
len, sum, err_ptr);
else
{
might_fault();
if (access_ok(VERIFY_WRITE, dst, len)) {
- if (segment_eq(get_fs(), get_ds()))
+ if (uaccess_kernel())
return __csum_partial_copy_kernel(src,
(__force void *)dst,
len, sum, err_ptr);
#include <asm/cpu-features.h>
#include <asm/fpu_emulator.h>
#include <asm/hazards.h>
+#include <asm/ptrace.h>
#include <asm/processor.h>
#include <asm/current.h>
#include <asm/msa.h>
#include <irq.h>
#define IRQ_STACK_SIZE THREAD_SIZE
+#define IRQ_STACK_START (IRQ_STACK_SIZE - sizeof(unsigned long))
extern void *irq_stack[NR_CPUS];
+/*
+ * The highest address on the IRQ stack contains a dummy frame put down in
+ * genex.S (handle_int & except_vec_vi_handler) which is structured as follows:
+ *
+ * top ------------
+ * | task sp | <- irq_stack[cpu] + IRQ_STACK_START
+ * ------------
+ * | | <- First frame of IRQ context
+ * ------------
+ *
+ * task sp holds a copy of the task stack pointer where the struct pt_regs
+ * from exception entry can be found.
+ */
+
static inline bool on_irq_stack(int cpu, unsigned long sp)
{
unsigned long low = (unsigned long)irq_stack[cpu];
#include <asm/cpu-features.h>
#include <asm/cpu-type.h>
#include <asm/mipsmtregs.h>
-#include <linux/uaccess.h> /* for segment_eq() */
+#include <linux/uaccess.h> /* for uaccess_kernel() */
extern void (*r4k_blast_dcache)(void);
extern void (*r4k_blast_icache)(void);
\
__##pfx##flush_prologue \
\
- if (segment_eq(get_fs(), USER_DS)) { \
+ if (!uaccess_kernel()) { \
while (1) { \
protected_cachee_op(hitop, addr); \
if (addr == aend) \
" andi %[ticket], %[ticket], 0xffff \n"
" bne %[ticket], %[my_ticket], 4f \n"
" subu %[ticket], %[my_ticket], %[ticket] \n"
- "2: \n"
+ "2: .insn \n"
" .subsection 2 \n"
"4: andi %[ticket], %[ticket], 0xffff \n"
" sll %[ticket], 5 \n"
" sc %[ticket], %[ticket_ptr] \n"
" beqz %[ticket], 1b \n"
" li %[ticket], 1 \n"
- "2: \n"
+ "2: .insn \n"
" .subsection 2 \n"
"3: b 2b \n"
" li %[ticket], 0 \n"
" .set reorder \n"
__WEAK_LLSC_MB
" li %2, 1 \n"
- "2: \n"
+ "2: .insn \n"
: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret)
: GCC_OFF_SMALL_ASM() (rw->lock)
: "memory");
" lui %1, 0x8000 \n"
" sc %1, %0 \n"
" li %2, 1 \n"
- "2: \n"
+ "2: .insn \n"
: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp),
"=&r" (ret)
: GCC_OFF_SMALL_ASM() (rw->lock)
#define _ASM_UACCESS_H
#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/thread_info.h>
#include <linux/string.h>
#include <asm/asm-eva.h>
#include <asm/extable.h>
#define USER_DS ((mm_segment_t) { __UA_LIMIT })
#endif
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
#define get_ds() (KERNEL_DS)
#define get_fs() (current_thread_info()->addr_limit)
#define set_fs(x) (current_thread_info()->addr_limit = (x))
if (!IS_ENABLED(CONFIG_EVA))
return false;
- return segment_eq(get_fs(), get_ds());
+ return uaccess_kernel();
}
/*
* this function, memory access functions may still return -EFAULT.
*/
-#define __access_mask get_fs().seg
-
-#define __access_ok(addr, size, mask) \
-({ \
- unsigned long __addr = (unsigned long) (addr); \
- unsigned long __size = size; \
- unsigned long __mask = mask; \
- unsigned long __ok; \
- \
- __chk_user_ptr(addr); \
- __ok = (signed long)(__mask & (__addr | (__addr + __size) | \
- __ua_size(__size))); \
- __ok == 0; \
-})
+static inline int __access_ok(const void __user *p, unsigned long size)
+{
+ unsigned long addr = (unsigned long)p;
+ return (get_fs().seg & (addr | (addr + size) | __ua_size(size))) == 0;
+}
#define access_ok(type, addr, size) \
- likely(__access_ok((addr), (size), __access_mask))
+ likely(__access_ok((addr), (size)))
/*
* put_user: - Write a simple value into user space.
extern size_t __copy_user(void *__to, const void *__from, size_t __n);
-#ifndef CONFIG_EVA
-#define __invoke_copy_to_user(to, from, n) \
-({ \
- register void __user *__cu_to_r __asm__("$4"); \
- register const void *__cu_from_r __asm__("$5"); \
- register long __cu_len_r __asm__("$6"); \
- \
- __cu_to_r = (to); \
- __cu_from_r = (from); \
- __cu_len_r = (n); \
- __asm__ __volatile__( \
- __MODULE_JAL(__copy_user) \
- : "+r" (__cu_to_r), "+r" (__cu_from_r), "+r" (__cu_len_r) \
- : \
- : "$8", "$9", "$10", "$11", "$12", "$14", "$15", "$24", "$31", \
- DADDI_SCRATCH, "memory"); \
- __cu_len_r; \
-})
-
-#define __invoke_copy_to_kernel(to, from, n) \
- __invoke_copy_to_user(to, from, n)
-
-#endif
-
-/*
- * __copy_to_user: - Copy a block of data into user space, with less checking.
- * @to: Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- * enabled.
- *
- * Copy data from kernel space to user space. Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- */
-#define __copy_to_user(to, from, n) \
-({ \
- void __user *__cu_to; \
- const void *__cu_from; \
- long __cu_len; \
- \
- __cu_to = (to); \
- __cu_from = (from); \
- __cu_len = (n); \
- \
- check_object_size(__cu_from, __cu_len, true); \
- might_fault(); \
- \
- if (eva_kernel_access()) \
- __cu_len = __invoke_copy_to_kernel(__cu_to, __cu_from, \
- __cu_len); \
- else \
- __cu_len = __invoke_copy_to_user(__cu_to, __cu_from, \
- __cu_len); \
- __cu_len; \
-})
-
-extern size_t __copy_user_inatomic(void *__to, const void *__from, size_t __n);
-
-#define __copy_to_user_inatomic(to, from, n) \
-({ \
- void __user *__cu_to; \
- const void *__cu_from; \
- long __cu_len; \
- \
- __cu_to = (to); \
- __cu_from = (from); \
- __cu_len = (n); \
- \
- check_object_size(__cu_from, __cu_len, true); \
- \
- if (eva_kernel_access()) \
- __cu_len = __invoke_copy_to_kernel(__cu_to, __cu_from, \
- __cu_len); \
- else \
- __cu_len = __invoke_copy_to_user(__cu_to, __cu_from, \
- __cu_len); \
- __cu_len; \
-})
-
-#define __copy_from_user_inatomic(to, from, n) \
-({ \
- void *__cu_to; \
- const void __user *__cu_from; \
- long __cu_len; \
- \
- __cu_to = (to); \
- __cu_from = (from); \
- __cu_len = (n); \
- \
- check_object_size(__cu_to, __cu_len, false); \
- \
- if (eva_kernel_access()) \
- __cu_len = __invoke_copy_from_kernel_inatomic(__cu_to, \
- __cu_from,\
- __cu_len);\
- else \
- __cu_len = __invoke_copy_from_user_inatomic(__cu_to, \
- __cu_from, \
- __cu_len); \
- __cu_len; \
-})
-
-/*
- * copy_to_user: - Copy a block of data into user space.
- * @to: Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- * enabled.
- *
- * Copy data from kernel space to user space.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- */
-#define copy_to_user(to, from, n) \
-({ \
- void __user *__cu_to; \
- const void *__cu_from; \
- long __cu_len; \
- \
- __cu_to = (to); \
- __cu_from = (from); \
- __cu_len = (n); \
- \
- check_object_size(__cu_from, __cu_len, true); \
- \
- if (eva_kernel_access()) { \
- __cu_len = __invoke_copy_to_kernel(__cu_to, \
- __cu_from, \
- __cu_len); \
- } else { \
- if (access_ok(VERIFY_WRITE, __cu_to, __cu_len)) { \
- might_fault(); \
- __cu_len = __invoke_copy_to_user(__cu_to, \
- __cu_from, \
- __cu_len); \
- } \
- } \
- __cu_len; \
-})
-
-#ifndef CONFIG_EVA
-
-#define __invoke_copy_from_user(to, from, n) \
+#define __invoke_copy_from(func, to, from, n) \
({ \
register void *__cu_to_r __asm__("$4"); \
register const void __user *__cu_from_r __asm__("$5"); \
__cu_len_r = (n); \
__asm__ __volatile__( \
".set\tnoreorder\n\t" \
- __MODULE_JAL(__copy_user) \
+ __MODULE_JAL(func) \
".set\tnoat\n\t" \
__UA_ADDU "\t$1, %1, %2\n\t" \
".set\tat\n\t" \
__cu_len_r; \
})
-#define __invoke_copy_from_kernel(to, from, n) \
- __invoke_copy_from_user(to, from, n)
-
-/* For userland <-> userland operations */
-#define ___invoke_copy_in_user(to, from, n) \
- __invoke_copy_from_user(to, from, n)
-
-/* For kernel <-> kernel operations */
-#define ___invoke_copy_in_kernel(to, from, n) \
- __invoke_copy_from_user(to, from, n)
-
-#define __invoke_copy_from_user_inatomic(to, from, n) \
+#define __invoke_copy_to(func, to, from, n) \
({ \
- register void *__cu_to_r __asm__("$4"); \
- register const void __user *__cu_from_r __asm__("$5"); \
+ register void __user *__cu_to_r __asm__("$4"); \
+ register const void *__cu_from_r __asm__("$5"); \
register long __cu_len_r __asm__("$6"); \
\
__cu_to_r = (to); \
__cu_from_r = (from); \
__cu_len_r = (n); \
__asm__ __volatile__( \
- ".set\tnoreorder\n\t" \
- __MODULE_JAL(__copy_user_inatomic) \
- ".set\tnoat\n\t" \
- __UA_ADDU "\t$1, %1, %2\n\t" \
- ".set\tat\n\t" \
- ".set\treorder" \
+ __MODULE_JAL(func) \
: "+r" (__cu_to_r), "+r" (__cu_from_r), "+r" (__cu_len_r) \
: \
: "$8", "$9", "$10", "$11", "$12", "$14", "$15", "$24", "$31", \
__cu_len_r; \
})
-#define __invoke_copy_from_kernel_inatomic(to, from, n) \
- __invoke_copy_from_user_inatomic(to, from, n) \
+#define __invoke_copy_from_kernel(to, from, n) \
+ __invoke_copy_from(__copy_user, to, from, n)
+
+#define __invoke_copy_to_kernel(to, from, n) \
+ __invoke_copy_to(__copy_user, to, from, n)
+
+#define ___invoke_copy_in_kernel(to, from, n) \
+ __invoke_copy_from(__copy_user, to, from, n)
+
+#ifndef CONFIG_EVA
+#define __invoke_copy_from_user(to, from, n) \
+ __invoke_copy_from(__copy_user, to, from, n)
+
+#define __invoke_copy_to_user(to, from, n) \
+ __invoke_copy_to(__copy_user, to, from, n)
+
+#define ___invoke_copy_in_user(to, from, n) \
+ __invoke_copy_from(__copy_user, to, from, n)
#else
/* EVA specific functions */
-extern size_t __copy_user_inatomic_eva(void *__to, const void *__from,
- size_t __n);
extern size_t __copy_from_user_eva(void *__to, const void *__from,
size_t __n);
extern size_t __copy_to_user_eva(void *__to, const void *__from,
size_t __n);
extern size_t __copy_in_user_eva(void *__to, const void *__from, size_t __n);
-#define __invoke_copy_from_user_eva_generic(to, from, n, func_ptr) \
-({ \
- register void *__cu_to_r __asm__("$4"); \
- register const void __user *__cu_from_r __asm__("$5"); \
- register long __cu_len_r __asm__("$6"); \
- \
- __cu_to_r = (to); \
- __cu_from_r = (from); \
- __cu_len_r = (n); \
- __asm__ __volatile__( \
- ".set\tnoreorder\n\t" \
- __MODULE_JAL(func_ptr) \
- ".set\tnoat\n\t" \
- __UA_ADDU "\t$1, %1, %2\n\t" \
- ".set\tat\n\t" \
- ".set\treorder" \
- : "+r" (__cu_to_r), "+r" (__cu_from_r), "+r" (__cu_len_r) \
- : \
- : "$8", "$9", "$10", "$11", "$12", "$14", "$15", "$24", "$31", \
- DADDI_SCRATCH, "memory"); \
- __cu_len_r; \
-})
-
-#define __invoke_copy_to_user_eva_generic(to, from, n, func_ptr) \
-({ \
- register void *__cu_to_r __asm__("$4"); \
- register const void __user *__cu_from_r __asm__("$5"); \
- register long __cu_len_r __asm__("$6"); \
- \
- __cu_to_r = (to); \
- __cu_from_r = (from); \
- __cu_len_r = (n); \
- __asm__ __volatile__( \
- __MODULE_JAL(func_ptr) \
- : "+r" (__cu_to_r), "+r" (__cu_from_r), "+r" (__cu_len_r) \
- : \
- : "$8", "$9", "$10", "$11", "$12", "$14", "$15", "$24", "$31", \
- DADDI_SCRATCH, "memory"); \
- __cu_len_r; \
-})
-
/*
* Source or destination address is in userland. We need to go through
* the TLB
*/
#define __invoke_copy_from_user(to, from, n) \
- __invoke_copy_from_user_eva_generic(to, from, n, __copy_from_user_eva)
-
-#define __invoke_copy_from_user_inatomic(to, from, n) \
- __invoke_copy_from_user_eva_generic(to, from, n, \
- __copy_user_inatomic_eva)
+ __invoke_copy_from(__copy_from_user_eva, to, from, n)
#define __invoke_copy_to_user(to, from, n) \
- __invoke_copy_to_user_eva_generic(to, from, n, __copy_to_user_eva)
+ __invoke_copy_to(__copy_to_user_eva, to, from, n)
#define ___invoke_copy_in_user(to, from, n) \
- __invoke_copy_from_user_eva_generic(to, from, n, __copy_in_user_eva)
-
-/*
- * Source or destination address in the kernel. We are not going through
- * the TLB
- */
-#define __invoke_copy_from_kernel(to, from, n) \
- __invoke_copy_from_user_eva_generic(to, from, n, __copy_user)
-
-#define __invoke_copy_from_kernel_inatomic(to, from, n) \
- __invoke_copy_from_user_eva_generic(to, from, n, __copy_user_inatomic)
-
-#define __invoke_copy_to_kernel(to, from, n) \
- __invoke_copy_to_user_eva_generic(to, from, n, __copy_user)
-
-#define ___invoke_copy_in_kernel(to, from, n) \
- __invoke_copy_from_user_eva_generic(to, from, n, __copy_user)
+ __invoke_copy_from(__copy_in_user_eva, to, from, n)
#endif /* CONFIG_EVA */
-/*
- * __copy_from_user: - Copy a block of data from user space, with less checking.
- * @to: Destination address, in kernel space.
- * @from: Source address, in user space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- * enabled.
- *
- * Copy data from user space to kernel space. Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- *
- * If some data could not be copied, this function will pad the copied
- * data to the requested size using zero bytes.
- */
-#define __copy_from_user(to, from, n) \
-({ \
- void *__cu_to; \
- const void __user *__cu_from; \
- long __cu_len; \
- \
- __cu_to = (to); \
- __cu_from = (from); \
- __cu_len = (n); \
- \
- check_object_size(__cu_to, __cu_len, false); \
- \
- if (eva_kernel_access()) { \
- __cu_len = __invoke_copy_from_kernel(__cu_to, \
- __cu_from, \
- __cu_len); \
- } else { \
- might_fault(); \
- __cu_len = __invoke_copy_from_user(__cu_to, __cu_from, \
- __cu_len); \
- } \
- __cu_len; \
-})
+static inline unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+ if (eva_kernel_access())
+ return __invoke_copy_to_kernel(to, from, n);
+ else
+ return __invoke_copy_to_user(to, from, n);
+}
-/*
- * copy_from_user: - Copy a block of data from user space.
- * @to: Destination address, in kernel space.
- * @from: Source address, in user space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- * enabled.
- *
- * Copy data from user space to kernel space.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- *
- * If some data could not be copied, this function will pad the copied
- * data to the requested size using zero bytes.
- */
-#define copy_from_user(to, from, n) \
-({ \
- void *__cu_to; \
- const void __user *__cu_from; \
- long __cu_len; \
- \
- __cu_to = (to); \
- __cu_from = (from); \
- __cu_len = (n); \
- \
- check_object_size(__cu_to, __cu_len, false); \
- \
- if (eva_kernel_access()) { \
- __cu_len = __invoke_copy_from_kernel(__cu_to, \
- __cu_from, \
- __cu_len); \
- } else { \
- if (access_ok(VERIFY_READ, __cu_from, __cu_len)) { \
- might_fault(); \
- __cu_len = __invoke_copy_from_user(__cu_to, \
- __cu_from, \
- __cu_len); \
- } else { \
- memset(__cu_to, 0, __cu_len); \
- } \
- } \
- __cu_len; \
-})
+static inline unsigned long
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+ if (eva_kernel_access())
+ return __invoke_copy_from_kernel(to, from, n);
+ else
+ return __invoke_copy_from_user(to, from, n);
+}
-#define __copy_in_user(to, from, n) \
-({ \
- void __user *__cu_to; \
- const void __user *__cu_from; \
- long __cu_len; \
- \
- __cu_to = (to); \
- __cu_from = (from); \
- __cu_len = (n); \
- if (eva_kernel_access()) { \
- __cu_len = ___invoke_copy_in_kernel(__cu_to, __cu_from, \
- __cu_len); \
- } else { \
- might_fault(); \
- __cu_len = ___invoke_copy_in_user(__cu_to, __cu_from, \
- __cu_len); \
- } \
- __cu_len; \
-})
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
-#define copy_in_user(to, from, n) \
-({ \
- void __user *__cu_to; \
- const void __user *__cu_from; \
- long __cu_len; \
- \
- __cu_to = (to); \
- __cu_from = (from); \
- __cu_len = (n); \
- if (eva_kernel_access()) { \
- __cu_len = ___invoke_copy_in_kernel(__cu_to,__cu_from, \
- __cu_len); \
- } else { \
- if (likely(access_ok(VERIFY_READ, __cu_from, __cu_len) &&\
- access_ok(VERIFY_WRITE, __cu_to, __cu_len))) {\
- might_fault(); \
- __cu_len = ___invoke_copy_in_user(__cu_to, \
- __cu_from, \
- __cu_len); \
- } \
- } \
- __cu_len; \
-})
+static inline unsigned long
+raw_copy_in_user(void __user*to, const void __user *from, unsigned long n)
+{
+ if (eva_kernel_access())
+ return ___invoke_copy_in_kernel(to, from, n);
+ else
+ return ___invoke_copy_in_user(to, from, n);
+}
extern __kernel_size_t __bzero_kernel(void __user *addr, __kernel_size_t size);
extern __kernel_size_t __bzero(void __user *addr, __kernel_size_t size);
#define __NR_pkey_mprotect (__NR_Linux + 363)
#define __NR_pkey_alloc (__NR_Linux + 364)
#define __NR_pkey_free (__NR_Linux + 365)
+#define __NR_statx (__NR_Linux + 366)
/*
* Offset of the last Linux o32 flavoured syscall
*/
-#define __NR_Linux_syscalls 365
+#define __NR_Linux_syscalls 366
#endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
#define __NR_O32_Linux 4000
-#define __NR_O32_Linux_syscalls 365
+#define __NR_O32_Linux_syscalls 366
#if _MIPS_SIM == _MIPS_SIM_ABI64
#define __NR_pkey_mprotect (__NR_Linux + 323)
#define __NR_pkey_alloc (__NR_Linux + 324)
#define __NR_pkey_free (__NR_Linux + 325)
+#define __NR_statx (__NR_Linux + 326)
/*
* Offset of the last Linux 64-bit flavoured syscall
*/
-#define __NR_Linux_syscalls 325
+#define __NR_Linux_syscalls 326
#endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
#define __NR_64_Linux 5000
-#define __NR_64_Linux_syscalls 325
+#define __NR_64_Linux_syscalls 326
#if _MIPS_SIM == _MIPS_SIM_NABI32
#define __NR_pkey_mprotect (__NR_Linux + 327)
#define __NR_pkey_alloc (__NR_Linux + 328)
#define __NR_pkey_free (__NR_Linux + 329)
+#define __NR_statx (__NR_Linux + 330)
/*
* Offset of the last N32 flavoured syscall
*/
-#define __NR_Linux_syscalls 329
+#define __NR_Linux_syscalls 330
#endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
#define __NR_N32_Linux 6000
-#define __NR_N32_Linux_syscalls 329
+#define __NR_N32_Linux_syscalls 330
#endif /* _UAPI_ASM_UNISTD_H */
clockevent_set_clock(&jz4740_clockevent, clk_rate);
jz4740_clockevent.min_delta_ns = clockevent_delta2ns(100, &jz4740_clockevent);
+ jz4740_clockevent.min_delta_ticks = 100;
jz4740_clockevent.max_delta_ns = clockevent_delta2ns(0xffff, &jz4740_clockevent);
+ jz4740_clockevent.max_delta_ticks = 0xffff;
jz4740_clockevent.cpumask = cpumask_of(0);
clockevents_register_device(&jz4740_clockevent);
DEFINE(_THREAD_SIZE, THREAD_SIZE);
DEFINE(_THREAD_MASK, THREAD_MASK);
DEFINE(_IRQ_STACK_SIZE, IRQ_STACK_SIZE);
+ DEFINE(_IRQ_STACK_START, IRQ_STACK_START);
BLANK();
}
CLOCK_EVT_FEAT_ONESHOT;
clockevent_set_clock(cd, V_SCD_TIMER_FREQ);
cd->max_delta_ns = clockevent_delta2ns(0x7fffff, cd);
+ cd->max_delta_ticks = 0x7fffff;
cd->min_delta_ns = clockevent_delta2ns(2, cd);
+ cd->min_delta_ticks = 2;
cd->rating = 200;
cd->irq = irq;
cd->cpumask = cpumask_of(cpu);
cd->irq = irq;
clockevent_set_clock(cd, 32768);
cd->max_delta_ns = clockevent_delta2ns(0x7fffffff, cd);
+ cd->max_delta_ticks = 0x7fffffff;
cd->min_delta_ns = clockevent_delta2ns(0x300, cd);
+ cd->min_delta_ticks = 0x300;
cd->cpumask = cpumask_of(0);
clockevents_register_device(&ds1287_clockevent);
cd->rating = 200 + gt641xx_base_clock / 10000000;
clockevent_set_clock(cd, gt641xx_base_clock);
cd->max_delta_ns = clockevent_delta2ns(0x7fffffff, cd);
+ cd->max_delta_ticks = 0x7fffffff;
cd->min_delta_ns = clockevent_delta2ns(0x300, cd);
+ cd->min_delta_ticks = 0x300;
cd->cpumask = cpumask_of(0);
clockevents_register_device(>641xx_timer0_clockevent);
}
/* Sorted insert of 75th percentile into buf2 */
- for (k = 0; k < i; ++k) {
+ for (k = 0; k < i && k < ARRAY_SIZE(buf2); ++k) {
if (buf1[ARRAY_SIZE(buf1) - 1] < buf2[k]) {
l = min_t(unsigned int,
i, ARRAY_SIZE(buf2) - 1);
CLOCK_EVT_FEAT_ONESHOT;
clockevent_set_clock(cd, V_SCD_TIMER_FREQ);
cd->max_delta_ns = clockevent_delta2ns(0x7fffff, cd);
+ cd->max_delta_ticks = 0x7fffff;
cd->min_delta_ns = clockevent_delta2ns(2, cd);
+ cd->min_delta_ticks = 2;
cd->rating = 200;
cd->irq = irq;
cd->cpumask = cpumask_of(cpu);
clockevent_set_clock(cd, TIMER_CLK(imbusclk));
cd->max_delta_ns =
clockevent_delta2ns(0xffffffff >> (32 - TXX9_TIMER_BITS), cd);
+ cd->max_delta_ticks = 0xffffffff >> (32 - TXX9_TIMER_BITS);
cd->min_delta_ns = clockevent_delta2ns(0xf, cd);
+ cd->min_delta_ticks = 0xf;
cd->irq = irq;
cd->cpumask = cpumask_of(0),
clockevents_register_device(cd);
END(mips_cps_get_bootcfg)
LEAF(mips_cps_boot_vpes)
- PTR_L ta2, COREBOOTCFG_VPEMASK(a0)
+ lw ta2, COREBOOTCFG_VPEMASK(a0)
PTR_L ta3, COREBOOTCFG_VPECONFIG(a0)
#if defined(CONFIG_CPU_MIPSR6)
}
decode_configs(c);
- c->options |= MIPS_CPU_TLBINV | MIPS_CPU_LDPTE;
+ c->options |= MIPS_CPU_FTLB | MIPS_CPU_TLBINV | MIPS_CPU_LDPTE;
c->writecombine = _CACHE_UNCACHED_ACCELERATED;
break;
default:
else if ((prog_req.fr1 && prog_req.frdefault) ||
(prog_req.single && !prog_req.frdefault))
/* Make sure 64-bit MIPS III/IV/64R1 will not pick FR1 */
- state->overall_fp_mode = ((current_cpu_data.fpu_id & MIPS_FPIR_F64) &&
+ state->overall_fp_mode = ((raw_current_cpu_data.fpu_id & MIPS_FPIR_F64) &&
cpu_has_mips_r2_r6) ?
FP_FR1 : FP_FR0;
else if (prog_req.fr1)
beq t0, t1, 2f
/* Switch to IRQ stack */
- li t1, _IRQ_STACK_SIZE
+ li t1, _IRQ_STACK_START
PTR_ADD sp, t0, t1
+ /* Save task's sp on IRQ stack so that unwinding can follow it */
+ LONG_S s1, 0(sp)
2:
jal plat_irq_dispatch
beq t0, t1, 2f
/* Switch to IRQ stack */
- li t1, _IRQ_STACK_SIZE
+ li t1, _IRQ_STACK_START
PTR_ADD sp, t0, t1
+ /* Save task's sp on IRQ stack so that unwinding can follow it */
+ LONG_S s1, 0(sp)
2:
jalr v0
BUILD_HANDLER reserved reserved sti verbose /* others */
.align 5
- LEAF(handle_ri_rdhwr_vivt)
+ LEAF(handle_ri_rdhwr_tlbp)
.set push
.set noat
.set noreorder
.set pop
bltz k1, handle_ri /* slow path */
/* fall thru */
- END(handle_ri_rdhwr_vivt)
+ END(handle_ri_rdhwr_tlbp)
LEAF(handle_ri_rdhwr)
.set push
void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p)
{
int reg;
- struct thread_info *ti = task_thread_info(p);
- unsigned long ksp = (unsigned long)ti + THREAD_SIZE - 32;
- struct pt_regs *regs = (struct pt_regs *)ksp - 1;
#if (KGDB_GDB_REG_SIZE == 32)
u32 *ptr = (u32 *)gdb_regs;
#else
#endif
for (reg = 0; reg < 16; reg++)
- *(ptr++) = regs->regs[reg];
+ *(ptr++) = 0;
/* S0 - S7 */
- for (reg = 16; reg < 24; reg++)
- *(ptr++) = regs->regs[reg];
+ *(ptr++) = p->thread.reg16;
+ *(ptr++) = p->thread.reg17;
+ *(ptr++) = p->thread.reg18;
+ *(ptr++) = p->thread.reg19;
+ *(ptr++) = p->thread.reg20;
+ *(ptr++) = p->thread.reg21;
+ *(ptr++) = p->thread.reg22;
+ *(ptr++) = p->thread.reg23;
for (reg = 24; reg < 28; reg++)
*(ptr++) = 0;
/* GP, SP, FP, RA */
- for (reg = 28; reg < 32; reg++)
- *(ptr++) = regs->regs[reg];
-
- *(ptr++) = regs->cp0_status;
- *(ptr++) = regs->lo;
- *(ptr++) = regs->hi;
- *(ptr++) = regs->cp0_badvaddr;
- *(ptr++) = regs->cp0_cause;
- *(ptr++) = regs->cp0_epc;
+ *(ptr++) = (long)p;
+ *(ptr++) = p->thread.reg29;
+ *(ptr++) = p->thread.reg30;
+ *(ptr++) = p->thread.reg31;
+
+ *(ptr++) = p->thread.cp0_status;
+
+ /* lo, hi */
+ *(ptr++) = 0;
+ *(ptr++) = 0;
+
+ /*
+ * BadVAddr, Cause
+ * Ideally these would come from the last exception frame up the stack
+ * but that requires unwinding, otherwise we can't know much for sure.
+ */
+ *(ptr++) = 0;
+ *(ptr++) = 0;
+
+ /*
+ * PC
+ * use return address (RA), i.e. the moment after return from resume()
+ */
+ *(ptr++) = p->thread.reg31;
}
void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)
case lwl_op:
rt = regs->regs[MIPSInst_RT(inst)];
vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
- if (!access_ok(VERIFY_READ, vaddr, 4)) {
+ if (!access_ok(VERIFY_READ, (void __user *)vaddr, 4)) {
current->thread.cp0_baduaddr = vaddr;
err = SIGSEGV;
break;
case lwr_op:
rt = regs->regs[MIPSInst_RT(inst)];
vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
- if (!access_ok(VERIFY_READ, vaddr, 4)) {
+ if (!access_ok(VERIFY_READ, (void __user *)vaddr, 4)) {
current->thread.cp0_baduaddr = vaddr;
err = SIGSEGV;
break;
case swl_op:
rt = regs->regs[MIPSInst_RT(inst)];
vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
- if (!access_ok(VERIFY_WRITE, vaddr, 4)) {
+ if (!access_ok(VERIFY_WRITE, (void __user *)vaddr, 4)) {
current->thread.cp0_baduaddr = vaddr;
err = SIGSEGV;
break;
case swr_op:
rt = regs->regs[MIPSInst_RT(inst)];
vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
- if (!access_ok(VERIFY_WRITE, vaddr, 4)) {
+ if (!access_ok(VERIFY_WRITE, (void __user *)vaddr, 4)) {
current->thread.cp0_baduaddr = vaddr;
err = SIGSEGV;
break;
rt = regs->regs[MIPSInst_RT(inst)];
vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
- if (!access_ok(VERIFY_READ, vaddr, 8)) {
+ if (!access_ok(VERIFY_READ, (void __user *)vaddr, 8)) {
current->thread.cp0_baduaddr = vaddr;
err = SIGSEGV;
break;
rt = regs->regs[MIPSInst_RT(inst)];
vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
- if (!access_ok(VERIFY_READ, vaddr, 8)) {
+ if (!access_ok(VERIFY_READ, (void __user *)vaddr, 8)) {
current->thread.cp0_baduaddr = vaddr;
err = SIGSEGV;
break;
rt = regs->regs[MIPSInst_RT(inst)];
vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
- if (!access_ok(VERIFY_WRITE, vaddr, 8)) {
+ if (!access_ok(VERIFY_WRITE, (void __user *)vaddr, 8)) {
current->thread.cp0_baduaddr = vaddr;
err = SIGSEGV;
break;
rt = regs->regs[MIPSInst_RT(inst)];
vaddr = regs->regs[MIPSInst_RS(inst)] + MIPSInst_SIMM(inst);
- if (!access_ok(VERIFY_WRITE, vaddr, 8)) {
+ if (!access_ok(VERIFY_WRITE, (void __user *)vaddr, 8)) {
current->thread.cp0_baduaddr = vaddr;
err = SIGSEGV;
break;
err = SIGBUS;
break;
}
- if (!access_ok(VERIFY_READ, vaddr, 4)) {
+ if (!access_ok(VERIFY_READ, (void __user *)vaddr, 4)) {
current->thread.cp0_baduaddr = vaddr;
err = SIGBUS;
break;
err = SIGBUS;
break;
}
- if (!access_ok(VERIFY_WRITE, vaddr, 4)) {
+ if (!access_ok(VERIFY_WRITE, (void __user *)vaddr, 4)) {
current->thread.cp0_baduaddr = vaddr;
err = SIGBUS;
break;
err = SIGBUS;
break;
}
- if (!access_ok(VERIFY_READ, vaddr, 8)) {
+ if (!access_ok(VERIFY_READ, (void __user *)vaddr, 8)) {
current->thread.cp0_baduaddr = vaddr;
err = SIGBUS;
break;
err = SIGBUS;
break;
}
- if (!access_ok(VERIFY_WRITE, vaddr, 8)) {
+ if (!access_ok(VERIFY_WRITE, (void __user *)vaddr, 8)) {
current->thread.cp0_baduaddr = vaddr;
err = SIGBUS;
break;
HANDLE_COUNTER(0)
}
+#ifdef CONFIG_MIPS_PERF_SHARED_TC_COUNTERS
+ read_unlock(&pmuint_rwlock);
+#endif
+ resume_local_counters();
+
/*
* Do all the work for the pending perf events. We can do this
* in here because the performance counter interrupt is a regular
if (handled == IRQ_HANDLED)
irq_work_run();
-#ifdef CONFIG_MIPS_PERF_SHARED_TC_COUNTERS
- read_unlock(&pmuint_rwlock);
-#endif
- resume_local_counters();
return handled;
}
unsigned long pc,
unsigned long *ra)
{
+ unsigned long low, high, irq_stack_high;
struct mips_frame_info info;
unsigned long size, ofs;
+ struct pt_regs *regs;
int leaf;
- extern void ret_from_irq(void);
- extern void ret_from_exception(void);
if (!stack_page)
return 0;
/*
- * If we reached the bottom of interrupt context,
- * return saved pc in pt_regs.
+ * IRQ stacks start at IRQ_STACK_START
+ * task stacks at THREAD_SIZE - 32
*/
- if (pc == (unsigned long)ret_from_irq ||
- pc == (unsigned long)ret_from_exception) {
- struct pt_regs *regs;
- if (*sp >= stack_page &&
- *sp + sizeof(*regs) <= stack_page + THREAD_SIZE - 32) {
- regs = (struct pt_regs *)*sp;
- pc = regs->cp0_epc;
- if (!user_mode(regs) && __kernel_text_address(pc)) {
- *sp = regs->regs[29];
- *ra = regs->regs[31];
- return pc;
- }
+ low = stack_page;
+ if (!preemptible() && on_irq_stack(raw_smp_processor_id(), *sp)) {
+ high = stack_page + IRQ_STACK_START;
+ irq_stack_high = high;
+ } else {
+ high = stack_page + THREAD_SIZE - 32;
+ irq_stack_high = 0;
+ }
+
+ /*
+ * If we reached the top of the interrupt stack, start unwinding
+ * the interrupted task stack.
+ */
+ if (unlikely(*sp == irq_stack_high)) {
+ unsigned long task_sp = *(unsigned long *)*sp;
+
+ /*
+ * Check that the pointer saved in the IRQ stack head points to
+ * something within the stack of the current task
+ */
+ if (!object_is_on_stack((void *)task_sp))
+ return 0;
+
+ /*
+ * Follow pointer to tasks kernel stack frame where interrupted
+ * state was saved.
+ */
+ regs = (struct pt_regs *)task_sp;
+ pc = regs->cp0_epc;
+ if (!user_mode(regs) && __kernel_text_address(pc)) {
+ *sp = regs->regs[29];
+ *ra = regs->regs[31];
+ return pc;
}
return 0;
}
if (leaf < 0)
return 0;
- if (*sp < stack_page ||
- *sp + info.frame_size > stack_page + THREAD_SIZE - 32)
+ if (*sp < low || *sp + info.frame_size > high)
return 0;
if (leaf)
#include <linux/kernel.h>
#include <linux/libfdt.h>
#include <linux/of_fdt.h>
-#include <linux/sched.h>
+#include <linux/sched/task.h>
#include <linux/start_kernel.h>
#include <linux/string.h>
#include <linux/printk.h>
PTR sys_pkey_mprotect
PTR sys_pkey_alloc
PTR sys_pkey_free /* 4365 */
+ PTR sys_statx
PTR sys_pkey_mprotect
PTR sys_pkey_alloc
PTR sys_pkey_free /* 5325 */
+ PTR sys_statx
.size sys_call_table,.-sys_call_table
PTR sys_pkey_mprotect
PTR sys_pkey_alloc
PTR sys_pkey_free
+ PTR sys_statx /* 6330 */
.size sysn32_call_table,.-sysn32_call_table
PTR sys_pkey_mprotect
PTR sys_pkey_alloc
PTR sys_pkey_free /* 4365 */
+ PTR sys_statx
.size sys32_call_table,.-sys32_call_table
local_irq_disable();
idle_task_exit();
cpu = smp_processor_id();
+ core = cpu_data[cpu].core;
cpu_death = CPU_DEATH_POWER;
pr_debug("CPU%d going offline\n", cpu);
if (cpu_has_mipsmt || cpu_has_vp) {
- core = cpu_data[cpu].core;
-
/* Look for another online VPE within the core */
for_each_online_cpu(cpu_death_sibling) {
if (cpu_data[cpu_death_sibling].core != core)
if (unlikely(addr & 3))
return -EINVAL;
- if (unlikely(!access_ok(VERIFY_WRITE, addr, 4)))
+ if (unlikely(!access_ok(VERIFY_WRITE, (const void __user *)addr, 4)))
return -EINVAL;
if (cpu_has_llsc && R10000_LLSC_WAR) {
extern asmlinkage void handle_sys(void);
extern asmlinkage void handle_bp(void);
extern asmlinkage void handle_ri(void);
-extern asmlinkage void handle_ri_rdhwr_vivt(void);
+extern asmlinkage void handle_ri_rdhwr_tlbp(void);
extern asmlinkage void handle_ri_rdhwr(void);
extern asmlinkage void handle_cpu(void);
extern asmlinkage void handle_ov(void);
set_except_vector(EXCCODE_SYS, handle_sys);
set_except_vector(EXCCODE_BP, handle_bp);
- set_except_vector(EXCCODE_RI, rdhwr_noopt ? handle_ri :
- (cpu_has_vtag_icache ?
- handle_ri_rdhwr_vivt : handle_ri_rdhwr));
+
+ if (rdhwr_noopt)
+ set_except_vector(EXCCODE_RI, handle_ri);
+ else {
+ if (cpu_has_vtag_icache)
+ set_except_vector(EXCCODE_RI, handle_ri_rdhwr_tlbp);
+ else if (current_cpu_type() == CPU_LOONGSON3)
+ set_except_vector(EXCCODE_RI, handle_ri_rdhwr_tlbp);
+ else
+ set_except_vector(EXCCODE_RI, handle_ri_rdhwr);
+ }
+
set_except_vector(EXCCODE_CPU, handle_cpu);
set_except_vector(EXCCODE_OV, handle_ov);
set_except_vector(EXCCODE_TR, handle_tr);
goto sigbus;
if (IS_ENABLED(CONFIG_EVA)) {
- if (segment_eq(get_fs(), get_ds()))
+ if (uaccess_kernel())
LoadHW(addr, value, res);
else
LoadHWE(addr, value, res);
goto sigbus;
if (IS_ENABLED(CONFIG_EVA)) {
- if (segment_eq(get_fs(), get_ds()))
+ if (uaccess_kernel())
LoadW(addr, value, res);
else
LoadWE(addr, value, res);
goto sigbus;
if (IS_ENABLED(CONFIG_EVA)) {
- if (segment_eq(get_fs(), get_ds()))
+ if (uaccess_kernel())
LoadHWU(addr, value, res);
else
LoadHWUE(addr, value, res);
value = regs->regs[insn.i_format.rt];
if (IS_ENABLED(CONFIG_EVA)) {
- if (segment_eq(get_fs(), get_ds()))
+ if (uaccess_kernel())
StoreHW(addr, value, res);
else
StoreHWE(addr, value, res);
value = regs->regs[insn.i_format.rt];
if (IS_ENABLED(CONFIG_EVA)) {
- if (segment_eq(get_fs(), get_ds()))
+ if (uaccess_kernel())
StoreW(addr, value, res);
else
StoreWE(addr, value, res);
if (!np_xbar)
panic("Failed to load xbar nodes from devicetree");
- if (of_address_to_resource(np_pmu, 0, &res_xbar))
+ if (of_address_to_resource(np_xbar, 0, &res_xbar))
panic("Failed to get xbar resources");
if (!request_mem_region(res_xbar.start, resource_size(&res_xbar),
res_xbar.name))
LOADK t0, THREAD_BUADDR(t0) # t0 is just past last good address
nop
SUB len, AT, t0 # len number of uncopied bytes
- bnez t6, .Ldone\@ /* Skip the zeroing part if inatomic */
- /*
- * Here's where we rely on src and dst being incremented in tandem,
- * See (3) above.
- * dst += (fault addr - src) to put dst at first byte to clear
- */
- ADD dst, t0 # compute start address in a1
- SUB dst, src
- /*
- * Clear len bytes starting at dst. Can't call __bzero because it
- * might modify len. An inefficient loop for these rare times...
- */
- .set reorder /* DADDI_WAR */
- SUB src, len, 1
- beqz len, .Ldone\@
- .set noreorder
-1: sb zero, 0(dst)
- ADD dst, dst, 1
-#ifndef CONFIG_CPU_DADDI_WORKAROUNDS
- bnez src, 1b
- SUB src, src, 1
-#else
- .set push
- .set noat
- li v1, 1
- bnez src, 1b
- SUB src, src, v1
- .set pop
-#endif
jr ra
nop
-
#define SEXC(n) \
.set reorder; /* DADDI_WAR */ \
.Ls_exc_p ## n ## u\@: \
END(__rmemcpy)
/*
- * t6 is used as a flag to note inatomic mode.
- */
-LEAF(__copy_user_inatomic)
-EXPORT_SYMBOL(__copy_user_inatomic)
- b __copy_user_common
- li t6, 1
- END(__copy_user_inatomic)
-
-/*
* A combined memcpy/__copy_user
* __copy_user sets len to 0 for success; else to an upper bound of
* the number of uncopied bytes.
.L__memcpy:
FEXPORT(__copy_user)
EXPORT_SYMBOL(__copy_user)
- li t6, 0 /* not inatomic */
-__copy_user_common:
/* Legacy Mode, user <-> user */
__BUILD_COPY_USER LEGACY_MODE USEROP USEROP
* space
*/
-LEAF(__copy_user_inatomic_eva)
-EXPORT_SYMBOL(__copy_user_inatomic_eva)
- b __copy_from_user_common
- li t6, 1
- END(__copy_user_inatomic_eva)
-
/*
* __copy_from_user (EVA)
*/
LEAF(__copy_from_user_eva)
EXPORT_SYMBOL(__copy_from_user_eva)
- li t6, 0 /* not inatomic */
-__copy_from_user_common:
__BUILD_COPY_USER EVA_MODE USEROP KERNELOP
END(__copy_from_user_eva)
clockevent_set_clock(cd, mips_hpt_frequency);
cd->max_delta_ns = clockevent_delta2ns(0xffffff, cd);
+ cd->max_delta_ticks = 0xffffff;
cd->min_delta_ns = clockevent_delta2ns(0x000300, cd);
+ cd->min_delta_ticks = 0x000300;
cd->cpumask = cpumask_of(smp_processor_id());
clockevents_register_device(cd);
cd->cpumask = cpumask_of(cpu);
clockevent_set_clock(cd, MFGPT_TICK_RATE);
cd->max_delta_ns = clockevent_delta2ns(0xffff, cd);
+ cd->max_delta_ticks = 0xffff;
cd->min_delta_ns = clockevent_delta2ns(0xf, cd);
+ cd->min_delta_ticks = 0xf;
/* Enable MFGPT0 Comparator 2 Output to the Interrupt Mapper */
_wrmsr(DIVIL_MSR_REG(MFGPT_IRQ), 0, 0x100);
cd->cpumask = cpumask_of(cpu);
clockevent_set_clock(cd, HPET_FREQ);
cd->max_delta_ns = clockevent_delta2ns(0x7fffffff, cd);
+ cd->max_delta_ticks = 0x7fffffff;
cd->min_delta_ns = clockevent_delta2ns(HPET_MIN_PROG_DELTA, cd);
+ cd->min_delta_ticks = HPET_MIN_PROG_DELTA;
clockevents_register_device(cd);
setup_irq(HPET_T0_IRQ, &hpet_irq);
vcache_size = c->vcache.sets * c->vcache.ways * c->vcache.linesz;
c->vcache.waybit = 0;
+ c->vcache.waysize = vcache_size / c->vcache.ways;
pr_info("Unified victim cache %ldkB %s, linesize %d bytes.\n",
vcache_size >> 10, way_string[c->vcache.ways], c->vcache.linesz);
/* Loongson-3 has 4 cores, 1MB scache for each. scaches are shared */
scache_size *= 4;
c->scache.waybit = 0;
+ c->scache.waysize = scache_size / c->scache.ways;
pr_info("Unified secondary cache %ldkB %s, linesize %d bytes.\n",
scache_size >> 10, way_string[c->scache.ways], c->scache.linesz);
if (scache_size)
static void build_huge_handler_tail(u32 **p, struct uasm_reloc **r,
struct uasm_label **l,
unsigned int pte,
- unsigned int ptr)
+ unsigned int ptr,
+ unsigned int flush)
{
#ifdef CONFIG_SMP
UASM_i_SC(p, pte, 0, ptr);
#else
UASM_i_SW(p, pte, 0, ptr);
#endif
+ if (cpu_has_ftlb && flush) {
+ BUG_ON(!cpu_has_tlbinv);
+
+ UASM_i_MFC0(p, ptr, C0_ENTRYHI);
+ uasm_i_ori(p, ptr, ptr, MIPS_ENTRYHI_EHINV);
+ UASM_i_MTC0(p, ptr, C0_ENTRYHI);
+ build_tlb_write_entry(p, l, r, tlb_indexed);
+
+ uasm_i_xori(p, ptr, ptr, MIPS_ENTRYHI_EHINV);
+ UASM_i_MTC0(p, ptr, C0_ENTRYHI);
+ build_huge_update_entries(p, pte, ptr);
+ build_huge_tlb_write_entry(p, l, r, pte, tlb_random, 0);
+
+ return;
+ }
+
build_huge_update_entries(p, pte, ptr);
build_huge_tlb_write_entry(p, l, r, pte, tlb_indexed, 0);
}
uasm_l_tlbl_goaround2(&l, p);
}
uasm_i_ori(&p, wr.r1, wr.r1, (_PAGE_ACCESSED | _PAGE_VALID));
- build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2);
+ build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2, 1);
#endif
uasm_l_nopage_tlbl(&l, p);
build_tlb_probe_entry(&p);
uasm_i_ori(&p, wr.r1, wr.r1,
_PAGE_ACCESSED | _PAGE_MODIFIED | _PAGE_VALID | _PAGE_DIRTY);
- build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2);
+ build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2, 1);
#endif
uasm_l_nopage_tlbs(&l, p);
build_tlb_probe_entry(&p);
uasm_i_ori(&p, wr.r1, wr.r1,
_PAGE_ACCESSED | _PAGE_MODIFIED | _PAGE_VALID | _PAGE_DIRTY);
- build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2);
+ build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2, 0);
#endif
uasm_l_nopage_tlbm(&l, p);
{
int corehi_irq;
+ /*
+ * Preallocate the i8259's expected virq's here. Since irqchip_init()
+ * will probe the irqchips in hierarchial order, i8259 is probed last.
+ * If anything allocates a virq before the i8259 is probed, it will
+ * be given one of the i8259's expected range and consequently setup
+ * of the i8259 will fail.
+ */
+ WARN(irq_alloc_descs(I8259A_IRQ_BASE, I8259A_IRQ_BASE,
+ 16, numa_node_id()) < 0,
+ "Cannot reserve i8259 virqs at IRQ%d\n", I8259A_IRQ_BASE);
+
i8259_set_poll(mips_pcibios_iack);
irqchip_init();
#include <linux/i8253.h>
#include <linux/init.h>
#include <linux/kernel_stat.h>
+#include <linux/libfdt.h>
#include <linux/math64.h>
#include <linux/sched.h>
#include <linux/spinlock.h>
CMOS_WRITE(ctrl & ~RTC_SET, RTC_CONTROL);
}
+#ifdef CONFIG_CLKSRC_MIPS_GIC
+static u32 gic_frequency_dt;
+
+static struct property gic_frequency_prop = {
+ .name = "clock-frequency",
+ .length = sizeof(u32),
+ .value = &gic_frequency_dt,
+};
+
+static void update_gic_frequency_dt(void)
+{
+ struct device_node *node;
+
+ gic_frequency_dt = cpu_to_be32(gic_frequency);
+
+ node = of_find_compatible_node(NULL, NULL, "mti,gic-timer");
+ if (!node) {
+ pr_err("mti,gic-timer device node not found\n");
+ return;
+ }
+
+ if (of_update_property(node, &gic_frequency_prop) < 0)
+ pr_err("error updating gic frequency property\n");
+}
+
+#endif
+
void __init plat_time_init(void)
{
unsigned int prid = read_c0_prid() & (PRID_COMP_MASK | PRID_IMP_MASK);
printk("GIC frequency %d.%02d MHz\n", freq/1000000,
(freq%1000000)*100/1000000);
#ifdef CONFIG_CLKSRC_MIPS_GIC
- gic_clocksource_init(gic_frequency);
+ update_gic_frequency_dt();
+ clocksource_probe();
#endif
}
#endif
static inline int get_mem(unsigned long addr, unsigned long *result)
{
unsigned long *address = (unsigned long *) addr;
- if (!access_ok(VERIFY_READ, addr, sizeof(unsigned long)))
+ if (!access_ok(VERIFY_READ, address, sizeof(unsigned long)))
return -1;
if (__copy_from_user_inatomic(result, address, sizeof(unsigned long)))
return -3;
}
INIT_LIST_HEAD(&hose->list);
- list_add(&hose->list, &controllers);
+ list_add_tail(&hose->list, &controllers);
/*
* Do not panic here but later - this might happen before console init.
systick.dev.name = np->name;
clockevents_calc_mult_shift(&systick.dev, SYSTICK_FREQ, 60);
systick.dev.max_delta_ns = clockevent_delta2ns(0x7fff, &systick.dev);
+ systick.dev.max_delta_ticks = 0x7fff;
systick.dev.min_delta_ns = clockevent_delta2ns(0x3, &systick.dev);
+ systick.dev.min_delta_ticks = 0x3;
systick.dev.irq = irq_of_parse_and_map(np, 0);
if (!systick.dev.irq) {
pr_err("%s: request_irq failed", np->name);
static struct rt2880_pmx_func jtag_func[] = { FUNC("jtag", 0, 17, 5) };
static struct rt2880_pmx_func mdio_func[] = { FUNC("mdio", 0, 22, 2) };
static struct rt2880_pmx_func lna_a_func[] = { FUNC("lna a", 0, 32, 3) };
-static struct rt2880_pmx_func lna_g_func[] = { FUNC("lna a", 0, 35, 3) };
+static struct rt2880_pmx_func lna_g_func[] = { FUNC("lna g", 0, 35, 3) };
static struct rt2880_pmx_func pci_func[] = {
FUNC("pci-dev", 0, 40, 32),
FUNC("pci-host2", 1, 40, 32),
FUNC("pci-fnc", 3, 40, 32)
};
static struct rt2880_pmx_func ge1_func[] = { FUNC("ge1", 0, 72, 12) };
-static struct rt2880_pmx_func ge2_func[] = { FUNC("ge1", 0, 84, 12) };
+static struct rt2880_pmx_func ge2_func[] = { FUNC("ge2", 0, 84, 12) };
static struct rt2880_pmx_group rt3883_pinmux_data[] = {
GRP("i2c", i2c_func, 1, RT3883_GPIO_MODE_I2C),
cd->features = CLOCK_EVT_FEAT_ONESHOT;
clockevent_set_clock(cd, CYCLES_PER_SEC);
cd->max_delta_ns = clockevent_delta2ns(0xfffffffffffff, cd);
+ cd->max_delta_ticks = 0xfffffffffffff;
cd->min_delta_ns = clockevent_delta2ns(0x300, cd);
+ cd->min_delta_ticks = 0x300;
cd->rating = 200;
cd->irq = irq;
cd->cpumask = cpumask_of(cpu);
generic-y += barrier.h
generic-y += clkdev.h
generic-y += exec.h
+generic-y += extable.h
generic-y += irq_work.h
generic-y += mcs_spinlock.h
generic-y += mm-arch-hooks.h
/*
* User space memory access functions
*/
-#include <linux/thread_info.h>
#include <linux/kernel.h>
#include <asm/page.h>
-#include <asm/errno.h>
-
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
/*
* The fs value determines whether argument validity checking should be
#define access_ok(type, addr, size) (__range_ok((addr), (size)) == 0)
#define __access_ok(addr, size) (__range_ok((addr), (size)) == 0)
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue. No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path. This means when everything is well,
- * we don't even have to jump over them. Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry
-{
- unsigned long insn, fixup;
-};
-
-/* Returns 0 if exception not found and fixup otherwise. */
-extern int fixup_exception(struct pt_regs *regs);
+#include <asm/extable.h>
#define put_user(x, ptr) __put_user_check((x), (ptr), sizeof(*(ptr)))
#define get_user(x, ptr) __get_user_check((x), (ptr), sizeof(*(ptr)))
} \
} while (0)
-#define __copy_user_zeroing(to, from, size) \
-do { \
- if (size) { \
- void *__to = to; \
- const void *__from = from; \
- int w; \
- asm volatile( \
- "0: movbu (%0),%3;\n" \
- "1: movbu %3,(%1);\n" \
- " inc %0;\n" \
- " inc %1;\n" \
- " add -1,%2;\n" \
- " bne 0b;\n" \
- "2:\n" \
- " .section .fixup,\"ax\"\n" \
- "3:\n" \
- " mov %2,%0\n" \
- " clr %3\n" \
- "4: movbu %3,(%1);\n" \
- " inc %1;\n" \
- " add -1,%2;\n" \
- " bne 4b;\n" \
- " mov %0,%2\n" \
- " jmp 2b\n" \
- " .previous\n" \
- " .section __ex_table,\"a\"\n" \
- " .balign 4\n" \
- " .long 0b,3b\n" \
- " .long 1b,3b\n" \
- " .previous\n" \
- : "=a"(__from), "=a"(__to), "=r"(size), "=&r"(w)\
- : "0"(__from), "1"(__to), "2"(size) \
- : "cc", "memory"); \
- } \
-} while (0)
-
-/* We let the __ versions of copy_from/to_user inline, because they're often
- * used in fast paths and have only a small space overhead.
- */
-static inline
-unsigned long __generic_copy_from_user_nocheck(void *to, const void *from,
- unsigned long n)
-{
- __copy_user_zeroing(to, from, n);
- return n;
-}
-
-static inline
-unsigned long __generic_copy_to_user_nocheck(void *to, const void *from,
- unsigned long n)
+static inline unsigned long
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
{
__copy_user(to, from, n);
return n;
}
-
-#if 0
-#error "don't use - these macros don't increment to & from pointers"
-/* Optimize just a little bit when we know the size of the move. */
-#define __constant_copy_user(to, from, size) \
-do { \
- asm volatile( \
- " mov %0,a0;\n" \
- "0: movbu (%1),d3;\n" \
- "1: movbu d3,(%2);\n" \
- " add -1,a0;\n" \
- " bne 0b;\n" \
- "2:;" \
- ".section .fixup,\"ax\"\n" \
- "3: jmp 2b\n" \
- ".previous\n" \
- ".section __ex_table,\"a\"\n" \
- " .balign 4\n" \
- " .long 0b,3b\n" \
- " .long 1b,3b\n" \
- ".previous" \
- : \
- : "d"(size), "d"(to), "d"(from) \
- : "d3", "a0"); \
-} while (0)
-
-/* Optimize just a little bit when we know the size of the move. */
-#define __constant_copy_user_zeroing(to, from, size) \
-do { \
- asm volatile( \
- " mov %0,a0;\n" \
- "0: movbu (%1),d3;\n" \
- "1: movbu d3,(%2);\n" \
- " add -1,a0;\n" \
- " bne 0b;\n" \
- "2:;" \
- ".section .fixup,\"ax\"\n" \
- "3: jmp 2b\n" \
- ".previous\n" \
- ".section __ex_table,\"a\"\n" \
- " .balign 4\n" \
- " .long 0b,3b\n" \
- " .long 1b,3b\n" \
- ".previous" \
- : \
- : "d"(size), "d"(to), "d"(from) \
- : "d3", "a0"); \
-} while (0)
-
-static inline
-unsigned long __constant_copy_to_user(void *to, const void *from,
- unsigned long n)
-{
- if (access_ok(VERIFY_WRITE, to, n))
- __constant_copy_user(to, from, n);
- return n;
-}
-
-static inline
-unsigned long __constant_copy_from_user(void *to, const void *from,
- unsigned long n)
+static inline unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
{
- if (access_ok(VERIFY_READ, from, n))
- __constant_copy_user_zeroing(to, from, n);
- return n;
-}
-
-static inline
-unsigned long __constant_copy_to_user_nocheck(void *to, const void *from,
- unsigned long n)
-{
- __constant_copy_user(to, from, n);
- return n;
-}
-
-static inline
-unsigned long __constant_copy_from_user_nocheck(void *to, const void *from,
- unsigned long n)
-{
- __constant_copy_user_zeroing(to, from, n);
+ __copy_user(to, from, n);
return n;
}
-#endif
-
-extern unsigned long __generic_copy_to_user(void __user *, const void *,
- unsigned long);
-extern unsigned long __generic_copy_from_user(void *, const void __user *,
- unsigned long);
-
-#define __copy_to_user_inatomic(to, from, n) \
- __generic_copy_to_user_nocheck((to), (from), (n))
-#define __copy_from_user_inatomic(to, from, n) \
- __generic_copy_from_user_nocheck((to), (from), (n))
-
-#define __copy_to_user(to, from, n) \
-({ \
- might_fault(); \
- __copy_to_user_inatomic((to), (from), (n)); \
-})
-
-#define __copy_from_user(to, from, n) \
-({ \
- might_fault(); \
- __copy_from_user_inatomic((to), (from), (n)); \
-})
-
-
-#define copy_to_user(to, from, n) __generic_copy_to_user((to), (from), (n))
-#define copy_from_user(to, from, n) __generic_copy_from_user((to), (from), (n))
extern long strncpy_from_user(char *dst, const char __user *src, long count);
extern long __strncpy_from_user(char *dst, const char __user *src, long count);
/* Calculate the min / max delta */
cd->max_delta_ns = clockevent_delta2ns(TMJCBR_MAX, cd);
+ cd->max_delta_ticks = TMJCBR_MAX;
cd->min_delta_ns = clockevent_delta2ns(100, cd);
+ cd->min_delta_ticks = 100;
cd->rating = 200;
cd->cpumask = cpumask_of(smp_processor_id());
EXPORT_SYMBOL(__strncpy_from_user);
EXPORT_SYMBOL(clear_user);
EXPORT_SYMBOL(__clear_user);
-EXPORT_SYMBOL(__generic_copy_from_user);
-EXPORT_SYMBOL(__generic_copy_to_user);
EXPORT_SYMBOL(strnlen_user);
extern u64 __ashrdi3(u64, unsigned);
*/
#include <linux/uaccess.h>
-unsigned long
-__generic_copy_to_user(void *to, const void *from, unsigned long n)
-{
- if (access_ok(VERIFY_WRITE, to, n))
- __copy_user(to, from, n);
- return n;
-}
-
-unsigned long
-__generic_copy_from_user(void *to, const void *from, unsigned long n)
-{
- if (access_ok(VERIFY_READ, from, n))
- __copy_user_zeroing(to, from, n);
- else
- memset(to, 0, n);
- return n;
-}
-
/*
* Copy a null terminated string from userspace.
*/
generic-y += emergency-restart.h
generic-y += errno.h
generic-y += exec.h
+generic-y += extable.h
generic-y += fb.h
generic-y += fcntl.h
generic-y += ftrace.h
#ifndef _ASM_NIOS2_UACCESS_H
#define _ASM_NIOS2_UACCESS_H
-#include <linux/errno.h>
-#include <linux/thread_info.h>
#include <linux/string.h>
#include <asm/page.h>
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue. No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path. This means when everything is well,
- * we don't even have to jump over them. Further, they do not intrude
- * on our cache or tlb entries.
- */
-struct exception_table_entry {
- unsigned long insn;
- unsigned long fixup;
-};
-
-extern int fixup_exception(struct pt_regs *regs);
+#include <asm/extable.h>
/*
* Segment stuff
return __clear_user(to, n);
}
-extern long __copy_from_user(void *to, const void __user *from,
- unsigned long n);
-extern long __copy_to_user(void __user *to, const void *from, unsigned long n);
-
-static inline long copy_from_user(void *to, const void __user *from,
- unsigned long n)
-{
- unsigned long res = n;
- if (access_ok(VERIFY_READ, from, n))
- res = __copy_from_user(to, from, n);
- if (unlikely(res))
- memset(to + (n - res), 0, res);
- return res;
-}
-
-static inline long copy_to_user(void __user *to, const void *from,
- unsigned long n)
-{
- if (!access_ok(VERIFY_WRITE, to, n))
- return n;
- return __copy_to_user(to, from, n);
-}
+extern unsigned long
+raw_copy_from_user(void *to, const void __user *from, unsigned long n);
+extern unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n);
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
extern long strncpy_from_user(char *__to, const char __user *__from,
long __len);
extern long strnlen_user(const char __user *s, long n);
-#define __copy_from_user_inatomic __copy_from_user
-#define __copy_to_user_inatomic __copy_to_user
-
/* Optimized macros */
#define __get_user_asm(val, insn, addr, err) \
{ \
#include <linux/export.h>
#include <linux/uaccess.h>
-asm(".global __copy_from_user\n"
- " .type __copy_from_user, @function\n"
- "__copy_from_user:\n"
+asm(".global raw_copy_from_user\n"
+ " .type raw_copy_from_user, @function\n"
+ "raw_copy_from_user:\n"
" movi r2,7\n"
" mov r3,r4\n"
" bge r2,r6,1f\n"
".word 7b,13b\n"
".previous\n"
);
-EXPORT_SYMBOL(__copy_from_user);
+EXPORT_SYMBOL(raw_copy_from_user);
asm(
- " .global __copy_to_user\n"
- " .type __copy_to_user, @function\n"
- "__copy_to_user:\n"
+ " .global raw_copy_to_user\n"
+ " .type raw_copy_to_user, @function\n"
+ "raw_copy_to_user:\n"
" movi r2,7\n"
" mov r3,r4\n"
" bge r2,r6,1f\n"
".word 11b,13b\n"
".word 12b,13b\n"
".previous\n");
-EXPORT_SYMBOL(__copy_to_user);
+EXPORT_SYMBOL(raw_copy_to_user);
long strncpy_from_user(char *__to, const char __user *__from, long __len)
{
generic-y += emergency-restart.h
generic-y += errno.h
generic-y += exec.h
+generic-y += extable.h
generic-y += fb.h
generic-y += fcntl.h
generic-y += ftrace.h
/*
* User space memory access functions
*/
-#include <linux/errno.h>
-#include <linux/thread_info.h>
#include <linux/prefetch.h>
#include <linux/string.h>
#include <asm/page.h>
-
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
+#include <asm/extable.h>
/*
* The fs value determines whether argument validity checking should be
__range_ok((unsigned long)addr, (unsigned long)size)
/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue. No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path. This means when everything is well,
- * we don't even have to jump over them. Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry {
- unsigned long insn, fixup;
-};
-
-/*
* These are the main single-value transfer routines. They automatically
* use the right size if we just have the right pointer type.
*
extern unsigned long __must_check
__copy_tofrom_user(void *to, const void *from, unsigned long size);
-
-#define __copy_from_user(to, from, size) \
- __copy_tofrom_user(to, from, size)
-#define __copy_to_user(to, from, size) \
- __copy_tofrom_user(to, from, size)
-
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
-
static inline unsigned long
-copy_from_user(void *to, const void *from, unsigned long n)
+raw_copy_from_user(void *to, const void __user *from, unsigned long size)
{
- unsigned long res = n;
-
- if (likely(access_ok(VERIFY_READ, from, n)))
- res = __copy_tofrom_user(to, from, n);
- if (unlikely(res))
- memset(to + (n - res), 0, res);
- return res;
+ return __copy_tofrom_user(to, (__force const void *)from, size);
}
-
static inline unsigned long
-copy_to_user(void *to, const void *from, unsigned long n)
+raw_copy_to_user(void *to, const void __user *from, unsigned long size)
{
- if (likely(access_ok(VERIFY_WRITE, to, n)))
- n = __copy_tofrom_user(to, from, n);
- return n;
+ return __copy_tofrom_user((__force void *)to, from, size);
}
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
extern unsigned long __clear_user(void *addr, unsigned long size);
}
#define user_addr_max() \
- (segment_eq(get_fs(), USER_DS) ? TASK_SIZE : ~0UL)
+ (uaccess_kernel() ? ~0UL : TASK_SIZE)
extern long strncpy_from_user(char *dest, const char __user *src, long count);
select SYSCTL_ARCH_UNALIGN_ALLOW
select SYSCTL_EXCEPTION_TRACE
select HAVE_MOD_ARCH_SPECIFIC
- select HAVE_ARCH_HARDENED_USERCOPY
select VIRT_TO_BUS
select MODULES_USE_ELF_RELA
select CLONE_BACKWARDS
/* futex.c wants to do a cmpxchg_inatomic on kernel NULL, which is
* our gateway page, and causes no end of trouble...
*/
- if (segment_eq(KERNEL_DS, get_fs()) && !uaddr)
+ if (uaccess_kernel() && !uaddr)
return -EFAULT;
if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
*/
#include <asm/page.h>
#include <asm/cache.h>
-#include <asm/errno.h>
#include <asm-generic/uaccess-unaligned.h>
#include <linux/bug.h>
#include <linux/string.h>
-#include <linux/thread_info.h>
-
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
#define KERNEL_DS ((mm_segment_t){0})
#define USER_DS ((mm_segment_t){1})
#define get_user __get_user
#if !defined(CONFIG_64BIT)
-#define LDD_USER(ptr) __get_user_asm64(ptr)
+#define LDD_USER(val, ptr) __get_user_asm64(val, ptr)
#define STD_USER(x, ptr) __put_user_asm64(x, ptr)
#else
-#define LDD_USER(ptr) __get_user_asm("ldd", ptr)
+#define LDD_USER(val, ptr) __get_user_asm(val, "ldd", ptr)
#define STD_USER(x, ptr) __put_user_asm("std", x, ptr)
#endif
" mtsp %0,%%sr2\n\t" \
: : "r"(get_fs()) : )
-#define __get_user(x, ptr) \
-({ \
- register long __gu_err __asm__ ("r8") = 0; \
- register long __gu_val; \
- \
- load_sr2(); \
- switch (sizeof(*(ptr))) { \
- case 1: __get_user_asm("ldb", ptr); break; \
- case 2: __get_user_asm("ldh", ptr); break; \
- case 4: __get_user_asm("ldw", ptr); break; \
- case 8: LDD_USER(ptr); break; \
- default: BUILD_BUG(); break; \
- } \
- \
- (x) = (__force __typeof__(*(ptr))) __gu_val; \
- __gu_err; \
+#define __get_user_internal(val, ptr) \
+({ \
+ register long __gu_err __asm__ ("r8") = 0; \
+ \
+ switch (sizeof(*(ptr))) { \
+ case 1: __get_user_asm(val, "ldb", ptr); break; \
+ case 2: __get_user_asm(val, "ldh", ptr); break; \
+ case 4: __get_user_asm(val, "ldw", ptr); break; \
+ case 8: LDD_USER(val, ptr); break; \
+ default: BUILD_BUG(); \
+ } \
+ \
+ __gu_err; \
+})
+
+#define __get_user(val, ptr) \
+({ \
+ load_sr2(); \
+ __get_user_internal(val, ptr); \
})
-#define __get_user_asm(ldx, ptr) \
+#define __get_user_asm(val, ldx, ptr) \
+{ \
+ register long __gu_val; \
+ \
__asm__("1: " ldx " 0(%%sr2,%2),%0\n" \
"9:\n" \
ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \
: "=r"(__gu_val), "=r"(__gu_err) \
- : "r"(ptr), "1"(__gu_err));
+ : "r"(ptr), "1"(__gu_err)); \
+ \
+ (val) = (__force __typeof__(*(ptr))) __gu_val; \
+}
#if !defined(CONFIG_64BIT)
-#define __get_user_asm64(ptr) \
+#define __get_user_asm64(val, ptr) \
+{ \
+ union { \
+ unsigned long long l; \
+ __typeof__(*(ptr)) t; \
+ } __gu_tmp; \
+ \
__asm__(" copy %%r0,%R0\n" \
"1: ldw 0(%%sr2,%2),%0\n" \
"2: ldw 4(%%sr2,%2),%R0\n" \
"9:\n" \
ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b) \
ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b) \
- : "=r"(__gu_val), "=r"(__gu_err) \
- : "r"(ptr), "1"(__gu_err));
+ : "=&r"(__gu_tmp.l), "=r"(__gu_err) \
+ : "r"(ptr), "1"(__gu_err)); \
+ \
+ (val) = __gu_tmp.t; \
+}
#endif /* !defined(CONFIG_64BIT) */
-#define __put_user(x, ptr) \
+#define __put_user_internal(x, ptr) \
({ \
register long __pu_err __asm__ ("r8") = 0; \
__typeof__(*(ptr)) __x = (__typeof__(*(ptr)))(x); \
\
- load_sr2(); \
switch (sizeof(*(ptr))) { \
- case 1: __put_user_asm("stb", __x, ptr); break; \
- case 2: __put_user_asm("sth", __x, ptr); break; \
- case 4: __put_user_asm("stw", __x, ptr); break; \
- case 8: STD_USER(__x, ptr); break; \
- default: BUILD_BUG(); break; \
- } \
+ case 1: __put_user_asm("stb", __x, ptr); break; \
+ case 2: __put_user_asm("sth", __x, ptr); break; \
+ case 4: __put_user_asm("stw", __x, ptr); break; \
+ case 8: STD_USER(__x, ptr); break; \
+ default: BUILD_BUG(); \
+ } \
\
__pu_err; \
})
+#define __put_user(x, ptr) \
+({ \
+ load_sr2(); \
+ __put_user_internal(x, ptr); \
+})
+
+
/*
* The "__put_user/kernel_asm()" macros tell gcc they read from memory
* instead of writing. This is because they do not write to any memory
* Complex access routines -- external declarations
*/
-extern unsigned long lcopy_to_user(void __user *, const void *, unsigned long);
-extern unsigned long lcopy_from_user(void *, const void __user *, unsigned long);
-extern unsigned long lcopy_in_user(void __user *, const void __user *, unsigned long);
extern long strncpy_from_user(char *, const char __user *, long);
extern unsigned lclear_user(void __user *, unsigned long);
extern long lstrnlen_user(const char __user *, long);
#define clear_user lclear_user
#define __clear_user lclear_user
-unsigned long __must_check __copy_to_user(void __user *dst, const void *src,
- unsigned long len);
-unsigned long __must_check __copy_from_user(void *dst, const void __user *src,
- unsigned long len);
-unsigned long copy_in_user(void __user *dst, const void __user *src,
- unsigned long len);
-#define __copy_in_user copy_in_user
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
-
-extern void __compiletime_error("usercopy buffer size is too small")
-__bad_copy_user(void);
-
-static inline void copy_user_overflow(int size, unsigned long count)
-{
- WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
-}
-
-static __always_inline unsigned long __must_check
-copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- int sz = __compiletime_object_size(to);
- unsigned long ret = n;
-
- if (likely(sz < 0 || sz >= n)) {
- check_object_size(to, n, false);
- ret = __copy_from_user(to, from, n);
- } else if (!__builtin_constant_p(n))
- copy_user_overflow(sz, n);
- else
- __bad_copy_user();
-
- if (unlikely(ret))
- memset(to + (n - ret), 0, ret);
-
- return ret;
-}
-
-static __always_inline unsigned long __must_check
-copy_to_user(void __user *to, const void *from, unsigned long n)
-{
- int sz = __compiletime_object_size(from);
-
- if (likely(sz < 0 || sz >= n)) {
- check_object_size(from, n, true);
- n = __copy_to_user(to, from, n);
- } else if (!__builtin_constant_p(n))
- copy_user_overflow(sz, n);
- else
- __bad_copy_user();
-
- return n;
-}
+unsigned long __must_check raw_copy_to_user(void __user *dst, const void *src,
+ unsigned long len);
+unsigned long __must_check raw_copy_from_user(void *dst, const void __user *src,
+ unsigned long len);
+unsigned long __must_check raw_copy_in_user(void __user *dst, const void __user *src,
+ unsigned long len);
+#define INLINE_COPY_TO_USER
+#define INLINE_COPY_FROM_USER
struct pt_regs;
int fixup_exception(struct pt_regs *regs);
add dst,len,end
/* short copy with less than 16 bytes? */
- cmpib,>>=,n 15,len,.Lbyte_loop
+ cmpib,COND(>>=),n 15,len,.Lbyte_loop
/* same alignment? */
xor src,dst,t0
/* loop until we are 64-bit aligned */
.Lalign_loop64:
extru dst,31,3,t1
- cmpib,=,n 0,t1,.Lcopy_loop_16
+ cmpib,=,n 0,t1,.Lcopy_loop_16_start
20: ldb,ma 1(srcspc,src),t1
21: stb,ma t1,1(dstspc,dst)
b .Lalign_loop64
ASM_EXCEPTIONTABLE_ENTRY(20b,.Lcopy_done)
ASM_EXCEPTIONTABLE_ENTRY(21b,.Lcopy_done)
+.Lcopy_loop_16_start:
ldi 31,t0
.Lcopy_loop_16:
cmpb,COND(>>=),n t0,len,.Lword_loop
/* loop until we are 32-bit aligned */
.Lalign_loop32:
extru dst,31,2,t1
- cmpib,=,n 0,t1,.Lcopy_loop_4
+ cmpib,=,n 0,t1,.Lcopy_loop_8
20: ldb,ma 1(srcspc,src),t1
21: stb,ma t1,1(dstspc,dst)
b .Lalign_loop32
ASM_EXCEPTIONTABLE_ENTRY(21b,.Lcopy_done)
-.Lcopy_loop_4:
+.Lcopy_loop_8:
cmpib,COND(>>=),n 15,len,.Lbyte_loop
10: ldw 0(srcspc,src),t1
ASM_EXCEPTIONTABLE_ENTRY(16b,.Lcopy_done)
ASM_EXCEPTIONTABLE_ENTRY(17b,.Lcopy_done)
- b .Lcopy_loop_4
+ b .Lcopy_loop_8
ldo -16(len),len
.Lbyte_loop:
.Lunaligned_copy:
/* align until dst is 32bit-word-aligned */
extru dst,31,2,t1
- cmpib,COND(=),n 0,t1,.Lcopy_dstaligned
+ cmpib,=,n 0,t1,.Lcopy_dstaligned
20: ldb 0(srcspc,src),t1
ldo 1(src),src
21: stb,ma t1,1(dstspc,dst)
cmpiclr,<> 1,t0,%r0
b,n .Lcase1
.Lcase0:
- cmpb,= %r0,len,.Lcda_finish
+ cmpb,COND(=) %r0,len,.Lcda_finish
nop
1: ldw,ma 4(srcspc,src), a3
1: ldw,ma 4(srcspc,src), a3
ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
ldo -1(len),len
- cmpb,=,n %r0,len,.Ldo0
+ cmpb,COND(=),n %r0,len,.Ldo0
.Ldo4:
1: ldw,ma 4(srcspc,src), a0
ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
1: stw,ma t0, 4(dstspc,dst)
ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcopy_done)
ldo -4(len),len
- cmpb,<> %r0,len,.Ldo4
+ cmpb,COND(<>) %r0,len,.Ldo4
nop
.Ldo0:
shrpw a2, a3, %sar, t0
/* fault exception fixup handlers: */
#ifdef CONFIG_64BIT
.Lcopy16_fault:
-10: b .Lcopy_done
- std,ma t1,8(dstspc,dst)
+ b .Lcopy_done
+10: std,ma t1,8(dstspc,dst)
ASM_EXCEPTIONTABLE_ENTRY(10b,.Lcopy_done)
#endif
.Lcopy8_fault:
-10: b .Lcopy_done
- stw,ma t1,4(dstspc,dst)
+ b .Lcopy_done
+10: stw,ma t1,4(dstspc,dst)
ASM_EXCEPTIONTABLE_ENTRY(10b,.Lcopy_done)
.exit
DECLARE_PER_CPU(struct exception_data, exception_data);
-#define get_user_space() (segment_eq(get_fs(), KERNEL_DS) ? 0 : mfsp(3))
+#define get_user_space() (uaccess_kernel() ? 0 : mfsp(3))
#define get_kernel_space() (0)
/* Returns 0 for success, otherwise, returns number of bytes not transferred. */
extern unsigned long pa_memcpy(void *dst, const void *src,
unsigned long len);
-unsigned long __copy_to_user(void __user *dst, const void *src,
- unsigned long len)
+unsigned long raw_copy_to_user(void __user *dst, const void *src,
+ unsigned long len)
{
mtsp(get_kernel_space(), 1);
mtsp(get_user_space(), 2);
return pa_memcpy((void __force *)dst, src, len);
}
-EXPORT_SYMBOL(__copy_to_user);
+EXPORT_SYMBOL(raw_copy_to_user);
-unsigned long __copy_from_user(void *dst, const void __user *src,
+unsigned long raw_copy_from_user(void *dst, const void __user *src,
unsigned long len)
{
mtsp(get_user_space(), 1);
mtsp(get_kernel_space(), 2);
return pa_memcpy(dst, (void __force *)src, len);
}
-EXPORT_SYMBOL(__copy_from_user);
+EXPORT_SYMBOL(raw_copy_from_user);
-unsigned long copy_in_user(void __user *dst, const void __user *src, unsigned long len)
+unsigned long raw_copy_in_user(void __user *dst, const void __user *src, unsigned long len)
{
mtsp(get_user_space(), 1);
mtsp(get_user_space(), 2);
return dst;
}
-EXPORT_SYMBOL(copy_in_user);
+EXPORT_SYMBOL(raw_copy_in_user);
EXPORT_SYMBOL(memcpy);
long probe_kernel_read(void *dst, const void *src, size_t size)
select GENERIC_STRNLEN_USER
select GENERIC_TIME_VSYSCALL_OLD
select HAVE_ARCH_AUDITSYSCALL
- select HAVE_ARCH_HARDENED_USERCOPY
select HAVE_ARCH_JUMP_LABEL
select HAVE_ARCH_KGDB
select HAVE_ARCH_SECCOMP_FILTER
CONFIG_DMADEVICES=y
CONFIG_E1000E=y
CONFIG_E1000=y
-CONFIG_EDAC_MM_EDAC=y
-CONFIG_EDAC_MPC85XX=y
CONFIG_EDAC=y
+CONFIG_EDAC_MPC85XX=y
CONFIG_EEPROM_AT24=y
CONFIG_EEPROM_LEGACY=y
CONFIG_FB_FSL_DIU=y
CONFIG_USB_OHCI_HCD_PPC_OF_LE=y
CONFIG_USB_STORAGE=y
CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
CONFIG_EDAC_MPC85XX=y
CONFIG_RTC_CLASS=y
# CONFIG_RTC_INTF_PROC is not set
CONFIG_LEDS_TRIGGER_TIMER=y
CONFIG_LEDS_TRIGGER_HEARTBEAT=y
CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_DS1307=y
CONFIG_RTC_DRV_CMOS=y
CONFIG_INFINIBAND_IPOIB=m
CONFIG_INFINIBAND_IPOIB_DEBUG_DATA=y
CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
CONFIG_EDAC_CELL=y
CONFIG_UIO=m
CONFIG_EXT2_FS=y
CONFIG_USB_SL811_HCD=y
CONFIG_USB_STORAGE=y
CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
CONFIG_EDAC_PASEMI=y
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_DS1307=y
CONFIG_INFINIBAND_SRP=m
CONFIG_INFINIBAND_ISER=m
CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
CONFIG_EDAC_PASEMI=y
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_DS1307=y
CONFIG_INFINIBAND_IPOIB=m
CONFIG_INFINIBAND_ISER=m
CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_DS1307=y
CONFIG_FS_DAX=y
CONFIG_LEDS_TRIGGER_DEFAULT_ON=m
CONFIG_ACCESSIBILITY=y
CONFIG_A11Y_BRAILLE_CONSOLE=y
-CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=m
+CONFIG_EDAC=m
CONFIG_RTC_CLASS=y
# CONFIG_RTC_HCTOSYS is not set
CONFIG_RTC_DRV_DS1307=m
}
if (len & ~VMX_ALIGN_MASK) {
+ preempt_disable();
pagefault_disable();
enable_kernel_altivec();
crc = __crc32c_vpmsum(crc, p, len & ~VMX_ALIGN_MASK);
+ disable_kernel_altivec();
pagefault_enable();
+ preempt_enable();
}
tail = len & VMX_ALIGN_MASK;
mtctr reg; \
bctr
-#define BRANCH_LINK_TO_FAR(reg, label) \
- __LOAD_FAR_HANDLER(reg, label); \
- mtctr reg; \
+#define BRANCH_LINK_TO_FAR(label) \
+ __LOAD_FAR_HANDLER(r12, label); \
+ mtctr r12; \
bctrl
/*
#define BRANCH_TO_COMMON(reg, label) \
b label
-#define BRANCH_LINK_TO_FAR(reg, label) \
+#define BRANCH_LINK_TO_FAR(label) \
bl label
#define BRANCH_TO_KVM(reg, label) \
--- /dev/null
+#ifndef _ARCH_POWERPC_EXTABLE_H
+#define _ARCH_POWERPC_EXTABLE_H
+
+/*
+ * The exception table consists of pairs of relative addresses: the first is
+ * the address of an instruction that is allowed to fault, and the second is
+ * the address at which the program should continue. No registers are
+ * modified, so it is entirely up to the continuation code to figure out what
+ * to do.
+ *
+ * All the routines below use bits of fixup code that are out of line with the
+ * main instruction path. This means when everything is well, we don't even
+ * have to jump over them. Further, they do not intrude on our cache or tlb
+ * entries.
+ */
+
+#define ARCH_HAS_RELATIVE_EXTABLE
+
+struct exception_table_entry {
+ int insn;
+ int fixup;
+};
+
+static inline unsigned long extable_fixup(const struct exception_table_entry *x)
+{
+ return (unsigned long)&x->fixup + x->fixup;
+}
+
+#endif
#ifndef _ARCH_POWERPC_UACCESS_H
#define _ARCH_POWERPC_UACCESS_H
-#ifdef __KERNEL__
-#ifndef __ASSEMBLY__
-
-#include <linux/sched.h>
-#include <linux/errno.h>
#include <asm/asm-compat.h>
#include <asm/ppc_asm.h>
#include <asm/processor.h>
#include <asm/page.h>
-
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
+#include <asm/extable.h>
/*
* The fs value determines whether argument validity checking should be
__access_ok((__force unsigned long)(addr), (size), get_fs()))
/*
- * The exception table consists of pairs of relative addresses: the first is
- * the address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue. No registers are
- * modified, so it is entirely up to the continuation code to figure out what
- * to do.
- *
- * All the routines below use bits of fixup code that are out of line with the
- * main instruction path. This means when everything is well, we don't even
- * have to jump over them. Further, they do not intrude on our cache or tlb
- * entries.
- */
-
-#define ARCH_HAS_RELATIVE_EXTABLE
-
-struct exception_table_entry {
- int insn;
- int fixup;
-};
-
-static inline unsigned long extable_fixup(const struct exception_table_entry *x)
-{
- return (unsigned long)&x->fixup + x->fixup;
-}
-
-/*
* These are the main single-value transfer routines. They automatically
* use the right size if we just have the right pointer type.
*
#ifndef __powerpc64__
-static inline unsigned long copy_from_user(void *to,
- const void __user *from, unsigned long n)
-{
- if (likely(access_ok(VERIFY_READ, from, n))) {
- check_object_size(to, n, false);
- return __copy_tofrom_user((__force void __user *)to, from, n);
- }
- memset(to, 0, n);
- return n;
-}
-
-static inline unsigned long copy_to_user(void __user *to,
- const void *from, unsigned long n)
-{
- if (access_ok(VERIFY_WRITE, to, n)) {
- check_object_size(from, n, true);
- return __copy_tofrom_user(to, (__force void __user *)from, n);
- }
- return n;
-}
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
#else /* __powerpc64__ */
-#define __copy_in_user(to, from, size) \
- __copy_tofrom_user((to), (from), (size))
-
-extern unsigned long copy_from_user(void *to, const void __user *from,
- unsigned long n);
-extern unsigned long copy_to_user(void __user *to, const void *from,
- unsigned long n);
-extern unsigned long copy_in_user(void __user *to, const void __user *from,
- unsigned long n);
-
+static inline unsigned long
+raw_copy_in_user(void __user *to, const void __user *from, unsigned long n)
+{
+ return __copy_tofrom_user(to, from, n);
+}
#endif /* __powerpc64__ */
-static inline unsigned long __copy_from_user_inatomic(void *to,
+static inline unsigned long raw_copy_from_user(void *to,
const void __user *from, unsigned long n)
{
if (__builtin_constant_p(n) && (n <= 8)) {
return 0;
}
- check_object_size(to, n, false);
-
return __copy_tofrom_user((__force void __user *)to, from, n);
}
-static inline unsigned long __copy_to_user_inatomic(void __user *to,
+static inline unsigned long raw_copy_to_user(void __user *to,
const void *from, unsigned long n)
{
if (__builtin_constant_p(n) && (n <= 8)) {
return 0;
}
- check_object_size(from, n, true);
-
return __copy_tofrom_user(to, (__force const void __user *)from, n);
}
-static inline unsigned long __copy_from_user(void *to,
- const void __user *from, unsigned long size)
-{
- might_fault();
- return __copy_from_user_inatomic(to, from, size);
-}
-
-static inline unsigned long __copy_to_user(void __user *to,
- const void *from, unsigned long size)
-{
- might_fault();
- return __copy_to_user_inatomic(to, from, size);
-}
-
extern unsigned long __clear_user(void __user *addr, unsigned long size);
static inline unsigned long clear_user(void __user *addr, unsigned long size)
extern __must_check long strlen_user(const char __user *str);
extern __must_check long strnlen_user(const char __user *str, long n);
-#endif /* __ASSEMBLY__ */
-#endif /* __KERNEL__ */
-
#endif /* _ARCH_POWERPC_UACCESS_H */
nb = aligninfo[instr].len;
flags = aligninfo[instr].flags;
- /* ldbrx/stdbrx overlap lfs/stfs in the DSISR unfortunately */
- if (IS_XFORM(instruction) && ((instruction >> 1) & 0x3ff) == 532) {
- nb = 8;
- flags = LD+SW;
- } else if (IS_XFORM(instruction) &&
- ((instruction >> 1) & 0x3ff) == 660) {
- nb = 8;
- flags = ST+SW;
+ /*
+ * Handle some cases which give overlaps in the DSISR values.
+ */
+ if (IS_XFORM(instruction)) {
+ switch (get_xop(instruction)) {
+ case 532: /* ldbrx */
+ nb = 8;
+ flags = LD+SW;
+ break;
+ case 660: /* stdbrx */
+ nb = 8;
+ flags = ST+SW;
+ break;
+ case 20: /* lwarx */
+ case 84: /* ldarx */
+ case 116: /* lharx */
+ case 276: /* lqarx */
+ return 0; /* not emulated ever */
+ }
}
/* Byteswap little endian loads and stores */
addi r8,r1,INT_FRAME_SIZE /* Get the kprobed function entry */
- lwz r3,GPR1(r1)
+ ld r3,GPR1(r1)
subi r3,r3,INT_FRAME_SIZE /* dst: Allocate a trampoline exception frame */
mr r4,r1 /* src: current exception frame */
mr r1,r3 /* Reroute the trampoline frame to r1 */
addi r6,r6,8
bdnz 2b
- /* Do real store operation to complete stwu */
- lwz r5,GPR1(r1)
+ /* Do real store operation to complete stdu */
+ ld r5,GPR1(r1)
std r8,0(r5)
/* Clear _TIF_EMULATE_STACK_STORE flag */
EXCEPTION_PROLOG_COMMON_2(PACA_EXGEN)
EXCEPTION_PROLOG_COMMON_3(0xe60)
addi r3,r1,STACK_FRAME_OVERHEAD
- BRANCH_LINK_TO_FAR(r4, hmi_exception_realmode)
+ BRANCH_LINK_TO_FAR(hmi_exception_realmode) /* Function call ABI */
/* Windup the stack. */
/* Move original HSRR0 and HSRR1 into the respective regs */
ld r9,_MSR(r1)
* flush all bytes from start through stop-1 inclusive
*/
-_GLOBAL(flush_icache_range)
+_GLOBAL_TOC(flush_icache_range)
BEGIN_FTR_SECTION
PURGE_PREFETCHED_INS
blr
*
* flush all bytes from start to stop-1 inclusive
*/
-_GLOBAL(flush_dcache_range)
+_GLOBAL_TOC(flush_dcache_range)
/*
* Flush the data cache to memory
mtspr(SPRN_LPCR, lpcr | LPCR_AIL_3);
}
+ /*
+ * Fixup HFSCR:TM based on CPU features. The bit is set by our
+ * early asm init because at that point we haven't updated our
+ * CPU features from firmware and device-tree. Here we have,
+ * so let's do it.
+ */
+ if (cpu_has_feature(CPU_FTR_HVMODE) && !cpu_has_feature(CPU_FTR_TM_COMP))
+ mtspr(SPRN_HFSCR, mfspr(SPRN_HFSCR) & ~HFSCR_TM);
+
/* Set IR and DR in PACA MSR */
get_paca()->kernel_msr = MSR_KERNEL;
}
{ NULL, },
};
-void __init smp_cpus_done(unsigned int max_cpus)
+static __init long smp_setup_cpu_workfn(void *data __always_unused)
{
- cpumask_var_t old_mask;
+ smp_ops->setup_cpu(boot_cpuid);
+ return 0;
+}
- /* We want the setup_cpu() here to be called from CPU 0, but our
- * init thread may have been "borrowed" by another CPU in the meantime
- * se we pin us down to CPU 0 for a short while
+void __init smp_cpus_done(unsigned int max_cpus)
+{
+ /*
+ * We want the setup_cpu() here to be called on the boot CPU, but
+ * init might run on any CPU, so make sure it's invoked on the boot
+ * CPU.
*/
- alloc_cpumask_var(&old_mask, GFP_NOWAIT);
- cpumask_copy(old_mask, ¤t->cpus_allowed);
- set_cpus_allowed_ptr(current, cpumask_of(boot_cpuid));
-
if (smp_ops && smp_ops->setup_cpu)
- smp_ops->setup_cpu(boot_cpuid);
-
- set_cpus_allowed_ptr(current, old_mask);
-
- free_cpumask_var(old_mask);
+ work_on_cpu_safe(boot_cpuid, smp_setup_cpu_workfn, NULL);
if (smp_ops && smp_ops->bringup_done)
smp_ops->bringup_done();
dump_numa_cpu_topology();
set_sched_topology(powerpc_topology);
-
}
#ifdef CONFIG_HOTPLUG_CPU
decrementer_clockevent.max_delta_ns =
clockevent_delta2ns(decrementer_max, &decrementer_clockevent);
+ decrementer_clockevent.max_delta_ticks = decrementer_max;
decrementer_clockevent.min_delta_ns =
clockevent_delta2ns(2, &decrementer_clockevent);
+ decrementer_clockevent.min_delta_ticks = 2;
register_decrementer_clockevent(cpu);
}
/* start new resize */
resize = kzalloc(sizeof(*resize), GFP_KERNEL);
+ if (!resize) {
+ ret = -ENOMEM;
+ goto out;
+ }
resize->order = shift;
resize->kvm = kvm;
INIT_WORK(&resize->work, resize_hpt_prepare_work);
obj-$(CONFIG_PPC32) += div64.o copy_32.o
-obj64-y += copypage_64.o copyuser_64.o usercopy_64.o mem_64.o hweight_64.o \
+obj64-y += copypage_64.o copyuser_64.o mem_64.o hweight_64.o \
copyuser_power7.o string_64.o copypage_power7.o memcpy_power7.o \
memcpy_64.o memcmp_64.o
bdnz 130b
/* then clear out the destination: r3 bytes starting at 4(r6) */
132: mfctr r3
- srwi. r0,r3,2
- li r9,0
- mtctr r0
- beq 113f
-112: stwu r9,4(r6)
- bdnz 112b
-113: andi. r0,r3,3
- mtctr r0
- beq 120f
-114: stb r9,4(r6)
- addi r6,r6,1
- bdnz 114b
120: blr
EX_TABLE(30b,108b)
EX_TABLE(41b,111b)
EX_TABLE(130b,132b)
EX_TABLE(131b,120b)
- EX_TABLE(112b,120b)
- EX_TABLE(114b,120b)
EXPORT_SYMBOL(__copy_tofrom_user)
blr
/*
- * here we have trapped again, need to clear ctr bytes starting at r3
+ * here we have trapped again, amount remaining is in ctr.
*/
-143: mfctr r5
- li r0,0
- mr r4,r3
- mr r3,r5 /* return the number of bytes not copied */
-1: andi. r9,r4,7
- beq 3f
-90: stb r0,0(r4)
- addic. r5,r5,-1
- addi r4,r4,1
- bne 1b
- blr
-3: cmpldi cr1,r5,8
- srdi r9,r5,3
- andi. r5,r5,7
- blt cr1,93f
- mtctr r9
-91: std r0,0(r4)
- addi r4,r4,8
- bdnz 91b
-93: beqlr
- mtctr r5
-92: stb r0,0(r4)
- addi r4,r4,1
- bdnz 92b
+143: mfctr r3
blr
/*
ld r5,-8(r1)
add r6,r6,r5
subf r3,r3,r6 /* #bytes not copied */
-190:
-191:
-192:
- blr /* #bytes not copied in r3 */
+ blr
EX_TABLE(20b,120b)
EX_TABLE(220b,320b)
EX_TABLE(88b,188b)
EX_TABLE(43b,143b)
EX_TABLE(89b,189b)
- EX_TABLE(90b,190b)
- EX_TABLE(91b,191b)
- EX_TABLE(92b,192b)
/*
* Routine to copy a whole page of data, optimized for POWER4.
+++ /dev/null
-/*
- * Functions which are too large to be inlined.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-#include <linux/module.h>
-#include <linux/uaccess.h>
-
-unsigned long copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- if (likely(access_ok(VERIFY_READ, from, n)))
- n = __copy_from_user(to, from, n);
- else
- memset(to, 0, n);
- return n;
-}
-
-unsigned long copy_to_user(void __user *to, const void *from, unsigned long n)
-{
- if (likely(access_ok(VERIFY_WRITE, to, n)))
- n = __copy_to_user(to, from, n);
- return n;
-}
-
-unsigned long copy_in_user(void __user *to, const void __user *from,
- unsigned long n)
-{
- might_sleep();
- if (likely(access_ok(VERIFY_READ, from, n) &&
- access_ok(VERIFY_WRITE, to, n)))
- n =__copy_tofrom_user(to, from, n);
- return n;
-}
-
-EXPORT_SYMBOL(copy_from_user);
-EXPORT_SYMBOL(copy_to_user);
-EXPORT_SYMBOL(copy_in_user);
-
unsigned long psize = batch->psize;
int ssize = batch->ssize;
int i;
+ unsigned int use_local;
+
+ use_local = local && mmu_has_feature(MMU_FTR_TLBIEL) &&
+ mmu_psize_defs[psize].tlbiel && !cxl_ctx_in_use();
local_irq_save(flags);
} pte_iterate_hashed_end();
}
- if (mmu_has_feature(MMU_FTR_TLBIEL) &&
- mmu_psize_defs[psize].tlbiel && local) {
+ if (use_local) {
asm volatile("ptesync":::"memory");
for (i = 0; i < number; i++) {
vpn = batch->vpn[i];
select HAVE_ALIGNED_STRUCT_PAGE if SLUB
select HAVE_ARCH_AUDITSYSCALL
select HAVE_ARCH_EARLY_PFN_TO_NID
- select HAVE_ARCH_HARDENED_USERCOPY
select HAVE_ARCH_JUMP_LABEL
select CPU_NO_EFFICIENT_FFS if !HAVE_MARCH_Z9_109_FEATURES
select HAVE_ARCH_SECCOMP_FILTER
--- /dev/null
+#ifndef __S390_EXTABLE_H
+#define __S390_EXTABLE_H
+/*
+ * The exception table consists of pairs of addresses: the first is the
+ * address of an instruction that is allowed to fault, and the second is
+ * the address at which the program should continue. No registers are
+ * modified, so it is entirely up to the continuation code to figure out
+ * what to do.
+ *
+ * All the routines below use bits of fixup code that are out of line
+ * with the main instruction path. This means when everything is well,
+ * we don't even have to jump over them. Further, they do not intrude
+ * on our cache or tlb entries.
+ */
+
+struct exception_table_entry
+{
+ int insn, fixup;
+};
+
+static inline unsigned long extable_fixup(const struct exception_table_entry *x)
+{
+ return (unsigned long)&x->fixup + x->fixup;
+}
+
+#define ARCH_HAS_RELATIVE_EXTABLE
+
+#endif
{
if (!MACHINE_HAS_NX)
pte_val(entry) &= ~_PAGE_NOEXEC;
+ if (pte_present(entry))
+ pte_val(entry) &= ~_PAGE_UNUSED;
if (mm_has_pgste(mm))
ptep_set_pte_at(mm, addr, ptep, entry);
else
/*
* User space memory access functions
*/
-#include <linux/sched.h>
-#include <linux/errno.h>
#include <asm/processor.h>
#include <asm/ctl_reg.h>
-
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
+#include <asm/extable.h>
/*
static inline void set_fs(mm_segment_t fs)
{
current->thread.mm_segment = fs;
- if (segment_eq(fs, KERNEL_DS)) {
+ if (uaccess_kernel()) {
set_cpu_flag(CIF_ASCE_SECONDARY);
__ctl_load(S390_lowcore.kernel_asce, 7, 7);
} else {
#define access_ok(type, addr, size) __access_ok(addr, size)
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue. No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path. This means when everything is well,
- * we don't even have to jump over them. Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry
-{
- int insn, fixup;
-};
-
-static inline unsigned long extable_fixup(const struct exception_table_entry *x)
-{
- return (unsigned long)&x->fixup + x->fixup;
-}
-
-#define ARCH_HAS_RELATIVE_EXTABLE
-
-/**
- * __copy_from_user: - Copy a block of data from user space, with less checking.
- * @to: Destination address, in kernel space.
- * @from: Source address, in user space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- * enabled.
- *
- * Copy data from user space to kernel space. Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- *
- * If some data could not be copied, this function will pad the copied
- * data to the requested size using zero bytes.
- */
-unsigned long __must_check __copy_from_user(void *to, const void __user *from,
- unsigned long n);
+unsigned long __must_check
+raw_copy_from_user(void *to, const void __user *from, unsigned long n);
-/**
- * __copy_to_user: - Copy a block of data into user space, with less checking.
- * @to: Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- * enabled.
- *
- * Copy data from kernel space to user space. Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- */
-unsigned long __must_check __copy_to_user(void __user *to, const void *from,
- unsigned long n);
+unsigned long __must_check
+raw_copy_to_user(void __user *to, const void *from, unsigned long n);
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
static inline int __put_user_fn(void *x, void __user *ptr, unsigned long size)
{
- size = __copy_to_user(ptr, x, size);
+ size = raw_copy_to_user(ptr, x, size);
return size ? -EFAULT : 0;
}
static inline int __get_user_fn(void *x, const void __user *ptr, unsigned long size)
{
- size = __copy_from_user(x, ptr, size);
+ size = raw_copy_from_user(x, ptr, size);
return size ? -EFAULT : 0;
}
#define __put_user_unaligned __put_user
#define __get_user_unaligned __get_user
-extern void __compiletime_error("usercopy buffer size is too small")
-__bad_copy_user(void);
-
-static inline void copy_user_overflow(int size, unsigned long count)
-{
- WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
-}
-
-/**
- * copy_to_user: - Copy a block of data into user space.
- * @to: Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- * enabled.
- *
- * Copy data from kernel space to user space.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- */
-static inline unsigned long __must_check
-copy_to_user(void __user *to, const void *from, unsigned long n)
-{
- might_fault();
- return __copy_to_user(to, from, n);
-}
-
-/**
- * copy_from_user: - Copy a block of data from user space.
- * @to: Destination address, in kernel space.
- * @from: Source address, in user space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- * enabled.
- *
- * Copy data from user space to kernel space.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- *
- * If some data could not be copied, this function will pad the copied
- * data to the requested size using zero bytes.
- */
-static inline unsigned long __must_check
-copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- unsigned int sz = __compiletime_object_size(to);
-
- might_fault();
- if (unlikely(sz != -1 && sz < n)) {
- if (!__builtin_constant_p(n))
- copy_user_overflow(sz, n);
- else
- __bad_copy_user();
- return n;
- }
- return __copy_from_user(to, from, n);
-}
-
unsigned long __must_check
-__copy_in_user(void __user *to, const void __user *from, unsigned long n);
-
-static inline unsigned long __must_check
-copy_in_user(void __user *to, const void __user *from, unsigned long n)
-{
- might_fault();
- return __copy_in_user(to, from, n);
-}
+raw_copy_in_user(void __user *to, const void __user *from, unsigned long n);
/*
* Copy a null terminated string from userspace.
cd->mult = 16777;
cd->shift = 12;
cd->min_delta_ns = 1;
+ cd->min_delta_ticks = 1;
cd->max_delta_ns = LONG_MAX;
+ cd->max_delta_ticks = ULONG_MAX;
cd->rating = 400;
cd->cpumask = cpumask_of(cpu);
cd->set_next_event = s390_next_event;
unsigned long z : 1; /* Zero Bit */
unsigned long i : 1; /* Page-Invalid Bit */
unsigned long p : 1; /* DAT-Protection Bit */
- unsigned long co : 1; /* Change-Recording Override */
- unsigned long : 8;
+ unsigned long : 9;
};
};
return PGM_PAGE_TRANSLATION;
if (pte.z)
return PGM_TRANSLATION_SPEC;
- if (pte.co && !edat1)
- return PGM_TRANSLATION_SPEC;
dat_protection |= pte.p;
raddr.pfra = pte.pfra;
real_address:
rc = gmap_read_table(sg->parent, pgt + vaddr.px * 8, &pte.val);
if (!rc && pte.i)
rc = PGM_PAGE_TRANSLATION;
- if (!rc && (pte.z || (pte.co && sg->edat_level < 1)))
+ if (!rc && pte.z)
rc = PGM_TRANSLATION_SPEC;
shadow_page:
pte.p |= dat_protection;
tmp1 = -4096UL;
asm volatile(
"0: .insn ss,0xc80000000000,0(%0,%2),0(%1),0\n"
- "9: jz 7f\n"
+ "6: jz 4f\n"
"1: algr %0,%3\n"
" slgr %1,%3\n"
" slgr %2,%3\n"
" nr %4,%3\n" /* %4 = (ptr + 4095) & -4096 */
" slgr %4,%1\n"
" clgr %0,%4\n" /* copy crosses next page boundary? */
- " jnh 4f\n"
+ " jnh 5f\n"
"3: .insn ss,0xc80000000000,0(%4,%2),0(%1),0\n"
- "10:slgr %0,%4\n"
- " algr %2,%4\n"
- "4: lghi %4,-1\n"
- " algr %4,%0\n" /* copy remaining size, subtract 1 */
- " bras %3,6f\n" /* memset loop */
- " xc 0(1,%2),0(%2)\n"
- "5: xc 0(256,%2),0(%2)\n"
- " la %2,256(%2)\n"
- "6: aghi %4,-256\n"
- " jnm 5b\n"
- " ex %4,0(%3)\n"
- " j 8f\n"
- "7: slgr %0,%0\n"
- "8:\n"
- EX_TABLE(0b,2b) EX_TABLE(3b,4b) EX_TABLE(9b,2b) EX_TABLE(10b,4b)
+ "7: slgr %0,%4\n"
+ " j 5f\n"
+ "4: slgr %0,%0\n"
+ "5:\n"
+ EX_TABLE(0b,2b) EX_TABLE(3b,5b) EX_TABLE(6b,2b) EX_TABLE(7b,5b)
: "+a" (size), "+a" (ptr), "+a" (x), "+a" (tmp1), "=a" (tmp2)
: "d" (reg0) : "cc", "memory");
return size;
asm volatile(
" sacf 0\n"
"0: mvcp 0(%0,%2),0(%1),%3\n"
- "10:jz 8f\n"
+ "7: jz 5f\n"
"1: algr %0,%3\n"
" la %1,256(%1)\n"
" la %2,256(%2)\n"
"2: mvcp 0(%0,%2),0(%1),%3\n"
- "11:jnz 1b\n"
- " j 8f\n"
+ "8: jnz 1b\n"
+ " j 5f\n"
"3: la %4,255(%1)\n" /* %4 = ptr + 255 */
" lghi %3,-4096\n"
" nr %4,%3\n" /* %4 = (ptr + 255) & -4096 */
" slgr %4,%1\n"
" clgr %0,%4\n" /* copy crosses next page boundary? */
- " jnh 5f\n"
+ " jnh 6f\n"
"4: mvcp 0(%4,%2),0(%1),%3\n"
- "12:slgr %0,%4\n"
- " algr %2,%4\n"
- "5: lghi %4,-1\n"
- " algr %4,%0\n" /* copy remaining size, subtract 1 */
- " bras %3,7f\n" /* memset loop */
- " xc 0(1,%2),0(%2)\n"
- "6: xc 0(256,%2),0(%2)\n"
- " la %2,256(%2)\n"
- "7: aghi %4,-256\n"
- " jnm 6b\n"
- " ex %4,0(%3)\n"
- " j 9f\n"
- "8: slgr %0,%0\n"
- "9: sacf 768\n"
- EX_TABLE(0b,3b) EX_TABLE(2b,3b) EX_TABLE(4b,5b)
- EX_TABLE(10b,3b) EX_TABLE(11b,3b) EX_TABLE(12b,5b)
+ "9: slgr %0,%4\n"
+ " j 6f\n"
+ "5: slgr %0,%0\n"
+ "6: sacf 768\n"
+ EX_TABLE(0b,3b) EX_TABLE(2b,3b) EX_TABLE(4b,6b)
+ EX_TABLE(7b,3b) EX_TABLE(8b,3b) EX_TABLE(9b,6b)
: "+a" (size), "+a" (ptr), "+a" (x), "+a" (tmp1), "=a" (tmp2)
: : "cc", "memory");
return size;
}
-unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n)
+unsigned long raw_copy_from_user(void *to, const void __user *from, unsigned long n)
{
- check_object_size(to, n, false);
if (static_branch_likely(&have_mvcos))
return copy_from_user_mvcos(to, from, n);
return copy_from_user_mvcp(to, from, n);
}
-EXPORT_SYMBOL(__copy_from_user);
+EXPORT_SYMBOL(raw_copy_from_user);
static inline unsigned long copy_to_user_mvcos(void __user *ptr, const void *x,
unsigned long size)
return size;
}
-unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n)
+unsigned long raw_copy_to_user(void __user *to, const void *from, unsigned long n)
{
- check_object_size(from, n, true);
if (static_branch_likely(&have_mvcos))
return copy_to_user_mvcos(to, from, n);
return copy_to_user_mvcs(to, from, n);
}
-EXPORT_SYMBOL(__copy_to_user);
+EXPORT_SYMBOL(raw_copy_to_user);
static inline unsigned long copy_in_user_mvcos(void __user *to, const void __user *from,
unsigned long size)
return size;
}
-unsigned long __copy_in_user(void __user *to, const void __user *from, unsigned long n)
+unsigned long raw_copy_in_user(void __user *to, const void __user *from, unsigned long n)
{
if (static_branch_likely(&have_mvcos))
return copy_in_user_mvcos(to, from, n);
return copy_in_user_mvc(to, from, n);
}
-EXPORT_SYMBOL(__copy_in_user);
+EXPORT_SYMBOL(raw_copy_in_user);
static inline unsigned long clear_user_mvcos(void __user *to, unsigned long size)
{
generic-y += barrier.h
generic-y += clkdev.h
generic-y += current.h
+generic-y += extable.h
generic-y += irq_work.h
generic-y += mcs_spinlock.h
generic-y += mm-arch-hooks.h
+++ /dev/null
-#ifndef _ASM_SCORE_EXTABLE_H
-#define _ASM_SCORE_EXTABLE_H
-
-struct exception_table_entry {
- unsigned long insn;
- unsigned long fixup;
-};
-
-struct pt_regs;
-extern int fixup_exception(struct pt_regs *regs);
-#endif
#define __SCORE_UACCESS_H
#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/thread_info.h>
#include <asm/extable.h>
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
#define get_ds() (KERNEL_DS)
#define get_fs() (current_thread_info()->addr_limit)
#define segment_eq(a, b) ((a).seg == (b).seg)
extern int __copy_tofrom_user(void *to, const void *from, unsigned long len);
static inline unsigned long
-copy_from_user(void *to, const void *from, unsigned long len)
-{
- unsigned long res = len;
-
- if (likely(access_ok(VERIFY_READ, from, len)))
- res = __copy_tofrom_user(to, from, len);
-
- if (unlikely(res))
- memset(to + (len - res), 0, res);
-
- return res;
-}
-
-static inline unsigned long
-copy_to_user(void *to, const void *from, unsigned long len)
-{
- if (likely(access_ok(VERIFY_WRITE, to, len)))
- len = __copy_tofrom_user(to, from, len);
-
- return len;
-}
-
-static inline unsigned long
-__copy_from_user(void *to, const void *from, unsigned long len)
+raw_copy_from_user(void *to, const void __user *from, unsigned long len)
{
- unsigned long left = __copy_tofrom_user(to, from, len);
- if (unlikely(left))
- memset(to + (len - left), 0, left);
- return left;
+ return __copy_tofrom_user(to, (__force const void *)from, len);
}
-#define __copy_to_user(to, from, len) \
- __copy_tofrom_user((to), (from), (len))
-
static inline unsigned long
-__copy_to_user_inatomic(void *to, const void *from, unsigned long len)
+raw_copy_to_user(void __user *to, const void *from, unsigned long len)
{
- return __copy_to_user(to, from, len);
+ return __copy_tofrom_user((__force void *)to, from, len);
}
-static inline unsigned long
-__copy_from_user_inatomic(void *to, const void *from, unsigned long len)
-{
- return __copy_tofrom_user(to, from, len);
-}
-
-#define __copy_in_user(to, from, len) __copy_tofrom_user(to, from, len)
-
-static inline unsigned long
-copy_in_user(void *to, const void *from, unsigned long len)
-{
- if (access_ok(VERIFY_READ, from, len) &&
- access_ok(VERFITY_WRITE, to, len))
- return __copy_tofrom_user(to, from, len);
-}
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
/*
* __clear_user: - Zero a block of memory in user space, with less checking.
score_clockevent.shift);
score_clockevent.max_delta_ns = clockevent_delta2ns((u32)~0,
&score_clockevent);
+ score_clockevent.max_delta_ticks = (u32)~0;
score_clockevent.min_delta_ns = clockevent_delta2ns(50,
&score_clockevent) + 1;
+ score_clockevent.min_delta_ticks = 50;
score_clockevent.cpumask = cpumask_of(0);
clockevents_register_device(&score_clockevent);
}
--- /dev/null
+#ifndef __ASM_SH_EXTABLE_H
+#define __ASM_SH_EXTABLE_H
+
+#include <asm-generic/extable.h>
+
+#if defined(CONFIG_SUPERH64) && defined(CONFIG_MMU)
+#define ARCH_HAS_SEARCH_EXTABLE
+#endif
+
+#endif
#ifndef __ASM_SH_UACCESS_H
#define __ASM_SH_UACCESS_H
-#include <linux/errno.h>
-#include <linux/sched.h>
#include <asm/segment.h>
-
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
+#include <asm/extable.h>
#define __addr_ok(addr) \
((unsigned long __force)(addr) < current_thread_info()->addr_limit.seg)
__kernel_size_t __copy_user(void *to, const void *from, __kernel_size_t n);
static __always_inline unsigned long
-__copy_from_user(void *to, const void __user *from, unsigned long n)
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
{
return __copy_user(to, (__force void *)from, n);
}
static __always_inline unsigned long __must_check
-__copy_to_user(void __user *to, const void *from, unsigned long n)
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
{
return __copy_user((__force void *)to, from, n);
}
-
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
/*
* Clear the area and return remaining number of bytes
__cl_size; \
})
-static inline unsigned long
-copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- unsigned long __copy_from = (unsigned long) from;
- __kernel_size_t __copy_size = (__kernel_size_t) n;
-
- if (__copy_size && __access_ok(__copy_from, __copy_size))
- __copy_size = __copy_user(to, from, __copy_size);
-
- if (unlikely(__copy_size))
- memset(to + (n - __copy_size), 0, __copy_size);
-
- return __copy_size;
-}
-
-static inline unsigned long
-copy_to_user(void __user *to, const void *from, unsigned long n)
-{
- unsigned long __copy_to = (unsigned long) to;
- __kernel_size_t __copy_size = (__kernel_size_t) n;
-
- if (__copy_size && __access_ok(__copy_to, __copy_size))
- return __copy_user(to, from, __copy_size);
-
- return __copy_size;
-}
-
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue. No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path. This means when everything is well,
- * we don't even have to jump over them. Further, they do not intrude
- * on our cache or tlb entries.
- */
-struct exception_table_entry {
- unsigned long insn, fixup;
-};
-
-#if defined(CONFIG_SUPERH64) && defined(CONFIG_MMU)
-#define ARCH_HAS_SEARCH_EXTABLE
-#endif
-
-int fixup_exception(struct pt_regs *regs);
-
extern void *set_exception_table_vec(unsigned int vec, void *handler);
static inline void *set_exception_table_evt(unsigned int evt, void *handler)
select OLD_SIGSUSPEND
select ARCH_HAS_SG_CHAIN
select CPU_NO_EFFICIENT_FFS
- select HAVE_ARCH_HARDENED_USERCOPY
- select PROVE_LOCKING_SMALL if PROVE_LOCKING
+ select LOCKDEP_SMALL if LOCKDEP
select ARCH_WANT_RELAX_ORDER
config SPARC32
select HAVE_ARCH_AUDITSYSCALL
select ARCH_SUPPORTS_ATOMIC_RMW
select HAVE_NMI
+ select HAVE_REGS_AND_STACK_ACCESS_API
config ARCH_DEFCONFIG
string
#define HPAGE_SHIFT 23
#define REAL_HPAGE_SHIFT 22
+#define HPAGE_2GB_SHIFT 31
#define HPAGE_256MB_SHIFT 28
#define HPAGE_64K_SHIFT 16
#define REAL_HPAGE_SIZE (_AC(1,UL) << REAL_HPAGE_SHIFT)
#define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT)
#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
#define REAL_HPAGE_PER_HPAGE (_AC(1,UL) << (HPAGE_SHIFT - REAL_HPAGE_SHIFT))
-#define HUGE_MAX_HSTATE 3
+#define HUGE_MAX_HSTATE 4
#endif
#ifndef __ASSEMBLY__
return pte_pfn(pte);
}
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline unsigned long pmd_dirty(pmd_t pmd)
+#define __HAVE_ARCH_PMD_WRITE
+static inline unsigned long pmd_write(pmd_t pmd)
{
pte_t pte = __pte(pmd_val(pmd));
- return pte_dirty(pte);
+ return pte_write(pte);
}
-static inline unsigned long pmd_young(pmd_t pmd)
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline unsigned long pmd_dirty(pmd_t pmd)
{
pte_t pte = __pte(pmd_val(pmd));
- return pte_young(pte);
+ return pte_dirty(pte);
}
-static inline unsigned long pmd_write(pmd_t pmd)
+static inline unsigned long pmd_young(pmd_t pmd)
{
pte_t pte = __pte(pmd_val(pmd));
- return pte_write(pte);
+ return pte_young(pte);
}
static inline unsigned long pmd_trans_huge(pmd_t pmd)
#include <asm/signal.h>
#include <asm/page.h>
-/*
- * The sparc has no problems with write protection
- */
-#define wp_works_ok 1
-#define wp_works_ok__is_a_macro /* for versions in ksyms.c */
-
/* Whee, this is STACK_TOP + PAGE_SIZE and the lowest kernel address too...
* That one page is used to protect kernel from intruders, so that
* we can make our access_ok test faster
#include <asm/ptrace.h>
#include <asm/page.h>
-/* The sparc has no problems with write protection */
-#define wp_works_ok 1
-#define wp_works_ok__is_a_macro /* for versions in ksyms.c */
-
/*
* User lives in his very own context, and cannot reference us. Note
* that TASK_SIZE is a misnomer, it really gives maximum user virtual
#define MAX_REG_OFFSET (offsetof(struct pt_regs, magic))
-extern int regs_query_register_offset(const char *name);
+int regs_query_register_offset(const char *name);
+unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n);
/**
* regs_get_register() - get register value from its offset
#endif
#define user_addr_max() \
- (segment_eq(get_fs(), USER_DS) ? TASK_SIZE : ~0UL)
+ (uaccess_kernel() ? ~0UL : TASK_SIZE)
long strncpy_from_user(char *dest, const char __user *src, long count);
#ifndef _ASM_UACCESS_H
#define _ASM_UACCESS_H
-#ifdef __KERNEL__
#include <linux/compiler.h>
-#include <linux/sched.h>
#include <linux/string.h>
-#include <linux/errno.h>
-#endif
-
-#ifndef __ASSEMBLY__
#include <asm/processor.h>
#define KERNEL_DS ((mm_segment_t) { 0 })
#define USER_DS ((mm_segment_t) { -1 })
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
#define get_ds() (KERNEL_DS)
#define get_fs() (current->thread.current_ds)
#define set_fs(val) ((current->thread.current_ds) = (val))
* large size and address near to PAGE_OFFSET - a fault will break his intentions.
*/
#define __user_ok(addr, size) ({ (void)(size); (addr) < STACK_TOP; })
-#define __kernel_ok (segment_eq(get_fs(), KERNEL_DS))
+#define __kernel_ok (uaccess_kernel())
#define __access_ok(addr, size) (__user_ok((addr) & get_fs().seg, (size)))
#define access_ok(type, addr, size) \
({ (void)(type); __access_ok((unsigned long)(addr), size); })
/* Returns 0 if exception not found and fixup otherwise. */
unsigned long search_extables_range(unsigned long addr, unsigned long *g2);
-void __ret_efault(void);
-
/* Uh, these should become the main single-value transfer routines..
* They automatically use the right size if we just have the right
* pointer type..
unsigned long __copy_user(void __user *to, const void __user *from, unsigned long size);
-static inline unsigned long copy_to_user(void __user *to, const void *from, unsigned long n)
-{
- if (n && __access_ok((unsigned long) to, n)) {
- check_object_size(from, n, true);
- return __copy_user(to, (__force void __user *) from, n);
- } else
- return n;
-}
-
-static inline unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n)
+static inline unsigned long raw_copy_to_user(void __user *to, const void *from, unsigned long n)
{
- check_object_size(from, n, true);
return __copy_user(to, (__force void __user *) from, n);
}
-static inline unsigned long copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- if (n && __access_ok((unsigned long) from, n)) {
- check_object_size(to, n, false);
- return __copy_user((__force void __user *) to, from, n);
- } else {
- memset(to, 0, n);
- return n;
- }
-}
-
-static inline unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n)
+static inline unsigned long raw_copy_from_user(void *to, const void __user *from, unsigned long n)
{
return __copy_user((__force void __user *) to, from, n);
}
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
static inline unsigned long __clear_user(void __user *addr, unsigned long size)
{
__must_check long strlen_user(const char __user *str);
__must_check long strnlen_user(const char __user *str, long n);
-#endif /* __ASSEMBLY__ */
-
#endif /* _ASM_UACCESS_H */
* User space memory access functions
*/
-#ifdef __KERNEL__
-#include <linux/errno.h>
#include <linux/compiler.h>
#include <linux/string.h>
-#include <linux/thread_info.h>
#include <asm/asi.h>
#include <asm/spitfire.h>
#include <asm-generic/uaccess-unaligned.h>
#include <asm/extable_64.h>
-#endif
-
-#ifndef __ASSEMBLY__
#include <asm/processor.h>
#define KERNEL_DS ((mm_segment_t) { ASI_P })
#define USER_DS ((mm_segment_t) { ASI_AIUS }) /* har har har */
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
#define get_fs() ((mm_segment_t){(current_thread_info()->current_ds)})
#define get_ds() (KERNEL_DS)
int __get_user_bad(void);
-unsigned long __must_check ___copy_from_user(void *to,
+unsigned long __must_check raw_copy_from_user(void *to,
const void __user *from,
unsigned long size);
-static inline unsigned long __must_check
-copy_from_user(void *to, const void __user *from, unsigned long size)
-{
- check_object_size(to, size, false);
- return ___copy_from_user(to, from, size);
-}
-#define __copy_from_user copy_from_user
-
-unsigned long __must_check ___copy_to_user(void __user *to,
+unsigned long __must_check raw_copy_to_user(void __user *to,
const void *from,
unsigned long size);
-static inline unsigned long __must_check
-copy_to_user(void __user *to, const void *from, unsigned long size)
-{
- check_object_size(from, size, true);
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
- return ___copy_to_user(to, from, size);
-}
-#define __copy_to_user copy_to_user
-
-unsigned long __must_check ___copy_in_user(void __user *to,
+unsigned long __must_check raw_copy_in_user(void __user *to,
const void __user *from,
unsigned long size);
-static inline unsigned long __must_check
-copy_in_user(void __user *to, void __user *from, unsigned long size)
-{
- return ___copy_in_user(to, from, size);
-}
-#define __copy_in_user copy_in_user
unsigned long __must_check __clear_user(void __user *, unsigned long);
__must_check long strlen_user(const char __user *str);
__must_check long strnlen_user(const char __user *str, long n);
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
-
struct pt_regs;
unsigned long compute_effective_address(struct pt_regs *,
unsigned int insn,
unsigned int rd);
-#endif /* __ASSEMBLY__ */
-
#endif /* _ASM_UACCESS_H */
#define __NR_copy_file_range 357
#define __NR_preadv2 358
#define __NR_pwritev2 359
+#define __NR_statx 360
-#define NR_syscalls 360
+#define NR_syscalls 361
/* Bitmask values returned from kern_features system call. */
#define KERN_FEATURE_MIXED_MODE_STACK 0x00000001
#define __IGNORE_getresgid
#endif
+/* Sparc doesn't have protection keys. */
+#define __IGNORE_pkey_mprotect
+#define __IGNORE_pkey_alloc
+#define __IGNORE_pkey_free
+
#endif /* _UAPI_SPARC_UNISTD_H */
.word 0
.word 0
.word t_irq14
-
- .section ".fixup",#alloc,#execinstr
- .globl __ret_efault
-__ret_efault:
- ret
- restore %g0, -EFAULT, %o0
-EXPORT_SYMBOL(__ret_efault)
andn %g1, PSTATE_AM, %g1
wrpr %g1, 0x0, %pstate
ba,a,pt %xcc, 1f
+ nop
.globl prom_finddev_name, prom_chosen_path, prom_root_node
.globl prom_getprop_name, prom_mmu_name, prom_peer_name
nop
ba,a,pt %xcc, 80f
+ nop
niagara4_patch:
call niagara4_patch_copyops
nop
nop
ba,a,pt %xcc, 80f
+ nop
niagara2_patch:
call niagara2_patch_copyops
nop
ba,a,pt %xcc, 80f
+ nop
niagara_patch:
call niagara_patch_copyops
call handle_stdfmna
add %sp, PTREGS_OFF, %o0
ba,a,pt %xcc, rtrap
+ nop
.size do_stdfmna,.-do_stdfmna
.type breakpoint_trap,#function
return roff->offset;
return -EINVAL;
}
+
+/**
+ * regs_within_kernel_stack() - check the address in the stack
+ * @regs: pt_regs which contains kernel stack pointer.
+ * @addr: address which is checked.
+ *
+ * regs_within_kernel_stack() checks @addr is within the kernel stack page(s).
+ * If @addr is within the kernel stack, it returns true. If not, returns false.
+ */
+static inline int regs_within_kernel_stack(struct pt_regs *regs,
+ unsigned long addr)
+{
+ unsigned long ksp = kernel_stack_pointer(regs) + STACK_BIAS;
+ return ((addr & ~(THREAD_SIZE - 1)) ==
+ (ksp & ~(THREAD_SIZE - 1)));
+}
+
+/**
+ * regs_get_kernel_stack_nth() - get Nth entry of the stack
+ * @regs: pt_regs which contains kernel stack pointer.
+ * @n: stack entry number.
+ *
+ * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which
+ * is specified by @regs. If the @n th entry is NOT in the kernel stack,
+ * this returns 0.
+ */
+unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n)
+{
+ unsigned long ksp = kernel_stack_pointer(regs) + STACK_BIAS;
+ unsigned long *addr = (unsigned long *)ksp;
+ addr += n;
+ if (regs_within_kernel_stack(regs, (unsigned long)addr))
+ return *addr;
+ else
+ return 0;
+}
bne,pt %xcc, user_rtt_fill_32bit
wrpr %g1, %cwp
ba,a,pt %xcc, user_rtt_fill_64bit
+ nop
user_rtt_fill_fixup_dax:
ba,pt %xcc, user_rtt_fill_fixup_common
rd %pc, %g7
ba,a,pt %xcc, 2f
+ nop
1: ba,pt %xcc, etrap_irq
rd %pc, %g7
call sun4v_do_mna
add %sp, PTREGS_OFF, %o0
ba,a,pt %xcc, rtrap
+ nop
/* Privileged Action. */
sun4v_privact:
.name = "mmu_stats",
};
-/* XXX convert to rusty's on_one_cpu */
-static unsigned long run_on_cpu(unsigned long cpu,
- unsigned long (*func)(unsigned long),
- unsigned long arg)
-{
- cpumask_t old_affinity;
- unsigned long ret;
-
- cpumask_copy(&old_affinity, ¤t->cpus_allowed);
- /* should return -EINVAL to userspace */
- if (set_cpus_allowed_ptr(current, cpumask_of(cpu)))
- return 0;
-
- ret = func(arg);
-
- set_cpus_allowed_ptr(current, &old_affinity);
-
- return ret;
-}
-
-static unsigned long read_mmustat_enable(unsigned long junk)
+static long read_mmustat_enable(void *data __maybe_unused)
{
unsigned long ra = 0;
return ra != 0;
}
-static unsigned long write_mmustat_enable(unsigned long val)
+static long write_mmustat_enable(void *data)
{
- unsigned long ra, orig_ra;
+ unsigned long ra, orig_ra, *val = data;
- if (val)
+ if (*val)
ra = __pa(&per_cpu(mmu_stats, smp_processor_id()));
else
ra = 0UL;
static ssize_t show_mmustat_enable(struct device *s,
struct device_attribute *attr, char *buf)
{
- unsigned long val = run_on_cpu(s->id, read_mmustat_enable, 0);
+ long val = work_on_cpu(s->id, read_mmustat_enable, NULL);
+
return sprintf(buf, "%lx\n", val);
}
struct device_attribute *attr, const char *buf,
size_t count)
{
- unsigned long val, err;
- int ret = sscanf(buf, "%lu", &val);
+ unsigned long val;
+ long err;
+ int ret;
+ ret = sscanf(buf, "%lu", &val);
if (ret != 1)
return -EINVAL;
- err = run_on_cpu(s->id, write_mmustat_enable, val);
+ err = work_on_cpu(s->id, write_mmustat_enable, &val);
if (err)
return -EIO;
/*345*/ .long sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf
/*350*/ .long sys_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen
/*355*/ .long sys_setsockopt, sys_mlock2, sys_copy_file_range, sys_preadv2, sys_pwritev2
+/*360*/ .long sys_statx
.word sys32_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf
/*350*/ .word sys32_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen
.word compat_sys_setsockopt, sys_mlock2, sys_copy_file_range, compat_sys_preadv2, compat_sys_pwritev2
+/*360*/ .word sys_statx
#endif /* CONFIG_COMPAT */
.word sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf
/*350*/ .word sys64_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen
.word sys_setsockopt, sys_mlock2, sys_copy_file_range, sys_preadv2, sys_pwritev2
+/*360*/ .word sys_statx
ce->mult = div_sc(sparc_config.clock_rate, NSEC_PER_SEC,
ce->shift);
ce->max_delta_ns = clockevent_delta2ns(sparc_config.clock_rate, ce);
+ ce->max_delta_ticks = (unsigned long)sparc_config.clock_rate;
ce->min_delta_ns = clockevent_delta2ns(100, ce);
+ ce->min_delta_ticks = 100;
clockevents_register_device(ce);
}
sparc64_clockevent.max_delta_ns =
clockevent_delta2ns(0x7fffffffffffffffUL, &sparc64_clockevent);
+ sparc64_clockevent.max_delta_ticks = 0x7fffffffffffffffUL;
sparc64_clockevent.min_delta_ns =
clockevent_delta2ns(0xF, &sparc64_clockevent);
+ sparc64_clockevent.min_delta_ticks = 0xF;
printk("clockevent: mult[%x] shift[%d]\n",
sparc64_clockevent.mult, sparc64_clockevent.shift);
call sun4v_data_access_exception
nop
ba,a,pt %xcc, rtrap
+ nop
1: call spitfire_data_access_exception
nop
call sun4v_data_access_exception
nop
ba,a,pt %xcc, rtrap
+ nop
1: call spitfire_data_access_exception
nop
ba,a,pt %xcc, rtrap
+ nop
#define PREAMBLE \
rd %asi, %g1; \
cmp %g1, ASI_AIUS; \
- bne,pn %icc, ___copy_in_user; \
+ bne,pn %icc, raw_copy_in_user; \
nop
#endif
#define PREAMBLE \
rd %asi, %g1; \
cmp %g1, ASI_AIUS; \
- bne,pn %icc, ___copy_in_user; \
+ bne,pn %icc, raw_copy_in_user; \
nop
#endif
.type generic_patch_copyops,#function
generic_patch_copyops:
GEN_DO_PATCH(memcpy, GENmemcpy)
- GEN_DO_PATCH(___copy_from_user, GENcopy_from_user)
- GEN_DO_PATCH(___copy_to_user, GENcopy_to_user)
+ GEN_DO_PATCH(raw_copy_from_user, GENcopy_from_user)
+ GEN_DO_PATCH(raw_copy_to_user, GENcopy_to_user)
retl
nop
.size generic_patch_copyops,.-generic_patch_copyops
#define PREAMBLE \
rd %asi, %g1; \
cmp %g1, ASI_AIUS; \
- bne,pn %icc, ___copy_in_user; \
+ bne,pn %icc, raw_copy_in_user; \
nop
#endif
#define PREAMBLE \
rd %asi, %g1; \
cmp %g1, ASI_AIUS; \
- bne,pn %icc, ___copy_in_user; \
+ bne,pn %icc, raw_copy_in_user; \
nop
#endif
blu 170f
nop
ba,a,pt %xcc, 180f
+ nop
4: /* 32 <= low bits < 48 */
blu 150f
nop
ba,a,pt %xcc, 160f
+ nop
5: /* 0 < low bits < 32 */
blu,a 6f
cmp %g2, 8
blu 130f
nop
ba,a,pt %xcc, 140f
+ nop
6: /* 0 < low bits < 16 */
bgeu 120f
nop
brz,pt %o2, 85f
sub %o0, %o1, GLOBAL_SPARE
ba,a,pt %XCC, 90f
+ nop
.align 64
75: /* 16 < len <= 64 */
.type niagara2_patch_copyops,#function
niagara2_patch_copyops:
NG_DO_PATCH(memcpy, NG2memcpy)
- NG_DO_PATCH(___copy_from_user, NG2copy_from_user)
- NG_DO_PATCH(___copy_to_user, NG2copy_to_user)
+ NG_DO_PATCH(raw_copy_from_user, NG2copy_from_user)
+ NG_DO_PATCH(raw_copy_to_user, NG2copy_to_user)
retl
nop
.size niagara2_patch_copyops,.-niagara2_patch_copyops
#define PREAMBLE \
rd %asi, %g1; \
cmp %g1, ASI_AIUS; \
- bne,pn %icc, ___copy_in_user; \
+ bne,pn %icc, raw_copy_in_user; \
nop
#endif
#define PREAMBLE \
rd %asi, %g1; \
cmp %g1, ASI_AIUS; \
- bne,pn %icc, ___copy_in_user; \
+ bne,pn %icc, raw_copy_in_user; \
nop
#endif
bne,pt %icc, 1b
EX_ST(STORE(stb, %g1, %o0 - 0x01), NG4_retl_o2_plus_1)
ba,a,pt %icc, .Lexit
+ nop
.size FUNC_NAME, .-FUNC_NAME
bne,pt %icc, 1b
add %o0, 0x30, %o0
ba,a,pt %icc, .Lpostloop
+ nop
.size NG4bzero,.-NG4bzero
.type niagara4_patch_copyops,#function
niagara4_patch_copyops:
NG_DO_PATCH(memcpy, NG4memcpy)
- NG_DO_PATCH(___copy_from_user, NG4copy_from_user)
- NG_DO_PATCH(___copy_to_user, NG4copy_to_user)
+ NG_DO_PATCH(raw_copy_from_user, NG4copy_from_user)
+ NG_DO_PATCH(raw_copy_to_user, NG4copy_to_user)
retl
nop
.size niagara4_patch_copyops,.-niagara4_patch_copyops
#define PREAMBLE \
rd %asi, %g1; \
cmp %g1, ASI_AIUS; \
- bne,pn %icc, ___copy_in_user; \
+ bne,pn %icc, raw_copy_in_user; \
nop
#endif
#define PREAMBLE \
rd %asi, %g1; \
cmp %g1, ASI_AIUS; \
- bne,pn %icc, ___copy_in_user; \
+ bne,pn %icc, raw_copy_in_user; \
nop
#endif
brz,pt %i2, 85f
sub %o0, %i1, %i3
ba,a,pt %XCC, 90f
+ nop
.align 64
70: /* 16 < len <= 64 */
.type niagara_patch_copyops,#function
niagara_patch_copyops:
NG_DO_PATCH(memcpy, NGmemcpy)
- NG_DO_PATCH(___copy_from_user, NGcopy_from_user)
- NG_DO_PATCH(___copy_to_user, NGcopy_to_user)
+ NG_DO_PATCH(raw_copy_from_user, NGcopy_from_user)
+ NG_DO_PATCH(raw_copy_to_user, NGcopy_to_user)
retl
nop
.size niagara_patch_copyops,.-niagara_patch_copyops
.text; \
.align 4;
-#define FUNC_NAME ___copy_from_user
+#define FUNC_NAME raw_copy_from_user
#define LOAD(type,addr,dest) type##a [addr] %asi, dest
#define LOAD_BLK(addr,dest) ldda [addr] ASI_BLK_AIUS, dest
#define EX_RETVAL(x) 0
#define PREAMBLE \
rd %asi, %g1; \
cmp %g1, ASI_AIUS; \
- bne,pn %icc, ___copy_in_user; \
+ bne,pn %icc, raw_copy_in_user; \
nop; \
#include "U1memcpy.S"
.text; \
.align 4;
-#define FUNC_NAME ___copy_to_user
+#define FUNC_NAME raw_copy_to_user
#define STORE(type,src,addr) type##a src, [addr] ASI_AIUS
#define STORE_BLK(src,addr) stda src, [addr] ASI_BLK_AIUS
#define EX_RETVAL(x) 0
#define PREAMBLE \
rd %asi, %g1; \
cmp %g1, ASI_AIUS; \
- bne,pn %icc, ___copy_in_user; \
+ bne,pn %icc, raw_copy_in_user; \
nop; \
#include "U1memcpy.S"
#define PREAMBLE \
rd %asi, %g1; \
cmp %g1, ASI_AIUS; \
- bne,pn %icc, ___copy_in_user; \
+ bne,pn %icc, raw_copy_in_user; \
nop; \
#include "U3memcpy.S"
.type cheetah_patch_copyops,#function
cheetah_patch_copyops:
ULTRA3_DO_PATCH(memcpy, U3memcpy)
- ULTRA3_DO_PATCH(___copy_from_user, U3copy_from_user)
- ULTRA3_DO_PATCH(___copy_to_user, U3copy_to_user)
+ ULTRA3_DO_PATCH(raw_copy_from_user, U3copy_from_user)
+ ULTRA3_DO_PATCH(raw_copy_to_user, U3copy_to_user)
retl
nop
.size cheetah_patch_copyops,.-cheetah_patch_copyops
* to copy register windows around during thread cloning.
*/
-ENTRY(___copy_in_user) /* %o0=dst, %o1=src, %o2=len */
+ENTRY(raw_copy_in_user) /* %o0=dst, %o1=src, %o2=len */
cmp %o2, 0
be,pn %XCC, 85f
or %o0, %o1, %o3
add %o0, 1, %o0
retl
clr %o0
-ENDPROC(___copy_in_user)
-EXPORT_SYMBOL(___copy_in_user)
+ENDPROC(raw_copy_in_user)
+EXPORT_SYMBOL(raw_copy_in_user)
97:
mov %o2, %g3
fixupretl:
- sethi %hi(PAGE_OFFSET), %g1
- cmp %o0, %g1
- blu 1f
- cmp %o1, %g1
- bgeu 1f
- ld [%g6 + TI_PREEMPT], %g1
- cmp %g1, 0
- bne 1f
- nop
- save %sp, -64, %sp
- mov %i0, %o0
- call __bzero
- mov %g3, %o1
- restore
-1: retl
+ retl
mov %g3, %o0
/* exception routine sets %g2 to (broken_insn - first_insn)>>2 */
pte_val(entry) = pte_val(entry) & ~_PAGE_SZALL_4V;
switch (shift) {
+ case HPAGE_2GB_SHIFT:
+ hugepage_size = _PAGE_SZ2GB_4V;
+ pte_val(entry) |= _PAGE_PMD_HUGE;
+ break;
case HPAGE_256MB_SHIFT:
hugepage_size = _PAGE_SZ256MB_4V;
pte_val(entry) |= _PAGE_PMD_HUGE;
unsigned int shift;
switch (tte_szbits) {
+ case _PAGE_SZ2GB_4V:
+ shift = HPAGE_2GB_SHIFT;
+ break;
case _PAGE_SZ256MB_4V:
shift = HPAGE_256MB_SHIFT;
break;
if (!pmd)
return NULL;
- if (sz == PMD_SHIFT)
+ if (sz >= PMD_SIZE)
pte = (pte_t *)pmd;
else
pte = pte_alloc_map(mm, pmd, addr);
pgd_t *pgd;
unsigned long next;
+ addr &= PMD_MASK;
+ if (addr < floor) {
+ addr += PMD_SIZE;
+ if (!addr)
+ return;
+ }
+ if (ceiling) {
+ ceiling &= PMD_MASK;
+ if (!ceiling)
+ return;
+ }
+ if (end - 1 > ceiling - 1)
+ end -= PMD_SIZE;
+ if (addr > end - 1)
+ return;
+
pgd = pgd_offset(tlb->mm, addr);
do {
next = pgd_addr_end(addr, end);
hugepage_shift = ilog2(hugepage_size);
switch (hugepage_shift) {
+ case HPAGE_2GB_SHIFT:
+ hv_pgsz_mask = HV_PGSZ_MASK_2GB;
+ hv_pgsz_idx = HV_PGSZ_IDX_2GB;
+ break;
case HPAGE_256MB_SHIFT:
hv_pgsz_mask = HV_PGSZ_MASK_256MB;
hv_pgsz_idx = HV_PGSZ_IDX_256MB;
if ((long)addr < 0L) {
unsigned long pa = __pa(addr);
- if ((addr >> max_phys_bits) != 0UL)
+ if ((pa >> max_phys_bits) != 0UL)
return false;
return pfn_valid(pa >> PAGE_SHIFT);
enum mbus_module srmmu_modtype;
static unsigned int hwbug_bitmask;
int vac_cache_size;
+EXPORT_SYMBOL(vac_cache_size);
int vac_line_size;
extern struct resource sparc_iomap;
if (pte_val(*pte) & _PAGE_VALID) {
bool exec = pte_exec(*pte);
- tlb_batch_add_one(mm, vaddr, exec, false);
+ tlb_batch_add_one(mm, vaddr, exec, PAGE_SHIFT);
}
pte++;
vaddr += PAGE_SIZE;
pte_t orig_pte = __pte(pmd_val(orig));
bool exec = pte_exec(orig_pte);
- tlb_batch_add_one(mm, addr, exec, true);
+ tlb_batch_add_one(mm, addr, exec, REAL_HPAGE_SHIFT);
tlb_batch_add_one(mm, addr + REAL_HPAGE_SIZE, exec,
- true);
+ REAL_HPAGE_SHIFT);
} else {
tlb_batch_pmd_scan(mm, addr, orig);
}
spin_lock_irqsave(&mm->context.lock, flags);
- if (tb->hugepage_shift < HPAGE_SHIFT) {
+ if (tb->hugepage_shift < REAL_HPAGE_SHIFT) {
base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
if (tlb_type == cheetah_plus || tlb_type == hypervisor)
spin_lock_irqsave(&mm->context.lock, flags);
- if (hugepage_shift < HPAGE_SHIFT) {
+ if (hugepage_shift < REAL_HPAGE_SHIFT) {
base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
if (tlb_type == cheetah_plus || tlb_type == hypervisor)
CONFIG_USB_OHCI_HCD=y
CONFIG_USB_STORAGE=y
CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_TILE=y
CONFIG_EXT2_FS=y
# CONFIG_VGA_ARB is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_TILE=y
CONFIG_EXT2_FS=y
generic-y += emergency-restart.h
generic-y += errno.h
generic-y += exec.h
+generic-y += extable.h
generic-y += fb.h
generic-y += fcntl.h
generic-y += hw_irq.h
/*
* User space memory access functions
*/
-#include <linux/sched.h>
#include <linux/mm.h>
#include <asm-generic/uaccess-unaligned.h>
#include <asm/processor.h>
#include <asm/page.h>
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
/*
* The fs value determines whether argument validity checking should be
* performed or not. If get_fs() == USER_DS, checking is performed, with
likely(__range_ok((unsigned long)(addr), (size)) == 0); \
})
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue. No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path. This means when everything is well,
- * we don't even have to jump over them. Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry {
- unsigned long insn, fixup;
-};
-
-extern int fixup_exception(struct pt_regs *regs);
+#include <asm/extable.h>
/*
* This is a type: either unsigned long, if the argument fits into
((x) = 0, -EFAULT); \
})
-/**
- * __copy_to_user() - copy data into user space, with less checking.
- * @to: Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- * enabled.
- *
- * Copy data from kernel space to user space. Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- *
- * An alternate version - __copy_to_user_inatomic() - is designed
- * to be called from atomic context, typically bracketed by calls
- * to pagefault_disable() and pagefault_enable().
- */
-extern unsigned long __must_check __copy_to_user_inatomic(
- void __user *to, const void *from, unsigned long n);
-
-static inline unsigned long __must_check
-__copy_to_user(void __user *to, const void *from, unsigned long n)
-{
- might_fault();
- return __copy_to_user_inatomic(to, from, n);
-}
-
-static inline unsigned long __must_check
-copy_to_user(void __user *to, const void *from, unsigned long n)
-{
- if (access_ok(VERIFY_WRITE, to, n))
- n = __copy_to_user(to, from, n);
- return n;
-}
-
-/**
- * __copy_from_user() - copy data from user space, with less checking.
- * @to: Destination address, in kernel space.
- * @from: Source address, in user space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- * enabled.
- *
- * Copy data from user space to kernel space. Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- *
- * If some data could not be copied, this function will pad the copied
- * data to the requested size using zero bytes.
- *
- * An alternate version - __copy_from_user_inatomic() - is designed
- * to be called from atomic context, typically bracketed by calls
- * to pagefault_disable() and pagefault_enable(). This version
- * does *NOT* pad with zeros.
- */
-extern unsigned long __must_check __copy_from_user_inatomic(
- void *to, const void __user *from, unsigned long n);
-extern unsigned long __must_check __copy_from_user_zeroing(
- void *to, const void __user *from, unsigned long n);
-
-static inline unsigned long __must_check
-__copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- might_fault();
- return __copy_from_user_zeroing(to, from, n);
-}
-
-static inline unsigned long __must_check
-_copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- if (access_ok(VERIFY_READ, from, n))
- n = __copy_from_user(to, from, n);
- else
- memset(to, 0, n);
- return n;
-}
-
-extern void __compiletime_error("usercopy buffer size is too small")
-__bad_copy_user(void);
-
-static inline void copy_user_overflow(int size, unsigned long count)
-{
- WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
-}
-
-static inline unsigned long __must_check copy_from_user(void *to,
- const void __user *from,
- unsigned long n)
-{
- int sz = __compiletime_object_size(to);
-
- if (likely(sz == -1 || sz >= n))
- n = _copy_from_user(to, from, n);
- else if (!__builtin_constant_p(n))
- copy_user_overflow(sz, n);
- else
- __bad_copy_user();
-
- return n;
-}
+extern unsigned long __must_check
+raw_copy_to_user(void __user *to, const void *from, unsigned long n);
+extern unsigned long __must_check
+raw_copy_from_user(void *to, const void __user *from, unsigned long n);
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
#ifdef __tilegx__
-/**
- * __copy_in_user() - copy data within user space, with less checking.
- * @to: Destination address, in user space.
- * @from: Source address, in user space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- * enabled.
- *
- * Copy data from user space to user space. Caller must check
- * the specified blocks with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- */
-extern unsigned long __copy_in_user_inatomic(
+extern unsigned long raw_copy_in_user(
void __user *to, const void __user *from, unsigned long n);
-
-static inline unsigned long __must_check
-__copy_in_user(void __user *to, const void __user *from, unsigned long n)
-{
- might_fault();
- return __copy_in_user_inatomic(to, from, n);
-}
-
-static inline unsigned long __must_check
-copy_in_user(void __user *to, const void __user *from, unsigned long n)
-{
- if (access_ok(VERIFY_WRITE, to, n) && access_ok(VERIFY_READ, from, n))
- n = __copy_in_user(to, from, n);
- return n;
-}
#endif
.name = "tile timer",
.features = CLOCK_EVT_FEAT_ONESHOT,
.min_delta_ns = 1000,
+ .min_delta_ticks = 1,
+ .max_delta_ticks = MAX_TICK,
.rating = 100,
.irq = -1,
.set_next_event = tile_timer_set_next_event,
/* arch/tile/lib/, various memcpy files */
EXPORT_SYMBOL(memcpy);
-EXPORT_SYMBOL(__copy_to_user_inatomic);
-EXPORT_SYMBOL(__copy_from_user_inatomic);
-EXPORT_SYMBOL(__copy_from_user_zeroing);
+EXPORT_SYMBOL(raw_copy_to_user);
+EXPORT_SYMBOL(raw_copy_from_user);
#ifdef __tilegx__
-EXPORT_SYMBOL(__copy_in_user_inatomic);
+EXPORT_SYMBOL(raw_copy_in_user);
#endif
/* hypervisor glue */
#define IS_MEMCPY 0
#define IS_COPY_FROM_USER 1
-#define IS_COPY_FROM_USER_ZEROING 2
#define IS_COPY_TO_USER -1
.section .text.memcpy_common, "ax"
9
-/* __copy_from_user_inatomic takes the kernel target address in r0,
+/* raw_copy_from_user takes the kernel target address in r0,
* the user source in r1, and the bytes to copy in r2.
* It returns the number of uncopiable bytes (hopefully zero) in r0.
*/
-ENTRY(__copy_from_user_inatomic)
-.type __copy_from_user_inatomic, @function
- FEEDBACK_ENTER_EXPLICIT(__copy_from_user_inatomic, \
+ENTRY(raw_copy_from_user)
+.type raw_copy_from_user, @function
+ FEEDBACK_ENTER_EXPLICIT(raw_copy_from_user, \
.text.memcpy_common, \
- .Lend_memcpy_common - __copy_from_user_inatomic)
+ .Lend_memcpy_common - raw_copy_from_user)
{ movei r29, IS_COPY_FROM_USER; j memcpy_common }
- .size __copy_from_user_inatomic, . - __copy_from_user_inatomic
+ .size raw_copy_from_user, . - raw_copy_from_user
-/* __copy_from_user_zeroing is like __copy_from_user_inatomic, but
- * any uncopiable bytes are zeroed in the target.
- */
-ENTRY(__copy_from_user_zeroing)
-.type __copy_from_user_zeroing, @function
- FEEDBACK_REENTER(__copy_from_user_inatomic)
- { movei r29, IS_COPY_FROM_USER_ZEROING; j memcpy_common }
- .size __copy_from_user_zeroing, . - __copy_from_user_zeroing
-
-/* __copy_to_user_inatomic takes the user target address in r0,
+/* raw_copy_to_user takes the user target address in r0,
* the kernel source in r1, and the bytes to copy in r2.
* It returns the number of uncopiable bytes (hopefully zero) in r0.
*/
-ENTRY(__copy_to_user_inatomic)
-.type __copy_to_user_inatomic, @function
- FEEDBACK_REENTER(__copy_from_user_inatomic)
+ENTRY(raw_copy_to_user)
+.type raw_copy_to_user, @function
+ FEEDBACK_REENTER(raw_copy_from_user)
{ movei r29, IS_COPY_TO_USER; j memcpy_common }
- .size __copy_to_user_inatomic, . - __copy_to_user_inatomic
+ .size raw_copy_to_user, . - raw_copy_to_user
ENTRY(memcpy)
.type memcpy, @function
- FEEDBACK_REENTER(__copy_from_user_inatomic)
+ FEEDBACK_REENTER(raw_copy_from_user)
{ movei r29, IS_MEMCPY }
.size memcpy, . - memcpy
/* Fall through */
{ bnzt r2, copy_from_user_fixup_loop }
.Lcopy_from_user_fixup_zero_remainder:
- { bbs r29, 2f } /* low bit set means IS_COPY_FROM_USER */
- /* byte-at-a-time loop faulted, so zero the rest. */
- { move r3, r2; bz r2, 2f /* should be impossible, but handle it. */ }
-1: { sb r0, zero; addi r0, r0, 1; addi r3, r3, -1 }
- { bnzt r3, 1b }
-2: move lr, r27
+ move lr, r27
{ move r0, r2; jrp lr }
copy_to_user_fixup_loop:
__v; \
})
-#define USERCOPY_FUNC __copy_to_user_inatomic
+#define USERCOPY_FUNC raw_copy_to_user
#define ST1(p, v) _ST((p), st1, (v))
#define ST2(p, v) _ST((p), st2, (v))
#define ST4(p, v) _ST((p), st4, (v))
#define LD8 LD
#include "memcpy_64.c"
-#define USERCOPY_FUNC __copy_from_user_inatomic
+#define USERCOPY_FUNC raw_copy_from_user
#define ST1 ST
#define ST2 ST
#define ST4 ST
#define LD8(p) _LD((p), ld)
#include "memcpy_64.c"
-#define USERCOPY_FUNC __copy_in_user_inatomic
+#define USERCOPY_FUNC raw_copy_in_user
#define ST1(p, v) _ST((p), st1, (v))
#define ST2(p, v) _ST((p), st2, (v))
#define ST4(p, v) _ST((p), st4, (v))
#define LD4(p) _LD((p), ld4u)
#define LD8(p) _LD((p), ld)
#include "memcpy_64.c"
-
-unsigned long __copy_from_user_zeroing(void *to, const void __user *from,
- unsigned long n)
-{
- unsigned long rc = __copy_from_user_inatomic(to, from, n);
- if (unlikely(rc))
- memset(to + n - rc, 0, rc);
- return rc;
-}
generic-y += device.h
generic-y += emergency-restart.h
generic-y += exec.h
+generic-y += extable.h
generic-y += ftrace.h
generic-y += futex.h
generic-y += hardirq.h
#ifndef __UM_UACCESS_H
#define __UM_UACCESS_H
-#include <asm/thread_info.h>
#include <asm/elf.h>
#define __under_task_size(addr, size) \
#define __addr_range_nowrap(addr, size) \
((unsigned long) (addr) <= ((unsigned long) (addr) + (size)))
-extern long __copy_from_user(void *to, const void __user *from, unsigned long n);
-extern long __copy_to_user(void __user *to, const void *from, unsigned long n);
+extern unsigned long raw_copy_from_user(void *to, const void __user *from, unsigned long n);
+extern unsigned long raw_copy_to_user(void __user *to, const void *from, unsigned long n);
extern long __strncpy_from_user(char *dst, const char __user *src, long count);
extern long __strnlen_user(const void __user *str, long len);
extern unsigned long __clear_user(void __user *mem, unsigned long len);
/* Teach asm-generic/uaccess.h that we have C functions for these. */
#define __access_ok __access_ok
#define __clear_user __clear_user
-#define __copy_to_user __copy_to_user
-#define __copy_from_user __copy_from_user
#define __strnlen_user __strnlen_user
#define __strncpy_from_user __strncpy_from_user
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
#include <asm-generic/uaccess.h>
return __addr_range_nowrap(addr, size) &&
(__under_task_size(addr, size) ||
__access_ok_vsyscall(addr, size) ||
- segment_eq(get_fs(), KERNEL_DS));
+ uaccess_kernel());
}
#endif
extern void maybe_sigio_broken(int fd, int read);
extern void sigio_broken(int fd, int read);
-/* sys-x86_64/prctl.c */
-extern int os_arch_prctl(int pid, int code, unsigned long *addr);
+/* prctl.c */
+extern int os_arch_prctl(int pid, int option, unsigned long *arg2);
/* tty.c */
extern int get_pty(void);
return 0;
}
-long __copy_from_user(void *to, const void __user *from, unsigned long n)
+unsigned long raw_copy_from_user(void *to, const void __user *from, unsigned long n)
{
- if (segment_eq(get_fs(), KERNEL_DS)) {
+ if (uaccess_kernel()) {
memcpy(to, (__force void*)from, n);
return 0;
}
return buffer_op((unsigned long) from, n, 0, copy_chunk_from_user, &to);
}
-EXPORT_SYMBOL(__copy_from_user);
+EXPORT_SYMBOL(raw_copy_from_user);
static int copy_chunk_to_user(unsigned long to, int len, void *arg)
{
return 0;
}
-long __copy_to_user(void __user *to, const void *from, unsigned long n)
+unsigned long raw_copy_to_user(void __user *to, const void *from, unsigned long n)
{
- if (segment_eq(get_fs(), KERNEL_DS)) {
+ if (uaccess_kernel()) {
memcpy((__force void *) to, from, n);
return 0;
}
return buffer_op((unsigned long) to, n, 1, copy_chunk_to_user, &from);
}
-EXPORT_SYMBOL(__copy_to_user);
+EXPORT_SYMBOL(raw_copy_to_user);
static int strncpy_chunk_from_user(unsigned long from, int len, void *arg)
{
long n;
char *ptr = dst;
- if (segment_eq(get_fs(), KERNEL_DS)) {
+ if (uaccess_kernel()) {
strncpy(dst, (__force void *) src, count);
return strnlen(dst, count);
}
unsigned long __clear_user(void __user *mem, unsigned long len)
{
- if (segment_eq(get_fs(), KERNEL_DS)) {
+ if (uaccess_kernel()) {
memset((__force void*)mem, 0, len);
return 0;
}
{
int count = 0, n;
- if (segment_eq(get_fs(), KERNEL_DS))
+ if (uaccess_kernel())
return strnlen((__force char*)str, len) + 1;
n = buffer_op((unsigned long) str, len, 0, strnlen_chunk, &count);
.set_next_event = itimer_next_event,
.shift = 0,
.max_delta_ns = 0xffffffff,
- .min_delta_ns = TIMER_MIN_DELTA, //microsecond resolution should be enough for anyone, same as 640K RAM
+ .max_delta_ticks = 0xffffffff,
+ .min_delta_ns = TIMER_MIN_DELTA,
+ .min_delta_ticks = TIMER_MIN_DELTA, // microsecond resolution should be enough for anyone, same as 640K RAM
.irq = 0,
.mult = 1,
};
generic-y += emergency-restart.h
generic-y += errno.h
generic-y += exec.h
+generic-y += extable.h
generic-y += fb.h
generic-y += fcntl.h
generic-y += ftrace.h
#ifndef __UNICORE_UACCESS_H__
#define __UNICORE_UACCESS_H__
-#include <linux/thread_info.h>
-#include <linux/errno.h>
-
#include <asm/memory.h>
-#define __copy_from_user __copy_from_user
-#define __copy_to_user __copy_to_user
#define __strncpy_from_user __strncpy_from_user
#define __strnlen_user __strnlen_user
#define __clear_user __clear_user
-#define __kernel_ok (segment_eq(get_fs(), KERNEL_DS))
+#define __kernel_ok (uaccess_kernel())
#define __user_ok(addr, size) (((size) <= TASK_SIZE) \
&& ((addr) <= TASK_SIZE - (size)))
#define __access_ok(addr, size) (__kernel_ok || __user_ok((addr), (size)))
extern unsigned long __must_check
-__copy_from_user(void *to, const void __user *from, unsigned long n);
+raw_copy_from_user(void *to, const void __user *from, unsigned long n);
extern unsigned long __must_check
-__copy_to_user(void __user *to, const void *from, unsigned long n);
+raw_copy_to_user(void __user *to, const void *from, unsigned long n);
extern unsigned long __must_check
__clear_user(void __user *addr, unsigned long n);
extern unsigned long __must_check
__strncpy_from_user(char *to, const char __user *from, unsigned long count);
extern unsigned long
__strnlen_user(const char __user *s, long n);
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
#include <asm-generic/uaccess.h>
-extern int fixup_exception(struct pt_regs *regs);
-
#endif /* __UNICORE_UACCESS_H__ */
EXPORT_SYMBOL(copy_page);
-EXPORT_SYMBOL(__copy_from_user);
-EXPORT_SYMBOL(__copy_to_user);
+EXPORT_SYMBOL(raw_copy_from_user);
+EXPORT_SYMBOL(raw_copy_to_user);
EXPORT_SYMBOL(__clear_user);
EXPORT_SYMBOL(__ashldi3);
buf, interrupts_enabled(regs) ? "n" : "ff",
fast_interrupts_enabled(regs) ? "n" : "ff",
processor_modes[processor_mode(regs)],
- segment_eq(get_fs(), get_ds()) ? "kernel" : "user");
+ uaccess_kernel() ? "kernel" : "user");
{
unsigned int ctrl;
ckevt_puv3_osmr0.max_delta_ns =
clockevent_delta2ns(0x7fffffff, &ckevt_puv3_osmr0);
+ ckevt_puv3_osmr0.max_delta_ticks = 0x7fffffff;
ckevt_puv3_osmr0.min_delta_ns =
clockevent_delta2ns(MIN_OSCR_DELTA * 2, &ckevt_puv3_osmr0) + 1;
+ ckevt_puv3_osmr0.min_delta_ticks = MIN_OSCR_DELTA * 2;
ckevt_puv3_osmr0.cpumask = cpumask_of(0);
setup_irq(IRQ_TIMER0, &puv3_timer_irq);
/*
* Prototype:
*
- * size_t __copy_from_user(void *to, const void *from, size_t n)
+ * size_t raw_copy_from_user(void *to, const void *from, size_t n)
*
* Purpose:
*
.text
-ENTRY(__copy_from_user)
+ENTRY(raw_copy_from_user)
#include "copy_template.S"
-ENDPROC(__copy_from_user)
+ENDPROC(raw_copy_from_user)
.pushsection .fixup,"ax"
.align 0
copy_abort_preamble
- ldm.w (r1, r2), [sp]+
- sub r3, r0, r1
- rsub r2, r3, r2
- stw r2, [sp]
- mov r1, #0
- b.l memset
- ldw.w r0, [sp]+, #4
+ ldm.w (r1, r2, r3), [sp]+
+ sub r0, r0, r1
+ rsub r0, r0, r2
copy_abort_end
.popsection
/*
* Prototype:
*
- * size_t __copy_to_user(void *to, const void *from, size_t n)
+ * size_t raw_copy_to_user(void *to, const void *from, size_t n)
*
* Purpose:
*
.text
-WEAK(__copy_to_user)
+WEAK(raw_copy_to_user)
#include "copy_template.S"
-ENDPROC(__copy_to_user)
+ENDPROC(raw_copy_to_user)
.pushsection .fixup,"ax"
.align 0
select HAVE_ACPI_APEI_NMI if ACPI
select HAVE_ALIGNED_STRUCT_PAGE if SLUB
select HAVE_ARCH_AUDITSYSCALL
- select HAVE_ARCH_HARDENED_USERCOPY
select HAVE_ARCH_HUGE_VMAP if X86_64 || X86_PAE
select HAVE_ARCH_JUMP_LABEL
select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP
The action the kernel takes depends on the severity of the problem,
ranging from warning messages to halting the machine.
+config X86_MCELOG_LEGACY
+ bool "Support for deprecated /dev/mcelog character device"
+ depends on X86_MCE
+ ---help---
+ Enable support for /dev/mcelog which is needed by the old mcelog
+ userspace logging daemon. Consider switching to the new generation
+ rasdaemon solution.
+
config X86_MCE_INTEL
def_bool y
prompt "Intel MCE features"
def_bool y
config X86_MCE_INJECT
- depends on X86_MCE && X86_LOCAL_APIC
+ depends on X86_MCE && X86_LOCAL_APIC && X86_MCELOG_LEGACY
tristate "Machine check injector support"
---help---
Provide support for injecting machine checks for testing purposes.
config RANDOMIZE_BASE
bool "Randomize the address of the kernel image (KASLR)"
depends on RELOCATABLE
- default n
+ default y
---help---
In support of Kernel Address Space Layout Randomization (KASLR),
this randomizes the physical address at which the kernel image
theoretically possible, but the implementations are further
limited due to memory layouts.
- If unsure, say N.
+ If unsure, say Y.
# Relocation on x86 needs some additional build support
config X86_NEED_RELOCS
configuration have in average 30,000 different possible virtual
addresses for each memory section.
- If unsure, say N.
+ If unsure, say Y.
config RANDOMIZE_MEMORY_PHYSICAL_PADDING
hex "Physical memory mapping padding" if EXPERT
else
ifeq ($(call cc-option-yn, -mfentry), n)
ACCUMULATE_OUTGOING_ARGS := 1
+
+ # GCC ignores '-maccumulate-outgoing-args' when used with '-Os'.
+ # If '-Os' is enabled, disable it and print a warning.
+ ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
+ undefine CONFIG_CC_OPTIMIZE_FOR_SIZE
+ $(warning Disabling CONFIG_CC_OPTIMIZE_FOR_SIZE. Your compiler does not have -mfentry so you cannot optimize for size with CONFIG_FUNCTION_GRAPH_TRACER.)
+ endif
+
endif
endif
endif
#ifndef BOOT_BOOT_H
#define BOOT_BOOT_H
-#define STACK_SIZE 512 /* Minimum number of bytes for stack */
+#define STACK_SIZE 1024 /* Minimum number of bytes for stack */
#ifndef __ASSEMBLY__
#include <linux/efi.h>
#include <linux/pci.h>
+
#include <asm/efi.h>
+#include <asm/e820/types.h>
#include <asm/setup.h>
#include <asm/desc.h>
unsigned long size;
e820ext->type = SETUP_E820_EXT;
- e820ext->len = nr_entries * sizeof(struct e820entry);
+ e820ext->len = nr_entries * sizeof(struct boot_e820_entry);
e820ext->next = 0;
data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
static efi_status_t setup_e820(struct boot_params *params,
struct setup_data *e820ext, u32 e820ext_size)
{
- struct e820entry *e820_map = ¶ms->e820_map[0];
+ struct boot_e820_entry *entry = params->e820_table;
struct efi_info *efi = ¶ms->efi_info;
- struct e820entry *prev = NULL;
+ struct boot_e820_entry *prev = NULL;
u32 nr_entries;
u32 nr_desc;
int i;
case EFI_MEMORY_MAPPED_IO:
case EFI_MEMORY_MAPPED_IO_PORT_SPACE:
case EFI_PAL_CODE:
- e820_type = E820_RESERVED;
+ e820_type = E820_TYPE_RESERVED;
break;
case EFI_UNUSABLE_MEMORY:
- e820_type = E820_UNUSABLE;
+ e820_type = E820_TYPE_UNUSABLE;
break;
case EFI_ACPI_RECLAIM_MEMORY:
- e820_type = E820_ACPI;
+ e820_type = E820_TYPE_ACPI;
break;
case EFI_LOADER_CODE:
case EFI_BOOT_SERVICES_CODE:
case EFI_BOOT_SERVICES_DATA:
case EFI_CONVENTIONAL_MEMORY:
- e820_type = E820_RAM;
+ e820_type = E820_TYPE_RAM;
break;
case EFI_ACPI_MEMORY_NVS:
- e820_type = E820_NVS;
+ e820_type = E820_TYPE_NVS;
break;
case EFI_PERSISTENT_MEMORY:
- e820_type = E820_PMEM;
+ e820_type = E820_TYPE_PMEM;
break;
default:
continue;
}
- if (nr_entries == ARRAY_SIZE(params->e820_map)) {
- u32 need = (nr_desc - i) * sizeof(struct e820entry) +
+ if (nr_entries == ARRAY_SIZE(params->e820_table)) {
+ u32 need = (nr_desc - i) * sizeof(struct e820_entry) +
sizeof(struct setup_data);
if (!e820ext || e820ext_size < need)
return EFI_BUFFER_TOO_SMALL;
/* boot_params map full, switch to e820 extended */
- e820_map = (struct e820entry *)e820ext->data;
+ entry = (struct boot_e820_entry *)e820ext->data;
}
- e820_map->addr = d->phys_addr;
- e820_map->size = d->num_pages << PAGE_SHIFT;
- e820_map->type = e820_type;
- prev = e820_map++;
+ entry->addr = d->phys_addr;
+ entry->size = d->num_pages << PAGE_SHIFT;
+ entry->type = e820_type;
+ prev = entry++;
nr_entries++;
}
- if (nr_entries > ARRAY_SIZE(params->e820_map)) {
- u32 nr_e820ext = nr_entries - ARRAY_SIZE(params->e820_map);
+ if (nr_entries > ARRAY_SIZE(params->e820_table)) {
+ u32 nr_e820ext = nr_entries - ARRAY_SIZE(params->e820_table);
add_e820ext(params, e820ext, nr_e820ext);
nr_entries -= nr_e820ext;
unsigned long size;
size = sizeof(struct setup_data) +
- sizeof(struct e820entry) * nr_desc;
+ sizeof(struct e820_entry) * nr_desc;
if (*e820ext) {
efi_call_early(free_pool, *e820ext);
if (first) {
nr_desc = *map->buff_size / *map->desc_size;
- if (nr_desc > ARRAY_SIZE(p->boot_params->e820_map)) {
+ if (nr_desc > ARRAY_SIZE(p->boot_params->e820_table)) {
u32 nr_e820ext = nr_desc -
- ARRAY_SIZE(p->boot_params->e820_map);
+ ARRAY_SIZE(p->boot_params->e820_table);
status = alloc_e820ext(nr_e820ext, &p->e820ext,
&p->e820ext_size);
return 0;
}
-static void process_e820_entry(struct e820entry *entry,
+static void process_e820_entry(struct boot_e820_entry *entry,
unsigned long minimum,
unsigned long image_size)
{
unsigned long start_orig;
/* Skip non-RAM entries. */
- if (entry->type != E820_RAM)
+ if (entry->type != E820_TYPE_RAM)
return;
/* On 32-bit, ignore entries entirely above our maximum. */
/* Verify potential e820 positions, appending to slots list. */
for (i = 0; i < boot_params->e820_entries; i++) {
- process_e820_entry(&boot_params->e820_map[i], minimum,
+ process_e820_entry(&boot_params->e820_table[i], minimum,
image_size);
if (slot_area_index == MAX_SLOT_AREA) {
debug_putstr("Aborted e820 scan (slot_areas full)!\n");
add_identity_map(random_addr, output_size);
*output = random_addr;
}
+
+ /*
+ * This loads the identity mapping page table.
+ * This should only be done if a new physical address
+ * is found for the kernel, otherwise we should keep
+ * the old page table to make it be like the "nokaslr"
+ * case.
+ */
+ finalize_identity_maps();
}
- /* This actually loads the identity pagetable on x86_64. */
- finalize_identity_maps();
/* Pick random virtual address starting from LOAD_PHYSICAL_ADDR. */
if (IS_ENABLED(CONFIG_X86_64))
#include <asm/segment.h>
#include <generated/utsrelease.h>
#include <asm/boot.h>
-#include <asm/e820.h>
#include <asm/page_types.h>
#include <asm/setup.h>
#include <asm/bootparam.h>
{
int count = 0;
struct biosregs ireg, oreg;
- struct e820entry *desc = boot_params.e820_map;
- static struct e820entry buf; /* static so it is zeroed */
+ struct boot_e820_entry *desc = boot_params.e820_table;
+ static struct boot_e820_entry buf; /* static so it is zeroed */
initregs(&ireg);
ireg.ax = 0xe820;
*desc++ = buf;
count++;
- } while (ireg.ebx && count < ARRAY_SIZE(boot_params.e820_map));
+ } while (ireg.ebx && count < ARRAY_SIZE(boot_params.e820_table));
return boot_params.e820_entries = count;
}
CONFIG_HZ_1000=y
CONFIG_KEXEC=y
CONFIG_CRASH_DUMP=y
+CONFIG_RANDOMIZE_BASE=y
+CONFIG_RANDOMIZE_MEMORY=y
# CONFIG_COMPAT_VDSO is not set
CONFIG_HIBERNATION=y
CONFIG_PM_DEBUG=y
CONFIG_HZ_1000=y
CONFIG_KEXEC=y
CONFIG_CRASH_DUMP=y
+CONFIG_RANDOMIZE_BASE=y
+CONFIG_RANDOMIZE_MEMORY=y
# CONFIG_COMPAT_VDSO is not set
CONFIG_HIBERNATION=y
CONFIG_PM_DEBUG=y
381 i386 pkey_alloc sys_pkey_alloc
382 i386 pkey_free sys_pkey_free
383 i386 statx sys_statx
+384 i386 arch_prctl sys_arch_prctl compat_sys_arch_prctl
* published by the Free Software Foundation.
*/
+#define pr_fmt(fmt) "perf/amd_iommu: " fmt
+
#include <linux/perf_event.h>
#include <linux/init.h>
#include <linux/cpumask.h>
#define COUNTER_SHIFT 16
-#define _GET_BANK(ev) ((u8)(ev->hw.extra_reg.reg >> 8))
-#define _GET_CNTR(ev) ((u8)(ev->hw.extra_reg.reg))
+/* iommu pmu conf masks */
+#define GET_CSOURCE(x) ((x)->conf & 0xFFULL)
+#define GET_DEVID(x) (((x)->conf >> 8) & 0xFFFFULL)
+#define GET_DOMID(x) (((x)->conf >> 24) & 0xFFFFULL)
+#define GET_PASID(x) (((x)->conf >> 40) & 0xFFFFFULL)
-/* iommu pmu config masks */
-#define _GET_CSOURCE(ev) ((ev->hw.config & 0xFFULL))
-#define _GET_DEVID(ev) ((ev->hw.config >> 8) & 0xFFFFULL)
-#define _GET_PASID(ev) ((ev->hw.config >> 24) & 0xFFFFULL)
-#define _GET_DOMID(ev) ((ev->hw.config >> 40) & 0xFFFFULL)
-#define _GET_DEVID_MASK(ev) ((ev->hw.extra_reg.config) & 0xFFFFULL)
-#define _GET_PASID_MASK(ev) ((ev->hw.extra_reg.config >> 16) & 0xFFFFULL)
-#define _GET_DOMID_MASK(ev) ((ev->hw.extra_reg.config >> 32) & 0xFFFFULL)
+/* iommu pmu conf1 masks */
+#define GET_DEVID_MASK(x) ((x)->conf1 & 0xFFFFULL)
+#define GET_DOMID_MASK(x) (((x)->conf1 >> 16) & 0xFFFFULL)
+#define GET_PASID_MASK(x) (((x)->conf1 >> 32) & 0xFFFFFULL)
-static struct perf_amd_iommu __perf_iommu;
+#define IOMMU_NAME_SIZE 16
struct perf_amd_iommu {
+ struct list_head list;
struct pmu pmu;
+ struct amd_iommu *iommu;
+ char name[IOMMU_NAME_SIZE];
u8 max_banks;
u8 max_counters;
u64 cntr_assign_mask;
raw_spinlock_t lock;
- const struct attribute_group *attr_groups[4];
};
-#define format_group attr_groups[0]
-#define cpumask_group attr_groups[1]
-#define events_group attr_groups[2]
-#define null_group attr_groups[3]
+static LIST_HEAD(perf_amd_iommu_list);
/*---------------------------------------------
* sysfs format attributes
*---------------------------------------------*/
PMU_FORMAT_ATTR(csource, "config:0-7");
PMU_FORMAT_ATTR(devid, "config:8-23");
-PMU_FORMAT_ATTR(pasid, "config:24-39");
-PMU_FORMAT_ATTR(domid, "config:40-55");
+PMU_FORMAT_ATTR(domid, "config:24-39");
+PMU_FORMAT_ATTR(pasid, "config:40-59");
PMU_FORMAT_ATTR(devid_mask, "config1:0-15");
-PMU_FORMAT_ATTR(pasid_mask, "config1:16-31");
-PMU_FORMAT_ATTR(domid_mask, "config1:32-47");
+PMU_FORMAT_ATTR(domid_mask, "config1:16-31");
+PMU_FORMAT_ATTR(pasid_mask, "config1:32-51");
static struct attribute *iommu_format_attrs[] = {
&format_attr_csource.attr,
/*---------------------------------------------
* sysfs events attributes
*---------------------------------------------*/
+static struct attribute_group amd_iommu_events_group = {
+ .name = "events",
+};
+
struct amd_iommu_event_desc {
struct kobj_attribute attr;
const char *event;
/*---------------------------------------------*/
-static int get_next_avail_iommu_bnk_cntr(struct perf_amd_iommu *perf_iommu)
+static int get_next_avail_iommu_bnk_cntr(struct perf_event *event)
{
+ struct perf_amd_iommu *piommu = container_of(event->pmu, struct perf_amd_iommu, pmu);
+ int max_cntrs = piommu->max_counters;
+ int max_banks = piommu->max_banks;
+ u32 shift, bank, cntr;
unsigned long flags;
- int shift, bank, cntr, retval;
- int max_banks = perf_iommu->max_banks;
- int max_cntrs = perf_iommu->max_counters;
+ int retval;
- raw_spin_lock_irqsave(&perf_iommu->lock, flags);
+ raw_spin_lock_irqsave(&piommu->lock, flags);
for (bank = 0, shift = 0; bank < max_banks; bank++) {
for (cntr = 0; cntr < max_cntrs; cntr++) {
shift = bank + (bank*3) + cntr;
- if (perf_iommu->cntr_assign_mask & (1ULL<<shift)) {
+ if (piommu->cntr_assign_mask & BIT_ULL(shift)) {
continue;
} else {
- perf_iommu->cntr_assign_mask |= (1ULL<<shift);
- retval = ((u16)((u16)bank<<8) | (u8)(cntr));
+ piommu->cntr_assign_mask |= BIT_ULL(shift);
+ event->hw.iommu_bank = bank;
+ event->hw.iommu_cntr = cntr;
+ retval = 0;
goto out;
}
}
}
retval = -ENOSPC;
out:
- raw_spin_unlock_irqrestore(&perf_iommu->lock, flags);
+ raw_spin_unlock_irqrestore(&piommu->lock, flags);
return retval;
}
static int perf_iommu_event_init(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
- struct perf_amd_iommu *perf_iommu;
- u64 config, config1;
/* test the event attr type check for PMU enumeration */
if (event->attr.type != event->pmu->type)
if (event->cpu < 0)
return -EINVAL;
- perf_iommu = &__perf_iommu;
-
- if (event->pmu != &perf_iommu->pmu)
- return -ENOENT;
-
- if (perf_iommu) {
- config = event->attr.config;
- config1 = event->attr.config1;
- } else {
- return -EINVAL;
- }
-
- /* integrate with iommu base devid (0000), assume one iommu */
- perf_iommu->max_banks =
- amd_iommu_pc_get_max_banks(IOMMU_BASE_DEVID);
- perf_iommu->max_counters =
- amd_iommu_pc_get_max_counters(IOMMU_BASE_DEVID);
- if ((perf_iommu->max_banks == 0) || (perf_iommu->max_counters == 0))
- return -EINVAL;
-
/* update the hw_perf_event struct with the iommu config data */
- hwc->config = config;
- hwc->extra_reg.config = config1;
+ hwc->conf = event->attr.config;
+ hwc->conf1 = event->attr.config1;
return 0;
}
+static inline struct amd_iommu *perf_event_2_iommu(struct perf_event *ev)
+{
+ return (container_of(ev->pmu, struct perf_amd_iommu, pmu))->iommu;
+}
+
static void perf_iommu_enable_event(struct perf_event *ev)
{
- u8 csource = _GET_CSOURCE(ev);
- u16 devid = _GET_DEVID(ev);
+ struct amd_iommu *iommu = perf_event_2_iommu(ev);
+ struct hw_perf_event *hwc = &ev->hw;
+ u8 bank = hwc->iommu_bank;
+ u8 cntr = hwc->iommu_cntr;
u64 reg = 0ULL;
- reg = csource;
- amd_iommu_pc_get_set_reg_val(devid,
- _GET_BANK(ev), _GET_CNTR(ev) ,
- IOMMU_PC_COUNTER_SRC_REG, ®, true);
+ reg = GET_CSOURCE(hwc);
+ amd_iommu_pc_set_reg(iommu, bank, cntr, IOMMU_PC_COUNTER_SRC_REG, ®);
- reg = 0ULL | devid | (_GET_DEVID_MASK(ev) << 32);
+ reg = GET_DEVID_MASK(hwc);
+ reg = GET_DEVID(hwc) | (reg << 32);
if (reg)
- reg |= (1UL << 31);
- amd_iommu_pc_get_set_reg_val(devid,
- _GET_BANK(ev), _GET_CNTR(ev) ,
- IOMMU_PC_DEVID_MATCH_REG, ®, true);
+ reg |= BIT(31);
+ amd_iommu_pc_set_reg(iommu, bank, cntr, IOMMU_PC_DEVID_MATCH_REG, ®);
- reg = 0ULL | _GET_PASID(ev) | (_GET_PASID_MASK(ev) << 32);
+ reg = GET_PASID_MASK(hwc);
+ reg = GET_PASID(hwc) | (reg << 32);
if (reg)
- reg |= (1UL << 31);
- amd_iommu_pc_get_set_reg_val(devid,
- _GET_BANK(ev), _GET_CNTR(ev) ,
- IOMMU_PC_PASID_MATCH_REG, ®, true);
+ reg |= BIT(31);
+ amd_iommu_pc_set_reg(iommu, bank, cntr, IOMMU_PC_PASID_MATCH_REG, ®);
- reg = 0ULL | _GET_DOMID(ev) | (_GET_DOMID_MASK(ev) << 32);
+ reg = GET_DOMID_MASK(hwc);
+ reg = GET_DOMID(hwc) | (reg << 32);
if (reg)
- reg |= (1UL << 31);
- amd_iommu_pc_get_set_reg_val(devid,
- _GET_BANK(ev), _GET_CNTR(ev) ,
- IOMMU_PC_DOMID_MATCH_REG, ®, true);
+ reg |= BIT(31);
+ amd_iommu_pc_set_reg(iommu, bank, cntr, IOMMU_PC_DOMID_MATCH_REG, ®);
}
static void perf_iommu_disable_event(struct perf_event *event)
{
+ struct amd_iommu *iommu = perf_event_2_iommu(event);
+ struct hw_perf_event *hwc = &event->hw;
u64 reg = 0ULL;
- amd_iommu_pc_get_set_reg_val(_GET_DEVID(event),
- _GET_BANK(event), _GET_CNTR(event),
- IOMMU_PC_COUNTER_SRC_REG, ®, true);
+ amd_iommu_pc_set_reg(iommu, hwc->iommu_bank, hwc->iommu_cntr,
+ IOMMU_PC_COUNTER_SRC_REG, ®);
}
static void perf_iommu_start(struct perf_event *event, int flags)
{
struct hw_perf_event *hwc = &event->hw;
- pr_debug("perf: amd_iommu:perf_iommu_start\n");
if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED)))
return;
hwc->state = 0;
if (flags & PERF_EF_RELOAD) {
- u64 prev_raw_count = local64_read(&hwc->prev_count);
- amd_iommu_pc_get_set_reg_val(_GET_DEVID(event),
- _GET_BANK(event), _GET_CNTR(event),
- IOMMU_PC_COUNTER_REG, &prev_raw_count, true);
+ u64 prev_raw_count = local64_read(&hwc->prev_count);
+ struct amd_iommu *iommu = perf_event_2_iommu(event);
+
+ amd_iommu_pc_set_reg(iommu, hwc->iommu_bank, hwc->iommu_cntr,
+ IOMMU_PC_COUNTER_REG, &prev_raw_count);
}
perf_iommu_enable_event(event);
static void perf_iommu_read(struct perf_event *event)
{
- u64 count = 0ULL;
- u64 prev_raw_count = 0ULL;
- u64 delta = 0ULL;
+ u64 count, prev, delta;
struct hw_perf_event *hwc = &event->hw;
- pr_debug("perf: amd_iommu:perf_iommu_read\n");
+ struct amd_iommu *iommu = perf_event_2_iommu(event);
- amd_iommu_pc_get_set_reg_val(_GET_DEVID(event),
- _GET_BANK(event), _GET_CNTR(event),
- IOMMU_PC_COUNTER_REG, &count, false);
+ if (amd_iommu_pc_get_reg(iommu, hwc->iommu_bank, hwc->iommu_cntr,
+ IOMMU_PC_COUNTER_REG, &count))
+ return;
/* IOMMU pc counter register is only 48 bits */
- count &= 0xFFFFFFFFFFFFULL;
+ count &= GENMASK_ULL(47, 0);
- prev_raw_count = local64_read(&hwc->prev_count);
- if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
- count) != prev_raw_count)
+ prev = local64_read(&hwc->prev_count);
+ if (local64_cmpxchg(&hwc->prev_count, prev, count) != prev)
return;
- /* Handling 48-bit counter overflowing */
- delta = (count << COUNTER_SHIFT) - (prev_raw_count << COUNTER_SHIFT);
+ /* Handle 48-bit counter overflow */
+ delta = (count << COUNTER_SHIFT) - (prev << COUNTER_SHIFT);
delta >>= COUNTER_SHIFT;
local64_add(delta, &event->count);
-
}
static void perf_iommu_stop(struct perf_event *event, int flags)
{
struct hw_perf_event *hwc = &event->hw;
- u64 config;
-
- pr_debug("perf: amd_iommu:perf_iommu_stop\n");
if (hwc->state & PERF_HES_UPTODATE)
return;
if (hwc->state & PERF_HES_UPTODATE)
return;
- config = hwc->config;
perf_iommu_read(event);
hwc->state |= PERF_HES_UPTODATE;
}
static int perf_iommu_add(struct perf_event *event, int flags)
{
int retval;
- struct perf_amd_iommu *perf_iommu =
- container_of(event->pmu, struct perf_amd_iommu, pmu);
- pr_debug("perf: amd_iommu:perf_iommu_add\n");
event->hw.state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
/* request an iommu bank/counter */
- retval = get_next_avail_iommu_bnk_cntr(perf_iommu);
- if (retval != -ENOSPC)
- event->hw.extra_reg.reg = (u16)retval;
- else
+ retval = get_next_avail_iommu_bnk_cntr(event);
+ if (retval)
return retval;
if (flags & PERF_EF_START)
static void perf_iommu_del(struct perf_event *event, int flags)
{
+ struct hw_perf_event *hwc = &event->hw;
struct perf_amd_iommu *perf_iommu =
container_of(event->pmu, struct perf_amd_iommu, pmu);
- pr_debug("perf: amd_iommu:perf_iommu_del\n");
perf_iommu_stop(event, PERF_EF_UPDATE);
/* clear the assigned iommu bank/counter */
clear_avail_iommu_bnk_cntr(perf_iommu,
- _GET_BANK(event),
- _GET_CNTR(event));
+ hwc->iommu_bank, hwc->iommu_cntr);
perf_event_update_userpage(event);
}
-static __init int _init_events_attrs(struct perf_amd_iommu *perf_iommu)
+static __init int _init_events_attrs(void)
{
- struct attribute **attrs;
- struct attribute_group *attr_group;
int i = 0, j;
+ struct attribute **attrs;
while (amd_iommu_v2_event_descs[i].attr.attr.name)
i++;
- attr_group = kzalloc(sizeof(struct attribute *)
- * (i + 1) + sizeof(*attr_group), GFP_KERNEL);
- if (!attr_group)
+ attrs = kzalloc(sizeof(struct attribute **) * (i + 1), GFP_KERNEL);
+ if (!attrs)
return -ENOMEM;
- attrs = (struct attribute **)(attr_group + 1);
for (j = 0; j < i; j++)
attrs[j] = &amd_iommu_v2_event_descs[j].attr.attr;
- attr_group->name = "events";
- attr_group->attrs = attrs;
- perf_iommu->events_group = attr_group;
-
+ amd_iommu_events_group.attrs = attrs;
return 0;
}
-static __init void amd_iommu_pc_exit(void)
-{
- if (__perf_iommu.events_group != NULL) {
- kfree(__perf_iommu.events_group);
- __perf_iommu.events_group = NULL;
- }
-}
+const struct attribute_group *amd_iommu_attr_groups[] = {
+ &amd_iommu_format_group,
+ &amd_iommu_cpumask_group,
+ &amd_iommu_events_group,
+ NULL,
+};
+
+static struct pmu iommu_pmu = {
+ .event_init = perf_iommu_event_init,
+ .add = perf_iommu_add,
+ .del = perf_iommu_del,
+ .start = perf_iommu_start,
+ .stop = perf_iommu_stop,
+ .read = perf_iommu_read,
+ .task_ctx_nr = perf_invalid_context,
+ .attr_groups = amd_iommu_attr_groups,
+};
-static __init int _init_perf_amd_iommu(
- struct perf_amd_iommu *perf_iommu, char *name)
+static __init int init_one_iommu(unsigned int idx)
{
+ struct perf_amd_iommu *perf_iommu;
int ret;
+ perf_iommu = kzalloc(sizeof(struct perf_amd_iommu), GFP_KERNEL);
+ if (!perf_iommu)
+ return -ENOMEM;
+
raw_spin_lock_init(&perf_iommu->lock);
- /* Init format attributes */
- perf_iommu->format_group = &amd_iommu_format_group;
+ perf_iommu->pmu = iommu_pmu;
+ perf_iommu->iommu = get_amd_iommu(idx);
+ perf_iommu->max_banks = amd_iommu_pc_get_max_banks(idx);
+ perf_iommu->max_counters = amd_iommu_pc_get_max_counters(idx);
- /* Init cpumask attributes to only core 0 */
- cpumask_set_cpu(0, &iommu_cpumask);
- perf_iommu->cpumask_group = &amd_iommu_cpumask_group;
-
- /* Init events attributes */
- if (_init_events_attrs(perf_iommu) != 0)
- pr_err("perf: amd_iommu: Only support raw events.\n");
+ if (!perf_iommu->iommu ||
+ !perf_iommu->max_banks ||
+ !perf_iommu->max_counters) {
+ kfree(perf_iommu);
+ return -EINVAL;
+ }
- /* Init null attributes */
- perf_iommu->null_group = NULL;
- perf_iommu->pmu.attr_groups = perf_iommu->attr_groups;
+ snprintf(perf_iommu->name, IOMMU_NAME_SIZE, "amd_iommu_%u", idx);
- ret = perf_pmu_register(&perf_iommu->pmu, name, -1);
- if (ret) {
- pr_err("perf: amd_iommu: Failed to initialized.\n");
- amd_iommu_pc_exit();
+ ret = perf_pmu_register(&perf_iommu->pmu, perf_iommu->name, -1);
+ if (!ret) {
+ pr_info("Detected AMD IOMMU #%d (%d banks, %d counters/bank).\n",
+ idx, perf_iommu->max_banks, perf_iommu->max_counters);
+ list_add_tail(&perf_iommu->list, &perf_amd_iommu_list);
} else {
- pr_info("perf: amd_iommu: Detected. (%d banks, %d counters/bank)\n",
- amd_iommu_pc_get_max_banks(IOMMU_BASE_DEVID),
- amd_iommu_pc_get_max_counters(IOMMU_BASE_DEVID));
+ pr_warn("Error initializing IOMMU %d.\n", idx);
+ kfree(perf_iommu);
}
-
return ret;
}
-static struct perf_amd_iommu __perf_iommu = {
- .pmu = {
- .task_ctx_nr = perf_invalid_context,
- .event_init = perf_iommu_event_init,
- .add = perf_iommu_add,
- .del = perf_iommu_del,
- .start = perf_iommu_start,
- .stop = perf_iommu_stop,
- .read = perf_iommu_read,
- },
- .max_banks = 0x00,
- .max_counters = 0x00,
- .cntr_assign_mask = 0ULL,
- .format_group = NULL,
- .cpumask_group = NULL,
- .events_group = NULL,
- .null_group = NULL,
-};
-
static __init int amd_iommu_pc_init(void)
{
+ unsigned int i, cnt = 0;
+ int ret;
+
/* Make sure the IOMMU PC resource is available */
if (!amd_iommu_pc_supported())
return -ENODEV;
- _init_perf_amd_iommu(&__perf_iommu, "amd_iommu");
+ ret = _init_events_attrs();
+ if (ret)
+ return ret;
+
+ /*
+ * An IOMMU PMU is specific to an IOMMU, and can function independently.
+ * So we go through all IOMMUs and ignore the one that fails init
+ * unless all IOMMU are failing.
+ */
+ for (i = 0; i < amd_iommu_get_num_iommus(); i++) {
+ ret = init_one_iommu(i);
+ if (!ret)
+ cnt++;
+ }
+
+ if (!cnt) {
+ kfree(amd_iommu_events_group.attrs);
+ return -ENODEV;
+ }
+ /* Init cpumask attributes to only core 0 */
+ cpumask_set_cpu(0, &iommu_cpumask);
return 0;
}
#define PC_MAX_SPEC_BNKS 64
#define PC_MAX_SPEC_CNTRS 16
-/* iommu pc reg masks*/
-#define IOMMU_BASE_DEVID 0x0000
+struct amd_iommu;
/* amd_iommu_init.c external support functions */
+extern int amd_iommu_get_num_iommus(void);
+
extern bool amd_iommu_pc_supported(void);
-extern u8 amd_iommu_pc_get_max_banks(u16 devid);
+extern u8 amd_iommu_pc_get_max_banks(unsigned int idx);
+
+extern u8 amd_iommu_pc_get_max_counters(unsigned int idx);
+
+extern int amd_iommu_pc_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
+ u8 fxn, u64 *value);
-extern u8 amd_iommu_pc_get_max_counters(u16 devid);
+extern int amd_iommu_pc_get_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
+ u8 fxn, u64 *value);
-extern int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr,
- u8 fxn, u64 *value, bool is_write);
+extern struct amd_iommu *get_amd_iommu(int idx);
#endif /*_PERF_EVENT_AMD_IOMMU_H_*/
#define COUNTER_SHIFT 16
+#undef pr_fmt
+#define pr_fmt(fmt) "amd_uncore: " fmt
+
static int num_counters_llc;
static int num_counters_nb;
int ret = -ENODEV;
if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
- goto fail_nodev;
-
- switch(boot_cpu_data.x86) {
- case 23:
- /* Family 17h: */
- num_counters_nb = NUM_COUNTERS_NB;
- num_counters_llc = NUM_COUNTERS_L3;
- /*
- * For Family17h, the NorthBridge counters are
- * re-purposed as Data Fabric counters. Also, support is
- * added for L3 counters. The pmus are exported based on
- * family as either L2 or L3 and NB or DF.
- */
- amd_nb_pmu.name = "amd_df";
- amd_llc_pmu.name = "amd_l3";
- format_attr_event_df.show = &event_show_df;
- format_attr_event_l3.show = &event_show_l3;
- break;
- case 22:
- /* Family 16h - may change: */
- num_counters_nb = NUM_COUNTERS_NB;
- num_counters_llc = NUM_COUNTERS_L2;
- amd_nb_pmu.name = "amd_nb";
- amd_llc_pmu.name = "amd_l2";
- format_attr_event_df = format_attr_event;
- format_attr_event_l3 = format_attr_event;
- break;
- default:
- /*
- * All prior families have the same number of
- * NorthBridge and Last Level Cache counters
- */
- num_counters_nb = NUM_COUNTERS_NB;
- num_counters_llc = NUM_COUNTERS_L2;
- amd_nb_pmu.name = "amd_nb";
- amd_llc_pmu.name = "amd_l2";
- format_attr_event_df = format_attr_event;
- format_attr_event_l3 = format_attr_event;
- break;
- }
- amd_nb_pmu.attr_groups = amd_uncore_attr_groups_df;
- amd_llc_pmu.attr_groups = amd_uncore_attr_groups_l3;
+ return -ENODEV;
if (!boot_cpu_has(X86_FEATURE_TOPOEXT))
- goto fail_nodev;
+ return -ENODEV;
+
+ if (boot_cpu_data.x86 == 0x17) {
+ /*
+ * For F17h, the Northbridge counters are repurposed as Data
+ * Fabric counters. Also, L3 counters are supported too. The PMUs
+ * are exported based on family as either L2 or L3 and NB or DF.
+ */
+ num_counters_nb = NUM_COUNTERS_NB;
+ num_counters_llc = NUM_COUNTERS_L3;
+ amd_nb_pmu.name = "amd_df";
+ amd_llc_pmu.name = "amd_l3";
+ format_attr_event_df.show = &event_show_df;
+ format_attr_event_l3.show = &event_show_l3;
+ } else {
+ num_counters_nb = NUM_COUNTERS_NB;
+ num_counters_llc = NUM_COUNTERS_L2;
+ amd_nb_pmu.name = "amd_nb";
+ amd_llc_pmu.name = "amd_l2";
+ format_attr_event_df = format_attr_event;
+ format_attr_event_l3 = format_attr_event;
+ }
+
+ amd_nb_pmu.attr_groups = amd_uncore_attr_groups_df;
+ amd_llc_pmu.attr_groups = amd_uncore_attr_groups_l3;
if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) {
amd_uncore_nb = alloc_percpu(struct amd_uncore *);
if (ret)
goto fail_nb;
- pr_info("perf: AMD NB counters detected\n");
+ pr_info("AMD NB counters detected\n");
ret = 0;
}
if (ret)
goto fail_llc;
- pr_info("perf: AMD LLC counters detected\n");
+ pr_info("AMD LLC counters detected\n");
ret = 0;
}
if (amd_uncore_nb)
free_percpu(amd_uncore_nb);
-fail_nodev:
return ret;
}
device_initcall(amd_uncore_init);
unsigned int cur_buf;
bool snapshot;
local_t data_size;
- local_t lost;
local_t head;
unsigned long end;
void **data_pages;
return;
if (ds->bts_index >= ds->bts_absolute_maximum)
- local_inc(&buf->lost);
+ perf_aux_output_flag(&bts->handle,
+ PERF_AUX_FLAG_TRUNCATED);
/*
* old and head are always in the same physical buffer, so we
return;
fail_end_stop:
- perf_aux_output_end(&bts->handle, 0, false);
+ perf_aux_output_end(&bts->handle, 0);
fail_stop:
event->hw.state = PERF_HES_STOPPED;
bts->handle.head =
local_xchg(&buf->data_size,
buf->nr_pages << PAGE_SHIFT);
-
- perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0),
- !!local_xchg(&buf->lost, 0));
+ perf_aux_output_end(&bts->handle,
+ local_xchg(&buf->data_size, 0));
}
cpuc->ds->bts_index = bts->ds_back.bts_buffer_base;
if (old_head == local_read(&buf->head))
return handled;
- perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0),
- !!local_xchg(&buf->lost, 0));
+ perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0));
buf = perf_aux_output_begin(&bts->handle, event);
if (buf)
* cleared handle::event
*/
barrier();
- perf_aux_output_end(&bts->handle, 0, false);
+ perf_aux_output_end(&bts->handle, 0);
}
}
},
};
+EVENT_ATTR_STR(topdown-total-slots, td_total_slots_glm, "event=0x3c");
+EVENT_ATTR_STR(topdown-total-slots.scale, td_total_slots_scale_glm, "3");
+/* UOPS_NOT_DELIVERED.ANY */
+EVENT_ATTR_STR(topdown-fetch-bubbles, td_fetch_bubbles_glm, "event=0x9c");
+/* ISSUE_SLOTS_NOT_CONSUMED.RECOVERY */
+EVENT_ATTR_STR(topdown-recovery-bubbles, td_recovery_bubbles_glm, "event=0xca,umask=0x02");
+/* UOPS_RETIRED.ANY */
+EVENT_ATTR_STR(topdown-slots-retired, td_slots_retired_glm, "event=0xc2");
+/* UOPS_ISSUED.ANY */
+EVENT_ATTR_STR(topdown-slots-issued, td_slots_issued_glm, "event=0x0e");
+
+static struct attribute *glm_events_attrs[] = {
+ EVENT_PTR(td_total_slots_glm),
+ EVENT_PTR(td_total_slots_scale_glm),
+ EVENT_PTR(td_fetch_bubbles_glm),
+ EVENT_PTR(td_recovery_bubbles_glm),
+ EVENT_PTR(td_slots_issued_glm),
+ EVENT_PTR(td_slots_retired_glm),
+ NULL
+};
+
static struct extra_reg intel_glm_extra_regs[] __read_mostly = {
/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x760005ffbfull, RSP_0),
* counters from the GLOBAL_STATUS mask and we always process PEBS
* events via drain_pebs().
*/
- status &= ~cpuc->pebs_enabled;
+ status &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK);
/*
* PEBS overflow sets bit 62 in the global status register
x86_pmu.pebs_prec_dist = true;
x86_pmu.lbr_pt_coexist = true;
x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+ x86_pmu.cpu_events = glm_events_attrs;
pr_cont("Goldmont events, ");
break;
/* clear non-PEBS bit and re-check */
pebs_status = p->status & cpuc->pebs_enabled;
- pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1;
+ pebs_status &= PEBS_COUNTER_MASK;
if (pebs_status == (1 << bit))
return at;
}
cpuc->lbr_entries[i].to = msr_lastbranch.to;
cpuc->lbr_entries[i].mispred = 0;
cpuc->lbr_entries[i].predicted = 0;
+ cpuc->lbr_entries[i].in_tx = 0;
+ cpuc->lbr_entries[i].abort = 0;
+ cpuc->lbr_entries[i].cycles = 0;
cpuc->lbr_entries[i].reserved = 0;
}
cpuc->lbr_stack.nr = i;
#include <asm/insn.h>
#include <asm/io.h>
#include <asm/intel_pt.h>
+#include <asm/intel-family.h>
#include "../perf_event.h"
#include "pt.h"
.name = "caps",
};
+PMU_FORMAT_ATTR(pt, "config:0" );
PMU_FORMAT_ATTR(cyc, "config:1" );
PMU_FORMAT_ATTR(pwr_evt, "config:4" );
PMU_FORMAT_ATTR(fup_on_ptw, "config:5" );
PMU_FORMAT_ATTR(tsc, "config:10" );
PMU_FORMAT_ATTR(noretcomp, "config:11" );
PMU_FORMAT_ATTR(ptw, "config:12" );
+PMU_FORMAT_ATTR(branch, "config:13" );
PMU_FORMAT_ATTR(mtc_period, "config:14-17" );
PMU_FORMAT_ATTR(cyc_thresh, "config:19-22" );
PMU_FORMAT_ATTR(psb_period, "config:24-27" );
static struct attribute *pt_formats_attr[] = {
+ &format_attr_pt.attr,
&format_attr_cyc.attr,
&format_attr_pwr_evt.attr,
&format_attr_fup_on_ptw.attr,
&format_attr_tsc.attr,
&format_attr_noretcomp.attr,
&format_attr_ptw.attr,
+ &format_attr_branch.attr,
&format_attr_mtc_period.attr,
&format_attr_cyc_thresh.attr,
&format_attr_psb_period.attr,
pt_pmu.tsc_art_den = eax;
}
+ /* model-specific quirks */
+ switch (boot_cpu_data.x86_model) {
+ case INTEL_FAM6_BROADWELL_CORE:
+ case INTEL_FAM6_BROADWELL_XEON_D:
+ case INTEL_FAM6_BROADWELL_GT3E:
+ case INTEL_FAM6_BROADWELL_X:
+ /* not setting BRANCH_EN will #GP, erratum BDM106 */
+ pt_pmu.branch_en_always_on = true;
+ break;
+ default:
+ break;
+ }
+
if (boot_cpu_has(X86_FEATURE_VMX)) {
/*
* Intel SDM, 36.5 "Tracing post-VMXON" says that
#define RTIT_CTL_PTW (RTIT_CTL_PTW_EN | \
RTIT_CTL_FUP_ON_PTW)
-#define PT_CONFIG_MASK (RTIT_CTL_TSC_EN | \
+/*
+ * Bit 0 (TraceEn) in the attr.config is meaningless as the
+ * corresponding bit in the RTIT_CTL can only be controlled
+ * by the driver; therefore, repurpose it to mean: pass
+ * through the bit that was previously assumed to be always
+ * on for PT, thereby allowing the user to *not* set it if
+ * they so wish. See also pt_event_valid() and pt_config().
+ */
+#define RTIT_CTL_PASSTHROUGH RTIT_CTL_TRACEEN
+
+#define PT_CONFIG_MASK (RTIT_CTL_TRACEEN | \
+ RTIT_CTL_TSC_EN | \
RTIT_CTL_DISRETC | \
+ RTIT_CTL_BRANCH_EN | \
RTIT_CTL_CYC_PSB | \
RTIT_CTL_MTC | \
RTIT_CTL_PWR_EVT_EN | \
return false;
}
+ /*
+ * Setting bit 0 (TraceEn in RTIT_CTL MSR) in the attr.config
+ * clears the assomption that BranchEn must always be enabled,
+ * as was the case with the first implementation of PT.
+ * If this bit is not set, the legacy behavior is preserved
+ * for compatibility with the older userspace.
+ *
+ * Re-using bit 0 for this purpose is fine because it is never
+ * directly set by the user; previous attempts at setting it in
+ * the attr.config resulted in -EINVAL.
+ */
+ if (config & RTIT_CTL_PASSTHROUGH) {
+ /*
+ * Disallow not setting BRANCH_EN where BRANCH_EN is
+ * always required.
+ */
+ if (pt_pmu.branch_en_always_on &&
+ !(config & RTIT_CTL_BRANCH_EN))
+ return false;
+ } else {
+ /*
+ * Disallow BRANCH_EN without the PASSTHROUGH.
+ */
+ if (config & RTIT_CTL_BRANCH_EN)
+ return false;
+ }
+
return true;
}
static void pt_config(struct perf_event *event)
{
+ struct pt *pt = this_cpu_ptr(&pt_ctx);
u64 reg;
if (!event->hw.itrace_started) {
}
reg = pt_config_filters(event);
- reg |= RTIT_CTL_TOPA | RTIT_CTL_BRANCH_EN | RTIT_CTL_TRACEEN;
+ reg |= RTIT_CTL_TOPA | RTIT_CTL_TRACEEN;
+
+ /*
+ * Previously, we had BRANCH_EN on by default, but now that PT has
+ * grown features outside of branch tracing, it is useful to allow
+ * the user to disable it. Setting bit 0 in the event's attr.config
+ * allows BRANCH_EN to pass through instead of being always on. See
+ * also the comment in pt_event_valid().
+ */
+ if (event->attr.config & BIT(0)) {
+ reg |= event->attr.config & RTIT_CTL_BRANCH_EN;
+ } else {
+ reg |= RTIT_CTL_BRANCH_EN;
+ }
if (!event->attr.exclude_kernel)
reg |= RTIT_CTL_OS;
reg |= (event->attr.config & PT_CONFIG_MASK);
event->hw.config = reg;
- wrmsrl(MSR_IA32_RTIT_CTL, reg);
+ if (READ_ONCE(pt->vmx_on))
+ perf_aux_output_flag(&pt->handle, PERF_AUX_FLAG_PARTIAL);
+ else
+ wrmsrl(MSR_IA32_RTIT_CTL, reg);
}
static void pt_config_stop(struct perf_event *event)
{
+ struct pt *pt = this_cpu_ptr(&pt_ctx);
u64 ctl = READ_ONCE(event->hw.config);
/* may be already stopped by a PMI */
return;
ctl &= ~RTIT_CTL_TRACEEN;
- wrmsrl(MSR_IA32_RTIT_CTL, ctl);
+ if (!READ_ONCE(pt->vmx_on))
+ wrmsrl(MSR_IA32_RTIT_CTL, ctl);
WRITE_ONCE(event->hw.config, ctl);
*/
if (!pt_cap_get(PT_CAP_topa_multiple_entries) ||
buf->output_off == sizes(TOPA_ENTRY(buf->cur, buf->cur_idx)->size)) {
- local_inc(&buf->lost);
+ perf_aux_output_flag(&pt->handle,
+ PERF_AUX_FLAG_TRUNCATED);
advance++;
}
}
/* can't stop in the middle of an output region */
if (buf->output_off + handle->size + 1 <
- sizes(TOPA_ENTRY(buf->cur, buf->cur_idx)->size))
+ sizes(TOPA_ENTRY(buf->cur, buf->cur_idx)->size)) {
+ perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
return -EINVAL;
+ }
/* single entry ToPA is handled by marking all regions STOP=1 INT=1 */
if (!READ_ONCE(pt->handle_nmi))
return;
- /*
- * If VMX is on and PT does not support it, don't touch anything.
- */
- if (READ_ONCE(pt->vmx_on))
- return;
-
if (!event)
return;
pt_update_head(pt);
- perf_aux_output_end(&pt->handle, local_xchg(&buf->data_size, 0),
- local_xchg(&buf->lost, 0));
+ perf_aux_output_end(&pt->handle, local_xchg(&buf->data_size, 0));
if (!event->hw.state) {
int ret;
/* snapshot counters don't use PMI, so it's safe */
ret = pt_buffer_reset_markers(buf, &pt->handle);
if (ret) {
- perf_aux_output_end(&pt->handle, 0, true);
+ perf_aux_output_end(&pt->handle, 0);
return;
}
local_irq_save(flags);
WRITE_ONCE(pt->vmx_on, on);
- if (on) {
- /* prevent pt_config_stop() from writing RTIT_CTL */
- event = pt->handle.event;
- if (event)
- event->hw.config = 0;
- }
+ /*
+ * If an AUX transaction is in progress, it will contain
+ * gap(s), so flag it PARTIAL to inform the user.
+ */
+ event = pt->handle.event;
+ if (event)
+ perf_aux_output_flag(&pt->handle,
+ PERF_AUX_FLAG_PARTIAL);
+
+ /* Turn PTs back on */
+ if (!on && event)
+ wrmsrl(MSR_IA32_RTIT_CTL, event->hw.config);
+
local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(intel_pt_handle_vmx);
struct pt *pt = this_cpu_ptr(&pt_ctx);
struct pt_buffer *buf;
- if (READ_ONCE(pt->vmx_on))
- return;
-
buf = perf_aux_output_begin(&pt->handle, event);
if (!buf)
goto fail_stop;
return;
fail_end_stop:
- perf_aux_output_end(&pt->handle, 0, true);
+ perf_aux_output_end(&pt->handle, 0);
fail_stop:
hwc->state = PERF_HES_STOPPED;
}
pt->handle.head =
local_xchg(&buf->data_size,
buf->nr_pages << PAGE_SHIFT);
- perf_aux_output_end(&pt->handle, local_xchg(&buf->data_size, 0),
- local_xchg(&buf->lost, 0));
+ perf_aux_output_end(&pt->handle, local_xchg(&buf->data_size, 0));
}
}
struct pmu pmu;
u32 caps[PT_CPUID_REGS_NUM * PT_CPUID_LEAVES];
bool vmx;
+ bool branch_en_always_on;
unsigned long max_nonturbo_ratio;
unsigned int tsc_art_num;
unsigned int tsc_art_den;
size_t output_off;
unsigned long nr_pages;
local_t data_size;
- local_t lost;
local64_t head;
bool snapshot;
unsigned long stop_pos, intr_pos;
/* The maximal number of PEBS events: */
#define MAX_PEBS_EVENTS 8
+#define PEBS_COUNTER_MASK ((1ULL << MAX_PEBS_EVENTS) - 1)
/*
* Flags PEBS can handle without an PMI.
extern int acpi_sci_override_gsi;
void acpi_pic_sci_set_trigger(unsigned int, u16);
+struct device;
+
extern int (*__acpi_register_gsi)(struct device *dev, u32 gsi,
int trigger, int polarity);
extern void (*__acpi_unregister_gsi)(u32 gsi);
return cmpxchg(&v->counter, old, new);
}
+#define atomic_try_cmpxchg atomic_try_cmpxchg
+static __always_inline bool atomic_try_cmpxchg(atomic_t *v, int *old, int new)
+{
+ return try_cmpxchg(&v->counter, old, new);
+}
+
static inline int atomic_xchg(atomic_t *v, int new)
{
return xchg(&v->counter, new);
}
#define ATOMIC_FETCH_OP(op, c_op) \
-static inline int atomic_fetch_##op(int i, atomic_t *v) \
+static inline int atomic_fetch_##op(int i, atomic_t *v) \
{ \
- int old, val = atomic_read(v); \
- for (;;) { \
- old = atomic_cmpxchg(v, val, val c_op i); \
- if (old == val) \
- break; \
- val = old; \
- } \
- return old; \
+ int val = atomic_read(v); \
+ do { \
+ } while (!atomic_try_cmpxchg(v, &val, val c_op i)); \
+ return val; \
}
#define ATOMIC_OPS(op, c_op) \
*/
static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
{
- int c, old;
- c = atomic_read(v);
- for (;;) {
- if (unlikely(c == (u)))
- break;
- old = atomic_cmpxchg((v), c, c + (a));
- if (likely(old == c))
+ int c = atomic_read(v);
+ do {
+ if (unlikely(c == u))
break;
- c = old;
- }
+ } while (!atomic_try_cmpxchg(v, &c, c + a));
return c;
}
return cmpxchg(&v->counter, old, new);
}
+#define atomic64_try_cmpxchg atomic64_try_cmpxchg
+static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, long *old, long new)
+{
+ return try_cmpxchg(&v->counter, old, new);
+}
+
static inline long atomic64_xchg(atomic64_t *v, long new)
{
return xchg(&v->counter, new);
*/
static inline bool atomic64_add_unless(atomic64_t *v, long a, long u)
{
- long c, old;
- c = atomic64_read(v);
- for (;;) {
- if (unlikely(c == (u)))
- break;
- old = atomic64_cmpxchg((v), c, c + (a));
- if (likely(old == c))
- break;
- c = old;
- }
- return c != (u);
+ long c = atomic64_read(v);
+ do {
+ if (unlikely(c == u))
+ return false;
+ } while (!atomic64_try_cmpxchg(v, &c, c + a));
+ return true;
}
#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
*/
static inline long atomic64_dec_if_positive(atomic64_t *v)
{
- long c, old, dec;
- c = atomic64_read(v);
- for (;;) {
+ long dec, c = atomic64_read(v);
+ do {
dec = c - 1;
if (unlikely(dec < 0))
break;
- old = atomic64_cmpxchg((v), c, dec);
- if (likely(old == c))
- break;
- c = old;
- }
+ } while (!atomic64_try_cmpxchg(v, &c, dec));
return dec;
}
#define ATOMIC64_FETCH_OP(op, c_op) \
static inline long atomic64_fetch_##op(long i, atomic64_t *v) \
{ \
- long old, val = atomic64_read(v); \
- for (;;) { \
- old = atomic64_cmpxchg(v, val, val c_op i); \
- if (old == val) \
- break; \
- val = old; \
- } \
- return old; \
+ long val = atomic64_read(v); \
+ do { \
+ } while (!atomic64_try_cmpxchg(v, &val, val c_op i)); \
+ return val; \
}
#define ATOMIC64_OPS(op, c_op) \
#define cmpxchg_local(ptr, old, new) \
__cmpxchg_local(ptr, old, new, sizeof(*(ptr)))
+
+#define __raw_try_cmpxchg(_ptr, _pold, _new, size, lock) \
+({ \
+ bool success; \
+ __typeof__(_ptr) _old = (_pold); \
+ __typeof__(*(_ptr)) __old = *_old; \
+ __typeof__(*(_ptr)) __new = (_new); \
+ switch (size) { \
+ case __X86_CASE_B: \
+ { \
+ volatile u8 *__ptr = (volatile u8 *)(_ptr); \
+ asm volatile(lock "cmpxchgb %[new], %[ptr]" \
+ CC_SET(z) \
+ : CC_OUT(z) (success), \
+ [ptr] "+m" (*__ptr), \
+ [old] "+a" (__old) \
+ : [new] "q" (__new) \
+ : "memory"); \
+ break; \
+ } \
+ case __X86_CASE_W: \
+ { \
+ volatile u16 *__ptr = (volatile u16 *)(_ptr); \
+ asm volatile(lock "cmpxchgw %[new], %[ptr]" \
+ CC_SET(z) \
+ : CC_OUT(z) (success), \
+ [ptr] "+m" (*__ptr), \
+ [old] "+a" (__old) \
+ : [new] "r" (__new) \
+ : "memory"); \
+ break; \
+ } \
+ case __X86_CASE_L: \
+ { \
+ volatile u32 *__ptr = (volatile u32 *)(_ptr); \
+ asm volatile(lock "cmpxchgl %[new], %[ptr]" \
+ CC_SET(z) \
+ : CC_OUT(z) (success), \
+ [ptr] "+m" (*__ptr), \
+ [old] "+a" (__old) \
+ : [new] "r" (__new) \
+ : "memory"); \
+ break; \
+ } \
+ case __X86_CASE_Q: \
+ { \
+ volatile u64 *__ptr = (volatile u64 *)(_ptr); \
+ asm volatile(lock "cmpxchgq %[new], %[ptr]" \
+ CC_SET(z) \
+ : CC_OUT(z) (success), \
+ [ptr] "+m" (*__ptr), \
+ [old] "+a" (__old) \
+ : [new] "r" (__new) \
+ : "memory"); \
+ break; \
+ } \
+ default: \
+ __cmpxchg_wrong_size(); \
+ } \
+ if (unlikely(!success)) \
+ *_old = __old; \
+ likely(success); \
+})
+
+#define __try_cmpxchg(ptr, pold, new, size) \
+ __raw_try_cmpxchg((ptr), (pold), (new), (size), LOCK_PREFIX)
+
+#define try_cmpxchg(ptr, pold, new) \
+ __try_cmpxchg((ptr), (pold), (new), sizeof(*(ptr)))
+
/*
* xadd() adds "inc" to "*ptr" and atomically returns the previous
* value of "*ptr".
* Reuse free bits when adding new feature flags!
*/
#define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* Ring 3 MONITOR/MWAIT */
+#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* Intel CPUID faulting */
#define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */
#define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */
+++ /dev/null
-#ifndef _ASM_X86_E820_H
-#define _ASM_X86_E820_H
-
-/*
- * E820_X_MAX is the maximum size of the extended E820 table. The extended
- * table may contain up to 3 extra E820 entries per possible NUMA node, so we
- * make room for 3 * MAX_NUMNODES possible entries, beyond the standard 128.
- * Also note that E820_X_MAX *must* be defined before we include uapi/asm/e820.h.
- */
-#include <linux/numa.h>
-#define E820_X_MAX (E820MAX + 3 * MAX_NUMNODES)
-
-#include <uapi/asm/e820.h>
-
-#ifndef __ASSEMBLY__
-/* see comment in arch/x86/kernel/e820.c */
-extern struct e820map *e820;
-extern struct e820map *e820_saved;
-
-extern unsigned long pci_mem_start;
-extern int e820_any_mapped(u64 start, u64 end, unsigned type);
-extern int e820_all_mapped(u64 start, u64 end, unsigned type);
-extern void e820_add_region(u64 start, u64 size, int type);
-extern void e820_print_map(char *who);
-extern int
-sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, u32 *pnr_map);
-extern u64 e820_update_range(u64 start, u64 size, unsigned old_type,
- unsigned new_type);
-extern u64 e820_remove_range(u64 start, u64 size, unsigned old_type,
- int checktype);
-extern void update_e820(void);
-extern void e820_setup_gap(void);
-struct setup_data;
-extern void parse_e820_ext(u64 phys_addr, u32 data_len);
-
-#if defined(CONFIG_X86_64) || \
- (defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION))
-extern void e820_mark_nosave_regions(unsigned long limit_pfn);
-#else
-static inline void e820_mark_nosave_regions(unsigned long limit_pfn)
-{
-}
-#endif
-
-extern unsigned long e820_end_of_ram_pfn(void);
-extern unsigned long e820_end_of_low_ram_pfn(void);
-extern u64 early_reserve_e820(u64 sizet, u64 align);
-
-void memblock_x86_fill(void);
-void memblock_find_dma_reserve(void);
-
-extern void finish_e820_parsing(void);
-extern void e820_reserve_resources(void);
-extern void e820_reserve_resources_late(void);
-extern void setup_memory_map(void);
-extern char *default_machine_specific_memory_setup(void);
-
-extern void e820_reallocate_tables(void);
-
-/*
- * Returns true iff the specified range [s,e) is completely contained inside
- * the ISA region.
- */
-static inline bool is_ISA_range(u64 s, u64 e)
-{
- return s >= ISA_START_ADDRESS && e <= ISA_END_ADDRESS;
-}
-
-#endif /* __ASSEMBLY__ */
-#include <linux/ioport.h>
-
-#define HIGH_MEMORY (1024*1024)
-#endif /* _ASM_X86_E820_H */
--- /dev/null
+#ifndef _ASM_E820_API_H
+#define _ASM_E820_API_H
+
+#include <asm/e820/types.h>
+
+extern struct e820_table *e820_table;
+extern struct e820_table *e820_table_firmware;
+
+extern unsigned long pci_mem_start;
+
+extern bool e820__mapped_any(u64 start, u64 end, enum e820_type type);
+extern bool e820__mapped_all(u64 start, u64 end, enum e820_type type);
+
+extern void e820__range_add (u64 start, u64 size, enum e820_type type);
+extern u64 e820__range_update(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type);
+extern u64 e820__range_remove(u64 start, u64 size, enum e820_type old_type, bool check_type);
+
+extern void e820__print_table(char *who);
+extern int e820__update_table(struct e820_table *table);
+extern void e820__update_table_print(void);
+
+extern unsigned long e820__end_of_ram_pfn(void);
+extern unsigned long e820__end_of_low_ram_pfn(void);
+
+extern u64 e820__memblock_alloc_reserved(u64 size, u64 align);
+extern void e820__memblock_setup(void);
+
+extern void e820__reserve_setup_data(void);
+extern void e820__finish_early_params(void);
+extern void e820__reserve_resources(void);
+extern void e820__reserve_resources_late(void);
+
+extern void e820__memory_setup(void);
+extern void e820__memory_setup_extended(u64 phys_addr, u32 data_len);
+extern char *e820__memory_setup_default(void);
+extern void e820__setup_pci_gap(void);
+
+extern void e820__reallocate_tables(void);
+extern void e820__register_nosave_regions(unsigned long limit_pfn);
+
+/*
+ * Returns true iff the specified range [start,end) is completely contained inside
+ * the ISA region.
+ */
+static inline bool is_ISA_range(u64 start, u64 end)
+{
+ return start >= ISA_START_ADDRESS && end <= ISA_END_ADDRESS;
+}
+
+#endif /* _ASM_E820_API_H */
--- /dev/null
+#ifndef _ASM_E820_TYPES_H
+#define _ASM_E820_TYPES_H
+
+#include <uapi/asm/bootparam.h>
+
+/*
+ * These are the E820 types known to the kernel:
+ */
+enum e820_type {
+ E820_TYPE_RAM = 1,
+ E820_TYPE_RESERVED = 2,
+ E820_TYPE_ACPI = 3,
+ E820_TYPE_NVS = 4,
+ E820_TYPE_UNUSABLE = 5,
+ E820_TYPE_PMEM = 7,
+
+ /*
+ * This is a non-standardized way to represent ADR or
+ * NVDIMM regions that persist over a reboot.
+ *
+ * The kernel will ignore their special capabilities
+ * unless the CONFIG_X86_PMEM_LEGACY=y option is set.
+ *
+ * ( Note that older platforms also used 6 for the same
+ * type of memory, but newer versions switched to 12 as
+ * 6 was assigned differently. Some time they will learn... )
+ */
+ E820_TYPE_PRAM = 12,
+
+ /*
+ * Reserved RAM used by the kernel itself if
+ * CONFIG_INTEL_TXT=y is enabled, memory of this type
+ * will be included in the S3 integrity calculation
+ * and so should not include any memory that the BIOS
+ * might alter over the S3 transition:
+ */
+ E820_TYPE_RESERVED_KERN = 128,
+};
+
+/*
+ * A single E820 map entry, describing a memory range of [addr...addr+size-1],
+ * of 'type' memory type:
+ *
+ * (We pack it because there can be thousands of them on large systems.)
+ */
+struct e820_entry {
+ u64 addr;
+ u64 size;
+ enum e820_type type;
+} __attribute__((packed));
+
+/*
+ * The legacy E820 BIOS limits us to 128 (E820_MAX_ENTRIES_ZEROPAGE) nodes
+ * due to the constrained space in the zeropage.
+ *
+ * On large systems we can easily have thousands of nodes with RAM,
+ * which cannot be fit into so few entries - so we have a mechanism
+ * to extend the e820 table size at build-time, via the E820_MAX_ENTRIES
+ * define below.
+ *
+ * ( Those extra entries are enumerated via the EFI memory map, not
+ * via the legacy zeropage mechanism. )
+ *
+ * Size our internal memory map tables to have room for these additional
+ * entries, based on a heuristic calculation: up to three entries per
+ * NUMA node, plus E820_MAX_ENTRIES_ZEROPAGE for some extra space.
+ *
+ * This allows for bootstrap/firmware quirks such as possible duplicate
+ * E820 entries that might need room in the same arrays, prior to the
+ * call to e820__update_table() to remove duplicates. The allowance
+ * of three memory map entries per node is "enough" entries for
+ * the initial hardware platform motivating this mechanism to make
+ * use of additional EFI map entries. Future platforms may want
+ * to allow more than three entries per node or otherwise refine
+ * this size.
+ */
+
+#include <linux/numa.h>
+
+#define E820_MAX_ENTRIES (E820_MAX_ENTRIES_ZEROPAGE + 3*MAX_NUMNODES)
+
+/*
+ * The whole array of E820 entries:
+ */
+struct e820_table {
+ __u32 nr_entries;
+ struct e820_entry entries[E820_MAX_ENTRIES];
+};
+
+/*
+ * Various well-known legacy memory ranges in physical memory:
+ */
+#define ISA_START_ADDRESS 0x000a0000
+#define ISA_END_ADDRESS 0x00100000
+
+#define BIOS_BEGIN 0x000a0000
+#define BIOS_END 0x00100000
+
+#define HIGH_MEMORY 0x00100000
+
+#define BIOS_ROM_BASE 0xffe00000
+#define BIOS_ROM_END 0xffffffff
+
+#endif /* _ASM_E820_TYPES_H */
#ifndef _ASM_X86_GART_H
#define _ASM_X86_GART_H
-#include <asm/e820.h>
+#include <asm/e820/api.h>
extern void set_up_gart_resume(u32, u32);
printk(KERN_INFO "Aperture beyond 4GB. Ignoring.\n");
return 0;
}
- if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) {
+ if (e820__mapped_any(aper_base, aper_base + aper_size, E820_TYPE_RAM)) {
printk(KERN_INFO "Aperture pointing to e820 RAM. Ignoring.\n");
return 0;
}
/* copy of the original instruction */
kprobe_opcode_t *insn;
/*
- * boostable = -1: This instruction type is not boostable.
- * boostable = 0: This instruction type is boostable.
- * boostable = 1: This instruction has been boosted: we have
+ * boostable = false: This instruction type is not boostable.
+ * boostable = true: This instruction has been boosted: we have
* added a relative jump after the instruction copy in insn,
* so no single-step and fixup are needed (unless there's
* a post_handler or break_handler).
*/
- int boostable;
+ bool boostable;
bool if_modifier;
};
* debugging tools. Each entry is only valid when its finished flag
* is set.
*/
-struct mce_log {
+struct mce_log_buffer {
char signature[12]; /* "MACHINECHECK" */
unsigned len; /* = MCE_LOG_LEN */
unsigned next;
extern struct mca_msr_regs msr_ops;
enum mce_notifier_prios {
- MCE_PRIO_SRAO = INT_MAX,
- MCE_PRIO_EXTLOG = INT_MAX - 1,
- MCE_PRIO_NFIT = INT_MAX - 2,
- MCE_PRIO_EDAC = INT_MAX - 3,
+ MCE_PRIO_FIRST = INT_MAX,
+ MCE_PRIO_SRAO = INT_MAX - 1,
+ MCE_PRIO_EXTLOG = INT_MAX - 2,
+ MCE_PRIO_NFIT = INT_MAX - 3,
+ MCE_PRIO_EDAC = INT_MAX - 4,
+ MCE_PRIO_MCELOG = 1,
MCE_PRIO_LOWEST = 0,
};
}
#ifdef CONFIG_X86_MPPARSE
-extern void early_reserve_e820_mpc_new(void);
+extern void e820__memblock_alloc_reserved_mpc_new(void);
extern int enable_update_mptable;
extern int default_mpc_apic_id(struct mpc_cpu *m);
extern void default_smp_read_mpc_oem(struct mpc_table *mpc);
extern void default_find_smp_config(void);
extern void default_get_smp_config(unsigned int early);
#else
-static inline void early_reserve_e820_mpc_new(void) { }
+static inline void e820__memblock_alloc_reserved_mpc_new(void) { }
#define enable_update_mptable 0
#define default_mpc_apic_id NULL
#define default_smp_read_mpc_oem NULL
#define MSR_IA32_PERFCTR1 0x000000c2
#define MSR_FSB_FREQ 0x000000cd
#define MSR_PLATFORM_INFO 0x000000ce
+#define MSR_PLATFORM_INFO_CPUID_FAULT_BIT 31
+#define MSR_PLATFORM_INFO_CPUID_FAULT BIT_ULL(MSR_PLATFORM_INFO_CPUID_FAULT_BIT)
#define MSR_PKG_CST_CONFIG_CONTROL 0x000000e2
#define NHM_C3_AUTO_DEMOTE (1UL << 25)
/* DEBUGCTLMSR bits (others vary by model): */
#define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */
+#define DEBUGCTLMSR_BTF_SHIFT 1
#define DEBUGCTLMSR_BTF (1UL << 1) /* single-step on branches */
#define DEBUGCTLMSR_TR (1UL << 6)
#define DEBUGCTLMSR_BTS (1UL << 7)
#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT 39
#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT)
-/* MISC_FEATURE_ENABLES non-architectural features */
-#define MSR_MISC_FEATURE_ENABLES 0x00000140
+/* MISC_FEATURES_ENABLES non-architectural features */
+#define MSR_MISC_FEATURES_ENABLES 0x00000140
-#define MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT 1
+#define MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT 0
+#define MSR_MISC_FEATURES_ENABLES_CPUID_FAULT BIT_ULL(MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT)
+#define MSR_MISC_FEATURES_ENABLES_RING3MWAIT_BIT 1
#define MSR_IA32_TSC_DEADLINE 0x000006E0
* (c) 1999 Martin Mares <mj@ucw.cz>
*/
+#include <linux/ioport.h>
+
#undef DEBUG
#ifdef DEBUG
#define _ASM_X86_PGTABLE_H
#include <asm/page.h>
-#include <asm/e820.h>
-
#include <asm/pgtable_types.h>
/*
extern int direct_gbpages;
void init_mem_mapping(void);
void early_alloc_pgt_buf(void);
+extern void memblock_find_dma_reserve(void);
#ifdef CONFIG_X86_64
/* Realmode trampoline initialization. */
* @size: number of bytes to write back
*
* Write back a cache range using the CLWB (cache line write back)
- * instruction.
+ * instruction. Note that @size is internally rounded up to be cache
+ * line size aligned.
*/
static inline void arch_wb_cache_pmem(void *addr, size_t size)
{
clwb(p);
}
-/*
- * copy_from_iter_nocache() on x86 only uses non-temporal stores for iovec
- * iterators, so for other types (bvec & kvec) we must do a cache write-back.
- */
-static inline bool __iter_needs_pmem_wb(struct iov_iter *i)
-{
- return iter_is_iovec(i) == false;
-}
-
/**
* arch_copy_from_iter_pmem - copy data from an iterator to PMEM
* @addr: PMEM destination address
/* TODO: skip the write-back by always using non-temporal stores */
len = copy_from_iter_nocache(addr, bytes, i);
- if (__iter_needs_pmem_wb(i))
+ /*
+ * In the iovec case on x86_64 copy_from_iter_nocache() uses
+ * non-temporal stores for the bulk of the transfer, but we need
+ * to manually flush if the transfer is unaligned. A cached
+ * memory copy is used when destination or size is not naturally
+ * aligned. That is:
+ * - Require 8-byte alignment when size is 8 bytes or larger.
+ * - Require 4-byte alignment when size is 4 bytes.
+ *
+ * In the non-iovec case the entire destination needs to be
+ * flushed.
+ */
+ if (iter_is_iovec(i)) {
+ unsigned long flushed, dest = (unsigned long) addr;
+
+ if (bytes < 8) {
+ if (!IS_ALIGNED(dest, 4) || (bytes != 4))
+ arch_wb_cache_pmem(addr, 1);
+ } else {
+ if (!IS_ALIGNED(dest, 8)) {
+ dest = ALIGN(dest, boot_cpu_data.x86_clflush_size);
+ arch_wb_cache_pmem(addr, 1);
+ }
+
+ flushed = dest - (unsigned long) addr;
+ if (bytes > flushed && !IS_ALIGNED(bytes - flushed, 8))
+ arch_wb_cache_pmem(addr + bytes - 1, 1);
+ }
+ } else
arch_wb_cache_pmem(addr, bytes);
return len;
extern int get_tsc_mode(unsigned long adr);
extern int set_tsc_mode(unsigned int val);
+DECLARE_PER_CPU(u64, msr_misc_features_shadow);
+
/* Register/unregister a process' MPX related resource */
#define MPX_ENABLE_MANAGEMENT() mpx_enable_management()
#define MPX_DISABLE_MANAGEMENT() mpx_disable_management()
#ifdef CONFIG_X86_64
void entry_SYSCALL_64(void);
+long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2);
#endif
#ifdef CONFIG_X86_32
extern int reboot_force;
-long do_arch_prctl(struct task_struct *task, int code, unsigned long addr);
+long do_arch_prctl_common(struct task_struct *task, int option,
+ unsigned long cpuid_enabled);
#endif /* _ASM_X86_PROTO_H */
};
extern struct machine_ops machine_ops;
+extern int crashing_cpu;
void native_machine_crash_shutdown(struct pt_regs *regs);
void native_machine_shutdown(void);
#define TIF_SECCOMP 8 /* secure computing */
#define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */
#define TIF_UPROBE 12 /* breakpointed or singlestepping */
+#define TIF_NOCPUID 15 /* CPUID is not accessible in userland */
#define TIF_NOTSC 16 /* TSC is not accessible in userland */
#define TIF_IA32 17 /* IA32 compatibility process */
#define TIF_NOHZ 19 /* in adaptive nohz mode */
#define _TIF_SECCOMP (1 << TIF_SECCOMP)
#define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY)
#define _TIF_UPROBE (1 << TIF_UPROBE)
+#define _TIF_NOCPUID (1 << TIF_NOCPUID)
#define _TIF_NOTSC (1 << TIF_NOTSC)
#define _TIF_IA32 (1 << TIF_IA32)
#define _TIF_NOHZ (1 << TIF_NOHZ)
/* flags to check in __switch_to() */
#define _TIF_WORK_CTXSW \
- (_TIF_IO_BITMAP|_TIF_NOTSC|_TIF_BLOCKSTEP)
+ (_TIF_IO_BITMAP|_TIF_NOCPUID|_TIF_NOTSC|_TIF_BLOCKSTEP)
#define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY)
#define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW)
extern void arch_task_cache_init(void);
extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
extern void arch_release_task_struct(struct task_struct *tsk);
+extern void arch_setup_new_exec(void);
+#define arch_setup_new_exec arch_setup_new_exec
#endif /* !__ASSEMBLY__ */
#endif /* _ASM_X86_THREAD_INFO_H */
}
}
+static inline void cr4_toggle_bits(unsigned long mask)
+{
+ unsigned long cr4;
+
+ cr4 = this_cpu_read(cpu_tlbstate.cr4);
+ cr4 ^= mask;
+ this_cpu_write(cpu_tlbstate.cr4, cr4);
+ __write_cr4(cr4);
+}
+
/* Read the CR4 shadow. */
static inline unsigned long cr4_read_shadow(void)
{
/*
* User space memory access functions
*/
-#include <linux/errno.h>
#include <linux/compiler.h>
#include <linux/kasan-checks.h>
-#include <linux/thread_info.h>
#include <linux/string.h>
#include <asm/asm.h>
#include <asm/page.h>
#include <asm/smap.h>
#include <asm/extable.h>
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
/*
* The fs value determines whether argument validity checking should be
* performed or not. If get_fs() == USER_DS, checking is performed, with
: "=r" (err), ltype(x) \
: "m" (__m(addr)), "i" (errret), "0" (err))
+#define __get_user_asm_nozero(x, addr, err, itype, rtype, ltype, errret) \
+ asm volatile("\n" \
+ "1: mov"itype" %2,%"rtype"1\n" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: mov %3,%0\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ _ASM_EXTABLE(1b, 3b) \
+ : "=r" (err), ltype(x) \
+ : "m" (__m(addr)), "i" (errret), "0" (err))
+
/*
* This doesn't do __uaccess_begin/end - the exception handling
* around it must do that.
# include <asm/uaccess_64.h>
#endif
-unsigned long __must_check _copy_from_user(void *to, const void __user *from,
- unsigned n);
-unsigned long __must_check _copy_to_user(void __user *to, const void *from,
- unsigned n);
-
-extern void __compiletime_error("usercopy buffer size is too small")
-__bad_copy_user(void);
-
-static inline void copy_user_overflow(int size, unsigned long count)
-{
- WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
-}
-
-static __always_inline unsigned long __must_check
-copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- int sz = __compiletime_object_size(to);
-
- might_fault();
-
- kasan_check_write(to, n);
-
- if (likely(sz < 0 || sz >= n)) {
- check_object_size(to, n, false);
- n = _copy_from_user(to, from, n);
- } else if (!__builtin_constant_p(n))
- copy_user_overflow(sz, n);
- else
- __bad_copy_user();
-
- return n;
-}
-
-static __always_inline unsigned long __must_check
-copy_to_user(void __user *to, const void *from, unsigned long n)
-{
- int sz = __compiletime_object_size(from);
-
- kasan_check_read(from, n);
-
- might_fault();
-
- if (likely(sz < 0 || sz >= n)) {
- check_object_size(from, n, true);
- n = _copy_to_user(to, from, n);
- } else if (!__builtin_constant_p(n))
- copy_user_overflow(sz, n);
- else
- __bad_copy_user();
-
- return n;
-}
-
/*
* We rely on the nested NMI work to allow atomic faults from the NMI path; the
* nested NMI paths are careful to preserve CR2.
/*
* User space memory access functions
*/
-#include <linux/errno.h>
-#include <linux/thread_info.h>
#include <linux/string.h>
#include <asm/asm.h>
#include <asm/page.h>
-unsigned long __must_check __copy_to_user_ll
- (void __user *to, const void *from, unsigned long n);
-unsigned long __must_check __copy_from_user_ll
- (void *to, const void __user *from, unsigned long n);
-unsigned long __must_check __copy_from_user_ll_nozero
- (void *to, const void __user *from, unsigned long n);
-unsigned long __must_check __copy_from_user_ll_nocache
- (void *to, const void __user *from, unsigned long n);
+unsigned long __must_check __copy_user_ll
+ (void *to, const void *from, unsigned long n);
unsigned long __must_check __copy_from_user_ll_nocache_nozero
(void *to, const void __user *from, unsigned long n);
-/**
- * __copy_to_user_inatomic: - Copy a block of data into user space, with less checking.
- * @to: Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only.
- *
- * Copy data from kernel space to user space. Caller must check
- * the specified block with access_ok() before calling this function.
- * The caller should also make sure he pins the user space address
- * so that we don't result in page fault and sleep.
- */
-static __always_inline unsigned long __must_check
-__copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
-{
- check_object_size(from, n, true);
- return __copy_to_user_ll(to, from, n);
-}
-
-/**
- * __copy_to_user: - Copy a block of data into user space, with less checking.
- * @to: Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- * enabled.
- *
- * Copy data from kernel space to user space. Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- */
static __always_inline unsigned long __must_check
-__copy_to_user(void __user *to, const void *from, unsigned long n)
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
{
- might_fault();
- return __copy_to_user_inatomic(to, from, n);
+ return __copy_user_ll((__force void *)to, from, n);
}
static __always_inline unsigned long
-__copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
-{
- return __copy_from_user_ll_nozero(to, from, n);
-}
-
-/**
- * __copy_from_user: - Copy a block of data from user space, with less checking.
- * @to: Destination address, in kernel space.
- * @from: Source address, in user space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- * enabled.
- *
- * Copy data from user space to kernel space. Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- *
- * If some data could not be copied, this function will pad the copied
- * data to the requested size using zero bytes.
- *
- * An alternate version - __copy_from_user_inatomic() - may be called from
- * atomic context and will fail rather than sleep. In this case the
- * uncopied bytes will *NOT* be padded with zeros. See fs/filemap.h
- * for explanation of why this is needed.
- */
-static __always_inline unsigned long
-__copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- might_fault();
- check_object_size(to, n, false);
- if (__builtin_constant_p(n)) {
- unsigned long ret;
-
- switch (n) {
- case 1:
- __uaccess_begin();
- __get_user_size(*(u8 *)to, from, 1, ret, 1);
- __uaccess_end();
- return ret;
- case 2:
- __uaccess_begin();
- __get_user_size(*(u16 *)to, from, 2, ret, 2);
- __uaccess_end();
- return ret;
- case 4:
- __uaccess_begin();
- __get_user_size(*(u32 *)to, from, 4, ret, 4);
- __uaccess_end();
- return ret;
- }
- }
- return __copy_from_user_ll(to, from, n);
-}
-
-static __always_inline unsigned long __copy_from_user_nocache(void *to,
- const void __user *from, unsigned long n)
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
{
- might_fault();
if (__builtin_constant_p(n)) {
unsigned long ret;
switch (n) {
case 1:
+ ret = 0;
__uaccess_begin();
- __get_user_size(*(u8 *)to, from, 1, ret, 1);
+ __get_user_asm_nozero(*(u8 *)to, from, ret,
+ "b", "b", "=q", 1);
__uaccess_end();
return ret;
case 2:
+ ret = 0;
__uaccess_begin();
- __get_user_size(*(u16 *)to, from, 2, ret, 2);
+ __get_user_asm_nozero(*(u16 *)to, from, ret,
+ "w", "w", "=r", 2);
__uaccess_end();
return ret;
case 4:
+ ret = 0;
__uaccess_begin();
- __get_user_size(*(u32 *)to, from, 4, ret, 4);
+ __get_user_asm_nozero(*(u32 *)to, from, ret,
+ "l", "k", "=r", 4);
__uaccess_end();
return ret;
}
}
- return __copy_from_user_ll_nocache(to, from, n);
+ return __copy_user_ll(to, (__force const void *)from, n);
}
static __always_inline unsigned long
* User space memory access functions
*/
#include <linux/compiler.h>
-#include <linux/errno.h>
#include <linux/lockdep.h>
#include <linux/kasan-checks.h>
#include <asm/alternative.h>
return ret;
}
-__must_check unsigned long
-copy_in_user(void __user *to, const void __user *from, unsigned len);
-
-static __always_inline __must_check
-int __copy_from_user_nocheck(void *dst, const void __user *src, unsigned size)
+static __always_inline __must_check unsigned long
+raw_copy_from_user(void *dst, const void __user *src, unsigned long size)
{
int ret = 0;
- check_object_size(dst, size, false);
if (!__builtin_constant_p(size))
return copy_user_generic(dst, (__force void *)src, size);
switch (size) {
case 1:
__uaccess_begin();
- __get_user_asm(*(u8 *)dst, (u8 __user *)src,
+ __get_user_asm_nozero(*(u8 *)dst, (u8 __user *)src,
ret, "b", "b", "=q", 1);
__uaccess_end();
return ret;
case 2:
__uaccess_begin();
- __get_user_asm(*(u16 *)dst, (u16 __user *)src,
+ __get_user_asm_nozero(*(u16 *)dst, (u16 __user *)src,
ret, "w", "w", "=r", 2);
__uaccess_end();
return ret;
case 4:
__uaccess_begin();
- __get_user_asm(*(u32 *)dst, (u32 __user *)src,
+ __get_user_asm_nozero(*(u32 *)dst, (u32 __user *)src,
ret, "l", "k", "=r", 4);
__uaccess_end();
return ret;
case 8:
__uaccess_begin();
- __get_user_asm(*(u64 *)dst, (u64 __user *)src,
+ __get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src,
ret, "q", "", "=r", 8);
__uaccess_end();
return ret;
case 10:
__uaccess_begin();
- __get_user_asm(*(u64 *)dst, (u64 __user *)src,
+ __get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src,
ret, "q", "", "=r", 10);
if (likely(!ret))
- __get_user_asm(*(u16 *)(8 + (char *)dst),
+ __get_user_asm_nozero(*(u16 *)(8 + (char *)dst),
(u16 __user *)(8 + (char __user *)src),
ret, "w", "w", "=r", 2);
__uaccess_end();
return ret;
case 16:
__uaccess_begin();
- __get_user_asm(*(u64 *)dst, (u64 __user *)src,
+ __get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src,
ret, "q", "", "=r", 16);
if (likely(!ret))
- __get_user_asm(*(u64 *)(8 + (char *)dst),
+ __get_user_asm_nozero(*(u64 *)(8 + (char *)dst),
(u64 __user *)(8 + (char __user *)src),
ret, "q", "", "=r", 8);
__uaccess_end();
}
}
-static __always_inline __must_check
-int __copy_from_user(void *dst, const void __user *src, unsigned size)
-{
- might_fault();
- kasan_check_write(dst, size);
- return __copy_from_user_nocheck(dst, src, size);
-}
-
-static __always_inline __must_check
-int __copy_to_user_nocheck(void __user *dst, const void *src, unsigned size)
+static __always_inline __must_check unsigned long
+raw_copy_to_user(void __user *dst, const void *src, unsigned long size)
{
int ret = 0;
- check_object_size(src, size, true);
if (!__builtin_constant_p(size))
return copy_user_generic((__force void *)dst, src, size);
switch (size) {
}
static __always_inline __must_check
-int __copy_to_user(void __user *dst, const void *src, unsigned size)
-{
- might_fault();
- kasan_check_read(src, size);
- return __copy_to_user_nocheck(dst, src, size);
-}
-
-static __always_inline __must_check
-int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
-{
- int ret = 0;
-
- might_fault();
- if (!__builtin_constant_p(size))
- return copy_user_generic((__force void *)dst,
- (__force void *)src, size);
- switch (size) {
- case 1: {
- u8 tmp;
- __uaccess_begin();
- __get_user_asm(tmp, (u8 __user *)src,
- ret, "b", "b", "=q", 1);
- if (likely(!ret))
- __put_user_asm(tmp, (u8 __user *)dst,
- ret, "b", "b", "iq", 1);
- __uaccess_end();
- return ret;
- }
- case 2: {
- u16 tmp;
- __uaccess_begin();
- __get_user_asm(tmp, (u16 __user *)src,
- ret, "w", "w", "=r", 2);
- if (likely(!ret))
- __put_user_asm(tmp, (u16 __user *)dst,
- ret, "w", "w", "ir", 2);
- __uaccess_end();
- return ret;
- }
-
- case 4: {
- u32 tmp;
- __uaccess_begin();
- __get_user_asm(tmp, (u32 __user *)src,
- ret, "l", "k", "=r", 4);
- if (likely(!ret))
- __put_user_asm(tmp, (u32 __user *)dst,
- ret, "l", "k", "ir", 4);
- __uaccess_end();
- return ret;
- }
- case 8: {
- u64 tmp;
- __uaccess_begin();
- __get_user_asm(tmp, (u64 __user *)src,
- ret, "q", "", "=r", 8);
- if (likely(!ret))
- __put_user_asm(tmp, (u64 __user *)dst,
- ret, "q", "", "er", 8);
- __uaccess_end();
- return ret;
- }
- default:
- return copy_user_generic((__force void *)dst,
- (__force void *)src, size);
- }
-}
-
-static __must_check __always_inline int
-__copy_from_user_inatomic(void *dst, const void __user *src, unsigned size)
-{
- kasan_check_write(dst, size);
- return __copy_from_user_nocheck(dst, src, size);
-}
-
-static __must_check __always_inline int
-__copy_to_user_inatomic(void __user *dst, const void *src, unsigned size)
+unsigned long raw_copy_in_user(void __user *dst, const void __user *src, unsigned long size)
{
- kasan_check_read(src, size);
- return __copy_to_user_nocheck(dst, src, size);
+ return copy_user_generic((__force void *)dst,
+ (__force void *)src, size);
}
extern long __copy_user_nocache(void *dst, const void __user *src,
unsigned size, int zerorest);
static inline int
-__copy_from_user_nocache(void *dst, const void __user *src, unsigned size)
-{
- might_fault();
- kasan_check_write(dst, size);
- return __copy_user_nocache(dst, src, size, 1);
-}
-
-static inline int
__copy_from_user_inatomic_nocache(void *dst, const void __user *src,
unsigned size)
{
#include <linux/spinlock.h>
#include <linux/pfn.h>
#include <linux/mm.h>
+#include <linux/device.h>
#include <linux/uaccess.h>
#include <asm/page.h>
#include <linux/screen_info.h>
#include <linux/apm_bios.h>
#include <linux/edd.h>
-#include <asm/e820.h>
#include <asm/ist.h>
#include <video/edid.h>
__u32 efi_memmap_hi;
};
+/*
+ * This is the maximum number of entries in struct boot_params::e820_table
+ * (the zeropage), which is part of the x86 boot protocol ABI:
+ */
+#define E820_MAX_ENTRIES_ZEROPAGE 128
+
+/*
+ * The E820 memory region entry of the boot protocol ABI:
+ */
+struct boot_e820_entry {
+ __u64 addr;
+ __u64 size;
+ __u32 type;
+} __attribute__((packed));
+
/* The so-called "zeropage" */
struct boot_params {
struct screen_info screen_info; /* 0x000 */
struct setup_header hdr; /* setup header */ /* 0x1f1 */
__u8 _pad7[0x290-0x1f1-sizeof(struct setup_header)];
__u32 edd_mbr_sig_buffer[EDD_MBR_SIG_MAX]; /* 0x290 */
- struct e820entry e820_map[E820MAX]; /* 0x2d0 */
+ struct boot_e820_entry e820_table[E820_MAX_ENTRIES_ZEROPAGE]; /* 0x2d0 */
__u8 _pad8[48]; /* 0xcd0 */
struct edd_info eddbuf[EDDMAXNR]; /* 0xd00 */
__u8 _pad9[276]; /* 0xeec */
#ifndef _ASM_X86_PRCTL_H
#define _ASM_X86_PRCTL_H
-#define ARCH_SET_GS 0x1001
-#define ARCH_SET_FS 0x1002
-#define ARCH_GET_FS 0x1003
-#define ARCH_GET_GS 0x1004
+#define ARCH_SET_GS 0x1001
+#define ARCH_SET_FS 0x1002
+#define ARCH_GET_FS 0x1003
+#define ARCH_GET_GS 0x1004
+
+#define ARCH_GET_CPUID 0x1011
+#define ARCH_SET_CPUID 0x1012
#define ARCH_MAP_VDSO_X32 0x2001
#define ARCH_MAP_VDSO_32 0x2002
#include <linux/pci.h>
#include <linux/efi-bgrt.h>
+#include <asm/e820/api.h>
#include <asm/irqdomain.h>
#include <asm/pci_x86.h>
#include <asm/pgtable.h>
return 0;
}
-static int __init acpi_parse_bgrt(struct acpi_table_header *table)
-{
- efi_bgrt_init(table);
- return 0;
-}
-
int __init acpi_boot_init(void)
{
/* those are executed after early-quirks are executed */
void __init arch_reserve_mem_area(acpi_physical_address addr, size_t size)
{
- e820_add_region(addr, size, E820_ACPI);
- update_e820();
+ e820__range_add(addr, size, E820_TYPE_ACPI);
+ e820__update_table_print();
}
#include <linux/pci.h>
#include <linux/bitops.h>
#include <linux/suspend.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/io.h>
#include <asm/iommu.h>
#include <asm/gart.h>
fix = 1;
if (gart_fix_e820 && !fix && aper_enabled) {
- if (e820_any_mapped(aper_base, aper_base + aper_size,
- E820_RAM)) {
+ if (e820__mapped_any(aper_base, aper_base + aper_size,
+ E820_TYPE_RAM)) {
/* reserve it, so we can reuse it in second kernel */
pr_info("e820: reserve [mem %#010Lx-%#010Lx] for GART\n",
aper_base, aper_base + aper_size - 1);
- e820_add_region(aper_base, aper_size, E820_RESERVED);
- update_e820();
+ e820__range_add(aper_base, aper_size, E820_TYPE_RESERVED);
+ e820__update_table_print();
}
}
TICK_NSEC, lapic_clockevent.shift);
lapic_clockevent.max_delta_ns =
clockevent_delta2ns(0x7FFFFF, &lapic_clockevent);
+ lapic_clockevent.max_delta_ticks = 0x7FFFFF;
lapic_clockevent.min_delta_ns =
clockevent_delta2ns(0xF, &lapic_clockevent);
+ lapic_clockevent.min_delta_ticks = 0xF;
lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
return 0;
}
lapic_clockevent.shift);
lapic_clockevent.max_delta_ns =
clockevent_delta2ns(0x7FFFFFFF, &lapic_clockevent);
+ lapic_clockevent.max_delta_ticks = 0x7FFFFFFF;
lapic_clockevent.min_delta_ns =
clockevent_delta2ns(0xF, &lapic_clockevent);
+ lapic_clockevent.min_delta_ticks = 0xF;
lapic_timer_frequency = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS;
}
/*
- * need call insert after e820_reserve_resources()
+ * need call insert after e820__reserve_resources()
* that is using request_resource
*/
late_initcall(lapic_insert_resource);
#include <linux/interrupt.h>
#include <asm/acpi.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
static void noop_init_apic_ldr(void) { }
static void noop_send_IPI(int cpu, int vector) { }
#include <linux/interrupt.h>
#include <asm/acpi.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#ifdef CONFIG_HOTPLUG_CPU
#define DEFAULT_SEND_IPI (1)
#include <asm/uv/bios.h>
#include <asm/uv/uv.h>
#include <asm/apic.h>
+#include <asm/e820/api.h>
#include <asm/ipi.h>
#include <asm/smp.h>
#include <asm/x86_init.h>
#include <linux/sched/clock.h>
#include <asm/cpufeature.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/mtrr.h>
#include <asm/msr.h>
return;
}
- if (ring3mwait_disabled) {
- msr_clear_bit(MSR_MISC_FEATURE_ENABLES,
- MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT);
+ if (ring3mwait_disabled)
return;
- }
-
- msr_set_bit(MSR_MISC_FEATURE_ENABLES,
- MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT);
set_cpu_cap(c, X86_FEATURE_RING3MWAIT);
+ this_cpu_or(msr_misc_features_shadow,
+ 1UL << MSR_MISC_FEATURES_ENABLES_RING3MWAIT_BIT);
if (c == &boot_cpu_data)
ELF_HWCAP2 |= HWCAP2_RING3MWAIT;
init_intel_energy_perf(c);
}
+static void init_cpuid_fault(struct cpuinfo_x86 *c)
+{
+ u64 msr;
+
+ if (!rdmsrl_safe(MSR_PLATFORM_INFO, &msr)) {
+ if (msr & MSR_PLATFORM_INFO_CPUID_FAULT)
+ set_cpu_cap(c, X86_FEATURE_CPUID_FAULT);
+ }
+}
+
+static void init_intel_misc_features(struct cpuinfo_x86 *c)
+{
+ u64 msr;
+
+ if (rdmsrl_safe(MSR_MISC_FEATURES_ENABLES, &msr))
+ return;
+
+ /* Clear all MISC features */
+ this_cpu_write(msr_misc_features_shadow, 0);
+
+ /* Check features and update capabilities and shadow control bits */
+ init_cpuid_fault(c);
+ probe_xeon_phi_r3mwait(c);
+
+ msr = this_cpu_read(msr_misc_features_shadow);
+ wrmsrl(MSR_MISC_FEATURES_ENABLES, msr);
+}
+
static void init_intel(struct cpuinfo_x86 *c)
{
unsigned int l2 = 0;
init_intel_energy_perf(c);
- probe_xeon_phi_r3mwait(c);
+ init_intel_misc_features(c);
}
#ifdef CONFIG_X86_32
obj-$(CONFIG_X86_THERMAL_VECTOR) += therm_throt.o
obj-$(CONFIG_ACPI_APEI) += mce-apei.o
+
+obj-$(CONFIG_X86_MCELOG_LEGACY) += dev-mcelog.o
--- /dev/null
+/*
+ * /dev/mcelog driver
+ *
+ * K8 parts Copyright 2002,2003 Andi Kleen, SuSE Labs.
+ * Rest from unknown author(s).
+ * 2004 Andi Kleen. Rewrote most of it.
+ * Copyright 2008 Intel Corporation
+ * Author: Andi Kleen
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/miscdevice.h>
+#include <linux/slab.h>
+#include <linux/kmod.h>
+#include <linux/poll.h>
+
+#include "mce-internal.h"
+
+static DEFINE_MUTEX(mce_chrdev_read_mutex);
+
+static char mce_helper[128];
+static char *mce_helper_argv[2] = { mce_helper, NULL };
+
+#define mce_log_get_idx_check(p) \
+({ \
+ RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \
+ !lockdep_is_held(&mce_chrdev_read_mutex), \
+ "suspicious mce_log_get_idx_check() usage"); \
+ smp_load_acquire(&(p)); \
+})
+
+/*
+ * Lockless MCE logging infrastructure.
+ * This avoids deadlocks on printk locks without having to break locks. Also
+ * separate MCEs from kernel messages to avoid bogus bug reports.
+ */
+
+static struct mce_log_buffer mcelog = {
+ .signature = MCE_LOG_SIGNATURE,
+ .len = MCE_LOG_LEN,
+ .recordlen = sizeof(struct mce),
+};
+
+static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait);
+
+/* User mode helper program triggered by machine check event */
+extern char mce_helper[128];
+
+static int dev_mce_log(struct notifier_block *nb, unsigned long val,
+ void *data)
+{
+ struct mce *mce = (struct mce *)data;
+ unsigned int next, entry;
+
+ wmb();
+ for (;;) {
+ entry = mce_log_get_idx_check(mcelog.next);
+ for (;;) {
+
+ /*
+ * When the buffer fills up discard new entries.
+ * Assume that the earlier errors are the more
+ * interesting ones:
+ */
+ if (entry >= MCE_LOG_LEN) {
+ set_bit(MCE_OVERFLOW,
+ (unsigned long *)&mcelog.flags);
+ return NOTIFY_OK;
+ }
+ /* Old left over entry. Skip: */
+ if (mcelog.entry[entry].finished) {
+ entry++;
+ continue;
+ }
+ break;
+ }
+ smp_rmb();
+ next = entry + 1;
+ if (cmpxchg(&mcelog.next, entry, next) == entry)
+ break;
+ }
+ memcpy(mcelog.entry + entry, mce, sizeof(struct mce));
+ wmb();
+ mcelog.entry[entry].finished = 1;
+ wmb();
+
+ /* wake processes polling /dev/mcelog */
+ wake_up_interruptible(&mce_chrdev_wait);
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block dev_mcelog_nb = {
+ .notifier_call = dev_mce_log,
+ .priority = MCE_PRIO_MCELOG,
+};
+
+static void mce_do_trigger(struct work_struct *work)
+{
+ call_usermodehelper(mce_helper, mce_helper_argv, NULL, UMH_NO_WAIT);
+}
+
+static DECLARE_WORK(mce_trigger_work, mce_do_trigger);
+
+
+void mce_work_trigger(void)
+{
+ if (mce_helper[0])
+ schedule_work(&mce_trigger_work);
+}
+
+static ssize_t
+show_trigger(struct device *s, struct device_attribute *attr, char *buf)
+{
+ strcpy(buf, mce_helper);
+ strcat(buf, "\n");
+ return strlen(mce_helper) + 1;
+}
+
+static ssize_t set_trigger(struct device *s, struct device_attribute *attr,
+ const char *buf, size_t siz)
+{
+ char *p;
+
+ strncpy(mce_helper, buf, sizeof(mce_helper));
+ mce_helper[sizeof(mce_helper)-1] = 0;
+ p = strchr(mce_helper, '\n');
+
+ if (p)
+ *p = 0;
+
+ return strlen(mce_helper) + !!p;
+}
+
+DEVICE_ATTR(trigger, 0644, show_trigger, set_trigger);
+
+/*
+ * mce_chrdev: Character device /dev/mcelog to read and clear the MCE log.
+ */
+
+static DEFINE_SPINLOCK(mce_chrdev_state_lock);
+static int mce_chrdev_open_count; /* #times opened */
+static int mce_chrdev_open_exclu; /* already open exclusive? */
+
+static int mce_chrdev_open(struct inode *inode, struct file *file)
+{
+ spin_lock(&mce_chrdev_state_lock);
+
+ if (mce_chrdev_open_exclu ||
+ (mce_chrdev_open_count && (file->f_flags & O_EXCL))) {
+ spin_unlock(&mce_chrdev_state_lock);
+
+ return -EBUSY;
+ }
+
+ if (file->f_flags & O_EXCL)
+ mce_chrdev_open_exclu = 1;
+ mce_chrdev_open_count++;
+
+ spin_unlock(&mce_chrdev_state_lock);
+
+ return nonseekable_open(inode, file);
+}
+
+static int mce_chrdev_release(struct inode *inode, struct file *file)
+{
+ spin_lock(&mce_chrdev_state_lock);
+
+ mce_chrdev_open_count--;
+ mce_chrdev_open_exclu = 0;
+
+ spin_unlock(&mce_chrdev_state_lock);
+
+ return 0;
+}
+
+static void collect_tscs(void *data)
+{
+ unsigned long *cpu_tsc = (unsigned long *)data;
+
+ cpu_tsc[smp_processor_id()] = rdtsc();
+}
+
+static int mce_apei_read_done;
+
+/* Collect MCE record of previous boot in persistent storage via APEI ERST. */
+static int __mce_read_apei(char __user **ubuf, size_t usize)
+{
+ int rc;
+ u64 record_id;
+ struct mce m;
+
+ if (usize < sizeof(struct mce))
+ return -EINVAL;
+
+ rc = apei_read_mce(&m, &record_id);
+ /* Error or no more MCE record */
+ if (rc <= 0) {
+ mce_apei_read_done = 1;
+ /*
+ * When ERST is disabled, mce_chrdev_read() should return
+ * "no record" instead of "no device."
+ */
+ if (rc == -ENODEV)
+ return 0;
+ return rc;
+ }
+ rc = -EFAULT;
+ if (copy_to_user(*ubuf, &m, sizeof(struct mce)))
+ return rc;
+ /*
+ * In fact, we should have cleared the record after that has
+ * been flushed to the disk or sent to network in
+ * /sbin/mcelog, but we have no interface to support that now,
+ * so just clear it to avoid duplication.
+ */
+ rc = apei_clear_mce(record_id);
+ if (rc) {
+ mce_apei_read_done = 1;
+ return rc;
+ }
+ *ubuf += sizeof(struct mce);
+
+ return 0;
+}
+
+static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf,
+ size_t usize, loff_t *off)
+{
+ char __user *buf = ubuf;
+ unsigned long *cpu_tsc;
+ unsigned prev, next;
+ int i, err;
+
+ cpu_tsc = kmalloc(nr_cpu_ids * sizeof(long), GFP_KERNEL);
+ if (!cpu_tsc)
+ return -ENOMEM;
+
+ mutex_lock(&mce_chrdev_read_mutex);
+
+ if (!mce_apei_read_done) {
+ err = __mce_read_apei(&buf, usize);
+ if (err || buf != ubuf)
+ goto out;
+ }
+
+ next = mce_log_get_idx_check(mcelog.next);
+
+ /* Only supports full reads right now */
+ err = -EINVAL;
+ if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce))
+ goto out;
+
+ err = 0;
+ prev = 0;
+ do {
+ for (i = prev; i < next; i++) {
+ unsigned long start = jiffies;
+ struct mce *m = &mcelog.entry[i];
+
+ while (!m->finished) {
+ if (time_after_eq(jiffies, start + 2)) {
+ memset(m, 0, sizeof(*m));
+ goto timeout;
+ }
+ cpu_relax();
+ }
+ smp_rmb();
+ err |= copy_to_user(buf, m, sizeof(*m));
+ buf += sizeof(*m);
+timeout:
+ ;
+ }
+
+ memset(mcelog.entry + prev, 0,
+ (next - prev) * sizeof(struct mce));
+ prev = next;
+ next = cmpxchg(&mcelog.next, prev, 0);
+ } while (next != prev);
+
+ synchronize_sched();
+
+ /*
+ * Collect entries that were still getting written before the
+ * synchronize.
+ */
+ on_each_cpu(collect_tscs, cpu_tsc, 1);
+
+ for (i = next; i < MCE_LOG_LEN; i++) {
+ struct mce *m = &mcelog.entry[i];
+
+ if (m->finished && m->tsc < cpu_tsc[m->cpu]) {
+ err |= copy_to_user(buf, m, sizeof(*m));
+ smp_rmb();
+ buf += sizeof(*m);
+ memset(m, 0, sizeof(*m));
+ }
+ }
+
+ if (err)
+ err = -EFAULT;
+
+out:
+ mutex_unlock(&mce_chrdev_read_mutex);
+ kfree(cpu_tsc);
+
+ return err ? err : buf - ubuf;
+}
+
+static unsigned int mce_chrdev_poll(struct file *file, poll_table *wait)
+{
+ poll_wait(file, &mce_chrdev_wait, wait);
+ if (READ_ONCE(mcelog.next))
+ return POLLIN | POLLRDNORM;
+ if (!mce_apei_read_done && apei_check_mce())
+ return POLLIN | POLLRDNORM;
+ return 0;
+}
+
+static long mce_chrdev_ioctl(struct file *f, unsigned int cmd,
+ unsigned long arg)
+{
+ int __user *p = (int __user *)arg;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ switch (cmd) {
+ case MCE_GET_RECORD_LEN:
+ return put_user(sizeof(struct mce), p);
+ case MCE_GET_LOG_LEN:
+ return put_user(MCE_LOG_LEN, p);
+ case MCE_GETCLEAR_FLAGS: {
+ unsigned flags;
+
+ do {
+ flags = mcelog.flags;
+ } while (cmpxchg(&mcelog.flags, flags, 0) != flags);
+
+ return put_user(flags, p);
+ }
+ default:
+ return -ENOTTY;
+ }
+}
+
+static ssize_t (*mce_write)(struct file *filp, const char __user *ubuf,
+ size_t usize, loff_t *off);
+
+void register_mce_write_callback(ssize_t (*fn)(struct file *filp,
+ const char __user *ubuf,
+ size_t usize, loff_t *off))
+{
+ mce_write = fn;
+}
+EXPORT_SYMBOL_GPL(register_mce_write_callback);
+
+static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf,
+ size_t usize, loff_t *off)
+{
+ if (mce_write)
+ return mce_write(filp, ubuf, usize, off);
+ else
+ return -EINVAL;
+}
+
+static const struct file_operations mce_chrdev_ops = {
+ .open = mce_chrdev_open,
+ .release = mce_chrdev_release,
+ .read = mce_chrdev_read,
+ .write = mce_chrdev_write,
+ .poll = mce_chrdev_poll,
+ .unlocked_ioctl = mce_chrdev_ioctl,
+ .llseek = no_llseek,
+};
+
+static struct miscdevice mce_chrdev_device = {
+ MISC_MCELOG_MINOR,
+ "mcelog",
+ &mce_chrdev_ops,
+};
+
+static __init int dev_mcelog_init_device(void)
+{
+ int err;
+
+ /* register character device /dev/mcelog */
+ err = misc_register(&mce_chrdev_device);
+ if (err) {
+ pr_err("Unable to init device /dev/mcelog (rc: %d)\n", err);
+ return err;
+ }
+ mce_register_decode_chain(&dev_mcelog_nb);
+ return 0;
+}
+device_initcall_sync(dev_mcelog_init_device);
head = llist_reverse_order(head);
llist_for_each_entry_safe(node, tmp, head, llnode) {
mce = &node->mce;
- atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce);
+ blocking_notifier_call_chain(&x86_mce_decoder_chain, 0, mce);
gen_pool_free(mce_evt_pool, (unsigned long)node, sizeof(*node));
}
}
MCE_PANIC_SEVERITY,
};
-extern struct atomic_notifier_head x86_mce_decoder_chain;
+extern struct blocking_notifier_head x86_mce_decoder_chain;
#define ATTR_LEN 16
#define INITIAL_CHECK_INTERVAL 5 * 60 /* 5 minutes */
m1->addr != m2->addr ||
m1->misc != m2->misc;
}
+
+extern struct device_attribute dev_attr_trigger;
+
+#ifdef CONFIG_X86_MCELOG_LEGACY
+extern void mce_work_trigger(void);
+#else
+static inline void mce_work_trigger(void) { }
+#endif
#include <linux/poll.h>
#include <linux/nmi.h>
#include <linux/cpu.h>
+#include <linux/ras.h>
#include <linux/smp.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <asm/tlbflush.h>
#include <asm/mce.h>
#include <asm/msr.h>
+#include <asm/reboot.h>
#include "mce-internal.h"
-static DEFINE_MUTEX(mce_chrdev_read_mutex);
-
-static int mce_chrdev_open_count; /* #times opened */
-
-#define mce_log_get_idx_check(p) \
-({ \
- RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \
- !lockdep_is_held(&mce_chrdev_read_mutex), \
- "suspicious mce_log_get_idx_check() usage"); \
- smp_load_acquire(&(p)); \
-})
+static DEFINE_MUTEX(mce_log_mutex);
#define CREATE_TRACE_POINTS
#include <trace/events/mce.h>
.monarch_timeout = -1
};
-/* User mode helper program triggered by machine check event */
-static unsigned long mce_need_notify;
-static char mce_helper[128];
-static char *mce_helper_argv[2] = { mce_helper, NULL };
-
-static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait);
-
static DEFINE_PER_CPU(struct mce, mces_seen);
-static int cpu_missing;
+static unsigned long mce_need_notify;
+static int cpu_missing;
/*
* MCA banks polled by the period polling timer for corrected events.
* CPU/chipset specific EDAC code can register a notifier call here to print
* MCE errors in a human-readable form.
*/
-ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
+BLOCKING_NOTIFIER_HEAD(x86_mce_decoder_chain);
/* Do initial initialization of a struct mce */
void mce_setup(struct mce *m)
DEFINE_PER_CPU(struct mce, injectm);
EXPORT_PER_CPU_SYMBOL_GPL(injectm);
-/*
- * Lockless MCE logging infrastructure.
- * This avoids deadlocks on printk locks without having to break locks. Also
- * separate MCEs from kernel messages to avoid bogus bug reports.
- */
-
-static struct mce_log mcelog = {
- .signature = MCE_LOG_SIGNATURE,
- .len = MCE_LOG_LEN,
- .recordlen = sizeof(struct mce),
-};
-
-void mce_log(struct mce *mce)
+void mce_log(struct mce *m)
{
- unsigned next, entry;
-
- /* Emit the trace record: */
- trace_mce_record(mce);
-
- if (!mce_gen_pool_add(mce))
+ if (!mce_gen_pool_add(m))
irq_work_queue(&mce_irq_work);
-
- wmb();
- for (;;) {
- entry = mce_log_get_idx_check(mcelog.next);
- for (;;) {
-
- /*
- * When the buffer fills up discard new entries.
- * Assume that the earlier errors are the more
- * interesting ones:
- */
- if (entry >= MCE_LOG_LEN) {
- set_bit(MCE_OVERFLOW,
- (unsigned long *)&mcelog.flags);
- return;
- }
- /* Old left over entry. Skip: */
- if (mcelog.entry[entry].finished) {
- entry++;
- continue;
- }
- break;
- }
- smp_rmb();
- next = entry + 1;
- if (cmpxchg(&mcelog.next, entry, next) == entry)
- break;
- }
- memcpy(mcelog.entry + entry, mce, sizeof(struct mce));
- wmb();
- mcelog.entry[entry].finished = 1;
- wmb();
-
- set_bit(0, &mce_need_notify);
}
void mce_inject_log(struct mce *m)
{
- mutex_lock(&mce_chrdev_read_mutex);
+ mutex_lock(&mce_log_mutex);
mce_log(m);
- mutex_unlock(&mce_chrdev_read_mutex);
+ mutex_unlock(&mce_log_mutex);
}
EXPORT_SYMBOL_GPL(mce_inject_log);
static struct notifier_block mce_srao_nb;
+/*
+ * We run the default notifier if we have only the SRAO, the first and the
+ * default notifier registered. I.e., the mandatory NUM_DEFAULT_NOTIFIERS
+ * notifiers registered on the chain.
+ */
+#define NUM_DEFAULT_NOTIFIERS 3
static atomic_t num_notifiers;
void mce_register_decode_chain(struct notifier_block *nb)
{
- atomic_inc(&num_notifiers);
+ if (WARN_ON(nb->priority > MCE_PRIO_MCELOG && nb->priority < MCE_PRIO_EDAC))
+ return;
- WARN_ON(nb->priority > MCE_PRIO_LOWEST && nb->priority < MCE_PRIO_EDAC);
+ atomic_inc(&num_notifiers);
- atomic_notifier_chain_register(&x86_mce_decoder_chain, nb);
+ blocking_notifier_chain_register(&x86_mce_decoder_chain, nb);
}
EXPORT_SYMBOL_GPL(mce_register_decode_chain);
{
atomic_dec(&num_notifiers);
- atomic_notifier_chain_unregister(&x86_mce_decoder_chain, nb);
+ blocking_notifier_chain_unregister(&x86_mce_decoder_chain, nb);
}
EXPORT_SYMBOL_GPL(mce_unregister_decode_chain);
static void print_mce(struct mce *m)
{
- int ret = 0;
-
__print_mce(m);
-
- /*
- * Print out human-readable details about the MCE error,
- * (if the CPU has an implementation for that)
- */
- ret = atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
- if (ret == NOTIFY_STOP)
- return;
-
pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n");
}
static void mce_irq_work_cb(struct irq_work *entry)
{
- mce_notify_irq();
mce_schedule_work();
}
*/
static int mce_usable_address(struct mce *m)
{
- if (!(m->status & MCI_STATUS_MISCV) || !(m->status & MCI_STATUS_ADDRV))
+ if (!(m->status & MCI_STATUS_ADDRV))
return 0;
/* Checks after this one are Intel-specific: */
if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
return 1;
+ if (!(m->status & MCI_STATUS_MISCV))
+ return 0;
+
if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT)
return 0;
+
if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS)
return 0;
+
return 1;
}
+static bool memory_error(struct mce *m)
+{
+ struct cpuinfo_x86 *c = &boot_cpu_data;
+
+ if (c->x86_vendor == X86_VENDOR_AMD) {
+ /* ErrCodeExt[20:16] */
+ u8 xec = (m->status >> 16) & 0x1f;
+
+ return (xec == 0x0 || xec == 0x8);
+ } else if (c->x86_vendor == X86_VENDOR_INTEL) {
+ /*
+ * Intel SDM Volume 3B - 15.9.2 Compound Error Codes
+ *
+ * Bit 7 of the MCACOD field of IA32_MCi_STATUS is used for
+ * indicating a memory error. Bit 8 is used for indicating a
+ * cache hierarchy error. The combination of bit 2 and bit 3
+ * is used for indicating a `generic' cache hierarchy error
+ * But we can't just blindly check the above bits, because if
+ * bit 11 is set, then it is a bus/interconnect error - and
+ * either way the above bits just gives more detail on what
+ * bus/interconnect error happened. Note that bit 12 can be
+ * ignored, as it's the "filter" bit.
+ */
+ return (m->status & 0xef80) == BIT(7) ||
+ (m->status & 0xef00) == BIT(8) ||
+ (m->status & 0xeffc) == 0xc;
+ }
+
+ return false;
+}
+
+static bool cec_add_mce(struct mce *m)
+{
+ if (!m)
+ return false;
+
+ /* We eat only correctable DRAM errors with usable addresses. */
+ if (memory_error(m) &&
+ !(m->status & MCI_STATUS_UC) &&
+ mce_usable_address(m))
+ if (!cec_add_elem(m->addr >> PAGE_SHIFT))
+ return true;
+
+ return false;
+}
+
+static int mce_first_notifier(struct notifier_block *nb, unsigned long val,
+ void *data)
+{
+ struct mce *m = (struct mce *)data;
+
+ if (!m)
+ return NOTIFY_DONE;
+
+ if (cec_add_mce(m))
+ return NOTIFY_STOP;
+
+ /* Emit the trace record: */
+ trace_mce_record(m);
+
+ set_bit(0, &mce_need_notify);
+
+ mce_notify_irq();
+
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block first_nb = {
+ .notifier_call = mce_first_notifier,
+ .priority = MCE_PRIO_FIRST,
+};
+
static int srao_decode_notifier(struct notifier_block *nb, unsigned long val,
void *data)
{
if (!m)
return NOTIFY_DONE;
- /*
- * Run the default notifier if we have only the SRAO
- * notifier and us registered.
- */
- if (atomic_read(&num_notifiers) > 2)
- return NOTIFY_DONE;
-
- /* Don't print when mcelog is running */
- if (mce_chrdev_open_count > 0)
+ if (atomic_read(&num_notifiers) > NUM_DEFAULT_NOTIFIERS)
return NOTIFY_DONE;
__print_mce(m);
}
}
-static bool memory_error(struct mce *m)
-{
- struct cpuinfo_x86 *c = &boot_cpu_data;
-
- if (c->x86_vendor == X86_VENDOR_AMD) {
- /* ErrCodeExt[20:16] */
- u8 xec = (m->status >> 16) & 0x1f;
-
- return (xec == 0x0 || xec == 0x8);
- } else if (c->x86_vendor == X86_VENDOR_INTEL) {
- /*
- * Intel SDM Volume 3B - 15.9.2 Compound Error Codes
- *
- * Bit 7 of the MCACOD field of IA32_MCi_STATUS is used for
- * indicating a memory error. Bit 8 is used for indicating a
- * cache hierarchy error. The combination of bit 2 and bit 3
- * is used for indicating a `generic' cache hierarchy error
- * But we can't just blindly check the above bits, because if
- * bit 11 is set, then it is a bus/interconnect error - and
- * either way the above bits just gives more detail on what
- * bus/interconnect error happened. Note that bit 12 can be
- * ignored, as it's the "filter" bit.
- */
- return (m->status & 0xef80) == BIT(7) ||
- (m->status & 0xef00) == BIT(8) ||
- (m->status & 0xeffc) == 0xc;
- }
-
- return false;
-}
-
DEFINE_PER_CPU(unsigned, mce_poll_count);
/*
* on Intel.
*/
int lmce = 1;
+ int cpu = smp_processor_id();
- /* If this CPU is offline, just bail out. */
- if (cpu_is_offline(smp_processor_id())) {
+ /*
+ * Cases where we avoid rendezvous handler timeout:
+ * 1) If this CPU is offline.
+ *
+ * 2) If crashing_cpu was set, e.g. we're entering kdump and we need to
+ * skip those CPUs which remain looping in the 1st kernel - see
+ * crash_nmi_callback().
+ *
+ * Note: there still is a small window between kexec-ing and the new,
+ * kdump kernel establishing a new #MC handler where a broadcasted MCE
+ * might not get handled properly.
+ */
+ if (cpu_is_offline(cpu) ||
+ (crashing_cpu != -1 && crashing_cpu != cpu)) {
u64 mcgstatus;
mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
del_timer_sync(&per_cpu(mce_timer, cpu));
}
-static void mce_do_trigger(struct work_struct *work)
-{
- call_usermodehelper(mce_helper, mce_helper_argv, NULL, UMH_NO_WAIT);
-}
-
-static DECLARE_WORK(mce_trigger_work, mce_do_trigger);
-
/*
* Notify the user(s) about new machine check events.
* Can be called from interrupt context, but not from machine check/NMI
static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2);
if (test_and_clear_bit(0, &mce_need_notify)) {
- /* wake processes polling /dev/mcelog */
- wake_up_interruptible(&mce_chrdev_wait);
-
- if (mce_helper[0])
- schedule_work(&mce_trigger_work);
+ mce_work_trigger();
if (__ratelimit(&ratelimit))
pr_info(HW_ERR "Machine check events logged\n");
return 0;
}
-static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
+/*
+ * Init basic CPU features needed for early decoding of MCEs.
+ */
+static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c)
{
- switch (c->x86_vendor) {
- case X86_VENDOR_INTEL:
- mce_intel_feature_init(c);
- mce_adjust_timer = cmci_intel_adjust_timer;
- break;
-
- case X86_VENDOR_AMD: {
+ if (c->x86_vendor == X86_VENDOR_AMD) {
mce_flags.overflow_recov = !!cpu_has(c, X86_FEATURE_OVERFLOW_RECOV);
mce_flags.succor = !!cpu_has(c, X86_FEATURE_SUCCOR);
mce_flags.smca = !!cpu_has(c, X86_FEATURE_SMCA);
- /*
- * Install proper ops for Scalable MCA enabled processors
- */
if (mce_flags.smca) {
msr_ops.ctl = smca_ctl_reg;
msr_ops.status = smca_status_reg;
msr_ops.addr = smca_addr_reg;
msr_ops.misc = smca_misc_reg;
}
- mce_amd_feature_init(c);
+ }
+}
+static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
+{
+ switch (c->x86_vendor) {
+ case X86_VENDOR_INTEL:
+ mce_intel_feature_init(c);
+ mce_adjust_timer = cmci_intel_adjust_timer;
+ break;
+
+ case X86_VENDOR_AMD: {
+ mce_amd_feature_init(c);
break;
}
machine_check_vector = do_machine_check;
+ __mcheck_cpu_init_early(c);
__mcheck_cpu_init_generic();
__mcheck_cpu_init_vendor(c);
__mcheck_cpu_init_clear_banks();
}
-/*
- * mce_chrdev: Character device /dev/mcelog to read and clear the MCE log.
- */
-
-static DEFINE_SPINLOCK(mce_chrdev_state_lock);
-static int mce_chrdev_open_exclu; /* already open exclusive? */
-
-static int mce_chrdev_open(struct inode *inode, struct file *file)
-{
- spin_lock(&mce_chrdev_state_lock);
-
- if (mce_chrdev_open_exclu ||
- (mce_chrdev_open_count && (file->f_flags & O_EXCL))) {
- spin_unlock(&mce_chrdev_state_lock);
-
- return -EBUSY;
- }
-
- if (file->f_flags & O_EXCL)
- mce_chrdev_open_exclu = 1;
- mce_chrdev_open_count++;
-
- spin_unlock(&mce_chrdev_state_lock);
-
- return nonseekable_open(inode, file);
-}
-
-static int mce_chrdev_release(struct inode *inode, struct file *file)
-{
- spin_lock(&mce_chrdev_state_lock);
-
- mce_chrdev_open_count--;
- mce_chrdev_open_exclu = 0;
-
- spin_unlock(&mce_chrdev_state_lock);
-
- return 0;
-}
-
-static void collect_tscs(void *data)
-{
- unsigned long *cpu_tsc = (unsigned long *)data;
-
- cpu_tsc[smp_processor_id()] = rdtsc();
-}
-
-static int mce_apei_read_done;
-
-/* Collect MCE record of previous boot in persistent storage via APEI ERST. */
-static int __mce_read_apei(char __user **ubuf, size_t usize)
-{
- int rc;
- u64 record_id;
- struct mce m;
-
- if (usize < sizeof(struct mce))
- return -EINVAL;
-
- rc = apei_read_mce(&m, &record_id);
- /* Error or no more MCE record */
- if (rc <= 0) {
- mce_apei_read_done = 1;
- /*
- * When ERST is disabled, mce_chrdev_read() should return
- * "no record" instead of "no device."
- */
- if (rc == -ENODEV)
- return 0;
- return rc;
- }
- rc = -EFAULT;
- if (copy_to_user(*ubuf, &m, sizeof(struct mce)))
- return rc;
- /*
- * In fact, we should have cleared the record after that has
- * been flushed to the disk or sent to network in
- * /sbin/mcelog, but we have no interface to support that now,
- * so just clear it to avoid duplication.
- */
- rc = apei_clear_mce(record_id);
- if (rc) {
- mce_apei_read_done = 1;
- return rc;
- }
- *ubuf += sizeof(struct mce);
-
- return 0;
-}
-
-static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf,
- size_t usize, loff_t *off)
-{
- char __user *buf = ubuf;
- unsigned long *cpu_tsc;
- unsigned prev, next;
- int i, err;
-
- cpu_tsc = kmalloc(nr_cpu_ids * sizeof(long), GFP_KERNEL);
- if (!cpu_tsc)
- return -ENOMEM;
-
- mutex_lock(&mce_chrdev_read_mutex);
-
- if (!mce_apei_read_done) {
- err = __mce_read_apei(&buf, usize);
- if (err || buf != ubuf)
- goto out;
- }
-
- next = mce_log_get_idx_check(mcelog.next);
-
- /* Only supports full reads right now */
- err = -EINVAL;
- if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce))
- goto out;
-
- err = 0;
- prev = 0;
- do {
- for (i = prev; i < next; i++) {
- unsigned long start = jiffies;
- struct mce *m = &mcelog.entry[i];
-
- while (!m->finished) {
- if (time_after_eq(jiffies, start + 2)) {
- memset(m, 0, sizeof(*m));
- goto timeout;
- }
- cpu_relax();
- }
- smp_rmb();
- err |= copy_to_user(buf, m, sizeof(*m));
- buf += sizeof(*m);
-timeout:
- ;
- }
-
- memset(mcelog.entry + prev, 0,
- (next - prev) * sizeof(struct mce));
- prev = next;
- next = cmpxchg(&mcelog.next, prev, 0);
- } while (next != prev);
-
- synchronize_sched();
-
- /*
- * Collect entries that were still getting written before the
- * synchronize.
- */
- on_each_cpu(collect_tscs, cpu_tsc, 1);
-
- for (i = next; i < MCE_LOG_LEN; i++) {
- struct mce *m = &mcelog.entry[i];
-
- if (m->finished && m->tsc < cpu_tsc[m->cpu]) {
- err |= copy_to_user(buf, m, sizeof(*m));
- smp_rmb();
- buf += sizeof(*m);
- memset(m, 0, sizeof(*m));
- }
- }
-
- if (err)
- err = -EFAULT;
-
-out:
- mutex_unlock(&mce_chrdev_read_mutex);
- kfree(cpu_tsc);
-
- return err ? err : buf - ubuf;
-}
-
-static unsigned int mce_chrdev_poll(struct file *file, poll_table *wait)
-{
- poll_wait(file, &mce_chrdev_wait, wait);
- if (READ_ONCE(mcelog.next))
- return POLLIN | POLLRDNORM;
- if (!mce_apei_read_done && apei_check_mce())
- return POLLIN | POLLRDNORM;
- return 0;
-}
-
-static long mce_chrdev_ioctl(struct file *f, unsigned int cmd,
- unsigned long arg)
-{
- int __user *p = (int __user *)arg;
-
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
-
- switch (cmd) {
- case MCE_GET_RECORD_LEN:
- return put_user(sizeof(struct mce), p);
- case MCE_GET_LOG_LEN:
- return put_user(MCE_LOG_LEN, p);
- case MCE_GETCLEAR_FLAGS: {
- unsigned flags;
-
- do {
- flags = mcelog.flags;
- } while (cmpxchg(&mcelog.flags, flags, 0) != flags);
-
- return put_user(flags, p);
- }
- default:
- return -ENOTTY;
- }
-}
-
-static ssize_t (*mce_write)(struct file *filp, const char __user *ubuf,
- size_t usize, loff_t *off);
-
-void register_mce_write_callback(ssize_t (*fn)(struct file *filp,
- const char __user *ubuf,
- size_t usize, loff_t *off))
-{
- mce_write = fn;
-}
-EXPORT_SYMBOL_GPL(register_mce_write_callback);
-
-static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf,
- size_t usize, loff_t *off)
-{
- if (mce_write)
- return mce_write(filp, ubuf, usize, off);
- else
- return -EINVAL;
-}
-
-static const struct file_operations mce_chrdev_ops = {
- .open = mce_chrdev_open,
- .release = mce_chrdev_release,
- .read = mce_chrdev_read,
- .write = mce_chrdev_write,
- .poll = mce_chrdev_poll,
- .unlocked_ioctl = mce_chrdev_ioctl,
- .llseek = no_llseek,
-};
-
-static struct miscdevice mce_chrdev_device = {
- MISC_MCELOG_MINOR,
- "mcelog",
- &mce_chrdev_ops,
-};
-
static void __mce_disable_bank(void *arg)
{
int bank = *((int *)arg);
int __init mcheck_init(void)
{
mcheck_intel_therm_init();
+ mce_register_decode_chain(&first_nb);
mce_register_decode_chain(&mce_srao_nb);
mce_register_decode_chain(&mce_default_nb);
mcheck_vendor_init_severity();
return size;
}
-static ssize_t
-show_trigger(struct device *s, struct device_attribute *attr, char *buf)
-{
- strcpy(buf, mce_helper);
- strcat(buf, "\n");
- return strlen(mce_helper) + 1;
-}
-
-static ssize_t set_trigger(struct device *s, struct device_attribute *attr,
- const char *buf, size_t siz)
-{
- char *p;
-
- strncpy(mce_helper, buf, sizeof(mce_helper));
- mce_helper[sizeof(mce_helper)-1] = 0;
- p = strchr(mce_helper, '\n');
-
- if (p)
- *p = 0;
-
- return strlen(mce_helper) + !!p;
-}
-
static ssize_t set_ignore_ce(struct device *s,
struct device_attribute *attr,
const char *buf, size_t size)
return ret;
}
-static DEVICE_ATTR(trigger, 0644, show_trigger, set_trigger);
static DEVICE_INT_ATTR(tolerant, 0644, mca_cfg.tolerant);
static DEVICE_INT_ATTR(monarch_timeout, 0644, mca_cfg.monarch_timeout);
static DEVICE_BOOL_ATTR(dont_log_ce, 0644, mca_cfg.dont_log_ce);
static struct device_attribute *mce_device_attrs[] = {
&dev_attr_tolerant.attr,
&dev_attr_check_interval.attr,
+#ifdef CONFIG_X86_MCELOG_LEGACY
&dev_attr_trigger,
+#endif
&dev_attr_monarch_timeout.attr,
&dev_attr_dont_log_ce.attr,
&dev_attr_ignore_ce.attr,
static __init int mcheck_init_device(void)
{
- enum cpuhp_state hp_online;
int err;
if (!mce_available(&boot_cpu_data)) {
mce_cpu_online, mce_cpu_pre_down);
if (err < 0)
goto err_out_online;
- hp_online = err;
register_syscore_ops(&mce_syscore_ops);
- /* register character device /dev/mcelog */
- err = misc_register(&mce_chrdev_device);
- if (err)
- goto err_register;
-
return 0;
-err_register:
- unregister_syscore_ops(&mce_syscore_ops);
- cpuhp_remove_state(hp_online);
-
err_out_online:
cpuhp_remove_state(CPUHP_X86_MCE_DEAD);
free_cpumask_var(mce_device_initialized);
err_out:
- pr_err("Unable to init device /dev/mcelog (rc: %d)\n", err);
+ pr_err("Unable to init MCE device (rc: %d)\n", err);
return err;
}
static_branch_inc(&mcsafe_key);
mcheck_debugfs_init();
+ cec_init();
/*
* Flush out everything that has been logged during early boot, now that
case INTEL_FAM6_BROADWELL_XEON_D:
case INTEL_FAM6_BROADWELL_X:
case INTEL_FAM6_SKYLAKE_X:
+ case INTEL_FAM6_XEON_PHI_KNL:
+ case INTEL_FAM6_XEON_PHI_KNM:
+
if (rdmsrl_safe(MSR_PPIN_CTL, &val))
return;
#include <linux/range.h>
#include <asm/processor.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/mtrr.h>
#include <asm/msr.h>
trim_size <<= PAGE_SHIFT;
trim_size -= trim_start;
- return e820_update_range(trim_start, trim_size, E820_RAM, E820_RESERVED);
+ return e820__range_update(trim_start, trim_size, E820_TYPE_RAM, E820_TYPE_RESERVED);
}
/**
WARN_ON(1);
pr_info("update e820 for mtrr\n");
- update_e820();
+ e820__update_table_print();
return 1;
}
#include <linux/syscore_ops.h>
#include <asm/cpufeature.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/mtrr.h>
#include <asm/msr.h>
#include <asm/pat.h>
#include <asm/nmi.h>
#include <asm/hw_irq.h>
#include <asm/apic.h>
+#include <asm/e820/types.h>
#include <asm/io_apic.h>
#include <asm/hpet.h>
#include <linux/kdebug.h>
return ret;
}
-static int add_e820_entry(struct boot_params *params, struct e820entry *entry)
+static int add_e820_entry(struct boot_params *params, struct e820_entry *entry)
{
unsigned int nr_e820_entries;
nr_e820_entries = params->e820_entries;
- if (nr_e820_entries >= E820MAX)
+ if (nr_e820_entries >= E820_MAX_ENTRIES_ZEROPAGE)
return 1;
- memcpy(¶ms->e820_map[nr_e820_entries], entry,
- sizeof(struct e820entry));
+ memcpy(¶ms->e820_table[nr_e820_entries], entry,
+ sizeof(struct e820_entry));
params->e820_entries++;
return 0;
}
{
struct crash_memmap_data *cmd = arg;
struct boot_params *params = cmd->params;
- struct e820entry ei;
+ struct e820_entry ei;
ei.addr = start;
ei.size = end - start + 1;
{
int i, ret = 0;
unsigned long flags;
- struct e820entry ei;
+ struct e820_entry ei;
struct crash_memmap_data cmd;
struct crash_mem *cmem;
/* Add first 640K segment */
ei.addr = image->arch.backup_src_start;
ei.size = image->arch.backup_src_sz;
- ei.type = E820_RAM;
+ ei.type = E820_TYPE_RAM;
add_e820_entry(params, &ei);
/* Add ACPI tables */
- cmd.type = E820_ACPI;
+ cmd.type = E820_TYPE_ACPI;
flags = IORESOURCE_MEM | IORESOURCE_BUSY;
walk_iomem_res_desc(IORES_DESC_ACPI_TABLES, flags, 0, -1, &cmd,
memmap_entry_callback);
/* Add ACPI Non-volatile Storage */
- cmd.type = E820_NVS;
+ cmd.type = E820_TYPE_NVS;
walk_iomem_res_desc(IORES_DESC_ACPI_NV_STORAGE, flags, 0, -1, &cmd,
memmap_entry_callback);
if (crashk_low_res.end) {
ei.addr = crashk_low_res.start;
ei.size = crashk_low_res.end - crashk_low_res.start + 1;
- ei.type = E820_RAM;
+ ei.type = E820_TYPE_RAM;
add_e820_entry(params, &ei);
}
if (ei.size < PAGE_SIZE)
continue;
ei.addr = cmem->ranges[i].start;
- ei.type = E820_RAM;
+ ei.type = E820_TYPE_RAM;
add_e820_entry(params, &ei);
}
/*
- * Handle the memory map.
- * The functions here do the job until bootmem takes over.
+ * Low level x86 E820 memory map handling functions.
*
- * Getting sanitize_e820_map() in sync with i386 version by applying change:
- * - Provisions for empty E820 memory regions (reported by certain BIOSes).
- * Alex Achenbach <xela@slit.de>, December 2002.
- * Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
+ * The firmware and bootloader passes us the "E820 table", which is the primary
+ * physical memory layout description available about x86 systems.
*
+ * The kernel takes the E820 memory layout and optionally modifies it with
+ * quirks and other tweaks, and feeds that into the generic Linux memory
+ * allocation code routines via a platform independent interface (memblock, etc.).
*/
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
#include <linux/crash_dump.h>
-#include <linux/export.h>
#include <linux/bootmem.h>
-#include <linux/pfn.h>
#include <linux/suspend.h>
#include <linux/acpi.h>
#include <linux/firmware-map.h>
#include <linux/memblock.h>
#include <linux/sort.h>
-#include <asm/e820.h>
-#include <asm/proto.h>
+#include <asm/e820/api.h>
#include <asm/setup.h>
-#include <asm/cpufeature.h>
/*
- * The e820 map is the map that gets modified e.g. with command line parameters
- * and that is also registered with modifications in the kernel resource tree
- * with the iomem_resource as parent.
+ * We organize the E820 table into two main data structures:
*
- * The e820_saved is directly saved after the BIOS-provided memory map is
- * copied. It doesn't get modified afterwards. It's registered for the
- * /sys/firmware/memmap interface.
+ * - 'e820_table_firmware': the original firmware version passed to us by the
+ * bootloader - not modified by the kernel. We use this to:
*
- * That memory map is not modified and is used as base for kexec. The kexec'd
- * kernel should get the same memory map as the firmware provides. Then the
- * user can e.g. boot the original kernel with mem=1G while still booting the
- * next kernel with full memory.
+ * - inform the user about the firmware's notion of memory layout
+ * via /sys/firmware/memmap
+ *
+ * - the hibernation code uses it to generate a kernel-independent MD5
+ * fingerprint of the physical memory layout of a system.
+ *
+ * - kexec, which is a bootloader in disguise, uses the original E820
+ * layout to pass to the kexec-ed kernel. This way the original kernel
+ * can have a restricted E820 map while the kexec()-ed kexec-kernel
+ * can have access to full memory - etc.
+ *
+ * - 'e820_table': this is the main E820 table that is massaged by the
+ * low level x86 platform code, or modified by boot parameters, before
+ * passed on to higher level MM layers.
+ *
+ * Once the E820 map has been converted to the standard Linux memory layout
+ * information its role stops - modifying it has no effect and does not get
+ * re-propagated. So itsmain role is a temporary bootstrap storage of firmware
+ * specific memory layout data during early bootup.
*/
-static struct e820map initial_e820 __initdata;
-static struct e820map initial_e820_saved __initdata;
-struct e820map *e820 __refdata = &initial_e820;
-struct e820map *e820_saved __refdata = &initial_e820_saved;
+static struct e820_table e820_table_init __initdata;
+static struct e820_table e820_table_firmware_init __initdata;
+
+struct e820_table *e820_table __refdata = &e820_table_init;
+struct e820_table *e820_table_firmware __refdata = &e820_table_firmware_init;
/* For PCI or other memory-mapped resources */
unsigned long pci_mem_start = 0xaeedbabe;
* This function checks if any part of the range <start,end> is mapped
* with type.
*/
-int
-e820_any_mapped(u64 start, u64 end, unsigned type)
+bool e820__mapped_any(u64 start, u64 end, enum e820_type type)
{
int i;
- for (i = 0; i < e820->nr_map; i++) {
- struct e820entry *ei = &e820->map[i];
+ for (i = 0; i < e820_table->nr_entries; i++) {
+ struct e820_entry *entry = &e820_table->entries[i];
- if (type && ei->type != type)
+ if (type && entry->type != type)
continue;
- if (ei->addr >= end || ei->addr + ei->size <= start)
+ if (entry->addr >= end || entry->addr + entry->size <= start)
continue;
return 1;
}
return 0;
}
-EXPORT_SYMBOL_GPL(e820_any_mapped);
+EXPORT_SYMBOL_GPL(e820__mapped_any);
/*
- * This function checks if the entire range <start,end> is mapped with type.
+ * This function checks if the entire <start,end> range is mapped with 'type'.
*
- * Note: this function only works correct if the e820 table is sorted and
- * not-overlapping, which is the case
+ * Note: this function only works correctly once the E820 table is sorted and
+ * not-overlapping (at least for the range specified), which is the case normally.
*/
-int __init e820_all_mapped(u64 start, u64 end, unsigned type)
+bool __init e820__mapped_all(u64 start, u64 end, enum e820_type type)
{
int i;
- for (i = 0; i < e820->nr_map; i++) {
- struct e820entry *ei = &e820->map[i];
+ for (i = 0; i < e820_table->nr_entries; i++) {
+ struct e820_entry *entry = &e820_table->entries[i];
- if (type && ei->type != type)
+ if (type && entry->type != type)
continue;
- /* is the region (part) in overlap with the current region ?*/
- if (ei->addr >= end || ei->addr + ei->size <= start)
+
+ /* Is the region (part) in overlap with the current region? */
+ if (entry->addr >= end || entry->addr + entry->size <= start)
continue;
- /* if the region is at the beginning of <start,end> we move
- * start to the end of the region since it's ok until there
+ /*
+ * If the region is at the beginning of <start,end> we move
+ * 'start' to the end of the region since it's ok until there
*/
- if (ei->addr <= start)
- start = ei->addr + ei->size;
+ if (entry->addr <= start)
+ start = entry->addr + entry->size;
+
/*
- * if start is now at or beyond end, we're done, full
- * coverage
+ * If 'start' is now at or beyond 'end', we're done, full
+ * coverage of the desired range exists:
*/
if (start >= end)
return 1;
}
/*
- * Add a memory region to the kernel e820 map.
+ * Add a memory region to the kernel E820 map.
*/
-static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size,
- int type)
+static void __init __e820__range_add(struct e820_table *table, u64 start, u64 size, enum e820_type type)
{
- int x = e820x->nr_map;
+ int x = table->nr_entries;
- if (x >= ARRAY_SIZE(e820x->map)) {
- printk(KERN_ERR "e820: too many entries; ignoring [mem %#010llx-%#010llx]\n",
- (unsigned long long) start,
- (unsigned long long) (start + size - 1));
+ if (x >= ARRAY_SIZE(table->entries)) {
+ pr_err("e820: too many entries; ignoring [mem %#010llx-%#010llx]\n", start, start + size - 1);
return;
}
- e820x->map[x].addr = start;
- e820x->map[x].size = size;
- e820x->map[x].type = type;
- e820x->nr_map++;
+ table->entries[x].addr = start;
+ table->entries[x].size = size;
+ table->entries[x].type = type;
+ table->nr_entries++;
}
-void __init e820_add_region(u64 start, u64 size, int type)
+void __init e820__range_add(u64 start, u64 size, enum e820_type type)
{
- __e820_add_region(e820, start, size, type);
+ __e820__range_add(e820_table, start, size, type);
}
-static void __init e820_print_type(u32 type)
+static void __init e820_print_type(enum e820_type type)
{
switch (type) {
- case E820_RAM:
- case E820_RESERVED_KERN:
- printk(KERN_CONT "usable");
- break;
- case E820_RESERVED:
- printk(KERN_CONT "reserved");
- break;
- case E820_ACPI:
- printk(KERN_CONT "ACPI data");
- break;
- case E820_NVS:
- printk(KERN_CONT "ACPI NVS");
- break;
- case E820_UNUSABLE:
- printk(KERN_CONT "unusable");
- break;
- case E820_PMEM:
- case E820_PRAM:
- printk(KERN_CONT "persistent (type %u)", type);
- break;
- default:
- printk(KERN_CONT "type %u", type);
- break;
+ case E820_TYPE_RAM: /* Fall through: */
+ case E820_TYPE_RESERVED_KERN: pr_cont("usable"); break;
+ case E820_TYPE_RESERVED: pr_cont("reserved"); break;
+ case E820_TYPE_ACPI: pr_cont("ACPI data"); break;
+ case E820_TYPE_NVS: pr_cont("ACPI NVS"); break;
+ case E820_TYPE_UNUSABLE: pr_cont("unusable"); break;
+ case E820_TYPE_PMEM: /* Fall through: */
+ case E820_TYPE_PRAM: pr_cont("persistent (type %u)", type); break;
+ default: pr_cont("type %u", type); break;
}
}
-void __init e820_print_map(char *who)
+void __init e820__print_table(char *who)
{
int i;
- for (i = 0; i < e820->nr_map; i++) {
- printk(KERN_INFO "%s: [mem %#018Lx-%#018Lx] ", who,
- (unsigned long long) e820->map[i].addr,
- (unsigned long long)
- (e820->map[i].addr + e820->map[i].size - 1));
- e820_print_type(e820->map[i].type);
- printk(KERN_CONT "\n");
+ for (i = 0; i < e820_table->nr_entries; i++) {
+ pr_info("%s: [mem %#018Lx-%#018Lx] ", who,
+ e820_table->entries[i].addr,
+ e820_table->entries[i].addr + e820_table->entries[i].size - 1);
+
+ e820_print_type(e820_table->entries[i].type);
+ pr_cont("\n");
}
}
/*
- * Sanitize the BIOS e820 map.
+ * Sanitize an E820 map.
*
- * Some e820 responses include overlapping entries. The following
- * replaces the original e820 map with a new one, removing overlaps,
+ * Some E820 layouts include overlapping entries. The following
+ * replaces the original E820 map with a new one, removing overlaps,
* and resolving conflicting memory types in favor of highest
* numbered type.
*
- * The input parameter biosmap points to an array of 'struct
- * e820entry' which on entry has elements in the range [0, *pnr_map)
- * valid, and which has space for up to max_nr_map entries.
- * On return, the resulting sanitized e820 map entries will be in
- * overwritten in the same location, starting at biosmap.
+ * The input parameter 'entries' points to an array of 'struct
+ * e820_entry' which on entry has elements in the range [0, *nr_entries)
+ * valid, and which has space for up to max_nr_entries entries.
+ * On return, the resulting sanitized E820 map entries will be in
+ * overwritten in the same location, starting at 'entries'.
*
- * The integer pointed to by pnr_map must be valid on entry (the
- * current number of valid entries located at biosmap). If the
- * sanitizing succeeds the *pnr_map will be updated with the new
- * number of valid entries (something no more than max_nr_map).
+ * The integer pointed to by nr_entries must be valid on entry (the
+ * current number of valid entries located at 'entries'). If the
+ * sanitizing succeeds the *nr_entries will be updated with the new
+ * number of valid entries (something no more than max_nr_entries).
*
- * The return value from sanitize_e820_map() is zero if it
+ * The return value from e820__update_table() is zero if it
* successfully 'sanitized' the map entries passed in, and is -1
* if it did nothing, which can happen if either of (1) it was
* only passed one map entry, or (2) any of the input map entries
* ______________________4_
*/
struct change_member {
- struct e820entry *pbios; /* pointer to original bios entry */
- unsigned long long addr; /* address for this change point */
+ /* Pointer to the original entry: */
+ struct e820_entry *entry;
+ /* Address for this change point: */
+ unsigned long long addr;
};
+static struct change_member change_point_list[2*E820_MAX_ENTRIES] __initdata;
+static struct change_member *change_point[2*E820_MAX_ENTRIES] __initdata;
+static struct e820_entry *overlap_list[E820_MAX_ENTRIES] __initdata;
+static struct e820_entry new_entries[E820_MAX_ENTRIES] __initdata;
+
static int __init cpcompare(const void *a, const void *b)
{
struct change_member * const *app = a, * const *bpp = b;
/*
* Inputs are pointers to two elements of change_point[]. If their
- * addresses are unequal, their difference dominates. If the addresses
+ * addresses are not equal, their difference dominates. If the addresses
* are equal, then consider one that represents the end of its region
* to be greater than one that does not.
*/
if (ap->addr != bp->addr)
return ap->addr > bp->addr ? 1 : -1;
- return (ap->addr != ap->pbios->addr) - (bp->addr != bp->pbios->addr);
+ return (ap->addr != ap->entry->addr) - (bp->addr != bp->entry->addr);
}
-int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map,
- u32 *pnr_map)
+int __init e820__update_table(struct e820_table *table)
{
- static struct change_member change_point_list[2*E820_X_MAX] __initdata;
- static struct change_member *change_point[2*E820_X_MAX] __initdata;
- static struct e820entry *overlap_list[E820_X_MAX] __initdata;
- static struct e820entry new_bios[E820_X_MAX] __initdata;
- unsigned long current_type, last_type;
+ struct e820_entry *entries = table->entries;
+ u32 max_nr_entries = ARRAY_SIZE(table->entries);
+ enum e820_type current_type, last_type;
unsigned long long last_addr;
- int chgidx;
- int overlap_entries;
- int new_bios_entry;
- int old_nr, new_nr, chg_nr;
- int i;
+ u32 new_nr_entries, overlap_entries;
+ u32 i, chg_idx, chg_nr;
- /* if there's only one memory region, don't bother */
- if (*pnr_map < 2)
+ /* If there's only one memory region, don't bother: */
+ if (table->nr_entries < 2)
return -1;
- old_nr = *pnr_map;
- BUG_ON(old_nr > max_nr_map);
+ table->nr_entries = table->nr_entries;
+ BUG_ON(table->nr_entries > max_nr_entries);
- /* bail out if we find any unreasonable addresses in bios map */
- for (i = 0; i < old_nr; i++)
- if (biosmap[i].addr + biosmap[i].size < biosmap[i].addr)
+ /* Bail out if we find any unreasonable addresses in the map: */
+ for (i = 0; i < table->nr_entries; i++) {
+ if (entries[i].addr + entries[i].size < entries[i].addr)
return -1;
+ }
- /* create pointers for initial change-point information (for sorting) */
- for (i = 0; i < 2 * old_nr; i++)
+ /* Create pointers for initial change-point information (for sorting): */
+ for (i = 0; i < 2 * table->nr_entries; i++)
change_point[i] = &change_point_list[i];
- /* record all known change-points (starting and ending addresses),
- omitting those that are for empty memory regions */
- chgidx = 0;
- for (i = 0; i < old_nr; i++) {
- if (biosmap[i].size != 0) {
- change_point[chgidx]->addr = biosmap[i].addr;
- change_point[chgidx++]->pbios = &biosmap[i];
- change_point[chgidx]->addr = biosmap[i].addr +
- biosmap[i].size;
- change_point[chgidx++]->pbios = &biosmap[i];
+ /*
+ * Record all known change-points (starting and ending addresses),
+ * omitting empty memory regions:
+ */
+ chg_idx = 0;
+ for (i = 0; i < table->nr_entries; i++) {
+ if (entries[i].size != 0) {
+ change_point[chg_idx]->addr = entries[i].addr;
+ change_point[chg_idx++]->entry = &entries[i];
+ change_point[chg_idx]->addr = entries[i].addr + entries[i].size;
+ change_point[chg_idx++]->entry = &entries[i];
}
}
- chg_nr = chgidx;
-
- /* sort change-point list by memory addresses (low -> high) */
- sort(change_point, chg_nr, sizeof *change_point, cpcompare, NULL);
-
- /* create a new bios memory map, removing overlaps */
- overlap_entries = 0; /* number of entries in the overlap table */
- new_bios_entry = 0; /* index for creating new bios map entries */
- last_type = 0; /* start with undefined memory type */
- last_addr = 0; /* start with 0 as last starting address */
-
- /* loop through change-points, determining affect on the new bios map */
- for (chgidx = 0; chgidx < chg_nr; chgidx++) {
- /* keep track of all overlapping bios entries */
- if (change_point[chgidx]->addr ==
- change_point[chgidx]->pbios->addr) {
- /*
- * add map entry to overlap list (> 1 entry
- * implies an overlap)
- */
- overlap_list[overlap_entries++] =
- change_point[chgidx]->pbios;
+ chg_nr = chg_idx;
+
+ /* Sort change-point list by memory addresses (low -> high): */
+ sort(change_point, chg_nr, sizeof(*change_point), cpcompare, NULL);
+
+ /* Create a new memory map, removing overlaps: */
+ overlap_entries = 0; /* Number of entries in the overlap table */
+ new_nr_entries = 0; /* Index for creating new map entries */
+ last_type = 0; /* Start with undefined memory type */
+ last_addr = 0; /* Start with 0 as last starting address */
+
+ /* Loop through change-points, determining effect on the new map: */
+ for (chg_idx = 0; chg_idx < chg_nr; chg_idx++) {
+ /* Keep track of all overlapping entries */
+ if (change_point[chg_idx]->addr == change_point[chg_idx]->entry->addr) {
+ /* Add map entry to overlap list (> 1 entry implies an overlap) */
+ overlap_list[overlap_entries++] = change_point[chg_idx]->entry;
} else {
- /*
- * remove entry from list (order independent,
- * so swap with last)
- */
+ /* Remove entry from list (order independent, so swap with last): */
for (i = 0; i < overlap_entries; i++) {
- if (overlap_list[i] ==
- change_point[chgidx]->pbios)
- overlap_list[i] =
- overlap_list[overlap_entries-1];
+ if (overlap_list[i] == change_point[chg_idx]->entry)
+ overlap_list[i] = overlap_list[overlap_entries-1];
}
overlap_entries--;
}
/*
- * if there are overlapping entries, decide which
+ * If there are overlapping entries, decide which
* "type" to use (larger value takes precedence --
* 1=usable, 2,3,4,4+=unusable)
*/
current_type = 0;
- for (i = 0; i < overlap_entries; i++)
+ for (i = 0; i < overlap_entries; i++) {
if (overlap_list[i]->type > current_type)
current_type = overlap_list[i]->type;
- /*
- * continue building up new bios map based on this
- * information
- */
- if (current_type != last_type || current_type == E820_PRAM) {
+ }
+
+ /* Continue building up new map based on this information: */
+ if (current_type != last_type || current_type == E820_TYPE_PRAM) {
if (last_type != 0) {
- new_bios[new_bios_entry].size =
- change_point[chgidx]->addr - last_addr;
- /*
- * move forward only if the new size
- * was non-zero
- */
- if (new_bios[new_bios_entry].size != 0)
- /*
- * no more space left for new
- * bios entries ?
- */
- if (++new_bios_entry >= max_nr_map)
+ new_entries[new_nr_entries].size = change_point[chg_idx]->addr - last_addr;
+ /* Move forward only if the new size was non-zero: */
+ if (new_entries[new_nr_entries].size != 0)
+ /* No more space left for new entries? */
+ if (++new_nr_entries >= max_nr_entries)
break;
}
if (current_type != 0) {
- new_bios[new_bios_entry].addr =
- change_point[chgidx]->addr;
- new_bios[new_bios_entry].type = current_type;
- last_addr = change_point[chgidx]->addr;
+ new_entries[new_nr_entries].addr = change_point[chg_idx]->addr;
+ new_entries[new_nr_entries].type = current_type;
+ last_addr = change_point[chg_idx]->addr;
}
last_type = current_type;
}
}
- /* retain count for new bios entries */
- new_nr = new_bios_entry;
- /* copy new bios mapping into original location */
- memcpy(biosmap, new_bios, new_nr * sizeof(struct e820entry));
- *pnr_map = new_nr;
+ /* Copy the new entries into the original location: */
+ memcpy(entries, new_entries, new_nr_entries*sizeof(*entries));
+ table->nr_entries = new_nr_entries;
return 0;
}
-static int __init __append_e820_map(struct e820entry *biosmap, int nr_map)
+static int __init __append_e820_table(struct boot_e820_entry *entries, u32 nr_entries)
{
- while (nr_map) {
- u64 start = biosmap->addr;
- u64 size = biosmap->size;
+ struct boot_e820_entry *entry = entries;
+
+ while (nr_entries) {
+ u64 start = entry->addr;
+ u64 size = entry->size;
u64 end = start + size - 1;
- u32 type = biosmap->type;
+ u32 type = entry->type;
- /* Overflow in 64 bits? Ignore the memory map. */
+ /* Ignore the entry on 64-bit overflow: */
if (start > end && likely(size))
return -1;
- e820_add_region(start, size, type);
+ e820__range_add(start, size, type);
- biosmap++;
- nr_map--;
+ entry++;
+ nr_entries--;
}
return 0;
}
/*
- * Copy the BIOS e820 map into a safe place.
+ * Copy the BIOS E820 map into a safe place.
*
* Sanity-check it while we're at it..
*
* will have given us a memory map that we can use to properly
* set up memory. If we aren't, we'll fake a memory map.
*/
-static int __init append_e820_map(struct e820entry *biosmap, int nr_map)
+static int __init append_e820_table(struct boot_e820_entry *entries, u32 nr_entries)
{
/* Only one memory region (or negative)? Ignore it */
- if (nr_map < 2)
+ if (nr_entries < 2)
return -1;
- return __append_e820_map(biosmap, nr_map);
+ return __append_e820_table(entries, nr_entries);
}
-static u64 __init __e820_update_range(struct e820map *e820x, u64 start,
- u64 size, unsigned old_type,
- unsigned new_type)
+static u64 __init
+__e820__range_update(struct e820_table *table, u64 start, u64 size, enum e820_type old_type, enum e820_type new_type)
{
u64 end;
unsigned int i;
size = ULLONG_MAX - start;
end = start + size;
- printk(KERN_DEBUG "e820: update [mem %#010Lx-%#010Lx] ",
- (unsigned long long) start, (unsigned long long) (end - 1));
+ printk(KERN_DEBUG "e820: update [mem %#010Lx-%#010Lx] ", start, end - 1);
e820_print_type(old_type);
- printk(KERN_CONT " ==> ");
+ pr_cont(" ==> ");
e820_print_type(new_type);
- printk(KERN_CONT "\n");
+ pr_cont("\n");
- for (i = 0; i < e820x->nr_map; i++) {
- struct e820entry *ei = &e820x->map[i];
+ for (i = 0; i < table->nr_entries; i++) {
+ struct e820_entry *entry = &table->entries[i];
u64 final_start, final_end;
- u64 ei_end;
+ u64 entry_end;
- if (ei->type != old_type)
+ if (entry->type != old_type)
continue;
- ei_end = ei->addr + ei->size;
- /* totally covered by new range? */
- if (ei->addr >= start && ei_end <= end) {
- ei->type = new_type;
- real_updated_size += ei->size;
+ entry_end = entry->addr + entry->size;
+
+ /* Completely covered by new range? */
+ if (entry->addr >= start && entry_end <= end) {
+ entry->type = new_type;
+ real_updated_size += entry->size;
continue;
}
- /* new range is totally covered? */
- if (ei->addr < start && ei_end > end) {
- __e820_add_region(e820x, start, size, new_type);
- __e820_add_region(e820x, end, ei_end - end, ei->type);
- ei->size = start - ei->addr;
+ /* New range is completely covered? */
+ if (entry->addr < start && entry_end > end) {
+ __e820__range_add(table, start, size, new_type);
+ __e820__range_add(table, end, entry_end - end, entry->type);
+ entry->size = start - entry->addr;
real_updated_size += size;
continue;
}
- /* partially covered */
- final_start = max(start, ei->addr);
- final_end = min(end, ei_end);
+ /* Partially covered: */
+ final_start = max(start, entry->addr);
+ final_end = min(end, entry_end);
if (final_start >= final_end)
continue;
- __e820_add_region(e820x, final_start, final_end - final_start,
- new_type);
+ __e820__range_add(table, final_start, final_end - final_start, new_type);
real_updated_size += final_end - final_start;
/*
- * left range could be head or tail, so need to update
- * size at first.
+ * Left range could be head or tail, so need to update
+ * its size first:
*/
- ei->size -= final_end - final_start;
- if (ei->addr < final_start)
+ entry->size -= final_end - final_start;
+ if (entry->addr < final_start)
continue;
- ei->addr = final_end;
+
+ entry->addr = final_end;
}
return real_updated_size;
}
-u64 __init e820_update_range(u64 start, u64 size, unsigned old_type,
- unsigned new_type)
+u64 __init e820__range_update(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type)
{
- return __e820_update_range(e820, start, size, old_type, new_type);
+ return __e820__range_update(e820_table, start, size, old_type, new_type);
}
-static u64 __init e820_update_range_saved(u64 start, u64 size,
- unsigned old_type, unsigned new_type)
+static u64 __init e820__range_update_firmware(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type)
{
- return __e820_update_range(e820_saved, start, size, old_type,
- new_type);
+ return __e820__range_update(e820_table_firmware, start, size, old_type, new_type);
}
-/* make e820 not cover the range */
-u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type,
- int checktype)
+/* Remove a range of memory from the E820 table: */
+u64 __init e820__range_remove(u64 start, u64 size, enum e820_type old_type, bool check_type)
{
int i;
u64 end;
size = ULLONG_MAX - start;
end = start + size;
- printk(KERN_DEBUG "e820: remove [mem %#010Lx-%#010Lx] ",
- (unsigned long long) start, (unsigned long long) (end - 1));
- if (checktype)
+ printk(KERN_DEBUG "e820: remove [mem %#010Lx-%#010Lx] ", start, end - 1);
+ if (check_type)
e820_print_type(old_type);
- printk(KERN_CONT "\n");
+ pr_cont("\n");
- for (i = 0; i < e820->nr_map; i++) {
- struct e820entry *ei = &e820->map[i];
+ for (i = 0; i < e820_table->nr_entries; i++) {
+ struct e820_entry *entry = &e820_table->entries[i];
u64 final_start, final_end;
- u64 ei_end;
+ u64 entry_end;
- if (checktype && ei->type != old_type)
+ if (check_type && entry->type != old_type)
continue;
- ei_end = ei->addr + ei->size;
- /* totally covered? */
- if (ei->addr >= start && ei_end <= end) {
- real_removed_size += ei->size;
- memset(ei, 0, sizeof(struct e820entry));
+ entry_end = entry->addr + entry->size;
+
+ /* Completely covered? */
+ if (entry->addr >= start && entry_end <= end) {
+ real_removed_size += entry->size;
+ memset(entry, 0, sizeof(*entry));
continue;
}
- /* new range is totally covered? */
- if (ei->addr < start && ei_end > end) {
- e820_add_region(end, ei_end - end, ei->type);
- ei->size = start - ei->addr;
+ /* Is the new range completely covered? */
+ if (entry->addr < start && entry_end > end) {
+ e820__range_add(end, entry_end - end, entry->type);
+ entry->size = start - entry->addr;
real_removed_size += size;
continue;
}
- /* partially covered */
- final_start = max(start, ei->addr);
- final_end = min(end, ei_end);
+ /* Partially covered: */
+ final_start = max(start, entry->addr);
+ final_end = min(end, entry_end);
if (final_start >= final_end)
continue;
+
real_removed_size += final_end - final_start;
/*
- * left range could be head or tail, so need to update
- * size at first.
+ * Left range could be head or tail, so need to update
+ * the size first:
*/
- ei->size -= final_end - final_start;
- if (ei->addr < final_start)
+ entry->size -= final_end - final_start;
+ if (entry->addr < final_start)
continue;
- ei->addr = final_end;
+
+ entry->addr = final_end;
}
return real_removed_size;
}
-void __init update_e820(void)
+void __init e820__update_table_print(void)
{
- if (sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map))
+ if (e820__update_table(e820_table))
return;
- printk(KERN_INFO "e820: modified physical RAM map:\n");
- e820_print_map("modified");
+
+ pr_info("e820: modified physical RAM map:\n");
+ e820__print_table("modified");
}
-static void __init update_e820_saved(void)
+
+static void __init e820__update_table_firmware(void)
{
- sanitize_e820_map(e820_saved->map, ARRAY_SIZE(e820_saved->map),
- &e820_saved->nr_map);
+ e820__update_table(e820_table_firmware);
}
+
#define MAX_GAP_END 0x100000000ull
+
/*
- * Search for a gap in the e820 memory space from 0 to MAX_GAP_END.
+ * Search for a gap in the E820 memory space from 0 to MAX_GAP_END (4GB).
*/
-static int __init e820_search_gap(unsigned long *gapstart,
- unsigned long *gapsize)
+static int __init e820_search_gap(unsigned long *gapstart, unsigned long *gapsize)
{
unsigned long long last = MAX_GAP_END;
- int i = e820->nr_map;
+ int i = e820_table->nr_entries;
int found = 0;
while (--i >= 0) {
- unsigned long long start = e820->map[i].addr;
- unsigned long long end = start + e820->map[i].size;
+ unsigned long long start = e820_table->entries[i].addr;
+ unsigned long long end = start + e820_table->entries[i].size;
/*
* Since "last" is at most 4GB, we know we'll
- * fit in 32 bits if this condition is true
+ * fit in 32 bits if this condition is true:
*/
if (last > end) {
unsigned long gap = last - end;
}
/*
- * Search for the biggest gap in the low 32 bits of the e820
- * memory space. We pass this space to PCI to assign MMIO resources
- * for hotplug or unconfigured devices in.
+ * Search for the biggest gap in the low 32 bits of the E820
+ * memory space. We pass this space to the PCI subsystem, so
+ * that it can assign MMIO resources for hotplug or
+ * unconfigured devices in.
+ *
* Hopefully the BIOS let enough space left.
*/
-__init void e820_setup_gap(void)
+__init void e820__setup_pci_gap(void)
{
unsigned long gapstart, gapsize;
int found;
if (!found) {
#ifdef CONFIG_X86_64
gapstart = (max_pfn << PAGE_SHIFT) + 1024*1024;
- printk(KERN_ERR
- "e820: cannot find a gap in the 32bit address range\n"
- "e820: PCI devices with unassigned 32bit BARs may break!\n");
+ pr_err(
+ "e820: Cannot find an available gap in the 32-bit address range\n"
+ "e820: PCI devices with unassigned 32-bit BARs may not work!\n");
#else
gapstart = 0x10000000;
#endif
}
/*
- * e820_reserve_resources_late protect stolen RAM already
+ * e820__reserve_resources_late() protects stolen RAM already:
*/
pci_mem_start = gapstart;
- printk(KERN_INFO
- "e820: [mem %#010lx-%#010lx] available for PCI devices\n",
- gapstart, gapstart + gapsize - 1);
+ pr_info("e820: [mem %#010lx-%#010lx] available for PCI devices\n", gapstart, gapstart + gapsize - 1);
}
/*
* Called late during init, in free_initmem().
*
- * Initial e820 and e820_saved are largish __initdata arrays.
- * Copy them to (usually much smaller) dynamically allocated area.
- * This is done after all tweaks we ever do to them:
- * all functions which modify them are __init functions,
- * they won't exist after this point.
+ * Initial e820_table and e820_table_firmware are largish __initdata arrays.
+ *
+ * Copy them to a (usually much smaller) dynamically allocated area that is
+ * sized precisely after the number of e820 entries.
+ *
+ * This is done after we've performed all the fixes and tweaks to the tables.
+ * All functions which modify them are __init functions, which won't exist
+ * after free_initmem().
*/
-__init void e820_reallocate_tables(void)
+__init void e820__reallocate_tables(void)
{
- struct e820map *n;
+ struct e820_table *n;
int size;
- size = offsetof(struct e820map, map) + sizeof(struct e820entry) * e820->nr_map;
+ size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry)*e820_table->nr_entries;
n = kmalloc(size, GFP_KERNEL);
BUG_ON(!n);
- memcpy(n, e820, size);
- e820 = n;
+ memcpy(n, e820_table, size);
+ e820_table = n;
- size = offsetof(struct e820map, map) + sizeof(struct e820entry) * e820_saved->nr_map;
+ size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry)*e820_table_firmware->nr_entries;
n = kmalloc(size, GFP_KERNEL);
BUG_ON(!n);
- memcpy(n, e820_saved, size);
- e820_saved = n;
+ memcpy(n, e820_table_firmware, size);
+ e820_table_firmware = n;
}
-/**
- * Because of the size limitation of struct boot_params, only first
- * 128 E820 memory entries are passed to kernel via
- * boot_params.e820_map, others are passed via SETUP_E820_EXT node of
- * linked list of struct setup_data, which is parsed here.
+/*
+ * Because of the small fixed size of struct boot_params, only the first
+ * 128 E820 memory entries are passed to the kernel via boot_params.e820_table,
+ * the remaining (if any) entries are passed via the SETUP_E820_EXT node of
+ * struct setup_data, which is parsed here.
*/
-void __init parse_e820_ext(u64 phys_addr, u32 data_len)
+void __init e820__memory_setup_extended(u64 phys_addr, u32 data_len)
{
int entries;
- struct e820entry *extmap;
+ struct boot_e820_entry *extmap;
struct setup_data *sdata;
sdata = early_memremap(phys_addr, data_len);
- entries = sdata->len / sizeof(struct e820entry);
- extmap = (struct e820entry *)(sdata->data);
- __append_e820_map(extmap, entries);
- sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map);
+ entries = sdata->len / sizeof(*extmap);
+ extmap = (struct boot_e820_entry *)(sdata->data);
+
+ __append_e820_table(extmap, entries);
+ e820__update_table(e820_table);
+
early_memunmap(sdata, data_len);
- printk(KERN_INFO "e820: extended physical RAM map:\n");
- e820_print_map("extended");
+ pr_info("e820: extended physical RAM map:\n");
+ e820__print_table("extended");
}
-#if defined(CONFIG_X86_64) || \
- (defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION))
-/**
+/*
* Find the ranges of physical addresses that do not correspond to
- * e820 RAM areas and mark the corresponding pages as nosave for
- * hibernation (32 bit) or software suspend and suspend to RAM (64 bit).
+ * E820 RAM areas and register the corresponding pages as 'nosave' for
+ * hibernation (32-bit) or software suspend and suspend to RAM (64-bit).
*
- * This function requires the e820 map to be sorted and without any
+ * This function requires the E820 map to be sorted and without any
* overlapping entries.
*/
-void __init e820_mark_nosave_regions(unsigned long limit_pfn)
+void __init e820__register_nosave_regions(unsigned long limit_pfn)
{
int i;
unsigned long pfn = 0;
- for (i = 0; i < e820->nr_map; i++) {
- struct e820entry *ei = &e820->map[i];
+ for (i = 0; i < e820_table->nr_entries; i++) {
+ struct e820_entry *entry = &e820_table->entries[i];
- if (pfn < PFN_UP(ei->addr))
- register_nosave_region(pfn, PFN_UP(ei->addr));
+ if (pfn < PFN_UP(entry->addr))
+ register_nosave_region(pfn, PFN_UP(entry->addr));
- pfn = PFN_DOWN(ei->addr + ei->size);
+ pfn = PFN_DOWN(entry->addr + entry->size);
- if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN)
- register_nosave_region(PFN_UP(ei->addr), pfn);
+ if (entry->type != E820_TYPE_RAM && entry->type != E820_TYPE_RESERVED_KERN)
+ register_nosave_region(PFN_UP(entry->addr), pfn);
if (pfn >= limit_pfn)
break;
}
}
-#endif
#ifdef CONFIG_ACPI
-/**
- * Mark ACPI NVS memory region, so that we can save/restore it during
- * hibernation and the subsequent resume.
+/*
+ * Register ACPI NVS memory regions, so that we can save/restore them during
+ * hibernation and the subsequent resume:
*/
-static int __init e820_mark_nvs_memory(void)
+static int __init e820__register_nvs_regions(void)
{
int i;
- for (i = 0; i < e820->nr_map; i++) {
- struct e820entry *ei = &e820->map[i];
+ for (i = 0; i < e820_table->nr_entries; i++) {
+ struct e820_entry *entry = &e820_table->entries[i];
- if (ei->type == E820_NVS)
- acpi_nvs_register(ei->addr, ei->size);
+ if (entry->type == E820_TYPE_NVS)
+ acpi_nvs_register(entry->addr, entry->size);
}
return 0;
}
-core_initcall(e820_mark_nvs_memory);
+core_initcall(e820__register_nvs_regions);
#endif
/*
- * pre allocated 4k and reserved it in memblock and e820_saved
+ * Allocate the requested number of bytes with the requsted alignment
+ * and return (the physical address) to the caller. Also register this
+ * range in the 'firmware' E820 table as a reserved range.
+ *
+ * This allows kexec to fake a new mptable, as if it came from the real
+ * system.
*/
-u64 __init early_reserve_e820(u64 size, u64 align)
+u64 __init e820__memblock_alloc_reserved(u64 size, u64 align)
{
u64 addr;
addr = __memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
if (addr) {
- e820_update_range_saved(addr, size, E820_RAM, E820_RESERVED);
- printk(KERN_INFO "e820: update e820_saved for early_reserve_e820\n");
- update_e820_saved();
+ e820__range_update_firmware(addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED);
+ pr_info("e820: update e820_table_firmware for e820__memblock_alloc_reserved()\n");
+ e820__update_table_firmware();
}
return addr;
/*
* Find the highest page frame number we have available
*/
-static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type)
+static unsigned long __init e820_end_pfn(unsigned long limit_pfn, enum e820_type type)
{
int i;
unsigned long last_pfn = 0;
unsigned long max_arch_pfn = MAX_ARCH_PFN;
- for (i = 0; i < e820->nr_map; i++) {
- struct e820entry *ei = &e820->map[i];
+ for (i = 0; i < e820_table->nr_entries; i++) {
+ struct e820_entry *entry = &e820_table->entries[i];
unsigned long start_pfn;
unsigned long end_pfn;
- if (ei->type != type)
+ if (entry->type != type)
continue;
- start_pfn = ei->addr >> PAGE_SHIFT;
- end_pfn = (ei->addr + ei->size) >> PAGE_SHIFT;
+ start_pfn = entry->addr >> PAGE_SHIFT;
+ end_pfn = (entry->addr + entry->size) >> PAGE_SHIFT;
if (start_pfn >= limit_pfn)
continue;
if (last_pfn > max_arch_pfn)
last_pfn = max_arch_pfn;
- printk(KERN_INFO "e820: last_pfn = %#lx max_arch_pfn = %#lx\n",
+ pr_info("e820: last_pfn = %#lx max_arch_pfn = %#lx\n",
last_pfn, max_arch_pfn);
return last_pfn;
}
-unsigned long __init e820_end_of_ram_pfn(void)
+
+unsigned long __init e820__end_of_ram_pfn(void)
{
- return e820_end_pfn(MAX_ARCH_PFN, E820_RAM);
+ return e820_end_pfn(MAX_ARCH_PFN, E820_TYPE_RAM);
}
-unsigned long __init e820_end_of_low_ram_pfn(void)
+unsigned long __init e820__end_of_low_ram_pfn(void)
{
- return e820_end_pfn(1UL << (32 - PAGE_SHIFT), E820_RAM);
+ return e820_end_pfn(1UL << (32 - PAGE_SHIFT), E820_TYPE_RAM);
}
static void __init early_panic(char *msg)
static int userdef __initdata;
-/* "mem=nopentium" disables the 4MB page tables. */
+/* The "mem=nopentium" boot option disables 4MB page tables on 32-bit kernels: */
static int __init parse_memopt(char *p)
{
u64 mem_size;
setup_clear_cpu_cap(X86_FEATURE_PSE);
return 0;
#else
- printk(KERN_WARNING "mem=nopentium ignored! (only supported on x86_32)\n");
+ pr_warn("mem=nopentium ignored! (only supported on x86_32)\n");
return -EINVAL;
#endif
}
userdef = 1;
mem_size = memparse(p, &p);
- /* don't remove all of memory when handling "mem={invalid}" param */
+
+ /* Don't remove all memory when getting "mem={invalid}" parameter: */
if (mem_size == 0)
return -EINVAL;
- e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);
+
+ e820__range_remove(mem_size, ULLONG_MAX - mem_size, E820_TYPE_RAM, 1);
return 0;
}
#ifdef CONFIG_CRASH_DUMP
/*
* If we are doing a crash dump, we still need to know
- * the real mem size before original memory map is
+ * the real memory size before the original memory map is
* reset.
*/
- saved_max_pfn = e820_end_of_ram_pfn();
+ saved_max_pfn = e820__end_of_ram_pfn();
#endif
- e820->nr_map = 0;
+ e820_table->nr_entries = 0;
userdef = 1;
return 0;
}
userdef = 1;
if (*p == '@') {
start_at = memparse(p+1, &p);
- e820_add_region(start_at, mem_size, E820_RAM);
+ e820__range_add(start_at, mem_size, E820_TYPE_RAM);
} else if (*p == '#') {
start_at = memparse(p+1, &p);
- e820_add_region(start_at, mem_size, E820_ACPI);
+ e820__range_add(start_at, mem_size, E820_TYPE_ACPI);
} else if (*p == '$') {
start_at = memparse(p+1, &p);
- e820_add_region(start_at, mem_size, E820_RESERVED);
+ e820__range_add(start_at, mem_size, E820_TYPE_RESERVED);
} else if (*p == '!') {
start_at = memparse(p+1, &p);
- e820_add_region(start_at, mem_size, E820_PRAM);
- } else
- e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);
+ e820__range_add(start_at, mem_size, E820_TYPE_PRAM);
+ } else {
+ e820__range_remove(mem_size, ULLONG_MAX - mem_size, E820_TYPE_RAM, 1);
+ }
return *p == '\0' ? 0 : -EINVAL;
}
+
static int __init parse_memmap_opt(char *str)
{
while (str) {
}
early_param("memmap", parse_memmap_opt);
-void __init finish_e820_parsing(void)
+/*
+ * Reserve all entries from the bootloader's extensible data nodes list,
+ * because if present we are going to use it later on to fetch e820
+ * entries from it:
+ */
+void __init e820__reserve_setup_data(void)
+{
+ struct setup_data *data;
+ u64 pa_data;
+
+ pa_data = boot_params.hdr.setup_data;
+ if (!pa_data)
+ return;
+
+ while (pa_data) {
+ data = early_memremap(pa_data, sizeof(*data));
+ e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
+ pa_data = data->next;
+ early_memunmap(data, sizeof(*data));
+ }
+
+ e820__update_table(e820_table);
+
+ memcpy(e820_table_firmware, e820_table, sizeof(*e820_table_firmware));
+
+ pr_info("extended physical RAM map:\n");
+ e820__print_table("reserve setup_data");
+}
+
+/*
+ * Called after parse_early_param(), after early parameters (such as mem=)
+ * have been processed, in which case we already have an E820 table filled in
+ * via the parameter callback function(s), but it's not sorted and printed yet:
+ */
+void __init e820__finish_early_params(void)
{
if (userdef) {
- if (sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map),
- &e820->nr_map) < 0)
+ if (e820__update_table(e820_table) < 0)
early_panic("Invalid user supplied memory map");
- printk(KERN_INFO "e820: user-defined physical RAM map:\n");
- e820_print_map("user");
+ pr_info("e820: user-defined physical RAM map:\n");
+ e820__print_table("user");
}
}
-static const char *__init e820_type_to_string(int e820_type)
+static const char *__init e820_type_to_string(struct e820_entry *entry)
{
- switch (e820_type) {
- case E820_RESERVED_KERN:
- case E820_RAM: return "System RAM";
- case E820_ACPI: return "ACPI Tables";
- case E820_NVS: return "ACPI Non-volatile Storage";
- case E820_UNUSABLE: return "Unusable memory";
- case E820_PRAM: return "Persistent Memory (legacy)";
- case E820_PMEM: return "Persistent Memory";
- default: return "reserved";
+ switch (entry->type) {
+ case E820_TYPE_RESERVED_KERN: /* Fall-through: */
+ case E820_TYPE_RAM: return "System RAM";
+ case E820_TYPE_ACPI: return "ACPI Tables";
+ case E820_TYPE_NVS: return "ACPI Non-volatile Storage";
+ case E820_TYPE_UNUSABLE: return "Unusable memory";
+ case E820_TYPE_PRAM: return "Persistent Memory (legacy)";
+ case E820_TYPE_PMEM: return "Persistent Memory";
+ case E820_TYPE_RESERVED: return "Reserved";
+ default: return "Unknown E820 type";
}
}
-static unsigned long __init e820_type_to_iomem_type(int e820_type)
+static unsigned long __init e820_type_to_iomem_type(struct e820_entry *entry)
{
- switch (e820_type) {
- case E820_RESERVED_KERN:
- case E820_RAM:
- return IORESOURCE_SYSTEM_RAM;
- case E820_ACPI:
- case E820_NVS:
- case E820_UNUSABLE:
- case E820_PRAM:
- case E820_PMEM:
- default:
- return IORESOURCE_MEM;
+ switch (entry->type) {
+ case E820_TYPE_RESERVED_KERN: /* Fall-through: */
+ case E820_TYPE_RAM: return IORESOURCE_SYSTEM_RAM;
+ case E820_TYPE_ACPI: /* Fall-through: */
+ case E820_TYPE_NVS: /* Fall-through: */
+ case E820_TYPE_UNUSABLE: /* Fall-through: */
+ case E820_TYPE_PRAM: /* Fall-through: */
+ case E820_TYPE_PMEM: /* Fall-through: */
+ case E820_TYPE_RESERVED: /* Fall-through: */
+ default: return IORESOURCE_MEM;
}
}
-static unsigned long __init e820_type_to_iores_desc(int e820_type)
+static unsigned long __init e820_type_to_iores_desc(struct e820_entry *entry)
{
- switch (e820_type) {
- case E820_ACPI:
- return IORES_DESC_ACPI_TABLES;
- case E820_NVS:
- return IORES_DESC_ACPI_NV_STORAGE;
- case E820_PMEM:
- return IORES_DESC_PERSISTENT_MEMORY;
- case E820_PRAM:
- return IORES_DESC_PERSISTENT_MEMORY_LEGACY;
- case E820_RESERVED_KERN:
- case E820_RAM:
- case E820_UNUSABLE:
- default:
- return IORES_DESC_NONE;
+ switch (entry->type) {
+ case E820_TYPE_ACPI: return IORES_DESC_ACPI_TABLES;
+ case E820_TYPE_NVS: return IORES_DESC_ACPI_NV_STORAGE;
+ case E820_TYPE_PMEM: return IORES_DESC_PERSISTENT_MEMORY;
+ case E820_TYPE_PRAM: return IORES_DESC_PERSISTENT_MEMORY_LEGACY;
+ case E820_TYPE_RESERVED_KERN: /* Fall-through: */
+ case E820_TYPE_RAM: /* Fall-through: */
+ case E820_TYPE_UNUSABLE: /* Fall-through: */
+ case E820_TYPE_RESERVED: /* Fall-through: */
+ default: return IORES_DESC_NONE;
}
}
-static bool __init do_mark_busy(u32 type, struct resource *res)
+static bool __init do_mark_busy(enum e820_type type, struct resource *res)
{
/* this is the legacy bios/dos rom-shadow + mmio region */
if (res->start < (1ULL<<20))
* for exclusive use of a driver
*/
switch (type) {
- case E820_RESERVED:
- case E820_PRAM:
- case E820_PMEM:
+ case E820_TYPE_RESERVED:
+ case E820_TYPE_PRAM:
+ case E820_TYPE_PMEM:
return false;
+ case E820_TYPE_RESERVED_KERN:
+ case E820_TYPE_RAM:
+ case E820_TYPE_ACPI:
+ case E820_TYPE_NVS:
+ case E820_TYPE_UNUSABLE:
default:
return true;
}
}
/*
- * Mark e820 reserved areas as busy for the resource manager.
+ * Mark E820 reserved areas as busy for the resource manager:
*/
+
static struct resource __initdata *e820_res;
-void __init e820_reserve_resources(void)
+
+void __init e820__reserve_resources(void)
{
int i;
struct resource *res;
u64 end;
- res = alloc_bootmem(sizeof(struct resource) * e820->nr_map);
+ res = alloc_bootmem(sizeof(*res) * e820_table->nr_entries);
e820_res = res;
- for (i = 0; i < e820->nr_map; i++) {
- end = e820->map[i].addr + e820->map[i].size - 1;
+
+ for (i = 0; i < e820_table->nr_entries; i++) {
+ struct e820_entry *entry = e820_table->entries + i;
+
+ end = entry->addr + entry->size - 1;
if (end != (resource_size_t)end) {
res++;
continue;
}
- res->name = e820_type_to_string(e820->map[i].type);
- res->start = e820->map[i].addr;
- res->end = end;
-
- res->flags = e820_type_to_iomem_type(e820->map[i].type);
- res->desc = e820_type_to_iores_desc(e820->map[i].type);
+ res->start = entry->addr;
+ res->end = end;
+ res->name = e820_type_to_string(entry);
+ res->flags = e820_type_to_iomem_type(entry);
+ res->desc = e820_type_to_iores_desc(entry);
/*
- * don't register the region that could be conflicted with
- * pci device BAR resource and insert them later in
- * pcibios_resource_survey()
+ * Don't register the region that could be conflicted with
+ * PCI device BAR resources and insert them later in
+ * pcibios_resource_survey():
*/
- if (do_mark_busy(e820->map[i].type, res)) {
+ if (do_mark_busy(entry->type, res)) {
res->flags |= IORESOURCE_BUSY;
insert_resource(&iomem_resource, res);
}
res++;
}
- for (i = 0; i < e820_saved->nr_map; i++) {
- struct e820entry *entry = &e820_saved->map[i];
- firmware_map_add_early(entry->addr,
- entry->addr + entry->size,
- e820_type_to_string(entry->type));
+ for (i = 0; i < e820_table_firmware->nr_entries; i++) {
+ struct e820_entry *entry = e820_table_firmware->entries + i;
+
+ firmware_map_add_early(entry->addr, entry->addr + entry->size, e820_type_to_string(entry));
}
}
-/* How much should we pad RAM ending depending on where it is? */
+/*
+ * How much should we pad the end of RAM, depending on where it is?
+ */
static unsigned long __init ram_alignment(resource_size_t pos)
{
unsigned long mb = pos >> 20;
#define MAX_RESOURCE_SIZE ((resource_size_t)-1)
-void __init e820_reserve_resources_late(void)
+void __init e820__reserve_resources_late(void)
{
int i;
struct resource *res;
res = e820_res;
- for (i = 0; i < e820->nr_map; i++) {
+ for (i = 0; i < e820_table->nr_entries; i++) {
if (!res->parent && res->end)
insert_resource_expand_to_fit(&iomem_resource, res);
res++;
}
/*
- * Try to bump up RAM regions to reasonable boundaries to
+ * Try to bump up RAM regions to reasonable boundaries, to
* avoid stolen RAM:
*/
- for (i = 0; i < e820->nr_map; i++) {
- struct e820entry *entry = &e820->map[i];
+ for (i = 0; i < e820_table->nr_entries; i++) {
+ struct e820_entry *entry = &e820_table->entries[i];
u64 start, end;
- if (entry->type != E820_RAM)
+ if (entry->type != E820_TYPE_RAM)
continue;
+
start = entry->addr + entry->size;
end = round_up(start, ram_alignment(start)) - 1;
if (end > MAX_RESOURCE_SIZE)
end = MAX_RESOURCE_SIZE;
if (start >= end)
continue;
- printk(KERN_DEBUG
- "e820: reserve RAM buffer [mem %#010llx-%#010llx]\n",
- start, end);
- reserve_region_with_split(&iomem_resource, start, end,
- "RAM buffer");
+
+ printk(KERN_DEBUG "e820: reserve RAM buffer [mem %#010llx-%#010llx]\n", start, end);
+ reserve_region_with_split(&iomem_resource, start, end, "RAM buffer");
}
}
-char *__init default_machine_specific_memory_setup(void)
+/*
+ * Pass the firmware (bootloader) E820 map to the kernel and process it:
+ */
+char *__init e820__memory_setup_default(void)
{
char *who = "BIOS-e820";
- u32 new_nr;
+
/*
* Try to copy the BIOS-supplied E820-map.
*
* Otherwise fake a memory map; one section from 0k->640k,
* the next section from 1mb->appropriate_mem_k
*/
- new_nr = boot_params.e820_entries;
- sanitize_e820_map(boot_params.e820_map,
- ARRAY_SIZE(boot_params.e820_map),
- &new_nr);
- boot_params.e820_entries = new_nr;
- if (append_e820_map(boot_params.e820_map, boot_params.e820_entries)
- < 0) {
+ if (append_e820_table(boot_params.e820_table, boot_params.e820_entries) < 0) {
u64 mem_size;
- /* compare results from other methods and take the greater */
- if (boot_params.alt_mem_k
- < boot_params.screen_info.ext_mem_k) {
+ /* Compare results from other methods and take the one that gives more RAM: */
+ if (boot_params.alt_mem_k < boot_params.screen_info.ext_mem_k) {
mem_size = boot_params.screen_info.ext_mem_k;
who = "BIOS-88";
} else {
who = "BIOS-e801";
}
- e820->nr_map = 0;
- e820_add_region(0, LOWMEMSIZE(), E820_RAM);
- e820_add_region(HIGH_MEMORY, mem_size << 10, E820_RAM);
+ e820_table->nr_entries = 0;
+ e820__range_add(0, LOWMEMSIZE(), E820_TYPE_RAM);
+ e820__range_add(HIGH_MEMORY, mem_size << 10, E820_TYPE_RAM);
}
- /* In case someone cares... */
+ /* We just appended a lot of ranges, sanitize the table: */
+ e820__update_table(e820_table);
+
return who;
}
-void __init setup_memory_map(void)
+/*
+ * Calls e820__memory_setup_default() in essence to pick up the firmware/bootloader
+ * E820 map - with an optional platform quirk available for virtual platforms
+ * to override this method of boot environment processing:
+ */
+void __init e820__memory_setup(void)
{
char *who;
+ /* This is a firmware interface ABI - make sure we don't break it: */
+ BUILD_BUG_ON(sizeof(struct boot_e820_entry) != 20);
+
who = x86_init.resources.memory_setup();
- memcpy(e820_saved, e820, sizeof(struct e820map));
- printk(KERN_INFO "e820: BIOS-provided physical RAM map:\n");
- e820_print_map(who);
+
+ memcpy(e820_table_firmware, e820_table, sizeof(*e820_table_firmware));
+
+ pr_info("e820: BIOS-provided physical RAM map:\n");
+ e820__print_table(who);
}
-void __init memblock_x86_fill(void)
+void __init e820__memblock_setup(void)
{
int i;
u64 end;
/*
- * EFI may have more than 128 entries
- * We are safe to enable resizing, beause memblock_x86_fill()
- * is rather later for x86
+ * The bootstrap memblock region count maximum is 128 entries
+ * (INIT_MEMBLOCK_REGIONS), but EFI might pass us more E820 entries
+ * than that - so allow memblock resizing.
+ *
+ * This is safe, because this call happens pretty late during x86 setup,
+ * so we know about reserved memory regions already. (This is important
+ * so that memblock resizing does no stomp over reserved areas.)
*/
memblock_allow_resize();
- for (i = 0; i < e820->nr_map; i++) {
- struct e820entry *ei = &e820->map[i];
+ for (i = 0; i < e820_table->nr_entries; i++) {
+ struct e820_entry *entry = &e820_table->entries[i];
- end = ei->addr + ei->size;
+ end = entry->addr + entry->size;
if (end != (resource_size_t)end)
continue;
- if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN)
+ if (entry->type != E820_TYPE_RAM && entry->type != E820_TYPE_RESERVED_KERN)
continue;
- memblock_add(ei->addr, ei->size);
+ memblock_add(entry->addr, entry->size);
}
- /* throw away partial pages */
+ /* Throw away partial pages: */
memblock_trim_memory(PAGE_SIZE);
memblock_dump_all();
}
-
-void __init memblock_find_dma_reserve(void)
-{
-#ifdef CONFIG_X86_64
- u64 nr_pages = 0, nr_free_pages = 0;
- unsigned long start_pfn, end_pfn;
- phys_addr_t start, end;
- int i;
- u64 u;
-
- /*
- * need to find out used area below MAX_DMA_PFN
- * need to use memblock to get free size in [0, MAX_DMA_PFN]
- * at first, and assume boot_mem will not take below MAX_DMA_PFN
- */
- for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
- start_pfn = min(start_pfn, MAX_DMA_PFN);
- end_pfn = min(end_pfn, MAX_DMA_PFN);
- nr_pages += end_pfn - start_pfn;
- }
-
- for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end,
- NULL) {
- start_pfn = min_t(unsigned long, PFN_UP(start), MAX_DMA_PFN);
- end_pfn = min_t(unsigned long, PFN_DOWN(end), MAX_DMA_PFN);
- if (start_pfn < end_pfn)
- nr_free_pages += end_pfn - start_pfn;
- }
-
- set_dma_reserve(nr_pages - nr_free_pages);
-#endif
-}
&base, &end);
/* Mark this space as reserved */
- e820_add_region(base, size, E820_RESERVED);
- sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map);
+ e820__range_add(base, size, E820_TYPE_RESERVED);
+ e820__update_table(e820_table);
}
static void __init intel_graphics_quirks(int num, int slot, int func)
#include <asm/ftrace.h>
#include <asm/nops.h>
-#if defined(CONFIG_FUNCTION_GRAPH_TRACER) && \
- !defined(CC_USING_FENTRY) && \
- !defined(CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE)
-# error The following combination is not supported: ((compiler missing -mfentry) || (CONFIG_X86_32 and !CONFIG_DYNAMIC_FTRACE)) && CONFIG_FUNCTION_GRAPH_TRACER && CONFIG_CC_OPTIMIZE_FOR_SIZE
-#endif
-
#ifdef CONFIG_DYNAMIC_FTRACE
int ftrace_arch_code_modify_prepare(void)
unsigned long return_hooker = (unsigned long)
&return_to_handler;
+ /*
+ * When resuming from suspend-to-ram, this function can be indirectly
+ * called from early CPU startup code while the CPU is in real mode,
+ * which would fail miserably. Make sure the stack pointer is a
+ * virtual address.
+ *
+ * This check isn't as accurate as virt_addr_valid(), but it should be
+ * good enough for this purpose, and it's fast.
+ */
+ if (unlikely((long)__builtin_frame_address(0) >= 0))
+ return;
+
if (unlikely(ftrace_graph_is_dead()))
return;
#include <asm/setup.h>
#include <asm/sections.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/page.h>
#include <asm/apic.h>
#include <asm/io_apic.h>
#include <asm/tlbflush.h>
#include <asm/sections.h>
#include <asm/kdebug.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/bios_ebda.h>
#include <asm/bootparam_utils.h>
#include <asm/microcode.h>
/* rsi is pointer to real mode structure with interesting info.
pass it to C */
movq %rsi, %rdi
- jmp start_cpu
-ENDPROC(secondary_startup_64)
-ENTRY(start_cpu)
+.Ljump_to_C_code:
/*
* Jump to run C code and to be on a real kernel address.
* Since we are running on identity-mapped space we have to jump
pushq %rax # target address in negative space
lretq
.Lafter_lret:
-ENDPROC(start_cpu)
+ENDPROC(secondary_startup_64)
#include "verify_cpu.S"
/*
* Boot CPU0 entry point. It's called from play_dead(). Everything has been set
* up already except stack. We just set up stack here. Then call
- * start_secondary() via start_cpu().
+ * start_secondary() via .Ljump_to_C_code.
*/
ENTRY(start_cpu0)
movq initial_stack(%rip), %rsp
- jmp start_cpu
+ jmp .Ljump_to_C_code
ENDPROC(start_cpu0)
#endif
#include <asm/setup.h>
#include <asm/crash.h>
#include <asm/efi.h>
+#include <asm/e820/api.h>
#include <asm/kexec-bzimage64.h>
#define MAX_ELFCOREHDR_STR_LEN 30 /* elfcorehdr=0x<64bit-value> */
{
unsigned int nr_e820_entries;
- nr_e820_entries = e820_saved->nr_map;
+ nr_e820_entries = e820_table_firmware->nr_entries;
- /* TODO: Pass entries more than E820MAX in bootparams setup data */
- if (nr_e820_entries > E820MAX)
- nr_e820_entries = E820MAX;
+ /* TODO: Pass entries more than E820_MAX_ENTRIES_ZEROPAGE in bootparams setup data */
+ if (nr_e820_entries > E820_MAX_ENTRIES_ZEROPAGE)
+ nr_e820_entries = E820_MAX_ENTRIES_ZEROPAGE;
params->e820_entries = nr_e820_entries;
- memcpy(¶ms->e820_map, &e820_saved->map,
- nr_e820_entries * sizeof(struct e820entry));
+ memcpy(¶ms->e820_table, &e820_table_firmware->entries, nr_e820_entries*sizeof(struct e820_entry));
return 0;
}
nr_e820_entries = params->e820_entries;
for (i = 0; i < nr_e820_entries; i++) {
- if (params->e820_map[i].type != E820_RAM)
+ if (params->e820_table[i].type != E820_TYPE_RAM)
continue;
- start = params->e820_map[i].addr;
- end = params->e820_map[i].addr + params->e820_map[i].size - 1;
+ start = params->e820_table[i].addr;
+ end = params->e820_table[i].addr + params->e820_table[i].size - 1;
if ((start <= 0x100000) && end > 0x100000) {
mem_k = (end >> 10) - (0x100000 >> 10);
#endif
/* Ensure if the instruction can be boostable */
-extern int can_boost(kprobe_opcode_t *instruction, void *addr);
+extern int can_boost(struct insn *insn, void *orig_addr);
/* Recover instruction if given address is probed */
extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf,
unsigned long addr);
* Copy an instruction and adjust the displacement if the instruction
* uses the %rip-relative addressing mode.
*/
-extern int __copy_instruction(u8 *dest, u8 *src);
+extern int __copy_instruction(u8 *dest, u8 *src, struct insn *insn);
/* Generate a relative-jump/call instruction */
extern void synthesize_reljump(void *from, void *to);
NOKPROBE_SYMBOL(skip_prefixes);
/*
- * Returns non-zero if opcode is boostable.
+ * Returns non-zero if INSN is boostable.
* RIP relative instructions are adjusted at copying time in 64 bits mode
*/
-int can_boost(kprobe_opcode_t *opcodes, void *addr)
+int can_boost(struct insn *insn, void *addr)
{
kprobe_opcode_t opcode;
- kprobe_opcode_t *orig_opcodes = opcodes;
if (search_exception_tables((unsigned long)addr))
return 0; /* Page fault may occur on this address. */
-retry:
- if (opcodes - orig_opcodes > MAX_INSN_SIZE - 1)
- return 0;
- opcode = *(opcodes++);
-
/* 2nd-byte opcode */
- if (opcode == 0x0f) {
- if (opcodes - orig_opcodes > MAX_INSN_SIZE - 1)
- return 0;
- return test_bit(*opcodes,
+ if (insn->opcode.nbytes == 2)
+ return test_bit(insn->opcode.bytes[1],
(unsigned long *)twobyte_is_boostable);
- }
+
+ if (insn->opcode.nbytes != 1)
+ return 0;
+
+ /* Can't boost Address-size override prefix */
+ if (unlikely(inat_is_address_size_prefix(insn->attr)))
+ return 0;
+
+ opcode = insn->opcode.bytes[0];
switch (opcode & 0xf0) {
-#ifdef CONFIG_X86_64
- case 0x40:
- goto retry; /* REX prefix is boostable */
-#endif
case 0x60:
- if (0x63 < opcode && opcode < 0x67)
- goto retry; /* prefixes */
- /* can't boost Address-size override and bound */
- return (opcode != 0x62 && opcode != 0x67);
+ /* can't boost "bound" */
+ return (opcode != 0x62);
case 0x70:
return 0; /* can't boost conditional jump */
+ case 0x90:
+ return opcode != 0x9a; /* can't boost call far */
case 0xc0:
/* can't boost software-interruptions */
return (0xc1 < opcode && opcode < 0xcc) || opcode == 0xcf;
/* can boost in/out and absolute jmps */
return ((opcode & 0x04) || opcode == 0xea);
case 0xf0:
- if ((opcode & 0x0c) == 0 && opcode != 0xf1)
- goto retry; /* lock/rep(ne) prefix */
/* clear and set flags are boostable */
return (opcode == 0xf5 || (0xf7 < opcode && opcode < 0xfe));
default:
- /* segment override prefixes are boostable */
- if (opcode == 0x26 || opcode == 0x36 || opcode == 0x3e)
- goto retry; /* prefixes */
/* CS override prefix and call are not boostable */
return (opcode != 0x2e && opcode != 0x9a);
}
* Fortunately, we know that the original code is the ideal 5-byte
* long NOP.
*/
- memcpy(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
+ if (probe_kernel_read(buf, (void *)addr,
+ MAX_INSN_SIZE * sizeof(kprobe_opcode_t)))
+ return 0UL;
+
if (faddr)
memcpy(buf, ideal_nops[NOP_ATOMIC5], 5);
else
* Recover the probed instruction at addr for further analysis.
* Caller must lock kprobes by kprobe_mutex, or disable preemption
* for preventing to release referencing kprobes.
- * Returns zero if the instruction can not get recovered.
+ * Returns zero if the instruction can not get recovered (or access failed).
*/
unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr)
{
}
/*
- * Copy an instruction and adjust the displacement if the instruction
- * uses the %rip-relative addressing mode.
- * If it does, Return the address of the 32-bit displacement word.
- * If not, return null.
- * Only applicable to 64-bit x86.
+ * Copy an instruction with recovering modified instruction by kprobes
+ * and adjust the displacement if the instruction uses the %rip-relative
+ * addressing mode.
+ * This returns the length of copied instruction, or 0 if it has an error.
*/
-int __copy_instruction(u8 *dest, u8 *src)
+int __copy_instruction(u8 *dest, u8 *src, struct insn *insn)
{
- struct insn insn;
kprobe_opcode_t buf[MAX_INSN_SIZE];
- int length;
unsigned long recovered_insn =
recover_probed_instruction(buf, (unsigned long)src);
- if (!recovered_insn)
+ if (!recovered_insn || !insn)
+ return 0;
+
+ /* This can access kernel text if given address is not recovered */
+ if (probe_kernel_read(dest, (void *)recovered_insn, MAX_INSN_SIZE))
return 0;
- kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE);
- insn_get_length(&insn);
- length = insn.length;
+
+ kernel_insn_init(insn, dest, MAX_INSN_SIZE);
+ insn_get_length(insn);
/* Another subsystem puts a breakpoint, failed to recover */
- if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
+ if (insn->opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
return 0;
- memcpy(dest, insn.kaddr, length);
#ifdef CONFIG_X86_64
- if (insn_rip_relative(&insn)) {
+ /* Only x86_64 has RIP relative instructions */
+ if (insn_rip_relative(insn)) {
s64 newdisp;
u8 *disp;
- kernel_insn_init(&insn, dest, length);
- insn_get_displacement(&insn);
/*
* The copied instruction uses the %rip-relative addressing
* mode. Adjust the displacement for the difference between
* extension of the original signed 32-bit displacement would
* have given.
*/
- newdisp = (u8 *) src + (s64) insn.displacement.value - (u8 *) dest;
+ newdisp = (u8 *) src + (s64) insn->displacement.value
+ - (u8 *) dest;
if ((s64) (s32) newdisp != newdisp) {
pr_err("Kprobes error: new displacement does not fit into s32 (%llx)\n", newdisp);
- pr_err("\tSrc: %p, Dest: %p, old disp: %x\n", src, dest, insn.displacement.value);
+ pr_err("\tSrc: %p, Dest: %p, old disp: %x\n",
+ src, dest, insn->displacement.value);
return 0;
}
- disp = (u8 *) dest + insn_offset_displacement(&insn);
+ disp = (u8 *) dest + insn_offset_displacement(insn);
*(s32 *) disp = (s32) newdisp;
}
#endif
- return length;
+ return insn->length;
+}
+
+/* Prepare reljump right after instruction to boost */
+static void prepare_boost(struct kprobe *p, struct insn *insn)
+{
+ if (can_boost(insn, p->addr) &&
+ MAX_INSN_SIZE - insn->length >= RELATIVEJUMP_SIZE) {
+ /*
+ * These instructions can be executed directly if it
+ * jumps back to correct address.
+ */
+ synthesize_reljump(p->ainsn.insn + insn->length,
+ p->addr + insn->length);
+ p->ainsn.boostable = true;
+ } else {
+ p->ainsn.boostable = false;
+ }
}
static int arch_copy_kprobe(struct kprobe *p)
{
- int ret;
+ struct insn insn;
+ int len;
+
+ set_memory_rw((unsigned long)p->ainsn.insn & PAGE_MASK, 1);
/* Copy an instruction with recovering if other optprobe modifies it.*/
- ret = __copy_instruction(p->ainsn.insn, p->addr);
- if (!ret)
+ len = __copy_instruction(p->ainsn.insn, p->addr, &insn);
+ if (!len)
return -EINVAL;
/*
* __copy_instruction can modify the displacement of the instruction,
* but it doesn't affect boostable check.
*/
- if (can_boost(p->ainsn.insn, p->addr))
- p->ainsn.boostable = 0;
- else
- p->ainsn.boostable = -1;
+ prepare_boost(p, &insn);
+
+ set_memory_ro((unsigned long)p->ainsn.insn & PAGE_MASK, 1);
/* Check whether the instruction modifies Interrupt Flag or not */
p->ainsn.if_modifier = is_IF_modifier(p->ainsn.insn);
void arch_remove_kprobe(struct kprobe *p)
{
if (p->ainsn.insn) {
- free_insn_slot(p->ainsn.insn, (p->ainsn.boostable == 1));
+ free_insn_slot(p->ainsn.insn, p->ainsn.boostable);
p->ainsn.insn = NULL;
}
}
return;
#if !defined(CONFIG_PREEMPT)
- if (p->ainsn.boostable == 1 && !p->post_handler) {
+ if (p->ainsn.boostable && !p->post_handler) {
/* Boost up -- we can execute copied instructions directly */
if (!reenter)
reset_current_kprobe();
case 0xcf:
case 0xea: /* jmp absolute -- ip is correct */
/* ip is already adjusted, no more changes required */
- p->ainsn.boostable = 1;
+ p->ainsn.boostable = true;
goto no_change;
case 0xe8: /* call relative - Fix return addr */
*tos = orig_ip + (*tos - copy_ip);
* jmp near and far, absolute indirect
* ip is correct. And this is boostable
*/
- p->ainsn.boostable = 1;
+ p->ainsn.boostable = true;
goto no_change;
}
default:
break;
}
- if (p->ainsn.boostable == 0) {
- if ((regs->ip > copy_ip) &&
- (regs->ip - copy_ip) + 5 < MAX_INSN_SIZE) {
- /*
- * These instructions can be executed directly if it
- * jumps back to correct address.
- */
- synthesize_reljump((void *)regs->ip,
- (void *)orig_ip + (regs->ip - copy_ip));
- p->ainsn.boostable = 1;
- } else {
- p->ainsn.boostable = -1;
- }
- }
-
regs->ip += orig_ip - copy_ip;
no_change:
int arch_prepare_kprobe_ftrace(struct kprobe *p)
{
p->ainsn.insn = NULL;
- p->ainsn.boostable = -1;
+ p->ainsn.boostable = false;
return 0;
}
* overwritten by jump destination address. In this case, original
* bytes must be recovered from op->optinsn.copied_insn buffer.
*/
- memcpy(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
+ if (probe_kernel_read(buf, (void *)addr,
+ MAX_INSN_SIZE * sizeof(kprobe_opcode_t)))
+ return 0UL;
+
if (addr == (unsigned long)kp->addr) {
buf[0] = kp->opcode;
memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
static int copy_optimized_instructions(u8 *dest, u8 *src)
{
+ struct insn insn;
int len = 0, ret;
while (len < RELATIVEJUMP_SIZE) {
- ret = __copy_instruction(dest + len, src + len);
- if (!ret || !can_boost(dest + len, src + len))
+ ret = __copy_instruction(dest + len, src + len, &insn);
+ if (!ret || !can_boost(&insn, src + len))
return -EINVAL;
len += ret;
}
}
buf = (u8 *)op->optinsn.insn;
+ set_memory_rw((unsigned long)buf & PAGE_MASK, 1);
/* Copy instructions into the out-of-line buffer */
ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr);
synthesize_reljump(buf + TMPL_END_IDX + op->optinsn.size,
(u8 *)op->kp.addr + op->optinsn.size);
+ set_memory_ro((unsigned long)buf & PAGE_MASK, 1);
+
flush_icache_range((unsigned long) buf,
(unsigned long) buf + TMPL_END_IDX +
op->optinsn.size + RELATIVEJUMP_SIZE);
#include <asm/io_apic.h>
#include <asm/proto.h>
#include <asm/bios_ebda.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/setup.h>
#include <asm/smp.h>
}
early_param("alloc_mptable", parse_alloc_mptable_opt);
-void __init early_reserve_e820_mpc_new(void)
+void __init e820__memblock_alloc_reserved_mpc_new(void)
{
if (enable_update_mptable && alloc_mptable)
- mpc_new_phys = early_reserve_e820(mpc_new_length, 4);
+ mpc_new_phys = e820__memblock_alloc_reserved(mpc_new_length, 4);
}
static int __init update_mp_table(void)
pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n",
reason, smp_processor_id());
- /*
- * On some machines, PCI SERR line is used to report memory
- * errors. EDAC makes use of it.
- */
-#if defined(CONFIG_EDAC)
- if (edac_handler_set()) {
- edac_atomic_assert_error();
- return;
- }
-#endif
-
if (panic_on_unrecovered_nmi)
nmi_panic(regs, "NMI: Not continuing");
#include <asm/probe_roms.h>
#include <asm/pci-direct.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/mmzone.h>
#include <asm/setup.h>
#include <asm/sections.h>
#include <asm/vm86.h>
#include <asm/switch_to.h>
#include <asm/desc.h>
+#include <asm/prctl.h>
/*
* per-CPU TSS segments. Threads are completely 'soft' on Linux,
fpu__clear(&tsk->thread.fpu);
}
-static void hard_disable_TSC(void)
-{
- cr4_set_bits(X86_CR4_TSD);
-}
-
void disable_TSC(void)
{
preempt_disable();
* Must flip the CPU state synchronously with
* TIF_NOTSC in the current running context.
*/
- hard_disable_TSC();
+ cr4_set_bits(X86_CR4_TSD);
preempt_enable();
}
-static void hard_enable_TSC(void)
-{
- cr4_clear_bits(X86_CR4_TSD);
-}
-
static void enable_TSC(void)
{
preempt_disable();
* Must flip the CPU state synchronously with
* TIF_NOTSC in the current running context.
*/
- hard_enable_TSC();
+ cr4_clear_bits(X86_CR4_TSD);
preempt_enable();
}
return 0;
}
-void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
- struct tss_struct *tss)
-{
- struct thread_struct *prev, *next;
-
- prev = &prev_p->thread;
- next = &next_p->thread;
+DEFINE_PER_CPU(u64, msr_misc_features_shadow);
- if (test_tsk_thread_flag(prev_p, TIF_BLOCKSTEP) ^
- test_tsk_thread_flag(next_p, TIF_BLOCKSTEP)) {
- unsigned long debugctl = get_debugctlmsr();
+static void set_cpuid_faulting(bool on)
+{
+ u64 msrval;
- debugctl &= ~DEBUGCTLMSR_BTF;
- if (test_tsk_thread_flag(next_p, TIF_BLOCKSTEP))
- debugctl |= DEBUGCTLMSR_BTF;
+ msrval = this_cpu_read(msr_misc_features_shadow);
+ msrval &= ~MSR_MISC_FEATURES_ENABLES_CPUID_FAULT;
+ msrval |= (on << MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT);
+ this_cpu_write(msr_misc_features_shadow, msrval);
+ wrmsrl(MSR_MISC_FEATURES_ENABLES, msrval);
+}
- update_debugctlmsr(debugctl);
+static void disable_cpuid(void)
+{
+ preempt_disable();
+ if (!test_and_set_thread_flag(TIF_NOCPUID)) {
+ /*
+ * Must flip the CPU state synchronously with
+ * TIF_NOCPUID in the current running context.
+ */
+ set_cpuid_faulting(true);
}
+ preempt_enable();
+}
- if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^
- test_tsk_thread_flag(next_p, TIF_NOTSC)) {
- /* prev and next are different */
- if (test_tsk_thread_flag(next_p, TIF_NOTSC))
- hard_disable_TSC();
- else
- hard_enable_TSC();
+static void enable_cpuid(void)
+{
+ preempt_disable();
+ if (test_and_clear_thread_flag(TIF_NOCPUID)) {
+ /*
+ * Must flip the CPU state synchronously with
+ * TIF_NOCPUID in the current running context.
+ */
+ set_cpuid_faulting(false);
}
+ preempt_enable();
+}
+
+static int get_cpuid_mode(void)
+{
+ return !test_thread_flag(TIF_NOCPUID);
+}
+
+static int set_cpuid_mode(struct task_struct *task, unsigned long cpuid_enabled)
+{
+ if (!static_cpu_has(X86_FEATURE_CPUID_FAULT))
+ return -ENODEV;
+
+ if (cpuid_enabled)
+ enable_cpuid();
+ else
+ disable_cpuid();
+
+ return 0;
+}
+
+/*
+ * Called immediately after a successful exec.
+ */
+void arch_setup_new_exec(void)
+{
+ /* If cpuid was previously disabled for this task, re-enable it. */
+ if (test_thread_flag(TIF_NOCPUID))
+ enable_cpuid();
+}
- if (test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) {
+static inline void switch_to_bitmap(struct tss_struct *tss,
+ struct thread_struct *prev,
+ struct thread_struct *next,
+ unsigned long tifp, unsigned long tifn)
+{
+ if (tifn & _TIF_IO_BITMAP) {
/*
* Copy the relevant range of the IO bitmap.
* Normally this is 128 bytes or less:
*/
memcpy(tss->io_bitmap, next->io_bitmap_ptr,
max(prev->io_bitmap_max, next->io_bitmap_max));
-
/*
* Make sure that the TSS limit is correct for the CPU
* to notice the IO bitmap.
*/
refresh_tss_limit();
- } else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) {
+ } else if (tifp & _TIF_IO_BITMAP) {
/*
* Clear any possible leftover bits:
*/
memset(tss->io_bitmap, 0xff, prev->io_bitmap_max);
}
+}
+
+void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
+ struct tss_struct *tss)
+{
+ struct thread_struct *prev, *next;
+ unsigned long tifp, tifn;
+
+ prev = &prev_p->thread;
+ next = &next_p->thread;
+
+ tifn = READ_ONCE(task_thread_info(next_p)->flags);
+ tifp = READ_ONCE(task_thread_info(prev_p)->flags);
+ switch_to_bitmap(tss, prev, next, tifp, tifn);
+
propagate_user_return_notify(prev_p, next_p);
+
+ if ((tifp & _TIF_BLOCKSTEP || tifn & _TIF_BLOCKSTEP) &&
+ arch_has_block_step()) {
+ unsigned long debugctl, msk;
+
+ rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+ debugctl &= ~DEBUGCTLMSR_BTF;
+ msk = tifn & _TIF_BLOCKSTEP;
+ debugctl |= (msk >> TIF_BLOCKSTEP) << DEBUGCTLMSR_BTF_SHIFT;
+ wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+ }
+
+ if ((tifp ^ tifn) & _TIF_NOTSC)
+ cr4_toggle_bits(X86_CR4_TSD);
+
+ if ((tifp ^ tifn) & _TIF_NOCPUID)
+ set_cpuid_faulting(!!(tifn & _TIF_NOCPUID));
}
/*
put_task_stack(p);
return ret;
}
+
+long do_arch_prctl_common(struct task_struct *task, int option,
+ unsigned long cpuid_enabled)
+{
+ switch (option) {
+ case ARCH_GET_CPUID:
+ return get_cpuid_mode();
+ case ARCH_SET_CPUID:
+ return set_cpuid_mode(task, cpuid_enabled);
+ }
+
+ return -EINVAL;
+}
#include <linux/uaccess.h>
#include <linux/io.h>
#include <linux/kdebug.h>
+#include <linux/syscalls.h>
#include <asm/pgtable.h>
#include <asm/ldt.h>
#include <asm/switch_to.h>
#include <asm/vm86.h>
#include <asm/intel_rdt.h>
+#include <asm/proto.h>
void __show_regs(struct pt_regs *regs, int all)
{
return prev_p;
}
+
+SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
+{
+ return do_arch_prctl_common(current, option, arg2);
+}
#include <linux/uaccess.h>
#include <linux/io.h>
#include <linux/ftrace.h>
+#include <linux/syscalls.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
(struct user_desc __user *)tls, 0);
else
#endif
- err = do_arch_prctl(p, ARCH_SET_FS, tls);
+ err = do_arch_prctl_64(p, ARCH_SET_FS, tls);
if (err)
goto out;
}
}
#endif
-long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
+long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2)
{
int ret = 0;
int doit = task == current;
int cpu;
- switch (code) {
+ switch (option) {
case ARCH_SET_GS:
- if (addr >= TASK_SIZE_MAX)
+ if (arg2 >= TASK_SIZE_MAX)
return -EPERM;
cpu = get_cpu();
task->thread.gsindex = 0;
- task->thread.gsbase = addr;
+ task->thread.gsbase = arg2;
if (doit) {
load_gs_index(0);
- ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, addr);
+ ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, arg2);
}
put_cpu();
break;
case ARCH_SET_FS:
/* Not strictly needed for fs, but do it for symmetry
with gs */
- if (addr >= TASK_SIZE_MAX)
+ if (arg2 >= TASK_SIZE_MAX)
return -EPERM;
cpu = get_cpu();
task->thread.fsindex = 0;
- task->thread.fsbase = addr;
+ task->thread.fsbase = arg2;
if (doit) {
/* set the selector to 0 to not confuse __switch_to */
loadsegment(fs, 0);
- ret = wrmsrl_safe(MSR_FS_BASE, addr);
+ ret = wrmsrl_safe(MSR_FS_BASE, arg2);
}
put_cpu();
break;
case ARCH_GET_FS: {
unsigned long base;
+
if (doit)
rdmsrl(MSR_FS_BASE, base);
else
base = task->thread.fsbase;
- ret = put_user(base, (unsigned long __user *)addr);
+ ret = put_user(base, (unsigned long __user *)arg2);
break;
}
case ARCH_GET_GS: {
unsigned long base;
+
if (doit)
rdmsrl(MSR_KERNEL_GS_BASE, base);
else
base = task->thread.gsbase;
- ret = put_user(base, (unsigned long __user *)addr);
+ ret = put_user(base, (unsigned long __user *)arg2);
break;
}
#ifdef CONFIG_CHECKPOINT_RESTORE
# ifdef CONFIG_X86_X32_ABI
case ARCH_MAP_VDSO_X32:
- return prctl_map_vdso(&vdso_image_x32, addr);
+ return prctl_map_vdso(&vdso_image_x32, arg2);
# endif
# if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
case ARCH_MAP_VDSO_32:
- return prctl_map_vdso(&vdso_image_32, addr);
+ return prctl_map_vdso(&vdso_image_32, arg2);
# endif
case ARCH_MAP_VDSO_64:
- return prctl_map_vdso(&vdso_image_64, addr);
+ return prctl_map_vdso(&vdso_image_64, arg2);
#endif
default:
return ret;
}
-long sys_arch_prctl(int code, unsigned long addr)
+SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
+{
+ long ret;
+
+ ret = do_arch_prctl_64(current, option, arg2);
+ if (ret == -EINVAL)
+ ret = do_arch_prctl_common(current, option, arg2);
+
+ return ret;
+}
+
+#ifdef CONFIG_IA32_EMULATION
+COMPAT_SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
{
- return do_arch_prctl(current, code, addr);
+ return do_arch_prctl_common(current, option, arg2);
}
+#endif
unsigned long KSTK_ESP(struct task_struct *task)
{
if (value >= TASK_SIZE_MAX)
return -EIO;
/*
- * When changing the segment base, use do_arch_prctl
+ * When changing the segment base, use do_arch_prctl_64
* to set either thread.fs or thread.fsindex and the
* corresponding GDT slot.
*/
if (child->thread.fsbase != value)
- return do_arch_prctl(child, ARCH_SET_FS, value);
+ return do_arch_prctl_64(child, ARCH_SET_FS, value);
return 0;
case offsetof(struct user_regs_struct,gs_base):
/*
if (value >= TASK_SIZE_MAX)
return -EIO;
if (child->thread.gsbase != value)
- return do_arch_prctl(child, ARCH_SET_GS, value);
+ return do_arch_prctl_64(child, ARCH_SET_GS, value);
return 0;
#endif
}
Works just like arch_prctl, except that the arguments
are reversed. */
case PTRACE_ARCH_PRCTL:
- ret = do_arch_prctl(child, data, addr);
+ ret = do_arch_prctl_64(child, data, addr);
break;
#endif
#endif
+/* This is the CPU performing the emergency shutdown work. */
+int crashing_cpu = -1;
+
#if defined(CONFIG_SMP)
-/* This keeps a track of which one is crashing cpu. */
-static int crashing_cpu;
static nmi_shootdown_cb shootdown_callback;
static atomic_t waiting_for_crash_ipi;
#include <linux/ioport.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
static void resource_clip(struct resource *res, resource_size_t start,
resource_size_t end)
static void remove_e820_regions(struct resource *avail)
{
int i;
- struct e820entry *entry;
+ struct e820_entry *entry;
- for (i = 0; i < e820->nr_map; i++) {
- entry = &e820->map[i];
+ for (i = 0; i < e820_table->nr_entries; i++) {
+ entry = &e820_table->entries[i];
resource_clip(avail, entry->addr,
entry->addr + entry->size - 1);
#include <asm/mtrr.h>
#include <asm/apic.h>
#include <asm/realmode.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/mpspec.h>
#include <asm/setup.h>
#include <asm/efi.h>
* max_low_pfn_mapped: highest direct mapped pfn under 4GB
* max_pfn_mapped: highest direct mapped pfn over 4GB
*
- * The direct mapping only covers E820_RAM regions, so the ranges and gaps are
+ * The direct mapping only covers E820_TYPE_RAM regions, so the ranges and gaps are
* represented by pfn_mapped
*/
unsigned long max_low_pfn_mapped;
switch (data_type) {
case SETUP_E820_EXT:
- parse_e820_ext(pa_data, data_len);
+ e820__memory_setup_extended(pa_data, data_len);
break;
case SETUP_DTB:
add_dtb(pa_data);
}
}
-static void __init e820_reserve_setup_data(void)
-{
- struct setup_data *data;
- u64 pa_data;
-
- pa_data = boot_params.hdr.setup_data;
- if (!pa_data)
- return;
-
- while (pa_data) {
- data = early_memremap(pa_data, sizeof(*data));
- e820_update_range(pa_data, sizeof(*data)+data->len,
- E820_RAM, E820_RESERVED_KERN);
- pa_data = data->next;
- early_memunmap(data, sizeof(*data));
- }
-
- sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map);
- memcpy(e820_saved, e820, sizeof(struct e820map));
- printk(KERN_INFO "extended physical RAM map:\n");
- e820_print_map("reserve setup_data");
-}
-
static void __init memblock_x86_reserve_range_setup_data(void)
{
struct setup_data *data;
* since some BIOSes are known to corrupt low memory. See the
* Kconfig help text for X86_RESERVE_LOW.
*/
- e820_update_range(0, PAGE_SIZE, E820_RAM, E820_RESERVED);
+ e820__range_update(0, PAGE_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
/*
* special case: Some BIOSen report the PC BIOS
* area (640->1Mb) as ram even though it is not.
* take them out.
*/
- e820_remove_range(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_RAM, 1);
+ e820__range_remove(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_TYPE_RAM, 1);
- sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map);
+ e820__update_table(e820_table);
}
/* called before trim_bios_range() to spare extra sanitize */
u64 size = __pa_symbol(_end) - start;
/*
- * Complain if .text .data and .bss are not marked as E820_RAM and
+ * Complain if .text .data and .bss are not marked as E820_TYPE_RAM and
* attempt to fix it by adding the range. We may have a confused BIOS,
* or the user may have used memmap=exactmap or memmap=xxM$yyM to
* exclude kernel range. If we really are running on top non-RAM,
* we will crash later anyways.
*/
- if (e820_all_mapped(start, start + size, E820_RAM))
+ if (e820__mapped_all(start, start + size, E820_TYPE_RAM))
return;
- pr_warn(".text .data .bss are not marked as E820_RAM!\n");
- e820_remove_range(start, size, E820_RAM, 0);
- e820_add_region(start, size, E820_RAM);
+ pr_warn(".text .data .bss are not marked as E820_TYPE_RAM!\n");
+ e820__range_remove(start, size, E820_TYPE_RAM, 0);
+ e820__range_add(start, size, E820_TYPE_RAM);
}
static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10;
x86_init.oem.arch_setup();
iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1;
- setup_memory_map();
+ e820__memory_setup();
parse_setup_data();
copy_edd();
early_dump_pci_devices();
#endif
- /* update the e820_saved too */
- e820_reserve_setup_data();
- finish_e820_parsing();
+ e820__reserve_setup_data();
+ e820__finish_early_params();
if (efi_enabled(EFI_BOOT))
efi_init();
trim_bios_range();
#ifdef CONFIG_X86_32
if (ppro_with_ram_bug()) {
- e820_update_range(0x70000000ULL, 0x40000ULL, E820_RAM,
- E820_RESERVED);
- sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map);
+ e820__range_update(0x70000000ULL, 0x40000ULL, E820_TYPE_RAM,
+ E820_TYPE_RESERVED);
+ e820__update_table(e820_table);
printk(KERN_INFO "fixed physical RAM map:\n");
- e820_print_map("bad_ppro");
+ e820__print_table("bad_ppro");
}
#else
early_gart_iommu_check();
* partially used pages are not usable - thus
* we are rounding upwards:
*/
- max_pfn = e820_end_of_ram_pfn();
+ max_pfn = e820__end_of_ram_pfn();
/* update e820 for memory not covered by WB MTRRs */
mtrr_bp_init();
if (mtrr_trim_uncached_memory(max_pfn))
- max_pfn = e820_end_of_ram_pfn();
+ max_pfn = e820__end_of_ram_pfn();
max_possible_pfn = max_pfn;
/* How many end-of-memory variables you have, grandma! */
/* need this before calling reserve_initrd */
if (max_pfn > (1UL<<(32 - PAGE_SHIFT)))
- max_low_pfn = e820_end_of_low_ram_pfn();
+ max_low_pfn = e820__end_of_low_ram_pfn();
else
max_low_pfn = max_pfn;
early_alloc_pgt_buf();
/*
- * Need to conclude brk, before memblock_x86_fill()
+ * Need to conclude brk, before e820__memblock_setup()
* it could use memblock_find_in_range, could overlap with
* brk area.
*/
cleanup_highmap();
memblock_set_current_limit(ISA_END_ADDRESS);
- memblock_x86_fill();
+ e820__memblock_setup();
reserve_bios_regions();
}
/* preallocate 4k for mptable mpc */
- early_reserve_e820_mpc_new();
+ e820__memblock_alloc_reserved_mpc_new();
#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
setup_bios_corruption_check();
kvm_guest_init();
- e820_reserve_resources();
- e820_mark_nosave_regions(max_low_pfn);
+ e820__reserve_resources();
+ e820__register_nosave_regions(max_low_pfn);
x86_init.resources.reserve_resources();
- e820_setup_gap();
+ e820__setup_pci_gap();
#ifdef CONFIG_VT
#if defined(CONFIG_VGA_CONSOLE)
#include <asm/mce.h>
#include <asm/trace/irq_vectors.h>
#include <asm/kexec.h>
+#include <asm/virtext.h>
/*
* Some notes on x86 processor bugs affecting SMP operation:
static void native_smp_send_reschedule(int cpu)
{
if (unlikely(cpu_is_offline(cpu))) {
- WARN_ON(1);
+ WARN(1, "sched: Unexpected reschedule of offline CPU#%d!\n", cpu);
return;
}
apic->send_IPI(cpu, RESCHEDULE_VECTOR);
if (raw_smp_processor_id() == atomic_read(&stopping_cpu))
return NMI_HANDLED;
+ cpu_emergency_vmxoff();
stop_this_cpu(NULL);
return NMI_HANDLED;
asmlinkage __visible void smp_reboot_interrupt(void)
{
ipi_entering_ack_irq();
+ cpu_emergency_vmxoff();
stop_this_cpu(NULL);
irq_exit();
}
#include <asm/fixmap.h>
#include <asm/proto.h>
#include <asm/setup.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/io.h>
#include "../realmode/rm/wakeup.h"
* also verify that it is mapped as we expect it before calling
* set_fixmap(), to reduce chance of garbage value causing crash
*/
- if (!e820_any_mapped(boot_params.tboot_addr,
- boot_params.tboot_addr, E820_RESERVED)) {
- pr_warning("non-0 tboot_addr but it is not of type E820_RESERVED\n");
+ if (!e820__mapped_any(boot_params.tboot_addr,
+ boot_params.tboot_addr, E820_TYPE_RESERVED)) {
+ pr_warning("non-0 tboot_addr but it is not of type E820_TYPE_RESERVED\n");
return;
}
tboot->num_mac_regions = 0;
- for (i = 0; i < e820->nr_map; i++) {
- if ((e820->map[i].type != E820_RAM)
- && (e820->map[i].type != E820_RESERVED_KERN))
+ for (i = 0; i < e820_table->nr_entries; i++) {
+ if ((e820_table->entries[i].type != E820_TYPE_RAM)
+ && (e820_table->entries[i].type != E820_TYPE_RESERVED_KERN))
continue;
- add_mac_region(e820->map[i].addr, e820->map[i].size);
+ add_mac_region(e820_table->entries[i].addr, e820_table->entries[i].size);
}
tboot->acpi_sinfo.kernel_s3_resume_vector =
#include <asm/mpspec.h>
#include <asm/setup.h>
#include <asm/apic.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/time.h>
#include <asm/irq.h>
#include <asm/io_apic.h>
.resources = {
.probe_roms = probe_roms,
.reserve_resources = reserve_standard_io_resources,
- .memory_setup = default_machine_specific_memory_setup,
+ .memory_setup = e820__memory_setup_default,
},
.mpparse = {
return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES);
case EXIT_REASON_PREEMPTION_TIMER:
return false;
+ case EXIT_REASON_PML_FULL:
+ /* We don't expose PML support to L1. */
+ return false;
default:
return true;
}
}
+ if (enable_pml) {
+ /*
+ * Conceptually we want to copy the PML address and index from
+ * vmcs01 here, and then back to vmcs01 on nested vmexit. But,
+ * since we always flush the log on each vmexit, this happens
+ * to be equivalent to simply resetting the fields in vmcs02.
+ */
+ ASSERT(vmx->pml_pg);
+ vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
+ vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
+ }
+
if (nested_cpu_has_ept(vmcs12)) {
kvm_mmu_unload(vcpu);
nested_ept_init_mmu_context(vcpu);
#include <asm/pgtable.h>
#include <asm/desc.h>
#include <asm/setup.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/mce.h>
#include <asm/io.h>
#include <asm/fpu/api.h>
.mult = 1,
.shift = 0,
.min_delta_ns = LG_CLOCK_MIN_DELTA,
+ .min_delta_ticks = LG_CLOCK_MIN_DELTA,
.max_delta_ns = LG_CLOCK_MAX_DELTA,
+ .max_delta_ticks = LG_CLOCK_MAX_DELTA,
};
/*
* The Linux bootloader header contains an "e820" memory map: the
* Launcher populated the first entry with our memory limit.
*/
- e820_add_region(boot_params.e820_map[0].addr,
- boot_params.e820_map[0].size,
- boot_params.e820_map[0].type);
+ e820__range_add(boot_params.e820_table[0].addr,
+ boot_params.e820_table[0].size,
+ boot_params.e820_table[0].type);
/* This string is for the boot messages. */
return "LGUEST";
{
u64 start, end, delay, loops = __loops;
+ /*
+ * Timer value of 0 causes MWAITX to wait indefinitely, unless there
+ * is a store on the memory monitored by MONITORX.
+ */
+ if (loops == 0)
+ return;
+
start = rdtsc_ordered();
for (;;) {
#include <asm/kaslr.h>
#include <asm/msr.h>
#include <asm/archrandom.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/io.h>
/*
* For licencing details see kernel-base/COPYING
*/
-#include <linux/highmem.h>
+#include <linux/uaccess.h>
#include <linux/export.h>
-#include <asm/word-at-a-time.h>
-#include <linux/sched.h>
-
/*
* We rely on the nested NMI work to allow atomic faults from the NMI path; the
* nested NMI paths are careful to preserve CR2.
return ret;
}
EXPORT_SYMBOL_GPL(copy_from_user_nmi);
-
-/**
- * copy_to_user: - Copy a block of data into user space.
- * @to: Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- * enabled.
- *
- * Copy data from kernel space to user space.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- */
-unsigned long _copy_to_user(void __user *to, const void *from, unsigned n)
-{
- if (access_ok(VERIFY_WRITE, to, n))
- n = __copy_to_user(to, from, n);
- return n;
-}
-EXPORT_SYMBOL(_copy_to_user);
-
-/**
- * copy_from_user: - Copy a block of data from user space.
- * @to: Destination address, in kernel space.
- * @from: Source address, in user space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- * enabled.
- *
- * Copy data from user space to kernel space.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- *
- * If some data could not be copied, this function will pad the copied
- * data to the requested size using zero bytes.
- */
-unsigned long _copy_from_user(void *to, const void __user *from, unsigned n)
-{
- if (access_ok(VERIFY_READ, from, n))
- n = __copy_from_user(to, from, n);
- else
- memset(to, 0, n);
- return n;
-}
-EXPORT_SYMBOL(_copy_from_user);
* Copyright 1997 Andi Kleen <ak@muc.de>
* Copyright 1997 Linus Torvalds
*/
-#include <linux/mm.h>
-#include <linux/highmem.h>
-#include <linux/blkdev.h>
#include <linux/export.h>
-#include <linux/backing-dev.h>
-#include <linux/interrupt.h>
#include <linux/uaccess.h>
#include <asm/mmx.h>
#include <asm/asm.h>
return size;
}
-static unsigned long
-__copy_user_zeroing_intel(void *to, const void __user *from, unsigned long size)
-{
- int d0, d1;
- __asm__ __volatile__(
- " .align 2,0x90\n"
- "0: movl 32(%4), %%eax\n"
- " cmpl $67, %0\n"
- " jbe 2f\n"
- "1: movl 64(%4), %%eax\n"
- " .align 2,0x90\n"
- "2: movl 0(%4), %%eax\n"
- "21: movl 4(%4), %%edx\n"
- " movl %%eax, 0(%3)\n"
- " movl %%edx, 4(%3)\n"
- "3: movl 8(%4), %%eax\n"
- "31: movl 12(%4),%%edx\n"
- " movl %%eax, 8(%3)\n"
- " movl %%edx, 12(%3)\n"
- "4: movl 16(%4), %%eax\n"
- "41: movl 20(%4), %%edx\n"
- " movl %%eax, 16(%3)\n"
- " movl %%edx, 20(%3)\n"
- "10: movl 24(%4), %%eax\n"
- "51: movl 28(%4), %%edx\n"
- " movl %%eax, 24(%3)\n"
- " movl %%edx, 28(%3)\n"
- "11: movl 32(%4), %%eax\n"
- "61: movl 36(%4), %%edx\n"
- " movl %%eax, 32(%3)\n"
- " movl %%edx, 36(%3)\n"
- "12: movl 40(%4), %%eax\n"
- "71: movl 44(%4), %%edx\n"
- " movl %%eax, 40(%3)\n"
- " movl %%edx, 44(%3)\n"
- "13: movl 48(%4), %%eax\n"
- "81: movl 52(%4), %%edx\n"
- " movl %%eax, 48(%3)\n"
- " movl %%edx, 52(%3)\n"
- "14: movl 56(%4), %%eax\n"
- "91: movl 60(%4), %%edx\n"
- " movl %%eax, 56(%3)\n"
- " movl %%edx, 60(%3)\n"
- " addl $-64, %0\n"
- " addl $64, %4\n"
- " addl $64, %3\n"
- " cmpl $63, %0\n"
- " ja 0b\n"
- "5: movl %0, %%eax\n"
- " shrl $2, %0\n"
- " andl $3, %%eax\n"
- " cld\n"
- "6: rep; movsl\n"
- " movl %%eax,%0\n"
- "7: rep; movsb\n"
- "8:\n"
- ".section .fixup,\"ax\"\n"
- "9: lea 0(%%eax,%0,4),%0\n"
- "16: pushl %0\n"
- " pushl %%eax\n"
- " xorl %%eax,%%eax\n"
- " rep; stosb\n"
- " popl %%eax\n"
- " popl %0\n"
- " jmp 8b\n"
- ".previous\n"
- _ASM_EXTABLE(0b,16b)
- _ASM_EXTABLE(1b,16b)
- _ASM_EXTABLE(2b,16b)
- _ASM_EXTABLE(21b,16b)
- _ASM_EXTABLE(3b,16b)
- _ASM_EXTABLE(31b,16b)
- _ASM_EXTABLE(4b,16b)
- _ASM_EXTABLE(41b,16b)
- _ASM_EXTABLE(10b,16b)
- _ASM_EXTABLE(51b,16b)
- _ASM_EXTABLE(11b,16b)
- _ASM_EXTABLE(61b,16b)
- _ASM_EXTABLE(12b,16b)
- _ASM_EXTABLE(71b,16b)
- _ASM_EXTABLE(13b,16b)
- _ASM_EXTABLE(81b,16b)
- _ASM_EXTABLE(14b,16b)
- _ASM_EXTABLE(91b,16b)
- _ASM_EXTABLE(6b,9b)
- _ASM_EXTABLE(7b,16b)
- : "=&c"(size), "=&D" (d0), "=&S" (d1)
- : "1"(to), "2"(from), "0"(size)
- : "eax", "edx", "memory");
- return size;
-}
-
-/*
- * Non Temporal Hint version of __copy_user_zeroing_intel. It is cache aware.
- * hyoshiok@miraclelinux.com
- */
-
-static unsigned long __copy_user_zeroing_intel_nocache(void *to,
- const void __user *from, unsigned long size)
-{
- int d0, d1;
-
- __asm__ __volatile__(
- " .align 2,0x90\n"
- "0: movl 32(%4), %%eax\n"
- " cmpl $67, %0\n"
- " jbe 2f\n"
- "1: movl 64(%4), %%eax\n"
- " .align 2,0x90\n"
- "2: movl 0(%4), %%eax\n"
- "21: movl 4(%4), %%edx\n"
- " movnti %%eax, 0(%3)\n"
- " movnti %%edx, 4(%3)\n"
- "3: movl 8(%4), %%eax\n"
- "31: movl 12(%4),%%edx\n"
- " movnti %%eax, 8(%3)\n"
- " movnti %%edx, 12(%3)\n"
- "4: movl 16(%4), %%eax\n"
- "41: movl 20(%4), %%edx\n"
- " movnti %%eax, 16(%3)\n"
- " movnti %%edx, 20(%3)\n"
- "10: movl 24(%4), %%eax\n"
- "51: movl 28(%4), %%edx\n"
- " movnti %%eax, 24(%3)\n"
- " movnti %%edx, 28(%3)\n"
- "11: movl 32(%4), %%eax\n"
- "61: movl 36(%4), %%edx\n"
- " movnti %%eax, 32(%3)\n"
- " movnti %%edx, 36(%3)\n"
- "12: movl 40(%4), %%eax\n"
- "71: movl 44(%4), %%edx\n"
- " movnti %%eax, 40(%3)\n"
- " movnti %%edx, 44(%3)\n"
- "13: movl 48(%4), %%eax\n"
- "81: movl 52(%4), %%edx\n"
- " movnti %%eax, 48(%3)\n"
- " movnti %%edx, 52(%3)\n"
- "14: movl 56(%4), %%eax\n"
- "91: movl 60(%4), %%edx\n"
- " movnti %%eax, 56(%3)\n"
- " movnti %%edx, 60(%3)\n"
- " addl $-64, %0\n"
- " addl $64, %4\n"
- " addl $64, %3\n"
- " cmpl $63, %0\n"
- " ja 0b\n"
- " sfence \n"
- "5: movl %0, %%eax\n"
- " shrl $2, %0\n"
- " andl $3, %%eax\n"
- " cld\n"
- "6: rep; movsl\n"
- " movl %%eax,%0\n"
- "7: rep; movsb\n"
- "8:\n"
- ".section .fixup,\"ax\"\n"
- "9: lea 0(%%eax,%0,4),%0\n"
- "16: pushl %0\n"
- " pushl %%eax\n"
- " xorl %%eax,%%eax\n"
- " rep; stosb\n"
- " popl %%eax\n"
- " popl %0\n"
- " jmp 8b\n"
- ".previous\n"
- _ASM_EXTABLE(0b,16b)
- _ASM_EXTABLE(1b,16b)
- _ASM_EXTABLE(2b,16b)
- _ASM_EXTABLE(21b,16b)
- _ASM_EXTABLE(3b,16b)
- _ASM_EXTABLE(31b,16b)
- _ASM_EXTABLE(4b,16b)
- _ASM_EXTABLE(41b,16b)
- _ASM_EXTABLE(10b,16b)
- _ASM_EXTABLE(51b,16b)
- _ASM_EXTABLE(11b,16b)
- _ASM_EXTABLE(61b,16b)
- _ASM_EXTABLE(12b,16b)
- _ASM_EXTABLE(71b,16b)
- _ASM_EXTABLE(13b,16b)
- _ASM_EXTABLE(81b,16b)
- _ASM_EXTABLE(14b,16b)
- _ASM_EXTABLE(91b,16b)
- _ASM_EXTABLE(6b,9b)
- _ASM_EXTABLE(7b,16b)
- : "=&c"(size), "=&D" (d0), "=&S" (d1)
- : "1"(to), "2"(from), "0"(size)
- : "eax", "edx", "memory");
- return size;
-}
-
static unsigned long __copy_user_intel_nocache(void *to,
const void __user *from, unsigned long size)
{
* Leave these declared but undefined. They should not be any references to
* them
*/
-unsigned long __copy_user_zeroing_intel(void *to, const void __user *from,
- unsigned long size);
unsigned long __copy_user_intel(void __user *to, const void *from,
unsigned long size);
-unsigned long __copy_user_zeroing_intel_nocache(void *to,
- const void __user *from, unsigned long size);
#endif /* CONFIG_X86_INTEL_USERCOPY */
/* Generic arbitrary sized copy. */
: "memory"); \
} while (0)
-#define __copy_user_zeroing(to, from, size) \
-do { \
- int __d0, __d1, __d2; \
- __asm__ __volatile__( \
- " cmp $7,%0\n" \
- " jbe 1f\n" \
- " movl %1,%0\n" \
- " negl %0\n" \
- " andl $7,%0\n" \
- " subl %0,%3\n" \
- "4: rep; movsb\n" \
- " movl %3,%0\n" \
- " shrl $2,%0\n" \
- " andl $3,%3\n" \
- " .align 2,0x90\n" \
- "0: rep; movsl\n" \
- " movl %3,%0\n" \
- "1: rep; movsb\n" \
- "2:\n" \
- ".section .fixup,\"ax\"\n" \
- "5: addl %3,%0\n" \
- " jmp 6f\n" \
- "3: lea 0(%3,%0,4),%0\n" \
- "6: pushl %0\n" \
- " pushl %%eax\n" \
- " xorl %%eax,%%eax\n" \
- " rep; stosb\n" \
- " popl %%eax\n" \
- " popl %0\n" \
- " jmp 2b\n" \
- ".previous\n" \
- _ASM_EXTABLE(4b,5b) \
- _ASM_EXTABLE(0b,3b) \
- _ASM_EXTABLE(1b,6b) \
- : "=&c"(size), "=&D" (__d0), "=&S" (__d1), "=r"(__d2) \
- : "3"(size), "0"(size), "1"(to), "2"(from) \
- : "memory"); \
-} while (0)
-
-unsigned long __copy_to_user_ll(void __user *to, const void *from,
- unsigned long n)
+unsigned long __copy_user_ll(void *to, const void *from, unsigned long n)
{
stac();
if (movsl_is_ok(to, from, n))
clac();
return n;
}
-EXPORT_SYMBOL(__copy_to_user_ll);
-
-unsigned long __copy_from_user_ll(void *to, const void __user *from,
- unsigned long n)
-{
- stac();
- if (movsl_is_ok(to, from, n))
- __copy_user_zeroing(to, from, n);
- else
- n = __copy_user_zeroing_intel(to, from, n);
- clac();
- return n;
-}
-EXPORT_SYMBOL(__copy_from_user_ll);
-
-unsigned long __copy_from_user_ll_nozero(void *to, const void __user *from,
- unsigned long n)
-{
- stac();
- if (movsl_is_ok(to, from, n))
- __copy_user(to, from, n);
- else
- n = __copy_user_intel((void __user *)to,
- (const void *)from, n);
- clac();
- return n;
-}
-EXPORT_SYMBOL(__copy_from_user_ll_nozero);
-
-unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from,
- unsigned long n)
-{
- stac();
-#ifdef CONFIG_X86_INTEL_USERCOPY
- if (n > 64 && static_cpu_has(X86_FEATURE_XMM2))
- n = __copy_user_zeroing_intel_nocache(to, from, n);
- else
- __copy_user_zeroing(to, from, n);
-#else
- __copy_user_zeroing(to, from, n);
-#endif
- clac();
- return n;
-}
-EXPORT_SYMBOL(__copy_from_user_ll_nocache);
+EXPORT_SYMBOL(__copy_user_ll);
unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from,
unsigned long n)
}
EXPORT_SYMBOL(clear_user);
-unsigned long copy_in_user(void __user *to, const void __user *from, unsigned len)
-{
- if (access_ok(VERIFY_WRITE, to, len) && access_ok(VERIFY_READ, from, len)) {
- return copy_user_generic((__force void *)to, (__force void *)from, len);
- }
- return len;
-}
-EXPORT_SYMBOL(copy_in_user);
-
/*
* Try to copy last bytes and clear the rest if needed.
* Since protection fault in copy_from/to_user is not a normal situation,
break;
}
clac();
-
- /* If the destination is a kernel buffer, we always clear the end */
- if (!__addr_ok(to))
- memset(to, 0, len);
return len;
}
#include <asm/types.h>
#include <asm/mmzone.h>
#include <asm/proto.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/pci-direct.h>
#include <asm/numa.h>
#include <asm/mpspec.h>
#include <linux/bootmem.h> /* for max_low_pfn */
#include <asm/cacheflush.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/init.h>
#include <asm/page.h>
#include <asm/page_types.h>
return nr_range;
}
-struct range pfn_mapped[E820_X_MAX];
+struct range pfn_mapped[E820_MAX_ENTRIES];
int nr_pfn_mapped;
static void add_pfn_range_mapped(unsigned long start_pfn, unsigned long end_pfn)
{
- nr_pfn_mapped = add_range_with_merge(pfn_mapped, E820_X_MAX,
+ nr_pfn_mapped = add_range_with_merge(pfn_mapped, E820_MAX_ENTRIES,
nr_pfn_mapped, start_pfn, end_pfn);
- nr_pfn_mapped = clean_sort_range(pfn_mapped, E820_X_MAX);
+ nr_pfn_mapped = clean_sort_range(pfn_mapped, E820_MAX_ENTRIES);
max_pfn_mapped = max(max_pfn_mapped, end_pfn);
/*
* We need to iterate through the E820 memory map and create direct mappings
- * for only E820_RAM and E820_KERN_RESERVED regions. We cannot simply
+ * for only E820_TYPE_RAM and E820_KERN_RESERVED regions. We cannot simply
* create direct mappings for all pfns from [0 to max_low_pfn) and
* [4GB to max_pfn) because of possible memory holes in high addresses
* that cannot be marked as UC by fixed/variable range MTRRs.
* devmem_is_allowed() checks to see if /dev/mem access to a certain address
* is valid. The argument is a physical page number.
*
- *
- * On x86, access has to be given to the first megabyte of ram because that area
- * contains BIOS code and data regions used by X and dosemu and similar apps.
- * Access has to be given to non-kernel-ram areas as well, these contain the PCI
- * mmio resources as well as potential bios/acpi data regions.
+ * On x86, access has to be given to the first megabyte of RAM because that
+ * area traditionally contains BIOS code and data regions used by X, dosemu,
+ * and similar apps. Since they map the entire memory range, the whole range
+ * must be allowed (for mapping), but any areas that would otherwise be
+ * disallowed are flagged as being "zero filled" instead of rejected.
+ * Access has to be given to non-kernel-ram areas as well, these contain the
+ * PCI mmio resources as well as potential bios/acpi data regions.
*/
int devmem_is_allowed(unsigned long pagenr)
{
- if (pagenr < 256)
- return 1;
- if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
+ if (page_is_ram(pagenr)) {
+ /*
+ * For disallowed memory regions in the low 1MB range,
+ * request that the page be shown as all zeros.
+ */
+ if (pagenr < 256)
+ return 2;
+
return 0;
- if (!page_is_ram(pagenr))
- return 1;
- return 0;
+ }
+
+ /*
+ * This must follow RAM test, since System RAM is considered a
+ * restricted resource under CONFIG_STRICT_IOMEM.
+ */
+ if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) {
+ /* Low 1MB bypasses iomem restrictions. */
+ if (pagenr < 256)
+ return 1;
+
+ return 0;
+ }
+
+ return 1;
}
void free_init_pages(char *what, unsigned long begin, unsigned long end)
void __ref free_initmem(void)
{
- e820_reallocate_tables();
+ e820__reallocate_tables();
free_init_pages("unused kernel",
(unsigned long)(&__init_begin),
}
#endif
+/*
+ * Calculate the precise size of the DMA zone (first 16 MB of RAM),
+ * and pass it to the MM layer - to help it set zone watermarks more
+ * accurately.
+ *
+ * Done on 64-bit systems only for the time being, although 32-bit systems
+ * might benefit from this as well.
+ */
+void __init memblock_find_dma_reserve(void)
+{
+#ifdef CONFIG_X86_64
+ u64 nr_pages = 0, nr_free_pages = 0;
+ unsigned long start_pfn, end_pfn;
+ phys_addr_t start_addr, end_addr;
+ int i;
+ u64 u;
+
+ /*
+ * Iterate over all memory ranges (free and reserved ones alike),
+ * to calculate the total number of pages in the first 16 MB of RAM:
+ */
+ nr_pages = 0;
+ for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
+ start_pfn = min(start_pfn, MAX_DMA_PFN);
+ end_pfn = min(end_pfn, MAX_DMA_PFN);
+
+ nr_pages += end_pfn - start_pfn;
+ }
+
+ /*
+ * Iterate over free memory ranges to calculate the number of free
+ * pages in the DMA zone, while not counting potential partial
+ * pages at the beginning or the end of the range:
+ */
+ nr_free_pages = 0;
+ for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start_addr, &end_addr, NULL) {
+ start_pfn = min_t(unsigned long, PFN_UP(start_addr), MAX_DMA_PFN);
+ end_pfn = min_t(unsigned long, PFN_DOWN(end_addr), MAX_DMA_PFN);
+
+ if (start_pfn < end_pfn)
+ nr_free_pages += end_pfn - start_pfn;
+ }
+
+ set_dma_reserve(nr_pages - nr_free_pages);
+#endif
+}
+
void __init zone_sizes_init(void)
{
unsigned long max_zone_pfns[MAX_NR_ZONES];
#include <asm/pgtable.h>
#include <asm/dma.h>
#include <asm/fixmap.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/apic.h>
#include <asm/bugs.h>
#include <asm/tlb.h>
#include <asm/pgalloc.h>
#include <asm/dma.h>
#include <asm/fixmap.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/apic.h>
#include <asm/tlb.h>
#include <asm/mmu_context.h>
paddr_next = (paddr & PAGE_MASK) + PAGE_SIZE;
if (paddr >= paddr_end) {
if (!after_bootmem &&
- !e820_any_mapped(paddr & PAGE_MASK, paddr_next,
- E820_RAM) &&
- !e820_any_mapped(paddr & PAGE_MASK, paddr_next,
- E820_RESERVED_KERN))
+ !e820__mapped_any(paddr & PAGE_MASK, paddr_next,
+ E820_TYPE_RAM) &&
+ !e820__mapped_any(paddr & PAGE_MASK, paddr_next,
+ E820_TYPE_RESERVED_KERN))
set_pte(pte, __pte(0));
continue;
}
paddr_next = (paddr & PMD_MASK) + PMD_SIZE;
if (paddr >= paddr_end) {
if (!after_bootmem &&
- !e820_any_mapped(paddr & PMD_MASK, paddr_next,
- E820_RAM) &&
- !e820_any_mapped(paddr & PMD_MASK, paddr_next,
- E820_RESERVED_KERN))
+ !e820__mapped_any(paddr & PMD_MASK, paddr_next,
+ E820_TYPE_RAM) &&
+ !e820__mapped_any(paddr & PMD_MASK, paddr_next,
+ E820_TYPE_RESERVED_KERN))
set_pmd(pmd, __pmd(0));
continue;
}
if (paddr >= paddr_end) {
if (!after_bootmem &&
- !e820_any_mapped(paddr & PUD_MASK, paddr_next,
- E820_RAM) &&
- !e820_any_mapped(paddr & PUD_MASK, paddr_next,
- E820_RESERVED_KERN))
+ !e820__mapped_any(paddr & PUD_MASK, paddr_next,
+ E820_TYPE_RAM) &&
+ !e820__mapped_any(paddr & PUD_MASK, paddr_next,
+ E820_TYPE_RESERVED_KERN))
set_pud(pud, __pud(0));
continue;
}
#include <linux/bootmem.h>
#include <linux/init.h>
#include <linux/io.h>
+#include <linux/ioport.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/mmiotrace.h>
#include <asm/cacheflush.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/fixmap.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <linux/sched/task.h>
#include <linux/vmalloc.h>
+#include <asm/e820/types.h>
#include <asm/tlbflush.h>
#include <asm/sections.h>
extern pgd_t early_level4_pgt[PTRS_PER_PGD];
-extern struct range pfn_mapped[E820_X_MAX];
+extern struct range pfn_mapped[E820_MAX_ENTRIES];
static int __init map_range(struct range *range)
{
kasan_populate_zero_shadow((void *)KASAN_SHADOW_START,
kasan_mem_to_shadow((void *)PAGE_OFFSET));
- for (i = 0; i < E820_X_MAX; i++) {
+ for (i = 0; i < E820_MAX_ENTRIES; i++) {
if (pfn_mapped[i].end == 0)
break;
#include <linux/kallsyms.h>
#include <asm/pgtable.h>
#include <linux/mmiotrace.h>
-#include <asm/e820.h> /* for ISA_START_ADDRESS */
+#include <asm/e820/api.h> /* for ISA_START_ADDRESS */
#include <linux/atomic.h>
#include <linux/percpu.h>
#include <linux/cpu.h>
#include <linux/sched.h>
#include <linux/topology.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/proto.h>
#include <asm/dma.h>
#include <asm/amd_nb.h>
#include <linux/pci.h>
#include <linux/vmalloc.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/processor.h>
#include <asm/tlbflush.h>
#include <asm/sections.h>
#include <linux/seq_file.h>
#include <linux/bootmem.h>
#include <linux/debugfs.h>
+#include <linux/ioport.h>
#include <linux/kernel.h>
#include <linux/pfn_t.h>
#include <linux/slab.h>
#include <asm/x86_init.h>
#include <asm/pgtable.h>
#include <asm/fcntl.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/mtrr.h>
#include <asm/page.h>
#include <asm/msr.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/fixmap.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/io.h>
#include <linux/mm.h>
#include <asm/proto.h>
#include <asm/numa.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/apic.h>
#include <asm/uv/uv.h>
#include <linux/bootmem.h>
#include <asm/pat.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/pci_x86.h>
#include <asm/io_apic.h>
list_for_each_entry(bus, &pci_root_buses, node)
pcibios_allocate_resources(bus, 1);
- e820_reserve_resources_late();
+ e820__reserve_resources_late();
/*
* Insert the IO APIC resources after PCI initialization has
* occurred to handle IO APICS that are mapped in on a BAR in
#include <linux/slab.h>
#include <linux/mutex.h>
#include <linux/rculist.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/pci_x86.h>
#include <asm/acpi.h>
return AE_OK;
}
-static int is_acpi_reserved(u64 start, u64 end, unsigned not_used)
+static bool is_acpi_reserved(u64 start, u64 end, unsigned not_used)
{
struct resource mcfg_res;
return mcfg_res.flags;
}
-typedef int (*check_reserved_t)(u64 start, u64 end, unsigned type);
+typedef bool (*check_reserved_t)(u64 start, u64 end, unsigned type);
-static int __ref is_mmconf_reserved(check_reserved_t is_reserved,
- struct pci_mmcfg_region *cfg,
- struct device *dev, int with_e820)
+static bool __ref is_mmconf_reserved(check_reserved_t is_reserved,
+ struct pci_mmcfg_region *cfg,
+ struct device *dev, int with_e820)
{
u64 addr = cfg->res.start;
u64 size = resource_size(&cfg->res);
int num_buses;
char *method = with_e820 ? "E820" : "ACPI motherboard resources";
- while (!is_reserved(addr, addr + size, E820_RESERVED)) {
+ while (!is_reserved(addr, addr + size, E820_TYPE_RESERVED)) {
size >>= 1;
if (size < (16UL<<20))
break;
return 1;
}
-static int __ref pci_mmcfg_check_reserved(struct device *dev,
- struct pci_mmcfg_region *cfg, int early)
+static bool __ref
+pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int early)
{
if (!early && !acpi_disabled) {
if (is_mmconf_reserved(is_acpi_reserved, cfg, dev, 0))
}
/*
- * e820_all_mapped() is marked as __init.
+ * e820__mapped_all() is marked as __init.
* All entries from ACPI MCFG table have been checked at boot time.
* For MCFG information constructed from hotpluggable host bridge's
* _CBA method, just assume it's reserved.
/* Don't try to do this check unless configuration
type 1 is available. how about type 2 ?*/
if (raw_pci_ops)
- return is_mmconf_reserved(e820_all_mapped, cfg, dev, 1);
+ return is_mmconf_reserved(e820__mapped_all, cfg, dev, 1);
return 0;
}
#include <linux/pci.h>
#include <linux/init.h>
#include <linux/rcupdate.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/pci_x86.h>
/* Assume systems with more busses have correct MCFG */
#include <linux/acpi.h>
#include <linux/bitmap.h>
#include <linux/rcupdate.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/pci_x86.h>
#define PREFIX "PCI: "
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/uaccess.h>
+
#include <asm/pci_x86.h>
+#include <asm/e820/types.h>
#include <asm/pci-functions.h>
#include <asm/cacheflush.h>
OBJECT_FILES_NON_STANDARD_efi_thunk_$(BITS).o := y
obj-$(CONFIG_EFI) += quirks.o efi.o efi_$(BITS).o efi_stub_$(BITS).o
-obj-$(CONFIG_ACPI_BGRT) += efi-bgrt.o
obj-$(CONFIG_EARLY_PRINTK_EFI) += early_printk.o
obj-$(CONFIG_EFI_MIXED) += efi_thunk_$(BITS).o
#include <asm/setup.h>
#include <asm/efi.h>
+#include <asm/e820/api.h>
#include <asm/time.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
case EFI_BOOT_SERVICES_DATA:
case EFI_CONVENTIONAL_MEMORY:
if (md->attribute & EFI_MEMORY_WB)
- e820_type = E820_RAM;
+ e820_type = E820_TYPE_RAM;
else
- e820_type = E820_RESERVED;
+ e820_type = E820_TYPE_RESERVED;
break;
case EFI_ACPI_RECLAIM_MEMORY:
- e820_type = E820_ACPI;
+ e820_type = E820_TYPE_ACPI;
break;
case EFI_ACPI_MEMORY_NVS:
- e820_type = E820_NVS;
+ e820_type = E820_TYPE_NVS;
break;
case EFI_UNUSABLE_MEMORY:
- e820_type = E820_UNUSABLE;
+ e820_type = E820_TYPE_UNUSABLE;
break;
case EFI_PERSISTENT_MEMORY:
- e820_type = E820_PMEM;
+ e820_type = E820_TYPE_PMEM;
break;
default:
/*
* EFI_RUNTIME_SERVICES_DATA EFI_MEMORY_MAPPED_IO
* EFI_MEMORY_MAPPED_IO_PORT_SPACE EFI_PAL_CODE
*/
- e820_type = E820_RESERVED;
+ e820_type = E820_TYPE_RESERVED;
break;
}
- e820_add_region(start, size, e820_type);
+ e820__range_add(start, size, e820_type);
}
- sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map);
+ e820__update_table(e820_table);
}
int __init efi_memblock_x86_reserve_range(void)
#include <asm/setup.h>
#include <asm/page.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/proto.h>
#include <asm/pgalloc.h>
/*
- * We allocate runtime services regions bottom-up, starting from -4G, i.e.
+ * We allocate runtime services regions top-down, starting from -4G, i.e.
* 0xffff_ffff_0000_0000 and limit EFI VA mapping space to 64G.
*/
static u64 efi_va = EFI_VA_START;
#include <linux/bootmem.h>
#include <linux/acpi.h>
#include <linux/dmi.h>
+
+#include <asm/e820/api.h>
#include <asm/efi.h>
#include <asm/uv/uv.h>
return;
}
+ /* No need to reserve regions that will never be freed. */
+ if (md.attribute & EFI_MEMORY_RUNTIME)
+ return;
+
size += addr % EFI_PAGE_SIZE;
size = round_up(size, EFI_PAGE_SIZE);
addr = round_down(addr, EFI_PAGE_SIZE);
* else. We must only reserve (and then free) regions:
*
* - Not within any part of the kernel
- * - Not the BIOS reserved area (E820_RESERVED, E820_NVS, etc)
+ * - Not the BIOS reserved area (E820_TYPE_RESERVED, E820_TYPE_NVS, etc)
*/
static bool can_free_region(u64 start, u64 size)
{
if (start + size > __pa_symbol(_text) && start <= __pa_symbol(_end))
return false;
- if (!e820_all_mapped(start, start+size, E820_RAM))
+ if (!e820__mapped_all(start, start+size, E820_TYPE_RAM))
return false;
return true;
* A good example of a critical region that must not be
* freed is page zero (first 4Kb of memory), which may
* contain boot services code/data but is marked
- * E820_RESERVED by trim_bios_range().
+ * E820_TYPE_RESERVED by trim_bios_range().
*/
if (!already_reserved) {
memblock_reserve(start, size);
clock_event_device_uv.min_delta_ns = NSEC_PER_SEC /
sn_rtc_cycles_per_second;
+ clock_event_device_uv.min_delta_ticks = 1;
clock_event_device_uv.max_delta_ns = clocksource_uv.mask *
(NSEC_PER_SEC / sn_rtc_cycles_per_second);
+ clock_event_device_uv.max_delta_ticks = clocksource_uv.mask;
rc = schedule_on_each_cpu(uv_rtc_register_clockevents);
if (rc) {
#include <crypto/hash.h>
+#include <asm/e820/api.h>
#include <asm/init.h>
#include <asm/proto.h>
#include <asm/page.h>
#if IS_BUILTIN(CONFIG_CRYPTO_MD5)
/**
- * get_e820_md5 - calculate md5 according to given e820 map
+ * get_e820_md5 - calculate md5 according to given e820 table
*
- * @map: the e820 map to be calculated
+ * @table: the e820 table to be calculated
* @buf: the md5 result to be stored to
*/
-static int get_e820_md5(struct e820map *map, void *buf)
+static int get_e820_md5(struct e820_table *table, void *buf)
{
struct scatterlist sg;
struct crypto_ahash *tfm;
{
AHASH_REQUEST_ON_STACK(req, tfm);
- size = offsetof(struct e820map, map)
- + sizeof(struct e820entry) * map->nr_map;
+ size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry) * table->nr_entries;
ahash_request_set_tfm(req, tfm);
- sg_init_one(&sg, (u8 *)map, size);
+ sg_init_one(&sg, (u8 *)table, size);
ahash_request_set_callback(req, 0, NULL, NULL);
ahash_request_set_crypt(req, &sg, buf, size);
static void hibernation_e820_save(void *buf)
{
- get_e820_md5(e820_saved, buf);
+ get_e820_md5(e820_table_firmware, buf);
}
static bool hibernation_e820_mismatch(void *buf)
if (!memcmp(result, buf, MD5_DIGEST_SIZE))
return false;
- ret = get_e820_md5(e820_saved, result);
+ ret = get_e820_md5(e820_table_firmware, result);
if (ret)
return true;
aspects of the MCE handling code.
WARNING: Do not even assume this interface is staying stable!
+
+config RAS_CEC
+ bool "Correctable Errors Collector"
+ depends on X86_MCE && MEMORY_FAILURE && DEBUG_FS
+ ---help---
+ This is a small cache which collects correctable memory errors per 4K
+ page PFN and counts their repeated occurrence. Once the counter for a
+ PFN overflows, we try to soft-offline that page as we take it to mean
+ that it has reached a relatively high error count and would probably
+ be best if we don't use it anymore.
+
+ Bear in mind that this is absolutely useless if your platform doesn't
+ have ECC DIMMs and doesn't have DRAM ECC checking enabled in the BIOS.
+
ifeq ($(CONFIG_X86_32),y)
-obj-y += checksum_32.o
+obj-y += checksum_32.o syscalls_32.o
obj-$(CONFIG_ELF_CORE) += elfcore.o
subarch-y = ../lib/string_32.o ../lib/atomic64_32.o ../lib/atomic64_cx8_32.o
return -ENOSYS;
}
-extern long arch_prctl(struct task_struct *task, int code,
+extern long arch_prctl(struct task_struct *task, int option,
unsigned long __user *addr);
#endif
#include <sys/ptrace.h>
#include <asm/ptrace.h>
-int os_arch_prctl(int pid, int code, unsigned long *addr)
+int os_arch_prctl(int pid, int option, unsigned long *arg2)
{
- return ptrace(PTRACE_ARCH_PRCTL, pid, (unsigned long) addr, code);
+ return ptrace(PTRACE_ARCH_PRCTL, pid, (unsigned long) arg2, option);
}
--- /dev/null
+#include <linux/syscalls.h>
+#include <os.h>
+
+SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
+{
+ return -EINVAL;
+}
#include <linux/sched.h>
#include <linux/sched/mm.h>
+#include <linux/syscalls.h>
#include <linux/uaccess.h>
#include <asm/prctl.h> /* XXX This should get the constants from libc */
#include <os.h>
-long arch_prctl(struct task_struct *task, int code, unsigned long __user *addr)
+long arch_prctl(struct task_struct *task, int option,
+ unsigned long __user *arg2)
{
- unsigned long *ptr = addr, tmp;
+ unsigned long *ptr = arg2, tmp;
long ret;
int pid = task->mm->context.id.u.pid;
* arch_prctl is run on the host, then the registers are read
* back.
*/
- switch (code) {
+ switch (option) {
case ARCH_SET_FS:
case ARCH_SET_GS:
ret = restore_registers(pid, ¤t->thread.regs.regs);
ptr = &tmp;
}
- ret = os_arch_prctl(pid, code, ptr);
+ ret = os_arch_prctl(pid, option, ptr);
if (ret)
return ret;
- switch (code) {
+ switch (option) {
case ARCH_SET_FS:
current->thread.arch.fs = (unsigned long) ptr;
ret = save_registers(pid, ¤t->thread.regs.regs);
ret = save_registers(pid, ¤t->thread.regs.regs);
break;
case ARCH_GET_FS:
- ret = put_user(tmp, addr);
+ ret = put_user(tmp, arg2);
break;
case ARCH_GET_GS:
- ret = put_user(tmp, addr);
+ ret = put_user(tmp, arg2);
break;
}
return ret;
}
-long sys_arch_prctl(int code, unsigned long addr)
+SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
{
- return arch_prctl(current, code, (unsigned long __user *) addr);
+ return arch_prctl(current, option, (unsigned long __user *) arg2);
}
void arch_switch_to(struct task_struct *to)
#include <asm/mwait.h>
#include <asm/pci_x86.h>
#include <asm/cpu.h>
+#include <asm/e820/api.h>
#ifdef CONFIG_ACPI
#include <linux/acpi.h>
memset(&pvh_bootparams, 0, sizeof(pvh_bootparams));
- memmap.nr_entries = ARRAY_SIZE(pvh_bootparams.e820_map);
- set_xen_guest_handle(memmap.buffer, pvh_bootparams.e820_map);
+ memmap.nr_entries = ARRAY_SIZE(pvh_bootparams.e820_table);
+ set_xen_guest_handle(memmap.buffer, pvh_bootparams.e820_table);
rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap);
if (rc) {
xen_raw_printk("XENMEM_memory_map failed (%d)\n", rc);
BUG();
}
- if (memmap.nr_entries < E820MAX - 1) {
- pvh_bootparams.e820_map[memmap.nr_entries].addr =
+ if (memmap.nr_entries < E820_MAX_ENTRIES_ZEROPAGE - 1) {
+ pvh_bootparams.e820_table[memmap.nr_entries].addr =
ISA_START_ADDRESS;
- pvh_bootparams.e820_map[memmap.nr_entries].size =
+ pvh_bootparams.e820_table[memmap.nr_entries].size =
ISA_END_ADDRESS - ISA_START_ADDRESS;
- pvh_bootparams.e820_map[memmap.nr_entries].type =
- E820_RESERVED;
+ pvh_bootparams.e820_table[memmap.nr_entries].type =
+ E820_TYPE_RESERVED;
memmap.nr_entries++;
} else
xen_raw_printk("Warning: Can fit ISA range into e820\n");
- sanitize_e820_map(pvh_bootparams.e820_map,
- ARRAY_SIZE(pvh_bootparams.e820_map),
- &memmap.nr_entries);
-
pvh_bootparams.e820_entries = memmap.nr_entries;
for (i = 0; i < pvh_bootparams.e820_entries; i++)
- e820_add_region(pvh_bootparams.e820_map[i].addr,
- pvh_bootparams.e820_map[i].size,
- pvh_bootparams.e820_map[i].type);
+ e820__range_add(pvh_bootparams.e820_table[i].addr,
+ pvh_bootparams.e820_table[i].size,
+ pvh_bootparams.e820_table[i].type);
+
+ e820__update_table(e820_table);
pvh_bootparams.hdr.cmd_line_ptr =
pvh_start_info.cmdline_paddr;
#include <asm/mmu_context.h>
#include <asm/setup.h>
#include <asm/paravirt.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/linkage.h>
#include <asm/page.h>
#include <asm/init.h>
#include <asm/elf.h>
#include <asm/vdso.h>
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/setup.h>
#include <asm/acpi.h>
#include <asm/numa.h>
unsigned long xen_released_pages;
/* E820 map used during setting up memory. */
-static struct e820entry xen_e820_map[E820_X_MAX] __initdata;
-static u32 xen_e820_map_entries __initdata;
+static struct e820_table xen_e820_table __initdata;
/*
* Buffer used to remap identity mapped pages. We only need the virtual space.
*/
static unsigned long __init xen_find_pfn_range(unsigned long *min_pfn)
{
- const struct e820entry *entry = xen_e820_map;
+ const struct e820_entry *entry = xen_e820_table.entries;
unsigned int i;
unsigned long done = 0;
- for (i = 0; i < xen_e820_map_entries; i++, entry++) {
+ for (i = 0; i < xen_e820_table.nr_entries; i++, entry++) {
unsigned long s_pfn;
unsigned long e_pfn;
- if (entry->type != E820_RAM)
+ if (entry->type != E820_TYPE_RAM)
continue;
e_pfn = PFN_DOWN(entry->addr + entry->size);
{
phys_addr_t start = 0;
unsigned long ret_val = 0;
- const struct e820entry *entry = xen_e820_map;
+ const struct e820_entry *entry = xen_e820_table.entries;
int i;
/*
* example) the DMI tables in a reserved region that begins on
* a non-page boundary.
*/
- for (i = 0; i < xen_e820_map_entries; i++, entry++) {
+ for (i = 0; i < xen_e820_table.nr_entries; i++, entry++) {
phys_addr_t end = entry->addr + entry->size;
- if (entry->type == E820_RAM || i == xen_e820_map_entries - 1) {
+ if (entry->type == E820_TYPE_RAM || i == xen_e820_table.nr_entries - 1) {
unsigned long start_pfn = PFN_DOWN(start);
unsigned long end_pfn = PFN_UP(end);
- if (entry->type == E820_RAM)
+ if (entry->type == E820_TYPE_RAM)
end_pfn = PFN_UP(entry->addr);
if (start_pfn < end_pfn)
phys_addr_t end = start + size;
/* Align RAM regions to page boundaries. */
- if (type == E820_RAM) {
+ if (type == E820_TYPE_RAM) {
start = PAGE_ALIGN(start);
end &= ~((phys_addr_t)PAGE_SIZE - 1);
}
- e820_add_region(start, end - start, type);
+ e820__range_add(start, end - start, type);
}
static void __init xen_ignore_unusable(void)
{
- struct e820entry *entry = xen_e820_map;
+ struct e820_entry *entry = xen_e820_table.entries;
unsigned int i;
- for (i = 0; i < xen_e820_map_entries; i++, entry++) {
- if (entry->type == E820_UNUSABLE)
- entry->type = E820_RAM;
+ for (i = 0; i < xen_e820_table.nr_entries; i++, entry++) {
+ if (entry->type == E820_TYPE_UNUSABLE)
+ entry->type = E820_TYPE_RAM;
}
}
bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size)
{
- struct e820entry *entry;
+ struct e820_entry *entry;
unsigned mapcnt;
phys_addr_t end;
return false;
end = start + size;
- entry = xen_e820_map;
+ entry = xen_e820_table.entries;
- for (mapcnt = 0; mapcnt < xen_e820_map_entries; mapcnt++) {
- if (entry->type == E820_RAM && entry->addr <= start &&
+ for (mapcnt = 0; mapcnt < xen_e820_table.nr_entries; mapcnt++) {
+ if (entry->type == E820_TYPE_RAM && entry->addr <= start &&
(entry->addr + entry->size) >= end)
return false;
{
unsigned mapcnt;
phys_addr_t addr, start;
- struct e820entry *entry = xen_e820_map;
+ struct e820_entry *entry = xen_e820_table.entries;
- for (mapcnt = 0; mapcnt < xen_e820_map_entries; mapcnt++, entry++) {
- if (entry->type != E820_RAM || entry->size < size)
+ for (mapcnt = 0; mapcnt < xen_e820_table.nr_entries; mapcnt++, entry++) {
+ if (entry->type != E820_TYPE_RAM || entry->size < size)
continue;
start = entry->addr;
for (addr = start; addr < start + size; addr += PAGE_SIZE) {
max_pfn = min(max_pfn, xen_start_info->nr_pages);
mem_end = PFN_PHYS(max_pfn);
- memmap.nr_entries = ARRAY_SIZE(xen_e820_map);
- set_xen_guest_handle(memmap.buffer, xen_e820_map);
+ memmap.nr_entries = ARRAY_SIZE(xen_e820_table.entries);
+ set_xen_guest_handle(memmap.buffer, xen_e820_table.entries);
op = xen_initial_domain() ?
XENMEM_machine_memory_map :
if (rc == -ENOSYS) {
BUG_ON(xen_initial_domain());
memmap.nr_entries = 1;
- xen_e820_map[0].addr = 0ULL;
- xen_e820_map[0].size = mem_end;
+ xen_e820_table.entries[0].addr = 0ULL;
+ xen_e820_table.entries[0].size = mem_end;
/* 8MB slack (to balance backend allocations). */
- xen_e820_map[0].size += 8ULL << 20;
- xen_e820_map[0].type = E820_RAM;
+ xen_e820_table.entries[0].size += 8ULL << 20;
+ xen_e820_table.entries[0].type = E820_TYPE_RAM;
rc = 0;
}
BUG_ON(rc);
BUG_ON(memmap.nr_entries == 0);
- xen_e820_map_entries = memmap.nr_entries;
+ xen_e820_table.nr_entries = memmap.nr_entries;
/*
* Xen won't allow a 1:1 mapping to be created to UNUSABLE
xen_ignore_unusable();
/* Make sure the Xen-supplied memory map is well-ordered. */
- sanitize_e820_map(xen_e820_map, ARRAY_SIZE(xen_e820_map),
- &xen_e820_map_entries);
+ e820__update_table(&xen_e820_table);
max_pages = xen_get_max_pages();
extra_pages = min3(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
extra_pages, max_pages - max_pfn);
i = 0;
- addr = xen_e820_map[0].addr;
- size = xen_e820_map[0].size;
- while (i < xen_e820_map_entries) {
+ addr = xen_e820_table.entries[0].addr;
+ size = xen_e820_table.entries[0].size;
+ while (i < xen_e820_table.nr_entries) {
bool discard = false;
chunk_size = size;
- type = xen_e820_map[i].type;
+ type = xen_e820_table.entries[i].type;
- if (type == E820_RAM) {
+ if (type == E820_TYPE_RAM) {
if (addr < mem_end) {
chunk_size = min(size, mem_end - addr);
} else if (extra_pages) {
size -= chunk_size;
if (size == 0) {
i++;
- if (i < xen_e820_map_entries) {
- addr = xen_e820_map[i].addr;
- size = xen_e820_map[i].size;
+ if (i < xen_e820_table.nr_entries) {
+ addr = xen_e820_table.entries[i].addr;
+ size = xen_e820_table.entries[i].size;
}
}
}
* reserve ISA memory anyway because too many things poke
* about in there.
*/
- e820_add_region(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS,
- E820_RESERVED);
+ e820__range_add(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS, E820_TYPE_RESERVED);
- sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map);
+ e820__update_table(e820_table);
/*
* Check whether the kernel itself conflicts with the target E820 map.
}
/*
+ * Machine specific memory setup for auto-translated guests.
+ */
+char * __init xen_auto_xlated_memory_setup(void)
+{
+ struct xen_memory_map memmap;
+ int i;
+ int rc;
+
+ memmap.nr_entries = ARRAY_SIZE(xen_e820_table.entries);
+ set_xen_guest_handle(memmap.buffer, xen_e820_table.entries);
+
+ rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap);
+ if (rc < 0)
+ panic("No memory map (%d)\n", rc);
+
+ xen_e820_table.nr_entries = memmap.nr_entries;
+
+ e820__update_table(&xen_e820_table);
+
+ for (i = 0; i < xen_e820_table.nr_entries; i++)
+ e820__range_add(xen_e820_table.entries[i].addr, xen_e820_table.entries[i].size, xen_e820_table.entries[i].type);
+
+ /* Remove p2m info, it is not needed. */
+ xen_start_info->mfn_list = 0;
+ xen_start_info->first_p2m_pfn = 0;
+ xen_start_info->nr_p2m_frames = 0;
+
+ return "Xen";
+}
+
+/*
* Set the bit indicating "nosegneg" library variants should be used.
* We only need to bother in pure 32-bit mode; compat 32-bit processes
* can have un-truncated segments, so wrapping around is allowed.
void __init xen_arch_setup(void)
{
xen_panic_handler_init();
-
- xen_pvmmu_arch_setup();
+ if (!xen_feature(XENFEAT_auto_translated_physmap))
+ xen_pvmmu_arch_setup();
#ifdef CONFIG_ACPI
if (!(xen_start_info->flags & SIF_INITDOMAIN)) {
.features = CLOCK_EVT_FEAT_ONESHOT,
.max_delta_ns = 0xffffffff,
+ .max_delta_ticks = 0xffffffff,
.min_delta_ns = TIMER_SLOP,
+ .min_delta_ticks = TIMER_SLOP,
.mult = 1,
.shift = 0,
.features = CLOCK_EVT_FEAT_ONESHOT,
.max_delta_ns = 0xffffffff,
+ .max_delta_ticks = 0xffffffff,
.min_delta_ns = TIMER_SLOP,
+ .min_delta_ticks = TIMER_SLOP,
.mult = 1,
.shift = 0,
generic-y += emergency-restart.h
generic-y += errno.h
generic-y += exec.h
+generic-y += extable.h
generic-y += fcntl.h
generic-y += hardirq.h
generic-y += ioctl.h
#include <linux/errno.h>
#include <asm/types.h>
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
#include <asm/current.h>
#include <asm/asm-offsets.h>
#include <asm/processor.h>
#ifndef _XTENSA_UACCESS_H
#define _XTENSA_UACCESS_H
-#include <linux/errno.h>
#include <linux/prefetch.h>
#include <asm/types.h>
-
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
-#include <linux/sched.h>
+#include <asm/extable.h>
/*
* The fs value determines whether argument validity checking should
#define segment_eq(a, b) ((a).seg == (b).seg)
-#define __kernel_ok (segment_eq(get_fs(), KERNEL_DS))
+#define __kernel_ok (uaccess_kernel())
#define __user_ok(addr, size) \
(((size) <= TASK_SIZE)&&((addr) <= TASK_SIZE-(size)))
#define __access_ok(addr, size) (__kernel_ok || __user_ok((addr), (size)))
* Copy to/from user space
*/
-/*
- * We use a generic, arbitrary-sized copy subroutine. The Xtensa
- * architecture would cause heavy code bloat if we tried to inline
- * these functions and provide __constant_copy_* equivalents like the
- * i386 versions. __xtensa_copy_user is quite efficient. See the
- * .fixup section of __xtensa_copy_user for a discussion on the
- * X_zeroing equivalents for Xtensa.
- */
-
extern unsigned __xtensa_copy_user(void *to, const void *from, unsigned n);
-#define __copy_user(to, from, size) __xtensa_copy_user(to, from, size)
-
static inline unsigned long
-__generic_copy_from_user_nocheck(void *to, const void *from, unsigned long n)
+raw_copy_from_user(void *to, const void __user *from, unsigned long n)
{
- return __copy_user(to, from, n);
-}
-
-static inline unsigned long
-__generic_copy_to_user_nocheck(void *to, const void *from, unsigned long n)
-{
- return __copy_user(to, from, n);
+ prefetchw(to);
+ return __xtensa_copy_user(to, (__force const void *)from, n);
}
-
static inline unsigned long
-__generic_copy_to_user(void *to, const void *from, unsigned long n)
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
{
prefetch(from);
- if (access_ok(VERIFY_WRITE, to, n))
- return __copy_user(to, from, n);
- return n;
-}
-
-static inline unsigned long
-__generic_copy_from_user(void *to, const void *from, unsigned long n)
-{
- prefetchw(to);
- if (access_ok(VERIFY_READ, from, n))
- return __copy_user(to, from, n);
- else
- memset(to, 0, n);
- return n;
+ return __xtensa_copy_user((__force void *)to, from, n);
}
-
-#define copy_to_user(to, from, n) __generic_copy_to_user((to), (from), (n))
-#define copy_from_user(to, from, n) __generic_copy_from_user((to), (from), (n))
-#define __copy_to_user(to, from, n) \
- __generic_copy_to_user_nocheck((to), (from), (n))
-#define __copy_from_user(to, from, n) \
- __generic_copy_from_user_nocheck((to), (from), (n))
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
-
+#define INLINE_COPY_FROM_USER
+#define INLINE_COPY_TO_USER
/*
* We need to return the number of bytes not cleared. Our memset()
return __strnlen_user(str, len);
}
-
-struct exception_table_entry
-{
- unsigned long insn, fixup;
-};
-
#endif /* _XTENSA_UACCESS_H */
bltui a4, 7, .Lbytecopy # do short copies byte by byte
# copy 1 byte
- EX(l8ui, a6, a3, 0, l_fixup)
+ EX(l8ui, a6, a3, 0, fixup)
addi a3, a3, 1
- EX(s8i, a6, a5, 0, s_fixup)
+ EX(s8i, a6, a5, 0, fixup)
addi a5, a5, 1
addi a4, a4, -1
bbci.l a5, 1, .Ldstaligned # if dst is now aligned, then
.Ldst2mod4: # dst 16-bit aligned
# copy 2 bytes
bltui a4, 6, .Lbytecopy # do short copies byte by byte
- EX(l8ui, a6, a3, 0, l_fixup)
- EX(l8ui, a7, a3, 1, l_fixup)
+ EX(l8ui, a6, a3, 0, fixup)
+ EX(l8ui, a7, a3, 1, fixup)
addi a3, a3, 2
- EX(s8i, a6, a5, 0, s_fixup)
- EX(s8i, a7, a5, 1, s_fixup)
+ EX(s8i, a6, a5, 0, fixup)
+ EX(s8i, a7, a5, 1, fixup)
addi a5, a5, 2
addi a4, a4, -2
j .Ldstaligned # dst is now aligned, return to main algorithm
add a7, a3, a4 # a7 = end address for source
#endif /* !XCHAL_HAVE_LOOPS */
.Lnextbyte:
- EX(l8ui, a6, a3, 0, l_fixup)
+ EX(l8ui, a6, a3, 0, fixup)
addi a3, a3, 1
- EX(s8i, a6, a5, 0, s_fixup)
+ EX(s8i, a6, a5, 0, fixup)
addi a5, a5, 1
#if !XCHAL_HAVE_LOOPS
blt a3, a7, .Lnextbyte
add a8, a8, a3 # a8 = end of last 16B source chunk
#endif /* !XCHAL_HAVE_LOOPS */
.Loop1:
- EX(l32i, a6, a3, 0, l_fixup)
- EX(l32i, a7, a3, 4, l_fixup)
- EX(s32i, a6, a5, 0, s_fixup)
- EX(l32i, a6, a3, 8, l_fixup)
- EX(s32i, a7, a5, 4, s_fixup)
- EX(l32i, a7, a3, 12, l_fixup)
- EX(s32i, a6, a5, 8, s_fixup)
+ EX(l32i, a6, a3, 0, fixup)
+ EX(l32i, a7, a3, 4, fixup)
+ EX(s32i, a6, a5, 0, fixup)
+ EX(l32i, a6, a3, 8, fixup)
+ EX(s32i, a7, a5, 4, fixup)
+ EX(l32i, a7, a3, 12, fixup)
+ EX(s32i, a6, a5, 8, fixup)
addi a3, a3, 16
- EX(s32i, a7, a5, 12, s_fixup)
+ EX(s32i, a7, a5, 12, fixup)
addi a5, a5, 16
#if !XCHAL_HAVE_LOOPS
blt a3, a8, .Loop1
.Loop1done:
bbci.l a4, 3, .L2
# copy 8 bytes
- EX(l32i, a6, a3, 0, l_fixup)
- EX(l32i, a7, a3, 4, l_fixup)
+ EX(l32i, a6, a3, 0, fixup)
+ EX(l32i, a7, a3, 4, fixup)
addi a3, a3, 8
- EX(s32i, a6, a5, 0, s_fixup)
- EX(s32i, a7, a5, 4, s_fixup)
+ EX(s32i, a6, a5, 0, fixup)
+ EX(s32i, a7, a5, 4, fixup)
addi a5, a5, 8
.L2:
bbci.l a4, 2, .L3
# copy 4 bytes
- EX(l32i, a6, a3, 0, l_fixup)
+ EX(l32i, a6, a3, 0, fixup)
addi a3, a3, 4
- EX(s32i, a6, a5, 0, s_fixup)
+ EX(s32i, a6, a5, 0, fixup)
addi a5, a5, 4
.L3:
bbci.l a4, 1, .L4
# copy 2 bytes
- EX(l16ui, a6, a3, 0, l_fixup)
+ EX(l16ui, a6, a3, 0, fixup)
addi a3, a3, 2
- EX(s16i, a6, a5, 0, s_fixup)
+ EX(s16i, a6, a5, 0, fixup)
addi a5, a5, 2
.L4:
bbci.l a4, 0, .L5
# copy 1 byte
- EX(l8ui, a6, a3, 0, l_fixup)
- EX(s8i, a6, a5, 0, s_fixup)
+ EX(l8ui, a6, a3, 0, fixup)
+ EX(s8i, a6, a5, 0, fixup)
.L5:
movi a2, 0 # return success for len bytes copied
retw
# copy 16 bytes per iteration for word-aligned dst and unaligned src
and a10, a3, a8 # save unalignment offset for below
sub a3, a3, a10 # align a3 (to avoid sim warnings only; not needed for hardware)
- EX(l32i, a6, a3, 0, l_fixup) # load first word
+ EX(l32i, a6, a3, 0, fixup) # load first word
#if XCHAL_HAVE_LOOPS
loopnez a7, .Loop2done
#else /* !XCHAL_HAVE_LOOPS */
add a12, a12, a3 # a12 = end of last 16B source chunk
#endif /* !XCHAL_HAVE_LOOPS */
.Loop2:
- EX(l32i, a7, a3, 4, l_fixup)
- EX(l32i, a8, a3, 8, l_fixup)
+ EX(l32i, a7, a3, 4, fixup)
+ EX(l32i, a8, a3, 8, fixup)
ALIGN( a6, a6, a7)
- EX(s32i, a6, a5, 0, s_fixup)
- EX(l32i, a9, a3, 12, l_fixup)
+ EX(s32i, a6, a5, 0, fixup)
+ EX(l32i, a9, a3, 12, fixup)
ALIGN( a7, a7, a8)
- EX(s32i, a7, a5, 4, s_fixup)
- EX(l32i, a6, a3, 16, l_fixup)
+ EX(s32i, a7, a5, 4, fixup)
+ EX(l32i, a6, a3, 16, fixup)
ALIGN( a8, a8, a9)
- EX(s32i, a8, a5, 8, s_fixup)
+ EX(s32i, a8, a5, 8, fixup)
addi a3, a3, 16
ALIGN( a9, a9, a6)
- EX(s32i, a9, a5, 12, s_fixup)
+ EX(s32i, a9, a5, 12, fixup)
addi a5, a5, 16
#if !XCHAL_HAVE_LOOPS
blt a3, a12, .Loop2
.Loop2done:
bbci.l a4, 3, .L12
# copy 8 bytes
- EX(l32i, a7, a3, 4, l_fixup)
- EX(l32i, a8, a3, 8, l_fixup)
+ EX(l32i, a7, a3, 4, fixup)
+ EX(l32i, a8, a3, 8, fixup)
ALIGN( a6, a6, a7)
- EX(s32i, a6, a5, 0, s_fixup)
+ EX(s32i, a6, a5, 0, fixup)
addi a3, a3, 8
ALIGN( a7, a7, a8)
- EX(s32i, a7, a5, 4, s_fixup)
+ EX(s32i, a7, a5, 4, fixup)
addi a5, a5, 8
mov a6, a8
.L12:
bbci.l a4, 2, .L13
# copy 4 bytes
- EX(l32i, a7, a3, 4, l_fixup)
+ EX(l32i, a7, a3, 4, fixup)
addi a3, a3, 4
ALIGN( a6, a6, a7)
- EX(s32i, a6, a5, 0, s_fixup)
+ EX(s32i, a6, a5, 0, fixup)
addi a5, a5, 4
mov a6, a7
.L13:
add a3, a3, a10 # readjust a3 with correct misalignment
bbci.l a4, 1, .L14
# copy 2 bytes
- EX(l8ui, a6, a3, 0, l_fixup)
- EX(l8ui, a7, a3, 1, l_fixup)
+ EX(l8ui, a6, a3, 0, fixup)
+ EX(l8ui, a7, a3, 1, fixup)
addi a3, a3, 2
- EX(s8i, a6, a5, 0, s_fixup)
- EX(s8i, a7, a5, 1, s_fixup)
+ EX(s8i, a6, a5, 0, fixup)
+ EX(s8i, a7, a5, 1, fixup)
addi a5, a5, 2
.L14:
bbci.l a4, 0, .L15
# copy 1 byte
- EX(l8ui, a6, a3, 0, l_fixup)
- EX(s8i, a6, a5, 0, s_fixup)
+ EX(l8ui, a6, a3, 0, fixup)
+ EX(s8i, a6, a5, 0, fixup)
.L15:
movi a2, 0 # return success for len bytes copied
retw
* bytes_copied = a5 - a2
* retval = bytes_not_copied = original len - bytes_copied
* retval = a11 - (a5 - a2)
- *
- * Clearing the remaining pieces of kernel memory plugs security
- * holes. This functionality is the equivalent of the *_zeroing
- * functions that some architectures provide.
*/
-.Lmemset:
- .word memset
-s_fixup:
+fixup:
sub a2, a5, a2 /* a2 <-- bytes copied */
sub a2, a11, a2 /* a2 <-- bytes not copied */
retw
-
-l_fixup:
- sub a2, a5, a2 /* a2 <-- bytes copied */
- sub a2, a11, a2 /* a2 <-- bytes not copied == return value */
-
- /* void *memset(void *s, int c, size_t n); */
- mov a6, a5 /* s */
- movi a7, 0 /* c */
- mov a8, a2 /* n */
- l32r a4, .Lmemset
- callx4 a4
- /* Ignore memset return value in a6. */
- /* a2 still contains bytes not copied. */
- retw
See Documentation/cgroups/blkio-controller.txt for more information.
+config BLK_DEV_THROTTLING_LOW
+ bool "Block throttling .low limit interface support (EXPERIMENTAL)"
+ depends on BLK_DEV_THROTTLING
+ default n
+ ---help---
+ Add .low limit interface for block throttling. The low limit is a best
+ effort limit to prioritize cgroups. Depending on the setting, the limit
+ can be used to protect cgroups in terms of bandwidth/iops and better
+ utilize disk resource.
+
+ Note, this is an experimental interface and could be changed someday.
+
config BLK_CMDLINE_PARSER
bool "Block device command line partition parser"
default n
Enable group IO scheduling in CFQ.
choice
+
prompt "Default I/O scheduler"
default DEFAULT_CFQ
help
---help---
MQ version of the deadline IO scheduler.
+config MQ_IOSCHED_KYBER
+ tristate "Kyber I/O scheduler"
+ default y
+ ---help---
+ The Kyber I/O scheduler is a low-overhead scheduler suitable for
+ multiqueue and other fast devices. Given target latencies for reads and
+ synchronous writes, it will self-tune queue depths to achieve that
+ goal.
+
+config IOSCHED_BFQ
+ tristate "BFQ I/O scheduler"
+ default n
+ ---help---
+ BFQ I/O scheduler for BLK-MQ. BFQ distributes the bandwidth of
+ of the device among all processes according to their weights,
+ regardless of the device parameters and with any workload. It
+ also guarantees a low latency to interactive and soft
+ real-time applications. Details in
+ Documentation/block/bfq-iosched.txt
+
+config BFQ_GROUP_IOSCHED
+ bool "BFQ hierarchical scheduling support"
+ depends on IOSCHED_BFQ && BLK_CGROUP
+ default n
+ ---help---
+
+ Enable hierarchical scheduling in BFQ, using the blkio
+ (cgroups-v1) or io (cgroups-v2) controller.
+
endmenu
endif
obj-$(CONFIG_IOSCHED_DEADLINE) += deadline-iosched.o
obj-$(CONFIG_IOSCHED_CFQ) += cfq-iosched.o
obj-$(CONFIG_MQ_IOSCHED_DEADLINE) += mq-deadline.o
+obj-$(CONFIG_MQ_IOSCHED_KYBER) += kyber-iosched.o
+bfq-y := bfq-iosched.o bfq-wf2q.o bfq-cgroup.o
+obj-$(CONFIG_IOSCHED_BFQ) += bfq.o
obj-$(CONFIG_BLOCK_COMPAT) += compat_ioctl.o
obj-$(CONFIG_BLK_CMDLINE_PARSER) += cmdline-parser.o
--- /dev/null
+/*
+ * cgroups support for the BFQ I/O scheduler.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/blkdev.h>
+#include <linux/cgroup.h>
+#include <linux/elevator.h>
+#include <linux/ktime.h>
+#include <linux/rbtree.h>
+#include <linux/ioprio.h>
+#include <linux/sbitmap.h>
+#include <linux/delay.h>
+
+#include "bfq-iosched.h"
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+
+/* bfqg stats flags */
+enum bfqg_stats_flags {
+ BFQG_stats_waiting = 0,
+ BFQG_stats_idling,
+ BFQG_stats_empty,
+};
+
+#define BFQG_FLAG_FNS(name) \
+static void bfqg_stats_mark_##name(struct bfqg_stats *stats) \
+{ \
+ stats->flags |= (1 << BFQG_stats_##name); \
+} \
+static void bfqg_stats_clear_##name(struct bfqg_stats *stats) \
+{ \
+ stats->flags &= ~(1 << BFQG_stats_##name); \
+} \
+static int bfqg_stats_##name(struct bfqg_stats *stats) \
+{ \
+ return (stats->flags & (1 << BFQG_stats_##name)) != 0; \
+} \
+
+BFQG_FLAG_FNS(waiting)
+BFQG_FLAG_FNS(idling)
+BFQG_FLAG_FNS(empty)
+#undef BFQG_FLAG_FNS
+
+/* This should be called with the queue_lock held. */
+static void bfqg_stats_update_group_wait_time(struct bfqg_stats *stats)
+{
+ unsigned long long now;
+
+ if (!bfqg_stats_waiting(stats))
+ return;
+
+ now = sched_clock();
+ if (time_after64(now, stats->start_group_wait_time))
+ blkg_stat_add(&stats->group_wait_time,
+ now - stats->start_group_wait_time);
+ bfqg_stats_clear_waiting(stats);
+}
+
+/* This should be called with the queue_lock held. */
+static void bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg,
+ struct bfq_group *curr_bfqg)
+{
+ struct bfqg_stats *stats = &bfqg->stats;
+
+ if (bfqg_stats_waiting(stats))
+ return;
+ if (bfqg == curr_bfqg)
+ return;
+ stats->start_group_wait_time = sched_clock();
+ bfqg_stats_mark_waiting(stats);
+}
+
+/* This should be called with the queue_lock held. */
+static void bfqg_stats_end_empty_time(struct bfqg_stats *stats)
+{
+ unsigned long long now;
+
+ if (!bfqg_stats_empty(stats))
+ return;
+
+ now = sched_clock();
+ if (time_after64(now, stats->start_empty_time))
+ blkg_stat_add(&stats->empty_time,
+ now - stats->start_empty_time);
+ bfqg_stats_clear_empty(stats);
+}
+
+void bfqg_stats_update_dequeue(struct bfq_group *bfqg)
+{
+ blkg_stat_add(&bfqg->stats.dequeue, 1);
+}
+
+void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg)
+{
+ struct bfqg_stats *stats = &bfqg->stats;
+
+ if (blkg_rwstat_total(&stats->queued))
+ return;
+
+ /*
+ * group is already marked empty. This can happen if bfqq got new
+ * request in parent group and moved to this group while being added
+ * to service tree. Just ignore the event and move on.
+ */
+ if (bfqg_stats_empty(stats))
+ return;
+
+ stats->start_empty_time = sched_clock();
+ bfqg_stats_mark_empty(stats);
+}
+
+void bfqg_stats_update_idle_time(struct bfq_group *bfqg)
+{
+ struct bfqg_stats *stats = &bfqg->stats;
+
+ if (bfqg_stats_idling(stats)) {
+ unsigned long long now = sched_clock();
+
+ if (time_after64(now, stats->start_idle_time))
+ blkg_stat_add(&stats->idle_time,
+ now - stats->start_idle_time);
+ bfqg_stats_clear_idling(stats);
+ }
+}
+
+void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg)
+{
+ struct bfqg_stats *stats = &bfqg->stats;
+
+ stats->start_idle_time = sched_clock();
+ bfqg_stats_mark_idling(stats);
+}
+
+void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg)
+{
+ struct bfqg_stats *stats = &bfqg->stats;
+
+ blkg_stat_add(&stats->avg_queue_size_sum,
+ blkg_rwstat_total(&stats->queued));
+ blkg_stat_add(&stats->avg_queue_size_samples, 1);
+ bfqg_stats_update_group_wait_time(stats);
+}
+
+/*
+ * blk-cgroup policy-related handlers
+ * The following functions help in converting between blk-cgroup
+ * internal structures and BFQ-specific structures.
+ */
+
+static struct bfq_group *pd_to_bfqg(struct blkg_policy_data *pd)
+{
+ return pd ? container_of(pd, struct bfq_group, pd) : NULL;
+}
+
+struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg)
+{
+ return pd_to_blkg(&bfqg->pd);
+}
+
+static struct bfq_group *blkg_to_bfqg(struct blkcg_gq *blkg)
+{
+ return pd_to_bfqg(blkg_to_pd(blkg, &blkcg_policy_bfq));
+}
+
+/*
+ * bfq_group handlers
+ * The following functions help in navigating the bfq_group hierarchy
+ * by allowing to find the parent of a bfq_group or the bfq_group
+ * associated to a bfq_queue.
+ */
+
+static struct bfq_group *bfqg_parent(struct bfq_group *bfqg)
+{
+ struct blkcg_gq *pblkg = bfqg_to_blkg(bfqg)->parent;
+
+ return pblkg ? blkg_to_bfqg(pblkg) : NULL;
+}
+
+struct bfq_group *bfqq_group(struct bfq_queue *bfqq)
+{
+ struct bfq_entity *group_entity = bfqq->entity.parent;
+
+ return group_entity ? container_of(group_entity, struct bfq_group,
+ entity) :
+ bfqq->bfqd->root_group;
+}
+
+/*
+ * The following two functions handle get and put of a bfq_group by
+ * wrapping the related blk-cgroup hooks.
+ */
+
+static void bfqg_get(struct bfq_group *bfqg)
+{
+ return blkg_get(bfqg_to_blkg(bfqg));
+}
+
+void bfqg_put(struct bfq_group *bfqg)
+{
+ return blkg_put(bfqg_to_blkg(bfqg));
+}
+
+void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
+ unsigned int op)
+{
+ blkg_rwstat_add(&bfqg->stats.queued, op, 1);
+ bfqg_stats_end_empty_time(&bfqg->stats);
+ if (!(bfqq == ((struct bfq_data *)bfqg->bfqd)->in_service_queue))
+ bfqg_stats_set_start_group_wait_time(bfqg, bfqq_group(bfqq));
+}
+
+void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op)
+{
+ blkg_rwstat_add(&bfqg->stats.queued, op, -1);
+}
+
+void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op)
+{
+ blkg_rwstat_add(&bfqg->stats.merged, op, 1);
+}
+
+void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time,
+ uint64_t io_start_time, unsigned int op)
+{
+ struct bfqg_stats *stats = &bfqg->stats;
+ unsigned long long now = sched_clock();
+
+ if (time_after64(now, io_start_time))
+ blkg_rwstat_add(&stats->service_time, op,
+ now - io_start_time);
+ if (time_after64(io_start_time, start_time))
+ blkg_rwstat_add(&stats->wait_time, op,
+ io_start_time - start_time);
+}
+
+/* @stats = 0 */
+static void bfqg_stats_reset(struct bfqg_stats *stats)
+{
+ /* queued stats shouldn't be cleared */
+ blkg_rwstat_reset(&stats->merged);
+ blkg_rwstat_reset(&stats->service_time);
+ blkg_rwstat_reset(&stats->wait_time);
+ blkg_stat_reset(&stats->time);
+ blkg_stat_reset(&stats->avg_queue_size_sum);
+ blkg_stat_reset(&stats->avg_queue_size_samples);
+ blkg_stat_reset(&stats->dequeue);
+ blkg_stat_reset(&stats->group_wait_time);
+ blkg_stat_reset(&stats->idle_time);
+ blkg_stat_reset(&stats->empty_time);
+}
+
+/* @to += @from */
+static void bfqg_stats_add_aux(struct bfqg_stats *to, struct bfqg_stats *from)
+{
+ if (!to || !from)
+ return;
+
+ /* queued stats shouldn't be cleared */
+ blkg_rwstat_add_aux(&to->merged, &from->merged);
+ blkg_rwstat_add_aux(&to->service_time, &from->service_time);
+ blkg_rwstat_add_aux(&to->wait_time, &from->wait_time);
+ blkg_stat_add_aux(&from->time, &from->time);
+ blkg_stat_add_aux(&to->avg_queue_size_sum, &from->avg_queue_size_sum);
+ blkg_stat_add_aux(&to->avg_queue_size_samples,
+ &from->avg_queue_size_samples);
+ blkg_stat_add_aux(&to->dequeue, &from->dequeue);
+ blkg_stat_add_aux(&to->group_wait_time, &from->group_wait_time);
+ blkg_stat_add_aux(&to->idle_time, &from->idle_time);
+ blkg_stat_add_aux(&to->empty_time, &from->empty_time);
+}
+
+/*
+ * Transfer @bfqg's stats to its parent's aux counts so that the ancestors'
+ * recursive stats can still account for the amount used by this bfqg after
+ * it's gone.
+ */
+static void bfqg_stats_xfer_dead(struct bfq_group *bfqg)
+{
+ struct bfq_group *parent;
+
+ if (!bfqg) /* root_group */
+ return;
+
+ parent = bfqg_parent(bfqg);
+
+ lockdep_assert_held(bfqg_to_blkg(bfqg)->q->queue_lock);
+
+ if (unlikely(!parent))
+ return;
+
+ bfqg_stats_add_aux(&parent->stats, &bfqg->stats);
+ bfqg_stats_reset(&bfqg->stats);
+}
+
+void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg)
+{
+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+ entity->weight = entity->new_weight;
+ entity->orig_weight = entity->new_weight;
+ if (bfqq) {
+ bfqq->ioprio = bfqq->new_ioprio;
+ bfqq->ioprio_class = bfqq->new_ioprio_class;
+ bfqg_get(bfqg);
+ }
+ entity->parent = bfqg->my_entity; /* NULL for root group */
+ entity->sched_data = &bfqg->sched_data;
+}
+
+static void bfqg_stats_exit(struct bfqg_stats *stats)
+{
+ blkg_rwstat_exit(&stats->merged);
+ blkg_rwstat_exit(&stats->service_time);
+ blkg_rwstat_exit(&stats->wait_time);
+ blkg_rwstat_exit(&stats->queued);
+ blkg_stat_exit(&stats->time);
+ blkg_stat_exit(&stats->avg_queue_size_sum);
+ blkg_stat_exit(&stats->avg_queue_size_samples);
+ blkg_stat_exit(&stats->dequeue);
+ blkg_stat_exit(&stats->group_wait_time);
+ blkg_stat_exit(&stats->idle_time);
+ blkg_stat_exit(&stats->empty_time);
+}
+
+static int bfqg_stats_init(struct bfqg_stats *stats, gfp_t gfp)
+{
+ if (blkg_rwstat_init(&stats->merged, gfp) ||
+ blkg_rwstat_init(&stats->service_time, gfp) ||
+ blkg_rwstat_init(&stats->wait_time, gfp) ||
+ blkg_rwstat_init(&stats->queued, gfp) ||
+ blkg_stat_init(&stats->time, gfp) ||
+ blkg_stat_init(&stats->avg_queue_size_sum, gfp) ||
+ blkg_stat_init(&stats->avg_queue_size_samples, gfp) ||
+ blkg_stat_init(&stats->dequeue, gfp) ||
+ blkg_stat_init(&stats->group_wait_time, gfp) ||
+ blkg_stat_init(&stats->idle_time, gfp) ||
+ blkg_stat_init(&stats->empty_time, gfp)) {
+ bfqg_stats_exit(stats);
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static struct bfq_group_data *cpd_to_bfqgd(struct blkcg_policy_data *cpd)
+{
+ return cpd ? container_of(cpd, struct bfq_group_data, pd) : NULL;
+}
+
+static struct bfq_group_data *blkcg_to_bfqgd(struct blkcg *blkcg)
+{
+ return cpd_to_bfqgd(blkcg_to_cpd(blkcg, &blkcg_policy_bfq));
+}
+
+struct blkcg_policy_data *bfq_cpd_alloc(gfp_t gfp)
+{
+ struct bfq_group_data *bgd;
+
+ bgd = kzalloc(sizeof(*bgd), gfp);
+ if (!bgd)
+ return NULL;
+ return &bgd->pd;
+}
+
+void bfq_cpd_init(struct blkcg_policy_data *cpd)
+{
+ struct bfq_group_data *d = cpd_to_bfqgd(cpd);
+
+ d->weight = cgroup_subsys_on_dfl(io_cgrp_subsys) ?
+ CGROUP_WEIGHT_DFL : BFQ_WEIGHT_LEGACY_DFL;
+}
+
+void bfq_cpd_free(struct blkcg_policy_data *cpd)
+{
+ kfree(cpd_to_bfqgd(cpd));
+}
+
+struct blkg_policy_data *bfq_pd_alloc(gfp_t gfp, int node)
+{
+ struct bfq_group *bfqg;
+
+ bfqg = kzalloc_node(sizeof(*bfqg), gfp, node);
+ if (!bfqg)
+ return NULL;
+
+ if (bfqg_stats_init(&bfqg->stats, gfp)) {
+ kfree(bfqg);
+ return NULL;
+ }
+
+ return &bfqg->pd;
+}
+
+void bfq_pd_init(struct blkg_policy_data *pd)
+{
+ struct blkcg_gq *blkg = pd_to_blkg(pd);
+ struct bfq_group *bfqg = blkg_to_bfqg(blkg);
+ struct bfq_data *bfqd = blkg->q->elevator->elevator_data;
+ struct bfq_entity *entity = &bfqg->entity;
+ struct bfq_group_data *d = blkcg_to_bfqgd(blkg->blkcg);
+
+ entity->orig_weight = entity->weight = entity->new_weight = d->weight;
+ entity->my_sched_data = &bfqg->sched_data;
+ bfqg->my_entity = entity; /*
+ * the root_group's will be set to NULL
+ * in bfq_init_queue()
+ */
+ bfqg->bfqd = bfqd;
+ bfqg->active_entities = 0;
+ bfqg->rq_pos_tree = RB_ROOT;
+}
+
+void bfq_pd_free(struct blkg_policy_data *pd)
+{
+ struct bfq_group *bfqg = pd_to_bfqg(pd);
+
+ bfqg_stats_exit(&bfqg->stats);
+ return kfree(bfqg);
+}
+
+void bfq_pd_reset_stats(struct blkg_policy_data *pd)
+{
+ struct bfq_group *bfqg = pd_to_bfqg(pd);
+
+ bfqg_stats_reset(&bfqg->stats);
+}
+
+static void bfq_group_set_parent(struct bfq_group *bfqg,
+ struct bfq_group *parent)
+{
+ struct bfq_entity *entity;
+
+ entity = &bfqg->entity;
+ entity->parent = parent->my_entity;
+ entity->sched_data = &parent->sched_data;
+}
+
+static struct bfq_group *bfq_lookup_bfqg(struct bfq_data *bfqd,
+ struct blkcg *blkcg)
+{
+ struct blkcg_gq *blkg;
+
+ blkg = blkg_lookup(blkcg, bfqd->queue);
+ if (likely(blkg))
+ return blkg_to_bfqg(blkg);
+ return NULL;
+}
+
+struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
+ struct blkcg *blkcg)
+{
+ struct bfq_group *bfqg, *parent;
+ struct bfq_entity *entity;
+
+ bfqg = bfq_lookup_bfqg(bfqd, blkcg);
+
+ if (unlikely(!bfqg))
+ return NULL;
+
+ /*
+ * Update chain of bfq_groups as we might be handling a leaf group
+ * which, along with some of its relatives, has not been hooked yet
+ * to the private hierarchy of BFQ.
+ */
+ entity = &bfqg->entity;
+ for_each_entity(entity) {
+ bfqg = container_of(entity, struct bfq_group, entity);
+ if (bfqg != bfqd->root_group) {
+ parent = bfqg_parent(bfqg);
+ if (!parent)
+ parent = bfqd->root_group;
+ bfq_group_set_parent(bfqg, parent);
+ }
+ }
+
+ return bfqg;
+}
+
+/**
+ * bfq_bfqq_move - migrate @bfqq to @bfqg.
+ * @bfqd: queue descriptor.
+ * @bfqq: the queue to move.
+ * @bfqg: the group to move to.
+ *
+ * Move @bfqq to @bfqg, deactivating it from its old group and reactivating
+ * it on the new one. Avoid putting the entity on the old group idle tree.
+ *
+ * Must be called under the queue lock; the cgroup owning @bfqg must
+ * not disappear (by now this just means that we are called under
+ * rcu_read_lock()).
+ */
+void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ struct bfq_group *bfqg)
+{
+ struct bfq_entity *entity = &bfqq->entity;
+
+ /* If bfqq is empty, then bfq_bfqq_expire also invokes
+ * bfq_del_bfqq_busy, thereby removing bfqq and its entity
+ * from data structures related to current group. Otherwise we
+ * need to remove bfqq explicitly with bfq_deactivate_bfqq, as
+ * we do below.
+ */
+ if (bfqq == bfqd->in_service_queue)
+ bfq_bfqq_expire(bfqd, bfqd->in_service_queue,
+ false, BFQQE_PREEMPTED);
+
+ if (bfq_bfqq_busy(bfqq))
+ bfq_deactivate_bfqq(bfqd, bfqq, false, false);
+ else if (entity->on_st)
+ bfq_put_idle_entity(bfq_entity_service_tree(entity), entity);
+ bfqg_put(bfqq_group(bfqq));
+
+ /*
+ * Here we use a reference to bfqg. We don't need a refcounter
+ * as the cgroup reference will not be dropped, so that its
+ * destroy() callback will not be invoked.
+ */
+ entity->parent = bfqg->my_entity;
+ entity->sched_data = &bfqg->sched_data;
+ bfqg_get(bfqg);
+
+ if (bfq_bfqq_busy(bfqq)) {
+ bfq_pos_tree_add_move(bfqd, bfqq);
+ bfq_activate_bfqq(bfqd, bfqq);
+ }
+
+ if (!bfqd->in_service_queue && !bfqd->rq_in_driver)
+ bfq_schedule_dispatch(bfqd);
+}
+
+/**
+ * __bfq_bic_change_cgroup - move @bic to @cgroup.
+ * @bfqd: the queue descriptor.
+ * @bic: the bic to move.
+ * @blkcg: the blk-cgroup to move to.
+ *
+ * Move bic to blkcg, assuming that bfqd->queue is locked; the caller
+ * has to make sure that the reference to cgroup is valid across the call.
+ *
+ * NOTE: an alternative approach might have been to store the current
+ * cgroup in bfqq and getting a reference to it, reducing the lookup
+ * time here, at the price of slightly more complex code.
+ */
+static struct bfq_group *__bfq_bic_change_cgroup(struct bfq_data *bfqd,
+ struct bfq_io_cq *bic,
+ struct blkcg *blkcg)
+{
+ struct bfq_queue *async_bfqq = bic_to_bfqq(bic, 0);
+ struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, 1);
+ struct bfq_group *bfqg;
+ struct bfq_entity *entity;
+
+ bfqg = bfq_find_set_group(bfqd, blkcg);
+
+ if (unlikely(!bfqg))
+ bfqg = bfqd->root_group;
+
+ if (async_bfqq) {
+ entity = &async_bfqq->entity;
+
+ if (entity->sched_data != &bfqg->sched_data) {
+ bic_set_bfqq(bic, NULL, 0);
+ bfq_log_bfqq(bfqd, async_bfqq,
+ "bic_change_group: %p %d",
+ async_bfqq, async_bfqq->ref);
+ bfq_put_queue(async_bfqq);
+ }
+ }
+
+ if (sync_bfqq) {
+ entity = &sync_bfqq->entity;
+ if (entity->sched_data != &bfqg->sched_data)
+ bfq_bfqq_move(bfqd, sync_bfqq, bfqg);
+ }
+
+ return bfqg;
+}
+
+void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio)
+{
+ struct bfq_data *bfqd = bic_to_bfqd(bic);
+ struct bfq_group *bfqg = NULL;
+ uint64_t serial_nr;
+
+ rcu_read_lock();
+ serial_nr = bio_blkcg(bio)->css.serial_nr;
+
+ /*
+ * Check whether blkcg has changed. The condition may trigger
+ * spuriously on a newly created cic but there's no harm.
+ */
+ if (unlikely(!bfqd) || likely(bic->blkcg_serial_nr == serial_nr))
+ goto out;
+
+ bfqg = __bfq_bic_change_cgroup(bfqd, bic, bio_blkcg(bio));
+ bic->blkcg_serial_nr = serial_nr;
+out:
+ rcu_read_unlock();
+}
+
+/**
+ * bfq_flush_idle_tree - deactivate any entity on the idle tree of @st.
+ * @st: the service tree being flushed.
+ */
+static void bfq_flush_idle_tree(struct bfq_service_tree *st)
+{
+ struct bfq_entity *entity = st->first_idle;
+
+ for (; entity ; entity = st->first_idle)
+ __bfq_deactivate_entity(entity, false);
+}
+
+/**
+ * bfq_reparent_leaf_entity - move leaf entity to the root_group.
+ * @bfqd: the device data structure with the root group.
+ * @entity: the entity to move.
+ */
+static void bfq_reparent_leaf_entity(struct bfq_data *bfqd,
+ struct bfq_entity *entity)
+{
+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+ bfq_bfqq_move(bfqd, bfqq, bfqd->root_group);
+}
+
+/**
+ * bfq_reparent_active_entities - move to the root group all active
+ * entities.
+ * @bfqd: the device data structure with the root group.
+ * @bfqg: the group to move from.
+ * @st: the service tree with the entities.
+ *
+ * Needs queue_lock to be taken and reference to be valid over the call.
+ */
+static void bfq_reparent_active_entities(struct bfq_data *bfqd,
+ struct bfq_group *bfqg,
+ struct bfq_service_tree *st)
+{
+ struct rb_root *active = &st->active;
+ struct bfq_entity *entity = NULL;
+
+ if (!RB_EMPTY_ROOT(&st->active))
+ entity = bfq_entity_of(rb_first(active));
+
+ for (; entity ; entity = bfq_entity_of(rb_first(active)))
+ bfq_reparent_leaf_entity(bfqd, entity);
+
+ if (bfqg->sched_data.in_service_entity)
+ bfq_reparent_leaf_entity(bfqd,
+ bfqg->sched_data.in_service_entity);
+}
+
+/**
+ * bfq_pd_offline - deactivate the entity associated with @pd,
+ * and reparent its children entities.
+ * @pd: descriptor of the policy going offline.
+ *
+ * blkio already grabs the queue_lock for us, so no need to use
+ * RCU-based magic
+ */
+void bfq_pd_offline(struct blkg_policy_data *pd)
+{
+ struct bfq_service_tree *st;
+ struct bfq_group *bfqg = pd_to_bfqg(pd);
+ struct bfq_data *bfqd = bfqg->bfqd;
+ struct bfq_entity *entity = bfqg->my_entity;
+ unsigned long flags;
+ int i;
+
+ if (!entity) /* root group */
+ return;
+
+ spin_lock_irqsave(&bfqd->lock, flags);
+ /*
+ * Empty all service_trees belonging to this group before
+ * deactivating the group itself.
+ */
+ for (i = 0; i < BFQ_IOPRIO_CLASSES; i++) {
+ st = bfqg->sched_data.service_tree + i;
+
+ /*
+ * The idle tree may still contain bfq_queues belonging
+ * to exited task because they never migrated to a different
+ * cgroup from the one being destroyed now. No one else
+ * can access them so it's safe to act without any lock.
+ */
+ bfq_flush_idle_tree(st);
+
+ /*
+ * It may happen that some queues are still active
+ * (busy) upon group destruction (if the corresponding
+ * processes have been forced to terminate). We move
+ * all the leaf entities corresponding to these queues
+ * to the root_group.
+ * Also, it may happen that the group has an entity
+ * in service, which is disconnected from the active
+ * tree: it must be moved, too.
+ * There is no need to put the sync queues, as the
+ * scheduler has taken no reference.
+ */
+ bfq_reparent_active_entities(bfqd, bfqg, st);
+ }
+
+ __bfq_deactivate_entity(entity, false);
+ bfq_put_async_queues(bfqd, bfqg);
+
+ spin_unlock_irqrestore(&bfqd->lock, flags);
+ /*
+ * @blkg is going offline and will be ignored by
+ * blkg_[rw]stat_recursive_sum(). Transfer stats to the parent so
+ * that they don't get lost. If IOs complete after this point, the
+ * stats for them will be lost. Oh well...
+ */
+ bfqg_stats_xfer_dead(bfqg);
+}
+
+void bfq_end_wr_async(struct bfq_data *bfqd)
+{
+ struct blkcg_gq *blkg;
+
+ list_for_each_entry(blkg, &bfqd->queue->blkg_list, q_node) {
+ struct bfq_group *bfqg = blkg_to_bfqg(blkg);
+
+ bfq_end_wr_async_queues(bfqd, bfqg);
+ }
+ bfq_end_wr_async_queues(bfqd, bfqd->root_group);
+}
+
+static int bfq_io_show_weight(struct seq_file *sf, void *v)
+{
+ struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
+ struct bfq_group_data *bfqgd = blkcg_to_bfqgd(blkcg);
+ unsigned int val = 0;
+
+ if (bfqgd)
+ val = bfqgd->weight;
+
+ seq_printf(sf, "%u\n", val);
+
+ return 0;
+}
+
+static int bfq_io_set_weight_legacy(struct cgroup_subsys_state *css,
+ struct cftype *cftype,
+ u64 val)
+{
+ struct blkcg *blkcg = css_to_blkcg(css);
+ struct bfq_group_data *bfqgd = blkcg_to_bfqgd(blkcg);
+ struct blkcg_gq *blkg;
+ int ret = -ERANGE;
+
+ if (val < BFQ_MIN_WEIGHT || val > BFQ_MAX_WEIGHT)
+ return ret;
+
+ ret = 0;
+ spin_lock_irq(&blkcg->lock);
+ bfqgd->weight = (unsigned short)val;
+ hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) {
+ struct bfq_group *bfqg = blkg_to_bfqg(blkg);
+
+ if (!bfqg)
+ continue;
+ /*
+ * Setting the prio_changed flag of the entity
+ * to 1 with new_weight == weight would re-set
+ * the value of the weight to its ioprio mapping.
+ * Set the flag only if necessary.
+ */
+ if ((unsigned short)val != bfqg->entity.new_weight) {
+ bfqg->entity.new_weight = (unsigned short)val;
+ /*
+ * Make sure that the above new value has been
+ * stored in bfqg->entity.new_weight before
+ * setting the prio_changed flag. In fact,
+ * this flag may be read asynchronously (in
+ * critical sections protected by a different
+ * lock than that held here), and finding this
+ * flag set may cause the execution of the code
+ * for updating parameters whose value may
+ * depend also on bfqg->entity.new_weight (in
+ * __bfq_entity_update_weight_prio).
+ * This barrier makes sure that the new value
+ * of bfqg->entity.new_weight is correctly
+ * seen in that code.
+ */
+ smp_wmb();
+ bfqg->entity.prio_changed = 1;
+ }
+ }
+ spin_unlock_irq(&blkcg->lock);
+
+ return ret;
+}
+
+static ssize_t bfq_io_set_weight(struct kernfs_open_file *of,
+ char *buf, size_t nbytes,
+ loff_t off)
+{
+ u64 weight;
+ /* First unsigned long found in the file is used */
+ int ret = kstrtoull(strim(buf), 0, &weight);
+
+ if (ret)
+ return ret;
+
+ return bfq_io_set_weight_legacy(of_css(of), NULL, weight);
+}
+
+static int bfqg_print_stat(struct seq_file *sf, void *v)
+{
+ blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat,
+ &blkcg_policy_bfq, seq_cft(sf)->private, false);
+ return 0;
+}
+
+static int bfqg_print_rwstat(struct seq_file *sf, void *v)
+{
+ blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat,
+ &blkcg_policy_bfq, seq_cft(sf)->private, true);
+ return 0;
+}
+
+static u64 bfqg_prfill_stat_recursive(struct seq_file *sf,
+ struct blkg_policy_data *pd, int off)
+{
+ u64 sum = blkg_stat_recursive_sum(pd_to_blkg(pd),
+ &blkcg_policy_bfq, off);
+ return __blkg_prfill_u64(sf, pd, sum);
+}
+
+static u64 bfqg_prfill_rwstat_recursive(struct seq_file *sf,
+ struct blkg_policy_data *pd, int off)
+{
+ struct blkg_rwstat sum = blkg_rwstat_recursive_sum(pd_to_blkg(pd),
+ &blkcg_policy_bfq,
+ off);
+ return __blkg_prfill_rwstat(sf, pd, &sum);
+}
+
+static int bfqg_print_stat_recursive(struct seq_file *sf, void *v)
+{
+ blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+ bfqg_prfill_stat_recursive, &blkcg_policy_bfq,
+ seq_cft(sf)->private, false);
+ return 0;
+}
+
+static int bfqg_print_rwstat_recursive(struct seq_file *sf, void *v)
+{
+ blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+ bfqg_prfill_rwstat_recursive, &blkcg_policy_bfq,
+ seq_cft(sf)->private, true);
+ return 0;
+}
+
+static u64 bfqg_prfill_sectors(struct seq_file *sf, struct blkg_policy_data *pd,
+ int off)
+{
+ u64 sum = blkg_rwstat_total(&pd->blkg->stat_bytes);
+
+ return __blkg_prfill_u64(sf, pd, sum >> 9);
+}
+
+static int bfqg_print_stat_sectors(struct seq_file *sf, void *v)
+{
+ blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+ bfqg_prfill_sectors, &blkcg_policy_bfq, 0, false);
+ return 0;
+}
+
+static u64 bfqg_prfill_sectors_recursive(struct seq_file *sf,
+ struct blkg_policy_data *pd, int off)
+{
+ struct blkg_rwstat tmp = blkg_rwstat_recursive_sum(pd->blkg, NULL,
+ offsetof(struct blkcg_gq, stat_bytes));
+ u64 sum = atomic64_read(&tmp.aux_cnt[BLKG_RWSTAT_READ]) +
+ atomic64_read(&tmp.aux_cnt[BLKG_RWSTAT_WRITE]);
+
+ return __blkg_prfill_u64(sf, pd, sum >> 9);
+}
+
+static int bfqg_print_stat_sectors_recursive(struct seq_file *sf, void *v)
+{
+ blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+ bfqg_prfill_sectors_recursive, &blkcg_policy_bfq, 0,
+ false);
+ return 0;
+}
+
+static u64 bfqg_prfill_avg_queue_size(struct seq_file *sf,
+ struct blkg_policy_data *pd, int off)
+{
+ struct bfq_group *bfqg = pd_to_bfqg(pd);
+ u64 samples = blkg_stat_read(&bfqg->stats.avg_queue_size_samples);
+ u64 v = 0;
+
+ if (samples) {
+ v = blkg_stat_read(&bfqg->stats.avg_queue_size_sum);
+ v = div64_u64(v, samples);
+ }
+ __blkg_prfill_u64(sf, pd, v);
+ return 0;
+}
+
+/* print avg_queue_size */
+static int bfqg_print_avg_queue_size(struct seq_file *sf, void *v)
+{
+ blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+ bfqg_prfill_avg_queue_size, &blkcg_policy_bfq,
+ 0, false);
+ return 0;
+}
+
+struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node)
+{
+ int ret;
+
+ ret = blkcg_activate_policy(bfqd->queue, &blkcg_policy_bfq);
+ if (ret)
+ return NULL;
+
+ return blkg_to_bfqg(bfqd->queue->root_blkg);
+}
+
+struct blkcg_policy blkcg_policy_bfq = {
+ .dfl_cftypes = bfq_blkg_files,
+ .legacy_cftypes = bfq_blkcg_legacy_files,
+
+ .cpd_alloc_fn = bfq_cpd_alloc,
+ .cpd_init_fn = bfq_cpd_init,
+ .cpd_bind_fn = bfq_cpd_init,
+ .cpd_free_fn = bfq_cpd_free,
+
+ .pd_alloc_fn = bfq_pd_alloc,
+ .pd_init_fn = bfq_pd_init,
+ .pd_offline_fn = bfq_pd_offline,
+ .pd_free_fn = bfq_pd_free,
+ .pd_reset_stats_fn = bfq_pd_reset_stats,
+};
+
+struct cftype bfq_blkcg_legacy_files[] = {
+ {
+ .name = "bfq.weight",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = bfq_io_show_weight,
+ .write_u64 = bfq_io_set_weight_legacy,
+ },
+
+ /* statistics, covers only the tasks in the bfqg */
+ {
+ .name = "bfq.time",
+ .private = offsetof(struct bfq_group, stats.time),
+ .seq_show = bfqg_print_stat,
+ },
+ {
+ .name = "bfq.sectors",
+ .seq_show = bfqg_print_stat_sectors,
+ },
+ {
+ .name = "bfq.io_service_bytes",
+ .private = (unsigned long)&blkcg_policy_bfq,
+ .seq_show = blkg_print_stat_bytes,
+ },
+ {
+ .name = "bfq.io_serviced",
+ .private = (unsigned long)&blkcg_policy_bfq,
+ .seq_show = blkg_print_stat_ios,
+ },
+ {
+ .name = "bfq.io_service_time",
+ .private = offsetof(struct bfq_group, stats.service_time),
+ .seq_show = bfqg_print_rwstat,
+ },
+ {
+ .name = "bfq.io_wait_time",
+ .private = offsetof(struct bfq_group, stats.wait_time),
+ .seq_show = bfqg_print_rwstat,
+ },
+ {
+ .name = "bfq.io_merged",
+ .private = offsetof(struct bfq_group, stats.merged),
+ .seq_show = bfqg_print_rwstat,
+ },
+ {
+ .name = "bfq.io_queued",
+ .private = offsetof(struct bfq_group, stats.queued),
+ .seq_show = bfqg_print_rwstat,
+ },
+
+ /* the same statictics which cover the bfqg and its descendants */
+ {
+ .name = "bfq.time_recursive",
+ .private = offsetof(struct bfq_group, stats.time),
+ .seq_show = bfqg_print_stat_recursive,
+ },
+ {
+ .name = "bfq.sectors_recursive",
+ .seq_show = bfqg_print_stat_sectors_recursive,
+ },
+ {
+ .name = "bfq.io_service_bytes_recursive",
+ .private = (unsigned long)&blkcg_policy_bfq,
+ .seq_show = blkg_print_stat_bytes_recursive,
+ },
+ {
+ .name = "bfq.io_serviced_recursive",
+ .private = (unsigned long)&blkcg_policy_bfq,
+ .seq_show = blkg_print_stat_ios_recursive,
+ },
+ {
+ .name = "bfq.io_service_time_recursive",
+ .private = offsetof(struct bfq_group, stats.service_time),
+ .seq_show = bfqg_print_rwstat_recursive,
+ },
+ {
+ .name = "bfq.io_wait_time_recursive",
+ .private = offsetof(struct bfq_group, stats.wait_time),
+ .seq_show = bfqg_print_rwstat_recursive,
+ },
+ {
+ .name = "bfq.io_merged_recursive",
+ .private = offsetof(struct bfq_group, stats.merged),
+ .seq_show = bfqg_print_rwstat_recursive,
+ },
+ {
+ .name = "bfq.io_queued_recursive",
+ .private = offsetof(struct bfq_group, stats.queued),
+ .seq_show = bfqg_print_rwstat_recursive,
+ },
+ {
+ .name = "bfq.avg_queue_size",
+ .seq_show = bfqg_print_avg_queue_size,
+ },
+ {
+ .name = "bfq.group_wait_time",
+ .private = offsetof(struct bfq_group, stats.group_wait_time),
+ .seq_show = bfqg_print_stat,
+ },
+ {
+ .name = "bfq.idle_time",
+ .private = offsetof(struct bfq_group, stats.idle_time),
+ .seq_show = bfqg_print_stat,
+ },
+ {
+ .name = "bfq.empty_time",
+ .private = offsetof(struct bfq_group, stats.empty_time),
+ .seq_show = bfqg_print_stat,
+ },
+ {
+ .name = "bfq.dequeue",
+ .private = offsetof(struct bfq_group, stats.dequeue),
+ .seq_show = bfqg_print_stat,
+ },
+ { } /* terminate */
+};
+
+struct cftype bfq_blkg_files[] = {
+ {
+ .name = "bfq.weight",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = bfq_io_show_weight,
+ .write = bfq_io_set_weight,
+ },
+ {} /* terminate */
+};
+
+#else /* CONFIG_BFQ_GROUP_IOSCHED */
+
+void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
+ unsigned int op) { }
+void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op) { }
+void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op) { }
+void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time,
+ uint64_t io_start_time, unsigned int op) { }
+void bfqg_stats_update_dequeue(struct bfq_group *bfqg) { }
+void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg) { }
+void bfqg_stats_update_idle_time(struct bfq_group *bfqg) { }
+void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg) { }
+void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg) { }
+
+void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ struct bfq_group *bfqg) {}
+
+void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg)
+{
+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+ entity->weight = entity->new_weight;
+ entity->orig_weight = entity->new_weight;
+ if (bfqq) {
+ bfqq->ioprio = bfqq->new_ioprio;
+ bfqq->ioprio_class = bfqq->new_ioprio_class;
+ }
+ entity->sched_data = &bfqg->sched_data;
+}
+
+void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio) {}
+
+void bfq_end_wr_async(struct bfq_data *bfqd)
+{
+ bfq_end_wr_async_queues(bfqd, bfqd->root_group);
+}
+
+struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd, struct blkcg *blkcg)
+{
+ return bfqd->root_group;
+}
+
+struct bfq_group *bfqq_group(struct bfq_queue *bfqq)
+{
+ return bfqq->bfqd->root_group;
+}
+
+struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node)
+{
+ struct bfq_group *bfqg;
+ int i;
+
+ bfqg = kmalloc_node(sizeof(*bfqg), GFP_KERNEL | __GFP_ZERO, node);
+ if (!bfqg)
+ return NULL;
+
+ for (i = 0; i < BFQ_IOPRIO_CLASSES; i++)
+ bfqg->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT;
+
+ return bfqg;
+}
+#endif /* CONFIG_BFQ_GROUP_IOSCHED */
--- /dev/null
+/*
+ * Budget Fair Queueing (BFQ) I/O scheduler.
+ *
+ * Based on ideas and code from CFQ:
+ * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
+ *
+ * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
+ * Paolo Valente <paolo.valente@unimore.it>
+ *
+ * Copyright (C) 2010 Paolo Valente <paolo.valente@unimore.it>
+ * Arianna Avanzini <avanzini@google.com>
+ *
+ * Copyright (C) 2017 Paolo Valente <paolo.valente@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * BFQ is a proportional-share I/O scheduler, with some extra
+ * low-latency capabilities. BFQ also supports full hierarchical
+ * scheduling through cgroups. Next paragraphs provide an introduction
+ * on BFQ inner workings. Details on BFQ benefits, usage and
+ * limitations can be found in Documentation/block/bfq-iosched.txt.
+ *
+ * BFQ is a proportional-share storage-I/O scheduling algorithm based
+ * on the slice-by-slice service scheme of CFQ. But BFQ assigns
+ * budgets, measured in number of sectors, to processes instead of
+ * time slices. The device is not granted to the in-service process
+ * for a given time slice, but until it has exhausted its assigned
+ * budget. This change from the time to the service domain enables BFQ
+ * to distribute the device throughput among processes as desired,
+ * without any distortion due to throughput fluctuations, or to device
+ * internal queueing. BFQ uses an ad hoc internal scheduler, called
+ * B-WF2Q+, to schedule processes according to their budgets. More
+ * precisely, BFQ schedules queues associated with processes. Each
+ * process/queue is assigned a user-configurable weight, and B-WF2Q+
+ * guarantees that each queue receives a fraction of the throughput
+ * proportional to its weight. Thanks to the accurate policy of
+ * B-WF2Q+, BFQ can afford to assign high budgets to I/O-bound
+ * processes issuing sequential requests (to boost the throughput),
+ * and yet guarantee a low latency to interactive and soft real-time
+ * applications.
+ *
+ * In particular, to provide these low-latency guarantees, BFQ
+ * explicitly privileges the I/O of two classes of time-sensitive
+ * applications: interactive and soft real-time. This feature enables
+ * BFQ to provide applications in these classes with a very low
+ * latency. Finally, BFQ also features additional heuristics for
+ * preserving both a low latency and a high throughput on NCQ-capable,
+ * rotational or flash-based devices, and to get the job done quickly
+ * for applications consisting in many I/O-bound processes.
+ *
+ * BFQ is described in [1], where also a reference to the initial, more
+ * theoretical paper on BFQ can be found. The interested reader can find
+ * in the latter paper full details on the main algorithm, as well as
+ * formulas of the guarantees and formal proofs of all the properties.
+ * With respect to the version of BFQ presented in these papers, this
+ * implementation adds a few more heuristics, such as the one that
+ * guarantees a low latency to soft real-time applications, and a
+ * hierarchical extension based on H-WF2Q+.
+ *
+ * B-WF2Q+ is based on WF2Q+, which is described in [2], together with
+ * H-WF2Q+, while the augmented tree used here to implement B-WF2Q+
+ * with O(log N) complexity derives from the one introduced with EEVDF
+ * in [3].
+ *
+ * [1] P. Valente, A. Avanzini, "Evolution of the BFQ Storage I/O
+ * Scheduler", Proceedings of the First Workshop on Mobile System
+ * Technologies (MST-2015), May 2015.
+ * http://algogroup.unimore.it/people/paolo/disk_sched/mst-2015.pdf
+ *
+ * [2] Jon C.R. Bennett and H. Zhang, "Hierarchical Packet Fair Queueing
+ * Algorithms", IEEE/ACM Transactions on Networking, 5(5):675-689,
+ * Oct 1997.
+ *
+ * http://www.cs.cmu.edu/~hzhang/papers/TON-97-Oct.ps.gz
+ *
+ * [3] I. Stoica and H. Abdel-Wahab, "Earliest Eligible Virtual Deadline
+ * First: A Flexible and Accurate Mechanism for Proportional Share
+ * Resource Allocation", technical report.
+ *
+ * http://www.cs.berkeley.edu/~istoica/papers/eevdf-tr-95.pdf
+ */
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/blkdev.h>
+#include <linux/cgroup.h>
+#include <linux/elevator.h>
+#include <linux/ktime.h>
+#include <linux/rbtree.h>
+#include <linux/ioprio.h>
+#include <linux/sbitmap.h>
+#include <linux/delay.h>
+
+#include "blk.h"
+#include "blk-mq.h"
+#include "blk-mq-tag.h"
+#include "blk-mq-sched.h"
+#include "bfq-iosched.h"
+
+#define BFQ_BFQQ_FNS(name) \
+void bfq_mark_bfqq_##name(struct bfq_queue *bfqq) \
+{ \
+ __set_bit(BFQQF_##name, &(bfqq)->flags); \
+} \
+void bfq_clear_bfqq_##name(struct bfq_queue *bfqq) \
+{ \
+ __clear_bit(BFQQF_##name, &(bfqq)->flags); \
+} \
+int bfq_bfqq_##name(const struct bfq_queue *bfqq) \
+{ \
+ return test_bit(BFQQF_##name, &(bfqq)->flags); \
+}
+
+BFQ_BFQQ_FNS(just_created);
+BFQ_BFQQ_FNS(busy);
+BFQ_BFQQ_FNS(wait_request);
+BFQ_BFQQ_FNS(non_blocking_wait_rq);
+BFQ_BFQQ_FNS(fifo_expire);
+BFQ_BFQQ_FNS(idle_window);
+BFQ_BFQQ_FNS(sync);
+BFQ_BFQQ_FNS(IO_bound);
+BFQ_BFQQ_FNS(in_large_burst);
+BFQ_BFQQ_FNS(coop);
+BFQ_BFQQ_FNS(split_coop);
+BFQ_BFQQ_FNS(softrt_update);
+#undef BFQ_BFQQ_FNS \
+
+/* Expiration time of sync (0) and async (1) requests, in ns. */
+static const u64 bfq_fifo_expire[2] = { NSEC_PER_SEC / 4, NSEC_PER_SEC / 8 };
+
+/* Maximum backwards seek (magic number lifted from CFQ), in KiB. */
+static const int bfq_back_max = 16 * 1024;
+
+/* Penalty of a backwards seek, in number of sectors. */
+static const int bfq_back_penalty = 2;
+
+/* Idling period duration, in ns. */
+static u64 bfq_slice_idle = NSEC_PER_SEC / 125;
+
+/* Minimum number of assigned budgets for which stats are safe to compute. */
+static const int bfq_stats_min_budgets = 194;
+
+/* Default maximum budget values, in sectors and number of requests. */
+static const int bfq_default_max_budget = 16 * 1024;
+
+/*
+ * Async to sync throughput distribution is controlled as follows:
+ * when an async request is served, the entity is charged the number
+ * of sectors of the request, multiplied by the factor below
+ */
+static const int bfq_async_charge_factor = 10;
+
+/* Default timeout values, in jiffies, approximating CFQ defaults. */
+const int bfq_timeout = HZ / 8;
+
+static struct kmem_cache *bfq_pool;
+
+/* Below this threshold (in ns), we consider thinktime immediate. */
+#define BFQ_MIN_TT (2 * NSEC_PER_MSEC)
+
+/* hw_tag detection: parallel requests threshold and min samples needed. */
+#define BFQ_HW_QUEUE_THRESHOLD 4
+#define BFQ_HW_QUEUE_SAMPLES 32
+
+#define BFQQ_SEEK_THR (sector_t)(8 * 100)
+#define BFQQ_SECT_THR_NONROT (sector_t)(2 * 32)
+#define BFQQ_CLOSE_THR (sector_t)(8 * 1024)
+#define BFQQ_SEEKY(bfqq) (hweight32(bfqq->seek_history) > 32/8)
+
+/* Min number of samples required to perform peak-rate update */
+#define BFQ_RATE_MIN_SAMPLES 32
+/* Min observation time interval required to perform a peak-rate update (ns) */
+#define BFQ_RATE_MIN_INTERVAL (300*NSEC_PER_MSEC)
+/* Target observation time interval for a peak-rate update (ns) */
+#define BFQ_RATE_REF_INTERVAL NSEC_PER_SEC
+
+/* Shift used for peak rate fixed precision calculations. */
+#define BFQ_RATE_SHIFT 16
+
+/*
+ * By default, BFQ computes the duration of the weight raising for
+ * interactive applications automatically, using the following formula:
+ * duration = (R / r) * T, where r is the peak rate of the device, and
+ * R and T are two reference parameters.
+ * In particular, R is the peak rate of the reference device (see below),
+ * and T is a reference time: given the systems that are likely to be
+ * installed on the reference device according to its speed class, T is
+ * about the maximum time needed, under BFQ and while reading two files in
+ * parallel, to load typical large applications on these systems.
+ * In practice, the slower/faster the device at hand is, the more/less it
+ * takes to load applications with respect to the reference device.
+ * Accordingly, the longer/shorter BFQ grants weight raising to interactive
+ * applications.
+ *
+ * BFQ uses four different reference pairs (R, T), depending on:
+ * . whether the device is rotational or non-rotational;
+ * . whether the device is slow, such as old or portable HDDs, as well as
+ * SD cards, or fast, such as newer HDDs and SSDs.
+ *
+ * The device's speed class is dynamically (re)detected in
+ * bfq_update_peak_rate() every time the estimated peak rate is updated.
+ *
+ * In the following definitions, R_slow[0]/R_fast[0] and
+ * T_slow[0]/T_fast[0] are the reference values for a slow/fast
+ * rotational device, whereas R_slow[1]/R_fast[1] and
+ * T_slow[1]/T_fast[1] are the reference values for a slow/fast
+ * non-rotational device. Finally, device_speed_thresh are the
+ * thresholds used to switch between speed classes. The reference
+ * rates are not the actual peak rates of the devices used as a
+ * reference, but slightly lower values. The reason for using these
+ * slightly lower values is that the peak-rate estimator tends to
+ * yield slightly lower values than the actual peak rate (it can yield
+ * the actual peak rate only if there is only one process doing I/O,
+ * and the process does sequential I/O).
+ *
+ * Both the reference peak rates and the thresholds are measured in
+ * sectors/usec, left-shifted by BFQ_RATE_SHIFT.
+ */
+static int R_slow[2] = {1000, 10700};
+static int R_fast[2] = {14000, 33000};
+/*
+ * To improve readability, a conversion function is used to initialize the
+ * following arrays, which entails that they can be initialized only in a
+ * function.
+ */
+static int T_slow[2];
+static int T_fast[2];
+static int device_speed_thresh[2];
+
+#define RQ_BIC(rq) ((struct bfq_io_cq *) (rq)->elv.priv[0])
+#define RQ_BFQQ(rq) ((rq)->elv.priv[1])
+
+struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync)
+{
+ return bic->bfqq[is_sync];
+}
+
+void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync)
+{
+ bic->bfqq[is_sync] = bfqq;
+}
+
+struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic)
+{
+ return bic->icq.q->elevator->elevator_data;
+}
+
+/**
+ * icq_to_bic - convert iocontext queue structure to bfq_io_cq.
+ * @icq: the iocontext queue.
+ */
+static struct bfq_io_cq *icq_to_bic(struct io_cq *icq)
+{
+ /* bic->icq is the first member, %NULL will convert to %NULL */
+ return container_of(icq, struct bfq_io_cq, icq);
+}
+
+/**
+ * bfq_bic_lookup - search into @ioc a bic associated to @bfqd.
+ * @bfqd: the lookup key.
+ * @ioc: the io_context of the process doing I/O.
+ * @q: the request queue.
+ */
+static struct bfq_io_cq *bfq_bic_lookup(struct bfq_data *bfqd,
+ struct io_context *ioc,
+ struct request_queue *q)
+{
+ if (ioc) {
+ unsigned long flags;
+ struct bfq_io_cq *icq;
+
+ spin_lock_irqsave(q->queue_lock, flags);
+ icq = icq_to_bic(ioc_lookup_icq(ioc, q));
+ spin_unlock_irqrestore(q->queue_lock, flags);
+
+ return icq;
+ }
+
+ return NULL;
+}
+
+/*
+ * Scheduler run of queue, if there are requests pending and no one in the
+ * driver that will restart queueing.
+ */
+void bfq_schedule_dispatch(struct bfq_data *bfqd)
+{
+ if (bfqd->queued != 0) {
+ bfq_log(bfqd, "schedule dispatch");
+ blk_mq_run_hw_queues(bfqd->queue, true);
+ }
+}
+
+#define bfq_class_idle(bfqq) ((bfqq)->ioprio_class == IOPRIO_CLASS_IDLE)
+#define bfq_class_rt(bfqq) ((bfqq)->ioprio_class == IOPRIO_CLASS_RT)
+
+#define bfq_sample_valid(samples) ((samples) > 80)
+
+/*
+ * Lifted from AS - choose which of rq1 and rq2 that is best served now.
+ * We choose the request that is closesr to the head right now. Distance
+ * behind the head is penalized and only allowed to a certain extent.
+ */
+static struct request *bfq_choose_req(struct bfq_data *bfqd,
+ struct request *rq1,
+ struct request *rq2,
+ sector_t last)
+{
+ sector_t s1, s2, d1 = 0, d2 = 0;
+ unsigned long back_max;
+#define BFQ_RQ1_WRAP 0x01 /* request 1 wraps */
+#define BFQ_RQ2_WRAP 0x02 /* request 2 wraps */
+ unsigned int wrap = 0; /* bit mask: requests behind the disk head? */
+
+ if (!rq1 || rq1 == rq2)
+ return rq2;
+ if (!rq2)
+ return rq1;
+
+ if (rq_is_sync(rq1) && !rq_is_sync(rq2))
+ return rq1;
+ else if (rq_is_sync(rq2) && !rq_is_sync(rq1))
+ return rq2;
+ if ((rq1->cmd_flags & REQ_META) && !(rq2->cmd_flags & REQ_META))
+ return rq1;
+ else if ((rq2->cmd_flags & REQ_META) && !(rq1->cmd_flags & REQ_META))
+ return rq2;
+
+ s1 = blk_rq_pos(rq1);
+ s2 = blk_rq_pos(rq2);
+
+ /*
+ * By definition, 1KiB is 2 sectors.
+ */
+ back_max = bfqd->bfq_back_max * 2;
+
+ /*
+ * Strict one way elevator _except_ in the case where we allow
+ * short backward seeks which are biased as twice the cost of a
+ * similar forward seek.
+ */
+ if (s1 >= last)
+ d1 = s1 - last;
+ else if (s1 + back_max >= last)
+ d1 = (last - s1) * bfqd->bfq_back_penalty;
+ else
+ wrap |= BFQ_RQ1_WRAP;
+
+ if (s2 >= last)
+ d2 = s2 - last;
+ else if (s2 + back_max >= last)
+ d2 = (last - s2) * bfqd->bfq_back_penalty;
+ else
+ wrap |= BFQ_RQ2_WRAP;
+
+ /* Found required data */
+
+ /*
+ * By doing switch() on the bit mask "wrap" we avoid having to
+ * check two variables for all permutations: --> faster!
+ */
+ switch (wrap) {
+ case 0: /* common case for CFQ: rq1 and rq2 not wrapped */
+ if (d1 < d2)
+ return rq1;
+ else if (d2 < d1)
+ return rq2;
+
+ if (s1 >= s2)
+ return rq1;
+ else
+ return rq2;
+
+ case BFQ_RQ2_WRAP:
+ return rq1;
+ case BFQ_RQ1_WRAP:
+ return rq2;
+ case BFQ_RQ1_WRAP|BFQ_RQ2_WRAP: /* both rqs wrapped */
+ default:
+ /*
+ * Since both rqs are wrapped,
+ * start with the one that's further behind head
+ * (--> only *one* back seek required),
+ * since back seek takes more time than forward.
+ */
+ if (s1 <= s2)
+ return rq1;
+ else
+ return rq2;
+ }
+}
+
+static struct bfq_queue *
+bfq_rq_pos_tree_lookup(struct bfq_data *bfqd, struct rb_root *root,
+ sector_t sector, struct rb_node **ret_parent,
+ struct rb_node ***rb_link)
+{
+ struct rb_node **p, *parent;
+ struct bfq_queue *bfqq = NULL;
+
+ parent = NULL;
+ p = &root->rb_node;
+ while (*p) {
+ struct rb_node **n;
+
+ parent = *p;
+ bfqq = rb_entry(parent, struct bfq_queue, pos_node);
+
+ /*
+ * Sort strictly based on sector. Smallest to the left,
+ * largest to the right.
+ */
+ if (sector > blk_rq_pos(bfqq->next_rq))
+ n = &(*p)->rb_right;
+ else if (sector < blk_rq_pos(bfqq->next_rq))
+ n = &(*p)->rb_left;
+ else
+ break;
+ p = n;
+ bfqq = NULL;
+ }
+
+ *ret_parent = parent;
+ if (rb_link)
+ *rb_link = p;
+
+ bfq_log(bfqd, "rq_pos_tree_lookup %llu: returning %d",
+ (unsigned long long)sector,
+ bfqq ? bfqq->pid : 0);
+
+ return bfqq;
+}
+
+void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+ struct rb_node **p, *parent;
+ struct bfq_queue *__bfqq;
+
+ if (bfqq->pos_root) {
+ rb_erase(&bfqq->pos_node, bfqq->pos_root);
+ bfqq->pos_root = NULL;
+ }
+
+ if (bfq_class_idle(bfqq))
+ return;
+ if (!bfqq->next_rq)
+ return;
+
+ bfqq->pos_root = &bfq_bfqq_to_bfqg(bfqq)->rq_pos_tree;
+ __bfqq = bfq_rq_pos_tree_lookup(bfqd, bfqq->pos_root,
+ blk_rq_pos(bfqq->next_rq), &parent, &p);
+ if (!__bfqq) {
+ rb_link_node(&bfqq->pos_node, parent, p);
+ rb_insert_color(&bfqq->pos_node, bfqq->pos_root);
+ } else
+ bfqq->pos_root = NULL;
+}
+
+/*
+ * Tell whether there are active queues or groups with differentiated weights.
+ */
+static bool bfq_differentiated_weights(struct bfq_data *bfqd)
+{
+ /*
+ * For weights to differ, at least one of the trees must contain
+ * at least two nodes.
+ */
+ return (!RB_EMPTY_ROOT(&bfqd->queue_weights_tree) &&
+ (bfqd->queue_weights_tree.rb_node->rb_left ||
+ bfqd->queue_weights_tree.rb_node->rb_right)
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ ) ||
+ (!RB_EMPTY_ROOT(&bfqd->group_weights_tree) &&
+ (bfqd->group_weights_tree.rb_node->rb_left ||
+ bfqd->group_weights_tree.rb_node->rb_right)
+#endif
+ );
+}
+
+/*
+ * The following function returns true if every queue must receive the
+ * same share of the throughput (this condition is used when deciding
+ * whether idling may be disabled, see the comments in the function
+ * bfq_bfqq_may_idle()).
+ *
+ * Such a scenario occurs when:
+ * 1) all active queues have the same weight,
+ * 2) all active groups at the same level in the groups tree have the same
+ * weight,
+ * 3) all active groups at the same level in the groups tree have the same
+ * number of children.
+ *
+ * Unfortunately, keeping the necessary state for evaluating exactly the
+ * above symmetry conditions would be quite complex and time-consuming.
+ * Therefore this function evaluates, instead, the following stronger
+ * sub-conditions, for which it is much easier to maintain the needed
+ * state:
+ * 1) all active queues have the same weight,
+ * 2) all active groups have the same weight,
+ * 3) all active groups have at most one active child each.
+ * In particular, the last two conditions are always true if hierarchical
+ * support and the cgroups interface are not enabled, thus no state needs
+ * to be maintained in this case.
+ */
+static bool bfq_symmetric_scenario(struct bfq_data *bfqd)
+{
+ return !bfq_differentiated_weights(bfqd);
+}
+
+/*
+ * If the weight-counter tree passed as input contains no counter for
+ * the weight of the input entity, then add that counter; otherwise just
+ * increment the existing counter.
+ *
+ * Note that weight-counter trees contain few nodes in mostly symmetric
+ * scenarios. For example, if all queues have the same weight, then the
+ * weight-counter tree for the queues may contain at most one node.
+ * This holds even if low_latency is on, because weight-raised queues
+ * are not inserted in the tree.
+ * In most scenarios, the rate at which nodes are created/destroyed
+ * should be low too.
+ */
+void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_entity *entity,
+ struct rb_root *root)
+{
+ struct rb_node **new = &(root->rb_node), *parent = NULL;
+
+ /*
+ * Do not insert if the entity is already associated with a
+ * counter, which happens if:
+ * 1) the entity is associated with a queue,
+ * 2) a request arrival has caused the queue to become both
+ * non-weight-raised, and hence change its weight, and
+ * backlogged; in this respect, each of the two events
+ * causes an invocation of this function,
+ * 3) this is the invocation of this function caused by the
+ * second event. This second invocation is actually useless,
+ * and we handle this fact by exiting immediately. More
+ * efficient or clearer solutions might possibly be adopted.
+ */
+ if (entity->weight_counter)
+ return;
+
+ while (*new) {
+ struct bfq_weight_counter *__counter = container_of(*new,
+ struct bfq_weight_counter,
+ weights_node);
+ parent = *new;
+
+ if (entity->weight == __counter->weight) {
+ entity->weight_counter = __counter;
+ goto inc_counter;
+ }
+ if (entity->weight < __counter->weight)
+ new = &((*new)->rb_left);
+ else
+ new = &((*new)->rb_right);
+ }
+
+ entity->weight_counter = kzalloc(sizeof(struct bfq_weight_counter),
+ GFP_ATOMIC);
+
+ /*
+ * In the unlucky event of an allocation failure, we just
+ * exit. This will cause the weight of entity to not be
+ * considered in bfq_differentiated_weights, which, in its
+ * turn, causes the scenario to be deemed wrongly symmetric in
+ * case entity's weight would have been the only weight making
+ * the scenario asymmetric. On the bright side, no unbalance
+ * will however occur when entity becomes inactive again (the
+ * invocation of this function is triggered by an activation
+ * of entity). In fact, bfq_weights_tree_remove does nothing
+ * if !entity->weight_counter.
+ */
+ if (unlikely(!entity->weight_counter))
+ return;
+
+ entity->weight_counter->weight = entity->weight;
+ rb_link_node(&entity->weight_counter->weights_node, parent, new);
+ rb_insert_color(&entity->weight_counter->weights_node, root);
+
+inc_counter:
+ entity->weight_counter->num_active++;
+}
+
+/*
+ * Decrement the weight counter associated with the entity, and, if the
+ * counter reaches 0, remove the counter from the tree.
+ * See the comments to the function bfq_weights_tree_add() for considerations
+ * about overhead.
+ */
+void bfq_weights_tree_remove(struct bfq_data *bfqd, struct bfq_entity *entity,
+ struct rb_root *root)
+{
+ if (!entity->weight_counter)
+ return;
+
+ entity->weight_counter->num_active--;
+ if (entity->weight_counter->num_active > 0)
+ goto reset_entity_pointer;
+
+ rb_erase(&entity->weight_counter->weights_node, root);
+ kfree(entity->weight_counter);
+
+reset_entity_pointer:
+ entity->weight_counter = NULL;
+}
+
+/*
+ * Return expired entry, or NULL to just start from scratch in rbtree.
+ */
+static struct request *bfq_check_fifo(struct bfq_queue *bfqq,
+ struct request *last)
+{
+ struct request *rq;
+
+ if (bfq_bfqq_fifo_expire(bfqq))
+ return NULL;
+
+ bfq_mark_bfqq_fifo_expire(bfqq);
+
+ rq = rq_entry_fifo(bfqq->fifo.next);
+
+ if (rq == last || ktime_get_ns() < rq->fifo_time)
+ return NULL;
+
+ bfq_log_bfqq(bfqq->bfqd, bfqq, "check_fifo: returned %p", rq);
+ return rq;
+}
+
+static struct request *bfq_find_next_rq(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq,
+ struct request *last)
+{
+ struct rb_node *rbnext = rb_next(&last->rb_node);
+ struct rb_node *rbprev = rb_prev(&last->rb_node);
+ struct request *next, *prev = NULL;
+
+ /* Follow expired path, else get first next available. */
+ next = bfq_check_fifo(bfqq, last);
+ if (next)
+ return next;
+
+ if (rbprev)
+ prev = rb_entry_rq(rbprev);
+
+ if (rbnext)
+ next = rb_entry_rq(rbnext);
+ else {
+ rbnext = rb_first(&bfqq->sort_list);
+ if (rbnext && rbnext != &last->rb_node)
+ next = rb_entry_rq(rbnext);
+ }
+
+ return bfq_choose_req(bfqd, next, prev, blk_rq_pos(last));
+}
+
+/* see the definition of bfq_async_charge_factor for details */
+static unsigned long bfq_serv_to_charge(struct request *rq,
+ struct bfq_queue *bfqq)
+{
+ if (bfq_bfqq_sync(bfqq) || bfqq->wr_coeff > 1)
+ return blk_rq_sectors(rq);
+
+ /*
+ * If there are no weight-raised queues, then amplify service
+ * by just the async charge factor; otherwise amplify service
+ * by twice the async charge factor, to further reduce latency
+ * for weight-raised queues.
+ */
+ if (bfqq->bfqd->wr_busy_queues == 0)
+ return blk_rq_sectors(rq) * bfq_async_charge_factor;
+
+ return blk_rq_sectors(rq) * 2 * bfq_async_charge_factor;
+}
+
+/**
+ * bfq_updated_next_req - update the queue after a new next_rq selection.
+ * @bfqd: the device data the queue belongs to.
+ * @bfqq: the queue to update.
+ *
+ * If the first request of a queue changes we make sure that the queue
+ * has enough budget to serve at least its first request (if the
+ * request has grown). We do this because if the queue has not enough
+ * budget for its first request, it has to go through two dispatch
+ * rounds to actually get it dispatched.
+ */
+static void bfq_updated_next_req(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq)
+{
+ struct bfq_entity *entity = &bfqq->entity;
+ struct request *next_rq = bfqq->next_rq;
+ unsigned long new_budget;
+
+ if (!next_rq)
+ return;
+
+ if (bfqq == bfqd->in_service_queue)
+ /*
+ * In order not to break guarantees, budgets cannot be
+ * changed after an entity has been selected.
+ */
+ return;
+
+ new_budget = max_t(unsigned long, bfqq->max_budget,
+ bfq_serv_to_charge(next_rq, bfqq));
+ if (entity->budget != new_budget) {
+ entity->budget = new_budget;
+ bfq_log_bfqq(bfqd, bfqq, "updated next rq: new budget %lu",
+ new_budget);
+ bfq_requeue_bfqq(bfqd, bfqq);
+ }
+}
+
+static void
+bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
+{
+ if (bic->saved_idle_window)
+ bfq_mark_bfqq_idle_window(bfqq);
+ else
+ bfq_clear_bfqq_idle_window(bfqq);
+
+ if (bic->saved_IO_bound)
+ bfq_mark_bfqq_IO_bound(bfqq);
+ else
+ bfq_clear_bfqq_IO_bound(bfqq);
+
+ bfqq->ttime = bic->saved_ttime;
+ bfqq->wr_coeff = bic->saved_wr_coeff;
+ bfqq->wr_start_at_switch_to_srt = bic->saved_wr_start_at_switch_to_srt;
+ bfqq->last_wr_start_finish = bic->saved_last_wr_start_finish;
+ bfqq->wr_cur_max_time = bic->saved_wr_cur_max_time;
+
+ if (bfqq->wr_coeff > 1 && (bfq_bfqq_in_large_burst(bfqq) ||
+ time_is_before_jiffies(bfqq->last_wr_start_finish +
+ bfqq->wr_cur_max_time))) {
+ bfq_log_bfqq(bfqq->bfqd, bfqq,
+ "resume state: switching off wr");
+
+ bfqq->wr_coeff = 1;
+ }
+
+ /* make sure weight will be updated, however we got here */
+ bfqq->entity.prio_changed = 1;
+}
+
+static int bfqq_process_refs(struct bfq_queue *bfqq)
+{
+ return bfqq->ref - bfqq->allocated - bfqq->entity.on_st;
+}
+
+/* Empty burst list and add just bfqq (see comments on bfq_handle_burst) */
+static void bfq_reset_burst_list(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+ struct bfq_queue *item;
+ struct hlist_node *n;
+
+ hlist_for_each_entry_safe(item, n, &bfqd->burst_list, burst_list_node)
+ hlist_del_init(&item->burst_list_node);
+ hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list);
+ bfqd->burst_size = 1;
+ bfqd->burst_parent_entity = bfqq->entity.parent;
+}
+
+/* Add bfqq to the list of queues in current burst (see bfq_handle_burst) */
+static void bfq_add_to_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+ /* Increment burst size to take into account also bfqq */
+ bfqd->burst_size++;
+
+ if (bfqd->burst_size == bfqd->bfq_large_burst_thresh) {
+ struct bfq_queue *pos, *bfqq_item;
+ struct hlist_node *n;
+
+ /*
+ * Enough queues have been activated shortly after each
+ * other to consider this burst as large.
+ */
+ bfqd->large_burst = true;
+
+ /*
+ * We can now mark all queues in the burst list as
+ * belonging to a large burst.
+ */
+ hlist_for_each_entry(bfqq_item, &bfqd->burst_list,
+ burst_list_node)
+ bfq_mark_bfqq_in_large_burst(bfqq_item);
+ bfq_mark_bfqq_in_large_burst(bfqq);
+
+ /*
+ * From now on, and until the current burst finishes, any
+ * new queue being activated shortly after the last queue
+ * was inserted in the burst can be immediately marked as
+ * belonging to a large burst. So the burst list is not
+ * needed any more. Remove it.
+ */
+ hlist_for_each_entry_safe(pos, n, &bfqd->burst_list,
+ burst_list_node)
+ hlist_del_init(&pos->burst_list_node);
+ } else /*
+ * Burst not yet large: add bfqq to the burst list. Do
+ * not increment the ref counter for bfqq, because bfqq
+ * is removed from the burst list before freeing bfqq
+ * in put_queue.
+ */
+ hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list);
+}
+
+/*
+ * If many queues belonging to the same group happen to be created
+ * shortly after each other, then the processes associated with these
+ * queues have typically a common goal. In particular, bursts of queue
+ * creations are usually caused by services or applications that spawn
+ * many parallel threads/processes. Examples are systemd during boot,
+ * or git grep. To help these processes get their job done as soon as
+ * possible, it is usually better to not grant either weight-raising
+ * or device idling to their queues.
+ *
+ * In this comment we describe, firstly, the reasons why this fact
+ * holds, and, secondly, the next function, which implements the main
+ * steps needed to properly mark these queues so that they can then be
+ * treated in a different way.
+ *
+ * The above services or applications benefit mostly from a high
+ * throughput: the quicker the requests of the activated queues are
+ * cumulatively served, the sooner the target job of these queues gets
+ * completed. As a consequence, weight-raising any of these queues,
+ * which also implies idling the device for it, is almost always
+ * counterproductive. In most cases it just lowers throughput.
+ *
+ * On the other hand, a burst of queue creations may be caused also by
+ * the start of an application that does not consist of a lot of
+ * parallel I/O-bound threads. In fact, with a complex application,
+ * several short processes may need to be executed to start-up the
+ * application. In this respect, to start an application as quickly as
+ * possible, the best thing to do is in any case to privilege the I/O
+ * related to the application with respect to all other
+ * I/O. Therefore, the best strategy to start as quickly as possible
+ * an application that causes a burst of queue creations is to
+ * weight-raise all the queues created during the burst. This is the
+ * exact opposite of the best strategy for the other type of bursts.
+ *
+ * In the end, to take the best action for each of the two cases, the
+ * two types of bursts need to be distinguished. Fortunately, this
+ * seems relatively easy, by looking at the sizes of the bursts. In
+ * particular, we found a threshold such that only bursts with a
+ * larger size than that threshold are apparently caused by
+ * services or commands such as systemd or git grep. For brevity,
+ * hereafter we call just 'large' these bursts. BFQ *does not*
+ * weight-raise queues whose creation occurs in a large burst. In
+ * addition, for each of these queues BFQ performs or does not perform
+ * idling depending on which choice boosts the throughput more. The
+ * exact choice depends on the device and request pattern at
+ * hand.
+ *
+ * Unfortunately, false positives may occur while an interactive task
+ * is starting (e.g., an application is being started). The
+ * consequence is that the queues associated with the task do not
+ * enjoy weight raising as expected. Fortunately these false positives
+ * are very rare. They typically occur if some service happens to
+ * start doing I/O exactly when the interactive task starts.
+ *
+ * Turning back to the next function, it implements all the steps
+ * needed to detect the occurrence of a large burst and to properly
+ * mark all the queues belonging to it (so that they can then be
+ * treated in a different way). This goal is achieved by maintaining a
+ * "burst list" that holds, temporarily, the queues that belong to the
+ * burst in progress. The list is then used to mark these queues as
+ * belonging to a large burst if the burst does become large. The main
+ * steps are the following.
+ *
+ * . when the very first queue is created, the queue is inserted into the
+ * list (as it could be the first queue in a possible burst)
+ *
+ * . if the current burst has not yet become large, and a queue Q that does
+ * not yet belong to the burst is activated shortly after the last time
+ * at which a new queue entered the burst list, then the function appends
+ * Q to the burst list
+ *
+ * . if, as a consequence of the previous step, the burst size reaches
+ * the large-burst threshold, then
+ *
+ * . all the queues in the burst list are marked as belonging to a
+ * large burst
+ *
+ * . the burst list is deleted; in fact, the burst list already served
+ * its purpose (keeping temporarily track of the queues in a burst,
+ * so as to be able to mark them as belonging to a large burst in the
+ * previous sub-step), and now is not needed any more
+ *
+ * . the device enters a large-burst mode
+ *
+ * . if a queue Q that does not belong to the burst is created while
+ * the device is in large-burst mode and shortly after the last time
+ * at which a queue either entered the burst list or was marked as
+ * belonging to the current large burst, then Q is immediately marked
+ * as belonging to a large burst.
+ *
+ * . if a queue Q that does not belong to the burst is created a while
+ * later, i.e., not shortly after, than the last time at which a queue
+ * either entered the burst list or was marked as belonging to the
+ * current large burst, then the current burst is deemed as finished and:
+ *
+ * . the large-burst mode is reset if set
+ *
+ * . the burst list is emptied
+ *
+ * . Q is inserted in the burst list, as Q may be the first queue
+ * in a possible new burst (then the burst list contains just Q
+ * after this step).
+ */
+static void bfq_handle_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+ /*
+ * If bfqq is already in the burst list or is part of a large
+ * burst, or finally has just been split, then there is
+ * nothing else to do.
+ */
+ if (!hlist_unhashed(&bfqq->burst_list_node) ||
+ bfq_bfqq_in_large_burst(bfqq) ||
+ time_is_after_eq_jiffies(bfqq->split_time +
+ msecs_to_jiffies(10)))
+ return;
+
+ /*
+ * If bfqq's creation happens late enough, or bfqq belongs to
+ * a different group than the burst group, then the current
+ * burst is finished, and related data structures must be
+ * reset.
+ *
+ * In this respect, consider the special case where bfqq is
+ * the very first queue created after BFQ is selected for this
+ * device. In this case, last_ins_in_burst and
+ * burst_parent_entity are not yet significant when we get
+ * here. But it is easy to verify that, whether or not the
+ * following condition is true, bfqq will end up being
+ * inserted into the burst list. In particular the list will
+ * happen to contain only bfqq. And this is exactly what has
+ * to happen, as bfqq may be the first queue of the first
+ * burst.
+ */
+ if (time_is_before_jiffies(bfqd->last_ins_in_burst +
+ bfqd->bfq_burst_interval) ||
+ bfqq->entity.parent != bfqd->burst_parent_entity) {
+ bfqd->large_burst = false;
+ bfq_reset_burst_list(bfqd, bfqq);
+ goto end;
+ }
+
+ /*
+ * If we get here, then bfqq is being activated shortly after the
+ * last queue. So, if the current burst is also large, we can mark
+ * bfqq as belonging to this large burst immediately.
+ */
+ if (bfqd->large_burst) {
+ bfq_mark_bfqq_in_large_burst(bfqq);
+ goto end;
+ }
+
+ /*
+ * If we get here, then a large-burst state has not yet been
+ * reached, but bfqq is being activated shortly after the last
+ * queue. Then we add bfqq to the burst.
+ */
+ bfq_add_to_burst(bfqd, bfqq);
+end:
+ /*
+ * At this point, bfqq either has been added to the current
+ * burst or has caused the current burst to terminate and a
+ * possible new burst to start. In particular, in the second
+ * case, bfqq has become the first queue in the possible new
+ * burst. In both cases last_ins_in_burst needs to be moved
+ * forward.
+ */
+ bfqd->last_ins_in_burst = jiffies;
+}
+
+static int bfq_bfqq_budget_left(struct bfq_queue *bfqq)
+{
+ struct bfq_entity *entity = &bfqq->entity;
+
+ return entity->budget - entity->service;
+}
+
+/*
+ * If enough samples have been computed, return the current max budget
+ * stored in bfqd, which is dynamically updated according to the
+ * estimated disk peak rate; otherwise return the default max budget
+ */
+static int bfq_max_budget(struct bfq_data *bfqd)
+{
+ if (bfqd->budgets_assigned < bfq_stats_min_budgets)
+ return bfq_default_max_budget;
+ else
+ return bfqd->bfq_max_budget;
+}
+
+/*
+ * Return min budget, which is a fraction of the current or default
+ * max budget (trying with 1/32)
+ */
+static int bfq_min_budget(struct bfq_data *bfqd)
+{
+ if (bfqd->budgets_assigned < bfq_stats_min_budgets)
+ return bfq_default_max_budget / 32;
+ else
+ return bfqd->bfq_max_budget / 32;
+}
+
+/*
+ * The next function, invoked after the input queue bfqq switches from
+ * idle to busy, updates the budget of bfqq. The function also tells
+ * whether the in-service queue should be expired, by returning
+ * true. The purpose of expiring the in-service queue is to give bfqq
+ * the chance to possibly preempt the in-service queue, and the reason
+ * for preempting the in-service queue is to achieve one of the two
+ * goals below.
+ *
+ * 1. Guarantee to bfqq its reserved bandwidth even if bfqq has
+ * expired because it has remained idle. In particular, bfqq may have
+ * expired for one of the following two reasons:
+ *
+ * - BFQQE_NO_MORE_REQUESTS bfqq did not enjoy any device idling
+ * and did not make it to issue a new request before its last
+ * request was served;
+ *
+ * - BFQQE_TOO_IDLE bfqq did enjoy device idling, but did not issue
+ * a new request before the expiration of the idling-time.
+ *
+ * Even if bfqq has expired for one of the above reasons, the process
+ * associated with the queue may be however issuing requests greedily,
+ * and thus be sensitive to the bandwidth it receives (bfqq may have
+ * remained idle for other reasons: CPU high load, bfqq not enjoying
+ * idling, I/O throttling somewhere in the path from the process to
+ * the I/O scheduler, ...). But if, after every expiration for one of
+ * the above two reasons, bfqq has to wait for the service of at least
+ * one full budget of another queue before being served again, then
+ * bfqq is likely to get a much lower bandwidth or resource time than
+ * its reserved ones. To address this issue, two countermeasures need
+ * to be taken.
+ *
+ * First, the budget and the timestamps of bfqq need to be updated in
+ * a special way on bfqq reactivation: they need to be updated as if
+ * bfqq did not remain idle and did not expire. In fact, if they are
+ * computed as if bfqq expired and remained idle until reactivation,
+ * then the process associated with bfqq is treated as if, instead of
+ * being greedy, it stopped issuing requests when bfqq remained idle,
+ * and restarts issuing requests only on this reactivation. In other
+ * words, the scheduler does not help the process recover the "service
+ * hole" between bfqq expiration and reactivation. As a consequence,
+ * the process receives a lower bandwidth than its reserved one. In
+ * contrast, to recover this hole, the budget must be updated as if
+ * bfqq was not expired at all before this reactivation, i.e., it must
+ * be set to the value of the remaining budget when bfqq was
+ * expired. Along the same line, timestamps need to be assigned the
+ * value they had the last time bfqq was selected for service, i.e.,
+ * before last expiration. Thus timestamps need to be back-shifted
+ * with respect to their normal computation (see [1] for more details
+ * on this tricky aspect).
+ *
+ * Secondly, to allow the process to recover the hole, the in-service
+ * queue must be expired too, to give bfqq the chance to preempt it
+ * immediately. In fact, if bfqq has to wait for a full budget of the
+ * in-service queue to be completed, then it may become impossible to
+ * let the process recover the hole, even if the back-shifted
+ * timestamps of bfqq are lower than those of the in-service queue. If
+ * this happens for most or all of the holes, then the process may not
+ * receive its reserved bandwidth. In this respect, it is worth noting
+ * that, being the service of outstanding requests unpreemptible, a
+ * little fraction of the holes may however be unrecoverable, thereby
+ * causing a little loss of bandwidth.
+ *
+ * The last important point is detecting whether bfqq does need this
+ * bandwidth recovery. In this respect, the next function deems the
+ * process associated with bfqq greedy, and thus allows it to recover
+ * the hole, if: 1) the process is waiting for the arrival of a new
+ * request (which implies that bfqq expired for one of the above two
+ * reasons), and 2) such a request has arrived soon. The first
+ * condition is controlled through the flag non_blocking_wait_rq,
+ * while the second through the flag arrived_in_time. If both
+ * conditions hold, then the function computes the budget in the
+ * above-described special way, and signals that the in-service queue
+ * should be expired. Timestamp back-shifting is done later in
+ * __bfq_activate_entity.
+ *
+ * 2. Reduce latency. Even if timestamps are not backshifted to let
+ * the process associated with bfqq recover a service hole, bfqq may
+ * however happen to have, after being (re)activated, a lower finish
+ * timestamp than the in-service queue. That is, the next budget of
+ * bfqq may have to be completed before the one of the in-service
+ * queue. If this is the case, then preempting the in-service queue
+ * allows this goal to be achieved, apart from the unpreemptible,
+ * outstanding requests mentioned above.
+ *
+ * Unfortunately, regardless of which of the above two goals one wants
+ * to achieve, service trees need first to be updated to know whether
+ * the in-service queue must be preempted. To have service trees
+ * correctly updated, the in-service queue must be expired and
+ * rescheduled, and bfqq must be scheduled too. This is one of the
+ * most costly operations (in future versions, the scheduling
+ * mechanism may be re-designed in such a way to make it possible to
+ * know whether preemption is needed without needing to update service
+ * trees). In addition, queue preemptions almost always cause random
+ * I/O, and thus loss of throughput. Because of these facts, the next
+ * function adopts the following simple scheme to avoid both costly
+ * operations and too frequent preemptions: it requests the expiration
+ * of the in-service queue (unconditionally) only for queues that need
+ * to recover a hole, or that either are weight-raised or deserve to
+ * be weight-raised.
+ */
+static bool bfq_bfqq_update_budg_for_activation(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq,
+ bool arrived_in_time,
+ bool wr_or_deserves_wr)
+{
+ struct bfq_entity *entity = &bfqq->entity;
+
+ if (bfq_bfqq_non_blocking_wait_rq(bfqq) && arrived_in_time) {
+ /*
+ * We do not clear the flag non_blocking_wait_rq here, as
+ * the latter is used in bfq_activate_bfqq to signal
+ * that timestamps need to be back-shifted (and is
+ * cleared right after).
+ */
+
+ /*
+ * In next assignment we rely on that either
+ * entity->service or entity->budget are not updated
+ * on expiration if bfqq is empty (see
+ * __bfq_bfqq_recalc_budget). Thus both quantities
+ * remain unchanged after such an expiration, and the
+ * following statement therefore assigns to
+ * entity->budget the remaining budget on such an
+ * expiration. For clarity, entity->service is not
+ * updated on expiration in any case, and, in normal
+ * operation, is reset only when bfqq is selected for
+ * service (see bfq_get_next_queue).
+ */
+ entity->budget = min_t(unsigned long,
+ bfq_bfqq_budget_left(bfqq),
+ bfqq->max_budget);
+
+ return true;
+ }
+
+ entity->budget = max_t(unsigned long, bfqq->max_budget,
+ bfq_serv_to_charge(bfqq->next_rq, bfqq));
+ bfq_clear_bfqq_non_blocking_wait_rq(bfqq);
+ return wr_or_deserves_wr;
+}
+
+static unsigned int bfq_wr_duration(struct bfq_data *bfqd)
+{
+ u64 dur;
+
+ if (bfqd->bfq_wr_max_time > 0)
+ return bfqd->bfq_wr_max_time;
+
+ dur = bfqd->RT_prod;
+ do_div(dur, bfqd->peak_rate);
+
+ /*
+ * Limit duration between 3 and 13 seconds. Tests show that
+ * higher values than 13 seconds often yield the opposite of
+ * the desired result, i.e., worsen responsiveness by letting
+ * non-interactive and non-soft-real-time applications
+ * preserve weight raising for a too long time interval.
+ *
+ * On the other end, lower values than 3 seconds make it
+ * difficult for most interactive tasks to complete their jobs
+ * before weight-raising finishes.
+ */
+ if (dur > msecs_to_jiffies(13000))
+ dur = msecs_to_jiffies(13000);
+ else if (dur < msecs_to_jiffies(3000))
+ dur = msecs_to_jiffies(3000);
+
+ return dur;
+}
+
+static void bfq_update_bfqq_wr_on_rq_arrival(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq,
+ unsigned int old_wr_coeff,
+ bool wr_or_deserves_wr,
+ bool interactive,
+ bool in_burst,
+ bool soft_rt)
+{
+ if (old_wr_coeff == 1 && wr_or_deserves_wr) {
+ /* start a weight-raising period */
+ if (interactive) {
+ bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+ bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+ } else {
+ bfqq->wr_start_at_switch_to_srt = jiffies;
+ bfqq->wr_coeff = bfqd->bfq_wr_coeff *
+ BFQ_SOFTRT_WEIGHT_FACTOR;
+ bfqq->wr_cur_max_time =
+ bfqd->bfq_wr_rt_max_time;
+ }
+
+ /*
+ * If needed, further reduce budget to make sure it is
+ * close to bfqq's backlog, so as to reduce the
+ * scheduling-error component due to a too large
+ * budget. Do not care about throughput consequences,
+ * but only about latency. Finally, do not assign a
+ * too small budget either, to avoid increasing
+ * latency by causing too frequent expirations.
+ */
+ bfqq->entity.budget = min_t(unsigned long,
+ bfqq->entity.budget,
+ 2 * bfq_min_budget(bfqd));
+ } else if (old_wr_coeff > 1) {
+ if (interactive) { /* update wr coeff and duration */
+ bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+ bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+ } else if (in_burst)
+ bfqq->wr_coeff = 1;
+ else if (soft_rt) {
+ /*
+ * The application is now or still meeting the
+ * requirements for being deemed soft rt. We
+ * can then correctly and safely (re)charge
+ * the weight-raising duration for the
+ * application with the weight-raising
+ * duration for soft rt applications.
+ *
+ * In particular, doing this recharge now, i.e.,
+ * before the weight-raising period for the
+ * application finishes, reduces the probability
+ * of the following negative scenario:
+ * 1) the weight of a soft rt application is
+ * raised at startup (as for any newly
+ * created application),
+ * 2) since the application is not interactive,
+ * at a certain time weight-raising is
+ * stopped for the application,
+ * 3) at that time the application happens to
+ * still have pending requests, and hence
+ * is destined to not have a chance to be
+ * deemed soft rt before these requests are
+ * completed (see the comments to the
+ * function bfq_bfqq_softrt_next_start()
+ * for details on soft rt detection),
+ * 4) these pending requests experience a high
+ * latency because the application is not
+ * weight-raised while they are pending.
+ */
+ if (bfqq->wr_cur_max_time !=
+ bfqd->bfq_wr_rt_max_time) {
+ bfqq->wr_start_at_switch_to_srt =
+ bfqq->last_wr_start_finish;
+
+ bfqq->wr_cur_max_time =
+ bfqd->bfq_wr_rt_max_time;
+ bfqq->wr_coeff = bfqd->bfq_wr_coeff *
+ BFQ_SOFTRT_WEIGHT_FACTOR;
+ }
+ bfqq->last_wr_start_finish = jiffies;
+ }
+ }
+}
+
+static bool bfq_bfqq_idle_for_long_time(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq)
+{
+ return bfqq->dispatched == 0 &&
+ time_is_before_jiffies(
+ bfqq->budget_timeout +
+ bfqd->bfq_wr_min_idle_time);
+}
+
+static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq,
+ int old_wr_coeff,
+ struct request *rq,
+ bool *interactive)
+{
+ bool soft_rt, in_burst, wr_or_deserves_wr,
+ bfqq_wants_to_preempt,
+ idle_for_long_time = bfq_bfqq_idle_for_long_time(bfqd, bfqq),
+ /*
+ * See the comments on
+ * bfq_bfqq_update_budg_for_activation for
+ * details on the usage of the next variable.
+ */
+ arrived_in_time = ktime_get_ns() <=
+ bfqq->ttime.last_end_request +
+ bfqd->bfq_slice_idle * 3;
+
+ bfqg_stats_update_io_add(bfqq_group(RQ_BFQQ(rq)), bfqq, rq->cmd_flags);
+
+ /*
+ * bfqq deserves to be weight-raised if:
+ * - it is sync,
+ * - it does not belong to a large burst,
+ * - it has been idle for enough time or is soft real-time,
+ * - is linked to a bfq_io_cq (it is not shared in any sense).
+ */
+ in_burst = bfq_bfqq_in_large_burst(bfqq);
+ soft_rt = bfqd->bfq_wr_max_softrt_rate > 0 &&
+ !in_burst &&
+ time_is_before_jiffies(bfqq->soft_rt_next_start);
+ *interactive = !in_burst && idle_for_long_time;
+ wr_or_deserves_wr = bfqd->low_latency &&
+ (bfqq->wr_coeff > 1 ||
+ (bfq_bfqq_sync(bfqq) &&
+ bfqq->bic && (*interactive || soft_rt)));
+
+ /*
+ * Using the last flag, update budget and check whether bfqq
+ * may want to preempt the in-service queue.
+ */
+ bfqq_wants_to_preempt =
+ bfq_bfqq_update_budg_for_activation(bfqd, bfqq,
+ arrived_in_time,
+ wr_or_deserves_wr);
+
+ /*
+ * If bfqq happened to be activated in a burst, but has been
+ * idle for much more than an interactive queue, then we
+ * assume that, in the overall I/O initiated in the burst, the
+ * I/O associated with bfqq is finished. So bfqq does not need
+ * to be treated as a queue belonging to a burst
+ * anymore. Accordingly, we reset bfqq's in_large_burst flag
+ * if set, and remove bfqq from the burst list if it's
+ * there. We do not decrement burst_size, because the fact
+ * that bfqq does not need to belong to the burst list any
+ * more does not invalidate the fact that bfqq was created in
+ * a burst.
+ */
+ if (likely(!bfq_bfqq_just_created(bfqq)) &&
+ idle_for_long_time &&
+ time_is_before_jiffies(
+ bfqq->budget_timeout +
+ msecs_to_jiffies(10000))) {
+ hlist_del_init(&bfqq->burst_list_node);
+ bfq_clear_bfqq_in_large_burst(bfqq);
+ }
+
+ bfq_clear_bfqq_just_created(bfqq);
+
+
+ if (!bfq_bfqq_IO_bound(bfqq)) {
+ if (arrived_in_time) {
+ bfqq->requests_within_timer++;
+ if (bfqq->requests_within_timer >=
+ bfqd->bfq_requests_within_timer)
+ bfq_mark_bfqq_IO_bound(bfqq);
+ } else
+ bfqq->requests_within_timer = 0;
+ }
+
+ if (bfqd->low_latency) {
+ if (unlikely(time_is_after_jiffies(bfqq->split_time)))
+ /* wraparound */
+ bfqq->split_time =
+ jiffies - bfqd->bfq_wr_min_idle_time - 1;
+
+ if (time_is_before_jiffies(bfqq->split_time +
+ bfqd->bfq_wr_min_idle_time)) {
+ bfq_update_bfqq_wr_on_rq_arrival(bfqd, bfqq,
+ old_wr_coeff,
+ wr_or_deserves_wr,
+ *interactive,
+ in_burst,
+ soft_rt);
+
+ if (old_wr_coeff != bfqq->wr_coeff)
+ bfqq->entity.prio_changed = 1;
+ }
+ }
+
+ bfqq->last_idle_bklogged = jiffies;
+ bfqq->service_from_backlogged = 0;
+ bfq_clear_bfqq_softrt_update(bfqq);
+
+ bfq_add_bfqq_busy(bfqd, bfqq);
+
+ /*
+ * Expire in-service queue only if preemption may be needed
+ * for guarantees. In this respect, the function
+ * next_queue_may_preempt just checks a simple, necessary
+ * condition, and not a sufficient condition based on
+ * timestamps. In fact, for the latter condition to be
+ * evaluated, timestamps would need first to be updated, and
+ * this operation is quite costly (see the comments on the
+ * function bfq_bfqq_update_budg_for_activation).
+ */
+ if (bfqd->in_service_queue && bfqq_wants_to_preempt &&
+ bfqd->in_service_queue->wr_coeff < bfqq->wr_coeff &&
+ next_queue_may_preempt(bfqd))
+ bfq_bfqq_expire(bfqd, bfqd->in_service_queue,
+ false, BFQQE_PREEMPTED);
+}
+
+static void bfq_add_request(struct request *rq)
+{
+ struct bfq_queue *bfqq = RQ_BFQQ(rq);
+ struct bfq_data *bfqd = bfqq->bfqd;
+ struct request *next_rq, *prev;
+ unsigned int old_wr_coeff = bfqq->wr_coeff;
+ bool interactive = false;
+
+ bfq_log_bfqq(bfqd, bfqq, "add_request %d", rq_is_sync(rq));
+ bfqq->queued[rq_is_sync(rq)]++;
+ bfqd->queued++;
+
+ elv_rb_add(&bfqq->sort_list, rq);
+
+ /*
+ * Check if this request is a better next-serve candidate.
+ */
+ prev = bfqq->next_rq;
+ next_rq = bfq_choose_req(bfqd, bfqq->next_rq, rq, bfqd->last_position);
+ bfqq->next_rq = next_rq;
+
+ /*
+ * Adjust priority tree position, if next_rq changes.
+ */
+ if (prev != bfqq->next_rq)
+ bfq_pos_tree_add_move(bfqd, bfqq);
+
+ if (!bfq_bfqq_busy(bfqq)) /* switching to busy ... */
+ bfq_bfqq_handle_idle_busy_switch(bfqd, bfqq, old_wr_coeff,
+ rq, &interactive);
+ else {
+ if (bfqd->low_latency && old_wr_coeff == 1 && !rq_is_sync(rq) &&
+ time_is_before_jiffies(
+ bfqq->last_wr_start_finish +
+ bfqd->bfq_wr_min_inter_arr_async)) {
+ bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+ bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+
+ bfqd->wr_busy_queues++;
+ bfqq->entity.prio_changed = 1;
+ }
+ if (prev != bfqq->next_rq)
+ bfq_updated_next_req(bfqd, bfqq);
+ }
+
+ /*
+ * Assign jiffies to last_wr_start_finish in the following
+ * cases:
+ *
+ * . if bfqq is not going to be weight-raised, because, for
+ * non weight-raised queues, last_wr_start_finish stores the
+ * arrival time of the last request; as of now, this piece
+ * of information is used only for deciding whether to
+ * weight-raise async queues
+ *
+ * . if bfqq is not weight-raised, because, if bfqq is now
+ * switching to weight-raised, then last_wr_start_finish
+ * stores the time when weight-raising starts
+ *
+ * . if bfqq is interactive, because, regardless of whether
+ * bfqq is currently weight-raised, the weight-raising
+ * period must start or restart (this case is considered
+ * separately because it is not detected by the above
+ * conditions, if bfqq is already weight-raised)
+ *
+ * last_wr_start_finish has to be updated also if bfqq is soft
+ * real-time, because the weight-raising period is constantly
+ * restarted on idle-to-busy transitions for these queues, but
+ * this is already done in bfq_bfqq_handle_idle_busy_switch if
+ * needed.
+ */
+ if (bfqd->low_latency &&
+ (old_wr_coeff == 1 || bfqq->wr_coeff == 1 || interactive))
+ bfqq->last_wr_start_finish = jiffies;
+}
+
+static struct request *bfq_find_rq_fmerge(struct bfq_data *bfqd,
+ struct bio *bio,
+ struct request_queue *q)
+{
+ struct bfq_queue *bfqq = bfqd->bio_bfqq;
+
+
+ if (bfqq)
+ return elv_rb_find(&bfqq->sort_list, bio_end_sector(bio));
+
+ return NULL;
+}
+
+static sector_t get_sdist(sector_t last_pos, struct request *rq)
+{
+ if (last_pos)
+ return abs(blk_rq_pos(rq) - last_pos);
+
+ return 0;
+}
+
+#if 0 /* Still not clear if we can do without next two functions */
+static void bfq_activate_request(struct request_queue *q, struct request *rq)
+{
+ struct bfq_data *bfqd = q->elevator->elevator_data;
+
+ bfqd->rq_in_driver++;
+}
+
+static void bfq_deactivate_request(struct request_queue *q, struct request *rq)
+{
+ struct bfq_data *bfqd = q->elevator->elevator_data;
+
+ bfqd->rq_in_driver--;
+}
+#endif
+
+static void bfq_remove_request(struct request_queue *q,
+ struct request *rq)
+{
+ struct bfq_queue *bfqq = RQ_BFQQ(rq);
+ struct bfq_data *bfqd = bfqq->bfqd;
+ const int sync = rq_is_sync(rq);
+
+ if (bfqq->next_rq == rq) {
+ bfqq->next_rq = bfq_find_next_rq(bfqd, bfqq, rq);
+ bfq_updated_next_req(bfqd, bfqq);
+ }
+
+ if (rq->queuelist.prev != &rq->queuelist)
+ list_del_init(&rq->queuelist);
+ bfqq->queued[sync]--;
+ bfqd->queued--;
+ elv_rb_del(&bfqq->sort_list, rq);
+
+ elv_rqhash_del(q, rq);
+ if (q->last_merge == rq)
+ q->last_merge = NULL;
+
+ if (RB_EMPTY_ROOT(&bfqq->sort_list)) {
+ bfqq->next_rq = NULL;
+
+ if (bfq_bfqq_busy(bfqq) && bfqq != bfqd->in_service_queue) {
+ bfq_del_bfqq_busy(bfqd, bfqq, false);
+ /*
+ * bfqq emptied. In normal operation, when
+ * bfqq is empty, bfqq->entity.service and
+ * bfqq->entity.budget must contain,
+ * respectively, the service received and the
+ * budget used last time bfqq emptied. These
+ * facts do not hold in this case, as at least
+ * this last removal occurred while bfqq is
+ * not in service. To avoid inconsistencies,
+ * reset both bfqq->entity.service and
+ * bfqq->entity.budget, if bfqq has still a
+ * process that may issue I/O requests to it.
+ */
+ bfqq->entity.budget = bfqq->entity.service = 0;
+ }
+
+ /*
+ * Remove queue from request-position tree as it is empty.
+ */
+ if (bfqq->pos_root) {
+ rb_erase(&bfqq->pos_node, bfqq->pos_root);
+ bfqq->pos_root = NULL;
+ }
+ }
+
+ if (rq->cmd_flags & REQ_META)
+ bfqq->meta_pending--;
+
+ bfqg_stats_update_io_remove(bfqq_group(bfqq), rq->cmd_flags);
+}
+
+static bool bfq_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio)
+{
+ struct request_queue *q = hctx->queue;
+ struct bfq_data *bfqd = q->elevator->elevator_data;
+ struct request *free = NULL;
+ /*
+ * bfq_bic_lookup grabs the queue_lock: invoke it now and
+ * store its return value for later use, to avoid nesting
+ * queue_lock inside the bfqd->lock. We assume that the bic
+ * returned by bfq_bic_lookup does not go away before
+ * bfqd->lock is taken.
+ */
+ struct bfq_io_cq *bic = bfq_bic_lookup(bfqd, current->io_context, q);
+ bool ret;
+
+ spin_lock_irq(&bfqd->lock);
+
+ if (bic)
+ bfqd->bio_bfqq = bic_to_bfqq(bic, op_is_sync(bio->bi_opf));
+ else
+ bfqd->bio_bfqq = NULL;
+ bfqd->bio_bic = bic;
+
+ ret = blk_mq_sched_try_merge(q, bio, &free);
+
+ if (free)
+ blk_mq_free_request(free);
+ spin_unlock_irq(&bfqd->lock);
+
+ return ret;
+}
+
+static int bfq_request_merge(struct request_queue *q, struct request **req,
+ struct bio *bio)
+{
+ struct bfq_data *bfqd = q->elevator->elevator_data;
+ struct request *__rq;
+
+ __rq = bfq_find_rq_fmerge(bfqd, bio, q);
+ if (__rq && elv_bio_merge_ok(__rq, bio)) {
+ *req = __rq;
+ return ELEVATOR_FRONT_MERGE;
+ }
+
+ return ELEVATOR_NO_MERGE;
+}
+
+static void bfq_request_merged(struct request_queue *q, struct request *req,
+ enum elv_merge type)
+{
+ if (type == ELEVATOR_FRONT_MERGE &&
+ rb_prev(&req->rb_node) &&
+ blk_rq_pos(req) <
+ blk_rq_pos(container_of(rb_prev(&req->rb_node),
+ struct request, rb_node))) {
+ struct bfq_queue *bfqq = RQ_BFQQ(req);
+ struct bfq_data *bfqd = bfqq->bfqd;
+ struct request *prev, *next_rq;
+
+ /* Reposition request in its sort_list */
+ elv_rb_del(&bfqq->sort_list, req);
+ elv_rb_add(&bfqq->sort_list, req);
+
+ /* Choose next request to be served for bfqq */
+ prev = bfqq->next_rq;
+ next_rq = bfq_choose_req(bfqd, bfqq->next_rq, req,
+ bfqd->last_position);
+ bfqq->next_rq = next_rq;
+ /*
+ * If next_rq changes, update both the queue's budget to
+ * fit the new request and the queue's position in its
+ * rq_pos_tree.
+ */
+ if (prev != bfqq->next_rq) {
+ bfq_updated_next_req(bfqd, bfqq);
+ bfq_pos_tree_add_move(bfqd, bfqq);
+ }
+ }
+}
+
+static void bfq_requests_merged(struct request_queue *q, struct request *rq,
+ struct request *next)
+{
+ struct bfq_queue *bfqq = RQ_BFQQ(rq), *next_bfqq = RQ_BFQQ(next);
+
+ if (!RB_EMPTY_NODE(&rq->rb_node))
+ goto end;
+ spin_lock_irq(&bfqq->bfqd->lock);
+
+ /*
+ * If next and rq belong to the same bfq_queue and next is older
+ * than rq, then reposition rq in the fifo (by substituting next
+ * with rq). Otherwise, if next and rq belong to different
+ * bfq_queues, never reposition rq: in fact, we would have to
+ * reposition it with respect to next's position in its own fifo,
+ * which would most certainly be too expensive with respect to
+ * the benefits.
+ */
+ if (bfqq == next_bfqq &&
+ !list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
+ next->fifo_time < rq->fifo_time) {
+ list_del_init(&rq->queuelist);
+ list_replace_init(&next->queuelist, &rq->queuelist);
+ rq->fifo_time = next->fifo_time;
+ }
+
+ if (bfqq->next_rq == next)
+ bfqq->next_rq = rq;
+
+ bfq_remove_request(q, next);
+
+ spin_unlock_irq(&bfqq->bfqd->lock);
+end:
+ bfqg_stats_update_io_merged(bfqq_group(bfqq), next->cmd_flags);
+}
+
+/* Must be called with bfqq != NULL */
+static void bfq_bfqq_end_wr(struct bfq_queue *bfqq)
+{
+ if (bfq_bfqq_busy(bfqq))
+ bfqq->bfqd->wr_busy_queues--;
+ bfqq->wr_coeff = 1;
+ bfqq->wr_cur_max_time = 0;
+ bfqq->last_wr_start_finish = jiffies;
+ /*
+ * Trigger a weight change on the next invocation of
+ * __bfq_entity_update_weight_prio.
+ */
+ bfqq->entity.prio_changed = 1;
+}
+
+void bfq_end_wr_async_queues(struct bfq_data *bfqd,
+ struct bfq_group *bfqg)
+{
+ int i, j;
+
+ for (i = 0; i < 2; i++)
+ for (j = 0; j < IOPRIO_BE_NR; j++)
+ if (bfqg->async_bfqq[i][j])
+ bfq_bfqq_end_wr(bfqg->async_bfqq[i][j]);
+ if (bfqg->async_idle_bfqq)
+ bfq_bfqq_end_wr(bfqg->async_idle_bfqq);
+}
+
+static void bfq_end_wr(struct bfq_data *bfqd)
+{
+ struct bfq_queue *bfqq;
+
+ spin_lock_irq(&bfqd->lock);
+
+ list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list)
+ bfq_bfqq_end_wr(bfqq);
+ list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list)
+ bfq_bfqq_end_wr(bfqq);
+ bfq_end_wr_async(bfqd);
+
+ spin_unlock_irq(&bfqd->lock);
+}
+
+static sector_t bfq_io_struct_pos(void *io_struct, bool request)
+{
+ if (request)
+ return blk_rq_pos(io_struct);
+ else
+ return ((struct bio *)io_struct)->bi_iter.bi_sector;
+}
+
+static int bfq_rq_close_to_sector(void *io_struct, bool request,
+ sector_t sector)
+{
+ return abs(bfq_io_struct_pos(io_struct, request) - sector) <=
+ BFQQ_CLOSE_THR;
+}
+
+static struct bfq_queue *bfqq_find_close(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq,
+ sector_t sector)
+{
+ struct rb_root *root = &bfq_bfqq_to_bfqg(bfqq)->rq_pos_tree;
+ struct rb_node *parent, *node;
+ struct bfq_queue *__bfqq;
+
+ if (RB_EMPTY_ROOT(root))
+ return NULL;
+
+ /*
+ * First, if we find a request starting at the end of the last
+ * request, choose it.
+ */
+ __bfqq = bfq_rq_pos_tree_lookup(bfqd, root, sector, &parent, NULL);
+ if (__bfqq)
+ return __bfqq;
+
+ /*
+ * If the exact sector wasn't found, the parent of the NULL leaf
+ * will contain the closest sector (rq_pos_tree sorted by
+ * next_request position).
+ */
+ __bfqq = rb_entry(parent, struct bfq_queue, pos_node);
+ if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector))
+ return __bfqq;
+
+ if (blk_rq_pos(__bfqq->next_rq) < sector)
+ node = rb_next(&__bfqq->pos_node);
+ else
+ node = rb_prev(&__bfqq->pos_node);
+ if (!node)
+ return NULL;
+
+ __bfqq = rb_entry(node, struct bfq_queue, pos_node);
+ if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector))
+ return __bfqq;
+
+ return NULL;
+}
+
+static struct bfq_queue *bfq_find_close_cooperator(struct bfq_data *bfqd,
+ struct bfq_queue *cur_bfqq,
+ sector_t sector)
+{
+ struct bfq_queue *bfqq;
+
+ /*
+ * We shall notice if some of the queues are cooperating,
+ * e.g., working closely on the same area of the device. In
+ * that case, we can group them together and: 1) don't waste
+ * time idling, and 2) serve the union of their requests in
+ * the best possible order for throughput.
+ */
+ bfqq = bfqq_find_close(bfqd, cur_bfqq, sector);
+ if (!bfqq || bfqq == cur_bfqq)
+ return NULL;
+
+ return bfqq;
+}
+
+static struct bfq_queue *
+bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
+{
+ int process_refs, new_process_refs;
+ struct bfq_queue *__bfqq;
+
+ /*
+ * If there are no process references on the new_bfqq, then it is
+ * unsafe to follow the ->new_bfqq chain as other bfqq's in the chain
+ * may have dropped their last reference (not just their last process
+ * reference).
+ */
+ if (!bfqq_process_refs(new_bfqq))
+ return NULL;
+
+ /* Avoid a circular list and skip interim queue merges. */
+ while ((__bfqq = new_bfqq->new_bfqq)) {
+ if (__bfqq == bfqq)
+ return NULL;
+ new_bfqq = __bfqq;
+ }
+
+ process_refs = bfqq_process_refs(bfqq);
+ new_process_refs = bfqq_process_refs(new_bfqq);
+ /*
+ * If the process for the bfqq has gone away, there is no
+ * sense in merging the queues.
+ */
+ if (process_refs == 0 || new_process_refs == 0)
+ return NULL;
+
+ bfq_log_bfqq(bfqq->bfqd, bfqq, "scheduling merge with queue %d",
+ new_bfqq->pid);
+
+ /*
+ * Merging is just a redirection: the requests of the process
+ * owning one of the two queues are redirected to the other queue.
+ * The latter queue, in its turn, is set as shared if this is the
+ * first time that the requests of some process are redirected to
+ * it.
+ *
+ * We redirect bfqq to new_bfqq and not the opposite, because
+ * we are in the context of the process owning bfqq, thus we
+ * have the io_cq of this process. So we can immediately
+ * configure this io_cq to redirect the requests of the
+ * process to new_bfqq. In contrast, the io_cq of new_bfqq is
+ * not available any more (new_bfqq->bic == NULL).
+ *
+ * Anyway, even in case new_bfqq coincides with the in-service
+ * queue, redirecting requests the in-service queue is the
+ * best option, as we feed the in-service queue with new
+ * requests close to the last request served and, by doing so,
+ * are likely to increase the throughput.
+ */
+ bfqq->new_bfqq = new_bfqq;
+ new_bfqq->ref += process_refs;
+ return new_bfqq;
+}
+
+static bool bfq_may_be_close_cooperator(struct bfq_queue *bfqq,
+ struct bfq_queue *new_bfqq)
+{
+ if (bfq_class_idle(bfqq) || bfq_class_idle(new_bfqq) ||
+ (bfqq->ioprio_class != new_bfqq->ioprio_class))
+ return false;
+
+ /*
+ * If either of the queues has already been detected as seeky,
+ * then merging it with the other queue is unlikely to lead to
+ * sequential I/O.
+ */
+ if (BFQQ_SEEKY(bfqq) || BFQQ_SEEKY(new_bfqq))
+ return false;
+
+ /*
+ * Interleaved I/O is known to be done by (some) applications
+ * only for reads, so it does not make sense to merge async
+ * queues.
+ */
+ if (!bfq_bfqq_sync(bfqq) || !bfq_bfqq_sync(new_bfqq))
+ return false;
+
+ return true;
+}
+
+/*
+ * If this function returns true, then bfqq cannot be merged. The idea
+ * is that true cooperation happens very early after processes start
+ * to do I/O. Usually, late cooperations are just accidental false
+ * positives. In case bfqq is weight-raised, such false positives
+ * would evidently degrade latency guarantees for bfqq.
+ */
+static bool wr_from_too_long(struct bfq_queue *bfqq)
+{
+ return bfqq->wr_coeff > 1 &&
+ time_is_before_jiffies(bfqq->last_wr_start_finish +
+ msecs_to_jiffies(100));
+}
+
+/*
+ * Attempt to schedule a merge of bfqq with the currently in-service
+ * queue or with a close queue among the scheduled queues. Return
+ * NULL if no merge was scheduled, a pointer to the shared bfq_queue
+ * structure otherwise.
+ *
+ * The OOM queue is not allowed to participate to cooperation: in fact, since
+ * the requests temporarily redirected to the OOM queue could be redirected
+ * again to dedicated queues at any time, the state needed to correctly
+ * handle merging with the OOM queue would be quite complex and expensive
+ * to maintain. Besides, in such a critical condition as an out of memory,
+ * the benefits of queue merging may be little relevant, or even negligible.
+ *
+ * Weight-raised queues can be merged only if their weight-raising
+ * period has just started. In fact cooperating processes are usually
+ * started together. Thus, with this filter we avoid false positives
+ * that would jeopardize low-latency guarantees.
+ *
+ * WARNING: queue merging may impair fairness among non-weight raised
+ * queues, for at least two reasons: 1) the original weight of a
+ * merged queue may change during the merged state, 2) even being the
+ * weight the same, a merged queue may be bloated with many more
+ * requests than the ones produced by its originally-associated
+ * process.
+ */
+static struct bfq_queue *
+bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ void *io_struct, bool request)
+{
+ struct bfq_queue *in_service_bfqq, *new_bfqq;
+
+ if (bfqq->new_bfqq)
+ return bfqq->new_bfqq;
+
+ if (!io_struct ||
+ wr_from_too_long(bfqq) ||
+ unlikely(bfqq == &bfqd->oom_bfqq))
+ return NULL;
+
+ /* If there is only one backlogged queue, don't search. */
+ if (bfqd->busy_queues == 1)
+ return NULL;
+
+ in_service_bfqq = bfqd->in_service_queue;
+
+ if (!in_service_bfqq || in_service_bfqq == bfqq
+ || wr_from_too_long(in_service_bfqq) ||
+ unlikely(in_service_bfqq == &bfqd->oom_bfqq))
+ goto check_scheduled;
+
+ if (bfq_rq_close_to_sector(io_struct, request, bfqd->last_position) &&
+ bfqq->entity.parent == in_service_bfqq->entity.parent &&
+ bfq_may_be_close_cooperator(bfqq, in_service_bfqq)) {
+ new_bfqq = bfq_setup_merge(bfqq, in_service_bfqq);
+ if (new_bfqq)
+ return new_bfqq;
+ }
+ /*
+ * Check whether there is a cooperator among currently scheduled
+ * queues. The only thing we need is that the bio/request is not
+ * NULL, as we need it to establish whether a cooperator exists.
+ */
+check_scheduled:
+ new_bfqq = bfq_find_close_cooperator(bfqd, bfqq,
+ bfq_io_struct_pos(io_struct, request));
+
+ if (new_bfqq && !wr_from_too_long(new_bfqq) &&
+ likely(new_bfqq != &bfqd->oom_bfqq) &&
+ bfq_may_be_close_cooperator(bfqq, new_bfqq))
+ return bfq_setup_merge(bfqq, new_bfqq);
+
+ return NULL;
+}
+
+static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
+{
+ struct bfq_io_cq *bic = bfqq->bic;
+
+ /*
+ * If !bfqq->bic, the queue is already shared or its requests
+ * have already been redirected to a shared queue; both idle window
+ * and weight raising state have already been saved. Do nothing.
+ */
+ if (!bic)
+ return;
+
+ bic->saved_ttime = bfqq->ttime;
+ bic->saved_idle_window = bfq_bfqq_idle_window(bfqq);
+ bic->saved_IO_bound = bfq_bfqq_IO_bound(bfqq);
+ bic->saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq);
+ bic->was_in_burst_list = !hlist_unhashed(&bfqq->burst_list_node);
+ bic->saved_wr_coeff = bfqq->wr_coeff;
+ bic->saved_wr_start_at_switch_to_srt = bfqq->wr_start_at_switch_to_srt;
+ bic->saved_last_wr_start_finish = bfqq->last_wr_start_finish;
+ bic->saved_wr_cur_max_time = bfqq->wr_cur_max_time;
+}
+
+static void
+bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
+ struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
+{
+ bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu",
+ (unsigned long)new_bfqq->pid);
+ /* Save weight raising and idle window of the merged queues */
+ bfq_bfqq_save_state(bfqq);
+ bfq_bfqq_save_state(new_bfqq);
+ if (bfq_bfqq_IO_bound(bfqq))
+ bfq_mark_bfqq_IO_bound(new_bfqq);
+ bfq_clear_bfqq_IO_bound(bfqq);
+
+ /*
+ * If bfqq is weight-raised, then let new_bfqq inherit
+ * weight-raising. To reduce false positives, neglect the case
+ * where bfqq has just been created, but has not yet made it
+ * to be weight-raised (which may happen because EQM may merge
+ * bfqq even before bfq_add_request is executed for the first
+ * time for bfqq). Handling this case would however be very
+ * easy, thanks to the flag just_created.
+ */
+ if (new_bfqq->wr_coeff == 1 && bfqq->wr_coeff > 1) {
+ new_bfqq->wr_coeff = bfqq->wr_coeff;
+ new_bfqq->wr_cur_max_time = bfqq->wr_cur_max_time;
+ new_bfqq->last_wr_start_finish = bfqq->last_wr_start_finish;
+ new_bfqq->wr_start_at_switch_to_srt =
+ bfqq->wr_start_at_switch_to_srt;
+ if (bfq_bfqq_busy(new_bfqq))
+ bfqd->wr_busy_queues++;
+ new_bfqq->entity.prio_changed = 1;
+ }
+
+ if (bfqq->wr_coeff > 1) { /* bfqq has given its wr to new_bfqq */
+ bfqq->wr_coeff = 1;
+ bfqq->entity.prio_changed = 1;
+ if (bfq_bfqq_busy(bfqq))
+ bfqd->wr_busy_queues--;
+ }
+
+ bfq_log_bfqq(bfqd, new_bfqq, "merge_bfqqs: wr_busy %d",
+ bfqd->wr_busy_queues);
+
+ /*
+ * Merge queues (that is, let bic redirect its requests to new_bfqq)
+ */
+ bic_set_bfqq(bic, new_bfqq, 1);
+ bfq_mark_bfqq_coop(new_bfqq);
+ /*
+ * new_bfqq now belongs to at least two bics (it is a shared queue):
+ * set new_bfqq->bic to NULL. bfqq either:
+ * - does not belong to any bic any more, and hence bfqq->bic must
+ * be set to NULL, or
+ * - is a queue whose owning bics have already been redirected to a
+ * different queue, hence the queue is destined to not belong to
+ * any bic soon and bfqq->bic is already NULL (therefore the next
+ * assignment causes no harm).
+ */
+ new_bfqq->bic = NULL;
+ bfqq->bic = NULL;
+ /* release process reference to bfqq */
+ bfq_put_queue(bfqq);
+}
+
+static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
+ struct bio *bio)
+{
+ struct bfq_data *bfqd = q->elevator->elevator_data;
+ bool is_sync = op_is_sync(bio->bi_opf);
+ struct bfq_queue *bfqq = bfqd->bio_bfqq, *new_bfqq;
+
+ /*
+ * Disallow merge of a sync bio into an async request.
+ */
+ if (is_sync && !rq_is_sync(rq))
+ return false;
+
+ /*
+ * Lookup the bfqq that this bio will be queued with. Allow
+ * merge only if rq is queued there.
+ */
+ if (!bfqq)
+ return false;
+
+ /*
+ * We take advantage of this function to perform an early merge
+ * of the queues of possible cooperating processes.
+ */
+ new_bfqq = bfq_setup_cooperator(bfqd, bfqq, bio, false);
+ if (new_bfqq) {
+ /*
+ * bic still points to bfqq, then it has not yet been
+ * redirected to some other bfq_queue, and a queue
+ * merge beween bfqq and new_bfqq can be safely
+ * fulfillled, i.e., bic can be redirected to new_bfqq
+ * and bfqq can be put.
+ */
+ bfq_merge_bfqqs(bfqd, bfqd->bio_bic, bfqq,
+ new_bfqq);
+ /*
+ * If we get here, bio will be queued into new_queue,
+ * so use new_bfqq to decide whether bio and rq can be
+ * merged.
+ */
+ bfqq = new_bfqq;
+
+ /*
+ * Change also bqfd->bio_bfqq, as
+ * bfqd->bio_bic now points to new_bfqq, and
+ * this function may be invoked again (and then may
+ * use again bqfd->bio_bfqq).
+ */
+ bfqd->bio_bfqq = bfqq;
+ }
+
+ return bfqq == RQ_BFQQ(rq);
+}
+
+/*
+ * Set the maximum time for the in-service queue to consume its
+ * budget. This prevents seeky processes from lowering the throughput.
+ * In practice, a time-slice service scheme is used with seeky
+ * processes.
+ */
+static void bfq_set_budget_timeout(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq)
+{
+ unsigned int timeout_coeff;
+
+ if (bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time)
+ timeout_coeff = 1;
+ else
+ timeout_coeff = bfqq->entity.weight / bfqq->entity.orig_weight;
+
+ bfqd->last_budget_start = ktime_get();
+
+ bfqq->budget_timeout = jiffies +
+ bfqd->bfq_timeout * timeout_coeff;
+}
+
+static void __bfq_set_in_service_queue(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq)
+{
+ if (bfqq) {
+ bfqg_stats_update_avg_queue_size(bfqq_group(bfqq));
+ bfq_clear_bfqq_fifo_expire(bfqq);
+
+ bfqd->budgets_assigned = (bfqd->budgets_assigned * 7 + 256) / 8;
+
+ if (time_is_before_jiffies(bfqq->last_wr_start_finish) &&
+ bfqq->wr_coeff > 1 &&
+ bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time &&
+ time_is_before_jiffies(bfqq->budget_timeout)) {
+ /*
+ * For soft real-time queues, move the start
+ * of the weight-raising period forward by the
+ * time the queue has not received any
+ * service. Otherwise, a relatively long
+ * service delay is likely to cause the
+ * weight-raising period of the queue to end,
+ * because of the short duration of the
+ * weight-raising period of a soft real-time
+ * queue. It is worth noting that this move
+ * is not so dangerous for the other queues,
+ * because soft real-time queues are not
+ * greedy.
+ *
+ * To not add a further variable, we use the
+ * overloaded field budget_timeout to
+ * determine for how long the queue has not
+ * received service, i.e., how much time has
+ * elapsed since the queue expired. However,
+ * this is a little imprecise, because
+ * budget_timeout is set to jiffies if bfqq
+ * not only expires, but also remains with no
+ * request.
+ */
+ if (time_after(bfqq->budget_timeout,
+ bfqq->last_wr_start_finish))
+ bfqq->last_wr_start_finish +=
+ jiffies - bfqq->budget_timeout;
+ else
+ bfqq->last_wr_start_finish = jiffies;
+ }
+
+ bfq_set_budget_timeout(bfqd, bfqq);
+ bfq_log_bfqq(bfqd, bfqq,
+ "set_in_service_queue, cur-budget = %d",
+ bfqq->entity.budget);
+ }
+
+ bfqd->in_service_queue = bfqq;
+}
+
+/*
+ * Get and set a new queue for service.
+ */
+static struct bfq_queue *bfq_set_in_service_queue(struct bfq_data *bfqd)
+{
+ struct bfq_queue *bfqq = bfq_get_next_queue(bfqd);
+
+ __bfq_set_in_service_queue(bfqd, bfqq);
+ return bfqq;
+}
+
+static void bfq_arm_slice_timer(struct bfq_data *bfqd)
+{
+ struct bfq_queue *bfqq = bfqd->in_service_queue;
+ u32 sl;
+
+ bfq_mark_bfqq_wait_request(bfqq);
+
+ /*
+ * We don't want to idle for seeks, but we do want to allow
+ * fair distribution of slice time for a process doing back-to-back
+ * seeks. So allow a little bit of time for him to submit a new rq.
+ */
+ sl = bfqd->bfq_slice_idle;
+ /*
+ * Unless the queue is being weight-raised or the scenario is
+ * asymmetric, grant only minimum idle time if the queue
+ * is seeky. A long idling is preserved for a weight-raised
+ * queue, or, more in general, in an asymmetric scenario,
+ * because a long idling is needed for guaranteeing to a queue
+ * its reserved share of the throughput (in particular, it is
+ * needed if the queue has a higher weight than some other
+ * queue).
+ */
+ if (BFQQ_SEEKY(bfqq) && bfqq->wr_coeff == 1 &&
+ bfq_symmetric_scenario(bfqd))
+ sl = min_t(u64, sl, BFQ_MIN_TT);
+
+ bfqd->last_idling_start = ktime_get();
+ hrtimer_start(&bfqd->idle_slice_timer, ns_to_ktime(sl),
+ HRTIMER_MODE_REL);
+ bfqg_stats_set_start_idle_time(bfqq_group(bfqq));
+}
+
+/*
+ * In autotuning mode, max_budget is dynamically recomputed as the
+ * amount of sectors transferred in timeout at the estimated peak
+ * rate. This enables BFQ to utilize a full timeslice with a full
+ * budget, even if the in-service queue is served at peak rate. And
+ * this maximises throughput with sequential workloads.
+ */
+static unsigned long bfq_calc_max_budget(struct bfq_data *bfqd)
+{
+ return (u64)bfqd->peak_rate * USEC_PER_MSEC *
+ jiffies_to_msecs(bfqd->bfq_timeout)>>BFQ_RATE_SHIFT;
+}
+
+/*
+ * Update parameters related to throughput and responsiveness, as a
+ * function of the estimated peak rate. See comments on
+ * bfq_calc_max_budget(), and on T_slow and T_fast arrays.
+ */
+static void update_thr_responsiveness_params(struct bfq_data *bfqd)
+{
+ int dev_type = blk_queue_nonrot(bfqd->queue);
+
+ if (bfqd->bfq_user_max_budget == 0)
+ bfqd->bfq_max_budget =
+ bfq_calc_max_budget(bfqd);
+
+ if (bfqd->device_speed == BFQ_BFQD_FAST &&
+ bfqd->peak_rate < device_speed_thresh[dev_type]) {
+ bfqd->device_speed = BFQ_BFQD_SLOW;
+ bfqd->RT_prod = R_slow[dev_type] *
+ T_slow[dev_type];
+ } else if (bfqd->device_speed == BFQ_BFQD_SLOW &&
+ bfqd->peak_rate > device_speed_thresh[dev_type]) {
+ bfqd->device_speed = BFQ_BFQD_FAST;
+ bfqd->RT_prod = R_fast[dev_type] *
+ T_fast[dev_type];
+ }
+
+ bfq_log(bfqd,
+"dev_type %s dev_speed_class = %s (%llu sects/sec), thresh %llu setcs/sec",
+ dev_type == 0 ? "ROT" : "NONROT",
+ bfqd->device_speed == BFQ_BFQD_FAST ? "FAST" : "SLOW",
+ bfqd->device_speed == BFQ_BFQD_FAST ?
+ (USEC_PER_SEC*(u64)R_fast[dev_type])>>BFQ_RATE_SHIFT :
+ (USEC_PER_SEC*(u64)R_slow[dev_type])>>BFQ_RATE_SHIFT,
+ (USEC_PER_SEC*(u64)device_speed_thresh[dev_type])>>
+ BFQ_RATE_SHIFT);
+}
+
+static void bfq_reset_rate_computation(struct bfq_data *bfqd,
+ struct request *rq)
+{
+ if (rq != NULL) { /* new rq dispatch now, reset accordingly */
+ bfqd->last_dispatch = bfqd->first_dispatch = ktime_get_ns();
+ bfqd->peak_rate_samples = 1;
+ bfqd->sequential_samples = 0;
+ bfqd->tot_sectors_dispatched = bfqd->last_rq_max_size =
+ blk_rq_sectors(rq);
+ } else /* no new rq dispatched, just reset the number of samples */
+ bfqd->peak_rate_samples = 0; /* full re-init on next disp. */
+
+ bfq_log(bfqd,
+ "reset_rate_computation at end, sample %u/%u tot_sects %llu",
+ bfqd->peak_rate_samples, bfqd->sequential_samples,
+ bfqd->tot_sectors_dispatched);
+}
+
+static void bfq_update_rate_reset(struct bfq_data *bfqd, struct request *rq)
+{
+ u32 rate, weight, divisor;
+
+ /*
+ * For the convergence property to hold (see comments on
+ * bfq_update_peak_rate()) and for the assessment to be
+ * reliable, a minimum number of samples must be present, and
+ * a minimum amount of time must have elapsed. If not so, do
+ * not compute new rate. Just reset parameters, to get ready
+ * for a new evaluation attempt.
+ */
+ if (bfqd->peak_rate_samples < BFQ_RATE_MIN_SAMPLES ||
+ bfqd->delta_from_first < BFQ_RATE_MIN_INTERVAL)
+ goto reset_computation;
+
+ /*
+ * If a new request completion has occurred after last
+ * dispatch, then, to approximate the rate at which requests
+ * have been served by the device, it is more precise to
+ * extend the observation interval to the last completion.
+ */
+ bfqd->delta_from_first =
+ max_t(u64, bfqd->delta_from_first,
+ bfqd->last_completion - bfqd->first_dispatch);
+
+ /*
+ * Rate computed in sects/usec, and not sects/nsec, for
+ * precision issues.
+ */
+ rate = div64_ul(bfqd->tot_sectors_dispatched<<BFQ_RATE_SHIFT,
+ div_u64(bfqd->delta_from_first, NSEC_PER_USEC));
+
+ /*
+ * Peak rate not updated if:
+ * - the percentage of sequential dispatches is below 3/4 of the
+ * total, and rate is below the current estimated peak rate
+ * - rate is unreasonably high (> 20M sectors/sec)
+ */
+ if ((bfqd->sequential_samples < (3 * bfqd->peak_rate_samples)>>2 &&
+ rate <= bfqd->peak_rate) ||
+ rate > 20<<BFQ_RATE_SHIFT)
+ goto reset_computation;
+
+ /*
+ * We have to update the peak rate, at last! To this purpose,
+ * we use a low-pass filter. We compute the smoothing constant
+ * of the filter as a function of the 'weight' of the new
+ * measured rate.
+ *
+ * As can be seen in next formulas, we define this weight as a
+ * quantity proportional to how sequential the workload is,
+ * and to how long the observation time interval is.
+ *
+ * The weight runs from 0 to 8. The maximum value of the
+ * weight, 8, yields the minimum value for the smoothing
+ * constant. At this minimum value for the smoothing constant,
+ * the measured rate contributes for half of the next value of
+ * the estimated peak rate.
+ *
+ * So, the first step is to compute the weight as a function
+ * of how sequential the workload is. Note that the weight
+ * cannot reach 9, because bfqd->sequential_samples cannot
+ * become equal to bfqd->peak_rate_samples, which, in its
+ * turn, holds true because bfqd->sequential_samples is not
+ * incremented for the first sample.
+ */
+ weight = (9 * bfqd->sequential_samples) / bfqd->peak_rate_samples;
+
+ /*
+ * Second step: further refine the weight as a function of the
+ * duration of the observation interval.
+ */
+ weight = min_t(u32, 8,
+ div_u64(weight * bfqd->delta_from_first,
+ BFQ_RATE_REF_INTERVAL));
+
+ /*
+ * Divisor ranging from 10, for minimum weight, to 2, for
+ * maximum weight.
+ */
+ divisor = 10 - weight;
+
+ /*
+ * Finally, update peak rate:
+ *
+ * peak_rate = peak_rate * (divisor-1) / divisor + rate / divisor
+ */
+ bfqd->peak_rate *= divisor-1;
+ bfqd->peak_rate /= divisor;
+ rate /= divisor; /* smoothing constant alpha = 1/divisor */
+
+ bfqd->peak_rate += rate;
+ update_thr_responsiveness_params(bfqd);
+
+reset_computation:
+ bfq_reset_rate_computation(bfqd, rq);
+}
+
+/*
+ * Update the read/write peak rate (the main quantity used for
+ * auto-tuning, see update_thr_responsiveness_params()).
+ *
+ * It is not trivial to estimate the peak rate (correctly): because of
+ * the presence of sw and hw queues between the scheduler and the
+ * device components that finally serve I/O requests, it is hard to
+ * say exactly when a given dispatched request is served inside the
+ * device, and for how long. As a consequence, it is hard to know
+ * precisely at what rate a given set of requests is actually served
+ * by the device.
+ *
+ * On the opposite end, the dispatch time of any request is trivially
+ * available, and, from this piece of information, the "dispatch rate"
+ * of requests can be immediately computed. So, the idea in the next
+ * function is to use what is known, namely request dispatch times
+ * (plus, when useful, request completion times), to estimate what is
+ * unknown, namely in-device request service rate.
+ *
+ * The main issue is that, because of the above facts, the rate at
+ * which a certain set of requests is dispatched over a certain time
+ * interval can vary greatly with respect to the rate at which the
+ * same requests are then served. But, since the size of any
+ * intermediate queue is limited, and the service scheme is lossless
+ * (no request is silently dropped), the following obvious convergence
+ * property holds: the number of requests dispatched MUST become
+ * closer and closer to the number of requests completed as the
+ * observation interval grows. This is the key property used in
+ * the next function to estimate the peak service rate as a function
+ * of the observed dispatch rate. The function assumes to be invoked
+ * on every request dispatch.
+ */
+static void bfq_update_peak_rate(struct bfq_data *bfqd, struct request *rq)
+{
+ u64 now_ns = ktime_get_ns();
+
+ if (bfqd->peak_rate_samples == 0) { /* first dispatch */
+ bfq_log(bfqd, "update_peak_rate: goto reset, samples %d",
+ bfqd->peak_rate_samples);
+ bfq_reset_rate_computation(bfqd, rq);
+ goto update_last_values; /* will add one sample */
+ }
+
+ /*
+ * Device idle for very long: the observation interval lasting
+ * up to this dispatch cannot be a valid observation interval
+ * for computing a new peak rate (similarly to the late-
+ * completion event in bfq_completed_request()). Go to
+ * update_rate_and_reset to have the following three steps
+ * taken:
+ * - close the observation interval at the last (previous)
+ * request dispatch or completion
+ * - compute rate, if possible, for that observation interval
+ * - start a new observation interval with this dispatch
+ */
+ if (now_ns - bfqd->last_dispatch > 100*NSEC_PER_MSEC &&
+ bfqd->rq_in_driver == 0)
+ goto update_rate_and_reset;
+
+ /* Update sampling information */
+ bfqd->peak_rate_samples++;
+
+ if ((bfqd->rq_in_driver > 0 ||
+ now_ns - bfqd->last_completion < BFQ_MIN_TT)
+ && get_sdist(bfqd->last_position, rq) < BFQQ_SEEK_THR)
+ bfqd->sequential_samples++;
+
+ bfqd->tot_sectors_dispatched += blk_rq_sectors(rq);
+
+ /* Reset max observed rq size every 32 dispatches */
+ if (likely(bfqd->peak_rate_samples % 32))
+ bfqd->last_rq_max_size =
+ max_t(u32, blk_rq_sectors(rq), bfqd->last_rq_max_size);
+ else
+ bfqd->last_rq_max_size = blk_rq_sectors(rq);
+
+ bfqd->delta_from_first = now_ns - bfqd->first_dispatch;
+
+ /* Target observation interval not yet reached, go on sampling */
+ if (bfqd->delta_from_first < BFQ_RATE_REF_INTERVAL)
+ goto update_last_values;
+
+update_rate_and_reset:
+ bfq_update_rate_reset(bfqd, rq);
+update_last_values:
+ bfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq);
+ bfqd->last_dispatch = now_ns;
+}
+
+/*
+ * Remove request from internal lists.
+ */
+static void bfq_dispatch_remove(struct request_queue *q, struct request *rq)
+{
+ struct bfq_queue *bfqq = RQ_BFQQ(rq);
+
+ /*
+ * For consistency, the next instruction should have been
+ * executed after removing the request from the queue and
+ * dispatching it. We execute instead this instruction before
+ * bfq_remove_request() (and hence introduce a temporary
+ * inconsistency), for efficiency. In fact, should this
+ * dispatch occur for a non in-service bfqq, this anticipated
+ * increment prevents two counters related to bfqq->dispatched
+ * from risking to be, first, uselessly decremented, and then
+ * incremented again when the (new) value of bfqq->dispatched
+ * happens to be taken into account.
+ */
+ bfqq->dispatched++;
+ bfq_update_peak_rate(q->elevator->elevator_data, rq);
+
+ bfq_remove_request(q, rq);
+}
+
+static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+ /*
+ * If this bfqq is shared between multiple processes, check
+ * to make sure that those processes are still issuing I/Os
+ * within the mean seek distance. If not, it may be time to
+ * break the queues apart again.
+ */
+ if (bfq_bfqq_coop(bfqq) && BFQQ_SEEKY(bfqq))
+ bfq_mark_bfqq_split_coop(bfqq);
+
+ if (RB_EMPTY_ROOT(&bfqq->sort_list)) {
+ if (bfqq->dispatched == 0)
+ /*
+ * Overloading budget_timeout field to store
+ * the time at which the queue remains with no
+ * backlog and no outstanding request; used by
+ * the weight-raising mechanism.
+ */
+ bfqq->budget_timeout = jiffies;
+
+ bfq_del_bfqq_busy(bfqd, bfqq, true);
+ } else {
+ bfq_requeue_bfqq(bfqd, bfqq);
+ /*
+ * Resort priority tree of potential close cooperators.
+ */
+ bfq_pos_tree_add_move(bfqd, bfqq);
+ }
+
+ /*
+ * All in-service entities must have been properly deactivated
+ * or requeued before executing the next function, which
+ * resets all in-service entites as no more in service.
+ */
+ __bfq_bfqd_reset_in_service(bfqd);
+}
+
+/**
+ * __bfq_bfqq_recalc_budget - try to adapt the budget to the @bfqq behavior.
+ * @bfqd: device data.
+ * @bfqq: queue to update.
+ * @reason: reason for expiration.
+ *
+ * Handle the feedback on @bfqq budget at queue expiration.
+ * See the body for detailed comments.
+ */
+static void __bfq_bfqq_recalc_budget(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq,
+ enum bfqq_expiration reason)
+{
+ struct request *next_rq;
+ int budget, min_budget;
+
+ min_budget = bfq_min_budget(bfqd);
+
+ if (bfqq->wr_coeff == 1)
+ budget = bfqq->max_budget;
+ else /*
+ * Use a constant, low budget for weight-raised queues,
+ * to help achieve a low latency. Keep it slightly higher
+ * than the minimum possible budget, to cause a little
+ * bit fewer expirations.
+ */
+ budget = 2 * min_budget;
+
+ bfq_log_bfqq(bfqd, bfqq, "recalc_budg: last budg %d, budg left %d",
+ bfqq->entity.budget, bfq_bfqq_budget_left(bfqq));
+ bfq_log_bfqq(bfqd, bfqq, "recalc_budg: last max_budg %d, min budg %d",
+ budget, bfq_min_budget(bfqd));
+ bfq_log_bfqq(bfqd, bfqq, "recalc_budg: sync %d, seeky %d",
+ bfq_bfqq_sync(bfqq), BFQQ_SEEKY(bfqd->in_service_queue));
+
+ if (bfq_bfqq_sync(bfqq) && bfqq->wr_coeff == 1) {
+ switch (reason) {
+ /*
+ * Caveat: in all the following cases we trade latency
+ * for throughput.
+ */
+ case BFQQE_TOO_IDLE:
+ /*
+ * This is the only case where we may reduce
+ * the budget: if there is no request of the
+ * process still waiting for completion, then
+ * we assume (tentatively) that the timer has
+ * expired because the batch of requests of
+ * the process could have been served with a
+ * smaller budget. Hence, betting that
+ * process will behave in the same way when it
+ * becomes backlogged again, we reduce its
+ * next budget. As long as we guess right,
+ * this budget cut reduces the latency
+ * experienced by the process.
+ *
+ * However, if there are still outstanding
+ * requests, then the process may have not yet
+ * issued its next request just because it is
+ * still waiting for the completion of some of
+ * the still outstanding ones. So in this
+ * subcase we do not reduce its budget, on the
+ * contrary we increase it to possibly boost
+ * the throughput, as discussed in the
+ * comments to the BUDGET_TIMEOUT case.
+ */
+ if (bfqq->dispatched > 0) /* still outstanding reqs */
+ budget = min(budget * 2, bfqd->bfq_max_budget);
+ else {
+ if (budget > 5 * min_budget)
+ budget -= 4 * min_budget;
+ else
+ budget = min_budget;
+ }
+ break;
+ case BFQQE_BUDGET_TIMEOUT:
+ /*
+ * We double the budget here because it gives
+ * the chance to boost the throughput if this
+ * is not a seeky process (and has bumped into
+ * this timeout because of, e.g., ZBR).
+ */
+ budget = min(budget * 2, bfqd->bfq_max_budget);
+ break;
+ case BFQQE_BUDGET_EXHAUSTED:
+ /*
+ * The process still has backlog, and did not
+ * let either the budget timeout or the disk
+ * idling timeout expire. Hence it is not
+ * seeky, has a short thinktime and may be
+ * happy with a higher budget too. So
+ * definitely increase the budget of this good
+ * candidate to boost the disk throughput.
+ */
+ budget = min(budget * 4, bfqd->bfq_max_budget);
+ break;
+ case BFQQE_NO_MORE_REQUESTS:
+ /*
+ * For queues that expire for this reason, it
+ * is particularly important to keep the
+ * budget close to the actual service they
+ * need. Doing so reduces the timestamp
+ * misalignment problem described in the
+ * comments in the body of
+ * __bfq_activate_entity. In fact, suppose
+ * that a queue systematically expires for
+ * BFQQE_NO_MORE_REQUESTS and presents a
+ * new request in time to enjoy timestamp
+ * back-shifting. The larger the budget of the
+ * queue is with respect to the service the
+ * queue actually requests in each service
+ * slot, the more times the queue can be
+ * reactivated with the same virtual finish
+ * time. It follows that, even if this finish
+ * time is pushed to the system virtual time
+ * to reduce the consequent timestamp
+ * misalignment, the queue unjustly enjoys for
+ * many re-activations a lower finish time
+ * than all newly activated queues.
+ *
+ * The service needed by bfqq is measured
+ * quite precisely by bfqq->entity.service.
+ * Since bfqq does not enjoy device idling,
+ * bfqq->entity.service is equal to the number
+ * of sectors that the process associated with
+ * bfqq requested to read/write before waiting
+ * for request completions, or blocking for
+ * other reasons.
+ */
+ budget = max_t(int, bfqq->entity.service, min_budget);
+ break;
+ default:
+ return;
+ }
+ } else if (!bfq_bfqq_sync(bfqq)) {
+ /*
+ * Async queues get always the maximum possible
+ * budget, as for them we do not care about latency
+ * (in addition, their ability to dispatch is limited
+ * by the charging factor).
+ */
+ budget = bfqd->bfq_max_budget;
+ }
+
+ bfqq->max_budget = budget;
+
+ if (bfqd->budgets_assigned >= bfq_stats_min_budgets &&
+ !bfqd->bfq_user_max_budget)
+ bfqq->max_budget = min(bfqq->max_budget, bfqd->bfq_max_budget);
+
+ /*
+ * If there is still backlog, then assign a new budget, making
+ * sure that it is large enough for the next request. Since
+ * the finish time of bfqq must be kept in sync with the
+ * budget, be sure to call __bfq_bfqq_expire() *after* this
+ * update.
+ *
+ * If there is no backlog, then no need to update the budget;
+ * it will be updated on the arrival of a new request.
+ */
+ next_rq = bfqq->next_rq;
+ if (next_rq)
+ bfqq->entity.budget = max_t(unsigned long, bfqq->max_budget,
+ bfq_serv_to_charge(next_rq, bfqq));
+
+ bfq_log_bfqq(bfqd, bfqq, "head sect: %u, new budget %d",
+ next_rq ? blk_rq_sectors(next_rq) : 0,
+ bfqq->entity.budget);
+}
+
+/*
+ * Return true if the process associated with bfqq is "slow". The slow
+ * flag is used, in addition to the budget timeout, to reduce the
+ * amount of service provided to seeky processes, and thus reduce
+ * their chances to lower the throughput. More details in the comments
+ * on the function bfq_bfqq_expire().
+ *
+ * An important observation is in order: as discussed in the comments
+ * on the function bfq_update_peak_rate(), with devices with internal
+ * queues, it is hard if ever possible to know when and for how long
+ * an I/O request is processed by the device (apart from the trivial
+ * I/O pattern where a new request is dispatched only after the
+ * previous one has been completed). This makes it hard to evaluate
+ * the real rate at which the I/O requests of each bfq_queue are
+ * served. In fact, for an I/O scheduler like BFQ, serving a
+ * bfq_queue means just dispatching its requests during its service
+ * slot (i.e., until the budget of the queue is exhausted, or the
+ * queue remains idle, or, finally, a timeout fires). But, during the
+ * service slot of a bfq_queue, around 100 ms at most, the device may
+ * be even still processing requests of bfq_queues served in previous
+ * service slots. On the opposite end, the requests of the in-service
+ * bfq_queue may be completed after the service slot of the queue
+ * finishes.
+ *
+ * Anyway, unless more sophisticated solutions are used
+ * (where possible), the sum of the sizes of the requests dispatched
+ * during the service slot of a bfq_queue is probably the only
+ * approximation available for the service received by the bfq_queue
+ * during its service slot. And this sum is the quantity used in this
+ * function to evaluate the I/O speed of a process.
+ */
+static bool bfq_bfqq_is_slow(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ bool compensate, enum bfqq_expiration reason,
+ unsigned long *delta_ms)
+{
+ ktime_t delta_ktime;
+ u32 delta_usecs;
+ bool slow = BFQQ_SEEKY(bfqq); /* if delta too short, use seekyness */
+
+ if (!bfq_bfqq_sync(bfqq))
+ return false;
+
+ if (compensate)
+ delta_ktime = bfqd->last_idling_start;
+ else
+ delta_ktime = ktime_get();
+ delta_ktime = ktime_sub(delta_ktime, bfqd->last_budget_start);
+ delta_usecs = ktime_to_us(delta_ktime);
+
+ /* don't use too short time intervals */
+ if (delta_usecs < 1000) {
+ if (blk_queue_nonrot(bfqd->queue))
+ /*
+ * give same worst-case guarantees as idling
+ * for seeky
+ */
+ *delta_ms = BFQ_MIN_TT / NSEC_PER_MSEC;
+ else /* charge at least one seek */
+ *delta_ms = bfq_slice_idle / NSEC_PER_MSEC;
+
+ return slow;
+ }
+
+ *delta_ms = delta_usecs / USEC_PER_MSEC;
+
+ /*
+ * Use only long (> 20ms) intervals to filter out excessive
+ * spikes in service rate estimation.
+ */
+ if (delta_usecs > 20000) {
+ /*
+ * Caveat for rotational devices: processes doing I/O
+ * in the slower disk zones tend to be slow(er) even
+ * if not seeky. In this respect, the estimated peak
+ * rate is likely to be an average over the disk
+ * surface. Accordingly, to not be too harsh with
+ * unlucky processes, a process is deemed slow only if
+ * its rate has been lower than half of the estimated
+ * peak rate.
+ */
+ slow = bfqq->entity.service < bfqd->bfq_max_budget / 2;
+ }
+
+ bfq_log_bfqq(bfqd, bfqq, "bfq_bfqq_is_slow: slow %d", slow);
+
+ return slow;
+}
+
+/*
+ * To be deemed as soft real-time, an application must meet two
+ * requirements. First, the application must not require an average
+ * bandwidth higher than the approximate bandwidth required to playback or
+ * record a compressed high-definition video.
+ * The next function is invoked on the completion of the last request of a
+ * batch, to compute the next-start time instant, soft_rt_next_start, such
+ * that, if the next request of the application does not arrive before
+ * soft_rt_next_start, then the above requirement on the bandwidth is met.
+ *
+ * The second requirement is that the request pattern of the application is
+ * isochronous, i.e., that, after issuing a request or a batch of requests,
+ * the application stops issuing new requests until all its pending requests
+ * have been completed. After that, the application may issue a new batch,
+ * and so on.
+ * For this reason the next function is invoked to compute
+ * soft_rt_next_start only for applications that meet this requirement,
+ * whereas soft_rt_next_start is set to infinity for applications that do
+ * not.
+ *
+ * Unfortunately, even a greedy application may happen to behave in an
+ * isochronous way if the CPU load is high. In fact, the application may
+ * stop issuing requests while the CPUs are busy serving other processes,
+ * then restart, then stop again for a while, and so on. In addition, if
+ * the disk achieves a low enough throughput with the request pattern
+ * issued by the application (e.g., because the request pattern is random
+ * and/or the device is slow), then the application may meet the above
+ * bandwidth requirement too. To prevent such a greedy application to be
+ * deemed as soft real-time, a further rule is used in the computation of
+ * soft_rt_next_start: soft_rt_next_start must be higher than the current
+ * time plus the maximum time for which the arrival of a request is waited
+ * for when a sync queue becomes idle, namely bfqd->bfq_slice_idle.
+ * This filters out greedy applications, as the latter issue instead their
+ * next request as soon as possible after the last one has been completed
+ * (in contrast, when a batch of requests is completed, a soft real-time
+ * application spends some time processing data).
+ *
+ * Unfortunately, the last filter may easily generate false positives if
+ * only bfqd->bfq_slice_idle is used as a reference time interval and one
+ * or both the following cases occur:
+ * 1) HZ is so low that the duration of a jiffy is comparable to or higher
+ * than bfqd->bfq_slice_idle. This happens, e.g., on slow devices with
+ * HZ=100.
+ * 2) jiffies, instead of increasing at a constant rate, may stop increasing
+ * for a while, then suddenly 'jump' by several units to recover the lost
+ * increments. This seems to happen, e.g., inside virtual machines.
+ * To address this issue, we do not use as a reference time interval just
+ * bfqd->bfq_slice_idle, but bfqd->bfq_slice_idle plus a few jiffies. In
+ * particular we add the minimum number of jiffies for which the filter
+ * seems to be quite precise also in embedded systems and KVM/QEMU virtual
+ * machines.
+ */
+static unsigned long bfq_bfqq_softrt_next_start(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq)
+{
+ return max(bfqq->last_idle_bklogged +
+ HZ * bfqq->service_from_backlogged /
+ bfqd->bfq_wr_max_softrt_rate,
+ jiffies + nsecs_to_jiffies(bfqq->bfqd->bfq_slice_idle) + 4);
+}
+
+/*
+ * Return the farthest future time instant according to jiffies
+ * macros.
+ */
+static unsigned long bfq_greatest_from_now(void)
+{
+ return jiffies + MAX_JIFFY_OFFSET;
+}
+
+/*
+ * Return the farthest past time instant according to jiffies
+ * macros.
+ */
+static unsigned long bfq_smallest_from_now(void)
+{
+ return jiffies - MAX_JIFFY_OFFSET;
+}
+
+/**
+ * bfq_bfqq_expire - expire a queue.
+ * @bfqd: device owning the queue.
+ * @bfqq: the queue to expire.
+ * @compensate: if true, compensate for the time spent idling.
+ * @reason: the reason causing the expiration.
+ *
+ * If the process associated with bfqq does slow I/O (e.g., because it
+ * issues random requests), we charge bfqq with the time it has been
+ * in service instead of the service it has received (see
+ * bfq_bfqq_charge_time for details on how this goal is achieved). As
+ * a consequence, bfqq will typically get higher timestamps upon
+ * reactivation, and hence it will be rescheduled as if it had
+ * received more service than what it has actually received. In the
+ * end, bfqq receives less service in proportion to how slowly its
+ * associated process consumes its budgets (and hence how seriously it
+ * tends to lower the throughput). In addition, this time-charging
+ * strategy guarantees time fairness among slow processes. In
+ * contrast, if the process associated with bfqq is not slow, we
+ * charge bfqq exactly with the service it has received.
+ *
+ * Charging time to the first type of queues and the exact service to
+ * the other has the effect of using the WF2Q+ policy to schedule the
+ * former on a timeslice basis, without violating service domain
+ * guarantees among the latter.
+ */
+void bfq_bfqq_expire(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq,
+ bool compensate,
+ enum bfqq_expiration reason)
+{
+ bool slow;
+ unsigned long delta = 0;
+ struct bfq_entity *entity = &bfqq->entity;
+ int ref;
+
+ /*
+ * Check whether the process is slow (see bfq_bfqq_is_slow).
+ */
+ slow = bfq_bfqq_is_slow(bfqd, bfqq, compensate, reason, &delta);
+
+ /*
+ * Increase service_from_backlogged before next statement,
+ * because the possible next invocation of
+ * bfq_bfqq_charge_time would likely inflate
+ * entity->service. In contrast, service_from_backlogged must
+ * contain real service, to enable the soft real-time
+ * heuristic to correctly compute the bandwidth consumed by
+ * bfqq.
+ */
+ bfqq->service_from_backlogged += entity->service;
+
+ /*
+ * As above explained, charge slow (typically seeky) and
+ * timed-out queues with the time and not the service
+ * received, to favor sequential workloads.
+ *
+ * Processes doing I/O in the slower disk zones will tend to
+ * be slow(er) even if not seeky. Therefore, since the
+ * estimated peak rate is actually an average over the disk
+ * surface, these processes may timeout just for bad luck. To
+ * avoid punishing them, do not charge time to processes that
+ * succeeded in consuming at least 2/3 of their budget. This
+ * allows BFQ to preserve enough elasticity to still perform
+ * bandwidth, and not time, distribution with little unlucky
+ * or quasi-sequential processes.
+ */
+ if (bfqq->wr_coeff == 1 &&
+ (slow ||
+ (reason == BFQQE_BUDGET_TIMEOUT &&
+ bfq_bfqq_budget_left(bfqq) >= entity->budget / 3)))
+ bfq_bfqq_charge_time(bfqd, bfqq, delta);
+
+ if (reason == BFQQE_TOO_IDLE &&
+ entity->service <= 2 * entity->budget / 10)
+ bfq_clear_bfqq_IO_bound(bfqq);
+
+ if (bfqd->low_latency && bfqq->wr_coeff == 1)
+ bfqq->last_wr_start_finish = jiffies;
+
+ if (bfqd->low_latency && bfqd->bfq_wr_max_softrt_rate > 0 &&
+ RB_EMPTY_ROOT(&bfqq->sort_list)) {
+ /*
+ * If we get here, and there are no outstanding
+ * requests, then the request pattern is isochronous
+ * (see the comments on the function
+ * bfq_bfqq_softrt_next_start()). Thus we can compute
+ * soft_rt_next_start. If, instead, the queue still
+ * has outstanding requests, then we have to wait for
+ * the completion of all the outstanding requests to
+ * discover whether the request pattern is actually
+ * isochronous.
+ */
+ if (bfqq->dispatched == 0)
+ bfqq->soft_rt_next_start =
+ bfq_bfqq_softrt_next_start(bfqd, bfqq);
+ else {
+ /*
+ * The application is still waiting for the
+ * completion of one or more requests:
+ * prevent it from possibly being incorrectly
+ * deemed as soft real-time by setting its
+ * soft_rt_next_start to infinity. In fact,
+ * without this assignment, the application
+ * would be incorrectly deemed as soft
+ * real-time if:
+ * 1) it issued a new request before the
+ * completion of all its in-flight
+ * requests, and
+ * 2) at that time, its soft_rt_next_start
+ * happened to be in the past.
+ */
+ bfqq->soft_rt_next_start =
+ bfq_greatest_from_now();
+ /*
+ * Schedule an update of soft_rt_next_start to when
+ * the task may be discovered to be isochronous.
+ */
+ bfq_mark_bfqq_softrt_update(bfqq);
+ }
+ }
+
+ bfq_log_bfqq(bfqd, bfqq,
+ "expire (%d, slow %d, num_disp %d, idle_win %d)", reason,
+ slow, bfqq->dispatched, bfq_bfqq_idle_window(bfqq));
+
+ /*
+ * Increase, decrease or leave budget unchanged according to
+ * reason.
+ */
+ __bfq_bfqq_recalc_budget(bfqd, bfqq, reason);
+ ref = bfqq->ref;
+ __bfq_bfqq_expire(bfqd, bfqq);
+
+ /* mark bfqq as waiting a request only if a bic still points to it */
+ if (ref > 1 && !bfq_bfqq_busy(bfqq) &&
+ reason != BFQQE_BUDGET_TIMEOUT &&
+ reason != BFQQE_BUDGET_EXHAUSTED)
+ bfq_mark_bfqq_non_blocking_wait_rq(bfqq);
+}
+
+/*
+ * Budget timeout is not implemented through a dedicated timer, but
+ * just checked on request arrivals and completions, as well as on
+ * idle timer expirations.
+ */
+static bool bfq_bfqq_budget_timeout(struct bfq_queue *bfqq)
+{
+ return time_is_before_eq_jiffies(bfqq->budget_timeout);
+}
+
+/*
+ * If we expire a queue that is actively waiting (i.e., with the
+ * device idled) for the arrival of a new request, then we may incur
+ * the timestamp misalignment problem described in the body of the
+ * function __bfq_activate_entity. Hence we return true only if this
+ * condition does not hold, or if the queue is slow enough to deserve
+ * only to be kicked off for preserving a high throughput.
+ */
+static bool bfq_may_expire_for_budg_timeout(struct bfq_queue *bfqq)
+{
+ bfq_log_bfqq(bfqq->bfqd, bfqq,
+ "may_budget_timeout: wait_request %d left %d timeout %d",
+ bfq_bfqq_wait_request(bfqq),
+ bfq_bfqq_budget_left(bfqq) >= bfqq->entity.budget / 3,
+ bfq_bfqq_budget_timeout(bfqq));
+
+ return (!bfq_bfqq_wait_request(bfqq) ||
+ bfq_bfqq_budget_left(bfqq) >= bfqq->entity.budget / 3)
+ &&
+ bfq_bfqq_budget_timeout(bfqq);
+}
+
+/*
+ * For a queue that becomes empty, device idling is allowed only if
+ * this function returns true for the queue. As a consequence, since
+ * device idling plays a critical role in both throughput boosting and
+ * service guarantees, the return value of this function plays a
+ * critical role in both these aspects as well.
+ *
+ * In a nutshell, this function returns true only if idling is
+ * beneficial for throughput or, even if detrimental for throughput,
+ * idling is however necessary to preserve service guarantees (low
+ * latency, desired throughput distribution, ...). In particular, on
+ * NCQ-capable devices, this function tries to return false, so as to
+ * help keep the drives' internal queues full, whenever this helps the
+ * device boost the throughput without causing any service-guarantee
+ * issue.
+ *
+ * In more detail, the return value of this function is obtained by,
+ * first, computing a number of boolean variables that take into
+ * account throughput and service-guarantee issues, and, then,
+ * combining these variables in a logical expression. Most of the
+ * issues taken into account are not trivial. We discuss these issues
+ * individually while introducing the variables.
+ */
+static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
+{
+ struct bfq_data *bfqd = bfqq->bfqd;
+ bool idling_boosts_thr, idling_boosts_thr_without_issues,
+ idling_needed_for_service_guarantees,
+ asymmetric_scenario;
+
+ if (bfqd->strict_guarantees)
+ return true;
+
+ /*
+ * The next variable takes into account the cases where idling
+ * boosts the throughput.
+ *
+ * The value of the variable is computed considering, first, that
+ * idling is virtually always beneficial for the throughput if:
+ * (a) the device is not NCQ-capable, or
+ * (b) regardless of the presence of NCQ, the device is rotational
+ * and the request pattern for bfqq is I/O-bound and sequential.
+ *
+ * Secondly, and in contrast to the above item (b), idling an
+ * NCQ-capable flash-based device would not boost the
+ * throughput even with sequential I/O; rather it would lower
+ * the throughput in proportion to how fast the device
+ * is. Accordingly, the next variable is true if any of the
+ * above conditions (a) and (b) is true, and, in particular,
+ * happens to be false if bfqd is an NCQ-capable flash-based
+ * device.
+ */
+ idling_boosts_thr = !bfqd->hw_tag ||
+ (!blk_queue_nonrot(bfqd->queue) && bfq_bfqq_IO_bound(bfqq) &&
+ bfq_bfqq_idle_window(bfqq));
+
+ /*
+ * The value of the next variable,
+ * idling_boosts_thr_without_issues, is equal to that of
+ * idling_boosts_thr, unless a special case holds. In this
+ * special case, described below, idling may cause problems to
+ * weight-raised queues.
+ *
+ * When the request pool is saturated (e.g., in the presence
+ * of write hogs), if the processes associated with
+ * non-weight-raised queues ask for requests at a lower rate,
+ * then processes associated with weight-raised queues have a
+ * higher probability to get a request from the pool
+ * immediately (or at least soon) when they need one. Thus
+ * they have a higher probability to actually get a fraction
+ * of the device throughput proportional to their high
+ * weight. This is especially true with NCQ-capable drives,
+ * which enqueue several requests in advance, and further
+ * reorder internally-queued requests.
+ *
+ * For this reason, we force to false the value of
+ * idling_boosts_thr_without_issues if there are weight-raised
+ * busy queues. In this case, and if bfqq is not weight-raised,
+ * this guarantees that the device is not idled for bfqq (if,
+ * instead, bfqq is weight-raised, then idling will be
+ * guaranteed by another variable, see below). Combined with
+ * the timestamping rules of BFQ (see [1] for details), this
+ * behavior causes bfqq, and hence any sync non-weight-raised
+ * queue, to get a lower number of requests served, and thus
+ * to ask for a lower number of requests from the request
+ * pool, before the busy weight-raised queues get served
+ * again. This often mitigates starvation problems in the
+ * presence of heavy write workloads and NCQ, thereby
+ * guaranteeing a higher application and system responsiveness
+ * in these hostile scenarios.
+ */
+ idling_boosts_thr_without_issues = idling_boosts_thr &&
+ bfqd->wr_busy_queues == 0;
+
+ /*
+ * There is then a case where idling must be performed not
+ * for throughput concerns, but to preserve service
+ * guarantees.
+ *
+ * To introduce this case, we can note that allowing the drive
+ * to enqueue more than one request at a time, and hence
+ * delegating de facto final scheduling decisions to the
+ * drive's internal scheduler, entails loss of control on the
+ * actual request service order. In particular, the critical
+ * situation is when requests from different processes happen
+ * to be present, at the same time, in the internal queue(s)
+ * of the drive. In such a situation, the drive, by deciding
+ * the service order of the internally-queued requests, does
+ * determine also the actual throughput distribution among
+ * these processes. But the drive typically has no notion or
+ * concern about per-process throughput distribution, and
+ * makes its decisions only on a per-request basis. Therefore,
+ * the service distribution enforced by the drive's internal
+ * scheduler is likely to coincide with the desired
+ * device-throughput distribution only in a completely
+ * symmetric scenario where:
+ * (i) each of these processes must get the same throughput as
+ * the others;
+ * (ii) all these processes have the same I/O pattern
+ (either sequential or random).
+ * In fact, in such a scenario, the drive will tend to treat
+ * the requests of each of these processes in about the same
+ * way as the requests of the others, and thus to provide
+ * each of these processes with about the same throughput
+ * (which is exactly the desired throughput distribution). In
+ * contrast, in any asymmetric scenario, device idling is
+ * certainly needed to guarantee that bfqq receives its
+ * assigned fraction of the device throughput (see [1] for
+ * details).
+ *
+ * We address this issue by controlling, actually, only the
+ * symmetry sub-condition (i), i.e., provided that
+ * sub-condition (i) holds, idling is not performed,
+ * regardless of whether sub-condition (ii) holds. In other
+ * words, only if sub-condition (i) holds, then idling is
+ * allowed, and the device tends to be prevented from queueing
+ * many requests, possibly of several processes. The reason
+ * for not controlling also sub-condition (ii) is that we
+ * exploit preemption to preserve guarantees in case of
+ * symmetric scenarios, even if (ii) does not hold, as
+ * explained in the next two paragraphs.
+ *
+ * Even if a queue, say Q, is expired when it remains idle, Q
+ * can still preempt the new in-service queue if the next
+ * request of Q arrives soon (see the comments on
+ * bfq_bfqq_update_budg_for_activation). If all queues and
+ * groups have the same weight, this form of preemption,
+ * combined with the hole-recovery heuristic described in the
+ * comments on function bfq_bfqq_update_budg_for_activation,
+ * are enough to preserve a correct bandwidth distribution in
+ * the mid term, even without idling. In fact, even if not
+ * idling allows the internal queues of the device to contain
+ * many requests, and thus to reorder requests, we can rather
+ * safely assume that the internal scheduler still preserves a
+ * minimum of mid-term fairness. The motivation for using
+ * preemption instead of idling is that, by not idling,
+ * service guarantees are preserved without minimally
+ * sacrificing throughput. In other words, both a high
+ * throughput and its desired distribution are obtained.
+ *
+ * More precisely, this preemption-based, idleless approach
+ * provides fairness in terms of IOPS, and not sectors per
+ * second. This can be seen with a simple example. Suppose
+ * that there are two queues with the same weight, but that
+ * the first queue receives requests of 8 sectors, while the
+ * second queue receives requests of 1024 sectors. In
+ * addition, suppose that each of the two queues contains at
+ * most one request at a time, which implies that each queue
+ * always remains idle after it is served. Finally, after
+ * remaining idle, each queue receives very quickly a new
+ * request. It follows that the two queues are served
+ * alternatively, preempting each other if needed. This
+ * implies that, although both queues have the same weight,
+ * the queue with large requests receives a service that is
+ * 1024/8 times as high as the service received by the other
+ * queue.
+ *
+ * On the other hand, device idling is performed, and thus
+ * pure sector-domain guarantees are provided, for the
+ * following queues, which are likely to need stronger
+ * throughput guarantees: weight-raised queues, and queues
+ * with a higher weight than other queues. When such queues
+ * are active, sub-condition (i) is false, which triggers
+ * device idling.
+ *
+ * According to the above considerations, the next variable is
+ * true (only) if sub-condition (i) holds. To compute the
+ * value of this variable, we not only use the return value of
+ * the function bfq_symmetric_scenario(), but also check
+ * whether bfqq is being weight-raised, because
+ * bfq_symmetric_scenario() does not take into account also
+ * weight-raised queues (see comments on
+ * bfq_weights_tree_add()).
+ *
+ * As a side note, it is worth considering that the above
+ * device-idling countermeasures may however fail in the
+ * following unlucky scenario: if idling is (correctly)
+ * disabled in a time period during which all symmetry
+ * sub-conditions hold, and hence the device is allowed to
+ * enqueue many requests, but at some later point in time some
+ * sub-condition stops to hold, then it may become impossible
+ * to let requests be served in the desired order until all
+ * the requests already queued in the device have been served.
+ */
+ asymmetric_scenario = bfqq->wr_coeff > 1 ||
+ !bfq_symmetric_scenario(bfqd);
+
+ /*
+ * Finally, there is a case where maximizing throughput is the
+ * best choice even if it may cause unfairness toward
+ * bfqq. Such a case is when bfqq became active in a burst of
+ * queue activations. Queues that became active during a large
+ * burst benefit only from throughput, as discussed in the
+ * comments on bfq_handle_burst. Thus, if bfqq became active
+ * in a burst and not idling the device maximizes throughput,
+ * then the device must no be idled, because not idling the
+ * device provides bfqq and all other queues in the burst with
+ * maximum benefit. Combining this and the above case, we can
+ * now establish when idling is actually needed to preserve
+ * service guarantees.
+ */
+ idling_needed_for_service_guarantees =
+ asymmetric_scenario && !bfq_bfqq_in_large_burst(bfqq);
+
+ /*
+ * We have now all the components we need to compute the return
+ * value of the function, which is true only if both the following
+ * conditions hold:
+ * 1) bfqq is sync, because idling make sense only for sync queues;
+ * 2) idling either boosts the throughput (without issues), or
+ * is necessary to preserve service guarantees.
+ */
+ return bfq_bfqq_sync(bfqq) &&
+ (idling_boosts_thr_without_issues ||
+ idling_needed_for_service_guarantees);
+}
+
+/*
+ * If the in-service queue is empty but the function bfq_bfqq_may_idle
+ * returns true, then:
+ * 1) the queue must remain in service and cannot be expired, and
+ * 2) the device must be idled to wait for the possible arrival of a new
+ * request for the queue.
+ * See the comments on the function bfq_bfqq_may_idle for the reasons
+ * why performing device idling is the best choice to boost the throughput
+ * and preserve service guarantees when bfq_bfqq_may_idle itself
+ * returns true.
+ */
+static bool bfq_bfqq_must_idle(struct bfq_queue *bfqq)
+{
+ struct bfq_data *bfqd = bfqq->bfqd;
+
+ return RB_EMPTY_ROOT(&bfqq->sort_list) && bfqd->bfq_slice_idle != 0 &&
+ bfq_bfqq_may_idle(bfqq);
+}
+
+/*
+ * Select a queue for service. If we have a current queue in service,
+ * check whether to continue servicing it, or retrieve and set a new one.
+ */
+static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
+{
+ struct bfq_queue *bfqq;
+ struct request *next_rq;
+ enum bfqq_expiration reason = BFQQE_BUDGET_TIMEOUT;
+
+ bfqq = bfqd->in_service_queue;
+ if (!bfqq)
+ goto new_queue;
+
+ bfq_log_bfqq(bfqd, bfqq, "select_queue: already in-service queue");
+
+ if (bfq_may_expire_for_budg_timeout(bfqq) &&
+ !bfq_bfqq_wait_request(bfqq) &&
+ !bfq_bfqq_must_idle(bfqq))
+ goto expire;
+
+check_queue:
+ /*
+ * This loop is rarely executed more than once. Even when it
+ * happens, it is much more convenient to re-execute this loop
+ * than to return NULL and trigger a new dispatch to get a
+ * request served.
+ */
+ next_rq = bfqq->next_rq;
+ /*
+ * If bfqq has requests queued and it has enough budget left to
+ * serve them, keep the queue, otherwise expire it.
+ */
+ if (next_rq) {
+ if (bfq_serv_to_charge(next_rq, bfqq) >
+ bfq_bfqq_budget_left(bfqq)) {
+ /*
+ * Expire the queue for budget exhaustion,
+ * which makes sure that the next budget is
+ * enough to serve the next request, even if
+ * it comes from the fifo expired path.
+ */
+ reason = BFQQE_BUDGET_EXHAUSTED;
+ goto expire;
+ } else {
+ /*
+ * The idle timer may be pending because we may
+ * not disable disk idling even when a new request
+ * arrives.
+ */
+ if (bfq_bfqq_wait_request(bfqq)) {
+ /*
+ * If we get here: 1) at least a new request
+ * has arrived but we have not disabled the
+ * timer because the request was too small,
+ * 2) then the block layer has unplugged
+ * the device, causing the dispatch to be
+ * invoked.
+ *
+ * Since the device is unplugged, now the
+ * requests are probably large enough to
+ * provide a reasonable throughput.
+ * So we disable idling.
+ */
+ bfq_clear_bfqq_wait_request(bfqq);
+ hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
+ bfqg_stats_update_idle_time(bfqq_group(bfqq));
+ }
+ goto keep_queue;
+ }
+ }
+
+ /*
+ * No requests pending. However, if the in-service queue is idling
+ * for a new request, or has requests waiting for a completion and
+ * may idle after their completion, then keep it anyway.
+ */
+ if (bfq_bfqq_wait_request(bfqq) ||
+ (bfqq->dispatched != 0 && bfq_bfqq_may_idle(bfqq))) {
+ bfqq = NULL;
+ goto keep_queue;
+ }
+
+ reason = BFQQE_NO_MORE_REQUESTS;
+expire:
+ bfq_bfqq_expire(bfqd, bfqq, false, reason);
+new_queue:
+ bfqq = bfq_set_in_service_queue(bfqd);
+ if (bfqq) {
+ bfq_log_bfqq(bfqd, bfqq, "select_queue: checking new queue");
+ goto check_queue;
+ }
+keep_queue:
+ if (bfqq)
+ bfq_log_bfqq(bfqd, bfqq, "select_queue: returned this queue");
+ else
+ bfq_log(bfqd, "select_queue: no queue returned");
+
+ return bfqq;
+}
+
+static void bfq_update_wr_data(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+ struct bfq_entity *entity = &bfqq->entity;
+
+ if (bfqq->wr_coeff > 1) { /* queue is being weight-raised */
+ bfq_log_bfqq(bfqd, bfqq,
+ "raising period dur %u/%u msec, old coeff %u, w %d(%d)",
+ jiffies_to_msecs(jiffies - bfqq->last_wr_start_finish),
+ jiffies_to_msecs(bfqq->wr_cur_max_time),
+ bfqq->wr_coeff,
+ bfqq->entity.weight, bfqq->entity.orig_weight);
+
+ if (entity->prio_changed)
+ bfq_log_bfqq(bfqd, bfqq, "WARN: pending prio change");
+
+ /*
+ * If the queue was activated in a burst, or too much
+ * time has elapsed from the beginning of this
+ * weight-raising period, then end weight raising.
+ */
+ if (bfq_bfqq_in_large_burst(bfqq))
+ bfq_bfqq_end_wr(bfqq);
+ else if (time_is_before_jiffies(bfqq->last_wr_start_finish +
+ bfqq->wr_cur_max_time)) {
+ if (bfqq->wr_cur_max_time != bfqd->bfq_wr_rt_max_time ||
+ time_is_before_jiffies(bfqq->wr_start_at_switch_to_srt +
+ bfq_wr_duration(bfqd)))
+ bfq_bfqq_end_wr(bfqq);
+ else {
+ /* switch back to interactive wr */
+ bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+ bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+ bfqq->last_wr_start_finish =
+ bfqq->wr_start_at_switch_to_srt;
+ bfqq->entity.prio_changed = 1;
+ }
+ }
+ }
+ /* Update weight both if it must be raised and if it must be lowered */
+ if ((entity->weight > entity->orig_weight) != (bfqq->wr_coeff > 1))
+ __bfq_entity_update_weight_prio(
+ bfq_entity_service_tree(entity),
+ entity);
+}
+
+/*
+ * Dispatch next request from bfqq.
+ */
+static struct request *bfq_dispatch_rq_from_bfqq(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq)
+{
+ struct request *rq = bfqq->next_rq;
+ unsigned long service_to_charge;
+
+ service_to_charge = bfq_serv_to_charge(rq, bfqq);
+
+ bfq_bfqq_served(bfqq, service_to_charge);
+
+ bfq_dispatch_remove(bfqd->queue, rq);
+
+ /*
+ * If weight raising has to terminate for bfqq, then next
+ * function causes an immediate update of bfqq's weight,
+ * without waiting for next activation. As a consequence, on
+ * expiration, bfqq will be timestamped as if has never been
+ * weight-raised during this service slot, even if it has
+ * received part or even most of the service as a
+ * weight-raised queue. This inflates bfqq's timestamps, which
+ * is beneficial, as bfqq is then more willing to leave the
+ * device immediately to possible other weight-raised queues.
+ */
+ bfq_update_wr_data(bfqd, bfqq);
+
+ /*
+ * Expire bfqq, pretending that its budget expired, if bfqq
+ * belongs to CLASS_IDLE and other queues are waiting for
+ * service.
+ */
+ if (bfqd->busy_queues > 1 && bfq_class_idle(bfqq))
+ goto expire;
+
+ return rq;
+
+expire:
+ bfq_bfqq_expire(bfqd, bfqq, false, BFQQE_BUDGET_EXHAUSTED);
+ return rq;
+}
+
+static bool bfq_has_work(struct blk_mq_hw_ctx *hctx)
+{
+ struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
+
+ /*
+ * Avoiding lock: a race on bfqd->busy_queues should cause at
+ * most a call to dispatch for nothing
+ */
+ return !list_empty_careful(&bfqd->dispatch) ||
+ bfqd->busy_queues > 0;
+}
+
+static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
+{
+ struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
+ struct request *rq = NULL;
+ struct bfq_queue *bfqq = NULL;
+
+ if (!list_empty(&bfqd->dispatch)) {
+ rq = list_first_entry(&bfqd->dispatch, struct request,
+ queuelist);
+ list_del_init(&rq->queuelist);
+
+ bfqq = RQ_BFQQ(rq);
+
+ if (bfqq) {
+ /*
+ * Increment counters here, because this
+ * dispatch does not follow the standard
+ * dispatch flow (where counters are
+ * incremented)
+ */
+ bfqq->dispatched++;
+
+ goto inc_in_driver_start_rq;
+ }
+
+ /*
+ * We exploit the put_rq_private hook to decrement
+ * rq_in_driver, but put_rq_private will not be
+ * invoked on this request. So, to avoid unbalance,
+ * just start this request, without incrementing
+ * rq_in_driver. As a negative consequence,
+ * rq_in_driver is deceptively lower than it should be
+ * while this request is in service. This may cause
+ * bfq_schedule_dispatch to be invoked uselessly.
+ *
+ * As for implementing an exact solution, the
+ * put_request hook, if defined, is probably invoked
+ * also on this request. So, by exploiting this hook,
+ * we could 1) increment rq_in_driver here, and 2)
+ * decrement it in put_request. Such a solution would
+ * let the value of the counter be always accurate,
+ * but it would entail using an extra interface
+ * function. This cost seems higher than the benefit,
+ * being the frequency of non-elevator-private
+ * requests very low.
+ */
+ goto start_rq;
+ }
+
+ bfq_log(bfqd, "dispatch requests: %d busy queues", bfqd->busy_queues);
+
+ if (bfqd->busy_queues == 0)
+ goto exit;
+
+ /*
+ * Force device to serve one request at a time if
+ * strict_guarantees is true. Forcing this service scheme is
+ * currently the ONLY way to guarantee that the request
+ * service order enforced by the scheduler is respected by a
+ * queueing device. Otherwise the device is free even to make
+ * some unlucky request wait for as long as the device
+ * wishes.
+ *
+ * Of course, serving one request at at time may cause loss of
+ * throughput.
+ */
+ if (bfqd->strict_guarantees && bfqd->rq_in_driver > 0)
+ goto exit;
+
+ bfqq = bfq_select_queue(bfqd);
+ if (!bfqq)
+ goto exit;
+
+ rq = bfq_dispatch_rq_from_bfqq(bfqd, bfqq);
+
+ if (rq) {
+inc_in_driver_start_rq:
+ bfqd->rq_in_driver++;
+start_rq:
+ rq->rq_flags |= RQF_STARTED;
+ }
+exit:
+ return rq;
+}
+
+static struct request *bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
+{
+ struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
+ struct request *rq;
+
+ spin_lock_irq(&bfqd->lock);
+
+ rq = __bfq_dispatch_request(hctx);
+ spin_unlock_irq(&bfqd->lock);
+
+ return rq;
+}
+
+/*
+ * Task holds one reference to the queue, dropped when task exits. Each rq
+ * in-flight on this queue also holds a reference, dropped when rq is freed.
+ *
+ * Scheduler lock must be held here. Recall not to use bfqq after calling
+ * this function on it.
+ */
+void bfq_put_queue(struct bfq_queue *bfqq)
+{
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ struct bfq_group *bfqg = bfqq_group(bfqq);
+#endif
+
+ if (bfqq->bfqd)
+ bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p %d",
+ bfqq, bfqq->ref);
+
+ bfqq->ref--;
+ if (bfqq->ref)
+ return;
+
+ if (bfq_bfqq_sync(bfqq))
+ /*
+ * The fact that this queue is being destroyed does not
+ * invalidate the fact that this queue may have been
+ * activated during the current burst. As a consequence,
+ * although the queue does not exist anymore, and hence
+ * needs to be removed from the burst list if there,
+ * the burst size has not to be decremented.
+ */
+ hlist_del_init(&bfqq->burst_list_node);
+
+ kmem_cache_free(bfq_pool, bfqq);
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ bfqg_put(bfqg);
+#endif
+}
+
+static void bfq_put_cooperator(struct bfq_queue *bfqq)
+{
+ struct bfq_queue *__bfqq, *next;
+
+ /*
+ * If this queue was scheduled to merge with another queue, be
+ * sure to drop the reference taken on that queue (and others in
+ * the merge chain). See bfq_setup_merge and bfq_merge_bfqqs.
+ */
+ __bfqq = bfqq->new_bfqq;
+ while (__bfqq) {
+ if (__bfqq == bfqq)
+ break;
+ next = __bfqq->new_bfqq;
+ bfq_put_queue(__bfqq);
+ __bfqq = next;
+ }
+}
+
+static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+ if (bfqq == bfqd->in_service_queue) {
+ __bfq_bfqq_expire(bfqd, bfqq);
+ bfq_schedule_dispatch(bfqd);
+ }
+
+ bfq_log_bfqq(bfqd, bfqq, "exit_bfqq: %p, %d", bfqq, bfqq->ref);
+
+ bfq_put_cooperator(bfqq);
+
+ bfq_put_queue(bfqq); /* release process reference */
+}
+
+static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync)
+{
+ struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync);
+ struct bfq_data *bfqd;
+
+ if (bfqq)
+ bfqd = bfqq->bfqd; /* NULL if scheduler already exited */
+
+ if (bfqq && bfqd) {
+ unsigned long flags;
+
+ spin_lock_irqsave(&bfqd->lock, flags);
+ bfq_exit_bfqq(bfqd, bfqq);
+ bic_set_bfqq(bic, NULL, is_sync);
+ spin_unlock_irqrestore(&bfqd->lock, flags);
+ }
+}
+
+static void bfq_exit_icq(struct io_cq *icq)
+{
+ struct bfq_io_cq *bic = icq_to_bic(icq);
+
+ bfq_exit_icq_bfqq(bic, true);
+ bfq_exit_icq_bfqq(bic, false);
+}
+
+/*
+ * Update the entity prio values; note that the new values will not
+ * be used until the next (re)activation.
+ */
+static void
+bfq_set_next_ioprio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
+{
+ struct task_struct *tsk = current;
+ int ioprio_class;
+ struct bfq_data *bfqd = bfqq->bfqd;
+
+ if (!bfqd)
+ return;
+
+ ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio);
+ switch (ioprio_class) {
+ default:
+ dev_err(bfqq->bfqd->queue->backing_dev_info->dev,
+ "bfq: bad prio class %d\n", ioprio_class);
+ case IOPRIO_CLASS_NONE:
+ /*
+ * No prio set, inherit CPU scheduling settings.
+ */
+ bfqq->new_ioprio = task_nice_ioprio(tsk);
+ bfqq->new_ioprio_class = task_nice_ioclass(tsk);
+ break;
+ case IOPRIO_CLASS_RT:
+ bfqq->new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
+ bfqq->new_ioprio_class = IOPRIO_CLASS_RT;
+ break;
+ case IOPRIO_CLASS_BE:
+ bfqq->new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
+ bfqq->new_ioprio_class = IOPRIO_CLASS_BE;
+ break;
+ case IOPRIO_CLASS_IDLE:
+ bfqq->new_ioprio_class = IOPRIO_CLASS_IDLE;
+ bfqq->new_ioprio = 7;
+ bfq_clear_bfqq_idle_window(bfqq);
+ break;
+ }
+
+ if (bfqq->new_ioprio >= IOPRIO_BE_NR) {
+ pr_crit("bfq_set_next_ioprio_data: new_ioprio %d\n",
+ bfqq->new_ioprio);
+ bfqq->new_ioprio = IOPRIO_BE_NR;
+ }
+
+ bfqq->entity.new_weight = bfq_ioprio_to_weight(bfqq->new_ioprio);
+ bfqq->entity.prio_changed = 1;
+}
+
+static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
+ struct bio *bio, bool is_sync,
+ struct bfq_io_cq *bic);
+
+static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio)
+{
+ struct bfq_data *bfqd = bic_to_bfqd(bic);
+ struct bfq_queue *bfqq;
+ int ioprio = bic->icq.ioc->ioprio;
+
+ /*
+ * This condition may trigger on a newly created bic, be sure to
+ * drop the lock before returning.
+ */
+ if (unlikely(!bfqd) || likely(bic->ioprio == ioprio))
+ return;
+
+ bic->ioprio = ioprio;
+
+ bfqq = bic_to_bfqq(bic, false);
+ if (bfqq) {
+ /* release process reference on this queue */
+ bfq_put_queue(bfqq);
+ bfqq = bfq_get_queue(bfqd, bio, BLK_RW_ASYNC, bic);
+ bic_set_bfqq(bic, bfqq, false);
+ }
+
+ bfqq = bic_to_bfqq(bic, true);
+ if (bfqq)
+ bfq_set_next_ioprio_data(bfqq, bic);
+}
+
+static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ struct bfq_io_cq *bic, pid_t pid, int is_sync)
+{
+ RB_CLEAR_NODE(&bfqq->entity.rb_node);
+ INIT_LIST_HEAD(&bfqq->fifo);
+ INIT_HLIST_NODE(&bfqq->burst_list_node);
+
+ bfqq->ref = 0;
+ bfqq->bfqd = bfqd;
+
+ if (bic)
+ bfq_set_next_ioprio_data(bfqq, bic);
+
+ if (is_sync) {
+ if (!bfq_class_idle(bfqq))
+ bfq_mark_bfqq_idle_window(bfqq);
+ bfq_mark_bfqq_sync(bfqq);
+ bfq_mark_bfqq_just_created(bfqq);
+ } else
+ bfq_clear_bfqq_sync(bfqq);
+
+ /* set end request to minus infinity from now */
+ bfqq->ttime.last_end_request = ktime_get_ns() + 1;
+
+ bfq_mark_bfqq_IO_bound(bfqq);
+
+ bfqq->pid = pid;
+
+ /* Tentative initial value to trade off between thr and lat */
+ bfqq->max_budget = (2 * bfq_max_budget(bfqd)) / 3;
+ bfqq->budget_timeout = bfq_smallest_from_now();
+
+ bfqq->wr_coeff = 1;
+ bfqq->last_wr_start_finish = jiffies;
+ bfqq->wr_start_at_switch_to_srt = bfq_smallest_from_now();
+ bfqq->split_time = bfq_smallest_from_now();
+
+ /*
+ * Set to the value for which bfqq will not be deemed as
+ * soft rt when it becomes backlogged.
+ */
+ bfqq->soft_rt_next_start = bfq_greatest_from_now();
+
+ /* first request is almost certainly seeky */
+ bfqq->seek_history = 1;
+}
+
+static struct bfq_queue **bfq_async_queue_prio(struct bfq_data *bfqd,
+ struct bfq_group *bfqg,
+ int ioprio_class, int ioprio)
+{
+ switch (ioprio_class) {
+ case IOPRIO_CLASS_RT:
+ return &bfqg->async_bfqq[0][ioprio];
+ case IOPRIO_CLASS_NONE:
+ ioprio = IOPRIO_NORM;
+ /* fall through */
+ case IOPRIO_CLASS_BE:
+ return &bfqg->async_bfqq[1][ioprio];
+ case IOPRIO_CLASS_IDLE:
+ return &bfqg->async_idle_bfqq;
+ default:
+ return NULL;
+ }
+}
+
+static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
+ struct bio *bio, bool is_sync,
+ struct bfq_io_cq *bic)
+{
+ const int ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
+ const int ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio);
+ struct bfq_queue **async_bfqq = NULL;
+ struct bfq_queue *bfqq;
+ struct bfq_group *bfqg;
+
+ rcu_read_lock();
+
+ bfqg = bfq_find_set_group(bfqd, bio_blkcg(bio));
+ if (!bfqg) {
+ bfqq = &bfqd->oom_bfqq;
+ goto out;
+ }
+
+ if (!is_sync) {
+ async_bfqq = bfq_async_queue_prio(bfqd, bfqg, ioprio_class,
+ ioprio);
+ bfqq = *async_bfqq;
+ if (bfqq)
+ goto out;
+ }
+
+ bfqq = kmem_cache_alloc_node(bfq_pool,
+ GFP_NOWAIT | __GFP_ZERO | __GFP_NOWARN,
+ bfqd->queue->node);
+
+ if (bfqq) {
+ bfq_init_bfqq(bfqd, bfqq, bic, current->pid,
+ is_sync);
+ bfq_init_entity(&bfqq->entity, bfqg);
+ bfq_log_bfqq(bfqd, bfqq, "allocated");
+ } else {
+ bfqq = &bfqd->oom_bfqq;
+ bfq_log_bfqq(bfqd, bfqq, "using oom bfqq");
+ goto out;
+ }
+
+ /*
+ * Pin the queue now that it's allocated, scheduler exit will
+ * prune it.
+ */
+ if (async_bfqq) {
+ bfqq->ref++; /*
+ * Extra group reference, w.r.t. sync
+ * queue. This extra reference is removed
+ * only if bfqq->bfqg disappears, to
+ * guarantee that this queue is not freed
+ * until its group goes away.
+ */
+ bfq_log_bfqq(bfqd, bfqq, "get_queue, bfqq not in async: %p, %d",
+ bfqq, bfqq->ref);
+ *async_bfqq = bfqq;
+ }
+
+out:
+ bfqq->ref++; /* get a process reference to this queue */
+ bfq_log_bfqq(bfqd, bfqq, "get_queue, at end: %p, %d", bfqq, bfqq->ref);
+ rcu_read_unlock();
+ return bfqq;
+}
+
+static void bfq_update_io_thinktime(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq)
+{
+ struct bfq_ttime *ttime = &bfqq->ttime;
+ u64 elapsed = ktime_get_ns() - bfqq->ttime.last_end_request;
+
+ elapsed = min_t(u64, elapsed, 2ULL * bfqd->bfq_slice_idle);
+
+ ttime->ttime_samples = (7*bfqq->ttime.ttime_samples + 256) / 8;
+ ttime->ttime_total = div_u64(7*ttime->ttime_total + 256*elapsed, 8);
+ ttime->ttime_mean = div64_ul(ttime->ttime_total + 128,
+ ttime->ttime_samples);
+}
+
+static void
+bfq_update_io_seektime(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ struct request *rq)
+{
+ bfqq->seek_history <<= 1;
+ bfqq->seek_history |=
+ get_sdist(bfqq->last_request_pos, rq) > BFQQ_SEEK_THR &&
+ (!blk_queue_nonrot(bfqd->queue) ||
+ blk_rq_sectors(rq) < BFQQ_SECT_THR_NONROT);
+}
+
+/*
+ * Disable idle window if the process thinks too long or seeks so much that
+ * it doesn't matter.
+ */
+static void bfq_update_idle_window(struct bfq_data *bfqd,
+ struct bfq_queue *bfqq,
+ struct bfq_io_cq *bic)
+{
+ int enable_idle;
+
+ /* Don't idle for async or idle io prio class. */
+ if (!bfq_bfqq_sync(bfqq) || bfq_class_idle(bfqq))
+ return;
+
+ /* Idle window just restored, statistics are meaningless. */
+ if (time_is_after_eq_jiffies(bfqq->split_time +
+ bfqd->bfq_wr_min_idle_time))
+ return;
+
+ enable_idle = bfq_bfqq_idle_window(bfqq);
+
+ if (atomic_read(&bic->icq.ioc->active_ref) == 0 ||
+ bfqd->bfq_slice_idle == 0 ||
+ (bfqd->hw_tag && BFQQ_SEEKY(bfqq) &&
+ bfqq->wr_coeff == 1))
+ enable_idle = 0;
+ else if (bfq_sample_valid(bfqq->ttime.ttime_samples)) {
+ if (bfqq->ttime.ttime_mean > bfqd->bfq_slice_idle &&
+ bfqq->wr_coeff == 1)
+ enable_idle = 0;
+ else
+ enable_idle = 1;
+ }
+ bfq_log_bfqq(bfqd, bfqq, "update_idle_window: enable_idle %d",
+ enable_idle);
+
+ if (enable_idle)
+ bfq_mark_bfqq_idle_window(bfqq);
+ else
+ bfq_clear_bfqq_idle_window(bfqq);
+}
+
+/*
+ * Called when a new fs request (rq) is added to bfqq. Check if there's
+ * something we should do about it.
+ */
+static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ struct request *rq)
+{
+ struct bfq_io_cq *bic = RQ_BIC(rq);
+
+ if (rq->cmd_flags & REQ_META)
+ bfqq->meta_pending++;
+
+ bfq_update_io_thinktime(bfqd, bfqq);
+ bfq_update_io_seektime(bfqd, bfqq, rq);
+ if (bfqq->entity.service > bfq_max_budget(bfqd) / 8 ||
+ !BFQQ_SEEKY(bfqq))
+ bfq_update_idle_window(bfqd, bfqq, bic);
+
+ bfq_log_bfqq(bfqd, bfqq,
+ "rq_enqueued: idle_window=%d (seeky %d)",
+ bfq_bfqq_idle_window(bfqq), BFQQ_SEEKY(bfqq));
+
+ bfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);
+
+ if (bfqq == bfqd->in_service_queue && bfq_bfqq_wait_request(bfqq)) {
+ bool small_req = bfqq->queued[rq_is_sync(rq)] == 1 &&
+ blk_rq_sectors(rq) < 32;
+ bool budget_timeout = bfq_bfqq_budget_timeout(bfqq);
+
+ /*
+ * There is just this request queued: if the request
+ * is small and the queue is not to be expired, then
+ * just exit.
+ *
+ * In this way, if the device is being idled to wait
+ * for a new request from the in-service queue, we
+ * avoid unplugging the device and committing the
+ * device to serve just a small request. On the
+ * contrary, we wait for the block layer to decide
+ * when to unplug the device: hopefully, new requests
+ * will be merged to this one quickly, then the device
+ * will be unplugged and larger requests will be
+ * dispatched.
+ */
+ if (small_req && !budget_timeout)
+ return;
+
+ /*
+ * A large enough request arrived, or the queue is to
+ * be expired: in both cases disk idling is to be
+ * stopped, so clear wait_request flag and reset
+ * timer.
+ */
+ bfq_clear_bfqq_wait_request(bfqq);
+ hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
+ bfqg_stats_update_idle_time(bfqq_group(bfqq));
+
+ /*
+ * The queue is not empty, because a new request just
+ * arrived. Hence we can safely expire the queue, in
+ * case of budget timeout, without risking that the
+ * timestamps of the queue are not updated correctly.
+ * See [1] for more details.
+ */
+ if (budget_timeout)
+ bfq_bfqq_expire(bfqd, bfqq, false,
+ BFQQE_BUDGET_TIMEOUT);
+ }
+}
+
+static void __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
+{
+ struct bfq_queue *bfqq = RQ_BFQQ(rq),
+ *new_bfqq = bfq_setup_cooperator(bfqd, bfqq, rq, true);
+
+ if (new_bfqq) {
+ if (bic_to_bfqq(RQ_BIC(rq), 1) != bfqq)
+ new_bfqq = bic_to_bfqq(RQ_BIC(rq), 1);
+ /*
+ * Release the request's reference to the old bfqq
+ * and make sure one is taken to the shared queue.
+ */
+ new_bfqq->allocated++;
+ bfqq->allocated--;
+ new_bfqq->ref++;
+ bfq_clear_bfqq_just_created(bfqq);
+ /*
+ * If the bic associated with the process
+ * issuing this request still points to bfqq
+ * (and thus has not been already redirected
+ * to new_bfqq or even some other bfq_queue),
+ * then complete the merge and redirect it to
+ * new_bfqq.
+ */
+ if (bic_to_bfqq(RQ_BIC(rq), 1) == bfqq)
+ bfq_merge_bfqqs(bfqd, RQ_BIC(rq),
+ bfqq, new_bfqq);
+ /*
+ * rq is about to be enqueued into new_bfqq,
+ * release rq reference on bfqq
+ */
+ bfq_put_queue(bfqq);
+ rq->elv.priv[1] = new_bfqq;
+ bfqq = new_bfqq;
+ }
+
+ bfq_add_request(rq);
+
+ rq->fifo_time = ktime_get_ns() + bfqd->bfq_fifo_expire[rq_is_sync(rq)];
+ list_add_tail(&rq->queuelist, &bfqq->fifo);
+
+ bfq_rq_enqueued(bfqd, bfqq, rq);
+}
+
+static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
+ bool at_head)
+{
+ struct request_queue *q = hctx->queue;
+ struct bfq_data *bfqd = q->elevator->elevator_data;
+
+ spin_lock_irq(&bfqd->lock);
+ if (blk_mq_sched_try_insert_merge(q, rq)) {
+ spin_unlock_irq(&bfqd->lock);
+ return;
+ }
+
+ spin_unlock_irq(&bfqd->lock);
+
+ blk_mq_sched_request_inserted(rq);
+
+ spin_lock_irq(&bfqd->lock);
+ if (at_head || blk_rq_is_passthrough(rq)) {
+ if (at_head)
+ list_add(&rq->queuelist, &bfqd->dispatch);
+ else
+ list_add_tail(&rq->queuelist, &bfqd->dispatch);
+ } else {
+ __bfq_insert_request(bfqd, rq);
+
+ if (rq_mergeable(rq)) {
+ elv_rqhash_add(q, rq);
+ if (!q->last_merge)
+ q->last_merge = rq;
+ }
+ }
+
+ spin_unlock_irq(&bfqd->lock);
+}
+
+static void bfq_insert_requests(struct blk_mq_hw_ctx *hctx,
+ struct list_head *list, bool at_head)
+{
+ while (!list_empty(list)) {
+ struct request *rq;
+
+ rq = list_first_entry(list, struct request, queuelist);
+ list_del_init(&rq->queuelist);
+ bfq_insert_request(hctx, rq, at_head);
+ }
+}
+
+static void bfq_update_hw_tag(struct bfq_data *bfqd)
+{
+ bfqd->max_rq_in_driver = max_t(int, bfqd->max_rq_in_driver,
+ bfqd->rq_in_driver);
+
+ if (bfqd->hw_tag == 1)
+ return;
+
+ /*
+ * This sample is valid if the number of outstanding requests
+ * is large enough to allow a queueing behavior. Note that the
+ * sum is not exact, as it's not taking into account deactivated
+ * requests.
+ */
+ if (bfqd->rq_in_driver + bfqd->queued < BFQ_HW_QUEUE_THRESHOLD)
+ return;
+
+ if (bfqd->hw_tag_samples++ < BFQ_HW_QUEUE_SAMPLES)
+ return;
+
+ bfqd->hw_tag = bfqd->max_rq_in_driver > BFQ_HW_QUEUE_THRESHOLD;
+ bfqd->max_rq_in_driver = 0;
+ bfqd->hw_tag_samples = 0;
+}
+
+static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
+{
+ u64 now_ns;
+ u32 delta_us;
+
+ bfq_update_hw_tag(bfqd);
+
+ bfqd->rq_in_driver--;
+ bfqq->dispatched--;
+
+ if (!bfqq->dispatched && !bfq_bfqq_busy(bfqq)) {
+ /*
+ * Set budget_timeout (which we overload to store the
+ * time at which the queue remains with no backlog and
+ * no outstanding request; used by the weight-raising
+ * mechanism).
+ */
+ bfqq->budget_timeout = jiffies;
+
+ bfq_weights_tree_remove(bfqd, &bfqq->entity,
+ &bfqd->queue_weights_tree);
+ }
+
+ now_ns = ktime_get_ns();
+
+ bfqq->ttime.last_end_request = now_ns;
+
+ /*
+ * Using us instead of ns, to get a reasonable precision in
+ * computing rate in next check.
+ */
+ delta_us = div_u64(now_ns - bfqd->last_completion, NSEC_PER_USEC);
+
+ /*
+ * If the request took rather long to complete, and, according
+ * to the maximum request size recorded, this completion latency
+ * implies that the request was certainly served at a very low
+ * rate (less than 1M sectors/sec), then the whole observation
+ * interval that lasts up to this time instant cannot be a
+ * valid time interval for computing a new peak rate. Invoke
+ * bfq_update_rate_reset to have the following three steps
+ * taken:
+ * - close the observation interval at the last (previous)
+ * request dispatch or completion
+ * - compute rate, if possible, for that observation interval
+ * - reset to zero samples, which will trigger a proper
+ * re-initialization of the observation interval on next
+ * dispatch
+ */
+ if (delta_us > BFQ_MIN_TT/NSEC_PER_USEC &&
+ (bfqd->last_rq_max_size<<BFQ_RATE_SHIFT)/delta_us <
+ 1UL<<(BFQ_RATE_SHIFT - 10))
+ bfq_update_rate_reset(bfqd, NULL);
+ bfqd->last_completion = now_ns;
+
+ /*
+ * If we are waiting to discover whether the request pattern
+ * of the task associated with the queue is actually
+ * isochronous, and both requisites for this condition to hold
+ * are now satisfied, then compute soft_rt_next_start (see the
+ * comments on the function bfq_bfqq_softrt_next_start()). We
+ * schedule this delayed check when bfqq expires, if it still
+ * has in-flight requests.
+ */
+ if (bfq_bfqq_softrt_update(bfqq) && bfqq->dispatched == 0 &&
+ RB_EMPTY_ROOT(&bfqq->sort_list))
+ bfqq->soft_rt_next_start =
+ bfq_bfqq_softrt_next_start(bfqd, bfqq);
+
+ /*
+ * If this is the in-service queue, check if it needs to be expired,
+ * or if we want to idle in case it has no pending requests.
+ */
+ if (bfqd->in_service_queue == bfqq) {
+ if (bfqq->dispatched == 0 && bfq_bfqq_must_idle(bfqq)) {
+ bfq_arm_slice_timer(bfqd);
+ return;
+ } else if (bfq_may_expire_for_budg_timeout(bfqq))
+ bfq_bfqq_expire(bfqd, bfqq, false,
+ BFQQE_BUDGET_TIMEOUT);
+ else if (RB_EMPTY_ROOT(&bfqq->sort_list) &&
+ (bfqq->dispatched == 0 ||
+ !bfq_bfqq_may_idle(bfqq)))
+ bfq_bfqq_expire(bfqd, bfqq, false,
+ BFQQE_NO_MORE_REQUESTS);
+ }
+}
+
+static void bfq_put_rq_priv_body(struct bfq_queue *bfqq)
+{
+ bfqq->allocated--;
+
+ bfq_put_queue(bfqq);
+}
+
+static void bfq_put_rq_private(struct request_queue *q, struct request *rq)
+{
+ struct bfq_queue *bfqq = RQ_BFQQ(rq);
+ struct bfq_data *bfqd = bfqq->bfqd;
+
+ if (rq->rq_flags & RQF_STARTED)
+ bfqg_stats_update_completion(bfqq_group(bfqq),
+ rq_start_time_ns(rq),
+ rq_io_start_time_ns(rq),
+ rq->cmd_flags);
+
+ if (likely(rq->rq_flags & RQF_STARTED)) {
+ unsigned long flags;
+
+ spin_lock_irqsave(&bfqd->lock, flags);
+
+ bfq_completed_request(bfqq, bfqd);
+ bfq_put_rq_priv_body(bfqq);
+
+ spin_unlock_irqrestore(&bfqd->lock, flags);
+ } else {
+ /*
+ * Request rq may be still/already in the scheduler,
+ * in which case we need to remove it. And we cannot
+ * defer such a check and removal, to avoid
+ * inconsistencies in the time interval from the end
+ * of this function to the start of the deferred work.
+ * This situation seems to occur only in process
+ * context, as a consequence of a merge. In the
+ * current version of the code, this implies that the
+ * lock is held.
+ */
+
+ if (!RB_EMPTY_NODE(&rq->rb_node))
+ bfq_remove_request(q, rq);
+ bfq_put_rq_priv_body(bfqq);
+ }
+
+ rq->elv.priv[0] = NULL;
+ rq->elv.priv[1] = NULL;
+}
+
+/*
+ * Returns NULL if a new bfqq should be allocated, or the old bfqq if this
+ * was the last process referring to that bfqq.
+ */
+static struct bfq_queue *
+bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq)
+{
+ bfq_log_bfqq(bfqq->bfqd, bfqq, "splitting queue");
+
+ if (bfqq_process_refs(bfqq) == 1) {
+ bfqq->pid = current->pid;
+ bfq_clear_bfqq_coop(bfqq);
+ bfq_clear_bfqq_split_coop(bfqq);
+ return bfqq;
+ }
+
+ bic_set_bfqq(bic, NULL, 1);
+
+ bfq_put_cooperator(bfqq);
+
+ bfq_put_queue(bfqq);
+ return NULL;
+}
+
+static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd,
+ struct bfq_io_cq *bic,
+ struct bio *bio,
+ bool split, bool is_sync,
+ bool *new_queue)
+{
+ struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync);
+
+ if (likely(bfqq && bfqq != &bfqd->oom_bfqq))
+ return bfqq;
+
+ if (new_queue)
+ *new_queue = true;
+
+ if (bfqq)
+ bfq_put_queue(bfqq);
+ bfqq = bfq_get_queue(bfqd, bio, is_sync, bic);
+
+ bic_set_bfqq(bic, bfqq, is_sync);
+ if (split && is_sync) {
+ if ((bic->was_in_burst_list && bfqd->large_burst) ||
+ bic->saved_in_large_burst)
+ bfq_mark_bfqq_in_large_burst(bfqq);
+ else {
+ bfq_clear_bfqq_in_large_burst(bfqq);
+ if (bic->was_in_burst_list)
+ hlist_add_head(&bfqq->burst_list_node,
+ &bfqd->burst_list);
+ }
+ bfqq->split_time = jiffies;
+ }
+
+ return bfqq;
+}
+
+/*
+ * Allocate bfq data structures associated with this request.
+ */
+static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
+ struct bio *bio)
+{
+ struct bfq_data *bfqd = q->elevator->elevator_data;
+ struct bfq_io_cq *bic = icq_to_bic(rq->elv.icq);
+ const int is_sync = rq_is_sync(rq);
+ struct bfq_queue *bfqq;
+ bool new_queue = false;
+ bool split = false;
+
+ spin_lock_irq(&bfqd->lock);
+
+ if (!bic)
+ goto queue_fail;
+
+ bfq_check_ioprio_change(bic, bio);
+
+ bfq_bic_update_cgroup(bic, bio);
+
+ bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio, false, is_sync,
+ &new_queue);
+
+ if (likely(!new_queue)) {
+ /* If the queue was seeky for too long, break it apart. */
+ if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq)) {
+ bfq_log_bfqq(bfqd, bfqq, "breaking apart bfqq");
+
+ /* Update bic before losing reference to bfqq */
+ if (bfq_bfqq_in_large_burst(bfqq))
+ bic->saved_in_large_burst = true;
+
+ bfqq = bfq_split_bfqq(bic, bfqq);
+ split = true;
+
+ if (!bfqq)
+ bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio,
+ true, is_sync,
+ NULL);
+ }
+ }
+
+ bfqq->allocated++;
+ bfqq->ref++;
+ bfq_log_bfqq(bfqd, bfqq, "get_request %p: bfqq %p, %d",
+ rq, bfqq, bfqq->ref);
+
+ rq->elv.priv[0] = bic;
+ rq->elv.priv[1] = bfqq;
+
+ /*
+ * If a bfq_queue has only one process reference, it is owned
+ * by only this bic: we can then set bfqq->bic = bic. in
+ * addition, if the queue has also just been split, we have to
+ * resume its state.
+ */
+ if (likely(bfqq != &bfqd->oom_bfqq) && bfqq_process_refs(bfqq) == 1) {
+ bfqq->bic = bic;
+ if (split) {
+ /*
+ * The queue has just been split from a shared
+ * queue: restore the idle window and the
+ * possible weight raising period.
+ */
+ bfq_bfqq_resume_state(bfqq, bic);
+ }
+ }
+
+ if (unlikely(bfq_bfqq_just_created(bfqq)))
+ bfq_handle_burst(bfqd, bfqq);
+
+ spin_unlock_irq(&bfqd->lock);
+
+ return 0;
+
+queue_fail:
+ spin_unlock_irq(&bfqd->lock);
+
+ return 1;
+}
+
+static void bfq_idle_slice_timer_body(struct bfq_queue *bfqq)
+{
+ struct bfq_data *bfqd = bfqq->bfqd;
+ enum bfqq_expiration reason;
+ unsigned long flags;
+
+ spin_lock_irqsave(&bfqd->lock, flags);
+ bfq_clear_bfqq_wait_request(bfqq);
+
+ if (bfqq != bfqd->in_service_queue) {
+ spin_unlock_irqrestore(&bfqd->lock, flags);
+ return;
+ }
+
+ if (bfq_bfqq_budget_timeout(bfqq))
+ /*
+ * Also here the queue can be safely expired
+ * for budget timeout without wasting
+ * guarantees
+ */
+ reason = BFQQE_BUDGET_TIMEOUT;
+ else if (bfqq->queued[0] == 0 && bfqq->queued[1] == 0)
+ /*
+ * The queue may not be empty upon timer expiration,
+ * because we may not disable the timer when the
+ * first request of the in-service queue arrives
+ * during disk idling.
+ */
+ reason = BFQQE_TOO_IDLE;
+ else
+ goto schedule_dispatch;
+
+ bfq_bfqq_expire(bfqd, bfqq, true, reason);
+
+schedule_dispatch:
+ spin_unlock_irqrestore(&bfqd->lock, flags);
+ bfq_schedule_dispatch(bfqd);
+}
+
+/*
+ * Handler of the expiration of the timer running if the in-service queue
+ * is idling inside its time slice.
+ */
+static enum hrtimer_restart bfq_idle_slice_timer(struct hrtimer *timer)
+{
+ struct bfq_data *bfqd = container_of(timer, struct bfq_data,
+ idle_slice_timer);
+ struct bfq_queue *bfqq = bfqd->in_service_queue;
+
+ /*
+ * Theoretical race here: the in-service queue can be NULL or
+ * different from the queue that was idling if a new request
+ * arrives for the current queue and there is a full dispatch
+ * cycle that changes the in-service queue. This can hardly
+ * happen, but in the worst case we just expire a queue too
+ * early.
+ */
+ if (bfqq)
+ bfq_idle_slice_timer_body(bfqq);
+
+ return HRTIMER_NORESTART;
+}
+
+static void __bfq_put_async_bfqq(struct bfq_data *bfqd,
+ struct bfq_queue **bfqq_ptr)
+{
+ struct bfq_queue *bfqq = *bfqq_ptr;
+
+ bfq_log(bfqd, "put_async_bfqq: %p", bfqq);
+ if (bfqq) {
+ bfq_bfqq_move(bfqd, bfqq, bfqd->root_group);
+
+ bfq_log_bfqq(bfqd, bfqq, "put_async_bfqq: putting %p, %d",
+ bfqq, bfqq->ref);
+ bfq_put_queue(bfqq);
+ *bfqq_ptr = NULL;
+ }
+}
+
+/*
+ * Release all the bfqg references to its async queues. If we are
+ * deallocating the group these queues may still contain requests, so
+ * we reparent them to the root cgroup (i.e., the only one that will
+ * exist for sure until all the requests on a device are gone).
+ */
+void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg)
+{
+ int i, j;
+
+ for (i = 0; i < 2; i++)
+ for (j = 0; j < IOPRIO_BE_NR; j++)
+ __bfq_put_async_bfqq(bfqd, &bfqg->async_bfqq[i][j]);
+
+ __bfq_put_async_bfqq(bfqd, &bfqg->async_idle_bfqq);
+}
+
+static void bfq_exit_queue(struct elevator_queue *e)
+{
+ struct bfq_data *bfqd = e->elevator_data;
+ struct bfq_queue *bfqq, *n;
+
+ hrtimer_cancel(&bfqd->idle_slice_timer);
+
+ spin_lock_irq(&bfqd->lock);
+ list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list)
+ bfq_deactivate_bfqq(bfqd, bfqq, false, false);
+ spin_unlock_irq(&bfqd->lock);
+
+ hrtimer_cancel(&bfqd->idle_slice_timer);
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ blkcg_deactivate_policy(bfqd->queue, &blkcg_policy_bfq);
+#else
+ spin_lock_irq(&bfqd->lock);
+ bfq_put_async_queues(bfqd, bfqd->root_group);
+ kfree(bfqd->root_group);
+ spin_unlock_irq(&bfqd->lock);
+#endif
+
+ kfree(bfqd);
+}
+
+static void bfq_init_root_group(struct bfq_group *root_group,
+ struct bfq_data *bfqd)
+{
+ int i;
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ root_group->entity.parent = NULL;
+ root_group->my_entity = NULL;
+ root_group->bfqd = bfqd;
+#endif
+ root_group->rq_pos_tree = RB_ROOT;
+ for (i = 0; i < BFQ_IOPRIO_CLASSES; i++)
+ root_group->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT;
+ root_group->sched_data.bfq_class_idle_last_service = jiffies;
+}
+
+static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
+{
+ struct bfq_data *bfqd;
+ struct elevator_queue *eq;
+
+ eq = elevator_alloc(q, e);
+ if (!eq)
+ return -ENOMEM;
+
+ bfqd = kzalloc_node(sizeof(*bfqd), GFP_KERNEL, q->node);
+ if (!bfqd) {
+ kobject_put(&eq->kobj);
+ return -ENOMEM;
+ }
+ eq->elevator_data = bfqd;
+
+ spin_lock_irq(q->queue_lock);
+ q->elevator = eq;
+ spin_unlock_irq(q->queue_lock);
+
+ /*
+ * Our fallback bfqq if bfq_find_alloc_queue() runs into OOM issues.
+ * Grab a permanent reference to it, so that the normal code flow
+ * will not attempt to free it.
+ */
+ bfq_init_bfqq(bfqd, &bfqd->oom_bfqq, NULL, 1, 0);
+ bfqd->oom_bfqq.ref++;
+ bfqd->oom_bfqq.new_ioprio = BFQ_DEFAULT_QUEUE_IOPRIO;
+ bfqd->oom_bfqq.new_ioprio_class = IOPRIO_CLASS_BE;
+ bfqd->oom_bfqq.entity.new_weight =
+ bfq_ioprio_to_weight(bfqd->oom_bfqq.new_ioprio);
+
+ /* oom_bfqq does not participate to bursts */
+ bfq_clear_bfqq_just_created(&bfqd->oom_bfqq);
+
+ /*
+ * Trigger weight initialization, according to ioprio, at the
+ * oom_bfqq's first activation. The oom_bfqq's ioprio and ioprio
+ * class won't be changed any more.
+ */
+ bfqd->oom_bfqq.entity.prio_changed = 1;
+
+ bfqd->queue = q;
+
+ INIT_LIST_HEAD(&bfqd->dispatch);
+
+ hrtimer_init(&bfqd->idle_slice_timer, CLOCK_MONOTONIC,
+ HRTIMER_MODE_REL);
+ bfqd->idle_slice_timer.function = bfq_idle_slice_timer;
+
+ bfqd->queue_weights_tree = RB_ROOT;
+ bfqd->group_weights_tree = RB_ROOT;
+
+ INIT_LIST_HEAD(&bfqd->active_list);
+ INIT_LIST_HEAD(&bfqd->idle_list);
+ INIT_HLIST_HEAD(&bfqd->burst_list);
+
+ bfqd->hw_tag = -1;
+
+ bfqd->bfq_max_budget = bfq_default_max_budget;
+
+ bfqd->bfq_fifo_expire[0] = bfq_fifo_expire[0];
+ bfqd->bfq_fifo_expire[1] = bfq_fifo_expire[1];
+ bfqd->bfq_back_max = bfq_back_max;
+ bfqd->bfq_back_penalty = bfq_back_penalty;
+ bfqd->bfq_slice_idle = bfq_slice_idle;
+ bfqd->bfq_timeout = bfq_timeout;
+
+ bfqd->bfq_requests_within_timer = 120;
+
+ bfqd->bfq_large_burst_thresh = 8;
+ bfqd->bfq_burst_interval = msecs_to_jiffies(180);
+
+ bfqd->low_latency = true;
+
+ /*
+ * Trade-off between responsiveness and fairness.
+ */
+ bfqd->bfq_wr_coeff = 30;
+ bfqd->bfq_wr_rt_max_time = msecs_to_jiffies(300);
+ bfqd->bfq_wr_max_time = 0;
+ bfqd->bfq_wr_min_idle_time = msecs_to_jiffies(2000);
+ bfqd->bfq_wr_min_inter_arr_async = msecs_to_jiffies(500);
+ bfqd->bfq_wr_max_softrt_rate = 7000; /*
+ * Approximate rate required
+ * to playback or record a
+ * high-definition compressed
+ * video.
+ */
+ bfqd->wr_busy_queues = 0;
+
+ /*
+ * Begin by assuming, optimistically, that the device is a
+ * high-speed one, and that its peak rate is equal to 2/3 of
+ * the highest reference rate.
+ */
+ bfqd->RT_prod = R_fast[blk_queue_nonrot(bfqd->queue)] *
+ T_fast[blk_queue_nonrot(bfqd->queue)];
+ bfqd->peak_rate = R_fast[blk_queue_nonrot(bfqd->queue)] * 2 / 3;
+ bfqd->device_speed = BFQ_BFQD_FAST;
+
+ spin_lock_init(&bfqd->lock);
+
+ /*
+ * The invocation of the next bfq_create_group_hierarchy
+ * function is the head of a chain of function calls
+ * (bfq_create_group_hierarchy->blkcg_activate_policy->
+ * blk_mq_freeze_queue) that may lead to the invocation of the
+ * has_work hook function. For this reason,
+ * bfq_create_group_hierarchy is invoked only after all
+ * scheduler data has been initialized, apart from the fields
+ * that can be initialized only after invoking
+ * bfq_create_group_hierarchy. This, in particular, enables
+ * has_work to correctly return false. Of course, to avoid
+ * other inconsistencies, the blk-mq stack must then refrain
+ * from invoking further scheduler hooks before this init
+ * function is finished.
+ */
+ bfqd->root_group = bfq_create_group_hierarchy(bfqd, q->node);
+ if (!bfqd->root_group)
+ goto out_free;
+ bfq_init_root_group(bfqd->root_group, bfqd);
+ bfq_init_entity(&bfqd->oom_bfqq.entity, bfqd->root_group);
+
+
+ return 0;
+
+out_free:
+ kfree(bfqd);
+ kobject_put(&eq->kobj);
+ return -ENOMEM;
+}
+
+static void bfq_slab_kill(void)
+{
+ kmem_cache_destroy(bfq_pool);
+}
+
+static int __init bfq_slab_setup(void)
+{
+ bfq_pool = KMEM_CACHE(bfq_queue, 0);
+ if (!bfq_pool)
+ return -ENOMEM;
+ return 0;
+}
+
+static ssize_t bfq_var_show(unsigned int var, char *page)
+{
+ return sprintf(page, "%u\n", var);
+}
+
+static ssize_t bfq_var_store(unsigned long *var, const char *page,
+ size_t count)
+{
+ unsigned long new_val;
+ int ret = kstrtoul(page, 10, &new_val);
+
+ if (ret == 0)
+ *var = new_val;
+
+ return count;
+}
+
+#define SHOW_FUNCTION(__FUNC, __VAR, __CONV) \
+static ssize_t __FUNC(struct elevator_queue *e, char *page) \
+{ \
+ struct bfq_data *bfqd = e->elevator_data; \
+ u64 __data = __VAR; \
+ if (__CONV == 1) \
+ __data = jiffies_to_msecs(__data); \
+ else if (__CONV == 2) \
+ __data = div_u64(__data, NSEC_PER_MSEC); \
+ return bfq_var_show(__data, (page)); \
+}
+SHOW_FUNCTION(bfq_fifo_expire_sync_show, bfqd->bfq_fifo_expire[1], 2);
+SHOW_FUNCTION(bfq_fifo_expire_async_show, bfqd->bfq_fifo_expire[0], 2);
+SHOW_FUNCTION(bfq_back_seek_max_show, bfqd->bfq_back_max, 0);
+SHOW_FUNCTION(bfq_back_seek_penalty_show, bfqd->bfq_back_penalty, 0);
+SHOW_FUNCTION(bfq_slice_idle_show, bfqd->bfq_slice_idle, 2);
+SHOW_FUNCTION(bfq_max_budget_show, bfqd->bfq_user_max_budget, 0);
+SHOW_FUNCTION(bfq_timeout_sync_show, bfqd->bfq_timeout, 1);
+SHOW_FUNCTION(bfq_strict_guarantees_show, bfqd->strict_guarantees, 0);
+SHOW_FUNCTION(bfq_low_latency_show, bfqd->low_latency, 0);
+#undef SHOW_FUNCTION
+
+#define USEC_SHOW_FUNCTION(__FUNC, __VAR) \
+static ssize_t __FUNC(struct elevator_queue *e, char *page) \
+{ \
+ struct bfq_data *bfqd = e->elevator_data; \
+ u64 __data = __VAR; \
+ __data = div_u64(__data, NSEC_PER_USEC); \
+ return bfq_var_show(__data, (page)); \
+}
+USEC_SHOW_FUNCTION(bfq_slice_idle_us_show, bfqd->bfq_slice_idle);
+#undef USEC_SHOW_FUNCTION
+
+#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV) \
+static ssize_t \
+__FUNC(struct elevator_queue *e, const char *page, size_t count) \
+{ \
+ struct bfq_data *bfqd = e->elevator_data; \
+ unsigned long uninitialized_var(__data); \
+ int ret = bfq_var_store(&__data, (page), count); \
+ if (__data < (MIN)) \
+ __data = (MIN); \
+ else if (__data > (MAX)) \
+ __data = (MAX); \
+ if (__CONV == 1) \
+ *(__PTR) = msecs_to_jiffies(__data); \
+ else if (__CONV == 2) \
+ *(__PTR) = (u64)__data * NSEC_PER_MSEC; \
+ else \
+ *(__PTR) = __data; \
+ return ret; \
+}
+STORE_FUNCTION(bfq_fifo_expire_sync_store, &bfqd->bfq_fifo_expire[1], 1,
+ INT_MAX, 2);
+STORE_FUNCTION(bfq_fifo_expire_async_store, &bfqd->bfq_fifo_expire[0], 1,
+ INT_MAX, 2);
+STORE_FUNCTION(bfq_back_seek_max_store, &bfqd->bfq_back_max, 0, INT_MAX, 0);
+STORE_FUNCTION(bfq_back_seek_penalty_store, &bfqd->bfq_back_penalty, 1,
+ INT_MAX, 0);
+STORE_FUNCTION(bfq_slice_idle_store, &bfqd->bfq_slice_idle, 0, INT_MAX, 2);
+#undef STORE_FUNCTION
+
+#define USEC_STORE_FUNCTION(__FUNC, __PTR, MIN, MAX) \
+static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)\
+{ \
+ struct bfq_data *bfqd = e->elevator_data; \
+ unsigned long uninitialized_var(__data); \
+ int ret = bfq_var_store(&__data, (page), count); \
+ if (__data < (MIN)) \
+ __data = (MIN); \
+ else if (__data > (MAX)) \
+ __data = (MAX); \
+ *(__PTR) = (u64)__data * NSEC_PER_USEC; \
+ return ret; \
+}
+USEC_STORE_FUNCTION(bfq_slice_idle_us_store, &bfqd->bfq_slice_idle, 0,
+ UINT_MAX);
+#undef USEC_STORE_FUNCTION
+
+static ssize_t bfq_max_budget_store(struct elevator_queue *e,
+ const char *page, size_t count)
+{
+ struct bfq_data *bfqd = e->elevator_data;
+ unsigned long uninitialized_var(__data);
+ int ret = bfq_var_store(&__data, (page), count);
+
+ if (__data == 0)
+ bfqd->bfq_max_budget = bfq_calc_max_budget(bfqd);
+ else {
+ if (__data > INT_MAX)
+ __data = INT_MAX;
+ bfqd->bfq_max_budget = __data;
+ }
+
+ bfqd->bfq_user_max_budget = __data;
+
+ return ret;
+}
+
+/*
+ * Leaving this name to preserve name compatibility with cfq
+ * parameters, but this timeout is used for both sync and async.
+ */
+static ssize_t bfq_timeout_sync_store(struct elevator_queue *e,
+ const char *page, size_t count)
+{
+ struct bfq_data *bfqd = e->elevator_data;
+ unsigned long uninitialized_var(__data);
+ int ret = bfq_var_store(&__data, (page), count);
+
+ if (__data < 1)
+ __data = 1;
+ else if (__data > INT_MAX)
+ __data = INT_MAX;
+
+ bfqd->bfq_timeout = msecs_to_jiffies(__data);
+ if (bfqd->bfq_user_max_budget == 0)
+ bfqd->bfq_max_budget = bfq_calc_max_budget(bfqd);
+
+ return ret;
+}
+
+static ssize_t bfq_strict_guarantees_store(struct elevator_queue *e,
+ const char *page, size_t count)
+{
+ struct bfq_data *bfqd = e->elevator_data;
+ unsigned long uninitialized_var(__data);
+ int ret = bfq_var_store(&__data, (page), count);
+
+ if (__data > 1)
+ __data = 1;
+ if (!bfqd->strict_guarantees && __data == 1
+ && bfqd->bfq_slice_idle < 8 * NSEC_PER_MSEC)
+ bfqd->bfq_slice_idle = 8 * NSEC_PER_MSEC;
+
+ bfqd->strict_guarantees = __data;
+
+ return ret;
+}
+
+static ssize_t bfq_low_latency_store(struct elevator_queue *e,
+ const char *page, size_t count)
+{
+ struct bfq_data *bfqd = e->elevator_data;
+ unsigned long uninitialized_var(__data);
+ int ret = bfq_var_store(&__data, (page), count);
+
+ if (__data > 1)
+ __data = 1;
+ if (__data == 0 && bfqd->low_latency != 0)
+ bfq_end_wr(bfqd);
+ bfqd->low_latency = __data;
+
+ return ret;
+}
+
+#define BFQ_ATTR(name) \
+ __ATTR(name, 0644, bfq_##name##_show, bfq_##name##_store)
+
+static struct elv_fs_entry bfq_attrs[] = {
+ BFQ_ATTR(fifo_expire_sync),
+ BFQ_ATTR(fifo_expire_async),
+ BFQ_ATTR(back_seek_max),
+ BFQ_ATTR(back_seek_penalty),
+ BFQ_ATTR(slice_idle),
+ BFQ_ATTR(slice_idle_us),
+ BFQ_ATTR(max_budget),
+ BFQ_ATTR(timeout_sync),
+ BFQ_ATTR(strict_guarantees),
+ BFQ_ATTR(low_latency),
+ __ATTR_NULL
+};
+
+static struct elevator_type iosched_bfq_mq = {
+ .ops.mq = {
+ .get_rq_priv = bfq_get_rq_private,
+ .put_rq_priv = bfq_put_rq_private,
+ .exit_icq = bfq_exit_icq,
+ .insert_requests = bfq_insert_requests,
+ .dispatch_request = bfq_dispatch_request,
+ .next_request = elv_rb_latter_request,
+ .former_request = elv_rb_former_request,
+ .allow_merge = bfq_allow_bio_merge,
+ .bio_merge = bfq_bio_merge,
+ .request_merge = bfq_request_merge,
+ .requests_merged = bfq_requests_merged,
+ .request_merged = bfq_request_merged,
+ .has_work = bfq_has_work,
+ .init_sched = bfq_init_queue,
+ .exit_sched = bfq_exit_queue,
+ },
+
+ .uses_mq = true,
+ .icq_size = sizeof(struct bfq_io_cq),
+ .icq_align = __alignof__(struct bfq_io_cq),
+ .elevator_attrs = bfq_attrs,
+ .elevator_name = "bfq",
+ .elevator_owner = THIS_MODULE,
+};
+
+static int __init bfq_init(void)
+{
+ int ret;
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ ret = blkcg_policy_register(&blkcg_policy_bfq);
+ if (ret)
+ return ret;
+#endif
+
+ ret = -ENOMEM;
+ if (bfq_slab_setup())
+ goto err_pol_unreg;
+
+ /*
+ * Times to load large popular applications for the typical
+ * systems installed on the reference devices (see the
+ * comments before the definitions of the next two
+ * arrays). Actually, we use slightly slower values, as the
+ * estimated peak rate tends to be smaller than the actual
+ * peak rate. The reason for this last fact is that estimates
+ * are computed over much shorter time intervals than the long
+ * intervals typically used for benchmarking. Why? First, to
+ * adapt more quickly to variations. Second, because an I/O
+ * scheduler cannot rely on a peak-rate-evaluation workload to
+ * be run for a long time.
+ */
+ T_slow[0] = msecs_to_jiffies(3500); /* actually 4 sec */
+ T_slow[1] = msecs_to_jiffies(6000); /* actually 6.5 sec */
+ T_fast[0] = msecs_to_jiffies(7000); /* actually 8 sec */
+ T_fast[1] = msecs_to_jiffies(2500); /* actually 3 sec */
+
+ /*
+ * Thresholds that determine the switch between speed classes
+ * (see the comments before the definition of the array
+ * device_speed_thresh). These thresholds are biased towards
+ * transitions to the fast class. This is safer than the
+ * opposite bias. In fact, a wrong transition to the slow
+ * class results in short weight-raising periods, because the
+ * speed of the device then tends to be higher that the
+ * reference peak rate. On the opposite end, a wrong
+ * transition to the fast class tends to increase
+ * weight-raising periods, because of the opposite reason.
+ */
+ device_speed_thresh[0] = (4 * R_slow[0]) / 3;
+ device_speed_thresh[1] = (4 * R_slow[1]) / 3;
+
+ ret = elv_register(&iosched_bfq_mq);
+ if (ret)
+ goto err_pol_unreg;
+
+ return 0;
+
+err_pol_unreg:
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ blkcg_policy_unregister(&blkcg_policy_bfq);
+#endif
+ return ret;
+}
+
+static void __exit bfq_exit(void)
+{
+ elv_unregister(&iosched_bfq_mq);
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ blkcg_policy_unregister(&blkcg_policy_bfq);
+#endif
+ bfq_slab_kill();
+}
+
+module_init(bfq_init);
+module_exit(bfq_exit);
+
+MODULE_AUTHOR("Paolo Valente");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("MQ Budget Fair Queueing I/O Scheduler");
--- /dev/null
+/*
+ * Header file for the BFQ I/O scheduler: data structures and
+ * prototypes of interface functions among BFQ components.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#ifndef _BFQ_H
+#define _BFQ_H
+
+#include <linux/blktrace_api.h>
+#include <linux/hrtimer.h>
+#include <linux/blk-cgroup.h>
+
+#define BFQ_IOPRIO_CLASSES 3
+#define BFQ_CL_IDLE_TIMEOUT (HZ/5)
+
+#define BFQ_MIN_WEIGHT 1
+#define BFQ_MAX_WEIGHT 1000
+#define BFQ_WEIGHT_CONVERSION_COEFF 10
+
+#define BFQ_DEFAULT_QUEUE_IOPRIO 4
+
+#define BFQ_WEIGHT_LEGACY_DFL 100
+#define BFQ_DEFAULT_GRP_IOPRIO 0
+#define BFQ_DEFAULT_GRP_CLASS IOPRIO_CLASS_BE
+
+/*
+ * Soft real-time applications are extremely more latency sensitive
+ * than interactive ones. Over-raise the weight of the former to
+ * privilege them against the latter.
+ */
+#define BFQ_SOFTRT_WEIGHT_FACTOR 100
+
+struct bfq_entity;
+
+/**
+ * struct bfq_service_tree - per ioprio_class service tree.
+ *
+ * Each service tree represents a B-WF2Q+ scheduler on its own. Each
+ * ioprio_class has its own independent scheduler, and so its own
+ * bfq_service_tree. All the fields are protected by the queue lock
+ * of the containing bfqd.
+ */
+struct bfq_service_tree {
+ /* tree for active entities (i.e., those backlogged) */
+ struct rb_root active;
+ /* tree for idle entities (i.e., not backlogged, with V <= F_i)*/
+ struct rb_root idle;
+
+ /* idle entity with minimum F_i */
+ struct bfq_entity *first_idle;
+ /* idle entity with maximum F_i */
+ struct bfq_entity *last_idle;
+
+ /* scheduler virtual time */
+ u64 vtime;
+ /* scheduler weight sum; active and idle entities contribute to it */
+ unsigned long wsum;
+};
+
+/**
+ * struct bfq_sched_data - multi-class scheduler.
+ *
+ * bfq_sched_data is the basic scheduler queue. It supports three
+ * ioprio_classes, and can be used either as a toplevel queue or as an
+ * intermediate queue on a hierarchical setup. @next_in_service
+ * points to the active entity of the sched_data service trees that
+ * will be scheduled next. It is used to reduce the number of steps
+ * needed for each hierarchical-schedule update.
+ *
+ * The supported ioprio_classes are the same as in CFQ, in descending
+ * priority order, IOPRIO_CLASS_RT, IOPRIO_CLASS_BE, IOPRIO_CLASS_IDLE.
+ * Requests from higher priority queues are served before all the
+ * requests from lower priority queues; among requests of the same
+ * queue requests are served according to B-WF2Q+.
+ * All the fields are protected by the queue lock of the containing bfqd.
+ */
+struct bfq_sched_data {
+ /* entity in service */
+ struct bfq_entity *in_service_entity;
+ /* head-of-line entity (see comments above) */
+ struct bfq_entity *next_in_service;
+ /* array of service trees, one per ioprio_class */
+ struct bfq_service_tree service_tree[BFQ_IOPRIO_CLASSES];
+ /* last time CLASS_IDLE was served */
+ unsigned long bfq_class_idle_last_service;
+
+};
+
+/**
+ * struct bfq_weight_counter - counter of the number of all active entities
+ * with a given weight.
+ */
+struct bfq_weight_counter {
+ unsigned int weight; /* weight of the entities this counter refers to */
+ unsigned int num_active; /* nr of active entities with this weight */
+ /*
+ * Weights tree member (see bfq_data's @queue_weights_tree and
+ * @group_weights_tree)
+ */
+ struct rb_node weights_node;
+};
+
+/**
+ * struct bfq_entity - schedulable entity.
+ *
+ * A bfq_entity is used to represent either a bfq_queue (leaf node in the
+ * cgroup hierarchy) or a bfq_group into the upper level scheduler. Each
+ * entity belongs to the sched_data of the parent group in the cgroup
+ * hierarchy. Non-leaf entities have also their own sched_data, stored
+ * in @my_sched_data.
+ *
+ * Each entity stores independently its priority values; this would
+ * allow different weights on different devices, but this
+ * functionality is not exported to userspace by now. Priorities and
+ * weights are updated lazily, first storing the new values into the
+ * new_* fields, then setting the @prio_changed flag. As soon as
+ * there is a transition in the entity state that allows the priority
+ * update to take place the effective and the requested priority
+ * values are synchronized.
+ *
+ * Unless cgroups are used, the weight value is calculated from the
+ * ioprio to export the same interface as CFQ. When dealing with
+ * ``well-behaved'' queues (i.e., queues that do not spend too much
+ * time to consume their budget and have true sequential behavior, and
+ * when there are no external factors breaking anticipation) the
+ * relative weights at each level of the cgroups hierarchy should be
+ * guaranteed. All the fields are protected by the queue lock of the
+ * containing bfqd.
+ */
+struct bfq_entity {
+ /* service_tree member */
+ struct rb_node rb_node;
+ /* pointer to the weight counter associated with this entity */
+ struct bfq_weight_counter *weight_counter;
+
+ /*
+ * Flag, true if the entity is on a tree (either the active or
+ * the idle one of its service_tree) or is in service.
+ */
+ bool on_st;
+
+ /* B-WF2Q+ start and finish timestamps [sectors/weight] */
+ u64 start, finish;
+
+ /* tree the entity is enqueued into; %NULL if not on a tree */
+ struct rb_root *tree;
+
+ /*
+ * minimum start time of the (active) subtree rooted at this
+ * entity; used for O(log N) lookups into active trees
+ */
+ u64 min_start;
+
+ /* amount of service received during the last service slot */
+ int service;
+
+ /* budget, used also to calculate F_i: F_i = S_i + @budget / @weight */
+ int budget;
+
+ /* weight of the queue */
+ int weight;
+ /* next weight if a change is in progress */
+ int new_weight;
+
+ /* original weight, used to implement weight boosting */
+ int orig_weight;
+
+ /* parent entity, for hierarchical scheduling */
+ struct bfq_entity *parent;
+
+ /*
+ * For non-leaf nodes in the hierarchy, the associated
+ * scheduler queue, %NULL on leaf nodes.
+ */
+ struct bfq_sched_data *my_sched_data;
+ /* the scheduler queue this entity belongs to */
+ struct bfq_sched_data *sched_data;
+
+ /* flag, set to request a weight, ioprio or ioprio_class change */
+ int prio_changed;
+};
+
+struct bfq_group;
+
+/**
+ * struct bfq_ttime - per process thinktime stats.
+ */
+struct bfq_ttime {
+ /* completion time of the last request */
+ u64 last_end_request;
+
+ /* total process thinktime */
+ u64 ttime_total;
+ /* number of thinktime samples */
+ unsigned long ttime_samples;
+ /* average process thinktime */
+ u64 ttime_mean;
+};
+
+/**
+ * struct bfq_queue - leaf schedulable entity.
+ *
+ * A bfq_queue is a leaf request queue; it can be associated with an
+ * io_context or more, if it is async or shared between cooperating
+ * processes. @cgroup holds a reference to the cgroup, to be sure that it
+ * does not disappear while a bfqq still references it (mostly to avoid
+ * races between request issuing and task migration followed by cgroup
+ * destruction).
+ * All the fields are protected by the queue lock of the containing bfqd.
+ */
+struct bfq_queue {
+ /* reference counter */
+ int ref;
+ /* parent bfq_data */
+ struct bfq_data *bfqd;
+
+ /* current ioprio and ioprio class */
+ unsigned short ioprio, ioprio_class;
+ /* next ioprio and ioprio class if a change is in progress */
+ unsigned short new_ioprio, new_ioprio_class;
+
+ /*
+ * Shared bfq_queue if queue is cooperating with one or more
+ * other queues.
+ */
+ struct bfq_queue *new_bfqq;
+ /* request-position tree member (see bfq_group's @rq_pos_tree) */
+ struct rb_node pos_node;
+ /* request-position tree root (see bfq_group's @rq_pos_tree) */
+ struct rb_root *pos_root;
+
+ /* sorted list of pending requests */
+ struct rb_root sort_list;
+ /* if fifo isn't expired, next request to serve */
+ struct request *next_rq;
+ /* number of sync and async requests queued */
+ int queued[2];
+ /* number of requests currently allocated */
+ int allocated;
+ /* number of pending metadata requests */
+ int meta_pending;
+ /* fifo list of requests in sort_list */
+ struct list_head fifo;
+
+ /* entity representing this queue in the scheduler */
+ struct bfq_entity entity;
+
+ /* maximum budget allowed from the feedback mechanism */
+ int max_budget;
+ /* budget expiration (in jiffies) */
+ unsigned long budget_timeout;
+
+ /* number of requests on the dispatch list or inside driver */
+ int dispatched;
+
+ /* status flags */
+ unsigned long flags;
+
+ /* node for active/idle bfqq list inside parent bfqd */
+ struct list_head bfqq_list;
+
+ /* associated @bfq_ttime struct */
+ struct bfq_ttime ttime;
+
+ /* bit vector: a 1 for each seeky requests in history */
+ u32 seek_history;
+
+ /* node for the device's burst list */
+ struct hlist_node burst_list_node;
+
+ /* position of the last request enqueued */
+ sector_t last_request_pos;
+
+ /* Number of consecutive pairs of request completion and
+ * arrival, such that the queue becomes idle after the
+ * completion, but the next request arrives within an idle
+ * time slice; used only if the queue's IO_bound flag has been
+ * cleared.
+ */
+ unsigned int requests_within_timer;
+
+ /* pid of the process owning the queue, used for logging purposes */
+ pid_t pid;
+
+ /*
+ * Pointer to the bfq_io_cq owning the bfq_queue, set to %NULL
+ * if the queue is shared.
+ */
+ struct bfq_io_cq *bic;
+
+ /* current maximum weight-raising time for this queue */
+ unsigned long wr_cur_max_time;
+ /*
+ * Minimum time instant such that, only if a new request is
+ * enqueued after this time instant in an idle @bfq_queue with
+ * no outstanding requests, then the task associated with the
+ * queue it is deemed as soft real-time (see the comments on
+ * the function bfq_bfqq_softrt_next_start())
+ */
+ unsigned long soft_rt_next_start;
+ /*
+ * Start time of the current weight-raising period if
+ * the @bfq-queue is being weight-raised, otherwise
+ * finish time of the last weight-raising period.
+ */
+ unsigned long last_wr_start_finish;
+ /* factor by which the weight of this queue is multiplied */
+ unsigned int wr_coeff;
+ /*
+ * Time of the last transition of the @bfq_queue from idle to
+ * backlogged.
+ */
+ unsigned long last_idle_bklogged;
+ /*
+ * Cumulative service received from the @bfq_queue since the
+ * last transition from idle to backlogged.
+ */
+ unsigned long service_from_backlogged;
+
+ /*
+ * Value of wr start time when switching to soft rt
+ */
+ unsigned long wr_start_at_switch_to_srt;
+
+ unsigned long split_time; /* time of last split */
+};
+
+/**
+ * struct bfq_io_cq - per (request_queue, io_context) structure.
+ */
+struct bfq_io_cq {
+ /* associated io_cq structure */
+ struct io_cq icq; /* must be the first member */
+ /* array of two process queues, the sync and the async */
+ struct bfq_queue *bfqq[2];
+ /* per (request_queue, blkcg) ioprio */
+ int ioprio;
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ uint64_t blkcg_serial_nr; /* the current blkcg serial */
+#endif
+ /*
+ * Snapshot of the idle window before merging; taken to
+ * remember this value while the queue is merged, so as to be
+ * able to restore it in case of split.
+ */
+ bool saved_idle_window;
+ /*
+ * Same purpose as the previous two fields for the I/O bound
+ * classification of a queue.
+ */
+ bool saved_IO_bound;
+
+ /*
+ * Same purpose as the previous fields for the value of the
+ * field keeping the queue's belonging to a large burst
+ */
+ bool saved_in_large_burst;
+ /*
+ * True if the queue belonged to a burst list before its merge
+ * with another cooperating queue.
+ */
+ bool was_in_burst_list;
+
+ /*
+ * Similar to previous fields: save wr information.
+ */
+ unsigned long saved_wr_coeff;
+ unsigned long saved_last_wr_start_finish;
+ unsigned long saved_wr_start_at_switch_to_srt;
+ unsigned int saved_wr_cur_max_time;
+ struct bfq_ttime saved_ttime;
+};
+
+enum bfq_device_speed {
+ BFQ_BFQD_FAST,
+ BFQ_BFQD_SLOW,
+};
+
+/**
+ * struct bfq_data - per-device data structure.
+ *
+ * All the fields are protected by @lock.
+ */
+struct bfq_data {
+ /* device request queue */
+ struct request_queue *queue;
+ /* dispatch queue */
+ struct list_head dispatch;
+
+ /* root bfq_group for the device */
+ struct bfq_group *root_group;
+
+ /*
+ * rbtree of weight counters of @bfq_queues, sorted by
+ * weight. Used to keep track of whether all @bfq_queues have
+ * the same weight. The tree contains one counter for each
+ * distinct weight associated to some active and not
+ * weight-raised @bfq_queue (see the comments to the functions
+ * bfq_weights_tree_[add|remove] for further details).
+ */
+ struct rb_root queue_weights_tree;
+ /*
+ * rbtree of non-queue @bfq_entity weight counters, sorted by
+ * weight. Used to keep track of whether all @bfq_groups have
+ * the same weight. The tree contains one counter for each
+ * distinct weight associated to some active @bfq_group (see
+ * the comments to the functions bfq_weights_tree_[add|remove]
+ * for further details).
+ */
+ struct rb_root group_weights_tree;
+
+ /*
+ * Number of bfq_queues containing requests (including the
+ * queue in service, even if it is idling).
+ */
+ int busy_queues;
+ /* number of weight-raised busy @bfq_queues */
+ int wr_busy_queues;
+ /* number of queued requests */
+ int queued;
+ /* number of requests dispatched and waiting for completion */
+ int rq_in_driver;
+
+ /*
+ * Maximum number of requests in driver in the last
+ * @hw_tag_samples completed requests.
+ */
+ int max_rq_in_driver;
+ /* number of samples used to calculate hw_tag */
+ int hw_tag_samples;
+ /* flag set to one if the driver is showing a queueing behavior */
+ int hw_tag;
+
+ /* number of budgets assigned */
+ int budgets_assigned;
+
+ /*
+ * Timer set when idling (waiting) for the next request from
+ * the queue in service.
+ */
+ struct hrtimer idle_slice_timer;
+
+ /* bfq_queue in service */
+ struct bfq_queue *in_service_queue;
+
+ /* on-disk position of the last served request */
+ sector_t last_position;
+
+ /* time of last request completion (ns) */
+ u64 last_completion;
+
+ /* time of first rq dispatch in current observation interval (ns) */
+ u64 first_dispatch;
+ /* time of last rq dispatch in current observation interval (ns) */
+ u64 last_dispatch;
+
+ /* beginning of the last budget */
+ ktime_t last_budget_start;
+ /* beginning of the last idle slice */
+ ktime_t last_idling_start;
+
+ /* number of samples in current observation interval */
+ int peak_rate_samples;
+ /* num of samples of seq dispatches in current observation interval */
+ u32 sequential_samples;
+ /* total num of sectors transferred in current observation interval */
+ u64 tot_sectors_dispatched;
+ /* max rq size seen during current observation interval (sectors) */
+ u32 last_rq_max_size;
+ /* time elapsed from first dispatch in current observ. interval (us) */
+ u64 delta_from_first;
+ /*
+ * Current estimate of the device peak rate, measured in
+ * [BFQ_RATE_SHIFT * sectors/usec]. The left-shift by
+ * BFQ_RATE_SHIFT is performed to increase precision in
+ * fixed-point calculations.
+ */
+ u32 peak_rate;
+
+ /* maximum budget allotted to a bfq_queue before rescheduling */
+ int bfq_max_budget;
+
+ /* list of all the bfq_queues active on the device */
+ struct list_head active_list;
+ /* list of all the bfq_queues idle on the device */
+ struct list_head idle_list;
+
+ /*
+ * Timeout for async/sync requests; when it fires, requests
+ * are served in fifo order.
+ */
+ u64 bfq_fifo_expire[2];
+ /* weight of backward seeks wrt forward ones */
+ unsigned int bfq_back_penalty;
+ /* maximum allowed backward seek */
+ unsigned int bfq_back_max;
+ /* maximum idling time */
+ u32 bfq_slice_idle;
+
+ /* user-configured max budget value (0 for auto-tuning) */
+ int bfq_user_max_budget;
+ /*
+ * Timeout for bfq_queues to consume their budget; used to
+ * prevent seeky queues from imposing long latencies to
+ * sequential or quasi-sequential ones (this also implies that
+ * seeky queues cannot receive guarantees in the service
+ * domain; after a timeout they are charged for the time they
+ * have been in service, to preserve fairness among them, but
+ * without service-domain guarantees).
+ */
+ unsigned int bfq_timeout;
+
+ /*
+ * Number of consecutive requests that must be issued within
+ * the idle time slice to set again idling to a queue which
+ * was marked as non-I/O-bound (see the definition of the
+ * IO_bound flag for further details).
+ */
+ unsigned int bfq_requests_within_timer;
+
+ /*
+ * Force device idling whenever needed to provide accurate
+ * service guarantees, without caring about throughput
+ * issues. CAVEAT: this may even increase latencies, in case
+ * of useless idling for processes that did stop doing I/O.
+ */
+ bool strict_guarantees;
+
+ /*
+ * Last time at which a queue entered the current burst of
+ * queues being activated shortly after each other; for more
+ * details about this and the following parameters related to
+ * a burst of activations, see the comments on the function
+ * bfq_handle_burst.
+ */
+ unsigned long last_ins_in_burst;
+ /*
+ * Reference time interval used to decide whether a queue has
+ * been activated shortly after @last_ins_in_burst.
+ */
+ unsigned long bfq_burst_interval;
+ /* number of queues in the current burst of queue activations */
+ int burst_size;
+
+ /* common parent entity for the queues in the burst */
+ struct bfq_entity *burst_parent_entity;
+ /* Maximum burst size above which the current queue-activation
+ * burst is deemed as 'large'.
+ */
+ unsigned long bfq_large_burst_thresh;
+ /* true if a large queue-activation burst is in progress */
+ bool large_burst;
+ /*
+ * Head of the burst list (as for the above fields, more
+ * details in the comments on the function bfq_handle_burst).
+ */
+ struct hlist_head burst_list;
+
+ /* if set to true, low-latency heuristics are enabled */
+ bool low_latency;
+ /*
+ * Maximum factor by which the weight of a weight-raised queue
+ * is multiplied.
+ */
+ unsigned int bfq_wr_coeff;
+ /* maximum duration of a weight-raising period (jiffies) */
+ unsigned int bfq_wr_max_time;
+
+ /* Maximum weight-raising duration for soft real-time processes */
+ unsigned int bfq_wr_rt_max_time;
+ /*
+ * Minimum idle period after which weight-raising may be
+ * reactivated for a queue (in jiffies).
+ */
+ unsigned int bfq_wr_min_idle_time;
+ /*
+ * Minimum period between request arrivals after which
+ * weight-raising may be reactivated for an already busy async
+ * queue (in jiffies).
+ */
+ unsigned long bfq_wr_min_inter_arr_async;
+
+ /* Max service-rate for a soft real-time queue, in sectors/sec */
+ unsigned int bfq_wr_max_softrt_rate;
+ /*
+ * Cached value of the product R*T, used for computing the
+ * maximum duration of weight raising automatically.
+ */
+ u64 RT_prod;
+ /* device-speed class for the low-latency heuristic */
+ enum bfq_device_speed device_speed;
+
+ /* fallback dummy bfqq for extreme OOM conditions */
+ struct bfq_queue oom_bfqq;
+
+ spinlock_t lock;
+
+ /*
+ * bic associated with the task issuing current bio for
+ * merging. This and the next field are used as a support to
+ * be able to perform the bic lookup, needed by bio-merge
+ * functions, before the scheduler lock is taken, and thus
+ * avoid taking the request-queue lock while the scheduler
+ * lock is being held.
+ */
+ struct bfq_io_cq *bio_bic;
+ /* bfqq associated with the task issuing current bio for merging */
+ struct bfq_queue *bio_bfqq;
+};
+
+enum bfqq_state_flags {
+ BFQQF_just_created = 0, /* queue just allocated */
+ BFQQF_busy, /* has requests or is in service */
+ BFQQF_wait_request, /* waiting for a request */
+ BFQQF_non_blocking_wait_rq, /*
+ * waiting for a request
+ * without idling the device
+ */
+ BFQQF_fifo_expire, /* FIFO checked in this slice */
+ BFQQF_idle_window, /* slice idling enabled */
+ BFQQF_sync, /* synchronous queue */
+ BFQQF_IO_bound, /*
+ * bfqq has timed-out at least once
+ * having consumed at most 2/10 of
+ * its budget
+ */
+ BFQQF_in_large_burst, /*
+ * bfqq activated in a large burst,
+ * see comments to bfq_handle_burst.
+ */
+ BFQQF_softrt_update, /*
+ * may need softrt-next-start
+ * update
+ */
+ BFQQF_coop, /* bfqq is shared */
+ BFQQF_split_coop /* shared bfqq will be split */
+};
+
+#define BFQ_BFQQ_FNS(name) \
+void bfq_mark_bfqq_##name(struct bfq_queue *bfqq); \
+void bfq_clear_bfqq_##name(struct bfq_queue *bfqq); \
+int bfq_bfqq_##name(const struct bfq_queue *bfqq);
+
+BFQ_BFQQ_FNS(just_created);
+BFQ_BFQQ_FNS(busy);
+BFQ_BFQQ_FNS(wait_request);
+BFQ_BFQQ_FNS(non_blocking_wait_rq);
+BFQ_BFQQ_FNS(fifo_expire);
+BFQ_BFQQ_FNS(idle_window);
+BFQ_BFQQ_FNS(sync);
+BFQ_BFQQ_FNS(IO_bound);
+BFQ_BFQQ_FNS(in_large_burst);
+BFQ_BFQQ_FNS(coop);
+BFQ_BFQQ_FNS(split_coop);
+BFQ_BFQQ_FNS(softrt_update);
+#undef BFQ_BFQQ_FNS
+
+/* Expiration reasons. */
+enum bfqq_expiration {
+ BFQQE_TOO_IDLE = 0, /*
+ * queue has been idling for
+ * too long
+ */
+ BFQQE_BUDGET_TIMEOUT, /* budget took too long to be used */
+ BFQQE_BUDGET_EXHAUSTED, /* budget consumed */
+ BFQQE_NO_MORE_REQUESTS, /* the queue has no more requests */
+ BFQQE_PREEMPTED /* preemption in progress */
+};
+
+struct bfqg_stats {
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ /* number of ios merged */
+ struct blkg_rwstat merged;
+ /* total time spent on device in ns, may not be accurate w/ queueing */
+ struct blkg_rwstat service_time;
+ /* total time spent waiting in scheduler queue in ns */
+ struct blkg_rwstat wait_time;
+ /* number of IOs queued up */
+ struct blkg_rwstat queued;
+ /* total disk time and nr sectors dispatched by this group */
+ struct blkg_stat time;
+ /* sum of number of ios queued across all samples */
+ struct blkg_stat avg_queue_size_sum;
+ /* count of samples taken for average */
+ struct blkg_stat avg_queue_size_samples;
+ /* how many times this group has been removed from service tree */
+ struct blkg_stat dequeue;
+ /* total time spent waiting for it to be assigned a timeslice. */
+ struct blkg_stat group_wait_time;
+ /* time spent idling for this blkcg_gq */
+ struct blkg_stat idle_time;
+ /* total time with empty current active q with other requests queued */
+ struct blkg_stat empty_time;
+ /* fields after this shouldn't be cleared on stat reset */
+ uint64_t start_group_wait_time;
+ uint64_t start_idle_time;
+ uint64_t start_empty_time;
+ uint16_t flags;
+#endif /* CONFIG_BFQ_GROUP_IOSCHED */
+};
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+
+/*
+ * struct bfq_group_data - per-blkcg storage for the blkio subsystem.
+ *
+ * @ps: @blkcg_policy_storage that this structure inherits
+ * @weight: weight of the bfq_group
+ */
+struct bfq_group_data {
+ /* must be the first member */
+ struct blkcg_policy_data pd;
+
+ unsigned int weight;
+};
+
+/**
+ * struct bfq_group - per (device, cgroup) data structure.
+ * @entity: schedulable entity to insert into the parent group sched_data.
+ * @sched_data: own sched_data, to contain child entities (they may be
+ * both bfq_queues and bfq_groups).
+ * @bfqd: the bfq_data for the device this group acts upon.
+ * @async_bfqq: array of async queues for all the tasks belonging to
+ * the group, one queue per ioprio value per ioprio_class,
+ * except for the idle class that has only one queue.
+ * @async_idle_bfqq: async queue for the idle class (ioprio is ignored).
+ * @my_entity: pointer to @entity, %NULL for the toplevel group; used
+ * to avoid too many special cases during group creation/
+ * migration.
+ * @stats: stats for this bfqg.
+ * @active_entities: number of active entities belonging to the group;
+ * unused for the root group. Used to know whether there
+ * are groups with more than one active @bfq_entity
+ * (see the comments to the function
+ * bfq_bfqq_may_idle()).
+ * @rq_pos_tree: rbtree sorted by next_request position, used when
+ * determining if two or more queues have interleaving
+ * requests (see bfq_find_close_cooperator()).
+ *
+ * Each (device, cgroup) pair has its own bfq_group, i.e., for each cgroup
+ * there is a set of bfq_groups, each one collecting the lower-level
+ * entities belonging to the group that are acting on the same device.
+ *
+ * Locking works as follows:
+ * o @bfqd is protected by the queue lock, RCU is used to access it
+ * from the readers.
+ * o All the other fields are protected by the @bfqd queue lock.
+ */
+struct bfq_group {
+ /* must be the first member */
+ struct blkg_policy_data pd;
+
+ struct bfq_entity entity;
+ struct bfq_sched_data sched_data;
+
+ void *bfqd;
+
+ struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR];
+ struct bfq_queue *async_idle_bfqq;
+
+ struct bfq_entity *my_entity;
+
+ int active_entities;
+
+ struct rb_root rq_pos_tree;
+
+ struct bfqg_stats stats;
+};
+
+#else
+struct bfq_group {
+ struct bfq_sched_data sched_data;
+
+ struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR];
+ struct bfq_queue *async_idle_bfqq;
+
+ struct rb_root rq_pos_tree;
+};
+#endif
+
+struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity);
+
+/* --------------- main algorithm interface ----------------- */
+
+#define BFQ_SERVICE_TREE_INIT ((struct bfq_service_tree) \
+ { RB_ROOT, RB_ROOT, NULL, NULL, 0, 0 })
+
+extern const int bfq_timeout;
+
+struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync);
+void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync);
+struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic);
+void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
+void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq);
+void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_entity *entity,
+ struct rb_root *root);
+void bfq_weights_tree_remove(struct bfq_data *bfqd, struct bfq_entity *entity,
+ struct rb_root *root);
+void bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ bool compensate, enum bfqq_expiration reason);
+void bfq_put_queue(struct bfq_queue *bfqq);
+void bfq_end_wr_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
+void bfq_schedule_dispatch(struct bfq_data *bfqd);
+void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
+
+/* ------------ end of main algorithm interface -------------- */
+
+/* ---------------- cgroups-support interface ---------------- */
+
+void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
+ unsigned int op);
+void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op);
+void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op);
+void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time,
+ uint64_t io_start_time, unsigned int op);
+void bfqg_stats_update_dequeue(struct bfq_group *bfqg);
+void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg);
+void bfqg_stats_update_idle_time(struct bfq_group *bfqg);
+void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg);
+void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg);
+void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ struct bfq_group *bfqg);
+
+void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg);
+void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio);
+void bfq_end_wr_async(struct bfq_data *bfqd);
+struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
+ struct blkcg *blkcg);
+struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
+struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
+struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node);
+void bfqg_put(struct bfq_group *bfqg);
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+extern struct cftype bfq_blkcg_legacy_files[];
+extern struct cftype bfq_blkg_files[];
+extern struct blkcg_policy blkcg_policy_bfq;
+#endif
+
+/* ------------- end of cgroups-support interface ------------- */
+
+/* - interface of the internal hierarchical B-WF2Q+ scheduler - */
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+/* both next loops stop at one of the child entities of the root group */
+#define for_each_entity(entity) \
+ for (; entity ; entity = entity->parent)
+
+/*
+ * For each iteration, compute parent in advance, so as to be safe if
+ * entity is deallocated during the iteration. Such a deallocation may
+ * happen as a consequence of a bfq_put_queue that frees the bfq_queue
+ * containing entity.
+ */
+#define for_each_entity_safe(entity, parent) \
+ for (; entity && ({ parent = entity->parent; 1; }); entity = parent)
+
+#else /* CONFIG_BFQ_GROUP_IOSCHED */
+/*
+ * Next two macros are fake loops when cgroups support is not
+ * enabled. I fact, in such a case, there is only one level to go up
+ * (to reach the root group).
+ */
+#define for_each_entity(entity) \
+ for (; entity ; entity = NULL)
+
+#define for_each_entity_safe(entity, parent) \
+ for (parent = NULL; entity ; entity = parent)
+#endif /* CONFIG_BFQ_GROUP_IOSCHED */
+
+struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq);
+struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity);
+struct bfq_service_tree *bfq_entity_service_tree(struct bfq_entity *entity);
+struct bfq_entity *bfq_entity_of(struct rb_node *node);
+unsigned short bfq_ioprio_to_weight(int ioprio);
+void bfq_put_idle_entity(struct bfq_service_tree *st,
+ struct bfq_entity *entity);
+struct bfq_service_tree *
+__bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
+ struct bfq_entity *entity);
+void bfq_bfqq_served(struct bfq_queue *bfqq, int served);
+void bfq_bfqq_charge_time(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ unsigned long time_ms);
+bool __bfq_deactivate_entity(struct bfq_entity *entity,
+ bool ins_into_idle_tree);
+bool next_queue_may_preempt(struct bfq_data *bfqd);
+struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd);
+void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd);
+void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ bool ins_into_idle_tree, bool expiration);
+void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
+void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
+void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ bool expiration);
+void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq);
+
+/* --------------- end of interface of B-WF2Q+ ---------------- */
+
+/* Logging facilities. */
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
+
+#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) do { \
+ char __pbuf[128]; \
+ \
+ blkg_path(bfqg_to_blkg(bfqq_group(bfqq)), __pbuf, sizeof(__pbuf)); \
+ blk_add_trace_msg((bfqd)->queue, "bfq%d%c %s " fmt, (bfqq)->pid, \
+ bfq_bfqq_sync((bfqq)) ? 'S' : 'A', \
+ __pbuf, ##args); \
+} while (0)
+
+#define bfq_log_bfqg(bfqd, bfqg, fmt, args...) do { \
+ char __pbuf[128]; \
+ \
+ blkg_path(bfqg_to_blkg(bfqg), __pbuf, sizeof(__pbuf)); \
+ blk_add_trace_msg((bfqd)->queue, "%s " fmt, __pbuf, ##args); \
+} while (0)
+
+#else /* CONFIG_BFQ_GROUP_IOSCHED */
+
+#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) \
+ blk_add_trace_msg((bfqd)->queue, "bfq%d%c " fmt, (bfqq)->pid, \
+ bfq_bfqq_sync((bfqq)) ? 'S' : 'A', \
+ ##args)
+#define bfq_log_bfqg(bfqd, bfqg, fmt, args...) do {} while (0)
+
+#endif /* CONFIG_BFQ_GROUP_IOSCHED */
+
+#define bfq_log(bfqd, fmt, args...) \
+ blk_add_trace_msg((bfqd)->queue, "bfq " fmt, ##args)
+
+#endif /* _BFQ_H */
--- /dev/null
+/*
+ * Hierarchical Budget Worst-case Fair Weighted Fair Queueing
+ * (B-WF2Q+): hierarchical scheduling algorithm by which the BFQ I/O
+ * scheduler schedules generic entities. The latter can represent
+ * either single bfq queues (associated with processes) or groups of
+ * bfq queues (associated with cgroups).
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#include "bfq-iosched.h"
+
+/**
+ * bfq_gt - compare two timestamps.
+ * @a: first ts.
+ * @b: second ts.
+ *
+ * Return @a > @b, dealing with wrapping correctly.
+ */
+static int bfq_gt(u64 a, u64 b)
+{
+ return (s64)(a - b) > 0;
+}
+
+static struct bfq_entity *bfq_root_active_entity(struct rb_root *tree)
+{
+ struct rb_node *node = tree->rb_node;
+
+ return rb_entry(node, struct bfq_entity, rb_node);
+}
+
+static unsigned int bfq_class_idx(struct bfq_entity *entity)
+{
+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+ return bfqq ? bfqq->ioprio_class - 1 :
+ BFQ_DEFAULT_GRP_CLASS - 1;
+}
+
+static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd);
+
+static bool bfq_update_parent_budget(struct bfq_entity *next_in_service);
+
+/**
+ * bfq_update_next_in_service - update sd->next_in_service
+ * @sd: sched_data for which to perform the update.
+ * @new_entity: if not NULL, pointer to the entity whose activation,
+ * requeueing or repositionig triggered the invocation of
+ * this function.
+ *
+ * This function is called to update sd->next_in_service, which, in
+ * its turn, may change as a consequence of the insertion or
+ * extraction of an entity into/from one of the active trees of
+ * sd. These insertions/extractions occur as a consequence of
+ * activations/deactivations of entities, with some activations being
+ * 'true' activations, and other activations being requeueings (i.e.,
+ * implementing the second, requeueing phase of the mechanism used to
+ * reposition an entity in its active tree; see comments on
+ * __bfq_activate_entity and __bfq_requeue_entity for details). In
+ * both the last two activation sub-cases, new_entity points to the
+ * just activated or requeued entity.
+ *
+ * Returns true if sd->next_in_service changes in such a way that
+ * entity->parent may become the next_in_service for its parent
+ * entity.
+ */
+static bool bfq_update_next_in_service(struct bfq_sched_data *sd,
+ struct bfq_entity *new_entity)
+{
+ struct bfq_entity *next_in_service = sd->next_in_service;
+ bool parent_sched_may_change = false;
+
+ /*
+ * If this update is triggered by the activation, requeueing
+ * or repositiong of an entity that does not coincide with
+ * sd->next_in_service, then a full lookup in the active tree
+ * can be avoided. In fact, it is enough to check whether the
+ * just-modified entity has a higher priority than
+ * sd->next_in_service, or, even if it has the same priority
+ * as sd->next_in_service, is eligible and has a lower virtual
+ * finish time than sd->next_in_service. If this compound
+ * condition holds, then the new entity becomes the new
+ * next_in_service. Otherwise no change is needed.
+ */
+ if (new_entity && new_entity != sd->next_in_service) {
+ /*
+ * Flag used to decide whether to replace
+ * sd->next_in_service with new_entity. Tentatively
+ * set to true, and left as true if
+ * sd->next_in_service is NULL.
+ */
+ bool replace_next = true;
+
+ /*
+ * If there is already a next_in_service candidate
+ * entity, then compare class priorities or timestamps
+ * to decide whether to replace sd->service_tree with
+ * new_entity.
+ */
+ if (next_in_service) {
+ unsigned int new_entity_class_idx =
+ bfq_class_idx(new_entity);
+ struct bfq_service_tree *st =
+ sd->service_tree + new_entity_class_idx;
+
+ /*
+ * For efficiency, evaluate the most likely
+ * sub-condition first.
+ */
+ replace_next =
+ (new_entity_class_idx ==
+ bfq_class_idx(next_in_service)
+ &&
+ !bfq_gt(new_entity->start, st->vtime)
+ &&
+ bfq_gt(next_in_service->finish,
+ new_entity->finish))
+ ||
+ new_entity_class_idx <
+ bfq_class_idx(next_in_service);
+ }
+
+ if (replace_next)
+ next_in_service = new_entity;
+ } else /* invoked because of a deactivation: lookup needed */
+ next_in_service = bfq_lookup_next_entity(sd);
+
+ if (next_in_service) {
+ parent_sched_may_change = !sd->next_in_service ||
+ bfq_update_parent_budget(next_in_service);
+ }
+
+ sd->next_in_service = next_in_service;
+
+ if (!next_in_service)
+ return parent_sched_may_change;
+
+ return parent_sched_may_change;
+}
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+
+struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq)
+{
+ struct bfq_entity *group_entity = bfqq->entity.parent;
+
+ if (!group_entity)
+ group_entity = &bfqq->bfqd->root_group->entity;
+
+ return container_of(group_entity, struct bfq_group, entity);
+}
+
+/*
+ * Returns true if this budget changes may let next_in_service->parent
+ * become the next_in_service entity for its parent entity.
+ */
+static bool bfq_update_parent_budget(struct bfq_entity *next_in_service)
+{
+ struct bfq_entity *bfqg_entity;
+ struct bfq_group *bfqg;
+ struct bfq_sched_data *group_sd;
+ bool ret = false;
+
+ group_sd = next_in_service->sched_data;
+
+ bfqg = container_of(group_sd, struct bfq_group, sched_data);
+ /*
+ * bfq_group's my_entity field is not NULL only if the group
+ * is not the root group. We must not touch the root entity
+ * as it must never become an in-service entity.
+ */
+ bfqg_entity = bfqg->my_entity;
+ if (bfqg_entity) {
+ if (bfqg_entity->budget > next_in_service->budget)
+ ret = true;
+ bfqg_entity->budget = next_in_service->budget;
+ }
+
+ return ret;
+}
+
+/*
+ * This function tells whether entity stops being a candidate for next
+ * service, according to the following logic.
+ *
+ * This function is invoked for an entity that is about to be set in
+ * service. If such an entity is a queue, then the entity is no longer
+ * a candidate for next service (i.e, a candidate entity to serve
+ * after the in-service entity is expired). The function then returns
+ * true.
+ *
+ * In contrast, the entity could stil be a candidate for next service
+ * if it is not a queue, and has more than one child. In fact, even if
+ * one of its children is about to be set in service, other children
+ * may still be the next to serve. As a consequence, a non-queue
+ * entity is not a candidate for next-service only if it has only one
+ * child. And only if this condition holds, then the function returns
+ * true for a non-queue entity.
+ */
+static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
+{
+ struct bfq_group *bfqg;
+
+ if (bfq_entity_to_bfqq(entity))
+ return true;
+
+ bfqg = container_of(entity, struct bfq_group, entity);
+
+ if (bfqg->active_entities == 1)
+ return true;
+
+ return false;
+}
+
+#else /* CONFIG_BFQ_GROUP_IOSCHED */
+
+struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq)
+{
+ return bfqq->bfqd->root_group;
+}
+
+static bool bfq_update_parent_budget(struct bfq_entity *next_in_service)
+{
+ return false;
+}
+
+static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
+{
+ return true;
+}
+
+#endif /* CONFIG_BFQ_GROUP_IOSCHED */
+
+/*
+ * Shift for timestamp calculations. This actually limits the maximum
+ * service allowed in one timestamp delta (small shift values increase it),
+ * the maximum total weight that can be used for the queues in the system
+ * (big shift values increase it), and the period of virtual time
+ * wraparounds.
+ */
+#define WFQ_SERVICE_SHIFT 22
+
+struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity)
+{
+ struct bfq_queue *bfqq = NULL;
+
+ if (!entity->my_sched_data)
+ bfqq = container_of(entity, struct bfq_queue, entity);
+
+ return bfqq;
+}
+
+
+/**
+ * bfq_delta - map service into the virtual time domain.
+ * @service: amount of service.
+ * @weight: scale factor (weight of an entity or weight sum).
+ */
+static u64 bfq_delta(unsigned long service, unsigned long weight)
+{
+ u64 d = (u64)service << WFQ_SERVICE_SHIFT;
+
+ do_div(d, weight);
+ return d;
+}
+
+/**
+ * bfq_calc_finish - assign the finish time to an entity.
+ * @entity: the entity to act upon.
+ * @service: the service to be charged to the entity.
+ */
+static void bfq_calc_finish(struct bfq_entity *entity, unsigned long service)
+{
+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+ entity->finish = entity->start +
+ bfq_delta(service, entity->weight);
+
+ if (bfqq) {
+ bfq_log_bfqq(bfqq->bfqd, bfqq,
+ "calc_finish: serv %lu, w %d",
+ service, entity->weight);
+ bfq_log_bfqq(bfqq->bfqd, bfqq,
+ "calc_finish: start %llu, finish %llu, delta %llu",
+ entity->start, entity->finish,
+ bfq_delta(service, entity->weight));
+ }
+}
+
+/**
+ * bfq_entity_of - get an entity from a node.
+ * @node: the node field of the entity.
+ *
+ * Convert a node pointer to the relative entity. This is used only
+ * to simplify the logic of some functions and not as the generic
+ * conversion mechanism because, e.g., in the tree walking functions,
+ * the check for a %NULL value would be redundant.
+ */
+struct bfq_entity *bfq_entity_of(struct rb_node *node)
+{
+ struct bfq_entity *entity = NULL;
+
+ if (node)
+ entity = rb_entry(node, struct bfq_entity, rb_node);
+
+ return entity;
+}
+
+/**
+ * bfq_extract - remove an entity from a tree.
+ * @root: the tree root.
+ * @entity: the entity to remove.
+ */
+static void bfq_extract(struct rb_root *root, struct bfq_entity *entity)
+{
+ entity->tree = NULL;
+ rb_erase(&entity->rb_node, root);
+}
+
+/**
+ * bfq_idle_extract - extract an entity from the idle tree.
+ * @st: the service tree of the owning @entity.
+ * @entity: the entity being removed.
+ */
+static void bfq_idle_extract(struct bfq_service_tree *st,
+ struct bfq_entity *entity)
+{
+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+ struct rb_node *next;
+
+ if (entity == st->first_idle) {
+ next = rb_next(&entity->rb_node);
+ st->first_idle = bfq_entity_of(next);
+ }
+
+ if (entity == st->last_idle) {
+ next = rb_prev(&entity->rb_node);
+ st->last_idle = bfq_entity_of(next);
+ }
+
+ bfq_extract(&st->idle, entity);
+
+ if (bfqq)
+ list_del(&bfqq->bfqq_list);
+}
+
+/**
+ * bfq_insert - generic tree insertion.
+ * @root: tree root.
+ * @entity: entity to insert.
+ *
+ * This is used for the idle and the active tree, since they are both
+ * ordered by finish time.
+ */
+static void bfq_insert(struct rb_root *root, struct bfq_entity *entity)
+{
+ struct bfq_entity *entry;
+ struct rb_node **node = &root->rb_node;
+ struct rb_node *parent = NULL;
+
+ while (*node) {
+ parent = *node;
+ entry = rb_entry(parent, struct bfq_entity, rb_node);
+
+ if (bfq_gt(entry->finish, entity->finish))
+ node = &parent->rb_left;
+ else
+ node = &parent->rb_right;
+ }
+
+ rb_link_node(&entity->rb_node, parent, node);
+ rb_insert_color(&entity->rb_node, root);
+
+ entity->tree = root;
+}
+
+/**
+ * bfq_update_min - update the min_start field of a entity.
+ * @entity: the entity to update.
+ * @node: one of its children.
+ *
+ * This function is called when @entity may store an invalid value for
+ * min_start due to updates to the active tree. The function assumes
+ * that the subtree rooted at @node (which may be its left or its right
+ * child) has a valid min_start value.
+ */
+static void bfq_update_min(struct bfq_entity *entity, struct rb_node *node)
+{
+ struct bfq_entity *child;
+
+ if (node) {
+ child = rb_entry(node, struct bfq_entity, rb_node);
+ if (bfq_gt(entity->min_start, child->min_start))
+ entity->min_start = child->min_start;
+ }
+}
+
+/**
+ * bfq_update_active_node - recalculate min_start.
+ * @node: the node to update.
+ *
+ * @node may have changed position or one of its children may have moved,
+ * this function updates its min_start value. The left and right subtrees
+ * are assumed to hold a correct min_start value.
+ */
+static void bfq_update_active_node(struct rb_node *node)
+{
+ struct bfq_entity *entity = rb_entry(node, struct bfq_entity, rb_node);
+
+ entity->min_start = entity->start;
+ bfq_update_min(entity, node->rb_right);
+ bfq_update_min(entity, node->rb_left);
+}
+
+/**
+ * bfq_update_active_tree - update min_start for the whole active tree.
+ * @node: the starting node.
+ *
+ * @node must be the deepest modified node after an update. This function
+ * updates its min_start using the values held by its children, assuming
+ * that they did not change, and then updates all the nodes that may have
+ * changed in the path to the root. The only nodes that may have changed
+ * are the ones in the path or their siblings.
+ */
+static void bfq_update_active_tree(struct rb_node *node)
+{
+ struct rb_node *parent;
+
+up:
+ bfq_update_active_node(node);
+
+ parent = rb_parent(node);
+ if (!parent)
+ return;
+
+ if (node == parent->rb_left && parent->rb_right)
+ bfq_update_active_node(parent->rb_right);
+ else if (parent->rb_left)
+ bfq_update_active_node(parent->rb_left);
+
+ node = parent;
+ goto up;
+}
+
+/**
+ * bfq_active_insert - insert an entity in the active tree of its
+ * group/device.
+ * @st: the service tree of the entity.
+ * @entity: the entity being inserted.
+ *
+ * The active tree is ordered by finish time, but an extra key is kept
+ * per each node, containing the minimum value for the start times of
+ * its children (and the node itself), so it's possible to search for
+ * the eligible node with the lowest finish time in logarithmic time.
+ */
+static void bfq_active_insert(struct bfq_service_tree *st,
+ struct bfq_entity *entity)
+{
+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+ struct rb_node *node = &entity->rb_node;
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ struct bfq_sched_data *sd = NULL;
+ struct bfq_group *bfqg = NULL;
+ struct bfq_data *bfqd = NULL;
+#endif
+
+ bfq_insert(&st->active, entity);
+
+ if (node->rb_left)
+ node = node->rb_left;
+ else if (node->rb_right)
+ node = node->rb_right;
+
+ bfq_update_active_tree(node);
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ sd = entity->sched_data;
+ bfqg = container_of(sd, struct bfq_group, sched_data);
+ bfqd = (struct bfq_data *)bfqg->bfqd;
+#endif
+ if (bfqq)
+ list_add(&bfqq->bfqq_list, &bfqq->bfqd->active_list);
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ else /* bfq_group */
+ bfq_weights_tree_add(bfqd, entity, &bfqd->group_weights_tree);
+
+ if (bfqg != bfqd->root_group)
+ bfqg->active_entities++;
+#endif
+}
+
+/**
+ * bfq_ioprio_to_weight - calc a weight from an ioprio.
+ * @ioprio: the ioprio value to convert.
+ */
+unsigned short bfq_ioprio_to_weight(int ioprio)
+{
+ return (IOPRIO_BE_NR - ioprio) * BFQ_WEIGHT_CONVERSION_COEFF;
+}
+
+/**
+ * bfq_weight_to_ioprio - calc an ioprio from a weight.
+ * @weight: the weight value to convert.
+ *
+ * To preserve as much as possible the old only-ioprio user interface,
+ * 0 is used as an escape ioprio value for weights (numerically) equal or
+ * larger than IOPRIO_BE_NR * BFQ_WEIGHT_CONVERSION_COEFF.
+ */
+static unsigned short bfq_weight_to_ioprio(int weight)
+{
+ return max_t(int, 0,
+ IOPRIO_BE_NR * BFQ_WEIGHT_CONVERSION_COEFF - weight);
+}
+
+static void bfq_get_entity(struct bfq_entity *entity)
+{
+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+ if (bfqq) {
+ bfqq->ref++;
+ bfq_log_bfqq(bfqq->bfqd, bfqq, "get_entity: %p %d",
+ bfqq, bfqq->ref);
+ }
+}
+
+/**
+ * bfq_find_deepest - find the deepest node that an extraction can modify.
+ * @node: the node being removed.
+ *
+ * Do the first step of an extraction in an rb tree, looking for the
+ * node that will replace @node, and returning the deepest node that
+ * the following modifications to the tree can touch. If @node is the
+ * last node in the tree return %NULL.
+ */
+static struct rb_node *bfq_find_deepest(struct rb_node *node)
+{
+ struct rb_node *deepest;
+
+ if (!node->rb_right && !node->rb_left)
+ deepest = rb_parent(node);
+ else if (!node->rb_right)
+ deepest = node->rb_left;
+ else if (!node->rb_left)
+ deepest = node->rb_right;
+ else {
+ deepest = rb_next(node);
+ if (deepest->rb_right)
+ deepest = deepest->rb_right;
+ else if (rb_parent(deepest) != node)
+ deepest = rb_parent(deepest);
+ }
+
+ return deepest;
+}
+
+/**
+ * bfq_active_extract - remove an entity from the active tree.
+ * @st: the service_tree containing the tree.
+ * @entity: the entity being removed.
+ */
+static void bfq_active_extract(struct bfq_service_tree *st,
+ struct bfq_entity *entity)
+{
+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+ struct rb_node *node;
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ struct bfq_sched_data *sd = NULL;
+ struct bfq_group *bfqg = NULL;
+ struct bfq_data *bfqd = NULL;
+#endif
+
+ node = bfq_find_deepest(&entity->rb_node);
+ bfq_extract(&st->active, entity);
+
+ if (node)
+ bfq_update_active_tree(node);
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ sd = entity->sched_data;
+ bfqg = container_of(sd, struct bfq_group, sched_data);
+ bfqd = (struct bfq_data *)bfqg->bfqd;
+#endif
+ if (bfqq)
+ list_del(&bfqq->bfqq_list);
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ else /* bfq_group */
+ bfq_weights_tree_remove(bfqd, entity,
+ &bfqd->group_weights_tree);
+
+ if (bfqg != bfqd->root_group)
+ bfqg->active_entities--;
+#endif
+}
+
+/**
+ * bfq_idle_insert - insert an entity into the idle tree.
+ * @st: the service tree containing the tree.
+ * @entity: the entity to insert.
+ */
+static void bfq_idle_insert(struct bfq_service_tree *st,
+ struct bfq_entity *entity)
+{
+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+ struct bfq_entity *first_idle = st->first_idle;
+ struct bfq_entity *last_idle = st->last_idle;
+
+ if (!first_idle || bfq_gt(first_idle->finish, entity->finish))
+ st->first_idle = entity;
+ if (!last_idle || bfq_gt(entity->finish, last_idle->finish))
+ st->last_idle = entity;
+
+ bfq_insert(&st->idle, entity);
+
+ if (bfqq)
+ list_add(&bfqq->bfqq_list, &bfqq->bfqd->idle_list);
+}
+
+/**
+ * bfq_forget_entity - do not consider entity any longer for scheduling
+ * @st: the service tree.
+ * @entity: the entity being removed.
+ * @is_in_service: true if entity is currently the in-service entity.
+ *
+ * Forget everything about @entity. In addition, if entity represents
+ * a queue, and the latter is not in service, then release the service
+ * reference to the queue (the one taken through bfq_get_entity). In
+ * fact, in this case, there is really no more service reference to
+ * the queue, as the latter is also outside any service tree. If,
+ * instead, the queue is in service, then __bfq_bfqd_reset_in_service
+ * will take care of putting the reference when the queue finally
+ * stops being served.
+ */
+static void bfq_forget_entity(struct bfq_service_tree *st,
+ struct bfq_entity *entity,
+ bool is_in_service)
+{
+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+ entity->on_st = false;
+ st->wsum -= entity->weight;
+ if (bfqq && !is_in_service)
+ bfq_put_queue(bfqq);
+}
+
+/**
+ * bfq_put_idle_entity - release the idle tree ref of an entity.
+ * @st: service tree for the entity.
+ * @entity: the entity being released.
+ */
+void bfq_put_idle_entity(struct bfq_service_tree *st, struct bfq_entity *entity)
+{
+ bfq_idle_extract(st, entity);
+ bfq_forget_entity(st, entity,
+ entity == entity->sched_data->in_service_entity);
+}
+
+/**
+ * bfq_forget_idle - update the idle tree if necessary.
+ * @st: the service tree to act upon.
+ *
+ * To preserve the global O(log N) complexity we only remove one entry here;
+ * as the idle tree will not grow indefinitely this can be done safely.
+ */
+static void bfq_forget_idle(struct bfq_service_tree *st)
+{
+ struct bfq_entity *first_idle = st->first_idle;
+ struct bfq_entity *last_idle = st->last_idle;
+
+ if (RB_EMPTY_ROOT(&st->active) && last_idle &&
+ !bfq_gt(last_idle->finish, st->vtime)) {
+ /*
+ * Forget the whole idle tree, increasing the vtime past
+ * the last finish time of idle entities.
+ */
+ st->vtime = last_idle->finish;
+ }
+
+ if (first_idle && !bfq_gt(first_idle->finish, st->vtime))
+ bfq_put_idle_entity(st, first_idle);
+}
+
+struct bfq_service_tree *bfq_entity_service_tree(struct bfq_entity *entity)
+{
+ struct bfq_sched_data *sched_data = entity->sched_data;
+ unsigned int idx = bfq_class_idx(entity);
+
+ return sched_data->service_tree + idx;
+}
+
+
+struct bfq_service_tree *
+__bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
+ struct bfq_entity *entity)
+{
+ struct bfq_service_tree *new_st = old_st;
+
+ if (entity->prio_changed) {
+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+ unsigned int prev_weight, new_weight;
+ struct bfq_data *bfqd = NULL;
+ struct rb_root *root;
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ struct bfq_sched_data *sd;
+ struct bfq_group *bfqg;
+#endif
+
+ if (bfqq)
+ bfqd = bfqq->bfqd;
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+ else {
+ sd = entity->my_sched_data;
+ bfqg = container_of(sd, struct bfq_group, sched_data);
+ bfqd = (struct bfq_data *)bfqg->bfqd;
+ }
+#endif
+
+ old_st->wsum -= entity->weight;
+
+ if (entity->new_weight != entity->orig_weight) {
+ if (entity->new_weight < BFQ_MIN_WEIGHT ||
+ entity->new_weight > BFQ_MAX_WEIGHT) {
+ pr_crit("update_weight_prio: new_weight %d\n",
+ entity->new_weight);
+ if (entity->new_weight < BFQ_MIN_WEIGHT)
+ entity->new_weight = BFQ_MIN_WEIGHT;
+ else
+ entity->new_weight = BFQ_MAX_WEIGHT;
+ }
+ entity->orig_weight = entity->new_weight;
+ if (bfqq)
+ bfqq->ioprio =
+ bfq_weight_to_ioprio(entity->orig_weight);
+ }
+
+ if (bfqq)
+ bfqq->ioprio_class = bfqq->new_ioprio_class;
+ entity->prio_changed = 0;
+
+ /*
+ * NOTE: here we may be changing the weight too early,
+ * this will cause unfairness. The correct approach
+ * would have required additional complexity to defer
+ * weight changes to the proper time instants (i.e.,
+ * when entity->finish <= old_st->vtime).
+ */
+ new_st = bfq_entity_service_tree(entity);
+
+ prev_weight = entity->weight;
+ new_weight = entity->orig_weight *
+ (bfqq ? bfqq->wr_coeff : 1);
+ /*
+ * If the weight of the entity changes, remove the entity
+ * from its old weight counter (if there is a counter
+ * associated with the entity), and add it to the counter
+ * associated with its new weight.
+ */
+ if (prev_weight != new_weight) {
+ root = bfqq ? &bfqd->queue_weights_tree :
+ &bfqd->group_weights_tree;
+ bfq_weights_tree_remove(bfqd, entity, root);
+ }
+ entity->weight = new_weight;
+ /*
+ * Add the entity to its weights tree only if it is
+ * not associated with a weight-raised queue.
+ */
+ if (prev_weight != new_weight &&
+ (bfqq ? bfqq->wr_coeff == 1 : 1))
+ /* If we get here, root has been initialized. */
+ bfq_weights_tree_add(bfqd, entity, root);
+
+ new_st->wsum += entity->weight;
+
+ if (new_st != old_st)
+ entity->start = new_st->vtime;
+ }
+
+ return new_st;
+}
+
+/**
+ * bfq_bfqq_served - update the scheduler status after selection for
+ * service.
+ * @bfqq: the queue being served.
+ * @served: bytes to transfer.
+ *
+ * NOTE: this can be optimized, as the timestamps of upper level entities
+ * are synchronized every time a new bfqq is selected for service. By now,
+ * we keep it to better check consistency.
+ */
+void bfq_bfqq_served(struct bfq_queue *bfqq, int served)
+{
+ struct bfq_entity *entity = &bfqq->entity;
+ struct bfq_service_tree *st;
+
+ for_each_entity(entity) {
+ st = bfq_entity_service_tree(entity);
+
+ entity->service += served;
+
+ st->vtime += bfq_delta(served, st->wsum);
+ bfq_forget_idle(st);
+ }
+ bfqg_stats_set_start_empty_time(bfqq_group(bfqq));
+ bfq_log_bfqq(bfqq->bfqd, bfqq, "bfqq_served %d secs", served);
+}
+
+/**
+ * bfq_bfqq_charge_time - charge an amount of service equivalent to the length
+ * of the time interval during which bfqq has been in
+ * service.
+ * @bfqd: the device
+ * @bfqq: the queue that needs a service update.
+ * @time_ms: the amount of time during which the queue has received service
+ *
+ * If a queue does not consume its budget fast enough, then providing
+ * the queue with service fairness may impair throughput, more or less
+ * severely. For this reason, queues that consume their budget slowly
+ * are provided with time fairness instead of service fairness. This
+ * goal is achieved through the BFQ scheduling engine, even if such an
+ * engine works in the service, and not in the time domain. The trick
+ * is charging these queues with an inflated amount of service, equal
+ * to the amount of service that they would have received during their
+ * service slot if they had been fast, i.e., if their requests had
+ * been dispatched at a rate equal to the estimated peak rate.
+ *
+ * It is worth noting that time fairness can cause important
+ * distortions in terms of bandwidth distribution, on devices with
+ * internal queueing. The reason is that I/O requests dispatched
+ * during the service slot of a queue may be served after that service
+ * slot is finished, and may have a total processing time loosely
+ * correlated with the duration of the service slot. This is
+ * especially true for short service slots.
+ */
+void bfq_bfqq_charge_time(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ unsigned long time_ms)
+{
+ struct bfq_entity *entity = &bfqq->entity;
+ int tot_serv_to_charge = entity->service;
+ unsigned int timeout_ms = jiffies_to_msecs(bfq_timeout);
+
+ if (time_ms > 0 && time_ms < timeout_ms)
+ tot_serv_to_charge =
+ (bfqd->bfq_max_budget * time_ms) / timeout_ms;
+
+ if (tot_serv_to_charge < entity->service)
+ tot_serv_to_charge = entity->service;
+
+ /* Increase budget to avoid inconsistencies */
+ if (tot_serv_to_charge > entity->budget)
+ entity->budget = tot_serv_to_charge;
+
+ bfq_bfqq_served(bfqq,
+ max_t(int, 0, tot_serv_to_charge - entity->service));
+}
+
+static void bfq_update_fin_time_enqueue(struct bfq_entity *entity,
+ struct bfq_service_tree *st,
+ bool backshifted)
+{
+ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+ st = __bfq_entity_update_weight_prio(st, entity);
+ bfq_calc_finish(entity, entity->budget);
+
+ /*
+ * If some queues enjoy backshifting for a while, then their
+ * (virtual) finish timestamps may happen to become lower and
+ * lower than the system virtual time. In particular, if
+ * these queues often happen to be idle for short time
+ * periods, and during such time periods other queues with
+ * higher timestamps happen to be busy, then the backshifted
+ * timestamps of the former queues can become much lower than
+ * the system virtual time. In fact, to serve the queues with
+ * higher timestamps while the ones with lower timestamps are
+ * idle, the system virtual time may be pushed-up to much
+ * higher values than the finish timestamps of the idle
+ * queues. As a consequence, the finish timestamps of all new
+ * or newly activated queues may end up being much larger than
+ * those of lucky queues with backshifted timestamps. The
+ * latter queues may then monopolize the device for a lot of
+ * time. This would simply break service guarantees.
+ *
+ * To reduce this problem, push up a little bit the
+ * backshifted timestamps of the queue associated with this
+ * entity (only a queue can happen to have the backshifted
+ * flag set): just enough to let the finish timestamp of the
+ * queue be equal to the current value of the system virtual
+ * time. This may introduce a little unfairness among queues
+ * with backshifted timestamps, but it does not break
+ * worst-case fairness guarantees.
+ *
+ * As a special case, if bfqq is weight-raised, push up
+ * timestamps much less, to keep very low the probability that
+ * this push up causes the backshifted finish timestamps of
+ * weight-raised queues to become higher than the backshifted
+ * finish timestamps of non weight-raised queues.
+ */
+ if (backshifted && bfq_gt(st->vtime, entity->finish)) {
+ unsigned long delta = st->vtime - entity->finish;
+
+ if (bfqq)
+ delta /= bfqq->wr_coeff;
+
+ entity->start += delta;
+ entity->finish += delta;
+ }
+
+ bfq_active_insert(st, entity);
+}
+
+/**
+ * __bfq_activate_entity - handle activation of entity.
+ * @entity: the entity being activated.
+ * @non_blocking_wait_rq: true if entity was waiting for a request
+ *
+ * Called for a 'true' activation, i.e., if entity is not active and
+ * one of its children receives a new request.
+ *
+ * Basically, this function updates the timestamps of entity and
+ * inserts entity into its active tree, ater possible extracting it
+ * from its idle tree.
+ */
+static void __bfq_activate_entity(struct bfq_entity *entity,
+ bool non_blocking_wait_rq)
+{
+ struct bfq_service_tree *st = bfq_entity_service_tree(entity);
+ bool backshifted = false;
+ unsigned long long min_vstart;
+
+ /* See comments on bfq_fqq_update_budg_for_activation */
+ if (non_blocking_wait_rq && bfq_gt(st->vtime, entity->finish)) {
+ backshifted = true;
+ min_vstart = entity->finish;
+ } else
+ min_vstart = st->vtime;
+
+ if (entity->tree == &st->idle) {
+ /*
+ * Must be on the idle tree, bfq_idle_extract() will
+ * check for that.
+ */
+ bfq_idle_extract(st, entity);
+ entity->start = bfq_gt(min_vstart, entity->finish) ?
+ min_vstart : entity->finish;
+ } else {
+ /*
+ * The finish time of the entity may be invalid, and
+ * it is in the past for sure, otherwise the queue
+ * would have been on the idle tree.
+ */
+ entity->start = min_vstart;
+ st->wsum += entity->weight;
+ /*
+ * entity is about to be inserted into a service tree,
+ * and then set in service: get a reference to make
+ * sure entity does not disappear until it is no
+ * longer in service or scheduled for service.
+ */
+ bfq_get_entity(entity);
+
+ entity->on_st = true;
+ }
+
+ bfq_update_fin_time_enqueue(entity, st, backshifted);
+}
+
+/**
+ * __bfq_requeue_entity - handle requeueing or repositioning of an entity.
+ * @entity: the entity being requeued or repositioned.
+ *
+ * Requeueing is needed if this entity stops being served, which
+ * happens if a leaf descendant entity has expired. On the other hand,
+ * repositioning is needed if the next_inservice_entity for the child
+ * entity has changed. See the comments inside the function for
+ * details.
+ *
+ * Basically, this function: 1) removes entity from its active tree if
+ * present there, 2) updates the timestamps of entity and 3) inserts
+ * entity back into its active tree (in the new, right position for
+ * the new values of the timestamps).
+ */
+static void __bfq_requeue_entity(struct bfq_entity *entity)
+{
+ struct bfq_sched_data *sd = entity->sched_data;
+ struct bfq_service_tree *st = bfq_entity_service_tree(entity);
+
+ if (entity == sd->in_service_entity) {
+ /*
+ * We are requeueing the current in-service entity,
+ * which may have to be done for one of the following
+ * reasons:
+ * - entity represents the in-service queue, and the
+ * in-service queue is being requeued after an
+ * expiration;
+ * - entity represents a group, and its budget has
+ * changed because one of its child entities has
+ * just been either activated or requeued for some
+ * reason; the timestamps of the entity need then to
+ * be updated, and the entity needs to be enqueued
+ * or repositioned accordingly.
+ *
+ * In particular, before requeueing, the start time of
+ * the entity must be moved forward to account for the
+ * service that the entity has received while in
+ * service. This is done by the next instructions. The
+ * finish time will then be updated according to this
+ * new value of the start time, and to the budget of
+ * the entity.
+ */
+ bfq_calc_finish(entity, entity->service);
+ entity->start = entity->finish;
+ /*
+ * In addition, if the entity had more than one child
+ * when set in service, then was not extracted from
+ * the active tree. This implies that the position of
+ * the entity in the active tree may need to be
+ * changed now, because we have just updated the start
+ * time of the entity, and we will update its finish
+ * time in a moment (the requeueing is then, more
+ * precisely, a repositioning in this case). To
+ * implement this repositioning, we: 1) dequeue the
+ * entity here, 2) update the finish time and
+ * requeue the entity according to the new
+ * timestamps below.
+ */
+ if (entity->tree)
+ bfq_active_extract(st, entity);
+ } else { /* The entity is already active, and not in service */
+ /*
+ * In this case, this function gets called only if the
+ * next_in_service entity below this entity has
+ * changed, and this change has caused the budget of
+ * this entity to change, which, finally implies that
+ * the finish time of this entity must be
+ * updated. Such an update may cause the scheduling,
+ * i.e., the position in the active tree, of this
+ * entity to change. We handle this change by: 1)
+ * dequeueing the entity here, 2) updating the finish
+ * time and requeueing the entity according to the new
+ * timestamps below. This is the same approach as the
+ * non-extracted-entity sub-case above.
+ */
+ bfq_active_extract(st, entity);
+ }
+
+ bfq_update_fin_time_enqueue(entity, st, false);
+}
+
+static void __bfq_activate_requeue_entity(struct bfq_entity *entity,
+ struct bfq_sched_data *sd,
+ bool non_blocking_wait_rq)
+{
+ struct bfq_service_tree *st = bfq_entity_service_tree(entity);
+
+ if (sd->in_service_entity == entity || entity->tree == &st->active)
+ /*
+ * in service or already queued on the active tree,
+ * requeue or reposition
+ */
+ __bfq_requeue_entity(entity);
+ else
+ /*
+ * Not in service and not queued on its active tree:
+ * the activity is idle and this is a true activation.
+ */
+ __bfq_activate_entity(entity, non_blocking_wait_rq);
+}
+
+
+/**
+ * bfq_activate_entity - activate or requeue an entity representing a bfq_queue,
+ * and activate, requeue or reposition all ancestors
+ * for which such an update becomes necessary.
+ * @entity: the entity to activate.
+ * @non_blocking_wait_rq: true if this entity was waiting for a request
+ * @requeue: true if this is a requeue, which implies that bfqq is
+ * being expired; thus ALL its ancestors stop being served and must
+ * therefore be requeued
+ */
+static void bfq_activate_requeue_entity(struct bfq_entity *entity,
+ bool non_blocking_wait_rq,
+ bool requeue)
+{
+ struct bfq_sched_data *sd;
+
+ for_each_entity(entity) {
+ sd = entity->sched_data;
+ __bfq_activate_requeue_entity(entity, sd, non_blocking_wait_rq);
+
+ if (!bfq_update_next_in_service(sd, entity) && !requeue)
+ break;
+ }
+}
+
+/**
+ * __bfq_deactivate_entity - deactivate an entity from its service tree.
+ * @entity: the entity to deactivate.
+ * @ins_into_idle_tree: if false, the entity will not be put into the
+ * idle tree.
+ *
+ * Deactivates an entity, independently from its previous state. Must
+ * be invoked only if entity is on a service tree. Extracts the entity
+ * from that tree, and if necessary and allowed, puts it on the idle
+ * tree.
+ */
+bool __bfq_deactivate_entity(struct bfq_entity *entity, bool ins_into_idle_tree)
+{
+ struct bfq_sched_data *sd = entity->sched_data;
+ struct bfq_service_tree *st = bfq_entity_service_tree(entity);
+ int is_in_service = entity == sd->in_service_entity;
+
+ if (!entity->on_st) /* entity never activated, or already inactive */
+ return false;
+
+ if (is_in_service)
+ bfq_calc_finish(entity, entity->service);
+
+ if (entity->tree == &st->active)
+ bfq_active_extract(st, entity);
+ else if (!is_in_service && entity->tree == &st->idle)
+ bfq_idle_extract(st, entity);
+
+ if (!ins_into_idle_tree || !bfq_gt(entity->finish, st->vtime))
+ bfq_forget_entity(st, entity, is_in_service);
+ else
+ bfq_idle_insert(st, entity);
+
+ return true;
+}
+
+/**
+ * bfq_deactivate_entity - deactivate an entity representing a bfq_queue.
+ * @entity: the entity to deactivate.
+ * @ins_into_idle_tree: true if the entity can be put on the idle tree
+ */
+static void bfq_deactivate_entity(struct bfq_entity *entity,
+ bool ins_into_idle_tree,
+ bool expiration)
+{
+ struct bfq_sched_data *sd;
+ struct bfq_entity *parent = NULL;
+
+ for_each_entity_safe(entity, parent) {
+ sd = entity->sched_data;
+
+ if (!__bfq_deactivate_entity(entity, ins_into_idle_tree)) {
+ /*
+ * entity is not in any tree any more, so
+ * this deactivation is a no-op, and there is
+ * nothing to change for upper-level entities
+ * (in case of expiration, this can never
+ * happen).
+ */
+ return;
+ }
+
+ if (sd->next_in_service == entity)
+ /*
+ * entity was the next_in_service entity,
+ * then, since entity has just been
+ * deactivated, a new one must be found.
+ */
+ bfq_update_next_in_service(sd, NULL);
+
+ if (sd->next_in_service)
+ /*
+ * The parent entity is still backlogged,
+ * because next_in_service is not NULL. So, no
+ * further upwards deactivation must be
+ * performed. Yet, next_in_service has
+ * changed. Then the schedule does need to be
+ * updated upwards.
+ */
+ break;
+
+ /*
+ * If we get here, then the parent is no more
+ * backlogged and we need to propagate the
+ * deactivation upwards. Thus let the loop go on.
+ */
+
+ /*
+ * Also let parent be queued into the idle tree on
+ * deactivation, to preserve service guarantees, and
+ * assuming that who invoked this function does not
+ * need parent entities too to be removed completely.
+ */
+ ins_into_idle_tree = true;
+ }
+
+ /*
+ * If the deactivation loop is fully executed, then there are
+ * no more entities to touch and next loop is not executed at
+ * all. Otherwise, requeue remaining entities if they are
+ * about to stop receiving service, or reposition them if this
+ * is not the case.
+ */
+ entity = parent;
+ for_each_entity(entity) {
+ /*
+ * Invoke __bfq_requeue_entity on entity, even if
+ * already active, to requeue/reposition it in the
+ * active tree (because sd->next_in_service has
+ * changed)
+ */
+ __bfq_requeue_entity(entity);
+
+ sd = entity->sched_data;
+ if (!bfq_update_next_in_service(sd, entity) &&
+ !expiration)
+ /*
+ * next_in_service unchanged or not causing
+ * any change in entity->parent->sd, and no
+ * requeueing needed for expiration: stop
+ * here.
+ */
+ break;
+ }
+}
+
+/**
+ * bfq_calc_vtime_jump - compute the value to which the vtime should jump,
+ * if needed, to have at least one entity eligible.
+ * @st: the service tree to act upon.
+ *
+ * Assumes that st is not empty.
+ */
+static u64 bfq_calc_vtime_jump(struct bfq_service_tree *st)
+{
+ struct bfq_entity *root_entity = bfq_root_active_entity(&st->active);
+
+ if (bfq_gt(root_entity->min_start, st->vtime))
+ return root_entity->min_start;
+
+ return st->vtime;
+}
+
+static void bfq_update_vtime(struct bfq_service_tree *st, u64 new_value)
+{
+ if (new_value > st->vtime) {
+ st->vtime = new_value;
+ bfq_forget_idle(st);
+ }
+}
+
+/**
+ * bfq_first_active_entity - find the eligible entity with
+ * the smallest finish time
+ * @st: the service tree to select from.
+ * @vtime: the system virtual to use as a reference for eligibility
+ *
+ * This function searches the first schedulable entity, starting from the
+ * root of the tree and going on the left every time on this side there is
+ * a subtree with at least one eligible (start >= vtime) entity. The path on
+ * the right is followed only if a) the left subtree contains no eligible
+ * entities and b) no eligible entity has been found yet.
+ */
+static struct bfq_entity *bfq_first_active_entity(struct bfq_service_tree *st,
+ u64 vtime)
+{
+ struct bfq_entity *entry, *first = NULL;
+ struct rb_node *node = st->active.rb_node;
+
+ while (node) {
+ entry = rb_entry(node, struct bfq_entity, rb_node);
+left:
+ if (!bfq_gt(entry->start, vtime))
+ first = entry;
+
+ if (node->rb_left) {
+ entry = rb_entry(node->rb_left,
+ struct bfq_entity, rb_node);
+ if (!bfq_gt(entry->min_start, vtime)) {
+ node = node->rb_left;
+ goto left;
+ }
+ }
+ if (first)
+ break;
+ node = node->rb_right;
+ }
+
+ return first;
+}
+
+/**
+ * __bfq_lookup_next_entity - return the first eligible entity in @st.
+ * @st: the service tree.
+ *
+ * If there is no in-service entity for the sched_data st belongs to,
+ * then return the entity that will be set in service if:
+ * 1) the parent entity this st belongs to is set in service;
+ * 2) no entity belonging to such parent entity undergoes a state change
+ * that would influence the timestamps of the entity (e.g., becomes idle,
+ * becomes backlogged, changes its budget, ...).
+ *
+ * In this first case, update the virtual time in @st too (see the
+ * comments on this update inside the function).
+ *
+ * In constrast, if there is an in-service entity, then return the
+ * entity that would be set in service if not only the above
+ * conditions, but also the next one held true: the currently
+ * in-service entity, on expiration,
+ * 1) gets a finish time equal to the current one, or
+ * 2) is not eligible any more, or
+ * 3) is idle.
+ */
+static struct bfq_entity *
+__bfq_lookup_next_entity(struct bfq_service_tree *st, bool in_service)
+{
+ struct bfq_entity *entity;
+ u64 new_vtime;
+
+ if (RB_EMPTY_ROOT(&st->active))
+ return NULL;
+
+ /*
+ * Get the value of the system virtual time for which at
+ * least one entity is eligible.
+ */
+ new_vtime = bfq_calc_vtime_jump(st);
+
+ /*
+ * If there is no in-service entity for the sched_data this
+ * active tree belongs to, then push the system virtual time
+ * up to the value that guarantees that at least one entity is
+ * eligible. If, instead, there is an in-service entity, then
+ * do not make any such update, because there is already an
+ * eligible entity, namely the in-service one (even if the
+ * entity is not on st, because it was extracted when set in
+ * service).
+ */
+ if (!in_service)
+ bfq_update_vtime(st, new_vtime);
+
+ entity = bfq_first_active_entity(st, new_vtime);
+
+ return entity;
+}
+
+/**
+ * bfq_lookup_next_entity - return the first eligible entity in @sd.
+ * @sd: the sched_data.
+ *
+ * This function is invoked when there has been a change in the trees
+ * for sd, and we need know what is the new next entity after this
+ * change.
+ */
+static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd)
+{
+ struct bfq_service_tree *st = sd->service_tree;
+ struct bfq_service_tree *idle_class_st = st + (BFQ_IOPRIO_CLASSES - 1);
+ struct bfq_entity *entity = NULL;
+ int class_idx = 0;
+
+ /*
+ * Choose from idle class, if needed to guarantee a minimum
+ * bandwidth to this class (and if there is some active entity
+ * in idle class). This should also mitigate
+ * priority-inversion problems in case a low priority task is
+ * holding file system resources.
+ */
+ if (time_is_before_jiffies(sd->bfq_class_idle_last_service +
+ BFQ_CL_IDLE_TIMEOUT)) {
+ if (!RB_EMPTY_ROOT(&idle_class_st->active))
+ class_idx = BFQ_IOPRIO_CLASSES - 1;
+ /* About to be served if backlogged, or not yet backlogged */
+ sd->bfq_class_idle_last_service = jiffies;
+ }
+
+ /*
+ * Find the next entity to serve for the highest-priority
+ * class, unless the idle class needs to be served.
+ */
+ for (; class_idx < BFQ_IOPRIO_CLASSES; class_idx++) {
+ entity = __bfq_lookup_next_entity(st + class_idx,
+ sd->in_service_entity);
+
+ if (entity)
+ break;
+ }
+
+ if (!entity)
+ return NULL;
+
+ return entity;
+}
+
+bool next_queue_may_preempt(struct bfq_data *bfqd)
+{
+ struct bfq_sched_data *sd = &bfqd->root_group->sched_data;
+
+ return sd->next_in_service != sd->in_service_entity;
+}
+
+/*
+ * Get next queue for service.
+ */
+struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd)
+{
+ struct bfq_entity *entity = NULL;
+ struct bfq_sched_data *sd;
+ struct bfq_queue *bfqq;
+
+ if (bfqd->busy_queues == 0)
+ return NULL;
+
+ /*
+ * Traverse the path from the root to the leaf entity to
+ * serve. Set in service all the entities visited along the
+ * way.
+ */
+ sd = &bfqd->root_group->sched_data;
+ for (; sd ; sd = entity->my_sched_data) {
+ /*
+ * WARNING. We are about to set the in-service entity
+ * to sd->next_in_service, i.e., to the (cached) value
+ * returned by bfq_lookup_next_entity(sd) the last
+ * time it was invoked, i.e., the last time when the
+ * service order in sd changed as a consequence of the
+ * activation or deactivation of an entity. In this
+ * respect, if we execute bfq_lookup_next_entity(sd)
+ * in this very moment, it may, although with low
+ * probability, yield a different entity than that
+ * pointed to by sd->next_in_service. This rare event
+ * happens in case there was no CLASS_IDLE entity to
+ * serve for sd when bfq_lookup_next_entity(sd) was
+ * invoked for the last time, while there is now one
+ * such entity.
+ *
+ * If the above event happens, then the scheduling of
+ * such entity in CLASS_IDLE is postponed until the
+ * service of the sd->next_in_service entity
+ * finishes. In fact, when the latter is expired,
+ * bfq_lookup_next_entity(sd) gets called again,
+ * exactly to update sd->next_in_service.
+ */
+
+ /* Make next_in_service entity become in_service_entity */
+ entity = sd->next_in_service;
+ sd->in_service_entity = entity;
+
+ /*
+ * Reset the accumulator of the amount of service that
+ * the entity is about to receive.
+ */
+ entity->service = 0;
+
+ /*
+ * If entity is no longer a candidate for next
+ * service, then we extract it from its active tree,
+ * for the following reason. To further boost the
+ * throughput in some special case, BFQ needs to know
+ * which is the next candidate entity to serve, while
+ * there is already an entity in service. In this
+ * respect, to make it easy to compute/update the next
+ * candidate entity to serve after the current
+ * candidate has been set in service, there is a case
+ * where it is necessary to extract the current
+ * candidate from its service tree. Such a case is
+ * when the entity just set in service cannot be also
+ * a candidate for next service. Details about when
+ * this conditions holds are reported in the comments
+ * on the function bfq_no_longer_next_in_service()
+ * invoked below.
+ */
+ if (bfq_no_longer_next_in_service(entity))
+ bfq_active_extract(bfq_entity_service_tree(entity),
+ entity);
+
+ /*
+ * For the same reason why we may have just extracted
+ * entity from its active tree, we may need to update
+ * next_in_service for the sched_data of entity too,
+ * regardless of whether entity has been extracted.
+ * In fact, even if entity has not been extracted, a
+ * descendant entity may get extracted. Such an event
+ * would cause a change in next_in_service for the
+ * level of the descendant entity, and thus possibly
+ * back to upper levels.
+ *
+ * We cannot perform the resulting needed update
+ * before the end of this loop, because, to know which
+ * is the correct next-to-serve candidate entity for
+ * each level, we need first to find the leaf entity
+ * to set in service. In fact, only after we know
+ * which is the next-to-serve leaf entity, we can
+ * discover whether the parent entity of the leaf
+ * entity becomes the next-to-serve, and so on.
+ */
+
+ }
+
+ bfqq = bfq_entity_to_bfqq(entity);
+
+ /*
+ * We can finally update all next-to-serve entities along the
+ * path from the leaf entity just set in service to the root.
+ */
+ for_each_entity(entity) {
+ struct bfq_sched_data *sd = entity->sched_data;
+
+ if (!bfq_update_next_in_service(sd, NULL))
+ break;
+ }
+
+ return bfqq;
+}
+
+void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
+{
+ struct bfq_queue *in_serv_bfqq = bfqd->in_service_queue;
+ struct bfq_entity *in_serv_entity = &in_serv_bfqq->entity;
+ struct bfq_entity *entity = in_serv_entity;
+
+ bfq_clear_bfqq_wait_request(in_serv_bfqq);
+ hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
+ bfqd->in_service_queue = NULL;
+
+ /*
+ * When this function is called, all in-service entities have
+ * been properly deactivated or requeued, so we can safely
+ * execute the final step: reset in_service_entity along the
+ * path from entity to the root.
+ */
+ for_each_entity(entity)
+ entity->sched_data->in_service_entity = NULL;
+
+ /*
+ * in_serv_entity is no longer in service, so, if it is in no
+ * service tree either, then release the service reference to
+ * the queue it represents (taken with bfq_get_entity).
+ */
+ if (!in_serv_entity->on_st)
+ bfq_put_queue(in_serv_bfqq);
+}
+
+void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ bool ins_into_idle_tree, bool expiration)
+{
+ struct bfq_entity *entity = &bfqq->entity;
+
+ bfq_deactivate_entity(entity, ins_into_idle_tree, expiration);
+}
+
+void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+ struct bfq_entity *entity = &bfqq->entity;
+
+ bfq_activate_requeue_entity(entity, bfq_bfqq_non_blocking_wait_rq(bfqq),
+ false);
+ bfq_clear_bfqq_non_blocking_wait_rq(bfqq);
+}
+
+void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+ struct bfq_entity *entity = &bfqq->entity;
+
+ bfq_activate_requeue_entity(entity, false,
+ bfqq == bfqd->in_service_queue);
+}
+
+/*
+ * Called when the bfqq no longer has requests pending, remove it from
+ * the service tree. As a special case, it can be invoked during an
+ * expiration.
+ */
+void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ bool expiration)
+{
+ bfq_log_bfqq(bfqd, bfqq, "del from busy");
+
+ bfq_clear_bfqq_busy(bfqq);
+
+ bfqd->busy_queues--;
+
+ if (!bfqq->dispatched)
+ bfq_weights_tree_remove(bfqd, &bfqq->entity,
+ &bfqd->queue_weights_tree);
+
+ if (bfqq->wr_coeff > 1)
+ bfqd->wr_busy_queues--;
+
+ bfqg_stats_update_dequeue(bfqq_group(bfqq));
+
+ bfq_deactivate_bfqq(bfqd, bfqq, true, expiration);
+}
+
+/*
+ * Called when an inactive queue receives a new request.
+ */
+void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+ bfq_log_bfqq(bfqd, bfqq, "add to busy");
+
+ bfq_activate_bfqq(bfqd, bfqq);
+
+ bfq_mark_bfqq_busy(bfqq);
+ bfqd->busy_queues++;
+
+ if (!bfqq->dispatched)
+ if (bfqq->wr_coeff == 1)
+ bfq_weights_tree_add(bfqd, &bfqq->entity,
+ &bfqd->queue_weights_tree);
+
+ if (bfqq->wr_coeff > 1)
+ bfqd->wr_busy_queues++;
+}
#include <linux/cgroup.h>
#include <trace/events/block.h>
+#include "blk.h"
/*
* Test patch to inline a certain number of bi_io_vec's inside the bio
* RETURNS:
* Pointer to new bio on success, NULL on failure.
*/
-struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
+struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned int nr_iovecs,
+ struct bio_set *bs)
{
gfp_t saved_gfp = gfp_mask;
unsigned front_pad;
* bio_endio() will end I/O on the whole bio. bio_endio() is the preferred
* way to end I/O on a bio. No one should call bi_end_io() directly on a
* bio unless they own it and thus know that it has an end_io function.
+ *
+ * bio_endio() can be called several times on a bio that has been chained
+ * using bio_chain(). The ->bi_end_io() function will only be called the
+ * last time. At this point the BLK_TA_COMPLETE tracing event will be
+ * generated if BIO_TRACE_COMPLETION is set.
**/
void bio_endio(struct bio *bio)
{
goto again;
}
+ if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) {
+ trace_block_bio_complete(bdev_get_queue(bio->bi_bdev),
+ bio, bio->bi_error);
+ bio_clear_flag(bio, BIO_TRACE_COMPLETION);
+ }
+
+ blk_throtl_bio_endio(bio);
if (bio->bi_end_io)
bio->bi_end_io(bio);
}
bio_advance(bio, split->bi_iter.bi_size);
+ if (bio_flagged(bio, BIO_TRACE_COMPLETION))
+ bio_set_flag(bio, BIO_TRACE_COMPLETION);
+
return split;
}
EXPORT_SYMBOL(bio_split);
}
EXPORT_SYMBOL_GPL(blkg_rwstat_recursive_sum);
+/* Performs queue bypass and policy enabled checks then looks up blkg. */
+static struct blkcg_gq *blkg_lookup_check(struct blkcg *blkcg,
+ const struct blkcg_policy *pol,
+ struct request_queue *q)
+{
+ WARN_ON_ONCE(!rcu_read_lock_held());
+ lockdep_assert_held(q->queue_lock);
+
+ if (!blkcg_policy_enabled(q, pol))
+ return ERR_PTR(-EOPNOTSUPP);
+
+ /*
+ * This could be the first entry point of blkcg implementation and
+ * we shouldn't allow anything to go through for a bypassing queue.
+ */
+ if (unlikely(blk_queue_bypass(q)))
+ return ERR_PTR(blk_queue_dying(q) ? -ENODEV : -EBUSY);
+
+ return __blkg_lookup(blkcg, q, true /* update_hint */);
+}
+
/**
* blkg_conf_prep - parse and prepare for per-blkg config update
* @blkcg: target block cgroup
__acquires(rcu) __acquires(disk->queue->queue_lock)
{
struct gendisk *disk;
+ struct request_queue *q;
struct blkcg_gq *blkg;
struct module *owner;
unsigned int major, minor;
if (!disk)
return -ENODEV;
if (part) {
- owner = disk->fops->owner;
- put_disk(disk);
- module_put(owner);
- return -ENODEV;
+ ret = -ENODEV;
+ goto fail;
}
- rcu_read_lock();
- spin_lock_irq(disk->queue->queue_lock);
+ q = disk->queue;
- if (blkcg_policy_enabled(disk->queue, pol))
- blkg = blkg_lookup_create(blkcg, disk->queue);
- else
- blkg = ERR_PTR(-EOPNOTSUPP);
+ rcu_read_lock();
+ spin_lock_irq(q->queue_lock);
+ blkg = blkg_lookup_check(blkcg, pol, q);
if (IS_ERR(blkg)) {
ret = PTR_ERR(blkg);
+ goto fail_unlock;
+ }
+
+ if (blkg)
+ goto success;
+
+ /*
+ * Create blkgs walking down from blkcg_root to @blkcg, so that all
+ * non-root blkgs have access to their parents.
+ */
+ while (true) {
+ struct blkcg *pos = blkcg;
+ struct blkcg *parent;
+ struct blkcg_gq *new_blkg;
+
+ parent = blkcg_parent(blkcg);
+ while (parent && !__blkg_lookup(parent, q, false)) {
+ pos = parent;
+ parent = blkcg_parent(parent);
+ }
+
+ /* Drop locks to do new blkg allocation with GFP_KERNEL. */
+ spin_unlock_irq(q->queue_lock);
rcu_read_unlock();
- spin_unlock_irq(disk->queue->queue_lock);
- owner = disk->fops->owner;
- put_disk(disk);
- module_put(owner);
- /*
- * If queue was bypassing, we should retry. Do so after a
- * short msleep(). It isn't strictly necessary but queue
- * can be bypassing for some time and it's always nice to
- * avoid busy looping.
- */
- if (ret == -EBUSY) {
- msleep(10);
- ret = restart_syscall();
+
+ new_blkg = blkg_alloc(pos, q, GFP_KERNEL);
+ if (unlikely(!new_blkg)) {
+ ret = -ENOMEM;
+ goto fail;
}
- return ret;
- }
+ rcu_read_lock();
+ spin_lock_irq(q->queue_lock);
+
+ blkg = blkg_lookup_check(pos, pol, q);
+ if (IS_ERR(blkg)) {
+ ret = PTR_ERR(blkg);
+ goto fail_unlock;
+ }
+
+ if (blkg) {
+ blkg_free(new_blkg);
+ } else {
+ blkg = blkg_create(pos, q, new_blkg);
+ if (unlikely(IS_ERR(blkg))) {
+ ret = PTR_ERR(blkg);
+ goto fail_unlock;
+ }
+ }
+
+ if (pos == blkcg)
+ goto success;
+ }
+success:
ctx->disk = disk;
ctx->blkg = blkg;
ctx->body = body;
return 0;
+
+fail_unlock:
+ spin_unlock_irq(q->queue_lock);
+ rcu_read_unlock();
+fail:
+ owner = disk->fops->owner;
+ put_disk(disk);
+ module_put(owner);
+ /*
+ * If queue was bypassing, we should retry. Do so after a
+ * short msleep(). It isn't strictly necessary but queue
+ * can be bypassing for some time and it's always nice to
+ * avoid busy looping.
+ */
+ if (ret == -EBUSY) {
+ msleep(10);
+ ret = restart_syscall();
+ }
+ return ret;
}
EXPORT_SYMBOL_GPL(blkg_conf_prep);
struct blk_mq_hw_ctx *hctx;
int i;
- queue_for_each_hw_ctx(q, hctx, i) {
- cancel_work_sync(&hctx->run_work);
- cancel_delayed_work_sync(&hctx->delay_work);
- }
+ queue_for_each_hw_ctx(q, hctx, i)
+ cancel_delayed_work_sync(&hctx->run_work);
} else {
cancel_delayed_work_sync(&q->delay_work);
}
queue_flag_set(QUEUE_FLAG_DYING, q);
spin_unlock_irq(q->queue_lock);
+ /*
+ * When queue DYING flag is set, we need to block new req
+ * entering queue, so we call blk_freeze_queue_start() to
+ * prevent I/O from crossing blk_queue_enter().
+ */
+ blk_freeze_queue_start(q);
+
if (q->mq_ops)
blk_mq_wake_waiters(q);
else {
* prevent that q->request_fn() gets invoked after draining finished.
*/
blk_freeze_queue(q);
- spin_lock_irq(lock);
- if (!q->mq_ops)
+ if (!q->mq_ops) {
+ spin_lock_irq(lock);
__blk_drain_queue(q, true);
+ } else {
+ blk_mq_debugfs_unregister_mq(q);
+ spin_lock_irq(lock);
+ }
queue_flag_set(QUEUE_FLAG_DEAD, q);
spin_unlock_irq(lock);
if (nowait)
return -EBUSY;
+ /*
+ * read pair of barrier in blk_freeze_queue_start(),
+ * we need to order reading __PERCPU_REF_DEAD flag of
+ * .q_usage_counter and reading .mq_freeze_depth or
+ * queue dying flag, otherwise the following wait may
+ * never return if the two reads are reordered.
+ */
+ smp_rmb();
+
ret = wait_event_interruptible(q->mq_freeze_wq,
!atomic_read(&q->mq_freeze_depth) ||
blk_queue_dying(q));
if (!q->backing_dev_info)
goto fail_split;
+ q->stats = blk_alloc_queue_stats();
+ if (!q->stats)
+ goto fail_stats;
+
q->backing_dev_info->ra_pages =
(VM_MAX_READAHEAD * 1024) / PAGE_SIZE;
q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK;
fail_ref:
percpu_ref_exit(&q->q_usage_counter);
fail_bdi:
+ blk_free_queue_stats(q->stats);
+fail_stats:
bdi_put(q->backing_dev_info);
fail_split:
bioset_free(q->bio_split);
q->exit_rq_fn(q, q->fq->flush_rq);
out_free_flush_queue:
blk_free_flush_queue(q->fq);
- wbt_exit(q);
return -ENOMEM;
}
EXPORT_SYMBOL(blk_init_allocated_queue);
blk_rq_init(q, rq);
blk_rq_set_rl(rq, rl);
- blk_rq_set_prio(rq, ioc);
rq->cmd_flags = op;
rq->rq_flags = rq_flags;
return ret;
}
-void init_request_from_bio(struct request *req, struct bio *bio)
+void blk_init_request_from_bio(struct request *req, struct bio *bio)
{
+ struct io_context *ioc = rq_ioc(bio);
+
if (bio->bi_opf & REQ_RAHEAD)
req->cmd_flags |= REQ_FAILFAST_MASK;
- req->errors = 0;
req->__sector = bio->bi_iter.bi_sector;
if (ioprio_valid(bio_prio(bio)))
req->ioprio = bio_prio(bio);
+ else if (ioc)
+ req->ioprio = ioc->ioprio;
+ else
+ req->ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0);
blk_rq_bio_prep(req->q, req, bio);
}
+EXPORT_SYMBOL_GPL(blk_init_request_from_bio);
static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
{
* We don't worry about that case for efficiency. It won't happen
* often, and the elevators are able to handle it.
*/
- init_request_from_bio(req, bio);
+ blk_init_request_from_bio(req, bio);
if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags))
req->cpu = raw_smp_processor_id();
if (!blkcg_bio_issue_check(q, bio))
return false;
- trace_block_bio_queue(q, bio);
+ if (!bio_flagged(bio, BIO_TRACE_COMPLETION)) {
+ trace_block_bio_queue(q, bio);
+ /* Now that enqueuing has been traced, we need to trace
+ * completion as well.
+ */
+ bio_set_flag(bio, BIO_TRACE_COMPLETION);
+ }
return true;
not_supported:
blk_dequeue_request(req);
if (test_bit(QUEUE_FLAG_STATS, &req->q->queue_flags)) {
- blk_stat_set_issue_time(&req->issue_stat);
+ blk_stat_set_issue(&req->issue_stat, blk_rq_sectors(req));
req->rq_flags |= RQF_STATS;
wbt_issue(req->q->rq_wb, &req->issue_stat);
}
{
int total_bytes;
- trace_block_rq_complete(req->q, req, nr_bytes);
+ trace_block_rq_complete(req, error, nr_bytes);
if (!req->bio)
return false;
- /*
- * For fs requests, rq is just carrier of independent bio's
- * and each partial completion should be handled separately.
- * Reset per-request error on each partial completion.
- *
- * TODO: tj: This is too subtle. It would be better to let
- * low level drivers do what they see fit.
- */
- if (!blk_rq_is_passthrough(req))
- req->errors = 0;
-
if (error && !blk_rq_is_passthrough(req) &&
!(req->rq_flags & RQF_QUIET)) {
char *error_type;
if (bio_bytes == bio->bi_iter.bi_size)
req->bio = bio->bi_next;
+ /* Completion has already been traced */
+ bio_clear_flag(bio, BIO_TRACE_COMPLETION);
req_bio_endio(req, bio, bio_bytes, error);
total_bytes += bio_bytes;
struct request_queue *q = req->q;
if (req->rq_flags & RQF_STATS)
- blk_stat_add(&q->rq_stats[rq_data_dir(req)], req);
+ blk_stat_add(req);
if (req->rq_flags & RQF_QUEUED)
blk_queue_end_tag(q, req);
* %false - we are done with this request
* %true - still buffers pending for this request
**/
-bool __blk_end_bidi_request(struct request *rq, int error,
+static bool __blk_end_bidi_request(struct request *rq, int error,
unsigned int nr_bytes, unsigned int bidi_bytes)
{
if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes))
EXPORT_SYMBOL(blk_end_request_all);
/**
- * blk_end_request_cur - Helper function to finish the current request chunk.
- * @rq: the request to finish the current chunk for
- * @error: %0 for success, < %0 for error
- *
- * Description:
- * Complete the current consecutively mapped chunk from @rq.
- *
- * Return:
- * %false - we are done with this request
- * %true - still buffers pending for this request
- */
-bool blk_end_request_cur(struct request *rq, int error)
-{
- return blk_end_request(rq, error, blk_rq_cur_bytes(rq));
-}
-EXPORT_SYMBOL(blk_end_request_cur);
-
-/**
- * blk_end_request_err - Finish a request till the next failure boundary.
- * @rq: the request to finish till the next failure boundary for
- * @error: must be negative errno
- *
- * Description:
- * Complete @rq till the next failure boundary.
- *
- * Return:
- * %false - we are done with this request
- * %true - still buffers pending for this request
- */
-bool blk_end_request_err(struct request *rq, int error)
-{
- WARN_ON(error >= 0);
- return blk_end_request(rq, error, blk_rq_err_bytes(rq));
-}
-EXPORT_SYMBOL_GPL(blk_end_request_err);
-
-/**
* __blk_end_request - Helper function for drivers to complete the request.
* @rq: the request being processed
* @error: %0 for success, < %0 for error
}
EXPORT_SYMBOL(__blk_end_request_cur);
-/**
- * __blk_end_request_err - Finish a request till the next failure boundary.
- * @rq: the request to finish till the next failure boundary for
- * @error: must be negative errno
- *
- * Description:
- * Complete @rq till the next failure boundary. Must be called
- * with queue lock held.
- *
- * Return:
- * %false - we are done with this request
- * %true - still buffers pending for this request
- */
-bool __blk_end_request_err(struct request *rq, int error)
-{
- WARN_ON(error >= 0);
- return __blk_end_request(rq, error, blk_rq_err_bytes(rq));
-}
-EXPORT_SYMBOL_GPL(__blk_end_request_err);
-
void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
struct bio *bio)
{
}
EXPORT_SYMBOL(kblockd_schedule_work_on);
+int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork,
+ unsigned long delay)
+{
+ return mod_delayed_work_on(cpu, kblockd_workqueue, dwork, delay);
+}
+EXPORT_SYMBOL(kblockd_mod_delayed_work_on);
+
int kblockd_schedule_delayed_work(struct delayed_work *dwork,
unsigned long delay)
{
if (unlikely(blk_queue_dying(q))) {
rq->rq_flags |= RQF_QUIET;
- rq->errors = -ENXIO;
- __blk_end_request_all(rq, rq->errors);
+ __blk_end_request_all(rq, -ENXIO);
spin_unlock_irq(q->queue_lock);
return;
}
* Insert a fully prepared request at the back of the I/O scheduler queue
* for execution and wait for completion.
*/
-int blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk,
+void blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk,
struct request *rq, int at_head)
{
DECLARE_COMPLETION_ONSTACK(wait);
- int err = 0;
unsigned long hang_check;
rq->end_io_data = &wait;
while (!wait_for_completion_io_timeout(&wait, hang_check * (HZ/2)));
else
wait_for_completion_io(&wait);
-
- if (rq->errors)
- err = -EIO;
-
- return err;
}
EXPORT_SYMBOL(blk_execute_rq);
if (q->mq_ops)
blk_mq_end_request(rq, 0);
else
- __blk_end_bidi_request(rq, 0, 0, 0);
+ __blk_end_request(rq, 0, 0);
return;
}
* Description:
* Issue a flush for the block device in question. Caller can supply
* room for storing the error offset in case of a flush error, if they
- * wish to. If WAIT flag is not passed then caller may check only what
- * request was pushed in some internal queue for later handling.
+ * wish to.
*/
int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
sector_t *error_sector)
return 0;
}
-static struct blk_integrity_profile nop_profile = {
+static const struct blk_integrity_profile nop_profile = {
.name = "nop",
.generate_fn = blk_integrity_nop_fn,
.verify_fn = blk_integrity_nop_fn,
bi->flags = BLK_INTEGRITY_VERIFY | BLK_INTEGRITY_GENERATE |
template->flags;
- bi->interval_exp = ilog2(queue_logical_block_size(disk->queue));
+ bi->interval_exp = template->interval_exp ? :
+ ilog2(queue_logical_block_size(disk->queue));
bi->profile = template->profile ? template->profile : &nop_profile;
bi->tuple_size = template->tuple_size;
bi->tag_size = template->tag_size;
- blk_integrity_revalidate(disk);
+ disk->queue->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
}
EXPORT_SYMBOL(blk_integrity_register);
*/
void blk_integrity_unregister(struct gendisk *disk)
{
- blk_integrity_revalidate(disk);
+ disk->queue->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES;
memset(&disk->queue->integrity, 0, sizeof(struct blk_integrity));
}
EXPORT_SYMBOL(blk_integrity_unregister);
-void blk_integrity_revalidate(struct gendisk *disk)
-{
- struct blk_integrity *bi = &disk->queue->integrity;
-
- if (!(disk->flags & GENHD_FL_UP))
- return;
-
- if (bi->profile)
- disk->queue->backing_dev_info->capabilities |=
- BDI_CAP_STABLE_WRITES;
- else
- disk->queue->backing_dev_info->capabilities &=
- ~BDI_CAP_STABLE_WRITES;
-}
-
void blk_integrity_add(struct gendisk *disk)
{
if (kobject_init_and_add(&disk->integrity_kobj, &integrity_ktype,
return -ENXIO;
if (flags & BLKDEV_DISCARD_SECURE) {
- if (flags & BLKDEV_DISCARD_ZERO)
- return -EOPNOTSUPP;
if (!blk_queue_secure_erase(q))
return -EOPNOTSUPP;
op = REQ_OP_SECURE_ERASE;
} else {
if (!blk_queue_discard(q))
return -EOPNOTSUPP;
- if ((flags & BLKDEV_DISCARD_ZERO) &&
- !q->limits.discard_zeroes_data)
- return -EOPNOTSUPP;
op = REQ_OP_DISCARD;
}
* @sector: start sector
* @nr_sects: number of sectors to discard
* @gfp_mask: memory allocation flags (for bio_alloc)
- * @flags: BLKDEV_IFL_* flags to control behaviour
+ * @flags: BLKDEV_DISCARD_* flags to control behaviour
*
* Description:
* Issue a discard request for the sectors in question.
&bio);
if (!ret && bio) {
ret = submit_bio_wait(bio);
- if (ret == -EOPNOTSUPP && !(flags & BLKDEV_DISCARD_ZERO))
+ if (ret == -EOPNOTSUPP)
ret = 0;
bio_put(bio);
}
}
EXPORT_SYMBOL(blkdev_issue_write_same);
-/**
- * __blkdev_issue_write_zeroes - generate number of bios with WRITE ZEROES
- * @bdev: blockdev to issue
- * @sector: start sector
- * @nr_sects: number of sectors to write
- * @gfp_mask: memory allocation flags (for bio_alloc)
- * @biop: pointer to anchor bio
- *
- * Description:
- * Generate and issue number of bios(REQ_OP_WRITE_ZEROES) with zerofiled pages.
- */
static int __blkdev_issue_write_zeroes(struct block_device *bdev,
sector_t sector, sector_t nr_sects, gfp_t gfp_mask,
- struct bio **biop)
+ struct bio **biop, unsigned flags)
{
struct bio *bio = *biop;
unsigned int max_write_zeroes_sectors;
bio = next_bio(bio, 0, gfp_mask);
bio->bi_iter.bi_sector = sector;
bio->bi_bdev = bdev;
- bio_set_op_attrs(bio, REQ_OP_WRITE_ZEROES, 0);
+ bio->bi_opf = REQ_OP_WRITE_ZEROES;
+ if (flags & BLKDEV_ZERO_NOUNMAP)
+ bio->bi_opf |= REQ_NOUNMAP;
if (nr_sects > max_write_zeroes_sectors) {
bio->bi_iter.bi_size = max_write_zeroes_sectors << 9;
* @nr_sects: number of sectors to write
* @gfp_mask: memory allocation flags (for bio_alloc)
* @biop: pointer to anchor bio
- * @discard: discard flag
+ * @flags: controls detailed behavior
*
* Description:
- * Generate and issue number of bios with zerofiled pages.
+ * Zero-fill a block range, either using hardware offload or by explicitly
+ * writing zeroes to the device.
+ *
+ * Note that this function may fail with -EOPNOTSUPP if the driver signals
+ * zeroing offload support, but the device fails to process the command (for
+ * some devices there is no non-destructive way to verify whether this
+ * operation is actually supported). In this case the caller should call
+ * retry the call to blkdev_issue_zeroout() and the fallback path will be used.
+ *
+ * If a device is using logical block provisioning, the underlying space will
+ * not be released if %flags contains BLKDEV_ZERO_NOUNMAP.
+ *
+ * If %flags contains BLKDEV_ZERO_NOFALLBACK, the function will return
+ * -EOPNOTSUPP if no explicit hardware offload for zeroing is provided.
*/
int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask, struct bio **biop,
- bool discard)
+ unsigned flags)
{
int ret;
int bi_size = 0;
return -EINVAL;
ret = __blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp_mask,
- biop);
- if (ret == 0 || (ret && ret != -EOPNOTSUPP))
+ biop, flags);
+ if (ret != -EOPNOTSUPP || (flags & BLKDEV_ZERO_NOFALLBACK))
goto out;
ret = 0;
* @sector: start sector
* @nr_sects: number of sectors to write
* @gfp_mask: memory allocation flags (for bio_alloc)
- * @discard: whether to discard the block range
+ * @flags: controls detailed behavior
*
* Description:
- * Zero-fill a block range. If the discard flag is set and the block
- * device guarantees that subsequent READ operations to the block range
- * in question will return zeroes, the blocks will be discarded. Should
- * the discard request fail, if the discard flag is not set, or if
- * discard_zeroes_data is not supported, this function will resort to
- * zeroing the blocks manually, thus provisioning (allocating,
- * anchoring) them. If the block device supports WRITE ZEROES or WRITE SAME
- * command(s), blkdev_issue_zeroout() will use it to optimize the process of
- * clearing the block range. Otherwise the zeroing will be performed
- * using regular WRITE calls.
+ * Zero-fill a block range, either using hardware offload or by explicitly
+ * writing zeroes to the device. See __blkdev_issue_zeroout() for the
+ * valid values for %flags.
*/
int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
- sector_t nr_sects, gfp_t gfp_mask, bool discard)
+ sector_t nr_sects, gfp_t gfp_mask, unsigned flags)
{
int ret;
struct bio *bio = NULL;
struct blk_plug plug;
- if (discard) {
- if (!blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask,
- BLKDEV_DISCARD_ZERO))
- return 0;
- }
-
- if (!blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask,
- ZERO_PAGE(0)))
- return 0;
-
blk_start_plug(&plug);
ret = __blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask,
- &bio, discard);
+ &bio, flags);
if (ret == 0 && bio) {
ret = submit_bio_wait(bio);
bio_put(bio);
return bio_split(bio, split_sectors, GFP_NOIO, bs);
}
+static struct bio *blk_bio_write_zeroes_split(struct request_queue *q,
+ struct bio *bio, struct bio_set *bs, unsigned *nsegs)
+{
+ *nsegs = 1;
+
+ if (!q->limits.max_write_zeroes_sectors)
+ return NULL;
+
+ if (bio_sectors(bio) <= q->limits.max_write_zeroes_sectors)
+ return NULL;
+
+ return bio_split(bio, q->limits.max_write_zeroes_sectors, GFP_NOIO, bs);
+}
+
static struct bio *blk_bio_write_same_split(struct request_queue *q,
struct bio *bio,
struct bio_set *bs,
split = blk_bio_discard_split(q, *bio, bs, &nsegs);
break;
case REQ_OP_WRITE_ZEROES:
- split = NULL;
- nsegs = (*bio)->bi_phys_segments;
+ split = blk_bio_write_zeroes_split(q, *bio, bs, &nsegs);
break;
case REQ_OP_WRITE_SAME:
split = blk_bio_write_same_split(q, *bio, bs, &nsegs);
return ret;
}
+static int blk_flags_show(struct seq_file *m, const unsigned long flags,
+ const char *const *flag_name, int flag_name_count)
+{
+ bool sep = false;
+ int i;
+
+ for (i = 0; i < sizeof(flags) * BITS_PER_BYTE; i++) {
+ if (!(flags & BIT(i)))
+ continue;
+ if (sep)
+ seq_puts(m, " ");
+ sep = true;
+ if (i < flag_name_count && flag_name[i])
+ seq_puts(m, flag_name[i]);
+ else
+ seq_printf(m, "%d", i);
+ }
+ return 0;
+}
+
+static const char *const blk_queue_flag_name[] = {
+ [QUEUE_FLAG_QUEUED] = "QUEUED",
+ [QUEUE_FLAG_STOPPED] = "STOPPED",
+ [QUEUE_FLAG_SYNCFULL] = "SYNCFULL",
+ [QUEUE_FLAG_ASYNCFULL] = "ASYNCFULL",
+ [QUEUE_FLAG_DYING] = "DYING",
+ [QUEUE_FLAG_BYPASS] = "BYPASS",
+ [QUEUE_FLAG_BIDI] = "BIDI",
+ [QUEUE_FLAG_NOMERGES] = "NOMERGES",
+ [QUEUE_FLAG_SAME_COMP] = "SAME_COMP",
+ [QUEUE_FLAG_FAIL_IO] = "FAIL_IO",
+ [QUEUE_FLAG_STACKABLE] = "STACKABLE",
+ [QUEUE_FLAG_NONROT] = "NONROT",
+ [QUEUE_FLAG_IO_STAT] = "IO_STAT",
+ [QUEUE_FLAG_DISCARD] = "DISCARD",
+ [QUEUE_FLAG_NOXMERGES] = "NOXMERGES",
+ [QUEUE_FLAG_ADD_RANDOM] = "ADD_RANDOM",
+ [QUEUE_FLAG_SECERASE] = "SECERASE",
+ [QUEUE_FLAG_SAME_FORCE] = "SAME_FORCE",
+ [QUEUE_FLAG_DEAD] = "DEAD",
+ [QUEUE_FLAG_INIT_DONE] = "INIT_DONE",
+ [QUEUE_FLAG_NO_SG_MERGE] = "NO_SG_MERGE",
+ [QUEUE_FLAG_POLL] = "POLL",
+ [QUEUE_FLAG_WC] = "WC",
+ [QUEUE_FLAG_FUA] = "FUA",
+ [QUEUE_FLAG_FLUSH_NQ] = "FLUSH_NQ",
+ [QUEUE_FLAG_DAX] = "DAX",
+ [QUEUE_FLAG_STATS] = "STATS",
+ [QUEUE_FLAG_POLL_STATS] = "POLL_STATS",
+ [QUEUE_FLAG_REGISTERED] = "REGISTERED",
+};
+
+static int blk_queue_flags_show(struct seq_file *m, void *v)
+{
+ struct request_queue *q = m->private;
+
+ blk_flags_show(m, q->queue_flags, blk_queue_flag_name,
+ ARRAY_SIZE(blk_queue_flag_name));
+ seq_puts(m, "\n");
+ return 0;
+}
+
+static ssize_t blk_queue_flags_store(struct file *file, const char __user *ubuf,
+ size_t len, loff_t *offp)
+{
+ struct request_queue *q = file_inode(file)->i_private;
+ char op[16] = { }, *s;
+
+ len = min(len, sizeof(op) - 1);
+ if (copy_from_user(op, ubuf, len))
+ return -EFAULT;
+ s = op;
+ strsep(&s, " \t\n"); /* strip trailing whitespace */
+ if (strcmp(op, "run") == 0) {
+ blk_mq_run_hw_queues(q, true);
+ } else if (strcmp(op, "start") == 0) {
+ blk_mq_start_stopped_hw_queues(q, true);
+ } else {
+ pr_err("%s: unsupported operation %s. Use either 'run' or 'start'\n",
+ __func__, op);
+ return -EINVAL;
+ }
+ return len;
+}
+
+static int blk_queue_flags_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, blk_queue_flags_show, inode->i_private);
+}
+
+static const struct file_operations blk_queue_flags_fops = {
+ .open = blk_queue_flags_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+ .write = blk_queue_flags_store,
+};
+
+static void print_stat(struct seq_file *m, struct blk_rq_stat *stat)
+{
+ if (stat->nr_samples) {
+ seq_printf(m, "samples=%d, mean=%lld, min=%llu, max=%llu",
+ stat->nr_samples, stat->mean, stat->min, stat->max);
+ } else {
+ seq_puts(m, "samples=0");
+ }
+}
+
+static int queue_poll_stat_show(struct seq_file *m, void *v)
+{
+ struct request_queue *q = m->private;
+ int bucket;
+
+ for (bucket = 0; bucket < BLK_MQ_POLL_STATS_BKTS/2; bucket++) {
+ seq_printf(m, "read (%d Bytes): ", 1 << (9+bucket));
+ print_stat(m, &q->poll_stat[2*bucket]);
+ seq_puts(m, "\n");
+
+ seq_printf(m, "write (%d Bytes): ", 1 << (9+bucket));
+ print_stat(m, &q->poll_stat[2*bucket+1]);
+ seq_puts(m, "\n");
+ }
+ return 0;
+}
+
+static int queue_poll_stat_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, queue_poll_stat_show, inode->i_private);
+}
+
+static const struct file_operations queue_poll_stat_fops = {
+ .open = queue_poll_stat_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static const char *const hctx_state_name[] = {
+ [BLK_MQ_S_STOPPED] = "STOPPED",
+ [BLK_MQ_S_TAG_ACTIVE] = "TAG_ACTIVE",
+ [BLK_MQ_S_SCHED_RESTART] = "SCHED_RESTART",
+ [BLK_MQ_S_TAG_WAITING] = "TAG_WAITING",
+
+};
static int hctx_state_show(struct seq_file *m, void *v)
{
struct blk_mq_hw_ctx *hctx = m->private;
- seq_printf(m, "0x%lx\n", hctx->state);
+ blk_flags_show(m, hctx->state, hctx_state_name,
+ ARRAY_SIZE(hctx_state_name));
+ seq_puts(m, "\n");
return 0;
}
.release = single_release,
};
+static const char *const alloc_policy_name[] = {
+ [BLK_TAG_ALLOC_FIFO] = "fifo",
+ [BLK_TAG_ALLOC_RR] = "rr",
+};
+
+static const char *const hctx_flag_name[] = {
+ [ilog2(BLK_MQ_F_SHOULD_MERGE)] = "SHOULD_MERGE",
+ [ilog2(BLK_MQ_F_TAG_SHARED)] = "TAG_SHARED",
+ [ilog2(BLK_MQ_F_SG_MERGE)] = "SG_MERGE",
+ [ilog2(BLK_MQ_F_BLOCKING)] = "BLOCKING",
+ [ilog2(BLK_MQ_F_NO_SCHED)] = "NO_SCHED",
+};
+
static int hctx_flags_show(struct seq_file *m, void *v)
{
struct blk_mq_hw_ctx *hctx = m->private;
-
- seq_printf(m, "0x%lx\n", hctx->flags);
+ const int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(hctx->flags);
+
+ seq_puts(m, "alloc_policy=");
+ if (alloc_policy < ARRAY_SIZE(alloc_policy_name) &&
+ alloc_policy_name[alloc_policy])
+ seq_puts(m, alloc_policy_name[alloc_policy]);
+ else
+ seq_printf(m, "%d", alloc_policy);
+ seq_puts(m, " ");
+ blk_flags_show(m,
+ hctx->flags ^ BLK_ALLOC_POLICY_TO_MQ_FLAG(alloc_policy),
+ hctx_flag_name, ARRAY_SIZE(hctx_flag_name));
+ seq_puts(m, "\n");
return 0;
}
.release = single_release,
};
+static const char *const op_name[] = {
+ [REQ_OP_READ] = "READ",
+ [REQ_OP_WRITE] = "WRITE",
+ [REQ_OP_FLUSH] = "FLUSH",
+ [REQ_OP_DISCARD] = "DISCARD",
+ [REQ_OP_ZONE_REPORT] = "ZONE_REPORT",
+ [REQ_OP_SECURE_ERASE] = "SECURE_ERASE",
+ [REQ_OP_ZONE_RESET] = "ZONE_RESET",
+ [REQ_OP_WRITE_SAME] = "WRITE_SAME",
+ [REQ_OP_WRITE_ZEROES] = "WRITE_ZEROES",
+ [REQ_OP_SCSI_IN] = "SCSI_IN",
+ [REQ_OP_SCSI_OUT] = "SCSI_OUT",
+ [REQ_OP_DRV_IN] = "DRV_IN",
+ [REQ_OP_DRV_OUT] = "DRV_OUT",
+};
+
+static const char *const cmd_flag_name[] = {
+ [__REQ_FAILFAST_DEV] = "FAILFAST_DEV",
+ [__REQ_FAILFAST_TRANSPORT] = "FAILFAST_TRANSPORT",
+ [__REQ_FAILFAST_DRIVER] = "FAILFAST_DRIVER",
+ [__REQ_SYNC] = "SYNC",
+ [__REQ_META] = "META",
+ [__REQ_PRIO] = "PRIO",
+ [__REQ_NOMERGE] = "NOMERGE",
+ [__REQ_IDLE] = "IDLE",
+ [__REQ_INTEGRITY] = "INTEGRITY",
+ [__REQ_FUA] = "FUA",
+ [__REQ_PREFLUSH] = "PREFLUSH",
+ [__REQ_RAHEAD] = "RAHEAD",
+ [__REQ_BACKGROUND] = "BACKGROUND",
+ [__REQ_NR_BITS] = "NR_BITS",
+};
+
+static const char *const rqf_name[] = {
+ [ilog2((__force u32)RQF_SORTED)] = "SORTED",
+ [ilog2((__force u32)RQF_STARTED)] = "STARTED",
+ [ilog2((__force u32)RQF_QUEUED)] = "QUEUED",
+ [ilog2((__force u32)RQF_SOFTBARRIER)] = "SOFTBARRIER",
+ [ilog2((__force u32)RQF_FLUSH_SEQ)] = "FLUSH_SEQ",
+ [ilog2((__force u32)RQF_MIXED_MERGE)] = "MIXED_MERGE",
+ [ilog2((__force u32)RQF_MQ_INFLIGHT)] = "MQ_INFLIGHT",
+ [ilog2((__force u32)RQF_DONTPREP)] = "DONTPREP",
+ [ilog2((__force u32)RQF_PREEMPT)] = "PREEMPT",
+ [ilog2((__force u32)RQF_COPY_USER)] = "COPY_USER",
+ [ilog2((__force u32)RQF_FAILED)] = "FAILED",
+ [ilog2((__force u32)RQF_QUIET)] = "QUIET",
+ [ilog2((__force u32)RQF_ELVPRIV)] = "ELVPRIV",
+ [ilog2((__force u32)RQF_IO_STAT)] = "IO_STAT",
+ [ilog2((__force u32)RQF_ALLOCED)] = "ALLOCED",
+ [ilog2((__force u32)RQF_PM)] = "PM",
+ [ilog2((__force u32)RQF_HASHED)] = "HASHED",
+ [ilog2((__force u32)RQF_STATS)] = "STATS",
+ [ilog2((__force u32)RQF_SPECIAL_PAYLOAD)] = "SPECIAL_PAYLOAD",
+};
+
static int blk_mq_debugfs_rq_show(struct seq_file *m, void *v)
{
struct request *rq = list_entry_rq(v);
-
- seq_printf(m, "%p {.cmd_flags=0x%x, .rq_flags=0x%x, .tag=%d, .internal_tag=%d}\n",
- rq, rq->cmd_flags, (__force unsigned int)rq->rq_flags,
- rq->tag, rq->internal_tag);
+ const struct blk_mq_ops *const mq_ops = rq->q->mq_ops;
+ const unsigned int op = rq->cmd_flags & REQ_OP_MASK;
+
+ seq_printf(m, "%p {.op=", rq);
+ if (op < ARRAY_SIZE(op_name) && op_name[op])
+ seq_printf(m, "%s", op_name[op]);
+ else
+ seq_printf(m, "%d", op);
+ seq_puts(m, ", .cmd_flags=");
+ blk_flags_show(m, rq->cmd_flags & ~REQ_OP_MASK, cmd_flag_name,
+ ARRAY_SIZE(cmd_flag_name));
+ seq_puts(m, ", .rq_flags=");
+ blk_flags_show(m, (__force unsigned int)rq->rq_flags, rqf_name,
+ ARRAY_SIZE(rqf_name));
+ seq_printf(m, ", .tag=%d, .internal_tag=%d", rq->tag,
+ rq->internal_tag);
+ if (mq_ops->show_rq)
+ mq_ops->show_rq(m, rq);
+ seq_puts(m, "}\n");
return 0;
}
.release = single_release,
};
-static void print_stat(struct seq_file *m, struct blk_rq_stat *stat)
-{
- seq_printf(m, "samples=%d, mean=%lld, min=%llu, max=%llu",
- stat->nr_samples, stat->mean, stat->min, stat->max);
-}
-
-static int hctx_stats_show(struct seq_file *m, void *v)
-{
- struct blk_mq_hw_ctx *hctx = m->private;
- struct blk_rq_stat stat[2];
-
- blk_stat_init(&stat[BLK_STAT_READ]);
- blk_stat_init(&stat[BLK_STAT_WRITE]);
-
- blk_hctx_stat_get(hctx, stat);
-
- seq_puts(m, "read: ");
- print_stat(m, &stat[BLK_STAT_READ]);
- seq_puts(m, "\n");
-
- seq_puts(m, "write: ");
- print_stat(m, &stat[BLK_STAT_WRITE]);
- seq_puts(m, "\n");
- return 0;
-}
-
-static int hctx_stats_open(struct inode *inode, struct file *file)
-{
- return single_open(file, hctx_stats_show, inode->i_private);
-}
-
-static ssize_t hctx_stats_write(struct file *file, const char __user *buf,
- size_t count, loff_t *ppos)
-{
- struct seq_file *m = file->private_data;
- struct blk_mq_hw_ctx *hctx = m->private;
- struct blk_mq_ctx *ctx;
- int i;
-
- hctx_for_each_ctx(hctx, ctx, i) {
- blk_stat_init(&ctx->stat[BLK_STAT_READ]);
- blk_stat_init(&ctx->stat[BLK_STAT_WRITE]);
- }
- return count;
-}
-
-static const struct file_operations hctx_stats_fops = {
- .open = hctx_stats_open,
- .read = seq_read,
- .write = hctx_stats_write,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
static int hctx_dispatched_show(struct seq_file *m, void *v)
{
struct blk_mq_hw_ctx *hctx = m->private;
.release = single_release,
};
+static const struct blk_mq_debugfs_attr blk_mq_debugfs_queue_attrs[] = {
+ {"poll_stat", 0400, &queue_poll_stat_fops},
+ {"state", 0600, &blk_queue_flags_fops},
+ {},
+};
+
static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = {
{"state", 0400, &hctx_state_fops},
{"flags", 0400, &hctx_flags_fops},
{"sched_tags", 0400, &hctx_sched_tags_fops},
{"sched_tags_bitmap", 0400, &hctx_sched_tags_bitmap_fops},
{"io_poll", 0600, &hctx_io_poll_fops},
- {"stats", 0600, &hctx_stats_fops},
{"dispatched", 0600, &hctx_dispatched_fops},
{"queued", 0600, &hctx_queued_fops},
{"run", 0600, &hctx_run_fops},
{},
};
-int blk_mq_debugfs_register(struct request_queue *q, const char *name)
+int blk_mq_debugfs_register(struct request_queue *q)
{
if (!blk_debugfs_root)
return -ENOENT;
- q->debugfs_dir = debugfs_create_dir(name, blk_debugfs_root);
+ q->debugfs_dir = debugfs_create_dir(kobject_name(q->kobj.parent),
+ blk_debugfs_root);
if (!q->debugfs_dir)
goto err;
- if (blk_mq_debugfs_register_hctxs(q))
+ if (blk_mq_debugfs_register_mq(q))
goto err;
return 0;
return 0;
}
-int blk_mq_debugfs_register_hctxs(struct request_queue *q)
+int blk_mq_debugfs_register_mq(struct request_queue *q)
{
struct blk_mq_hw_ctx *hctx;
int i;
if (!q->mq_debugfs_dir)
goto err;
+ if (!debugfs_create_files(q->mq_debugfs_dir, q, blk_mq_debugfs_queue_attrs))
+ goto err;
+
queue_for_each_hw_ctx(q, hctx, i) {
if (blk_mq_debugfs_register_hctx(q, hctx))
goto err;
return 0;
err:
- blk_mq_debugfs_unregister_hctxs(q);
+ blk_mq_debugfs_unregister_mq(q);
return -ENOMEM;
}
-void blk_mq_debugfs_unregister_hctxs(struct request_queue *q)
+void blk_mq_debugfs_unregister_mq(struct request_queue *q)
{
debugfs_remove_recursive(q->mq_debugfs_dir);
q->mq_debugfs_dir = NULL;
* @pdev: PCI device associated with @set.
*
* This function assumes the PCI device @pdev has at least as many available
- * interrupt vetors as @set has queues. It will then queuery the vector
+ * interrupt vectors as @set has queues. It will then query the vector
* corresponding to each queue for it's affinity mask and built queue mapping
* that maps a queue to the CPUs that have irq affinity for the corresponding
* vector.
}
EXPORT_SYMBOL_GPL(blk_mq_sched_free_hctx_data);
-int blk_mq_sched_init_hctx_data(struct request_queue *q, size_t size,
- int (*init)(struct blk_mq_hw_ctx *),
- void (*exit)(struct blk_mq_hw_ctx *))
-{
- struct blk_mq_hw_ctx *hctx;
- int ret;
- int i;
-
- queue_for_each_hw_ctx(q, hctx, i) {
- hctx->sched_data = kmalloc_node(size, GFP_KERNEL, hctx->numa_node);
- if (!hctx->sched_data) {
- ret = -ENOMEM;
- goto error;
- }
-
- if (init) {
- ret = init(hctx);
- if (ret) {
- /*
- * We don't want to give exit() a partially
- * initialized sched_data. init() must clean up
- * if it fails.
- */
- kfree(hctx->sched_data);
- hctx->sched_data = NULL;
- goto error;
- }
- }
- }
-
- return 0;
-error:
- blk_mq_sched_free_hctx_data(q, exit);
- return ret;
-}
-EXPORT_SYMBOL_GPL(blk_mq_sched_init_hctx_data);
-
static void __blk_mq_sched_assign_ioc(struct request_queue *q,
struct request *rq,
struct bio *bio,
if (likely(!data->hctx))
data->hctx = blk_mq_map_queue(q, data->ctx->cpu);
- if (e) {
+ /*
+ * For a reserved tag, allocate a normal request since we might
+ * have driver dependencies on the value of the internal tag.
+ */
+ if (e && !(data->flags & BLK_MQ_REQ_RESERVED)) {
data->flags |= BLK_MQ_REQ_INTERNAL;
/*
void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
{
- struct elevator_queue *e = hctx->queue->elevator;
+ struct request_queue *q = hctx->queue;
+ struct elevator_queue *e = q->elevator;
const bool has_sched_dispatch = e && e->type->ops.mq.dispatch_request;
bool did_work = false;
LIST_HEAD(rq_list);
*/
if (!list_empty(&rq_list)) {
blk_mq_sched_mark_restart_hctx(hctx);
- did_work = blk_mq_dispatch_rq_list(hctx, &rq_list);
+ did_work = blk_mq_dispatch_rq_list(q, &rq_list);
} else if (!has_sched_dispatch) {
blk_mq_flush_busy_ctxs(hctx, &rq_list);
- blk_mq_dispatch_rq_list(hctx, &rq_list);
+ blk_mq_dispatch_rq_list(q, &rq_list);
}
/*
if (!rq)
break;
list_add(&rq->queuelist, &rq_list);
- } while (blk_mq_dispatch_rq_list(hctx, &rq_list));
+ } while (blk_mq_dispatch_rq_list(q, &rq_list));
}
}
-void blk_mq_sched_move_to_dispatch(struct blk_mq_hw_ctx *hctx,
- struct list_head *rq_list,
- struct request *(*get_rq)(struct blk_mq_hw_ctx *))
-{
- do {
- struct request *rq;
-
- rq = get_rq(hctx);
- if (!rq)
- break;
-
- list_add_tail(&rq->queuelist, rq_list);
- } while (1);
-}
-EXPORT_SYMBOL_GPL(blk_mq_sched_move_to_dispatch);
-
bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
struct request **merged_request)
{
return true;
}
-static void blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx)
+static bool blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx)
{
if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) {
clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
- if (blk_mq_hctx_has_pending(hctx))
+ if (blk_mq_hctx_has_pending(hctx)) {
blk_mq_run_hw_queue(hctx, true);
+ return true;
+ }
}
+ return false;
}
-void blk_mq_sched_restart_queues(struct blk_mq_hw_ctx *hctx)
-{
- struct request_queue *q = hctx->queue;
- unsigned int i;
+/**
+ * list_for_each_entry_rcu_rr - iterate in a round-robin fashion over rcu list
+ * @pos: loop cursor.
+ * @skip: the list element that will not be examined. Iteration starts at
+ * @skip->next.
+ * @head: head of the list to examine. This list must have at least one
+ * element, namely @skip.
+ * @member: name of the list_head structure within typeof(*pos).
+ */
+#define list_for_each_entry_rcu_rr(pos, skip, head, member) \
+ for ((pos) = (skip); \
+ (pos = (pos)->member.next != (head) ? list_entry_rcu( \
+ (pos)->member.next, typeof(*pos), member) : \
+ list_entry_rcu((pos)->member.next->next, typeof(*pos), member)), \
+ (pos) != (skip); )
- if (test_bit(QUEUE_FLAG_RESTART, &q->queue_flags)) {
- if (test_and_clear_bit(QUEUE_FLAG_RESTART, &q->queue_flags)) {
- queue_for_each_hw_ctx(q, hctx, i)
- blk_mq_sched_restart_hctx(hctx);
+/*
+ * Called after a driver tag has been freed to check whether a hctx needs to
+ * be restarted. Restarts @hctx if its tag set is not shared. Restarts hardware
+ * queues in a round-robin fashion if the tag set of @hctx is shared with other
+ * hardware queues.
+ */
+void blk_mq_sched_restart(struct blk_mq_hw_ctx *const hctx)
+{
+ struct blk_mq_tags *const tags = hctx->tags;
+ struct blk_mq_tag_set *const set = hctx->queue->tag_set;
+ struct request_queue *const queue = hctx->queue, *q;
+ struct blk_mq_hw_ctx *hctx2;
+ unsigned int i, j;
+
+ if (set->flags & BLK_MQ_F_TAG_SHARED) {
+ rcu_read_lock();
+ list_for_each_entry_rcu_rr(q, queue, &set->tag_list,
+ tag_set_list) {
+ queue_for_each_hw_ctx(q, hctx2, i)
+ if (hctx2->tags == tags &&
+ blk_mq_sched_restart_hctx(hctx2))
+ goto done;
}
+ j = hctx->queue_num + 1;
+ for (i = 0; i < queue->nr_hw_queues; i++, j++) {
+ if (j == queue->nr_hw_queues)
+ j = 0;
+ hctx2 = queue->queue_hw_ctx[j];
+ if (hctx2->tags == tags &&
+ blk_mq_sched_restart_hctx(hctx2))
+ break;
+ }
+done:
+ rcu_read_unlock();
} else {
blk_mq_sched_restart_hctx(hctx);
}
}
}
-int blk_mq_sched_setup(struct request_queue *q)
+static int blk_mq_sched_alloc_tags(struct request_queue *q,
+ struct blk_mq_hw_ctx *hctx,
+ unsigned int hctx_idx)
{
struct blk_mq_tag_set *set = q->tag_set;
+ int ret;
+
+ hctx->sched_tags = blk_mq_alloc_rq_map(set, hctx_idx, q->nr_requests,
+ set->reserved_tags);
+ if (!hctx->sched_tags)
+ return -ENOMEM;
+
+ ret = blk_mq_alloc_rqs(set, hctx->sched_tags, hctx_idx, q->nr_requests);
+ if (ret)
+ blk_mq_sched_free_tags(set, hctx, hctx_idx);
+
+ return ret;
+}
+
+static void blk_mq_sched_tags_teardown(struct request_queue *q)
+{
+ struct blk_mq_tag_set *set = q->tag_set;
+ struct blk_mq_hw_ctx *hctx;
+ int i;
+
+ queue_for_each_hw_ctx(q, hctx, i)
+ blk_mq_sched_free_tags(set, hctx, i);
+}
+
+int blk_mq_sched_init_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
+ unsigned int hctx_idx)
+{
+ struct elevator_queue *e = q->elevator;
+ int ret;
+
+ if (!e)
+ return 0;
+
+ ret = blk_mq_sched_alloc_tags(q, hctx, hctx_idx);
+ if (ret)
+ return ret;
+
+ if (e->type->ops.mq.init_hctx) {
+ ret = e->type->ops.mq.init_hctx(hctx, hctx_idx);
+ if (ret) {
+ blk_mq_sched_free_tags(q->tag_set, hctx, hctx_idx);
+ return ret;
+ }
+ }
+
+ return 0;
+}
+
+void blk_mq_sched_exit_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
+ unsigned int hctx_idx)
+{
+ struct elevator_queue *e = q->elevator;
+
+ if (!e)
+ return;
+
+ if (e->type->ops.mq.exit_hctx && hctx->sched_data) {
+ e->type->ops.mq.exit_hctx(hctx, hctx_idx);
+ hctx->sched_data = NULL;
+ }
+
+ blk_mq_sched_free_tags(q->tag_set, hctx, hctx_idx);
+}
+
+int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
+{
struct blk_mq_hw_ctx *hctx;
- int ret, i;
+ struct elevator_queue *eq;
+ unsigned int i;
+ int ret;
+
+ if (!e) {
+ q->elevator = NULL;
+ return 0;
+ }
/*
* Default to 256, since we don't split into sync/async like the
*/
q->nr_requests = 2 * BLKDEV_MAX_RQ;
- /*
- * We're switching to using an IO scheduler, so setup the hctx
- * scheduler tags and switch the request map from the regular
- * tags to scheduler tags. First allocate what we need, so we
- * can safely fail and fallback, if needed.
- */
- ret = 0;
queue_for_each_hw_ctx(q, hctx, i) {
- hctx->sched_tags = blk_mq_alloc_rq_map(set, i,
- q->nr_requests, set->reserved_tags);
- if (!hctx->sched_tags) {
- ret = -ENOMEM;
- break;
- }
- ret = blk_mq_alloc_rqs(set, hctx->sched_tags, i, q->nr_requests);
+ ret = blk_mq_sched_alloc_tags(q, hctx, i);
if (ret)
- break;
+ goto err;
}
- /*
- * If we failed, free what we did allocate
- */
- if (ret) {
+ ret = e->ops.mq.init_sched(q, e);
+ if (ret)
+ goto err;
+
+ if (e->ops.mq.init_hctx) {
queue_for_each_hw_ctx(q, hctx, i) {
- if (!hctx->sched_tags)
- continue;
- blk_mq_sched_free_tags(set, hctx, i);
+ ret = e->ops.mq.init_hctx(hctx, i);
+ if (ret) {
+ eq = q->elevator;
+ blk_mq_exit_sched(q, eq);
+ kobject_put(&eq->kobj);
+ return ret;
+ }
}
-
- return ret;
}
return 0;
+
+err:
+ blk_mq_sched_tags_teardown(q);
+ q->elevator = NULL;
+ return ret;
}
-void blk_mq_sched_teardown(struct request_queue *q)
+void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e)
{
- struct blk_mq_tag_set *set = q->tag_set;
struct blk_mq_hw_ctx *hctx;
- int i;
+ unsigned int i;
- queue_for_each_hw_ctx(q, hctx, i)
- blk_mq_sched_free_tags(set, hctx, i);
+ if (e->type->ops.mq.exit_hctx) {
+ queue_for_each_hw_ctx(q, hctx, i) {
+ if (hctx->sched_data) {
+ e->type->ops.mq.exit_hctx(hctx, i);
+ hctx->sched_data = NULL;
+ }
+ }
+ }
+ if (e->type->ops.mq.exit_sched)
+ e->type->ops.mq.exit_sched(e);
+ blk_mq_sched_tags_teardown(q);
+ q->elevator = NULL;
}
int blk_mq_sched_init(struct request_queue *q)
#include "blk-mq.h"
#include "blk-mq-tag.h"
-int blk_mq_sched_init_hctx_data(struct request_queue *q, size_t size,
- int (*init)(struct blk_mq_hw_ctx *),
- void (*exit)(struct blk_mq_hw_ctx *));
-
void blk_mq_sched_free_hctx_data(struct request_queue *q,
void (*exit)(struct blk_mq_hw_ctx *));
struct request **merged_request);
bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio);
bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq);
-void blk_mq_sched_restart_queues(struct blk_mq_hw_ctx *hctx);
+void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx);
void blk_mq_sched_insert_request(struct request *rq, bool at_head,
bool run_queue, bool async, bool can_block);
struct list_head *list, bool run_queue_async);
void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx);
-void blk_mq_sched_move_to_dispatch(struct blk_mq_hw_ctx *hctx,
- struct list_head *rq_list,
- struct request *(*get_rq)(struct blk_mq_hw_ctx *));
-int blk_mq_sched_setup(struct request_queue *q);
-void blk_mq_sched_teardown(struct request_queue *q);
+int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e);
+void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e);
+
+int blk_mq_sched_init_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
+ unsigned int hctx_idx);
+void blk_mq_sched_exit_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
+ unsigned int hctx_idx);
int blk_mq_sched_init(struct request_queue *q);
return true;
}
-static inline void
-blk_mq_sched_completed_request(struct blk_mq_hw_ctx *hctx, struct request *rq)
+static inline void blk_mq_sched_completed_request(struct request *rq)
{
- struct elevator_queue *e = hctx->queue->elevator;
+ struct elevator_queue *e = rq->q->elevator;
if (e && e->type->ops.mq.completed_request)
- e->type->ops.mq.completed_request(hctx, rq);
-
- BUG_ON(rq->internal_tag == -1);
-
- blk_mq_put_tag(hctx, hctx->sched_tags, rq->mq_ctx, rq->internal_tag);
+ e->type->ops.mq.completed_request(rq);
}
static inline void blk_mq_sched_started_request(struct request *rq)
set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
}
-/*
- * Mark a hardware queue and the request queue it belongs to as needing a
- * restart.
- */
-static inline void blk_mq_sched_mark_restart_queue(struct blk_mq_hw_ctx *hctx)
-{
- struct request_queue *q = hctx->queue;
-
- if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
- set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
- if (!test_bit(QUEUE_FLAG_RESTART, &q->queue_flags))
- set_bit(QUEUE_FLAG_RESTART, &q->queue_flags);
-}
-
static inline bool blk_mq_sched_needs_restart(struct blk_mq_hw_ctx *hctx)
{
return test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
struct blk_mq_hw_ctx *hctx;
int i;
+ lockdep_assert_held(&q->sysfs_lock);
+
queue_for_each_hw_ctx(q, hctx, i)
blk_mq_unregister_hctx(hctx);
- blk_mq_debugfs_unregister_hctxs(q);
+ blk_mq_debugfs_unregister_mq(q);
kobject_uevent(&q->mq_kobj, KOBJ_REMOVE);
kobject_del(&q->mq_kobj);
void blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
{
- blk_mq_disable_hotplug();
+ mutex_lock(&q->sysfs_lock);
__blk_mq_unregister_dev(dev, q);
- blk_mq_enable_hotplug();
+ mutex_unlock(&q->sysfs_lock);
}
void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx)
}
}
-int blk_mq_register_dev(struct device *dev, struct request_queue *q)
+int __blk_mq_register_dev(struct device *dev, struct request_queue *q)
{
struct blk_mq_hw_ctx *hctx;
int ret, i;
- blk_mq_disable_hotplug();
+ WARN_ON_ONCE(!q->kobj.parent);
+ lockdep_assert_held(&q->sysfs_lock);
ret = kobject_add(&q->mq_kobj, kobject_get(&dev->kobj), "%s", "mq");
if (ret < 0)
kobject_uevent(&q->mq_kobj, KOBJ_ADD);
- blk_mq_debugfs_register(q, kobject_name(&dev->kobj));
+ blk_mq_debugfs_register(q);
queue_for_each_hw_ctx(q, hctx, i) {
ret = blk_mq_register_hctx(hctx);
if (ret)
- break;
+ goto unreg;
}
- if (ret)
- __blk_mq_unregister_dev(dev, q);
- else
- q->mq_sysfs_init_done = true;
+ q->mq_sysfs_init_done = true;
+
out:
- blk_mq_enable_hotplug();
+ return ret;
+
+unreg:
+ while (--i >= 0)
+ blk_mq_unregister_hctx(q->queue_hw_ctx[i]);
+
+ blk_mq_debugfs_unregister_mq(q);
+
+ kobject_uevent(&q->mq_kobj, KOBJ_REMOVE);
+ kobject_del(&q->mq_kobj);
+ kobject_put(&dev->kobj);
+ return ret;
+}
+
+int blk_mq_register_dev(struct device *dev, struct request_queue *q)
+{
+ int ret;
+
+ mutex_lock(&q->sysfs_lock);
+ ret = __blk_mq_register_dev(dev, q);
+ mutex_unlock(&q->sysfs_lock);
return ret;
}
struct blk_mq_hw_ctx *hctx;
int i;
+ mutex_lock(&q->sysfs_lock);
if (!q->mq_sysfs_init_done)
- return;
+ goto unlock;
- blk_mq_debugfs_unregister_hctxs(q);
+ blk_mq_debugfs_unregister_mq(q);
queue_for_each_hw_ctx(q, hctx, i)
blk_mq_unregister_hctx(hctx);
+
+unlock:
+ mutex_unlock(&q->sysfs_lock);
}
int blk_mq_sysfs_register(struct request_queue *q)
struct blk_mq_hw_ctx *hctx;
int i, ret = 0;
+ mutex_lock(&q->sysfs_lock);
if (!q->mq_sysfs_init_done)
- return ret;
+ goto unlock;
- blk_mq_debugfs_register_hctxs(q);
+ blk_mq_debugfs_register_mq(q);
queue_for_each_hw_ctx(q, hctx, i) {
ret = blk_mq_register_hctx(hctx);
break;
}
+unlock:
+ mutex_unlock(&q->sysfs_lock);
+
return ret;
}
if (!(data->flags & BLK_MQ_REQ_INTERNAL) &&
!hctx_may_queue(data->hctx, bt))
return -1;
- return __sbitmap_queue_get(bt);
+ if (data->shallow_depth)
+ return __sbitmap_queue_get_shallow(bt, data->shallow_depth);
+ else
+ return __sbitmap_queue_get(bt);
}
unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
static DEFINE_MUTEX(all_q_mutex);
static LIST_HEAD(all_q_list);
+static void blk_mq_poll_stats_start(struct request_queue *q);
+static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb);
+
+static int blk_mq_poll_stats_bkt(const struct request *rq)
+{
+ int ddir, bytes, bucket;
+
+ ddir = rq_data_dir(rq);
+ bytes = blk_rq_bytes(rq);
+
+ bucket = ddir + 2*(ilog2(bytes) - 9);
+
+ if (bucket < 0)
+ return -1;
+ else if (bucket >= BLK_MQ_POLL_STATS_BKTS)
+ return ddir + BLK_MQ_POLL_STATS_BKTS - 2;
+
+ return bucket;
+}
+
/*
* Check if any of the ctx's have pending work in this hardware queue
*/
sbitmap_clear_bit(&hctx->ctx_map, ctx->index_hw);
}
-void blk_mq_freeze_queue_start(struct request_queue *q)
+void blk_freeze_queue_start(struct request_queue *q)
{
int freeze_depth;
blk_mq_run_hw_queues(q, false);
}
}
-EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_start);
+EXPORT_SYMBOL_GPL(blk_freeze_queue_start);
void blk_mq_freeze_queue_wait(struct request_queue *q)
{
* no blk_unfreeze_queue(), and blk_freeze_queue() is not
* exported to drivers as the only user for unfreeze is blk_mq.
*/
- blk_mq_freeze_queue_start(q);
+ blk_freeze_queue_start(q);
blk_mq_freeze_queue_wait(q);
}
#endif
rq->special = NULL;
/* tag was already set */
- rq->errors = 0;
rq->extra_len = 0;
INIT_LIST_HEAD(&rq->timeout_list);
rq = blk_mq_sched_get_request(q, NULL, rw, &alloc_data);
- blk_mq_put_ctx(alloc_data.ctx);
blk_queue_exit(q);
if (!rq)
if (rq->tag != -1)
blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag);
if (sched_tag != -1)
- blk_mq_sched_completed_request(hctx, rq);
- blk_mq_sched_restart_queues(hctx);
+ blk_mq_put_tag(hctx, hctx->sched_tags, ctx, sched_tag);
+ blk_mq_sched_restart(hctx);
blk_queue_exit(q);
}
{
blk_mq_finish_hctx_request(blk_mq_map_queue(rq->q, rq->mq_ctx->cpu), rq);
}
+EXPORT_SYMBOL_GPL(blk_mq_finish_request);
void blk_mq_free_request(struct request *rq)
{
rq->q->softirq_done_fn(rq);
}
-static void blk_mq_ipi_complete_request(struct request *rq)
+static void __blk_mq_complete_request(struct request *rq)
{
struct blk_mq_ctx *ctx = rq->mq_ctx;
bool shared = false;
int cpu;
+ if (rq->internal_tag != -1)
+ blk_mq_sched_completed_request(rq);
+ if (rq->rq_flags & RQF_STATS) {
+ blk_mq_poll_stats_start(rq->q);
+ blk_stat_add(rq);
+ }
+
if (!test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags)) {
rq->q->softirq_done_fn(rq);
return;
put_cpu();
}
-static void blk_mq_stat_add(struct request *rq)
-{
- if (rq->rq_flags & RQF_STATS) {
- /*
- * We could rq->mq_ctx here, but there's less of a risk
- * of races if we have the completion event add the stats
- * to the local software queue.
- */
- struct blk_mq_ctx *ctx;
-
- ctx = __blk_mq_get_ctx(rq->q, raw_smp_processor_id());
- blk_stat_add(&ctx->stat[rq_data_dir(rq)], rq);
- }
-}
-
-static void __blk_mq_complete_request(struct request *rq)
-{
- struct request_queue *q = rq->q;
-
- blk_mq_stat_add(rq);
-
- if (!q->softirq_done_fn)
- blk_mq_end_request(rq, rq->errors);
- else
- blk_mq_ipi_complete_request(rq);
-}
-
/**
* blk_mq_complete_request - end I/O on a request
* @rq: the request being processed
* Ends all I/O on a request. It does not handle partial completions.
* The actual completion happens out-of-order, through a IPI handler.
**/
-void blk_mq_complete_request(struct request *rq, int error)
+void blk_mq_complete_request(struct request *rq)
{
struct request_queue *q = rq->q;
if (unlikely(blk_should_fake_timeout(q)))
return;
- if (!blk_mark_rq_complete(rq)) {
- rq->errors = error;
+ if (!blk_mark_rq_complete(rq))
__blk_mq_complete_request(rq);
- }
}
EXPORT_SYMBOL(blk_mq_complete_request);
trace_block_rq_issue(q, rq);
if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
- blk_stat_set_issue_time(&rq->issue_stat);
+ blk_stat_set_issue(&rq->issue_stat, blk_rq_sectors(rq));
rq->rq_flags |= RQF_STATS;
wbt_issue(q->rq_wb, &rq->issue_stat);
}
}
EXPORT_SYMBOL(blk_mq_start_request);
+/*
+ * When we reach here because queue is busy, REQ_ATOM_COMPLETE
+ * flag isn't set yet, so there may be race with timeout handler,
+ * but given rq->deadline is just set in .queue_rq() under
+ * this situation, the race won't be possible in reality because
+ * rq->timeout should be set as big enough to cover the window
+ * between blk_mq_start_request() called from .queue_rq() and
+ * clearing REQ_ATOM_STARTED here.
+ */
static void __blk_mq_requeue_request(struct request *rq)
{
struct request_queue *q = rq->q;
rq = list_first_entry(&rq_list, struct request, queuelist);
list_del_init(&rq->queuelist);
- rq->errors = -EIO;
- blk_mq_end_request(rq, rq->errors);
+ blk_mq_end_request(rq, -EIO);
}
}
EXPORT_SYMBOL(blk_mq_abort_requeue_list);
* just be ignored. This can happen due to the bitflag ordering.
* Timeout first checks if STARTED is set, and if it is, assumes
* the request is active. But if we race with completion, then
- * we both flags will get cleared. So check here again, and ignore
+ * both flags will get cleared. So check here again, and ignore
* a timeout event with a request that isn't active.
*/
if (!test_bit(REQ_ATOM_STARTED, &req->atomic_flags))
if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))
return;
+ /*
+ * The rq being checked may have been freed and reallocated
+ * out already here, we avoid this race by checking rq->deadline
+ * and REQ_ATOM_COMPLETE flag together:
+ *
+ * - if rq->deadline is observed as new value because of
+ * reusing, the rq won't be timed out because of timing.
+ * - if rq->deadline is observed as previous value,
+ * REQ_ATOM_COMPLETE flag won't be cleared in reuse path
+ * because we put a barrier between setting rq->deadline
+ * and clearing the flag in blk_mq_start_request(), so
+ * this rq won't be timed out too.
+ */
if (time_after_eq(jiffies, rq->deadline)) {
if (!blk_mark_rq_complete(rq))
blk_mq_rq_timed_out(rq, reserved);
* percpu_ref_tryget directly, because we need to be able to
* obtain a reference even in the short window between the queue
* starting to freeze, by dropping the first reference in
- * blk_mq_freeze_queue_start, and the moment the last request is
+ * blk_freeze_queue_start, and the moment the last request is
* consumed, marked by the instant q_usage_counter reaches
* zero.
*/
.flags = wait ? 0 : BLK_MQ_REQ_NOWAIT,
};
- if (rq->tag != -1) {
-done:
- if (hctx)
- *hctx = data.hctx;
- return true;
- }
+ might_sleep_if(wait);
+
+ if (rq->tag != -1)
+ goto done;
if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag))
data.flags |= BLK_MQ_REQ_RESERVED;
atomic_inc(&data.hctx->nr_active);
}
data.hctx->tags->rqs[rq->tag] = rq;
- goto done;
}
- return false;
+done:
+ if (hctx)
+ *hctx = data.hctx;
+ return rq->tag != -1;
}
static void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
return true;
}
-bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
+bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)
{
- struct request_queue *q = hctx->queue;
+ struct blk_mq_hw_ctx *hctx;
struct request *rq;
- LIST_HEAD(driver_list);
- struct list_head *dptr;
int errors, queued, ret = BLK_MQ_RQ_QUEUE_OK;
- /*
- * Start off with dptr being NULL, so we start the first request
- * immediately, even if we have more pending.
- */
- dptr = NULL;
+ if (list_empty(list))
+ return false;
/*
* Now process all the entries, sending them to the driver.
*/
errors = queued = 0;
- while (!list_empty(list)) {
+ do {
struct blk_mq_queue_data bd;
rq = list_first_entry(list, struct request, queuelist);
* The initial allocation attempt failed, so we need to
* rerun the hardware queue when a tag is freed.
*/
- if (blk_mq_dispatch_wait_add(hctx)) {
- /*
- * It's possible that a tag was freed in the
- * window between the allocation failure and
- * adding the hardware queue to the wait queue.
- */
- if (!blk_mq_get_driver_tag(rq, &hctx, false))
- break;
- } else {
+ if (!blk_mq_dispatch_wait_add(hctx))
+ break;
+
+ /*
+ * It's possible that a tag was freed in the window
+ * between the allocation failure and adding the
+ * hardware queue to the wait queue.
+ */
+ if (!blk_mq_get_driver_tag(rq, &hctx, false))
break;
- }
}
list_del_init(&rq->queuelist);
bd.rq = rq;
- bd.list = dptr;
/*
* Flag last if we have no more requests, or if we have more
pr_err("blk-mq: bad return on queue: %d\n", ret);
case BLK_MQ_RQ_QUEUE_ERROR:
errors++;
- rq->errors = -EIO;
- blk_mq_end_request(rq, rq->errors);
+ blk_mq_end_request(rq, -EIO);
break;
}
if (ret == BLK_MQ_RQ_QUEUE_BUSY)
break;
-
- /*
- * We've done the first request. If we have more than 1
- * left in the list, set dptr to defer issue.
- */
- if (!dptr && list->next != list->prev)
- dptr = &driver_list;
- }
+ } while (!list_empty(list));
hctx->dispatched[queued_to_index(queued)]++;
*/
if (!list_empty(list)) {
/*
- * If we got a driver tag for the next request already,
- * free it again.
+ * If an I/O scheduler has been configured and we got a driver
+ * tag for the next request already, free it again.
*/
rq = list_first_entry(list, struct request, queuelist);
blk_mq_put_driver_tag(rq);
spin_unlock(&hctx->lock);
/*
- * the queue is expected stopped with BLK_MQ_RQ_QUEUE_BUSY, but
- * it's possible the queue is stopped and restarted again
- * before this. Queue restart will dispatch requests. And since
- * requests in rq_list aren't added into hctx->dispatch yet,
- * the requests in rq_list might get lost.
+ * If SCHED_RESTART was set by the caller of this function and
+ * it is no longer set that means that it was cleared by another
+ * thread and hence that a queue rerun is needed.
*
- * blk_mq_run_hw_queue() already checks the STOPPED bit
+ * If TAG_WAITING is set that means that an I/O scheduler has
+ * been configured and another thread is waiting for a driver
+ * tag. To guarantee fairness, do not rerun this hardware queue
+ * but let the other thread grab the driver tag.
*
- * If RESTART or TAG_WAITING is set, then let completion restart
- * the queue instead of potentially looping here.
+ * If no I/O scheduler has been configured it is possible that
+ * the hardware queue got stopped and restarted before requests
+ * were pushed back onto the dispatch list. Rerun the queue to
+ * avoid starvation. Notes:
+ * - blk_mq_run_hw_queue() checks whether or not a queue has
+ * been stopped before rerunning a queue.
+ * - Some but not all block drivers stop a queue before
+ * returning BLK_MQ_RQ_QUEUE_BUSY. Two exceptions are scsi-mq
+ * and dm-rq.
*/
if (!blk_mq_sched_needs_restart(hctx) &&
!test_bit(BLK_MQ_S_TAG_WAITING, &hctx->state))
blk_mq_sched_dispatch_requests(hctx);
rcu_read_unlock();
} else {
+ might_sleep();
+
srcu_idx = srcu_read_lock(&hctx->queue_rq_srcu);
blk_mq_sched_dispatch_requests(hctx);
srcu_read_unlock(&hctx->queue_rq_srcu, srcu_idx);
return hctx->next_cpu;
}
-void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
+static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
+ unsigned long msecs)
{
if (unlikely(blk_mq_hctx_stopped(hctx) ||
!blk_mq_hw_queue_mapped(hctx)))
put_cpu();
}
- kblockd_schedule_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work);
+ kblockd_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
+ &hctx->run_work,
+ msecs_to_jiffies(msecs));
+}
+
+void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
+{
+ __blk_mq_delay_run_hw_queue(hctx, true, msecs);
+}
+EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
+
+void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
+{
+ __blk_mq_delay_run_hw_queue(hctx, async, 0);
}
+EXPORT_SYMBOL(blk_mq_run_hw_queue);
void blk_mq_run_hw_queues(struct request_queue *q, bool async)
{
void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx)
{
- cancel_work(&hctx->run_work);
- cancel_delayed_work(&hctx->delay_work);
+ cancel_delayed_work_sync(&hctx->run_work);
set_bit(BLK_MQ_S_STOPPED, &hctx->state);
}
EXPORT_SYMBOL(blk_mq_stop_hw_queue);
{
struct blk_mq_hw_ctx *hctx;
- hctx = container_of(work, struct blk_mq_hw_ctx, run_work);
+ hctx = container_of(work, struct blk_mq_hw_ctx, run_work.work);
- __blk_mq_run_hw_queue(hctx);
-}
-
-static void blk_mq_delay_work_fn(struct work_struct *work)
-{
- struct blk_mq_hw_ctx *hctx;
+ /*
+ * If we are stopped, don't run the queue. The exception is if
+ * BLK_MQ_S_START_ON_RUN is set. For that case, we auto-clear
+ * the STOPPED bit and run it.
+ */
+ if (test_bit(BLK_MQ_S_STOPPED, &hctx->state)) {
+ if (!test_bit(BLK_MQ_S_START_ON_RUN, &hctx->state))
+ return;
- hctx = container_of(work, struct blk_mq_hw_ctx, delay_work.work);
+ clear_bit(BLK_MQ_S_START_ON_RUN, &hctx->state);
+ clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
+ }
- if (test_and_clear_bit(BLK_MQ_S_STOPPED, &hctx->state))
- __blk_mq_run_hw_queue(hctx);
+ __blk_mq_run_hw_queue(hctx);
}
+
void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
{
if (unlikely(!blk_mq_hw_queue_mapped(hctx)))
return;
+ /*
+ * Stop the hw queue, then modify currently delayed work.
+ * This should prevent us from running the queue prematurely.
+ * Mark the queue as auto-clearing STOPPED when it runs.
+ */
blk_mq_stop_hw_queue(hctx);
- kblockd_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
- &hctx->delay_work, msecs_to_jiffies(msecs));
+ set_bit(BLK_MQ_S_START_ON_RUN, &hctx->state);
+ kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
+ &hctx->run_work,
+ msecs_to_jiffies(msecs));
}
EXPORT_SYMBOL(blk_mq_delay_queue);
static void blk_mq_bio_to_request(struct request *rq, struct bio *bio)
{
- init_request_from_bio(rq, bio);
+ blk_init_request_from_bio(rq, bio);
blk_account_io_start(rq, true);
}
return blk_tag_to_qc_t(rq->internal_tag, hctx->queue_num, true);
}
-static void blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie,
+static void __blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie,
bool may_sleep)
{
struct request_queue *q = rq->q;
struct blk_mq_queue_data bd = {
.rq = rq,
- .list = NULL,
- .last = 1
+ .last = true,
};
struct blk_mq_hw_ctx *hctx;
blk_qc_t new_cookie;
return;
}
- __blk_mq_requeue_request(rq);
-
if (ret == BLK_MQ_RQ_QUEUE_ERROR) {
*cookie = BLK_QC_T_NONE;
- rq->errors = -EIO;
- blk_mq_end_request(rq, rq->errors);
+ blk_mq_end_request(rq, -EIO);
return;
}
+ __blk_mq_requeue_request(rq);
insert:
blk_mq_sched_insert_request(rq, false, true, false, may_sleep);
}
-/*
- * Multiple hardware queue variant. This will not use per-process plugs,
- * but will attempt to bypass the hctx queueing if we can go straight to
- * hardware for SYNC IO.
- */
+static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
+ struct request *rq, blk_qc_t *cookie)
+{
+ if (!(hctx->flags & BLK_MQ_F_BLOCKING)) {
+ rcu_read_lock();
+ __blk_mq_try_issue_directly(rq, cookie, false);
+ rcu_read_unlock();
+ } else {
+ unsigned int srcu_idx;
+
+ might_sleep();
+
+ srcu_idx = srcu_read_lock(&hctx->queue_rq_srcu);
+ __blk_mq_try_issue_directly(rq, cookie, true);
+ srcu_read_unlock(&hctx->queue_rq_srcu, srcu_idx);
+ }
+}
+
static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
{
const int is_sync = op_is_sync(bio->bi_opf);
const int is_flush_fua = op_is_flush(bio->bi_opf);
struct blk_mq_alloc_data data = { .flags = 0 };
struct request *rq;
- unsigned int request_count = 0, srcu_idx;
+ unsigned int request_count = 0;
struct blk_plug *plug;
struct request *same_queue_rq = NULL;
blk_qc_t cookie;
cookie = request_to_qc_t(data.hctx, rq);
- if (unlikely(is_flush_fua)) {
- if (q->elevator)
- goto elv_insert;
- blk_mq_bio_to_request(rq, bio);
- blk_insert_flush(rq);
- goto run_queue;
- }
-
plug = current->plug;
- /*
- * If the driver supports defer issued based on 'last', then
- * queue it up like normal since we can potentially save some
- * CPU this way.
- */
- if (((plug && !blk_queue_nomerges(q)) || is_sync) &&
- !(data.hctx->flags & BLK_MQ_F_DEFER_ISSUE)) {
- struct request *old_rq = NULL;
-
- blk_mq_bio_to_request(rq, bio);
-
- /*
- * We do limited plugging. If the bio can be merged, do that.
- * Otherwise the existing request in the plug list will be
- * issued. So the plug list will have one request at most
- */
- if (plug) {
- /*
- * The plug list might get flushed before this. If that
- * happens, same_queue_rq is invalid and plug list is
- * empty
- */
- if (same_queue_rq && !list_empty(&plug->mq_list)) {
- old_rq = same_queue_rq;
- list_del_init(&old_rq->queuelist);
- }
- list_add_tail(&rq->queuelist, &plug->mq_list);
- } else /* is_sync */
- old_rq = rq;
+ if (unlikely(is_flush_fua)) {
blk_mq_put_ctx(data.ctx);
- if (!old_rq)
- goto done;
-
- if (!(data.hctx->flags & BLK_MQ_F_BLOCKING)) {
- rcu_read_lock();
- blk_mq_try_issue_directly(old_rq, &cookie, false);
- rcu_read_unlock();
+ blk_mq_bio_to_request(rq, bio);
+ if (q->elevator) {
+ blk_mq_sched_insert_request(rq, false, true, true,
+ true);
} else {
- srcu_idx = srcu_read_lock(&data.hctx->queue_rq_srcu);
- blk_mq_try_issue_directly(old_rq, &cookie, true);
- srcu_read_unlock(&data.hctx->queue_rq_srcu, srcu_idx);
+ blk_insert_flush(rq);
+ blk_mq_run_hw_queue(data.hctx, true);
}
- goto done;
- }
-
- if (q->elevator) {
-elv_insert:
- blk_mq_put_ctx(data.ctx);
- blk_mq_bio_to_request(rq, bio);
- blk_mq_sched_insert_request(rq, false, true,
- !is_sync || is_flush_fua, true);
- goto done;
- }
- if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
- /*
- * For a SYNC request, send it to the hardware immediately. For
- * an ASYNC request, just ensure that we run it later on. The
- * latter allows for merging opportunities and more efficient
- * dispatching.
- */
-run_queue:
- blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua);
- }
- blk_mq_put_ctx(data.ctx);
-done:
- return cookie;
-}
-
-/*
- * Single hardware queue variant. This will attempt to use any per-process
- * plug for merging and IO deferral.
- */
-static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
-{
- const int is_sync = op_is_sync(bio->bi_opf);
- const int is_flush_fua = op_is_flush(bio->bi_opf);
- struct blk_plug *plug;
- unsigned int request_count = 0;
- struct blk_mq_alloc_data data = { .flags = 0 };
- struct request *rq;
- blk_qc_t cookie;
- unsigned int wb_acct;
-
- blk_queue_bounce(q, &bio);
-
- if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
- bio_io_error(bio);
- return BLK_QC_T_NONE;
- }
-
- blk_queue_split(q, &bio, q->bio_split);
-
- if (!is_flush_fua && !blk_queue_nomerges(q)) {
- if (blk_attempt_plug_merge(q, bio, &request_count, NULL))
- return BLK_QC_T_NONE;
- } else
- request_count = blk_plug_queued_count(q);
-
- if (blk_mq_sched_bio_merge(q, bio))
- return BLK_QC_T_NONE;
-
- wb_acct = wbt_wait(q->rq_wb, bio, NULL);
-
- trace_block_getrq(q, bio, bio->bi_opf);
-
- rq = blk_mq_sched_get_request(q, bio, bio->bi_opf, &data);
- if (unlikely(!rq)) {
- __wbt_done(q->rq_wb, wb_acct);
- return BLK_QC_T_NONE;
- }
-
- wbt_track(&rq->issue_stat, wb_acct);
-
- cookie = request_to_qc_t(data.hctx, rq);
-
- if (unlikely(is_flush_fua)) {
- if (q->elevator)
- goto elv_insert;
- blk_mq_bio_to_request(rq, bio);
- blk_insert_flush(rq);
- goto run_queue;
- }
-
- /*
- * A task plug currently exists. Since this is completely lockless,
- * utilize that to temporarily store requests until the task is
- * either done or scheduled away.
- */
- plug = current->plug;
- if (plug) {
+ } else if (plug && q->nr_hw_queues == 1) {
struct request *last = NULL;
+ blk_mq_put_ctx(data.ctx);
blk_mq_bio_to_request(rq, bio);
/*
*/
if (list_empty(&plug->mq_list))
request_count = 0;
+ else if (blk_queue_nomerges(q))
+ request_count = blk_plug_queued_count(q);
+
if (!request_count)
trace_block_plug(q);
else
last = list_entry_rq(plug->mq_list.prev);
- blk_mq_put_ctx(data.ctx);
-
if (request_count >= BLK_MAX_REQUEST_COUNT || (last &&
blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) {
blk_flush_plug_list(plug, false);
}
list_add_tail(&rq->queuelist, &plug->mq_list);
- return cookie;
- }
-
- if (q->elevator) {
-elv_insert:
- blk_mq_put_ctx(data.ctx);
+ } else if (plug && !blk_queue_nomerges(q)) {
blk_mq_bio_to_request(rq, bio);
- blk_mq_sched_insert_request(rq, false, true,
- !is_sync || is_flush_fua, true);
- goto done;
- }
- if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
+
/*
- * For a SYNC request, send it to the hardware immediately. For
- * an ASYNC request, just ensure that we run it later on. The
- * latter allows for merging opportunities and more efficient
- * dispatching.
+ * We do limited plugging. If the bio can be merged, do that.
+ * Otherwise the existing request in the plug list will be
+ * issued. So the plug list will have one request at most
+ * The plug list might get flushed before this. If that happens,
+ * the plug list is empty, and same_queue_rq is invalid.
*/
-run_queue:
- blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua);
- }
+ if (list_empty(&plug->mq_list))
+ same_queue_rq = NULL;
+ if (same_queue_rq)
+ list_del_init(&same_queue_rq->queuelist);
+ list_add_tail(&rq->queuelist, &plug->mq_list);
+
+ blk_mq_put_ctx(data.ctx);
+
+ if (same_queue_rq)
+ blk_mq_try_issue_directly(data.hctx, same_queue_rq,
+ &cookie);
+ } else if (q->nr_hw_queues > 1 && is_sync) {
+ blk_mq_put_ctx(data.ctx);
+ blk_mq_bio_to_request(rq, bio);
+ blk_mq_try_issue_directly(data.hctx, rq, &cookie);
+ } else if (q->elevator) {
+ blk_mq_put_ctx(data.ctx);
+ blk_mq_bio_to_request(rq, bio);
+ blk_mq_sched_insert_request(rq, false, true, true, true);
+ } else if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
+ blk_mq_put_ctx(data.ctx);
+ blk_mq_run_hw_queue(data.hctx, true);
+ } else
+ blk_mq_put_ctx(data.ctx);
- blk_mq_put_ctx(data.ctx);
-done:
return cookie;
}
hctx->fq->flush_rq, hctx_idx,
flush_start_tag + hctx_idx);
+ blk_mq_sched_exit_hctx(q, hctx, hctx_idx);
+
if (set->ops->exit_hctx)
set->ops->exit_hctx(hctx, hctx_idx);
if (node == NUMA_NO_NODE)
node = hctx->numa_node = set->numa_node;
- INIT_WORK(&hctx->run_work, blk_mq_run_work_fn);
- INIT_DELAYED_WORK(&hctx->delay_work, blk_mq_delay_work_fn);
+ INIT_DELAYED_WORK(&hctx->run_work, blk_mq_run_work_fn);
spin_lock_init(&hctx->lock);
INIT_LIST_HEAD(&hctx->dispatch);
hctx->queue = q;
set->ops->init_hctx(hctx, set->driver_data, hctx_idx))
goto free_bitmap;
+ if (blk_mq_sched_init_hctx(q, hctx, hctx_idx))
+ goto exit_hctx;
+
hctx->fq = blk_alloc_flush_queue(q, hctx->numa_node, set->cmd_size);
if (!hctx->fq)
- goto exit_hctx;
+ goto sched_exit_hctx;
if (set->ops->init_request &&
set->ops->init_request(set->driver_data,
free_fq:
kfree(hctx->fq);
+ sched_exit_hctx:
+ blk_mq_sched_exit_hctx(q, hctx, hctx_idx);
exit_hctx:
if (set->ops->exit_hctx)
set->ops->exit_hctx(hctx, hctx_idx);
spin_lock_init(&__ctx->lock);
INIT_LIST_HEAD(&__ctx->rq_list);
__ctx->queue = q;
- blk_stat_init(&__ctx->stat[BLK_STAT_READ]);
- blk_stat_init(&__ctx->stat[BLK_STAT_WRITE]);
/* If the cpu isn't online, the cpu is mapped to first hctx */
if (!cpu_online(i))
{
struct request_queue *q;
+ lockdep_assert_held(&set->tag_list_lock);
+
list_for_each_entry(q, &set->tag_list, tag_set_list) {
blk_mq_freeze_queue(q);
queue_set_hctx_shared(q, shared);
struct blk_mq_tag_set *set = q->tag_set;
mutex_lock(&set->tag_list_lock);
- list_del_init(&q->tag_set_list);
+ list_del_rcu(&q->tag_set_list);
+ INIT_LIST_HEAD(&q->tag_set_list);
if (list_is_singular(&set->tag_list)) {
/* just transitioned to unshared */
set->flags &= ~BLK_MQ_F_TAG_SHARED;
blk_mq_update_tag_set_depth(set, false);
}
mutex_unlock(&set->tag_list_lock);
+
+ synchronize_rcu();
}
static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set,
}
if (set->flags & BLK_MQ_F_TAG_SHARED)
queue_set_hctx_shared(q, true);
- list_add_tail(&q->tag_set_list, &set->tag_list);
+ list_add_tail_rcu(&q->tag_set_list, &set->tag_list);
mutex_unlock(&set->tag_list_lock);
}
struct blk_mq_hw_ctx *hctx;
unsigned int i;
- blk_mq_sched_teardown(q);
-
/* hctx kobj stays in hctx */
queue_for_each_hw_ctx(q, hctx, i) {
if (!hctx)
/* mark the queue as mq asap */
q->mq_ops = set->ops;
+ q->poll_cb = blk_stat_alloc_callback(blk_mq_poll_stats_fn,
+ blk_mq_poll_stats_bkt,
+ BLK_MQ_POLL_STATS_BKTS, q);
+ if (!q->poll_cb)
+ goto err_exit;
+
q->queue_ctx = alloc_percpu(struct blk_mq_ctx);
if (!q->queue_ctx)
goto err_exit;
INIT_LIST_HEAD(&q->requeue_list);
spin_lock_init(&q->requeue_lock);
- if (q->nr_hw_queues > 1)
- blk_queue_make_request(q, blk_mq_make_request);
- else
- blk_queue_make_request(q, blk_sq_make_request);
+ blk_queue_make_request(q, blk_mq_make_request);
/*
* Do this after blk_queue_make_request() overrides it...
list_del_init(&q->all_q_node);
mutex_unlock(&all_q_mutex);
- wbt_exit(q);
-
blk_mq_del_queue_tag_set(q);
blk_mq_exit_hw_queues(q, set, set->nr_hw_queues);
* take place in parallel.
*/
list_for_each_entry(q, &all_q_list, all_q_node)
- blk_mq_freeze_queue_start(q);
+ blk_freeze_queue_start(q);
list_for_each_entry(q, &all_q_list, all_q_node)
blk_mq_freeze_queue_wait(q);
return 0;
}
+static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
+{
+ if (set->ops->map_queues)
+ return set->ops->map_queues(set);
+ else
+ return blk_mq_map_queues(set);
+}
+
/*
* Alloc a tag set to be associated with one or more request queues.
* May fail with EINVAL for various error conditions. May adjust the
if (!set->mq_map)
goto out_free_tags;
- if (set->ops->map_queues)
- ret = set->ops->map_queues(set);
- else
- ret = blk_mq_map_queues(set);
+ ret = blk_mq_update_queue_map(set);
if (ret)
goto out_free_mq_map;
{
struct request_queue *q;
+ lockdep_assert_held(&set->tag_list_lock);
+
if (nr_hw_queues > nr_cpu_ids)
nr_hw_queues = nr_cpu_ids;
if (nr_hw_queues < 1 || nr_hw_queues == set->nr_hw_queues)
blk_mq_freeze_queue(q);
set->nr_hw_queues = nr_hw_queues;
+ blk_mq_update_queue_map(set);
list_for_each_entry(q, &set->tag_list, tag_set_list) {
blk_mq_realloc_hw_ctxs(set, q);
-
- /*
- * Manually set the make_request_fn as blk_queue_make_request
- * resets a lot of the queue settings.
- */
- if (q->nr_hw_queues > 1)
- q->make_request_fn = blk_mq_make_request;
- else
- q->make_request_fn = blk_sq_make_request;
-
blk_mq_queue_reinit(q, cpu_online_mask);
}
}
EXPORT_SYMBOL_GPL(blk_mq_update_nr_hw_queues);
+/* Enable polling stats and return whether they were already enabled. */
+static bool blk_poll_stats_enable(struct request_queue *q)
+{
+ if (test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags) ||
+ test_and_set_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags))
+ return true;
+ blk_stat_add_callback(q, q->poll_cb);
+ return false;
+}
+
+static void blk_mq_poll_stats_start(struct request_queue *q)
+{
+ /*
+ * We don't arm the callback if polling stats are not enabled or the
+ * callback is already active.
+ */
+ if (!test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags) ||
+ blk_stat_is_active(q->poll_cb))
+ return;
+
+ blk_stat_activate_msecs(q->poll_cb, 100);
+}
+
+static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb)
+{
+ struct request_queue *q = cb->data;
+ int bucket;
+
+ for (bucket = 0; bucket < BLK_MQ_POLL_STATS_BKTS; bucket++) {
+ if (cb->stat[bucket].nr_samples)
+ q->poll_stat[bucket] = cb->stat[bucket];
+ }
+}
+
static unsigned long blk_mq_poll_nsecs(struct request_queue *q,
struct blk_mq_hw_ctx *hctx,
struct request *rq)
{
- struct blk_rq_stat stat[2];
unsigned long ret = 0;
+ int bucket;
/*
* If stats collection isn't on, don't sleep but turn it on for
* future users
*/
- if (!blk_stat_enable(q))
+ if (!blk_poll_stats_enable(q))
return 0;
/*
- * We don't have to do this once per IO, should optimize this
- * to just use the current window of stats until it changes
- */
- memset(&stat, 0, sizeof(stat));
- blk_hctx_stat_get(hctx, stat);
-
- /*
* As an optimistic guess, use half of the mean service time
* for this type of request. We can (and should) make this smarter.
* For instance, if the completion latencies are tight, we can
* get closer than just half the mean. This is especially
* important on devices where the completion latencies are longer
- * than ~10 usec.
+ * than ~10 usec. We do use the stats for the relevant IO size
+ * if available which does lead to better estimates.
*/
- if (req_op(rq) == REQ_OP_READ && stat[BLK_STAT_READ].nr_samples)
- ret = (stat[BLK_STAT_READ].mean + 1) / 2;
- else if (req_op(rq) == REQ_OP_WRITE && stat[BLK_STAT_WRITE].nr_samples)
- ret = (stat[BLK_STAT_WRITE].mean + 1) / 2;
+ bucket = blk_mq_poll_stats_bkt(rq);
+ if (bucket < 0)
+ return ret;
+
+ if (q->poll_stat[bucket].nr_samples)
+ ret = (q->poll_stat[bucket].mean + 1) / 2;
return ret;
}
hctx = q->queue_hw_ctx[blk_qc_t_to_queue_num(cookie)];
if (!blk_qc_t_is_internal(cookie))
rq = blk_mq_tag_to_rq(hctx->tags, blk_qc_t_to_tag(cookie));
- else
+ else {
rq = blk_mq_tag_to_rq(hctx->sched_tags, blk_qc_t_to_tag(cookie));
+ /*
+ * With scheduling, if the request has completed, we'll
+ * get a NULL return here, as we clear the sched tag when
+ * that happens. The request still remains valid, like always,
+ * so we should be safe with just the NULL check.
+ */
+ if (!rq)
+ return false;
+ }
return __blk_mq_poll(hctx, rq);
}
/* incremented at completion time */
unsigned long ____cacheline_aligned_in_smp rq_completed[2];
- struct blk_rq_stat stat[2];
struct request_queue *queue;
struct kobject kobj;
void blk_mq_free_queue(struct request_queue *q);
int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
void blk_mq_wake_waiters(struct request_queue *q);
-bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *, struct list_head *);
+bool blk_mq_dispatch_rq_list(struct request_queue *, struct list_head *);
void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx);
bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
*/
extern void blk_mq_sysfs_init(struct request_queue *q);
extern void blk_mq_sysfs_deinit(struct request_queue *q);
+extern int __blk_mq_register_dev(struct device *dev, struct request_queue *q);
extern int blk_mq_sysfs_register(struct request_queue *q);
extern void blk_mq_sysfs_unregister(struct request_queue *q);
extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
* debugfs helpers
*/
#ifdef CONFIG_BLK_DEBUG_FS
-int blk_mq_debugfs_register(struct request_queue *q, const char *name);
+int blk_mq_debugfs_register(struct request_queue *q);
void blk_mq_debugfs_unregister(struct request_queue *q);
-int blk_mq_debugfs_register_hctxs(struct request_queue *q);
-void blk_mq_debugfs_unregister_hctxs(struct request_queue *q);
+int blk_mq_debugfs_register_mq(struct request_queue *q);
+void blk_mq_debugfs_unregister_mq(struct request_queue *q);
#else
-static inline int blk_mq_debugfs_register(struct request_queue *q,
- const char *name)
+static inline int blk_mq_debugfs_register(struct request_queue *q)
{
return 0;
}
{
}
-static inline int blk_mq_debugfs_register_hctxs(struct request_queue *q)
+static inline int blk_mq_debugfs_register_mq(struct request_queue *q)
{
return 0;
}
-static inline void blk_mq_debugfs_unregister_hctxs(struct request_queue *q)
+static inline void blk_mq_debugfs_unregister_mq(struct request_queue *q)
{
}
#endif
/* input parameter */
struct request_queue *q;
unsigned int flags;
+ unsigned int shallow_depth;
/* input & output parameter */
struct blk_mq_ctx *ctx;
lim->discard_granularity = 0;
lim->discard_alignment = 0;
lim->discard_misaligned = 0;
- lim->discard_zeroes_data = 0;
lim->logical_block_size = lim->physical_block_size = lim->io_min = 512;
lim->bounce_pfn = (unsigned long)(BLK_BOUNCE_ANY >> PAGE_SHIFT);
lim->alignment_offset = 0;
blk_set_default_limits(lim);
/* Inherit limits from component devices */
- lim->discard_zeroes_data = 1;
lim->max_segments = USHRT_MAX;
lim->max_discard_segments = 1;
lim->max_hw_sectors = UINT_MAX;
t->io_opt = lcm_not_zero(t->io_opt, b->io_opt);
t->cluster &= b->cluster;
- t->discard_zeroes_data &= b->discard_zeroes_data;
/* Physical block size a multiple of the logical block size? */
if (t->physical_block_size & (t->logical_block_size - 1)) {
* Copyright (C) 2016 Jens Axboe
*/
#include <linux/kernel.h>
+#include <linux/rculist.h>
#include <linux/blk-mq.h>
#include "blk-stat.h"
#include "blk-mq.h"
+#include "blk.h"
+
+#define BLK_RQ_STAT_BATCH 64
+
+struct blk_queue_stats {
+ struct list_head callbacks;
+ spinlock_t lock;
+ bool enable_accounting;
+};
+
+static void blk_stat_init(struct blk_rq_stat *stat)
+{
+ stat->min = -1ULL;
+ stat->max = stat->nr_samples = stat->mean = 0;
+ stat->batch = stat->nr_batch = 0;
+}
static void blk_stat_flush_batch(struct blk_rq_stat *stat)
{
dst->nr_samples += src->nr_samples;
}
-static void blk_mq_stat_get(struct request_queue *q, struct blk_rq_stat *dst)
+static void __blk_stat_add(struct blk_rq_stat *stat, u64 value)
{
- struct blk_mq_hw_ctx *hctx;
- struct blk_mq_ctx *ctx;
- uint64_t latest = 0;
- int i, j, nr;
-
- blk_stat_init(&dst[BLK_STAT_READ]);
- blk_stat_init(&dst[BLK_STAT_WRITE]);
-
- nr = 0;
- do {
- uint64_t newest = 0;
-
- queue_for_each_hw_ctx(q, hctx, i) {
- hctx_for_each_ctx(hctx, ctx, j) {
- blk_stat_flush_batch(&ctx->stat[BLK_STAT_READ]);
- blk_stat_flush_batch(&ctx->stat[BLK_STAT_WRITE]);
-
- if (!ctx->stat[BLK_STAT_READ].nr_samples &&
- !ctx->stat[BLK_STAT_WRITE].nr_samples)
- continue;
- if (ctx->stat[BLK_STAT_READ].time > newest)
- newest = ctx->stat[BLK_STAT_READ].time;
- if (ctx->stat[BLK_STAT_WRITE].time > newest)
- newest = ctx->stat[BLK_STAT_WRITE].time;
- }
- }
+ stat->min = min(stat->min, value);
+ stat->max = max(stat->max, value);
- /*
- * No samples
- */
- if (!newest)
- break;
-
- if (newest > latest)
- latest = newest;
-
- queue_for_each_hw_ctx(q, hctx, i) {
- hctx_for_each_ctx(hctx, ctx, j) {
- if (ctx->stat[BLK_STAT_READ].time == newest) {
- blk_stat_sum(&dst[BLK_STAT_READ],
- &ctx->stat[BLK_STAT_READ]);
- nr++;
- }
- if (ctx->stat[BLK_STAT_WRITE].time == newest) {
- blk_stat_sum(&dst[BLK_STAT_WRITE],
- &ctx->stat[BLK_STAT_WRITE]);
- nr++;
- }
- }
- }
- /*
- * If we race on finding an entry, just loop back again.
- * Should be very rare.
- */
- } while (!nr);
+ if (stat->batch + value < stat->batch ||
+ stat->nr_batch + 1 == BLK_RQ_STAT_BATCH)
+ blk_stat_flush_batch(stat);
- dst[BLK_STAT_READ].time = dst[BLK_STAT_WRITE].time = latest;
+ stat->batch += value;
+ stat->nr_batch++;
}
-void blk_queue_stat_get(struct request_queue *q, struct blk_rq_stat *dst)
+void blk_stat_add(struct request *rq)
{
- if (q->mq_ops)
- blk_mq_stat_get(q, dst);
- else {
- blk_stat_flush_batch(&q->rq_stats[BLK_STAT_READ]);
- blk_stat_flush_batch(&q->rq_stats[BLK_STAT_WRITE]);
- memcpy(&dst[BLK_STAT_READ], &q->rq_stats[BLK_STAT_READ],
- sizeof(struct blk_rq_stat));
- memcpy(&dst[BLK_STAT_WRITE], &q->rq_stats[BLK_STAT_WRITE],
- sizeof(struct blk_rq_stat));
+ struct request_queue *q = rq->q;
+ struct blk_stat_callback *cb;
+ struct blk_rq_stat *stat;
+ int bucket;
+ s64 now, value;
+
+ now = __blk_stat_time(ktime_to_ns(ktime_get()));
+ if (now < blk_stat_time(&rq->issue_stat))
+ return;
+
+ value = now - blk_stat_time(&rq->issue_stat);
+
+ blk_throtl_stat_add(rq, value);
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(cb, &q->stats->callbacks, list) {
+ if (blk_stat_is_active(cb)) {
+ bucket = cb->bucket_fn(rq);
+ if (bucket < 0)
+ continue;
+ stat = &this_cpu_ptr(cb->cpu_stat)[bucket];
+ __blk_stat_add(stat, value);
+ }
}
+ rcu_read_unlock();
}
-void blk_hctx_stat_get(struct blk_mq_hw_ctx *hctx, struct blk_rq_stat *dst)
+static void blk_stat_timer_fn(unsigned long data)
{
- struct blk_mq_ctx *ctx;
- unsigned int i, nr;
+ struct blk_stat_callback *cb = (void *)data;
+ unsigned int bucket;
+ int cpu;
- nr = 0;
- do {
- uint64_t newest = 0;
+ for (bucket = 0; bucket < cb->buckets; bucket++)
+ blk_stat_init(&cb->stat[bucket]);
- hctx_for_each_ctx(hctx, ctx, i) {
- blk_stat_flush_batch(&ctx->stat[BLK_STAT_READ]);
- blk_stat_flush_batch(&ctx->stat[BLK_STAT_WRITE]);
+ for_each_online_cpu(cpu) {
+ struct blk_rq_stat *cpu_stat;
- if (!ctx->stat[BLK_STAT_READ].nr_samples &&
- !ctx->stat[BLK_STAT_WRITE].nr_samples)
- continue;
-
- if (ctx->stat[BLK_STAT_READ].time > newest)
- newest = ctx->stat[BLK_STAT_READ].time;
- if (ctx->stat[BLK_STAT_WRITE].time > newest)
- newest = ctx->stat[BLK_STAT_WRITE].time;
+ cpu_stat = per_cpu_ptr(cb->cpu_stat, cpu);
+ for (bucket = 0; bucket < cb->buckets; bucket++) {
+ blk_stat_sum(&cb->stat[bucket], &cpu_stat[bucket]);
+ blk_stat_init(&cpu_stat[bucket]);
}
+ }
- if (!newest)
- break;
-
- hctx_for_each_ctx(hctx, ctx, i) {
- if (ctx->stat[BLK_STAT_READ].time == newest) {
- blk_stat_sum(&dst[BLK_STAT_READ],
- &ctx->stat[BLK_STAT_READ]);
- nr++;
- }
- if (ctx->stat[BLK_STAT_WRITE].time == newest) {
- blk_stat_sum(&dst[BLK_STAT_WRITE],
- &ctx->stat[BLK_STAT_WRITE]);
- nr++;
- }
- }
- /*
- * If we race on finding an entry, just loop back again.
- * Should be very rare, as the window is only updated
- * occasionally
- */
- } while (!nr);
+ cb->timer_fn(cb);
}
-static void __blk_stat_init(struct blk_rq_stat *stat, s64 time_now)
+struct blk_stat_callback *
+blk_stat_alloc_callback(void (*timer_fn)(struct blk_stat_callback *),
+ int (*bucket_fn)(const struct request *),
+ unsigned int buckets, void *data)
{
- stat->min = -1ULL;
- stat->max = stat->nr_samples = stat->mean = 0;
- stat->batch = stat->nr_batch = 0;
- stat->time = time_now & BLK_STAT_NSEC_MASK;
-}
+ struct blk_stat_callback *cb;
-void blk_stat_init(struct blk_rq_stat *stat)
-{
- __blk_stat_init(stat, ktime_to_ns(ktime_get()));
-}
+ cb = kmalloc(sizeof(*cb), GFP_KERNEL);
+ if (!cb)
+ return NULL;
-static bool __blk_stat_is_current(struct blk_rq_stat *stat, s64 now)
-{
- return (now & BLK_STAT_NSEC_MASK) == (stat->time & BLK_STAT_NSEC_MASK);
+ cb->stat = kmalloc_array(buckets, sizeof(struct blk_rq_stat),
+ GFP_KERNEL);
+ if (!cb->stat) {
+ kfree(cb);
+ return NULL;
+ }
+ cb->cpu_stat = __alloc_percpu(buckets * sizeof(struct blk_rq_stat),
+ __alignof__(struct blk_rq_stat));
+ if (!cb->cpu_stat) {
+ kfree(cb->stat);
+ kfree(cb);
+ return NULL;
+ }
+
+ cb->timer_fn = timer_fn;
+ cb->bucket_fn = bucket_fn;
+ cb->data = data;
+ cb->buckets = buckets;
+ setup_timer(&cb->timer, blk_stat_timer_fn, (unsigned long)cb);
+
+ return cb;
}
+EXPORT_SYMBOL_GPL(blk_stat_alloc_callback);
-bool blk_stat_is_current(struct blk_rq_stat *stat)
+void blk_stat_add_callback(struct request_queue *q,
+ struct blk_stat_callback *cb)
{
- return __blk_stat_is_current(stat, ktime_to_ns(ktime_get()));
+ unsigned int bucket;
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct blk_rq_stat *cpu_stat;
+
+ cpu_stat = per_cpu_ptr(cb->cpu_stat, cpu);
+ for (bucket = 0; bucket < cb->buckets; bucket++)
+ blk_stat_init(&cpu_stat[bucket]);
+ }
+
+ spin_lock(&q->stats->lock);
+ list_add_tail_rcu(&cb->list, &q->stats->callbacks);
+ set_bit(QUEUE_FLAG_STATS, &q->queue_flags);
+ spin_unlock(&q->stats->lock);
}
+EXPORT_SYMBOL_GPL(blk_stat_add_callback);
-void blk_stat_add(struct blk_rq_stat *stat, struct request *rq)
+void blk_stat_remove_callback(struct request_queue *q,
+ struct blk_stat_callback *cb)
{
- s64 now, value;
+ spin_lock(&q->stats->lock);
+ list_del_rcu(&cb->list);
+ if (list_empty(&q->stats->callbacks) && !q->stats->enable_accounting)
+ clear_bit(QUEUE_FLAG_STATS, &q->queue_flags);
+ spin_unlock(&q->stats->lock);
- now = __blk_stat_time(ktime_to_ns(ktime_get()));
- if (now < blk_stat_time(&rq->issue_stat))
- return;
-
- if (!__blk_stat_is_current(stat, now))
- __blk_stat_init(stat, now);
+ del_timer_sync(&cb->timer);
+}
+EXPORT_SYMBOL_GPL(blk_stat_remove_callback);
- value = now - blk_stat_time(&rq->issue_stat);
- if (value > stat->max)
- stat->max = value;
- if (value < stat->min)
- stat->min = value;
+static void blk_stat_free_callback_rcu(struct rcu_head *head)
+{
+ struct blk_stat_callback *cb;
- if (stat->batch + value < stat->batch ||
- stat->nr_batch + 1 == BLK_RQ_STAT_BATCH)
- blk_stat_flush_batch(stat);
+ cb = container_of(head, struct blk_stat_callback, rcu);
+ free_percpu(cb->cpu_stat);
+ kfree(cb->stat);
+ kfree(cb);
+}
- stat->batch += value;
- stat->nr_batch++;
+void blk_stat_free_callback(struct blk_stat_callback *cb)
+{
+ if (cb)
+ call_rcu(&cb->rcu, blk_stat_free_callback_rcu);
}
+EXPORT_SYMBOL_GPL(blk_stat_free_callback);
-void blk_stat_clear(struct request_queue *q)
+void blk_stat_enable_accounting(struct request_queue *q)
{
- if (q->mq_ops) {
- struct blk_mq_hw_ctx *hctx;
- struct blk_mq_ctx *ctx;
- int i, j;
-
- queue_for_each_hw_ctx(q, hctx, i) {
- hctx_for_each_ctx(hctx, ctx, j) {
- blk_stat_init(&ctx->stat[BLK_STAT_READ]);
- blk_stat_init(&ctx->stat[BLK_STAT_WRITE]);
- }
- }
- } else {
- blk_stat_init(&q->rq_stats[BLK_STAT_READ]);
- blk_stat_init(&q->rq_stats[BLK_STAT_WRITE]);
- }
+ spin_lock(&q->stats->lock);
+ q->stats->enable_accounting = true;
+ set_bit(QUEUE_FLAG_STATS, &q->queue_flags);
+ spin_unlock(&q->stats->lock);
}
-void blk_stat_set_issue_time(struct blk_issue_stat *stat)
+struct blk_queue_stats *blk_alloc_queue_stats(void)
{
- stat->time = (stat->time & BLK_STAT_MASK) |
- (ktime_to_ns(ktime_get()) & BLK_STAT_TIME_MASK);
+ struct blk_queue_stats *stats;
+
+ stats = kmalloc(sizeof(*stats), GFP_KERNEL);
+ if (!stats)
+ return NULL;
+
+ INIT_LIST_HEAD(&stats->callbacks);
+ spin_lock_init(&stats->lock);
+ stats->enable_accounting = false;
+
+ return stats;
}
-/*
- * Enable stat tracking, return whether it was enabled
- */
-bool blk_stat_enable(struct request_queue *q)
+void blk_free_queue_stats(struct blk_queue_stats *stats)
{
- if (!test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
- set_bit(QUEUE_FLAG_STATS, &q->queue_flags);
- return false;
- }
+ if (!stats)
+ return;
+
+ WARN_ON(!list_empty(&stats->callbacks));
- return true;
+ kfree(stats);
}
#ifndef BLK_STAT_H
#define BLK_STAT_H
-/*
- * ~0.13s window as a power-of-2 (2^27 nsecs)
- */
-#define BLK_STAT_NSEC 134217728ULL
-#define BLK_STAT_NSEC_MASK ~(BLK_STAT_NSEC - 1)
+#include <linux/kernel.h>
+#include <linux/blkdev.h>
+#include <linux/ktime.h>
+#include <linux/rcupdate.h>
+#include <linux/timer.h>
/*
- * Upper 3 bits can be used elsewhere
+ * from upper:
+ * 3 bits: reserved for other usage
+ * 12 bits: size
+ * 49 bits: time
*/
#define BLK_STAT_RES_BITS 3
-#define BLK_STAT_SHIFT (64 - BLK_STAT_RES_BITS)
-#define BLK_STAT_TIME_MASK ((1ULL << BLK_STAT_SHIFT) - 1)
-#define BLK_STAT_MASK ~BLK_STAT_TIME_MASK
+#define BLK_STAT_SIZE_BITS 12
+#define BLK_STAT_RES_SHIFT (64 - BLK_STAT_RES_BITS)
+#define BLK_STAT_SIZE_SHIFT (BLK_STAT_RES_SHIFT - BLK_STAT_SIZE_BITS)
+#define BLK_STAT_TIME_MASK ((1ULL << BLK_STAT_SIZE_SHIFT) - 1)
+#define BLK_STAT_SIZE_MASK \
+ (((1ULL << BLK_STAT_SIZE_BITS) - 1) << BLK_STAT_SIZE_SHIFT)
+#define BLK_STAT_RES_MASK (~((1ULL << BLK_STAT_RES_SHIFT) - 1))
+
+/**
+ * struct blk_stat_callback - Block statistics callback.
+ *
+ * A &struct blk_stat_callback is associated with a &struct request_queue. While
+ * @timer is active, that queue's request completion latencies are sorted into
+ * buckets by @bucket_fn and added to a per-cpu buffer, @cpu_stat. When the
+ * timer fires, @cpu_stat is flushed to @stat and @timer_fn is invoked.
+ */
+struct blk_stat_callback {
+ /*
+ * @list: RCU list of callbacks for a &struct request_queue.
+ */
+ struct list_head list;
+
+ /**
+ * @timer: Timer for the next callback invocation.
+ */
+ struct timer_list timer;
+
+ /**
+ * @cpu_stat: Per-cpu statistics buckets.
+ */
+ struct blk_rq_stat __percpu *cpu_stat;
+
+ /**
+ * @bucket_fn: Given a request, returns which statistics bucket it
+ * should be accounted under. Return -1 for no bucket for this
+ * request.
+ */
+ int (*bucket_fn)(const struct request *);
+
+ /**
+ * @buckets: Number of statistics buckets.
+ */
+ unsigned int buckets;
+
+ /**
+ * @stat: Array of statistics buckets.
+ */
+ struct blk_rq_stat *stat;
+
+ /**
+ * @fn: Callback function.
+ */
+ void (*timer_fn)(struct blk_stat_callback *);
+
+ /**
+ * @data: Private pointer for the user.
+ */
+ void *data;
-enum {
- BLK_STAT_READ = 0,
- BLK_STAT_WRITE,
+ struct rcu_head rcu;
};
-void blk_stat_add(struct blk_rq_stat *, struct request *);
-void blk_hctx_stat_get(struct blk_mq_hw_ctx *, struct blk_rq_stat *);
-void blk_queue_stat_get(struct request_queue *, struct blk_rq_stat *);
-void blk_stat_clear(struct request_queue *);
-void blk_stat_init(struct blk_rq_stat *);
-bool blk_stat_is_current(struct blk_rq_stat *);
-void blk_stat_set_issue_time(struct blk_issue_stat *);
-bool blk_stat_enable(struct request_queue *);
+struct blk_queue_stats *blk_alloc_queue_stats(void);
+void blk_free_queue_stats(struct blk_queue_stats *);
+
+void blk_stat_add(struct request *);
static inline u64 __blk_stat_time(u64 time)
{
static inline u64 blk_stat_time(struct blk_issue_stat *stat)
{
- return __blk_stat_time(stat->time);
+ return __blk_stat_time(stat->stat);
+}
+
+static inline sector_t blk_capped_size(sector_t size)
+{
+ return size & ((1ULL << BLK_STAT_SIZE_BITS) - 1);
+}
+
+static inline sector_t blk_stat_size(struct blk_issue_stat *stat)
+{
+ return (stat->stat & BLK_STAT_SIZE_MASK) >> BLK_STAT_SIZE_SHIFT;
+}
+
+static inline void blk_stat_set_issue(struct blk_issue_stat *stat,
+ sector_t size)
+{
+ stat->stat = (stat->stat & BLK_STAT_RES_MASK) |
+ (ktime_to_ns(ktime_get()) & BLK_STAT_TIME_MASK) |
+ (((u64)blk_capped_size(size)) << BLK_STAT_SIZE_SHIFT);
+}
+
+/* record time/size info in request but not add a callback */
+void blk_stat_enable_accounting(struct request_queue *q);
+
+/**
+ * blk_stat_alloc_callback() - Allocate a block statistics callback.
+ * @timer_fn: Timer callback function.
+ * @bucket_fn: Bucket callback function.
+ * @buckets: Number of statistics buckets.
+ * @data: Value for the @data field of the &struct blk_stat_callback.
+ *
+ * See &struct blk_stat_callback for details on the callback functions.
+ *
+ * Return: &struct blk_stat_callback on success or NULL on ENOMEM.
+ */
+struct blk_stat_callback *
+blk_stat_alloc_callback(void (*timer_fn)(struct blk_stat_callback *),
+ int (*bucket_fn)(const struct request *),
+ unsigned int buckets, void *data);
+
+/**
+ * blk_stat_add_callback() - Add a block statistics callback to be run on a
+ * request queue.
+ * @q: The request queue.
+ * @cb: The callback.
+ *
+ * Note that a single &struct blk_stat_callback can only be added to a single
+ * &struct request_queue.
+ */
+void blk_stat_add_callback(struct request_queue *q,
+ struct blk_stat_callback *cb);
+
+/**
+ * blk_stat_remove_callback() - Remove a block statistics callback from a
+ * request queue.
+ * @q: The request queue.
+ * @cb: The callback.
+ *
+ * When this returns, the callback is not running on any CPUs and will not be
+ * called again unless readded.
+ */
+void blk_stat_remove_callback(struct request_queue *q,
+ struct blk_stat_callback *cb);
+
+/**
+ * blk_stat_free_callback() - Free a block statistics callback.
+ * @cb: The callback.
+ *
+ * @cb may be NULL, in which case this does nothing. If it is not NULL, @cb must
+ * not be associated with a request queue. I.e., if it was previously added with
+ * blk_stat_add_callback(), it must also have been removed since then with
+ * blk_stat_remove_callback().
+ */
+void blk_stat_free_callback(struct blk_stat_callback *cb);
+
+/**
+ * blk_stat_is_active() - Check if a block statistics callback is currently
+ * gathering statistics.
+ * @cb: The callback.
+ */
+static inline bool blk_stat_is_active(struct blk_stat_callback *cb)
+{
+ return timer_pending(&cb->timer);
+}
+
+/**
+ * blk_stat_activate_nsecs() - Gather block statistics during a time window in
+ * nanoseconds.
+ * @cb: The callback.
+ * @nsecs: Number of nanoseconds to gather statistics for.
+ *
+ * The timer callback will be called when the window expires.
+ */
+static inline void blk_stat_activate_nsecs(struct blk_stat_callback *cb,
+ u64 nsecs)
+{
+ mod_timer(&cb->timer, jiffies + nsecs_to_jiffies(nsecs));
+}
+
+/**
+ * blk_stat_activate_msecs() - Gather block statistics during a time window in
+ * milliseconds.
+ * @cb: The callback.
+ * @msecs: Number of milliseconds to gather statistics for.
+ *
+ * The timer callback will be called when the window expires.
+ */
+static inline void blk_stat_activate_msecs(struct blk_stat_callback *cb,
+ unsigned int msecs)
+{
+ mod_timer(&cb->timer, jiffies + msecs_to_jiffies(msecs));
}
#endif
static ssize_t queue_discard_zeroes_data_show(struct request_queue *q, char *page)
{
- return queue_var_show(queue_discard_zeroes_data(q), page);
+ return queue_var_show(0, page);
}
static ssize_t queue_write_same_max_show(struct request_queue *q, char *page)
return queue_var_show(blk_queue_dax(q), page);
}
-static ssize_t print_stat(char *page, struct blk_rq_stat *stat, const char *pre)
-{
- return sprintf(page, "%s samples=%llu, mean=%lld, min=%lld, max=%lld\n",
- pre, (long long) stat->nr_samples,
- (long long) stat->mean, (long long) stat->min,
- (long long) stat->max);
-}
-
-static ssize_t queue_stats_show(struct request_queue *q, char *page)
-{
- struct blk_rq_stat stat[2];
- ssize_t ret;
-
- blk_queue_stat_get(q, stat);
-
- ret = print_stat(page, &stat[BLK_STAT_READ], "read :");
- ret += print_stat(page + ret, &stat[BLK_STAT_WRITE], "write:");
- return ret;
-}
-
static struct queue_sysfs_entry queue_requests_entry = {
.attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR },
.show = queue_requests_show,
.show = queue_dax_show,
};
-static struct queue_sysfs_entry queue_stats_entry = {
- .attr = {.name = "stats", .mode = S_IRUGO },
- .show = queue_stats_show,
-};
-
static struct queue_sysfs_entry queue_wb_lat_entry = {
.attr = {.name = "wbt_lat_usec", .mode = S_IRUGO | S_IWUSR },
.show = queue_wb_lat_show,
.store = queue_wb_lat_store,
};
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+static struct queue_sysfs_entry throtl_sample_time_entry = {
+ .attr = {.name = "throttle_sample_time", .mode = S_IRUGO | S_IWUSR },
+ .show = blk_throtl_sample_time_show,
+ .store = blk_throtl_sample_time_store,
+};
+#endif
+
static struct attribute *default_attrs[] = {
&queue_requests_entry.attr,
&queue_ra_entry.attr,
&queue_poll_entry.attr,
&queue_wc_entry.attr,
&queue_dax_entry.attr,
- &queue_stats_entry.attr,
&queue_wb_lat_entry.attr,
&queue_poll_delay_entry.attr,
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+ &throtl_sample_time_entry.attr,
+#endif
NULL,
};
struct request_queue *q =
container_of(kobj, struct request_queue, kobj);
- wbt_exit(q);
+ if (test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags))
+ blk_stat_remove_callback(q, q->poll_cb);
+ blk_stat_free_callback(q->poll_cb);
bdi_put(q->backing_dev_info);
blkcg_exit_queue(q);
if (q->elevator) {
ioc_clear_queue(q);
- elevator_exit(q->elevator);
+ elevator_exit(q, q->elevator);
}
+ blk_free_queue_stats(q->stats);
+
blk_exit_rl(&q->root_rl);
if (q->queue_tags)
.release = blk_release_queue,
};
-static void blk_wb_init(struct request_queue *q)
-{
-#ifndef CONFIG_BLK_WBT_MQ
- if (q->mq_ops)
- return;
-#endif
-#ifndef CONFIG_BLK_WBT_SQ
- if (q->request_fn)
- return;
-#endif
-
- /*
- * If this fails, we don't get throttling
- */
- wbt_init(q);
-}
-
int blk_register_queue(struct gendisk *disk)
{
int ret;
if (WARN_ON(!q))
return -ENXIO;
+ WARN_ONCE(test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags),
+ "%s is registering an already registered queue\n",
+ kobject_name(&dev->kobj));
+ queue_flag_set_unlocked(QUEUE_FLAG_REGISTERED, q);
+
/*
* SCSI probing may synchronously create and destroy a lot of
* request_queues for non-existent devices. Shutting down a fully
if (ret)
return ret;
- if (q->mq_ops)
- blk_mq_register_dev(dev, q);
-
/* Prevent changes through sysfs until registration is completed. */
mutex_lock(&q->sysfs_lock);
goto unlock;
}
+ if (q->mq_ops)
+ __blk_mq_register_dev(dev, q);
+
kobject_uevent(&q->kobj, KOBJ_ADD);
- blk_wb_init(q);
+ wbt_enable_default(q);
+
+ blk_throtl_register_queue(q);
if (q->request_fn || (q->mq_ops && q->elevator)) {
ret = elv_register_queue(q);
if (WARN_ON(!q))
return;
+ queue_flag_clear_unlocked(QUEUE_FLAG_REGISTERED, q);
+
+ wbt_exit(q);
+
+
if (q->mq_ops)
blk_mq_unregister_dev(disk_to_dev(disk), q);
/* Total max dispatch from all groups in one round */
static int throtl_quantum = 32;
-/* Throttling is performed over 100ms slice and after that slice is renewed */
-static unsigned long throtl_slice = HZ/10; /* 100 ms */
+/* Throttling is performed over a slice and after that slice is renewed */
+#define DFL_THROTL_SLICE_HD (HZ / 10)
+#define DFL_THROTL_SLICE_SSD (HZ / 50)
+#define MAX_THROTL_SLICE (HZ)
+#define DFL_IDLE_THRESHOLD_SSD (1000L) /* 1 ms */
+#define DFL_IDLE_THRESHOLD_HD (100L * 1000) /* 100 ms */
+#define MAX_IDLE_TIME (5L * 1000 * 1000) /* 5 s */
+/* default latency target is 0, eg, guarantee IO latency by default */
+#define DFL_LATENCY_TARGET (0)
+
+#define SKIP_LATENCY (((u64)1) << BLK_STAT_RES_SHIFT)
static struct blkcg_policy blkcg_policy_throtl;
#define rb_entry_tg(node) rb_entry((node), struct throtl_grp, rb_node)
+enum {
+ LIMIT_LOW,
+ LIMIT_MAX,
+ LIMIT_CNT,
+};
+
struct throtl_grp {
/* must be the first member */
struct blkg_policy_data pd;
/* are there any throtl rules between this group and td? */
bool has_rules[2];
- /* bytes per second rate limits */
- uint64_t bps[2];
+ /* internally used bytes per second rate limits */
+ uint64_t bps[2][LIMIT_CNT];
+ /* user configured bps limits */
+ uint64_t bps_conf[2][LIMIT_CNT];
- /* IOPS limits */
- unsigned int iops[2];
+ /* internally used IOPS limits */
+ unsigned int iops[2][LIMIT_CNT];
+ /* user configured IOPS limits */
+ unsigned int iops_conf[2][LIMIT_CNT];
/* Number of bytes disptached in current slice */
uint64_t bytes_disp[2];
/* Number of bio's dispatched in current slice */
unsigned int io_disp[2];
+ unsigned long last_low_overflow_time[2];
+
+ uint64_t last_bytes_disp[2];
+ unsigned int last_io_disp[2];
+
+ unsigned long last_check_time;
+
+ unsigned long latency_target; /* us */
/* When did we start a new slice */
unsigned long slice_start[2];
unsigned long slice_end[2];
+
+ unsigned long last_finish_time; /* ns / 1024 */
+ unsigned long checked_last_finish_time; /* ns / 1024 */
+ unsigned long avg_idletime; /* ns / 1024 */
+ unsigned long idletime_threshold; /* us */
+
+ unsigned int bio_cnt; /* total bios */
+ unsigned int bad_bio_cnt; /* bios exceeding latency threshold */
+ unsigned long bio_cnt_reset_time;
+};
+
+/* We measure latency for request size from <= 4k to >= 1M */
+#define LATENCY_BUCKET_SIZE 9
+
+struct latency_bucket {
+ unsigned long total_latency; /* ns / 1024 */
+ int samples;
+};
+
+struct avg_latency_bucket {
+ unsigned long latency; /* ns / 1024 */
+ bool valid;
};
struct throtl_data
/* Total Number of queued bios on READ and WRITE lists */
unsigned int nr_queued[2];
+ unsigned int throtl_slice;
+
/* Work for dispatching throttled bios */
struct work_struct dispatch_work;
+ unsigned int limit_index;
+ bool limit_valid[LIMIT_CNT];
+
+ unsigned long dft_idletime_threshold; /* us */
+
+ unsigned long low_upgrade_time;
+ unsigned long low_downgrade_time;
+
+ unsigned int scale;
+
+ struct latency_bucket tmp_buckets[LATENCY_BUCKET_SIZE];
+ struct avg_latency_bucket avg_buckets[LATENCY_BUCKET_SIZE];
+ struct latency_bucket __percpu *latency_buckets;
+ unsigned long last_calculate_time;
+
+ bool track_bio_latency;
};
static void throtl_pending_timer_fn(unsigned long arg);
return container_of(sq, struct throtl_data, service_queue);
}
+/*
+ * cgroup's limit in LIMIT_MAX is scaled if low limit is set. This scale is to
+ * make the IO dispatch more smooth.
+ * Scale up: linearly scale up according to lapsed time since upgrade. For
+ * every throtl_slice, the limit scales up 1/2 .low limit till the
+ * limit hits .max limit
+ * Scale down: exponentially scale down if a cgroup doesn't hit its .low limit
+ */
+static uint64_t throtl_adjusted_limit(uint64_t low, struct throtl_data *td)
+{
+ /* arbitrary value to avoid too big scale */
+ if (td->scale < 4096 && time_after_eq(jiffies,
+ td->low_upgrade_time + td->scale * td->throtl_slice))
+ td->scale = (jiffies - td->low_upgrade_time) / td->throtl_slice;
+
+ return low + (low >> 1) * td->scale;
+}
+
+static uint64_t tg_bps_limit(struct throtl_grp *tg, int rw)
+{
+ struct blkcg_gq *blkg = tg_to_blkg(tg);
+ struct throtl_data *td;
+ uint64_t ret;
+
+ if (cgroup_subsys_on_dfl(io_cgrp_subsys) && !blkg->parent)
+ return U64_MAX;
+
+ td = tg->td;
+ ret = tg->bps[rw][td->limit_index];
+ if (ret == 0 && td->limit_index == LIMIT_LOW)
+ return tg->bps[rw][LIMIT_MAX];
+
+ if (td->limit_index == LIMIT_MAX && tg->bps[rw][LIMIT_LOW] &&
+ tg->bps[rw][LIMIT_LOW] != tg->bps[rw][LIMIT_MAX]) {
+ uint64_t adjusted;
+
+ adjusted = throtl_adjusted_limit(tg->bps[rw][LIMIT_LOW], td);
+ ret = min(tg->bps[rw][LIMIT_MAX], adjusted);
+ }
+ return ret;
+}
+
+static unsigned int tg_iops_limit(struct throtl_grp *tg, int rw)
+{
+ struct blkcg_gq *blkg = tg_to_blkg(tg);
+ struct throtl_data *td;
+ unsigned int ret;
+
+ if (cgroup_subsys_on_dfl(io_cgrp_subsys) && !blkg->parent)
+ return UINT_MAX;
+ td = tg->td;
+ ret = tg->iops[rw][td->limit_index];
+ if (ret == 0 && tg->td->limit_index == LIMIT_LOW)
+ return tg->iops[rw][LIMIT_MAX];
+
+ if (td->limit_index == LIMIT_MAX && tg->iops[rw][LIMIT_LOW] &&
+ tg->iops[rw][LIMIT_LOW] != tg->iops[rw][LIMIT_MAX]) {
+ uint64_t adjusted;
+
+ adjusted = throtl_adjusted_limit(tg->iops[rw][LIMIT_LOW], td);
+ if (adjusted > UINT_MAX)
+ adjusted = UINT_MAX;
+ ret = min_t(unsigned int, tg->iops[rw][LIMIT_MAX], adjusted);
+ }
+ return ret;
+}
+
+#define request_bucket_index(sectors) \
+ clamp_t(int, order_base_2(sectors) - 3, 0, LATENCY_BUCKET_SIZE - 1)
+
/**
* throtl_log - log debug message via blktrace
* @sq: the service_queue being reported
}
RB_CLEAR_NODE(&tg->rb_node);
- tg->bps[READ] = -1;
- tg->bps[WRITE] = -1;
- tg->iops[READ] = -1;
- tg->iops[WRITE] = -1;
+ tg->bps[READ][LIMIT_MAX] = U64_MAX;
+ tg->bps[WRITE][LIMIT_MAX] = U64_MAX;
+ tg->iops[READ][LIMIT_MAX] = UINT_MAX;
+ tg->iops[WRITE][LIMIT_MAX] = UINT_MAX;
+ tg->bps_conf[READ][LIMIT_MAX] = U64_MAX;
+ tg->bps_conf[WRITE][LIMIT_MAX] = U64_MAX;
+ tg->iops_conf[READ][LIMIT_MAX] = UINT_MAX;
+ tg->iops_conf[WRITE][LIMIT_MAX] = UINT_MAX;
+ /* LIMIT_LOW will have default value 0 */
+
+ tg->latency_target = DFL_LATENCY_TARGET;
return &tg->pd;
}
if (cgroup_subsys_on_dfl(io_cgrp_subsys) && blkg->parent)
sq->parent_sq = &blkg_to_tg(blkg->parent)->service_queue;
tg->td = td;
+
+ tg->idletime_threshold = td->dft_idletime_threshold;
}
/*
static void tg_update_has_rules(struct throtl_grp *tg)
{
struct throtl_grp *parent_tg = sq_to_tg(tg->service_queue.parent_sq);
+ struct throtl_data *td = tg->td;
int rw;
for (rw = READ; rw <= WRITE; rw++)
tg->has_rules[rw] = (parent_tg && parent_tg->has_rules[rw]) ||
- (tg->bps[rw] != -1 || tg->iops[rw] != -1);
+ (td->limit_valid[td->limit_index] &&
+ (tg_bps_limit(tg, rw) != U64_MAX ||
+ tg_iops_limit(tg, rw) != UINT_MAX));
}
static void throtl_pd_online(struct blkg_policy_data *pd)
{
+ struct throtl_grp *tg = pd_to_tg(pd);
/*
* We don't want new groups to escape the limits of its ancestors.
* Update has_rules[] after a new group is brought online.
*/
- tg_update_has_rules(pd_to_tg(pd));
+ tg_update_has_rules(tg);
+}
+
+static void blk_throtl_update_limit_valid(struct throtl_data *td)
+{
+ struct cgroup_subsys_state *pos_css;
+ struct blkcg_gq *blkg;
+ bool low_valid = false;
+
+ rcu_read_lock();
+ blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
+ struct throtl_grp *tg = blkg_to_tg(blkg);
+
+ if (tg->bps[READ][LIMIT_LOW] || tg->bps[WRITE][LIMIT_LOW] ||
+ tg->iops[READ][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW])
+ low_valid = true;
+ }
+ rcu_read_unlock();
+
+ td->limit_valid[LIMIT_LOW] = low_valid;
+}
+
+static void throtl_upgrade_state(struct throtl_data *td);
+static void throtl_pd_offline(struct blkg_policy_data *pd)
+{
+ struct throtl_grp *tg = pd_to_tg(pd);
+
+ tg->bps[READ][LIMIT_LOW] = 0;
+ tg->bps[WRITE][LIMIT_LOW] = 0;
+ tg->iops[READ][LIMIT_LOW] = 0;
+ tg->iops[WRITE][LIMIT_LOW] = 0;
+
+ blk_throtl_update_limit_valid(tg->td);
+
+ if (!tg->td->limit_valid[tg->td->limit_index])
+ throtl_upgrade_state(tg->td);
}
static void throtl_pd_free(struct blkg_policy_data *pd)
static void throtl_schedule_pending_timer(struct throtl_service_queue *sq,
unsigned long expires)
{
+ unsigned long max_expire = jiffies + 8 * sq_to_tg(sq)->td->throtl_slice;
+
+ /*
+ * Since we are adjusting the throttle limit dynamically, the sleep
+ * time calculated according to previous limit might be invalid. It's
+ * possible the cgroup sleep time is very long and no other cgroups
+ * have IO running so notify the limit changes. Make sure the cgroup
+ * doesn't sleep too long to avoid the missed notification.
+ */
+ if (time_after(expires, max_expire))
+ expires = max_expire;
mod_timer(&sq->pending_timer, expires);
throtl_log(sq, "schedule timer. delay=%lu jiffies=%lu",
expires - jiffies, jiffies);
if (time_after_eq(start, tg->slice_start[rw]))
tg->slice_start[rw] = start;
- tg->slice_end[rw] = jiffies + throtl_slice;
+ tg->slice_end[rw] = jiffies + tg->td->throtl_slice;
throtl_log(&tg->service_queue,
"[%c] new slice with credit start=%lu end=%lu jiffies=%lu",
rw == READ ? 'R' : 'W', tg->slice_start[rw],
tg->bytes_disp[rw] = 0;
tg->io_disp[rw] = 0;
tg->slice_start[rw] = jiffies;
- tg->slice_end[rw] = jiffies + throtl_slice;
+ tg->slice_end[rw] = jiffies + tg->td->throtl_slice;
throtl_log(&tg->service_queue,
"[%c] new slice start=%lu end=%lu jiffies=%lu",
rw == READ ? 'R' : 'W', tg->slice_start[rw],
static inline void throtl_set_slice_end(struct throtl_grp *tg, bool rw,
unsigned long jiffy_end)
{
- tg->slice_end[rw] = roundup(jiffy_end, throtl_slice);
+ tg->slice_end[rw] = roundup(jiffy_end, tg->td->throtl_slice);
}
static inline void throtl_extend_slice(struct throtl_grp *tg, bool rw,
unsigned long jiffy_end)
{
- tg->slice_end[rw] = roundup(jiffy_end, throtl_slice);
+ tg->slice_end[rw] = roundup(jiffy_end, tg->td->throtl_slice);
throtl_log(&tg->service_queue,
"[%c] extend slice start=%lu end=%lu jiffies=%lu",
rw == READ ? 'R' : 'W', tg->slice_start[rw],
* is bad because it does not allow new slice to start.
*/
- throtl_set_slice_end(tg, rw, jiffies + throtl_slice);
+ throtl_set_slice_end(tg, rw, jiffies + tg->td->throtl_slice);
time_elapsed = jiffies - tg->slice_start[rw];
- nr_slices = time_elapsed / throtl_slice;
+ nr_slices = time_elapsed / tg->td->throtl_slice;
if (!nr_slices)
return;
- tmp = tg->bps[rw] * throtl_slice * nr_slices;
+ tmp = tg_bps_limit(tg, rw) * tg->td->throtl_slice * nr_slices;
do_div(tmp, HZ);
bytes_trim = tmp;
- io_trim = (tg->iops[rw] * throtl_slice * nr_slices)/HZ;
+ io_trim = (tg_iops_limit(tg, rw) * tg->td->throtl_slice * nr_slices) /
+ HZ;
if (!bytes_trim && !io_trim)
return;
else
tg->io_disp[rw] = 0;
- tg->slice_start[rw] += nr_slices * throtl_slice;
+ tg->slice_start[rw] += nr_slices * tg->td->throtl_slice;
throtl_log(&tg->service_queue,
"[%c] trim slice nr=%lu bytes=%llu io=%lu start=%lu end=%lu jiffies=%lu",
/* Slice has just started. Consider one slice interval */
if (!jiffy_elapsed)
- jiffy_elapsed_rnd = throtl_slice;
+ jiffy_elapsed_rnd = tg->td->throtl_slice;
- jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, throtl_slice);
+ jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, tg->td->throtl_slice);
/*
* jiffy_elapsed_rnd should not be a big value as minimum iops can be
* have been trimmed.
*/
- tmp = (u64)tg->iops[rw] * jiffy_elapsed_rnd;
+ tmp = (u64)tg_iops_limit(tg, rw) * jiffy_elapsed_rnd;
do_div(tmp, HZ);
if (tmp > UINT_MAX)
}
/* Calc approx time to dispatch */
- jiffy_wait = ((tg->io_disp[rw] + 1) * HZ)/tg->iops[rw] + 1;
+ jiffy_wait = ((tg->io_disp[rw] + 1) * HZ) / tg_iops_limit(tg, rw) + 1;
if (jiffy_wait > jiffy_elapsed)
jiffy_wait = jiffy_wait - jiffy_elapsed;
/* Slice has just started. Consider one slice interval */
if (!jiffy_elapsed)
- jiffy_elapsed_rnd = throtl_slice;
+ jiffy_elapsed_rnd = tg->td->throtl_slice;
- jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, throtl_slice);
+ jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, tg->td->throtl_slice);
- tmp = tg->bps[rw] * jiffy_elapsed_rnd;
+ tmp = tg_bps_limit(tg, rw) * jiffy_elapsed_rnd;
do_div(tmp, HZ);
bytes_allowed = tmp;
/* Calc approx time to dispatch */
extra_bytes = tg->bytes_disp[rw] + bio->bi_iter.bi_size - bytes_allowed;
- jiffy_wait = div64_u64(extra_bytes * HZ, tg->bps[rw]);
+ jiffy_wait = div64_u64(extra_bytes * HZ, tg_bps_limit(tg, rw));
if (!jiffy_wait)
jiffy_wait = 1;
bio != throtl_peek_queued(&tg->service_queue.queued[rw]));
/* If tg->bps = -1, then BW is unlimited */
- if (tg->bps[rw] == -1 && tg->iops[rw] == -1) {
+ if (tg_bps_limit(tg, rw) == U64_MAX &&
+ tg_iops_limit(tg, rw) == UINT_MAX) {
if (wait)
*wait = 0;
return true;
if (throtl_slice_used(tg, rw) && !(tg->service_queue.nr_queued[rw]))
throtl_start_new_slice(tg, rw);
else {
- if (time_before(tg->slice_end[rw], jiffies + throtl_slice))
- throtl_extend_slice(tg, rw, jiffies + throtl_slice);
+ if (time_before(tg->slice_end[rw],
+ jiffies + tg->td->throtl_slice))
+ throtl_extend_slice(tg, rw,
+ jiffies + tg->td->throtl_slice);
}
if (tg_with_in_bps_limit(tg, bio, &bps_wait) &&
/* Charge the bio to the group */
tg->bytes_disp[rw] += bio->bi_iter.bi_size;
tg->io_disp[rw]++;
+ tg->last_bytes_disp[rw] += bio->bi_iter.bi_size;
+ tg->last_io_disp[rw]++;
/*
* BIO_THROTTLED is used to prevent the same bio to be throttled
return nr_disp;
}
+static bool throtl_can_upgrade(struct throtl_data *td,
+ struct throtl_grp *this_tg);
/**
* throtl_pending_timer_fn - timer function for service_queue->pending_timer
* @arg: the throtl_service_queue being serviced
int ret;
spin_lock_irq(q->queue_lock);
+ if (throtl_can_upgrade(td, NULL))
+ throtl_upgrade_state(td);
+
again:
parent_sq = sq->parent_sq;
dispatched = false;
struct throtl_grp *tg = pd_to_tg(pd);
u64 v = *(u64 *)((void *)tg + off);
- if (v == -1)
+ if (v == U64_MAX)
return 0;
return __blkg_prfill_u64(sf, pd, v);
}
struct throtl_grp *tg = pd_to_tg(pd);
unsigned int v = *(unsigned int *)((void *)tg + off);
- if (v == -1)
+ if (v == UINT_MAX)
return 0;
return __blkg_prfill_u64(sf, pd, v);
}
throtl_log(&tg->service_queue,
"limit change rbps=%llu wbps=%llu riops=%u wiops=%u",
- tg->bps[READ], tg->bps[WRITE],
- tg->iops[READ], tg->iops[WRITE]);
+ tg_bps_limit(tg, READ), tg_bps_limit(tg, WRITE),
+ tg_iops_limit(tg, READ), tg_iops_limit(tg, WRITE));
/*
* Update has_rules[] flags for the updated tg's subtree. A tg is
if (sscanf(ctx.body, "%llu", &v) != 1)
goto out_finish;
if (!v)
- v = -1;
+ v = U64_MAX;
tg = blkg_to_tg(ctx.blkg);
static struct cftype throtl_legacy_files[] = {
{
.name = "throttle.read_bps_device",
- .private = offsetof(struct throtl_grp, bps[READ]),
+ .private = offsetof(struct throtl_grp, bps[READ][LIMIT_MAX]),
.seq_show = tg_print_conf_u64,
.write = tg_set_conf_u64,
},
{
.name = "throttle.write_bps_device",
- .private = offsetof(struct throtl_grp, bps[WRITE]),
+ .private = offsetof(struct throtl_grp, bps[WRITE][LIMIT_MAX]),
.seq_show = tg_print_conf_u64,
.write = tg_set_conf_u64,
},
{
.name = "throttle.read_iops_device",
- .private = offsetof(struct throtl_grp, iops[READ]),
+ .private = offsetof(struct throtl_grp, iops[READ][LIMIT_MAX]),
.seq_show = tg_print_conf_uint,
.write = tg_set_conf_uint,
},
{
.name = "throttle.write_iops_device",
- .private = offsetof(struct throtl_grp, iops[WRITE]),
+ .private = offsetof(struct throtl_grp, iops[WRITE][LIMIT_MAX]),
.seq_show = tg_print_conf_uint,
.write = tg_set_conf_uint,
},
{ } /* terminate */
};
-static u64 tg_prfill_max(struct seq_file *sf, struct blkg_policy_data *pd,
+static u64 tg_prfill_limit(struct seq_file *sf, struct blkg_policy_data *pd,
int off)
{
struct throtl_grp *tg = pd_to_tg(pd);
const char *dname = blkg_dev_name(pd->blkg);
char bufs[4][21] = { "max", "max", "max", "max" };
+ u64 bps_dft;
+ unsigned int iops_dft;
+ char idle_time[26] = "";
+ char latency_time[26] = "";
if (!dname)
return 0;
- if (tg->bps[READ] == -1 && tg->bps[WRITE] == -1 &&
- tg->iops[READ] == -1 && tg->iops[WRITE] == -1)
+
+ if (off == LIMIT_LOW) {
+ bps_dft = 0;
+ iops_dft = 0;
+ } else {
+ bps_dft = U64_MAX;
+ iops_dft = UINT_MAX;
+ }
+
+ if (tg->bps_conf[READ][off] == bps_dft &&
+ tg->bps_conf[WRITE][off] == bps_dft &&
+ tg->iops_conf[READ][off] == iops_dft &&
+ tg->iops_conf[WRITE][off] == iops_dft &&
+ (off != LIMIT_LOW ||
+ (tg->idletime_threshold == tg->td->dft_idletime_threshold &&
+ tg->latency_target == DFL_LATENCY_TARGET)))
return 0;
- if (tg->bps[READ] != -1)
- snprintf(bufs[0], sizeof(bufs[0]), "%llu", tg->bps[READ]);
- if (tg->bps[WRITE] != -1)
- snprintf(bufs[1], sizeof(bufs[1]), "%llu", tg->bps[WRITE]);
- if (tg->iops[READ] != -1)
- snprintf(bufs[2], sizeof(bufs[2]), "%u", tg->iops[READ]);
- if (tg->iops[WRITE] != -1)
- snprintf(bufs[3], sizeof(bufs[3]), "%u", tg->iops[WRITE]);
-
- seq_printf(sf, "%s rbps=%s wbps=%s riops=%s wiops=%s\n",
- dname, bufs[0], bufs[1], bufs[2], bufs[3]);
+ if (tg->bps_conf[READ][off] != bps_dft)
+ snprintf(bufs[0], sizeof(bufs[0]), "%llu",
+ tg->bps_conf[READ][off]);
+ if (tg->bps_conf[WRITE][off] != bps_dft)
+ snprintf(bufs[1], sizeof(bufs[1]), "%llu",
+ tg->bps_conf[WRITE][off]);
+ if (tg->iops_conf[READ][off] != iops_dft)
+ snprintf(bufs[2], sizeof(bufs[2]), "%u",
+ tg->iops_conf[READ][off]);
+ if (tg->iops_conf[WRITE][off] != iops_dft)
+ snprintf(bufs[3], sizeof(bufs[3]), "%u",
+ tg->iops_conf[WRITE][off]);
+ if (off == LIMIT_LOW) {
+ if (tg->idletime_threshold == ULONG_MAX)
+ strcpy(idle_time, " idle=max");
+ else
+ snprintf(idle_time, sizeof(idle_time), " idle=%lu",
+ tg->idletime_threshold);
+
+ if (tg->latency_target == ULONG_MAX)
+ strcpy(latency_time, " latency=max");
+ else
+ snprintf(latency_time, sizeof(latency_time),
+ " latency=%lu", tg->latency_target);
+ }
+
+ seq_printf(sf, "%s rbps=%s wbps=%s riops=%s wiops=%s%s%s\n",
+ dname, bufs[0], bufs[1], bufs[2], bufs[3], idle_time,
+ latency_time);
return 0;
}
-static int tg_print_max(struct seq_file *sf, void *v)
+static int tg_print_limit(struct seq_file *sf, void *v)
{
- blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), tg_prfill_max,
+ blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), tg_prfill_limit,
&blkcg_policy_throtl, seq_cft(sf)->private, false);
return 0;
}
-static ssize_t tg_set_max(struct kernfs_open_file *of,
+static ssize_t tg_set_limit(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
{
struct blkcg *blkcg = css_to_blkcg(of_css(of));
struct blkg_conf_ctx ctx;
struct throtl_grp *tg;
u64 v[4];
+ unsigned long idle_time;
+ unsigned long latency_time;
int ret;
+ int index = of_cft(of)->private;
ret = blkg_conf_prep(blkcg, &blkcg_policy_throtl, buf, &ctx);
if (ret)
tg = blkg_to_tg(ctx.blkg);
- v[0] = tg->bps[READ];
- v[1] = tg->bps[WRITE];
- v[2] = tg->iops[READ];
- v[3] = tg->iops[WRITE];
+ v[0] = tg->bps_conf[READ][index];
+ v[1] = tg->bps_conf[WRITE][index];
+ v[2] = tg->iops_conf[READ][index];
+ v[3] = tg->iops_conf[WRITE][index];
+ idle_time = tg->idletime_threshold;
+ latency_time = tg->latency_target;
while (true) {
char tok[27]; /* wiops=18446744073709551616 */
char *p;
- u64 val = -1;
+ u64 val = U64_MAX;
int len;
if (sscanf(ctx.body, "%26s%n", tok, &len) != 1)
v[2] = min_t(u64, val, UINT_MAX);
else if (!strcmp(tok, "wiops"))
v[3] = min_t(u64, val, UINT_MAX);
+ else if (off == LIMIT_LOW && !strcmp(tok, "idle"))
+ idle_time = val;
+ else if (off == LIMIT_LOW && !strcmp(tok, "latency"))
+ latency_time = val;
else
goto out_finish;
}
- tg->bps[READ] = v[0];
- tg->bps[WRITE] = v[1];
- tg->iops[READ] = v[2];
- tg->iops[WRITE] = v[3];
+ tg->bps_conf[READ][index] = v[0];
+ tg->bps_conf[WRITE][index] = v[1];
+ tg->iops_conf[READ][index] = v[2];
+ tg->iops_conf[WRITE][index] = v[3];
+ if (index == LIMIT_MAX) {
+ tg->bps[READ][index] = v[0];
+ tg->bps[WRITE][index] = v[1];
+ tg->iops[READ][index] = v[2];
+ tg->iops[WRITE][index] = v[3];
+ }
+ tg->bps[READ][LIMIT_LOW] = min(tg->bps_conf[READ][LIMIT_LOW],
+ tg->bps_conf[READ][LIMIT_MAX]);
+ tg->bps[WRITE][LIMIT_LOW] = min(tg->bps_conf[WRITE][LIMIT_LOW],
+ tg->bps_conf[WRITE][LIMIT_MAX]);
+ tg->iops[READ][LIMIT_LOW] = min(tg->iops_conf[READ][LIMIT_LOW],
+ tg->iops_conf[READ][LIMIT_MAX]);
+ tg->iops[WRITE][LIMIT_LOW] = min(tg->iops_conf[WRITE][LIMIT_LOW],
+ tg->iops_conf[WRITE][LIMIT_MAX]);
+
+ if (index == LIMIT_LOW) {
+ blk_throtl_update_limit_valid(tg->td);
+ if (tg->td->limit_valid[LIMIT_LOW])
+ tg->td->limit_index = LIMIT_LOW;
+ tg->idletime_threshold = (idle_time == ULONG_MAX) ?
+ ULONG_MAX : idle_time;
+ tg->latency_target = (latency_time == ULONG_MAX) ?
+ ULONG_MAX : latency_time;
+ }
tg_conf_updated(tg);
ret = 0;
out_finish:
}
static struct cftype throtl_files[] = {
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+ {
+ .name = "low",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = tg_print_limit,
+ .write = tg_set_limit,
+ .private = LIMIT_LOW,
+ },
+#endif
{
.name = "max",
.flags = CFTYPE_NOT_ON_ROOT,
- .seq_show = tg_print_max,
- .write = tg_set_max,
+ .seq_show = tg_print_limit,
+ .write = tg_set_limit,
+ .private = LIMIT_MAX,
},
{ } /* terminate */
};
.pd_alloc_fn = throtl_pd_alloc,
.pd_init_fn = throtl_pd_init,
.pd_online_fn = throtl_pd_online,
+ .pd_offline_fn = throtl_pd_offline,
.pd_free_fn = throtl_pd_free,
};
+static unsigned long __tg_last_low_overflow_time(struct throtl_grp *tg)
+{
+ unsigned long rtime = jiffies, wtime = jiffies;
+
+ if (tg->bps[READ][LIMIT_LOW] || tg->iops[READ][LIMIT_LOW])
+ rtime = tg->last_low_overflow_time[READ];
+ if (tg->bps[WRITE][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW])
+ wtime = tg->last_low_overflow_time[WRITE];
+ return min(rtime, wtime);
+}
+
+/* tg should not be an intermediate node */
+static unsigned long tg_last_low_overflow_time(struct throtl_grp *tg)
+{
+ struct throtl_service_queue *parent_sq;
+ struct throtl_grp *parent = tg;
+ unsigned long ret = __tg_last_low_overflow_time(tg);
+
+ while (true) {
+ parent_sq = parent->service_queue.parent_sq;
+ parent = sq_to_tg(parent_sq);
+ if (!parent)
+ break;
+
+ /*
+ * The parent doesn't have low limit, it always reaches low
+ * limit. Its overflow time is useless for children
+ */
+ if (!parent->bps[READ][LIMIT_LOW] &&
+ !parent->iops[READ][LIMIT_LOW] &&
+ !parent->bps[WRITE][LIMIT_LOW] &&
+ !parent->iops[WRITE][LIMIT_LOW])
+ continue;
+ if (time_after(__tg_last_low_overflow_time(parent), ret))
+ ret = __tg_last_low_overflow_time(parent);
+ }
+ return ret;
+}
+
+static bool throtl_tg_is_idle(struct throtl_grp *tg)
+{
+ /*
+ * cgroup is idle if:
+ * - single idle is too long, longer than a fixed value (in case user
+ * configure a too big threshold) or 4 times of slice
+ * - average think time is more than threshold
+ * - IO latency is largely below threshold
+ */
+ unsigned long time = jiffies_to_usecs(4 * tg->td->throtl_slice);
+
+ time = min_t(unsigned long, MAX_IDLE_TIME, time);
+ return (ktime_get_ns() >> 10) - tg->last_finish_time > time ||
+ tg->avg_idletime > tg->idletime_threshold ||
+ (tg->latency_target && tg->bio_cnt &&
+ tg->bad_bio_cnt * 5 < tg->bio_cnt);
+}
+
+static bool throtl_tg_can_upgrade(struct throtl_grp *tg)
+{
+ struct throtl_service_queue *sq = &tg->service_queue;
+ bool read_limit, write_limit;
+
+ /*
+ * if cgroup reaches low limit (if low limit is 0, the cgroup always
+ * reaches), it's ok to upgrade to next limit
+ */
+ read_limit = tg->bps[READ][LIMIT_LOW] || tg->iops[READ][LIMIT_LOW];
+ write_limit = tg->bps[WRITE][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW];
+ if (!read_limit && !write_limit)
+ return true;
+ if (read_limit && sq->nr_queued[READ] &&
+ (!write_limit || sq->nr_queued[WRITE]))
+ return true;
+ if (write_limit && sq->nr_queued[WRITE] &&
+ (!read_limit || sq->nr_queued[READ]))
+ return true;
+
+ if (time_after_eq(jiffies,
+ tg_last_low_overflow_time(tg) + tg->td->throtl_slice) &&
+ throtl_tg_is_idle(tg))
+ return true;
+ return false;
+}
+
+static bool throtl_hierarchy_can_upgrade(struct throtl_grp *tg)
+{
+ while (true) {
+ if (throtl_tg_can_upgrade(tg))
+ return true;
+ tg = sq_to_tg(tg->service_queue.parent_sq);
+ if (!tg || !tg_to_blkg(tg)->parent)
+ return false;
+ }
+ return false;
+}
+
+static bool throtl_can_upgrade(struct throtl_data *td,
+ struct throtl_grp *this_tg)
+{
+ struct cgroup_subsys_state *pos_css;
+ struct blkcg_gq *blkg;
+
+ if (td->limit_index != LIMIT_LOW)
+ return false;
+
+ if (time_before(jiffies, td->low_downgrade_time + td->throtl_slice))
+ return false;
+
+ rcu_read_lock();
+ blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
+ struct throtl_grp *tg = blkg_to_tg(blkg);
+
+ if (tg == this_tg)
+ continue;
+ if (!list_empty(&tg_to_blkg(tg)->blkcg->css.children))
+ continue;
+ if (!throtl_hierarchy_can_upgrade(tg)) {
+ rcu_read_unlock();
+ return false;
+ }
+ }
+ rcu_read_unlock();
+ return true;
+}
+
+static void throtl_upgrade_check(struct throtl_grp *tg)
+{
+ unsigned long now = jiffies;
+
+ if (tg->td->limit_index != LIMIT_LOW)
+ return;
+
+ if (time_after(tg->last_check_time + tg->td->throtl_slice, now))
+ return;
+
+ tg->last_check_time = now;
+
+ if (!time_after_eq(now,
+ __tg_last_low_overflow_time(tg) + tg->td->throtl_slice))
+ return;
+
+ if (throtl_can_upgrade(tg->td, NULL))
+ throtl_upgrade_state(tg->td);
+}
+
+static void throtl_upgrade_state(struct throtl_data *td)
+{
+ struct cgroup_subsys_state *pos_css;
+ struct blkcg_gq *blkg;
+
+ td->limit_index = LIMIT_MAX;
+ td->low_upgrade_time = jiffies;
+ td->scale = 0;
+ rcu_read_lock();
+ blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
+ struct throtl_grp *tg = blkg_to_tg(blkg);
+ struct throtl_service_queue *sq = &tg->service_queue;
+
+ tg->disptime = jiffies - 1;
+ throtl_select_dispatch(sq);
+ throtl_schedule_next_dispatch(sq, false);
+ }
+ rcu_read_unlock();
+ throtl_select_dispatch(&td->service_queue);
+ throtl_schedule_next_dispatch(&td->service_queue, false);
+ queue_work(kthrotld_workqueue, &td->dispatch_work);
+}
+
+static void throtl_downgrade_state(struct throtl_data *td, int new)
+{
+ td->scale /= 2;
+
+ if (td->scale) {
+ td->low_upgrade_time = jiffies - td->scale * td->throtl_slice;
+ return;
+ }
+
+ td->limit_index = new;
+ td->low_downgrade_time = jiffies;
+}
+
+static bool throtl_tg_can_downgrade(struct throtl_grp *tg)
+{
+ struct throtl_data *td = tg->td;
+ unsigned long now = jiffies;
+
+ /*
+ * If cgroup is below low limit, consider downgrade and throttle other
+ * cgroups
+ */
+ if (time_after_eq(now, td->low_upgrade_time + td->throtl_slice) &&
+ time_after_eq(now, tg_last_low_overflow_time(tg) +
+ td->throtl_slice) &&
+ (!throtl_tg_is_idle(tg) ||
+ !list_empty(&tg_to_blkg(tg)->blkcg->css.children)))
+ return true;
+ return false;
+}
+
+static bool throtl_hierarchy_can_downgrade(struct throtl_grp *tg)
+{
+ while (true) {
+ if (!throtl_tg_can_downgrade(tg))
+ return false;
+ tg = sq_to_tg(tg->service_queue.parent_sq);
+ if (!tg || !tg_to_blkg(tg)->parent)
+ break;
+ }
+ return true;
+}
+
+static void throtl_downgrade_check(struct throtl_grp *tg)
+{
+ uint64_t bps;
+ unsigned int iops;
+ unsigned long elapsed_time;
+ unsigned long now = jiffies;
+
+ if (tg->td->limit_index != LIMIT_MAX ||
+ !tg->td->limit_valid[LIMIT_LOW])
+ return;
+ if (!list_empty(&tg_to_blkg(tg)->blkcg->css.children))
+ return;
+ if (time_after(tg->last_check_time + tg->td->throtl_slice, now))
+ return;
+
+ elapsed_time = now - tg->last_check_time;
+ tg->last_check_time = now;
+
+ if (time_before(now, tg_last_low_overflow_time(tg) +
+ tg->td->throtl_slice))
+ return;
+
+ if (tg->bps[READ][LIMIT_LOW]) {
+ bps = tg->last_bytes_disp[READ] * HZ;
+ do_div(bps, elapsed_time);
+ if (bps >= tg->bps[READ][LIMIT_LOW])
+ tg->last_low_overflow_time[READ] = now;
+ }
+
+ if (tg->bps[WRITE][LIMIT_LOW]) {
+ bps = tg->last_bytes_disp[WRITE] * HZ;
+ do_div(bps, elapsed_time);
+ if (bps >= tg->bps[WRITE][LIMIT_LOW])
+ tg->last_low_overflow_time[WRITE] = now;
+ }
+
+ if (tg->iops[READ][LIMIT_LOW]) {
+ iops = tg->last_io_disp[READ] * HZ / elapsed_time;
+ if (iops >= tg->iops[READ][LIMIT_LOW])
+ tg->last_low_overflow_time[READ] = now;
+ }
+
+ if (tg->iops[WRITE][LIMIT_LOW]) {
+ iops = tg->last_io_disp[WRITE] * HZ / elapsed_time;
+ if (iops >= tg->iops[WRITE][LIMIT_LOW])
+ tg->last_low_overflow_time[WRITE] = now;
+ }
+
+ /*
+ * If cgroup is below low limit, consider downgrade and throttle other
+ * cgroups
+ */
+ if (throtl_hierarchy_can_downgrade(tg))
+ throtl_downgrade_state(tg->td, LIMIT_LOW);
+
+ tg->last_bytes_disp[READ] = 0;
+ tg->last_bytes_disp[WRITE] = 0;
+ tg->last_io_disp[READ] = 0;
+ tg->last_io_disp[WRITE] = 0;
+}
+
+static void blk_throtl_update_idletime(struct throtl_grp *tg)
+{
+ unsigned long now = ktime_get_ns() >> 10;
+ unsigned long last_finish_time = tg->last_finish_time;
+
+ if (now <= last_finish_time || last_finish_time == 0 ||
+ last_finish_time == tg->checked_last_finish_time)
+ return;
+
+ tg->avg_idletime = (tg->avg_idletime * 7 + now - last_finish_time) >> 3;
+ tg->checked_last_finish_time = last_finish_time;
+}
+
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+static void throtl_update_latency_buckets(struct throtl_data *td)
+{
+ struct avg_latency_bucket avg_latency[LATENCY_BUCKET_SIZE];
+ int i, cpu;
+ unsigned long last_latency = 0;
+ unsigned long latency;
+
+ if (!blk_queue_nonrot(td->queue))
+ return;
+ if (time_before(jiffies, td->last_calculate_time + HZ))
+ return;
+ td->last_calculate_time = jiffies;
+
+ memset(avg_latency, 0, sizeof(avg_latency));
+ for (i = 0; i < LATENCY_BUCKET_SIZE; i++) {
+ struct latency_bucket *tmp = &td->tmp_buckets[i];
+
+ for_each_possible_cpu(cpu) {
+ struct latency_bucket *bucket;
+
+ /* this isn't race free, but ok in practice */
+ bucket = per_cpu_ptr(td->latency_buckets, cpu);
+ tmp->total_latency += bucket[i].total_latency;
+ tmp->samples += bucket[i].samples;
+ bucket[i].total_latency = 0;
+ bucket[i].samples = 0;
+ }
+
+ if (tmp->samples >= 32) {
+ int samples = tmp->samples;
+
+ latency = tmp->total_latency;
+
+ tmp->total_latency = 0;
+ tmp->samples = 0;
+ latency /= samples;
+ if (latency == 0)
+ continue;
+ avg_latency[i].latency = latency;
+ }
+ }
+
+ for (i = 0; i < LATENCY_BUCKET_SIZE; i++) {
+ if (!avg_latency[i].latency) {
+ if (td->avg_buckets[i].latency < last_latency)
+ td->avg_buckets[i].latency = last_latency;
+ continue;
+ }
+
+ if (!td->avg_buckets[i].valid)
+ latency = avg_latency[i].latency;
+ else
+ latency = (td->avg_buckets[i].latency * 7 +
+ avg_latency[i].latency) >> 3;
+
+ td->avg_buckets[i].latency = max(latency, last_latency);
+ td->avg_buckets[i].valid = true;
+ last_latency = td->avg_buckets[i].latency;
+ }
+}
+#else
+static inline void throtl_update_latency_buckets(struct throtl_data *td)
+{
+}
+#endif
+
+static void blk_throtl_assoc_bio(struct throtl_grp *tg, struct bio *bio)
+{
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+ int ret;
+
+ ret = bio_associate_current(bio);
+ if (ret == 0 || ret == -EBUSY)
+ bio->bi_cg_private = tg;
+ blk_stat_set_issue(&bio->bi_issue_stat, bio_sectors(bio));
+#else
+ bio_associate_current(bio);
+#endif
+}
+
bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
struct bio *bio)
{
struct throtl_service_queue *sq;
bool rw = bio_data_dir(bio);
bool throttled = false;
+ struct throtl_data *td = tg->td;
WARN_ON_ONCE(!rcu_read_lock_held());
spin_lock_irq(q->queue_lock);
+ throtl_update_latency_buckets(td);
+
if (unlikely(blk_queue_bypass(q)))
goto out_unlock;
+ blk_throtl_assoc_bio(tg, bio);
+ blk_throtl_update_idletime(tg);
+
sq = &tg->service_queue;
+again:
while (true) {
+ if (tg->last_low_overflow_time[rw] == 0)
+ tg->last_low_overflow_time[rw] = jiffies;
+ throtl_downgrade_check(tg);
+ throtl_upgrade_check(tg);
/* throtl is FIFO - if bios are already queued, should queue */
if (sq->nr_queued[rw])
break;
/* if above limits, break to queue */
- if (!tg_may_dispatch(tg, bio, NULL))
+ if (!tg_may_dispatch(tg, bio, NULL)) {
+ tg->last_low_overflow_time[rw] = jiffies;
+ if (throtl_can_upgrade(td, tg)) {
+ throtl_upgrade_state(td);
+ goto again;
+ }
break;
+ }
/* within limits, let's charge and dispatch directly */
throtl_charge_bio(tg, bio);
/* out-of-limit, queue to @tg */
throtl_log(sq, "[%c] bio. bdisp=%llu sz=%u bps=%llu iodisp=%u iops=%u queued=%d/%d",
rw == READ ? 'R' : 'W',
- tg->bytes_disp[rw], bio->bi_iter.bi_size, tg->bps[rw],
- tg->io_disp[rw], tg->iops[rw],
+ tg->bytes_disp[rw], bio->bi_iter.bi_size,
+ tg_bps_limit(tg, rw),
+ tg->io_disp[rw], tg_iops_limit(tg, rw),
sq->nr_queued[READ], sq->nr_queued[WRITE]);
- bio_associate_current(bio);
- tg->td->nr_queued[rw]++;
+ tg->last_low_overflow_time[rw] = jiffies;
+
+ td->nr_queued[rw]++;
throtl_add_bio_tg(bio, qn, tg);
throttled = true;
*/
if (!throttled)
bio_clear_flag(bio, BIO_THROTTLED);
+
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+ if (throttled || !td->track_bio_latency)
+ bio->bi_issue_stat.stat |= SKIP_LATENCY;
+#endif
return throttled;
}
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+static void throtl_track_latency(struct throtl_data *td, sector_t size,
+ int op, unsigned long time)
+{
+ struct latency_bucket *latency;
+ int index;
+
+ if (!td || td->limit_index != LIMIT_LOW || op != REQ_OP_READ ||
+ !blk_queue_nonrot(td->queue))
+ return;
+
+ index = request_bucket_index(size);
+
+ latency = get_cpu_ptr(td->latency_buckets);
+ latency[index].total_latency += time;
+ latency[index].samples++;
+ put_cpu_ptr(td->latency_buckets);
+}
+
+void blk_throtl_stat_add(struct request *rq, u64 time_ns)
+{
+ struct request_queue *q = rq->q;
+ struct throtl_data *td = q->td;
+
+ throtl_track_latency(td, blk_stat_size(&rq->issue_stat),
+ req_op(rq), time_ns >> 10);
+}
+
+void blk_throtl_bio_endio(struct bio *bio)
+{
+ struct throtl_grp *tg;
+ u64 finish_time_ns;
+ unsigned long finish_time;
+ unsigned long start_time;
+ unsigned long lat;
+
+ tg = bio->bi_cg_private;
+ if (!tg)
+ return;
+ bio->bi_cg_private = NULL;
+
+ finish_time_ns = ktime_get_ns();
+ tg->last_finish_time = finish_time_ns >> 10;
+
+ start_time = blk_stat_time(&bio->bi_issue_stat) >> 10;
+ finish_time = __blk_stat_time(finish_time_ns) >> 10;
+ if (!start_time || finish_time <= start_time)
+ return;
+
+ lat = finish_time - start_time;
+ /* this is only for bio based driver */
+ if (!(bio->bi_issue_stat.stat & SKIP_LATENCY))
+ throtl_track_latency(tg->td, blk_stat_size(&bio->bi_issue_stat),
+ bio_op(bio), lat);
+
+ if (tg->latency_target) {
+ int bucket;
+ unsigned int threshold;
+
+ bucket = request_bucket_index(
+ blk_stat_size(&bio->bi_issue_stat));
+ threshold = tg->td->avg_buckets[bucket].latency +
+ tg->latency_target;
+ if (lat > threshold)
+ tg->bad_bio_cnt++;
+ /*
+ * Not race free, could get wrong count, which means cgroups
+ * will be throttled
+ */
+ tg->bio_cnt++;
+ }
+
+ if (time_after(jiffies, tg->bio_cnt_reset_time) || tg->bio_cnt > 1024) {
+ tg->bio_cnt_reset_time = tg->td->throtl_slice + jiffies;
+ tg->bio_cnt /= 2;
+ tg->bad_bio_cnt /= 2;
+ }
+}
+#endif
+
/*
* Dispatch all bios from all children tg's queued on @parent_sq. On
* return, @parent_sq is guaranteed to not have any active children tg's
td = kzalloc_node(sizeof(*td), GFP_KERNEL, q->node);
if (!td)
return -ENOMEM;
+ td->latency_buckets = __alloc_percpu(sizeof(struct latency_bucket) *
+ LATENCY_BUCKET_SIZE, __alignof__(u64));
+ if (!td->latency_buckets) {
+ kfree(td);
+ return -ENOMEM;
+ }
INIT_WORK(&td->dispatch_work, blk_throtl_dispatch_work_fn);
throtl_service_queue_init(&td->service_queue);
q->td = td;
td->queue = q;
+ td->limit_valid[LIMIT_MAX] = true;
+ td->limit_index = LIMIT_MAX;
+ td->low_upgrade_time = jiffies;
+ td->low_downgrade_time = jiffies;
+
/* activate policy */
ret = blkcg_activate_policy(q, &blkcg_policy_throtl);
- if (ret)
+ if (ret) {
+ free_percpu(td->latency_buckets);
kfree(td);
+ }
return ret;
}
BUG_ON(!q->td);
throtl_shutdown_wq(q);
blkcg_deactivate_policy(q, &blkcg_policy_throtl);
+ free_percpu(q->td->latency_buckets);
kfree(q->td);
}
+void blk_throtl_register_queue(struct request_queue *q)
+{
+ struct throtl_data *td;
+ struct cgroup_subsys_state *pos_css;
+ struct blkcg_gq *blkg;
+
+ td = q->td;
+ BUG_ON(!td);
+
+ if (blk_queue_nonrot(q)) {
+ td->throtl_slice = DFL_THROTL_SLICE_SSD;
+ td->dft_idletime_threshold = DFL_IDLE_THRESHOLD_SSD;
+ } else {
+ td->throtl_slice = DFL_THROTL_SLICE_HD;
+ td->dft_idletime_threshold = DFL_IDLE_THRESHOLD_HD;
+ }
+#ifndef CONFIG_BLK_DEV_THROTTLING_LOW
+ /* if no low limit, use previous default */
+ td->throtl_slice = DFL_THROTL_SLICE_HD;
+#endif
+
+ td->track_bio_latency = !q->mq_ops && !q->request_fn;
+ if (!td->track_bio_latency)
+ blk_stat_enable_accounting(q);
+
+ /*
+ * some tg are created before queue is fully initialized, eg, nonrot
+ * isn't initialized yet
+ */
+ rcu_read_lock();
+ blkg_for_each_descendant_post(blkg, pos_css, q->root_blkg) {
+ struct throtl_grp *tg = blkg_to_tg(blkg);
+
+ tg->idletime_threshold = td->dft_idletime_threshold;
+ }
+ rcu_read_unlock();
+}
+
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+ssize_t blk_throtl_sample_time_show(struct request_queue *q, char *page)
+{
+ if (!q->td)
+ return -EINVAL;
+ return sprintf(page, "%u\n", jiffies_to_msecs(q->td->throtl_slice));
+}
+
+ssize_t blk_throtl_sample_time_store(struct request_queue *q,
+ const char *page, size_t count)
+{
+ unsigned long v;
+ unsigned long t;
+
+ if (!q->td)
+ return -EINVAL;
+ if (kstrtoul(page, 10, &v))
+ return -EINVAL;
+ t = msecs_to_jiffies(v);
+ if (t == 0 || t > MAX_THROTL_SLICE)
+ return -EINVAL;
+ q->td->throtl_slice = t;
+ return count;
+}
+#endif
+
static int __init throtl_init(void)
{
kthrotld_workqueue = alloc_workqueue("kthrotld", WQ_MEM_RECLAIM, 0);
ret = q->rq_timed_out_fn(req);
switch (ret) {
case BLK_EH_HANDLED:
- /* Can we use req->errors here? */
__blk_complete_request(req);
break;
case BLK_EH_RESET_TIMER:
* that it's writes impacting us, and not just some sole read on
* a device that is in a lower power state.
*/
- return stat[BLK_STAT_READ].nr_samples >= 1 &&
- stat[BLK_STAT_WRITE].nr_samples >= RWB_MIN_WRITE_SAMPLES;
+ return (stat[READ].nr_samples >= 1 &&
+ stat[WRITE].nr_samples >= RWB_MIN_WRITE_SAMPLES);
}
static u64 rwb_sync_issue_lat(struct rq_wb *rwb)
LAT_EXCEEDED,
};
-static int __latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
+static int latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
{
struct backing_dev_info *bdi = rwb->queue->backing_dev_info;
u64 thislat;
*/
thislat = rwb_sync_issue_lat(rwb);
if (thislat > rwb->cur_win_nsec ||
- (thislat > rwb->min_lat_nsec && !stat[BLK_STAT_READ].nr_samples)) {
+ (thislat > rwb->min_lat_nsec && !stat[READ].nr_samples)) {
trace_wbt_lat(bdi, thislat);
return LAT_EXCEEDED;
}
* waited or still has writes in flights, consider us doing
* just writes as well.
*/
- if ((stat[BLK_STAT_WRITE].nr_samples && blk_stat_is_current(stat)) ||
- wb_recent_wait(rwb) || wbt_inflight(rwb))
+ if (stat[WRITE].nr_samples || wb_recent_wait(rwb) ||
+ wbt_inflight(rwb))
return LAT_UNKNOWN_WRITES;
return LAT_UNKNOWN;
}
/*
* If the 'min' latency exceeds our target, step down.
*/
- if (stat[BLK_STAT_READ].min > rwb->min_lat_nsec) {
- trace_wbt_lat(bdi, stat[BLK_STAT_READ].min);
+ if (stat[READ].min > rwb->min_lat_nsec) {
+ trace_wbt_lat(bdi, stat[READ].min);
trace_wbt_stat(bdi, stat);
return LAT_EXCEEDED;
}
return LAT_OK;
}
-static int latency_exceeded(struct rq_wb *rwb)
-{
- struct blk_rq_stat stat[2];
-
- blk_queue_stat_get(rwb->queue, stat);
- return __latency_exceeded(rwb, stat);
-}
-
static void rwb_trace_step(struct rq_wb *rwb, const char *msg)
{
struct backing_dev_info *bdi = rwb->queue->backing_dev_info;
rwb->scale_step--;
rwb->unknown_cnt = 0;
- blk_stat_clear(rwb->queue);
rwb->scaled_max = calc_wb_limits(rwb);
rwb->scaled_max = false;
rwb->unknown_cnt = 0;
- blk_stat_clear(rwb->queue);
calc_wb_limits(rwb);
rwb_trace_step(rwb, "step down");
}
static void rwb_arm_timer(struct rq_wb *rwb)
{
- unsigned long expires;
-
if (rwb->scale_step > 0) {
/*
* We should speed this up, using some variant of a fast
rwb->cur_win_nsec = rwb->win_nsec;
}
- expires = jiffies + nsecs_to_jiffies(rwb->cur_win_nsec);
- mod_timer(&rwb->window_timer, expires);
+ blk_stat_activate_nsecs(rwb->cb, rwb->cur_win_nsec);
}
-static void wb_timer_fn(unsigned long data)
+static void wb_timer_fn(struct blk_stat_callback *cb)
{
- struct rq_wb *rwb = (struct rq_wb *) data;
+ struct rq_wb *rwb = cb->data;
unsigned int inflight = wbt_inflight(rwb);
int status;
- status = latency_exceeded(rwb);
+ status = latency_exceeded(rwb, cb->stat);
trace_wbt_timer(rwb->queue->backing_dev_info, status, rwb->scale_step,
inflight);
__wbt_wait(rwb, bio->bi_opf, lock);
- if (!timer_pending(&rwb->window_timer))
+ if (!blk_stat_is_active(rwb->cb))
rwb_arm_timer(rwb);
if (current_is_kswapd())
rwb->wc = write_cache_on;
}
- /*
- * Disable wbt, if enabled by default. Only called from CFQ, if we have
- * cgroups enabled
+/*
+ * Disable wbt, if enabled by default. Only called from CFQ.
*/
void wbt_disable_default(struct request_queue *q)
{
struct rq_wb *rwb = q->rq_wb;
- if (rwb && rwb->enable_state == WBT_STATE_ON_DEFAULT) {
- del_timer_sync(&rwb->window_timer);
- rwb->win_nsec = rwb->min_lat_nsec = 0;
- wbt_update_limits(rwb);
- }
+ if (rwb && rwb->enable_state == WBT_STATE_ON_DEFAULT)
+ wbt_exit(q);
}
EXPORT_SYMBOL_GPL(wbt_disable_default);
+/*
+ * Enable wbt if defaults are configured that way
+ */
+void wbt_enable_default(struct request_queue *q)
+{
+ /* Throttling already enabled? */
+ if (q->rq_wb)
+ return;
+
+ /* Queue not registered? Maybe shutting down... */
+ if (!test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags))
+ return;
+
+ if ((q->mq_ops && IS_ENABLED(CONFIG_BLK_WBT_MQ)) ||
+ (q->request_fn && IS_ENABLED(CONFIG_BLK_WBT_SQ)))
+ wbt_init(q);
+}
+EXPORT_SYMBOL_GPL(wbt_enable_default);
+
u64 wbt_default_latency_nsec(struct request_queue *q)
{
/*
return 75000000ULL;
}
+static int wbt_data_dir(const struct request *rq)
+{
+ return rq_data_dir(rq);
+}
+
int wbt_init(struct request_queue *q)
{
struct rq_wb *rwb;
int i;
- /*
- * For now, we depend on the stats window being larger than
- * our monitoring window. Ensure that this isn't inadvertently
- * violated.
- */
- BUILD_BUG_ON(RWB_WINDOW_NSEC > BLK_STAT_NSEC);
BUILD_BUG_ON(WBT_NR_BITS > BLK_STAT_RES_BITS);
rwb = kzalloc(sizeof(*rwb), GFP_KERNEL);
if (!rwb)
return -ENOMEM;
+ rwb->cb = blk_stat_alloc_callback(wb_timer_fn, wbt_data_dir, 2, rwb);
+ if (!rwb->cb) {
+ kfree(rwb);
+ return -ENOMEM;
+ }
+
for (i = 0; i < WBT_NUM_RWQ; i++) {
atomic_set(&rwb->rq_wait[i].inflight, 0);
init_waitqueue_head(&rwb->rq_wait[i].wait);
}
- setup_timer(&rwb->window_timer, wb_timer_fn, (unsigned long) rwb);
rwb->wc = 1;
rwb->queue_depth = RWB_DEF_DEPTH;
rwb->last_comp = rwb->last_issue = jiffies;
wbt_update_limits(rwb);
/*
- * Assign rwb, and turn on stats tracking for this queue
+ * Assign rwb and add the stats callback.
*/
q->rq_wb = rwb;
- blk_stat_enable(q);
+ blk_stat_add_callback(q, rwb->cb);
rwb->min_lat_nsec = wbt_default_latency_nsec(q);
struct rq_wb *rwb = q->rq_wb;
if (rwb) {
- del_timer_sync(&rwb->window_timer);
+ blk_stat_remove_callback(q, rwb->cb);
+ blk_stat_free_callback(rwb->cb);
q->rq_wb = NULL;
kfree(rwb);
}
static inline void wbt_clear_state(struct blk_issue_stat *stat)
{
- stat->time &= BLK_STAT_TIME_MASK;
+ stat->stat &= ~BLK_STAT_RES_MASK;
}
static inline enum wbt_flags wbt_stat_to_mask(struct blk_issue_stat *stat)
{
- return (stat->time & BLK_STAT_MASK) >> BLK_STAT_SHIFT;
+ return (stat->stat & BLK_STAT_RES_MASK) >> BLK_STAT_RES_SHIFT;
}
static inline void wbt_track(struct blk_issue_stat *stat, enum wbt_flags wb_acct)
{
- stat->time |= ((u64) wb_acct) << BLK_STAT_SHIFT;
+ stat->stat |= ((u64) wb_acct) << BLK_STAT_RES_SHIFT;
}
static inline bool wbt_is_tracked(struct blk_issue_stat *stat)
{
- return (stat->time >> BLK_STAT_SHIFT) & WBT_TRACKED;
+ return (stat->stat >> BLK_STAT_RES_SHIFT) & WBT_TRACKED;
}
static inline bool wbt_is_read(struct blk_issue_stat *stat)
{
- return (stat->time >> BLK_STAT_SHIFT) & WBT_READ;
+ return (stat->stat >> BLK_STAT_RES_SHIFT) & WBT_READ;
}
struct rq_wait {
u64 win_nsec; /* default window size */
u64 cur_win_nsec; /* current window size */
- struct timer_list window_timer;
+ struct blk_stat_callback *cb;
s64 sync_issue;
void *sync_cookie;
void wbt_requeue(struct rq_wb *, struct blk_issue_stat *);
void wbt_issue(struct rq_wb *, struct blk_issue_stat *);
void wbt_disable_default(struct request_queue *);
+void wbt_enable_default(struct request_queue *);
void wbt_set_queue_depth(struct rq_wb *, unsigned int);
void wbt_set_write_cache(struct rq_wb *, bool);
static inline void wbt_disable_default(struct request_queue *q)
{
}
+static inline void wbt_enable_default(struct request_queue *q)
+{
+}
static inline void wbt_set_queue_depth(struct rq_wb *rwb, unsigned int depth)
{
}
int blk_init_rl(struct request_list *rl, struct request_queue *q,
gfp_t gfp_mask);
void blk_exit_rl(struct request_list *rl);
-void init_request_from_bio(struct request *req, struct bio *bio);
void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
struct bio *bio);
void blk_queue_bypass_start(struct request_queue *q);
void blk_queue_bypass_end(struct request_queue *q);
void blk_dequeue_request(struct request *rq);
void __blk_queue_free_tags(struct request_queue *q);
-bool __blk_end_bidi_request(struct request *rq, int error,
- unsigned int nr_bytes, unsigned int bidi_bytes);
void blk_freeze_queue(struct request_queue *q);
static inline void blk_queue_enter_live(struct request_queue *q)
extern void blk_throtl_drain(struct request_queue *q);
extern int blk_throtl_init(struct request_queue *q);
extern void blk_throtl_exit(struct request_queue *q);
+extern void blk_throtl_register_queue(struct request_queue *q);
#else /* CONFIG_BLK_DEV_THROTTLING */
static inline void blk_throtl_drain(struct request_queue *q) { }
static inline int blk_throtl_init(struct request_queue *q) { return 0; }
static inline void blk_throtl_exit(struct request_queue *q) { }
+static inline void blk_throtl_register_queue(struct request_queue *q) { }
#endif /* CONFIG_BLK_DEV_THROTTLING */
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+extern ssize_t blk_throtl_sample_time_show(struct request_queue *q, char *page);
+extern ssize_t blk_throtl_sample_time_store(struct request_queue *q,
+ const char *page, size_t count);
+extern void blk_throtl_bio_endio(struct bio *bio);
+extern void blk_throtl_stat_add(struct request *rq, u64 time);
+#else
+static inline void blk_throtl_bio_endio(struct bio *bio) { }
+static inline void blk_throtl_stat_add(struct request *rq, u64 time) { }
+#endif
#endif /* BLK_INTERNAL_H */
struct bsg_job *job = container_of(kref, struct bsg_job, kref);
struct request *rq = job->req;
- blk_end_request_all(rq, rq->errors);
+ blk_end_request_all(rq, scsi_req(rq)->result);
put_device(job->dev); /* release reference for the request */
struct scsi_request *rq = scsi_req(req);
int err;
- err = job->req->errors = result;
+ err = scsi_req(job->req)->result = result;
if (err < 0)
/* we're only returning the result field in the reply */
rq->sense_len = sizeof(u32);
* @q: request queue to manage
*
* On error the create_bsg_job function should return a -Exyz error value
- * that will be set to the req->errors.
+ * that will be set to ->result.
*
* Drivers/subsys should pass this to the queue init function.
*/
ret = bsg_create_job(dev, req);
if (ret) {
- req->errors = ret;
+ scsi_req(req)->result = ret;
blk_end_request_all(req, ret);
spin_lock_irq(q->queue_lock);
continue;
struct scsi_request *req = scsi_req(rq);
int ret = 0;
- dprintk("rq %p bio %p 0x%x\n", rq, bio, rq->errors);
+ dprintk("rq %p bio %p 0x%x\n", rq, bio, req->result);
/*
* fill in all the output members
*/
- hdr->device_status = rq->errors & 0xff;
- hdr->transport_status = host_byte(rq->errors);
- hdr->driver_status = driver_byte(rq->errors);
+ hdr->device_status = req->result & 0xff;
+ hdr->transport_status = host_byte(req->result);
+ hdr->driver_status = driver_byte(req->result);
hdr->info = 0;
if (hdr->device_status || hdr->transport_status || hdr->driver_status)
hdr->info |= SG_INFO_CHECK;
* just a protocol response (i.e. non negative), that gets
* processed above.
*/
- if (!ret && rq->errors < 0)
- ret = rq->errors;
+ if (!ret && req->result < 0)
+ ret = req->result;
blk_rq_unmap_user(bio);
scsi_req_free_cmd(req);
dprintk("%s: write %zd bytes\n", bd->name, count);
- if (unlikely(segment_eq(get_fs(), KERNEL_DS)))
+ if (unlikely(uaccess_kernel()))
return -EINVAL;
bsg_set_block(bd, file);
}
#ifdef CONFIG_CFQ_GROUP_IOSCHED
-static bool check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
+static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
{
struct cfq_data *cfqd = cic_to_cfqd(cic);
struct cfq_queue *cfqq;
uint64_t serial_nr;
- bool nonroot_cg;
rcu_read_lock();
serial_nr = bio_blkcg(bio)->css.serial_nr;
- nonroot_cg = bio_blkcg(bio) != &blkcg_root;
rcu_read_unlock();
/*
* spuriously on a newly created cic but there's no harm.
*/
if (unlikely(!cfqd) || likely(cic->blkcg_serial_nr == serial_nr))
- return nonroot_cg;
+ return;
/*
* Drop reference to queues. New queues will be assigned in new
}
cic->blkcg_serial_nr = serial_nr;
- return nonroot_cg;
}
#else
-static inline bool check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
+static inline void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
{
- return false;
}
#endif /* CONFIG_CFQ_GROUP_IOSCHED */
const int rw = rq_data_dir(rq);
const bool is_sync = rq_is_sync(rq);
struct cfq_queue *cfqq;
- bool disable_wbt;
spin_lock_irq(q->queue_lock);
check_ioprio_changed(cic, bio);
- disable_wbt = check_blkcg_changed(cic, bio);
+ check_blkcg_changed(cic, bio);
new_queue:
cfqq = cic_to_cfqq(cic, is_sync);
if (!cfqq || cfqq == &cfqd->oom_cfqq) {
rq->elv.priv[1] = cfqq->cfqg;
spin_unlock_irq(q->queue_lock);
- if (disable_wbt)
- wbt_disable_default(q);
-
return 0;
}
*/
if (blk_queue_nonrot(q))
cfqd->cfq_slice_idle = 0;
+ wbt_disable_default(q);
}
/*
case BLKALIGNOFF:
return compat_put_int(arg, bdev_alignment_offset(bdev));
case BLKDISCARDZEROES:
- return compat_put_uint(arg, bdev_discard_zeroes_data(bdev));
+ return compat_put_uint(arg, 0);
case BLKFLSBUF:
case BLKROSET:
case BLKDISCARD:
#include "blk.h"
#include "blk-mq-sched.h"
+#include "blk-wbt.h"
static DEFINE_SPINLOCK(elv_list_lock);
static LIST_HEAD(elv_list);
}
}
- if (e->uses_mq) {
- err = blk_mq_sched_setup(q);
- if (!err)
- err = e->ops.mq.init_sched(q, e);
- } else
+ if (e->uses_mq)
+ err = blk_mq_init_sched(q, e);
+ else
err = e->ops.sq.elevator_init_fn(q, e);
- if (err) {
- if (e->uses_mq)
- blk_mq_sched_teardown(q);
+ if (err)
elevator_put(e);
- }
return err;
}
EXPORT_SYMBOL(elevator_init);
-void elevator_exit(struct elevator_queue *e)
+void elevator_exit(struct request_queue *q, struct elevator_queue *e)
{
mutex_lock(&e->sysfs_lock);
if (e->uses_mq && e->type->ops.mq.exit_sched)
- e->type->ops.mq.exit_sched(e);
+ blk_mq_exit_sched(q, e);
else if (!e->uses_mq && e->type->ops.sq.elevator_exit_fn)
e->type->ops.sq.elevator_exit_fn(e);
mutex_unlock(&e->sysfs_lock);
kobject_uevent(&e->kobj, KOBJ_REMOVE);
kobject_del(&e->kobj);
e->registered = 0;
+ /* Re-enable throttling in case elevator disabled it */
+ wbt_enable_default(q);
}
}
EXPORT_SYMBOL(elv_unregister_queue);
}
EXPORT_SYMBOL_GPL(elv_unregister);
+static int elevator_switch_mq(struct request_queue *q,
+ struct elevator_type *new_e)
+{
+ int ret;
+
+ blk_mq_freeze_queue(q);
+ blk_mq_quiesce_queue(q);
+
+ if (q->elevator) {
+ if (q->elevator->registered)
+ elv_unregister_queue(q);
+ ioc_clear_queue(q);
+ elevator_exit(q, q->elevator);
+ }
+
+ ret = blk_mq_init_sched(q, new_e);
+ if (ret)
+ goto out;
+
+ if (new_e) {
+ ret = elv_register_queue(q);
+ if (ret) {
+ elevator_exit(q, q->elevator);
+ goto out;
+ }
+ }
+
+ if (new_e)
+ blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name);
+ else
+ blk_add_trace_msg(q, "elv switch: none");
+
+out:
+ blk_mq_unfreeze_queue(q);
+ blk_mq_start_stopped_hw_queues(q, true);
+ return ret;
+
+}
+
/*
* switch to new_e io scheduler. be careful not to introduce deadlocks -
* we don't free the old io scheduler, before we have allocated what we
bool old_registered = false;
int err;
- if (q->mq_ops) {
- blk_mq_freeze_queue(q);
- blk_mq_quiesce_queue(q);
- }
+ if (q->mq_ops)
+ return elevator_switch_mq(q, new_e);
/*
* Turn on BYPASS and drain all requests w/ elevator private data.
if (old) {
old_registered = old->registered;
- if (old->uses_mq)
- blk_mq_sched_teardown(q);
-
- if (!q->mq_ops)
- blk_queue_bypass_start(q);
+ blk_queue_bypass_start(q);
/* unregister and clear all auxiliary data of the old elevator */
if (old_registered)
}
/* allocate, init and register new elevator */
- if (new_e) {
- if (new_e->uses_mq) {
- err = blk_mq_sched_setup(q);
- if (!err)
- err = new_e->ops.mq.init_sched(q, new_e);
- } else
- err = new_e->ops.sq.elevator_init_fn(q, new_e);
- if (err)
- goto fail_init;
+ err = new_e->ops.sq.elevator_init_fn(q, new_e);
+ if (err)
+ goto fail_init;
- err = elv_register_queue(q);
- if (err)
- goto fail_register;
- } else
- q->elevator = NULL;
+ err = elv_register_queue(q);
+ if (err)
+ goto fail_register;
/* done, kill the old one and finish */
if (old) {
- elevator_exit(old);
- if (!q->mq_ops)
- blk_queue_bypass_end(q);
+ elevator_exit(q, old);
+ blk_queue_bypass_end(q);
}
- if (q->mq_ops) {
- blk_mq_unfreeze_queue(q);
- blk_mq_start_stopped_hw_queues(q, true);
- }
-
- if (new_e)
- blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name);
- else
- blk_add_trace_msg(q, "elv switch: none");
+ blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name);
return 0;
fail_register:
- if (q->mq_ops)
- blk_mq_sched_teardown(q);
- elevator_exit(q->elevator);
+ elevator_exit(q, q->elevator);
fail_init:
/* switch failed, restore and re-register old elevator */
if (old) {
q->elevator = old;
elv_register_queue(q);
- if (!q->mq_ops)
- blk_queue_bypass_end(q);
- }
- if (q->mq_ops) {
- blk_mq_unfreeze_queue(q);
- blk_mq_start_stopped_hw_queues(q, true);
+ blk_queue_bypass_end(q);
}
return err;
}
EXPORT_SYMBOL(elevator_change);
+static inline bool elv_support_iosched(struct request_queue *q)
+{
+ if (q->mq_ops && q->tag_set && (q->tag_set->flags &
+ BLK_MQ_F_NO_SCHED))
+ return false;
+ return true;
+}
+
ssize_t elv_iosched_store(struct request_queue *q, const char *name,
size_t count)
{
int ret;
- if (!(q->mq_ops || q->request_fn))
+ if (!(q->mq_ops || q->request_fn) || !elv_support_iosched(q))
return count;
ret = __elevator_change(q, name);
len += sprintf(name+len, "[%s] ", elv->elevator_name);
continue;
}
- if (__e->uses_mq && q->mq_ops)
+ if (__e->uses_mq && q->mq_ops && elv_support_iosched(q))
len += sprintf(name+len, "%s ", __e->elevator_name);
else if (!__e->uses_mq && !q->mq_ops)
len += sprintf(name+len, "%s ", __e->elevator_name);
NULL
};
+static umode_t disk_visible(struct kobject *kobj, struct attribute *a, int n)
+{
+ struct device *dev = container_of(kobj, typeof(*dev), kobj);
+ struct gendisk *disk = dev_to_disk(dev);
+
+ if (a == &dev_attr_badblocks.attr && !disk->bb)
+ return 0;
+ return a->mode;
+}
+
static struct attribute_group disk_attr_group = {
.attrs = disk_attrs,
+ .is_visible = disk_visible,
};
static const struct attribute_group *disk_attr_groups[] = {
owner = disk->fops->owner;
if (owner && !try_module_get(owner))
return NULL;
- kobj = kobject_get(&disk_to_dev(disk)->kobj);
+ kobj = kobject_get_unless_zero(&disk_to_dev(disk)->kobj);
if (kobj == NULL) {
module_put(owner);
return NULL;
truncate_inode_pages_range(mapping, start, end);
return blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL,
- false);
+ BLKDEV_ZERO_NOUNMAP);
}
static int put_ushort(unsigned long arg, unsigned short val)
case BLKALIGNOFF:
return put_int(arg, bdev_alignment_offset(bdev));
case BLKDISCARDZEROES:
- return put_uint(arg, bdev_discard_zeroes_data(bdev));
+ return put_uint(arg, 0);
case BLKSECTGET:
max_sectors = min_t(unsigned int, USHRT_MAX,
queue_max_sectors(bdev_get_queue(bdev)));
int ioprio_best(unsigned short aprio, unsigned short bprio)
{
- unsigned short aclass;
- unsigned short bclass;
-
if (!ioprio_valid(aprio))
aprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
if (!ioprio_valid(bprio))
bprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
- aclass = IOPRIO_PRIO_CLASS(aprio);
- bclass = IOPRIO_PRIO_CLASS(bprio);
- if (aclass == bclass)
- return min(aprio, bprio);
- if (aclass > bclass)
- return bprio;
- else
- return aprio;
+ return min(aprio, bprio);
}
SYSCALL_DEFINE2(ioprio_get, int, which, int, who)
--- /dev/null
+/*
+ * The Kyber I/O scheduler. Controls latency by throttling queue depths using
+ * scalable techniques.
+ *
+ * Copyright (C) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <https://www.gnu.org/licenses/>.
+ */
+
+#include <linux/kernel.h>
+#include <linux/blkdev.h>
+#include <linux/blk-mq.h>
+#include <linux/elevator.h>
+#include <linux/module.h>
+#include <linux/sbitmap.h>
+
+#include "blk.h"
+#include "blk-mq.h"
+#include "blk-mq-sched.h"
+#include "blk-mq-tag.h"
+#include "blk-stat.h"
+
+/* Scheduling domains. */
+enum {
+ KYBER_READ,
+ KYBER_SYNC_WRITE,
+ KYBER_OTHER, /* Async writes, discard, etc. */
+ KYBER_NUM_DOMAINS,
+};
+
+enum {
+ KYBER_MIN_DEPTH = 256,
+
+ /*
+ * In order to prevent starvation of synchronous requests by a flood of
+ * asynchronous requests, we reserve 25% of requests for synchronous
+ * operations.
+ */
+ KYBER_ASYNC_PERCENT = 75,
+};
+
+/*
+ * Initial device-wide depths for each scheduling domain.
+ *
+ * Even for fast devices with lots of tags like NVMe, you can saturate
+ * the device with only a fraction of the maximum possible queue depth.
+ * So, we cap these to a reasonable value.
+ */
+static const unsigned int kyber_depth[] = {
+ [KYBER_READ] = 256,
+ [KYBER_SYNC_WRITE] = 128,
+ [KYBER_OTHER] = 64,
+};
+
+/*
+ * Scheduling domain batch sizes. We favor reads.
+ */
+static const unsigned int kyber_batch_size[] = {
+ [KYBER_READ] = 16,
+ [KYBER_SYNC_WRITE] = 8,
+ [KYBER_OTHER] = 8,
+};
+
+struct kyber_queue_data {
+ struct request_queue *q;
+
+ struct blk_stat_callback *cb;
+
+ /*
+ * The device is divided into multiple scheduling domains based on the
+ * request type. Each domain has a fixed number of in-flight requests of
+ * that type device-wide, limited by these tokens.
+ */
+ struct sbitmap_queue domain_tokens[KYBER_NUM_DOMAINS];
+
+ /*
+ * Async request percentage, converted to per-word depth for
+ * sbitmap_get_shallow().
+ */
+ unsigned int async_depth;
+
+ /* Target latencies in nanoseconds. */
+ u64 read_lat_nsec, write_lat_nsec;
+};
+
+struct kyber_hctx_data {
+ spinlock_t lock;
+ struct list_head rqs[KYBER_NUM_DOMAINS];
+ unsigned int cur_domain;
+ unsigned int batching;
+ wait_queue_t domain_wait[KYBER_NUM_DOMAINS];
+ atomic_t wait_index[KYBER_NUM_DOMAINS];
+};
+
+static int rq_sched_domain(const struct request *rq)
+{
+ unsigned int op = rq->cmd_flags;
+
+ if ((op & REQ_OP_MASK) == REQ_OP_READ)
+ return KYBER_READ;
+ else if ((op & REQ_OP_MASK) == REQ_OP_WRITE && op_is_sync(op))
+ return KYBER_SYNC_WRITE;
+ else
+ return KYBER_OTHER;
+}
+
+enum {
+ NONE = 0,
+ GOOD = 1,
+ GREAT = 2,
+ BAD = -1,
+ AWFUL = -2,
+};
+
+#define IS_GOOD(status) ((status) > 0)
+#define IS_BAD(status) ((status) < 0)
+
+static int kyber_lat_status(struct blk_stat_callback *cb,
+ unsigned int sched_domain, u64 target)
+{
+ u64 latency;
+
+ if (!cb->stat[sched_domain].nr_samples)
+ return NONE;
+
+ latency = cb->stat[sched_domain].mean;
+ if (latency >= 2 * target)
+ return AWFUL;
+ else if (latency > target)
+ return BAD;
+ else if (latency <= target / 2)
+ return GREAT;
+ else /* (latency <= target) */
+ return GOOD;
+}
+
+/*
+ * Adjust the read or synchronous write depth given the status of reads and
+ * writes. The goal is that the latencies of the two domains are fair (i.e., if
+ * one is good, then the other is good).
+ */
+static void kyber_adjust_rw_depth(struct kyber_queue_data *kqd,
+ unsigned int sched_domain, int this_status,
+ int other_status)
+{
+ unsigned int orig_depth, depth;
+
+ /*
+ * If this domain had no samples, or reads and writes are both good or
+ * both bad, don't adjust the depth.
+ */
+ if (this_status == NONE ||
+ (IS_GOOD(this_status) && IS_GOOD(other_status)) ||
+ (IS_BAD(this_status) && IS_BAD(other_status)))
+ return;
+
+ orig_depth = depth = kqd->domain_tokens[sched_domain].sb.depth;
+
+ if (other_status == NONE) {
+ depth++;
+ } else {
+ switch (this_status) {
+ case GOOD:
+ if (other_status == AWFUL)
+ depth -= max(depth / 4, 1U);
+ else
+ depth -= max(depth / 8, 1U);
+ break;
+ case GREAT:
+ if (other_status == AWFUL)
+ depth /= 2;
+ else
+ depth -= max(depth / 4, 1U);
+ break;
+ case BAD:
+ depth++;
+ break;
+ case AWFUL:
+ if (other_status == GREAT)
+ depth += 2;
+ else
+ depth++;
+ break;
+ }
+ }
+
+ depth = clamp(depth, 1U, kyber_depth[sched_domain]);
+ if (depth != orig_depth)
+ sbitmap_queue_resize(&kqd->domain_tokens[sched_domain], depth);
+}
+
+/*
+ * Adjust the depth of other requests given the status of reads and synchronous
+ * writes. As long as either domain is doing fine, we don't throttle, but if
+ * both domains are doing badly, we throttle heavily.
+ */
+static void kyber_adjust_other_depth(struct kyber_queue_data *kqd,
+ int read_status, int write_status,
+ bool have_samples)
+{
+ unsigned int orig_depth, depth;
+ int status;
+
+ orig_depth = depth = kqd->domain_tokens[KYBER_OTHER].sb.depth;
+
+ if (read_status == NONE && write_status == NONE) {
+ depth += 2;
+ } else if (have_samples) {
+ if (read_status == NONE)
+ status = write_status;
+ else if (write_status == NONE)
+ status = read_status;
+ else
+ status = max(read_status, write_status);
+ switch (status) {
+ case GREAT:
+ depth += 2;
+ break;
+ case GOOD:
+ depth++;
+ break;
+ case BAD:
+ depth -= max(depth / 4, 1U);
+ break;
+ case AWFUL:
+ depth /= 2;
+ break;
+ }
+ }
+
+ depth = clamp(depth, 1U, kyber_depth[KYBER_OTHER]);
+ if (depth != orig_depth)
+ sbitmap_queue_resize(&kqd->domain_tokens[KYBER_OTHER], depth);
+}
+
+/*
+ * Apply heuristics for limiting queue depths based on gathered latency
+ * statistics.
+ */
+static void kyber_stat_timer_fn(struct blk_stat_callback *cb)
+{
+ struct kyber_queue_data *kqd = cb->data;
+ int read_status, write_status;
+
+ read_status = kyber_lat_status(cb, KYBER_READ, kqd->read_lat_nsec);
+ write_status = kyber_lat_status(cb, KYBER_SYNC_WRITE, kqd->write_lat_nsec);
+
+ kyber_adjust_rw_depth(kqd, KYBER_READ, read_status, write_status);
+ kyber_adjust_rw_depth(kqd, KYBER_SYNC_WRITE, write_status, read_status);
+ kyber_adjust_other_depth(kqd, read_status, write_status,
+ cb->stat[KYBER_OTHER].nr_samples != 0);
+
+ /*
+ * Continue monitoring latencies if we aren't hitting the targets or
+ * we're still throttling other requests.
+ */
+ if (!blk_stat_is_active(kqd->cb) &&
+ ((IS_BAD(read_status) || IS_BAD(write_status) ||
+ kqd->domain_tokens[KYBER_OTHER].sb.depth < kyber_depth[KYBER_OTHER])))
+ blk_stat_activate_msecs(kqd->cb, 100);
+}
+
+static unsigned int kyber_sched_tags_shift(struct kyber_queue_data *kqd)
+{
+ /*
+ * All of the hardware queues have the same depth, so we can just grab
+ * the shift of the first one.
+ */
+ return kqd->q->queue_hw_ctx[0]->sched_tags->bitmap_tags.sb.shift;
+}
+
+static struct kyber_queue_data *kyber_queue_data_alloc(struct request_queue *q)
+{
+ struct kyber_queue_data *kqd;
+ unsigned int max_tokens;
+ unsigned int shift;
+ int ret = -ENOMEM;
+ int i;
+
+ kqd = kmalloc_node(sizeof(*kqd), GFP_KERNEL, q->node);
+ if (!kqd)
+ goto err;
+ kqd->q = q;
+
+ kqd->cb = blk_stat_alloc_callback(kyber_stat_timer_fn, rq_sched_domain,
+ KYBER_NUM_DOMAINS, kqd);
+ if (!kqd->cb)
+ goto err_kqd;
+
+ /*
+ * The maximum number of tokens for any scheduling domain is at least
+ * the queue depth of a single hardware queue. If the hardware doesn't
+ * have many tags, still provide a reasonable number.
+ */
+ max_tokens = max_t(unsigned int, q->tag_set->queue_depth,
+ KYBER_MIN_DEPTH);
+ for (i = 0; i < KYBER_NUM_DOMAINS; i++) {
+ WARN_ON(!kyber_depth[i]);
+ WARN_ON(!kyber_batch_size[i]);
+ ret = sbitmap_queue_init_node(&kqd->domain_tokens[i],
+ max_tokens, -1, false, GFP_KERNEL,
+ q->node);
+ if (ret) {
+ while (--i >= 0)
+ sbitmap_queue_free(&kqd->domain_tokens[i]);
+ goto err_cb;
+ }
+ sbitmap_queue_resize(&kqd->domain_tokens[i], kyber_depth[i]);
+ }
+
+ shift = kyber_sched_tags_shift(kqd);
+ kqd->async_depth = (1U << shift) * KYBER_ASYNC_PERCENT / 100U;
+
+ kqd->read_lat_nsec = 2000000ULL;
+ kqd->write_lat_nsec = 10000000ULL;
+
+ return kqd;
+
+err_cb:
+ blk_stat_free_callback(kqd->cb);
+err_kqd:
+ kfree(kqd);
+err:
+ return ERR_PTR(ret);
+}
+
+static int kyber_init_sched(struct request_queue *q, struct elevator_type *e)
+{
+ struct kyber_queue_data *kqd;
+ struct elevator_queue *eq;
+
+ eq = elevator_alloc(q, e);
+ if (!eq)
+ return -ENOMEM;
+
+ kqd = kyber_queue_data_alloc(q);
+ if (IS_ERR(kqd)) {
+ kobject_put(&eq->kobj);
+ return PTR_ERR(kqd);
+ }
+
+ eq->elevator_data = kqd;
+ q->elevator = eq;
+
+ blk_stat_add_callback(q, kqd->cb);
+
+ return 0;
+}
+
+static void kyber_exit_sched(struct elevator_queue *e)
+{
+ struct kyber_queue_data *kqd = e->elevator_data;
+ struct request_queue *q = kqd->q;
+ int i;
+
+ blk_stat_remove_callback(q, kqd->cb);
+
+ for (i = 0; i < KYBER_NUM_DOMAINS; i++)
+ sbitmap_queue_free(&kqd->domain_tokens[i]);
+ blk_stat_free_callback(kqd->cb);
+ kfree(kqd);
+}
+
+static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
+{
+ struct kyber_hctx_data *khd;
+ int i;
+
+ khd = kmalloc_node(sizeof(*khd), GFP_KERNEL, hctx->numa_node);
+ if (!khd)
+ return -ENOMEM;
+
+ spin_lock_init(&khd->lock);
+
+ for (i = 0; i < KYBER_NUM_DOMAINS; i++) {
+ INIT_LIST_HEAD(&khd->rqs[i]);
+ INIT_LIST_HEAD(&khd->domain_wait[i].task_list);
+ atomic_set(&khd->wait_index[i], 0);
+ }
+
+ khd->cur_domain = 0;
+ khd->batching = 0;
+
+ hctx->sched_data = khd;
+
+ return 0;
+}
+
+static void kyber_exit_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
+{
+ kfree(hctx->sched_data);
+}
+
+static int rq_get_domain_token(struct request *rq)
+{
+ return (long)rq->elv.priv[0];
+}
+
+static void rq_set_domain_token(struct request *rq, int token)
+{
+ rq->elv.priv[0] = (void *)(long)token;
+}
+
+static void rq_clear_domain_token(struct kyber_queue_data *kqd,
+ struct request *rq)
+{
+ unsigned int sched_domain;
+ int nr;
+
+ nr = rq_get_domain_token(rq);
+ if (nr != -1) {
+ sched_domain = rq_sched_domain(rq);
+ sbitmap_queue_clear(&kqd->domain_tokens[sched_domain], nr,
+ rq->mq_ctx->cpu);
+ }
+}
+
+static struct request *kyber_get_request(struct request_queue *q,
+ unsigned int op,
+ struct blk_mq_alloc_data *data)
+{
+ struct kyber_queue_data *kqd = q->elevator->elevator_data;
+ struct request *rq;
+
+ /*
+ * We use the scheduler tags as per-hardware queue queueing tokens.
+ * Async requests can be limited at this stage.
+ */
+ if (!op_is_sync(op))
+ data->shallow_depth = kqd->async_depth;
+
+ rq = __blk_mq_alloc_request(data, op);
+ if (rq)
+ rq_set_domain_token(rq, -1);
+ return rq;
+}
+
+static void kyber_put_request(struct request *rq)
+{
+ struct request_queue *q = rq->q;
+ struct kyber_queue_data *kqd = q->elevator->elevator_data;
+
+ rq_clear_domain_token(kqd, rq);
+ blk_mq_finish_request(rq);
+}
+
+static void kyber_completed_request(struct request *rq)
+{
+ struct request_queue *q = rq->q;
+ struct kyber_queue_data *kqd = q->elevator->elevator_data;
+ unsigned int sched_domain;
+ u64 now, latency, target;
+
+ /*
+ * Check if this request met our latency goal. If not, quickly gather
+ * some statistics and start throttling.
+ */
+ sched_domain = rq_sched_domain(rq);
+ switch (sched_domain) {
+ case KYBER_READ:
+ target = kqd->read_lat_nsec;
+ break;
+ case KYBER_SYNC_WRITE:
+ target = kqd->write_lat_nsec;
+ break;
+ default:
+ return;
+ }
+
+ /* If we are already monitoring latencies, don't check again. */
+ if (blk_stat_is_active(kqd->cb))
+ return;
+
+ now = __blk_stat_time(ktime_to_ns(ktime_get()));
+ if (now < blk_stat_time(&rq->issue_stat))
+ return;
+
+ latency = now - blk_stat_time(&rq->issue_stat);
+
+ if (latency > target)
+ blk_stat_activate_msecs(kqd->cb, 10);
+}
+
+static void kyber_flush_busy_ctxs(struct kyber_hctx_data *khd,
+ struct blk_mq_hw_ctx *hctx)
+{
+ LIST_HEAD(rq_list);
+ struct request *rq, *next;
+
+ blk_mq_flush_busy_ctxs(hctx, &rq_list);
+ list_for_each_entry_safe(rq, next, &rq_list, queuelist) {
+ unsigned int sched_domain;
+
+ sched_domain = rq_sched_domain(rq);
+ list_move_tail(&rq->queuelist, &khd->rqs[sched_domain]);
+ }
+}
+
+static int kyber_domain_wake(wait_queue_t *wait, unsigned mode, int flags,
+ void *key)
+{
+ struct blk_mq_hw_ctx *hctx = READ_ONCE(wait->private);
+
+ list_del_init(&wait->task_list);
+ blk_mq_run_hw_queue(hctx, true);
+ return 1;
+}
+
+static int kyber_get_domain_token(struct kyber_queue_data *kqd,
+ struct kyber_hctx_data *khd,
+ struct blk_mq_hw_ctx *hctx)
+{
+ unsigned int sched_domain = khd->cur_domain;
+ struct sbitmap_queue *domain_tokens = &kqd->domain_tokens[sched_domain];
+ wait_queue_t *wait = &khd->domain_wait[sched_domain];
+ struct sbq_wait_state *ws;
+ int nr;
+
+ nr = __sbitmap_queue_get(domain_tokens);
+ if (nr >= 0)
+ return nr;
+
+ /*
+ * If we failed to get a domain token, make sure the hardware queue is
+ * run when one becomes available. Note that this is serialized on
+ * khd->lock, but we still need to be careful about the waker.
+ */
+ if (list_empty_careful(&wait->task_list)) {
+ init_waitqueue_func_entry(wait, kyber_domain_wake);
+ wait->private = hctx;
+ ws = sbq_wait_ptr(domain_tokens,
+ &khd->wait_index[sched_domain]);
+ add_wait_queue(&ws->wait, wait);
+
+ /*
+ * Try again in case a token was freed before we got on the wait
+ * queue.
+ */
+ nr = __sbitmap_queue_get(domain_tokens);
+ }
+ return nr;
+}
+
+static struct request *
+kyber_dispatch_cur_domain(struct kyber_queue_data *kqd,
+ struct kyber_hctx_data *khd,
+ struct blk_mq_hw_ctx *hctx,
+ bool *flushed)
+{
+ struct list_head *rqs;
+ struct request *rq;
+ int nr;
+
+ rqs = &khd->rqs[khd->cur_domain];
+ rq = list_first_entry_or_null(rqs, struct request, queuelist);
+
+ /*
+ * If there wasn't already a pending request and we haven't flushed the
+ * software queues yet, flush the software queues and check again.
+ */
+ if (!rq && !*flushed) {
+ kyber_flush_busy_ctxs(khd, hctx);
+ *flushed = true;
+ rq = list_first_entry_or_null(rqs, struct request, queuelist);
+ }
+
+ if (rq) {
+ nr = kyber_get_domain_token(kqd, khd, hctx);
+ if (nr >= 0) {
+ khd->batching++;
+ rq_set_domain_token(rq, nr);
+ list_del_init(&rq->queuelist);
+ return rq;
+ }
+ }
+
+ /* There were either no pending requests or no tokens. */
+ return NULL;
+}
+
+static struct request *kyber_dispatch_request(struct blk_mq_hw_ctx *hctx)
+{
+ struct kyber_queue_data *kqd = hctx->queue->elevator->elevator_data;
+ struct kyber_hctx_data *khd = hctx->sched_data;
+ bool flushed = false;
+ struct request *rq;
+ int i;
+
+ spin_lock(&khd->lock);
+
+ /*
+ * First, if we are still entitled to batch, try to dispatch a request
+ * from the batch.
+ */
+ if (khd->batching < kyber_batch_size[khd->cur_domain]) {
+ rq = kyber_dispatch_cur_domain(kqd, khd, hctx, &flushed);
+ if (rq)
+ goto out;
+ }
+
+ /*
+ * Either,
+ * 1. We were no longer entitled to a batch.
+ * 2. The domain we were batching didn't have any requests.
+ * 3. The domain we were batching was out of tokens.
+ *
+ * Start another batch. Note that this wraps back around to the original
+ * domain if no other domains have requests or tokens.
+ */
+ khd->batching = 0;
+ for (i = 0; i < KYBER_NUM_DOMAINS; i++) {
+ if (khd->cur_domain == KYBER_NUM_DOMAINS - 1)
+ khd->cur_domain = 0;
+ else
+ khd->cur_domain++;
+
+ rq = kyber_dispatch_cur_domain(kqd, khd, hctx, &flushed);
+ if (rq)
+ goto out;
+ }
+
+ rq = NULL;
+out:
+ spin_unlock(&khd->lock);
+ return rq;
+}
+
+static bool kyber_has_work(struct blk_mq_hw_ctx *hctx)
+{
+ struct kyber_hctx_data *khd = hctx->sched_data;
+ int i;
+
+ for (i = 0; i < KYBER_NUM_DOMAINS; i++) {
+ if (!list_empty_careful(&khd->rqs[i]))
+ return true;
+ }
+ return false;
+}
+
+#define KYBER_LAT_SHOW_STORE(op) \
+static ssize_t kyber_##op##_lat_show(struct elevator_queue *e, \
+ char *page) \
+{ \
+ struct kyber_queue_data *kqd = e->elevator_data; \
+ \
+ return sprintf(page, "%llu\n", kqd->op##_lat_nsec); \
+} \
+ \
+static ssize_t kyber_##op##_lat_store(struct elevator_queue *e, \
+ const char *page, size_t count) \
+{ \
+ struct kyber_queue_data *kqd = e->elevator_data; \
+ unsigned long long nsec; \
+ int ret; \
+ \
+ ret = kstrtoull(page, 10, &nsec); \
+ if (ret) \
+ return ret; \
+ \
+ kqd->op##_lat_nsec = nsec; \
+ \
+ return count; \
+}
+KYBER_LAT_SHOW_STORE(read);
+KYBER_LAT_SHOW_STORE(write);
+#undef KYBER_LAT_SHOW_STORE
+
+#define KYBER_LAT_ATTR(op) __ATTR(op##_lat_nsec, 0644, kyber_##op##_lat_show, kyber_##op##_lat_store)
+static struct elv_fs_entry kyber_sched_attrs[] = {
+ KYBER_LAT_ATTR(read),
+ KYBER_LAT_ATTR(write),
+ __ATTR_NULL
+};
+#undef KYBER_LAT_ATTR
+
+static struct elevator_type kyber_sched = {
+ .ops.mq = {
+ .init_sched = kyber_init_sched,
+ .exit_sched = kyber_exit_sched,
+ .init_hctx = kyber_init_hctx,
+ .exit_hctx = kyber_exit_hctx,
+ .get_request = kyber_get_request,
+ .put_request = kyber_put_request,
+ .completed_request = kyber_completed_request,
+ .dispatch_request = kyber_dispatch_request,
+ .has_work = kyber_has_work,
+ },
+ .uses_mq = true,
+ .elevator_attrs = kyber_sched_attrs,
+ .elevator_name = "kyber",
+ .elevator_owner = THIS_MODULE,
+};
+
+static int __init kyber_init(void)
+{
+ return elv_register(&kyber_sched);
+}
+
+static void __exit kyber_exit(void)
+{
+ elv_unregister(&kyber_sched);
+}
+
+module_init(kyber_init);
+module_exit(kyber_exit);
+
+MODULE_AUTHOR("Omar Sandoval");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Kyber I/O scheduler");
if (disk->fops->revalidate_disk)
disk->fops->revalidate_disk(disk);
- blk_integrity_revalidate(disk);
check_disk_size_change(disk, bdev);
bdev->bd_invalidated = 0;
if (!get_capacity(disk) || !(state = check_partition(disk, bdev)))
/*
* fill in all the output members
*/
- hdr->status = rq->errors & 0xff;
- hdr->masked_status = status_byte(rq->errors);
- hdr->msg_status = msg_byte(rq->errors);
- hdr->host_status = host_byte(rq->errors);
- hdr->driver_status = driver_byte(rq->errors);
+ hdr->status = req->result & 0xff;
+ hdr->masked_status = status_byte(req->result);
+ hdr->msg_status = msg_byte(req->result);
+ hdr->host_status = host_byte(req->result);
+ hdr->driver_status = driver_byte(req->result);
hdr->info = 0;
if (hdr->masked_status || hdr->host_status || hdr->driver_status)
hdr->info |= SG_INFO_CHECK;
goto out_free_cdb;
bio = rq->bio;
- rq->retries = 0;
+ req->retries = 0;
start_time = jiffies;
goto error;
/* default. possible overriden later */
- rq->retries = 5;
+ req->retries = 5;
switch (opcode) {
case SEND_DIAGNOSTIC:
case FORMAT_UNIT:
rq->timeout = FORMAT_UNIT_TIMEOUT;
- rq->retries = 1;
+ req->retries = 1;
break;
case START_STOP:
rq->timeout = START_STOP_TIMEOUT;
break;
case READ_DEFECT_DATA:
rq->timeout = READ_DEFECT_DATA_TIMEOUT;
- rq->retries = 1;
+ req->retries = 1;
break;
default:
rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
blk_execute_rq(q, disk, rq, 0);
- err = rq->errors & 0xff; /* only 8 bit SCSI status */
+ err = req->result & 0xff; /* only 8 bit SCSI status */
if (err) {
if (req->sense_len && req->sense) {
bytes = (OMAX_SB_LEN > req->sense_len) ?
scsi_req(rq)->cmd[0] = cmd;
scsi_req(rq)->cmd[4] = data;
scsi_req(rq)->cmd_len = 6;
- err = blk_execute_rq(q, bd_disk, rq, 0);
+ blk_execute_rq(q, bd_disk, rq, 0);
+ err = scsi_req(rq)->result ? -EIO : 0;
blk_put_request(rq);
return err;
u8 flags = tper->supported_features;
if (!(flags & TPER_SYNC_SUPPORTED)) {
- pr_err("TPer sync not supported. flags = %d\n",
- tper->supported_features);
+ pr_debug("TPer sync not supported. flags = %d\n",
+ tper->supported_features);
return false;
}
u32 nlo = be32_to_cpu(sum->num_locking_objects);
if (nlo == 0) {
- pr_err("Need at least one locking object.\n");
+ pr_debug("Need at least one locking object.\n");
return false;
}
error = step->fn(dev, step->data);
if (error) {
- pr_err("Error on step function: %d with error %d: %s\n",
- state, error,
- opal_error_to_human(error));
+ pr_debug("Error on step function: %d with error %d: %s\n",
+ state, error,
+ opal_error_to_human(error));
/* For each OPAL command we do a discovery0 then we
* start some sort of session.
print_buffer(dev->resp, hlen);
if (hlen > IO_BUFFER_LENGTH - sizeof(*hdr)) {
- pr_warn("Discovery length overflows buffer (%zu+%u)/%u\n",
- sizeof(*hdr), hlen, IO_BUFFER_LENGTH);
+ pr_debug("Discovery length overflows buffer (%zu+%u)/%u\n",
+ sizeof(*hdr), hlen, IO_BUFFER_LENGTH);
return -EFAULT;
}
if (*err)
return;
if (cmd->pos >= IO_BUFFER_LENGTH - 1) {
- pr_err("Error adding u8: end of buffer.\n");
+ pr_debug("Error adding u8: end of buffer.\n");
*err = -ERANGE;
return;
}
len = DIV_ROUND_UP(msb, 4);
if (cmd->pos >= IO_BUFFER_LENGTH - len - 1) {
- pr_err("Error adding u64: end of buffer.\n");
+ pr_debug("Error adding u64: end of buffer.\n");
*err = -ERANGE;
return;
}
}
if (len >= IO_BUFFER_LENGTH - cmd->pos - header_len) {
- pr_err("Error adding bytestring: end of buffer.\n");
+ pr_debug("Error adding bytestring: end of buffer.\n");
*err = -ERANGE;
return;
}
static int build_locking_range(u8 *buffer, size_t length, u8 lr)
{
if (length > OPAL_UID_LENGTH) {
- pr_err("Can't build locking range. Length OOB\n");
+ pr_debug("Can't build locking range. Length OOB\n");
return -ERANGE;
}
static int build_locking_user(u8 *buffer, size_t length, u8 lr)
{
if (length > OPAL_UID_LENGTH) {
- pr_err("Can't build locking range user, Length OOB\n");
+ pr_debug("Can't build locking range user, Length OOB\n");
return -ERANGE;
}
add_token_u8(&err, cmd, OPAL_ENDLIST);
if (err) {
- pr_err("Error finalizing command.\n");
+ pr_debug("Error finalizing command.\n");
return -EFAULT;
}
hdr->subpkt.length = cpu_to_be32(cmd->pos - sizeof(*hdr));
while (cmd->pos % 4) {
if (cmd->pos >= IO_BUFFER_LENGTH) {
- pr_err("Error: Buffer overrun\n");
+ pr_debug("Error: Buffer overrun\n");
return -ERANGE;
}
cmd->cmd[cmd->pos++] = 0;
const struct opal_resp_tok *tok;
if (n >= resp->num) {
- pr_err("Token number doesn't exist: %d, resp: %d\n",
- n, resp->num);
+ pr_debug("Token number doesn't exist: %d, resp: %d\n",
+ n, resp->num);
return ERR_PTR(-EINVAL);
}
tok = &resp->toks[n];
if (tok->len == 0) {
- pr_err("Token length must be non-zero\n");
+ pr_debug("Token length must be non-zero\n");
return ERR_PTR(-EINVAL);
}
tok->type = OPAL_DTA_TOKENID_UINT;
if (tok->len > 9) {
- pr_warn("uint64 with more than 8 bytes\n");
+ pr_debug("uint64 with more than 8 bytes\n");
return -EINVAL;
}
for (i = tok->len - 1; i > 0; i--) {
if (clen == 0 || plen == 0 || slen == 0 ||
slen > IO_BUFFER_LENGTH - sizeof(*hdr)) {
- pr_err("Bad header length. cp: %u, pkt: %u, subpkt: %u\n",
- clen, plen, slen);
+ pr_debug("Bad header length. cp: %u, pkt: %u, subpkt: %u\n",
+ clen, plen, slen);
print_buffer(pos, sizeof(*hdr));
return -EINVAL;
}
}
if (num_entries == 0) {
- pr_err("Couldn't parse response.\n");
+ pr_debug("Couldn't parse response.\n");
return -EINVAL;
}
resp->num = num_entries;
{
*store = NULL;
if (!resp) {
- pr_err("Response is NULL\n");
+ pr_debug("Response is NULL\n");
return 0;
}
if (n > resp->num) {
- pr_err("Response has %d tokens. Can't access %d\n",
- resp->num, n);
+ pr_debug("Response has %d tokens. Can't access %d\n",
+ resp->num, n);
return 0;
}
if (resp->toks[n].type != OPAL_DTA_TOKENID_BYTESTRING) {
- pr_err("Token is not a byte string!\n");
+ pr_debug("Token is not a byte string!\n");
return 0;
}
static u64 response_get_u64(const struct parsed_resp *resp, int n)
{
if (!resp) {
- pr_err("Response is NULL\n");
+ pr_debug("Response is NULL\n");
return 0;
}
if (n > resp->num) {
- pr_err("Response has %d tokens. Can't access %d\n",
- resp->num, n);
+ pr_debug("Response has %d tokens. Can't access %d\n",
+ resp->num, n);
return 0;
}
if (resp->toks[n].type != OPAL_DTA_TOKENID_UINT) {
- pr_err("Token is not unsigned it: %d\n",
- resp->toks[n].type);
+ pr_debug("Token is not unsigned it: %d\n",
+ resp->toks[n].type);
return 0;
}
if (!(resp->toks[n].width == OPAL_WIDTH_TINY ||
resp->toks[n].width == OPAL_WIDTH_SHORT)) {
- pr_err("Atom is not short or tiny: %d\n",
- resp->toks[n].width);
+ pr_debug("Atom is not short or tiny: %d\n",
+ resp->toks[n].width);
return 0;
}
error = response_parse(dev->resp, IO_BUFFER_LENGTH, &dev->parsed);
if (error) {
- pr_err("Couldn't parse response.\n");
+ pr_debug("Couldn't parse response.\n");
return error;
}
tsn = response_get_u64(&dev->parsed, 5);
if (hsn == 0 && tsn == 0) {
- pr_err("Couldn't authenticate session\n");
+ pr_debug("Couldn't authenticate session\n");
return -EPERM;
}
ret = cmd_finalize(dev, dev->hsn, dev->tsn);
if (ret) {
- pr_err("Error finalizing command buffer: %d\n", ret);
+ pr_debug("Error finalizing command buffer: %d\n", ret);
return ret;
}
add_token_u8(&err, dev, OPAL_ENDLIST);
if (err) {
- pr_err("Error building gen key command\n");
+ pr_debug("Error building gen key command\n");
return err;
}
return error;
keylen = response_get_string(&dev->parsed, 4, &activekey);
if (!activekey) {
- pr_err("%s: Couldn't extract the Activekey from the response\n",
- __func__);
+ pr_debug("%s: Couldn't extract the Activekey from the response\n",
+ __func__);
return OPAL_INVAL_PARAM;
}
dev->prev_data = kmemdup(activekey, keylen, GFP_KERNEL);
add_token_u8(&err, dev, OPAL_ENDLIST);
add_token_u8(&err, dev, OPAL_ENDLIST);
if (err) {
- pr_err("Error building get active key command\n");
+ pr_debug("Error building get active key command\n");
return err;
}
err = generic_lr_enable_disable(dev, uid, !!setup->RLE, !!setup->WLE,
0, 0);
if (err)
- pr_err("Failed to create enable global lr command\n");
+ pr_debug("Failed to create enable global lr command\n");
return err;
}
}
if (err) {
- pr_err("Error building Setup Locking range command.\n");
+ pr_debug("Error building Setup Locking range command.\n");
return err;
}
u32 hsn;
int err = 0;
- if (key == NULL && auth != OPAL_ANYBODY_UID) {
- pr_err("%s: Attempted to open ADMIN_SP Session without a Host" \
- "Challenge, and not as the Anybody UID\n", __func__);
+ if (key == NULL && auth != OPAL_ANYBODY_UID)
return OPAL_INVAL_PARAM;
- }
clear_opal_cmd(dev);
add_token_u8(&err, dev, OPAL_ENDLIST);
break;
default:
- pr_err("Cannot start Admin SP session with auth %d\n", auth);
+ pr_debug("Cannot start Admin SP session with auth %d\n", auth);
return OPAL_INVAL_PARAM;
}
if (err) {
- pr_err("Error building start adminsp session command.\n");
+ pr_debug("Error building start adminsp session command.\n");
return err;
}
add_token_u8(&err, dev, OPAL_ENDLIST);
if (err) {
- pr_err("Error building STARTSESSION command.\n");
+ pr_debug("Error building STARTSESSION command.\n");
return err;
}
add_token_u8(&err, dev, OPAL_STARTLIST);
add_token_u8(&err, dev, OPAL_ENDLIST);
if (err) {
- pr_err("Error building REVERT TPER command.\n");
+ pr_debug("Error building REVERT TPER command.\n");
return err;
}
add_token_u8(&err, dev, OPAL_ENDLIST);
if (err) {
- pr_err("Error building Activate UserN command.\n");
+ pr_debug("Error building Activate UserN command.\n");
return err;
}
add_token_u8(&err, dev, OPAL_ENDLIST);
if (err) {
- pr_err("Error building Erase Locking Range Command.\n");
+ pr_debug("Error building Erase Locking Range Command.\n");
return err;
}
return finalize_and_send(dev, parse_and_check_status);
add_token_u8(&err, dev, OPAL_ENDLIST);
if (err) {
- pr_err("Error Building set MBR Done command\n");
+ pr_debug("Error Building set MBR Done command\n");
return err;
}
add_token_u8(&err, dev, OPAL_ENDLIST);
if (err) {
- pr_err("Error Building set MBR done command\n");
+ pr_debug("Error Building set MBR done command\n");
return err;
}
if (generic_pw_cmd(usr->opal_key.key, usr->opal_key.key_len,
cpin_uid, dev)) {
- pr_err("Error building set password command.\n");
+ pr_debug("Error building set password command.\n");
return -ERANGE;
}
memcpy(cpin_uid, opaluid[OPAL_C_PIN_SID], OPAL_UID_LENGTH);
if (generic_pw_cmd(key->key, key->key_len, cpin_uid, dev)) {
- pr_err("Error building Set SID cpin\n");
+ pr_debug("Error building Set SID cpin\n");
return -ERANGE;
}
return finalize_and_send(dev, parse_and_check_status);
add_token_u8(&err, dev, OPAL_ENDLIST);
if (err) {
- pr_err("Error building add user to locking range command.\n");
+ pr_debug("Error building add user to locking range command.\n");
return err;
}
/* vars are initalized to locked */
break;
default:
- pr_err("Tried to set an invalid locking state... returning to uland\n");
+ pr_debug("Tried to set an invalid locking state... returning to uland\n");
return OPAL_INVAL_PARAM;
}
add_token_u8(&err, dev, OPAL_ENDLIST);
if (err) {
- pr_err("Error building SET command.\n");
+ pr_debug("Error building SET command.\n");
return err;
}
return finalize_and_send(dev, parse_and_check_status);
/* vars are initalized to locked */
break;
default:
- pr_err("Tried to set an invalid locking state.\n");
+ pr_debug("Tried to set an invalid locking state.\n");
return OPAL_INVAL_PARAM;
}
ret = generic_lr_enable_disable(dev, lr_buffer, 1, 1,
read_locked, write_locked);
if (ret < 0) {
- pr_err("Error building SET command.\n");
+ pr_debug("Error building SET command.\n");
return ret;
}
return finalize_and_send(dev, parse_and_check_status);
}
if (err) {
- pr_err("Error building Activate LockingSP command.\n");
+ pr_debug("Error building Activate LockingSP command.\n");
return err;
}
/* 0x08 is Manufacured Inactive */
/* 0x09 is Manufactured */
if (lc_status != OPAL_MANUFACTURED_INACTIVE) {
- pr_err("Couldn't determine the status of the Lifcycle state\n");
+ pr_debug("Couldn't determine the status of the Lifecycle state\n");
return -ENODEV;
}
add_token_u8(&err, dev, OPAL_ENDLIST);
if (err) {
- pr_err("Error Building GET Lifecycle Status command\n");
+ pr_debug("Error Building GET Lifecycle Status command\n");
return err;
}
strlen = response_get_string(&dev->parsed, 4, &msid_pin);
if (!msid_pin) {
- pr_err("%s: Couldn't extract PIN from response\n", __func__);
+ pr_debug("%s: Couldn't extract PIN from response\n", __func__);
return OPAL_INVAL_PARAM;
}
add_token_u8(&err, dev, OPAL_ENDLIST);
if (err) {
- pr_err("Error building Get MSID CPIN PIN command.\n");
+ pr_debug("Error building Get MSID CPIN PIN command.\n");
return err;
}
if (lk_unlk->l_state != OPAL_RO &&
lk_unlk->l_state != OPAL_RW) {
- pr_err("Locking state was not RO or RW\n");
+ pr_debug("Locking state was not RO or RW\n");
return -EINVAL;
}
if (lk_unlk->session.who < OPAL_USER1 ||
lk_unlk->session.who > OPAL_USER9) {
- pr_err("Authority was not within the range of users: %d\n",
- lk_unlk->session.who);
+ pr_debug("Authority was not within the range of users: %d\n",
+ lk_unlk->session.who);
return -EINVAL;
}
if (lk_unlk->session.sum) {
- pr_err("%s not supported in sum. Use setup locking range\n",
- __func__);
+ pr_debug("%s not supported in sum. Use setup locking range\n",
+ __func__);
return -EINVAL;
}
/* We can't activate Admin1 it's active as manufactured */
if (opal_session->who < OPAL_USER1 ||
opal_session->who > OPAL_USER9) {
- pr_err("Who was not a valid user: %d\n", opal_session->who);
+ pr_debug("Who was not a valid user: %d\n", opal_session->who);
return -EINVAL;
}
ret = __opal_lock_unlock(dev, &suspend->unlk);
if (ret) {
- pr_warn("Failed to unlock LR %hhu with sum %d\n",
- suspend->unlk.session.opal_key.lr,
- suspend->unlk.session.sum);
+ pr_debug("Failed to unlock LR %hhu with sum %d\n",
+ suspend->unlk.session.opal_key.lr,
+ suspend->unlk.session.sum);
was_failure = true;
}
}
return -EACCES;
if (!dev)
return -ENOTSUPP;
- if (!dev->supported) {
- pr_err("Not supported\n");
+ if (!dev->supported)
return -ENOTSUPP;
- }
p = memdup_user(arg, _IOC_SIZE(cmd));
if (IS_ERR(p))
ret = opal_secure_erase_locking_range(dev, p);
break;
default:
- pr_warn("No such Opal Ioctl %u\n", cmd);
+ break;
}
kfree(p);
return t10_pi_verify(iter, t10_pi_ip_fn, 3);
}
-struct blk_integrity_profile t10_pi_type1_crc = {
+const struct blk_integrity_profile t10_pi_type1_crc = {
.name = "T10-DIF-TYPE1-CRC",
.generate_fn = t10_pi_type1_generate_crc,
.verify_fn = t10_pi_type1_verify_crc,
};
EXPORT_SYMBOL(t10_pi_type1_crc);
-struct blk_integrity_profile t10_pi_type1_ip = {
+const struct blk_integrity_profile t10_pi_type1_ip = {
.name = "T10-DIF-TYPE1-IP",
.generate_fn = t10_pi_type1_generate_ip,
.verify_fn = t10_pi_type1_verify_ip,
};
EXPORT_SYMBOL(t10_pi_type1_ip);
-struct blk_integrity_profile t10_pi_type3_crc = {
+const struct blk_integrity_profile t10_pi_type3_crc = {
.name = "T10-DIF-TYPE3-CRC",
.generate_fn = t10_pi_type3_generate_crc,
.verify_fn = t10_pi_type3_verify_crc,
};
EXPORT_SYMBOL(t10_pi_type3_crc);
-struct blk_integrity_profile t10_pi_type3_ip = {
+const struct blk_integrity_profile t10_pi_type3_ip = {
.name = "T10-DIF-TYPE3-IP",
.generate_fn = t10_pi_type3_generate_ip,
.verify_fn = t10_pi_type3_verify_ip,
crypto_completion_t complete;
void *data;
u8 *result;
+ u32 flags;
void *ubuf[] CRYPTO_MINALIGN_ATTR;
};
priv->result = req->result;
priv->complete = req->base.complete;
priv->data = req->base.data;
+ priv->flags = req->base.flags;
+
/*
* WARNING: We do not backup req->priv here! The req->priv
* is for internal use of the Crypto API and the
return 0;
}
-static void ahash_restore_req(struct ahash_request *req)
+static void ahash_restore_req(struct ahash_request *req, int err)
{
struct ahash_request_priv *priv = req->priv;
+ if (!err)
+ memcpy(priv->result, req->result,
+ crypto_ahash_digestsize(crypto_ahash_reqtfm(req)));
+
/* Restore the original crypto request. */
req->result = priv->result;
- req->base.complete = priv->complete;
- req->base.data = priv->data;
+
+ ahash_request_set_callback(req, priv->flags,
+ priv->complete, priv->data);
req->priv = NULL;
/* Free the req->priv.priv from the ADJUSTED request. */
kzfree(priv);
}
-static void ahash_op_unaligned_finish(struct ahash_request *req, int err)
+static void ahash_notify_einprogress(struct ahash_request *req)
{
struct ahash_request_priv *priv = req->priv;
+ struct crypto_async_request oreq;
- if (err == -EINPROGRESS)
- return;
-
- if (!err)
- memcpy(priv->result, req->result,
- crypto_ahash_digestsize(crypto_ahash_reqtfm(req)));
+ oreq.data = priv->data;
- ahash_restore_req(req);
+ priv->complete(&oreq, -EINPROGRESS);
}
static void ahash_op_unaligned_done(struct crypto_async_request *req, int err)
{
struct ahash_request *areq = req->data;
+ if (err == -EINPROGRESS) {
+ ahash_notify_einprogress(areq);
+ return;
+ }
+
/*
* Restore the original request, see ahash_op_unaligned() for what
* goes where.
*/
/* First copy req->result into req->priv.result */
- ahash_op_unaligned_finish(areq, err);
+ ahash_restore_req(areq, err);
/* Complete the ORIGINAL request. */
areq->base.complete(&areq->base, err);
return err;
err = op(req);
- ahash_op_unaligned_finish(req, err);
+ if (err == -EINPROGRESS ||
+ (err == -EBUSY && (ahash_request_flags(req) &
+ CRYPTO_TFM_REQ_MAY_BACKLOG)))
+ return err;
+
+ ahash_restore_req(req, err);
return err;
}
}
EXPORT_SYMBOL_GPL(crypto_ahash_digest);
-static void ahash_def_finup_finish2(struct ahash_request *req, int err)
+static void ahash_def_finup_done2(struct crypto_async_request *req, int err)
{
- struct ahash_request_priv *priv = req->priv;
+ struct ahash_request *areq = req->data;
if (err == -EINPROGRESS)
return;
- if (!err)
- memcpy(priv->result, req->result,
- crypto_ahash_digestsize(crypto_ahash_reqtfm(req)));
-
- ahash_restore_req(req);
-}
-
-static void ahash_def_finup_done2(struct crypto_async_request *req, int err)
-{
- struct ahash_request *areq = req->data;
-
- ahash_def_finup_finish2(areq, err);
+ ahash_restore_req(areq, err);
areq->base.complete(&areq->base, err);
}
goto out;
req->base.complete = ahash_def_finup_done2;
- req->base.flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+
err = crypto_ahash_reqtfm(req)->final(req);
+ if (err == -EINPROGRESS ||
+ (err == -EBUSY && (ahash_request_flags(req) &
+ CRYPTO_TFM_REQ_MAY_BACKLOG)))
+ return err;
out:
- ahash_def_finup_finish2(req, err);
+ ahash_restore_req(req, err);
return err;
}
{
struct ahash_request *areq = req->data;
+ if (err == -EINPROGRESS) {
+ ahash_notify_einprogress(areq);
+ return;
+ }
+
+ areq->base.flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+
err = ahash_def_finup_finish1(areq, err);
+ if (areq->priv)
+ return;
areq->base.complete(&areq->base, err);
}
return err;
err = tfm->update(req);
+ if (err == -EINPROGRESS ||
+ (err == -EBUSY && (ahash_request_flags(req) &
+ CRYPTO_TFM_REQ_MAY_BACKLOG)))
+ return err;
+
return ahash_def_finup_finish1(req, err);
}
struct aead_async_rsgl first_rsgl;
struct list_head list;
struct kiocb *iocb;
+ struct sock *sk;
unsigned int tsgls;
char iv[];
};
static void aead_async_cb(struct crypto_async_request *_req, int err)
{
- struct sock *sk = _req->data;
- struct alg_sock *ask = alg_sk(sk);
- struct aead_ctx *ctx = ask->private;
- struct crypto_aead *tfm = crypto_aead_reqtfm(&ctx->aead_req);
- struct aead_request *req = aead_request_cast(_req);
+ struct aead_request *req = _req->data;
+ struct crypto_aead *tfm = crypto_aead_reqtfm(req);
struct aead_async_req *areq = GET_ASYM_REQ(req, tfm);
+ struct sock *sk = areq->sk;
struct scatterlist *sg = areq->tsgl;
struct aead_async_rsgl *rsgl;
struct kiocb *iocb = areq->iocb;
memset(&areq->first_rsgl, '\0', sizeof(areq->first_rsgl));
INIT_LIST_HEAD(&areq->list);
areq->iocb = msg->msg_iocb;
+ areq->sk = sk;
memcpy(areq->iv, ctx->iv, crypto_aead_ivsize(tfm));
aead_request_set_tfm(req, tfm);
aead_request_set_ad(req, ctx->aead_assoclen);
aead_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
- aead_async_cb, sk);
+ aead_async_cb, req);
used -= ctx->aead_assoclen;
/* take over all tx sgls from ctx */
struct rctx *rctx;
rctx = skcipher_request_ctx(req);
+
+ if (err == -EINPROGRESS) {
+ if (rctx->left != req->cryptlen)
+ return;
+ goto out;
+ }
+
subreq = &rctx->subreq;
subreq->base.flags &= CRYPTO_TFM_REQ_MAY_BACKLOG;
if (rctx->left)
return;
+out:
skcipher_request_complete(req, err);
}
struct rctx *rctx;
rctx = skcipher_request_ctx(req);
+
+ if (err == -EINPROGRESS) {
+ if (rctx->left != req->cryptlen)
+ return;
+ goto out;
+ }
+
subreq = &rctx->subreq;
subreq->base.flags &= CRYPTO_TFM_REQ_MAY_BACKLOG;
if (rctx->left)
return;
+out:
skcipher_request_complete(req, err);
}
struct rctx *rctx;
rctx = skcipher_request_ctx(req);
+
+ if (err == -EINPROGRESS) {
+ if (rctx->left != req->cryptlen)
+ return;
+ goto out;
+ }
+
subreq = &rctx->subreq;
subreq->base.flags &= CRYPTO_TFM_REQ_MAY_BACKLOG;
if (rctx->left)
return;
+out:
skcipher_request_complete(req, err);
}
struct rctx *rctx;
rctx = skcipher_request_ctx(req);
+
+ if (err == -EINPROGRESS) {
+ if (rctx->left != req->cryptlen)
+ return;
+ goto out;
+ }
+
subreq = &rctx->subreq;
subreq->base.flags &= CRYPTO_TFM_REQ_MAY_BACKLOG;
if (rctx->left)
return;
+out:
skcipher_request_complete(req, err);
}
config ACPI_IPMI
tristate "IPMI"
- depends on IPMI_SI
+ depends on IPMI_HANDLER
default n
help
This driver enables the ACPI to access the BMC controller. And it
config ACPI_BGRT
bool "Boottime Graphics Resource Table support"
- depends on EFI && X86
+ depends on EFI && (X86 || ARM64)
help
This driver adds support for exposing the ACPI Boottime Graphics
Resource Table, which allows the operating system to obtain
config ACPI_EXTLOG
tristate "Extended Error Log support"
- depends on X86_MCE && X86_LOCAL_APIC
+ depends on X86_MCE && X86_LOCAL_APIC && EDAC
select UEFI_CPER
- select RAS
default n
help
Certain usages such as Predictive Failure Analysis (PFA) require
config XPOWER_PMIC_OPREGION
bool "ACPI operation region support for XPower AXP288 PMIC"
- depends on AXP288_ADC = y
+ depends on MFD_AXP20X_I2C
help
This config adds ACPI operation region support for XPower AXP288 PMIC.
help
This config adds ACPI operation region support for BXT WhiskeyCove PMIC.
+config CHT_WC_PMIC_OPREGION
+ bool "ACPI operation region support for CHT Whiskey Cove PMIC"
+ depends on INTEL_SOC_PMIC_CHTWC
+ help
+ This config adds ACPI operation region support for CHT Whiskey Cove PMIC.
+
endif
config ACPI_CONFIGFS
obj-$(CONFIG_CRC_PMIC_OPREGION) += pmic/intel_pmic_crc.o
obj-$(CONFIG_XPOWER_PMIC_OPREGION) += pmic/intel_pmic_xpower.o
obj-$(CONFIG_BXT_WC_PMIC_OPREGION) += pmic/intel_pmic_bxtwc.o
+obj-$(CONFIG_CHT_WC_PMIC_OPREGION) += pmic/intel_pmic_chtwc.o
obj-$(CONFIG_ACPI_CONFIGFS) += acpi_configfs.o
static int acpi_ac_remove(struct acpi_device *device);
static void acpi_ac_notify(struct acpi_device *device, u32 event);
+struct acpi_ac_bl {
+ const char *hid;
+ int hrv;
+};
+
static const struct acpi_device_id ac_device_ids[] = {
{"ACPI0003", 0},
{"", 0},
};
MODULE_DEVICE_TABLE(acpi, ac_device_ids);
+/* Lists of PMIC ACPI HIDs with an (often better) native charger driver */
+static const struct acpi_ac_bl acpi_ac_blacklist[] = {
+ { "INT33F4", -1 }, /* X-Powers AXP288 PMIC */
+ { "INT34D3", 3 }, /* Intel Cherrytrail Whiskey Cove PMIC */
+};
+
#ifdef CONFIG_PM_SLEEP
static int acpi_ac_resume(struct device *dev);
#endif
static int __init acpi_ac_init(void)
{
+ unsigned int i;
int result;
if (acpi_disabled)
return -ENODEV;
+ for (i = 0; i < ARRAY_SIZE(acpi_ac_blacklist); i++)
+ if (acpi_dev_present(acpi_ac_blacklist[i].hid, "1",
+ acpi_ac_blacklist[i].hrv)) {
+ pr_info(PREFIX "AC: found native %s PMIC, not loading\n",
+ acpi_ac_blacklist[i].hid);
+ return -ENODEV;
+ }
+
#ifdef CONFIG_ACPI_PROCFS_POWER
acpi_ac_dir = acpi_lock_ac_dir();
if (!acpi_ac_dir)
if (!(cap & MCG_ELOG_P) || !extlog_get_l1addr())
return -ENODEV;
- if (get_edac_report_status() == EDAC_REPORTING_FORCE) {
+ if (edac_get_report_status() == EDAC_REPORTING_FORCE) {
pr_warn("Not loading eMCA, error reporting force-enabled through EDAC.\n");
return -EPERM;
}
* eMCA event report method has higher priority than EDAC method,
* unless EDAC event report method is mandatory.
*/
- old_edac_report_status = get_edac_report_status();
- set_edac_report_status(EDAC_REPORTING_DISABLED);
+ old_edac_report_status = edac_get_report_status();
+ edac_set_report_status(EDAC_REPORTING_DISABLED);
mce_register_decode_chain(&extlog_mce_dec);
/* enable OS to be involved to take over management from BIOS */
((struct extlog_l1_head *)extlog_l1_addr)->flags |= FLAG_OS_OPTIN;
static void __exit extlog_exit(void)
{
- set_edac_report_status(old_edac_report_status);
+ edac_set_report_status(old_edac_report_status);
mce_unregister_decode_chain(&extlog_mce_dec);
((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN;
if (extlog_l1_addr)
if (msg->recv_type == IPMI_RESPONSE_RECV_TYPE &&
msg->msg.data_len == 1) {
if (msg->msg.data[0] == IPMI_TIMEOUT_COMPLETION_CODE) {
- dev_WARN_ONCE(dev, true,
- "Unexpected response (timeout).\n");
+ dev_dbg_once(dev, "Unexpected response (timeout).\n");
tx_msg->msg_done = ACPI_IPMI_TIMEOUT;
}
goto out_comp;
if (IS_ERR(pdev))
dev_err(&adev->dev, "platform device creation failed: %ld\n",
PTR_ERR(pdev));
- else
+ else {
+ set_dev_node(&pdev->dev, acpi_get_node(adev->handle));
dev_dbg(&adev->dev, "created platform device %s\n",
dev_name(&pdev->dev));
+ }
kfree(resources);
+
return pdev;
}
EXPORT_SYMBOL_GPL(acpi_create_platform_device);
if (result) /* Processor is not physically present or unavailable */
return 0;
-#ifdef CONFIG_SMP
- if (pr->id >= setup_max_cpus && pr->id != 0)
- return 0;
-#endif
-
BUG_ON(pr->id >= nr_cpu_ids);
/*
MODULE_PARM_DESC(report_key_events,
"0: none, 1: output changes, 2: brightness changes, 3: all");
+/*
+ * Whether the struct acpi_video_device_attrib::device_id_scheme bit should be
+ * assumed even if not actually set.
+ */
static bool device_id_scheme = false;
module_param(device_id_scheme, bool, 0444);
static void acpi_video_bus_notify(struct acpi_device *device, u32 event);
void acpi_video_detect_exit(void);
+/*
+ * Indices in the _BCL method response: the first two items are special,
+ * the rest are all supported levels.
+ *
+ * See page 575 of the ACPI spec 3.0
+ */
+enum acpi_video_level_idx {
+ ACPI_VIDEO_AC_LEVEL, /* level when machine has full power */
+ ACPI_VIDEO_BATTERY_LEVEL, /* level when machine is on batteries */
+ ACPI_VIDEO_FIRST_LEVEL, /* actual supported levels begin here */
+};
+
static const struct acpi_device_id video_device_ids[] = {
{ACPI_VIDEO_HID, 0},
{"", 0},
the VGA device. */
u32 pipe_id:3; /* For VGA multiple-head devices. */
u32 reserved:10; /* Must be 0 */
- u32 device_id_scheme:1; /* Device ID Scheme */
+
+ /*
+ * The device ID might not actually follow the scheme described by this
+ * struct acpi_video_device_attrib. If it does, then this bit
+ * device_id_scheme is set; otherwise, other fields should be ignored.
+ *
+ * (but also see the global flag device_id_scheme)
+ */
+ u32 device_id_scheme:1;
};
struct acpi_video_enumerated_device {
if (acpi_video_device_lcd_get_level_current(vd, &cur_level, false))
return -EINVAL;
- for (i = 2; i < vd->brightness->count; i++) {
+ for (i = ACPI_VIDEO_FIRST_LEVEL; i < vd->brightness->count; i++) {
if (vd->brightness->levels[i] == cur_level)
- /*
- * The first two entries are special - see page 575
- * of the ACPI spec 3.0
- */
- return i - 2;
+ return i - ACPI_VIDEO_FIRST_LEVEL;
}
return 0;
}
static int acpi_video_set_brightness(struct backlight_device *bd)
{
- int request_level = bd->props.brightness + 2;
+ int request_level = bd->props.brightness + ACPI_VIDEO_FIRST_LEVEL;
struct acpi_video_device *vd = bl_get_data(bd);
cancel_delayed_work(&vd->switch_brightness_work);
};
/* thermal cooling device callbacks */
-static int video_get_max_state(struct thermal_cooling_device *cooling_dev, unsigned
- long *state)
+static int video_get_max_state(struct thermal_cooling_device *cooling_dev,
+ unsigned long *state)
{
struct acpi_device *device = cooling_dev->devdata;
struct acpi_video_device *video = acpi_driver_data(device);
- *state = video->brightness->count - 3;
+ *state = video->brightness->count - ACPI_VIDEO_FIRST_LEVEL - 1;
return 0;
}
-static int video_get_cur_state(struct thermal_cooling_device *cooling_dev, unsigned
- long *state)
+static int video_get_cur_state(struct thermal_cooling_device *cooling_dev,
+ unsigned long *state)
{
struct acpi_device *device = cooling_dev->devdata;
struct acpi_video_device *video = acpi_driver_data(device);
if (acpi_video_device_lcd_get_level_current(video, &level, false))
return -EINVAL;
- for (offset = 2; offset < video->brightness->count; offset++)
+ for (offset = ACPI_VIDEO_FIRST_LEVEL; offset < video->brightness->count;
+ offset++)
if (level == video->brightness->levels[offset]) {
*state = video->brightness->count - offset - 1;
return 0;
struct acpi_video_device *video = acpi_driver_data(device);
int level;
- if (state >= video->brightness->count - 2)
+ if (state >= video->brightness->count - ACPI_VIDEO_FIRST_LEVEL)
return -EINVAL;
state = video->brightness->count - state;
}
device->brightness->curr = level;
- for (state = 2; state < device->brightness->count; state++)
+ for (state = ACPI_VIDEO_FIRST_LEVEL; state < device->brightness->count;
+ state++)
if (level == device->brightness->levels[state]) {
if (device->backlight)
- device->backlight->props.brightness = state - 2;
+ device->backlight->props.brightness =
+ state - ACPI_VIDEO_FIRST_LEVEL;
return 0;
}
if (device->brightness->flags._BQC_use_index) {
/*
- * _BQC returns an index that doesn't account for
- * the first 2 items with special meaning, so we need
- * to compensate for that by offsetting ourselves
+ * _BQC returns an index that doesn't account for the first 2
+ * items with special meaning (see enum acpi_video_level_idx),
+ * so we need to compensate for that by offsetting ourselves
*/
if (device->brightness->flags._BCL_reversed)
- bqc_value = device->brightness->count - 3 - bqc_value;
+ bqc_value = device->brightness->count -
+ ACPI_VIDEO_FIRST_LEVEL - 1 - bqc_value;
- level = device->brightness->levels[bqc_value + 2];
+ level = device->brightness->levels[bqc_value +
+ ACPI_VIDEO_FIRST_LEVEL];
} else {
level = bqc_value;
}
*level = acpi_video_bqc_value_to_level(device, *level);
- for (i = 2; i < device->brightness->count; i++)
+ for (i = ACPI_VIDEO_FIRST_LEVEL;
+ i < device->brightness->count; i++)
if (device->brightness->levels[i] == *level) {
device->brightness->curr = *level;
return 0;
/*
* Some systems always report current brightness level as maximum
- * through _BQC, we need to test another value for them.
+ * through _BQC, we need to test another value for them. However,
+ * there is a subtlety:
+ *
+ * If the _BCL package ordering is descending, the first level
+ * (br->levels[2]) is likely to be 0, and if the number of levels
+ * matches the number of steps, we might confuse a returned level to
+ * mean the index.
+ *
+ * For example:
+ *
+ * current_level = max_level = 100
+ * test_level = 0
+ * returned level = 100
+ *
+ * In this case 100 means the level, not the index, and _BCM failed.
+ * Still, if the _BCL package ordering is descending, the index of
+ * level 0 is also 100, so we assume _BQC is indexed, when it's not.
+ *
+ * This causes all _BQC calls to return bogus values causing weird
+ * behavior from the user's perspective. For example:
+ *
+ * xbacklight -set 10; xbacklight -set 20;
+ *
+ * would flash to 90% and then slowly down to the desired level (20).
+ *
+ * The solution is simple; test anything other than the first level
+ * (e.g. 1).
*/
- test_level = current_level == max_level ? br->levels[3] : max_level;
+ test_level = current_level == max_level
+ ? br->levels[ACPI_VIDEO_FIRST_LEVEL + 1]
+ : max_level;
result = acpi_video_device_lcd_set_level(device, test_level);
if (result)
/* buggy _BQC found, need to find out if it uses index */
if (level < br->count) {
if (br->flags._BCL_reversed)
- level = br->count - 3 - level;
- if (br->levels[level + 2] == test_level)
+ level = br->count - ACPI_VIDEO_FIRST_LEVEL - 1 - level;
+ if (br->levels[level + ACPI_VIDEO_FIRST_LEVEL] == test_level)
br->flags._BQC_use_index = 1;
}
goto out;
}
- if (obj->package.count < 2) {
+ if (obj->package.count < ACPI_VIDEO_FIRST_LEVEL) {
result = -EINVAL;
goto out;
}
goto out;
}
- br->levels = kmalloc((obj->package.count + 2) * sizeof *(br->levels),
- GFP_KERNEL);
+ /*
+ * Note that we have to reserve 2 extra items (ACPI_VIDEO_FIRST_LEVEL),
+ * in order to account for buggy BIOS which don't export the first two
+ * special levels (see below)
+ */
+ br->levels = kmalloc((obj->package.count + ACPI_VIDEO_FIRST_LEVEL) *
+ sizeof(*br->levels), GFP_KERNEL);
if (!br->levels) {
result = -ENOMEM;
goto out_free;
}
value = (u32) o->integer.value;
/* Skip duplicate entries */
- if (count > 2 && br->levels[count - 1] == value)
+ if (count > ACPI_VIDEO_FIRST_LEVEL
+ && br->levels[count - 1] == value)
continue;
br->levels[count] = value;
* In this case, the first two elements in _BCL packages
* are also supported brightness levels that OS should take care of.
*/
- for (i = 2; i < count; i++) {
- if (br->levels[i] == br->levels[0])
+ for (i = ACPI_VIDEO_FIRST_LEVEL; i < count; i++) {
+ if (br->levels[i] == br->levels[ACPI_VIDEO_AC_LEVEL])
level_ac_battery++;
- if (br->levels[i] == br->levels[1])
+ if (br->levels[i] == br->levels[ACPI_VIDEO_BATTERY_LEVEL])
level_ac_battery++;
}
- if (level_ac_battery < 2) {
- level_ac_battery = 2 - level_ac_battery;
+ if (level_ac_battery < ACPI_VIDEO_FIRST_LEVEL) {
+ level_ac_battery = ACPI_VIDEO_FIRST_LEVEL - level_ac_battery;
br->flags._BCL_no_ac_battery_levels = 1;
- for (i = (count - 1 + level_ac_battery); i >= 2; i--)
+ for (i = (count - 1 + level_ac_battery);
+ i >= ACPI_VIDEO_FIRST_LEVEL; i--)
br->levels[i] = br->levels[i - level_ac_battery];
count += level_ac_battery;
- } else if (level_ac_battery > 2)
+ } else if (level_ac_battery > ACPI_VIDEO_FIRST_LEVEL)
ACPI_ERROR((AE_INFO, "Too many duplicates in _BCL package"));
/* Check if the _BCL package is in a reversed order */
- if (max_level == br->levels[2]) {
+ if (max_level == br->levels[ACPI_VIDEO_FIRST_LEVEL]) {
br->flags._BCL_reversed = 1;
- sort(&br->levels[2], count - 2, sizeof(br->levels[2]),
- acpi_video_cmp_level, NULL);
+ sort(&br->levels[ACPI_VIDEO_FIRST_LEVEL],
+ count - ACPI_VIDEO_FIRST_LEVEL,
+ sizeof(br->levels[ACPI_VIDEO_FIRST_LEVEL]),
+ acpi_video_cmp_level, NULL);
} else if (max_level != br->levels[count - 1])
ACPI_ERROR((AE_INFO,
"Found unordered _BCL package"));
* level_old is invalid (no matter whether it's a level
* or an index). Set the backlight to max_level in this case.
*/
- for (i = 2; i < br->count; i++)
+ for (i = ACPI_VIDEO_FIRST_LEVEL; i < br->count; i++)
if (level == br->levels[i])
break;
if (i == br->count || !level)
goto out_free_levels;
ACPI_DEBUG_PRINT((ACPI_DB_INFO,
- "found %d brightness levels\n", br->count - 2));
+ "found %d brightness levels\n",
+ br->count - ACPI_VIDEO_FIRST_LEVEL));
return 0;
out_free_levels:
max = max_below = 0;
min = min_above = 255;
/* Find closest level to level_current */
- for (i = 2; i < device->brightness->count; i++) {
+ for (i = ACPI_VIDEO_FIRST_LEVEL; i < device->brightness->count; i++) {
l = device->brightness->levels[i];
if (abs(l - level_current) < abs(delta)) {
delta = l - level_current;
}
/* Ajust level_current to closest available level */
level_current += delta;
- for (i = 2; i < device->brightness->count; i++) {
+ for (i = ACPI_VIDEO_FIRST_LEVEL; i < device->brightness->count; i++) {
l = device->brightness->levels[i];
if (l < min)
min = l;
memset(&props, 0, sizeof(struct backlight_properties));
props.type = BACKLIGHT_FIRMWARE;
- props.max_brightness = device->brightness->count - 3;
+ props.max_brightness =
+ device->brightness->count - ACPI_VIDEO_FIRST_LEVEL - 1;
device->backlight = backlight_device_register(name,
parent,
device,
ACPI_FUNCTION_TRACE(ut_walk_aml_resources);
- /*
- * The absolute minimum resource template is one end_tag descriptor.
- * However, we will treat a lone end_tag as just a simple buffer.
- */
+ /* The absolute minimum resource template is one end_tag descriptor */
+
if (aml_length < sizeof(struct aml_resource_end_tag)) {
return_ACPI_STATUS(AE_AML_NO_RESOURCE_END_TAG);
}
/* Invoke the user function */
if (user_function) {
- status = user_function(aml, length, offset,
- resource_index, context);
+ status =
+ user_function(aml, length, offset, resource_index,
+ context);
if (ACPI_FAILURE(status)) {
return_ACPI_STATUS(status);
}
*context = aml;
}
- /* Check if buffer is defined to be longer than the resource length */
-
- if (aml_length > (offset + length)) {
- return_ACPI_STATUS(AE_AML_NO_RESOURCE_END_TAG);
- }
-
/* Normal exit */
return_ACPI_STATUS(AE_OK);
switch (generic->notify.type) {
case ACPI_HEST_NOTIFY_POLLED:
- ghes->timer.function = ghes_poll_func;
- ghes->timer.data = (unsigned long)ghes;
- init_timer_deferrable(&ghes->timer);
+ setup_deferrable_timer(&ghes->timer, ghes_poll_func,
+ (unsigned long)ghes);
ghes_add_timer(ghes);
break;
case ACPI_HEST_NOTIFY_EXTERNAL:
config ACPI_IORT
bool
+
+config ACPI_GTDT
+ bool
obj-$(CONFIG_ACPI_IORT) += iort.o
+obj-$(CONFIG_ACPI_GTDT) += gtdt.o
--- /dev/null
+/*
+ * ARM Specific GTDT table Support
+ *
+ * Copyright (C) 2016, Linaro Ltd.
+ * Author: Daniel Lezcano <daniel.lezcano@linaro.org>
+ * Fu Wei <fu.wei@linaro.org>
+ * Hanjun Guo <hanjun.guo@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/acpi.h>
+#include <linux/init.h>
+#include <linux/irqdomain.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+
+#include <clocksource/arm_arch_timer.h>
+
+#undef pr_fmt
+#define pr_fmt(fmt) "ACPI GTDT: " fmt
+
+/**
+ * struct acpi_gtdt_descriptor - Store the key info of GTDT for all functions
+ * @gtdt: The pointer to the struct acpi_table_gtdt of GTDT table.
+ * @gtdt_end: The pointer to the end of GTDT table.
+ * @platform_timer: The pointer to the start of Platform Timer Structure
+ *
+ * The struct store the key info of GTDT table, it should be initialized by
+ * acpi_gtdt_init.
+ */
+struct acpi_gtdt_descriptor {
+ struct acpi_table_gtdt *gtdt;
+ void *gtdt_end;
+ void *platform_timer;
+};
+
+static struct acpi_gtdt_descriptor acpi_gtdt_desc __initdata;
+
+static inline void *next_platform_timer(void *platform_timer)
+{
+ struct acpi_gtdt_header *gh = platform_timer;
+
+ platform_timer += gh->length;
+ if (platform_timer < acpi_gtdt_desc.gtdt_end)
+ return platform_timer;
+
+ return NULL;
+}
+
+#define for_each_platform_timer(_g) \
+ for (_g = acpi_gtdt_desc.platform_timer; _g; \
+ _g = next_platform_timer(_g))
+
+static inline bool is_timer_block(void *platform_timer)
+{
+ struct acpi_gtdt_header *gh = platform_timer;
+
+ return gh->type == ACPI_GTDT_TYPE_TIMER_BLOCK;
+}
+
+static inline bool is_non_secure_watchdog(void *platform_timer)
+{
+ struct acpi_gtdt_header *gh = platform_timer;
+ struct acpi_gtdt_watchdog *wd = platform_timer;
+
+ if (gh->type != ACPI_GTDT_TYPE_WATCHDOG)
+ return false;
+
+ return !(wd->timer_flags & ACPI_GTDT_WATCHDOG_SECURE);
+}
+
+static int __init map_gt_gsi(u32 interrupt, u32 flags)
+{
+ int trigger, polarity;
+
+ trigger = (flags & ACPI_GTDT_INTERRUPT_MODE) ? ACPI_EDGE_SENSITIVE
+ : ACPI_LEVEL_SENSITIVE;
+
+ polarity = (flags & ACPI_GTDT_INTERRUPT_POLARITY) ? ACPI_ACTIVE_LOW
+ : ACPI_ACTIVE_HIGH;
+
+ return acpi_register_gsi(NULL, interrupt, trigger, polarity);
+}
+
+/**
+ * acpi_gtdt_map_ppi() - Map the PPIs of per-cpu arch_timer.
+ * @type: the type of PPI.
+ *
+ * Note: Secure state is not managed by the kernel on ARM64 systems.
+ * So we only handle the non-secure timer PPIs,
+ * ARCH_TIMER_PHYS_SECURE_PPI is treated as invalid type.
+ *
+ * Return: the mapped PPI value, 0 if error.
+ */
+int __init acpi_gtdt_map_ppi(int type)
+{
+ struct acpi_table_gtdt *gtdt = acpi_gtdt_desc.gtdt;
+
+ switch (type) {
+ case ARCH_TIMER_PHYS_NONSECURE_PPI:
+ return map_gt_gsi(gtdt->non_secure_el1_interrupt,
+ gtdt->non_secure_el1_flags);
+ case ARCH_TIMER_VIRT_PPI:
+ return map_gt_gsi(gtdt->virtual_timer_interrupt,
+ gtdt->virtual_timer_flags);
+
+ case ARCH_TIMER_HYP_PPI:
+ return map_gt_gsi(gtdt->non_secure_el2_interrupt,
+ gtdt->non_secure_el2_flags);
+ default:
+ pr_err("Failed to map timer interrupt: invalid type.\n");
+ }
+
+ return 0;
+}
+
+/**
+ * acpi_gtdt_c3stop() - Got c3stop info from GTDT according to the type of PPI.
+ * @type: the type of PPI.
+ *
+ * Return: true if the timer HW state is lost when a CPU enters an idle state,
+ * false otherwise
+ */
+bool __init acpi_gtdt_c3stop(int type)
+{
+ struct acpi_table_gtdt *gtdt = acpi_gtdt_desc.gtdt;
+
+ switch (type) {
+ case ARCH_TIMER_PHYS_NONSECURE_PPI:
+ return !(gtdt->non_secure_el1_flags & ACPI_GTDT_ALWAYS_ON);
+
+ case ARCH_TIMER_VIRT_PPI:
+ return !(gtdt->virtual_timer_flags & ACPI_GTDT_ALWAYS_ON);
+
+ case ARCH_TIMER_HYP_PPI:
+ return !(gtdt->non_secure_el2_flags & ACPI_GTDT_ALWAYS_ON);
+
+ default:
+ pr_err("Failed to get c3stop info: invalid type.\n");
+ }
+
+ return false;
+}
+
+/**
+ * acpi_gtdt_init() - Get the info of GTDT table to prepare for further init.
+ * @table: The pointer to GTDT table.
+ * @platform_timer_count: It points to a integer variable which is used
+ * for storing the number of platform timers.
+ * This pointer could be NULL, if the caller
+ * doesn't need this info.
+ *
+ * Return: 0 if success, -EINVAL if error.
+ */
+int __init acpi_gtdt_init(struct acpi_table_header *table,
+ int *platform_timer_count)
+{
+ void *platform_timer;
+ struct acpi_table_gtdt *gtdt;
+
+ gtdt = container_of(table, struct acpi_table_gtdt, header);
+ acpi_gtdt_desc.gtdt = gtdt;
+ acpi_gtdt_desc.gtdt_end = (void *)table + table->length;
+ acpi_gtdt_desc.platform_timer = NULL;
+ if (platform_timer_count)
+ *platform_timer_count = 0;
+
+ if (table->revision < 2) {
+ pr_warn("Revision:%d doesn't support Platform Timers.\n",
+ table->revision);
+ return 0;
+ }
+
+ if (!gtdt->platform_timer_count) {
+ pr_debug("No Platform Timer.\n");
+ return 0;
+ }
+
+ platform_timer = (void *)gtdt + gtdt->platform_timer_offset;
+ if (platform_timer < (void *)table + sizeof(struct acpi_table_gtdt)) {
+ pr_err(FW_BUG "invalid timer data.\n");
+ return -EINVAL;
+ }
+ acpi_gtdt_desc.platform_timer = platform_timer;
+ if (platform_timer_count)
+ *platform_timer_count = gtdt->platform_timer_count;
+
+ return 0;
+}
+
+static int __init gtdt_parse_timer_block(struct acpi_gtdt_timer_block *block,
+ struct arch_timer_mem *timer_mem)
+{
+ int i;
+ struct arch_timer_mem_frame *frame;
+ struct acpi_gtdt_timer_entry *gtdt_frame;
+
+ if (!block->timer_count) {
+ pr_err(FW_BUG "GT block present, but frame count is zero.");
+ return -ENODEV;
+ }
+
+ if (block->timer_count > ARCH_TIMER_MEM_MAX_FRAMES) {
+ pr_err(FW_BUG "GT block lists %d frames, ACPI spec only allows 8\n",
+ block->timer_count);
+ return -EINVAL;
+ }
+
+ timer_mem->cntctlbase = (phys_addr_t)block->block_address;
+ /*
+ * The CNTCTLBase frame is 4KB (register offsets 0x000 - 0xFFC).
+ * See ARM DDI 0487A.k_iss10775, page I1-5129, Table I1-3
+ * "CNTCTLBase memory map".
+ */
+ timer_mem->size = SZ_4K;
+
+ gtdt_frame = (void *)block + block->timer_offset;
+ if (gtdt_frame + block->timer_count != (void *)block + block->header.length)
+ return -EINVAL;
+
+ /*
+ * Get the GT timer Frame data for every GT Block Timer
+ */
+ for (i = 0; i < block->timer_count; i++, gtdt_frame++) {
+ if (gtdt_frame->common_flags & ACPI_GTDT_GT_IS_SECURE_TIMER)
+ continue;
+ if (gtdt_frame->frame_number >= ARCH_TIMER_MEM_MAX_FRAMES ||
+ !gtdt_frame->base_address || !gtdt_frame->timer_interrupt)
+ goto error;
+
+ frame = &timer_mem->frame[gtdt_frame->frame_number];
+
+ /* duplicate frame */
+ if (frame->valid)
+ goto error;
+
+ frame->phys_irq = map_gt_gsi(gtdt_frame->timer_interrupt,
+ gtdt_frame->timer_flags);
+ if (frame->phys_irq <= 0) {
+ pr_warn("failed to map physical timer irq in frame %d.\n",
+ gtdt_frame->frame_number);
+ goto error;
+ }
+
+ if (gtdt_frame->virtual_timer_interrupt) {
+ frame->virt_irq =
+ map_gt_gsi(gtdt_frame->virtual_timer_interrupt,
+ gtdt_frame->virtual_timer_flags);
+ if (frame->virt_irq <= 0) {
+ pr_warn("failed to map virtual timer irq in frame %d.\n",
+ gtdt_frame->frame_number);
+ goto error;
+ }
+ } else {
+ pr_debug("virtual timer in frame %d not implemented.\n",
+ gtdt_frame->frame_number);
+ }
+
+ frame->cntbase = gtdt_frame->base_address;
+ /*
+ * The CNTBaseN frame is 4KB (register offsets 0x000 - 0xFFC).
+ * See ARM DDI 0487A.k_iss10775, page I1-5130, Table I1-4
+ * "CNTBaseN memory map".
+ */
+ frame->size = SZ_4K;
+ frame->valid = true;
+ }
+
+ return 0;
+
+error:
+ do {
+ if (gtdt_frame->common_flags & ACPI_GTDT_GT_IS_SECURE_TIMER ||
+ gtdt_frame->frame_number >= ARCH_TIMER_MEM_MAX_FRAMES)
+ continue;
+
+ frame = &timer_mem->frame[gtdt_frame->frame_number];
+
+ if (frame->phys_irq > 0)
+ acpi_unregister_gsi(gtdt_frame->timer_interrupt);
+ frame->phys_irq = 0;
+
+ if (frame->virt_irq > 0)
+ acpi_unregister_gsi(gtdt_frame->virtual_timer_interrupt);
+ frame->virt_irq = 0;
+ } while (i-- >= 0 && gtdt_frame--);
+
+ return -EINVAL;
+}
+
+/**
+ * acpi_arch_timer_mem_init() - Get the info of all GT blocks in GTDT table.
+ * @timer_mem: The pointer to the array of struct arch_timer_mem for returning
+ * the result of parsing. The element number of this array should
+ * be platform_timer_count(the total number of platform timers).
+ * @timer_count: It points to a integer variable which is used for storing the
+ * number of GT blocks we have parsed.
+ *
+ * Return: 0 if success, -EINVAL/-ENODEV if error.
+ */
+int __init acpi_arch_timer_mem_init(struct arch_timer_mem *timer_mem,
+ int *timer_count)
+{
+ int ret;
+ void *platform_timer;
+
+ *timer_count = 0;
+ for_each_platform_timer(platform_timer) {
+ if (is_timer_block(platform_timer)) {
+ ret = gtdt_parse_timer_block(platform_timer, timer_mem);
+ if (ret)
+ return ret;
+ timer_mem++;
+ (*timer_count)++;
+ }
+ }
+
+ if (*timer_count)
+ pr_info("found %d memory-mapped timer block(s).\n",
+ *timer_count);
+
+ return 0;
+}
+
+/*
+ * Initialize a SBSA generic Watchdog platform device info from GTDT
+ */
+static int __init gtdt_import_sbsa_gwdt(struct acpi_gtdt_watchdog *wd,
+ int index)
+{
+ struct platform_device *pdev;
+ int irq = map_gt_gsi(wd->timer_interrupt, wd->timer_flags);
+
+ /*
+ * According to SBSA specification the size of refresh and control
+ * frames of SBSA Generic Watchdog is SZ_4K(Offset 0x000 – 0xFFF).
+ */
+ struct resource res[] = {
+ DEFINE_RES_MEM(wd->control_frame_address, SZ_4K),
+ DEFINE_RES_MEM(wd->refresh_frame_address, SZ_4K),
+ DEFINE_RES_IRQ(irq),
+ };
+ int nr_res = ARRAY_SIZE(res);
+
+ pr_debug("found a Watchdog (0x%llx/0x%llx gsi:%u flags:0x%x).\n",
+ wd->refresh_frame_address, wd->control_frame_address,
+ wd->timer_interrupt, wd->timer_flags);
+
+ if (!(wd->refresh_frame_address && wd->control_frame_address)) {
+ pr_err(FW_BUG "failed to get the Watchdog base address.\n");
+ acpi_unregister_gsi(wd->timer_interrupt);
+ return -EINVAL;
+ }
+
+ if (irq <= 0) {
+ pr_warn("failed to map the Watchdog interrupt.\n");
+ nr_res--;
+ }
+
+ /*
+ * Add a platform device named "sbsa-gwdt" to match the platform driver.
+ * "sbsa-gwdt": SBSA(Server Base System Architecture) Generic Watchdog
+ * The platform driver can get device info below by matching this name.
+ */
+ pdev = platform_device_register_simple("sbsa-gwdt", index, res, nr_res);
+ if (IS_ERR(pdev)) {
+ acpi_unregister_gsi(wd->timer_interrupt);
+ return PTR_ERR(pdev);
+ }
+
+ return 0;
+}
+
+static int __init gtdt_sbsa_gwdt_init(void)
+{
+ void *platform_timer;
+ struct acpi_table_header *table;
+ int ret, timer_count, gwdt_count = 0;
+
+ if (acpi_disabled)
+ return 0;
+
+ if (ACPI_FAILURE(acpi_get_table(ACPI_SIG_GTDT, 0, &table)))
+ return -EINVAL;
+
+ /*
+ * Note: Even though the global variable acpi_gtdt_desc has been
+ * initialized by acpi_gtdt_init() while initializing the arch timers,
+ * when we call this function to get SBSA watchdogs info from GTDT, the
+ * pointers stashed in it are stale (since they are early temporary
+ * mappings carried out before acpi_permanent_mmap is set) and we need
+ * to re-initialize them with permanent mapped pointer values to let the
+ * GTDT parsing possible.
+ */
+ ret = acpi_gtdt_init(table, &timer_count);
+ if (ret || !timer_count)
+ return ret;
+
+ for_each_platform_timer(platform_timer) {
+ if (is_non_secure_watchdog(platform_timer)) {
+ ret = gtdt_import_sbsa_gwdt(platform_timer, gwdt_count);
+ if (ret)
+ break;
+ gwdt_count++;
+ }
+ }
+
+ if (gwdt_count)
+ pr_info("found %d SBSA generic Watchdog(s).\n", gwdt_count);
+
+ return ret;
+}
+
+device_initcall(gtdt_sbsa_gwdt_init);
MODULE_LICENSE("GPL");
static async_cookie_t async_cookie;
+static bool battery_driver_registered;
static int battery_bix_broken_package;
static int battery_notification_delay_ms;
static unsigned int cache_time = 1000;
MODULE_DEVICE_TABLE(acpi, battery_device_ids);
+/* Lists of PMIC ACPI HIDs with an (often better) native battery driver */
+static const char * const acpi_battery_blacklist[] = {
+ "INT33F4", /* X-Powers AXP288 PMIC */
+};
+
enum {
ACPI_BATTERY_ALARM_PRESENT,
ACPI_BATTERY_XINFO_PRESENT,
static void __init acpi_battery_init_async(void *unused, async_cookie_t cookie)
{
+ unsigned int i;
int result;
+ for (i = 0; i < ARRAY_SIZE(acpi_battery_blacklist); i++)
+ if (acpi_dev_present(acpi_battery_blacklist[i], "1", -1)) {
+ pr_info(PREFIX ACPI_BATTERY_DEVICE_NAME
+ ": found native %s PMIC, not loading\n",
+ acpi_battery_blacklist[i]);
+ return;
+ }
+
dmi_check_system(bat_dmi_table);
#ifdef CONFIG_ACPI_PROCFS_POWER
if (result < 0)
acpi_unlock_battery_dir(acpi_battery_dir);
#endif
+ battery_driver_registered = (result == 0);
}
static int __init acpi_battery_init(void)
static void __exit acpi_battery_exit(void)
{
async_synchronize_cookie(async_cookie + 1);
- acpi_bus_unregister_driver(&acpi_battery_driver);
+ if (battery_driver_registered)
+ acpi_bus_unregister_driver(&acpi_battery_driver);
#ifdef CONFIG_ACPI_PROCFS_POWER
- acpi_unlock_battery_dir(acpi_battery_dir);
+ if (acpi_battery_dir)
+ acpi_unlock_battery_dir(acpi_battery_dir);
#endif
}
.bin_attrs = bgrt_bin_attributes,
};
+int __init acpi_parse_bgrt(struct acpi_table_header *table)
+{
+ efi_bgrt_init(table);
+ return 0;
+}
+
static int __init bgrt_init(void)
{
int ret;
DMI_MATCH(DMI_PRODUCT_NAME, "Latitude 3350"),
},
},
+ {
+ .callback = dmi_enable_rev_override,
+ .ident = "DELL Inspiron 7537",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 7537"),
+ },
+ },
#endif
{}
};
#define to_cpc_desc(a) container_of(a, struct cpc_desc, kobj)
+#define show_cppc_data(access_fn, struct_name, member_name) \
+ static ssize_t show_##member_name(struct kobject *kobj, \
+ struct attribute *attr, char *buf) \
+ { \
+ struct cpc_desc *cpc_ptr = to_cpc_desc(kobj); \
+ struct struct_name st_name = {0}; \
+ int ret; \
+ \
+ ret = access_fn(cpc_ptr->cpu_id, &st_name); \
+ if (ret) \
+ return ret; \
+ \
+ return scnprintf(buf, PAGE_SIZE, "%llu\n", \
+ (u64)st_name.member_name); \
+ } \
+ define_one_cppc_ro(member_name)
+
+show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, highest_perf);
+show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, lowest_perf);
+show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, nominal_perf);
+show_cppc_data(cppc_get_perf_caps, cppc_perf_caps, lowest_nonlinear_perf);
+show_cppc_data(cppc_get_perf_ctrs, cppc_perf_fb_ctrs, reference_perf);
+show_cppc_data(cppc_get_perf_ctrs, cppc_perf_fb_ctrs, wraparound_time);
+
static ssize_t show_feedback_ctrs(struct kobject *kobj,
struct attribute *attr, char *buf)
{
struct cpc_desc *cpc_ptr = to_cpc_desc(kobj);
struct cppc_perf_fb_ctrs fb_ctrs = {0};
+ int ret;
- cppc_get_perf_ctrs(cpc_ptr->cpu_id, &fb_ctrs);
+ ret = cppc_get_perf_ctrs(cpc_ptr->cpu_id, &fb_ctrs);
+ if (ret)
+ return ret;
return scnprintf(buf, PAGE_SIZE, "ref:%llu del:%llu\n",
fb_ctrs.reference, fb_ctrs.delivered);
}
define_one_cppc_ro(feedback_ctrs);
-static ssize_t show_reference_perf(struct kobject *kobj,
- struct attribute *attr, char *buf)
-{
- struct cpc_desc *cpc_ptr = to_cpc_desc(kobj);
- struct cppc_perf_fb_ctrs fb_ctrs = {0};
-
- cppc_get_perf_ctrs(cpc_ptr->cpu_id, &fb_ctrs);
-
- return scnprintf(buf, PAGE_SIZE, "%llu\n",
- fb_ctrs.reference_perf);
-}
-define_one_cppc_ro(reference_perf);
-
-static ssize_t show_wraparound_time(struct kobject *kobj,
- struct attribute *attr, char *buf)
-{
- struct cpc_desc *cpc_ptr = to_cpc_desc(kobj);
- struct cppc_perf_fb_ctrs fb_ctrs = {0};
-
- cppc_get_perf_ctrs(cpc_ptr->cpu_id, &fb_ctrs);
-
- return scnprintf(buf, PAGE_SIZE, "%llu\n", fb_ctrs.ctr_wrap_time);
-
-}
-define_one_cppc_ro(wraparound_time);
-
static struct attribute *cppc_attrs[] = {
&feedback_ctrs.attr,
&reference_perf.attr,
&wraparound_time.attr,
+ &highest_perf.attr,
+ &lowest_perf.attr,
+ &lowest_nonlinear_perf.attr,
+ &nominal_perf.attr,
NULL
};
int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps)
{
struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpunum);
- struct cpc_register_resource *highest_reg, *lowest_reg, *ref_perf,
- *nom_perf;
- u64 high, low, nom;
+ struct cpc_register_resource *highest_reg, *lowest_reg,
+ *lowest_non_linear_reg, *nominal_reg;
+ u64 high, low, nom, min_nonlinear;
int ret = 0, regs_in_pcc = 0;
if (!cpc_desc) {
highest_reg = &cpc_desc->cpc_regs[HIGHEST_PERF];
lowest_reg = &cpc_desc->cpc_regs[LOWEST_PERF];
- ref_perf = &cpc_desc->cpc_regs[REFERENCE_PERF];
- nom_perf = &cpc_desc->cpc_regs[NOMINAL_PERF];
+ lowest_non_linear_reg = &cpc_desc->cpc_regs[LOW_NON_LINEAR_PERF];
+ nominal_reg = &cpc_desc->cpc_regs[NOMINAL_PERF];
/* Are any of the regs PCC ?*/
if (CPC_IN_PCC(highest_reg) || CPC_IN_PCC(lowest_reg) ||
- CPC_IN_PCC(ref_perf) || CPC_IN_PCC(nom_perf)) {
+ CPC_IN_PCC(lowest_non_linear_reg) || CPC_IN_PCC(nominal_reg)) {
regs_in_pcc = 1;
down_write(&pcc_data.pcc_lock);
/* Ring doorbell once to update PCC subspace */
cpc_read(cpunum, lowest_reg, &low);
perf_caps->lowest_perf = low;
- cpc_read(cpunum, nom_perf, &nom);
+ cpc_read(cpunum, nominal_reg, &nom);
perf_caps->nominal_perf = nom;
- if (!high || !low || !nom)
+ cpc_read(cpunum, lowest_non_linear_reg, &min_nonlinear);
+ perf_caps->lowest_nonlinear_perf = min_nonlinear;
+
+ if (!high || !low || !nom || !min_nonlinear)
ret = -EFAULT;
out_err:
perf_fb_ctrs->delivered = delivered;
perf_fb_ctrs->reference = reference;
perf_fb_ctrs->reference_perf = ref_perf;
- perf_fb_ctrs->ctr_wrap_time = ctr_wrap_time;
+ perf_fb_ctrs->wraparound_time = ctr_wrap_time;
out_err:
if (regs_in_pcc)
up_write(&pcc_data.pcc_lock);
return -ENODEV;
/*
- * If the device has a _HID (or _CID) returning a valid ACPI/PNP
- * device ID, it is better to make it look less attractive here, so that
- * the other device with the same _ADR value (that may not have a valid
- * device ID) can be matched going forward. [This means a second spec
- * violation in a row, so whatever we do here is best effort anyway.]
+ * If the device has a _HID returning a valid ACPI/PNP device ID, it is
+ * better to make it look less attractive here, so that the other device
+ * with the same _ADR value (that may not have a valid device ID) can be
+ * matched going forward. [This means a second spec violation in a row,
+ * so whatever we do here is best effort anyway.]
*/
- return sta_present && list_empty(&adev->pnp.ids) ?
+ return sta_present && !adev->pnp.type.platform_id ?
FIND_CHILD_MAX_SCORE : FIND_CHILD_MIN_SCORE;
}
#endif
int acpi_rev_override_setup(char *str);
-extern bool acpi_force_hot_remove;
-
void acpi_sysfs_add_hotplug_profile(struct acpi_hotplug_profile *hotplug,
const char *name);
int acpi_scan_add_handler_with_hotplug(struct acpi_scan_handler *handler,
const struct nfit_set_info_map *map0 = m0;
const struct nfit_set_info_map *map1 = m1;
- return map0->region_offset - map1->region_offset;
+ if (map0->region_offset < map1->region_offset)
+ return -1;
+ else if (map0->region_offset > map1->region_offset)
+ return 1;
+ return 0;
}
/* Retrieve the nth entry referencing this spa */
--- /dev/null
+/*
+ * Intel CHT Whiskey Cove PMIC operation region driver
+ * Copyright (C) 2017 Hans de Goede <hdegoede@redhat.com>
+ *
+ * Based on various non upstream patches to support the CHT Whiskey Cove PMIC:
+ * Copyright (C) 2013-2015 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/acpi.h>
+#include <linux/init.h>
+#include <linux/mfd/intel_soc_pmic.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include "intel_pmic.h"
+
+#define CHT_WC_V1P05A_CTRL 0x6e3b
+#define CHT_WC_V1P15_CTRL 0x6e3c
+#define CHT_WC_V1P05A_VSEL 0x6e3d
+#define CHT_WC_V1P15_VSEL 0x6e3e
+#define CHT_WC_V1P8A_CTRL 0x6e56
+#define CHT_WC_V1P8SX_CTRL 0x6e57
+#define CHT_WC_VDDQ_CTRL 0x6e58
+#define CHT_WC_V1P2A_CTRL 0x6e59
+#define CHT_WC_V1P2SX_CTRL 0x6e5a
+#define CHT_WC_V1P8A_VSEL 0x6e5b
+#define CHT_WC_VDDQ_VSEL 0x6e5c
+#define CHT_WC_V2P8SX_CTRL 0x6e5d
+#define CHT_WC_V3P3A_CTRL 0x6e5e
+#define CHT_WC_V3P3SD_CTRL 0x6e5f
+#define CHT_WC_VSDIO_CTRL 0x6e67
+#define CHT_WC_V3P3A_VSEL 0x6e68
+#define CHT_WC_VPROG1A_CTRL 0x6e90
+#define CHT_WC_VPROG1B_CTRL 0x6e91
+#define CHT_WC_VPROG1F_CTRL 0x6e95
+#define CHT_WC_VPROG2D_CTRL 0x6e99
+#define CHT_WC_VPROG3A_CTRL 0x6e9a
+#define CHT_WC_VPROG3B_CTRL 0x6e9b
+#define CHT_WC_VPROG4A_CTRL 0x6e9c
+#define CHT_WC_VPROG4B_CTRL 0x6e9d
+#define CHT_WC_VPROG4C_CTRL 0x6e9e
+#define CHT_WC_VPROG4D_CTRL 0x6e9f
+#define CHT_WC_VPROG5A_CTRL 0x6ea0
+#define CHT_WC_VPROG5B_CTRL 0x6ea1
+#define CHT_WC_VPROG6A_CTRL 0x6ea2
+#define CHT_WC_VPROG6B_CTRL 0x6ea3
+#define CHT_WC_VPROG1A_VSEL 0x6ec0
+#define CHT_WC_VPROG1B_VSEL 0x6ec1
+#define CHT_WC_V1P8SX_VSEL 0x6ec2
+#define CHT_WC_V1P2SX_VSEL 0x6ec3
+#define CHT_WC_V1P2A_VSEL 0x6ec4
+#define CHT_WC_VPROG1F_VSEL 0x6ec5
+#define CHT_WC_VSDIO_VSEL 0x6ec6
+#define CHT_WC_V2P8SX_VSEL 0x6ec7
+#define CHT_WC_V3P3SD_VSEL 0x6ec8
+#define CHT_WC_VPROG2D_VSEL 0x6ec9
+#define CHT_WC_VPROG3A_VSEL 0x6eca
+#define CHT_WC_VPROG3B_VSEL 0x6ecb
+#define CHT_WC_VPROG4A_VSEL 0x6ecc
+#define CHT_WC_VPROG4B_VSEL 0x6ecd
+#define CHT_WC_VPROG4C_VSEL 0x6ece
+#define CHT_WC_VPROG4D_VSEL 0x6ecf
+#define CHT_WC_VPROG5A_VSEL 0x6ed0
+#define CHT_WC_VPROG5B_VSEL 0x6ed1
+#define CHT_WC_VPROG6A_VSEL 0x6ed2
+#define CHT_WC_VPROG6B_VSEL 0x6ed3
+
+/*
+ * Regulator support is based on the non upstream patch:
+ * "regulator: whiskey_cove: implements Whiskey Cove pmic VRF support"
+ * https://github.com/intel-aero/meta-intel-aero/blob/master/recipes-kernel/linux/linux-yocto/0019-regulator-whiskey_cove-implements-WhiskeyCove-pmic-V.patch
+ */
+static struct pmic_table power_table[] = {
+ {
+ .address = 0x0,
+ .reg = CHT_WC_V1P8A_CTRL,
+ .bit = 0x01,
+ }, /* V18A */
+ {
+ .address = 0x04,
+ .reg = CHT_WC_V1P8SX_CTRL,
+ .bit = 0x07,
+ }, /* V18X */
+ {
+ .address = 0x08,
+ .reg = CHT_WC_VDDQ_CTRL,
+ .bit = 0x01,
+ }, /* VDDQ */
+ {
+ .address = 0x0c,
+ .reg = CHT_WC_V1P2A_CTRL,
+ .bit = 0x07,
+ }, /* V12A */
+ {
+ .address = 0x10,
+ .reg = CHT_WC_V1P2SX_CTRL,
+ .bit = 0x07,
+ }, /* V12X */
+ {
+ .address = 0x14,
+ .reg = CHT_WC_V2P8SX_CTRL,
+ .bit = 0x07,
+ }, /* V28X */
+ {
+ .address = 0x18,
+ .reg = CHT_WC_V3P3A_CTRL,
+ .bit = 0x01,
+ }, /* V33A */
+ {
+ .address = 0x1c,
+ .reg = CHT_WC_V3P3SD_CTRL,
+ .bit = 0x07,
+ }, /* V3SD */
+ {
+ .address = 0x20,
+ .reg = CHT_WC_VSDIO_CTRL,
+ .bit = 0x07,
+ }, /* VSD */
+/* {
+ .address = 0x24,
+ .reg = ??,
+ .bit = ??,
+ }, ** VSW2 */
+/* {
+ .address = 0x28,
+ .reg = ??,
+ .bit = ??,
+ }, ** VSW1 */
+/* {
+ .address = 0x2c,
+ .reg = ??,
+ .bit = ??,
+ }, ** VUPY */
+/* {
+ .address = 0x30,
+ .reg = ??,
+ .bit = ??,
+ }, ** VRSO */
+ {
+ .address = 0x34,
+ .reg = CHT_WC_VPROG1A_CTRL,
+ .bit = 0x07,
+ }, /* VP1A */
+ {
+ .address = 0x38,
+ .reg = CHT_WC_VPROG1B_CTRL,
+ .bit = 0x07,
+ }, /* VP1B */
+ {
+ .address = 0x3c,
+ .reg = CHT_WC_VPROG1F_CTRL,
+ .bit = 0x07,
+ }, /* VP1F */
+ {
+ .address = 0x40,
+ .reg = CHT_WC_VPROG2D_CTRL,
+ .bit = 0x07,
+ }, /* VP2D */
+ {
+ .address = 0x44,
+ .reg = CHT_WC_VPROG3A_CTRL,
+ .bit = 0x07,
+ }, /* VP3A */
+ {
+ .address = 0x48,
+ .reg = CHT_WC_VPROG3B_CTRL,
+ .bit = 0x07,
+ }, /* VP3B */
+ {
+ .address = 0x4c,
+ .reg = CHT_WC_VPROG4A_CTRL,
+ .bit = 0x07,
+ }, /* VP4A */
+ {
+ .address = 0x50,
+ .reg = CHT_WC_VPROG4B_CTRL,
+ .bit = 0x07,
+ }, /* VP4B */
+ {
+ .address = 0x54,
+ .reg = CHT_WC_VPROG4C_CTRL,
+ .bit = 0x07,
+ }, /* VP4C */
+ {
+ .address = 0x58,
+ .reg = CHT_WC_VPROG4D_CTRL,
+ .bit = 0x07,
+ }, /* VP4D */
+ {
+ .address = 0x5c,
+ .reg = CHT_WC_VPROG5A_CTRL,
+ .bit = 0x07,
+ }, /* VP5A */
+ {
+ .address = 0x60,
+ .reg = CHT_WC_VPROG5B_CTRL,
+ .bit = 0x07,
+ }, /* VP5B */
+ {
+ .address = 0x64,
+ .reg = CHT_WC_VPROG6A_CTRL,
+ .bit = 0x07,
+ }, /* VP6A */
+ {
+ .address = 0x68,
+ .reg = CHT_WC_VPROG6B_CTRL,
+ .bit = 0x07,
+ }, /* VP6B */
+/* {
+ .address = 0x6c,
+ .reg = ??,
+ .bit = ??,
+ } ** VP7A */
+};
+
+static int intel_cht_wc_pmic_get_power(struct regmap *regmap, int reg,
+ int bit, u64 *value)
+{
+ int data;
+
+ if (regmap_read(regmap, reg, &data))
+ return -EIO;
+
+ *value = (data & bit) ? 1 : 0;
+ return 0;
+}
+
+static int intel_cht_wc_pmic_update_power(struct regmap *regmap, int reg,
+ int bitmask, bool on)
+{
+ return regmap_update_bits(regmap, reg, bitmask, on ? 1 : 0);
+}
+
+/*
+ * The thermal table and ops are empty, we do not support the Thermal opregion
+ * (DPTF) due to lacking documentation.
+ */
+static struct intel_pmic_opregion_data intel_cht_wc_pmic_opregion_data = {
+ .get_power = intel_cht_wc_pmic_get_power,
+ .update_power = intel_cht_wc_pmic_update_power,
+ .power_table = power_table,
+ .power_table_count = ARRAY_SIZE(power_table),
+};
+
+static int intel_cht_wc_pmic_opregion_probe(struct platform_device *pdev)
+{
+ struct intel_soc_pmic *pmic = dev_get_drvdata(pdev->dev.parent);
+
+ return intel_pmic_install_opregion_handler(&pdev->dev,
+ ACPI_HANDLE(pdev->dev.parent),
+ pmic->regmap,
+ &intel_cht_wc_pmic_opregion_data);
+}
+
+static struct platform_device_id cht_wc_opregion_id_table[] = {
+ { .name = "cht_wcove_region" },
+ {},
+};
+MODULE_DEVICE_TABLE(platform, cht_wc_opregion_id_table);
+
+static struct platform_driver intel_cht_wc_pmic_opregion_driver = {
+ .probe = intel_cht_wc_pmic_opregion_probe,
+ .driver = {
+ .name = "cht_whiskey_cove_pmic",
+ },
+ .id_table = cht_wc_opregion_id_table,
+};
+module_platform_driver(intel_cht_wc_pmic_opregion_driver);
+
+MODULE_DESCRIPTION("Intel CHT Whiskey Cove PMIC operation region driver");
+MODULE_AUTHOR("Hans de Goede <hdegoede@redhat.com>");
+MODULE_LICENSE("GPL");
#include <linux/mfd/axp20x.h>
#include <linux/regmap.h>
#include <linux/platform_device.h>
-#include <linux/iio/consumer.h>
#include "intel_pmic.h"
#define XPOWER_GPADC_LOW 0x5b
* @regmap: regmap of the PMIC device
* @reg: register to get the reading
*
- * We could get the sensor value by manipulating the HW regs here, but since
- * the axp288 IIO driver may also access the same regs at the same time, the
- * APIs provided by IIO subsystem are used here instead to avoid problems. As
- * a result, the two passed in params are of no actual use.
- *
* Return a positive value on success, errno on failure.
*/
static int intel_xpower_pmic_get_raw_temp(struct regmap *regmap, int reg)
{
- struct iio_channel *gpadc_chan;
- int ret, val;
-
- gpadc_chan = iio_channel_get(NULL, "axp288-system-temp");
- if (IS_ERR_OR_NULL(gpadc_chan))
- return -EACCES;
+ u8 buf[2];
- ret = iio_read_channel_raw(gpadc_chan, &val);
- if (ret < 0)
- val = ret;
+ if (regmap_bulk_read(regmap, AXP288_GP_ADC_H, buf, 2))
+ return -EIO;
- iio_channel_release(gpadc_chan);
- return val;
+ return (buf[0] << 4) + ((buf[1] >> 4) & 0x0F);
}
static struct intel_pmic_opregion_data intel_xpower_pmic_opregion_data = {
return -EINVAL;
/* The state of the list is 'on' IFF all resources are 'on'. */
+ cur_state = 0;
list_for_each_entry(entry, list, node) {
struct acpi_power_resource *resource = entry->resource;
acpi_handle handle = resource->device.handle;
if (ACPI_SUCCESS(status))
return 0;
+ result = -ENODEV;
+ acpi_pss_perf_exit(pr, device);
+
err_power_exit:
acpi_processor_power_exit(pr);
return result;
static int acpi_processor_start(struct device *dev)
{
struct acpi_device *device = ACPI_COMPANION(dev);
+ int ret;
if (!device)
return -ENODEV;
- return __acpi_processor_start(device);
+ /* Protect against concurrent CPU hotplug operations */
+ get_online_cpus();
+ ret = __acpi_processor_start(device);
+ put_online_cpus();
+ return ret;
}
static int acpi_processor_stop(struct device *dev)
#define THROTTLING_POSTCHANGE (2)
static int acpi_processor_get_throttling(struct acpi_processor *pr);
-int acpi_processor_set_throttling(struct acpi_processor *pr,
- int state, bool force);
+static int __acpi_processor_set_throttling(struct acpi_processor *pr,
+ int state, bool force, bool direct);
static int acpi_processor_update_tsd_coord(void)
{
ACPI_DEBUG_PRINT((ACPI_DB_INFO,
"Invalid throttling state, reset\n"));
state = 0;
- ret = acpi_processor_set_throttling(pr, state, true);
+ ret = __acpi_processor_set_throttling(pr, state, true,
+ true);
if (ret)
return ret;
}
return 0;
}
-static int acpi_processor_get_throttling(struct acpi_processor *pr)
+static long __acpi_processor_get_throttling(void *data)
{
- cpumask_var_t saved_mask;
- int ret;
+ struct acpi_processor *pr = data;
+
+ return pr->throttling.acpi_processor_get_throttling(pr);
+}
+static int acpi_processor_get_throttling(struct acpi_processor *pr)
+{
if (!pr)
return -EINVAL;
if (!pr->flags.throttling)
return -ENODEV;
- if (!alloc_cpumask_var(&saved_mask, GFP_KERNEL))
- return -ENOMEM;
-
/*
- * Migrate task to the cpu pointed by pr.
+ * This is either called from the CPU hotplug callback of
+ * processor_driver or via the ACPI probe function. In the latter
+ * case the CPU is not guaranteed to be online. Both call sites are
+ * protected against CPU hotplug.
*/
- cpumask_copy(saved_mask, ¤t->cpus_allowed);
- /* FIXME: use work_on_cpu() */
- if (set_cpus_allowed_ptr(current, cpumask_of(pr->id))) {
- /* Can't migrate to the target pr->id CPU. Exit */
- free_cpumask_var(saved_mask);
+ if (!cpu_online(pr->id))
return -ENODEV;
- }
- ret = pr->throttling.acpi_processor_get_throttling(pr);
- /* restore the previous state */
- set_cpus_allowed_ptr(current, saved_mask);
- free_cpumask_var(saved_mask);
- return ret;
+ return work_on_cpu(pr->id, __acpi_processor_get_throttling, pr);
}
static int acpi_processor_get_fadt_info(struct acpi_processor *pr)
arg->target_state, arg->force);
}
-int acpi_processor_set_throttling(struct acpi_processor *pr,
- int state, bool force)
+static int call_on_cpu(int cpu, long (*fn)(void *), void *arg, bool direct)
+{
+ if (direct)
+ return fn(arg);
+ return work_on_cpu(cpu, fn, arg);
+}
+
+static int __acpi_processor_set_throttling(struct acpi_processor *pr,
+ int state, bool force, bool direct)
{
int ret = 0;
unsigned int i;
arg.pr = pr;
arg.target_state = state;
arg.force = force;
- ret = work_on_cpu(pr->id, acpi_processor_throttling_fn, &arg);
+ ret = call_on_cpu(pr->id, acpi_processor_throttling_fn, &arg,
+ direct);
} else {
/*
* When the T-state coordination is SW_ALL or HW_ALL,
arg.pr = match_pr;
arg.target_state = state;
arg.force = force;
- ret = work_on_cpu(pr->id, acpi_processor_throttling_fn,
- &arg);
+ ret = call_on_cpu(pr->id, acpi_processor_throttling_fn,
+ &arg, direct);
}
}
/*
return ret;
}
+int acpi_processor_set_throttling(struct acpi_processor *pr, int state,
+ bool force)
+{
+ return __acpi_processor_set_throttling(pr, state, force, false);
+}
+
int acpi_processor_get_throttling_info(struct acpi_processor *pr)
{
int result = 0;
static bool acpi_enumerate_nondev_subnodes(acpi_handle scope,
const union acpi_object *desc,
- struct acpi_device_data *data);
+ struct acpi_device_data *data,
+ struct fwnode_handle *parent);
static bool acpi_extract_properties(const union acpi_object *desc,
struct acpi_device_data *data);
static bool acpi_nondev_subnode_extract(const union acpi_object *desc,
acpi_handle handle,
const union acpi_object *link,
- struct list_head *list)
+ struct list_head *list,
+ struct fwnode_handle *parent)
{
struct acpi_data_node *dn;
bool result;
dn->name = link->package.elements[0].string.pointer;
dn->fwnode.type = FWNODE_ACPI_DATA;
+ dn->parent = parent;
INIT_LIST_HEAD(&dn->data.subnodes);
result = acpi_extract_properties(desc, &dn->data);
*/
status = acpi_get_parent(handle, &scope);
if (ACPI_SUCCESS(status)
- && acpi_enumerate_nondev_subnodes(scope, desc, &dn->data))
+ && acpi_enumerate_nondev_subnodes(scope, desc, &dn->data,
+ &dn->fwnode))
result = true;
- } else if (acpi_enumerate_nondev_subnodes(NULL, desc, &dn->data)) {
+ } else if (acpi_enumerate_nondev_subnodes(NULL, desc, &dn->data,
+ &dn->fwnode)) {
result = true;
}
static bool acpi_nondev_subnode_data_ok(acpi_handle handle,
const union acpi_object *link,
- struct list_head *list)
+ struct list_head *list,
+ struct fwnode_handle *parent)
{
struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER };
acpi_status status;
if (ACPI_FAILURE(status))
return false;
- if (acpi_nondev_subnode_extract(buf.pointer, handle, link, list))
+ if (acpi_nondev_subnode_extract(buf.pointer, handle, link, list,
+ parent))
return true;
ACPI_FREE(buf.pointer);
static bool acpi_nondev_subnode_ok(acpi_handle scope,
const union acpi_object *link,
- struct list_head *list)
+ struct list_head *list,
+ struct fwnode_handle *parent)
{
acpi_handle handle;
acpi_status status;
if (ACPI_FAILURE(status))
return false;
- return acpi_nondev_subnode_data_ok(handle, link, list);
+ return acpi_nondev_subnode_data_ok(handle, link, list, parent);
}
static int acpi_add_nondev_subnodes(acpi_handle scope,
const union acpi_object *links,
- struct list_head *list)
+ struct list_head *list,
+ struct fwnode_handle *parent)
{
bool ret = false;
int i;
/* The second one may be a string, a reference or a package. */
switch (link->package.elements[1].type) {
case ACPI_TYPE_STRING:
- result = acpi_nondev_subnode_ok(scope, link, list);
+ result = acpi_nondev_subnode_ok(scope, link, list,
+ parent);
break;
case ACPI_TYPE_LOCAL_REFERENCE:
handle = link->package.elements[1].reference.handle;
- result = acpi_nondev_subnode_data_ok(handle, link, list);
+ result = acpi_nondev_subnode_data_ok(handle, link, list,
+ parent);
break;
case ACPI_TYPE_PACKAGE:
desc = &link->package.elements[1];
- result = acpi_nondev_subnode_extract(desc, NULL, link, list);
+ result = acpi_nondev_subnode_extract(desc, NULL, link,
+ list, parent);
break;
default:
result = false;
static bool acpi_enumerate_nondev_subnodes(acpi_handle scope,
const union acpi_object *desc,
- struct acpi_device_data *data)
+ struct acpi_device_data *data,
+ struct fwnode_handle *parent)
{
int i;
if (memcmp(uuid->buffer.pointer, ads_uuid, sizeof(ads_uuid)))
continue;
- return acpi_add_nondev_subnodes(scope, links, &data->subnodes);
+ return acpi_add_nondev_subnodes(scope, links, &data->subnodes,
+ parent);
}
return false;
if (acpi_of)
acpi_init_of_compatible(adev);
}
- if (acpi_enumerate_nondev_subnodes(adev->handle, buf.pointer, &adev->data))
+ if (acpi_enumerate_nondev_subnodes(adev->handle, buf.pointer,
+ &adev->data, acpi_fwnode_handle(adev)))
adev->data.pointer = buf.pointer;
if (!adev->data.pointer) {
return ret;
*(char **)val = obj->string.pointer;
+
+ return 1;
} else {
ret = -EINVAL;
}
int acpi_dev_prop_read_single(struct acpi_device *adev, const char *propname,
enum dev_prop_type proptype, void *val)
{
- return adev ? acpi_data_prop_read_single(&adev->data, propname, proptype, val) : -EINVAL;
+ int ret;
+
+ if (!adev)
+ return -EINVAL;
+
+ ret = acpi_data_prop_read_single(&adev->data, propname, proptype, val);
+ if (ret < 0 || proptype != ACPI_TYPE_STRING)
+ return ret;
+ return 0;
}
static int acpi_copy_property_array_u8(const union acpi_object *items, u8 *val,
val[i] = items[i].string.pointer;
}
- return 0;
+ return nval;
}
static int acpi_data_prop_read(struct acpi_device_data *data,
if (val && nval == 1) {
ret = acpi_data_prop_read_single(data, propname, proptype, val);
- if (!ret)
+ if (ret >= 0)
return ret;
}
if (!val)
return obj->package.count;
- if (nval > obj->package.count)
+ if (proptype != DEV_PROP_STRING && nval > obj->package.count)
return -EOVERFLOW;
else if (nval <= 0)
return -EINVAL;
ret = acpi_copy_property_array_u64(items, (u64 *)val, nval);
break;
case DEV_PROP_STRING:
- ret = acpi_copy_property_array_string(items, (char **)val, nval);
+ ret = acpi_copy_property_array_string(
+ items, (char **)val,
+ min_t(u32, nval, obj->package.count));
break;
default:
ret = -EINVAL;
}
/**
- * acpi_get_next_subnode - Return the next child node handle for a device.
- * @dev: Device to find the next child node for.
+ * acpi_get_next_subnode - Return the next child node handle for a fwnode
+ * @fwnode: Firmware node to find the next child node for.
* @child: Handle to one of the device's child nodes or a null handle.
*/
-struct fwnode_handle *acpi_get_next_subnode(struct device *dev,
+struct fwnode_handle *acpi_get_next_subnode(struct fwnode_handle *fwnode,
struct fwnode_handle *child)
{
- struct acpi_device *adev = ACPI_COMPANION(dev);
+ struct acpi_device *adev = to_acpi_device_node(fwnode);
struct list_head *head, *next;
- if (!adev)
- return NULL;
-
if (!child || child->type == FWNODE_ACPI) {
- head = &adev->children;
+ if (adev)
+ head = &adev->children;
+ else
+ goto nondev;
+
if (list_empty(head))
goto nondev;
next = adev->node.next;
if (next == head) {
child = NULL;
- adev = ACPI_COMPANION(dev);
goto nondev;
}
adev = list_entry(next, struct acpi_device, node);
nondev:
if (!child || child->type == FWNODE_ACPI_DATA) {
+ struct acpi_data_node *data = to_acpi_data_node(fwnode);
struct acpi_data_node *dn;
- head = &adev->data.subnodes;
+ if (adev)
+ head = &adev->data.subnodes;
+ else if (data)
+ head = &data->data.subnodes;
+ else
+ return NULL;
+
if (list_empty(head))
return NULL;
}
return NULL;
}
+
+/**
+ * acpi_node_get_parent - Return parent fwnode of this fwnode
+ * @fwnode: Firmware node whose parent to get
+ *
+ * Returns parent node of an ACPI device or data firmware node or %NULL if
+ * not available.
+ */
+struct fwnode_handle *acpi_node_get_parent(struct fwnode_handle *fwnode)
+{
+ if (is_acpi_data_node(fwnode)) {
+ /* All data nodes have parent pointer so just return that */
+ return to_acpi_data_node(fwnode)->parent;
+ } else if (is_acpi_device_node(fwnode)) {
+ acpi_handle handle, parent_handle;
+
+ handle = to_acpi_device_node(fwnode)->handle;
+ if (ACPI_SUCCESS(acpi_get_parent(handle, &parent_handle))) {
+ struct acpi_device *adev;
+
+ if (!acpi_bus_get_device(parent_handle, &adev))
+ return acpi_fwnode_handle(adev);
+ }
+ }
+
+ return NULL;
+}
+
+/**
+ * acpi_graph_get_next_endpoint - Get next endpoint ACPI firmware node
+ * @fwnode: Pointer to the parent firmware node
+ * @prev: Previous endpoint node or %NULL to get the first
+ *
+ * Looks up next endpoint ACPI firmware node below a given @fwnode. Returns
+ * %NULL if there is no next endpoint, ERR_PTR() in case of error. In case
+ * of success the next endpoint is returned.
+ */
+struct fwnode_handle *acpi_graph_get_next_endpoint(struct fwnode_handle *fwnode,
+ struct fwnode_handle *prev)
+{
+ struct fwnode_handle *port = NULL;
+ struct fwnode_handle *endpoint;
+
+ if (!prev) {
+ do {
+ port = fwnode_get_next_child_node(fwnode, port);
+ /* Ports must have port property */
+ if (fwnode_property_present(port, "port"))
+ break;
+ } while (port);
+ } else {
+ port = fwnode_get_parent(prev);
+ }
+
+ if (!port)
+ return NULL;
+
+ endpoint = fwnode_get_next_child_node(port, prev);
+ while (!endpoint) {
+ port = fwnode_get_next_child_node(fwnode, port);
+ if (!port)
+ break;
+ if (fwnode_property_present(port, "port"))
+ endpoint = fwnode_get_next_child_node(port, NULL);
+ }
+
+ if (endpoint) {
+ /* Endpoints must have "endpoint" property */
+ if (!fwnode_property_present(endpoint, "endpoint"))
+ return ERR_PTR(-EPROTO);
+ }
+
+ return endpoint;
+}
+
+/**
+ * acpi_graph_get_child_prop_value - Return a child with a given property value
+ * @fwnode: device fwnode
+ * @prop_name: The name of the property to look for
+ * @val: the desired property value
+ *
+ * Return the port node corresponding to a given port number. Returns
+ * the child node on success, NULL otherwise.
+ */
+static struct fwnode_handle *acpi_graph_get_child_prop_value(
+ struct fwnode_handle *fwnode, const char *prop_name, unsigned int val)
+{
+ struct fwnode_handle *child;
+
+ fwnode_for_each_child_node(fwnode, child) {
+ u32 nr;
+
+ if (!fwnode_property_read_u32(fwnode, prop_name, &nr))
+ continue;
+
+ if (val == nr)
+ return child;
+ }
+
+ return NULL;
+}
+
+
+/**
+ * acpi_graph_get_remote_enpoint - Parses and returns remote end of an endpoint
+ * @fwnode: Endpoint firmware node pointing to a remote device
+ * @parent: Firmware node of remote port parent is filled here if not %NULL
+ * @port: Firmware node of remote port is filled here if not %NULL
+ * @endpoint: Firmware node of remote endpoint is filled here if not %NULL
+ *
+ * Function parses remote end of ACPI firmware remote endpoint and fills in
+ * fields requested by the caller. Returns %0 in case of success and
+ * negative errno otherwise.
+ */
+int acpi_graph_get_remote_endpoint(struct fwnode_handle *fwnode,
+ struct fwnode_handle **parent,
+ struct fwnode_handle **port,
+ struct fwnode_handle **endpoint)
+{
+ unsigned int port_nr, endpoint_nr;
+ struct acpi_reference_args args;
+ int ret;
+
+ memset(&args, 0, sizeof(args));
+ ret = acpi_node_get_property_reference(fwnode, "remote-endpoint", 0,
+ &args);
+ if (ret)
+ return ret;
+
+ /*
+ * Always require two arguments with the reference: port and
+ * endpoint indices.
+ */
+ if (args.nargs != 2)
+ return -EPROTO;
+
+ fwnode = acpi_fwnode_handle(args.adev);
+ port_nr = args.args[0];
+ endpoint_nr = args.args[1];
+
+ if (parent)
+ *parent = fwnode;
+
+ if (!port && !endpoint)
+ return 0;
+
+ fwnode = acpi_graph_get_child_prop_value(fwnode, "port", port_nr);
+ if (!fwnode)
+ return -EPROTO;
+
+ if (port)
+ *port = fwnode;
+
+ if (!endpoint)
+ return 0;
+
+ fwnode = acpi_graph_get_child_prop_value(fwnode, "endpoint",
+ endpoint_nr);
+ if (!fwnode)
+ return -EPROTO;
+
+ *endpoint = fwnode;
+
+ return 0;
+}
#define INVALID_ACPI_HANDLE ((acpi_handle)empty_zero_page)
-/*
- * If set, devices will be hot-removed even if they cannot be put offline
- * gracefully (from the kernel's standpoint).
- */
-bool acpi_force_hot_remove;
-
static const char *dummy_hid = "device";
static LIST_HEAD(acpi_dep_list);
pn->put_online = false;
}
ret = device_offline(pn->dev);
- if (acpi_force_hot_remove)
- continue;
-
if (ret >= 0) {
pn->put_online = !ret;
} else {
acpi_walk_namespace(ACPI_TYPE_ANY, handle, ACPI_UINT32_MAX,
NULL, acpi_bus_offline, (void *)true,
(void **)&errdev);
- if (!errdev || acpi_force_hot_remove)
+ if (!errdev)
acpi_bus_offline(handle, 0, (void *)true,
(void **)&errdev);
- if (errdev && !acpi_force_hot_remove) {
+ if (errdev) {
dev_warn(errdev, "Offline failed.\n");
acpi_bus_online(handle, 0, NULL, NULL);
acpi_walk_namespace(ACPI_TYPE_ANY, handle,
unsigned long long sta;
acpi_status status;
- if (device->handler && device->handler->hotplug.demand_offline
- && !acpi_force_hot_remove) {
+ if (device->handler && device->handler->hotplug.demand_offline) {
if (!acpi_scan_is_offline(device, true))
return -EBUSY;
} else {
device->flags.power_manageable = 0;
device->flags.initialized = true;
+ } else if (device->flags.visited) {
+ goto ok;
}
ret = acpi_scan_attach_handler(device);
return;
device->flags.match_driver = true;
- if (!ret) {
- ret = device_attach(&device->dev);
- if (ret < 0)
- return;
-
- if (!ret && device->pnp.type.platform_id)
- acpi_default_enumeration(device);
+ if (ret > 0) {
+ acpi_device_set_enumerated(device);
+ goto ok;
}
+ ret = device_attach(&device->dev);
+ if (ret < 0)
+ return;
+
+ if (device->pnp.type.platform_id)
+ acpi_default_enumeration(device);
+ else
+ acpi_device_set_enumerated(device);
+
ok:
list_for_each_entry(child, &device->children, node)
acpi_bus_attach(child);
static ssize_t force_remove_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
- return sprintf(buf, "%d\n", !!acpi_force_hot_remove);
+ return sprintf(buf, "%d\n", 0);
}
static ssize_t force_remove_store(struct kobject *kobj,
if (ret < 0)
return ret;
- lock_device_hotplug();
- acpi_force_hot_remove = val;
- unlock_device_hotplug();
+ if (val) {
+ pr_err("Enabling force_remove is not supported anymore. Please report to linux-acpi@vger.kernel.org if you depend on this functionality\n");
+ return -EINVAL;
+ }
return size;
}
}
int __init
-acpi_parse_entries(char *id,
- unsigned long table_size,
- acpi_tbl_entry_handler handler,
- struct acpi_table_header *table_header,
- int entry_id, unsigned int max_entries)
-{
- struct acpi_subtable_proc proc = {
- .id = entry_id,
- .handler = handler,
- };
-
- return acpi_parse_entries_array(id, table_size, table_header,
- &proc, 1, max_entries);
-}
-
-int __init
acpi_table_parse_entries_array(char *id,
unsigned long table_size,
struct acpi_subtable_proc *proc, int proc_num,
* But it's not enough on X86 because ioremap will
* complain later (used by acpi_os_map_memory) that the pages
* that should get mapped are not marked "reserved".
- * Both memblock_reserve and e820_add_region (via arch_reserve_mem_area)
+ * Both memblock_reserve and e820__range_add (via arch_reserve_mem_area)
* works fine.
*/
memblock_reserve(acpi_tables_addr, all_tables_size);
}
EXPORT_SYMBOL(acpi_dev_found);
+struct acpi_dev_present_info {
+ struct acpi_device_id hid[2];
+ const char *uid;
+ s64 hrv;
+};
+
+static int acpi_dev_present_cb(struct device *dev, void *data)
+{
+ struct acpi_device *adev = to_acpi_device(dev);
+ struct acpi_dev_present_info *match = data;
+ unsigned long long hrv;
+ acpi_status status;
+
+ if (acpi_match_device_ids(adev, match->hid))
+ return 0;
+
+ if (match->uid && (!adev->pnp.unique_id ||
+ strcmp(adev->pnp.unique_id, match->uid)))
+ return 0;
+
+ if (match->hrv == -1)
+ return 1;
+
+ status = acpi_evaluate_integer(adev->handle, "_HRV", NULL, &hrv);
+ if (ACPI_FAILURE(status))
+ return 0;
+
+ return hrv == match->hrv;
+}
+
+/**
+ * acpi_dev_present - Detect that a given ACPI device is present
+ * @hid: Hardware ID of the device.
+ * @uid: Unique ID of the device, pass NULL to not check _UID
+ * @hrv: Hardware Revision of the device, pass -1 to not check _HRV
+ *
+ * Return %true if a matching device was present at the moment of invocation.
+ * Note that if the device is pluggable, it may since have disappeared.
+ *
+ * Note that unlike acpi_dev_found() this function checks the status
+ * of the device. So for devices which are present in the dsdt, but
+ * which are disabled (their _STA callback returns 0) this function
+ * will return false.
+ *
+ * For this function to work, acpi_bus_scan() must have been executed
+ * which happens in the subsys_initcall() subsection. Hence, do not
+ * call from a subsys_initcall() or earlier (use acpi_get_devices()
+ * instead). Calling from module_init() is fine (which is synonymous
+ * with device_initcall()).
+ */
+bool acpi_dev_present(const char *hid, const char *uid, s64 hrv)
+{
+ struct acpi_dev_present_info match = {};
+ struct device *dev;
+
+ strlcpy(match.hid[0].id, hid, sizeof(match.hid[0].id));
+ match.uid = uid;
+ match.hrv = hrv;
+
+ dev = bus_find_device(&acpi_bus_type, NULL, &match,
+ acpi_dev_present_cb);
+
+ return !!dev;
+}
+EXPORT_SYMBOL(acpi_dev_present);
+
/*
* acpi_backlight= handling, this is done here rather then in video_detect.c
* because __setup cannot be used in modules.
tristate "Serial ATA and Parallel ATA drivers (libata)"
depends on HAS_IOMEM
depends on BLOCK
- depends on !(M32R || S390) || BROKEN
select SCSI
select GLOB
---help---
If unsure, say N.
+config AHCI_DM816
+ tristate "DaVinci DM816 AHCI SATA support"
+ depends on ARCH_OMAP2PLUS
+ help
+ This option enables support for the DaVinci DM816 SoC's
+ onboard AHCI SATA controller.
+
+ If unsure, say N.
+
config AHCI_ST
tristate "ST AHCI SATA support"
depends on ARCH_STI
If unsure, say N.
-config PATA_AT91
- tristate "PATA support for AT91SAM9260"
- depends on ARM && SOC_AT91SAM9
- help
- This option enables support for IDE devices on the Atmel AT91SAM9260 SoC.
-
- If unsure, say N.
-
config PATA_CMD640_PCI
tristate "CMD640 PCI PATA support (Experimental)"
depends on PCI
obj-$(CONFIG_AHCI_BRCM) += ahci_brcm.o libahci.o libahci_platform.o
obj-$(CONFIG_AHCI_CEVA) += ahci_ceva.o libahci.o libahci_platform.o
obj-$(CONFIG_AHCI_DA850) += ahci_da850.o libahci.o libahci_platform.o
+obj-$(CONFIG_AHCI_DM816) += ahci_dm816.o libahci.o libahci_platform.o
obj-$(CONFIG_AHCI_IMX) += ahci_imx.o libahci.o libahci_platform.o
obj-$(CONFIG_AHCI_MVEBU) += ahci_mvebu.o libahci.o libahci_platform.o
obj-$(CONFIG_AHCI_OCTEON) += ahci_octeon.o
# SFF PIO only
obj-$(CONFIG_PATA_AT32) += pata_at32.o
-obj-$(CONFIG_PATA_AT91) += pata_at91.o
obj-$(CONFIG_PATA_CMD640_PCI) += pata_cmd640.o
obj-$(CONFIG_PATA_FALCON) += pata_falcon.o
obj-$(CONFIG_PATA_ISAPNP) += pata_isapnp.o
--- /dev/null
+/*
+ * DaVinci DM816 AHCI SATA platform driver
+ *
+ * Copyright (C) 2017 BayLibre SAS
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/pm.h>
+#include <linux/platform_device.h>
+#include <linux/libata.h>
+#include <linux/ahci_platform.h>
+
+#include "ahci.h"
+
+#define AHCI_DM816_DRV_NAME "ahci-dm816"
+
+#define AHCI_DM816_PHY_ENPLL(x) ((x) << 0)
+#define AHCI_DM816_PHY_MPY(x) ((x) << 1)
+#define AHCI_DM816_PHY_LOS(x) ((x) << 12)
+#define AHCI_DM816_PHY_RXCDR(x) ((x) << 13)
+#define AHCI_DM816_PHY_RXEQ(x) ((x) << 16)
+#define AHCI_DM816_PHY_TXSWING(x) ((x) << 23)
+
+#define AHCI_DM816_P0PHYCR_REG 0x178
+#define AHCI_DM816_P1PHYCR_REG 0x1f8
+
+#define AHCI_DM816_PLL_OUT 1500000000LU
+
+static const unsigned long pll_mpy_table[] = {
+ 400, 500, 600, 800, 825, 1000, 1200,
+ 1250, 1500, 1600, 1650, 2000, 2200, 2500
+};
+
+static int ahci_dm816_get_mpy_bits(unsigned long refclk_rate)
+{
+ unsigned long pll_multiplier;
+ int i;
+
+ /*
+ * We need to determine the value of the multiplier (MPY) bits.
+ * In order to include the 8.25 multiplier we need to first divide
+ * the refclk rate by 100.
+ */
+ pll_multiplier = AHCI_DM816_PLL_OUT / (refclk_rate / 100);
+
+ for (i = 0; i < ARRAY_SIZE(pll_mpy_table); i++) {
+ if (pll_mpy_table[i] == pll_multiplier)
+ return i;
+ }
+
+ /*
+ * We should have divided evenly - if not, return an invalid
+ * value.
+ */
+ return -1;
+}
+
+static int ahci_dm816_phy_init(struct ahci_host_priv *hpriv, struct device *dev)
+{
+ unsigned long refclk_rate;
+ int mpy;
+ u32 val;
+
+ /*
+ * We should have been supplied two clocks: the functional and
+ * keep-alive clock and the external reference clock. We need the
+ * rate of the latter to calculate the correct value of MPY bits.
+ */
+ if (!hpriv->clks[1]) {
+ dev_err(dev, "reference clock not supplied\n");
+ return -EINVAL;
+ }
+
+ refclk_rate = clk_get_rate(hpriv->clks[1]);
+ if ((refclk_rate % 100) != 0) {
+ dev_err(dev, "reference clock rate must be divisible by 100\n");
+ return -EINVAL;
+ }
+
+ mpy = ahci_dm816_get_mpy_bits(refclk_rate);
+ if (mpy < 0) {
+ dev_err(dev, "can't calculate the MPY bits value\n");
+ return -EINVAL;
+ }
+
+ /* Enable the PHY and configure the first HBA port. */
+ val = AHCI_DM816_PHY_MPY(mpy) | AHCI_DM816_PHY_LOS(1) |
+ AHCI_DM816_PHY_RXCDR(4) | AHCI_DM816_PHY_RXEQ(1) |
+ AHCI_DM816_PHY_TXSWING(3) | AHCI_DM816_PHY_ENPLL(1);
+ writel(val, hpriv->mmio + AHCI_DM816_P0PHYCR_REG);
+
+ /* Configure the second HBA port. */
+ val = AHCI_DM816_PHY_LOS(1) | AHCI_DM816_PHY_RXCDR(4) |
+ AHCI_DM816_PHY_RXEQ(1) | AHCI_DM816_PHY_TXSWING(3);
+ writel(val, hpriv->mmio + AHCI_DM816_P1PHYCR_REG);
+
+ return 0;
+}
+
+static int ahci_dm816_softreset(struct ata_link *link,
+ unsigned int *class, unsigned long deadline)
+{
+ int pmp, ret;
+
+ pmp = sata_srst_pmp(link);
+
+ /*
+ * There's an issue with the SATA controller on DM816 SoC: if we
+ * enable Port Multiplier support, but the drive is connected directly
+ * to the board, it can't be detected. As a workaround: if PMP is
+ * enabled, we first call ahci_do_softreset() and pass it the result of
+ * sata_srst_pmp(). If this call fails, we retry with pmp = 0.
+ */
+ ret = ahci_do_softreset(link, class, pmp, deadline, ahci_check_ready);
+ if (pmp && ret == -EBUSY)
+ return ahci_do_softreset(link, class, 0,
+ deadline, ahci_check_ready);
+
+ return ret;
+}
+
+static struct ata_port_operations ahci_dm816_port_ops = {
+ .inherits = &ahci_platform_ops,
+ .softreset = ahci_dm816_softreset,
+};
+
+static const struct ata_port_info ahci_dm816_port_info = {
+ .flags = AHCI_FLAG_COMMON,
+ .pio_mask = ATA_PIO4,
+ .udma_mask = ATA_UDMA6,
+ .port_ops = &ahci_dm816_port_ops,
+};
+
+static struct scsi_host_template ahci_dm816_platform_sht = {
+ AHCI_SHT(AHCI_DM816_DRV_NAME),
+};
+
+static int ahci_dm816_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct ahci_host_priv *hpriv;
+ int rc;
+
+ hpriv = ahci_platform_get_resources(pdev);
+ if (IS_ERR(hpriv))
+ return PTR_ERR(hpriv);
+
+ rc = ahci_platform_enable_resources(hpriv);
+ if (rc)
+ return rc;
+
+ rc = ahci_dm816_phy_init(hpriv, dev);
+ if (rc)
+ goto disable_resources;
+
+ rc = ahci_platform_init_host(pdev, hpriv,
+ &ahci_dm816_port_info,
+ &ahci_dm816_platform_sht);
+ if (rc)
+ goto disable_resources;
+
+ return 0;
+
+disable_resources:
+ ahci_platform_disable_resources(hpriv);
+
+ return rc;
+}
+
+static SIMPLE_DEV_PM_OPS(ahci_dm816_pm_ops,
+ ahci_platform_suspend,
+ ahci_platform_resume);
+
+static const struct of_device_id ahci_dm816_of_match[] = {
+ { .compatible = "ti,dm816-ahci", },
+ { },
+};
+MODULE_DEVICE_TABLE(of, ahci_dm816_of_match);
+
+static struct platform_driver ahci_dm816_driver = {
+ .probe = ahci_dm816_probe,
+ .remove = ata_platform_remove_one,
+ .driver = {
+ .name = AHCI_DM816_DRV_NAME,
+ .of_match_table = ahci_dm816_of_match,
+ .pm = &ahci_dm816_pm_ops,
+ },
+};
+module_platform_driver(ahci_dm816_driver);
+
+MODULE_DESCRIPTION("DaVinci DM816 AHCI SATA platform driver");
+MODULE_AUTHOR("Bartosz Golaszewski <bgolaszewski@baylibre.com>");
+MODULE_LICENSE("GPL");
int ret;
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!res) {
- dev_err(&pdev->dev, "Platform resource[0] is missing\n");
- return -ENODEV;
- }
-
base = devm_ioremap_resource(&pdev->dev, res);
if (IS_ERR(base))
return PTR_ERR(base);
* LOCKING:
* spin_lock_irqsave(host lock)
*/
-void ata_sg_clean(struct ata_queued_cmd *qc)
+static void ata_sg_clean(struct ata_queued_cmd *qc)
{
struct ata_port *ap = qc->ap;
struct scatterlist *sg = qc->sg;
INIT_LIST_HEAD(&ap->eh_done_q);
init_waitqueue_head(&ap->eh_wait_q);
init_completion(&ap->park_req_pending);
- init_timer_deferrable(&ap->fastdrain_timer);
- ap->fastdrain_timer.function = ata_eh_fastdrain_timerfn;
- ap->fastdrain_timer.data = (unsigned long)ap;
+ setup_deferrable_timer(&ap->fastdrain_timer,
+ ata_eh_fastdrain_timerfn,
+ (unsigned long)ap);
ap->cbl = ATA_CBL_NONE;
}
/**
- * ata_format_dsm_trim_descr() - SATL Write Same to ATA SCT Write Same
- * @cmd: SCSI command being translated
- * @lba: Starting sector
- * @num: Number of sectors to be zero'd.
- *
- * Rewrite the WRITE SAME payload to be an SCT Write Same formatted
- * descriptor.
- * NOTE: Writes a pattern (0's) in the foreground.
- *
- * Return: Number of bytes copied into sglist.
- */
-static size_t ata_format_sct_write_same(struct scsi_cmnd *cmd, u64 lba, u64 num)
-{
- struct scsi_device *sdp = cmd->device;
- size_t len = sdp->sector_size;
- size_t r;
- u16 *buf;
- unsigned long flags;
-
- spin_lock_irqsave(&ata_scsi_rbuf_lock, flags);
- buf = ((void *)ata_scsi_rbuf);
-
- put_unaligned_le16(0x0002, &buf[0]); /* SCT_ACT_WRITE_SAME */
- put_unaligned_le16(0x0101, &buf[1]); /* WRITE PTRN FG */
- put_unaligned_le64(lba, &buf[2]);
- put_unaligned_le64(num, &buf[6]);
- put_unaligned_le32(0u, &buf[10]); /* pattern */
-
- WARN_ON(len > ATA_SCSI_RBUF_SIZE);
-
- if (len > ATA_SCSI_RBUF_SIZE)
- len = ATA_SCSI_RBUF_SIZE;
-
- r = sg_copy_from_buffer(scsi_sglist(cmd), scsi_sg_count(cmd), buf, len);
- spin_unlock_irqrestore(&ata_scsi_rbuf_lock, flags);
-
- return r;
-}
-
-/**
* ata_scsi_write_same_xlat() - SATL Write Same to ATA SCT Write Same
* @qc: Command to be translated
*
if (unlikely(!dev->dma_mode))
goto invalid_opcode;
+ /*
+ * We only allow sending this command through the block layer,
+ * as it modifies the DATA OUT buffer, which would corrupt user
+ * memory for SG_IO commands.
+ */
+ if (unlikely(blk_rq_is_passthrough(scmd->request)))
+ goto invalid_opcode;
+
if (unlikely(scmd->cmd_len < 16)) {
fp = 15;
goto invalid_fld;
}
scsi_16_lba_len(cdb, &block, &n_block);
- if (unmap) {
- /* If trim is not enabled the cmd is invalid. */
- if ((dev->horkage & ATA_HORKAGE_NOTRIM) ||
- !ata_id_has_trim(dev->id)) {
- fp = 1;
- bp = 3;
- goto invalid_fld;
- }
- /* If the request is too large the cmd is invalid */
- if (n_block > 0xffff * trmax) {
- fp = 2;
- goto invalid_fld;
- }
- } else {
- /* If write same is not available the cmd is invalid */
- if (!ata_id_sct_write_same(dev->id)) {
- fp = 1;
- bp = 3;
- goto invalid_fld;
- }
+ if (!unmap ||
+ (dev->horkage & ATA_HORKAGE_NOTRIM) ||
+ !ata_id_has_trim(dev->id)) {
+ fp = 1;
+ bp = 3;
+ goto invalid_fld;
+ }
+ /* If the request is too large the cmd is invalid */
+ if (n_block > 0xffff * trmax) {
+ fp = 2;
+ goto invalid_fld;
}
/*
* For DATA SET MANAGEMENT TRIM in ACS-2 nsect (aka count)
* is defined as number of 512 byte blocks to be transferred.
*/
- if (unmap) {
- size = ata_format_dsm_trim_descr(scmd, trmax, block, n_block);
- if (size != len)
- goto invalid_param_len;
- if (ata_ncq_enabled(dev) && ata_fpdma_dsm_supported(dev)) {
- /* Newer devices support queued TRIM commands */
- tf->protocol = ATA_PROT_NCQ;
- tf->command = ATA_CMD_FPDMA_SEND;
- tf->hob_nsect = ATA_SUBCMD_FPDMA_SEND_DSM & 0x1f;
- tf->nsect = qc->tag << 3;
- tf->hob_feature = (size / 512) >> 8;
- tf->feature = size / 512;
+ size = ata_format_dsm_trim_descr(scmd, trmax, block, n_block);
+ if (size != len)
+ goto invalid_param_len;
- tf->auxiliary = 1;
- } else {
- tf->protocol = ATA_PROT_DMA;
- tf->hob_feature = 0;
- tf->feature = ATA_DSM_TRIM;
- tf->hob_nsect = (size / 512) >> 8;
- tf->nsect = size / 512;
- tf->command = ATA_CMD_DSM;
- }
- } else {
- size = ata_format_sct_write_same(scmd, block, n_block);
- if (size != len)
- goto invalid_param_len;
+ if (ata_ncq_enabled(dev) && ata_fpdma_dsm_supported(dev)) {
+ /* Newer devices support queued TRIM commands */
+ tf->protocol = ATA_PROT_NCQ;
+ tf->command = ATA_CMD_FPDMA_SEND;
+ tf->hob_nsect = ATA_SUBCMD_FPDMA_SEND_DSM & 0x1f;
+ tf->nsect = qc->tag << 3;
+ tf->hob_feature = (size / 512) >> 8;
+ tf->feature = size / 512;
- tf->hob_feature = 0;
- tf->feature = 0;
- tf->hob_nsect = 0;
- tf->nsect = 1;
- tf->lbah = 0;
- tf->lbam = 0;
- tf->lbal = ATA_CMD_STANDBYNOW1;
- tf->hob_lbah = 0;
- tf->hob_lbam = 0;
- tf->hob_lbal = 0;
- tf->device = ATA_CMD_STANDBYNOW1;
+ tf->auxiliary = 1;
+ } else {
tf->protocol = ATA_PROT_DMA;
- tf->command = ATA_CMD_WRITE_LOG_DMA_EXT;
- if (unlikely(dev->flags & ATA_DFLAG_PIO))
- tf->command = ATA_CMD_WRITE_LOG_EXT;
+ tf->hob_feature = 0;
+ tf->feature = ATA_DSM_TRIM;
+ tf->hob_nsect = (size / 512) >> 8;
+ tf->nsect = size / 512;
+ tf->command = ATA_CMD_DSM;
}
tf->flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE | ATA_TFLAG_LBA48 |
case START_STOP:
supported = 3;
break;
- case WRITE_SAME_16:
- if (!ata_id_sct_write_same(dev->id))
- break;
- /* fallthrough: if SCT ... only enable for ZBC */
case ZBC_IN:
case ZBC_OUT:
if (ata_id_zoned_cap(dev->id) ||
+++ /dev/null
-/*
- * PATA driver for AT91SAM9260 Static Memory Controller
- * with CompactFlash interface in True IDE mode
- *
- * Copyright (C) 2009 Matyukevich Sergey
- * 2011 Igor Plyatov
- *
- * Based on:
- * * generic platform driver by Paul Mundt: drivers/ata/pata_platform.c
- * * pata_at32 driver by Kristoffer Nyborg Gregertsen
- * * at91_ide driver by Stanislaw Gruszka
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation.
- *
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/blkdev.h>
-#include <linux/gfp.h>
-#include <scsi/scsi_host.h>
-#include <linux/ata.h>
-#include <linux/clk.h>
-#include <linux/libata.h>
-#include <linux/mfd/syscon.h>
-#include <linux/mfd/syscon/atmel-smc.h>
-#include <linux/platform_device.h>
-#include <linux/ata_platform.h>
-#include <linux/platform_data/atmel.h>
-#include <linux/regmap.h>
-#include <linux/gpio.h>
-
-#define DRV_NAME "pata_at91"
-#define DRV_VERSION "0.3"
-
-#define CF_IDE_OFFSET 0x00c00000
-#define CF_ALT_IDE_OFFSET 0x00e00000
-#define CF_IDE_RES_SIZE 0x08
-#define CS_PULSE_MAXIMUM 319
-#define ER_SMC_CALC 1
-#define ER_SMC_RECALC 2
-
-struct at91_ide_info {
- unsigned long mode;
- unsigned int cs;
- struct clk *mck;
- void __iomem *ide_addr;
- void __iomem *alt_addr;
-};
-
-/**
- * struct smc_range - range of valid values for SMC register.
- */
-struct smc_range {
- int min;
- int max;
-};
-
-struct regmap *smc;
-
-struct at91sam9_smc_generic_fields {
- struct regmap_field *setup;
- struct regmap_field *pulse;
- struct regmap_field *cycle;
- struct regmap_field *mode;
-} fields;
-
-/**
- * adjust_smc_value - adjust value for one of SMC registers.
- * @value: adjusted value
- * @range: array of SMC ranges with valid values
- * @size: SMC ranges array size
- *
- * This returns the difference between input and output value or negative
- * in case of invalid input value.
- * If negative returned, then output value = maximal possible from ranges.
- */
-static int adjust_smc_value(int *value, struct smc_range *range, int size)
-{
- int maximum = (range + size - 1)->max;
- int remainder;
-
- do {
- if (*value < range->min) {
- remainder = range->min - *value;
- *value = range->min; /* nearest valid value */
- return remainder;
- } else if ((range->min <= *value) && (*value <= range->max))
- return 0;
-
- range++;
- } while (--size);
- *value = maximum;
-
- return -1; /* invalid value */
-}
-
-/**
- * calc_smc_vals - calculate SMC register values
- * @dev: ATA device
- * @setup: SMC_SETUP register value
- * @pulse: SMC_PULSE register value
- * @cycle: SMC_CYCLE register value
- *
- * This returns negative in case of invalid values for SMC registers:
- * -ER_SMC_RECALC - recalculation required for SMC values,
- * -ER_SMC_CALC - calculation failed (invalid input values).
- *
- * SMC use special coding scheme, see "Coding and Range of Timing
- * Parameters" table from AT91SAM9 datasheets.
- *
- * SMC_SETUP = 128*setup[5] + setup[4:0]
- * SMC_PULSE = 256*pulse[6] + pulse[5:0]
- * SMC_CYCLE = 256*cycle[8:7] + cycle[6:0]
- */
-static int calc_smc_vals(struct device *dev,
- int *setup, int *pulse, int *cycle, int *cs_pulse)
-{
- int ret_val;
- int err = 0;
- struct smc_range range_setup[] = { /* SMC_SETUP valid values */
- {.min = 0, .max = 31}, /* first range */
- {.min = 128, .max = 159} /* second range */
- };
- struct smc_range range_pulse[] = { /* SMC_PULSE valid values */
- {.min = 0, .max = 63}, /* first range */
- {.min = 256, .max = 319} /* second range */
- };
- struct smc_range range_cycle[] = { /* SMC_CYCLE valid values */
- {.min = 0, .max = 127}, /* first range */
- {.min = 256, .max = 383}, /* second range */
- {.min = 512, .max = 639}, /* third range */
- {.min = 768, .max = 895} /* fourth range */
- };
-
- ret_val = adjust_smc_value(setup, range_setup, ARRAY_SIZE(range_setup));
- if (ret_val < 0)
- dev_warn(dev, "maximal SMC Setup value\n");
- else
- *cycle += ret_val;
-
- ret_val = adjust_smc_value(pulse, range_pulse, ARRAY_SIZE(range_pulse));
- if (ret_val < 0)
- dev_warn(dev, "maximal SMC Pulse value\n");
- else
- *cycle += ret_val;
-
- ret_val = adjust_smc_value(cycle, range_cycle, ARRAY_SIZE(range_cycle));
- if (ret_val < 0)
- dev_warn(dev, "maximal SMC Cycle value\n");
-
- *cs_pulse = *cycle;
- if (*cs_pulse > CS_PULSE_MAXIMUM) {
- dev_err(dev, "unable to calculate valid SMC settings\n");
- return -ER_SMC_CALC;
- }
-
- ret_val = adjust_smc_value(cs_pulse, range_pulse,
- ARRAY_SIZE(range_pulse));
- if (ret_val < 0) {
- dev_warn(dev, "maximal SMC CS Pulse value\n");
- } else if (ret_val != 0) {
- *cycle = *cs_pulse;
- dev_warn(dev, "SMC Cycle extended\n");
- err = -ER_SMC_RECALC;
- }
-
- return err;
-}
-
-/**
- * to_smc_format - convert values into SMC format
- * @setup: SETUP value of SMC Setup Register
- * @pulse: PULSE value of SMC Pulse Register
- * @cycle: CYCLE value of SMC Cycle Register
- * @cs_pulse: NCS_PULSE value of SMC Pulse Register
- */
-static void to_smc_format(int *setup, int *pulse, int *cycle, int *cs_pulse)
-{
- *setup = (*setup & 0x1f) | ((*setup & 0x80) >> 2);
- *pulse = (*pulse & 0x3f) | ((*pulse & 0x100) >> 2);
- *cycle = (*cycle & 0x7f) | ((*cycle & 0x300) >> 1);
- *cs_pulse = (*cs_pulse & 0x3f) | ((*cs_pulse & 0x100) >> 2);
-}
-
-static unsigned long calc_mck_cycles(unsigned long ns, unsigned long mck_hz)
-{
- unsigned long mul;
-
- /*
- * cycles = x [nsec] * f [Hz] / 10^9 [ns in sec] =
- * x * (f / 1_000_000_000) =
- * x * ((f * 65536) / 1_000_000_000) / 65536 =
- * x * (((f / 10_000) * 65536) / 100_000) / 65536 =
- */
-
- mul = (mck_hz / 10000) << 16;
- mul /= 100000;
-
- return (ns * mul + 65536) >> 16; /* rounding */
-}
-
-/**
- * set_smc_timing - SMC timings setup.
- * @dev: device
- * @info: AT91 IDE info
- * @ata: ATA timings
- *
- * Its assumed that write timings are same as read timings,
- * cs_setup = 0 and cs_pulse = cycle.
- */
-static void set_smc_timing(struct device *dev, struct ata_device *adev,
- struct at91_ide_info *info, const struct ata_timing *ata)
-{
- int ret = 0;
- int use_iordy;
- unsigned int t6z; /* data tristate time in ns */
- unsigned int cycle; /* SMC Cycle width in MCK ticks */
- unsigned int setup; /* SMC Setup width in MCK ticks */
- unsigned int pulse; /* CFIOR and CFIOW pulse width in MCK ticks */
- unsigned int cs_pulse; /* CS4 or CS5 pulse width in MCK ticks*/
- unsigned int tdf_cycles; /* SMC TDF MCK ticks */
- unsigned long mck_hz; /* MCK frequency in Hz */
-
- t6z = (ata->mode < XFER_PIO_5) ? 30 : 20;
- mck_hz = clk_get_rate(info->mck);
- cycle = calc_mck_cycles(ata->cyc8b, mck_hz);
- setup = calc_mck_cycles(ata->setup, mck_hz);
- pulse = calc_mck_cycles(ata->act8b, mck_hz);
- tdf_cycles = calc_mck_cycles(t6z, mck_hz);
-
- do {
- ret = calc_smc_vals(dev, &setup, &pulse, &cycle, &cs_pulse);
- } while (ret == -ER_SMC_RECALC);
-
- if (ret == -ER_SMC_CALC)
- dev_err(dev, "Interface may not operate correctly\n");
-
- dev_dbg(dev, "SMC Setup=%u, Pulse=%u, Cycle=%u, CS Pulse=%u\n",
- setup, pulse, cycle, cs_pulse);
- to_smc_format(&setup, &pulse, &cycle, &cs_pulse);
- /* disable or enable waiting for IORDY signal */
- use_iordy = ata_pio_need_iordy(adev);
- if (use_iordy)
- info->mode |= AT91_SMC_EXNWMODE_READY;
-
- if (tdf_cycles > 15) {
- tdf_cycles = 15;
- dev_warn(dev, "maximal SMC TDF Cycles value\n");
- }
-
- dev_dbg(dev, "Use IORDY=%u, TDF Cycles=%u\n", use_iordy, tdf_cycles);
-
- regmap_fields_write(fields.setup, info->cs,
- AT91SAM9_SMC_NRDSETUP(setup) |
- AT91SAM9_SMC_NWESETUP(setup) |
- AT91SAM9_SMC_NCS_NRDSETUP(0) |
- AT91SAM9_SMC_NCS_WRSETUP(0));
- regmap_fields_write(fields.pulse, info->cs,
- AT91SAM9_SMC_NRDPULSE(pulse) |
- AT91SAM9_SMC_NWEPULSE(pulse) |
- AT91SAM9_SMC_NCS_NRDPULSE(cs_pulse) |
- AT91SAM9_SMC_NCS_WRPULSE(cs_pulse));
- regmap_fields_write(fields.cycle, info->cs,
- AT91SAM9_SMC_NRDCYCLE(cycle) |
- AT91SAM9_SMC_NWECYCLE(cycle));
- regmap_fields_write(fields.mode, info->cs, info->mode |
- AT91_SMC_TDF_(tdf_cycles));
-}
-
-static void pata_at91_set_piomode(struct ata_port *ap, struct ata_device *adev)
-{
- struct at91_ide_info *info = ap->host->private_data;
- struct ata_timing timing;
- int ret;
-
- /* Compute ATA timing and set it to SMC */
- ret = ata_timing_compute(adev, adev->pio_mode, &timing, 1000, 0);
- if (ret) {
- dev_warn(ap->dev, "Failed to compute ATA timing %d, "
- "set PIO_0 timing\n", ret);
- timing = *ata_timing_find_mode(XFER_PIO_0);
- }
- set_smc_timing(ap->dev, adev, info, &timing);
-}
-
-static unsigned int pata_at91_data_xfer_noirq(struct ata_queued_cmd *qc,
- unsigned char *buf, unsigned int buflen, int rw)
-{
- struct at91_ide_info *info = qc->dev->link->ap->host->private_data;
- unsigned int consumed;
- unsigned int mode;
- unsigned long flags;
-
- local_irq_save(flags);
- regmap_fields_read(fields.mode, info->cs, &mode);
-
- /* set 16bit mode before writing data */
- regmap_fields_write(fields.mode, info->cs, (mode & ~AT91_SMC_DBW) |
- AT91_SMC_DBW_16);
-
- consumed = ata_sff_data_xfer(qc, buf, buflen, rw);
-
- /* restore 8bit mode after data is written */
- regmap_fields_write(fields.mode, info->cs, (mode & ~AT91_SMC_DBW) |
- AT91_SMC_DBW_8);
-
- local_irq_restore(flags);
- return consumed;
-}
-
-static struct scsi_host_template pata_at91_sht = {
- ATA_PIO_SHT(DRV_NAME),
-};
-
-static struct ata_port_operations pata_at91_port_ops = {
- .inherits = &ata_sff_port_ops,
-
- .sff_data_xfer = pata_at91_data_xfer_noirq,
- .set_piomode = pata_at91_set_piomode,
- .cable_detect = ata_cable_40wire,
-};
-
-static int at91sam9_smc_fields_init(struct device *dev)
-{
- struct reg_field field = REG_FIELD(0, 0, 31);
-
- field.id_size = 8;
- field.id_offset = AT91SAM9_SMC_GENERIC_BLK_SZ;
-
- field.reg = AT91SAM9_SMC_SETUP(AT91SAM9_SMC_GENERIC);
- fields.setup = devm_regmap_field_alloc(dev, smc, field);
- if (IS_ERR(fields.setup))
- return PTR_ERR(fields.setup);
-
- field.reg = AT91SAM9_SMC_PULSE(AT91SAM9_SMC_GENERIC);
- fields.pulse = devm_regmap_field_alloc(dev, smc, field);
- if (IS_ERR(fields.pulse))
- return PTR_ERR(fields.pulse);
-
- field.reg = AT91SAM9_SMC_CYCLE(AT91SAM9_SMC_GENERIC);
- fields.cycle = devm_regmap_field_alloc(dev, smc, field);
- if (IS_ERR(fields.cycle))
- return PTR_ERR(fields.cycle);
-
- field.reg = AT91SAM9_SMC_MODE(AT91SAM9_SMC_GENERIC);
- fields.mode = devm_regmap_field_alloc(dev, smc, field);
-
- return PTR_ERR_OR_ZERO(fields.mode);
-}
-
-static int pata_at91_probe(struct platform_device *pdev)
-{
- struct at91_cf_data *board = dev_get_platdata(&pdev->dev);
- struct device *dev = &pdev->dev;
- struct at91_ide_info *info;
- struct resource *mem_res;
- struct ata_host *host;
- struct ata_port *ap;
-
- int irq_flags = 0;
- int irq = 0;
- int ret;
-
- /* get platform resources: IO/CTL memories and irq/rst pins */
-
- if (pdev->num_resources != 1) {
- dev_err(&pdev->dev, "invalid number of resources\n");
- return -EINVAL;
- }
-
- mem_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-
- if (!mem_res) {
- dev_err(dev, "failed to get mem resource\n");
- return -EINVAL;
- }
-
- irq = board->irq_pin;
-
- smc = syscon_regmap_lookup_by_phandle(pdev->dev.of_node, "atmel,smc");
- if (IS_ERR(smc))
- return PTR_ERR(smc);
-
- ret = at91sam9_smc_fields_init(dev);
- if (ret < 0)
- return ret;
-
- /* init ata host */
-
- host = ata_host_alloc(dev, 1);
-
- if (!host)
- return -ENOMEM;
-
- ap = host->ports[0];
- ap->ops = &pata_at91_port_ops;
- ap->flags |= ATA_FLAG_SLAVE_POSS;
- ap->pio_mask = ATA_PIO4;
-
- if (!gpio_is_valid(irq)) {
- ap->flags |= ATA_FLAG_PIO_POLLING;
- ata_port_desc(ap, "no IRQ, using PIO polling");
- }
-
- info = devm_kzalloc(dev, sizeof(*info), GFP_KERNEL);
-
- if (!info) {
- dev_err(dev, "failed to allocate memory for private data\n");
- return -ENOMEM;
- }
-
- info->mck = clk_get(NULL, "mck");
-
- if (IS_ERR(info->mck)) {
- dev_err(dev, "failed to get access to mck clock\n");
- return -ENODEV;
- }
-
- info->cs = board->chipselect;
- info->mode = AT91_SMC_READMODE | AT91_SMC_WRITEMODE |
- AT91_SMC_EXNWMODE_READY | AT91_SMC_BAT_SELECT |
- AT91_SMC_DBW_8 | AT91_SMC_TDF_(0);
-
- info->ide_addr = devm_ioremap(dev,
- mem_res->start + CF_IDE_OFFSET, CF_IDE_RES_SIZE);
-
- if (!info->ide_addr) {
- dev_err(dev, "failed to map IO base\n");
- ret = -ENOMEM;
- goto err_put;
- }
-
- info->alt_addr = devm_ioremap(dev,
- mem_res->start + CF_ALT_IDE_OFFSET, CF_IDE_RES_SIZE);
-
- if (!info->alt_addr) {
- dev_err(dev, "failed to map CTL base\n");
- ret = -ENOMEM;
- goto err_put;
- }
-
- ap->ioaddr.cmd_addr = info->ide_addr;
- ap->ioaddr.ctl_addr = info->alt_addr + 0x06;
- ap->ioaddr.altstatus_addr = ap->ioaddr.ctl_addr;
-
- ata_sff_std_ports(&ap->ioaddr);
-
- ata_port_desc(ap, "mmio cmd 0x%llx ctl 0x%llx",
- (unsigned long long)mem_res->start + CF_IDE_OFFSET,
- (unsigned long long)mem_res->start + CF_ALT_IDE_OFFSET);
-
- host->private_data = info;
-
- ret = ata_host_activate(host, gpio_is_valid(irq) ? gpio_to_irq(irq) : 0,
- gpio_is_valid(irq) ? ata_sff_interrupt : NULL,
- irq_flags, &pata_at91_sht);
- if (ret)
- goto err_put;
-
- return 0;
-
-err_put:
- clk_put(info->mck);
- return ret;
-}
-
-static int pata_at91_remove(struct platform_device *pdev)
-{
- struct ata_host *host = platform_get_drvdata(pdev);
- struct at91_ide_info *info;
-
- if (!host)
- return 0;
- info = host->private_data;
-
- ata_host_detach(host);
-
- if (!info)
- return 0;
-
- clk_put(info->mck);
-
- return 0;
-}
-
-static struct platform_driver pata_at91_driver = {
- .probe = pata_at91_probe,
- .remove = pata_at91_remove,
- .driver = {
- .name = DRV_NAME,
- },
-};
-
-module_platform_driver(pata_at91_driver);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Driver for CF in True IDE mode on AT91SAM9260 SoC");
-MODULE_AUTHOR("Matyukevich Sergey");
-MODULE_VERSION(DRV_VERSION);
-
};
const struct ata_port_info *ppi[] = { &info, &info };
- /* SB600/700 don't have secondary port wired */
- if ((pdev->device == PCI_DEVICE_ID_ATI_IXP600_IDE) ||
- (pdev->device == PCI_DEVICE_ID_ATI_IXP700_IDE))
- ppi[1] = &ata_dummy_port_info;
-
return ata_pci_bmdma_init_one(pdev, ppi, &atiixp_sht, NULL,
ATA_HOST_PARALLEL_SCAN);
}
}
#endif /* CONFIG_PM_SLEEP */
-static struct of_device_id pata_macio_match[] =
+static const struct of_device_id pata_macio_match[] =
{
{
.name = "IDE",
}
#endif
-static struct of_device_id mpc52xx_ata_of_match[] = {
+static const struct of_device_id mpc52xx_ata_of_match[] = {
{ .compatible = "fsl,mpc5200-ata", },
{ .compatible = "mpc5200-ata", },
{},
reg_shift, pio_mask, &pata_platform_sht);
}
-static struct of_device_id pata_of_platform_match[] = {
+static const struct of_device_id pata_of_platform_match[] = {
{ .compatible = "ata-generic", },
{ },
};
}
#endif
-static struct of_device_id fsl_sata_match[] = {
+static const struct of_device_id fsl_sata_match[] = {
{
.compatible = "fsl,pq-sata",
},
#endif
#ifdef CONFIG_OF
-static struct of_device_id mv_sata_dt_ids[] = {
+static const struct of_device_id mv_sata_dt_ids[] = {
{ .compatible = "marvell,armada-370-sata", },
{ .compatible = "marvell,orion-sata", },
{},
pci_write_config_byte(pdev, SATA_NATIVE_MODE, tmp8);
}
- /* enable IRQ on hotplug */
- pci_read_config_byte(pdev, SVIA_MISC_3, &tmp8);
- if ((tmp8 & SATA_HOTPLUG) != SATA_HOTPLUG) {
- dev_dbg(&pdev->dev,
- "enabling SATA hotplug (0x%x)\n",
- (int) tmp8);
- tmp8 |= SATA_HOTPLUG;
- pci_write_config_byte(pdev, SVIA_MISC_3, tmp8);
+ if (board_id == vt6421) {
+ /* enable IRQ on hotplug */
+ pci_read_config_byte(pdev, SVIA_MISC_3, &tmp8);
+ if ((tmp8 & SATA_HOTPLUG) != SATA_HOTPLUG) {
+ dev_dbg(&pdev->dev,
+ "enabling SATA hotplug (0x%x)\n",
+ (int) tmp8);
+ tmp8 |= SATA_HOTPLUG;
+ pci_write_config_byte(pdev, SVIA_MISC_3, tmp8);
+ }
}
/*
data->host_data = host_data;
domain = irq_domain_create_hierarchy(dev->msi_domain, 0, nvec,
- of_node_to_fwnode(dev->of_node),
- ops, data);
+ dev->fwnode, ops, data);
if (!domain)
goto free_priv;
#define genpd_lock_interruptible(p) p->lock_ops->lock_interruptible(p)
#define genpd_unlock(p) p->lock_ops->unlock(p)
+#define genpd_status_on(genpd) (genpd->status == GPD_STATE_ACTIVE)
#define genpd_is_irq_safe(genpd) (genpd->flags & GENPD_FLAG_IRQ_SAFE)
+#define genpd_is_always_on(genpd) (genpd->flags & GENPD_FLAG_ALWAYS_ON)
static inline bool irq_safe_dev_in_no_sleep_domain(struct device *dev,
struct generic_pm_domain *genpd)
ret = pm_runtime_is_irq_safe(dev) && !genpd_is_irq_safe(genpd);
- /* Warn once if IRQ safe dev in no sleep domain */
- if (ret)
+ /*
+ * Warn once if an IRQ safe device is attached to a no sleep domain, as
+ * to indicate a suboptimal configuration for PM. For an always on
+ * domain this isn't case, thus don't warn.
+ */
+ if (ret && !genpd_is_always_on(genpd))
dev_warn_once(dev, "PM domain %s will not be powered off\n",
genpd->name);
* (1) The domain is already in the "power off" state.
* (2) System suspend is in progress.
*/
- if (genpd->status == GPD_STATE_POWER_OFF
- || genpd->prepared_count > 0)
+ if (!genpd_status_on(genpd) || genpd->prepared_count > 0)
return 0;
- if (atomic_read(&genpd->sd_count) > 0)
+ /*
+ * Abort power off for the PM domain in the following situations:
+ * (1) The domain is configured as always on.
+ * (2) When the domain has a subdomain being powered on.
+ */
+ if (genpd_is_always_on(genpd) || atomic_read(&genpd->sd_count) > 0)
return -EBUSY;
list_for_each_entry(pdd, &genpd->dev_list, list_node) {
struct gpd_link *link;
int ret = 0;
- if (genpd->status == GPD_STATE_ACTIVE)
+ if (genpd_status_on(genpd))
return 0;
/*
{
struct gpd_link *link;
- if (genpd->status == GPD_STATE_POWER_OFF)
+ if (!genpd_status_on(genpd) || genpd_is_always_on(genpd))
return;
if (genpd->suspended_count != genpd->device_count
/* Choose the deepest state when suspending */
genpd->state_idx = genpd->state_count - 1;
- _genpd_power_off(genpd, false);
+ if (_genpd_power_off(genpd, false))
+ return;
genpd->status = GPD_STATE_POWER_OFF;
{
struct gpd_link *link;
- if (genpd->status == GPD_STATE_ACTIVE)
+ if (genpd_status_on(genpd))
return;
list_for_each_entry(link, &genpd->slave_links, slave_node) {
genpd_lock(subdomain);
genpd_lock_nested(genpd, SINGLE_DEPTH_NESTING);
- if (genpd->status == GPD_STATE_POWER_OFF
- && subdomain->status != GPD_STATE_POWER_OFF) {
+ if (!genpd_status_on(genpd) && genpd_status_on(subdomain)) {
ret = -EINVAL;
goto out;
}
list_add_tail(&link->master_node, &genpd->master_links);
link->slave = subdomain;
list_add_tail(&link->slave_node, &subdomain->slave_links);
- if (subdomain->status != GPD_STATE_POWER_OFF)
+ if (genpd_status_on(subdomain))
genpd_sd_counter_inc(genpd);
out:
list_del(&link->master_node);
list_del(&link->slave_node);
kfree(link);
- if (subdomain->status != GPD_STATE_POWER_OFF)
+ if (genpd_status_on(subdomain))
genpd_sd_counter_dec(genpd);
ret = 0;
genpd->dev_ops.start = pm_clk_resume;
}
+ /* Always-on domains must be powered on at initialization. */
+ if (genpd_is_always_on(genpd) && !genpd_status_on(genpd))
+ return -EINVAL;
+
/* Use only one "off" state if there were no states declared */
if (genpd->state_count == 0) {
ret = genpd_set_default_power_state(genpd);
mutex_lock(&gpd_list_lock);
- if (pm_genpd_present(genpd))
+ if (pm_genpd_present(genpd)) {
ret = genpd_add_provider(np, genpd_xlate_simple, genpd);
-
- if (!ret) {
- genpd->provider = &np->fwnode;
- genpd->has_provider = true;
+ if (!ret) {
+ genpd->provider = &np->fwnode;
+ genpd->has_provider = true;
+ }
}
mutex_unlock(&gpd_list_lock);
int err;
u32 residency;
u32 entry_latency, exit_latency;
- const struct of_device_id *match_id;
-
- match_id = of_match_node(idle_state_match, state_node);
- if (!match_id)
- return -EINVAL;
err = of_property_read_u32(state_node, "entry-latency-us",
&entry_latency);
int err, ret;
int count;
struct of_phandle_iterator it;
+ const struct of_device_id *match_id;
count = of_count_phandle_with_args(dn, "domain-idle-states", NULL);
if (count <= 0)
/* Loop over the phandles until all the requested entry is found */
of_for_each_phandle(&it, err, dn, "domain-idle-states", NULL, 0) {
np = it.node;
+ match_id = of_match_node(idle_state_match, np);
+ if (!match_id)
+ continue;
ret = genpd_parse_state(&st[i++], np);
if (ret) {
pr_err
}
}
- *n = count;
- *states = st;
+ *n = i;
+ if (!i)
+ kfree(st);
+ else
+ *states = st;
return 0;
}
if (WARN_ON(genpd->status >= ARRAY_SIZE(status_lookup)))
goto exit;
- if (genpd->status == GPD_STATE_POWER_OFF)
+ if (!genpd_status_on(genpd))
snprintf(state, sizeof(state), "%s-%u",
status_lookup[genpd->status], genpd->state_idx);
else
#include <linux/kernel.h>
#include <linux/of.h>
#include <linux/of_address.h>
+#include <linux/of_graph.h>
#include <linux/property.h>
#include <linux/etherdevice.h>
#include <linux/phy.h>
const char *propname,
const char **strings, size_t nval)
{
+ const struct property_entry *prop;
const void *pointer;
- size_t length = nval * sizeof(*strings);
+ size_t array_len, length;
+
+ /* Find out the array length. */
+ prop = pset_prop_get(pset, propname);
+ if (!prop)
+ return -EINVAL;
+
+ if (!prop->is_array)
+ /* The array length for a non-array string property is 1. */
+ array_len = 1;
+ else
+ /* Find the length of an array. */
+ array_len = pset_prop_count_elems_of_size(pset, propname,
+ sizeof(const char *));
+
+ /* Return how many there are if strings is NULL. */
+ if (!strings)
+ return array_len;
+
+ array_len = min(nval, array_len);
+ length = array_len * sizeof(*strings);
pointer = pset_prop_find(pset, propname, length);
if (IS_ERR(pointer))
return PTR_ERR(pointer);
memcpy(strings, pointer, length);
- return 0;
-}
-static int pset_prop_read_string(struct property_set *pset,
- const char *propname, const char **strings)
-{
- const struct property_entry *prop;
- const char * const *pointer;
-
- prop = pset_prop_get(pset, propname);
- if (!prop)
- return -EINVAL;
- if (!prop->is_string)
- return -EILSEQ;
- if (prop->is_array) {
- pointer = prop->pointer.str;
- if (!pointer)
- return -ENODATA;
- } else {
- pointer = &prop->value.str;
- if (*pointer && strnlen(*pointer, prop->length) >= prop->length)
- return -EILSEQ;
- }
-
- *strings = *pointer;
- return 0;
+ return array_len;
}
-static inline struct fwnode_handle *dev_fwnode(struct device *dev)
+struct fwnode_handle *dev_fwnode(struct device *dev)
{
return IS_ENABLED(CONFIG_OF) && dev->of_node ?
&dev->of_node->fwnode : dev->fwnode;
}
+EXPORT_SYMBOL_GPL(dev_fwnode);
/**
* device_property_present - check if a property of a device is present
* Function reads an array of string properties with @propname from the device
* firmware description and stores them to @val if found.
*
- * Return: number of values if @val was %NULL,
- * %0 if the property was found (success),
+ * Return: number of values read on success if @val is non-NULL,
+ * number of values available on success if @val is NULL,
* %-EINVAL if given arguments are not valid,
* %-ENODATA if the property does not have a value,
* %-EPROTO or %-EILSEQ if the property is not an array of strings,
return acpi_node_prop_read(fwnode, propname, DEV_PROP_STRING,
val, nval);
else if (is_pset_node(fwnode))
- return val ?
- pset_prop_read_string_array(to_pset_node(fwnode),
- propname, val, nval) :
- pset_prop_count_elems_of_size(to_pset_node(fwnode),
- propname,
- sizeof(const char *));
- return -ENXIO;
-}
-
-static int __fwnode_property_read_string(struct fwnode_handle *fwnode,
- const char *propname, const char **val)
-{
- if (is_of_node(fwnode))
- return of_property_read_string(to_of_node(fwnode), propname, val);
- else if (is_acpi_node(fwnode))
- return acpi_node_prop_read(fwnode, propname, DEV_PROP_STRING,
- val, 1);
- else if (is_pset_node(fwnode))
- return pset_prop_read_string(to_pset_node(fwnode), propname, val);
+ return pset_prop_read_string_array(to_pset_node(fwnode),
+ propname, val, nval);
return -ENXIO;
}
* Read an string list property @propname from the given firmware node and store
* them to @val if found.
*
- * Return: number of values if @val was %NULL,
- * %0 if the property was found (success),
+ * Return: number of values read on success if @val is non-NULL,
+ * number of values available on success if @val is NULL,
* %-EINVAL if given arguments are not valid,
* %-ENODATA if the property does not have a value,
- * %-EPROTO if the property is not an array of strings,
+ * %-EPROTO or %-EILSEQ if the property is not an array of strings,
* %-EOVERFLOW if the size of the property is not as expected,
* %-ENXIO if no suitable firmware interface is present.
*/
int fwnode_property_read_string(struct fwnode_handle *fwnode,
const char *propname, const char **val)
{
- int ret;
+ int ret = fwnode_property_read_string_array(fwnode, propname, val, 1);
- ret = __fwnode_property_read_string(fwnode, propname, val);
- if (ret == -EINVAL && !IS_ERR_OR_NULL(fwnode) &&
- !IS_ERR_OR_NULL(fwnode->secondary))
- ret = __fwnode_property_read_string(fwnode->secondary,
- propname, val);
- return ret;
+ return ret < 0 ? ret : 0;
}
EXPORT_SYMBOL_GPL(fwnode_property_read_string);
EXPORT_SYMBOL_GPL(device_add_properties);
/**
- * device_get_next_child_node - Return the next child node handle for a device
- * @dev: Device to find the next child node for.
- * @child: Handle to one of the device's child nodes or a null handle.
+ * fwnode_get_next_parent - Iterate to the node's parent
+ * @fwnode: Firmware whose parent is retrieved
+ *
+ * This is like fwnode_get_parent() except that it drops the refcount
+ * on the passed node, making it suitable for iterating through a
+ * node's parents.
+ *
+ * Returns a node pointer with refcount incremented, use
+ * fwnode_handle_node() on it when done.
*/
-struct fwnode_handle *device_get_next_child_node(struct device *dev,
+struct fwnode_handle *fwnode_get_next_parent(struct fwnode_handle *fwnode)
+{
+ struct fwnode_handle *parent = fwnode_get_parent(fwnode);
+
+ fwnode_handle_put(fwnode);
+
+ return parent;
+}
+EXPORT_SYMBOL_GPL(fwnode_get_next_parent);
+
+/**
+ * fwnode_get_parent - Return parent firwmare node
+ * @fwnode: Firmware whose parent is retrieved
+ *
+ * Return parent firmware node of the given node if possible or %NULL if no
+ * parent was available.
+ */
+struct fwnode_handle *fwnode_get_parent(struct fwnode_handle *fwnode)
+{
+ struct fwnode_handle *parent = NULL;
+
+ if (is_of_node(fwnode)) {
+ struct device_node *node;
+
+ node = of_get_parent(to_of_node(fwnode));
+ if (node)
+ parent = &node->fwnode;
+ } else if (is_acpi_node(fwnode)) {
+ parent = acpi_node_get_parent(fwnode);
+ }
+
+ return parent;
+}
+EXPORT_SYMBOL_GPL(fwnode_get_parent);
+
+/**
+ * fwnode_get_next_child_node - Return the next child node handle for a node
+ * @fwnode: Firmware node to find the next child node for.
+ * @child: Handle to one of the node's child nodes or a %NULL handle.
+ */
+struct fwnode_handle *fwnode_get_next_child_node(struct fwnode_handle *fwnode,
struct fwnode_handle *child)
{
- if (IS_ENABLED(CONFIG_OF) && dev->of_node) {
+ if (is_of_node(fwnode)) {
struct device_node *node;
- node = of_get_next_available_child(dev->of_node, to_of_node(child));
+ node = of_get_next_available_child(to_of_node(fwnode),
+ to_of_node(child));
if (node)
return &node->fwnode;
- } else if (IS_ENABLED(CONFIG_ACPI)) {
- return acpi_get_next_subnode(dev, child);
+ } else if (is_acpi_node(fwnode)) {
+ return acpi_get_next_subnode(fwnode, child);
}
+
return NULL;
}
+EXPORT_SYMBOL_GPL(fwnode_get_next_child_node);
+
+/**
+ * device_get_next_child_node - Return the next child node handle for a device
+ * @dev: Device to find the next child node for.
+ * @child: Handle to one of the device's child nodes or a null handle.
+ */
+struct fwnode_handle *device_get_next_child_node(struct device *dev,
+ struct fwnode_handle *child)
+{
+ struct acpi_device *adev = ACPI_COMPANION(dev);
+ struct fwnode_handle *fwnode = NULL;
+
+ if (dev->of_node)
+ fwnode = &dev->of_node->fwnode;
+ else if (adev)
+ fwnode = acpi_fwnode_handle(adev);
+
+ return fwnode_get_next_child_node(fwnode, child);
+}
EXPORT_SYMBOL_GPL(device_get_next_child_node);
/**
- * device_get_named_child_node - Return first matching named child node handle
- * @dev: Device to find the named child node for.
+ * fwnode_get_named_child_node - Return first matching named child node handle
+ * @fwnode: Firmware node to find the named child node for.
* @childname: String to match child node name against.
*/
-struct fwnode_handle *device_get_named_child_node(struct device *dev,
+struct fwnode_handle *fwnode_get_named_child_node(struct fwnode_handle *fwnode,
const char *childname)
{
struct fwnode_handle *child;
/*
- * Find first matching named child node of this device.
+ * Find first matching named child node of this fwnode.
* For ACPI this will be a data only sub-node.
*/
- device_for_each_child_node(dev, child) {
+ fwnode_for_each_child_node(fwnode, child) {
if (is_of_node(child)) {
if (!of_node_cmp(to_of_node(child)->name, childname))
return child;
return NULL;
}
+EXPORT_SYMBOL_GPL(fwnode_get_named_child_node);
+
+/**
+ * device_get_named_child_node - Return first matching named child node handle
+ * @dev: Device to find the named child node for.
+ * @childname: String to match child node name against.
+ */
+struct fwnode_handle *device_get_named_child_node(struct device *dev,
+ const char *childname)
+{
+ return fwnode_get_named_child_node(dev_fwnode(dev), childname);
+}
EXPORT_SYMBOL_GPL(device_get_named_child_node);
/**
+ * fwnode_handle_get - Obtain a reference to a device node
+ * @fwnode: Pointer to the device node to obtain the reference to.
+ */
+void fwnode_handle_get(struct fwnode_handle *fwnode)
+{
+ if (is_of_node(fwnode))
+ of_node_get(to_of_node(fwnode));
+}
+EXPORT_SYMBOL_GPL(fwnode_handle_get);
+
+/**
* fwnode_handle_put - Drop reference to a device node
* @fwnode: Pointer to the device node to drop the reference to.
*
return device_get_mac_addr(dev, "address", addr, alen);
}
EXPORT_SYMBOL(device_get_mac_address);
+
+/**
+ * device_graph_get_next_endpoint - Get next endpoint firmware node
+ * @fwnode: Pointer to the parent firmware node
+ * @prev: Previous endpoint node or %NULL to get the first
+ *
+ * Returns an endpoint firmware node pointer or %NULL if no more endpoints
+ * are available.
+ */
+struct fwnode_handle *
+fwnode_graph_get_next_endpoint(struct fwnode_handle *fwnode,
+ struct fwnode_handle *prev)
+{
+ struct fwnode_handle *endpoint = NULL;
+
+ if (is_of_node(fwnode)) {
+ struct device_node *node;
+
+ node = of_graph_get_next_endpoint(to_of_node(fwnode),
+ to_of_node(prev));
+
+ if (node)
+ endpoint = &node->fwnode;
+ } else if (is_acpi_node(fwnode)) {
+ endpoint = acpi_graph_get_next_endpoint(fwnode, prev);
+ if (IS_ERR(endpoint))
+ endpoint = NULL;
+ }
+
+ return endpoint;
+
+}
+EXPORT_SYMBOL_GPL(fwnode_graph_get_next_endpoint);
+
+/**
+ * fwnode_graph_get_remote_port_parent - Return fwnode of a remote device
+ * @fwnode: Endpoint firmware node pointing to the remote endpoint
+ *
+ * Extracts firmware node of a remote device the @fwnode points to.
+ */
+struct fwnode_handle *
+fwnode_graph_get_remote_port_parent(struct fwnode_handle *fwnode)
+{
+ struct fwnode_handle *parent = NULL;
+
+ if (is_of_node(fwnode)) {
+ struct device_node *node;
+
+ node = of_graph_get_remote_port_parent(to_of_node(fwnode));
+ if (node)
+ parent = &node->fwnode;
+ } else if (is_acpi_node(fwnode)) {
+ int ret;
+
+ ret = acpi_graph_get_remote_endpoint(fwnode, &parent, NULL,
+ NULL);
+ if (ret)
+ return NULL;
+ }
+
+ return parent;
+}
+EXPORT_SYMBOL_GPL(fwnode_graph_get_remote_port_parent);
+
+/**
+ * fwnode_graph_get_remote_port - Return fwnode of a remote port
+ * @fwnode: Endpoint firmware node pointing to the remote endpoint
+ *
+ * Extracts firmware node of a remote port the @fwnode points to.
+ */
+struct fwnode_handle *fwnode_graph_get_remote_port(struct fwnode_handle *fwnode)
+{
+ struct fwnode_handle *port = NULL;
+
+ if (is_of_node(fwnode)) {
+ struct device_node *node;
+
+ node = of_graph_get_remote_port(to_of_node(fwnode));
+ if (node)
+ port = &node->fwnode;
+ } else if (is_acpi_node(fwnode)) {
+ int ret;
+
+ ret = acpi_graph_get_remote_endpoint(fwnode, NULL, &port, NULL);
+ if (ret)
+ return NULL;
+ }
+
+ return port;
+}
+EXPORT_SYMBOL_GPL(fwnode_graph_get_remote_port);
+
+/**
+ * fwnode_graph_get_remote_endpoint - Return fwnode of a remote endpoint
+ * @fwnode: Endpoint firmware node pointing to the remote endpoint
+ *
+ * Extracts firmware node of a remote endpoint the @fwnode points to.
+ */
+struct fwnode_handle *
+fwnode_graph_get_remote_endpoint(struct fwnode_handle *fwnode)
+{
+ struct fwnode_handle *endpoint = NULL;
+
+ if (is_of_node(fwnode)) {
+ struct device_node *node;
+
+ node = of_parse_phandle(to_of_node(fwnode), "remote-endpoint",
+ 0);
+ if (node)
+ endpoint = &node->fwnode;
+ } else if (is_acpi_node(fwnode)) {
+ int ret;
+
+ ret = acpi_graph_get_remote_endpoint(fwnode, NULL, NULL,
+ &endpoint);
+ if (ret)
+ return NULL;
+ }
+
+ return endpoint;
+}
+EXPORT_SYMBOL_GPL(fwnode_graph_get_remote_endpoint);
+
+/**
+ * fwnode_graph_parse_endpoint - parse common endpoint node properties
+ * @fwnode: pointer to endpoint fwnode_handle
+ * @endpoint: pointer to the fwnode endpoint data structure
+ *
+ * Parse @fwnode representing a graph endpoint node and store the
+ * information in @endpoint. The caller must hold a reference to
+ * @fwnode.
+ */
+int fwnode_graph_parse_endpoint(struct fwnode_handle *fwnode,
+ struct fwnode_endpoint *endpoint)
+{
+ struct fwnode_handle *port_fwnode = fwnode_get_parent(fwnode);
+
+ memset(endpoint, 0, sizeof(*endpoint));
+
+ endpoint->local_fwnode = fwnode;
+
+ if (is_acpi_node(port_fwnode)) {
+ fwnode_property_read_u32(port_fwnode, "port", &endpoint->port);
+ fwnode_property_read_u32(fwnode, "endpoint", &endpoint->id);
+ } else {
+ fwnode_property_read_u32(port_fwnode, "reg", &endpoint->port);
+ fwnode_property_read_u32(fwnode, "reg", &endpoint->id);
+ }
+
+ fwnode_handle_put(port_fwnode);
+
+ return 0;
+}
+EXPORT_SYMBOL(fwnode_graph_parse_endpoint);
Use device /dev/skd$N amd /dev/skd$Np$M.
-config BLK_DEV_OSD
- tristate "OSD object-as-blkdev support"
- depends on SCSI_OSD_ULD
- ---help---
- Saying Y or M here will allow the exporting of a single SCSI
- OSD (object-based storage) object as a Linux block device.
-
- For example, if you create a 2G object on an OSD device,
- you can then use this module to present that 2G object as
- a Linux block device.
-
- To compile this driver as a module, choose M here: the
- module will be called osdblk.
-
- If unsure, say N.
-
config BLK_DEV_SX8
tristate "Promise SATA SX8 support"
depends on PCI
This driver provides Support for ATA over Ethernet block
devices like the Coraid EtherDrive (R) Storage Blade.
-config MG_DISK
- tristate "mGine mflash, gflash support"
- depends on ARM && GPIOLIB
- help
- mGine mFlash(gFlash) block device driver
-
-config MG_DISK_RES
- int "Size of reserved area before MBR"
- depends on MG_DISK
- default 0
- help
- Define size of reserved area that usually used for boot. Unit is KB.
- All of the block device operation will be taken this value as start
- offset
- Examples:
- 1024 => 1 MB
-
config SUNVDC
tristate "Sun Virtual Disk Client support"
depends on SUN_LDOMS
Enable support for SCSI passthrough (e.g. the SG_IO ioctl) on
virtio-blk devices. This is only supported for the legacy
virtio protocol and not enabled by default by any hypervisor.
- Your probably want to virtio-scsi instead.
-
-config BLK_DEV_HD
- bool "Very old hard disk (MFM/RLL/IDE) driver"
- depends on HAVE_IDE
- depends on !ARM || ARCH_RPC || BROKEN
- help
- This is a very old hard disk driver that lacks the enhanced
- functionality of the newer ones.
-
- It is required for systems with ancient MFM/RLL/ESDI drives.
-
- If unsure, say N.
+ You probably want to use virtio-scsi instead.
config BLK_DEV_RBD
tristate "Rados block device (RBD)"
obj-$(CONFIG_BLK_DEV_DAC960) += DAC960.o
obj-$(CONFIG_XILINX_SYSACE) += xsysace.o
obj-$(CONFIG_CDROM_PKTCDVD) += pktcdvd.o
-obj-$(CONFIG_MG_DISK) += mg_disk.o
obj-$(CONFIG_SUNVDC) += sunvdc.o
obj-$(CONFIG_BLK_DEV_SKD) += skd.o
-obj-$(CONFIG_BLK_DEV_OSD) += osdblk.o
obj-$(CONFIG_BLK_DEV_UMEM) += umem.o
obj-$(CONFIG_BLK_DEV_NBD) += nbd.o
obj-$(CONFIG_VIRTIO_BLK) += virtio_blk.o
obj-$(CONFIG_BLK_DEV_SX8) += sx8.o
-obj-$(CONFIG_BLK_DEV_HD) += hd.o
obj-$(CONFIG_XEN_BLKDEV_FRONTEND) += xen-blkfront.o
obj-$(CONFIG_XEN_BLKDEV_BACKEND) += xen-blkback/
if (!fd_request)
return;
- fd_request->errors++;
- if (fd_request->errors >= MAX_ERRORS) {
+ fd_request->error_count++;
+ if (fd_request->error_count >= MAX_ERRORS) {
printk(KERN_ERR "fd%d: too many errors.\n", SelectedDrive );
fd_end_request_cur(-EIO);
}
- else if (fd_request->errors == RECALIBRATE_ERRORS) {
+ else if (fd_request->error_count == RECALIBRATE_ERRORS) {
printk(KERN_WARNING "fd%d: recalibrating\n", SelectedDrive );
if (SelectedDrive != -1)
SUD.track = -1;
ReqData = ReqBuffer + 512 * ReqCnt;
if (UseTrackbuffer)
- read_track = (ReqCmd == READ && fd_request->errors == 0);
+ read_track = (ReqCmd == READ && fd_request->error_count == 0);
else
read_track = 0;
fdc_queue = 0;
if (q) {
rq = blk_fetch_request(q);
- if (rq)
+ if (rq) {
+ rq->error_count = 0;
break;
+ }
}
} while (fdc_queue != old_pos);
return page;
}
-static void brd_free_page(struct brd_device *brd, sector_t sector)
-{
- struct page *page;
- pgoff_t idx;
-
- spin_lock(&brd->brd_lock);
- idx = sector >> PAGE_SECTORS_SHIFT;
- page = radix_tree_delete(&brd->brd_pages, idx);
- spin_unlock(&brd->brd_lock);
- if (page)
- __free_page(page);
-}
-
-static void brd_zero_page(struct brd_device *brd, sector_t sector)
-{
- struct page *page;
-
- page = brd_lookup_page(brd, sector);
- if (page)
- clear_highpage(page);
-}
-
/*
* Free all backing store pages and radix tree. This must only be called when
* there are no other users of the device.
return 0;
}
-static void discard_from_brd(struct brd_device *brd,
- sector_t sector, size_t n)
-{
- while (n >= PAGE_SIZE) {
- /*
- * Don't want to actually discard pages here because
- * re-allocating the pages can result in writeback
- * deadlocks under heavy load.
- */
- if (0)
- brd_free_page(brd, sector);
- else
- brd_zero_page(brd, sector);
- sector += PAGE_SIZE >> SECTOR_SHIFT;
- n -= PAGE_SIZE;
- }
-}
-
/*
* Copy n bytes from src to the brd starting at sector. Does not sleep.
*/
if (bio_end_sector(bio) > get_capacity(bdev->bd_disk))
goto io_error;
- if (unlikely(bio_op(bio) == REQ_OP_DISCARD)) {
- if (sector & ((PAGE_SIZE >> SECTOR_SHIFT) - 1) ||
- bio->bi_iter.bi_size & ~PAGE_MASK)
- goto io_error;
- discard_from_brd(brd, sector, bio->bi_iter.bi_size);
- goto out;
- }
-
bio_for_each_segment(bvec, bio, iter) {
unsigned int len = bvec.bv_len;
int err;
sector += len >> SECTOR_SHIFT;
}
-out:
bio_endio(bio);
return BLK_QC_T_NONE;
io_error:
* is harmless)
*/
blk_queue_physical_block_size(brd->brd_queue, PAGE_SIZE);
-
- brd->brd_queue->limits.discard_granularity = PAGE_SIZE;
- blk_queue_max_discard_sectors(brd->brd_queue, UINT_MAX);
- brd->brd_queue->limits.discard_zeroes_data = 1;
- queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, brd->brd_queue);
#ifdef CONFIG_BLK_DEV_RAM_DAX
queue_flag_set_unlocked(QUEUE_FLAG_DAX, brd->brd_queue);
#endif
/* set the residual count for pc requests */
if (blk_rq_is_passthrough(rq))
scsi_req(rq)->resid_len = c->err_info->ResidualCnt;
-
- blk_end_request_all(rq, (rq->errors == 0) ? 0 : -EIO);
+ blk_end_request_all(rq, scsi_req(rq)->result ? -EIO : 0);
spin_lock_irqsave(&h->lock, flags);
cmd_free(h, c);
{
int retry_cmd = 0;
struct request *rq = cmd->rq;
+ struct scsi_request *sreq = scsi_req(rq);
- rq->errors = 0;
+ sreq->result = 0;
if (timeout)
- rq->errors = make_status_bytes(0, 0, 0, DRIVER_TIMEOUT);
+ sreq->result = make_status_bytes(0, 0, 0, DRIVER_TIMEOUT);
if (cmd->err_info->CommandStatus == 0) /* no error has occurred */
goto after_error_processing;
switch (cmd->err_info->CommandStatus) {
case CMD_TARGET_STATUS:
- rq->errors = evaluate_target_status(h, cmd, &retry_cmd);
+ sreq->result = evaluate_target_status(h, cmd, &retry_cmd);
break;
case CMD_DATA_UNDERRUN:
if (!blk_rq_is_passthrough(cmd->rq)) {
case CMD_INVALID:
dev_warn(&h->pdev->dev, "cciss: cmd %p is "
"reported invalid\n", cmd);
- rq->errors = make_status_bytes(SAM_STAT_GOOD,
+ sreq->result = make_status_bytes(SAM_STAT_GOOD,
cmd->err_info->CommandStatus, DRIVER_OK,
blk_rq_is_passthrough(cmd->rq) ?
DID_PASSTHROUGH : DID_ERROR);
case CMD_PROTOCOL_ERR:
dev_warn(&h->pdev->dev, "cciss: cmd %p has "
"protocol error\n", cmd);
- rq->errors = make_status_bytes(SAM_STAT_GOOD,
+ sreq->result = make_status_bytes(SAM_STAT_GOOD,
cmd->err_info->CommandStatus, DRIVER_OK,
blk_rq_is_passthrough(cmd->rq) ?
DID_PASSTHROUGH : DID_ERROR);
case CMD_HARDWARE_ERR:
dev_warn(&h->pdev->dev, "cciss: cmd %p had "
" hardware error\n", cmd);
- rq->errors = make_status_bytes(SAM_STAT_GOOD,
+ sreq->result = make_status_bytes(SAM_STAT_GOOD,
cmd->err_info->CommandStatus, DRIVER_OK,
blk_rq_is_passthrough(cmd->rq) ?
DID_PASSTHROUGH : DID_ERROR);
case CMD_CONNECTION_LOST:
dev_warn(&h->pdev->dev, "cciss: cmd %p had "
"connection lost\n", cmd);
- rq->errors = make_status_bytes(SAM_STAT_GOOD,
+ sreq->result = make_status_bytes(SAM_STAT_GOOD,
cmd->err_info->CommandStatus, DRIVER_OK,
blk_rq_is_passthrough(cmd->rq) ?
DID_PASSTHROUGH : DID_ERROR);
case CMD_ABORTED:
dev_warn(&h->pdev->dev, "cciss: cmd %p was "
"aborted\n", cmd);
- rq->errors = make_status_bytes(SAM_STAT_GOOD,
+ sreq->result = make_status_bytes(SAM_STAT_GOOD,
cmd->err_info->CommandStatus, DRIVER_OK,
blk_rq_is_passthrough(cmd->rq) ?
DID_PASSTHROUGH : DID_ABORT);
case CMD_ABORT_FAILED:
dev_warn(&h->pdev->dev, "cciss: cmd %p reports "
"abort failed\n", cmd);
- rq->errors = make_status_bytes(SAM_STAT_GOOD,
+ sreq->result = make_status_bytes(SAM_STAT_GOOD,
cmd->err_info->CommandStatus, DRIVER_OK,
blk_rq_is_passthrough(cmd->rq) ?
DID_PASSTHROUGH : DID_ERROR);
} else
dev_warn(&h->pdev->dev,
"%p retried too many times\n", cmd);
- rq->errors = make_status_bytes(SAM_STAT_GOOD,
+ sreq->result = make_status_bytes(SAM_STAT_GOOD,
cmd->err_info->CommandStatus, DRIVER_OK,
blk_rq_is_passthrough(cmd->rq) ?
DID_PASSTHROUGH : DID_ABORT);
break;
case CMD_TIMEOUT:
dev_warn(&h->pdev->dev, "cmd %p timedout\n", cmd);
- rq->errors = make_status_bytes(SAM_STAT_GOOD,
+ sreq->result = make_status_bytes(SAM_STAT_GOOD,
cmd->err_info->CommandStatus, DRIVER_OK,
blk_rq_is_passthrough(cmd->rq) ?
DID_PASSTHROUGH : DID_ERROR);
break;
case CMD_UNABORTABLE:
dev_warn(&h->pdev->dev, "cmd %p unabortable\n", cmd);
- rq->errors = make_status_bytes(SAM_STAT_GOOD,
+ sreq->result = make_status_bytes(SAM_STAT_GOOD,
cmd->err_info->CommandStatus, DRIVER_OK,
blk_rq_is_passthrough(cmd->rq) ?
DID_PASSTHROUGH : DID_ERROR);
dev_warn(&h->pdev->dev, "cmd %p returned "
"unknown status %x\n", cmd,
cmd->err_info->CommandStatus);
- rq->errors = make_status_bytes(SAM_STAT_GOOD,
+ sreq->result = make_status_bytes(SAM_STAT_GOOD,
cmd->err_info->CommandStatus, DRIVER_OK,
blk_rq_is_passthrough(cmd->rq) ?
DID_PASSTHROUGH : DID_ERROR);
if (dma_mapping_error(&h->pdev->dev, temp64.val)) {
dev_warn(&h->pdev->dev,
"%s: error mapping page for DMA\n", __func__);
- creq->errors = make_status_bytes(SAM_STAT_GOOD,
- 0, DRIVER_OK,
- DID_SOFT_ERROR);
+ scsi_req(creq)->result =
+ make_status_bytes(SAM_STAT_GOOD, 0, DRIVER_OK,
+ DID_SOFT_ERROR);
cmd_free(h, c);
return;
}
if (cciss_map_sg_chain_block(h, c, h->cmd_sg_list[c->cmdindex],
(seg - (h->max_cmd_sgentries - 1)) *
sizeof(SGDescriptor_struct))) {
- creq->errors = make_status_bytes(SAM_STAT_GOOD,
- 0, DRIVER_OK,
- DID_SOFT_ERROR);
+ scsi_req(creq)->result =
+ make_status_bytes(SAM_STAT_GOOD, 0, DRIVER_OK,
+ DID_SOFT_ERROR);
cmd_free(h, c);
return;
}
seq_print_rq_state_bit(m, f & EE_CALL_AL_COMPLETE_IO, &sep, "in-AL");
seq_print_rq_state_bit(m, f & EE_SEND_WRITE_ACK, &sep, "C");
seq_print_rq_state_bit(m, f & EE_MAY_SET_IN_SYNC, &sep, "set-in-sync");
-
- if (f & EE_IS_TRIM)
- __seq_print_rq_state_bit(m, f & EE_IS_TRIM_USE_ZEROOUT, &sep, "zero-out", "trim");
seq_print_rq_state_bit(m, f & EE_WRITE_SAME, &sep, "write-same");
seq_putc(m, '\n');
}
/* is this a TRIM aka REQ_DISCARD? */
__EE_IS_TRIM,
- /* our lower level cannot handle trim,
- * and we want to fall back to zeroout instead */
- __EE_IS_TRIM_USE_ZEROOUT,
/* In case a barrier failed,
* we need to resubmit without the barrier flag. */
#define EE_CALL_AL_COMPLETE_IO (1<<__EE_CALL_AL_COMPLETE_IO)
#define EE_MAY_SET_IN_SYNC (1<<__EE_MAY_SET_IN_SYNC)
#define EE_IS_TRIM (1<<__EE_IS_TRIM)
-#define EE_IS_TRIM_USE_ZEROOUT (1<<__EE_IS_TRIM_USE_ZEROOUT)
#define EE_RESUBMITTED (1<<__EE_RESUBMITTED)
#define EE_WAS_ERROR (1<<__EE_WAS_ERROR)
#define EE_HAS_DIGEST (1<<__EE_HAS_DIGEST)
extern void drbd_endio_write_sec_final(struct drbd_peer_request *peer_req);
/* drbd_receiver.c */
-extern int drbd_issue_discard_or_zero_out(struct drbd_device *device,
- sector_t start, unsigned int nr_sectors, bool discard);
extern int drbd_receiver(struct drbd_thread *thi);
extern int drbd_ack_receiver(struct drbd_thread *thi);
extern void drbd_send_ping_wf(struct work_struct *ws);
p->qlim->io_min = cpu_to_be32(queue_io_min(q));
p->qlim->io_opt = cpu_to_be32(queue_io_opt(q));
p->qlim->discard_enabled = blk_queue_discard(q);
- p->qlim->discard_zeroes_data = queue_discard_zeroes_data(q);
p->qlim->write_same_capable = !!q->limits.max_write_same_sectors;
} else {
q = device->rq_queue;
p->qlim->io_min = cpu_to_be32(queue_io_min(q));
p->qlim->io_opt = cpu_to_be32(queue_io_opt(q));
p->qlim->discard_enabled = 0;
- p->qlim->discard_zeroes_data = 0;
p->qlim->write_same_capable = 0;
}
}
(bio->bi_opf & REQ_FUA ? DP_FUA : 0) |
(bio->bi_opf & REQ_PREFLUSH ? DP_FLUSH : 0) |
(bio_op(bio) == REQ_OP_WRITE_SAME ? DP_WSAME : 0) |
- (bio_op(bio) == REQ_OP_DISCARD ? DP_DISCARD : 0);
+ (bio_op(bio) == REQ_OP_DISCARD ? DP_DISCARD : 0) |
+ (bio_op(bio) == REQ_OP_WRITE_ZEROES ? DP_DISCARD : 0);
else
return bio->bi_opf & REQ_SYNC ? DP_RW_SYNC : 0;
}
struct drbd_connection *connection = first_peer_device(device)->connection;
bool can_do = b ? blk_queue_discard(b) : true;
- if (can_do && b && !b->limits.discard_zeroes_data && !discard_zeroes_if_aligned) {
- can_do = false;
- drbd_info(device, "discard_zeroes_data=0 and discard_zeroes_if_aligned=no: disabling discards\n");
- }
if (can_do && connection->cstate >= C_CONNECTED && !(connection->agreed_features & DRBD_FF_TRIM)) {
can_do = false;
drbd_info(connection, "peer DRBD too old, does not support TRIM: disabling discards\n");
blk_queue_discard_granularity(q, 512);
q->limits.max_discard_sectors = drbd_max_discard_sectors(connection);
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
+ q->limits.max_write_zeroes_sectors = drbd_max_discard_sectors(connection);
} else {
queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q);
blk_queue_discard_granularity(q, 0);
q->limits.max_discard_sectors = 0;
+ q->limits.max_write_zeroes_sectors = 0;
}
}
if (disk_conf->al_extents > drbd_al_extents_max(nbc))
disk_conf->al_extents = drbd_al_extents_max(nbc);
- if (!blk_queue_discard(q)
- || (!q->limits.discard_zeroes_data && !disk_conf->discard_zeroes_if_aligned)) {
+ if (!blk_queue_discard(q)) {
if (disk_conf->rs_discard_granularity) {
disk_conf->rs_discard_granularity = 0; /* disable feature */
drbd_info(device, "rs_discard_granularity feature disabled\n");
drbd_info(resource, "Method to ensure write ordering: %s\n", write_ordering_str[resource->write_ordering]);
}
-/*
- * We *may* ignore the discard-zeroes-data setting, if so configured.
- *
- * Assumption is that it "discard_zeroes_data=0" is only because the backend
- * may ignore partial unaligned discards.
- *
- * LVM/DM thin as of at least
- * LVM version: 2.02.115(2)-RHEL7 (2015-01-28)
- * Library version: 1.02.93-RHEL7 (2015-01-28)
- * Driver version: 4.29.0
- * still behaves this way.
- *
- * For unaligned (wrt. alignment and granularity) or too small discards,
- * we zero-out the initial (and/or) trailing unaligned partial chunks,
- * but discard all the aligned full chunks.
- *
- * At least for LVM/DM thin, the result is effectively "discard_zeroes_data=1".
- */
-int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, unsigned int nr_sectors, bool discard)
-{
- struct block_device *bdev = device->ldev->backing_bdev;
- struct request_queue *q = bdev_get_queue(bdev);
- sector_t tmp, nr;
- unsigned int max_discard_sectors, granularity;
- int alignment;
- int err = 0;
-
- if (!discard)
- goto zero_out;
-
- /* Zero-sector (unknown) and one-sector granularities are the same. */
- granularity = max(q->limits.discard_granularity >> 9, 1U);
- alignment = (bdev_discard_alignment(bdev) >> 9) % granularity;
-
- max_discard_sectors = min(q->limits.max_discard_sectors, (1U << 22));
- max_discard_sectors -= max_discard_sectors % granularity;
- if (unlikely(!max_discard_sectors))
- goto zero_out;
-
- if (nr_sectors < granularity)
- goto zero_out;
-
- tmp = start;
- if (sector_div(tmp, granularity) != alignment) {
- if (nr_sectors < 2*granularity)
- goto zero_out;
- /* start + gran - (start + gran - align) % gran */
- tmp = start + granularity - alignment;
- tmp = start + granularity - sector_div(tmp, granularity);
-
- nr = tmp - start;
- err |= blkdev_issue_zeroout(bdev, start, nr, GFP_NOIO, 0);
- nr_sectors -= nr;
- start = tmp;
- }
- while (nr_sectors >= granularity) {
- nr = min_t(sector_t, nr_sectors, max_discard_sectors);
- err |= blkdev_issue_discard(bdev, start, nr, GFP_NOIO, 0);
- nr_sectors -= nr;
- start += nr;
- }
- zero_out:
- if (nr_sectors) {
- err |= blkdev_issue_zeroout(bdev, start, nr_sectors, GFP_NOIO, 0);
- }
- return err != 0;
-}
-
-static bool can_do_reliable_discards(struct drbd_device *device)
-{
- struct request_queue *q = bdev_get_queue(device->ldev->backing_bdev);
- struct disk_conf *dc;
- bool can_do;
-
- if (!blk_queue_discard(q))
- return false;
-
- if (q->limits.discard_zeroes_data)
- return true;
-
- rcu_read_lock();
- dc = rcu_dereference(device->ldev->disk_conf);
- can_do = dc->discard_zeroes_if_aligned;
- rcu_read_unlock();
- return can_do;
-}
-
static void drbd_issue_peer_discard(struct drbd_device *device, struct drbd_peer_request *peer_req)
{
- /* If the backend cannot discard, or does not guarantee
- * read-back zeroes in discarded ranges, we fall back to
- * zero-out. Unless configuration specifically requested
- * otherwise. */
- if (!can_do_reliable_discards(device))
- peer_req->flags |= EE_IS_TRIM_USE_ZEROOUT;
+ struct block_device *bdev = device->ldev->backing_bdev;
- if (drbd_issue_discard_or_zero_out(device, peer_req->i.sector,
- peer_req->i.size >> 9, !(peer_req->flags & EE_IS_TRIM_USE_ZEROOUT)))
+ if (blkdev_issue_zeroout(bdev, peer_req->i.sector, peer_req->i.size >> 9,
+ GFP_NOIO, 0))
peer_req->flags |= EE_WAS_ERROR;
+
drbd_endio_write_sec_final(peer_req);
}
static unsigned long wire_flags_to_bio_op(u32 dpf)
{
if (dpf & DP_DISCARD)
- return REQ_OP_DISCARD;
+ return REQ_OP_WRITE_ZEROES;
else
return REQ_OP_WRITE;
}
op_flags = wire_flags_to_bio_flags(dp_flags);
if (pi->cmd == P_TRIM) {
D_ASSERT(peer_device, peer_req->i.size > 0);
- D_ASSERT(peer_device, op == REQ_OP_DISCARD);
+ D_ASSERT(peer_device, op == REQ_OP_WRITE_ZEROES);
D_ASSERT(peer_device, peer_req->pages == NULL);
} else if (peer_req->pages == NULL) {
D_ASSERT(device, peer_req->i.size == 0);
if (get_ldev(device)) {
struct drbd_peer_request *peer_req;
- const int op = REQ_OP_DISCARD;
+ const int op = REQ_OP_WRITE_ZEROES;
peer_req = drbd_alloc_peer_req(peer_device, ID_SYNCER, sector,
size, 0, GFP_NOIO);
drbd_req_make_private_bio(req, bio_src);
req->rq_state = (bio_data_dir(bio_src) == WRITE ? RQ_WRITE : 0)
| (bio_op(bio_src) == REQ_OP_WRITE_SAME ? RQ_WSAME : 0)
+ | (bio_op(bio_src) == REQ_OP_WRITE_ZEROES ? RQ_UNMAP : 0)
| (bio_op(bio_src) == REQ_OP_DISCARD ? RQ_UNMAP : 0);
req->device = device;
req->master_bio = bio_src;
static void drbd_process_discard_req(struct drbd_request *req)
{
- int err = drbd_issue_discard_or_zero_out(req->device,
- req->i.sector, req->i.size >> 9, true);
+ struct block_device *bdev = req->device->ldev->backing_bdev;
- if (err)
+ if (blkdev_issue_zeroout(bdev, req->i.sector, req->i.size >> 9,
+ GFP_NOIO, 0))
req->private_bio->bi_error = -EIO;
bio_endio(req->private_bio);
}
if (get_ldev(device)) {
if (drbd_insert_fault(device, type))
bio_io_error(bio);
- else if (bio_op(bio) == REQ_OP_DISCARD)
+ else if (bio_op(bio) == REQ_OP_WRITE_ZEROES ||
+ bio_op(bio) == REQ_OP_DISCARD)
drbd_process_discard_req(req);
else
generic_make_request(bio);
_drbd_start_io_acct(device, req);
/* process discards always from our submitter thread */
- if (bio_op(bio) & REQ_OP_DISCARD)
+ if ((bio_op(bio) & REQ_OP_WRITE_ZEROES) ||
+ (bio_op(bio) & REQ_OP_DISCARD))
goto queue_for_submitter_thread;
if (rw == WRITE && req->private_bio && req->i.size
struct drbd_peer_request *peer_req = bio->bi_private;
struct drbd_device *device = peer_req->peer_device->device;
bool is_write = bio_data_dir(bio) == WRITE;
- bool is_discard = !!(bio_op(bio) == REQ_OP_DISCARD);
+ bool is_discard = bio_op(bio) == REQ_OP_WRITE_ZEROES ||
+ bio_op(bio) == REQ_OP_DISCARD;
if (bio->bi_error && __ratelimit(&drbd_ratelimit_state))
drbd_warn(device, "%s: error=%d s=%llus\n",
/* to avoid recursion in __req_mod */
if (unlikely(bio->bi_error)) {
switch (bio_op(bio)) {
+ case REQ_OP_WRITE_ZEROES:
case REQ_OP_DISCARD:
if (bio->bi_error == -EOPNOTSUPP)
what = DISCARD_COMPLETED_NOTSUPP;
fdc_queue = 0;
if (q) {
current_req = blk_fetch_request(q);
- if (current_req)
+ if (current_req) {
+ current_req->error_count = 0;
break;
+ }
}
} while (fdc_queue != old_pos);
_floppy = floppy_type + DP->autodetect[DRS->probed_format];
} else
probing = 0;
- errors = &(current_req->errors);
+ errors = &(current_req->error_count);
tmp = make_raw_rw_request();
if (tmp < 2) {
request_done(tmp);
disks[drive]->fops = &floppy_fops;
sprintf(disks[drive]->disk_name, "fd%d", drive);
- init_timer(&motor_off_timer[drive]);
- motor_off_timer[drive].data = drive;
- motor_off_timer[drive].function = motor_off_callback;
+ setup_timer(&motor_off_timer[drive], motor_off_callback, drive);
}
err = register_blkdev(FLOPPY_MAJOR, "fd");
+++ /dev/null
-/*
- * Copyright (C) 1991, 1992 Linus Torvalds
- *
- * This is the low-level hd interrupt support. It traverses the
- * request-list, using interrupts to jump between functions. As
- * all the functions are called within interrupts, we may not
- * sleep. Special care is recommended.
- *
- * modified by Drew Eckhardt to check nr of hd's from the CMOS.
- *
- * Thanks to Branko Lankester, lankeste@fwi.uva.nl, who found a bug
- * in the early extended-partition checks and added DM partitions
- *
- * IRQ-unmask, drive-id, multiple-mode, support for ">16 heads",
- * and general streamlining by Mark Lord.
- *
- * Removed 99% of above. Use Mark's ide driver for those options.
- * This is now a lightweight ST-506 driver. (Paul Gortmaker)
- *
- * Modified 1995 Russell King for ARM processor.
- *
- * Bugfix: max_sectors must be <= 255 or the wheels tend to come
- * off in a hurry once you queue things up - Paul G. 02/2001
- */
-
-/* Uncomment the following if you want verbose error reports. */
-/* #define VERBOSE_ERRORS */
-
-#include <linux/blkdev.h>
-#include <linux/errno.h>
-#include <linux/signal.h>
-#include <linux/interrupt.h>
-#include <linux/timer.h>
-#include <linux/fs.h>
-#include <linux/kernel.h>
-#include <linux/genhd.h>
-#include <linux/string.h>
-#include <linux/ioport.h>
-#include <linux/init.h>
-#include <linux/blkpg.h>
-#include <linux/ata.h>
-#include <linux/hdreg.h>
-
-#define HD_IRQ 14
-
-#define REALLY_SLOW_IO
-#include <asm/io.h>
-#include <linux/uaccess.h>
-
-#ifdef __arm__
-#undef HD_IRQ
-#endif
-#include <asm/irq.h>
-#ifdef __arm__
-#define HD_IRQ IRQ_HARDDISK
-#endif
-
-/* Hd controller regster ports */
-
-#define HD_DATA 0x1f0 /* _CTL when writing */
-#define HD_ERROR 0x1f1 /* see err-bits */
-#define HD_NSECTOR 0x1f2 /* nr of sectors to read/write */
-#define HD_SECTOR 0x1f3 /* starting sector */
-#define HD_LCYL 0x1f4 /* starting cylinder */
-#define HD_HCYL 0x1f5 /* high byte of starting cyl */
-#define HD_CURRENT 0x1f6 /* 101dhhhh , d=drive, hhhh=head */
-#define HD_STATUS 0x1f7 /* see status-bits */
-#define HD_FEATURE HD_ERROR /* same io address, read=error, write=feature */
-#define HD_PRECOMP HD_FEATURE /* obsolete use of this port - predates IDE */
-#define HD_COMMAND HD_STATUS /* same io address, read=status, write=cmd */
-
-#define HD_CMD 0x3f6 /* used for resets */
-#define HD_ALTSTATUS 0x3f6 /* same as HD_STATUS but doesn't clear irq */
-
-/* Bits of HD_STATUS */
-#define ERR_STAT 0x01
-#define INDEX_STAT 0x02
-#define ECC_STAT 0x04 /* Corrected error */
-#define DRQ_STAT 0x08
-#define SEEK_STAT 0x10
-#define SERVICE_STAT SEEK_STAT
-#define WRERR_STAT 0x20
-#define READY_STAT 0x40
-#define BUSY_STAT 0x80
-
-/* Bits for HD_ERROR */
-#define MARK_ERR 0x01 /* Bad address mark */
-#define TRK0_ERR 0x02 /* couldn't find track 0 */
-#define ABRT_ERR 0x04 /* Command aborted */
-#define MCR_ERR 0x08 /* media change request */
-#define ID_ERR 0x10 /* ID field not found */
-#define MC_ERR 0x20 /* media changed */
-#define ECC_ERR 0x40 /* Uncorrectable ECC error */
-#define BBD_ERR 0x80 /* pre-EIDE meaning: block marked bad */
-#define ICRC_ERR 0x80 /* new meaning: CRC error during transfer */
-
-static DEFINE_SPINLOCK(hd_lock);
-static struct request_queue *hd_queue;
-static struct request *hd_req;
-
-#define TIMEOUT_VALUE (6*HZ)
-#define HD_DELAY 0
-
-#define MAX_ERRORS 16 /* Max read/write errors/sector */
-#define RESET_FREQ 8 /* Reset controller every 8th retry */
-#define RECAL_FREQ 4 /* Recalibrate every 4th retry */
-#define MAX_HD 2
-
-#define STAT_OK (READY_STAT|SEEK_STAT)
-#define OK_STATUS(s) (((s)&(STAT_OK|(BUSY_STAT|WRERR_STAT|ERR_STAT)))==STAT_OK)
-
-static void recal_intr(void);
-static void bad_rw_intr(void);
-
-static int reset;
-static int hd_error;
-
-/*
- * This struct defines the HD's and their types.
- */
-struct hd_i_struct {
- unsigned int head, sect, cyl, wpcom, lzone, ctl;
- int unit;
- int recalibrate;
- int special_op;
-};
-
-#ifdef HD_TYPE
-static struct hd_i_struct hd_info[] = { HD_TYPE };
-static int NR_HD = ARRAY_SIZE(hd_info);
-#else
-static struct hd_i_struct hd_info[MAX_HD];
-static int NR_HD;
-#endif
-
-static struct gendisk *hd_gendisk[MAX_HD];
-
-static struct timer_list device_timer;
-
-#define TIMEOUT_VALUE (6*HZ)
-
-#define SET_TIMER \
- do { \
- mod_timer(&device_timer, jiffies + TIMEOUT_VALUE); \
- } while (0)
-
-static void (*do_hd)(void) = NULL;
-#define SET_HANDLER(x) \
-if ((do_hd = (x)) != NULL) \
- SET_TIMER; \
-else \
- del_timer(&device_timer);
-
-
-#if (HD_DELAY > 0)
-
-#include <linux/i8253.h>
-
-unsigned long last_req;
-
-unsigned long read_timer(void)
-{
- unsigned long t, flags;
- int i;
-
- raw_spin_lock_irqsave(&i8253_lock, flags);
- t = jiffies * 11932;
- outb_p(0, 0x43);
- i = inb_p(0x40);
- i |= inb(0x40) << 8;
- raw_spin_unlock_irqrestore(&i8253_lock, flags);
- return(t - i);
-}
-#endif
-
-static void __init hd_setup(char *str, int *ints)
-{
- int hdind = 0;
-
- if (ints[0] != 3)
- return;
- if (hd_info[0].head != 0)
- hdind = 1;
- hd_info[hdind].head = ints[2];
- hd_info[hdind].sect = ints[3];
- hd_info[hdind].cyl = ints[1];
- hd_info[hdind].wpcom = 0;
- hd_info[hdind].lzone = ints[1];
- hd_info[hdind].ctl = (ints[2] > 8 ? 8 : 0);
- NR_HD = hdind+1;
-}
-
-static bool hd_end_request(int err, unsigned int bytes)
-{
- if (__blk_end_request(hd_req, err, bytes))
- return true;
- hd_req = NULL;
- return false;
-}
-
-static bool hd_end_request_cur(int err)
-{
- return hd_end_request(err, blk_rq_cur_bytes(hd_req));
-}
-
-static void dump_status(const char *msg, unsigned int stat)
-{
- char *name = "hd?";
- if (hd_req)
- name = hd_req->rq_disk->disk_name;
-
-#ifdef VERBOSE_ERRORS
- printk("%s: %s: status=0x%02x { ", name, msg, stat & 0xff);
- if (stat & BUSY_STAT) printk("Busy ");
- if (stat & READY_STAT) printk("DriveReady ");
- if (stat & WRERR_STAT) printk("WriteFault ");
- if (stat & SEEK_STAT) printk("SeekComplete ");
- if (stat & DRQ_STAT) printk("DataRequest ");
- if (stat & ECC_STAT) printk("CorrectedError ");
- if (stat & INDEX_STAT) printk("Index ");
- if (stat & ERR_STAT) printk("Error ");
- printk("}\n");
- if ((stat & ERR_STAT) == 0) {
- hd_error = 0;
- } else {
- hd_error = inb(HD_ERROR);
- printk("%s: %s: error=0x%02x { ", name, msg, hd_error & 0xff);
- if (hd_error & BBD_ERR) printk("BadSector ");
- if (hd_error & ECC_ERR) printk("UncorrectableError ");
- if (hd_error & ID_ERR) printk("SectorIdNotFound ");
- if (hd_error & ABRT_ERR) printk("DriveStatusError ");
- if (hd_error & TRK0_ERR) printk("TrackZeroNotFound ");
- if (hd_error & MARK_ERR) printk("AddrMarkNotFound ");
- printk("}");
- if (hd_error & (BBD_ERR|ECC_ERR|ID_ERR|MARK_ERR)) {
- printk(", CHS=%d/%d/%d", (inb(HD_HCYL)<<8) + inb(HD_LCYL),
- inb(HD_CURRENT) & 0xf, inb(HD_SECTOR));
- if (hd_req)
- printk(", sector=%ld", blk_rq_pos(hd_req));
- }
- printk("\n");
- }
-#else
- printk("%s: %s: status=0x%02x.\n", name, msg, stat & 0xff);
- if ((stat & ERR_STAT) == 0) {
- hd_error = 0;
- } else {
- hd_error = inb(HD_ERROR);
- printk("%s: %s: error=0x%02x.\n", name, msg, hd_error & 0xff);
- }
-#endif
-}
-
-static void check_status(void)
-{
- int i = inb_p(HD_STATUS);
-
- if (!OK_STATUS(i)) {
- dump_status("check_status", i);
- bad_rw_intr();
- }
-}
-
-static int controller_busy(void)
-{
- int retries = 100000;
- unsigned char status;
-
- do {
- status = inb_p(HD_STATUS);
- } while ((status & BUSY_STAT) && --retries);
- return status;
-}
-
-static int status_ok(void)
-{
- unsigned char status = inb_p(HD_STATUS);
-
- if (status & BUSY_STAT)
- return 1; /* Ancient, but does it make sense??? */
- if (status & WRERR_STAT)
- return 0;
- if (!(status & READY_STAT))
- return 0;
- if (!(status & SEEK_STAT))
- return 0;
- return 1;
-}
-
-static int controller_ready(unsigned int drive, unsigned int head)
-{
- int retry = 100;
-
- do {
- if (controller_busy() & BUSY_STAT)
- return 0;
- outb_p(0xA0 | (drive<<4) | head, HD_CURRENT);
- if (status_ok())
- return 1;
- } while (--retry);
- return 0;
-}
-
-static void hd_out(struct hd_i_struct *disk,
- unsigned int nsect,
- unsigned int sect,
- unsigned int head,
- unsigned int cyl,
- unsigned int cmd,
- void (*intr_addr)(void))
-{
- unsigned short port;
-
-#if (HD_DELAY > 0)
- while (read_timer() - last_req < HD_DELAY)
- /* nothing */;
-#endif
- if (reset)
- return;
- if (!controller_ready(disk->unit, head)) {
- reset = 1;
- return;
- }
- SET_HANDLER(intr_addr);
- outb_p(disk->ctl, HD_CMD);
- port = HD_DATA;
- outb_p(disk->wpcom >> 2, ++port);
- outb_p(nsect, ++port);
- outb_p(sect, ++port);
- outb_p(cyl, ++port);
- outb_p(cyl >> 8, ++port);
- outb_p(0xA0 | (disk->unit << 4) | head, ++port);
- outb_p(cmd, ++port);
-}
-
-static void hd_request (void);
-
-static int drive_busy(void)
-{
- unsigned int i;
- unsigned char c;
-
- for (i = 0; i < 500000 ; i++) {
- c = inb_p(HD_STATUS);
- if ((c & (BUSY_STAT | READY_STAT | SEEK_STAT)) == STAT_OK)
- return 0;
- }
- dump_status("reset timed out", c);
- return 1;
-}
-
-static void reset_controller(void)
-{
- int i;
-
- outb_p(4, HD_CMD);
- for (i = 0; i < 1000; i++) barrier();
- outb_p(hd_info[0].ctl & 0x0f, HD_CMD);
- for (i = 0; i < 1000; i++) barrier();
- if (drive_busy())
- printk("hd: controller still busy\n");
- else if ((hd_error = inb(HD_ERROR)) != 1)
- printk("hd: controller reset failed: %02x\n", hd_error);
-}
-
-static void reset_hd(void)
-{
- static int i;
-
-repeat:
- if (reset) {
- reset = 0;
- i = -1;
- reset_controller();
- } else {
- check_status();
- if (reset)
- goto repeat;
- }
- if (++i < NR_HD) {
- struct hd_i_struct *disk = &hd_info[i];
- disk->special_op = disk->recalibrate = 1;
- hd_out(disk, disk->sect, disk->sect, disk->head-1,
- disk->cyl, ATA_CMD_INIT_DEV_PARAMS, &reset_hd);
- if (reset)
- goto repeat;
- } else
- hd_request();
-}
-
-/*
- * Ok, don't know what to do with the unexpected interrupts: on some machines
- * doing a reset and a retry seems to result in an eternal loop. Right now I
- * ignore it, and just set the timeout.
- *
- * On laptops (and "green" PCs), an unexpected interrupt occurs whenever the
- * drive enters "idle", "standby", or "sleep" mode, so if the status looks
- * "good", we just ignore the interrupt completely.
- */
-static void unexpected_hd_interrupt(void)
-{
- unsigned int stat = inb_p(HD_STATUS);
-
- if (stat & (BUSY_STAT|DRQ_STAT|ECC_STAT|ERR_STAT)) {
- dump_status("unexpected interrupt", stat);
- SET_TIMER;
- }
-}
-
-/*
- * bad_rw_intr() now tries to be a bit smarter and does things
- * according to the error returned by the controller.
- * -Mika Liljeberg (liljeber@cs.Helsinki.FI)
- */
-static void bad_rw_intr(void)
-{
- struct request *req = hd_req;
-
- if (req != NULL) {
- struct hd_i_struct *disk = req->rq_disk->private_data;
- if (++req->errors >= MAX_ERRORS || (hd_error & BBD_ERR)) {
- hd_end_request_cur(-EIO);
- disk->special_op = disk->recalibrate = 1;
- } else if (req->errors % RESET_FREQ == 0)
- reset = 1;
- else if ((hd_error & TRK0_ERR) || req->errors % RECAL_FREQ == 0)
- disk->special_op = disk->recalibrate = 1;
- /* Otherwise just retry */
- }
-}
-
-static inline int wait_DRQ(void)
-{
- int retries;
- int stat;
-
- for (retries = 0; retries < 100000; retries++) {
- stat = inb_p(HD_STATUS);
- if (stat & DRQ_STAT)
- return 0;
- }
- dump_status("wait_DRQ", stat);
- return -1;
-}
-
-static void read_intr(void)
-{
- struct request *req;
- int i, retries = 100000;
-
- do {
- i = (unsigned) inb_p(HD_STATUS);
- if (i & BUSY_STAT)
- continue;
- if (!OK_STATUS(i))
- break;
- if (i & DRQ_STAT)
- goto ok_to_read;
- } while (--retries > 0);
- dump_status("read_intr", i);
- bad_rw_intr();
- hd_request();
- return;
-
-ok_to_read:
- req = hd_req;
- insw(HD_DATA, bio_data(req->bio), 256);
-#ifdef DEBUG
- printk("%s: read: sector %ld, remaining = %u, buffer=%p\n",
- req->rq_disk->disk_name, blk_rq_pos(req) + 1,
- blk_rq_sectors(req) - 1, bio_data(req->bio)+512);
-#endif
- if (hd_end_request(0, 512)) {
- SET_HANDLER(&read_intr);
- return;
- }
-
- (void) inb_p(HD_STATUS);
-#if (HD_DELAY > 0)
- last_req = read_timer();
-#endif
- hd_request();
-}
-
-static void write_intr(void)
-{
- struct request *req = hd_req;
- int i;
- int retries = 100000;
-
- do {
- i = (unsigned) inb_p(HD_STATUS);
- if (i & BUSY_STAT)
- continue;
- if (!OK_STATUS(i))
- break;
- if ((blk_rq_sectors(req) <= 1) || (i & DRQ_STAT))
- goto ok_to_write;
- } while (--retries > 0);
- dump_status("write_intr", i);
- bad_rw_intr();
- hd_request();
- return;
-
-ok_to_write:
- if (hd_end_request(0, 512)) {
- SET_HANDLER(&write_intr);
- outsw(HD_DATA, bio_data(req->bio), 256);
- return;
- }
-
-#if (HD_DELAY > 0)
- last_req = read_timer();
-#endif
- hd_request();
-}
-
-static void recal_intr(void)
-{
- check_status();
-#if (HD_DELAY > 0)
- last_req = read_timer();
-#endif
- hd_request();
-}
-
-/*
- * This is another of the error-routines I don't know what to do with. The
- * best idea seems to just set reset, and start all over again.
- */
-static void hd_times_out(unsigned long dummy)
-{
- char *name;
-
- do_hd = NULL;
-
- if (!hd_req)
- return;
-
- spin_lock_irq(hd_queue->queue_lock);
- reset = 1;
- name = hd_req->rq_disk->disk_name;
- printk("%s: timeout\n", name);
- if (++hd_req->errors >= MAX_ERRORS) {
-#ifdef DEBUG
- printk("%s: too many errors\n", name);
-#endif
- hd_end_request_cur(-EIO);
- }
- hd_request();
- spin_unlock_irq(hd_queue->queue_lock);
-}
-
-static int do_special_op(struct hd_i_struct *disk, struct request *req)
-{
- if (disk->recalibrate) {
- disk->recalibrate = 0;
- hd_out(disk, disk->sect, 0, 0, 0, ATA_CMD_RESTORE, &recal_intr);
- return reset;
- }
- if (disk->head > 16) {
- printk("%s: cannot handle device with more than 16 heads - giving up\n", req->rq_disk->disk_name);
- hd_end_request_cur(-EIO);
- }
- disk->special_op = 0;
- return 1;
-}
-
-/*
- * The driver enables interrupts as much as possible. In order to do this,
- * (a) the device-interrupt is disabled before entering hd_request(),
- * and (b) the timeout-interrupt is disabled before the sti().
- *
- * Interrupts are still masked (by default) whenever we are exchanging
- * data/cmds with a drive, because some drives seem to have very poor
- * tolerance for latency during I/O. The IDE driver has support to unmask
- * interrupts for non-broken hardware, so use that driver if required.
- */
-static void hd_request(void)
-{
- unsigned int block, nsect, sec, track, head, cyl;
- struct hd_i_struct *disk;
- struct request *req;
-
- if (do_hd)
- return;
-repeat:
- del_timer(&device_timer);
-
- if (!hd_req) {
- hd_req = blk_fetch_request(hd_queue);
- if (!hd_req) {
- do_hd = NULL;
- return;
- }
- }
- req = hd_req;
-
- if (reset) {
- reset_hd();
- return;
- }
- disk = req->rq_disk->private_data;
- block = blk_rq_pos(req);
- nsect = blk_rq_sectors(req);
- if (block >= get_capacity(req->rq_disk) ||
- ((block+nsect) > get_capacity(req->rq_disk))) {
- printk("%s: bad access: block=%d, count=%d\n",
- req->rq_disk->disk_name, block, nsect);
- hd_end_request_cur(-EIO);
- goto repeat;
- }
-
- if (disk->special_op) {
- if (do_special_op(disk, req))
- goto repeat;
- return;
- }
- sec = block % disk->sect + 1;
- track = block / disk->sect;
- head = track % disk->head;
- cyl = track / disk->head;
-#ifdef DEBUG
- printk("%s: %sing: CHS=%d/%d/%d, sectors=%d, buffer=%p\n",
- req->rq_disk->disk_name,
- req_data_dir(req) == READ ? "read" : "writ",
- cyl, head, sec, nsect, bio_data(req->bio));
-#endif
-
- switch (req_op(req)) {
- case REQ_OP_READ:
- hd_out(disk, nsect, sec, head, cyl, ATA_CMD_PIO_READ,
- &read_intr);
- if (reset)
- goto repeat;
- break;
- case REQ_OP_WRITE:
- hd_out(disk, nsect, sec, head, cyl, ATA_CMD_PIO_WRITE,
- &write_intr);
- if (reset)
- goto repeat;
- if (wait_DRQ()) {
- bad_rw_intr();
- goto repeat;
- }
- outsw(HD_DATA, bio_data(req->bio), 256);
- break;
- default:
- printk("unknown hd-command\n");
- hd_end_request_cur(-EIO);
- break;
- }
-}
-
-static void do_hd_request(struct request_queue *q)
-{
- hd_request();
-}
-
-static int hd_getgeo(struct block_device *bdev, struct hd_geometry *geo)
-{
- struct hd_i_struct *disk = bdev->bd_disk->private_data;
-
- geo->heads = disk->head;
- geo->sectors = disk->sect;
- geo->cylinders = disk->cyl;
- return 0;
-}
-
-/*
- * Releasing a block device means we sync() it, so that it can safely
- * be forgotten about...
- */
-
-static irqreturn_t hd_interrupt(int irq, void *dev_id)
-{
- void (*handler)(void) = do_hd;
-
- spin_lock(hd_queue->queue_lock);
-
- do_hd = NULL;
- del_timer(&device_timer);
- if (!handler)
- handler = unexpected_hd_interrupt;
- handler();
-
- spin_unlock(hd_queue->queue_lock);
-
- return IRQ_HANDLED;
-}
-
-static const struct block_device_operations hd_fops = {
- .getgeo = hd_getgeo,
-};
-
-static int __init hd_init(void)
-{
- int drive;
-
- if (register_blkdev(HD_MAJOR, "hd"))
- return -1;
-
- hd_queue = blk_init_queue(do_hd_request, &hd_lock);
- if (!hd_queue) {
- unregister_blkdev(HD_MAJOR, "hd");
- return -ENOMEM;
- }
-
- blk_queue_max_hw_sectors(hd_queue, 255);
- init_timer(&device_timer);
- device_timer.function = hd_times_out;
- blk_queue_logical_block_size(hd_queue, 512);
-
- if (!NR_HD) {
- /*
- * We don't know anything about the drive. This means
- * that you *MUST* specify the drive parameters to the
- * kernel yourself.
- *
- * If we were on an i386, we used to read this info from
- * the BIOS or CMOS. This doesn't work all that well,
- * since this assumes that this is a primary or secondary
- * drive, and if we're using this legacy driver, it's
- * probably an auxiliary controller added to recover
- * legacy data off an ST-506 drive. Either way, it's
- * definitely safest to have the user explicitly specify
- * the information.
- */
- printk("hd: no drives specified - use hd=cyl,head,sectors"
- " on kernel command line\n");
- goto out;
- }
-
- for (drive = 0 ; drive < NR_HD ; drive++) {
- struct gendisk *disk = alloc_disk(64);
- struct hd_i_struct *p = &hd_info[drive];
- if (!disk)
- goto Enomem;
- disk->major = HD_MAJOR;
- disk->first_minor = drive << 6;
- disk->fops = &hd_fops;
- sprintf(disk->disk_name, "hd%c", 'a'+drive);
- disk->private_data = p;
- set_capacity(disk, p->head * p->sect * p->cyl);
- disk->queue = hd_queue;
- p->unit = drive;
- hd_gendisk[drive] = disk;
- printk("%s: %luMB, CHS=%d/%d/%d\n",
- disk->disk_name, (unsigned long)get_capacity(disk)/2048,
- p->cyl, p->head, p->sect);
- }
-
- if (request_irq(HD_IRQ, hd_interrupt, 0, "hd", NULL)) {
- printk("hd: unable to get IRQ%d for the hard disk driver\n",
- HD_IRQ);
- goto out1;
- }
- if (!request_region(HD_DATA, 8, "hd")) {
- printk(KERN_WARNING "hd: port 0x%x busy\n", HD_DATA);
- goto out2;
- }
- if (!request_region(HD_CMD, 1, "hd(cmd)")) {
- printk(KERN_WARNING "hd: port 0x%x busy\n", HD_CMD);
- goto out3;
- }
-
- /* Let them fly */
- for (drive = 0; drive < NR_HD; drive++)
- add_disk(hd_gendisk[drive]);
-
- return 0;
-
-out3:
- release_region(HD_DATA, 8);
-out2:
- free_irq(HD_IRQ, NULL);
-out1:
- for (drive = 0; drive < NR_HD; drive++)
- put_disk(hd_gendisk[drive]);
- NR_HD = 0;
-out:
- del_timer(&device_timer);
- unregister_blkdev(HD_MAJOR, "hd");
- blk_cleanup_queue(hd_queue);
- return -1;
-Enomem:
- while (drive--)
- put_disk(hd_gendisk[drive]);
- goto out;
-}
-
-static int __init parse_hd_setup(char *line)
-{
- int ints[6];
-
- (void) get_options(line, ARRAY_SIZE(ints), ints);
- hd_setup(NULL, ints);
-
- return 1;
-}
-__setup("hd=", parse_hd_setup);
-
-late_initcall(hd_init);
return ret;
}
-static inline void handle_partial_read(struct loop_cmd *cmd, long bytes)
+static void lo_complete_rq(struct request *rq)
{
- if (bytes < 0 || op_is_write(req_op(cmd->rq)))
- return;
+ struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
- if (unlikely(bytes < blk_rq_bytes(cmd->rq))) {
+ if (unlikely(req_op(cmd->rq) == REQ_OP_READ && cmd->use_aio &&
+ cmd->ret >= 0 && cmd->ret < blk_rq_bytes(cmd->rq))) {
struct bio *bio = cmd->rq->bio;
- bio_advance(bio, bytes);
+ bio_advance(bio, cmd->ret);
zero_fill_bio(bio);
}
+
+ blk_mq_end_request(rq, cmd->ret < 0 ? -EIO : 0);
}
static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2)
{
struct loop_cmd *cmd = container_of(iocb, struct loop_cmd, iocb);
- struct request *rq = cmd->rq;
-
- handle_partial_read(cmd, ret);
- if (ret > 0)
- ret = 0;
- else if (ret < 0)
- ret = -EIO;
-
- blk_mq_complete_request(rq, ret);
+ cmd->ret = ret;
+ blk_mq_complete_request(cmd->rq);
}
static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
case REQ_OP_FLUSH:
return lo_req_flush(lo, rq);
case REQ_OP_DISCARD:
+ case REQ_OP_WRITE_ZEROES:
return lo_discard(lo, rq, pos);
case REQ_OP_WRITE:
if (lo->transfer)
q->limits.discard_granularity = 0;
q->limits.discard_alignment = 0;
blk_queue_max_discard_sectors(q, 0);
- q->limits.discard_zeroes_data = 0;
+ blk_queue_max_write_zeroes_sectors(q, 0);
queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q);
return;
}
q->limits.discard_granularity = inode->i_sb->s_blocksize;
q->limits.discard_alignment = 0;
blk_queue_max_discard_sectors(q, UINT_MAX >> 9);
- q->limits.discard_zeroes_data = 1;
+ blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> 9);
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
}
switch (req_op(cmd->rq)) {
case REQ_OP_FLUSH:
case REQ_OP_DISCARD:
+ case REQ_OP_WRITE_ZEROES:
cmd->use_aio = false;
break;
default:
ret = do_req_filebacked(lo, cmd->rq);
failed:
/* complete non-aio request */
- if (!cmd->use_aio || ret)
- blk_mq_complete_request(cmd->rq, ret ? -EIO : 0);
+ if (!cmd->use_aio || ret) {
+ cmd->ret = ret ? -EIO : 0;
+ blk_mq_complete_request(cmd->rq);
+ }
}
static void loop_queue_work(struct kthread_work *work)
return 0;
}
-static struct blk_mq_ops loop_mq_ops = {
+static const struct blk_mq_ops loop_mq_ops = {
.queue_rq = loop_queue_rq,
.init_request = loop_init_request,
+ .complete = lo_complete_rq,
};
static int loop_add(struct loop_device **l, int i)
struct request *rq;
struct list_head list;
bool use_aio; /* use AIO interface to handle I/O */
+ long ret;
struct kiocb iocb;
};
+++ /dev/null
-/*
- * drivers/block/mg_disk.c
- *
- * Support for the mGine m[g]flash IO mode.
- * Based on legacy hd.c
- *
- * (c) 2008 mGine Co.,LTD
- * (c) 2008 unsik Kim <donari75@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/fs.h>
-#include <linux/blkdev.h>
-#include <linux/hdreg.h>
-#include <linux/ata.h>
-#include <linux/interrupt.h>
-#include <linux/delay.h>
-#include <linux/platform_device.h>
-#include <linux/gpio.h>
-#include <linux/mg_disk.h>
-#include <linux/slab.h>
-
-#define MG_RES_SEC (CONFIG_MG_DISK_RES << 1)
-
-/* name for block device */
-#define MG_DISK_NAME "mgd"
-
-#define MG_DISK_MAJ 0
-#define MG_DISK_MAX_PART 16
-#define MG_SECTOR_SIZE 512
-#define MG_MAX_SECTS 256
-
-/* Register offsets */
-#define MG_BUFF_OFFSET 0x8000
-#define MG_REG_OFFSET 0xC000
-#define MG_REG_FEATURE (MG_REG_OFFSET + 2) /* write case */
-#define MG_REG_ERROR (MG_REG_OFFSET + 2) /* read case */
-#define MG_REG_SECT_CNT (MG_REG_OFFSET + 4)
-#define MG_REG_SECT_NUM (MG_REG_OFFSET + 6)
-#define MG_REG_CYL_LOW (MG_REG_OFFSET + 8)
-#define MG_REG_CYL_HIGH (MG_REG_OFFSET + 0xA)
-#define MG_REG_DRV_HEAD (MG_REG_OFFSET + 0xC)
-#define MG_REG_COMMAND (MG_REG_OFFSET + 0xE) /* write case */
-#define MG_REG_STATUS (MG_REG_OFFSET + 0xE) /* read case */
-#define MG_REG_DRV_CTRL (MG_REG_OFFSET + 0x10)
-#define MG_REG_BURST_CTRL (MG_REG_OFFSET + 0x12)
-
-/* handy status */
-#define MG_STAT_READY (ATA_DRDY | ATA_DSC)
-#define MG_READY_OK(s) (((s) & (MG_STAT_READY | (ATA_BUSY | ATA_DF | \
- ATA_ERR))) == MG_STAT_READY)
-
-/* error code for others */
-#define MG_ERR_NONE 0
-#define MG_ERR_TIMEOUT 0x100
-#define MG_ERR_INIT_STAT 0x101
-#define MG_ERR_TRANSLATION 0x102
-#define MG_ERR_CTRL_RST 0x103
-#define MG_ERR_INV_STAT 0x104
-#define MG_ERR_RSTOUT 0x105
-
-#define MG_MAX_ERRORS 6 /* Max read/write errors */
-
-/* command */
-#define MG_CMD_RD 0x20
-#define MG_CMD_WR 0x30
-#define MG_CMD_SLEEP 0x99
-#define MG_CMD_WAKEUP 0xC3
-#define MG_CMD_ID 0xEC
-#define MG_CMD_WR_CONF 0x3C
-#define MG_CMD_RD_CONF 0x40
-
-/* operation mode */
-#define MG_OP_CASCADE (1 << 0)
-#define MG_OP_CASCADE_SYNC_RD (1 << 1)
-#define MG_OP_CASCADE_SYNC_WR (1 << 2)
-#define MG_OP_INTERLEAVE (1 << 3)
-
-/* synchronous */
-#define MG_BURST_LAT_4 (3 << 4)
-#define MG_BURST_LAT_5 (4 << 4)
-#define MG_BURST_LAT_6 (5 << 4)
-#define MG_BURST_LAT_7 (6 << 4)
-#define MG_BURST_LAT_8 (7 << 4)
-#define MG_BURST_LEN_4 (1 << 1)
-#define MG_BURST_LEN_8 (2 << 1)
-#define MG_BURST_LEN_16 (3 << 1)
-#define MG_BURST_LEN_32 (4 << 1)
-#define MG_BURST_LEN_CONT (0 << 1)
-
-/* timeout value (unit: ms) */
-#define MG_TMAX_CONF_TO_CMD 1
-#define MG_TMAX_WAIT_RD_DRQ 10
-#define MG_TMAX_WAIT_WR_DRQ 500
-#define MG_TMAX_RST_TO_BUSY 10
-#define MG_TMAX_HDRST_TO_RDY 500
-#define MG_TMAX_SWRST_TO_RDY 500
-#define MG_TMAX_RSTOUT 3000
-
-#define MG_DEV_MASK (MG_BOOT_DEV | MG_STORAGE_DEV | MG_STORAGE_DEV_SKIP_RST)
-
-/* main structure for mflash driver */
-struct mg_host {
- struct device *dev;
-
- struct request_queue *breq;
- struct request *req;
- spinlock_t lock;
- struct gendisk *gd;
-
- struct timer_list timer;
- void (*mg_do_intr) (struct mg_host *);
-
- u16 id[ATA_ID_WORDS];
-
- u16 cyls;
- u16 heads;
- u16 sectors;
- u32 n_sectors;
- u32 nres_sectors;
-
- void __iomem *dev_base;
- unsigned int irq;
- unsigned int rst;
- unsigned int rstout;
-
- u32 major;
- u32 error;
-};
-
-/*
- * Debugging macro and defines
- */
-#undef DO_MG_DEBUG
-#ifdef DO_MG_DEBUG
-# define MG_DBG(fmt, args...) \
- printk(KERN_DEBUG "%s:%d "fmt, __func__, __LINE__, ##args)
-#else /* CONFIG_MG_DEBUG */
-# define MG_DBG(fmt, args...) do { } while (0)
-#endif /* CONFIG_MG_DEBUG */
-
-static void mg_request(struct request_queue *);
-
-static bool mg_end_request(struct mg_host *host, int err, unsigned int nr_bytes)
-{
- if (__blk_end_request(host->req, err, nr_bytes))
- return true;
-
- host->req = NULL;
- return false;
-}
-
-static bool mg_end_request_cur(struct mg_host *host, int err)
-{
- return mg_end_request(host, err, blk_rq_cur_bytes(host->req));
-}
-
-static void mg_dump_status(const char *msg, unsigned int stat,
- struct mg_host *host)
-{
- char *name = MG_DISK_NAME;
-
- if (host->req)
- name = host->req->rq_disk->disk_name;
-
- printk(KERN_ERR "%s: %s: status=0x%02x { ", name, msg, stat & 0xff);
- if (stat & ATA_BUSY)
- printk("Busy ");
- if (stat & ATA_DRDY)
- printk("DriveReady ");
- if (stat & ATA_DF)
- printk("WriteFault ");
- if (stat & ATA_DSC)
- printk("SeekComplete ");
- if (stat & ATA_DRQ)
- printk("DataRequest ");
- if (stat & ATA_CORR)
- printk("CorrectedError ");
- if (stat & ATA_ERR)
- printk("Error ");
- printk("}\n");
- if ((stat & ATA_ERR) == 0) {
- host->error = 0;
- } else {
- host->error = inb((unsigned long)host->dev_base + MG_REG_ERROR);
- printk(KERN_ERR "%s: %s: error=0x%02x { ", name, msg,
- host->error & 0xff);
- if (host->error & ATA_BBK)
- printk("BadSector ");
- if (host->error & ATA_UNC)
- printk("UncorrectableError ");
- if (host->error & ATA_IDNF)
- printk("SectorIdNotFound ");
- if (host->error & ATA_ABORTED)
- printk("DriveStatusError ");
- if (host->error & ATA_AMNF)
- printk("AddrMarkNotFound ");
- printk("}");
- if (host->error & (ATA_BBK | ATA_UNC | ATA_IDNF | ATA_AMNF)) {
- if (host->req)
- printk(", sector=%u",
- (unsigned int)blk_rq_pos(host->req));
- }
- printk("\n");
- }
-}
-
-static unsigned int mg_wait(struct mg_host *host, u32 expect, u32 msec)
-{
- u8 status;
- unsigned long expire, cur_jiffies;
- struct mg_drv_data *prv_data = host->dev->platform_data;
-
- host->error = MG_ERR_NONE;
- expire = jiffies + msecs_to_jiffies(msec);
-
- /* These 2 times dummy status read prevents reading invalid
- * status. A very little time (3 times of mflash operating clk)
- * is required for busy bit is set. Use dummy read instead of
- * busy wait, because mflash's PLL is machine dependent.
- */
- if (prv_data->use_polling) {
- status = inb((unsigned long)host->dev_base + MG_REG_STATUS);
- status = inb((unsigned long)host->dev_base + MG_REG_STATUS);
- }
-
- status = inb((unsigned long)host->dev_base + MG_REG_STATUS);
-
- do {
- cur_jiffies = jiffies;
- if (status & ATA_BUSY) {
- if (expect == ATA_BUSY)
- break;
- } else {
- /* Check the error condition! */
- if (status & ATA_ERR) {
- mg_dump_status("mg_wait", status, host);
- break;
- }
-
- if (expect == MG_STAT_READY)
- if (MG_READY_OK(status))
- break;
-
- if (expect == ATA_DRQ)
- if (status & ATA_DRQ)
- break;
- }
- if (!msec) {
- mg_dump_status("not ready", status, host);
- return MG_ERR_INV_STAT;
- }
-
- status = inb((unsigned long)host->dev_base + MG_REG_STATUS);
- } while (time_before(cur_jiffies, expire));
-
- if (time_after_eq(cur_jiffies, expire) && msec)
- host->error = MG_ERR_TIMEOUT;
-
- return host->error;
-}
-
-static unsigned int mg_wait_rstout(u32 rstout, u32 msec)
-{
- unsigned long expire;
-
- expire = jiffies + msecs_to_jiffies(msec);
- while (time_before(jiffies, expire)) {
- if (gpio_get_value(rstout) == 1)
- return MG_ERR_NONE;
- msleep(10);
- }
-
- return MG_ERR_RSTOUT;
-}
-
-static void mg_unexpected_intr(struct mg_host *host)
-{
- u32 status = inb((unsigned long)host->dev_base + MG_REG_STATUS);
-
- mg_dump_status("mg_unexpected_intr", status, host);
-}
-
-static irqreturn_t mg_irq(int irq, void *dev_id)
-{
- struct mg_host *host = dev_id;
- void (*handler)(struct mg_host *) = host->mg_do_intr;
-
- spin_lock(&host->lock);
-
- host->mg_do_intr = NULL;
- del_timer(&host->timer);
- if (!handler)
- handler = mg_unexpected_intr;
- handler(host);
-
- spin_unlock(&host->lock);
-
- return IRQ_HANDLED;
-}
-
-/* local copy of ata_id_string() */
-static void mg_id_string(const u16 *id, unsigned char *s,
- unsigned int ofs, unsigned int len)
-{
- unsigned int c;
-
- BUG_ON(len & 1);
-
- while (len > 0) {
- c = id[ofs] >> 8;
- *s = c;
- s++;
-
- c = id[ofs] & 0xff;
- *s = c;
- s++;
-
- ofs++;
- len -= 2;
- }
-}
-
-/* local copy of ata_id_c_string() */
-static void mg_id_c_string(const u16 *id, unsigned char *s,
- unsigned int ofs, unsigned int len)
-{
- unsigned char *p;
-
- mg_id_string(id, s, ofs, len - 1);
-
- p = s + strnlen(s, len - 1);
- while (p > s && p[-1] == ' ')
- p--;
- *p = '\0';
-}
-
-static int mg_get_disk_id(struct mg_host *host)
-{
- u32 i;
- s32 err;
- const u16 *id = host->id;
- struct mg_drv_data *prv_data = host->dev->platform_data;
- char fwrev[ATA_ID_FW_REV_LEN + 1];
- char model[ATA_ID_PROD_LEN + 1];
- char serial[ATA_ID_SERNO_LEN + 1];
-
- if (!prv_data->use_polling)
- outb(ATA_NIEN, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-
- outb(MG_CMD_ID, (unsigned long)host->dev_base + MG_REG_COMMAND);
- err = mg_wait(host, ATA_DRQ, MG_TMAX_WAIT_RD_DRQ);
- if (err)
- return err;
-
- for (i = 0; i < (MG_SECTOR_SIZE >> 1); i++)
- host->id[i] = le16_to_cpu(inw((unsigned long)host->dev_base +
- MG_BUFF_OFFSET + i * 2));
-
- outb(MG_CMD_RD_CONF, (unsigned long)host->dev_base + MG_REG_COMMAND);
- err = mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD);
- if (err)
- return err;
-
- if ((id[ATA_ID_FIELD_VALID] & 1) == 0)
- return MG_ERR_TRANSLATION;
-
- host->n_sectors = ata_id_u32(id, ATA_ID_LBA_CAPACITY);
- host->cyls = id[ATA_ID_CYLS];
- host->heads = id[ATA_ID_HEADS];
- host->sectors = id[ATA_ID_SECTORS];
-
- if (MG_RES_SEC && host->heads && host->sectors) {
- /* modify cyls, n_sectors */
- host->cyls = (host->n_sectors - MG_RES_SEC) /
- host->heads / host->sectors;
- host->nres_sectors = host->n_sectors - host->cyls *
- host->heads * host->sectors;
- host->n_sectors -= host->nres_sectors;
- }
-
- mg_id_c_string(id, fwrev, ATA_ID_FW_REV, sizeof(fwrev));
- mg_id_c_string(id, model, ATA_ID_PROD, sizeof(model));
- mg_id_c_string(id, serial, ATA_ID_SERNO, sizeof(serial));
- printk(KERN_INFO "mg_disk: model: %s\n", model);
- printk(KERN_INFO "mg_disk: firm: %.8s\n", fwrev);
- printk(KERN_INFO "mg_disk: serial: %s\n", serial);
- printk(KERN_INFO "mg_disk: %d + reserved %d sectors\n",
- host->n_sectors, host->nres_sectors);
-
- if (!prv_data->use_polling)
- outb(0, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-
- return err;
-}
-
-
-static int mg_disk_init(struct mg_host *host)
-{
- struct mg_drv_data *prv_data = host->dev->platform_data;
- s32 err;
- u8 init_status;
-
- /* hdd rst low */
- gpio_set_value(host->rst, 0);
- err = mg_wait(host, ATA_BUSY, MG_TMAX_RST_TO_BUSY);
- if (err)
- return err;
-
- /* hdd rst high */
- gpio_set_value(host->rst, 1);
- err = mg_wait(host, MG_STAT_READY, MG_TMAX_HDRST_TO_RDY);
- if (err)
- return err;
-
- /* soft reset on */
- outb(ATA_SRST | (prv_data->use_polling ? ATA_NIEN : 0),
- (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
- err = mg_wait(host, ATA_BUSY, MG_TMAX_RST_TO_BUSY);
- if (err)
- return err;
-
- /* soft reset off */
- outb(prv_data->use_polling ? ATA_NIEN : 0,
- (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
- err = mg_wait(host, MG_STAT_READY, MG_TMAX_SWRST_TO_RDY);
- if (err)
- return err;
-
- init_status = inb((unsigned long)host->dev_base + MG_REG_STATUS) & 0xf;
-
- if (init_status == 0xf)
- return MG_ERR_INIT_STAT;
-
- return err;
-}
-
-static void mg_bad_rw_intr(struct mg_host *host)
-{
- if (host->req)
- if (++host->req->errors >= MG_MAX_ERRORS ||
- host->error == MG_ERR_TIMEOUT)
- mg_end_request_cur(host, -EIO);
-}
-
-static unsigned int mg_out(struct mg_host *host,
- unsigned int sect_num,
- unsigned int sect_cnt,
- unsigned int cmd,
- void (*intr_addr)(struct mg_host *))
-{
- struct mg_drv_data *prv_data = host->dev->platform_data;
-
- if (mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD))
- return host->error;
-
- if (!prv_data->use_polling) {
- host->mg_do_intr = intr_addr;
- mod_timer(&host->timer, jiffies + 3 * HZ);
- }
- if (MG_RES_SEC)
- sect_num += MG_RES_SEC;
- outb((u8)sect_cnt, (unsigned long)host->dev_base + MG_REG_SECT_CNT);
- outb((u8)sect_num, (unsigned long)host->dev_base + MG_REG_SECT_NUM);
- outb((u8)(sect_num >> 8), (unsigned long)host->dev_base +
- MG_REG_CYL_LOW);
- outb((u8)(sect_num >> 16), (unsigned long)host->dev_base +
- MG_REG_CYL_HIGH);
- outb((u8)((sect_num >> 24) | ATA_LBA | ATA_DEVICE_OBS),
- (unsigned long)host->dev_base + MG_REG_DRV_HEAD);
- outb(cmd, (unsigned long)host->dev_base + MG_REG_COMMAND);
- return MG_ERR_NONE;
-}
-
-static void mg_read_one(struct mg_host *host, struct request *req)
-{
- u16 *buff = (u16 *)bio_data(req->bio);
- u32 i;
-
- for (i = 0; i < MG_SECTOR_SIZE >> 1; i++)
- *buff++ = inw((unsigned long)host->dev_base + MG_BUFF_OFFSET +
- (i << 1));
-}
-
-static void mg_read(struct request *req)
-{
- struct mg_host *host = req->rq_disk->private_data;
-
- if (mg_out(host, blk_rq_pos(req), blk_rq_sectors(req),
- MG_CMD_RD, NULL) != MG_ERR_NONE)
- mg_bad_rw_intr(host);
-
- MG_DBG("requested %d sects (from %ld), buffer=0x%p\n",
- blk_rq_sectors(req), blk_rq_pos(req), bio_data(req->bio));
-
- do {
- if (mg_wait(host, ATA_DRQ,
- MG_TMAX_WAIT_RD_DRQ) != MG_ERR_NONE) {
- mg_bad_rw_intr(host);
- return;
- }
-
- mg_read_one(host, req);
-
- outb(MG_CMD_RD_CONF, (unsigned long)host->dev_base +
- MG_REG_COMMAND);
- } while (mg_end_request(host, 0, MG_SECTOR_SIZE));
-}
-
-static void mg_write_one(struct mg_host *host, struct request *req)
-{
- u16 *buff = (u16 *)bio_data(req->bio);
- u32 i;
-
- for (i = 0; i < MG_SECTOR_SIZE >> 1; i++)
- outw(*buff++, (unsigned long)host->dev_base + MG_BUFF_OFFSET +
- (i << 1));
-}
-
-static void mg_write(struct request *req)
-{
- struct mg_host *host = req->rq_disk->private_data;
- unsigned int rem = blk_rq_sectors(req);
-
- if (mg_out(host, blk_rq_pos(req), rem,
- MG_CMD_WR, NULL) != MG_ERR_NONE) {
- mg_bad_rw_intr(host);
- return;
- }
-
- MG_DBG("requested %d sects (from %ld), buffer=0x%p\n",
- rem, blk_rq_pos(req), bio_data(req->bio));
-
- if (mg_wait(host, ATA_DRQ,
- MG_TMAX_WAIT_WR_DRQ) != MG_ERR_NONE) {
- mg_bad_rw_intr(host);
- return;
- }
-
- do {
- mg_write_one(host, req);
-
- outb(MG_CMD_WR_CONF, (unsigned long)host->dev_base +
- MG_REG_COMMAND);
-
- rem--;
- if (rem > 1 && mg_wait(host, ATA_DRQ,
- MG_TMAX_WAIT_WR_DRQ) != MG_ERR_NONE) {
- mg_bad_rw_intr(host);
- return;
- } else if (mg_wait(host, MG_STAT_READY,
- MG_TMAX_WAIT_WR_DRQ) != MG_ERR_NONE) {
- mg_bad_rw_intr(host);
- return;
- }
- } while (mg_end_request(host, 0, MG_SECTOR_SIZE));
-}
-
-static void mg_read_intr(struct mg_host *host)
-{
- struct request *req = host->req;
- u32 i;
-
- /* check status */
- do {
- i = inb((unsigned long)host->dev_base + MG_REG_STATUS);
- if (i & ATA_BUSY)
- break;
- if (!MG_READY_OK(i))
- break;
- if (i & ATA_DRQ)
- goto ok_to_read;
- } while (0);
- mg_dump_status("mg_read_intr", i, host);
- mg_bad_rw_intr(host);
- mg_request(host->breq);
- return;
-
-ok_to_read:
- mg_read_one(host, req);
-
- MG_DBG("sector %ld, remaining=%ld, buffer=0x%p\n",
- blk_rq_pos(req), blk_rq_sectors(req) - 1, bio_data(req->bio));
-
- /* send read confirm */
- outb(MG_CMD_RD_CONF, (unsigned long)host->dev_base + MG_REG_COMMAND);
-
- if (mg_end_request(host, 0, MG_SECTOR_SIZE)) {
- /* set handler if read remains */
- host->mg_do_intr = mg_read_intr;
- mod_timer(&host->timer, jiffies + 3 * HZ);
- } else /* goto next request */
- mg_request(host->breq);
-}
-
-static void mg_write_intr(struct mg_host *host)
-{
- struct request *req = host->req;
- u32 i;
- bool rem;
-
- /* check status */
- do {
- i = inb((unsigned long)host->dev_base + MG_REG_STATUS);
- if (i & ATA_BUSY)
- break;
- if (!MG_READY_OK(i))
- break;
- if ((blk_rq_sectors(req) <= 1) || (i & ATA_DRQ))
- goto ok_to_write;
- } while (0);
- mg_dump_status("mg_write_intr", i, host);
- mg_bad_rw_intr(host);
- mg_request(host->breq);
- return;
-
-ok_to_write:
- if ((rem = mg_end_request(host, 0, MG_SECTOR_SIZE))) {
- /* write 1 sector and set handler if remains */
- mg_write_one(host, req);
- MG_DBG("sector %ld, remaining=%ld, buffer=0x%p\n",
- blk_rq_pos(req), blk_rq_sectors(req), bio_data(req->bio));
- host->mg_do_intr = mg_write_intr;
- mod_timer(&host->timer, jiffies + 3 * HZ);
- }
-
- /* send write confirm */
- outb(MG_CMD_WR_CONF, (unsigned long)host->dev_base + MG_REG_COMMAND);
-
- if (!rem)
- mg_request(host->breq);
-}
-
-static void mg_times_out(unsigned long data)
-{
- struct mg_host *host = (struct mg_host *)data;
- char *name;
-
- spin_lock_irq(&host->lock);
-
- if (!host->req)
- goto out_unlock;
-
- host->mg_do_intr = NULL;
-
- name = host->req->rq_disk->disk_name;
- printk(KERN_DEBUG "%s: timeout\n", name);
-
- host->error = MG_ERR_TIMEOUT;
- mg_bad_rw_intr(host);
-
-out_unlock:
- mg_request(host->breq);
- spin_unlock_irq(&host->lock);
-}
-
-static void mg_request_poll(struct request_queue *q)
-{
- struct mg_host *host = q->queuedata;
-
- while (1) {
- if (!host->req) {
- host->req = blk_fetch_request(q);
- if (!host->req)
- break;
- }
-
- switch (req_op(host->req)) {
- case REQ_OP_READ:
- mg_read(host->req);
- break;
- case REQ_OP_WRITE:
- mg_write(host->req);
- break;
- default:
- mg_end_request_cur(host, -EIO);
- break;
- }
- }
-}
-
-static unsigned int mg_issue_req(struct request *req,
- struct mg_host *host,
- unsigned int sect_num,
- unsigned int sect_cnt)
-{
- switch (req_op(host->req)) {
- case REQ_OP_READ:
- if (mg_out(host, sect_num, sect_cnt, MG_CMD_RD, &mg_read_intr)
- != MG_ERR_NONE) {
- mg_bad_rw_intr(host);
- return host->error;
- }
- break;
- case REQ_OP_WRITE:
- /* TODO : handler */
- outb(ATA_NIEN, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
- if (mg_out(host, sect_num, sect_cnt, MG_CMD_WR, &mg_write_intr)
- != MG_ERR_NONE) {
- mg_bad_rw_intr(host);
- return host->error;
- }
- del_timer(&host->timer);
- mg_wait(host, ATA_DRQ, MG_TMAX_WAIT_WR_DRQ);
- outb(0, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
- if (host->error) {
- mg_bad_rw_intr(host);
- return host->error;
- }
- mg_write_one(host, req);
- mod_timer(&host->timer, jiffies + 3 * HZ);
- outb(MG_CMD_WR_CONF, (unsigned long)host->dev_base +
- MG_REG_COMMAND);
- break;
- default:
- mg_end_request_cur(host, -EIO);
- break;
- }
- return MG_ERR_NONE;
-}
-
-/* This function also called from IRQ context */
-static void mg_request(struct request_queue *q)
-{
- struct mg_host *host = q->queuedata;
- struct request *req;
- u32 sect_num, sect_cnt;
-
- while (1) {
- if (!host->req) {
- host->req = blk_fetch_request(q);
- if (!host->req)
- break;
- }
- req = host->req;
-
- /* check unwanted request call */
- if (host->mg_do_intr)
- return;
-
- del_timer(&host->timer);
-
- sect_num = blk_rq_pos(req);
- /* deal whole segments */
- sect_cnt = blk_rq_sectors(req);
-
- /* sanity check */
- if (sect_num >= get_capacity(req->rq_disk) ||
- ((sect_num + sect_cnt) >
- get_capacity(req->rq_disk))) {
- printk(KERN_WARNING
- "%s: bad access: sector=%d, count=%d\n",
- req->rq_disk->disk_name,
- sect_num, sect_cnt);
- mg_end_request_cur(host, -EIO);
- continue;
- }
-
- if (!mg_issue_req(req, host, sect_num, sect_cnt))
- return;
- }
-}
-
-static int mg_getgeo(struct block_device *bdev, struct hd_geometry *geo)
-{
- struct mg_host *host = bdev->bd_disk->private_data;
-
- geo->cylinders = (unsigned short)host->cyls;
- geo->heads = (unsigned char)host->heads;
- geo->sectors = (unsigned char)host->sectors;
- return 0;
-}
-
-static const struct block_device_operations mg_disk_ops = {
- .getgeo = mg_getgeo
-};
-
-#ifdef CONFIG_PM_SLEEP
-static int mg_suspend(struct device *dev)
-{
- struct mg_drv_data *prv_data = dev->platform_data;
- struct mg_host *host = prv_data->host;
-
- if (mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD))
- return -EIO;
-
- if (!prv_data->use_polling)
- outb(ATA_NIEN, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-
- outb(MG_CMD_SLEEP, (unsigned long)host->dev_base + MG_REG_COMMAND);
- /* wait until mflash deep sleep */
- msleep(1);
-
- if (mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD)) {
- if (!prv_data->use_polling)
- outb(0, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
- return -EIO;
- }
-
- return 0;
-}
-
-static int mg_resume(struct device *dev)
-{
- struct mg_drv_data *prv_data = dev->platform_data;
- struct mg_host *host = prv_data->host;
-
- if (mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD))
- return -EIO;
-
- outb(MG_CMD_WAKEUP, (unsigned long)host->dev_base + MG_REG_COMMAND);
- /* wait until mflash wakeup */
- msleep(1);
-
- if (mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD))
- return -EIO;
-
- if (!prv_data->use_polling)
- outb(0, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-
- return 0;
-}
-#endif
-
-static SIMPLE_DEV_PM_OPS(mg_pm, mg_suspend, mg_resume);
-
-static int mg_probe(struct platform_device *plat_dev)
-{
- struct mg_host *host;
- struct resource *rsc;
- struct mg_drv_data *prv_data = plat_dev->dev.platform_data;
- int err = 0;
-
- if (!prv_data) {
- printk(KERN_ERR "%s:%d fail (no driver_data)\n",
- __func__, __LINE__);
- err = -EINVAL;
- goto probe_err;
- }
-
- /* alloc mg_host */
- host = kzalloc(sizeof(struct mg_host), GFP_KERNEL);
- if (!host) {
- printk(KERN_ERR "%s:%d fail (no memory for mg_host)\n",
- __func__, __LINE__);
- err = -ENOMEM;
- goto probe_err;
- }
- host->major = MG_DISK_MAJ;
-
- /* link each other */
- prv_data->host = host;
- host->dev = &plat_dev->dev;
-
- /* io remap */
- rsc = platform_get_resource(plat_dev, IORESOURCE_MEM, 0);
- if (!rsc) {
- printk(KERN_ERR "%s:%d platform_get_resource fail\n",
- __func__, __LINE__);
- err = -EINVAL;
- goto probe_err_2;
- }
- host->dev_base = ioremap(rsc->start, resource_size(rsc));
- if (!host->dev_base) {
- printk(KERN_ERR "%s:%d ioremap fail\n",
- __func__, __LINE__);
- err = -EIO;
- goto probe_err_2;
- }
- MG_DBG("dev_base = 0x%x\n", (u32)host->dev_base);
-
- /* get reset pin */
- rsc = platform_get_resource_byname(plat_dev, IORESOURCE_IO,
- MG_RST_PIN);
- if (!rsc) {
- printk(KERN_ERR "%s:%d get reset pin fail\n",
- __func__, __LINE__);
- err = -EIO;
- goto probe_err_3;
- }
- host->rst = rsc->start;
-
- /* init rst pin */
- err = gpio_request(host->rst, MG_RST_PIN);
- if (err)
- goto probe_err_3;
- gpio_direction_output(host->rst, 1);
-
- /* reset out pin */
- if (!(prv_data->dev_attr & MG_DEV_MASK)) {
- err = -EINVAL;
- goto probe_err_3a;
- }
-
- if (prv_data->dev_attr != MG_BOOT_DEV) {
- rsc = platform_get_resource_byname(plat_dev, IORESOURCE_IO,
- MG_RSTOUT_PIN);
- if (!rsc) {
- printk(KERN_ERR "%s:%d get reset-out pin fail\n",
- __func__, __LINE__);
- err = -EIO;
- goto probe_err_3a;
- }
- host->rstout = rsc->start;
- err = gpio_request(host->rstout, MG_RSTOUT_PIN);
- if (err)
- goto probe_err_3a;
- gpio_direction_input(host->rstout);
- }
-
- /* disk reset */
- if (prv_data->dev_attr == MG_STORAGE_DEV) {
- /* If POR seq. not yet finished, wait */
- err = mg_wait_rstout(host->rstout, MG_TMAX_RSTOUT);
- if (err)
- goto probe_err_3b;
- err = mg_disk_init(host);
- if (err) {
- printk(KERN_ERR "%s:%d fail (err code : %d)\n",
- __func__, __LINE__, err);
- err = -EIO;
- goto probe_err_3b;
- }
- }
-
- /* get irq resource */
- if (!prv_data->use_polling) {
- host->irq = platform_get_irq(plat_dev, 0);
- if (host->irq == -ENXIO) {
- err = host->irq;
- goto probe_err_3b;
- }
- err = request_irq(host->irq, mg_irq,
- IRQF_TRIGGER_RISING,
- MG_DEV_NAME, host);
- if (err) {
- printk(KERN_ERR "%s:%d fail (request_irq err=%d)\n",
- __func__, __LINE__, err);
- goto probe_err_3b;
- }
-
- }
-
- /* get disk id */
- err = mg_get_disk_id(host);
- if (err) {
- printk(KERN_ERR "%s:%d fail (err code : %d)\n",
- __func__, __LINE__, err);
- err = -EIO;
- goto probe_err_4;
- }
-
- err = register_blkdev(host->major, MG_DISK_NAME);
- if (err < 0) {
- printk(KERN_ERR "%s:%d register_blkdev fail (err code : %d)\n",
- __func__, __LINE__, err);
- goto probe_err_4;
- }
- if (!host->major)
- host->major = err;
-
- spin_lock_init(&host->lock);
-
- if (prv_data->use_polling)
- host->breq = blk_init_queue(mg_request_poll, &host->lock);
- else
- host->breq = blk_init_queue(mg_request, &host->lock);
-
- if (!host->breq) {
- err = -ENOMEM;
- printk(KERN_ERR "%s:%d (blk_init_queue) fail\n",
- __func__, __LINE__);
- goto probe_err_5;
- }
- host->breq->queuedata = host;
-
- /* mflash is random device, thanx for the noop */
- err = elevator_change(host->breq, "noop");
- if (err) {
- printk(KERN_ERR "%s:%d (elevator_init) fail\n",
- __func__, __LINE__);
- goto probe_err_6;
- }
- blk_queue_max_hw_sectors(host->breq, MG_MAX_SECTS);
- blk_queue_logical_block_size(host->breq, MG_SECTOR_SIZE);
-
- init_timer(&host->timer);
- host->timer.function = mg_times_out;
- host->timer.data = (unsigned long)host;
-
- host->gd = alloc_disk(MG_DISK_MAX_PART);
- if (!host->gd) {
- printk(KERN_ERR "%s:%d (alloc_disk) fail\n",
- __func__, __LINE__);
- err = -ENOMEM;
- goto probe_err_7;
- }
- host->gd->major = host->major;
- host->gd->first_minor = 0;
- host->gd->fops = &mg_disk_ops;
- host->gd->queue = host->breq;
- host->gd->private_data = host;
- sprintf(host->gd->disk_name, MG_DISK_NAME"a");
-
- set_capacity(host->gd, host->n_sectors);
-
- add_disk(host->gd);
-
- return err;
-
-probe_err_7:
- del_timer_sync(&host->timer);
-probe_err_6:
- blk_cleanup_queue(host->breq);
-probe_err_5:
- unregister_blkdev(host->major, MG_DISK_NAME);
-probe_err_4:
- if (!prv_data->use_polling)
- free_irq(host->irq, host);
-probe_err_3b:
- gpio_free(host->rstout);
-probe_err_3a:
- gpio_free(host->rst);
-probe_err_3:
- iounmap(host->dev_base);
-probe_err_2:
- kfree(host);
-probe_err:
- return err;
-}
-
-static int mg_remove(struct platform_device *plat_dev)
-{
- struct mg_drv_data *prv_data = plat_dev->dev.platform_data;
- struct mg_host *host = prv_data->host;
- int err = 0;
-
- /* delete timer */
- del_timer_sync(&host->timer);
-
- /* remove disk */
- if (host->gd) {
- del_gendisk(host->gd);
- put_disk(host->gd);
- }
- /* remove queue */
- if (host->breq)
- blk_cleanup_queue(host->breq);
-
- /* unregister blk device */
- unregister_blkdev(host->major, MG_DISK_NAME);
-
- /* free irq */
- if (!prv_data->use_polling)
- free_irq(host->irq, host);
-
- /* free reset-out pin */
- if (prv_data->dev_attr != MG_BOOT_DEV)
- gpio_free(host->rstout);
-
- /* free rst pin */
- if (host->rst)
- gpio_free(host->rst);
-
- /* unmap io */
- if (host->dev_base)
- iounmap(host->dev_base);
-
- /* free mg_host */
- kfree(host);
-
- return err;
-}
-
-static struct platform_driver mg_disk_driver = {
- .probe = mg_probe,
- .remove = mg_remove,
- .driver = {
- .name = MG_DEV_NAME,
- .pm = &mg_pm,
- }
-};
-
-/****************************************************************************
- *
- * Module stuff
- *
- ****************************************************************************/
-
-static int __init mg_init(void)
-{
- printk(KERN_INFO "mGine mflash driver, (c) 2008 mGine Co.\n");
- return platform_driver_register(&mg_disk_driver);
-}
-
-static void __exit mg_exit(void)
-{
- printk(KERN_INFO "mflash driver : bye bye\n");
- platform_driver_unregister(&mg_disk_driver);
-}
-
-module_init(mg_init);
-module_exit(mg_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("unsik Kim <donari75@gmail.com>");
-MODULE_DESCRIPTION("mGine m[g]flash device driver");
return false; /* device present */
}
+/* we have to use runtime tag to setup command header */
+static void mtip_init_cmd_header(struct request *rq)
+{
+ struct driver_data *dd = rq->q->queuedata;
+ struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq);
+ u32 host_cap_64 = readl(dd->mmio + HOST_CAP) & HOST_CAP_64;
+
+ /* Point the command headers at the command tables. */
+ cmd->command_header = dd->port->command_list +
+ (sizeof(struct mtip_cmd_hdr) * rq->tag);
+ cmd->command_header_dma = dd->port->command_list_dma +
+ (sizeof(struct mtip_cmd_hdr) * rq->tag);
+
+ if (host_cap_64)
+ cmd->command_header->ctbau = __force_bit2int cpu_to_le32((cmd->command_dma >> 16) >> 16);
+
+ cmd->command_header->ctba = __force_bit2int cpu_to_le32(cmd->command_dma & 0xFFFFFFFF);
+}
+
static struct mtip_cmd *mtip_get_int_command(struct driver_data *dd)
{
struct request *rq;
if (IS_ERR(rq))
return NULL;
+ /* Internal cmd isn't submitted via .queue_rq */
+ mtip_init_cmd_header(rq);
+
return blk_mq_rq_to_pdu(rq);
}
rq = mtip_rq_from_tag(dd, tag);
- blk_mq_complete_request(rq, status);
+ cmd->status = status;
+ blk_mq_complete_request(rq);
}
/*
if (unlikely(cmd->unaligned))
up(&dd->port->cmd_slot_unal);
- blk_mq_end_request(rq, rq->errors);
+ blk_mq_end_request(rq, cmd->status);
}
static void mtip_abort_cmd(struct request *req, void *data,
bool reserved)
{
+ struct mtip_cmd *cmd = blk_mq_rq_to_pdu(req);
struct driver_data *dd = data;
dbg_printk(MTIP_DRV_NAME " Aborting request, tag = %d\n", req->tag);
clear_bit(req->tag, dd->port->cmds_to_issue);
- req->errors = -EIO;
+ cmd->status = -EIO;
mtip_softirq_done_fn(req);
}
struct request *rq = bd->rq;
int ret;
+ mtip_init_cmd_header(rq);
+
if (unlikely(mtip_check_unal_depth(hctx, rq)))
return BLK_MQ_RQ_QUEUE_BUSY;
if (likely(!ret))
return BLK_MQ_RQ_QUEUE_OK;
- rq->errors = ret;
return BLK_MQ_RQ_QUEUE_ERROR;
}
{
struct driver_data *dd = data;
struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq);
- u32 host_cap_64 = readl(dd->mmio + HOST_CAP) & HOST_CAP_64;
/*
* For flush requests, request_idx starts at the end of the
memset(cmd->command, 0, CMD_DMA_ALLOC_SZ);
- /* Point the command headers at the command tables. */
- cmd->command_header = dd->port->command_list +
- (sizeof(struct mtip_cmd_hdr) * request_idx);
- cmd->command_header_dma = dd->port->command_list_dma +
- (sizeof(struct mtip_cmd_hdr) * request_idx);
-
- if (host_cap_64)
- cmd->command_header->ctbau = __force_bit2int cpu_to_le32((cmd->command_dma >> 16) >> 16);
-
- cmd->command_header->ctba = __force_bit2int cpu_to_le32(cmd->command_dma & 0xFFFFFFFF);
-
sg_init_table(cmd->sg, MTIP_MAX_SG);
return 0;
}
return BLK_EH_RESET_TIMER;
}
-static struct blk_mq_ops mtip_mq_ops = {
+static const struct blk_mq_ops mtip_mq_ops = {
.queue_rq = mtip_queue_rq,
.init_request = mtip_init_cmd,
.exit_request = mtip_free_cmd,
dd->tags.reserved_tags = 1;
dd->tags.cmd_size = sizeof(struct mtip_cmd);
dd->tags.numa_node = dd->numa_node;
- dd->tags.flags = BLK_MQ_F_SHOULD_MERGE;
+ dd->tags.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_NO_SCHED;
dd->tags.driver_data = dd;
dd->tags.timeout = MTIP_NCQ_CMD_TIMEOUT_MS;
dd->queue->limits.discard_granularity = 4096;
blk_queue_max_discard_sectors(dd->queue,
MTIP_MAX_TRIM_ENTRY_LEN * MTIP_MAX_TRIM_ENTRIES);
- dd->queue->limits.discard_zeroes_data = 0;
}
/* Set the capacity of the device in 512 byte sectors. */
struct driver_data *dd = (struct driver_data *)data;
struct mtip_cmd *cmd;
- if (likely(!reserv))
- blk_mq_complete_request(rq, -ENODEV);
- else if (test_bit(MTIP_PF_IC_ACTIVE_BIT, &dd->port->flags)) {
+ if (likely(!reserv)) {
+ cmd = blk_mq_rq_to_pdu(rq);
+ cmd->status = -ENODEV;
+ blk_mq_complete_request(rq);
+ } else if (test_bit(MTIP_PF_IC_ACTIVE_BIT, &dd->port->flags)) {
cmd = mtip_cmd_from_tag(dd, MTIP_TAG_INTERNAL);
if (cmd->comp_func)
dev_info(&dd->pdev->dev, "device %s surprise removal\n",
dd->disk->disk_name);
- blk_mq_freeze_queue_start(dd->queue);
+ blk_freeze_queue_start(dd->queue);
blk_mq_stop_hw_queues(dd->queue);
blk_mq_tagset_busy_iter(&dd->tags, mtip_no_dev_cleanup, dd);
int retries; /* The number of retries left for this command. */
int direction; /* Data transfer direction */
+ int status;
};
/* Structure used to describe a port. */
#include <asm/types.h>
#include <linux/nbd.h>
+#include <linux/nbd-netlink.h>
+#include <net/genetlink.h>
static DEFINE_IDR(nbd_index_idr);
static DEFINE_MUTEX(nbd_index_mutex);
+static int nbd_total_devices = 0;
struct nbd_sock {
struct socket *sock;
struct mutex tx_lock;
struct request *pending;
int sent;
+ bool dead;
+ int fallback_index;
+ int cookie;
+};
+
+struct recv_thread_args {
+ struct work_struct work;
+ struct nbd_device *nbd;
+ int index;
+};
+
+struct link_dead_args {
+ struct work_struct work;
+ int index;
};
#define NBD_TIMEDOUT 0
#define NBD_DISCONNECT_REQUESTED 1
#define NBD_DISCONNECTED 2
-#define NBD_RUNNING 3
+#define NBD_HAS_PID_FILE 3
+#define NBD_HAS_CONFIG_REF 4
+#define NBD_BOUND 5
+#define NBD_DESTROY_ON_DISCONNECT 6
-struct nbd_device {
+struct nbd_config {
u32 flags;
unsigned long runtime_flags;
- struct nbd_sock **socks;
- int magic;
+ u64 dead_conn_timeout;
- struct blk_mq_tag_set tag_set;
-
- struct mutex config_lock;
- struct gendisk *disk;
+ struct nbd_sock **socks;
int num_connections;
+ atomic_t live_connections;
+ wait_queue_head_t conn_wait;
+
atomic_t recv_threads;
wait_queue_head_t recv_wq;
loff_t blksize;
loff_t bytesize;
-
- struct task_struct *task_recv;
- struct task_struct *task_setup;
-
#if IS_ENABLED(CONFIG_DEBUG_FS)
struct dentry *dbg_dir;
#endif
};
+struct nbd_device {
+ struct blk_mq_tag_set tag_set;
+
+ int index;
+ refcount_t config_refs;
+ refcount_t refs;
+ struct nbd_config *config;
+ struct mutex config_lock;
+ struct gendisk *disk;
+
+ struct list_head list;
+ struct task_struct *task_recv;
+ struct task_struct *task_setup;
+};
+
struct nbd_cmd {
struct nbd_device *nbd;
+ int index;
+ int cookie;
struct completion send_complete;
+ int status;
};
#if IS_ENABLED(CONFIG_DEBUG_FS)
static int nbd_dev_dbg_init(struct nbd_device *nbd);
static void nbd_dev_dbg_close(struct nbd_device *nbd);
-
+static void nbd_config_put(struct nbd_device *nbd);
+static void nbd_connect_reply(struct genl_info *info, int index);
+static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info);
+static void nbd_dead_link_work(struct work_struct *work);
static inline struct device *nbd_to_dev(struct nbd_device *nbd)
{
return disk_to_dev(nbd->disk);
}
-static bool nbd_is_connected(struct nbd_device *nbd)
-{
- return !!nbd->task_recv;
-}
-
static const char *nbdcmd_to_ascii(int cmd)
{
switch (cmd) {
return "invalid";
}
-static int nbd_size_clear(struct nbd_device *nbd, struct block_device *bdev)
+static ssize_t pid_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
- if (bdev->bd_openers <= 1)
- bd_set_size(bdev, 0);
- set_capacity(nbd->disk, 0);
- kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
+ struct gendisk *disk = dev_to_disk(dev);
+ struct nbd_device *nbd = (struct nbd_device *)disk->private_data;
- return 0;
+ return sprintf(buf, "%d\n", task_pid_nr(nbd->task_recv));
+}
+
+static struct device_attribute pid_attr = {
+ .attr = { .name = "pid", .mode = S_IRUGO},
+ .show = pid_show,
+};
+
+static void nbd_dev_remove(struct nbd_device *nbd)
+{
+ struct gendisk *disk = nbd->disk;
+ if (disk) {
+ del_gendisk(disk);
+ blk_cleanup_queue(disk->queue);
+ blk_mq_free_tag_set(&nbd->tag_set);
+ disk->private_data = NULL;
+ put_disk(disk);
+ }
+ kfree(nbd);
+}
+
+static void nbd_put(struct nbd_device *nbd)
+{
+ if (refcount_dec_and_mutex_lock(&nbd->refs,
+ &nbd_index_mutex)) {
+ idr_remove(&nbd_index_idr, nbd->index);
+ mutex_unlock(&nbd_index_mutex);
+ nbd_dev_remove(nbd);
+ }
+}
+
+static int nbd_disconnected(struct nbd_config *config)
+{
+ return test_bit(NBD_DISCONNECTED, &config->runtime_flags) ||
+ test_bit(NBD_DISCONNECT_REQUESTED, &config->runtime_flags);
+}
+
+static void nbd_mark_nsock_dead(struct nbd_device *nbd, struct nbd_sock *nsock,
+ int notify)
+{
+ if (!nsock->dead && notify && !nbd_disconnected(nbd->config)) {
+ struct link_dead_args *args;
+ args = kmalloc(sizeof(struct link_dead_args), GFP_NOIO);
+ if (args) {
+ INIT_WORK(&args->work, nbd_dead_link_work);
+ args->index = nbd->index;
+ queue_work(system_wq, &args->work);
+ }
+ }
+ if (!nsock->dead) {
+ kernel_sock_shutdown(nsock->sock, SHUT_RDWR);
+ atomic_dec(&nbd->config->live_connections);
+ }
+ nsock->dead = true;
+ nsock->pending = NULL;
+ nsock->sent = 0;
+}
+
+static void nbd_size_clear(struct nbd_device *nbd)
+{
+ if (nbd->config->bytesize) {
+ set_capacity(nbd->disk, 0);
+ kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
+ }
}
-static void nbd_size_update(struct nbd_device *nbd, struct block_device *bdev)
+static void nbd_size_update(struct nbd_device *nbd)
{
- blk_queue_logical_block_size(nbd->disk->queue, nbd->blksize);
- blk_queue_physical_block_size(nbd->disk->queue, nbd->blksize);
- bd_set_size(bdev, nbd->bytesize);
- set_capacity(nbd->disk, nbd->bytesize >> 9);
+ struct nbd_config *config = nbd->config;
+ blk_queue_logical_block_size(nbd->disk->queue, config->blksize);
+ blk_queue_physical_block_size(nbd->disk->queue, config->blksize);
+ set_capacity(nbd->disk, config->bytesize >> 9);
kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
}
-static void nbd_size_set(struct nbd_device *nbd, struct block_device *bdev,
- loff_t blocksize, loff_t nr_blocks)
+static void nbd_size_set(struct nbd_device *nbd, loff_t blocksize,
+ loff_t nr_blocks)
{
- nbd->blksize = blocksize;
- nbd->bytesize = blocksize * nr_blocks;
- if (nbd_is_connected(nbd))
- nbd_size_update(nbd, bdev);
+ struct nbd_config *config = nbd->config;
+ config->blksize = blocksize;
+ config->bytesize = blocksize * nr_blocks;
+ nbd_size_update(nbd);
}
-static void nbd_end_request(struct nbd_cmd *cmd)
+static void nbd_complete_rq(struct request *req)
{
- struct nbd_device *nbd = cmd->nbd;
- struct request *req = blk_mq_rq_from_pdu(cmd);
- int error = req->errors ? -EIO : 0;
+ struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req);
- dev_dbg(nbd_to_dev(nbd), "request %p: %s\n", cmd,
- error ? "failed" : "done");
+ dev_dbg(nbd_to_dev(cmd->nbd), "request %p: %s\n", cmd,
+ cmd->status ? "failed" : "done");
- blk_mq_complete_request(req, error);
+ blk_mq_end_request(req, cmd->status);
}
/*
*/
static void sock_shutdown(struct nbd_device *nbd)
{
+ struct nbd_config *config = nbd->config;
int i;
- if (nbd->num_connections == 0)
+ if (config->num_connections == 0)
return;
- if (test_and_set_bit(NBD_DISCONNECTED, &nbd->runtime_flags))
+ if (test_and_set_bit(NBD_DISCONNECTED, &config->runtime_flags))
return;
- for (i = 0; i < nbd->num_connections; i++) {
- struct nbd_sock *nsock = nbd->socks[i];
+ for (i = 0; i < config->num_connections; i++) {
+ struct nbd_sock *nsock = config->socks[i];
mutex_lock(&nsock->tx_lock);
- kernel_sock_shutdown(nsock->sock, SHUT_RDWR);
+ nbd_mark_nsock_dead(nbd, nsock, 0);
mutex_unlock(&nsock->tx_lock);
}
dev_warn(disk_to_dev(nbd->disk), "shutting down sockets\n");
{
struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req);
struct nbd_device *nbd = cmd->nbd;
+ struct nbd_config *config;
- dev_err(nbd_to_dev(nbd), "Connection timed out, shutting down connection\n");
- set_bit(NBD_TIMEDOUT, &nbd->runtime_flags);
- req->errors = -EIO;
+ if (!refcount_inc_not_zero(&nbd->config_refs)) {
+ cmd->status = -EIO;
+ return BLK_EH_HANDLED;
+ }
- mutex_lock(&nbd->config_lock);
+ /* If we are waiting on our dead timer then we could get timeout
+ * callbacks for our request. For this we just want to reset the timer
+ * and let the queue side take care of everything.
+ */
+ if (!completion_done(&cmd->send_complete)) {
+ nbd_config_put(nbd);
+ return BLK_EH_RESET_TIMER;
+ }
+ config = nbd->config;
+
+ if (config->num_connections > 1) {
+ dev_err_ratelimited(nbd_to_dev(nbd),
+ "Connection timed out, retrying\n");
+ /*
+ * Hooray we have more connections, requeue this IO, the submit
+ * path will put it on a real connection.
+ */
+ if (config->socks && config->num_connections > 1) {
+ if (cmd->index < config->num_connections) {
+ struct nbd_sock *nsock =
+ config->socks[cmd->index];
+ mutex_lock(&nsock->tx_lock);
+ /* We can have multiple outstanding requests, so
+ * we don't want to mark the nsock dead if we've
+ * already reconnected with a new socket, so
+ * only mark it dead if its the same socket we
+ * were sent out on.
+ */
+ if (cmd->cookie == nsock->cookie)
+ nbd_mark_nsock_dead(nbd, nsock, 1);
+ mutex_unlock(&nsock->tx_lock);
+ }
+ blk_mq_requeue_request(req, true);
+ nbd_config_put(nbd);
+ return BLK_EH_NOT_HANDLED;
+ }
+ } else {
+ dev_err_ratelimited(nbd_to_dev(nbd),
+ "Connection timed out\n");
+ }
+ set_bit(NBD_TIMEDOUT, &config->runtime_flags);
+ cmd->status = -EIO;
sock_shutdown(nbd);
- mutex_unlock(&nbd->config_lock);
+ nbd_config_put(nbd);
+
return BLK_EH_HANDLED;
}
static int sock_xmit(struct nbd_device *nbd, int index, int send,
struct iov_iter *iter, int msg_flags, int *sent)
{
- struct socket *sock = nbd->socks[index]->sock;
+ struct nbd_config *config = nbd->config;
+ struct socket *sock = config->socks[index]->sock;
int result;
struct msghdr msg;
unsigned long pflags = current->flags;
*sent += result;
} while (msg_data_left(&msg));
- tsk_restore_flags(current, pflags, PF_MEMALLOC);
+ current_restore_flags(pflags, PF_MEMALLOC);
return result;
}
static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
{
struct request *req = blk_mq_rq_from_pdu(cmd);
- struct nbd_sock *nsock = nbd->socks[index];
+ struct nbd_config *config = nbd->config;
+ struct nbd_sock *nsock = config->socks[index];
int result;
struct nbd_request request = {.magic = htonl(NBD_REQUEST_MAGIC)};
struct kvec iov = {.iov_base = &request, .iov_len = sizeof(request)};
}
if (rq_data_dir(req) == WRITE &&
- (nbd->flags & NBD_FLAG_READ_ONLY)) {
+ (config->flags & NBD_FLAG_READ_ONLY)) {
dev_err_ratelimited(disk_to_dev(nbd->disk),
"Write on read-only\n");
return -EIO;
}
iov_iter_advance(&from, sent);
}
+ cmd->index = index;
+ cmd->cookie = nsock->cookie;
request.type = htonl(type);
if (type != NBD_CMD_FLUSH) {
request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9);
}
dev_err_ratelimited(disk_to_dev(nbd->disk),
"Send control failed (result %d)\n", result);
- return -EIO;
+ return -EAGAIN;
}
send_pages:
if (type != NBD_CMD_WRITE)
dev_err(disk_to_dev(nbd->disk),
"Send data failed (result %d)\n",
result);
- return -EIO;
+ return -EAGAIN;
}
/*
* The completion might already have come in,
/* NULL returned = something went wrong, inform userspace */
static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
{
+ struct nbd_config *config = nbd->config;
int result;
struct nbd_reply reply;
struct nbd_cmd *cmd;
iov_iter_kvec(&to, READ | ITER_KVEC, &iov, 1, sizeof(reply));
result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL);
if (result <= 0) {
- if (!test_bit(NBD_DISCONNECTED, &nbd->runtime_flags) &&
- !test_bit(NBD_DISCONNECT_REQUESTED, &nbd->runtime_flags))
+ if (!nbd_disconnected(config))
dev_err(disk_to_dev(nbd->disk),
"Receive control failed (result %d)\n", result);
return ERR_PTR(result);
if (ntohl(reply.error)) {
dev_err(disk_to_dev(nbd->disk), "Other side returned error (%d)\n",
ntohl(reply.error));
- req->errors = -EIO;
+ cmd->status = -EIO;
return cmd;
}
if (result <= 0) {
dev_err(disk_to_dev(nbd->disk), "Receive data failed (result %d)\n",
result);
- req->errors = -EIO;
- return cmd;
+ /*
+ * If we've disconnected or we only have 1
+ * connection then we need to make sure we
+ * complete this request, otherwise error out
+ * and let the timeout stuff handle resubmitting
+ * this request onto another connection.
+ */
+ if (nbd_disconnected(config) ||
+ config->num_connections <= 1) {
+ cmd->status = -EIO;
+ return cmd;
+ }
+ return ERR_PTR(-EIO);
}
dev_dbg(nbd_to_dev(nbd), "request %p: got %d bytes data\n",
cmd, bvec.bv_len);
return cmd;
}
-static ssize_t pid_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct gendisk *disk = dev_to_disk(dev);
- struct nbd_device *nbd = (struct nbd_device *)disk->private_data;
-
- return sprintf(buf, "%d\n", task_pid_nr(nbd->task_recv));
-}
-
-static struct device_attribute pid_attr = {
- .attr = { .name = "pid", .mode = S_IRUGO},
- .show = pid_show,
-};
-
-struct recv_thread_args {
- struct work_struct work;
- struct nbd_device *nbd;
- int index;
-};
-
static void recv_work(struct work_struct *work)
{
struct recv_thread_args *args = container_of(work,
struct recv_thread_args,
work);
struct nbd_device *nbd = args->nbd;
+ struct nbd_config *config = nbd->config;
struct nbd_cmd *cmd;
int ret = 0;
- BUG_ON(nbd->magic != NBD_MAGIC);
while (1) {
cmd = nbd_read_stat(nbd, args->index);
if (IS_ERR(cmd)) {
+ struct nbd_sock *nsock = config->socks[args->index];
+
+ mutex_lock(&nsock->tx_lock);
+ nbd_mark_nsock_dead(nbd, nsock, 1);
+ mutex_unlock(&nsock->tx_lock);
ret = PTR_ERR(cmd);
break;
}
- nbd_end_request(cmd);
+ blk_mq_complete_request(blk_mq_rq_from_pdu(cmd));
}
-
- /*
- * We got an error, shut everybody down if this wasn't the result of a
- * disconnect request.
- */
- if (ret && !test_bit(NBD_DISCONNECT_REQUESTED, &nbd->runtime_flags))
- sock_shutdown(nbd);
- atomic_dec(&nbd->recv_threads);
- wake_up(&nbd->recv_wq);
+ atomic_dec(&config->recv_threads);
+ wake_up(&config->recv_wq);
+ nbd_config_put(nbd);
+ kfree(args);
}
static void nbd_clear_req(struct request *req, void *data, bool reserved)
if (!blk_mq_request_started(req))
return;
cmd = blk_mq_rq_to_pdu(req);
- req->errors = -EIO;
- nbd_end_request(cmd);
+ cmd->status = -EIO;
+ blk_mq_complete_request(req);
}
static void nbd_clear_que(struct nbd_device *nbd)
{
- BUG_ON(nbd->magic != NBD_MAGIC);
-
+ blk_mq_stop_hw_queues(nbd->disk->queue);
blk_mq_tagset_busy_iter(&nbd->tag_set, nbd_clear_req, NULL);
+ blk_mq_start_hw_queues(nbd->disk->queue);
dev_dbg(disk_to_dev(nbd->disk), "queue cleared\n");
}
+static int find_fallback(struct nbd_device *nbd, int index)
+{
+ struct nbd_config *config = nbd->config;
+ int new_index = -1;
+ struct nbd_sock *nsock = config->socks[index];
+ int fallback = nsock->fallback_index;
+
+ if (test_bit(NBD_DISCONNECTED, &config->runtime_flags))
+ return new_index;
+
+ if (config->num_connections <= 1) {
+ dev_err_ratelimited(disk_to_dev(nbd->disk),
+ "Attempted send on invalid socket\n");
+ return new_index;
+ }
+
+ if (fallback >= 0 && fallback < config->num_connections &&
+ !config->socks[fallback]->dead)
+ return fallback;
+
+ if (nsock->fallback_index < 0 ||
+ nsock->fallback_index >= config->num_connections ||
+ config->socks[nsock->fallback_index]->dead) {
+ int i;
+ for (i = 0; i < config->num_connections; i++) {
+ if (i == index)
+ continue;
+ if (!config->socks[i]->dead) {
+ new_index = i;
+ break;
+ }
+ }
+ nsock->fallback_index = new_index;
+ if (new_index < 0) {
+ dev_err_ratelimited(disk_to_dev(nbd->disk),
+ "Dead connection, failed to find a fallback\n");
+ return new_index;
+ }
+ }
+ new_index = nsock->fallback_index;
+ return new_index;
+}
+
+static int wait_for_reconnect(struct nbd_device *nbd)
+{
+ struct nbd_config *config = nbd->config;
+ if (!config->dead_conn_timeout)
+ return 0;
+ if (test_bit(NBD_DISCONNECTED, &config->runtime_flags))
+ return 0;
+ wait_event_interruptible_timeout(config->conn_wait,
+ atomic_read(&config->live_connections),
+ config->dead_conn_timeout);
+ return atomic_read(&config->live_connections);
+}
static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
{
struct request *req = blk_mq_rq_from_pdu(cmd);
struct nbd_device *nbd = cmd->nbd;
+ struct nbd_config *config;
struct nbd_sock *nsock;
int ret;
- if (index >= nbd->num_connections) {
+ if (!refcount_inc_not_zero(&nbd->config_refs)) {
dev_err_ratelimited(disk_to_dev(nbd->disk),
- "Attempted send on invalid socket\n");
+ "Socks array is empty\n");
return -EINVAL;
}
+ config = nbd->config;
- if (test_bit(NBD_DISCONNECTED, &nbd->runtime_flags)) {
+ if (index >= config->num_connections) {
dev_err_ratelimited(disk_to_dev(nbd->disk),
- "Attempted send on closed socket\n");
+ "Attempted send on invalid socket\n");
+ nbd_config_put(nbd);
return -EINVAL;
}
-
- req->errors = 0;
-
- nsock = nbd->socks[index];
+ cmd->status = 0;
+again:
+ nsock = config->socks[index];
mutex_lock(&nsock->tx_lock);
- if (unlikely(!nsock->sock)) {
+ if (nsock->dead) {
+ int old_index = index;
+ index = find_fallback(nbd, index);
mutex_unlock(&nsock->tx_lock);
- dev_err_ratelimited(disk_to_dev(nbd->disk),
- "Attempted send on closed socket\n");
- return -EINVAL;
+ if (index < 0) {
+ if (wait_for_reconnect(nbd)) {
+ index = old_index;
+ goto again;
+ }
+ /* All the sockets should already be down at this point,
+ * we just want to make sure that DISCONNECTED is set so
+ * any requests that come in that were queue'ed waiting
+ * for the reconnect timer don't trigger the timer again
+ * and instead just error out.
+ */
+ sock_shutdown(nbd);
+ nbd_config_put(nbd);
+ return -EIO;
+ }
+ goto again;
}
/* Handle the case that we have a pending request that was partially
ret = 0;
goto out;
}
+ /*
+ * Some failures are related to the link going down, so anything that
+ * returns EAGAIN can be retried on a different socket.
+ */
ret = nbd_send_cmd(nbd, cmd, index);
+ if (ret == -EAGAIN) {
+ dev_err_ratelimited(disk_to_dev(nbd->disk),
+ "Request send failed trying another connection\n");
+ nbd_mark_nsock_dead(nbd, nsock, 1);
+ mutex_unlock(&nsock->tx_lock);
+ goto again;
+ }
out:
mutex_unlock(&nsock->tx_lock);
+ nbd_config_put(nbd);
return ret;
}
return ret;
}
-static int nbd_add_socket(struct nbd_device *nbd, struct block_device *bdev,
- unsigned long arg)
+static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
+ bool netlink)
{
+ struct nbd_config *config = nbd->config;
struct socket *sock;
struct nbd_sock **socks;
struct nbd_sock *nsock;
if (!sock)
return err;
- if (!nbd->task_setup)
+ if (!netlink && !nbd->task_setup &&
+ !test_bit(NBD_BOUND, &config->runtime_flags))
nbd->task_setup = current;
- if (nbd->task_setup != current) {
+
+ if (!netlink &&
+ (nbd->task_setup != current ||
+ test_bit(NBD_BOUND, &config->runtime_flags))) {
dev_err(disk_to_dev(nbd->disk),
"Device being setup by another task");
- return -EINVAL;
+ sockfd_put(sock);
+ return -EBUSY;
}
- socks = krealloc(nbd->socks, (nbd->num_connections + 1) *
+ socks = krealloc(config->socks, (config->num_connections + 1) *
sizeof(struct nbd_sock *), GFP_KERNEL);
- if (!socks)
+ if (!socks) {
+ sockfd_put(sock);
return -ENOMEM;
+ }
nsock = kzalloc(sizeof(struct nbd_sock), GFP_KERNEL);
- if (!nsock)
+ if (!nsock) {
+ sockfd_put(sock);
return -ENOMEM;
+ }
- nbd->socks = socks;
+ config->socks = socks;
+ nsock->fallback_index = -1;
+ nsock->dead = false;
mutex_init(&nsock->tx_lock);
nsock->sock = sock;
nsock->pending = NULL;
nsock->sent = 0;
- socks[nbd->num_connections++] = nsock;
+ nsock->cookie = 0;
+ socks[config->num_connections++] = nsock;
+ atomic_inc(&config->live_connections);
- if (max_part)
- bdev->bd_invalidated = 1;
return 0;
}
+static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg)
+{
+ struct nbd_config *config = nbd->config;
+ struct socket *sock, *old;
+ struct recv_thread_args *args;
+ int i;
+ int err;
+
+ sock = sockfd_lookup(arg, &err);
+ if (!sock)
+ return err;
+
+ args = kzalloc(sizeof(*args), GFP_KERNEL);
+ if (!args) {
+ sockfd_put(sock);
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < config->num_connections; i++) {
+ struct nbd_sock *nsock = config->socks[i];
+
+ if (!nsock->dead)
+ continue;
+
+ mutex_lock(&nsock->tx_lock);
+ if (!nsock->dead) {
+ mutex_unlock(&nsock->tx_lock);
+ continue;
+ }
+ sk_set_memalloc(sock->sk);
+ atomic_inc(&config->recv_threads);
+ refcount_inc(&nbd->config_refs);
+ old = nsock->sock;
+ nsock->fallback_index = -1;
+ nsock->sock = sock;
+ nsock->dead = false;
+ INIT_WORK(&args->work, recv_work);
+ args->index = i;
+ args->nbd = nbd;
+ nsock->cookie++;
+ mutex_unlock(&nsock->tx_lock);
+ sockfd_put(old);
+
+ /* We take the tx_mutex in an error path in the recv_work, so we
+ * need to queue_work outside of the tx_mutex.
+ */
+ queue_work(recv_workqueue, &args->work);
+
+ atomic_inc(&config->live_connections);
+ wake_up(&config->conn_wait);
+ return 0;
+ }
+ sockfd_put(sock);
+ kfree(args);
+ return -ENOSPC;
+}
+
/* Reset all properties of an NBD device */
static void nbd_reset(struct nbd_device *nbd)
{
- nbd->runtime_flags = 0;
- nbd->blksize = 1024;
- nbd->bytesize = 0;
- set_capacity(nbd->disk, 0);
- nbd->flags = 0;
+ nbd->config = NULL;
nbd->tag_set.timeout = 0;
queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, nbd->disk->queue);
}
{
if (bdev->bd_openers > 1)
return;
- set_device_ro(bdev, false);
- bdev->bd_inode->i_size = 0;
+ bd_set_size(bdev, 0);
if (max_part > 0) {
blkdev_reread_part(bdev);
bdev->bd_invalidated = 1;
}
}
-static void nbd_parse_flags(struct nbd_device *nbd, struct block_device *bdev)
+static void nbd_parse_flags(struct nbd_device *nbd)
{
- if (nbd->flags & NBD_FLAG_READ_ONLY)
- set_device_ro(bdev, true);
- if (nbd->flags & NBD_FLAG_SEND_TRIM)
+ struct nbd_config *config = nbd->config;
+ if (config->flags & NBD_FLAG_READ_ONLY)
+ set_disk_ro(nbd->disk, true);
+ else
+ set_disk_ro(nbd->disk, false);
+ if (config->flags & NBD_FLAG_SEND_TRIM)
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, nbd->disk->queue);
- if (nbd->flags & NBD_FLAG_SEND_FLUSH)
+ if (config->flags & NBD_FLAG_SEND_FLUSH)
blk_queue_write_cache(nbd->disk->queue, true, false);
else
blk_queue_write_cache(nbd->disk->queue, false, false);
static void send_disconnects(struct nbd_device *nbd)
{
+ struct nbd_config *config = nbd->config;
struct nbd_request request = {
.magic = htonl(NBD_REQUEST_MAGIC),
.type = htonl(NBD_CMD_DISC),
struct iov_iter from;
int i, ret;
- for (i = 0; i < nbd->num_connections; i++) {
+ for (i = 0; i < config->num_connections; i++) {
iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request));
ret = sock_xmit(nbd, i, 1, &from, 0, NULL);
if (ret <= 0)
}
}
-static int nbd_disconnect(struct nbd_device *nbd, struct block_device *bdev)
+static int nbd_disconnect(struct nbd_device *nbd)
{
- dev_info(disk_to_dev(nbd->disk), "NBD_DISCONNECT\n");
- if (!nbd->socks)
- return -EINVAL;
-
- mutex_unlock(&nbd->config_lock);
- fsync_bdev(bdev);
- mutex_lock(&nbd->config_lock);
-
- /* Check again after getting mutex back. */
- if (!nbd->socks)
- return -EINVAL;
+ struct nbd_config *config = nbd->config;
+ dev_info(disk_to_dev(nbd->disk), "NBD_DISCONNECT\n");
if (!test_and_set_bit(NBD_DISCONNECT_REQUESTED,
- &nbd->runtime_flags))
+ &config->runtime_flags))
send_disconnects(nbd);
return 0;
}
-static int nbd_clear_sock(struct nbd_device *nbd, struct block_device *bdev)
+static void nbd_clear_sock(struct nbd_device *nbd)
{
sock_shutdown(nbd);
nbd_clear_que(nbd);
+ nbd->task_setup = NULL;
+}
- __invalidate_device(bdev, true);
- nbd_bdev_reset(bdev);
- /*
- * We want to give the run thread a chance to wait for everybody
- * to clean up and then do it's own cleanup.
- */
- if (!test_bit(NBD_RUNNING, &nbd->runtime_flags) &&
- nbd->num_connections) {
- int i;
-
- for (i = 0; i < nbd->num_connections; i++) {
- sockfd_put(nbd->socks[i]->sock);
- kfree(nbd->socks[i]);
+static void nbd_config_put(struct nbd_device *nbd)
+{
+ if (refcount_dec_and_mutex_lock(&nbd->config_refs,
+ &nbd->config_lock)) {
+ struct nbd_config *config = nbd->config;
+ nbd_dev_dbg_close(nbd);
+ nbd_size_clear(nbd);
+ if (test_and_clear_bit(NBD_HAS_PID_FILE,
+ &config->runtime_flags))
+ device_remove_file(disk_to_dev(nbd->disk), &pid_attr);
+ nbd->task_recv = NULL;
+ nbd_clear_sock(nbd);
+ if (config->num_connections) {
+ int i;
+ for (i = 0; i < config->num_connections; i++) {
+ sockfd_put(config->socks[i]->sock);
+ kfree(config->socks[i]);
+ }
+ kfree(config->socks);
}
- kfree(nbd->socks);
- nbd->socks = NULL;
- nbd->num_connections = 0;
- }
- nbd->task_setup = NULL;
+ nbd_reset(nbd);
- return 0;
+ mutex_unlock(&nbd->config_lock);
+ nbd_put(nbd);
+ module_put(THIS_MODULE);
+ }
}
-static int nbd_start_device(struct nbd_device *nbd, struct block_device *bdev)
+static int nbd_start_device(struct nbd_device *nbd)
{
- struct recv_thread_args *args;
- int num_connections = nbd->num_connections;
+ struct nbd_config *config = nbd->config;
+ int num_connections = config->num_connections;
int error = 0, i;
if (nbd->task_recv)
return -EBUSY;
- if (!nbd->socks)
+ if (!config->socks)
return -EINVAL;
if (num_connections > 1 &&
- !(nbd->flags & NBD_FLAG_CAN_MULTI_CONN)) {
+ !(config->flags & NBD_FLAG_CAN_MULTI_CONN)) {
dev_err(disk_to_dev(nbd->disk), "server does not support multiple connections per device.\n");
- error = -EINVAL;
- goto out_err;
+ return -EINVAL;
}
- set_bit(NBD_RUNNING, &nbd->runtime_flags);
- blk_mq_update_nr_hw_queues(&nbd->tag_set, nbd->num_connections);
- args = kcalloc(num_connections, sizeof(*args), GFP_KERNEL);
- if (!args) {
- error = -ENOMEM;
- goto out_err;
- }
+ blk_mq_update_nr_hw_queues(&nbd->tag_set, config->num_connections);
nbd->task_recv = current;
- mutex_unlock(&nbd->config_lock);
- nbd_parse_flags(nbd, bdev);
+ nbd_parse_flags(nbd);
error = device_create_file(disk_to_dev(nbd->disk), &pid_attr);
if (error) {
dev_err(disk_to_dev(nbd->disk), "device_create_file failed!\n");
- goto out_recv;
+ return error;
}
-
- nbd_size_update(nbd, bdev);
+ set_bit(NBD_HAS_PID_FILE, &config->runtime_flags);
nbd_dev_dbg_init(nbd);
for (i = 0; i < num_connections; i++) {
- sk_set_memalloc(nbd->socks[i]->sock->sk);
- atomic_inc(&nbd->recv_threads);
- INIT_WORK(&args[i].work, recv_work);
- args[i].nbd = nbd;
- args[i].index = i;
- queue_work(recv_workqueue, &args[i].work);
- }
- wait_event_interruptible(nbd->recv_wq,
- atomic_read(&nbd->recv_threads) == 0);
- for (i = 0; i < num_connections; i++)
- flush_work(&args[i].work);
- nbd_dev_dbg_close(nbd);
- nbd_size_clear(nbd, bdev);
- device_remove_file(disk_to_dev(nbd->disk), &pid_attr);
-out_recv:
- mutex_lock(&nbd->config_lock);
- nbd->task_recv = NULL;
-out_err:
- clear_bit(NBD_RUNNING, &nbd->runtime_flags);
- nbd_clear_sock(nbd, bdev);
+ struct recv_thread_args *args;
+ args = kzalloc(sizeof(*args), GFP_KERNEL);
+ if (!args) {
+ sock_shutdown(nbd);
+ return -ENOMEM;
+ }
+ sk_set_memalloc(config->socks[i]->sock->sk);
+ atomic_inc(&config->recv_threads);
+ refcount_inc(&nbd->config_refs);
+ INIT_WORK(&args->work, recv_work);
+ args->nbd = nbd;
+ args->index = i;
+ queue_work(recv_workqueue, &args->work);
+ }
+ return error;
+}
+
+static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *bdev)
+{
+ struct nbd_config *config = nbd->config;
+ int ret;
+
+ ret = nbd_start_device(nbd);
+ if (ret)
+ return ret;
+
+ bd_set_size(bdev, config->bytesize);
+ if (max_part)
+ bdev->bd_invalidated = 1;
+ mutex_unlock(&nbd->config_lock);
+ ret = wait_event_interruptible(config->recv_wq,
+ atomic_read(&config->recv_threads) == 0);
+ if (ret)
+ sock_shutdown(nbd);
+ mutex_lock(&nbd->config_lock);
+ bd_set_size(bdev, 0);
/* user requested, ignore socket errors */
- if (test_bit(NBD_DISCONNECT_REQUESTED, &nbd->runtime_flags))
- error = 0;
- if (test_bit(NBD_TIMEDOUT, &nbd->runtime_flags))
- error = -ETIMEDOUT;
+ if (test_bit(NBD_DISCONNECT_REQUESTED, &config->runtime_flags))
+ ret = 0;
+ if (test_bit(NBD_TIMEDOUT, &config->runtime_flags))
+ ret = -ETIMEDOUT;
+ return ret;
+}
- nbd_reset(nbd);
- return error;
+static void nbd_clear_sock_ioctl(struct nbd_device *nbd,
+ struct block_device *bdev)
+{
+ sock_shutdown(nbd);
+ kill_bdev(bdev);
+ nbd_bdev_reset(bdev);
+ if (test_and_clear_bit(NBD_HAS_CONFIG_REF,
+ &nbd->config->runtime_flags))
+ nbd_config_put(nbd);
}
/* Must be called with config_lock held */
static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
unsigned int cmd, unsigned long arg)
{
+ struct nbd_config *config = nbd->config;
+
switch (cmd) {
case NBD_DISCONNECT:
- return nbd_disconnect(nbd, bdev);
+ return nbd_disconnect(nbd);
case NBD_CLEAR_SOCK:
- return nbd_clear_sock(nbd, bdev);
+ nbd_clear_sock_ioctl(nbd, bdev);
+ return 0;
case NBD_SET_SOCK:
- return nbd_add_socket(nbd, bdev, arg);
+ return nbd_add_socket(nbd, arg, false);
case NBD_SET_BLKSIZE:
- nbd_size_set(nbd, bdev, arg,
- div_s64(nbd->bytesize, arg));
+ nbd_size_set(nbd, arg,
+ div_s64(config->bytesize, arg));
return 0;
case NBD_SET_SIZE:
- nbd_size_set(nbd, bdev, nbd->blksize,
- div_s64(arg, nbd->blksize));
+ nbd_size_set(nbd, config->blksize,
+ div_s64(arg, config->blksize));
return 0;
case NBD_SET_SIZE_BLOCKS:
- nbd_size_set(nbd, bdev, nbd->blksize, arg);
+ nbd_size_set(nbd, config->blksize, arg);
return 0;
case NBD_SET_TIMEOUT:
if (arg) {
return 0;
case NBD_SET_FLAGS:
- nbd->flags = arg;
+ config->flags = arg;
return 0;
case NBD_DO_IT:
- return nbd_start_device(nbd, bdev);
+ return nbd_start_device_ioctl(nbd, bdev);
case NBD_CLEAR_QUE:
/*
* This is for compatibility only. The queue is always cleared
unsigned int cmd, unsigned long arg)
{
struct nbd_device *nbd = bdev->bd_disk->private_data;
- int error;
+ struct nbd_config *config = nbd->config;
+ int error = -EINVAL;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- BUG_ON(nbd->magic != NBD_MAGIC);
-
mutex_lock(&nbd->config_lock);
- error = __nbd_ioctl(bdev, nbd, cmd, arg);
- mutex_unlock(&nbd->config_lock);
+ /* Don't allow ioctl operations on a nbd device that was created with
+ * netlink, unless it's DISCONNECT or CLEAR_SOCK, which are fine.
+ */
+ if (!test_bit(NBD_BOUND, &config->runtime_flags) ||
+ (cmd == NBD_DISCONNECT || cmd == NBD_CLEAR_SOCK))
+ error = __nbd_ioctl(bdev, nbd, cmd, arg);
+ else
+ dev_err(nbd_to_dev(nbd), "Cannot use ioctl interface on a netlink controlled device.\n");
+ mutex_unlock(&nbd->config_lock);
return error;
}
+static struct nbd_config *nbd_alloc_config(void)
+{
+ struct nbd_config *config;
+
+ config = kzalloc(sizeof(struct nbd_config), GFP_NOFS);
+ if (!config)
+ return NULL;
+ atomic_set(&config->recv_threads, 0);
+ init_waitqueue_head(&config->recv_wq);
+ init_waitqueue_head(&config->conn_wait);
+ config->blksize = 1024;
+ atomic_set(&config->live_connections, 0);
+ try_module_get(THIS_MODULE);
+ return config;
+}
+
+static int nbd_open(struct block_device *bdev, fmode_t mode)
+{
+ struct nbd_device *nbd;
+ int ret = 0;
+
+ mutex_lock(&nbd_index_mutex);
+ nbd = bdev->bd_disk->private_data;
+ if (!nbd) {
+ ret = -ENXIO;
+ goto out;
+ }
+ if (!refcount_inc_not_zero(&nbd->refs)) {
+ ret = -ENXIO;
+ goto out;
+ }
+ if (!refcount_inc_not_zero(&nbd->config_refs)) {
+ struct nbd_config *config;
+
+ mutex_lock(&nbd->config_lock);
+ if (refcount_inc_not_zero(&nbd->config_refs)) {
+ mutex_unlock(&nbd->config_lock);
+ goto out;
+ }
+ config = nbd->config = nbd_alloc_config();
+ if (!config) {
+ ret = -ENOMEM;
+ mutex_unlock(&nbd->config_lock);
+ goto out;
+ }
+ refcount_set(&nbd->config_refs, 1);
+ refcount_inc(&nbd->refs);
+ mutex_unlock(&nbd->config_lock);
+ }
+out:
+ mutex_unlock(&nbd_index_mutex);
+ return ret;
+}
+
+static void nbd_release(struct gendisk *disk, fmode_t mode)
+{
+ struct nbd_device *nbd = disk->private_data;
+ nbd_config_put(nbd);
+ nbd_put(nbd);
+}
+
static const struct block_device_operations nbd_fops =
{
.owner = THIS_MODULE,
+ .open = nbd_open,
+ .release = nbd_release,
.ioctl = nbd_ioctl,
.compat_ioctl = nbd_ioctl,
};
static int nbd_dbg_flags_show(struct seq_file *s, void *unused)
{
struct nbd_device *nbd = s->private;
- u32 flags = nbd->flags;
+ u32 flags = nbd->config->flags;
seq_printf(s, "Hex: 0x%08x\n\n", flags);
static int nbd_dev_dbg_init(struct nbd_device *nbd)
{
struct dentry *dir;
+ struct nbd_config *config = nbd->config;
if (!nbd_dbg_dir)
return -EIO;
nbd_name(nbd));
return -EIO;
}
- nbd->dbg_dir = dir;
+ config->dbg_dir = dir;
debugfs_create_file("tasks", 0444, dir, nbd, &nbd_dbg_tasks_ops);
- debugfs_create_u64("size_bytes", 0444, dir, &nbd->bytesize);
+ debugfs_create_u64("size_bytes", 0444, dir, &config->bytesize);
debugfs_create_u32("timeout", 0444, dir, &nbd->tag_set.timeout);
- debugfs_create_u64("blocksize", 0444, dir, &nbd->blksize);
+ debugfs_create_u64("blocksize", 0444, dir, &config->blksize);
debugfs_create_file("flags", 0444, dir, nbd, &nbd_dbg_flags_ops);
return 0;
static void nbd_dev_dbg_close(struct nbd_device *nbd)
{
- debugfs_remove_recursive(nbd->dbg_dir);
+ debugfs_remove_recursive(nbd->config->dbg_dir);
}
static int nbd_dbg_init(void)
return 0;
}
-static struct blk_mq_ops nbd_mq_ops = {
+static const struct blk_mq_ops nbd_mq_ops = {
.queue_rq = nbd_queue_rq,
+ .complete = nbd_complete_rq,
.init_request = nbd_init_request,
.timeout = nbd_xmit_timeout,
};
-static void nbd_dev_remove(struct nbd_device *nbd)
-{
- struct gendisk *disk = nbd->disk;
- nbd->magic = 0;
- if (disk) {
- del_gendisk(disk);
- blk_cleanup_queue(disk->queue);
- blk_mq_free_tag_set(&nbd->tag_set);
- put_disk(disk);
- }
- kfree(nbd);
-}
-
static int nbd_dev_add(int index)
{
struct nbd_device *nbd;
if (err < 0)
goto out_free_disk;
+ nbd->index = index;
nbd->disk = disk;
nbd->tag_set.ops = &nbd_mq_ops;
nbd->tag_set.nr_hw_queues = 1;
queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, disk->queue);
disk->queue->limits.discard_granularity = 512;
blk_queue_max_discard_sectors(disk->queue, UINT_MAX);
- disk->queue->limits.discard_zeroes_data = 0;
+ blk_queue_max_segment_size(disk->queue, UINT_MAX);
+ blk_queue_max_segments(disk->queue, USHRT_MAX);
blk_queue_max_hw_sectors(disk->queue, 65536);
disk->queue->limits.max_sectors = 256;
- nbd->magic = NBD_MAGIC;
mutex_init(&nbd->config_lock);
+ refcount_set(&nbd->config_refs, 0);
+ refcount_set(&nbd->refs, 1);
+ INIT_LIST_HEAD(&nbd->list);
disk->major = NBD_MAJOR;
disk->first_minor = index << part_shift;
disk->fops = &nbd_fops;
disk->private_data = nbd;
sprintf(disk->disk_name, "nbd%d", index);
- init_waitqueue_head(&nbd->recv_wq);
nbd_reset(nbd);
add_disk(disk);
+ nbd_total_devices++;
return index;
out_free_tags:
return err;
}
-/*
- * And here should be modules and kernel interface
- * (Just smiley confuses emacs :-)
+static int find_free_cb(int id, void *ptr, void *data)
+{
+ struct nbd_device *nbd = ptr;
+ struct nbd_device **found = data;
+
+ if (!refcount_read(&nbd->config_refs)) {
+ *found = nbd;
+ return 1;
+ }
+ return 0;
+}
+
+/* Netlink interface. */
+static struct nla_policy nbd_attr_policy[NBD_ATTR_MAX + 1] = {
+ [NBD_ATTR_INDEX] = { .type = NLA_U32 },
+ [NBD_ATTR_SIZE_BYTES] = { .type = NLA_U64 },
+ [NBD_ATTR_BLOCK_SIZE_BYTES] = { .type = NLA_U64 },
+ [NBD_ATTR_TIMEOUT] = { .type = NLA_U64 },
+ [NBD_ATTR_SERVER_FLAGS] = { .type = NLA_U64 },
+ [NBD_ATTR_CLIENT_FLAGS] = { .type = NLA_U64 },
+ [NBD_ATTR_SOCKETS] = { .type = NLA_NESTED},
+ [NBD_ATTR_DEAD_CONN_TIMEOUT] = { .type = NLA_U64 },
+ [NBD_ATTR_DEVICE_LIST] = { .type = NLA_NESTED},
+};
+
+static struct nla_policy nbd_sock_policy[NBD_SOCK_MAX + 1] = {
+ [NBD_SOCK_FD] = { .type = NLA_U32 },
+};
+
+/* We don't use this right now since we don't parse the incoming list, but we
+ * still want it here so userspace knows what to expect.
*/
+static struct nla_policy __attribute__((unused))
+nbd_device_policy[NBD_DEVICE_ATTR_MAX + 1] = {
+ [NBD_DEVICE_INDEX] = { .type = NLA_U32 },
+ [NBD_DEVICE_CONNECTED] = { .type = NLA_U8 },
+};
+
+static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info)
+{
+ struct nbd_device *nbd = NULL;
+ struct nbd_config *config;
+ int index = -1;
+ int ret;
+ bool put_dev = false;
+
+ if (!netlink_capable(skb, CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (info->attrs[NBD_ATTR_INDEX])
+ index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]);
+ if (!info->attrs[NBD_ATTR_SOCKETS]) {
+ printk(KERN_ERR "nbd: must specify at least one socket\n");
+ return -EINVAL;
+ }
+ if (!info->attrs[NBD_ATTR_SIZE_BYTES]) {
+ printk(KERN_ERR "nbd: must specify a size in bytes for the device\n");
+ return -EINVAL;
+ }
+again:
+ mutex_lock(&nbd_index_mutex);
+ if (index == -1) {
+ ret = idr_for_each(&nbd_index_idr, &find_free_cb, &nbd);
+ if (ret == 0) {
+ int new_index;
+ new_index = nbd_dev_add(-1);
+ if (new_index < 0) {
+ mutex_unlock(&nbd_index_mutex);
+ printk(KERN_ERR "nbd: failed to add new device\n");
+ return ret;
+ }
+ nbd = idr_find(&nbd_index_idr, new_index);
+ }
+ } else {
+ nbd = idr_find(&nbd_index_idr, index);
+ }
+ if (!nbd) {
+ printk(KERN_ERR "nbd: couldn't find device at index %d\n",
+ index);
+ mutex_unlock(&nbd_index_mutex);
+ return -EINVAL;
+ }
+ if (!refcount_inc_not_zero(&nbd->refs)) {
+ mutex_unlock(&nbd_index_mutex);
+ if (index == -1)
+ goto again;
+ printk(KERN_ERR "nbd: device at index %d is going down\n",
+ index);
+ return -EINVAL;
+ }
+ mutex_unlock(&nbd_index_mutex);
+
+ mutex_lock(&nbd->config_lock);
+ if (refcount_read(&nbd->config_refs)) {
+ mutex_unlock(&nbd->config_lock);
+ nbd_put(nbd);
+ if (index == -1)
+ goto again;
+ printk(KERN_ERR "nbd: nbd%d already in use\n", index);
+ return -EBUSY;
+ }
+ if (WARN_ON(nbd->config)) {
+ mutex_unlock(&nbd->config_lock);
+ nbd_put(nbd);
+ return -EINVAL;
+ }
+ config = nbd->config = nbd_alloc_config();
+ if (!nbd->config) {
+ mutex_unlock(&nbd->config_lock);
+ nbd_put(nbd);
+ printk(KERN_ERR "nbd: couldn't allocate config\n");
+ return -ENOMEM;
+ }
+ refcount_set(&nbd->config_refs, 1);
+ set_bit(NBD_BOUND, &config->runtime_flags);
+
+ if (info->attrs[NBD_ATTR_SIZE_BYTES]) {
+ u64 bytes = nla_get_u64(info->attrs[NBD_ATTR_SIZE_BYTES]);
+ nbd_size_set(nbd, config->blksize,
+ div64_u64(bytes, config->blksize));
+ }
+ if (info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]) {
+ u64 bsize =
+ nla_get_u64(info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]);
+ nbd_size_set(nbd, bsize, div64_u64(config->bytesize, bsize));
+ }
+ if (info->attrs[NBD_ATTR_TIMEOUT]) {
+ u64 timeout = nla_get_u64(info->attrs[NBD_ATTR_TIMEOUT]);
+ nbd->tag_set.timeout = timeout * HZ;
+ blk_queue_rq_timeout(nbd->disk->queue, timeout * HZ);
+ }
+ if (info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]) {
+ config->dead_conn_timeout =
+ nla_get_u64(info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]);
+ config->dead_conn_timeout *= HZ;
+ }
+ if (info->attrs[NBD_ATTR_SERVER_FLAGS])
+ config->flags =
+ nla_get_u64(info->attrs[NBD_ATTR_SERVER_FLAGS]);
+ if (info->attrs[NBD_ATTR_CLIENT_FLAGS]) {
+ u64 flags = nla_get_u64(info->attrs[NBD_ATTR_CLIENT_FLAGS]);
+ if (flags & NBD_CFLAG_DESTROY_ON_DISCONNECT) {
+ set_bit(NBD_DESTROY_ON_DISCONNECT,
+ &config->runtime_flags);
+ put_dev = true;
+ }
+ }
+
+ if (info->attrs[NBD_ATTR_SOCKETS]) {
+ struct nlattr *attr;
+ int rem, fd;
+
+ nla_for_each_nested(attr, info->attrs[NBD_ATTR_SOCKETS],
+ rem) {
+ struct nlattr *socks[NBD_SOCK_MAX+1];
+
+ if (nla_type(attr) != NBD_SOCK_ITEM) {
+ printk(KERN_ERR "nbd: socks must be embedded in a SOCK_ITEM attr\n");
+ ret = -EINVAL;
+ goto out;
+ }
+ ret = nla_parse_nested(socks, NBD_SOCK_MAX, attr,
+ nbd_sock_policy);
+ if (ret != 0) {
+ printk(KERN_ERR "nbd: error processing sock list\n");
+ ret = -EINVAL;
+ goto out;
+ }
+ if (!socks[NBD_SOCK_FD])
+ continue;
+ fd = (int)nla_get_u32(socks[NBD_SOCK_FD]);
+ ret = nbd_add_socket(nbd, fd, true);
+ if (ret)
+ goto out;
+ }
+ }
+ ret = nbd_start_device(nbd);
+out:
+ mutex_unlock(&nbd->config_lock);
+ if (!ret) {
+ set_bit(NBD_HAS_CONFIG_REF, &config->runtime_flags);
+ refcount_inc(&nbd->config_refs);
+ nbd_connect_reply(info, nbd->index);
+ }
+ nbd_config_put(nbd);
+ if (put_dev)
+ nbd_put(nbd);
+ return ret;
+}
+
+static int nbd_genl_disconnect(struct sk_buff *skb, struct genl_info *info)
+{
+ struct nbd_device *nbd;
+ int index;
+
+ if (!netlink_capable(skb, CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (!info->attrs[NBD_ATTR_INDEX]) {
+ printk(KERN_ERR "nbd: must specify an index to disconnect\n");
+ return -EINVAL;
+ }
+ index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]);
+ mutex_lock(&nbd_index_mutex);
+ nbd = idr_find(&nbd_index_idr, index);
+ if (!nbd) {
+ mutex_unlock(&nbd_index_mutex);
+ printk(KERN_ERR "nbd: couldn't find device at index %d\n",
+ index);
+ return -EINVAL;
+ }
+ if (!refcount_inc_not_zero(&nbd->refs)) {
+ mutex_unlock(&nbd_index_mutex);
+ printk(KERN_ERR "nbd: device at index %d is going down\n",
+ index);
+ return -EINVAL;
+ }
+ mutex_unlock(&nbd_index_mutex);
+ if (!refcount_inc_not_zero(&nbd->config_refs)) {
+ nbd_put(nbd);
+ return 0;
+ }
+ mutex_lock(&nbd->config_lock);
+ nbd_disconnect(nbd);
+ mutex_unlock(&nbd->config_lock);
+ if (test_and_clear_bit(NBD_HAS_CONFIG_REF,
+ &nbd->config->runtime_flags))
+ nbd_config_put(nbd);
+ nbd_config_put(nbd);
+ nbd_put(nbd);
+ return 0;
+}
+
+static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
+{
+ struct nbd_device *nbd = NULL;
+ struct nbd_config *config;
+ int index;
+ int ret = -EINVAL;
+ bool put_dev = false;
+
+ if (!netlink_capable(skb, CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (!info->attrs[NBD_ATTR_INDEX]) {
+ printk(KERN_ERR "nbd: must specify a device to reconfigure\n");
+ return -EINVAL;
+ }
+ index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]);
+ mutex_lock(&nbd_index_mutex);
+ nbd = idr_find(&nbd_index_idr, index);
+ if (!nbd) {
+ mutex_unlock(&nbd_index_mutex);
+ printk(KERN_ERR "nbd: couldn't find a device at index %d\n",
+ index);
+ return -EINVAL;
+ }
+ if (!refcount_inc_not_zero(&nbd->refs)) {
+ mutex_unlock(&nbd_index_mutex);
+ printk(KERN_ERR "nbd: device at index %d is going down\n",
+ index);
+ return -EINVAL;
+ }
+ mutex_unlock(&nbd_index_mutex);
+
+ if (!refcount_inc_not_zero(&nbd->config_refs)) {
+ dev_err(nbd_to_dev(nbd),
+ "not configured, cannot reconfigure\n");
+ nbd_put(nbd);
+ return -EINVAL;
+ }
+
+ mutex_lock(&nbd->config_lock);
+ config = nbd->config;
+ if (!test_bit(NBD_BOUND, &config->runtime_flags) ||
+ !nbd->task_recv) {
+ dev_err(nbd_to_dev(nbd),
+ "not configured, cannot reconfigure\n");
+ goto out;
+ }
+
+ if (info->attrs[NBD_ATTR_TIMEOUT]) {
+ u64 timeout = nla_get_u64(info->attrs[NBD_ATTR_TIMEOUT]);
+ nbd->tag_set.timeout = timeout * HZ;
+ blk_queue_rq_timeout(nbd->disk->queue, timeout * HZ);
+ }
+ if (info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]) {
+ config->dead_conn_timeout =
+ nla_get_u64(info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]);
+ config->dead_conn_timeout *= HZ;
+ }
+ if (info->attrs[NBD_ATTR_CLIENT_FLAGS]) {
+ u64 flags = nla_get_u64(info->attrs[NBD_ATTR_CLIENT_FLAGS]);
+ if (flags & NBD_CFLAG_DESTROY_ON_DISCONNECT) {
+ if (!test_and_set_bit(NBD_DESTROY_ON_DISCONNECT,
+ &config->runtime_flags))
+ put_dev = true;
+ } else {
+ if (test_and_clear_bit(NBD_DESTROY_ON_DISCONNECT,
+ &config->runtime_flags))
+ refcount_inc(&nbd->refs);
+ }
+ }
+
+ if (info->attrs[NBD_ATTR_SOCKETS]) {
+ struct nlattr *attr;
+ int rem, fd;
+
+ nla_for_each_nested(attr, info->attrs[NBD_ATTR_SOCKETS],
+ rem) {
+ struct nlattr *socks[NBD_SOCK_MAX+1];
+
+ if (nla_type(attr) != NBD_SOCK_ITEM) {
+ printk(KERN_ERR "nbd: socks must be embedded in a SOCK_ITEM attr\n");
+ ret = -EINVAL;
+ goto out;
+ }
+ ret = nla_parse_nested(socks, NBD_SOCK_MAX, attr,
+ nbd_sock_policy);
+ if (ret != 0) {
+ printk(KERN_ERR "nbd: error processing sock list\n");
+ ret = -EINVAL;
+ goto out;
+ }
+ if (!socks[NBD_SOCK_FD])
+ continue;
+ fd = (int)nla_get_u32(socks[NBD_SOCK_FD]);
+ ret = nbd_reconnect_socket(nbd, fd);
+ if (ret) {
+ if (ret == -ENOSPC)
+ ret = 0;
+ goto out;
+ }
+ dev_info(nbd_to_dev(nbd), "reconnected socket\n");
+ }
+ }
+out:
+ mutex_unlock(&nbd->config_lock);
+ nbd_config_put(nbd);
+ nbd_put(nbd);
+ if (put_dev)
+ nbd_put(nbd);
+ return ret;
+}
+
+static const struct genl_ops nbd_connect_genl_ops[] = {
+ {
+ .cmd = NBD_CMD_CONNECT,
+ .policy = nbd_attr_policy,
+ .doit = nbd_genl_connect,
+ },
+ {
+ .cmd = NBD_CMD_DISCONNECT,
+ .policy = nbd_attr_policy,
+ .doit = nbd_genl_disconnect,
+ },
+ {
+ .cmd = NBD_CMD_RECONFIGURE,
+ .policy = nbd_attr_policy,
+ .doit = nbd_genl_reconfigure,
+ },
+ {
+ .cmd = NBD_CMD_STATUS,
+ .policy = nbd_attr_policy,
+ .doit = nbd_genl_status,
+ },
+};
+
+static const struct genl_multicast_group nbd_mcast_grps[] = {
+ { .name = NBD_GENL_MCAST_GROUP_NAME, },
+};
+
+static struct genl_family nbd_genl_family __ro_after_init = {
+ .hdrsize = 0,
+ .name = NBD_GENL_FAMILY_NAME,
+ .version = NBD_GENL_VERSION,
+ .module = THIS_MODULE,
+ .ops = nbd_connect_genl_ops,
+ .n_ops = ARRAY_SIZE(nbd_connect_genl_ops),
+ .maxattr = NBD_ATTR_MAX,
+ .mcgrps = nbd_mcast_grps,
+ .n_mcgrps = ARRAY_SIZE(nbd_mcast_grps),
+};
+
+static int populate_nbd_status(struct nbd_device *nbd, struct sk_buff *reply)
+{
+ struct nlattr *dev_opt;
+ u8 connected = 0;
+ int ret;
+
+ /* This is a little racey, but for status it's ok. The
+ * reason we don't take a ref here is because we can't
+ * take a ref in the index == -1 case as we would need
+ * to put under the nbd_index_mutex, which could
+ * deadlock if we are configured to remove ourselves
+ * once we're disconnected.
+ */
+ if (refcount_read(&nbd->config_refs))
+ connected = 1;
+ dev_opt = nla_nest_start(reply, NBD_DEVICE_ITEM);
+ if (!dev_opt)
+ return -EMSGSIZE;
+ ret = nla_put_u32(reply, NBD_DEVICE_INDEX, nbd->index);
+ if (ret)
+ return -EMSGSIZE;
+ ret = nla_put_u8(reply, NBD_DEVICE_CONNECTED,
+ connected);
+ if (ret)
+ return -EMSGSIZE;
+ nla_nest_end(reply, dev_opt);
+ return 0;
+}
+
+static int status_cb(int id, void *ptr, void *data)
+{
+ struct nbd_device *nbd = ptr;
+ return populate_nbd_status(nbd, (struct sk_buff *)data);
+}
+
+static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info)
+{
+ struct nlattr *dev_list;
+ struct sk_buff *reply;
+ void *reply_head;
+ size_t msg_size;
+ int index = -1;
+ int ret = -ENOMEM;
+
+ if (info->attrs[NBD_ATTR_INDEX])
+ index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]);
+
+ mutex_lock(&nbd_index_mutex);
+
+ msg_size = nla_total_size(nla_attr_size(sizeof(u32)) +
+ nla_attr_size(sizeof(u8)));
+ msg_size *= (index == -1) ? nbd_total_devices : 1;
+
+ reply = genlmsg_new(msg_size, GFP_KERNEL);
+ if (!reply)
+ goto out;
+ reply_head = genlmsg_put_reply(reply, info, &nbd_genl_family, 0,
+ NBD_CMD_STATUS);
+ if (!reply_head) {
+ nlmsg_free(reply);
+ goto out;
+ }
+
+ dev_list = nla_nest_start(reply, NBD_ATTR_DEVICE_LIST);
+ if (index == -1) {
+ ret = idr_for_each(&nbd_index_idr, &status_cb, reply);
+ if (ret) {
+ nlmsg_free(reply);
+ goto out;
+ }
+ } else {
+ struct nbd_device *nbd;
+ nbd = idr_find(&nbd_index_idr, index);
+ if (nbd) {
+ ret = populate_nbd_status(nbd, reply);
+ if (ret) {
+ nlmsg_free(reply);
+ goto out;
+ }
+ }
+ }
+ nla_nest_end(reply, dev_list);
+ genlmsg_end(reply, reply_head);
+ genlmsg_reply(reply, info);
+ ret = 0;
+out:
+ mutex_unlock(&nbd_index_mutex);
+ return ret;
+}
+
+static void nbd_connect_reply(struct genl_info *info, int index)
+{
+ struct sk_buff *skb;
+ void *msg_head;
+ int ret;
+
+ skb = genlmsg_new(nla_total_size(sizeof(u32)), GFP_KERNEL);
+ if (!skb)
+ return;
+ msg_head = genlmsg_put_reply(skb, info, &nbd_genl_family, 0,
+ NBD_CMD_CONNECT);
+ if (!msg_head) {
+ nlmsg_free(skb);
+ return;
+ }
+ ret = nla_put_u32(skb, NBD_ATTR_INDEX, index);
+ if (ret) {
+ nlmsg_free(skb);
+ return;
+ }
+ genlmsg_end(skb, msg_head);
+ genlmsg_reply(skb, info);
+}
+
+static void nbd_mcast_index(int index)
+{
+ struct sk_buff *skb;
+ void *msg_head;
+ int ret;
+
+ skb = genlmsg_new(nla_total_size(sizeof(u32)), GFP_KERNEL);
+ if (!skb)
+ return;
+ msg_head = genlmsg_put(skb, 0, 0, &nbd_genl_family, 0,
+ NBD_CMD_LINK_DEAD);
+ if (!msg_head) {
+ nlmsg_free(skb);
+ return;
+ }
+ ret = nla_put_u32(skb, NBD_ATTR_INDEX, index);
+ if (ret) {
+ nlmsg_free(skb);
+ return;
+ }
+ genlmsg_end(skb, msg_head);
+ genlmsg_multicast(&nbd_genl_family, skb, 0, 0, GFP_KERNEL);
+}
+
+static void nbd_dead_link_work(struct work_struct *work)
+{
+ struct link_dead_args *args = container_of(work, struct link_dead_args,
+ work);
+ nbd_mcast_index(args->index);
+ kfree(args);
+}
static int __init nbd_init(void)
{
return -EIO;
}
+ if (genl_register_family(&nbd_genl_family)) {
+ unregister_blkdev(NBD_MAJOR, "nbd");
+ destroy_workqueue(recv_workqueue);
+ return -EINVAL;
+ }
nbd_dbg_init();
mutex_lock(&nbd_index_mutex);
static int nbd_exit_cb(int id, void *ptr, void *data)
{
+ struct list_head *list = (struct list_head *)data;
struct nbd_device *nbd = ptr;
- nbd_dev_remove(nbd);
+
+ list_add_tail(&nbd->list, list);
return 0;
}
static void __exit nbd_cleanup(void)
{
+ struct nbd_device *nbd;
+ LIST_HEAD(del_list);
+
nbd_dbg_close();
- idr_for_each(&nbd_index_idr, &nbd_exit_cb, NULL);
+ mutex_lock(&nbd_index_mutex);
+ idr_for_each(&nbd_index_idr, &nbd_exit_cb, &del_list);
+ mutex_unlock(&nbd_index_mutex);
+
+ while (!list_empty(&del_list)) {
+ nbd = list_first_entry(&del_list, struct nbd_device, list);
+ list_del_init(&nbd->list);
+ if (refcount_read(&nbd->refs) != 1)
+ printk(KERN_ERR "nbd: possibly leaking a device\n");
+ nbd_put(nbd);
+ }
+
idr_destroy(&nbd_index_idr);
+ genl_unregister_family(&nbd_genl_family);
destroy_workqueue(recv_workqueue);
unregister_blkdev(NBD_MAJOR, "nbd");
}
module_param(use_lightnvm, bool, S_IRUGO);
MODULE_PARM_DESC(use_lightnvm, "Register as a LightNVM device");
+static bool blocking;
+module_param(blocking, bool, S_IRUGO);
+MODULE_PARM_DESC(blocking, "Register as a blocking blk-mq driver device");
+
static int irqmode = NULL_IRQ_SOFTIRQ;
static int null_set_irqmode(const char *str, const struct kernel_param *kp)
case NULL_IRQ_SOFTIRQ:
switch (queue_mode) {
case NULL_Q_MQ:
- blk_mq_complete_request(cmd->rq, cmd->rq->errors);
+ blk_mq_complete_request(cmd->rq);
break;
case NULL_Q_RQ:
blk_complete_request(cmd->rq);
{
struct nullb_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
+ might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING);
+
if (irqmode == NULL_IRQ_TIMER) {
hrtimer_init(&cmd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
cmd->timer.function = null_cmd_timer_expired;
return 0;
}
-static struct blk_mq_ops null_mq_ops = {
+static const struct blk_mq_ops null_mq_ops = {
.queue_rq = null_queue_rq,
.init_hctx = null_init_hctx,
.complete = null_softirq_done_fn,
if (IS_ERR(rq))
return -ENOMEM;
- rq->__sector = bio->bi_iter.bi_sector;
- rq->ioprio = bio_prio(bio);
-
- if (bio_has_data(bio))
- rq->nr_phys_segments = bio_phys_segments(q, bio);
-
- rq->__data_len = bio->bi_iter.bi_size;
- rq->bio = rq->biotail = bio;
+ blk_init_request_from_bio(rq, bio);
rq->end_io_data = rqd;
nullb->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
nullb->tag_set.driver_data = nullb;
+ if (blocking)
+ nullb->tag_set.flags |= BLK_MQ_F_BLOCKING;
+
rv = blk_mq_alloc_tag_set(&nullb->tag_set);
if (rv)
goto out_cleanup_queues;
+++ /dev/null
-
-/*
- osdblk.c -- Export a single SCSI OSD object as a Linux block device
-
-
- Copyright 2009 Red Hat, Inc.
-
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation.
-
- This program is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY; without even the implied warranty of
- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- GNU General Public License for more details.
-
- You should have received a copy of the GNU General Public License
- along with this program; see the file COPYING. If not, write to
- the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
-
-
- Instructions for use
- --------------------
-
- 1) Map a Linux block device to an existing OSD object.
-
- In this example, we will use partition id 1234, object id 5678,
- OSD device /dev/osd1.
-
- $ echo "1234 5678 /dev/osd1" > /sys/class/osdblk/add
-
-
- 2) List all active blkdev<->object mappings.
-
- In this example, we have performed step #1 twice, creating two blkdevs,
- mapped to two separate OSD objects.
-
- $ cat /sys/class/osdblk/list
- 0 174 1234 5678 /dev/osd1
- 1 179 1994 897123 /dev/osd0
-
- The columns, in order, are:
- - blkdev unique id
- - blkdev assigned major
- - OSD object partition id
- - OSD object id
- - OSD device
-
-
- 3) Remove an active blkdev<->object mapping.
-
- In this example, we remove the mapping with blkdev unique id 1.
-
- $ echo 1 > /sys/class/osdblk/remove
-
-
- NOTE: The actual creation and deletion of OSD objects is outside the scope
- of this driver.
-
- */
-
-#include <linux/kernel.h>
-#include <linux/device.h>
-#include <linux/module.h>
-#include <linux/fs.h>
-#include <linux/slab.h>
-#include <scsi/osd_initiator.h>
-#include <scsi/osd_attributes.h>
-#include <scsi/osd_sec.h>
-#include <scsi/scsi_device.h>
-
-#define DRV_NAME "osdblk"
-#define PFX DRV_NAME ": "
-
-/* #define _OSDBLK_DEBUG */
-#ifdef _OSDBLK_DEBUG
-#define OSDBLK_DEBUG(fmt, a...) \
- printk(KERN_NOTICE "osdblk @%s:%d: " fmt, __func__, __LINE__, ##a)
-#else
-#define OSDBLK_DEBUG(fmt, a...) \
- do { if (0) printk(fmt, ##a); } while (0)
-#endif
-
-MODULE_AUTHOR("Jeff Garzik <jeff@garzik.org>");
-MODULE_DESCRIPTION("block device inside an OSD object osdblk.ko");
-MODULE_LICENSE("GPL");
-
-struct osdblk_device;
-
-enum {
- OSDBLK_MINORS_PER_MAJOR = 256, /* max minors per blkdev */
- OSDBLK_MAX_REQ = 32, /* max parallel requests */
- OSDBLK_OP_TIMEOUT = 4 * 60, /* sync OSD req timeout */
-};
-
-struct osdblk_request {
- struct request *rq; /* blk layer request */
- struct bio *bio; /* cloned bio */
- struct osdblk_device *osdev; /* associated blkdev */
-};
-
-struct osdblk_device {
- int id; /* blkdev unique id */
-
- int major; /* blkdev assigned major */
- struct gendisk *disk; /* blkdev's gendisk and rq */
- struct request_queue *q;
-
- struct osd_dev *osd; /* associated OSD */
-
- char name[32]; /* blkdev name, e.g. osdblk34 */
-
- spinlock_t lock; /* queue lock */
-
- struct osd_obj_id obj; /* OSD partition, obj id */
- uint8_t obj_cred[OSD_CAP_LEN]; /* OSD cred */
-
- struct osdblk_request req[OSDBLK_MAX_REQ]; /* request table */
-
- struct list_head node;
-
- char osd_path[0]; /* OSD device path */
-};
-
-static struct class *class_osdblk; /* /sys/class/osdblk */
-static DEFINE_MUTEX(ctl_mutex); /* Serialize open/close/setup/teardown */
-static LIST_HEAD(osdblkdev_list);
-
-static const struct block_device_operations osdblk_bd_ops = {
- .owner = THIS_MODULE,
-};
-
-static const struct osd_attr g_attr_logical_length = ATTR_DEF(
- OSD_APAGE_OBJECT_INFORMATION, OSD_ATTR_OI_LOGICAL_LENGTH, 8);
-
-static void osdblk_make_credential(u8 cred_a[OSD_CAP_LEN],
- const struct osd_obj_id *obj)
-{
- osd_sec_init_nosec_doall_caps(cred_a, obj, false, true);
-}
-
-/* copied from exofs; move to libosd? */
-/*
- * Perform a synchronous OSD operation. copied from exofs; move to libosd?
- */
-static int osd_sync_op(struct osd_request *or, int timeout, uint8_t *credential)
-{
- int ret;
-
- or->timeout = timeout;
- ret = osd_finalize_request(or, 0, credential, NULL);
- if (ret)
- return ret;
-
- ret = osd_execute_request(or);
-
- /* osd_req_decode_sense(or, ret); */
- return ret;
-}
-
-/*
- * Perform an asynchronous OSD operation. copied from exofs; move to libosd?
- */
-static int osd_async_op(struct osd_request *or, osd_req_done_fn *async_done,
- void *caller_context, u8 *cred)
-{
- int ret;
-
- ret = osd_finalize_request(or, 0, cred, NULL);
- if (ret)
- return ret;
-
- ret = osd_execute_request_async(or, async_done, caller_context);
-
- return ret;
-}
-
-/* copied from exofs; move to libosd? */
-static int extract_attr_from_req(struct osd_request *or, struct osd_attr *attr)
-{
- struct osd_attr cur_attr = {.attr_page = 0}; /* start with zeros */
- void *iter = NULL;
- int nelem;
-
- do {
- nelem = 1;
- osd_req_decode_get_attr_list(or, &cur_attr, &nelem, &iter);
- if ((cur_attr.attr_page == attr->attr_page) &&
- (cur_attr.attr_id == attr->attr_id)) {
- attr->len = cur_attr.len;
- attr->val_ptr = cur_attr.val_ptr;
- return 0;
- }
- } while (iter);
-
- return -EIO;
-}
-
-static int osdblk_get_obj_size(struct osdblk_device *osdev, u64 *size_out)
-{
- struct osd_request *or;
- struct osd_attr attr;
- int ret;
-
- /* start request */
- or = osd_start_request(osdev->osd, GFP_KERNEL);
- if (!or)
- return -ENOMEM;
-
- /* create a get-attributes(length) request */
- osd_req_get_attributes(or, &osdev->obj);
-
- osd_req_add_get_attr_list(or, &g_attr_logical_length, 1);
-
- /* execute op synchronously */
- ret = osd_sync_op(or, OSDBLK_OP_TIMEOUT, osdev->obj_cred);
- if (ret)
- goto out;
-
- /* extract length from returned attribute info */
- attr = g_attr_logical_length;
- ret = extract_attr_from_req(or, &attr);
- if (ret)
- goto out;
-
- *size_out = get_unaligned_be64(attr.val_ptr);
-
-out:
- osd_end_request(or);
- return ret;
-
-}
-
-static void osdblk_osd_complete(struct osd_request *or, void *private)
-{
- struct osdblk_request *orq = private;
- struct osd_sense_info osi;
- int ret = osd_req_decode_sense(or, &osi);
-
- if (ret) {
- ret = -EIO;
- OSDBLK_DEBUG("osdblk_osd_complete with err=%d\n", ret);
- }
-
- /* complete OSD request */
- osd_end_request(or);
-
- /* complete request passed to osdblk by block layer */
- __blk_end_request_all(orq->rq, ret);
-}
-
-static void bio_chain_put(struct bio *chain)
-{
- struct bio *tmp;
-
- while (chain) {
- tmp = chain;
- chain = chain->bi_next;
-
- bio_put(tmp);
- }
-}
-
-static struct bio *bio_chain_clone(struct bio *old_chain, gfp_t gfpmask)
-{
- struct bio *tmp, *new_chain = NULL, *tail = NULL;
-
- while (old_chain) {
- tmp = bio_clone_kmalloc(old_chain, gfpmask);
- if (!tmp)
- goto err_out;
-
- tmp->bi_bdev = NULL;
- gfpmask &= ~__GFP_DIRECT_RECLAIM;
- tmp->bi_next = NULL;
-
- if (!new_chain)
- new_chain = tail = tmp;
- else {
- tail->bi_next = tmp;
- tail = tmp;
- }
-
- old_chain = old_chain->bi_next;
- }
-
- return new_chain;
-
-err_out:
- OSDBLK_DEBUG("bio_chain_clone with err\n");
- bio_chain_put(new_chain);
- return NULL;
-}
-
-static void osdblk_rq_fn(struct request_queue *q)
-{
- struct osdblk_device *osdev = q->queuedata;
-
- while (1) {
- struct request *rq;
- struct osdblk_request *orq;
- struct osd_request *or;
- struct bio *bio;
- bool do_write, do_flush;
-
- /* peek at request from block layer */
- rq = blk_fetch_request(q);
- if (!rq)
- break;
-
- /* deduce our operation (read, write, flush) */
- /* I wish the block layer simplified cmd_type/cmd_flags/cmd[]
- * into a clearly defined set of RPC commands:
- * read, write, flush, scsi command, power mgmt req,
- * driver-specific, etc.
- */
-
- do_flush = (req_op(rq) == REQ_OP_FLUSH);
- do_write = (rq_data_dir(rq) == WRITE);
-
- if (!do_flush) { /* osd_flush does not use a bio */
- /* a bio clone to be passed down to OSD request */
- bio = bio_chain_clone(rq->bio, GFP_ATOMIC);
- if (!bio)
- break;
- } else
- bio = NULL;
-
- /* alloc internal OSD request, for OSD command execution */
- or = osd_start_request(osdev->osd, GFP_ATOMIC);
- if (!or) {
- bio_chain_put(bio);
- OSDBLK_DEBUG("osd_start_request with err\n");
- break;
- }
-
- orq = &osdev->req[rq->tag];
- orq->rq = rq;
- orq->bio = bio;
- orq->osdev = osdev;
-
- /* init OSD command: flush, write or read */
- if (do_flush)
- osd_req_flush_object(or, &osdev->obj,
- OSD_CDB_FLUSH_ALL, 0, 0);
- else if (do_write)
- osd_req_write(or, &osdev->obj, blk_rq_pos(rq) * 512ULL,
- bio, blk_rq_bytes(rq));
- else
- osd_req_read(or, &osdev->obj, blk_rq_pos(rq) * 512ULL,
- bio, blk_rq_bytes(rq));
-
- OSDBLK_DEBUG("%s 0x%x bytes at 0x%llx\n",
- do_flush ? "flush" : do_write ?
- "write" : "read", blk_rq_bytes(rq),
- blk_rq_pos(rq) * 512ULL);
-
- /* begin OSD command execution */
- if (osd_async_op(or, osdblk_osd_complete, orq,
- osdev->obj_cred)) {
- osd_end_request(or);
- blk_requeue_request(q, rq);
- bio_chain_put(bio);
- OSDBLK_DEBUG("osd_execute_request_async with err\n");
- break;
- }
-
- /* remove the special 'flush' marker, now that the command
- * is executing
- */
- rq->special = NULL;
- }
-}
-
-static void osdblk_free_disk(struct osdblk_device *osdev)
-{
- struct gendisk *disk = osdev->disk;
-
- if (!disk)
- return;
-
- if (disk->flags & GENHD_FL_UP)
- del_gendisk(disk);
- if (disk->queue)
- blk_cleanup_queue(disk->queue);
- put_disk(disk);
-}
-
-static int osdblk_init_disk(struct osdblk_device *osdev)
-{
- struct gendisk *disk;
- struct request_queue *q;
- int rc;
- u64 obj_size = 0;
-
- /* contact OSD, request size info about the object being mapped */
- rc = osdblk_get_obj_size(osdev, &obj_size);
- if (rc)
- return rc;
-
- /* create gendisk info */
- disk = alloc_disk(OSDBLK_MINORS_PER_MAJOR);
- if (!disk)
- return -ENOMEM;
-
- sprintf(disk->disk_name, DRV_NAME "%d", osdev->id);
- disk->major = osdev->major;
- disk->first_minor = 0;
- disk->fops = &osdblk_bd_ops;
- disk->private_data = osdev;
-
- /* init rq */
- q = blk_init_queue(osdblk_rq_fn, &osdev->lock);
- if (!q) {
- put_disk(disk);
- return -ENOMEM;
- }
-
- /* switch queue to TCQ mode; allocate tag map */
- rc = blk_queue_init_tags(q, OSDBLK_MAX_REQ, NULL, BLK_TAG_ALLOC_FIFO);
- if (rc) {
- blk_cleanup_queue(q);
- put_disk(disk);
- return rc;
- }
-
- /* Set our limits to the lower device limits, because osdblk cannot
- * sleep when allocating a lower-request and therefore cannot be
- * bouncing.
- */
- blk_queue_stack_limits(q, osd_request_queue(osdev->osd));
-
- blk_queue_prep_rq(q, blk_queue_start_tag);
- blk_queue_write_cache(q, true, false);
-
- disk->queue = q;
-
- q->queuedata = osdev;
-
- osdev->disk = disk;
- osdev->q = q;
-
- /* finally, announce the disk to the world */
- set_capacity(disk, obj_size / 512ULL);
- add_disk(disk);
-
- printk(KERN_INFO "%s: Added of size 0x%llx\n",
- disk->disk_name, (unsigned long long)obj_size);
-
- return 0;
-}
-
-/********************************************************************
- * /sys/class/osdblk/
- * add map OSD object to blkdev
- * remove unmap OSD object
- * list show mappings
- *******************************************************************/
-
-static void class_osdblk_release(struct class *cls)
-{
- kfree(cls);
-}
-
-static ssize_t class_osdblk_list(struct class *c,
- struct class_attribute *attr,
- char *data)
-{
- int n = 0;
- struct list_head *tmp;
-
- mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
-
- list_for_each(tmp, &osdblkdev_list) {
- struct osdblk_device *osdev;
-
- osdev = list_entry(tmp, struct osdblk_device, node);
-
- n += sprintf(data+n, "%d %d %llu %llu %s\n",
- osdev->id,
- osdev->major,
- osdev->obj.partition,
- osdev->obj.id,
- osdev->osd_path);
- }
-
- mutex_unlock(&ctl_mutex);
- return n;
-}
-
-static ssize_t class_osdblk_add(struct class *c,
- struct class_attribute *attr,
- const char *buf, size_t count)
-{
- struct osdblk_device *osdev;
- ssize_t rc;
- int irc, new_id = 0;
- struct list_head *tmp;
-
- if (!try_module_get(THIS_MODULE))
- return -ENODEV;
-
- /* new osdblk_device object */
- osdev = kzalloc(sizeof(*osdev) + strlen(buf) + 1, GFP_KERNEL);
- if (!osdev) {
- rc = -ENOMEM;
- goto err_out_mod;
- }
-
- /* static osdblk_device initialization */
- spin_lock_init(&osdev->lock);
- INIT_LIST_HEAD(&osdev->node);
-
- /* generate unique id: find highest unique id, add one */
-
- mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
-
- list_for_each(tmp, &osdblkdev_list) {
- struct osdblk_device *osdev;
-
- osdev = list_entry(tmp, struct osdblk_device, node);
- if (osdev->id > new_id)
- new_id = osdev->id + 1;
- }
-
- osdev->id = new_id;
-
- /* add to global list */
- list_add_tail(&osdev->node, &osdblkdev_list);
-
- mutex_unlock(&ctl_mutex);
-
- /* parse add command */
- if (sscanf(buf, "%llu %llu %s", &osdev->obj.partition, &osdev->obj.id,
- osdev->osd_path) != 3) {
- rc = -EINVAL;
- goto err_out_slot;
- }
-
- /* initialize rest of new object */
- sprintf(osdev->name, DRV_NAME "%d", osdev->id);
-
- /* contact requested OSD */
- osdev->osd = osduld_path_lookup(osdev->osd_path);
- if (IS_ERR(osdev->osd)) {
- rc = PTR_ERR(osdev->osd);
- goto err_out_slot;
- }
-
- /* build OSD credential */
- osdblk_make_credential(osdev->obj_cred, &osdev->obj);
-
- /* register our block device */
- irc = register_blkdev(0, osdev->name);
- if (irc < 0) {
- rc = irc;
- goto err_out_osd;
- }
-
- osdev->major = irc;
-
- /* set up and announce blkdev mapping */
- rc = osdblk_init_disk(osdev);
- if (rc)
- goto err_out_blkdev;
-
- return count;
-
-err_out_blkdev:
- unregister_blkdev(osdev->major, osdev->name);
-err_out_osd:
- osduld_put_device(osdev->osd);
-err_out_slot:
- mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
- list_del_init(&osdev->node);
- mutex_unlock(&ctl_mutex);
-
- kfree(osdev);
-err_out_mod:
- OSDBLK_DEBUG("Error adding device %s\n", buf);
- module_put(THIS_MODULE);
- return rc;
-}
-
-static ssize_t class_osdblk_remove(struct class *c,
- struct class_attribute *attr,
- const char *buf,
- size_t count)
-{
- struct osdblk_device *osdev = NULL;
- int target_id, rc;
- unsigned long ul;
- struct list_head *tmp;
-
- rc = kstrtoul(buf, 10, &ul);
- if (rc)
- return rc;
-
- /* convert to int; abort if we lost anything in the conversion */
- target_id = (int) ul;
- if (target_id != ul)
- return -EINVAL;
-
- /* remove object from list immediately */
- mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
-
- list_for_each(tmp, &osdblkdev_list) {
- osdev = list_entry(tmp, struct osdblk_device, node);
- if (osdev->id == target_id) {
- list_del_init(&osdev->node);
- break;
- }
- osdev = NULL;
- }
-
- mutex_unlock(&ctl_mutex);
-
- if (!osdev)
- return -ENOENT;
-
- /* clean up and free blkdev and associated OSD connection */
- osdblk_free_disk(osdev);
- unregister_blkdev(osdev->major, osdev->name);
- osduld_put_device(osdev->osd);
- kfree(osdev);
-
- /* release module ref */
- module_put(THIS_MODULE);
-
- return count;
-}
-
-static struct class_attribute class_osdblk_attrs[] = {
- __ATTR(add, 0200, NULL, class_osdblk_add),
- __ATTR(remove, 0200, NULL, class_osdblk_remove),
- __ATTR(list, 0444, class_osdblk_list, NULL),
- __ATTR_NULL
-};
-
-static int osdblk_sysfs_init(void)
-{
- int ret = 0;
-
- /*
- * create control files in sysfs
- * /sys/class/osdblk/...
- */
- class_osdblk = kzalloc(sizeof(*class_osdblk), GFP_KERNEL);
- if (!class_osdblk)
- return -ENOMEM;
-
- class_osdblk->name = DRV_NAME;
- class_osdblk->owner = THIS_MODULE;
- class_osdblk->class_release = class_osdblk_release;
- class_osdblk->class_attrs = class_osdblk_attrs;
-
- ret = class_register(class_osdblk);
- if (ret) {
- kfree(class_osdblk);
- class_osdblk = NULL;
- printk(PFX "failed to create class osdblk\n");
- return ret;
- }
-
- return 0;
-}
-
-static void osdblk_sysfs_cleanup(void)
-{
- if (class_osdblk)
- class_destroy(class_osdblk);
- class_osdblk = NULL;
-}
-
-static int __init osdblk_init(void)
-{
- int rc;
-
- rc = osdblk_sysfs_init();
- if (rc)
- return rc;
-
- return 0;
-}
-
-static void __exit osdblk_exit(void)
-{
- osdblk_sysfs_cleanup();
-}
-
-module_init(osdblk_init);
-module_exit(osdblk_exit);
-
struct gendisk *disk = alloc_disk(1);
if (!disk)
continue;
+ disk->queue = blk_init_queue(do_pcd_request, &pcd_lock);
+ if (!disk->queue) {
+ put_disk(disk);
+ continue;
+ }
cd->disk = disk;
cd->pi = &cd->pia;
cd->present = 0;
}
/* I/O request processing */
-static struct request_queue *pcd_queue;
+static int pcd_queue;
+
+static int set_next_request(void)
+{
+ struct pcd_unit *cd;
+ struct request_queue *q;
+ int old_pos = pcd_queue;
+
+ do {
+ cd = &pcd[pcd_queue];
+ q = cd->present ? cd->disk->queue : NULL;
+ if (++pcd_queue == PCD_UNITS)
+ pcd_queue = 0;
+ if (q) {
+ pcd_req = blk_fetch_request(q);
+ if (pcd_req)
+ break;
+ }
+ } while (pcd_queue != old_pos);
+
+ return pcd_req != NULL;
+}
-static void do_pcd_request(struct request_queue * q)
+static void pcd_request(void)
{
if (pcd_busy)
return;
while (1) {
- if (!pcd_req) {
- pcd_req = blk_fetch_request(q);
- if (!pcd_req)
- return;
- }
+ if (!pcd_req && !set_next_request())
+ return;
if (rq_data_dir(pcd_req) == READ) {
struct pcd_unit *cd = pcd_req->rq_disk->private_data;
}
}
+static void do_pcd_request(struct request_queue *q)
+{
+ pcd_request();
+}
+
static inline void next_request(int err)
{
unsigned long saved_flags;
if (!__blk_end_request_cur(pcd_req, err))
pcd_req = NULL;
pcd_busy = 0;
- do_pcd_request(pcd_queue);
+ pcd_request();
spin_unlock_irqrestore(&pcd_lock, saved_flags);
}
do_pcd_read();
spin_lock_irqsave(&pcd_lock, saved_flags);
- do_pcd_request(pcd_queue);
+ pcd_request();
spin_unlock_irqrestore(&pcd_lock, saved_flags);
}
return -EBUSY;
}
- pcd_queue = blk_init_queue(do_pcd_request, &pcd_lock);
- if (!pcd_queue) {
- unregister_blkdev(major, name);
- for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++)
- put_disk(cd->disk);
- return -ENOMEM;
- }
-
for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
if (cd->present) {
register_cdrom(&cd->info);
cd->disk->private_data = cd;
- cd->disk->queue = pcd_queue;
add_disk(cd->disk);
}
}
pi_release(cd->pi);
unregister_cdrom(&cd->info);
}
+ blk_cleanup_queue(cd->disk->queue);
put_disk(cd->disk);
}
- blk_cleanup_queue(pcd_queue);
unregister_blkdev(major, name);
pi_unregister_driver(par_drv);
}
static enum action do_pd_read_drq(void);
static enum action do_pd_write_done(void);
-static struct request_queue *pd_queue;
+static int pd_queue;
static int pd_claimed;
static struct pd_unit *pd_current; /* current request's drive */
static PIA *pi_current; /* current request's PIA */
+static int set_next_request(void)
+{
+ struct gendisk *disk;
+ struct request_queue *q;
+ int old_pos = pd_queue;
+
+ do {
+ disk = pd[pd_queue].gd;
+ q = disk ? disk->queue : NULL;
+ if (++pd_queue == PD_UNITS)
+ pd_queue = 0;
+ if (q) {
+ pd_req = blk_fetch_request(q);
+ if (pd_req)
+ break;
+ }
+ } while (pd_queue != old_pos);
+
+ return pd_req != NULL;
+}
+
static void run_fsm(void)
{
while (1) {
spin_lock_irqsave(&pd_lock, saved_flags);
if (!__blk_end_request_cur(pd_req,
res == Ok ? 0 : -EIO)) {
- pd_req = blk_fetch_request(pd_queue);
- if (!pd_req)
+ if (!set_next_request())
stop = 1;
}
spin_unlock_irqrestore(&pd_lock, saved_flags);
enum action (*func)(struct pd_unit *disk))
{
struct request *rq;
- int err = 0;
rq = blk_get_request(disk->gd->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
if (IS_ERR(rq))
return PTR_ERR(rq);
rq->special = func;
-
- err = blk_execute_rq(disk->gd->queue, disk->gd, rq, 0);
-
+ blk_execute_rq(disk->gd->queue, disk->gd, rq, 0);
blk_put_request(rq);
- return err;
+ return 0;
}
/* kernel glue structures */
p->first_minor = (disk - pd) << PD_BITS;
disk->gd = p;
p->private_data = disk;
- p->queue = pd_queue;
+ p->queue = blk_init_queue(do_pd_request, &pd_lock);
+ if (!p->queue) {
+ disk->gd = NULL;
+ put_disk(p);
+ return;
+ }
+ blk_queue_max_hw_sectors(p->queue, cluster);
if (disk->drive == -1) {
for (disk->drive = 0; disk->drive <= 1; disk->drive++)
if (disable)
goto out1;
- pd_queue = blk_init_queue(do_pd_request, &pd_lock);
- if (!pd_queue)
- goto out1;
-
- blk_queue_max_hw_sectors(pd_queue, cluster);
-
if (register_blkdev(major, name))
- goto out2;
+ goto out1;
printk("%s: %s version %s, major %d, cluster %d, nice %d\n",
name, name, PD_VERSION, major, cluster, nice);
if (!pd_detect())
- goto out3;
+ goto out2;
return 0;
-out3:
- unregister_blkdev(major, name);
out2:
- blk_cleanup_queue(pd_queue);
+ unregister_blkdev(major, name);
out1:
return -ENODEV;
}
if (p) {
disk->gd = NULL;
del_gendisk(p);
+ blk_cleanup_queue(p->queue);
put_disk(p);
pi_release(disk->pi);
}
}
- blk_cleanup_queue(pd_queue);
}
MODULE_LICENSE("GPL");
struct gendisk *disk = alloc_disk(1);
if (!disk)
continue;
+ disk->queue = blk_init_queue(do_pf_request, &pf_spin_lock);
+ if (!disk->queue) {
+ put_disk(disk);
+ return;
+ }
+ blk_queue_max_segments(disk->queue, cluster);
pf->disk = disk;
pf->pi = &pf->pia;
pf->media_status = PF_NM;
return (((status_reg(pf_current) & (STAT_BUSY | pf_mask)) == pf_mask));
}
-static struct request_queue *pf_queue;
+static int pf_queue;
+
+static int set_next_request(void)
+{
+ struct pf_unit *pf;
+ struct request_queue *q;
+ int old_pos = pf_queue;
+
+ do {
+ pf = &units[pf_queue];
+ q = pf->present ? pf->disk->queue : NULL;
+ if (++pf_queue == PF_UNITS)
+ pf_queue = 0;
+ if (q) {
+ pf_req = blk_fetch_request(q);
+ if (pf_req)
+ break;
+ }
+ } while (pf_queue != old_pos);
+
+ return pf_req != NULL;
+}
static void pf_end_request(int err)
{
pf_req = NULL;
}
-static void do_pf_request(struct request_queue * q)
+static void pf_request(void)
{
if (pf_busy)
return;
repeat:
- if (!pf_req) {
- pf_req = blk_fetch_request(q);
- if (!pf_req)
- return;
- }
+ if (!pf_req && !set_next_request())
+ return;
pf_current = pf_req->rq_disk->private_data;
pf_block = blk_rq_pos(pf_req);
}
}
+static void do_pf_request(struct request_queue *q)
+{
+ pf_request();
+}
+
static int pf_next_buf(void)
{
unsigned long saved_flags;
spin_lock_irqsave(&pf_spin_lock, saved_flags);
pf_end_request(err);
pf_busy = 0;
- do_pf_request(pf_queue);
+ pf_request();
spin_unlock_irqrestore(&pf_spin_lock, saved_flags);
}
put_disk(pf->disk);
return -EBUSY;
}
- pf_queue = blk_init_queue(do_pf_request, &pf_spin_lock);
- if (!pf_queue) {
- unregister_blkdev(major, name);
- for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++)
- put_disk(pf->disk);
- return -ENOMEM;
- }
-
- blk_queue_max_segments(pf_queue, cluster);
for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) {
struct gendisk *disk = pf->disk;
if (!pf->present)
continue;
disk->private_data = pf;
- disk->queue = pf_queue;
add_disk(disk);
}
return 0;
if (!pf->present)
continue;
del_gendisk(pf->disk);
+ blk_cleanup_queue(pf->disk->queue);
put_disk(pf->disk);
pi_release(pf->pi);
}
- blk_cleanup_queue(pf_queue);
}
MODULE_LICENSE("GPL");
rq->rq_flags |= RQF_QUIET;
blk_execute_rq(rq->q, pd->bdev->bd_disk, rq, 0);
- if (rq->errors)
+ if (scsi_req(rq)->result)
ret = -EIO;
out:
blk_put_request(rq);
return 0;
}
-static struct blk_mq_ops rbd_mq_ops = {
+static const struct blk_mq_ops rbd_mq_ops = {
.queue_rq = rbd_queue_rq,
.init_request = rbd_init_request,
};
q->limits.discard_granularity = segment_size;
q->limits.discard_alignment = segment_size;
blk_queue_max_discard_sectors(q, segment_size / SECTOR_SIZE);
- q->limits.discard_zeroes_data = 1;
if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC))
q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
RSXX_HW_BLK_SIZE >> 9);
card->queue->limits.discard_granularity = RSXX_HW_BLK_SIZE;
card->queue->limits.discard_alignment = RSXX_HW_BLK_SIZE;
- card->queue->limits.discard_zeroes_data = 1;
}
card->queue->queuedata = card;
struct swim_priv {
struct swim __iomem *base;
spinlock_t lock;
- struct request_queue *queue;
+ int fdc_queue;
int floppy_count;
struct floppy_state unit[FD_MAX_UNIT];
};
return 0;
}
-static void redo_fd_request(struct request_queue *q)
+static struct request *swim_next_request(struct swim_priv *swd)
{
+ struct request_queue *q;
+ struct request *rq;
+ int old_pos = swd->fdc_queue;
+
+ do {
+ q = swd->unit[swd->fdc_queue].disk->queue;
+ if (++swd->fdc_queue == swd->floppy_count)
+ swd->fdc_queue = 0;
+ if (q) {
+ rq = blk_fetch_request(q);
+ if (rq)
+ return rq;
+ }
+ } while (swd->fdc_queue != old_pos);
+
+ return NULL;
+}
+
+static void do_fd_request(struct request_queue *q)
+{
+ struct swim_priv *swd = q->queuedata;
struct request *req;
struct floppy_state *fs;
- req = blk_fetch_request(q);
+ req = swim_next_request(swd);
while (req) {
int err = -EIO;
}
done:
if (!__blk_end_request_cur(req, err))
- req = blk_fetch_request(q);
+ req = swim_next_request(swd);
}
}
-static void do_fd_request(struct request_queue *q)
-{
- redo_fd_request(q);
-}
-
static struct floppy_struct floppy_type[4] = {
{ 0, 0, 0, 0, 0, 0x00, 0x00, 0x00, 0x00, NULL }, /* no testing */
{ 720, 9, 1, 80, 0, 0x2A, 0x02, 0xDF, 0x50, NULL }, /* 360KB SS 3.5"*/
return -EBUSY;
}
+ spin_lock_init(&swd->lock);
+
for (drive = 0; drive < swd->floppy_count; drive++) {
swd->unit[drive].disk = alloc_disk(1);
if (swd->unit[drive].disk == NULL) {
err = -ENOMEM;
goto exit_put_disks;
}
+ swd->unit[drive].disk->queue = blk_init_queue(do_fd_request,
+ &swd->lock);
+ if (!swd->unit[drive].disk->queue) {
+ err = -ENOMEM;
+ put_disk(swd->unit[drive].disk);
+ goto exit_put_disks;
+ }
+ swd->unit[drive].disk->queue->queuedata = swd;
swd->unit[drive].swd = swd;
}
- spin_lock_init(&swd->lock);
- swd->queue = blk_init_queue(do_fd_request, &swd->lock);
- if (!swd->queue) {
- err = -ENOMEM;
- goto exit_put_disks;
- }
-
for (drive = 0; drive < swd->floppy_count; drive++) {
swd->unit[drive].disk->flags = GENHD_FL_REMOVABLE;
swd->unit[drive].disk->major = FLOPPY_MAJOR;
sprintf(swd->unit[drive].disk->disk_name, "fd%d", drive);
swd->unit[drive].disk->fops = &floppy_fops;
swd->unit[drive].disk->private_data = &swd->unit[drive];
- swd->unit[drive].disk->queue = swd->queue;
set_capacity(swd->unit[drive].disk, 2880);
add_disk(swd->unit[drive].disk);
}
for (drive = 0; drive < swd->floppy_count; drive++) {
del_gendisk(swd->unit[drive].disk);
+ blk_cleanup_queue(swd->unit[drive].disk->queue);
put_disk(swd->unit[drive].disk);
}
unregister_blkdev(FLOPPY_MAJOR, "fd");
- blk_cleanup_queue(swd->queue);
-
/* eject floppies */
for (drive = 0; drive < swd->floppy_count; drive++)
req->rq_disk->disk_name, req->cmd,
(long)blk_rq_pos(req), blk_rq_sectors(req),
bio_data(req->bio));
- swim3_dbg(" errors=%d current_nr_sectors=%u\n",
- req->errors, blk_rq_cur_sectors(req));
+ swim3_dbg(" current_nr_sectors=%u\n",
+ blk_rq_cur_sectors(req));
#endif
if (blk_rq_pos(req) >= fs->total_secs) {
return virtqueue_add_sgs(vq, sgs, num_out, num_in, vbr, GFP_ATOMIC);
}
-static inline void virtblk_scsi_reques_done(struct request *req)
+static inline void virtblk_scsi_request_done(struct request *req)
{
struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
struct virtio_blk *vblk = req->q->queuedata;
sreq->resid_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.residual);
sreq->sense_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.sense_len);
- req->errors = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.errors);
+ sreq->result = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.errors);
}
static int virtblk_ioctl(struct block_device *bdev, fmode_t mode,
{
return -EIO;
}
-static inline void virtblk_scsi_reques_done(struct request *req)
+static inline void virtblk_scsi_request_done(struct request *req)
{
}
#define virtblk_ioctl NULL
static inline void virtblk_request_done(struct request *req)
{
struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
- int error = virtblk_result(vbr);
switch (req_op(req)) {
case REQ_OP_SCSI_IN:
case REQ_OP_SCSI_OUT:
- virtblk_scsi_reques_done(req);
- break;
- case REQ_OP_DRV_IN:
- req->errors = (error != 0);
+ virtblk_scsi_request_done(req);
break;
}
- blk_mq_end_request(req, error);
+ blk_mq_end_request(req, virtblk_result(vbr));
}
static void virtblk_done(struct virtqueue *vq)
while ((vbr = virtqueue_get_buf(vblk->vqs[qid].vq, &len)) != NULL) {
struct request *req = blk_mq_rq_from_pdu(vbr);
- blk_mq_complete_request(req, req->errors);
+ blk_mq_complete_request(req);
req_done = true;
}
if (unlikely(virtqueue_is_broken(vq)))
if (err)
goto out;
- err = blk_execute_rq(vblk->disk->queue, vblk->disk, req, false);
+ blk_execute_rq(vblk->disk->queue, vblk->disk, req, false);
+ err = virtblk_result(blk_mq_rq_to_pdu(req));
out:
blk_put_request(req);
return err;
return blk_mq_virtio_map_queues(set, vblk->vdev, 0);
}
-static struct blk_mq_ops virtio_mq_ops = {
+static const struct blk_mq_ops virtio_mq_ops = {
.queue_rq = virtio_queue_rq,
.complete = virtblk_request_done,
.init_request = virtblk_init_request,
atomic_t pending;
};
+struct blkif_req {
+ int error;
+};
+
+static inline struct blkif_req *blkif_req(struct request *rq)
+{
+ return blk_mq_rq_to_pdu(rq);
+}
+
static DEFINE_MUTEX(blkfront_mutex);
static const struct block_device_operations xlvbd_block_fops;
return BLK_MQ_RQ_QUEUE_BUSY;
}
-static struct blk_mq_ops blkfront_mq_ops = {
+static void blkif_complete_rq(struct request *rq)
+{
+ blk_mq_end_request(rq, blkif_req(rq)->error);
+}
+
+static const struct blk_mq_ops blkfront_mq_ops = {
.queue_rq = blkif_queue_rq,
+ .complete = blkif_complete_rq,
};
static void blkif_set_queue_limits(struct blkfront_info *info)
info->tag_set.queue_depth = BLK_RING_SIZE(info);
info->tag_set.numa_node = NUMA_NO_NODE;
info->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
- info->tag_set.cmd_size = 0;
+ info->tag_set.cmd_size = sizeof(struct blkif_req);
info->tag_set.driver_data = info;
if (blk_mq_alloc_tag_set(&info->tag_set))
unsigned long flags;
struct blkfront_ring_info *rinfo = (struct blkfront_ring_info *)dev_id;
struct blkfront_info *info = rinfo->dev_info;
- int error;
if (unlikely(info->connected != BLKIF_STATE_CONNECTED))
return IRQ_HANDLED;
continue;
}
- error = (bret->status == BLKIF_RSP_OKAY) ? 0 : -EIO;
+ blkif_req(req)->error = (bret->status == BLKIF_RSP_OKAY) ? 0 : -EIO;
switch (bret->operation) {
case BLKIF_OP_DISCARD:
if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
struct request_queue *rq = info->rq;
printk(KERN_WARNING "blkfront: %s: %s op failed\n",
info->gd->disk_name, op_name(bret->operation));
- error = -EOPNOTSUPP;
+ blkif_req(req)->error = -EOPNOTSUPP;
info->feature_discard = 0;
info->feature_secdiscard = 0;
queue_flag_clear(QUEUE_FLAG_DISCARD, rq);
queue_flag_clear(QUEUE_FLAG_SECERASE, rq);
}
- blk_mq_complete_request(req, error);
break;
case BLKIF_OP_FLUSH_DISKCACHE:
case BLKIF_OP_WRITE_BARRIER:
if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
printk(KERN_WARNING "blkfront: %s: %s op failed\n",
info->gd->disk_name, op_name(bret->operation));
- error = -EOPNOTSUPP;
+ blkif_req(req)->error = -EOPNOTSUPP;
}
if (unlikely(bret->status == BLKIF_RSP_ERROR &&
rinfo->shadow[id].req.u.rw.nr_segments == 0)) {
printk(KERN_WARNING "blkfront: %s: empty %s op failed\n",
info->gd->disk_name, op_name(bret->operation));
- error = -EOPNOTSUPP;
+ blkif_req(req)->error = -EOPNOTSUPP;
}
- if (unlikely(error)) {
- if (error == -EOPNOTSUPP)
- error = 0;
+ if (unlikely(blkif_req(req)->error)) {
+ if (blkif_req(req)->error == -EOPNOTSUPP)
+ blkif_req(req)->error = 0;
info->feature_fua = 0;
info->feature_flush = 0;
xlvbd_flush(info);
dev_dbg(&info->xbdev->dev, "Bad return from blkdev data "
"request: %x\n", bret->status);
- blk_mq_complete_request(req, error);
break;
default:
BUG();
}
+
+ blk_mq_complete_request(req);
}
rinfo->ring.rsp_cons = i;
unsigned long sector_size;
unsigned int physical_sector_size;
unsigned int binfo;
+ char *envp[] = { "RESIZE=1", NULL };
int err, i;
switch (info->connected) {
sectors);
set_capacity(info->gd, sectors);
revalidate_disk(info->gd);
+ kobject_uevent_env(&disk_to_dev(info->gd)->kobj,
+ KOBJ_CHANGE, envp);
return;
case BLKIF_STATE_SUSPENDED:
cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_RO);
if (size == PAGE_SIZE) {
- copy_page(mem, cmem);
+ memcpy(mem, cmem, PAGE_SIZE);
} else {
struct zcomp_strm *zstrm = zcomp_stream_get(zram->comp);
if ((clen == PAGE_SIZE) && !is_partial_io(bvec)) {
src = kmap_atomic(page);
- copy_page(cmem, src);
+ memcpy(cmem, src, PAGE_SIZE);
kunmap_atomic(src);
} else {
memcpy(cmem, src, clen);
offset = (bio->bi_iter.bi_sector &
(SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT;
- if (unlikely(bio_op(bio) == REQ_OP_DISCARD)) {
+ switch (bio_op(bio)) {
+ case REQ_OP_DISCARD:
+ case REQ_OP_WRITE_ZEROES:
zram_bio_discard(zram, index, offset, bio);
bio_endio(bio);
return;
+ default:
+ break;
}
bio_for_each_segment(bvec, bio, iter) {
}
index = sector >> SECTORS_PER_PAGE_SHIFT;
- offset = sector & (SECTORS_PER_PAGE - 1) << SECTOR_SHIFT;
+ offset = (sector & (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT;
bv.bv_page = page;
bv.bv_len = PAGE_SIZE;
zram->disk->queue->limits.max_sectors = SECTORS_PER_PAGE;
zram->disk->queue->limits.chunk_sectors = 0;
blk_queue_max_discard_sectors(zram->disk->queue, UINT_MAX);
+ queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, zram->disk->queue);
+
/*
* zram_bio_discard() will clear all logical blocks if logical block
* size is identical with physical block size(PAGE_SIZE). But if it is
* zeroed.
*/
if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE)
- zram->disk->queue->limits.discard_zeroes_data = 1;
- else
- zram->disk->queue->limits.discard_zeroes_data = 0;
- queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, zram->disk->queue);
+ blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX);
add_disk(zram->disk);
rq->timeout = 60 * HZ;
bio = rq->bio;
- if (blk_execute_rq(q, cdi->disk, rq, 0)) {
+ blk_execute_rq(q, cdi->disk, rq, 0);
+ if (scsi_req(rq)->result) {
struct request_sense *s = req->sense;
ret = -EIO;
cdi->last_sense = s->sense_key;
#include <linux/agp_backend.h>
#include <linux/mmzone.h>
#include <asm/page.h> /* PAGE_SIZE */
-#include <asm/e820.h>
+#include <asm/e820/api.h>
#include <asm/amd_nb.h>
#include <asm/gart.h>
#include "agp.h"
static const struct of_device_id bt_bmc_match[] = {
{ .compatible = "aspeed,ast2400-ibt-bmc" },
+ { .compatible = "aspeed,ast2500-ibt-bmc" },
{ },
};
kfree(info);
goto out;
}
+ mutex_lock(&smi_infos_lock);
rv = try_smi_init(info);
+ mutex_unlock(&smi_infos_lock);
if (rv) {
cleanup_one_si(info);
goto out;
info->slave_addr = slave_addrs[i];
if (!add_smi(info)) {
+ mutex_lock(&smi_infos_lock);
if (try_smi_init(info))
cleanup_one_si(info);
+ mutex_unlock(&smi_infos_lock);
ret = 0;
} else {
kfree(info);
return rv;
}
+/*
+ * Try to start up an interface. Must be called with smi_infos_lock
+ * held, primarily to keep smi_num consistent, we only one to do these
+ * one at a time.
+ */
static int try_smi_init(struct smi_info *new_smi)
{
int rv = 0;
goto out_err;
}
+ new_smi->intf_num = smi_num;
+
/* Do this early so it's available for logs. */
if (!new_smi->dev) {
- init_name = kasprintf(GFP_KERNEL, "ipmi_si.%d", 0);
+ init_name = kasprintf(GFP_KERNEL, "ipmi_si.%d",
+ new_smi->intf_num);
/*
* If we don't already have a device from something
new_smi->interrupt_disabled = true;
atomic_set(&new_smi->need_watch, 0);
- new_smi->intf_num = smi_num;
- smi_num++;
rv = try_enable_event_buffer(new_smi);
if (rv == 0)
goto out_err_stop_timer;
}
+ /* Don't increment till we know we have succeeded. */
+ smi_num++;
+
dev_info(new_smi->dev, "IPMI %s interface initialized\n",
si_to_str[new_smi->si_type]);
* for details on the intricacies of this.
*/
int left;
+ unsigned char *data_to_send;
ssif_inc_stat(ssif_info, sent_messages_parts);
left = 32;
/* Length byte. */
ssif_info->multi_data[ssif_info->multi_pos] = left;
+ data_to_send = ssif_info->multi_data + ssif_info->multi_pos;
ssif_info->multi_pos += left;
if (left < 32)
/*
rv = ssif_i2c_send(ssif_info, msg_written_handler,
I2C_SMBUS_WRITE,
SSIF_IPMI_MULTI_PART_REQUEST_MIDDLE,
- ssif_info->multi_data + ssif_info->multi_pos,
+ data_to_send,
I2C_SMBUS_BLOCK_DATA);
if (rv < 0) {
/* request failed, just return the error. */
spin_lock_init(&ssif_info->lock);
ssif_info->ssif_state = SSIF_NORMAL;
- init_timer(&ssif_info->retry_timer);
- ssif_info->retry_timer.data = (unsigned long) ssif_info;
- ssif_info->retry_timer.function = retry_timeout;
+ setup_timer(&ssif_info->retry_timer, retry_timeout,
+ (unsigned long)ssif_info);
for (i = 0; i < SSIF_NUM_STATS; i++)
atomic_set(&ssif_info->stats[i], 0);
msg.cmd = IPMI_WDOG_RESET_TIMER;
msg.data = NULL;
msg.data_len = 0;
- atomic_add(2, &panic_done_count);
+ atomic_add(1, &panic_done_count);
rv = ipmi_request_supply_msgs(watchdog_user,
(struct ipmi_addr *) &addr,
0,
&panic_halt_heartbeat_recv_msg,
1);
if (rv)
- atomic_sub(2, &panic_done_count);
+ atomic_sub(1, &panic_done_count);
}
static struct ipmi_smi_msg panic_halt_smi_msg = {
/* Wait for the messages to be free. */
while (atomic_read(&panic_done_count) != 0)
ipmi_poll_interface(watchdog_user);
- atomic_add(2, &panic_done_count);
+ atomic_add(1, &panic_done_count);
rv = i_ipmi_set_timeout(&panic_halt_smi_msg,
&panic_halt_recv_msg,
&send_heartbeat_now);
if (rv) {
- atomic_sub(2, &panic_done_count);
+ atomic_sub(1, &panic_done_count);
printk(KERN_WARNING PFX
"Unable to extend the watchdog timeout.");
} else {
#endif
#ifdef CONFIG_STRICT_DEVMEM
+static inline int page_is_allowed(unsigned long pfn)
+{
+ return devmem_is_allowed(pfn);
+}
static inline int range_is_allowed(unsigned long pfn, unsigned long size)
{
u64 from = ((u64)pfn) << PAGE_SHIFT;
return 1;
}
#else
+static inline int page_is_allowed(unsigned long pfn)
+{
+ return 1;
+}
static inline int range_is_allowed(unsigned long pfn, unsigned long size)
{
return 1;
while (count > 0) {
unsigned long remaining;
+ int allowed;
sz = size_inside_page(p, count);
- if (!range_is_allowed(p >> PAGE_SHIFT, count))
+ allowed = page_is_allowed(p >> PAGE_SHIFT);
+ if (!allowed)
return -EPERM;
+ if (allowed == 2) {
+ /* Show zeros for restricted memory. */
+ remaining = clear_user(buf, sz);
+ } else {
+ /*
+ * On ia64 if a page has been mapped somewhere as
+ * uncached, then it must also be accessed uncached
+ * by the kernel or data corruption may occur.
+ */
+ ptr = xlate_dev_mem_ptr(p);
+ if (!ptr)
+ return -EFAULT;
- /*
- * On ia64 if a page has been mapped somewhere as uncached, then
- * it must also be accessed uncached by the kernel or data
- * corruption may occur.
- */
- ptr = xlate_dev_mem_ptr(p);
- if (!ptr)
- return -EFAULT;
+ remaining = copy_to_user(buf, ptr, sz);
+
+ unxlate_dev_mem_ptr(p, ptr);
+ }
- remaining = copy_to_user(buf, ptr, sz);
- unxlate_dev_mem_ptr(p, ptr);
if (remaining)
return -EFAULT;
#endif
while (count > 0) {
+ int allowed;
+
sz = size_inside_page(p, count);
- if (!range_is_allowed(p >> PAGE_SHIFT, sz))
+ allowed = page_is_allowed(p >> PAGE_SHIFT);
+ if (!allowed)
return -EPERM;
- /*
- * On ia64 if a page has been mapped somewhere as uncached, then
- * it must also be accessed uncached by the kernel or data
- * corruption may occur.
- */
- ptr = xlate_dev_mem_ptr(p);
- if (!ptr) {
- if (written)
- break;
- return -EFAULT;
- }
+ /* Skip actual writing when a page is marked as restricted. */
+ if (allowed == 1) {
+ /*
+ * On ia64 if a page has been mapped somewhere as
+ * uncached, then it must also be accessed uncached
+ * by the kernel or data corruption may occur.
+ */
+ ptr = xlate_dev_mem_ptr(p);
+ if (!ptr) {
+ if (written)
+ break;
+ return -EFAULT;
+ }
- copied = copy_from_user(ptr, buf, sz);
- unxlate_dev_mem_ptr(p, ptr);
- if (copied) {
- written += sz - copied;
- if (written)
- break;
- return -EFAULT;
+ copied = copy_from_user(ptr, buf, sz);
+ unxlate_dev_mem_ptr(p, ptr);
+ if (copied) {
+ written += sz - copied;
+ if (written)
+ break;
+ return -EFAULT;
+ }
}
buf += sz;
static struct timespec sgi_clock_offset;
static int sgi_clock_period;
-static int sgi_clock_get(clockid_t clockid, struct timespec *tp)
+static int sgi_clock_get(clockid_t clockid, struct timespec64 *tp)
{
u64 nsec;
nsec = rtc_time() * sgi_clock_period
+ sgi_clock_offset.tv_nsec;
- *tp = ns_to_timespec(nsec);
+ *tp = ns_to_timespec64(nsec);
tp->tv_sec += sgi_clock_offset.tv_sec;
return 0;
};
-static int sgi_clock_set(const clockid_t clockid, const struct timespec *tp)
+static int sgi_clock_set(const clockid_t clockid, const struct timespec64 *tp)
{
u64 nsec;
}
/* Assumption: it_lock is already held with irq's disabled */
-static void sgi_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting)
+static void sgi_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting)
{
if (timr->it.mmtimer.clock == TIMER_OFF) {
return;
}
- cur_setting->it_interval = ns_to_timespec(timr->it.mmtimer.incr * sgi_clock_period);
- cur_setting->it_value = ns_to_timespec((timr->it.mmtimer.expires - rtc_time()) * sgi_clock_period);
+ cur_setting->it_interval = ns_to_timespec64(timr->it.mmtimer.incr * sgi_clock_period);
+ cur_setting->it_value = ns_to_timespec64((timr->it.mmtimer.expires - rtc_time()) * sgi_clock_period);
}
static int sgi_timer_set(struct k_itimer *timr, int flags,
- struct itimerspec * new_setting,
- struct itimerspec * old_setting)
+ struct itimerspec64 *new_setting,
+ struct itimerspec64 *old_setting)
{
unsigned long when, period, irqflags;
int err = 0;
sgi_timer_get(timr, old_setting);
sgi_timer_del(timr);
- when = timespec_to_ns(&new_setting->it_value);
- period = timespec_to_ns(&new_setting->it_interval);
+ when = timespec64_to_ns(&new_setting->it_value);
+ period = timespec64_to_ns(&new_setting->it_interval);
if (when == 0)
/* Clear timer */
return -ENOMEM;
if (flags & TIMER_ABSTIME) {
- struct timespec n;
+ struct timespec64 n;
unsigned long now;
- getnstimeofday(&n);
- now = timespec_to_ns(&n);
+ getnstimeofday64(&n);
+ now = timespec64_to_ns(&n);
if (when > now)
when -= now;
else
return err;
}
-static int sgi_clock_getres(const clockid_t which_clock, struct timespec *tp)
+static int sgi_clock_getres(const clockid_t which_clock, struct timespec64 *tp)
{
tp->tv_sec = 0;
tp->tv_nsec = sgi_clock_period;
vdev->config->reset(vdev);
- virtqueue_disable_cb(portdev->c_ivq);
+ if (use_multiport(portdev))
+ virtqueue_disable_cb(portdev->c_ivq);
cancel_work_sync(&portdev->control_work);
cancel_work_sync(&portdev->config_work);
/*
* Once more: if control_work_handler() was running, it would
* enable the cb as the last step.
*/
- virtqueue_disable_cb(portdev->c_ivq);
+ if (use_multiport(portdev))
+ virtqueue_disable_cb(portdev->c_ivq);
remove_controlq_data(portdev);
list_for_each_entry(port, &portdev->ports, list) {
{ 0, 2 }, { 1, 4 }, { 2, 6 }, { 3, 8 }, { 0 }
};
+static const struct clk_div_table pll_divq_table[] = {
+ { 2, 2 }, { 3, 3 }, { 4, 4 }, { 5, 5 }, { 6, 6 }, { 7, 7 },
+ { 8, 8 }, { 9, 9 }, { 10, 10 }, { 11, 11 }, { 12, 12 }, { 13, 13 },
+ { 14, 14 }, { 15, 15 },
+ { 0 }
+};
+
static const struct clk_div_table pll_divr_table[] = {
{ 2, 2 }, { 3, 3 }, { 4, 4 }, { 5, 5 }, { 6, 6 }, { 7, 7 }, { 0 }
};
#define MAX_PLL_DIV 3
static const struct stm32f4_div_data div_data[MAX_PLL_DIV] = {
- { 16, 2, 0, pll_divp_table },
- { 24, 4, CLK_DIVIDER_ONE_BASED, NULL },
- { 28, 3, 0, pll_divr_table },
+ { 16, 2, 0, pll_divp_table },
+ { 24, 4, 0, pll_divq_table },
+ { 28, 3, 0, pll_divr_table },
};
struct stm32f4_pll_data {
config SUNXI_CCU
bool "Clock support for Allwinner SoCs"
depends on ARCH_SUNXI || COMPILE_TEST
+ select RESET_CONTROLLER
default ARCH_SUNXI
if SUNXI_CCU
bool
config SUNXI_CCU_GATE
- bool
+ def_bool y
config SUNXI_CCU_MUX
bool
config SUN9I_A80_CCU
bool "Support for the Allwinner A80 CCU"
select SUNXI_CCU_DIV
+ select SUNXI_CCU_MULT
select SUNXI_CCU_GATE
select SUNXI_CCU_NKMP
select SUNXI_CCU_NM
.num_resets = ARRAY_SIZE(sun8i_a33_ccu_resets),
};
+static struct ccu_pll_nb sun8i_a33_pll_cpu_nb = {
+ .common = &pll_cpux_clk.common,
+ /* copy from pll_cpux_clk */
+ .enable = BIT(31),
+ .lock = BIT(28),
+};
+
static struct ccu_mux_nb sun8i_a33_cpu_nb = {
.common = &cpux_clk.common,
.cm = &cpux_clk.mux,
sunxi_ccu_probe(node, reg, &sun8i_a33_ccu_desc);
+ /* Gate then ungate PLL CPU after any rate changes */
+ ccu_pll_notifier_register(&sun8i_a33_pll_cpu_nb);
+
+ /* Reparent CPU during PLL CPU rate changes */
ccu_mux_notifier_register(pll_cpux_clk.common.hw.clk,
&sun8i_a33_cpu_nb);
}
* GNU General Public License for more details.
*/
+#include <linux/clk.h>
#include <linux/clk-provider.h>
#include <linux/iopoll.h>
#include <linux/slab.h>
#include "ccu_common.h"
+#include "ccu_gate.h"
#include "ccu_reset.h"
static DEFINE_SPINLOCK(ccu_lock);
WARN_ON(readl_relaxed_poll_timeout(addr, reg, reg & lock, 100, 70000));
}
+/*
+ * This clock notifier is called when the frequency of a PLL clock is
+ * changed. In common PLL designs, changes to the dividers take effect
+ * almost immediately, while changes to the multipliers (implemented
+ * as dividers in the feedback loop) take a few cycles to work into
+ * the feedback loop for the PLL to stablize.
+ *
+ * Sometimes when the PLL clock rate is changed, the decrease in the
+ * divider is too much for the decrease in the multiplier to catch up.
+ * The PLL clock rate will spike, and in some cases, might lock up
+ * completely.
+ *
+ * This notifier callback will gate and then ungate the clock,
+ * effectively resetting it, so it proceeds to work. Care must be
+ * taken to reparent consumers to other temporary clocks during the
+ * rate change, and that this notifier callback must be the first
+ * to be registered.
+ */
+static int ccu_pll_notifier_cb(struct notifier_block *nb,
+ unsigned long event, void *data)
+{
+ struct ccu_pll_nb *pll = to_ccu_pll_nb(nb);
+ int ret = 0;
+
+ if (event != POST_RATE_CHANGE)
+ goto out;
+
+ ccu_gate_helper_disable(pll->common, pll->enable);
+
+ ret = ccu_gate_helper_enable(pll->common, pll->enable);
+ if (ret)
+ goto out;
+
+ ccu_helper_wait_for_lock(pll->common, pll->lock);
+
+out:
+ return notifier_from_errno(ret);
+}
+
+int ccu_pll_notifier_register(struct ccu_pll_nb *pll_nb)
+{
+ pll_nb->clk_nb.notifier_call = ccu_pll_notifier_cb;
+
+ return clk_notifier_register(pll_nb->common->hw.clk,
+ &pll_nb->clk_nb);
+}
+
int sunxi_ccu_probe(struct device_node *node, void __iomem *reg,
const struct sunxi_ccu_desc *desc)
{
void ccu_helper_wait_for_lock(struct ccu_common *common, u32 lock);
+struct ccu_pll_nb {
+ struct notifier_block clk_nb;
+ struct ccu_common *common;
+
+ u32 enable;
+ u32 lock;
+};
+
+#define to_ccu_pll_nb(_nb) container_of(_nb, struct ccu_pll_nb, clk_nb)
+
+int ccu_pll_notifier_register(struct ccu_pll_nb *pll_nb);
+
int sunxi_ccu_probe(struct device_node *node, void __iomem *reg,
const struct sunxi_ccu_desc *desc);
select DW_APB_TIMER
select CLKSRC_OF
-config GEMINI_TIMER
- bool "Cortina Gemini timer driver" if COMPILE_TEST
+config FTTMR010_TIMER
+ bool "Faraday Technology timer driver" if COMPILE_TEST
depends on GENERIC_CLOCKEVENTS
depends on HAS_IOMEM
select CLKSRC_MMIO
select CLKSRC_OF
select MFD_SYSCON
help
- Enables support for the Gemini timer
+ Enables support for the Faraday Technology timer block
+ FTTMR010.
config ROCKCHIP_TIMER
bool "Rockchip timer driver" if COMPILE_TEST
depends on ARM || ARM64
select CLKSRC_OF
+ select CLKSRC_MMIO
help
Enables the support for the rockchip timer driver.
161010101. The workaround will be active if the hisilicon,erratum-161010101
property is found in the timer node.
+config ARM64_ERRATUM_858921
+ bool "Workaround for Cortex-A73 erratum 858921"
+ default y
+ select ARM_ARCH_TIMER_OOL_WORKAROUND
+ depends on ARM_ARCH_TIMER && ARM64
+ help
+ This option enables a workaround applicable to Cortex-A73
+ (all versions), whose counter may return incorrect values.
+ The workaround will be dynamically enabled when an affected
+ core is detected.
+
config ARM_GLOBAL_TIMER
bool "Support for the ARM global timer" if COMPILE_TEST
select CLKSRC_OF if OF
obj-$(CONFIG_DIGICOLOR_TIMER) += timer-digicolor.o
obj-$(CONFIG_DW_APB_TIMER) += dw_apb_timer.o
obj-$(CONFIG_DW_APB_TIMER_OF) += dw_apb_timer_of.o
-obj-$(CONFIG_GEMINI_TIMER) += timer-gemini.o
+obj-$(CONFIG_FTTMR010_TIMER) += timer-fttmr010.o
obj-$(CONFIG_ROCKCHIP_TIMER) += rockchip_timer.o
obj-$(CONFIG_CLKSRC_NOMADIK_MTU) += nomadik-mtu.o
obj-$(CONFIG_CLKSRC_DBX500_PRCMU) += clksrc-dbx500-prcmu.o
clk = of_clk_get(node, 0);
if (IS_ERR(clk)) {
- pr_err("timer missing clk");
+ pr_err("timer missing clk\n");
return PTR_ERR(clk);
}
READ_BCR(ARC_REG_MCIP_BCR, mp);
if (!mp.gfrc) {
- pr_warn("Global-64-bit-Ctr clocksource not detected");
+ pr_warn("Global-64-bit-Ctr clocksource not detected\n");
return -ENXIO;
}
READ_BCR(ARC_REG_TIMERS_BCR, timer);
if (!timer.rtc) {
- pr_warn("Local-64-bit-Ctr clocksource not detected");
+ pr_warn("Local-64-bit-Ctr clocksource not detected\n");
return -ENXIO;
}
/* Local to CPU hence not usable in SMP */
if (IS_ENABLED(CONFIG_SMP)) {
- pr_warn("Local-64-bit-Ctr not usable in SMP");
+ pr_warn("Local-64-bit-Ctr not usable in SMP\n");
return -EINVAL;
}
arc_timer_irq = irq_of_parse_and_map(node, 0);
if (arc_timer_irq <= 0) {
- pr_err("clockevent: missing irq");
+ pr_err("clockevent: missing irq\n");
return -EINVAL;
}
ret = arc_get_timer_clk(node);
if (ret) {
- pr_err("clockevent: missing clk");
+ pr_err("clockevent: missing clk\n");
return ret;
}
arc_timer_starting_cpu,
arc_timer_dying_cpu);
if (ret) {
- pr_err("Failed to setup hotplug state");
+ pr_err("Failed to setup hotplug state\n");
return ret;
}
return 0;
#include <clocksource/arm_arch_timer.h>
+#undef pr_fmt
+#define pr_fmt(fmt) "arch_timer: " fmt
+
#define CNTTIDR 0x08
#define CNTTIDR_VIRT(n) (BIT(1) << ((n) * 4))
#define CNTV_TVAL 0x38
#define CNTV_CTL 0x3c
-#define ARCH_CP15_TIMER BIT(0)
-#define ARCH_MEM_TIMER BIT(1)
static unsigned arch_timers_present __initdata;
static void __iomem *arch_counter_base;
#define to_arch_timer(e) container_of(e, struct arch_timer, evt)
static u32 arch_timer_rate;
-
-enum ppi_nr {
- PHYS_SECURE_PPI,
- PHYS_NONSECURE_PPI,
- VIRT_PPI,
- HYP_PPI,
- MAX_TIMER_PPI
-};
-
-static int arch_timer_ppi[MAX_TIMER_PPI];
+static int arch_timer_ppi[ARCH_TIMER_MAX_TIMER_PPI];
static struct clock_event_device __percpu *arch_timer_evt;
-static enum ppi_nr arch_timer_uses_ppi = VIRT_PPI;
+static enum arch_timer_ppi_nr arch_timer_uses_ppi = ARCH_TIMER_VIRT_PPI;
static bool arch_timer_c3stop;
static bool arch_timer_mem_use_virtual;
static bool arch_counter_suspend_stop;
+static bool vdso_default = true;
static bool evtstrm_enable = IS_ENABLED(CONFIG_ARM_ARCH_TIMER_EVTSTREAM);
* Architected system timer support.
*/
+static __always_inline
+void arch_timer_reg_write(int access, enum arch_timer_reg reg, u32 val,
+ struct clock_event_device *clk)
+{
+ if (access == ARCH_TIMER_MEM_PHYS_ACCESS) {
+ struct arch_timer *timer = to_arch_timer(clk);
+ switch (reg) {
+ case ARCH_TIMER_REG_CTRL:
+ writel_relaxed(val, timer->base + CNTP_CTL);
+ break;
+ case ARCH_TIMER_REG_TVAL:
+ writel_relaxed(val, timer->base + CNTP_TVAL);
+ break;
+ }
+ } else if (access == ARCH_TIMER_MEM_VIRT_ACCESS) {
+ struct arch_timer *timer = to_arch_timer(clk);
+ switch (reg) {
+ case ARCH_TIMER_REG_CTRL:
+ writel_relaxed(val, timer->base + CNTV_CTL);
+ break;
+ case ARCH_TIMER_REG_TVAL:
+ writel_relaxed(val, timer->base + CNTV_TVAL);
+ break;
+ }
+ } else {
+ arch_timer_reg_write_cp15(access, reg, val);
+ }
+}
+
+static __always_inline
+u32 arch_timer_reg_read(int access, enum arch_timer_reg reg,
+ struct clock_event_device *clk)
+{
+ u32 val;
+
+ if (access == ARCH_TIMER_MEM_PHYS_ACCESS) {
+ struct arch_timer *timer = to_arch_timer(clk);
+ switch (reg) {
+ case ARCH_TIMER_REG_CTRL:
+ val = readl_relaxed(timer->base + CNTP_CTL);
+ break;
+ case ARCH_TIMER_REG_TVAL:
+ val = readl_relaxed(timer->base + CNTP_TVAL);
+ break;
+ }
+ } else if (access == ARCH_TIMER_MEM_VIRT_ACCESS) {
+ struct arch_timer *timer = to_arch_timer(clk);
+ switch (reg) {
+ case ARCH_TIMER_REG_CTRL:
+ val = readl_relaxed(timer->base + CNTV_CTL);
+ break;
+ case ARCH_TIMER_REG_TVAL:
+ val = readl_relaxed(timer->base + CNTV_TVAL);
+ break;
+ }
+ } else {
+ val = arch_timer_reg_read_cp15(access, reg);
+ }
+
+ return val;
+}
+
+/*
+ * Default to cp15 based access because arm64 uses this function for
+ * sched_clock() before DT is probed and the cp15 method is guaranteed
+ * to exist on arm64. arm doesn't use this before DT is probed so even
+ * if we don't have the cp15 accessors we won't have a problem.
+ */
+u64 (*arch_timer_read_counter)(void) = arch_counter_get_cntvct;
+
+static u64 arch_counter_read(struct clocksource *cs)
+{
+ return arch_timer_read_counter();
+}
+
+static u64 arch_counter_read_cc(const struct cyclecounter *cc)
+{
+ return arch_timer_read_counter();
+}
+
+static struct clocksource clocksource_counter = {
+ .name = "arch_sys_counter",
+ .rating = 400,
+ .read = arch_counter_read,
+ .mask = CLOCKSOURCE_MASK(56),
+ .flags = CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+static struct cyclecounter cyclecounter __ro_after_init = {
+ .read = arch_counter_read_cc,
+ .mask = CLOCKSOURCE_MASK(56),
+};
+
+struct ate_acpi_oem_info {
+ char oem_id[ACPI_OEM_ID_SIZE + 1];
+ char oem_table_id[ACPI_OEM_TABLE_ID_SIZE + 1];
+ u32 oem_revision;
+};
+
#ifdef CONFIG_FSL_ERRATUM_A008585
/*
* The number of retries is an arbitrary value well beyond the highest number
{
return __hisi_161010101_read_reg(cntvct_el0);
}
+
+static struct ate_acpi_oem_info hisi_161010101_oem_info[] = {
+ /*
+ * Note that trailing spaces are required to properly match
+ * the OEM table information.
+ */
+ {
+ .oem_id = "HISI ",
+ .oem_table_id = "HIP05 ",
+ .oem_revision = 0,
+ },
+ {
+ .oem_id = "HISI ",
+ .oem_table_id = "HIP06 ",
+ .oem_revision = 0,
+ },
+ {
+ .oem_id = "HISI ",
+ .oem_table_id = "HIP07 ",
+ .oem_revision = 0,
+ },
+ { /* Sentinel indicating the end of the OEM array */ },
+};
+#endif
+
+#ifdef CONFIG_ARM64_ERRATUM_858921
+static u64 notrace arm64_858921_read_cntvct_el0(void)
+{
+ u64 old, new;
+
+ old = read_sysreg(cntvct_el0);
+ new = read_sysreg(cntvct_el0);
+ return (((old ^ new) >> 32) & 1) ? old : new;
+}
#endif
#ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND
-const struct arch_timer_erratum_workaround *timer_unstable_counter_workaround = NULL;
+DEFINE_PER_CPU(const struct arch_timer_erratum_workaround *,
+ timer_unstable_counter_workaround);
EXPORT_SYMBOL_GPL(timer_unstable_counter_workaround);
DEFINE_STATIC_KEY_FALSE(arch_timer_read_ool_enabled);
EXPORT_SYMBOL_GPL(arch_timer_read_ool_enabled);
+static void erratum_set_next_event_tval_generic(const int access, unsigned long evt,
+ struct clock_event_device *clk)
+{
+ unsigned long ctrl;
+ u64 cval = evt + arch_counter_get_cntvct();
+
+ ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, clk);
+ ctrl |= ARCH_TIMER_CTRL_ENABLE;
+ ctrl &= ~ARCH_TIMER_CTRL_IT_MASK;
+
+ if (access == ARCH_TIMER_PHYS_ACCESS)
+ write_sysreg(cval, cntp_cval_el0);
+ else
+ write_sysreg(cval, cntv_cval_el0);
+
+ arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
+}
+
+static __maybe_unused int erratum_set_next_event_tval_virt(unsigned long evt,
+ struct clock_event_device *clk)
+{
+ erratum_set_next_event_tval_generic(ARCH_TIMER_VIRT_ACCESS, evt, clk);
+ return 0;
+}
+
+static __maybe_unused int erratum_set_next_event_tval_phys(unsigned long evt,
+ struct clock_event_device *clk)
+{
+ erratum_set_next_event_tval_generic(ARCH_TIMER_PHYS_ACCESS, evt, clk);
+ return 0;
+}
+
static const struct arch_timer_erratum_workaround ool_workarounds[] = {
#ifdef CONFIG_FSL_ERRATUM_A008585
{
+ .match_type = ate_match_dt,
.id = "fsl,erratum-a008585",
+ .desc = "Freescale erratum a005858",
.read_cntp_tval_el0 = fsl_a008585_read_cntp_tval_el0,
.read_cntv_tval_el0 = fsl_a008585_read_cntv_tval_el0,
.read_cntvct_el0 = fsl_a008585_read_cntvct_el0,
+ .set_next_event_phys = erratum_set_next_event_tval_phys,
+ .set_next_event_virt = erratum_set_next_event_tval_virt,
},
#endif
#ifdef CONFIG_HISILICON_ERRATUM_161010101
{
+ .match_type = ate_match_dt,
.id = "hisilicon,erratum-161010101",
+ .desc = "HiSilicon erratum 161010101",
.read_cntp_tval_el0 = hisi_161010101_read_cntp_tval_el0,
.read_cntv_tval_el0 = hisi_161010101_read_cntv_tval_el0,
.read_cntvct_el0 = hisi_161010101_read_cntvct_el0,
+ .set_next_event_phys = erratum_set_next_event_tval_phys,
+ .set_next_event_virt = erratum_set_next_event_tval_virt,
+ },
+ {
+ .match_type = ate_match_acpi_oem_info,
+ .id = hisi_161010101_oem_info,
+ .desc = "HiSilicon erratum 161010101",
+ .read_cntp_tval_el0 = hisi_161010101_read_cntp_tval_el0,
+ .read_cntv_tval_el0 = hisi_161010101_read_cntv_tval_el0,
+ .read_cntvct_el0 = hisi_161010101_read_cntvct_el0,
+ .set_next_event_phys = erratum_set_next_event_tval_phys,
+ .set_next_event_virt = erratum_set_next_event_tval_virt,
+ },
+#endif
+#ifdef CONFIG_ARM64_ERRATUM_858921
+ {
+ .match_type = ate_match_local_cap_id,
+ .id = (void *)ARM64_WORKAROUND_858921,
+ .desc = "ARM erratum 858921",
+ .read_cntvct_el0 = arm64_858921_read_cntvct_el0,
},
#endif
};
-#endif /* CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND */
-static __always_inline
-void arch_timer_reg_write(int access, enum arch_timer_reg reg, u32 val,
- struct clock_event_device *clk)
+typedef bool (*ate_match_fn_t)(const struct arch_timer_erratum_workaround *,
+ const void *);
+
+static
+bool arch_timer_check_dt_erratum(const struct arch_timer_erratum_workaround *wa,
+ const void *arg)
{
- if (access == ARCH_TIMER_MEM_PHYS_ACCESS) {
- struct arch_timer *timer = to_arch_timer(clk);
- switch (reg) {
- case ARCH_TIMER_REG_CTRL:
- writel_relaxed(val, timer->base + CNTP_CTL);
- break;
- case ARCH_TIMER_REG_TVAL:
- writel_relaxed(val, timer->base + CNTP_TVAL);
- break;
- }
- } else if (access == ARCH_TIMER_MEM_VIRT_ACCESS) {
- struct arch_timer *timer = to_arch_timer(clk);
- switch (reg) {
- case ARCH_TIMER_REG_CTRL:
- writel_relaxed(val, timer->base + CNTV_CTL);
- break;
- case ARCH_TIMER_REG_TVAL:
- writel_relaxed(val, timer->base + CNTV_TVAL);
- break;
- }
- } else {
- arch_timer_reg_write_cp15(access, reg, val);
+ const struct device_node *np = arg;
+
+ return of_property_read_bool(np, wa->id);
+}
+
+static
+bool arch_timer_check_local_cap_erratum(const struct arch_timer_erratum_workaround *wa,
+ const void *arg)
+{
+ return this_cpu_has_cap((uintptr_t)wa->id);
+}
+
+
+static
+bool arch_timer_check_acpi_oem_erratum(const struct arch_timer_erratum_workaround *wa,
+ const void *arg)
+{
+ static const struct ate_acpi_oem_info empty_oem_info = {};
+ const struct ate_acpi_oem_info *info = wa->id;
+ const struct acpi_table_header *table = arg;
+
+ /* Iterate over the ACPI OEM info array, looking for a match */
+ while (memcmp(info, &empty_oem_info, sizeof(*info))) {
+ if (!memcmp(info->oem_id, table->oem_id, ACPI_OEM_ID_SIZE) &&
+ !memcmp(info->oem_table_id, table->oem_table_id, ACPI_OEM_TABLE_ID_SIZE) &&
+ info->oem_revision == table->oem_revision)
+ return true;
+
+ info++;
}
+
+ return false;
}
-static __always_inline
-u32 arch_timer_reg_read(int access, enum arch_timer_reg reg,
- struct clock_event_device *clk)
+static const struct arch_timer_erratum_workaround *
+arch_timer_iterate_errata(enum arch_timer_erratum_match_type type,
+ ate_match_fn_t match_fn,
+ void *arg)
{
- u32 val;
+ int i;
- if (access == ARCH_TIMER_MEM_PHYS_ACCESS) {
- struct arch_timer *timer = to_arch_timer(clk);
- switch (reg) {
- case ARCH_TIMER_REG_CTRL:
- val = readl_relaxed(timer->base + CNTP_CTL);
- break;
- case ARCH_TIMER_REG_TVAL:
- val = readl_relaxed(timer->base + CNTP_TVAL);
- break;
- }
- } else if (access == ARCH_TIMER_MEM_VIRT_ACCESS) {
- struct arch_timer *timer = to_arch_timer(clk);
- switch (reg) {
- case ARCH_TIMER_REG_CTRL:
- val = readl_relaxed(timer->base + CNTV_CTL);
- break;
- case ARCH_TIMER_REG_TVAL:
- val = readl_relaxed(timer->base + CNTV_TVAL);
- break;
- }
+ for (i = 0; i < ARRAY_SIZE(ool_workarounds); i++) {
+ if (ool_workarounds[i].match_type != type)
+ continue;
+
+ if (match_fn(&ool_workarounds[i], arg))
+ return &ool_workarounds[i];
+ }
+
+ return NULL;
+}
+
+static
+void arch_timer_enable_workaround(const struct arch_timer_erratum_workaround *wa,
+ bool local)
+{
+ int i;
+
+ if (local) {
+ __this_cpu_write(timer_unstable_counter_workaround, wa);
} else {
- val = arch_timer_reg_read_cp15(access, reg);
+ for_each_possible_cpu(i)
+ per_cpu(timer_unstable_counter_workaround, i) = wa;
}
- return val;
+ static_branch_enable(&arch_timer_read_ool_enabled);
+
+ /*
+ * Don't use the vdso fastpath if errata require using the
+ * out-of-line counter accessor. We may change our mind pretty
+ * late in the game (with a per-CPU erratum, for example), so
+ * change both the default value and the vdso itself.
+ */
+ if (wa->read_cntvct_el0) {
+ clocksource_counter.archdata.vdso_direct = false;
+ vdso_default = false;
+ }
+}
+
+static void arch_timer_check_ool_workaround(enum arch_timer_erratum_match_type type,
+ void *arg)
+{
+ const struct arch_timer_erratum_workaround *wa;
+ ate_match_fn_t match_fn = NULL;
+ bool local = false;
+
+ switch (type) {
+ case ate_match_dt:
+ match_fn = arch_timer_check_dt_erratum;
+ break;
+ case ate_match_local_cap_id:
+ match_fn = arch_timer_check_local_cap_erratum;
+ local = true;
+ break;
+ case ate_match_acpi_oem_info:
+ match_fn = arch_timer_check_acpi_oem_erratum;
+ break;
+ default:
+ WARN_ON(1);
+ return;
+ }
+
+ wa = arch_timer_iterate_errata(type, match_fn, arg);
+ if (!wa)
+ return;
+
+ if (needs_unstable_timer_counter_workaround()) {
+ const struct arch_timer_erratum_workaround *__wa;
+ __wa = __this_cpu_read(timer_unstable_counter_workaround);
+ if (__wa && wa != __wa)
+ pr_warn("Can't enable workaround for %s (clashes with %s\n)",
+ wa->desc, __wa->desc);
+
+ if (__wa)
+ return;
+ }
+
+ arch_timer_enable_workaround(wa, local);
+ pr_info("Enabling %s workaround for %s\n",
+ local ? "local" : "global", wa->desc);
}
+#define erratum_handler(fn, r, ...) \
+({ \
+ bool __val; \
+ if (needs_unstable_timer_counter_workaround()) { \
+ const struct arch_timer_erratum_workaround *__wa; \
+ __wa = __this_cpu_read(timer_unstable_counter_workaround); \
+ if (__wa && __wa->fn) { \
+ r = __wa->fn(__VA_ARGS__); \
+ __val = true; \
+ } else { \
+ __val = false; \
+ } \
+ } else { \
+ __val = false; \
+ } \
+ __val; \
+})
+
+static bool arch_timer_this_cpu_has_cntvct_wa(void)
+{
+ const struct arch_timer_erratum_workaround *wa;
+
+ wa = __this_cpu_read(timer_unstable_counter_workaround);
+ return wa && wa->read_cntvct_el0;
+}
+#else
+#define arch_timer_check_ool_workaround(t,a) do { } while(0)
+#define erratum_set_next_event_tval_virt(...) ({BUG(); 0;})
+#define erratum_set_next_event_tval_phys(...) ({BUG(); 0;})
+#define erratum_handler(fn, r, ...) ({false;})
+#define arch_timer_this_cpu_has_cntvct_wa() ({false;})
+#endif /* CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND */
+
static __always_inline irqreturn_t timer_handler(const int access,
struct clock_event_device *evt)
{
arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
}
-#ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND
-static __always_inline void erratum_set_next_event_generic(const int access,
- unsigned long evt, struct clock_event_device *clk)
-{
- unsigned long ctrl;
- u64 cval = evt + arch_counter_get_cntvct();
-
- ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, clk);
- ctrl |= ARCH_TIMER_CTRL_ENABLE;
- ctrl &= ~ARCH_TIMER_CTRL_IT_MASK;
-
- if (access == ARCH_TIMER_PHYS_ACCESS)
- write_sysreg(cval, cntp_cval_el0);
- else if (access == ARCH_TIMER_VIRT_ACCESS)
- write_sysreg(cval, cntv_cval_el0);
-
- arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
-}
-
-static int erratum_set_next_event_virt(unsigned long evt,
- struct clock_event_device *clk)
-{
- erratum_set_next_event_generic(ARCH_TIMER_VIRT_ACCESS, evt, clk);
- return 0;
-}
-
-static int erratum_set_next_event_phys(unsigned long evt,
- struct clock_event_device *clk)
-{
- erratum_set_next_event_generic(ARCH_TIMER_PHYS_ACCESS, evt, clk);
- return 0;
-}
-#endif /* CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND */
-
static int arch_timer_set_next_event_virt(unsigned long evt,
struct clock_event_device *clk)
{
+ int ret;
+
+ if (erratum_handler(set_next_event_virt, ret, evt, clk))
+ return ret;
+
set_next_event(ARCH_TIMER_VIRT_ACCESS, evt, clk);
return 0;
}
static int arch_timer_set_next_event_phys(unsigned long evt,
struct clock_event_device *clk)
{
+ int ret;
+
+ if (erratum_handler(set_next_event_phys, ret, evt, clk))
+ return ret;
+
set_next_event(ARCH_TIMER_PHYS_ACCESS, evt, clk);
return 0;
}
return 0;
}
-static void erratum_workaround_set_sne(struct clock_event_device *clk)
-{
-#ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND
- if (!static_branch_unlikely(&arch_timer_read_ool_enabled))
- return;
-
- if (arch_timer_uses_ppi == VIRT_PPI)
- clk->set_next_event = erratum_set_next_event_virt;
- else
- clk->set_next_event = erratum_set_next_event_phys;
-#endif
-}
-
static void __arch_timer_setup(unsigned type,
struct clock_event_device *clk)
{
clk->features = CLOCK_EVT_FEAT_ONESHOT;
- if (type == ARCH_CP15_TIMER) {
+ if (type == ARCH_TIMER_TYPE_CP15) {
if (arch_timer_c3stop)
clk->features |= CLOCK_EVT_FEAT_C3STOP;
clk->name = "arch_sys_timer";
clk->cpumask = cpumask_of(smp_processor_id());
clk->irq = arch_timer_ppi[arch_timer_uses_ppi];
switch (arch_timer_uses_ppi) {
- case VIRT_PPI:
+ case ARCH_TIMER_VIRT_PPI:
clk->set_state_shutdown = arch_timer_shutdown_virt;
clk->set_state_oneshot_stopped = arch_timer_shutdown_virt;
clk->set_next_event = arch_timer_set_next_event_virt;
break;
- case PHYS_SECURE_PPI:
- case PHYS_NONSECURE_PPI:
- case HYP_PPI:
+ case ARCH_TIMER_PHYS_SECURE_PPI:
+ case ARCH_TIMER_PHYS_NONSECURE_PPI:
+ case ARCH_TIMER_HYP_PPI:
clk->set_state_shutdown = arch_timer_shutdown_phys;
clk->set_state_oneshot_stopped = arch_timer_shutdown_phys;
clk->set_next_event = arch_timer_set_next_event_phys;
BUG();
}
- erratum_workaround_set_sne(clk);
+ arch_timer_check_ool_workaround(ate_match_local_cap_id, NULL);
} else {
clk->features |= CLOCK_EVT_FEAT_DYNIRQ;
clk->name = "arch_mem_timer";
{
u32 cntkctl = arch_timer_get_cntkctl();
- /* Disable user access to the timers and the physical counter */
+ /* Disable user access to the timers and both counters */
/* Also disable virtual event stream */
cntkctl &= ~(ARCH_TIMER_USR_PT_ACCESS_EN
| ARCH_TIMER_USR_VT_ACCESS_EN
+ | ARCH_TIMER_USR_VCT_ACCESS_EN
| ARCH_TIMER_VIRT_EVT_EN
| ARCH_TIMER_USR_PCT_ACCESS_EN);
- /* Enable user access to the virtual counter */
- cntkctl |= ARCH_TIMER_USR_VCT_ACCESS_EN;
+ /*
+ * Enable user access to the virtual counter if it doesn't
+ * need to be workaround. The vdso may have been already
+ * disabled though.
+ */
+ if (arch_timer_this_cpu_has_cntvct_wa())
+ pr_info("CPU%d: Trapping CNTVCT access\n", smp_processor_id());
+ else
+ cntkctl |= ARCH_TIMER_USR_VCT_ACCESS_EN;
arch_timer_set_cntkctl(cntkctl);
}
static bool arch_timer_has_nonsecure_ppi(void)
{
- return (arch_timer_uses_ppi == PHYS_SECURE_PPI &&
- arch_timer_ppi[PHYS_NONSECURE_PPI]);
+ return (arch_timer_uses_ppi == ARCH_TIMER_PHYS_SECURE_PPI &&
+ arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI]);
}
static u32 check_ppi_trigger(int irq)
struct clock_event_device *clk = this_cpu_ptr(arch_timer_evt);
u32 flags;
- __arch_timer_setup(ARCH_CP15_TIMER, clk);
+ __arch_timer_setup(ARCH_TIMER_TYPE_CP15, clk);
flags = check_ppi_trigger(arch_timer_ppi[arch_timer_uses_ppi]);
enable_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi], flags);
if (arch_timer_has_nonsecure_ppi()) {
- flags = check_ppi_trigger(arch_timer_ppi[PHYS_NONSECURE_PPI]);
- enable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI], flags);
+ flags = check_ppi_trigger(arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI]);
+ enable_percpu_irq(arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI],
+ flags);
}
arch_counter_set_user_access();
return 0;
}
-static void
-arch_timer_detect_rate(void __iomem *cntbase, struct device_node *np)
+/*
+ * For historical reasons, when probing with DT we use whichever (non-zero)
+ * rate was probed first, and don't verify that others match. If the first node
+ * probed has a clock-frequency property, this overrides the HW register.
+ */
+static void arch_timer_of_configure_rate(u32 rate, struct device_node *np)
{
/* Who has more than one independent system counter? */
if (arch_timer_rate)
return;
- /*
- * Try to determine the frequency from the device tree or CNTFRQ,
- * if ACPI is enabled, get the frequency from CNTFRQ ONLY.
- */
- if (!acpi_disabled ||
- of_property_read_u32(np, "clock-frequency", &arch_timer_rate)) {
- if (cntbase)
- arch_timer_rate = readl_relaxed(cntbase + CNTFRQ);
- else
- arch_timer_rate = arch_timer_get_cntfrq();
- }
+ if (of_property_read_u32(np, "clock-frequency", &arch_timer_rate))
+ arch_timer_rate = rate;
/* Check the timer frequency. */
if (arch_timer_rate == 0)
- pr_warn("Architected timer frequency not available\n");
+ pr_warn("frequency not available\n");
}
static void arch_timer_banner(unsigned type)
{
- pr_info("Architected %s%s%s timer(s) running at %lu.%02luMHz (%s%s%s).\n",
- type & ARCH_CP15_TIMER ? "cp15" : "",
- type == (ARCH_CP15_TIMER | ARCH_MEM_TIMER) ? " and " : "",
- type & ARCH_MEM_TIMER ? "mmio" : "",
- (unsigned long)arch_timer_rate / 1000000,
- (unsigned long)(arch_timer_rate / 10000) % 100,
- type & ARCH_CP15_TIMER ?
- (arch_timer_uses_ppi == VIRT_PPI) ? "virt" : "phys" :
+ pr_info("%s%s%s timer(s) running at %lu.%02luMHz (%s%s%s).\n",
+ type & ARCH_TIMER_TYPE_CP15 ? "cp15" : "",
+ type == (ARCH_TIMER_TYPE_CP15 | ARCH_TIMER_TYPE_MEM) ?
+ " and " : "",
+ type & ARCH_TIMER_TYPE_MEM ? "mmio" : "",
+ (unsigned long)arch_timer_rate / 1000000,
+ (unsigned long)(arch_timer_rate / 10000) % 100,
+ type & ARCH_TIMER_TYPE_CP15 ?
+ (arch_timer_uses_ppi == ARCH_TIMER_VIRT_PPI) ? "virt" : "phys" :
"",
- type == (ARCH_CP15_TIMER | ARCH_MEM_TIMER) ? "/" : "",
- type & ARCH_MEM_TIMER ?
+ type == (ARCH_TIMER_TYPE_CP15 | ARCH_TIMER_TYPE_MEM) ? "/" : "",
+ type & ARCH_TIMER_TYPE_MEM ?
arch_timer_mem_use_virtual ? "virt" : "phys" :
"");
}
return ((u64) vct_hi << 32) | vct_lo;
}
-/*
- * Default to cp15 based access because arm64 uses this function for
- * sched_clock() before DT is probed and the cp15 method is guaranteed
- * to exist on arm64. arm doesn't use this before DT is probed so even
- * if we don't have the cp15 accessors we won't have a problem.
- */
-u64 (*arch_timer_read_counter)(void) = arch_counter_get_cntvct;
-
-static u64 arch_counter_read(struct clocksource *cs)
-{
- return arch_timer_read_counter();
-}
-
-static u64 arch_counter_read_cc(const struct cyclecounter *cc)
-{
- return arch_timer_read_counter();
-}
-
-static struct clocksource clocksource_counter = {
- .name = "arch_sys_counter",
- .rating = 400,
- .read = arch_counter_read,
- .mask = CLOCKSOURCE_MASK(56),
- .flags = CLOCK_SOURCE_IS_CONTINUOUS,
-};
-
-static struct cyclecounter cyclecounter __ro_after_init = {
- .read = arch_counter_read_cc,
- .mask = CLOCKSOURCE_MASK(56),
-};
-
static struct arch_timer_kvm_info arch_timer_kvm_info;
struct arch_timer_kvm_info *arch_timer_get_kvm_info(void)
u64 start_count;
/* Register the CP15 based counter if we have one */
- if (type & ARCH_CP15_TIMER) {
- if (IS_ENABLED(CONFIG_ARM64) || arch_timer_uses_ppi == VIRT_PPI)
+ if (type & ARCH_TIMER_TYPE_CP15) {
+ if (IS_ENABLED(CONFIG_ARM64) ||
+ arch_timer_uses_ppi == ARCH_TIMER_VIRT_PPI)
arch_timer_read_counter = arch_counter_get_cntvct;
else
arch_timer_read_counter = arch_counter_get_cntpct;
- clocksource_counter.archdata.vdso_direct = true;
-
-#ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND
- /*
- * Don't use the vdso fastpath if errata require using
- * the out-of-line counter accessor.
- */
- if (static_branch_unlikely(&arch_timer_read_ool_enabled))
- clocksource_counter.archdata.vdso_direct = false;
-#endif
+ clocksource_counter.archdata.vdso_direct = vdso_default;
} else {
arch_timer_read_counter = arch_counter_get_cntvct_mem;
}
static void arch_timer_stop(struct clock_event_device *clk)
{
- pr_debug("arch_timer_teardown disable IRQ%d cpu #%d\n",
- clk->irq, smp_processor_id());
+ pr_debug("disable IRQ%d cpu #%d\n", clk->irq, smp_processor_id());
disable_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi]);
if (arch_timer_has_nonsecure_ppi())
- disable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI]);
+ disable_percpu_irq(arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI]);
clk->set_state_shutdown(clk);
}
}
#ifdef CONFIG_CPU_PM
-static unsigned int saved_cntkctl;
+static DEFINE_PER_CPU(unsigned long, saved_cntkctl);
static int arch_timer_cpu_pm_notify(struct notifier_block *self,
unsigned long action, void *hcpu)
{
if (action == CPU_PM_ENTER)
- saved_cntkctl = arch_timer_get_cntkctl();
+ __this_cpu_write(saved_cntkctl, arch_timer_get_cntkctl());
else if (action == CPU_PM_ENTER_FAILED || action == CPU_PM_EXIT)
- arch_timer_set_cntkctl(saved_cntkctl);
+ arch_timer_set_cntkctl(__this_cpu_read(saved_cntkctl));
return NOTIFY_OK;
}
ppi = arch_timer_ppi[arch_timer_uses_ppi];
switch (arch_timer_uses_ppi) {
- case VIRT_PPI:
+ case ARCH_TIMER_VIRT_PPI:
err = request_percpu_irq(ppi, arch_timer_handler_virt,
"arch_timer", arch_timer_evt);
break;
- case PHYS_SECURE_PPI:
- case PHYS_NONSECURE_PPI:
+ case ARCH_TIMER_PHYS_SECURE_PPI:
+ case ARCH_TIMER_PHYS_NONSECURE_PPI:
err = request_percpu_irq(ppi, arch_timer_handler_phys,
"arch_timer", arch_timer_evt);
- if (!err && arch_timer_ppi[PHYS_NONSECURE_PPI]) {
- ppi = arch_timer_ppi[PHYS_NONSECURE_PPI];
+ if (!err && arch_timer_has_nonsecure_ppi()) {
+ ppi = arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI];
err = request_percpu_irq(ppi, arch_timer_handler_phys,
"arch_timer", arch_timer_evt);
if (err)
- free_percpu_irq(arch_timer_ppi[PHYS_SECURE_PPI],
+ free_percpu_irq(arch_timer_ppi[ARCH_TIMER_PHYS_SECURE_PPI],
arch_timer_evt);
}
break;
- case HYP_PPI:
+ case ARCH_TIMER_HYP_PPI:
err = request_percpu_irq(ppi, arch_timer_handler_phys,
"arch_timer", arch_timer_evt);
break;
}
if (err) {
- pr_err("arch_timer: can't register interrupt %d (%d)\n",
- ppi, err);
+ pr_err("can't register interrupt %d (%d)\n", ppi, err);
goto out_free;
}
out_unreg_notify:
free_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi], arch_timer_evt);
if (arch_timer_has_nonsecure_ppi())
- free_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI],
+ free_percpu_irq(arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI],
arch_timer_evt);
out_free:
t->base = base;
t->evt.irq = irq;
- __arch_timer_setup(ARCH_MEM_TIMER, &t->evt);
+ __arch_timer_setup(ARCH_TIMER_TYPE_MEM, &t->evt);
if (arch_timer_mem_use_virtual)
func = arch_timer_handler_virt_mem;
ret = request_irq(irq, func, IRQF_TIMER, "arch_mem_timer", &t->evt);
if (ret) {
- pr_err("arch_timer: Failed to request mem timer irq\n");
+ pr_err("Failed to request mem timer irq\n");
kfree(t);
}
{},
};
-static bool __init
-arch_timer_needs_probing(int type, const struct of_device_id *matches)
+static bool __init arch_timer_needs_of_probing(void)
{
struct device_node *dn;
bool needs_probing = false;
+ unsigned int mask = ARCH_TIMER_TYPE_CP15 | ARCH_TIMER_TYPE_MEM;
+
+ /* We have two timers, and both device-tree nodes are probed. */
+ if ((arch_timers_present & mask) == mask)
+ return false;
- dn = of_find_matching_node(NULL, matches);
- if (dn && of_device_is_available(dn) && !(arch_timers_present & type))
+ /*
+ * Only one type of timer is probed,
+ * check if we have another type of timer node in device-tree.
+ */
+ if (arch_timers_present & ARCH_TIMER_TYPE_CP15)
+ dn = of_find_matching_node(NULL, arch_timer_mem_of_match);
+ else
+ dn = of_find_matching_node(NULL, arch_timer_of_match);
+
+ if (dn && of_device_is_available(dn))
needs_probing = true;
+
of_node_put(dn);
return needs_probing;
static int __init arch_timer_common_init(void)
{
- unsigned mask = ARCH_CP15_TIMER | ARCH_MEM_TIMER;
-
- /* Wait until both nodes are probed if we have two timers */
- if ((arch_timers_present & mask) != mask) {
- if (arch_timer_needs_probing(ARCH_MEM_TIMER, arch_timer_mem_of_match))
- return 0;
- if (arch_timer_needs_probing(ARCH_CP15_TIMER, arch_timer_of_match))
- return 0;
- }
-
arch_timer_banner(arch_timers_present);
arch_counter_register(arch_timers_present);
return arch_timer_arch_init();
}
-static int __init arch_timer_init(void)
+/**
+ * arch_timer_select_ppi() - Select suitable PPI for the current system.
+ *
+ * If HYP mode is available, we know that the physical timer
+ * has been configured to be accessible from PL1. Use it, so
+ * that a guest can use the virtual timer instead.
+ *
+ * On ARMv8.1 with VH extensions, the kernel runs in HYP. VHE
+ * accesses to CNTP_*_EL1 registers are silently redirected to
+ * their CNTHP_*_EL2 counterparts, and use a different PPI
+ * number.
+ *
+ * If no interrupt provided for virtual timer, we'll have to
+ * stick to the physical timer. It'd better be accessible...
+ * For arm64 we never use the secure interrupt.
+ *
+ * Return: a suitable PPI type for the current system.
+ */
+static enum arch_timer_ppi_nr __init arch_timer_select_ppi(void)
{
- int ret;
- /*
- * If HYP mode is available, we know that the physical timer
- * has been configured to be accessible from PL1. Use it, so
- * that a guest can use the virtual timer instead.
- *
- * If no interrupt provided for virtual timer, we'll have to
- * stick to the physical timer. It'd better be accessible...
- *
- * On ARMv8.1 with VH extensions, the kernel runs in HYP. VHE
- * accesses to CNTP_*_EL1 registers are silently redirected to
- * their CNTHP_*_EL2 counterparts, and use a different PPI
- * number.
- */
- if (is_hyp_mode_available() || !arch_timer_ppi[VIRT_PPI]) {
- bool has_ppi;
-
- if (is_kernel_in_hyp_mode()) {
- arch_timer_uses_ppi = HYP_PPI;
- has_ppi = !!arch_timer_ppi[HYP_PPI];
- } else {
- arch_timer_uses_ppi = PHYS_SECURE_PPI;
- has_ppi = (!!arch_timer_ppi[PHYS_SECURE_PPI] ||
- !!arch_timer_ppi[PHYS_NONSECURE_PPI]);
- }
-
- if (!has_ppi) {
- pr_warn("arch_timer: No interrupt available, giving up\n");
- return -EINVAL;
- }
- }
+ if (is_kernel_in_hyp_mode())
+ return ARCH_TIMER_HYP_PPI;
- ret = arch_timer_register();
- if (ret)
- return ret;
+ if (!is_hyp_mode_available() && arch_timer_ppi[ARCH_TIMER_VIRT_PPI])
+ return ARCH_TIMER_VIRT_PPI;
- ret = arch_timer_common_init();
- if (ret)
- return ret;
+ if (IS_ENABLED(CONFIG_ARM64))
+ return ARCH_TIMER_PHYS_NONSECURE_PPI;
- arch_timer_kvm_info.virtual_irq = arch_timer_ppi[VIRT_PPI];
-
- return 0;
+ return ARCH_TIMER_PHYS_SECURE_PPI;
}
static int __init arch_timer_of_init(struct device_node *np)
{
- int i;
+ int i, ret;
+ u32 rate;
- if (arch_timers_present & ARCH_CP15_TIMER) {
- pr_warn("arch_timer: multiple nodes in dt, skipping\n");
+ if (arch_timers_present & ARCH_TIMER_TYPE_CP15) {
+ pr_warn("multiple nodes in dt, skipping\n");
return 0;
}
- arch_timers_present |= ARCH_CP15_TIMER;
- for (i = PHYS_SECURE_PPI; i < MAX_TIMER_PPI; i++)
+ arch_timers_present |= ARCH_TIMER_TYPE_CP15;
+ for (i = ARCH_TIMER_PHYS_SECURE_PPI; i < ARCH_TIMER_MAX_TIMER_PPI; i++)
arch_timer_ppi[i] = irq_of_parse_and_map(np, i);
- arch_timer_detect_rate(NULL, np);
+ arch_timer_kvm_info.virtual_irq = arch_timer_ppi[ARCH_TIMER_VIRT_PPI];
+
+ rate = arch_timer_get_cntfrq();
+ arch_timer_of_configure_rate(rate, np);
arch_timer_c3stop = !of_property_read_bool(np, "always-on");
-#ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND
- for (i = 0; i < ARRAY_SIZE(ool_workarounds); i++) {
- if (of_property_read_bool(np, ool_workarounds[i].id)) {
- timer_unstable_counter_workaround = &ool_workarounds[i];
- static_branch_enable(&arch_timer_read_ool_enabled);
- pr_info("arch_timer: Enabling workaround for %s\n",
- timer_unstable_counter_workaround->id);
- break;
- }
- }
-#endif
+ /* Check for globally applicable workarounds */
+ arch_timer_check_ool_workaround(ate_match_dt, np);
/*
* If we cannot rely on firmware initializing the timer registers then
*/
if (IS_ENABLED(CONFIG_ARM) &&
of_property_read_bool(np, "arm,cpu-registers-not-fw-configured"))
- arch_timer_uses_ppi = PHYS_SECURE_PPI;
+ arch_timer_uses_ppi = ARCH_TIMER_PHYS_SECURE_PPI;
+ else
+ arch_timer_uses_ppi = arch_timer_select_ppi();
+
+ if (!arch_timer_ppi[arch_timer_uses_ppi]) {
+ pr_err("No interrupt available, giving up\n");
+ return -EINVAL;
+ }
/* On some systems, the counter stops ticking when in suspend. */
arch_counter_suspend_stop = of_property_read_bool(np,
"arm,no-tick-in-suspend");
- return arch_timer_init();
+ ret = arch_timer_register();
+ if (ret)
+ return ret;
+
+ if (arch_timer_needs_of_probing())
+ return 0;
+
+ return arch_timer_common_init();
}
CLOCKSOURCE_OF_DECLARE(armv7_arch_timer, "arm,armv7-timer", arch_timer_of_init);
CLOCKSOURCE_OF_DECLARE(armv8_arch_timer, "arm,armv8-timer", arch_timer_of_init);
-static int __init arch_timer_mem_init(struct device_node *np)
+static u32 __init
+arch_timer_mem_frame_get_cntfrq(struct arch_timer_mem_frame *frame)
{
- struct device_node *frame, *best_frame = NULL;
- void __iomem *cntctlbase, *base;
- unsigned int irq, ret = -EINVAL;
+ void __iomem *base;
+ u32 rate;
+
+ base = ioremap(frame->cntbase, frame->size);
+ if (!base) {
+ pr_err("Unable to map frame @ %pa\n", &frame->cntbase);
+ return 0;
+ }
+
+ rate = readl_relaxed(frame + CNTFRQ);
+
+ iounmap(frame);
+
+ return rate;
+}
+
+static struct arch_timer_mem_frame * __init
+arch_timer_mem_find_best_frame(struct arch_timer_mem *timer_mem)
+{
+ struct arch_timer_mem_frame *frame, *best_frame = NULL;
+ void __iomem *cntctlbase;
u32 cnttidr;
+ int i;
- arch_timers_present |= ARCH_MEM_TIMER;
- cntctlbase = of_iomap(np, 0);
+ cntctlbase = ioremap(timer_mem->cntctlbase, timer_mem->size);
if (!cntctlbase) {
- pr_err("arch_timer: Can't find CNTCTLBase\n");
- return -ENXIO;
+ pr_err("Can't map CNTCTLBase @ %pa\n",
+ &timer_mem->cntctlbase);
+ return NULL;
}
cnttidr = readl_relaxed(cntctlbase + CNTTIDR);
* Try to find a virtual capable frame. Otherwise fall back to a
* physical capable frame.
*/
- for_each_available_child_of_node(np, frame) {
- int n;
- u32 cntacr;
+ for (i = 0; i < ARCH_TIMER_MEM_MAX_FRAMES; i++) {
+ u32 cntacr = CNTACR_RFRQ | CNTACR_RWPT | CNTACR_RPCT |
+ CNTACR_RWVT | CNTACR_RVOFF | CNTACR_RVCT;
- if (of_property_read_u32(frame, "frame-number", &n)) {
- pr_err("arch_timer: Missing frame-number\n");
- of_node_put(frame);
- goto out;
- }
+ frame = &timer_mem->frame[i];
+ if (!frame->valid)
+ continue;
/* Try enabling everything, and see what sticks */
- cntacr = CNTACR_RFRQ | CNTACR_RWPT | CNTACR_RPCT |
- CNTACR_RWVT | CNTACR_RVOFF | CNTACR_RVCT;
- writel_relaxed(cntacr, cntctlbase + CNTACR(n));
- cntacr = readl_relaxed(cntctlbase + CNTACR(n));
+ writel_relaxed(cntacr, cntctlbase + CNTACR(i));
+ cntacr = readl_relaxed(cntctlbase + CNTACR(i));
- if ((cnttidr & CNTTIDR_VIRT(n)) &&
+ if ((cnttidr & CNTTIDR_VIRT(i)) &&
!(~cntacr & (CNTACR_RWVT | CNTACR_RVCT))) {
- of_node_put(best_frame);
best_frame = frame;
arch_timer_mem_use_virtual = true;
break;
if (~cntacr & (CNTACR_RWPT | CNTACR_RPCT))
continue;
- of_node_put(best_frame);
- best_frame = of_node_get(frame);
+ best_frame = frame;
}
- ret= -ENXIO;
- base = arch_counter_base = of_io_request_and_map(best_frame, 0,
- "arch_mem_timer");
- if (IS_ERR(base)) {
- pr_err("arch_timer: Can't map frame's registers\n");
- goto out;
- }
+ iounmap(cntctlbase);
+
+ if (!best_frame)
+ pr_err("Unable to find a suitable frame in timer @ %pa\n",
+ &timer_mem->cntctlbase);
+
+ return frame;
+}
+
+static int __init
+arch_timer_mem_frame_register(struct arch_timer_mem_frame *frame)
+{
+ void __iomem *base;
+ int ret, irq = 0;
if (arch_timer_mem_use_virtual)
- irq = irq_of_parse_and_map(best_frame, 1);
+ irq = frame->virt_irq;
else
- irq = irq_of_parse_and_map(best_frame, 0);
+ irq = frame->phys_irq;
- ret = -EINVAL;
if (!irq) {
- pr_err("arch_timer: Frame missing %s irq",
+ pr_err("Frame missing %s irq.\n",
arch_timer_mem_use_virtual ? "virt" : "phys");
- goto out;
+ return -EINVAL;
+ }
+
+ if (!request_mem_region(frame->cntbase, frame->size,
+ "arch_mem_timer"))
+ return -EBUSY;
+
+ base = ioremap(frame->cntbase, frame->size);
+ if (!base) {
+ pr_err("Can't map frame's registers\n");
+ return -ENXIO;
}
- arch_timer_detect_rate(base, np);
ret = arch_timer_mem_register(base, irq);
- if (ret)
+ if (ret) {
+ iounmap(base);
+ return ret;
+ }
+
+ arch_counter_base = base;
+ arch_timers_present |= ARCH_TIMER_TYPE_MEM;
+
+ return 0;
+}
+
+static int __init arch_timer_mem_of_init(struct device_node *np)
+{
+ struct arch_timer_mem *timer_mem;
+ struct arch_timer_mem_frame *frame;
+ struct device_node *frame_node;
+ struct resource res;
+ int ret = -EINVAL;
+ u32 rate;
+
+ timer_mem = kzalloc(sizeof(*timer_mem), GFP_KERNEL);
+ if (!timer_mem)
+ return -ENOMEM;
+
+ if (of_address_to_resource(np, 0, &res))
goto out;
+ timer_mem->cntctlbase = res.start;
+ timer_mem->size = resource_size(&res);
- return arch_timer_common_init();
+ for_each_available_child_of_node(np, frame_node) {
+ u32 n;
+ struct arch_timer_mem_frame *frame;
+
+ if (of_property_read_u32(frame_node, "frame-number", &n)) {
+ pr_err(FW_BUG "Missing frame-number.\n");
+ of_node_put(frame_node);
+ goto out;
+ }
+ if (n >= ARCH_TIMER_MEM_MAX_FRAMES) {
+ pr_err(FW_BUG "Wrong frame-number, only 0-%u are permitted.\n",
+ ARCH_TIMER_MEM_MAX_FRAMES - 1);
+ of_node_put(frame_node);
+ goto out;
+ }
+ frame = &timer_mem->frame[n];
+
+ if (frame->valid) {
+ pr_err(FW_BUG "Duplicated frame-number.\n");
+ of_node_put(frame_node);
+ goto out;
+ }
+
+ if (of_address_to_resource(frame_node, 0, &res)) {
+ of_node_put(frame_node);
+ goto out;
+ }
+ frame->cntbase = res.start;
+ frame->size = resource_size(&res);
+
+ frame->virt_irq = irq_of_parse_and_map(frame_node,
+ ARCH_TIMER_VIRT_SPI);
+ frame->phys_irq = irq_of_parse_and_map(frame_node,
+ ARCH_TIMER_PHYS_SPI);
+
+ frame->valid = true;
+ }
+
+ frame = arch_timer_mem_find_best_frame(timer_mem);
+ if (!frame) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ rate = arch_timer_mem_frame_get_cntfrq(frame);
+ arch_timer_of_configure_rate(rate, np);
+
+ ret = arch_timer_mem_frame_register(frame);
+ if (!ret && !arch_timer_needs_of_probing())
+ ret = arch_timer_common_init();
out:
- iounmap(cntctlbase);
- of_node_put(best_frame);
+ kfree(timer_mem);
return ret;
}
CLOCKSOURCE_OF_DECLARE(armv7_arch_timer_mem, "arm,armv7-timer-mem",
- arch_timer_mem_init);
+ arch_timer_mem_of_init);
-#ifdef CONFIG_ACPI
-static int __init map_generic_timer_interrupt(u32 interrupt, u32 flags)
+#ifdef CONFIG_ACPI_GTDT
+static int __init
+arch_timer_mem_verify_cntfrq(struct arch_timer_mem *timer_mem)
{
- int trigger, polarity;
+ struct arch_timer_mem_frame *frame;
+ u32 rate;
+ int i;
- if (!interrupt)
- return 0;
+ for (i = 0; i < ARCH_TIMER_MEM_MAX_FRAMES; i++) {
+ frame = &timer_mem->frame[i];
- trigger = (flags & ACPI_GTDT_INTERRUPT_MODE) ? ACPI_EDGE_SENSITIVE
- : ACPI_LEVEL_SENSITIVE;
+ if (!frame->valid)
+ continue;
+
+ rate = arch_timer_mem_frame_get_cntfrq(frame);
+ if (rate == arch_timer_rate)
+ continue;
+
+ pr_err(FW_BUG "CNTFRQ mismatch: frame @ %pa: (0x%08lx), CPU: (0x%08lx)\n",
+ &frame->cntbase,
+ (unsigned long)rate, (unsigned long)arch_timer_rate);
- polarity = (flags & ACPI_GTDT_INTERRUPT_POLARITY) ? ACPI_ACTIVE_LOW
- : ACPI_ACTIVE_HIGH;
+ return -EINVAL;
+ }
- return acpi_register_gsi(NULL, interrupt, trigger, polarity);
+ return 0;
}
-/* Initialize per-processor generic timer */
+static int __init arch_timer_mem_acpi_init(int platform_timer_count)
+{
+ struct arch_timer_mem *timers, *timer;
+ struct arch_timer_mem_frame *frame;
+ int timer_count, i, ret = 0;
+
+ timers = kcalloc(platform_timer_count, sizeof(*timers),
+ GFP_KERNEL);
+ if (!timers)
+ return -ENOMEM;
+
+ ret = acpi_arch_timer_mem_init(timers, &timer_count);
+ if (ret || !timer_count)
+ goto out;
+
+ for (i = 0; i < timer_count; i++) {
+ ret = arch_timer_mem_verify_cntfrq(&timers[i]);
+ if (ret) {
+ pr_err("Disabling MMIO timers due to CNTFRQ mismatch\n");
+ goto out;
+ }
+ }
+
+ /*
+ * While unlikely, it's theoretically possible that none of the frames
+ * in a timer expose the combination of feature we want.
+ */
+ for (i = i; i < timer_count; i++) {
+ timer = &timers[i];
+
+ frame = arch_timer_mem_find_best_frame(timer);
+ if (frame)
+ break;
+ }
+
+ if (frame)
+ ret = arch_timer_mem_frame_register(frame);
+out:
+ kfree(timers);
+ return ret;
+}
+
+/* Initialize per-processor generic timer and memory-mapped timer(if present) */
static int __init arch_timer_acpi_init(struct acpi_table_header *table)
{
- struct acpi_table_gtdt *gtdt;
+ int ret, platform_timer_count;
- if (arch_timers_present & ARCH_CP15_TIMER) {
- pr_warn("arch_timer: already initialized, skipping\n");
+ if (arch_timers_present & ARCH_TIMER_TYPE_CP15) {
+ pr_warn("already initialized, skipping\n");
return -EINVAL;
}
- gtdt = container_of(table, struct acpi_table_gtdt, header);
+ arch_timers_present |= ARCH_TIMER_TYPE_CP15;
+
+ ret = acpi_gtdt_init(table, &platform_timer_count);
+ if (ret) {
+ pr_err("Failed to init GTDT table.\n");
+ return ret;
+ }
- arch_timers_present |= ARCH_CP15_TIMER;
+ arch_timer_ppi[ARCH_TIMER_PHYS_NONSECURE_PPI] =
+ acpi_gtdt_map_ppi(ARCH_TIMER_PHYS_NONSECURE_PPI);
- arch_timer_ppi[PHYS_SECURE_PPI] =
- map_generic_timer_interrupt(gtdt->secure_el1_interrupt,
- gtdt->secure_el1_flags);
+ arch_timer_ppi[ARCH_TIMER_VIRT_PPI] =
+ acpi_gtdt_map_ppi(ARCH_TIMER_VIRT_PPI);
- arch_timer_ppi[PHYS_NONSECURE_PPI] =
- map_generic_timer_interrupt(gtdt->non_secure_el1_interrupt,
- gtdt->non_secure_el1_flags);
+ arch_timer_ppi[ARCH_TIMER_HYP_PPI] =
+ acpi_gtdt_map_ppi(ARCH_TIMER_HYP_PPI);
- arch_timer_ppi[VIRT_PPI] =
- map_generic_timer_interrupt(gtdt->virtual_timer_interrupt,
- gtdt->virtual_timer_flags);
+ arch_timer_kvm_info.virtual_irq = arch_timer_ppi[ARCH_TIMER_VIRT_PPI];
- arch_timer_ppi[HYP_PPI] =
- map_generic_timer_interrupt(gtdt->non_secure_el2_interrupt,
- gtdt->non_secure_el2_flags);
+ /*
+ * When probing via ACPI, we have no mechanism to override the sysreg
+ * CNTFRQ value. This *must* be correct.
+ */
+ arch_timer_rate = arch_timer_get_cntfrq();
+ if (!arch_timer_rate) {
+ pr_err(FW_BUG "frequency not available.\n");
+ return -EINVAL;
+ }
- /* Get the frequency from CNTFRQ */
- arch_timer_detect_rate(NULL, NULL);
+ arch_timer_uses_ppi = arch_timer_select_ppi();
+ if (!arch_timer_ppi[arch_timer_uses_ppi]) {
+ pr_err("No interrupt available, giving up\n");
+ return -EINVAL;
+ }
/* Always-on capability */
- arch_timer_c3stop = !(gtdt->non_secure_el1_flags & ACPI_GTDT_ALWAYS_ON);
+ arch_timer_c3stop = acpi_gtdt_c3stop(arch_timer_uses_ppi);
- arch_timer_init();
- return 0;
+ /* Check for globally applicable workarounds */
+ arch_timer_check_ool_workaround(ate_match_acpi_oem_info, table);
+
+ ret = arch_timer_register();
+ if (ret)
+ return ret;
+
+ if (platform_timer_count &&
+ arch_timer_mem_acpi_init(platform_timer_count))
+ pr_err("Failed to initialize memory-mapped timer.\n");
+
+ return arch_timer_common_init();
}
CLOCKSOURCE_ACPI_DECLARE(arch_timer, ACPI_SIG_GTDT, arch_timer_acpi_init);
#endif
priv.base = of_io_request_and_map(np, 0, np->name);
if (IS_ERR(priv.base)) {
- pr_err("%s: unable to map resource", np->name);
+ pr_err("%s: unable to map resource\n", np->name);
return PTR_ERR(priv.base);
}
base = of_iomap(node, 0);
if (!base) {
- pr_err("Can't remap registers");
+ pr_err("Can't remap registers\n");
return -ENXIO;
}
ret = of_property_read_u32(node, "clock-frequency", &freq);
if (ret) {
- pr_err("Can't read clock-frequency");
+ pr_err("Can't read clock-frequency\n");
goto err_iounmap;
}
irq = irq_of_parse_and_map(node, DEFAULT_TIMER);
if (irq <= 0) {
- pr_err("Can't parse IRQ");
+ pr_err("Can't parse IRQ\n");
ret = -EINVAL;
goto err_iounmap;
}
} else if (!of_property_read_u32(node, "clock-frequency", &freq)) {
arch_timer_rate = freq;
} else {
- pr_err("Kona Timer v1 unable to determine clock-frequency");
+ pr_err("Kona Timer v1 unable to determine clock-frequency\n");
return -EINVAL;
}
ret = init_func_ret(np);
if (ret) {
- pr_err("Failed to initialize '%s': %d",
+ pr_err("Failed to initialize '%s': %d\n",
of_node_full_name(np), ret);
continue;
}
struct dw_apb_clock_event_device *dw_ced = ced_to_dw_apb_ced(evt);
if (!evt->event_handler) {
- pr_info("Spurious APBT timer interrupt %d", irq);
+ pr_info("Spurious APBT timer interrupt %d\n", irq);
return IRQ_NONE;
}
clockevents_calc_mult_shift(&dw_ced->ced, freq, APBT_MIN_PERIOD);
dw_ced->ced.max_delta_ns = clockevent_delta2ns(0x7fffffff,
&dw_ced->ced);
+ dw_ced->ced.max_delta_ticks = 0x7fffffff;
dw_ced->ced.min_delta_ns = clockevent_delta2ns(5000, &dw_ced->ced);
+ dw_ced->ced.min_delta_ticks = 5000;
dw_ced->ced.cpumask = cpumask_of(cpu);
dw_ced->ced.features = CLOCK_EVT_FEAT_PERIODIC |
CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_DYNIRQ;
int ret;
/* enable clock */
- ret = clk_prepare_enable(p->clk);
+ ret = clk_enable(p->clk);
if (ret) {
dev_err(&p->pdev->dev, "cannot enable clock\n");
return ret;
}
- /* configure channel, periodic mode and maximum timeout */
- p->rate = clk_get_rate(p->clk);
-
/* reset the counter */
em_sti_write(p, STI_SET_H, 0x40000000);
em_sti_write(p, STI_SET_L, 0x00000000);
em_sti_write(p, STI_INTENCLR, 3);
/* stop clock */
- clk_disable_unprepare(p->clk);
+ clk_disable(p->clk);
}
static u64 em_sti_count(struct em_sti_priv *p)
static int em_sti_clocksource_enable(struct clocksource *cs)
{
- int ret;
struct em_sti_priv *p = cs_to_em_sti(cs);
- ret = em_sti_start(p, USER_CLOCKSOURCE);
- if (!ret)
- __clocksource_update_freq_hz(cs, p->rate);
- return ret;
+ return em_sti_start(p, USER_CLOCKSOURCE);
}
static void em_sti_clocksource_disable(struct clocksource *cs)
dev_info(&p->pdev->dev, "used as clock source\n");
- /* Register with dummy 1 Hz value, gets updated in ->enable() */
- clocksource_register_hz(cs, 1);
+ clocksource_register_hz(cs, p->rate);
return 0;
}
dev_info(&p->pdev->dev, "used for oneshot clock events\n");
em_sti_start(p, USER_CLOCKEVENT);
- clockevents_config(&p->ced, p->rate);
return 0;
}
dev_info(&p->pdev->dev, "used for clock events\n");
- /* Register with dummy 1 Hz value, gets updated in ->set_state_oneshot() */
- clockevents_config_and_register(ced, 1, 2, 0xffffffff);
+ clockevents_config_and_register(ced, p->rate, 2, 0xffffffff);
}
static int em_sti_probe(struct platform_device *pdev)
struct em_sti_priv *p;
struct resource *res;
int irq;
+ int ret;
p = devm_kzalloc(&pdev->dev, sizeof(*p), GFP_KERNEL);
if (p == NULL)
if (IS_ERR(p->base))
return PTR_ERR(p->base);
+ if (devm_request_irq(&pdev->dev, irq, em_sti_interrupt,
+ IRQF_TIMER | IRQF_IRQPOLL | IRQF_NOBALANCING,
+ dev_name(&pdev->dev), p)) {
+ dev_err(&pdev->dev, "failed to request low IRQ\n");
+ return -ENOENT;
+ }
+
/* get hold of clock */
p->clk = devm_clk_get(&pdev->dev, "sclk");
if (IS_ERR(p->clk)) {
return PTR_ERR(p->clk);
}
- if (devm_request_irq(&pdev->dev, irq, em_sti_interrupt,
- IRQF_TIMER | IRQF_IRQPOLL | IRQF_NOBALANCING,
- dev_name(&pdev->dev), p)) {
- dev_err(&pdev->dev, "failed to request low IRQ\n");
- return -ENOENT;
+ ret = clk_prepare(p->clk);
+ if (ret < 0) {
+ dev_err(&pdev->dev, "cannot prepare clock\n");
+ return ret;
+ }
+
+ ret = clk_enable(p->clk);
+ if (ret < 0) {
+ dev_err(&p->pdev->dev, "cannot enable clock\n");
+ clk_unprepare(p->clk);
+ return ret;
}
+ p->rate = clk_get_rate(p->clk);
+ clk_disable(p->clk);
raw_spin_lock_init(&p->lock);
em_sti_register_clockevent(p);
static void timer8_clock_event_start(struct timer8_priv *p, unsigned long delta)
{
- struct clock_event_device *ced = &p->ced;
-
timer8_start(p);
-
- ced->shift = 32;
- ced->mult = div_sc(p->rate, NSEC_PER_SEC, ced->shift);
- ced->max_delta_ns = clockevent_delta2ns(0xffff, ced);
- ced->min_delta_ns = clockevent_delta2ns(0x0001, ced);
-
timer8_set_next(p, delta);
}
timer_base = of_io_request_and_map(node, 0, "meson6-timer");
if (IS_ERR(timer_base)) {
- pr_err("Can't map registers");
+ pr_err("Can't map registers\n");
return -ENXIO;
}
irq = irq_of_parse_and_map(node, 0);
if (irq <= 0) {
- pr_err("Can't parse IRQ");
+ pr_err("Can't parse IRQ\n");
return -EINVAL;
}
clk->mult = div_sc(hwtimer_freq, NSEC_PER_SEC, clk->shift);
clk->max_delta_ns = clockevent_delta2ns(0x7fffffff, clk);
+ clk->max_delta_ticks = 0x7fffffff;
clk->min_delta_ns = clockevent_delta2ns(0xf, clk);
+ clk->min_delta_ticks = 0xf;
clk->cpumask = cpumask_of(cpu);
clockevents_register_device(clk);
return ret;
}
-void __init gic_clocksource_init(unsigned int frequency)
-{
- gic_frequency = frequency;
- gic_timer_irq = MIPS_GIC_IRQ_BASE +
- GIC_LOCAL_TO_HWIRQ(GIC_LOCAL_INT_COMPARE);
-
- __gic_clocksource_init();
- gic_clockevent_init();
-
- /* And finally start the counter */
- gic_start_count();
-}
-
static int __init gic_clocksource_of_init(struct device_node *node)
{
struct clk *clk;
if (!gic_present || !node->parent ||
!of_device_is_compatible(node->parent, "mti,gic")) {
- pr_warn("No DT definition for the mips gic driver");
+ pr_warn("No DT definition for the mips gic driver\n");
return -ENXIO;
}
base = of_iomap(node, 0);
if (!base) {
- pr_err("Can't remap registers");
+ pr_err("Can't remap registers\n");
return -ENXIO;
}
pclk = of_clk_get_by_name(node, "apb_pclk");
if (IS_ERR(pclk)) {
- pr_err("could not get apb_pclk");
+ pr_err("could not get apb_pclk\n");
return PTR_ERR(pclk);
}
clk = of_clk_get_by_name(node, "timclk");
if (IS_ERR(clk)) {
- pr_err("could not get timclk");
+ pr_err("could not get timclk\n");
return PTR_ERR(clk);
}
irq = irq_of_parse_and_map(node, 0);
if (irq <= 0) {
- pr_err("Can't parse IRQ");
+ pr_err("Can't parse IRQ\n");
return -EINVAL;
}
.mult = 1,
.shift = 0,
.min_delta_ns = 1250,
+ .min_delta_ticks = 1250,
.max_delta_ns = LONG_MAX,
+ .max_delta_ticks = LONG_MAX,
};
static void numachip_timer_interrupt(void)
ret = setup_irq(irq, &pxa_ost0_irq);
if (ret) {
- pr_err("Failed to setup irq");
+ pr_err("Failed to setup irq\n");
return ret;
}
ret = clocksource_mmio_init(timer_base + OSCR, "oscr0", clock_tick_rate, 200,
32, clocksource_mmio_readl_up);
if (ret) {
- pr_err("Failed to init clocksource");
+ pr_err("Failed to init clocksource\n");
return ret;
}
ret = clk_prepare_enable(clk);
if (ret) {
- pr_crit("Failed to prepare clock");
+ pr_crit("Failed to prepare clock\n");
return ret;
}
#include <linux/clockchips.h>
#include <linux/init.h>
#include <linux/interrupt.h>
+#include <linux/sched_clock.h>
+#include <linux/slab.h>
#include <linux/of.h>
#include <linux/of_address.h>
#include <linux/of_irq.h>
#define TIMER_LOAD_COUNT0 0x00
#define TIMER_LOAD_COUNT1 0x04
+#define TIMER_CURRENT_VALUE0 0x08
+#define TIMER_CURRENT_VALUE1 0x0C
#define TIMER_CONTROL_REG3288 0x10
#define TIMER_CONTROL_REG3399 0x1c
#define TIMER_INT_STATUS 0x18
#define TIMER_MODE_USER_DEFINED_COUNT (1 << 1)
#define TIMER_INT_UNMASK (1 << 2)
-struct bc_timer {
- struct clock_event_device ce;
+struct rk_timer {
void __iomem *base;
void __iomem *ctrl;
+ struct clk *clk;
+ struct clk *pclk;
u32 freq;
+ int irq;
};
-static struct bc_timer bc_timer;
-
-static inline struct bc_timer *rk_timer(struct clock_event_device *ce)
-{
- return container_of(ce, struct bc_timer, ce);
-}
+struct rk_clkevt {
+ struct clock_event_device ce;
+ struct rk_timer timer;
+};
-static inline void __iomem *rk_base(struct clock_event_device *ce)
-{
- return rk_timer(ce)->base;
-}
+static struct rk_clkevt *rk_clkevt;
+static struct rk_timer *rk_clksrc;
-static inline void __iomem *rk_ctrl(struct clock_event_device *ce)
+static inline struct rk_timer *rk_timer(struct clock_event_device *ce)
{
- return rk_timer(ce)->ctrl;
+ return &container_of(ce, struct rk_clkevt, ce)->timer;
}
-static inline void rk_timer_disable(struct clock_event_device *ce)
+static inline void rk_timer_disable(struct rk_timer *timer)
{
- writel_relaxed(TIMER_DISABLE, rk_ctrl(ce));
+ writel_relaxed(TIMER_DISABLE, timer->ctrl);
}
-static inline void rk_timer_enable(struct clock_event_device *ce, u32 flags)
+static inline void rk_timer_enable(struct rk_timer *timer, u32 flags)
{
- writel_relaxed(TIMER_ENABLE | TIMER_INT_UNMASK | flags,
- rk_ctrl(ce));
+ writel_relaxed(TIMER_ENABLE | flags, timer->ctrl);
}
static void rk_timer_update_counter(unsigned long cycles,
- struct clock_event_device *ce)
+ struct rk_timer *timer)
{
- writel_relaxed(cycles, rk_base(ce) + TIMER_LOAD_COUNT0);
- writel_relaxed(0, rk_base(ce) + TIMER_LOAD_COUNT1);
+ writel_relaxed(cycles, timer->base + TIMER_LOAD_COUNT0);
+ writel_relaxed(0, timer->base + TIMER_LOAD_COUNT1);
}
-static void rk_timer_interrupt_clear(struct clock_event_device *ce)
+static void rk_timer_interrupt_clear(struct rk_timer *timer)
{
- writel_relaxed(1, rk_base(ce) + TIMER_INT_STATUS);
+ writel_relaxed(1, timer->base + TIMER_INT_STATUS);
}
static inline int rk_timer_set_next_event(unsigned long cycles,
struct clock_event_device *ce)
{
- rk_timer_disable(ce);
- rk_timer_update_counter(cycles, ce);
- rk_timer_enable(ce, TIMER_MODE_USER_DEFINED_COUNT);
+ struct rk_timer *timer = rk_timer(ce);
+
+ rk_timer_disable(timer);
+ rk_timer_update_counter(cycles, timer);
+ rk_timer_enable(timer, TIMER_MODE_USER_DEFINED_COUNT |
+ TIMER_INT_UNMASK);
return 0;
}
static int rk_timer_shutdown(struct clock_event_device *ce)
{
- rk_timer_disable(ce);
+ struct rk_timer *timer = rk_timer(ce);
+
+ rk_timer_disable(timer);
return 0;
}
static int rk_timer_set_periodic(struct clock_event_device *ce)
{
- rk_timer_disable(ce);
- rk_timer_update_counter(rk_timer(ce)->freq / HZ - 1, ce);
- rk_timer_enable(ce, TIMER_MODE_FREE_RUNNING);
+ struct rk_timer *timer = rk_timer(ce);
+
+ rk_timer_disable(timer);
+ rk_timer_update_counter(timer->freq / HZ - 1, timer);
+ rk_timer_enable(timer, TIMER_MODE_FREE_RUNNING | TIMER_INT_UNMASK);
return 0;
}
static irqreturn_t rk_timer_interrupt(int irq, void *dev_id)
{
struct clock_event_device *ce = dev_id;
+ struct rk_timer *timer = rk_timer(ce);
- rk_timer_interrupt_clear(ce);
+ rk_timer_interrupt_clear(timer);
if (clockevent_state_oneshot(ce))
- rk_timer_disable(ce);
+ rk_timer_disable(timer);
ce->event_handler(ce);
return IRQ_HANDLED;
}
-static int __init rk_timer_init(struct device_node *np, u32 ctrl_reg)
+static u64 notrace rk_timer_sched_read(void)
+{
+ return ~readl_relaxed(rk_clksrc->base + TIMER_CURRENT_VALUE0);
+}
+
+static int __init
+rk_timer_probe(struct rk_timer *timer, struct device_node *np)
{
- struct clock_event_device *ce = &bc_timer.ce;
struct clk *timer_clk;
struct clk *pclk;
int ret = -EINVAL, irq;
+ u32 ctrl_reg = TIMER_CONTROL_REG3288;
- bc_timer.base = of_iomap(np, 0);
- if (!bc_timer.base) {
+ timer->base = of_iomap(np, 0);
+ if (!timer->base) {
pr_err("Failed to get base address for '%s'\n", TIMER_NAME);
return -ENXIO;
}
- bc_timer.ctrl = bc_timer.base + ctrl_reg;
+
+ if (of_device_is_compatible(np, "rockchip,rk3399-timer"))
+ ctrl_reg = TIMER_CONTROL_REG3399;
+
+ timer->ctrl = timer->base + ctrl_reg;
pclk = of_clk_get_by_name(np, "pclk");
if (IS_ERR(pclk)) {
pr_err("Failed to enable pclk for '%s'\n", TIMER_NAME);
goto out_unmap;
}
+ timer->pclk = pclk;
timer_clk = of_clk_get_by_name(np, "timer");
if (IS_ERR(timer_clk)) {
pr_err("Failed to enable timer clock\n");
goto out_timer_clk;
}
+ timer->clk = timer_clk;
- bc_timer.freq = clk_get_rate(timer_clk);
+ timer->freq = clk_get_rate(timer_clk);
irq = irq_of_parse_and_map(np, 0);
if (!irq) {
pr_err("Failed to map interrupts for '%s'\n", TIMER_NAME);
goto out_irq;
}
+ timer->irq = irq;
+
+ rk_timer_interrupt_clear(timer);
+ rk_timer_disable(timer);
+ return 0;
+
+out_irq:
+ clk_disable_unprepare(timer_clk);
+out_timer_clk:
+ clk_disable_unprepare(pclk);
+out_unmap:
+ iounmap(timer->base);
+
+ return ret;
+}
+
+static void __init rk_timer_cleanup(struct rk_timer *timer)
+{
+ clk_disable_unprepare(timer->clk);
+ clk_disable_unprepare(timer->pclk);
+ iounmap(timer->base);
+}
+
+static int __init rk_clkevt_init(struct device_node *np)
+{
+ struct clock_event_device *ce;
+ int ret = -EINVAL;
+
+ rk_clkevt = kzalloc(sizeof(struct rk_clkevt), GFP_KERNEL);
+ if (!rk_clkevt) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ ret = rk_timer_probe(&rk_clkevt->timer, np);
+ if (ret)
+ goto out_probe;
+
+ ce = &rk_clkevt->ce;
ce->name = TIMER_NAME;
ce->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT |
CLOCK_EVT_FEAT_DYNIRQ;
ce->set_next_event = rk_timer_set_next_event;
ce->set_state_shutdown = rk_timer_shutdown;
ce->set_state_periodic = rk_timer_set_periodic;
- ce->irq = irq;
+ ce->irq = rk_clkevt->timer.irq;
ce->cpumask = cpu_possible_mask;
ce->rating = 250;
- rk_timer_interrupt_clear(ce);
- rk_timer_disable(ce);
-
- ret = request_irq(irq, rk_timer_interrupt, IRQF_TIMER, TIMER_NAME, ce);
+ ret = request_irq(rk_clkevt->timer.irq, rk_timer_interrupt, IRQF_TIMER,
+ TIMER_NAME, ce);
if (ret) {
- pr_err("Failed to initialize '%s': %d\n", TIMER_NAME, ret);
+ pr_err("Failed to initialize '%s': %d\n",
+ TIMER_NAME, ret);
goto out_irq;
}
- clockevents_config_and_register(ce, bc_timer.freq, 1, UINT_MAX);
-
+ clockevents_config_and_register(&rk_clkevt->ce,
+ rk_clkevt->timer.freq, 1, UINT_MAX);
return 0;
out_irq:
- clk_disable_unprepare(timer_clk);
-out_timer_clk:
- clk_disable_unprepare(pclk);
-out_unmap:
- iounmap(bc_timer.base);
-
+ rk_timer_cleanup(&rk_clkevt->timer);
+out_probe:
+ kfree(rk_clkevt);
+out:
+ /* Leave rk_clkevt not NULL to prevent future init */
+ rk_clkevt = ERR_PTR(ret);
return ret;
}
-static int __init rk3288_timer_init(struct device_node *np)
+static int __init rk_clksrc_init(struct device_node *np)
{
- return rk_timer_init(np, TIMER_CONTROL_REG3288);
+ int ret = -EINVAL;
+
+ rk_clksrc = kzalloc(sizeof(struct rk_timer), GFP_KERNEL);
+ if (!rk_clksrc) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ ret = rk_timer_probe(rk_clksrc, np);
+ if (ret)
+ goto out_probe;
+
+ rk_timer_update_counter(UINT_MAX, rk_clksrc);
+ rk_timer_enable(rk_clksrc, 0);
+
+ ret = clocksource_mmio_init(rk_clksrc->base + TIMER_CURRENT_VALUE0,
+ TIMER_NAME, rk_clksrc->freq, 250, 32,
+ clocksource_mmio_readl_down);
+ if (ret) {
+ pr_err("Failed to register clocksource");
+ goto out_clocksource;
+ }
+
+ sched_clock_register(rk_timer_sched_read, 32, rk_clksrc->freq);
+ return 0;
+
+out_clocksource:
+ rk_timer_cleanup(rk_clksrc);
+out_probe:
+ kfree(rk_clksrc);
+out:
+ /* Leave rk_clksrc not NULL to prevent future init */
+ rk_clksrc = ERR_PTR(ret);
+ return ret;
}
-static int __init rk3399_timer_init(struct device_node *np)
+static int __init rk_timer_init(struct device_node *np)
{
- return rk_timer_init(np, TIMER_CONTROL_REG3399);
+ if (!rk_clkevt)
+ return rk_clkevt_init(np);
+
+ if (!rk_clksrc)
+ return rk_clksrc_init(np);
+
+ pr_err("Too many timer definitions for '%s'\n", TIMER_NAME);
+ return -EINVAL;
}
-CLOCKSOURCE_OF_DECLARE(rk3288_timer, "rockchip,rk3288-timer",
- rk3288_timer_init);
-CLOCKSOURCE_OF_DECLARE(rk3399_timer, "rockchip,rk3399-timer",
- rk3399_timer_init);
+CLOCKSOURCE_OF_DECLARE(rk3288_timer, "rockchip,rk3288-timer", rk_timer_init);
+CLOCKSOURCE_OF_DECLARE(rk3399_timer, "rockchip,rk3399-timer", rk_timer_init);
mask = ~pwm.variant.output_mask & ((1 << SAMSUNG_PWM_NUM) - 1);
channel = fls(mask) - 1;
if (channel < 0) {
- pr_crit("failed to find PWM channel for clocksource");
+ pr_crit("failed to find PWM channel for clocksource\n");
return -EINVAL;
}
pwm.source_id = channel;
mask &= ~(1 << channel);
channel = fls(mask) - 1;
if (channel < 0) {
- pr_crit("failed to find PWM channel for clock event");
+ pr_crit("failed to find PWM channel for clock event\n");
return -EINVAL;
}
pwm.event_id = channel;
pwm.timerclk = of_clk_get_by_name(np, "timers");
if (IS_ERR(pwm.timerclk)) {
- pr_crit("failed to get timers clock for timer");
+ pr_crit("failed to get timers clock for timer\n");
return PTR_ERR(pwm.timerclk);
}
unsigned long match_value;
unsigned long next_match_value;
unsigned long max_match_value;
- unsigned long rate;
raw_spinlock_t lock;
struct clock_event_device ced;
struct clocksource cs;
void __iomem *mapbase;
struct clk *clk;
+ unsigned long rate;
raw_spinlock_t lock; /* Protect the shared start/stop register */
raw_spin_unlock_irqrestore(&ch->cmt->lock, flags);
}
-static int sh_cmt_enable(struct sh_cmt_channel *ch, unsigned long *rate)
+static int sh_cmt_enable(struct sh_cmt_channel *ch)
{
int k, ret;
/* configure channel, periodic mode and maximum timeout */
if (ch->cmt->info->width == 16) {
- *rate = clk_get_rate(ch->cmt->clk) / 512;
sh_cmt_write_cmcsr(ch, SH_CMT16_CMCSR_CMIE |
SH_CMT16_CMCSR_CKS512);
} else {
- *rate = clk_get_rate(ch->cmt->clk) / 8;
sh_cmt_write_cmcsr(ch, SH_CMT32_CMCSR_CMM |
SH_CMT32_CMCSR_CMTOUT_IE |
SH_CMT32_CMCSR_CMR_IRQ |
raw_spin_lock_irqsave(&ch->lock, flags);
if (!(ch->flags & (FLAG_CLOCKEVENT | FLAG_CLOCKSOURCE)))
- ret = sh_cmt_enable(ch, &ch->rate);
+ ret = sh_cmt_enable(ch);
if (ret)
goto out;
ch->total_cycles = 0;
ret = sh_cmt_start(ch, FLAG_CLOCKSOURCE);
- if (!ret) {
- __clocksource_update_freq_hz(cs, ch->rate);
+ if (!ret)
ch->cs_enabled = true;
- }
+
return ret;
}
dev_info(&ch->cmt->pdev->dev, "ch%u: used as clock source\n",
ch->index);
- /* Register with dummy 1 Hz value, gets updated in ->enable() */
- clocksource_register_hz(cs, 1);
+ clocksource_register_hz(cs, ch->cmt->rate);
return 0;
}
static void sh_cmt_clock_event_start(struct sh_cmt_channel *ch, int periodic)
{
- struct clock_event_device *ced = &ch->ced;
-
sh_cmt_start(ch, FLAG_CLOCKEVENT);
- /* TODO: calculate good shift from rate and counter bit width */
-
- ced->shift = 32;
- ced->mult = div_sc(ch->rate, NSEC_PER_SEC, ced->shift);
- ced->max_delta_ns = clockevent_delta2ns(ch->max_match_value, ced);
- ced->min_delta_ns = clockevent_delta2ns(0x1f, ced);
-
if (periodic)
- sh_cmt_set_next(ch, ((ch->rate + HZ/2) / HZ) - 1);
+ sh_cmt_set_next(ch, ((ch->cmt->rate + HZ/2) / HZ) - 1);
else
sh_cmt_set_next(ch, ch->max_match_value);
}
ced->suspend = sh_cmt_clock_event_suspend;
ced->resume = sh_cmt_clock_event_resume;
+ /* TODO: calculate good shift from rate and counter bit width */
+ ced->shift = 32;
+ ced->mult = div_sc(ch->cmt->rate, NSEC_PER_SEC, ced->shift);
+ ced->max_delta_ns = clockevent_delta2ns(ch->max_match_value, ced);
+ ced->max_delta_ticks = ch->max_match_value;
+ ced->min_delta_ns = clockevent_delta2ns(0x1f, ced);
+ ced->min_delta_ticks = 0x1f;
+
dev_info(&ch->cmt->pdev->dev, "ch%u: used for clock events\n",
ch->index);
clockevents_register_device(ced);
if (ret < 0)
goto err_clk_put;
+ /* Determine clock rate. */
+ ret = clk_enable(cmt->clk);
+ if (ret < 0)
+ goto err_clk_unprepare;
+
+ if (cmt->info->width == 16)
+ cmt->rate = clk_get_rate(cmt->clk) / 512;
+ else
+ cmt->rate = clk_get_rate(cmt->clk) / 8;
+
+ clk_disable(cmt->clk);
+
/* Map the memory resource(s). */
ret = sh_cmt_map_memory(cmt);
if (ret < 0)
void __iomem *base;
int irq;
- unsigned long rate;
unsigned long periodic;
struct clock_event_device ced;
struct clocksource cs;
void __iomem *mapbase;
struct clk *clk;
+ unsigned long rate;
enum sh_tmu_model model;
sh_tmu_write(ch, TCNT, 0xffffffff);
/* configure channel to parent clock / 4, irq off */
- ch->rate = clk_get_rate(ch->tmu->clk) / 4;
sh_tmu_write(ch, TCR, TCR_TPSC_CLK4);
/* enable channel */
return 0;
ret = sh_tmu_enable(ch);
- if (!ret) {
- __clocksource_update_freq_hz(cs, ch->rate);
+ if (!ret)
ch->cs_enabled = true;
- }
return ret;
}
dev_info(&ch->tmu->pdev->dev, "ch%u: used as clock source\n",
ch->index);
- /* Register with dummy 1 Hz value, gets updated in ->enable() */
- clocksource_register_hz(cs, 1);
+ clocksource_register_hz(cs, ch->tmu->rate);
return 0;
}
static void sh_tmu_clock_event_start(struct sh_tmu_channel *ch, int periodic)
{
- struct clock_event_device *ced = &ch->ced;
-
sh_tmu_enable(ch);
- clockevents_config(ced, ch->rate);
-
if (periodic) {
- ch->periodic = (ch->rate + HZ/2) / HZ;
+ ch->periodic = (ch->tmu->rate + HZ/2) / HZ;
sh_tmu_set_next(ch, ch->periodic, 1);
}
}
dev_info(&ch->tmu->pdev->dev, "ch%u: used for clock events\n",
ch->index);
- clockevents_config_and_register(ced, 1, 0x300, 0xffffffff);
+ clockevents_config_and_register(ced, ch->tmu->rate, 0x300, 0xffffffff);
ret = request_irq(ch->irq, sh_tmu_interrupt,
IRQF_TIMER | IRQF_IRQPOLL | IRQF_NOBALANCING,
if (ret < 0)
goto err_clk_put;
+ /* Determine clock rate. */
+ ret = clk_enable(tmu->clk);
+ if (ret < 0)
+ goto err_clk_unprepare;
+
+ tmu->rate = clk_get_rate(tmu->clk) / 4;
+ clk_disable(tmu->clk);
+
/* Map the memory resource. */
ret = sh_tmu_map_memory(tmu);
if (ret < 0) {
timer_base = of_iomap(node, 0);
if (!timer_base) {
- pr_crit("Can't map registers");
+ pr_crit("Can't map registers\n");
return -ENXIO;
}
irq = irq_of_parse_and_map(node, 0);
if (irq <= 0) {
- pr_crit("Can't parse IRQ");
+ pr_crit("Can't parse IRQ\n");
return -EINVAL;
}
clk = of_clk_get(node, 0);
if (IS_ERR(clk)) {
- pr_crit("Can't get timer clock");
+ pr_crit("Can't get timer clock\n");
return PTR_ERR(clk);
}
ret = clk_prepare_enable(clk);
if (ret) {
- pr_err("Failed to prepare clock");
+ pr_err("Failed to prepare clock\n");
return ret;
}
ret = clocksource_mmio_init(timer_base + TIMER_CNTVAL_REG(1), node->name,
rate, 350, 32, clocksource_mmio_readl_down);
if (ret) {
- pr_err("Failed to register clocksource");
+ pr_err("Failed to register clocksource\n");
return ret;
}
rtc_base = of_iomap(np, 0);
if (!rtc_base) {
- pr_err("Can't map RTC registers");
+ pr_err("Can't map RTC registers\n");
return -ENXIO;
}
timer_base = of_iomap(np, 0);
if (!timer_base) {
- pr_err("Failed to iomap");
+ pr_err("Failed to iomap\n");
return -ENXIO;
}
local_base = of_iomap(np, 1);
if (!local_base) {
- pr_err("Failed to iomap");
+ pr_err("Failed to iomap\n");
return -ENXIO;
}
"armada_370_xp_clocksource",
timer_clk, 300, 32, clocksource_mmio_readl_down);
if (res) {
- pr_err("Failed to initialize clocksource mmio");
+ pr_err("Failed to initialize clocksource mmio\n");
return res;
}
armada_370_xp_evt);
/* Immediately configure the timer on the boot CPU */
if (res) {
- pr_err("Failed to request percpu irq");
+ pr_err("Failed to request percpu irq\n");
return res;
}
armada_370_xp_timer_starting_cpu,
armada_370_xp_timer_dying_cpu);
if (res) {
- pr_err("Failed to setup hotplug state and timer");
+ pr_err("Failed to setup hotplug state and timer\n");
return res;
}
int ret;
if (IS_ERR(clk)) {
- pr_err("Failed to get clock");
+ pr_err("Failed to get clock\n");
return PTR_ERR(clk);
}
/* Must have at least a clock */
if (IS_ERR(clk)) {
- pr_err("Failed to get clock");
+ pr_err("Failed to get clock\n");
return PTR_ERR(clk);
}
clk = of_clk_get(np, 0);
if (IS_ERR(clk)) {
- pr_err("Failed to get clock");
+ pr_err("Failed to get clock\n");
return PTR_ERR(clk);
}
ret = setup_irq(irq, &efm32_clock_event_irq);
if (ret) {
- pr_err("Failed setup irq");
+ pr_err("Failed setup irq\n");
goto err_setup_irq;
}
#include <linux/bitops.h>
#include <linux/clk.h>
#include <linux/clockchips.h>
+#include <linux/delay.h>
#include <linux/interrupt.h>
#include <linux/of_address.h>
#include <linux/of_irq.h>
static void __iomem *timer_base;
+static unsigned long notrace orion_read_timer(void)
+{
+ return ~readl(timer_base + TIMER0_VAL);
+}
+
+static struct delay_timer orion_delay_timer = {
+ .read_current_timer = orion_read_timer,
+};
+
+static void orion_delay_timer_init(unsigned long rate)
+{
+ orion_delay_timer.freq = rate;
+ register_current_timer_delay(&orion_delay_timer);
+}
+
/*
* Free-running clocksource handling.
*/
static int __init orion_timer_init(struct device_node *np)
{
+ unsigned long rate;
struct clk *clk;
int irq, ret;
ret = clk_prepare_enable(clk);
if (ret) {
- pr_err("Failed to prepare clock");
+ pr_err("Failed to prepare clock\n");
return ret;
}
return -EINVAL;
}
+ rate = clk_get_rate(clk);
+
/* setup timer0 as free-running clocksource */
writel(~0, timer_base + TIMER0_VAL);
writel(~0, timer_base + TIMER0_RELOAD);
TIMER0_RELOAD_EN | TIMER0_EN,
TIMER0_RELOAD_EN | TIMER0_EN);
- ret = clocksource_mmio_init(timer_base + TIMER0_VAL, "orion_clocksource",
- clk_get_rate(clk), 300, 32,
+ ret = clocksource_mmio_init(timer_base + TIMER0_VAL,
+ "orion_clocksource", rate, 300, 32,
clocksource_mmio_readl_down);
if (ret) {
- pr_err("Failed to initialize mmio timer");
+ pr_err("Failed to initialize mmio timer\n");
return ret;
}
- sched_clock_register(orion_read_sched_clock, 32, clk_get_rate(clk));
+ sched_clock_register(orion_read_sched_clock, 32, rate);
/* setup timer1 as clockevent timer */
ret = setup_irq(irq, &orion_clkevt_irq);
ticks_per_jiffy = (clk_get_rate(clk) + HZ/2) / HZ;
orion_clkevt.cpumask = cpumask_of(0);
orion_clkevt.irq = irq;
- clockevents_config_and_register(&orion_clkevt, clk_get_rate(clk),
+ clockevents_config_and_register(&orion_clkevt, rate,
ORION_ONESHOT_MIN, ORION_ONESHOT_MAX);
+
+ orion_delay_timer_init(rate);
+
return 0;
}
CLOCKSOURCE_OF_DECLARE(orion_timer, "marvell,orion-timer", orion_timer_init);
ce->set_next_event = sirfsoc_timer_set_next_event;
clockevents_calc_mult_shift(ce, atlas7_timer_rate, 60);
ce->max_delta_ns = clockevent_delta2ns(-2, ce);
+ ce->max_delta_ticks = (unsigned long)-2;
ce->min_delta_ns = clockevent_delta2ns(2, ce);
+ ce->min_delta_ticks = 2;
ce->cpumask = cpumask_of(cpu);
action->dev_id = ce;
ret = clocksource_register_hz(&data->clksrc, pit_rate);
if (ret) {
- pr_err("Failed to register clocksource");
+ pr_err("Failed to register clocksource\n");
return ret;
}
*/
dc_timer_dev.base = of_iomap(node, 0);
if (!dc_timer_dev.base) {
- pr_err("Can't map registers");
+ pr_err("Can't map registers\n");
return -ENXIO;
}
irq = irq_of_parse_and_map(node, dc_timer_dev.timer_id);
if (irq <= 0) {
- pr_err("Can't parse IRQ");
+ pr_err("Can't parse IRQ\n");
return -EINVAL;
}
clk = of_clk_get(node, 0);
if (IS_ERR(clk)) {
- pr_err("Can't get timer clock");
+ pr_err("Can't get timer clock\n");
return PTR_ERR(clk);
}
clk_prepare_enable(clk);
/*
- * Gemini timer driver
+ * Faraday Technology FTTMR010 timer driver
* Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org>
*
* Based on a rewrite of arch/arm/mach-gemini/timer.c:
#include <linux/clockchips.h>
#include <linux/clocksource.h>
#include <linux/sched_clock.h>
-
-/*
- * Relevant registers in the global syscon
- */
-#define GLOBAL_STATUS 0x04
-#define CPU_AHB_RATIO_MASK (0x3 << 18)
-#define CPU_AHB_1_1 (0x0 << 18)
-#define CPU_AHB_3_2 (0x1 << 18)
-#define CPU_AHB_24_13 (0x2 << 18)
-#define CPU_AHB_2_1 (0x3 << 18)
-#define REG_TO_AHB_SPEED(reg) ((((reg) >> 15) & 0x7) * 10 + 130)
+#include <linux/clk.h>
/*
* Register definitions for the timers
static unsigned int tick_rate;
static void __iomem *base;
-static u64 notrace gemini_read_sched_clock(void)
+static u64 notrace fttmr010_read_sched_clock(void)
{
return readl(base + TIMER3_COUNT);
}
-static int gemini_timer_set_next_event(unsigned long cycles,
+static int fttmr010_timer_set_next_event(unsigned long cycles,
struct clock_event_device *evt)
{
u32 cr;
return 0;
}
-static int gemini_timer_shutdown(struct clock_event_device *evt)
+static int fttmr010_timer_shutdown(struct clock_event_device *evt)
{
u32 cr;
return 0;
}
-static int gemini_timer_set_periodic(struct clock_event_device *evt)
+static int fttmr010_timer_set_periodic(struct clock_event_device *evt)
{
u32 period = DIV_ROUND_CLOSEST(tick_rate, HZ);
u32 cr;
}
/* Use TIMER1 as clock event */
-static struct clock_event_device gemini_clockevent = {
+static struct clock_event_device fttmr010_clockevent = {
.name = "TIMER1",
/* Reasonably fast and accurate clock event */
.rating = 300,
.shift = 32,
.features = CLOCK_EVT_FEAT_PERIODIC |
CLOCK_EVT_FEAT_ONESHOT,
- .set_next_event = gemini_timer_set_next_event,
- .set_state_shutdown = gemini_timer_shutdown,
- .set_state_periodic = gemini_timer_set_periodic,
- .set_state_oneshot = gemini_timer_shutdown,
- .tick_resume = gemini_timer_shutdown,
+ .set_next_event = fttmr010_timer_set_next_event,
+ .set_state_shutdown = fttmr010_timer_shutdown,
+ .set_state_periodic = fttmr010_timer_set_periodic,
+ .set_state_oneshot = fttmr010_timer_shutdown,
+ .tick_resume = fttmr010_timer_shutdown,
};
/*
* IRQ handler for the timer
*/
-static irqreturn_t gemini_timer_interrupt(int irq, void *dev_id)
+static irqreturn_t fttmr010_timer_interrupt(int irq, void *dev_id)
{
- struct clock_event_device *evt = &gemini_clockevent;
+ struct clock_event_device *evt = &fttmr010_clockevent;
evt->event_handler(evt);
return IRQ_HANDLED;
}
-static struct irqaction gemini_timer_irq = {
- .name = "Gemini Timer Tick",
+static struct irqaction fttmr010_timer_irq = {
+ .name = "Faraday FTTMR010 Timer Tick",
.flags = IRQF_TIMER,
- .handler = gemini_timer_interrupt,
+ .handler = fttmr010_timer_interrupt,
};
-static int __init gemini_timer_of_init(struct device_node *np)
+static int __init fttmr010_timer_common_init(struct device_node *np)
{
- static struct regmap *map;
int irq;
- int ret;
- u32 val;
-
- map = syscon_regmap_lookup_by_phandle(np, "syscon");
- if (IS_ERR(map)) {
- pr_err("Can't get regmap for syscon handle");
- return -ENODEV;
- }
- ret = regmap_read(map, GLOBAL_STATUS, &val);
- if (ret) {
- pr_err("Can't read syscon status register");
- return -ENXIO;
- }
base = of_iomap(np, 0);
if (!base) {
return -EINVAL;
}
- tick_rate = REG_TO_AHB_SPEED(val) * 1000000;
- printk(KERN_INFO "Bus: %dMHz", tick_rate / 1000000);
-
- tick_rate /= 6; /* APB bus run AHB*(1/6) */
-
- switch (val & CPU_AHB_RATIO_MASK) {
- case CPU_AHB_1_1:
- printk(KERN_CONT "(1/1)\n");
- break;
- case CPU_AHB_3_2:
- printk(KERN_CONT "(3/2)\n");
- break;
- case CPU_AHB_24_13:
- printk(KERN_CONT "(24/13)\n");
- break;
- case CPU_AHB_2_1:
- printk(KERN_CONT "(2/1)\n");
- break;
- }
-
/*
* Reset the interrupt mask and status
*/
writel(0, base + TIMER3_MATCH1);
writel(0, base + TIMER3_MATCH2);
clocksource_mmio_init(base + TIMER3_COUNT,
- "gemini_clocksource", tick_rate,
+ "fttmr010_clocksource", tick_rate,
300, 32, clocksource_mmio_readl_up);
- sched_clock_register(gemini_read_sched_clock, 32, tick_rate);
+ sched_clock_register(fttmr010_read_sched_clock, 32, tick_rate);
/*
* Setup clockevent timer (interrupt-driven.)
writel(0, base + TIMER1_LOAD);
writel(0, base + TIMER1_MATCH1);
writel(0, base + TIMER1_MATCH2);
- setup_irq(irq, &gemini_timer_irq);
- gemini_clockevent.cpumask = cpumask_of(0);
- clockevents_config_and_register(&gemini_clockevent, tick_rate,
+ setup_irq(irq, &fttmr010_timer_irq);
+ fttmr010_clockevent.cpumask = cpumask_of(0);
+ clockevents_config_and_register(&fttmr010_clockevent, tick_rate,
1, 0xffffffff);
return 0;
}
-CLOCKSOURCE_OF_DECLARE(nomadik_mtu, "cortina,gemini-timer",
- gemini_timer_of_init);
+
+static int __init fttmr010_timer_of_init(struct device_node *np)
+{
+ /*
+ * These implementations require a clock reference.
+ * FIXME: we currently only support clocking using PCLK
+ * and using EXTCLK is not supported in the driver.
+ */
+ struct clk *clk;
+
+ clk = of_clk_get_by_name(np, "PCLK");
+ if (IS_ERR(clk)) {
+ pr_err("could not get PCLK");
+ return PTR_ERR(clk);
+ }
+ tick_rate = clk_get_rate(clk);
+
+ return fttmr010_timer_common_init(np);
+}
+CLOCKSOURCE_OF_DECLARE(fttmr010, "faraday,fttmr010", fttmr010_timer_of_init);
+
+/*
+ * Gemini-specific: relevant registers in the global syscon
+ */
+#define GLOBAL_STATUS 0x04
+#define CPU_AHB_RATIO_MASK (0x3 << 18)
+#define CPU_AHB_1_1 (0x0 << 18)
+#define CPU_AHB_3_2 (0x1 << 18)
+#define CPU_AHB_24_13 (0x2 << 18)
+#define CPU_AHB_2_1 (0x3 << 18)
+#define REG_TO_AHB_SPEED(reg) ((((reg) >> 15) & 0x7) * 10 + 130)
+
+static int __init gemini_timer_of_init(struct device_node *np)
+{
+ static struct regmap *map;
+ int ret;
+ u32 val;
+
+ map = syscon_regmap_lookup_by_phandle(np, "syscon");
+ if (IS_ERR(map)) {
+ pr_err("Can't get regmap for syscon handle\n");
+ return -ENODEV;
+ }
+ ret = regmap_read(map, GLOBAL_STATUS, &val);
+ if (ret) {
+ pr_err("Can't read syscon status register\n");
+ return -ENXIO;
+ }
+
+ tick_rate = REG_TO_AHB_SPEED(val) * 1000000;
+ pr_info("Bus: %dMHz ", tick_rate / 1000000);
+
+ tick_rate /= 6; /* APB bus run AHB*(1/6) */
+
+ switch (val & CPU_AHB_RATIO_MASK) {
+ case CPU_AHB_1_1:
+ pr_cont("(1/1)\n");
+ break;
+ case CPU_AHB_3_2:
+ pr_cont("(3/2)\n");
+ break;
+ case CPU_AHB_24_13:
+ pr_cont("(24/13)\n");
+ break;
+ case CPU_AHB_2_1:
+ pr_cont("(2/1)\n");
+ break;
+ }
+
+ return fttmr010_timer_common_init(np);
+}
+CLOCKSOURCE_OF_DECLARE(gemini, "cortina,gemini-timer", gemini_timer_of_init);
err = of_property_read_string(of_aliases,
"arm,timer-primary", &path);
if (err) {
- pr_warn("Failed to read property");
+ pr_warn("Failed to read property\n");
return err;
}
err = of_property_read_string(of_aliases,
"arm,timer-secondary", &path);
if (err) {
- pr_warn("Failed to read property");
+ pr_warn("Failed to read property\n");
return err;
}
*clk = of_clk_get(node, 0);
ret = PTR_ERR_OR_ZERO(*clk);
if (ret) {
- pr_err("timer missing clk");
+ pr_err("timer missing clk\n");
return ret;
}
nps_timer0_irq = irq_of_parse_and_map(node, 0);
if (nps_timer0_irq <= 0) {
- pr_err("clockevent: missing irq");
+ pr_err("clockevent: missing irq\n");
return -EINVAL;
}
nps_timer_starting_cpu,
nps_timer_dying_cpu);
if (ret) {
- pr_err("Failed to setup hotplug state");
+ pr_err("Failed to setup hotplug state\n");
clk_disable_unprepare(clk);
free_percpu_irq(nps_timer0_irq, &nps_clockevent_device);
return ret;
clk = of_clk_get(np, 0);
if (IS_ERR(clk)) {
- pr_err("Failed to get clock");
+ pr_err("Failed to get clock\n");
return PTR_ERR(clk);
}
ret = clk_prepare_enable(clk);
if (ret) {
- pr_err("Failed to enable clock");
+ pr_err("Failed to enable clock\n");
return ret;
}
rate = clk_get_rate(clk);
if (rate < PRIMA2_CLOCK_FREQ || rate % PRIMA2_CLOCK_FREQ) {
- pr_err("Invalid clock rate");
+ pr_err("Invalid clock rate\n");
return -EINVAL;
}
ret = clocksource_register_hz(&sirfsoc_clocksource, PRIMA2_CLOCK_FREQ);
if (ret) {
- pr_err("Failed to register clocksource");
+ pr_err("Failed to register clocksource\n");
return ret;
}
ret = setup_irq(sirfsoc_timer_irq.irq, &sirfsoc_timer_irq);
if (ret) {
- pr_err("Failed to setup irq");
+ pr_err("Failed to setup irq\n");
return ret;
}
base = of_iomap(np, 0);
if (!base) {
- pr_err("Failed to iomap");
+ pr_err("Failed to iomap\n");
return -ENXIO;
}
clk = of_clk_get(np, 0);
if (IS_ERR(clk)) {
- pr_err("Failed to get clock");
+ pr_err("Failed to get clock\n");
return PTR_ERR(clk);
}
timer_base = of_io_request_and_map(node, 0, of_node_full_name(node));
if (IS_ERR(timer_base)) {
- pr_err("Can't map registers");
+ pr_err("Can't map registers\n");
return PTR_ERR(timer_base);;
}
irq = irq_of_parse_and_map(node, 0);
if (irq <= 0) {
- pr_err("Can't parse IRQ");
+ pr_err("Can't parse IRQ\n");
return -EINVAL;
}
clk = of_clk_get(node, 0);
if (IS_ERR(clk)) {
- pr_err("Can't get timer clock");
+ pr_err("Can't get timer clock\n");
return PTR_ERR(clk);
}
timer_base = of_iomap(np, 0);
if (!timer_base) {
- pr_err("Failed to iomap");
+ pr_err("Failed to iomap\n");
return -ENXIO;
}
help
This adds the CPUFreq driver support for Tegra124 SOCs.
+config ARM_TEGRA186_CPUFREQ
+ tristate "Tegra186 CPUFreq support"
+ depends on ARCH_TEGRA && TEGRA_BPMP
+ help
+ This adds the CPUFreq driver support for Tegra186 SOCs.
+
config ARM_TI_CPUFREQ
bool "Texas Instruments CPUFreq support"
depends on ARCH_OMAP2PLUS
obj-$(CONFIG_ARM_STI_CPUFREQ) += sti-cpufreq.o
obj-$(CONFIG_ARM_TEGRA20_CPUFREQ) += tegra20-cpufreq.o
obj-$(CONFIG_ARM_TEGRA124_CPUFREQ) += tegra124-cpufreq.o
+obj-$(CONFIG_ARM_TEGRA186_CPUFREQ) += tegra186-cpufreq.o
obj-$(CONFIG_ARM_TI_CPUFREQ) += ti-cpufreq.o
obj-$(CONFIG_ARM_VEXPRESS_SPC_CPUFREQ) += vexpress-spc-cpufreq.o
obj-$(CONFIG_ACPI_CPPC_CPUFREQ) += cppc_cpufreq.o
*********************************************************************/
static enum cpuhp_state hp_online;
+static int cpuhp_cpufreq_online(unsigned int cpu)
+{
+ cpufreq_online(cpu);
+
+ return 0;
+}
+
+static int cpuhp_cpufreq_offline(unsigned int cpu)
+{
+ cpufreq_offline(cpu);
+
+ return 0;
+}
+
/**
* cpufreq_register_driver - register a CPU Frequency driver
* @driver_data: A struct cpufreq_driver containing the values#
}
ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "cpufreq:online",
- cpufreq_online,
- cpufreq_offline);
+ cpuhp_cpufreq_online,
+ cpuhp_cpufreq_offline);
if (ret < 0)
goto err_if_unreg;
hp_online = ret;
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/cpufreq.h>
+#include <linux/cpu_cooling.h>
#include <linux/delay.h>
#include <linux/slab.h>
#include <linux/platform_device.h>
static struct cpufreq_frequency_table *freq_table;
static struct clk *armss_clk;
+static struct thermal_cooling_device *cdev;
static int dbx500_cpufreq_target(struct cpufreq_policy *policy,
unsigned int index)
return cpufreq_generic_init(policy, freq_table, 20 * 1000);
}
+static int dbx500_cpufreq_exit(struct cpufreq_policy *policy)
+{
+ if (!IS_ERR(cdev))
+ cpufreq_cooling_unregister(cdev);
+ return 0;
+}
+
+static void dbx500_cpufreq_ready(struct cpufreq_policy *policy)
+{
+ cdev = cpufreq_cooling_register(policy->cpus);
+ if (IS_ERR(cdev))
+ pr_err("Failed to register cooling device %ld\n", PTR_ERR(cdev));
+ else
+ pr_info("Cooling device registered: %s\n", cdev->type);
+}
+
static struct cpufreq_driver dbx500_cpufreq_driver = {
.flags = CPUFREQ_STICKY | CPUFREQ_CONST_LOOPS |
CPUFREQ_NEED_INITIAL_FREQ_CHECK,
.target_index = dbx500_cpufreq_target,
.get = cpufreq_generic_get,
.init = dbx500_cpufreq_init,
+ .exit = dbx500_cpufreq_exit,
+ .ready = dbx500_cpufreq_ready,
.name = "DBX500",
.attr = cpufreq_generic_attr,
};
unsigned int resume;
};
+struct cpufreq_acpi_req {
+ unsigned int cpu;
+ unsigned int state;
+};
+
static struct cpufreq_acpi_io *acpi_io_data[NR_CPUS];
static struct cpufreq_driver acpi_cpufreq_driver;
static unsigned
extract_clock (
struct cpufreq_acpi_io *data,
- unsigned value,
- unsigned int cpu)
+ unsigned value)
{
unsigned long i;
}
-static unsigned int
+static long
processor_get_freq (
- struct cpufreq_acpi_io *data,
- unsigned int cpu)
+ void *arg)
{
- int ret = 0;
- u32 value = 0;
- cpumask_t saved_mask;
- unsigned long clock_freq;
+ struct cpufreq_acpi_req *req = arg;
+ unsigned int cpu = req->cpu;
+ struct cpufreq_acpi_io *data = acpi_io_data[cpu];
+ u32 value;
+ int ret;
pr_debug("processor_get_freq\n");
-
- saved_mask = current->cpus_allowed;
- set_cpus_allowed_ptr(current, cpumask_of(cpu));
if (smp_processor_id() != cpu)
- goto migrate_end;
+ return -EAGAIN;
/* processor_get_pstate gets the instantaneous frequency */
ret = processor_get_pstate(&value);
-
if (ret) {
- set_cpus_allowed_ptr(current, &saved_mask);
pr_warn("get performance failed with error %d\n", ret);
- ret = 0;
- goto migrate_end;
+ return ret;
}
- clock_freq = extract_clock(data, value, cpu);
- ret = (clock_freq*1000);
-
-migrate_end:
- set_cpus_allowed_ptr(current, &saved_mask);
- return ret;
+ return 1000 * extract_clock(data, value);
}
-static int
+static long
processor_set_freq (
- struct cpufreq_acpi_io *data,
- struct cpufreq_policy *policy,
- int state)
+ void *arg)
{
- int ret = 0;
- u32 value = 0;
- cpumask_t saved_mask;
- int retval;
+ struct cpufreq_acpi_req *req = arg;
+ unsigned int cpu = req->cpu;
+ struct cpufreq_acpi_io *data = acpi_io_data[cpu];
+ int ret, state = req->state;
+ u32 value;
pr_debug("processor_set_freq\n");
-
- saved_mask = current->cpus_allowed;
- set_cpus_allowed_ptr(current, cpumask_of(policy->cpu));
- if (smp_processor_id() != policy->cpu) {
- retval = -EAGAIN;
- goto migrate_end;
- }
+ if (smp_processor_id() != cpu)
+ return -EAGAIN;
if (state == data->acpi_data.state) {
if (unlikely(data->resume)) {
data->resume = 0;
} else {
pr_debug("Already at target state (P%d)\n", state);
- retval = 0;
- goto migrate_end;
+ return 0;
}
}
* First we write the target state's 'control' value to the
* control_register.
*/
-
value = (u32) data->acpi_data.states[state].control;
pr_debug("Transitioning to state: 0x%08x\n", value);
ret = processor_set_pstate(value);
if (ret) {
pr_warn("Transition failed with error %d\n", ret);
- retval = -ENODEV;
- goto migrate_end;
+ return -ENODEV;
}
data->acpi_data.state = state;
-
- retval = 0;
-
-migrate_end:
- set_cpus_allowed_ptr(current, &saved_mask);
- return (retval);
+ return 0;
}
acpi_cpufreq_get (
unsigned int cpu)
{
- struct cpufreq_acpi_io *data = acpi_io_data[cpu];
+ struct cpufreq_acpi_req req;
+ long ret;
- pr_debug("acpi_cpufreq_get\n");
+ req.cpu = cpu;
+ ret = work_on_cpu(cpu, processor_get_freq, &req);
- return processor_get_freq(data, cpu);
+ return ret > 0 ? (unsigned int) ret : 0;
}
struct cpufreq_policy *policy,
unsigned int index)
{
- return processor_set_freq(acpi_io_data[policy->cpu], policy, index);
+ struct cpufreq_acpi_req req;
+
+ req.cpu = policy->cpu;
+ req.state = index;
+
+ return work_on_cpu(req.cpu, processor_set_freq, &req);
}
static int
static int imx6q_cpufreq_init(struct cpufreq_policy *policy)
{
+ int ret;
+
policy->clk = arm_clk;
- return cpufreq_generic_init(policy, freq_table, transition_latency);
+ ret = cpufreq_generic_init(policy, freq_table, transition_latency);
+ policy->suspend_freq = policy->max;
+
+ return ret;
}
static struct cpufreq_driver imx6q_cpufreq_driver = {
.init = imx6q_cpufreq_init,
.name = "imx6q-cpufreq",
.attr = cpufreq_generic_attr,
+ .suspend = cpufreq_generic_suspend,
};
static int imx6q_cpufreq_probe(struct platform_device *pdev)
arm_reg = regulator_get(cpu_dev, "arm");
pu_reg = regulator_get_optional(cpu_dev, "pu");
soc_reg = regulator_get(cpu_dev, "soc");
+ if (PTR_ERR(arm_reg) == -EPROBE_DEFER ||
+ PTR_ERR(soc_reg) == -EPROBE_DEFER ||
+ PTR_ERR(pu_reg) == -EPROBE_DEFER) {
+ ret = -EPROBE_DEFER;
+ dev_dbg(cpu_dev, "regulators not ready, defer\n");
+ goto put_reg;
+ }
if (IS_ERR(arm_reg) || IS_ERR(soc_reg)) {
dev_err(cpu_dev, "failed to get regulators\n");
ret = -ENOENT;
ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table);
if (ret) {
dev_err(cpu_dev, "failed to init cpufreq table: %d\n", ret);
- goto put_reg;
+ goto out_free_opp;
}
/* Make imx6_soc_volt array's size same as arm opp number */
#include <asm/cpufeature.h>
#include <asm/intel-family.h>
+#define INTEL_PSTATE_DEFAULT_SAMPLING_INTERVAL (10 * NSEC_PER_MSEC)
+#define INTEL_PSTATE_HWP_SAMPLING_INTERVAL (50 * NSEC_PER_MSEC)
+
#define INTEL_CPUFREQ_TRANSITION_LATENCY 20000
+#define INTEL_CPUFREQ_TRANSITION_DELAY 500
#ifdef CONFIG_ACPI
#include <acpi/processor.h>
return ret;
}
+static inline int32_t percent_fp(int percent)
+{
+ return div_fp(percent, 100);
+}
+
static inline u64 mul_ext_fp(u64 x, u64 y)
{
return (x * y) >> EXT_FRAC_BITS;
};
/**
- * struct perf_limits - Store user and policy limits
- * @no_turbo: User requested turbo state from intel_pstate sysfs
- * @turbo_disabled: Platform turbo status either from msr
- * MSR_IA32_MISC_ENABLE or when maximum available pstate
- * matches the maximum turbo pstate
- * @max_perf_pct: Effective maximum performance limit in percentage, this
- * is minimum of either limits enforced by cpufreq policy
- * or limits from user set limits via intel_pstate sysfs
- * @min_perf_pct: Effective minimum performance limit in percentage, this
- * is maximum of either limits enforced by cpufreq policy
- * or limits from user set limits via intel_pstate sysfs
- * @max_perf: This is a scaled value between 0 to 255 for max_perf_pct
- * This value is used to limit max pstate
- * @min_perf: This is a scaled value between 0 to 255 for min_perf_pct
- * This value is used to limit min pstate
- * @max_policy_pct: The maximum performance in percentage enforced by
- * cpufreq setpolicy interface
- * @max_sysfs_pct: The maximum performance in percentage enforced by
- * intel pstate sysfs interface, unused when per cpu
- * controls are enforced
- * @min_policy_pct: The minimum performance in percentage enforced by
- * cpufreq setpolicy interface
- * @min_sysfs_pct: The minimum performance in percentage enforced by
- * intel pstate sysfs interface, unused when per cpu
- * controls are enforced
- *
- * Storage for user and policy defined limits.
+ * struct global_params - Global parameters, mostly tunable via sysfs.
+ * @no_turbo: Whether or not to use turbo P-states.
+ * @turbo_disabled: Whethet or not turbo P-states are available at all,
+ * based on the MSR_IA32_MISC_ENABLE value and whether or
+ * not the maximum reported turbo P-state is different from
+ * the maximum reported non-turbo one.
+ * @min_perf_pct: Minimum capacity limit in percent of the maximum turbo
+ * P-state capacity.
+ * @max_perf_pct: Maximum capacity limit in percent of the maximum turbo
+ * P-state capacity.
*/
-struct perf_limits {
- int no_turbo;
- int turbo_disabled;
+struct global_params {
+ bool no_turbo;
+ bool turbo_disabled;
int max_perf_pct;
int min_perf_pct;
- int32_t max_perf;
- int32_t min_perf;
- int max_policy_pct;
- int max_sysfs_pct;
- int min_policy_pct;
- int min_sysfs_pct;
};
/**
* @prev_cummulative_iowait: IO Wait time difference from last and
* current sample
* @sample: Storage for storing last Sample data
- * @perf_limits: Pointer to perf_limit unique to this CPU
- * Not all field in the structure are applicable
- * when per cpu controls are enforced
+ * @min_perf: Minimum capacity limit as a fraction of the maximum
+ * turbo P-state capacity.
+ * @max_perf: Maximum capacity limit as a fraction of the maximum
+ * turbo P-state capacity.
* @acpi_perf_data: Stores ACPI perf information read from _PSS
* @valid_pss_table: Set to true for valid ACPI _PSS entries found
* @epp_powersave: Last saved HWP energy performance preference
u64 prev_tsc;
u64 prev_cummulative_iowait;
struct sample sample;
- struct perf_limits *perf_limits;
+ int32_t min_perf;
+ int32_t max_perf;
#ifdef CONFIG_ACPI
struct acpi_processor_performance acpi_perf_data;
bool valid_pss_table;
* @get_scaling: Callback to get frequency scaling factor
* @get_val: Callback to convert P state to actual MSR write value
* @get_vid: Callback to get VID data for Atom platforms
- * @get_target_pstate: Callback to a function to calculate next P state to use
+ * @update_util: Active mode utilization update callback.
*
* Core and Atom CPU models have different way to get P State limits. This
* structure is used to store those callbacks.
int (*get_scaling)(void);
u64 (*get_val)(struct cpudata*, int pstate);
void (*get_vid)(struct cpudata *);
- int32_t (*get_target_pstate)(struct cpudata *);
+ void (*update_util)(struct update_util_data *data, u64 time,
+ unsigned int flags);
};
-/**
- * struct cpu_defaults- Per CPU model default config data
- * @pid_policy: PID config data
- * @funcs: Callback function data
- */
-struct cpu_defaults {
- struct pstate_adjust_policy pid_policy;
- struct pstate_funcs funcs;
+static struct pstate_funcs pstate_funcs __read_mostly;
+static struct pstate_adjust_policy pid_params __read_mostly = {
+ .sample_rate_ms = 10,
+ .sample_rate_ns = 10 * NSEC_PER_MSEC,
+ .deadband = 0,
+ .setpoint = 97,
+ .p_gain_pct = 20,
+ .d_gain_pct = 0,
+ .i_gain_pct = 0,
};
-static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu);
-static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu);
-
-static struct pstate_adjust_policy pid_params __read_mostly;
-static struct pstate_funcs pstate_funcs __read_mostly;
static int hwp_active __read_mostly;
static bool per_cpu_limits __read_mostly;
-static bool driver_registered __read_mostly;
+static struct cpufreq_driver *intel_pstate_driver __read_mostly;
#ifdef CONFIG_ACPI
static bool acpi_ppc;
#endif
-static struct perf_limits global;
-
-static void intel_pstate_init_limits(struct perf_limits *limits)
-{
- memset(limits, 0, sizeof(*limits));
- limits->max_perf_pct = 100;
- limits->max_perf = int_ext_tofp(1);
- limits->max_policy_pct = 100;
- limits->max_sysfs_pct = 100;
-}
+static struct global_params global;
static DEFINE_MUTEX(intel_pstate_driver_lock);
static DEFINE_MUTEX(intel_pstate_limits_lock);
}
#endif
-static inline void pid_reset(struct _pid *pid, int setpoint, int busy,
- int deadband, int integral) {
- pid->setpoint = int_tofp(setpoint);
- pid->deadband = int_tofp(deadband);
- pid->integral = int_tofp(integral);
- pid->last_err = int_tofp(setpoint) - int_tofp(busy);
-}
-
-static inline void pid_p_gain_set(struct _pid *pid, int percent)
-{
- pid->p_gain = div_fp(percent, 100);
-}
-
-static inline void pid_i_gain_set(struct _pid *pid, int percent)
-{
- pid->i_gain = div_fp(percent, 100);
-}
-
-static inline void pid_d_gain_set(struct _pid *pid, int percent)
-{
- pid->d_gain = div_fp(percent, 100);
-}
-
static signed int pid_calc(struct _pid *pid, int32_t busy)
{
signed int result;
return (signed int)fp_toint(result);
}
-static inline void intel_pstate_busy_pid_reset(struct cpudata *cpu)
-{
- pid_p_gain_set(&cpu->pid, pid_params.p_gain_pct);
- pid_d_gain_set(&cpu->pid, pid_params.d_gain_pct);
- pid_i_gain_set(&cpu->pid, pid_params.i_gain_pct);
-
- pid_reset(&cpu->pid, pid_params.setpoint, 100, pid_params.deadband, 0);
-}
-
-static inline void intel_pstate_reset_all_pid(void)
+static inline void intel_pstate_pid_reset(struct cpudata *cpu)
{
- unsigned int cpu;
+ struct _pid *pid = &cpu->pid;
- for_each_online_cpu(cpu) {
- if (all_cpu_data[cpu])
- intel_pstate_busy_pid_reset(all_cpu_data[cpu]);
- }
+ pid->p_gain = percent_fp(pid_params.p_gain_pct);
+ pid->d_gain = percent_fp(pid_params.d_gain_pct);
+ pid->i_gain = percent_fp(pid_params.i_gain_pct);
+ pid->setpoint = int_tofp(pid_params.setpoint);
+ pid->last_err = pid->setpoint - int_tofp(100);
+ pid->deadband = int_tofp(pid_params.deadband);
+ pid->integral = 0;
}
static inline void update_turbo_state(void)
cpu->pstate.max_pstate == cpu->pstate.turbo_pstate);
}
+static int min_perf_pct_min(void)
+{
+ struct cpudata *cpu = all_cpu_data[0];
+
+ return DIV_ROUND_UP(cpu->pstate.min_pstate * 100,
+ cpu->pstate.turbo_pstate);
+}
+
static s16 intel_pstate_get_epb(struct cpudata *cpu_data)
{
u64 epb;
NULL,
};
-static void intel_pstate_hwp_set(struct cpufreq_policy *policy)
+static void intel_pstate_hwp_set(unsigned int cpu)
{
- int min, hw_min, max, hw_max, cpu;
- struct perf_limits *perf_limits = &global;
+ struct cpudata *cpu_data = all_cpu_data[cpu];
+ int min, hw_min, max, hw_max;
u64 value, cap;
+ s16 epp;
- for_each_cpu(cpu, policy->cpus) {
- struct cpudata *cpu_data = all_cpu_data[cpu];
- s16 epp;
-
- if (per_cpu_limits)
- perf_limits = all_cpu_data[cpu]->perf_limits;
-
- rdmsrl_on_cpu(cpu, MSR_HWP_CAPABILITIES, &cap);
- hw_min = HWP_LOWEST_PERF(cap);
- if (global.no_turbo)
- hw_max = HWP_GUARANTEED_PERF(cap);
- else
- hw_max = HWP_HIGHEST_PERF(cap);
-
- max = fp_ext_toint(hw_max * perf_limits->max_perf);
- if (cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE)
- min = max;
- else
- min = fp_ext_toint(hw_max * perf_limits->min_perf);
+ rdmsrl_on_cpu(cpu, MSR_HWP_CAPABILITIES, &cap);
+ hw_min = HWP_LOWEST_PERF(cap);
+ if (global.no_turbo)
+ hw_max = HWP_GUARANTEED_PERF(cap);
+ else
+ hw_max = HWP_HIGHEST_PERF(cap);
- rdmsrl_on_cpu(cpu, MSR_HWP_REQUEST, &value);
+ max = fp_ext_toint(hw_max * cpu_data->max_perf);
+ if (cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE)
+ min = max;
+ else
+ min = fp_ext_toint(hw_max * cpu_data->min_perf);
- value &= ~HWP_MIN_PERF(~0L);
- value |= HWP_MIN_PERF(min);
+ rdmsrl_on_cpu(cpu, MSR_HWP_REQUEST, &value);
- value &= ~HWP_MAX_PERF(~0L);
- value |= HWP_MAX_PERF(max);
+ value &= ~HWP_MIN_PERF(~0L);
+ value |= HWP_MIN_PERF(min);
- if (cpu_data->epp_policy == cpu_data->policy)
- goto skip_epp;
+ value &= ~HWP_MAX_PERF(~0L);
+ value |= HWP_MAX_PERF(max);
- cpu_data->epp_policy = cpu_data->policy;
+ if (cpu_data->epp_policy == cpu_data->policy)
+ goto skip_epp;
- if (cpu_data->epp_saved >= 0) {
- epp = cpu_data->epp_saved;
- cpu_data->epp_saved = -EINVAL;
- goto update_epp;
- }
+ cpu_data->epp_policy = cpu_data->policy;
- if (cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE) {
- epp = intel_pstate_get_epp(cpu_data, value);
- cpu_data->epp_powersave = epp;
- /* If EPP read was failed, then don't try to write */
- if (epp < 0)
- goto skip_epp;
+ if (cpu_data->epp_saved >= 0) {
+ epp = cpu_data->epp_saved;
+ cpu_data->epp_saved = -EINVAL;
+ goto update_epp;
+ }
+ if (cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE) {
+ epp = intel_pstate_get_epp(cpu_data, value);
+ cpu_data->epp_powersave = epp;
+ /* If EPP read was failed, then don't try to write */
+ if (epp < 0)
+ goto skip_epp;
- epp = 0;
- } else {
- /* skip setting EPP, when saved value is invalid */
- if (cpu_data->epp_powersave < 0)
- goto skip_epp;
+ epp = 0;
+ } else {
+ /* skip setting EPP, when saved value is invalid */
+ if (cpu_data->epp_powersave < 0)
+ goto skip_epp;
- /*
- * No need to restore EPP when it is not zero. This
- * means:
- * - Policy is not changed
- * - user has manually changed
- * - Error reading EPB
- */
- epp = intel_pstate_get_epp(cpu_data, value);
- if (epp)
- goto skip_epp;
+ /*
+ * No need to restore EPP when it is not zero. This
+ * means:
+ * - Policy is not changed
+ * - user has manually changed
+ * - Error reading EPB
+ */
+ epp = intel_pstate_get_epp(cpu_data, value);
+ if (epp)
+ goto skip_epp;
- epp = cpu_data->epp_powersave;
- }
+ epp = cpu_data->epp_powersave;
+ }
update_epp:
- if (static_cpu_has(X86_FEATURE_HWP_EPP)) {
- value &= ~GENMASK_ULL(31, 24);
- value |= (u64)epp << 24;
- } else {
- intel_pstate_set_epb(cpu, epp);
- }
-skip_epp:
- wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value);
+ if (static_cpu_has(X86_FEATURE_HWP_EPP)) {
+ value &= ~GENMASK_ULL(31, 24);
+ value |= (u64)epp << 24;
+ } else {
+ intel_pstate_set_epb(cpu, epp);
}
-}
-
-static int intel_pstate_hwp_set_policy(struct cpufreq_policy *policy)
-{
- if (hwp_active)
- intel_pstate_hwp_set(policy);
-
- return 0;
+skip_epp:
+ wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value);
}
static int intel_pstate_hwp_save_state(struct cpufreq_policy *policy)
static int intel_pstate_resume(struct cpufreq_policy *policy)
{
- int ret;
-
if (!hwp_active)
return 0;
mutex_lock(&intel_pstate_limits_lock);
all_cpu_data[policy->cpu]->epp_policy = 0;
-
- ret = intel_pstate_hwp_set_policy(policy);
+ intel_pstate_hwp_set(policy->cpu);
mutex_unlock(&intel_pstate_limits_lock);
- return ret;
+ return 0;
}
static void intel_pstate_update_policies(void)
/************************** debugfs begin ************************/
static int pid_param_set(void *data, u64 val)
{
+ unsigned int cpu;
+
*(u32 *)data = val;
pid_params.sample_rate_ns = pid_params.sample_rate_ms * NSEC_PER_MSEC;
- intel_pstate_reset_all_pid();
+ for_each_possible_cpu(cpu)
+ if (all_cpu_data[cpu])
+ intel_pstate_pid_reset(all_cpu_data[cpu]);
+
return 0;
}
mutex_lock(&intel_pstate_driver_lock);
- if (!driver_registered) {
+ if (!intel_pstate_driver) {
mutex_unlock(&intel_pstate_driver_lock);
return -EAGAIN;
}
mutex_lock(&intel_pstate_driver_lock);
- if (!driver_registered) {
+ if (!intel_pstate_driver) {
mutex_unlock(&intel_pstate_driver_lock);
return -EAGAIN;
}
mutex_lock(&intel_pstate_driver_lock);
- if (!driver_registered) {
+ if (!intel_pstate_driver) {
mutex_unlock(&intel_pstate_driver_lock);
return -EAGAIN;
}
mutex_lock(&intel_pstate_driver_lock);
- if (!driver_registered) {
+ if (!intel_pstate_driver) {
mutex_unlock(&intel_pstate_driver_lock);
return -EAGAIN;
}
global.no_turbo = clamp_t(int, input, 0, 1);
+ if (global.no_turbo) {
+ struct cpudata *cpu = all_cpu_data[0];
+ int pct = cpu->pstate.max_pstate * 100 / cpu->pstate.turbo_pstate;
+
+ /* Squash the global minimum into the permitted range. */
+ if (global.min_perf_pct > pct)
+ global.min_perf_pct = pct;
+ }
+
mutex_unlock(&intel_pstate_limits_lock);
intel_pstate_update_policies();
mutex_lock(&intel_pstate_driver_lock);
- if (!driver_registered) {
+ if (!intel_pstate_driver) {
mutex_unlock(&intel_pstate_driver_lock);
return -EAGAIN;
}
mutex_lock(&intel_pstate_limits_lock);
- global.max_sysfs_pct = clamp_t(int, input, 0 , 100);
- global.max_perf_pct = min(global.max_policy_pct, global.max_sysfs_pct);
- global.max_perf_pct = max(global.min_policy_pct, global.max_perf_pct);
- global.max_perf_pct = max(global.min_perf_pct, global.max_perf_pct);
- global.max_perf = percent_ext_fp(global.max_perf_pct);
+ global.max_perf_pct = clamp_t(int, input, global.min_perf_pct, 100);
mutex_unlock(&intel_pstate_limits_lock);
mutex_lock(&intel_pstate_driver_lock);
- if (!driver_registered) {
+ if (!intel_pstate_driver) {
mutex_unlock(&intel_pstate_driver_lock);
return -EAGAIN;
}
mutex_lock(&intel_pstate_limits_lock);
- global.min_sysfs_pct = clamp_t(int, input, 0 , 100);
- global.min_perf_pct = max(global.min_policy_pct, global.min_sysfs_pct);
- global.min_perf_pct = min(global.max_policy_pct, global.min_perf_pct);
- global.min_perf_pct = min(global.max_perf_pct, global.min_perf_pct);
- global.min_perf = percent_ext_fp(global.min_perf_pct);
+ global.min_perf_pct = clamp_t(int, input,
+ min_perf_pct_min(), global.max_perf_pct);
mutex_unlock(&intel_pstate_limits_lock);
return ret;
}
-static struct cpu_defaults core_params = {
- .pid_policy = {
- .sample_rate_ms = 10,
- .deadband = 0,
- .setpoint = 97,
- .p_gain_pct = 20,
- .d_gain_pct = 0,
- .i_gain_pct = 0,
- },
- .funcs = {
- .get_max = core_get_max_pstate,
- .get_max_physical = core_get_max_pstate_physical,
- .get_min = core_get_min_pstate,
- .get_turbo = core_get_turbo_pstate,
- .get_scaling = core_get_scaling,
- .get_val = core_get_val,
- .get_target_pstate = get_target_pstate_use_performance,
- },
-};
-
-static const struct cpu_defaults silvermont_params = {
- .pid_policy = {
- .sample_rate_ms = 10,
- .deadband = 0,
- .setpoint = 60,
- .p_gain_pct = 14,
- .d_gain_pct = 0,
- .i_gain_pct = 4,
- },
- .funcs = {
- .get_max = atom_get_max_pstate,
- .get_max_physical = atom_get_max_pstate,
- .get_min = atom_get_min_pstate,
- .get_turbo = atom_get_turbo_pstate,
- .get_val = atom_get_val,
- .get_scaling = silvermont_get_scaling,
- .get_vid = atom_get_vid,
- .get_target_pstate = get_target_pstate_use_cpu_load,
- },
-};
-
-static const struct cpu_defaults airmont_params = {
- .pid_policy = {
- .sample_rate_ms = 10,
- .deadband = 0,
- .setpoint = 60,
- .p_gain_pct = 14,
- .d_gain_pct = 0,
- .i_gain_pct = 4,
- },
- .funcs = {
- .get_max = atom_get_max_pstate,
- .get_max_physical = atom_get_max_pstate,
- .get_min = atom_get_min_pstate,
- .get_turbo = atom_get_turbo_pstate,
- .get_val = atom_get_val,
- .get_scaling = airmont_get_scaling,
- .get_vid = atom_get_vid,
- .get_target_pstate = get_target_pstate_use_cpu_load,
- },
-};
-
-static const struct cpu_defaults knl_params = {
- .pid_policy = {
- .sample_rate_ms = 10,
- .deadband = 0,
- .setpoint = 97,
- .p_gain_pct = 20,
- .d_gain_pct = 0,
- .i_gain_pct = 0,
- },
- .funcs = {
- .get_max = core_get_max_pstate,
- .get_max_physical = core_get_max_pstate_physical,
- .get_min = core_get_min_pstate,
- .get_turbo = knl_get_turbo_pstate,
- .get_scaling = core_get_scaling,
- .get_val = core_get_val,
- .get_target_pstate = get_target_pstate_use_performance,
- },
-};
-
-static const struct cpu_defaults bxt_params = {
- .pid_policy = {
- .sample_rate_ms = 10,
- .deadband = 0,
- .setpoint = 60,
- .p_gain_pct = 14,
- .d_gain_pct = 0,
- .i_gain_pct = 4,
- },
- .funcs = {
- .get_max = core_get_max_pstate,
- .get_max_physical = core_get_max_pstate_physical,
- .get_min = core_get_min_pstate,
- .get_turbo = core_get_turbo_pstate,
- .get_scaling = core_get_scaling,
- .get_val = core_get_val,
- .get_target_pstate = get_target_pstate_use_cpu_load,
- },
-};
-
-static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
+static int intel_pstate_get_base_pstate(struct cpudata *cpu)
{
- int max_perf = cpu->pstate.turbo_pstate;
- int max_perf_adj;
- int min_perf;
- struct perf_limits *perf_limits = &global;
-
- if (global.no_turbo || global.turbo_disabled)
- max_perf = cpu->pstate.max_pstate;
-
- if (per_cpu_limits)
- perf_limits = cpu->perf_limits;
-
- /*
- * performance can be limited by user through sysfs, by cpufreq
- * policy, or by cpu specific default values determined through
- * experimentation.
- */
- max_perf_adj = fp_ext_toint(max_perf * perf_limits->max_perf);
- *max = clamp_t(int, max_perf_adj,
- cpu->pstate.min_pstate, cpu->pstate.turbo_pstate);
-
- min_perf = fp_ext_toint(max_perf * perf_limits->min_perf);
- *min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf);
+ return global.no_turbo || global.turbo_disabled ?
+ cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
}
static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
static void intel_pstate_max_within_limits(struct cpudata *cpu)
{
- int min_pstate, max_pstate;
+ int pstate;
update_turbo_state();
- intel_pstate_get_min_max(cpu, &min_pstate, &max_pstate);
- intel_pstate_set_pstate(cpu, max_pstate);
+ pstate = intel_pstate_get_base_pstate(cpu);
+ pstate = max(cpu->pstate.min_pstate,
+ fp_ext_toint(pstate * cpu->max_perf));
+ intel_pstate_set_pstate(cpu, pstate);
}
static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
* that sample.time will always be reset before setting the utilization
* update hook and make the caller skip the sample then.
*/
- return !!cpu->last_sample_time;
+ if (cpu->last_sample_time) {
+ intel_pstate_calc_avg_perf(cpu);
+ return true;
+ }
+ return false;
}
static inline int32_t get_avg_frequency(struct cpudata *cpu)
int32_t busy_frac, boost;
int target, avg_pstate;
+ if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE)
+ return cpu->pstate.turbo_pstate;
+
busy_frac = div_fp(sample->mperf, sample->tsc);
boost = cpu->iowait_boost;
int32_t perf_scaled, max_pstate, current_pstate, sample_ratio;
u64 duration_ns;
+ if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE)
+ return cpu->pstate.turbo_pstate;
+
/*
* perf_scaled is the ratio of the average P-state during the last
* sampling period to the P-state requested last time (in percent).
static int intel_pstate_prepare_request(struct cpudata *cpu, int pstate)
{
- int max_perf, min_perf;
+ int max_pstate = intel_pstate_get_base_pstate(cpu);
+ int min_pstate;
- intel_pstate_get_min_max(cpu, &min_perf, &max_perf);
- pstate = clamp_t(int, pstate, min_perf, max_perf);
- return pstate;
+ min_pstate = max(cpu->pstate.min_pstate,
+ fp_ext_toint(max_pstate * cpu->min_perf));
+ max_pstate = max(min_pstate, fp_ext_toint(max_pstate * cpu->max_perf));
+ return clamp_t(int, pstate, min_pstate, max_pstate);
}
static void intel_pstate_update_pstate(struct cpudata *cpu, int pstate)
wrmsrl(MSR_IA32_PERF_CTL, pstate_funcs.get_val(cpu, pstate));
}
-static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
+static void intel_pstate_adjust_pstate(struct cpudata *cpu, int target_pstate)
{
- int from, target_pstate;
+ int from = cpu->pstate.current_pstate;
struct sample *sample;
- from = cpu->pstate.current_pstate;
-
- target_pstate = cpu->policy == CPUFREQ_POLICY_PERFORMANCE ?
- cpu->pstate.turbo_pstate : pstate_funcs.get_target_pstate(cpu);
-
update_turbo_state();
target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
fp_toint(cpu->iowait_boost * 100));
}
+static void intel_pstate_update_util_hwp(struct update_util_data *data,
+ u64 time, unsigned int flags)
+{
+ struct cpudata *cpu = container_of(data, struct cpudata, update_util);
+ u64 delta_ns = time - cpu->sample.time;
+
+ if ((s64)delta_ns >= INTEL_PSTATE_HWP_SAMPLING_INTERVAL)
+ intel_pstate_sample(cpu, time);
+}
+
+static void intel_pstate_update_util_pid(struct update_util_data *data,
+ u64 time, unsigned int flags)
+{
+ struct cpudata *cpu = container_of(data, struct cpudata, update_util);
+ u64 delta_ns = time - cpu->sample.time;
+
+ if ((s64)delta_ns < pid_params.sample_rate_ns)
+ return;
+
+ if (intel_pstate_sample(cpu, time)) {
+ int target_pstate;
+
+ target_pstate = get_target_pstate_use_performance(cpu);
+ intel_pstate_adjust_pstate(cpu, target_pstate);
+ }
+}
+
static void intel_pstate_update_util(struct update_util_data *data, u64 time,
unsigned int flags)
{
struct cpudata *cpu = container_of(data, struct cpudata, update_util);
u64 delta_ns;
- if (pstate_funcs.get_target_pstate == get_target_pstate_use_cpu_load) {
- if (flags & SCHED_CPUFREQ_IOWAIT) {
- cpu->iowait_boost = int_tofp(1);
- } else if (cpu->iowait_boost) {
- /* Clear iowait_boost if the CPU may have been idle. */
- delta_ns = time - cpu->last_update;
- if (delta_ns > TICK_NSEC)
- cpu->iowait_boost = 0;
- }
- cpu->last_update = time;
+ if (flags & SCHED_CPUFREQ_IOWAIT) {
+ cpu->iowait_boost = int_tofp(1);
+ } else if (cpu->iowait_boost) {
+ /* Clear iowait_boost if the CPU may have been idle. */
+ delta_ns = time - cpu->last_update;
+ if (delta_ns > TICK_NSEC)
+ cpu->iowait_boost = 0;
}
-
+ cpu->last_update = time;
delta_ns = time - cpu->sample.time;
- if ((s64)delta_ns >= pid_params.sample_rate_ns) {
- bool sample_taken = intel_pstate_sample(cpu, time);
+ if ((s64)delta_ns < INTEL_PSTATE_DEFAULT_SAMPLING_INTERVAL)
+ return;
- if (sample_taken) {
- intel_pstate_calc_avg_perf(cpu);
- if (!hwp_active)
- intel_pstate_adjust_busy_pstate(cpu);
- }
+ if (intel_pstate_sample(cpu, time)) {
+ int target_pstate;
+
+ target_pstate = get_target_pstate_use_cpu_load(cpu);
+ intel_pstate_adjust_pstate(cpu, target_pstate);
}
}
+static struct pstate_funcs core_funcs = {
+ .get_max = core_get_max_pstate,
+ .get_max_physical = core_get_max_pstate_physical,
+ .get_min = core_get_min_pstate,
+ .get_turbo = core_get_turbo_pstate,
+ .get_scaling = core_get_scaling,
+ .get_val = core_get_val,
+ .update_util = intel_pstate_update_util_pid,
+};
+
+static const struct pstate_funcs silvermont_funcs = {
+ .get_max = atom_get_max_pstate,
+ .get_max_physical = atom_get_max_pstate,
+ .get_min = atom_get_min_pstate,
+ .get_turbo = atom_get_turbo_pstate,
+ .get_val = atom_get_val,
+ .get_scaling = silvermont_get_scaling,
+ .get_vid = atom_get_vid,
+ .update_util = intel_pstate_update_util,
+};
+
+static const struct pstate_funcs airmont_funcs = {
+ .get_max = atom_get_max_pstate,
+ .get_max_physical = atom_get_max_pstate,
+ .get_min = atom_get_min_pstate,
+ .get_turbo = atom_get_turbo_pstate,
+ .get_val = atom_get_val,
+ .get_scaling = airmont_get_scaling,
+ .get_vid = atom_get_vid,
+ .update_util = intel_pstate_update_util,
+};
+
+static const struct pstate_funcs knl_funcs = {
+ .get_max = core_get_max_pstate,
+ .get_max_physical = core_get_max_pstate_physical,
+ .get_min = core_get_min_pstate,
+ .get_turbo = knl_get_turbo_pstate,
+ .get_scaling = core_get_scaling,
+ .get_val = core_get_val,
+ .update_util = intel_pstate_update_util_pid,
+};
+
+static const struct pstate_funcs bxt_funcs = {
+ .get_max = core_get_max_pstate,
+ .get_max_physical = core_get_max_pstate_physical,
+ .get_min = core_get_min_pstate,
+ .get_turbo = core_get_turbo_pstate,
+ .get_scaling = core_get_scaling,
+ .get_val = core_get_val,
+ .update_util = intel_pstate_update_util,
+};
+
#define ICPU(model, policy) \
{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_APERFMPERF,\
(unsigned long)&policy }
static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
- ICPU(INTEL_FAM6_SANDYBRIDGE, core_params),
- ICPU(INTEL_FAM6_SANDYBRIDGE_X, core_params),
- ICPU(INTEL_FAM6_ATOM_SILVERMONT1, silvermont_params),
- ICPU(INTEL_FAM6_IVYBRIDGE, core_params),
- ICPU(INTEL_FAM6_HASWELL_CORE, core_params),
- ICPU(INTEL_FAM6_BROADWELL_CORE, core_params),
- ICPU(INTEL_FAM6_IVYBRIDGE_X, core_params),
- ICPU(INTEL_FAM6_HASWELL_X, core_params),
- ICPU(INTEL_FAM6_HASWELL_ULT, core_params),
- ICPU(INTEL_FAM6_HASWELL_GT3E, core_params),
- ICPU(INTEL_FAM6_BROADWELL_GT3E, core_params),
- ICPU(INTEL_FAM6_ATOM_AIRMONT, airmont_params),
- ICPU(INTEL_FAM6_SKYLAKE_MOBILE, core_params),
- ICPU(INTEL_FAM6_BROADWELL_X, core_params),
- ICPU(INTEL_FAM6_SKYLAKE_DESKTOP, core_params),
- ICPU(INTEL_FAM6_BROADWELL_XEON_D, core_params),
- ICPU(INTEL_FAM6_XEON_PHI_KNL, knl_params),
- ICPU(INTEL_FAM6_XEON_PHI_KNM, knl_params),
- ICPU(INTEL_FAM6_ATOM_GOLDMONT, bxt_params),
+ ICPU(INTEL_FAM6_SANDYBRIDGE, core_funcs),
+ ICPU(INTEL_FAM6_SANDYBRIDGE_X, core_funcs),
+ ICPU(INTEL_FAM6_ATOM_SILVERMONT1, silvermont_funcs),
+ ICPU(INTEL_FAM6_IVYBRIDGE, core_funcs),
+ ICPU(INTEL_FAM6_HASWELL_CORE, core_funcs),
+ ICPU(INTEL_FAM6_BROADWELL_CORE, core_funcs),
+ ICPU(INTEL_FAM6_IVYBRIDGE_X, core_funcs),
+ ICPU(INTEL_FAM6_HASWELL_X, core_funcs),
+ ICPU(INTEL_FAM6_HASWELL_ULT, core_funcs),
+ ICPU(INTEL_FAM6_HASWELL_GT3E, core_funcs),
+ ICPU(INTEL_FAM6_BROADWELL_GT3E, core_funcs),
+ ICPU(INTEL_FAM6_ATOM_AIRMONT, airmont_funcs),
+ ICPU(INTEL_FAM6_SKYLAKE_MOBILE, core_funcs),
+ ICPU(INTEL_FAM6_BROADWELL_X, core_funcs),
+ ICPU(INTEL_FAM6_SKYLAKE_DESKTOP, core_funcs),
+ ICPU(INTEL_FAM6_BROADWELL_XEON_D, core_funcs),
+ ICPU(INTEL_FAM6_XEON_PHI_KNL, knl_funcs),
+ ICPU(INTEL_FAM6_XEON_PHI_KNM, knl_funcs),
+ ICPU(INTEL_FAM6_ATOM_GOLDMONT, bxt_funcs),
+ ICPU(INTEL_FAM6_ATOM_GEMINI_LAKE, bxt_funcs),
{}
};
MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);
static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] __initconst = {
- ICPU(INTEL_FAM6_BROADWELL_XEON_D, core_params),
- ICPU(INTEL_FAM6_BROADWELL_X, core_params),
- ICPU(INTEL_FAM6_SKYLAKE_X, core_params),
+ ICPU(INTEL_FAM6_BROADWELL_XEON_D, core_funcs),
+ ICPU(INTEL_FAM6_BROADWELL_X, core_funcs),
+ ICPU(INTEL_FAM6_SKYLAKE_X, core_funcs),
{}
};
static const struct x86_cpu_id intel_pstate_cpu_ee_disable_ids[] = {
- ICPU(INTEL_FAM6_KABYLAKE_DESKTOP, core_params),
+ ICPU(INTEL_FAM6_KABYLAKE_DESKTOP, core_funcs),
{}
};
+static bool pid_in_use(void);
+
static int intel_pstate_init_cpu(unsigned int cpunum)
{
struct cpudata *cpu;
cpu = all_cpu_data[cpunum];
if (!cpu) {
- unsigned int size = sizeof(struct cpudata);
-
- if (per_cpu_limits)
- size += sizeof(struct perf_limits);
-
- cpu = kzalloc(size, GFP_KERNEL);
+ cpu = kzalloc(sizeof(*cpu), GFP_KERNEL);
if (!cpu)
return -ENOMEM;
all_cpu_data[cpunum] = cpu;
- if (per_cpu_limits)
- cpu->perf_limits = (struct perf_limits *)(cpu + 1);
cpu->epp_default = -EINVAL;
cpu->epp_powersave = -EINVAL;
intel_pstate_disable_ee(cpunum);
intel_pstate_hwp_enable(cpu);
- pid_params.sample_rate_ms = 50;
- pid_params.sample_rate_ns = 50 * NSEC_PER_MSEC;
+ } else if (pid_in_use()) {
+ intel_pstate_pid_reset(cpu);
}
intel_pstate_get_cpu_pstates(cpu);
- intel_pstate_busy_pid_reset(cpu);
-
pr_debug("controlling: cpu %d\n", cpunum);
return 0;
/* Prevent intel_pstate_update_util() from using stale data. */
cpu->sample.time = 0;
cpufreq_add_update_util_hook(cpu_num, &cpu->update_util,
- intel_pstate_update_util);
+ pstate_funcs.update_util);
cpu->update_util_set = true;
}
synchronize_sched();
}
+static int intel_pstate_get_max_freq(struct cpudata *cpu)
+{
+ return global.turbo_disabled || global.no_turbo ?
+ cpu->pstate.max_freq : cpu->pstate.turbo_freq;
+}
+
static void intel_pstate_update_perf_limits(struct cpufreq_policy *policy,
- struct perf_limits *limits)
+ struct cpudata *cpu)
{
+ int max_freq = intel_pstate_get_max_freq(cpu);
int32_t max_policy_perf, min_policy_perf;
- max_policy_perf = div_ext_fp(policy->max, policy->cpuinfo.max_freq);
+ max_policy_perf = div_ext_fp(policy->max, max_freq);
max_policy_perf = clamp_t(int32_t, max_policy_perf, 0, int_ext_tofp(1));
if (policy->max == policy->min) {
min_policy_perf = max_policy_perf;
} else {
- min_policy_perf = div_ext_fp(policy->min,
- policy->cpuinfo.max_freq);
+ min_policy_perf = div_ext_fp(policy->min, max_freq);
min_policy_perf = clamp_t(int32_t, min_policy_perf,
0, max_policy_perf);
}
/* Normalize user input to [min_perf, max_perf] */
- limits->min_perf = max(min_policy_perf,
- percent_ext_fp(limits->min_sysfs_pct));
- limits->min_perf = min(limits->min_perf, max_policy_perf);
- limits->max_perf = min(max_policy_perf,
- percent_ext_fp(limits->max_sysfs_pct));
- limits->max_perf = max(min_policy_perf, limits->max_perf);
+ if (per_cpu_limits) {
+ cpu->min_perf = min_policy_perf;
+ cpu->max_perf = max_policy_perf;
+ } else {
+ int32_t global_min, global_max;
+
+ /* Global limits are in percent of the maximum turbo P-state. */
+ global_max = percent_ext_fp(global.max_perf_pct);
+ global_min = percent_ext_fp(global.min_perf_pct);
+ if (max_freq != cpu->pstate.turbo_freq) {
+ int32_t turbo_factor;
+
+ turbo_factor = div_ext_fp(cpu->pstate.turbo_pstate,
+ cpu->pstate.max_pstate);
+ global_min = mul_ext_fp(global_min, turbo_factor);
+ global_max = mul_ext_fp(global_max, turbo_factor);
+ }
+ global_min = clamp_t(int32_t, global_min, 0, global_max);
+
+ cpu->min_perf = max(min_policy_perf, global_min);
+ cpu->min_perf = min(cpu->min_perf, max_policy_perf);
+ cpu->max_perf = min(max_policy_perf, global_max);
+ cpu->max_perf = max(min_policy_perf, cpu->max_perf);
- /* Make sure min_perf <= max_perf */
- limits->min_perf = min(limits->min_perf, limits->max_perf);
+ /* Make sure min_perf <= max_perf */
+ cpu->min_perf = min(cpu->min_perf, cpu->max_perf);
+ }
- limits->max_perf = round_up(limits->max_perf, EXT_FRAC_BITS);
- limits->min_perf = round_up(limits->min_perf, EXT_FRAC_BITS);
- limits->max_perf_pct = fp_ext_toint(limits->max_perf * 100);
- limits->min_perf_pct = fp_ext_toint(limits->min_perf * 100);
+ cpu->max_perf = round_up(cpu->max_perf, EXT_FRAC_BITS);
+ cpu->min_perf = round_up(cpu->min_perf, EXT_FRAC_BITS);
pr_debug("cpu:%d max_perf_pct:%d min_perf_pct:%d\n", policy->cpu,
- limits->max_perf_pct, limits->min_perf_pct);
+ fp_ext_toint(cpu->max_perf * 100),
+ fp_ext_toint(cpu->min_perf * 100));
}
static int intel_pstate_set_policy(struct cpufreq_policy *policy)
{
struct cpudata *cpu;
- struct perf_limits *perf_limits = &global;
if (!policy->cpuinfo.max_freq)
return -ENODEV;
cpu = all_cpu_data[policy->cpu];
cpu->policy = policy->policy;
- if (cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate &&
- policy->max < policy->cpuinfo.max_freq &&
- policy->max > cpu->pstate.max_pstate * cpu->pstate.scaling) {
- pr_debug("policy->max > max non turbo frequency\n");
- policy->max = policy->cpuinfo.max_freq;
- }
-
- if (per_cpu_limits)
- perf_limits = cpu->perf_limits;
-
mutex_lock(&intel_pstate_limits_lock);
- intel_pstate_update_perf_limits(policy, perf_limits);
+ intel_pstate_update_perf_limits(policy, cpu);
if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) {
/*
intel_pstate_set_update_util_hook(policy->cpu);
- intel_pstate_hwp_set_policy(policy);
+ if (hwp_active)
+ intel_pstate_hwp_set(policy->cpu);
mutex_unlock(&intel_pstate_limits_lock);
return 0;
}
+static void intel_pstate_adjust_policy_max(struct cpufreq_policy *policy,
+ struct cpudata *cpu)
+{
+ if (cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate &&
+ policy->max < policy->cpuinfo.max_freq &&
+ policy->max > cpu->pstate.max_freq) {
+ pr_debug("policy->max > max non turbo frequency\n");
+ policy->max = policy->cpuinfo.max_freq;
+ }
+}
+
static int intel_pstate_verify_policy(struct cpufreq_policy *policy)
{
struct cpudata *cpu = all_cpu_data[policy->cpu];
update_turbo_state();
- policy->cpuinfo.max_freq = global.turbo_disabled || global.no_turbo ?
- cpu->pstate.max_freq :
- cpu->pstate.turbo_freq;
-
- cpufreq_verify_within_cpu_limits(policy);
+ cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
+ intel_pstate_get_max_freq(cpu));
if (policy->policy != CPUFREQ_POLICY_POWERSAVE &&
policy->policy != CPUFREQ_POLICY_PERFORMANCE)
return -EINVAL;
- /* When per-CPU limits are used, sysfs limits are not used */
- if (!per_cpu_limits) {
- unsigned int max_freq, min_freq;
-
- max_freq = policy->cpuinfo.max_freq *
- global.max_sysfs_pct / 100;
- min_freq = policy->cpuinfo.max_freq *
- global.min_sysfs_pct / 100;
- cpufreq_verify_within_limits(policy, min_freq, max_freq);
- }
+ intel_pstate_adjust_policy_max(policy, cpu);
return 0;
}
cpu = all_cpu_data[policy->cpu];
- if (per_cpu_limits)
- intel_pstate_init_limits(cpu->perf_limits);
+ cpu->max_perf = int_ext_tofp(1);
+ cpu->min_perf = 0;
policy->min = cpu->pstate.min_pstate * cpu->pstate.scaling;
policy->max = cpu->pstate.turbo_pstate * cpu->pstate.scaling;
struct cpudata *cpu = all_cpu_data[policy->cpu];
update_turbo_state();
- policy->cpuinfo.max_freq = global.no_turbo || global.turbo_disabled ?
- cpu->pstate.max_freq : cpu->pstate.turbo_freq;
+ cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
+ intel_pstate_get_max_freq(cpu));
- cpufreq_verify_within_cpu_limits(policy);
+ intel_pstate_adjust_policy_max(policy, cpu);
+
+ intel_pstate_update_perf_limits(policy, cpu);
return 0;
}
return ret;
policy->cpuinfo.transition_latency = INTEL_CPUFREQ_TRANSITION_LATENCY;
+ policy->transition_delay_us = INTEL_CPUFREQ_TRANSITION_DELAY;
/* This reflects the intel_pstate_get_cpu_pstates() setting. */
policy->cur = policy->cpuinfo.min_freq;
.name = "intel_cpufreq",
};
-static struct cpufreq_driver *intel_pstate_driver = &intel_pstate;
+static struct cpufreq_driver *default_driver = &intel_pstate;
+
+static bool pid_in_use(void)
+{
+ return intel_pstate_driver == &intel_pstate &&
+ pstate_funcs.update_util == intel_pstate_update_util_pid;
+}
static void intel_pstate_driver_cleanup(void)
{
}
}
put_online_cpus();
+ intel_pstate_driver = NULL;
}
-static int intel_pstate_register_driver(void)
+static int intel_pstate_register_driver(struct cpufreq_driver *driver)
{
int ret;
- intel_pstate_init_limits(&global);
+ memset(&global, 0, sizeof(global));
+ global.max_perf_pct = 100;
+ intel_pstate_driver = driver;
ret = cpufreq_register_driver(intel_pstate_driver);
if (ret) {
intel_pstate_driver_cleanup();
return ret;
}
- mutex_lock(&intel_pstate_limits_lock);
- driver_registered = true;
- mutex_unlock(&intel_pstate_limits_lock);
+ global.min_perf_pct = min_perf_pct_min();
- if (intel_pstate_driver == &intel_pstate && !hwp_active &&
- pstate_funcs.get_target_pstate != get_target_pstate_use_cpu_load)
+ if (pid_in_use())
intel_pstate_debug_expose_params();
return 0;
if (hwp_active)
return -EBUSY;
- if (intel_pstate_driver == &intel_pstate && !hwp_active &&
- pstate_funcs.get_target_pstate != get_target_pstate_use_cpu_load)
+ if (pid_in_use())
intel_pstate_debug_hide_params();
- mutex_lock(&intel_pstate_limits_lock);
- driver_registered = false;
- mutex_unlock(&intel_pstate_limits_lock);
-
cpufreq_unregister_driver(intel_pstate_driver);
intel_pstate_driver_cleanup();
static ssize_t intel_pstate_show_status(char *buf)
{
- if (!driver_registered)
+ if (!intel_pstate_driver)
return sprintf(buf, "off\n");
return sprintf(buf, "%s\n", intel_pstate_driver == &intel_pstate ?
int ret;
if (size == 3 && !strncmp(buf, "off", size))
- return driver_registered ?
+ return intel_pstate_driver ?
intel_pstate_unregister_driver() : -EINVAL;
if (size == 6 && !strncmp(buf, "active", size)) {
- if (driver_registered) {
+ if (intel_pstate_driver) {
if (intel_pstate_driver == &intel_pstate)
return 0;
return ret;
}
- intel_pstate_driver = &intel_pstate;
- return intel_pstate_register_driver();
+ return intel_pstate_register_driver(&intel_pstate);
}
if (size == 7 && !strncmp(buf, "passive", size)) {
- if (driver_registered) {
- if (intel_pstate_driver != &intel_pstate)
+ if (intel_pstate_driver) {
+ if (intel_pstate_driver == &intel_cpufreq)
return 0;
ret = intel_pstate_unregister_driver();
return ret;
}
- intel_pstate_driver = &intel_cpufreq;
- return intel_pstate_register_driver();
+ return intel_pstate_register_driver(&intel_cpufreq);
}
return -EINVAL;
return 0;
}
-static void __init copy_pid_params(struct pstate_adjust_policy *policy)
-{
- pid_params.sample_rate_ms = policy->sample_rate_ms;
- pid_params.sample_rate_ns = pid_params.sample_rate_ms * NSEC_PER_MSEC;
- pid_params.p_gain_pct = policy->p_gain_pct;
- pid_params.i_gain_pct = policy->i_gain_pct;
- pid_params.d_gain_pct = policy->d_gain_pct;
- pid_params.deadband = policy->deadband;
- pid_params.setpoint = policy->setpoint;
-}
-
#ifdef CONFIG_ACPI
static void intel_pstate_use_acpi_profile(void)
{
- if (acpi_gbl_FADT.preferred_profile == PM_MOBILE)
- pstate_funcs.get_target_pstate =
- get_target_pstate_use_cpu_load;
+ switch (acpi_gbl_FADT.preferred_profile) {
+ case PM_MOBILE:
+ case PM_TABLET:
+ case PM_APPLIANCE_PC:
+ case PM_DESKTOP:
+ case PM_WORKSTATION:
+ pstate_funcs.update_util = intel_pstate_update_util;
+ }
}
#else
static void intel_pstate_use_acpi_profile(void)
pstate_funcs.get_scaling = funcs->get_scaling;
pstate_funcs.get_val = funcs->get_val;
pstate_funcs.get_vid = funcs->get_vid;
- pstate_funcs.get_target_pstate = funcs->get_target_pstate;
+ pstate_funcs.update_util = funcs->update_util;
intel_pstate_use_acpi_profile();
}
static int __init intel_pstate_init(void)
{
- const struct x86_cpu_id *id;
- struct cpu_defaults *cpu_def;
- int rc = 0;
+ int rc;
if (no_load)
return -ENODEV;
- if (x86_match_cpu(hwp_support_ids) && !no_hwp) {
- copy_cpu_funcs(&core_params.funcs);
- hwp_active++;
- intel_pstate.attr = hwp_cpufreq_attrs;
- goto hwp_cpu_matched;
- }
-
- id = x86_match_cpu(intel_pstate_cpu_ids);
- if (!id)
- return -ENODEV;
+ if (x86_match_cpu(hwp_support_ids)) {
+ copy_cpu_funcs(&core_funcs);
+ if (no_hwp) {
+ pstate_funcs.update_util = intel_pstate_update_util;
+ } else {
+ hwp_active++;
+ intel_pstate.attr = hwp_cpufreq_attrs;
+ pstate_funcs.update_util = intel_pstate_update_util_hwp;
+ goto hwp_cpu_matched;
+ }
+ } else {
+ const struct x86_cpu_id *id;
- cpu_def = (struct cpu_defaults *)id->driver_data;
+ id = x86_match_cpu(intel_pstate_cpu_ids);
+ if (!id)
+ return -ENODEV;
- copy_pid_params(&cpu_def->pid_policy);
- copy_cpu_funcs(&cpu_def->funcs);
+ copy_cpu_funcs((struct pstate_funcs *)id->driver_data);
+ }
if (intel_pstate_msrs_not_valid())
return -ENODEV;
intel_pstate_sysfs_expose_params();
mutex_lock(&intel_pstate_driver_lock);
- rc = intel_pstate_register_driver();
+ rc = intel_pstate_register_driver(default_driver);
mutex_unlock(&intel_pstate_driver_lock);
if (rc)
return rc;
no_load = 1;
} else if (!strcmp(str, "passive")) {
pr_info("Passive mode enabled\n");
- intel_pstate_driver = &intel_cpufreq;
+ default_driver = &intel_cpufreq;
no_hwp = 1;
}
if (!strcmp(str, "no_hwp")) {
.probe = mt8173_cpufreq_probe,
};
-static int mt8173_cpufreq_driver_init(void)
+/* List of machines supported by this driver */
+static const struct of_device_id mt8173_cpufreq_machines[] __initconst = {
+ { .compatible = "mediatek,mt817x", },
+ { .compatible = "mediatek,mt8173", },
+ { .compatible = "mediatek,mt8176", },
+
+ { }
+};
+
+static int __init mt8173_cpufreq_driver_init(void)
{
+ struct device_node *np;
+ const struct of_device_id *match;
struct platform_device *pdev;
int err;
- if (!of_machine_is_compatible("mediatek,mt8173"))
+ np = of_find_node_by_path("/");
+ if (!np)
return -ENODEV;
+ match = of_match_node(mt8173_cpufreq_machines, np);
+ of_node_put(np);
+ if (!match) {
+ pr_warn("Machine is not compatible with mt8173-cpufreq\n");
+ return -ENODEV;
+ }
+
err = platform_driver_register(&mt8173_cpufreq_platdrv);
if (err)
return err;
{
struct device_node *soc;
u32 sysfreq;
+ struct clk *pltclk;
+ int ret;
+ /* get platform freq by searching bus-frequency property */
soc = of_find_node_by_type(NULL, "soc");
- if (!soc)
- return 0;
-
- if (of_property_read_u32(soc, "bus-frequency", &sysfreq))
- sysfreq = 0;
+ if (soc) {
+ ret = of_property_read_u32(soc, "bus-frequency", &sysfreq);
+ of_node_put(soc);
+ if (!ret)
+ return sysfreq;
+ }
- of_node_put(soc);
+ /* get platform freq by its clock name */
+ pltclk = clk_get(NULL, "cg-pll0-div1");
+ if (IS_ERR(pltclk)) {
+ pr_err("%s: can't get bus frequency %ld\n",
+ __func__, PTR_ERR(pltclk));
+ return PTR_ERR(pltclk);
+ }
- return sysfreq;
+ return clk_get_rate(pltclk);
}
static struct clk *cpu_to_clk(int cpu)
static DEFINE_PER_CPU(struct clk, sh_cpuclk);
+struct cpufreq_target {
+ struct cpufreq_policy *policy;
+ unsigned int freq;
+};
+
static unsigned int sh_cpufreq_get(unsigned int cpu)
{
return (clk_get_rate(&per_cpu(sh_cpuclk, cpu)) + 500) / 1000;
}
-/*
- * Here we notify other drivers of the proposed change and the final change.
- */
-static int sh_cpufreq_target(struct cpufreq_policy *policy,
- unsigned int target_freq,
- unsigned int relation)
+static long __sh_cpufreq_target(void *arg)
{
- unsigned int cpu = policy->cpu;
+ struct cpufreq_target *target = arg;
+ struct cpufreq_policy *policy = target->policy;
+ int cpu = policy->cpu;
struct clk *cpuclk = &per_cpu(sh_cpuclk, cpu);
- cpumask_t cpus_allowed;
struct cpufreq_freqs freqs;
struct device *dev;
long freq;
- cpus_allowed = current->cpus_allowed;
- set_cpus_allowed_ptr(current, cpumask_of(cpu));
-
- BUG_ON(smp_processor_id() != cpu);
+ if (smp_processor_id() != cpu)
+ return -ENODEV;
dev = get_cpu_device(cpu);
/* Convert target_freq from kHz to Hz */
- freq = clk_round_rate(cpuclk, target_freq * 1000);
+ freq = clk_round_rate(cpuclk, target->freq * 1000);
if (freq < (policy->min * 1000) || freq > (policy->max * 1000))
return -EINVAL;
- dev_dbg(dev, "requested frequency %u Hz\n", target_freq * 1000);
+ dev_dbg(dev, "requested frequency %u Hz\n", target->freq * 1000);
freqs.old = sh_cpufreq_get(cpu);
freqs.new = (freq + 500) / 1000;
freqs.flags = 0;
- cpufreq_freq_transition_begin(policy, &freqs);
- set_cpus_allowed_ptr(current, &cpus_allowed);
+ cpufreq_freq_transition_begin(target->policy, &freqs);
clk_set_rate(cpuclk, freq);
- cpufreq_freq_transition_end(policy, &freqs, 0);
+ cpufreq_freq_transition_end(target->policy, &freqs, 0);
dev_dbg(dev, "set frequency %lu Hz\n", freq);
-
return 0;
}
+/*
+ * Here we notify other drivers of the proposed change and the final change.
+ */
+static int sh_cpufreq_target(struct cpufreq_policy *policy,
+ unsigned int target_freq,
+ unsigned int relation)
+{
+ struct cpufreq_target data = { .policy = policy, .freq = target_freq };
+
+ return work_on_cpu(policy->cpu, __sh_cpufreq_target, &data);
+}
+
static int sh_cpufreq_verify(struct cpufreq_policy *policy)
{
struct clk *cpuclk = &per_cpu(sh_cpuclk, policy->cpu);
unsigned long clock_tick,
unsigned long old_divisor, unsigned long divisor)
{
- unsigned long flags;
-
- local_irq_save(flags);
-
estar &= ~ESTAR_MODE_DIV_MASK;
/* This is based upon the state transition diagram in the IIe manual. */
} else {
BUG();
}
-
- local_irq_restore(flags);
}
static unsigned long index_to_estar_mode(unsigned int index)
return ret;
}
+static void __us2e_freq_get(void *arg)
+{
+ unsigned long *estar = arg;
+
+ *estar = read_hbreg(HBIRD_ESTAR_MODE_ADDR);
+}
+
static unsigned int us2e_freq_get(unsigned int cpu)
{
- cpumask_t cpus_allowed;
unsigned long clock_tick, estar;
- cpumask_copy(&cpus_allowed, ¤t->cpus_allowed);
- set_cpus_allowed_ptr(current, cpumask_of(cpu));
-
clock_tick = sparc64_get_clock_tick(cpu) / 1000;
- estar = read_hbreg(HBIRD_ESTAR_MODE_ADDR);
-
- set_cpus_allowed_ptr(current, &cpus_allowed);
+ if (smp_call_function_single(cpu, __us2e_freq_get, &estar, 1))
+ return 0;
return clock_tick / estar_to_divisor(estar);
}
-static int us2e_freq_target(struct cpufreq_policy *policy, unsigned int index)
+static void __us2e_freq_target(void *arg)
{
- unsigned int cpu = policy->cpu;
+ unsigned int cpu = smp_processor_id();
+ unsigned int *index = arg;
unsigned long new_bits, new_freq;
unsigned long clock_tick, divisor, old_divisor, estar;
- cpumask_t cpus_allowed;
-
- cpumask_copy(&cpus_allowed, ¤t->cpus_allowed);
- set_cpus_allowed_ptr(current, cpumask_of(cpu));
new_freq = clock_tick = sparc64_get_clock_tick(cpu) / 1000;
- new_bits = index_to_estar_mode(index);
- divisor = index_to_divisor(index);
+ new_bits = index_to_estar_mode(*index);
+ divisor = index_to_divisor(*index);
new_freq /= divisor;
estar = read_hbreg(HBIRD_ESTAR_MODE_ADDR);
old_divisor = estar_to_divisor(estar);
- if (old_divisor != divisor)
+ if (old_divisor != divisor) {
us2e_transition(estar, new_bits, clock_tick * 1000,
old_divisor, divisor);
+ }
+}
- set_cpus_allowed_ptr(current, &cpus_allowed);
+static int us2e_freq_target(struct cpufreq_policy *policy, unsigned int index)
+{
+ unsigned int cpu = policy->cpu;
- return 0;
+ return smp_call_function_single(cpu, __us2e_freq_target, &index, 1);
}
static int __init us2e_freq_cpu_init(struct cpufreq_policy *policy)
#define SAFARI_CFG_DIV_32 0x0000000080000000UL
#define SAFARI_CFG_DIV_MASK 0x00000000C0000000UL
-static unsigned long read_safari_cfg(void)
+static void read_safari_cfg(void *arg)
{
- unsigned long ret;
+ unsigned long ret, *val = arg;
__asm__ __volatile__("ldxa [%%g0] %1, %0"
: "=&r" (ret)
: "i" (ASI_SAFARI_CONFIG));
- return ret;
+ *val = ret;
}
-static void write_safari_cfg(unsigned long val)
+static void update_safari_cfg(void *arg)
{
+ unsigned long reg, *new_bits = arg;
+
+ read_safari_cfg(®);
+ reg &= ~SAFARI_CFG_DIV_MASK;
+ reg |= *new_bits;
+
__asm__ __volatile__("stxa %0, [%%g0] %1\n\t"
"membar #Sync"
: /* no outputs */
- : "r" (val), "i" (ASI_SAFARI_CONFIG)
+ : "r" (reg), "i" (ASI_SAFARI_CONFIG)
: "memory");
}
static unsigned int us3_freq_get(unsigned int cpu)
{
- cpumask_t cpus_allowed;
unsigned long reg;
- unsigned int ret;
-
- cpumask_copy(&cpus_allowed, ¤t->cpus_allowed);
- set_cpus_allowed_ptr(current, cpumask_of(cpu));
-
- reg = read_safari_cfg();
- ret = get_current_freq(cpu, reg);
-
- set_cpus_allowed_ptr(current, &cpus_allowed);
- return ret;
+ if (smp_call_function_single(cpu, read_safari_cfg, ®, 1))
+ return 0;
+ return get_current_freq(cpu, reg);
}
static int us3_freq_target(struct cpufreq_policy *policy, unsigned int index)
{
unsigned int cpu = policy->cpu;
- unsigned long new_bits, new_freq, reg;
- cpumask_t cpus_allowed;
-
- cpumask_copy(&cpus_allowed, ¤t->cpus_allowed);
- set_cpus_allowed_ptr(current, cpumask_of(cpu));
+ unsigned long new_bits, new_freq;
new_freq = sparc64_get_clock_tick(cpu) / 1000;
switch (index) {
BUG();
}
- reg = read_safari_cfg();
-
- reg &= ~SAFARI_CFG_DIV_MASK;
- reg |= new_bits;
- write_safari_cfg(reg);
-
- set_cpus_allowed_ptr(current, &cpus_allowed);
-
- return 0;
+ return smp_call_function_single(cpu, update_safari_cfg, &new_bits, 1);
}
static int __init us3_freq_cpu_init(struct cpufreq_policy *policy)
--- /dev/null
+/*
+ * Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/cpufreq.h>
+#include <linux/dma-mapping.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+#include <soc/tegra/bpmp.h>
+#include <soc/tegra/bpmp-abi.h>
+
+#define EDVD_CORE_VOLT_FREQ(core) (0x20 + (core) * 0x4)
+#define EDVD_CORE_VOLT_FREQ_F_SHIFT 0
+#define EDVD_CORE_VOLT_FREQ_V_SHIFT 16
+
+struct tegra186_cpufreq_cluster_info {
+ unsigned long offset;
+ int cpus[4];
+ unsigned int bpmp_cluster_id;
+};
+
+#define NO_CPU -1
+static const struct tegra186_cpufreq_cluster_info tegra186_clusters[] = {
+ /* Denver cluster */
+ {
+ .offset = SZ_64K * 7,
+ .cpus = { 1, 2, NO_CPU, NO_CPU },
+ .bpmp_cluster_id = 0,
+ },
+ /* A57 cluster */
+ {
+ .offset = SZ_64K * 6,
+ .cpus = { 0, 3, 4, 5 },
+ .bpmp_cluster_id = 1,
+ },
+};
+
+struct tegra186_cpufreq_cluster {
+ const struct tegra186_cpufreq_cluster_info *info;
+ struct cpufreq_frequency_table *table;
+};
+
+struct tegra186_cpufreq_data {
+ void __iomem *regs;
+
+ size_t num_clusters;
+ struct tegra186_cpufreq_cluster *clusters;
+};
+
+static int tegra186_cpufreq_init(struct cpufreq_policy *policy)
+{
+ struct tegra186_cpufreq_data *data = cpufreq_get_driver_data();
+ unsigned int i;
+
+ for (i = 0; i < data->num_clusters; i++) {
+ struct tegra186_cpufreq_cluster *cluster = &data->clusters[i];
+ const struct tegra186_cpufreq_cluster_info *info =
+ cluster->info;
+ int core;
+
+ for (core = 0; core < ARRAY_SIZE(info->cpus); core++) {
+ if (info->cpus[core] == policy->cpu)
+ break;
+ }
+ if (core == ARRAY_SIZE(info->cpus))
+ continue;
+
+ policy->driver_data =
+ data->regs + info->offset + EDVD_CORE_VOLT_FREQ(core);
+ cpufreq_table_validate_and_show(policy, cluster->table);
+ }
+
+ policy->cpuinfo.transition_latency = 300 * 1000;
+
+ return 0;
+}
+
+static int tegra186_cpufreq_set_target(struct cpufreq_policy *policy,
+ unsigned int index)
+{
+ struct cpufreq_frequency_table *tbl = policy->freq_table + index;
+ void __iomem *edvd_reg = policy->driver_data;
+ u32 edvd_val = tbl->driver_data;
+
+ writel(edvd_val, edvd_reg);
+
+ return 0;
+}
+
+static struct cpufreq_driver tegra186_cpufreq_driver = {
+ .name = "tegra186",
+ .flags = CPUFREQ_STICKY | CPUFREQ_HAVE_GOVERNOR_PER_POLICY,
+ .verify = cpufreq_generic_frequency_table_verify,
+ .target_index = tegra186_cpufreq_set_target,
+ .init = tegra186_cpufreq_init,
+ .attr = cpufreq_generic_attr,
+};
+
+static struct cpufreq_frequency_table *init_vhint_table(
+ struct platform_device *pdev, struct tegra_bpmp *bpmp,
+ unsigned int cluster_id)
+{
+ struct cpufreq_frequency_table *table;
+ struct mrq_cpu_vhint_request req;
+ struct tegra_bpmp_message msg;
+ struct cpu_vhint_data *data;
+ int err, i, j, num_rates = 0;
+ dma_addr_t phys;
+ void *virt;
+
+ virt = dma_alloc_coherent(bpmp->dev, sizeof(*data), &phys,
+ GFP_KERNEL | GFP_DMA32);
+ if (!virt)
+ return ERR_PTR(-ENOMEM);
+
+ data = (struct cpu_vhint_data *)virt;
+
+ memset(&req, 0, sizeof(req));
+ req.addr = phys;
+ req.cluster_id = cluster_id;
+
+ memset(&msg, 0, sizeof(msg));
+ msg.mrq = MRQ_CPU_VHINT;
+ msg.tx.data = &req;
+ msg.tx.size = sizeof(req);
+
+ err = tegra_bpmp_transfer(bpmp, &msg);
+ if (err) {
+ table = ERR_PTR(err);
+ goto free;
+ }
+
+ for (i = data->vfloor; i <= data->vceil; i++) {
+ u16 ndiv = data->ndiv[i];
+
+ if (ndiv < data->ndiv_min || ndiv > data->ndiv_max)
+ continue;
+
+ /* Only store lowest voltage index for each rate */
+ if (i > 0 && ndiv == data->ndiv[i - 1])
+ continue;
+
+ num_rates++;
+ }
+
+ table = devm_kcalloc(&pdev->dev, num_rates + 1, sizeof(*table),
+ GFP_KERNEL);
+ if (!table) {
+ table = ERR_PTR(-ENOMEM);
+ goto free;
+ }
+
+ for (i = data->vfloor, j = 0; i <= data->vceil; i++) {
+ struct cpufreq_frequency_table *point;
+ u16 ndiv = data->ndiv[i];
+ u32 edvd_val = 0;
+
+ if (ndiv < data->ndiv_min || ndiv > data->ndiv_max)
+ continue;
+
+ /* Only store lowest voltage index for each rate */
+ if (i > 0 && ndiv == data->ndiv[i - 1])
+ continue;
+
+ edvd_val |= i << EDVD_CORE_VOLT_FREQ_V_SHIFT;
+ edvd_val |= ndiv << EDVD_CORE_VOLT_FREQ_F_SHIFT;
+
+ point = &table[j++];
+ point->driver_data = edvd_val;
+ point->frequency = data->ref_clk_hz * ndiv / data->pdiv /
+ data->mdiv / 1000;
+ }
+
+ table[j].frequency = CPUFREQ_TABLE_END;
+
+free:
+ dma_free_coherent(bpmp->dev, sizeof(*data), virt, phys);
+
+ return table;
+}
+
+static int tegra186_cpufreq_probe(struct platform_device *pdev)
+{
+ struct tegra186_cpufreq_data *data;
+ struct tegra_bpmp *bpmp;
+ struct resource *res;
+ unsigned int i = 0, err;
+
+ data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ data->clusters = devm_kcalloc(&pdev->dev, ARRAY_SIZE(tegra186_clusters),
+ sizeof(*data->clusters), GFP_KERNEL);
+ if (!data->clusters)
+ return -ENOMEM;
+
+ data->num_clusters = ARRAY_SIZE(tegra186_clusters);
+
+ bpmp = tegra_bpmp_get(&pdev->dev);
+ if (IS_ERR(bpmp))
+ return PTR_ERR(bpmp);
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ data->regs = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(data->regs)) {
+ err = PTR_ERR(data->regs);
+ goto put_bpmp;
+ }
+
+ for (i = 0; i < data->num_clusters; i++) {
+ struct tegra186_cpufreq_cluster *cluster = &data->clusters[i];
+
+ cluster->info = &tegra186_clusters[i];
+ cluster->table = init_vhint_table(
+ pdev, bpmp, cluster->info->bpmp_cluster_id);
+ if (IS_ERR(cluster->table)) {
+ err = PTR_ERR(cluster->table);
+ goto put_bpmp;
+ }
+ }
+
+ tegra_bpmp_put(bpmp);
+
+ tegra186_cpufreq_driver.driver_data = data;
+
+ err = cpufreq_register_driver(&tegra186_cpufreq_driver);
+ if (err)
+ return err;
+
+ return 0;
+
+put_bpmp:
+ tegra_bpmp_put(bpmp);
+
+ return err;
+}
+
+static int tegra186_cpufreq_remove(struct platform_device *pdev)
+{
+ cpufreq_unregister_driver(&tegra186_cpufreq_driver);
+
+ return 0;
+}
+
+static const struct of_device_id tegra186_cpufreq_of_match[] = {
+ { .compatible = "nvidia,tegra186-ccplex-cluster", },
+ { }
+};
+MODULE_DEVICE_TABLE(of, tegra186_cpufreq_of_match);
+
+static struct platform_driver tegra186_cpufreq_platform_driver = {
+ .driver = {
+ .name = "tegra186-cpufreq",
+ .of_match_table = tegra186_cpufreq_of_match,
+ },
+ .probe = tegra186_cpufreq_probe,
+ .remove = tegra186_cpufreq_remove,
+};
+module_platform_driver(tegra186_cpufreq_platform_driver);
+
+MODULE_AUTHOR("Mikko Perttunen <mperttunen@nvidia.com>");
+MODULE_DESCRIPTION("NVIDIA Tegra186 cpufreq driver");
+MODULE_LICENSE("GPL v2");
static int __init cps_cpuidle_init(void)
{
- int err, cpu, core, i;
+ int err, cpu, i;
struct cpuidle_device *device;
/* Detect supported states */
}
for_each_possible_cpu(cpu) {
- core = cpu_data[cpu].core;
device = &per_cpu(cpuidle_dev, cpu);
device->cpu = cpu;
#ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED
snooze_exit_time = get_tb() + snooze_timeout;
ppc64_runlatch_off();
+ HMT_very_low();
while (!need_resched()) {
- HMT_low();
- HMT_very_low();
- if (snooze_timeout_en && get_tb() > snooze_exit_time)
+ if (likely(snooze_timeout_en) && get_tb() > snooze_exit_time)
break;
}
stop_psscr_table[index].mask = psscr_mask;
}
+/*
+ * Returns 0 if prop1_len == prop2_len. Else returns -1
+ */
+static inline int validate_dt_prop_sizes(const char *prop1, int prop1_len,
+ const char *prop2, int prop2_len)
+{
+ if (prop1_len == prop2_len)
+ return 0;
+
+ pr_warn("cpuidle-powernv: array sizes don't match for %s and %s\n",
+ prop1, prop2);
+ return -1;
+}
+
static int powernv_add_idle_states(void)
{
struct device_node *power_mgt;
int nr_idle_states = 1; /* Snooze */
- int dt_idle_states;
+ int dt_idle_states, count;
u32 latency_ns[CPUIDLE_STATE_MAX];
u32 residency_ns[CPUIDLE_STATE_MAX];
u32 flags[CPUIDLE_STATE_MAX];
goto out;
}
+ count = of_property_count_u32_elems(power_mgt,
+ "ibm,cpu-idle-state-latencies-ns");
+
+ if (validate_dt_prop_sizes("ibm,cpu-idle-state-flags", dt_idle_states,
+ "ibm,cpu-idle-state-latencies-ns",
+ count) != 0)
+ goto out;
+
+ count = of_property_count_strings(power_mgt,
+ "ibm,cpu-idle-state-names");
+ if (validate_dt_prop_sizes("ibm,cpu-idle-state-flags", dt_idle_states,
+ "ibm,cpu-idle-state-names",
+ count) != 0)
+ goto out;
+
/*
* Since snooze is used as first idle state, max idle states allowed is
* CPUIDLE_STATE_MAX -1
has_stop_states = (flags[0] &
(OPAL_PM_STOP_INST_FAST | OPAL_PM_STOP_INST_DEEP));
if (has_stop_states) {
+ count = of_property_count_u64_elems(power_mgt,
+ "ibm,cpu-idle-state-psscr");
+ if (validate_dt_prop_sizes("ibm,cpu-idle-state-flags",
+ dt_idle_states,
+ "ibm,cpu-idle-state-psscr",
+ count) != 0)
+ goto out;
+
+ count = of_property_count_u64_elems(power_mgt,
+ "ibm,cpu-idle-state-psscr-mask");
+ if (validate_dt_prop_sizes("ibm,cpu-idle-state-flags",
+ dt_idle_states,
+ "ibm,cpu-idle-state-psscr-mask",
+ count) != 0)
+ goto out;
+
if (of_property_read_u64_array(power_mgt,
"ibm,cpu-idle-state-psscr", psscr_val, dt_idle_states)) {
pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-psscr in DT\n");
}
}
- rc = of_property_read_u32_array(power_mgt,
- "ibm,cpu-idle-state-residency-ns", residency_ns, dt_idle_states);
+ count = of_property_count_u32_elems(power_mgt,
+ "ibm,cpu-idle-state-residency-ns");
+
+ if (count < 0) {
+ rc = count;
+ } else if (validate_dt_prop_sizes("ibm,cpu-idle-state-flags",
+ dt_idle_states,
+ "ibm,cpu-idle-state-residency-ns",
+ count) != 0) {
+ goto out;
+ } else {
+ rc = of_property_read_u32_array(power_mgt,
+ "ibm,cpu-idle-state-residency-ns",
+ residency_ns, dt_idle_states);
+ }
for (i = 0; i < dt_idle_states; i++) {
unsigned int exit_latency, target_residency;
ctx->dev = caam_jr_alloc();
if (IS_ERR(ctx->dev)) {
- dev_err(ctx->dev, "Job Ring Device allocation for transform failed\n");
+ pr_err("Job Ring Device allocation for transform failed\n");
return PTR_ERR(ctx->dev);
}
/* Try to run it through DECO0 */
ret = run_descriptor_deco0(ctrldev, desc, &status);
- if (ret || status) {
+ if (ret ||
+ (status && status != JRSTA_SSRC_JUMP_HALT_CC)) {
dev_err(ctrldev,
"Failed to deinstantiate RNG4 SH%d\n",
sh_idx);
struct device *ctrldev;
struct caam_drv_private *ctrlpriv;
struct caam_ctrl __iomem *ctrl;
- int ring;
ctrldev = &pdev->dev;
ctrlpriv = dev_get_drvdata(ctrldev);
ctrl = (struct caam_ctrl __iomem *)ctrlpriv->ctrl;
- /* Remove platform devices for JobRs */
- for (ring = 0; ring < ctrlpriv->total_jobrs; ring++)
- of_device_unregister(ctrlpriv->jrpdev[ring]);
+ /* Remove platform devices under the crypto node */
+ of_platform_depopulate(ctrldev);
/* De-initialize RNG state handles initialized by this driver. */
if (ctrlpriv->rng4_sh_init)
DEFINE_SIMPLE_ATTRIBUTE(caam_fops_u64_ro, caam_debugfs_u64_get, NULL, "%llu\n");
#endif
+static const struct of_device_id caam_match[] = {
+ {
+ .compatible = "fsl,sec-v4.0",
+ },
+ {
+ .compatible = "fsl,sec4.0",
+ },
+ {},
+};
+MODULE_DEVICE_TABLE(of, caam_match);
+
/* Probe routine for CAAM top (controller) level */
static int caam_probe(struct platform_device *pdev)
{
- int ret, ring, ridx, rspec, gen_sk, ent_delay = RTSDCTL_ENT_DLY_MIN;
+ int ret, ring, gen_sk, ent_delay = RTSDCTL_ENT_DLY_MIN;
u64 caam_id;
struct device *dev;
struct device_node *nprop, *np;
goto iounmap_ctrl;
}
- /*
- * Detect and enable JobRs
- * First, find out how many ring spec'ed, allocate references
- * for all, then go probe each one.
- */
- rspec = 0;
- for_each_available_child_of_node(nprop, np)
- if (of_device_is_compatible(np, "fsl,sec-v4.0-job-ring") ||
- of_device_is_compatible(np, "fsl,sec4.0-job-ring"))
- rspec++;
-
- ctrlpriv->jrpdev = devm_kcalloc(&pdev->dev, rspec,
- sizeof(*ctrlpriv->jrpdev), GFP_KERNEL);
- if (ctrlpriv->jrpdev == NULL) {
- ret = -ENOMEM;
+ ret = of_platform_populate(nprop, caam_match, NULL, dev);
+ if (ret) {
+ dev_err(dev, "JR platform devices creation error\n");
goto iounmap_ctrl;
}
ring = 0;
- ridx = 0;
- ctrlpriv->total_jobrs = 0;
for_each_available_child_of_node(nprop, np)
if (of_device_is_compatible(np, "fsl,sec-v4.0-job-ring") ||
of_device_is_compatible(np, "fsl,sec4.0-job-ring")) {
- ctrlpriv->jrpdev[ring] =
- of_platform_device_create(np, NULL, dev);
- if (!ctrlpriv->jrpdev[ring]) {
- pr_warn("JR physical index %d: Platform device creation error\n",
- ridx);
- ridx++;
- continue;
- }
ctrlpriv->jr[ring] = (struct caam_job_ring __iomem __force *)
((__force uint8_t *)ctrl +
- (ridx + JR_BLOCK_NUMBER) *
+ (ring + JR_BLOCK_NUMBER) *
BLOCK_OFFSET
);
ctrlpriv->total_jobrs++;
ring++;
- ridx++;
- }
+ }
/* Check to see if QI present. If so, enable */
ctrlpriv->qi_present =
return ret;
}
-static struct of_device_id caam_match[] = {
- {
- .compatible = "fsl,sec-v4.0",
- },
- {
- .compatible = "fsl,sec4.0",
- },
- {},
-};
-MODULE_DEVICE_TABLE(of, caam_match);
-
static struct platform_driver caam_driver = {
.driver = {
.name = "caam",
struct caam_drv_private {
struct device *dev;
- struct platform_device **jrpdev; /* Alloc'ed array per sub-device */
struct platform_device *pdev;
/* Physical-presence section */
struct list_head list;
};
+struct spu_qreg {
+ struct spu_queue *queue;
+ unsigned long type;
+};
+
static struct spu_queue **cpu_to_cwq;
static struct spu_queue **cpu_to_mau;
kmem_cache_destroy(queue_cache[HV_NCS_QTYPE_CWQ - 1]);
}
-static int spu_queue_register(struct spu_queue *p, unsigned long q_type)
+static long spu_queue_register_workfn(void *arg)
{
- cpumask_var_t old_allowed;
+ struct spu_qreg *qr = arg;
+ struct spu_queue *p = qr->queue;
+ unsigned long q_type = qr->type;
unsigned long hv_ret;
- if (cpumask_empty(&p->sharing))
- return -EINVAL;
-
- if (!alloc_cpumask_var(&old_allowed, GFP_KERNEL))
- return -ENOMEM;
-
- cpumask_copy(old_allowed, ¤t->cpus_allowed);
-
- set_cpus_allowed_ptr(current, &p->sharing);
-
hv_ret = sun4v_ncs_qconf(q_type, __pa(p->q),
CWQ_NUM_ENTRIES, &p->qhandle);
if (!hv_ret)
sun4v_ncs_sethead_marker(p->qhandle, 0);
- set_cpus_allowed_ptr(current, old_allowed);
+ return hv_ret ? -EINVAL : 0;
+}
- free_cpumask_var(old_allowed);
+static int spu_queue_register(struct spu_queue *p, unsigned long q_type)
+{
+ int cpu = cpumask_any_and(&p->sharing, cpu_online_mask);
+ struct spu_qreg qr = { .queue = p, .type = q_type };
- return (hv_ret ? -EINVAL : 0);
+ return work_on_cpu_safe(cpu, spu_queue_register_workfn, &qr);
}
static int spu_queue_setup(struct spu_queue *p)
tristate "DAX: direct access to differentiated memory"
default m if NVDIMM_DAX
depends on TRANSPARENT_HUGEPAGE
+ select SRCU
help
Support raw access to differentiated (persistence, bandwidth,
latency...) memory via an mmap(2) capable character
#include "dax.h"
static dev_t dax_devt;
+DEFINE_STATIC_SRCU(dax_srcu);
static struct class *dax_class;
static DEFINE_IDA(dax_minor_ida);
static int nr_dax = CONFIG_NR_DEV_DAX;
* @region - parent region
* @dev - device backing the character device
* @cdev - core chardev data
- * @alive - !alive + rcu grace period == no new mappings can be established
+ * @alive - !alive + srcu grace period == no new mappings can be established
* @id - child id in the region
* @num_resources - number of physical address extents in this device
* @res - array of physical address ranges
static int dax_dev_huge_fault(struct vm_fault *vmf,
enum page_entry_size pe_size)
{
- int rc;
+ int rc, id;
struct file *filp = vmf->vma->vm_file;
struct dax_dev *dax_dev = filp->private_data;
? "write" : "read",
vmf->vma->vm_start, vmf->vma->vm_end);
- rcu_read_lock();
+ id = srcu_read_lock(&dax_srcu);
switch (pe_size) {
case PE_SIZE_PTE:
rc = __dax_dev_pte_fault(dax_dev, vmf);
default:
return VM_FAULT_FALLBACK;
}
- rcu_read_unlock();
+ srcu_read_unlock(&dax_srcu, id);
return rc;
}
* Note, rcu is not protecting the liveness of dax_dev, rcu is
* ensuring that any fault handlers that might have seen
* dax_dev->alive == true, have completed. Any fault handlers
- * that start after synchronize_rcu() has started will abort
+ * that start after synchronize_srcu() has started will abort
* upon seeing dax_dev->alive == false.
*/
dax_dev->alive = false;
- synchronize_rcu();
+ synchronize_srcu(&dax_srcu);
unmap_mapping_range(dax_dev->inode->i_mapping, 0, 0, 1);
cdev_del(cdev);
device_unregister(dev);
#define DEVFREQ_GOV_SUSPEND 0x4
#define DEVFREQ_GOV_RESUME 0x5
+/**
+ * struct devfreq_governor - Devfreq policy governor
+ * @node: list node - contains registered devfreq governors
+ * @name: Governor's name
+ * @immutable: Immutable flag for governor. If the value is 1,
+ * this govenror is never changeable to other governor.
+ * @get_target_freq: Returns desired operating frequency for the device.
+ * Basically, get_target_freq will run
+ * devfreq_dev_profile.get_dev_status() to get the
+ * status of the device (load = busy_time / total_time).
+ * If no_central_polling is set, this callback is called
+ * only with update_devfreq() notified by OPP.
+ * @event_handler: Callback for devfreq core framework to notify events
+ * to governors. Events include per device governor
+ * init and exit, opp changes out of devfreq, suspend
+ * and resume of per device devfreq during device idle.
+ *
+ * Note that the callbacks are called with devfreq->lock locked by devfreq.
+ */
+struct devfreq_governor {
+ struct list_head node;
+
+ const char name[DEVFREQ_NAME_LEN];
+ const unsigned int immutable;
+ int (*get_target_freq)(struct devfreq *this, unsigned long *freq);
+ int (*event_handler)(struct devfreq *devfreq,
+ unsigned int event, void *data);
+};
+
/* Caution: devfreq->lock must be locked before calling update_devfreq */
extern int update_devfreq(struct devfreq *devfreq);
bool
menuconfig EDAC
- bool "EDAC (Error Detection And Correction) reporting"
- depends on HAS_IOMEM && EDAC_SUPPORT
+ tristate "EDAC (Error Detection And Correction) reporting"
+ depends on HAS_IOMEM && EDAC_SUPPORT && RAS
help
- EDAC is designed to report errors in the core system.
- These are low-level errors that are reported in the CPU or
- supporting chipset or other subsystems:
+ EDAC is a subsystem along with hardware-specific drivers designed to
+ report hardware errors. These are low-level errors that are reported
+ in the CPU or supporting chipset or other subsystems:
memory errors, cache errors, PCI errors, thermal throttling, etc..
If unsure, select 'Y'.
- If this code is reporting problems on your system, please
- see the EDAC project web pages for more information at:
-
- <http://bluesmoke.sourceforge.net/>
-
- and:
-
- <http://buttersideup.com/edacwiki>
-
- There is also a mailing list for the EDAC project, which can
- be found via the sourceforge page.
+ The mailing list for the EDAC project is linux-edac@vger.kernel.org.
if EDAC
which occur really early upon boot, before the module infrastructure
has been initialized.
-config EDAC_MM_EDAC
- tristate "Main Memory EDAC (Error Detection And Correction) reporting"
- select RAS
- help
- Some systems are able to detect and correct errors in main
- memory. EDAC can report statistics on memory error
- detection and correction (EDAC - or commonly referred to ECC
- errors). EDAC will also try to decode where these errors
- occurred so that a particular failing memory module can be
- replaced. If unsure, select 'Y'.
-
config EDAC_GHES
bool "Output ACPI APEI/GHES BIOS detected errors via EDAC"
- depends on ACPI_APEI_GHES && (EDAC_MM_EDAC=y)
- default y
+ depends on ACPI_APEI_GHES && (EDAC=y)
help
Not all machines support hardware-driven error report. Some of those
provide a BIOS-driven error report mechanism via ACPI, using the
config EDAC_AMD64
tristate "AMD64 (Opteron, Athlon64)"
- depends on EDAC_MM_EDAC && AMD_NB && EDAC_DECODE_MCE
+ depends on AMD_NB && EDAC_DECODE_MCE
help
Support for error detection and correction of DRAM ECC errors on
the AMD64 families (>= K8) of memory controllers.
config EDAC_AMD76X
tristate "AMD 76x (760, 762, 768)"
- depends on EDAC_MM_EDAC && PCI && X86_32
+ depends on PCI && X86_32
help
Support for error detection and correction on the AMD 76x
series of chipsets used with the Athlon processor.
config EDAC_E7XXX
tristate "Intel e7xxx (e7205, e7500, e7501, e7505)"
- depends on EDAC_MM_EDAC && PCI && X86_32
+ depends on PCI && X86_32
help
Support for error detection and correction on the Intel
E7205, E7500, E7501 and E7505 server chipsets.
config EDAC_E752X
tristate "Intel e752x (e7520, e7525, e7320) and 3100"
- depends on EDAC_MM_EDAC && PCI && X86
+ depends on PCI && X86
help
Support for error detection and correction on the Intel
E7520, E7525, E7320 server chipsets.
config EDAC_I82443BXGX
tristate "Intel 82443BX/GX (440BX/GX)"
- depends on EDAC_MM_EDAC && PCI && X86_32
+ depends on PCI && X86_32
depends on BROKEN
help
Support for error detection and correction on the Intel
config EDAC_I82875P
tristate "Intel 82875p (D82875P, E7210)"
- depends on EDAC_MM_EDAC && PCI && X86_32
+ depends on PCI && X86_32
help
Support for error detection and correction on the Intel
DP82785P and E7210 server chipsets.
config EDAC_I82975X
tristate "Intel 82975x (D82975x)"
- depends on EDAC_MM_EDAC && PCI && X86
+ depends on PCI && X86
help
Support for error detection and correction on the Intel
DP82975x server chipsets.
config EDAC_I3000
tristate "Intel 3000/3010"
- depends on EDAC_MM_EDAC && PCI && X86
+ depends on PCI && X86
help
Support for error detection and correction on the Intel
3000 and 3010 server chipsets.
config EDAC_I3200
tristate "Intel 3200"
- depends on EDAC_MM_EDAC && PCI && X86
+ depends on PCI && X86
help
Support for error detection and correction on the Intel
3200 and 3210 server chipsets.
config EDAC_IE31200
tristate "Intel e312xx"
- depends on EDAC_MM_EDAC && PCI && X86
+ depends on PCI && X86
help
Support for error detection and correction on the Intel
E3-1200 based DRAM controllers.
config EDAC_X38
tristate "Intel X38"
- depends on EDAC_MM_EDAC && PCI && X86
+ depends on PCI && X86
help
Support for error detection and correction on the Intel
X38 server chipsets.
config EDAC_I5400
tristate "Intel 5400 (Seaburg) chipsets"
- depends on EDAC_MM_EDAC && PCI && X86
+ depends on PCI && X86
help
Support for error detection and correction the Intel
i5400 MCH chipset (Seaburg).
config EDAC_I7CORE
tristate "Intel i7 Core (Nehalem) processors"
- depends on EDAC_MM_EDAC && PCI && X86 && X86_MCE_INTEL
+ depends on PCI && X86 && X86_MCE_INTEL
help
Support for error detection and correction the Intel
i7 Core (Nehalem) Integrated Memory Controller that exists on
config EDAC_I82860
tristate "Intel 82860"
- depends on EDAC_MM_EDAC && PCI && X86_32
+ depends on PCI && X86_32
help
Support for error detection and correction on the Intel
82860 chipset.
config EDAC_R82600
tristate "Radisys 82600 embedded chipset"
- depends on EDAC_MM_EDAC && PCI && X86_32
+ depends on PCI && X86_32
help
Support for error detection and correction on the Radisys
82600 embedded chipset.
config EDAC_I5000
tristate "Intel Greencreek/Blackford chipset"
- depends on EDAC_MM_EDAC && X86 && PCI
+ depends on X86 && PCI
help
Support for error detection and correction the Intel
Greekcreek/Blackford chipsets.
config EDAC_I5100
tristate "Intel San Clemente MCH"
- depends on EDAC_MM_EDAC && X86 && PCI
+ depends on X86 && PCI
help
Support for error detection and correction the Intel
San Clemente MCH.
config EDAC_I7300
tristate "Intel Clarksboro MCH"
- depends on EDAC_MM_EDAC && X86 && PCI
+ depends on X86 && PCI
help
Support for error detection and correction the Intel
Clarksboro MCH (Intel 7300 chipset).
config EDAC_SBRIDGE
tristate "Intel Sandy-Bridge/Ivy-Bridge/Haswell Integrated MC"
- depends on EDAC_MM_EDAC && PCI && X86_64 && X86_MCE_INTEL
- depends on PCI_MMCONFIG
+ depends on PCI && X86_64 && X86_MCE_INTEL && PCI_MMCONFIG
help
Support for error detection and correction the Intel
Sandy Bridge, Ivy Bridge and Haswell Integrated Memory Controllers.
config EDAC_SKX
tristate "Intel Skylake server Integrated MC"
- depends on EDAC_MM_EDAC && PCI && X86_64 && X86_MCE_INTEL
- depends on PCI_MMCONFIG
+ depends on PCI && X86_64 && X86_MCE_INTEL && PCI_MMCONFIG
help
Support for error detection and correction the Intel
Skylake server Integrated Memory Controllers.
config EDAC_PND2
tristate "Intel Pondicherry2"
- depends on EDAC_MM_EDAC && PCI && X86_64 && X86_MCE_INTEL
+ depends on PCI && X86_64 && X86_MCE_INTEL
help
Support for error detection and correction on the Intel
Pondicherry2 Integrated Memory Controller. This SoC IP is
config EDAC_MPC85XX
tristate "Freescale MPC83xx / MPC85xx"
- depends on EDAC_MM_EDAC && FSL_SOC
+ depends on FSL_SOC
help
Support for error detection and correction on the Freescale
MPC8349, MPC8560, MPC8540, MPC8548, T4240
config EDAC_LAYERSCAPE
tristate "Freescale Layerscape DDR"
- depends on EDAC_MM_EDAC && ARCH_LAYERSCAPE
+ depends on ARCH_LAYERSCAPE
help
Support for error detection and correction on Freescale memory
controllers on Layerscape SoCs.
config EDAC_MV64X60
tristate "Marvell MV64x60"
- depends on EDAC_MM_EDAC && MV64X60
+ depends on MV64X60
help
Support for error detection and correction on the Marvell
MV64360 and MV64460 chipsets.
config EDAC_PASEMI
tristate "PA Semi PWRficient"
- depends on EDAC_MM_EDAC && PCI
- depends on PPC_PASEMI
+ depends on PPC_PASEMI && PCI
help
Support for error detection and correction on PA Semi
PWRficient.
config EDAC_CELL
tristate "Cell Broadband Engine memory controller"
- depends on EDAC_MM_EDAC && PPC_CELL_COMMON
+ depends on PPC_CELL_COMMON
help
Support for error detection and correction on the
Cell Broadband Engine internal memory controller
config EDAC_PPC4XX
tristate "PPC4xx IBM DDR2 Memory Controller"
- depends on EDAC_MM_EDAC && 4xx
+ depends on 4xx
help
This enables support for EDAC on the ECC memory used
with the IBM DDR2 memory controller found in various
config EDAC_AMD8131
tristate "AMD8131 HyperTransport PCI-X Tunnel"
- depends on EDAC_MM_EDAC && PCI && PPC_MAPLE
+ depends on PCI && PPC_MAPLE
help
Support for error detection and correction on the
AMD8131 HyperTransport PCI-X Tunnel chip.
config EDAC_AMD8111
tristate "AMD8111 HyperTransport I/O Hub"
- depends on EDAC_MM_EDAC && PCI && PPC_MAPLE
+ depends on PCI && PPC_MAPLE
help
Support for error detection and correction on the
AMD8111 HyperTransport I/O Hub chip.
config EDAC_CPC925
tristate "IBM CPC925 Memory Controller (PPC970FX)"
- depends on EDAC_MM_EDAC && PPC64
+ depends on PPC64
help
Support for error detection and correction on the
IBM CPC925 Bridge and Memory Controller, which is
config EDAC_TILE
tristate "Tilera Memory Controller"
- depends on EDAC_MM_EDAC && TILE
+ depends on TILE
default y
help
Support for error detection and correction on the
config EDAC_HIGHBANK_MC
tristate "Highbank Memory Controller"
- depends on EDAC_MM_EDAC && ARCH_HIGHBANK
+ depends on ARCH_HIGHBANK
help
Support for error detection and correction on the
Calxeda Highbank memory controller.
config EDAC_HIGHBANK_L2
tristate "Highbank L2 Cache"
- depends on EDAC_MM_EDAC && ARCH_HIGHBANK
+ depends on ARCH_HIGHBANK
help
Support for error detection and correction on the
Calxeda Highbank memory controller.
config EDAC_OCTEON_PC
tristate "Cavium Octeon Primary Caches"
- depends on EDAC_MM_EDAC && CPU_CAVIUM_OCTEON
+ depends on CPU_CAVIUM_OCTEON
help
Support for error detection and correction on the primary caches of
the cnMIPS cores of Cavium Octeon family SOCs.
config EDAC_OCTEON_L2C
tristate "Cavium Octeon Secondary Caches (L2C)"
- depends on EDAC_MM_EDAC && CAVIUM_OCTEON_SOC
+ depends on CAVIUM_OCTEON_SOC
help
Support for error detection and correction on the
Cavium Octeon family of SOCs.
config EDAC_OCTEON_LMC
tristate "Cavium Octeon DRAM Memory Controller (LMC)"
- depends on EDAC_MM_EDAC && CAVIUM_OCTEON_SOC
+ depends on CAVIUM_OCTEON_SOC
help
Support for error detection and correction on the
Cavium Octeon family of SOCs.
config EDAC_OCTEON_PCI
tristate "Cavium Octeon PCI Controller"
- depends on EDAC_MM_EDAC && PCI && CAVIUM_OCTEON_SOC
+ depends on PCI && CAVIUM_OCTEON_SOC
help
Support for error detection and correction on the
Cavium Octeon family of SOCs.
+config EDAC_THUNDERX
+ tristate "Cavium ThunderX EDAC"
+ depends on ARM64
+ depends on PCI
+ help
+ Support for error detection and correction on the
+ Cavium ThunderX memory controllers (LMC), Cache
+ Coherent Processor Interconnect (CCPI) and L2 cache
+ blocks (TAD, CBC, MCI).
+
config EDAC_ALTERA
bool "Altera SOCFPGA ECC"
- depends on EDAC_MM_EDAC=y && ARCH_SOCFPGA
+ depends on EDAC=y && ARCH_SOCFPGA
help
Support for error detection and correction on the
Altera SOCs. This must be selected for SDRAM ECC.
config EDAC_SYNOPSYS
tristate "Synopsys DDR Memory Controller"
- depends on EDAC_MM_EDAC && ARCH_ZYNQ
+ depends on ARCH_ZYNQ
help
Support for error detection and correction on the Synopsys DDR
memory controller.
config EDAC_XGENE
tristate "APM X-Gene SoC"
- depends on EDAC_MM_EDAC && (ARM64 || COMPILE_TEST)
+ depends on (ARM64 || COMPILE_TEST)
help
Support for error detection and correction on the
APM X-Gene family of SOCs.
# GNU General Public License.
#
-obj-$(CONFIG_EDAC) := edac_stub.o
-obj-$(CONFIG_EDAC_MM_EDAC) += edac_core.o
+obj-$(CONFIG_EDAC) := edac_core.o
edac_core-y := edac_mc.o edac_device.o edac_mc_sysfs.o
edac_core-y += edac_module.o edac_device_sysfs.o wq.o
obj-$(CONFIG_EDAC_TILE) += tile_edac.o
-obj-$(CONFIG_EDAC_HIGHBANK_MC) += highbank_mc_edac.o
-obj-$(CONFIG_EDAC_HIGHBANK_L2) += highbank_l2_edac.o
+obj-$(CONFIG_EDAC_HIGHBANK_MC) += highbank_mc_edac.o
+obj-$(CONFIG_EDAC_HIGHBANK_L2) += highbank_l2_edac.o
obj-$(CONFIG_EDAC_OCTEON_PC) += octeon_edac-pc.o
obj-$(CONFIG_EDAC_OCTEON_L2C) += octeon_edac-l2c.o
obj-$(CONFIG_EDAC_OCTEON_LMC) += octeon_edac-lmc.o
obj-$(CONFIG_EDAC_OCTEON_PCI) += octeon_edac-pci.o
+obj-$(CONFIG_EDAC_THUNDERX) += thunderx_edac.o
obj-$(CONFIG_EDAC_ALTERA) += altera_edac.o
obj-$(CONFIG_EDAC_SYNOPSYS) += synopsys_edac.o
return ret;
}
+static int socfpga_is_a10(void)
+{
+ return of_machine_is_compatible("altr,socfpga-arria10");
+}
+
static int validate_parent_available(struct device_node *np);
static const struct of_device_id altr_edac_a10_device_of_match[];
static int __init __maybe_unused altr_init_a10_ecc_device_type(char *compat)
{
int irq;
- struct device_node *child, *np = of_find_compatible_node(NULL, NULL,
- "altr,socfpga-a10-ecc-manager");
+ struct device_node *child, *np;
+
+ if (!socfpga_is_a10())
+ return -ENODEV;
+
+ np = of_find_compatible_node(NULL, NULL,
+ "altr,socfpga-a10-ecc-manager");
if (!np) {
edac_printk(KERN_ERR, EDAC_DEVICE, "ECC Manager not found\n");
return -ENODEV;
static int __init socfpga_init_sdmmc_ecc(void)
{
int rc = -ENODEV;
- struct device_node *child = of_find_compatible_node(NULL, NULL,
- "altr,socfpga-sdmmc-ecc");
+ struct device_node *child;
+
+ if (!socfpga_is_a10())
+ return -ENODEV;
+
+ child = of_find_compatible_node(NULL, NULL, "altr,socfpga-sdmmc-ecc");
if (!child) {
edac_printk(KERN_WARNING, EDAC_DEVICE, "SDMMC node not found\n");
return -ENODEV;
#define edac_atomic_scrub(va, size) do { } while (0)
#endif
+int edac_op_state = EDAC_OPSTATE_INVAL;
+EXPORT_SYMBOL_GPL(edac_op_state);
+
+static int edac_report = EDAC_REPORTING_ENABLED;
+
/* lock to memory controller's control array */
static DEFINE_MUTEX(mem_ctls_mutex);
static LIST_HEAD(mc_devices);
static struct bus_type mc_bus[EDAC_MAX_MCS];
+int edac_get_report_status(void)
+{
+ return edac_report;
+}
+EXPORT_SYMBOL_GPL(edac_get_report_status);
+
+void edac_set_report_status(int new)
+{
+ if (new == EDAC_REPORTING_ENABLED ||
+ new == EDAC_REPORTING_DISABLED ||
+ new == EDAC_REPORTING_FORCE)
+ edac_report = new;
+}
+EXPORT_SYMBOL_GPL(edac_set_report_status);
+
+static int edac_report_set(const char *str, const struct kernel_param *kp)
+{
+ if (!str)
+ return -EINVAL;
+
+ if (!strncmp(str, "on", 2))
+ edac_report = EDAC_REPORTING_ENABLED;
+ else if (!strncmp(str, "off", 3))
+ edac_report = EDAC_REPORTING_DISABLED;
+ else if (!strncmp(str, "force", 5))
+ edac_report = EDAC_REPORTING_FORCE;
+
+ return 0;
+}
+
+static int edac_report_get(char *buffer, const struct kernel_param *kp)
+{
+ int ret = 0;
+
+ switch (edac_report) {
+ case EDAC_REPORTING_ENABLED:
+ ret = sprintf(buffer, "on");
+ break;
+ case EDAC_REPORTING_DISABLED:
+ ret = sprintf(buffer, "off");
+ break;
+ case EDAC_REPORTING_FORCE:
+ ret = sprintf(buffer, "force");
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+ return ret;
+}
+
+static const struct kernel_param_ops edac_report_ops = {
+ .set = edac_report_set,
+ .get = edac_report_get,
+};
+
+module_param_cb(edac_report, &edac_report_ops, &edac_report, 0644);
+
unsigned edac_dimm_info_location(struct dimm_info *dimm, char *buf,
unsigned len)
{
EXPORT_SYMBOL_GPL(find_mci_by_dev);
/*
- * handler for EDAC to check if NMI type handler has asserted interrupt
- */
-static int edac_mc_assert_error_check_and_clear(void)
-{
- int old_state;
-
- if (edac_op_state == EDAC_OPSTATE_POLL)
- return 1;
-
- old_state = edac_err_assert;
- edac_err_assert = 0;
-
- return old_state;
-}
-
-/*
* edac_mc_workq_function
* performs the operation scheduled by a workq request
*/
return;
}
- if (edac_mc_assert_error_check_and_clear())
+ if (edac_op_state == EDAC_OPSTATE_POLL)
mci->edac_check(mci);
mutex_unlock(&mem_ctls_mutex);
}
list_add_tail_rcu(&mci->link, insert_before);
- atomic_inc(&edac_handlers);
return 0;
fail0:
static int del_mc_from_global_list(struct mem_ctl_info *mci)
{
- int handlers = atomic_dec_return(&edac_handlers);
list_del_rcu(&mci->link);
/* these are for safe removal of devices from global list while
synchronize_rcu();
INIT_LIST_HEAD(&mci->link);
- return handlers;
+ return list_empty(&mc_devices);
}
struct mem_ctl_info *edac_mc_find(int idx)
/* mark MCI offline: */
mci->op_state = OP_OFFLINE;
- if (!del_mc_from_global_list(mci))
+ if (del_mc_from_global_list(mci))
edac_mc_owner = NULL;
mutex_unlock(&mem_ctls_mutex);
/* Report the error via the trace interface */
grain_bits = fls_long(e->grain) + 1;
- trace_mc_event(type, e->msg, e->label, e->error_count,
- mci->mc_idx, e->top_layer, e->mid_layer, e->low_layer,
- (e->page_frame_number << PAGE_SHIFT) | e->offset_in_page,
- grain_bits, e->syndrome, e->other_detail);
+
+ if (IS_ENABLED(CONFIG_RAS))
+ trace_mc_event(type, e->msg, e->label, e->error_count,
+ mci->mc_idx, e->top_layer, e->mid_layer,
+ e->low_layer,
+ (e->page_frame_number << PAGE_SHIFT) | e->offset_in_page,
+ grain_bits, e->syndrome, e->other_detail);
edac_raw_mc_handle_error(type, mci, e);
}
+++ /dev/null
-/*
- * common EDAC components that must be in kernel
- *
- * Author: Dave Jiang <djiang@mvista.com>
- *
- * 2007 (c) MontaVista Software, Inc.
- * 2010 (c) Advanced Micro Devices Inc.
- * Borislav Petkov <bp@alien8.de>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- *
- */
-#include <linux/module.h>
-#include <linux/edac.h>
-#include <linux/atomic.h>
-#include <linux/device.h>
-
-int edac_op_state = EDAC_OPSTATE_INVAL;
-EXPORT_SYMBOL_GPL(edac_op_state);
-
-atomic_t edac_handlers = ATOMIC_INIT(0);
-EXPORT_SYMBOL_GPL(edac_handlers);
-
-int edac_err_assert = 0;
-EXPORT_SYMBOL_GPL(edac_err_assert);
-
-int edac_report_status = EDAC_REPORTING_ENABLED;
-EXPORT_SYMBOL_GPL(edac_report_status);
-
-static int __init edac_report_setup(char *str)
-{
- if (!str)
- return -EINVAL;
-
- if (!strncmp(str, "on", 2))
- set_edac_report_status(EDAC_REPORTING_ENABLED);
- else if (!strncmp(str, "off", 3))
- set_edac_report_status(EDAC_REPORTING_DISABLED);
- else if (!strncmp(str, "force", 5))
- set_edac_report_status(EDAC_REPORTING_FORCE);
-
- return 0;
-}
-__setup("edac_report=", edac_report_setup);
-
-/*
- * called to determine if there is an EDAC driver interested in
- * knowing an event (such as NMI) occurred
- */
-int edac_handler_set(void)
-{
- if (edac_op_state == EDAC_OPSTATE_POLL)
- return 0;
-
- return atomic_read(&edac_handlers);
-}
-EXPORT_SYMBOL_GPL(edac_handler_set);
-
-/*
- * handler for NMI type of interrupts to assert error
- */
-void edac_atomic_assert_error(void)
-{
- edac_err_assert++;
-}
-EXPORT_SYMBOL_GPL(edac_atomic_assert_error);
struct dram_addr daddr;
char *type;
- if (get_edac_report_status() == EDAC_REPORTING_DISABLED)
+ if (edac_get_report_status() == EDAC_REPORTING_DISABLED)
return NOTIFY_DONE;
mci = pnd2_mci;
struct sbridge_pvt *pvt;
char *type;
- if (get_edac_report_status() == EDAC_REPORTING_DISABLED)
+ if (edac_get_report_status() == EDAC_REPORTING_DISABLED)
return NOTIFY_DONE;
mci = get_mci_for_node_id(mce->socketid);
if (rc >= 0) {
mce_register_decode_chain(&sbridge_mce_dec);
- if (get_edac_report_status() == EDAC_REPORTING_DISABLED)
+ if (edac_get_report_status() == EDAC_REPORTING_DISABLED)
sbridge_printk(KERN_WARNING, "Loading driver, error reporting disabled.\n");
return 0;
}
struct mem_ctl_info *mci;
char *type;
- if (get_edac_report_status() == EDAC_REPORTING_DISABLED)
+ if (edac_get_report_status() == EDAC_REPORTING_DISABLED)
return NOTIFY_DONE;
/* ignore unless this is memory related with an address */
--- /dev/null
+/*
+ * Cavium ThunderX memory controller kernel module
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright Cavium, Inc. (C) 2015-2017. All rights reserved.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/edac.h>
+#include <linux/interrupt.h>
+#include <linux/string.h>
+#include <linux/stop_machine.h>
+#include <linux/delay.h>
+#include <linux/sizes.h>
+#include <linux/atomic.h>
+#include <linux/bitfield.h>
+#include <linux/circ_buf.h>
+
+#include <asm/page.h>
+
+#include "edac_module.h"
+
+#define phys_to_pfn(phys) (PFN_DOWN(phys))
+
+#define THUNDERX_NODE GENMASK(45, 44)
+
+enum {
+ ERR_CORRECTED = 1,
+ ERR_UNCORRECTED = 2,
+ ERR_UNKNOWN = 3,
+};
+
+#define MAX_SYNDROME_REGS 4
+
+struct error_syndrome {
+ u64 reg[MAX_SYNDROME_REGS];
+};
+
+struct error_descr {
+ int type;
+ u64 mask;
+ char *descr;
+};
+
+static void decode_register(char *str, size_t size,
+ const struct error_descr *descr,
+ const uint64_t reg)
+{
+ int ret = 0;
+
+ while (descr->type && descr->mask && descr->descr) {
+ if (reg & descr->mask) {
+ ret = snprintf(str, size, "\n\t%s, %s",
+ descr->type == ERR_CORRECTED ?
+ "Corrected" : "Uncorrected",
+ descr->descr);
+ str += ret;
+ size -= ret;
+ }
+ descr++;
+ }
+}
+
+static unsigned long get_bits(unsigned long data, int pos, int width)
+{
+ return (data >> pos) & ((1 << width) - 1);
+}
+
+#define L2C_CTL 0x87E080800000
+#define L2C_CTL_DISIDXALIAS BIT(0)
+
+#define PCI_DEVICE_ID_THUNDER_LMC 0xa022
+
+#define LMC_FADR 0x20
+#define LMC_FADR_FDIMM(x) ((x >> 37) & 0x1)
+#define LMC_FADR_FBUNK(x) ((x >> 36) & 0x1)
+#define LMC_FADR_FBANK(x) ((x >> 32) & 0xf)
+#define LMC_FADR_FROW(x) ((x >> 14) & 0xffff)
+#define LMC_FADR_FCOL(x) ((x >> 0) & 0x1fff)
+
+#define LMC_NXM_FADR 0x28
+#define LMC_ECC_SYND 0x38
+
+#define LMC_ECC_PARITY_TEST 0x108
+
+#define LMC_INT_W1S 0x150
+
+#define LMC_INT_ENA_W1C 0x158
+#define LMC_INT_ENA_W1S 0x160
+
+#define LMC_CONFIG 0x188
+
+#define LMC_CONFIG_BG2 BIT(62)
+#define LMC_CONFIG_RANK_ENA BIT(42)
+#define LMC_CONFIG_PBANK_LSB(x) (((x) >> 5) & 0xF)
+#define LMC_CONFIG_ROW_LSB(x) (((x) >> 2) & 0x7)
+
+#define LMC_CONTROL 0x190
+#define LMC_CONTROL_XOR_BANK BIT(16)
+
+#define LMC_INT 0x1F0
+
+#define LMC_INT_DDR_ERR BIT(11)
+#define LMC_INT_DED_ERR (0xFUL << 5)
+#define LMC_INT_SEC_ERR (0xFUL << 1)
+#define LMC_INT_NXM_WR_MASK BIT(0)
+
+#define LMC_DDR_PLL_CTL 0x258
+#define LMC_DDR_PLL_CTL_DDR4 BIT(29)
+
+#define LMC_FADR_SCRAMBLED 0x330
+
+#define LMC_INT_UE (LMC_INT_DDR_ERR | LMC_INT_DED_ERR | \
+ LMC_INT_NXM_WR_MASK)
+
+#define LMC_INT_CE (LMC_INT_SEC_ERR)
+
+static const struct error_descr lmc_errors[] = {
+ {
+ .type = ERR_CORRECTED,
+ .mask = LMC_INT_SEC_ERR,
+ .descr = "Single-bit ECC error",
+ },
+ {
+ .type = ERR_UNCORRECTED,
+ .mask = LMC_INT_DDR_ERR,
+ .descr = "DDR chip error",
+ },
+ {
+ .type = ERR_UNCORRECTED,
+ .mask = LMC_INT_DED_ERR,
+ .descr = "Double-bit ECC error",
+ },
+ {
+ .type = ERR_UNCORRECTED,
+ .mask = LMC_INT_NXM_WR_MASK,
+ .descr = "Non-existent memory write",
+ },
+ {0, 0, NULL},
+};
+
+#define LMC_INT_EN_DDR_ERROR_ALERT_ENA BIT(5)
+#define LMC_INT_EN_DLCRAM_DED_ERR BIT(4)
+#define LMC_INT_EN_DLCRAM_SEC_ERR BIT(3)
+#define LMC_INT_INTR_DED_ENA BIT(2)
+#define LMC_INT_INTR_SEC_ENA BIT(1)
+#define LMC_INT_INTR_NXM_WR_ENA BIT(0)
+
+#define LMC_INT_ENA_ALL GENMASK(5, 0)
+
+#define LMC_DDR_PLL_CTL 0x258
+#define LMC_DDR_PLL_CTL_DDR4 BIT(29)
+
+#define LMC_CONTROL 0x190
+#define LMC_CONTROL_RDIMM BIT(0)
+
+#define LMC_SCRAM_FADR 0x330
+
+#define LMC_CHAR_MASK0 0x228
+#define LMC_CHAR_MASK2 0x238
+
+#define RING_ENTRIES 8
+
+struct debugfs_entry {
+ const char *name;
+ umode_t mode;
+ const struct file_operations fops;
+};
+
+struct lmc_err_ctx {
+ u64 reg_int;
+ u64 reg_fadr;
+ u64 reg_nxm_fadr;
+ u64 reg_scram_fadr;
+ u64 reg_ecc_synd;
+};
+
+struct thunderx_lmc {
+ void __iomem *regs;
+ struct pci_dev *pdev;
+ struct msix_entry msix_ent;
+
+ atomic_t ecc_int;
+
+ u64 mask0;
+ u64 mask2;
+ u64 parity_test;
+ u64 node;
+
+ int xbits;
+ int bank_width;
+ int pbank_lsb;
+ int dimm_lsb;
+ int rank_lsb;
+ int bank_lsb;
+ int row_lsb;
+ int col_hi_lsb;
+
+ int xor_bank;
+ int l2c_alias;
+
+ struct page *mem;
+
+ struct lmc_err_ctx err_ctx[RING_ENTRIES];
+ unsigned long ring_head;
+ unsigned long ring_tail;
+};
+
+#define ring_pos(pos, size) ((pos) & (size - 1))
+
+#define DEBUGFS_STRUCT(_name, _mode, _write, _read) \
+static struct debugfs_entry debugfs_##_name = { \
+ .name = __stringify(_name), \
+ .mode = VERIFY_OCTAL_PERMISSIONS(_mode), \
+ .fops = { \
+ .open = simple_open, \
+ .write = _write, \
+ .read = _read, \
+ .llseek = generic_file_llseek, \
+ }, \
+}
+
+#define DEBUGFS_FIELD_ATTR(_type, _field) \
+static ssize_t thunderx_##_type##_##_field##_read(struct file *file, \
+ char __user *data, \
+ size_t count, loff_t *ppos) \
+{ \
+ struct thunderx_##_type *pdata = file->private_data; \
+ char buf[20]; \
+ \
+ snprintf(buf, count, "0x%016llx", pdata->_field); \
+ return simple_read_from_buffer(data, count, ppos, \
+ buf, sizeof(buf)); \
+} \
+ \
+static ssize_t thunderx_##_type##_##_field##_write(struct file *file, \
+ const char __user *data, \
+ size_t count, loff_t *ppos) \
+{ \
+ struct thunderx_##_type *pdata = file->private_data; \
+ int res; \
+ \
+ res = kstrtoull_from_user(data, count, 0, &pdata->_field); \
+ \
+ return res ? res : count; \
+} \
+ \
+DEBUGFS_STRUCT(_field, 0600, \
+ thunderx_##_type##_##_field##_write, \
+ thunderx_##_type##_##_field##_read) \
+
+#define DEBUGFS_REG_ATTR(_type, _name, _reg) \
+static ssize_t thunderx_##_type##_##_name##_read(struct file *file, \
+ char __user *data, \
+ size_t count, loff_t *ppos) \
+{ \
+ struct thunderx_##_type *pdata = file->private_data; \
+ char buf[20]; \
+ \
+ sprintf(buf, "0x%016llx", readq(pdata->regs + _reg)); \
+ return simple_read_from_buffer(data, count, ppos, \
+ buf, sizeof(buf)); \
+} \
+ \
+static ssize_t thunderx_##_type##_##_name##_write(struct file *file, \
+ const char __user *data, \
+ size_t count, loff_t *ppos) \
+{ \
+ struct thunderx_##_type *pdata = file->private_data; \
+ u64 val; \
+ int res; \
+ \
+ res = kstrtoull_from_user(data, count, 0, &val); \
+ \
+ if (!res) { \
+ writeq(val, pdata->regs + _reg); \
+ res = count; \
+ } \
+ \
+ return res; \
+} \
+ \
+DEBUGFS_STRUCT(_name, 0600, \
+ thunderx_##_type##_##_name##_write, \
+ thunderx_##_type##_##_name##_read)
+
+#define LMC_DEBUGFS_ENT(_field) DEBUGFS_FIELD_ATTR(lmc, _field)
+
+/*
+ * To get an ECC error injected, the following steps are needed:
+ * - Setup the ECC injection by writing the appropriate parameters:
+ * echo <bit mask value> > /sys/kernel/debug/<device number>/ecc_mask0
+ * echo <bit mask value> > /sys/kernel/debug/<device number>/ecc_mask2
+ * echo 0x802 > /sys/kernel/debug/<device number>/ecc_parity_test
+ * - Do the actual injection:
+ * echo 1 > /sys/kernel/debug/<device number>/inject_ecc
+ */
+static ssize_t thunderx_lmc_inject_int_write(struct file *file,
+ const char __user *data,
+ size_t count, loff_t *ppos)
+{
+ struct thunderx_lmc *lmc = file->private_data;
+ u64 val;
+ int res;
+
+ res = kstrtoull_from_user(data, count, 0, &val);
+
+ if (!res) {
+ /* Trigger the interrupt */
+ writeq(val, lmc->regs + LMC_INT_W1S);
+ res = count;
+ }
+
+ return res;
+}
+
+static ssize_t thunderx_lmc_int_read(struct file *file,
+ char __user *data,
+ size_t count, loff_t *ppos)
+{
+ struct thunderx_lmc *lmc = file->private_data;
+ char buf[20];
+ u64 lmc_int = readq(lmc->regs + LMC_INT);
+
+ snprintf(buf, sizeof(buf), "0x%016llx", lmc_int);
+ return simple_read_from_buffer(data, count, ppos, buf, sizeof(buf));
+}
+
+#define TEST_PATTERN 0xa5
+
+static int inject_ecc_fn(void *arg)
+{
+ struct thunderx_lmc *lmc = arg;
+ uintptr_t addr, phys;
+ unsigned int cline_size = cache_line_size();
+ const unsigned int lines = PAGE_SIZE / cline_size;
+ unsigned int i, cl_idx;
+
+ addr = (uintptr_t)page_address(lmc->mem);
+ phys = (uintptr_t)page_to_phys(lmc->mem);
+
+ cl_idx = (phys & 0x7f) >> 4;
+ lmc->parity_test &= ~(7ULL << 8);
+ lmc->parity_test |= (cl_idx << 8);
+
+ writeq(lmc->mask0, lmc->regs + LMC_CHAR_MASK0);
+ writeq(lmc->mask2, lmc->regs + LMC_CHAR_MASK2);
+ writeq(lmc->parity_test, lmc->regs + LMC_ECC_PARITY_TEST);
+
+ readq(lmc->regs + LMC_CHAR_MASK0);
+ readq(lmc->regs + LMC_CHAR_MASK2);
+ readq(lmc->regs + LMC_ECC_PARITY_TEST);
+
+ for (i = 0; i < lines; i++) {
+ memset((void *)addr, TEST_PATTERN, cline_size);
+ barrier();
+
+ /*
+ * Flush L1 cachelines to the PoC (L2).
+ * This will cause cacheline eviction to the L2.
+ */
+ asm volatile("dc civac, %0\n"
+ "dsb sy\n"
+ : : "r"(addr + i * cline_size));
+ }
+
+ for (i = 0; i < lines; i++) {
+ /*
+ * Flush L2 cachelines to the DRAM.
+ * This will cause cacheline eviction to the DRAM
+ * and ECC corruption according to the masks set.
+ */
+ __asm__ volatile("sys #0,c11,C1,#2, %0\n"
+ : : "r"(phys + i * cline_size));
+ }
+
+ for (i = 0; i < lines; i++) {
+ /*
+ * Invalidate L2 cachelines.
+ * The subsequent load will cause cacheline fetch
+ * from the DRAM and an error interrupt
+ */
+ __asm__ volatile("sys #0,c11,C1,#1, %0"
+ : : "r"(phys + i * cline_size));
+ }
+
+ for (i = 0; i < lines; i++) {
+ /*
+ * Invalidate L1 cachelines.
+ * The subsequent load will cause cacheline fetch
+ * from the L2 and/or DRAM
+ */
+ asm volatile("dc ivac, %0\n"
+ "dsb sy\n"
+ : : "r"(addr + i * cline_size));
+ }
+
+ return 0;
+}
+
+static ssize_t thunderx_lmc_inject_ecc_write(struct file *file,
+ const char __user *data,
+ size_t count, loff_t *ppos)
+{
+ struct thunderx_lmc *lmc = file->private_data;
+
+ unsigned int cline_size = cache_line_size();
+
+ u8 tmp[cline_size];
+ void __iomem *addr;
+ unsigned int offs, timeout = 100000;
+
+ atomic_set(&lmc->ecc_int, 0);
+
+ lmc->mem = alloc_pages_node(lmc->node, GFP_KERNEL, 0);
+
+ if (!lmc->mem)
+ return -ENOMEM;
+
+ addr = page_address(lmc->mem);
+
+ while (!atomic_read(&lmc->ecc_int) && timeout--) {
+ stop_machine(inject_ecc_fn, lmc, NULL);
+
+ for (offs = 0; offs < PAGE_SIZE; offs += sizeof(tmp)) {
+ /*
+ * Do a load from the previously rigged location
+ * This should generate an error interrupt.
+ */
+ memcpy(tmp, addr + offs, cline_size);
+ asm volatile("dsb ld\n");
+ }
+ }
+
+ __free_pages(lmc->mem, 0);
+
+ return count;
+}
+
+LMC_DEBUGFS_ENT(mask0);
+LMC_DEBUGFS_ENT(mask2);
+LMC_DEBUGFS_ENT(parity_test);
+
+DEBUGFS_STRUCT(inject_int, 0200, thunderx_lmc_inject_int_write, NULL);
+DEBUGFS_STRUCT(inject_ecc, 0200, thunderx_lmc_inject_ecc_write, NULL);
+DEBUGFS_STRUCT(int_w1c, 0400, NULL, thunderx_lmc_int_read);
+
+struct debugfs_entry *lmc_dfs_ents[] = {
+ &debugfs_mask0,
+ &debugfs_mask2,
+ &debugfs_parity_test,
+ &debugfs_inject_ecc,
+ &debugfs_inject_int,
+ &debugfs_int_w1c,
+};
+
+static int thunderx_create_debugfs_nodes(struct dentry *parent,
+ struct debugfs_entry *attrs[],
+ void *data,
+ size_t num)
+{
+ int i;
+ struct dentry *ent;
+
+ if (!IS_ENABLED(CONFIG_EDAC_DEBUG))
+ return 0;
+
+ if (!parent)
+ return -ENOENT;
+
+ for (i = 0; i < num; i++) {
+ ent = edac_debugfs_create_file(attrs[i]->name, attrs[i]->mode,
+ parent, data, &attrs[i]->fops);
+
+ if (!ent)
+ break;
+ }
+
+ return i;
+}
+
+static phys_addr_t thunderx_faddr_to_phys(u64 faddr, struct thunderx_lmc *lmc)
+{
+ phys_addr_t addr = 0;
+ int bank, xbits;
+
+ addr |= lmc->node << 40;
+ addr |= LMC_FADR_FDIMM(faddr) << lmc->dimm_lsb;
+ addr |= LMC_FADR_FBUNK(faddr) << lmc->rank_lsb;
+ addr |= LMC_FADR_FROW(faddr) << lmc->row_lsb;
+ addr |= (LMC_FADR_FCOL(faddr) >> 4) << lmc->col_hi_lsb;
+
+ bank = LMC_FADR_FBANK(faddr) << lmc->bank_lsb;
+
+ if (lmc->xor_bank)
+ bank ^= get_bits(addr, 12 + lmc->xbits, lmc->bank_width);
+
+ addr |= bank << lmc->bank_lsb;
+
+ xbits = PCI_FUNC(lmc->pdev->devfn);
+
+ if (lmc->l2c_alias)
+ xbits ^= get_bits(addr, 20, lmc->xbits) ^
+ get_bits(addr, 12, lmc->xbits);
+
+ addr |= xbits << 7;
+
+ return addr;
+}
+
+static unsigned int thunderx_get_num_lmcs(unsigned int node)
+{
+ unsigned int number = 0;
+ struct pci_dev *pdev = NULL;
+
+ do {
+ pdev = pci_get_device(PCI_VENDOR_ID_CAVIUM,
+ PCI_DEVICE_ID_THUNDER_LMC,
+ pdev);
+ if (pdev) {
+#ifdef CONFIG_NUMA
+ if (pdev->dev.numa_node == node)
+ number++;
+#else
+ number++;
+#endif
+ }
+ } while (pdev);
+
+ return number;
+}
+
+#define LMC_MESSAGE_SIZE 120
+#define LMC_OTHER_SIZE (50 * ARRAY_SIZE(lmc_errors))
+
+static irqreturn_t thunderx_lmc_err_isr(int irq, void *dev_id)
+{
+ struct mem_ctl_info *mci = dev_id;
+ struct thunderx_lmc *lmc = mci->pvt_info;
+
+ unsigned long head = ring_pos(lmc->ring_head, ARRAY_SIZE(lmc->err_ctx));
+ struct lmc_err_ctx *ctx = &lmc->err_ctx[head];
+
+ writeq(0, lmc->regs + LMC_CHAR_MASK0);
+ writeq(0, lmc->regs + LMC_CHAR_MASK2);
+ writeq(0x2, lmc->regs + LMC_ECC_PARITY_TEST);
+
+ ctx->reg_int = readq(lmc->regs + LMC_INT);
+ ctx->reg_fadr = readq(lmc->regs + LMC_FADR);
+ ctx->reg_nxm_fadr = readq(lmc->regs + LMC_NXM_FADR);
+ ctx->reg_scram_fadr = readq(lmc->regs + LMC_SCRAM_FADR);
+ ctx->reg_ecc_synd = readq(lmc->regs + LMC_ECC_SYND);
+
+ lmc->ring_head++;
+
+ atomic_set(&lmc->ecc_int, 1);
+
+ /* Clear the interrupt */
+ writeq(ctx->reg_int, lmc->regs + LMC_INT);
+
+ return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t thunderx_lmc_threaded_isr(int irq, void *dev_id)
+{
+ struct mem_ctl_info *mci = dev_id;
+ struct thunderx_lmc *lmc = mci->pvt_info;
+ phys_addr_t phys_addr;
+
+ unsigned long tail;
+ struct lmc_err_ctx *ctx;
+
+ irqreturn_t ret = IRQ_NONE;
+
+ char *msg;
+ char *other;
+
+ msg = kmalloc(LMC_MESSAGE_SIZE, GFP_KERNEL);
+ other = kmalloc(LMC_OTHER_SIZE, GFP_KERNEL);
+
+ if (!msg || !other)
+ goto err_free;
+
+ while (CIRC_CNT(lmc->ring_head, lmc->ring_tail,
+ ARRAY_SIZE(lmc->err_ctx))) {
+ tail = ring_pos(lmc->ring_tail, ARRAY_SIZE(lmc->err_ctx));
+
+ ctx = &lmc->err_ctx[tail];
+
+ dev_dbg(&lmc->pdev->dev, "LMC_INT: %016llx\n",
+ ctx->reg_int);
+ dev_dbg(&lmc->pdev->dev, "LMC_FADR: %016llx\n",
+ ctx->reg_fadr);
+ dev_dbg(&lmc->pdev->dev, "LMC_NXM_FADR: %016llx\n",
+ ctx->reg_nxm_fadr);
+ dev_dbg(&lmc->pdev->dev, "LMC_SCRAM_FADR: %016llx\n",
+ ctx->reg_scram_fadr);
+ dev_dbg(&lmc->pdev->dev, "LMC_ECC_SYND: %016llx\n",
+ ctx->reg_ecc_synd);
+
+ snprintf(msg, LMC_MESSAGE_SIZE,
+ "DIMM %lld rank %lld bank %lld row %lld col %lld",
+ LMC_FADR_FDIMM(ctx->reg_scram_fadr),
+ LMC_FADR_FBUNK(ctx->reg_scram_fadr),
+ LMC_FADR_FBANK(ctx->reg_scram_fadr),
+ LMC_FADR_FROW(ctx->reg_scram_fadr),
+ LMC_FADR_FCOL(ctx->reg_scram_fadr));
+
+ decode_register(other, LMC_OTHER_SIZE, lmc_errors,
+ ctx->reg_int);
+
+ phys_addr = thunderx_faddr_to_phys(ctx->reg_fadr, lmc);
+
+ if (ctx->reg_int & LMC_INT_UE)
+ edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1,
+ phys_to_pfn(phys_addr),
+ offset_in_page(phys_addr),
+ 0, -1, -1, -1, msg, other);
+ else if (ctx->reg_int & LMC_INT_CE)
+ edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1,
+ phys_to_pfn(phys_addr),
+ offset_in_page(phys_addr),
+ 0, -1, -1, -1, msg, other);
+
+ lmc->ring_tail++;
+ }
+
+ ret = IRQ_HANDLED;
+
+err_free:
+ kfree(msg);
+ kfree(other);
+
+ return ret;
+}
+
+#ifdef CONFIG_PM
+static int thunderx_lmc_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+ pci_save_state(pdev);
+ pci_disable_device(pdev);
+
+ pci_set_power_state(pdev, pci_choose_state(pdev, state));
+
+ return 0;
+}
+
+static int thunderx_lmc_resume(struct pci_dev *pdev)
+{
+ pci_set_power_state(pdev, PCI_D0);
+ pci_enable_wake(pdev, PCI_D0, 0);
+ pci_restore_state(pdev);
+
+ return 0;
+}
+#endif
+
+static const struct pci_device_id thunderx_lmc_pci_tbl[] = {
+ { PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVICE_ID_THUNDER_LMC) },
+ { 0, },
+};
+
+static inline int pci_dev_to_mc_idx(struct pci_dev *pdev)
+{
+ int node = dev_to_node(&pdev->dev);
+ int ret = PCI_FUNC(pdev->devfn);
+
+ ret += max(node, 0) << 3;
+
+ return ret;
+}
+
+static int thunderx_lmc_probe(struct pci_dev *pdev,
+ const struct pci_device_id *id)
+{
+ struct thunderx_lmc *lmc;
+ struct edac_mc_layer layer;
+ struct mem_ctl_info *mci;
+ u64 lmc_control, lmc_ddr_pll_ctl, lmc_config;
+ int ret;
+ u64 lmc_int;
+ void *l2c_ioaddr;
+
+ layer.type = EDAC_MC_LAYER_SLOT;
+ layer.size = 2;
+ layer.is_virt_csrow = false;
+
+ ret = pcim_enable_device(pdev);
+ if (ret) {
+ dev_err(&pdev->dev, "Cannot enable PCI device: %d\n", ret);
+ return ret;
+ }
+
+ ret = pcim_iomap_regions(pdev, BIT(0), "thunderx_lmc");
+ if (ret) {
+ dev_err(&pdev->dev, "Cannot map PCI resources: %d\n", ret);
+ return ret;
+ }
+
+ mci = edac_mc_alloc(pci_dev_to_mc_idx(pdev), 1, &layer,
+ sizeof(struct thunderx_lmc));
+ if (!mci)
+ return -ENOMEM;
+
+ mci->pdev = &pdev->dev;
+ lmc = mci->pvt_info;
+
+ pci_set_drvdata(pdev, mci);
+
+ lmc->regs = pcim_iomap_table(pdev)[0];
+
+ lmc_control = readq(lmc->regs + LMC_CONTROL);
+ lmc_ddr_pll_ctl = readq(lmc->regs + LMC_DDR_PLL_CTL);
+ lmc_config = readq(lmc->regs + LMC_CONFIG);
+
+ if (lmc_control & LMC_CONTROL_RDIMM) {
+ mci->mtype_cap = FIELD_GET(LMC_DDR_PLL_CTL_DDR4,
+ lmc_ddr_pll_ctl) ?
+ MEM_RDDR4 : MEM_RDDR3;
+ } else {
+ mci->mtype_cap = FIELD_GET(LMC_DDR_PLL_CTL_DDR4,
+ lmc_ddr_pll_ctl) ?
+ MEM_DDR4 : MEM_DDR3;
+ }
+
+ mci->edac_ctl_cap = EDAC_FLAG_NONE | EDAC_FLAG_SECDED;
+ mci->edac_cap = EDAC_FLAG_SECDED;
+
+ mci->mod_name = "thunderx-lmc";
+ mci->mod_ver = "1";
+ mci->ctl_name = "thunderx-lmc";
+ mci->dev_name = dev_name(&pdev->dev);
+ mci->scrub_mode = SCRUB_NONE;
+
+ lmc->pdev = pdev;
+ lmc->msix_ent.entry = 0;
+
+ lmc->ring_head = 0;
+ lmc->ring_tail = 0;
+
+ ret = pci_enable_msix_exact(pdev, &lmc->msix_ent, 1);
+ if (ret) {
+ dev_err(&pdev->dev, "Cannot enable interrupt: %d\n", ret);
+ goto err_free;
+ }
+
+ ret = devm_request_threaded_irq(&pdev->dev, lmc->msix_ent.vector,
+ thunderx_lmc_err_isr,
+ thunderx_lmc_threaded_isr, 0,
+ "[EDAC] ThunderX LMC", mci);
+ if (ret) {
+ dev_err(&pdev->dev, "Cannot set ISR: %d\n", ret);
+ goto err_free;
+ }
+
+ lmc->node = FIELD_GET(THUNDERX_NODE, pci_resource_start(pdev, 0));
+
+ lmc->xbits = thunderx_get_num_lmcs(lmc->node) >> 1;
+ lmc->bank_width = (FIELD_GET(LMC_DDR_PLL_CTL_DDR4, lmc_ddr_pll_ctl) &&
+ FIELD_GET(LMC_CONFIG_BG2, lmc_config)) ? 4 : 3;
+
+ lmc->pbank_lsb = (lmc_config >> 5) & 0xf;
+ lmc->dimm_lsb = 28 + lmc->pbank_lsb + lmc->xbits;
+ lmc->rank_lsb = lmc->dimm_lsb;
+ lmc->rank_lsb -= FIELD_GET(LMC_CONFIG_RANK_ENA, lmc_config) ? 1 : 0;
+ lmc->bank_lsb = 7 + lmc->xbits;
+ lmc->row_lsb = 14 + LMC_CONFIG_ROW_LSB(lmc_config) + lmc->xbits;
+
+ lmc->col_hi_lsb = lmc->bank_lsb + lmc->bank_width;
+
+ lmc->xor_bank = lmc_control & LMC_CONTROL_XOR_BANK;
+
+ l2c_ioaddr = ioremap(L2C_CTL | FIELD_PREP(THUNDERX_NODE, lmc->node),
+ PAGE_SIZE);
+
+ if (!l2c_ioaddr) {
+ dev_err(&pdev->dev, "Cannot map L2C_CTL\n");
+ goto err_free;
+ }
+
+ lmc->l2c_alias = !(readq(l2c_ioaddr) & L2C_CTL_DISIDXALIAS);
+
+ iounmap(l2c_ioaddr);
+
+ ret = edac_mc_add_mc(mci);
+ if (ret) {
+ dev_err(&pdev->dev, "Cannot add the MC: %d\n", ret);
+ goto err_free;
+ }
+
+ lmc_int = readq(lmc->regs + LMC_INT);
+ writeq(lmc_int, lmc->regs + LMC_INT);
+
+ writeq(LMC_INT_ENA_ALL, lmc->regs + LMC_INT_ENA_W1S);
+
+ if (IS_ENABLED(CONFIG_EDAC_DEBUG)) {
+ ret = thunderx_create_debugfs_nodes(mci->debugfs,
+ lmc_dfs_ents,
+ lmc,
+ ARRAY_SIZE(lmc_dfs_ents));
+
+ if (ret != ARRAY_SIZE(lmc_dfs_ents)) {
+ dev_warn(&pdev->dev, "Error creating debugfs entries: %d%s\n",
+ ret, ret >= 0 ? " created" : "");
+ }
+ }
+
+ return 0;
+
+err_free:
+ pci_set_drvdata(pdev, NULL);
+ edac_mc_free(mci);
+
+ return ret;
+}
+
+static void thunderx_lmc_remove(struct pci_dev *pdev)
+{
+ struct mem_ctl_info *mci = pci_get_drvdata(pdev);
+ struct thunderx_lmc *lmc = mci->pvt_info;
+
+ writeq(LMC_INT_ENA_ALL, lmc->regs + LMC_INT_ENA_W1C);
+
+ edac_mc_del_mc(&pdev->dev);
+ edac_mc_free(mci);
+}
+
+MODULE_DEVICE_TABLE(pci, thunderx_lmc_pci_tbl);
+
+static struct pci_driver thunderx_lmc_driver = {
+ .name = "thunderx_lmc_edac",
+ .probe = thunderx_lmc_probe,
+ .remove = thunderx_lmc_remove,
+#ifdef CONFIG_PM
+ .suspend = thunderx_lmc_suspend,
+ .resume = thunderx_lmc_resume,
+#endif
+ .id_table = thunderx_lmc_pci_tbl,
+};
+
+/*---------------------- OCX driver ---------------------------------*/
+
+#define PCI_DEVICE_ID_THUNDER_OCX 0xa013
+
+#define OCX_LINK_INTS 3
+#define OCX_INTS (OCX_LINK_INTS + 1)
+#define OCX_RX_LANES 24
+#define OCX_RX_LANE_STATS 15
+
+#define OCX_COM_INT 0x100
+#define OCX_COM_INT_W1S 0x108
+#define OCX_COM_INT_ENA_W1S 0x110
+#define OCX_COM_INT_ENA_W1C 0x118
+
+#define OCX_COM_IO_BADID BIT(54)
+#define OCX_COM_MEM_BADID BIT(53)
+#define OCX_COM_COPR_BADID BIT(52)
+#define OCX_COM_WIN_REQ_BADID BIT(51)
+#define OCX_COM_WIN_REQ_TOUT BIT(50)
+#define OCX_COM_RX_LANE GENMASK(23, 0)
+
+#define OCX_COM_INT_CE (OCX_COM_IO_BADID | \
+ OCX_COM_MEM_BADID | \
+ OCX_COM_COPR_BADID | \
+ OCX_COM_WIN_REQ_BADID | \
+ OCX_COM_WIN_REQ_TOUT)
+
+static const struct error_descr ocx_com_errors[] = {
+ {
+ .type = ERR_CORRECTED,
+ .mask = OCX_COM_IO_BADID,
+ .descr = "Invalid IO transaction node ID",
+ },
+ {
+ .type = ERR_CORRECTED,
+ .mask = OCX_COM_MEM_BADID,
+ .descr = "Invalid memory transaction node ID",
+ },
+ {
+ .type = ERR_CORRECTED,
+ .mask = OCX_COM_COPR_BADID,
+ .descr = "Invalid coprocessor transaction node ID",
+ },
+ {
+ .type = ERR_CORRECTED,
+ .mask = OCX_COM_WIN_REQ_BADID,
+ .descr = "Invalid SLI transaction node ID",
+ },
+ {
+ .type = ERR_CORRECTED,
+ .mask = OCX_COM_WIN_REQ_TOUT,
+ .descr = "Window/core request timeout",
+ },
+ {0, 0, NULL},
+};
+
+#define OCX_COM_LINKX_INT(x) (0x120 + (x) * 8)
+#define OCX_COM_LINKX_INT_W1S(x) (0x140 + (x) * 8)
+#define OCX_COM_LINKX_INT_ENA_W1S(x) (0x160 + (x) * 8)
+#define OCX_COM_LINKX_INT_ENA_W1C(x) (0x180 + (x) * 8)
+
+#define OCX_COM_LINK_BAD_WORD BIT(13)
+#define OCX_COM_LINK_ALIGN_FAIL BIT(12)
+#define OCX_COM_LINK_ALIGN_DONE BIT(11)
+#define OCX_COM_LINK_UP BIT(10)
+#define OCX_COM_LINK_STOP BIT(9)
+#define OCX_COM_LINK_BLK_ERR BIT(8)
+#define OCX_COM_LINK_REINIT BIT(7)
+#define OCX_COM_LINK_LNK_DATA BIT(6)
+#define OCX_COM_LINK_RXFIFO_DBE BIT(5)
+#define OCX_COM_LINK_RXFIFO_SBE BIT(4)
+#define OCX_COM_LINK_TXFIFO_DBE BIT(3)
+#define OCX_COM_LINK_TXFIFO_SBE BIT(2)
+#define OCX_COM_LINK_REPLAY_DBE BIT(1)
+#define OCX_COM_LINK_REPLAY_SBE BIT(0)
+
+static const struct error_descr ocx_com_link_errors[] = {
+ {
+ .type = ERR_CORRECTED,
+ .mask = OCX_COM_LINK_REPLAY_SBE,
+ .descr = "Replay buffer single-bit error",
+ },
+ {
+ .type = ERR_CORRECTED,
+ .mask = OCX_COM_LINK_TXFIFO_SBE,
+ .descr = "TX FIFO single-bit error",
+ },
+ {
+ .type = ERR_CORRECTED,
+ .mask = OCX_COM_LINK_RXFIFO_SBE,
+ .descr = "RX FIFO single-bit error",
+ },
+ {
+ .type = ERR_CORRECTED,
+ .mask = OCX_COM_LINK_BLK_ERR,
+ .descr = "Block code error",
+ },
+ {
+ .type = ERR_CORRECTED,
+ .mask = OCX_COM_LINK_ALIGN_FAIL,
+ .descr = "Link alignment failure",
+ },
+ {
+ .type = ERR_CORRECTED,
+ .mask = OCX_COM_LINK_BAD_WORD,
+ .descr = "Bad code word",
+ },
+ {
+ .type = ERR_UNCORRECTED,
+ .mask = OCX_COM_LINK_REPLAY_DBE,
+ .descr = "Replay buffer double-bit error",
+ },
+ {
+ .type = ERR_UNCORRECTED,
+ .mask = OCX_COM_LINK_TXFIFO_DBE,
+ .descr = "TX FIFO double-bit error",
+ },
+ {
+ .type = ERR_UNCORRECTED,
+ .mask = OCX_COM_LINK_RXFIFO_DBE,
+ .descr = "RX FIFO double-bit error",
+ },
+ {
+ .type = ERR_UNCORRECTED,
+ .mask = OCX_COM_LINK_STOP,
+ .descr = "Link stopped",
+ },
+ {0, 0, NULL},
+};
+
+#define OCX_COM_LINK_INT_UE (OCX_COM_LINK_REPLAY_DBE | \
+ OCX_COM_LINK_TXFIFO_DBE | \
+ OCX_COM_LINK_RXFIFO_DBE | \
+ OCX_COM_LINK_STOP)
+
+#define OCX_COM_LINK_INT_CE (OCX_COM_LINK_REPLAY_SBE | \
+ OCX_COM_LINK_TXFIFO_SBE | \
+ OCX_COM_LINK_RXFIFO_SBE | \
+ OCX_COM_LINK_BLK_ERR | \
+ OCX_COM_LINK_ALIGN_FAIL | \
+ OCX_COM_LINK_BAD_WORD)
+
+#define OCX_LNE_INT(x) (0x8018 + (x) * 0x100)
+#define OCX_LNE_INT_EN(x) (0x8020 + (x) * 0x100)
+#define OCX_LNE_BAD_CNT(x) (0x8028 + (x) * 0x100)
+#define OCX_LNE_CFG(x) (0x8000 + (x) * 0x100)
+#define OCX_LNE_STAT(x, y) (0x8040 + (x) * 0x100 + (y) * 8)
+
+#define OCX_LNE_CFG_RX_BDRY_LOCK_DIS BIT(8)
+#define OCX_LNE_CFG_RX_STAT_WRAP_DIS BIT(2)
+#define OCX_LNE_CFG_RX_STAT_RDCLR BIT(1)
+#define OCX_LNE_CFG_RX_STAT_ENA BIT(0)
+
+
+#define OCX_LANE_BAD_64B67B BIT(8)
+#define OCX_LANE_DSKEW_FIFO_OVFL BIT(5)
+#define OCX_LANE_SCRM_SYNC_LOSS BIT(4)
+#define OCX_LANE_UKWN_CNTL_WORD BIT(3)
+#define OCX_LANE_CRC32_ERR BIT(2)
+#define OCX_LANE_BDRY_SYNC_LOSS BIT(1)
+#define OCX_LANE_SERDES_LOCK_LOSS BIT(0)
+
+#define OCX_COM_LANE_INT_UE (0)
+#define OCX_COM_LANE_INT_CE (OCX_LANE_SERDES_LOCK_LOSS | \
+ OCX_LANE_BDRY_SYNC_LOSS | \
+ OCX_LANE_CRC32_ERR | \
+ OCX_LANE_UKWN_CNTL_WORD | \
+ OCX_LANE_SCRM_SYNC_LOSS | \
+ OCX_LANE_DSKEW_FIFO_OVFL | \
+ OCX_LANE_BAD_64B67B)
+
+static const struct error_descr ocx_lane_errors[] = {
+ {
+ .type = ERR_CORRECTED,
+ .mask = OCX_LANE_SERDES_LOCK_LOSS,
+ .descr = "RX SerDes lock lost",
+ },
+ {
+ .type = ERR_CORRECTED,
+ .mask = OCX_LANE_BDRY_SYNC_LOSS,
+ .descr = "RX word boundary lost",
+ },
+ {
+ .type = ERR_CORRECTED,
+ .mask = OCX_LANE_CRC32_ERR,
+ .descr = "CRC32 error",
+ },
+ {
+ .type = ERR_CORRECTED,
+ .mask = OCX_LANE_UKWN_CNTL_WORD,
+ .descr = "Unknown control word",
+ },
+ {
+ .type = ERR_CORRECTED,
+ .mask = OCX_LANE_SCRM_SYNC_LOSS,
+ .descr = "Scrambler synchronization lost",
+ },
+ {
+ .type = ERR_CORRECTED,
+ .mask = OCX_LANE_DSKEW_FIFO_OVFL,
+ .descr = "RX deskew FIFO overflow",
+ },
+ {
+ .type = ERR_CORRECTED,
+ .mask = OCX_LANE_BAD_64B67B,
+ .descr = "Bad 64B/67B codeword",
+ },
+ {0, 0, NULL},
+};
+
+#define OCX_LNE_INT_ENA_ALL (GENMASK(9, 8) | GENMASK(6, 0))
+#define OCX_COM_INT_ENA_ALL (GENMASK(54, 50) | GENMASK(23, 0))
+#define OCX_COM_LINKX_INT_ENA_ALL (GENMASK(13, 12) | \
+ GENMASK(9, 7) | GENMASK(5, 0))
+
+#define OCX_TLKX_ECC_CTL(x) (0x10018 + (x) * 0x2000)
+#define OCX_RLKX_ECC_CTL(x) (0x18018 + (x) * 0x2000)
+
+struct ocx_com_err_ctx {
+ u64 reg_com_int;
+ u64 reg_lane_int[OCX_RX_LANES];
+ u64 reg_lane_stat11[OCX_RX_LANES];
+};
+
+struct ocx_link_err_ctx {
+ u64 reg_com_link_int;
+ int link;
+};
+
+struct thunderx_ocx {
+ void __iomem *regs;
+ int com_link;
+ struct pci_dev *pdev;
+ struct edac_device_ctl_info *edac_dev;
+
+ struct dentry *debugfs;
+ struct msix_entry msix_ent[OCX_INTS];
+
+ struct ocx_com_err_ctx com_err_ctx[RING_ENTRIES];
+ struct ocx_link_err_ctx link_err_ctx[RING_ENTRIES];
+
+ unsigned long com_ring_head;
+ unsigned long com_ring_tail;
+
+ unsigned long link_ring_head;
+ unsigned long link_ring_tail;
+};
+
+#define OCX_MESSAGE_SIZE SZ_1K
+#define OCX_OTHER_SIZE (50 * ARRAY_SIZE(ocx_com_link_errors))
+
+/* This handler is threaded */
+static irqreturn_t thunderx_ocx_com_isr(int irq, void *irq_id)
+{
+ struct msix_entry *msix = irq_id;
+ struct thunderx_ocx *ocx = container_of(msix, struct thunderx_ocx,
+ msix_ent[msix->entry]);
+
+ int lane;
+ unsigned long head = ring_pos(ocx->com_ring_head,
+ ARRAY_SIZE(ocx->com_err_ctx));
+ struct ocx_com_err_ctx *ctx = &ocx->com_err_ctx[head];
+
+ ctx->reg_com_int = readq(ocx->regs + OCX_COM_INT);
+
+ for (lane = 0; lane < OCX_RX_LANES; lane++) {
+ ctx->reg_lane_int[lane] =
+ readq(ocx->regs + OCX_LNE_INT(lane));
+ ctx->reg_lane_stat11[lane] =
+ readq(ocx->regs + OCX_LNE_STAT(lane, 11));
+
+ writeq(ctx->reg_lane_int[lane], ocx->regs + OCX_LNE_INT(lane));
+ }
+
+ writeq(ctx->reg_com_int, ocx->regs + OCX_COM_INT);
+
+ ocx->com_ring_head++;
+
+ return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t thunderx_ocx_com_threaded_isr(int irq, void *irq_id)
+{
+ struct msix_entry *msix = irq_id;
+ struct thunderx_ocx *ocx = container_of(msix, struct thunderx_ocx,
+ msix_ent[msix->entry]);
+
+ irqreturn_t ret = IRQ_NONE;
+
+ unsigned long tail;
+ struct ocx_com_err_ctx *ctx;
+ int lane;
+ char *msg;
+ char *other;
+
+ msg = kmalloc(OCX_MESSAGE_SIZE, GFP_KERNEL);
+ other = kmalloc(OCX_OTHER_SIZE, GFP_KERNEL);
+
+ if (!msg || !other)
+ goto err_free;
+
+ while (CIRC_CNT(ocx->com_ring_head, ocx->com_ring_tail,
+ ARRAY_SIZE(ocx->com_err_ctx))) {
+ tail = ring_pos(ocx->com_ring_tail,
+ ARRAY_SIZE(ocx->com_err_ctx));
+ ctx = &ocx->com_err_ctx[tail];
+
+ snprintf(msg, OCX_MESSAGE_SIZE, "%s: OCX_COM_INT: %016llx",
+ ocx->edac_dev->ctl_name, ctx->reg_com_int);
+
+ decode_register(other, OCX_OTHER_SIZE,
+ ocx_com_errors, ctx->reg_com_int);
+
+ strncat(msg, other, OCX_MESSAGE_SIZE);
+
+ for (lane = 0; lane < OCX_RX_LANES; lane++)
+ if (ctx->reg_com_int & BIT(lane)) {
+ snprintf(other, OCX_OTHER_SIZE,
+ "\n\tOCX_LNE_INT[%02d]: %016llx OCX_LNE_STAT11[%02d]: %016llx",
+ lane, ctx->reg_lane_int[lane],
+ lane, ctx->reg_lane_stat11[lane]);
+
+ strncat(msg, other, OCX_MESSAGE_SIZE);
+
+ decode_register(other, OCX_OTHER_SIZE,
+ ocx_lane_errors,
+ ctx->reg_lane_int[lane]);
+ strncat(msg, other, OCX_MESSAGE_SIZE);
+ }
+
+ if (ctx->reg_com_int & OCX_COM_INT_CE)
+ edac_device_handle_ce(ocx->edac_dev, 0, 0, msg);
+
+ ocx->com_ring_tail++;
+ }
+
+ ret = IRQ_HANDLED;
+
+err_free:
+ kfree(other);
+ kfree(msg);
+
+ return ret;
+}
+
+static irqreturn_t thunderx_ocx_lnk_isr(int irq, void *irq_id)
+{
+ struct msix_entry *msix = irq_id;
+ struct thunderx_ocx *ocx = container_of(msix, struct thunderx_ocx,
+ msix_ent[msix->entry]);
+ unsigned long head = ring_pos(ocx->link_ring_head,
+ ARRAY_SIZE(ocx->link_err_ctx));
+ struct ocx_link_err_ctx *ctx = &ocx->link_err_ctx[head];
+
+ ctx->link = msix->entry;
+ ctx->reg_com_link_int = readq(ocx->regs + OCX_COM_LINKX_INT(ctx->link));
+
+ writeq(ctx->reg_com_link_int, ocx->regs + OCX_COM_LINKX_INT(ctx->link));
+
+ ocx->link_ring_head++;
+
+ return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t thunderx_ocx_lnk_threaded_isr(int irq, void *irq_id)
+{
+ struct msix_entry *msix = irq_id;
+ struct thunderx_ocx *ocx = container_of(msix, struct thunderx_ocx,
+ msix_ent[msix->entry]);
+ irqreturn_t ret = IRQ_NONE;
+ unsigned long tail;
+ struct ocx_link_err_ctx *ctx;
+
+ char *msg;
+ char *other;
+
+ msg = kmalloc(OCX_MESSAGE_SIZE, GFP_KERNEL);
+ other = kmalloc(OCX_OTHER_SIZE, GFP_KERNEL);
+
+ if (!msg || !other)
+ goto err_free;
+
+ while (CIRC_CNT(ocx->link_ring_head, ocx->link_ring_tail,
+ ARRAY_SIZE(ocx->link_err_ctx))) {
+ tail = ring_pos(ocx->link_ring_head,
+ ARRAY_SIZE(ocx->link_err_ctx));
+
+ ctx = &ocx->link_err_ctx[tail];
+
+ snprintf(msg, OCX_MESSAGE_SIZE,
+ "%s: OCX_COM_LINK_INT[%d]: %016llx",
+ ocx->edac_dev->ctl_name,
+ ctx->link, ctx->reg_com_link_int);
+
+ decode_register(other, OCX_OTHER_SIZE,
+ ocx_com_link_errors, ctx->reg_com_link_int);
+
+ strncat(msg, other, OCX_MESSAGE_SIZE);
+
+ if (ctx->reg_com_link_int & OCX_COM_LINK_INT_UE)
+ edac_device_handle_ue(ocx->edac_dev, 0, 0, msg);
+ else if (ctx->reg_com_link_int & OCX_COM_LINK_INT_CE)
+ edac_device_handle_ce(ocx->edac_dev, 0, 0, msg);
+
+ ocx->link_ring_tail++;
+ }
+
+ ret = IRQ_HANDLED;
+err_free:
+ kfree(other);
+ kfree(msg);
+
+ return ret;
+}
+
+#define OCX_DEBUGFS_ATTR(_name, _reg) DEBUGFS_REG_ATTR(ocx, _name, _reg)
+
+OCX_DEBUGFS_ATTR(tlk0_ecc_ctl, OCX_TLKX_ECC_CTL(0));
+OCX_DEBUGFS_ATTR(tlk1_ecc_ctl, OCX_TLKX_ECC_CTL(1));
+OCX_DEBUGFS_ATTR(tlk2_ecc_ctl, OCX_TLKX_ECC_CTL(2));
+
+OCX_DEBUGFS_ATTR(rlk0_ecc_ctl, OCX_RLKX_ECC_CTL(0));
+OCX_DEBUGFS_ATTR(rlk1_ecc_ctl, OCX_RLKX_ECC_CTL(1));
+OCX_DEBUGFS_ATTR(rlk2_ecc_ctl, OCX_RLKX_ECC_CTL(2));
+
+OCX_DEBUGFS_ATTR(com_link0_int, OCX_COM_LINKX_INT_W1S(0));
+OCX_DEBUGFS_ATTR(com_link1_int, OCX_COM_LINKX_INT_W1S(1));
+OCX_DEBUGFS_ATTR(com_link2_int, OCX_COM_LINKX_INT_W1S(2));
+
+OCX_DEBUGFS_ATTR(lne00_badcnt, OCX_LNE_BAD_CNT(0));
+OCX_DEBUGFS_ATTR(lne01_badcnt, OCX_LNE_BAD_CNT(1));
+OCX_DEBUGFS_ATTR(lne02_badcnt, OCX_LNE_BAD_CNT(2));
+OCX_DEBUGFS_ATTR(lne03_badcnt, OCX_LNE_BAD_CNT(3));
+OCX_DEBUGFS_ATTR(lne04_badcnt, OCX_LNE_BAD_CNT(4));
+OCX_DEBUGFS_ATTR(lne05_badcnt, OCX_LNE_BAD_CNT(5));
+OCX_DEBUGFS_ATTR(lne06_badcnt, OCX_LNE_BAD_CNT(6));
+OCX_DEBUGFS_ATTR(lne07_badcnt, OCX_LNE_BAD_CNT(7));
+
+OCX_DEBUGFS_ATTR(lne08_badcnt, OCX_LNE_BAD_CNT(8));
+OCX_DEBUGFS_ATTR(lne09_badcnt, OCX_LNE_BAD_CNT(9));
+OCX_DEBUGFS_ATTR(lne10_badcnt, OCX_LNE_BAD_CNT(10));
+OCX_DEBUGFS_ATTR(lne11_badcnt, OCX_LNE_BAD_CNT(11));
+OCX_DEBUGFS_ATTR(lne12_badcnt, OCX_LNE_BAD_CNT(12));
+OCX_DEBUGFS_ATTR(lne13_badcnt, OCX_LNE_BAD_CNT(13));
+OCX_DEBUGFS_ATTR(lne14_badcnt, OCX_LNE_BAD_CNT(14));
+OCX_DEBUGFS_ATTR(lne15_badcnt, OCX_LNE_BAD_CNT(15));
+
+OCX_DEBUGFS_ATTR(lne16_badcnt, OCX_LNE_BAD_CNT(16));
+OCX_DEBUGFS_ATTR(lne17_badcnt, OCX_LNE_BAD_CNT(17));
+OCX_DEBUGFS_ATTR(lne18_badcnt, OCX_LNE_BAD_CNT(18));
+OCX_DEBUGFS_ATTR(lne19_badcnt, OCX_LNE_BAD_CNT(19));
+OCX_DEBUGFS_ATTR(lne20_badcnt, OCX_LNE_BAD_CNT(20));
+OCX_DEBUGFS_ATTR(lne21_badcnt, OCX_LNE_BAD_CNT(21));
+OCX_DEBUGFS_ATTR(lne22_badcnt, OCX_LNE_BAD_CNT(22));
+OCX_DEBUGFS_ATTR(lne23_badcnt, OCX_LNE_BAD_CNT(23));
+
+OCX_DEBUGFS_ATTR(com_int, OCX_COM_INT_W1S);
+
+struct debugfs_entry *ocx_dfs_ents[] = {
+ &debugfs_tlk0_ecc_ctl,
+ &debugfs_tlk1_ecc_ctl,
+ &debugfs_tlk2_ecc_ctl,
+
+ &debugfs_rlk0_ecc_ctl,
+ &debugfs_rlk1_ecc_ctl,
+ &debugfs_rlk2_ecc_ctl,
+
+ &debugfs_com_link0_int,
+ &debugfs_com_link1_int,
+ &debugfs_com_link2_int,
+
+ &debugfs_lne00_badcnt,
+ &debugfs_lne01_badcnt,
+ &debugfs_lne02_badcnt,
+ &debugfs_lne03_badcnt,
+ &debugfs_lne04_badcnt,
+ &debugfs_lne05_badcnt,
+ &debugfs_lne06_badcnt,
+ &debugfs_lne07_badcnt,
+ &debugfs_lne08_badcnt,
+ &debugfs_lne09_badcnt,
+ &debugfs_lne10_badcnt,
+ &debugfs_lne11_badcnt,
+ &debugfs_lne12_badcnt,
+ &debugfs_lne13_badcnt,
+ &debugfs_lne14_badcnt,
+ &debugfs_lne15_badcnt,
+ &debugfs_lne16_badcnt,
+ &debugfs_lne17_badcnt,
+ &debugfs_lne18_badcnt,
+ &debugfs_lne19_badcnt,
+ &debugfs_lne20_badcnt,
+ &debugfs_lne21_badcnt,
+ &debugfs_lne22_badcnt,
+ &debugfs_lne23_badcnt,
+
+ &debugfs_com_int,
+};
+
+static const struct pci_device_id thunderx_ocx_pci_tbl[] = {
+ { PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVICE_ID_THUNDER_OCX) },
+ { 0, },
+};
+
+static void thunderx_ocx_clearstats(struct thunderx_ocx *ocx)
+{
+ int lane, stat, cfg;
+
+ for (lane = 0; lane < OCX_RX_LANES; lane++) {
+ cfg = readq(ocx->regs + OCX_LNE_CFG(lane));
+ cfg |= OCX_LNE_CFG_RX_STAT_RDCLR;
+ cfg &= ~OCX_LNE_CFG_RX_STAT_ENA;
+ writeq(cfg, ocx->regs + OCX_LNE_CFG(lane));
+
+ for (stat = 0; stat < OCX_RX_LANE_STATS; stat++)
+ readq(ocx->regs + OCX_LNE_STAT(lane, stat));
+ }
+}
+
+static int thunderx_ocx_probe(struct pci_dev *pdev,
+ const struct pci_device_id *id)
+{
+ struct thunderx_ocx *ocx;
+ struct edac_device_ctl_info *edac_dev;
+ char name[32];
+ int idx;
+ int i;
+ int ret;
+ u64 reg;
+
+ ret = pcim_enable_device(pdev);
+ if (ret) {
+ dev_err(&pdev->dev, "Cannot enable PCI device: %d\n", ret);
+ return ret;
+ }
+
+ ret = pcim_iomap_regions(pdev, BIT(0), "thunderx_ocx");
+ if (ret) {
+ dev_err(&pdev->dev, "Cannot map PCI resources: %d\n", ret);
+ return ret;
+ }
+
+ idx = edac_device_alloc_index();
+ snprintf(name, sizeof(name), "OCX%d", idx);
+ edac_dev = edac_device_alloc_ctl_info(sizeof(struct thunderx_ocx),
+ name, 1, "CCPI", 1,
+ 0, NULL, 0, idx);
+ if (!edac_dev) {
+ dev_err(&pdev->dev, "Cannot allocate EDAC device: %d\n", ret);
+ return -ENOMEM;
+ }
+ ocx = edac_dev->pvt_info;
+ ocx->edac_dev = edac_dev;
+ ocx->com_ring_head = 0;
+ ocx->com_ring_tail = 0;
+ ocx->link_ring_head = 0;
+ ocx->link_ring_tail = 0;
+
+ ocx->regs = pcim_iomap_table(pdev)[0];
+ if (!ocx->regs) {
+ dev_err(&pdev->dev, "Cannot map PCI resources: %d\n", ret);
+ ret = -ENODEV;
+ goto err_free;
+ }
+
+ ocx->pdev = pdev;
+
+ for (i = 0; i < OCX_INTS; i++) {
+ ocx->msix_ent[i].entry = i;
+ ocx->msix_ent[i].vector = 0;
+ }
+
+ ret = pci_enable_msix_exact(pdev, ocx->msix_ent, OCX_INTS);
+ if (ret) {
+ dev_err(&pdev->dev, "Cannot enable interrupt: %d\n", ret);
+ goto err_free;
+ }
+
+ for (i = 0; i < OCX_INTS; i++) {
+ ret = devm_request_threaded_irq(&pdev->dev,
+ ocx->msix_ent[i].vector,
+ (i == 3) ?
+ thunderx_ocx_com_isr :
+ thunderx_ocx_lnk_isr,
+ (i == 3) ?
+ thunderx_ocx_com_threaded_isr :
+ thunderx_ocx_lnk_threaded_isr,
+ 0, "[EDAC] ThunderX OCX",
+ &ocx->msix_ent[i]);
+ if (ret)
+ goto err_free;
+ }
+
+ edac_dev->dev = &pdev->dev;
+ edac_dev->dev_name = dev_name(&pdev->dev);
+ edac_dev->mod_name = "thunderx-ocx";
+ edac_dev->ctl_name = "thunderx-ocx";
+
+ ret = edac_device_add_device(edac_dev);
+ if (ret) {
+ dev_err(&pdev->dev, "Cannot add EDAC device: %d\n", ret);
+ goto err_free;
+ }
+
+ if (IS_ENABLED(CONFIG_EDAC_DEBUG)) {
+ ocx->debugfs = edac_debugfs_create_dir(pdev->dev.kobj.name);
+
+ ret = thunderx_create_debugfs_nodes(ocx->debugfs,
+ ocx_dfs_ents,
+ ocx,
+ ARRAY_SIZE(ocx_dfs_ents));
+ if (ret != ARRAY_SIZE(ocx_dfs_ents)) {
+ dev_warn(&pdev->dev, "Error creating debugfs entries: %d%s\n",
+ ret, ret >= 0 ? " created" : "");
+ }
+ }
+
+ pci_set_drvdata(pdev, edac_dev);
+
+ thunderx_ocx_clearstats(ocx);
+
+ for (i = 0; i < OCX_RX_LANES; i++) {
+ writeq(OCX_LNE_INT_ENA_ALL,
+ ocx->regs + OCX_LNE_INT_EN(i));
+
+ reg = readq(ocx->regs + OCX_LNE_INT(i));
+ writeq(reg, ocx->regs + OCX_LNE_INT(i));
+
+ }
+
+ for (i = 0; i < OCX_LINK_INTS; i++) {
+ reg = readq(ocx->regs + OCX_COM_LINKX_INT(i));
+ writeq(reg, ocx->regs + OCX_COM_LINKX_INT(i));
+
+ writeq(OCX_COM_LINKX_INT_ENA_ALL,
+ ocx->regs + OCX_COM_LINKX_INT_ENA_W1S(i));
+ }
+
+ reg = readq(ocx->regs + OCX_COM_INT);
+ writeq(reg, ocx->regs + OCX_COM_INT);
+
+ writeq(OCX_COM_INT_ENA_ALL, ocx->regs + OCX_COM_INT_ENA_W1S);
+
+ return 0;
+err_free:
+ edac_device_free_ctl_info(edac_dev);
+
+ return ret;
+}
+
+static void thunderx_ocx_remove(struct pci_dev *pdev)
+{
+ struct edac_device_ctl_info *edac_dev = pci_get_drvdata(pdev);
+ struct thunderx_ocx *ocx = edac_dev->pvt_info;
+ int i;
+
+ writeq(OCX_COM_INT_ENA_ALL, ocx->regs + OCX_COM_INT_ENA_W1C);
+
+ for (i = 0; i < OCX_INTS; i++) {
+ writeq(OCX_COM_LINKX_INT_ENA_ALL,
+ ocx->regs + OCX_COM_LINKX_INT_ENA_W1C(i));
+ }
+
+ edac_debugfs_remove_recursive(ocx->debugfs);
+
+ edac_device_del_device(&pdev->dev);
+ edac_device_free_ctl_info(edac_dev);
+}
+
+MODULE_DEVICE_TABLE(pci, thunderx_ocx_pci_tbl);
+
+static struct pci_driver thunderx_ocx_driver = {
+ .name = "thunderx_ocx_edac",
+ .probe = thunderx_ocx_probe,
+ .remove = thunderx_ocx_remove,
+ .id_table = thunderx_ocx_pci_tbl,
+};
+
+/*---------------------- L2C driver ---------------------------------*/
+
+#define PCI_DEVICE_ID_THUNDER_L2C_TAD 0xa02e
+#define PCI_DEVICE_ID_THUNDER_L2C_CBC 0xa02f
+#define PCI_DEVICE_ID_THUNDER_L2C_MCI 0xa030
+
+#define L2C_TAD_INT_W1C 0x40000
+#define L2C_TAD_INT_W1S 0x40008
+
+#define L2C_TAD_INT_ENA_W1C 0x40020
+#define L2C_TAD_INT_ENA_W1S 0x40028
+
+
+#define L2C_TAD_INT_L2DDBE BIT(1)
+#define L2C_TAD_INT_SBFSBE BIT(2)
+#define L2C_TAD_INT_SBFDBE BIT(3)
+#define L2C_TAD_INT_FBFSBE BIT(4)
+#define L2C_TAD_INT_FBFDBE BIT(5)
+#define L2C_TAD_INT_TAGDBE BIT(9)
+#define L2C_TAD_INT_RDDISLMC BIT(15)
+#define L2C_TAD_INT_WRDISLMC BIT(16)
+#define L2C_TAD_INT_LFBTO BIT(17)
+#define L2C_TAD_INT_GSYNCTO BIT(18)
+#define L2C_TAD_INT_RTGSBE BIT(32)
+#define L2C_TAD_INT_RTGDBE BIT(33)
+#define L2C_TAD_INT_RDDISOCI BIT(34)
+#define L2C_TAD_INT_WRDISOCI BIT(35)
+
+#define L2C_TAD_INT_ECC (L2C_TAD_INT_L2DDBE | \
+ L2C_TAD_INT_SBFSBE | L2C_TAD_INT_SBFDBE | \
+ L2C_TAD_INT_FBFSBE | L2C_TAD_INT_FBFDBE)
+
+#define L2C_TAD_INT_CE (L2C_TAD_INT_SBFSBE | \
+ L2C_TAD_INT_FBFSBE)
+
+#define L2C_TAD_INT_UE (L2C_TAD_INT_L2DDBE | \
+ L2C_TAD_INT_SBFDBE | \
+ L2C_TAD_INT_FBFDBE | \
+ L2C_TAD_INT_TAGDBE | \
+ L2C_TAD_INT_RTGDBE | \
+ L2C_TAD_INT_WRDISOCI | \
+ L2C_TAD_INT_RDDISOCI | \
+ L2C_TAD_INT_WRDISLMC | \
+ L2C_TAD_INT_RDDISLMC | \
+ L2C_TAD_INT_LFBTO | \
+ L2C_TAD_INT_GSYNCTO)
+
+static const struct error_descr l2_tad_errors[] = {
+ {
+ .type = ERR_CORRECTED,
+ .mask = L2C_TAD_INT_SBFSBE,
+ .descr = "SBF single-bit error",
+ },
+ {
+ .type = ERR_CORRECTED,
+ .mask = L2C_TAD_INT_FBFSBE,
+ .descr = "FBF single-bit error",
+ },
+ {
+ .type = ERR_UNCORRECTED,
+ .mask = L2C_TAD_INT_L2DDBE,
+ .descr = "L2D double-bit error",
+ },
+ {
+ .type = ERR_UNCORRECTED,
+ .mask = L2C_TAD_INT_SBFDBE,
+ .descr = "SBF double-bit error",
+ },
+ {
+ .type = ERR_UNCORRECTED,
+ .mask = L2C_TAD_INT_FBFDBE,
+ .descr = "FBF double-bit error",
+ },
+ {
+ .type = ERR_UNCORRECTED,
+ .mask = L2C_TAD_INT_TAGDBE,
+ .descr = "TAG double-bit error",
+ },
+ {
+ .type = ERR_UNCORRECTED,
+ .mask = L2C_TAD_INT_RTGDBE,
+ .descr = "RTG double-bit error",
+ },
+ {
+ .type = ERR_UNCORRECTED,
+ .mask = L2C_TAD_INT_WRDISOCI,
+ .descr = "Write to a disabled CCPI",
+ },
+ {
+ .type = ERR_UNCORRECTED,
+ .mask = L2C_TAD_INT_RDDISOCI,
+ .descr = "Read from a disabled CCPI",
+ },
+ {
+ .type = ERR_UNCORRECTED,
+ .mask = L2C_TAD_INT_WRDISLMC,
+ .descr = "Write to a disabled LMC",
+ },
+ {
+ .type = ERR_UNCORRECTED,
+ .mask = L2C_TAD_INT_RDDISLMC,
+ .descr = "Read from a disabled LMC",
+ },
+ {
+ .type = ERR_UNCORRECTED,
+ .mask = L2C_TAD_INT_LFBTO,
+ .descr = "LFB entry timeout",
+ },
+ {
+ .type = ERR_UNCORRECTED,
+ .mask = L2C_TAD_INT_GSYNCTO,
+ .descr = "Global sync CCPI timeout",
+ },
+ {0, 0, NULL},
+};
+
+#define L2C_TAD_INT_TAG (L2C_TAD_INT_TAGDBE)
+
+#define L2C_TAD_INT_RTG (L2C_TAD_INT_RTGDBE)
+
+#define L2C_TAD_INT_DISLMC (L2C_TAD_INT_WRDISLMC | L2C_TAD_INT_RDDISLMC)
+
+#define L2C_TAD_INT_DISOCI (L2C_TAD_INT_WRDISOCI | L2C_TAD_INT_RDDISOCI)
+
+#define L2C_TAD_INT_ENA_ALL (L2C_TAD_INT_ECC | L2C_TAD_INT_TAG | \
+ L2C_TAD_INT_RTG | \
+ L2C_TAD_INT_DISLMC | L2C_TAD_INT_DISOCI | \
+ L2C_TAD_INT_LFBTO)
+
+#define L2C_TAD_TIMETWO 0x50000
+#define L2C_TAD_TIMEOUT 0x50100
+#define L2C_TAD_ERR 0x60000
+#define L2C_TAD_TQD_ERR 0x60100
+#define L2C_TAD_TTG_ERR 0x60200
+
+
+#define L2C_CBC_INT_W1C 0x60000
+
+#define L2C_CBC_INT_RSDSBE BIT(0)
+#define L2C_CBC_INT_RSDDBE BIT(1)
+
+#define L2C_CBC_INT_RSD (L2C_CBC_INT_RSDSBE | L2C_CBC_INT_RSDDBE)
+
+#define L2C_CBC_INT_MIBSBE BIT(4)
+#define L2C_CBC_INT_MIBDBE BIT(5)
+
+#define L2C_CBC_INT_MIB (L2C_CBC_INT_MIBSBE | L2C_CBC_INT_MIBDBE)
+
+#define L2C_CBC_INT_IORDDISOCI BIT(6)
+#define L2C_CBC_INT_IOWRDISOCI BIT(7)
+
+#define L2C_CBC_INT_IODISOCI (L2C_CBC_INT_IORDDISOCI | \
+ L2C_CBC_INT_IOWRDISOCI)
+
+#define L2C_CBC_INT_CE (L2C_CBC_INT_RSDSBE | L2C_CBC_INT_MIBSBE)
+#define L2C_CBC_INT_UE (L2C_CBC_INT_RSDDBE | L2C_CBC_INT_MIBDBE)
+
+
+static const struct error_descr l2_cbc_errors[] = {
+ {
+ .type = ERR_CORRECTED,
+ .mask = L2C_CBC_INT_RSDSBE,
+ .descr = "RSD single-bit error",
+ },
+ {
+ .type = ERR_CORRECTED,
+ .mask = L2C_CBC_INT_MIBSBE,
+ .descr = "MIB single-bit error",
+ },
+ {
+ .type = ERR_UNCORRECTED,
+ .mask = L2C_CBC_INT_RSDDBE,
+ .descr = "RSD double-bit error",
+ },
+ {
+ .type = ERR_UNCORRECTED,
+ .mask = L2C_CBC_INT_MIBDBE,
+ .descr = "MIB double-bit error",
+ },
+ {
+ .type = ERR_UNCORRECTED,
+ .mask = L2C_CBC_INT_IORDDISOCI,
+ .descr = "Read from a disabled CCPI",
+ },
+ {
+ .type = ERR_UNCORRECTED,
+ .mask = L2C_CBC_INT_IOWRDISOCI,
+ .descr = "Write to a disabled CCPI",
+ },
+ {0, 0, NULL},
+};
+
+#define L2C_CBC_INT_W1S 0x60008
+#define L2C_CBC_INT_ENA_W1C 0x60020
+
+#define L2C_CBC_INT_ENA_ALL (L2C_CBC_INT_RSD | L2C_CBC_INT_MIB | \
+ L2C_CBC_INT_IODISOCI)
+
+#define L2C_CBC_INT_ENA_W1S 0x60028
+
+#define L2C_CBC_IODISOCIERR 0x80008
+#define L2C_CBC_IOCERR 0x80010
+#define L2C_CBC_RSDERR 0x80018
+#define L2C_CBC_MIBERR 0x80020
+
+
+#define L2C_MCI_INT_W1C 0x0
+
+#define L2C_MCI_INT_VBFSBE BIT(0)
+#define L2C_MCI_INT_VBFDBE BIT(1)
+
+static const struct error_descr l2_mci_errors[] = {
+ {
+ .type = ERR_CORRECTED,
+ .mask = L2C_MCI_INT_VBFSBE,
+ .descr = "VBF single-bit error",
+ },
+ {
+ .type = ERR_UNCORRECTED,
+ .mask = L2C_MCI_INT_VBFDBE,
+ .descr = "VBF double-bit error",
+ },
+ {0, 0, NULL},
+};
+
+#define L2C_MCI_INT_W1S 0x8
+#define L2C_MCI_INT_ENA_W1C 0x20
+
+#define L2C_MCI_INT_ENA_ALL (L2C_MCI_INT_VBFSBE | L2C_MCI_INT_VBFDBE)
+
+#define L2C_MCI_INT_ENA_W1S 0x28
+
+#define L2C_MCI_ERR 0x10000
+
+#define L2C_MESSAGE_SIZE SZ_1K
+#define L2C_OTHER_SIZE (50 * ARRAY_SIZE(l2_tad_errors))
+
+struct l2c_err_ctx {
+ char *reg_ext_name;
+ u64 reg_int;
+ u64 reg_ext;
+};
+
+struct thunderx_l2c {
+ void __iomem *regs;
+ struct pci_dev *pdev;
+ struct edac_device_ctl_info *edac_dev;
+
+ struct dentry *debugfs;
+
+ int index;
+
+ struct msix_entry msix_ent;
+
+ struct l2c_err_ctx err_ctx[RING_ENTRIES];
+ unsigned long ring_head;
+ unsigned long ring_tail;
+};
+
+static irqreturn_t thunderx_l2c_tad_isr(int irq, void *irq_id)
+{
+ struct msix_entry *msix = irq_id;
+ struct thunderx_l2c *tad = container_of(msix, struct thunderx_l2c,
+ msix_ent);
+
+ unsigned long head = ring_pos(tad->ring_head, ARRAY_SIZE(tad->err_ctx));
+ struct l2c_err_ctx *ctx = &tad->err_ctx[head];
+
+ ctx->reg_int = readq(tad->regs + L2C_TAD_INT_W1C);
+
+ if (ctx->reg_int & L2C_TAD_INT_ECC) {
+ ctx->reg_ext_name = "TQD_ERR";
+ ctx->reg_ext = readq(tad->regs + L2C_TAD_TQD_ERR);
+ } else if (ctx->reg_int & L2C_TAD_INT_TAG) {
+ ctx->reg_ext_name = "TTG_ERR";
+ ctx->reg_ext = readq(tad->regs + L2C_TAD_TTG_ERR);
+ } else if (ctx->reg_int & L2C_TAD_INT_LFBTO) {
+ ctx->reg_ext_name = "TIMEOUT";
+ ctx->reg_ext = readq(tad->regs + L2C_TAD_TIMEOUT);
+ } else if (ctx->reg_int & L2C_TAD_INT_DISOCI) {
+ ctx->reg_ext_name = "ERR";
+ ctx->reg_ext = readq(tad->regs + L2C_TAD_ERR);
+ }
+
+ writeq(ctx->reg_int, tad->regs + L2C_TAD_INT_W1C);
+
+ tad->ring_head++;
+
+ return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t thunderx_l2c_cbc_isr(int irq, void *irq_id)
+{
+ struct msix_entry *msix = irq_id;
+ struct thunderx_l2c *cbc = container_of(msix, struct thunderx_l2c,
+ msix_ent);
+
+ unsigned long head = ring_pos(cbc->ring_head, ARRAY_SIZE(cbc->err_ctx));
+ struct l2c_err_ctx *ctx = &cbc->err_ctx[head];
+
+ ctx->reg_int = readq(cbc->regs + L2C_CBC_INT_W1C);
+
+ if (ctx->reg_int & L2C_CBC_INT_RSD) {
+ ctx->reg_ext_name = "RSDERR";
+ ctx->reg_ext = readq(cbc->regs + L2C_CBC_RSDERR);
+ } else if (ctx->reg_int & L2C_CBC_INT_MIB) {
+ ctx->reg_ext_name = "MIBERR";
+ ctx->reg_ext = readq(cbc->regs + L2C_CBC_MIBERR);
+ } else if (ctx->reg_int & L2C_CBC_INT_IODISOCI) {
+ ctx->reg_ext_name = "IODISOCIERR";
+ ctx->reg_ext = readq(cbc->regs + L2C_CBC_IODISOCIERR);
+ }
+
+ writeq(ctx->reg_int, cbc->regs + L2C_CBC_INT_W1C);
+
+ cbc->ring_head++;
+
+ return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t thunderx_l2c_mci_isr(int irq, void *irq_id)
+{
+ struct msix_entry *msix = irq_id;
+ struct thunderx_l2c *mci = container_of(msix, struct thunderx_l2c,
+ msix_ent);
+
+ unsigned long head = ring_pos(mci->ring_head, ARRAY_SIZE(mci->err_ctx));
+ struct l2c_err_ctx *ctx = &mci->err_ctx[head];
+
+ ctx->reg_int = readq(mci->regs + L2C_MCI_INT_W1C);
+ ctx->reg_ext = readq(mci->regs + L2C_MCI_ERR);
+
+ writeq(ctx->reg_int, mci->regs + L2C_MCI_INT_W1C);
+
+ ctx->reg_ext_name = "ERR";
+
+ mci->ring_head++;
+
+ return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t thunderx_l2c_threaded_isr(int irq, void *irq_id)
+{
+ struct msix_entry *msix = irq_id;
+ struct thunderx_l2c *l2c = container_of(msix, struct thunderx_l2c,
+ msix_ent);
+
+ unsigned long tail = ring_pos(l2c->ring_tail, ARRAY_SIZE(l2c->err_ctx));
+ struct l2c_err_ctx *ctx = &l2c->err_ctx[tail];
+ irqreturn_t ret = IRQ_NONE;
+
+ u64 mask_ue, mask_ce;
+ const struct error_descr *l2_errors;
+ char *reg_int_name;
+
+ char *msg;
+ char *other;
+
+ msg = kmalloc(OCX_MESSAGE_SIZE, GFP_KERNEL);
+ other = kmalloc(OCX_OTHER_SIZE, GFP_KERNEL);
+
+ if (!msg || !other)
+ goto err_free;
+
+ switch (l2c->pdev->device) {
+ case PCI_DEVICE_ID_THUNDER_L2C_TAD:
+ reg_int_name = "L2C_TAD_INT";
+ mask_ue = L2C_TAD_INT_UE;
+ mask_ce = L2C_TAD_INT_CE;
+ l2_errors = l2_tad_errors;
+ break;
+ case PCI_DEVICE_ID_THUNDER_L2C_CBC:
+ reg_int_name = "L2C_CBC_INT";
+ mask_ue = L2C_CBC_INT_UE;
+ mask_ce = L2C_CBC_INT_CE;
+ l2_errors = l2_cbc_errors;
+ break;
+ case PCI_DEVICE_ID_THUNDER_L2C_MCI:
+ reg_int_name = "L2C_MCI_INT";
+ mask_ue = L2C_MCI_INT_VBFDBE;
+ mask_ce = L2C_MCI_INT_VBFSBE;
+ l2_errors = l2_mci_errors;
+ break;
+ default:
+ dev_err(&l2c->pdev->dev, "Unsupported device: %04x\n",
+ l2c->pdev->device);
+ return IRQ_NONE;
+ }
+
+ while (CIRC_CNT(l2c->ring_head, l2c->ring_tail,
+ ARRAY_SIZE(l2c->err_ctx))) {
+ snprintf(msg, L2C_MESSAGE_SIZE,
+ "%s: %s: %016llx, %s: %016llx",
+ l2c->edac_dev->ctl_name, reg_int_name, ctx->reg_int,
+ ctx->reg_ext_name, ctx->reg_ext);
+
+ decode_register(other, L2C_OTHER_SIZE, l2_errors, ctx->reg_int);
+
+ strncat(msg, other, L2C_MESSAGE_SIZE);
+
+ if (ctx->reg_int & mask_ue)
+ edac_device_handle_ue(l2c->edac_dev, 0, 0, msg);
+ else if (ctx->reg_int & mask_ce)
+ edac_device_handle_ce(l2c->edac_dev, 0, 0, msg);
+
+ l2c->ring_tail++;
+ }
+
+ return IRQ_HANDLED;
+
+err_free:
+ kfree(other);
+ kfree(msg);
+
+ return ret;
+}
+
+#define L2C_DEBUGFS_ATTR(_name, _reg) DEBUGFS_REG_ATTR(l2c, _name, _reg)
+
+L2C_DEBUGFS_ATTR(tad_int, L2C_TAD_INT_W1S);
+
+struct debugfs_entry *l2c_tad_dfs_ents[] = {
+ &debugfs_tad_int,
+};
+
+L2C_DEBUGFS_ATTR(cbc_int, L2C_CBC_INT_W1S);
+
+struct debugfs_entry *l2c_cbc_dfs_ents[] = {
+ &debugfs_cbc_int,
+};
+
+L2C_DEBUGFS_ATTR(mci_int, L2C_MCI_INT_W1S);
+
+struct debugfs_entry *l2c_mci_dfs_ents[] = {
+ &debugfs_mci_int,
+};
+
+static const struct pci_device_id thunderx_l2c_pci_tbl[] = {
+ { PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVICE_ID_THUNDER_L2C_TAD), },
+ { PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVICE_ID_THUNDER_L2C_CBC), },
+ { PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVICE_ID_THUNDER_L2C_MCI), },
+ { 0, },
+};
+
+static int thunderx_l2c_probe(struct pci_dev *pdev,
+ const struct pci_device_id *id)
+{
+ struct thunderx_l2c *l2c;
+ struct edac_device_ctl_info *edac_dev;
+ struct debugfs_entry **l2c_devattr;
+ size_t dfs_entries;
+ irqreturn_t (*thunderx_l2c_isr)(int, void *) = NULL;
+ char name[32];
+ const char *fmt;
+ u64 reg_en_offs, reg_en_mask;
+ int idx;
+ int ret;
+
+ ret = pcim_enable_device(pdev);
+ if (ret) {
+ dev_err(&pdev->dev, "Cannot enable PCI device: %d\n", ret);
+ return ret;
+ }
+
+ ret = pcim_iomap_regions(pdev, BIT(0), "thunderx_l2c");
+ if (ret) {
+ dev_err(&pdev->dev, "Cannot map PCI resources: %d\n", ret);
+ return ret;
+ }
+
+ switch (pdev->device) {
+ case PCI_DEVICE_ID_THUNDER_L2C_TAD:
+ thunderx_l2c_isr = thunderx_l2c_tad_isr;
+ l2c_devattr = l2c_tad_dfs_ents;
+ dfs_entries = ARRAY_SIZE(l2c_tad_dfs_ents);
+ fmt = "L2C-TAD%d";
+ reg_en_offs = L2C_TAD_INT_ENA_W1S;
+ reg_en_mask = L2C_TAD_INT_ENA_ALL;
+ break;
+ case PCI_DEVICE_ID_THUNDER_L2C_CBC:
+ thunderx_l2c_isr = thunderx_l2c_cbc_isr;
+ l2c_devattr = l2c_cbc_dfs_ents;
+ dfs_entries = ARRAY_SIZE(l2c_cbc_dfs_ents);
+ fmt = "L2C-CBC%d";
+ reg_en_offs = L2C_CBC_INT_ENA_W1S;
+ reg_en_mask = L2C_CBC_INT_ENA_ALL;
+ break;
+ case PCI_DEVICE_ID_THUNDER_L2C_MCI:
+ thunderx_l2c_isr = thunderx_l2c_mci_isr;
+ l2c_devattr = l2c_mci_dfs_ents;
+ dfs_entries = ARRAY_SIZE(l2c_mci_dfs_ents);
+ fmt = "L2C-MCI%d";
+ reg_en_offs = L2C_MCI_INT_ENA_W1S;
+ reg_en_mask = L2C_MCI_INT_ENA_ALL;
+ break;
+ default:
+ //Should never ever get here
+ dev_err(&pdev->dev, "Unsupported PCI device: %04x\n",
+ pdev->device);
+ return -EINVAL;
+ }
+
+ idx = edac_device_alloc_index();
+ snprintf(name, sizeof(name), fmt, idx);
+
+ edac_dev = edac_device_alloc_ctl_info(sizeof(struct thunderx_l2c),
+ name, 1, "L2C", 1, 0,
+ NULL, 0, idx);
+ if (!edac_dev) {
+ dev_err(&pdev->dev, "Cannot allocate EDAC device\n");
+ return -ENOMEM;
+ }
+
+ l2c = edac_dev->pvt_info;
+ l2c->edac_dev = edac_dev;
+
+ l2c->regs = pcim_iomap_table(pdev)[0];
+ if (!l2c->regs) {
+ dev_err(&pdev->dev, "Cannot map PCI resources\n");
+ ret = -ENODEV;
+ goto err_free;
+ }
+
+ l2c->pdev = pdev;
+
+ l2c->ring_head = 0;
+ l2c->ring_tail = 0;
+
+ l2c->msix_ent.entry = 0;
+ l2c->msix_ent.vector = 0;
+
+ ret = pci_enable_msix_exact(pdev, &l2c->msix_ent, 1);
+ if (ret) {
+ dev_err(&pdev->dev, "Cannot enable interrupt: %d\n", ret);
+ goto err_free;
+ }
+
+ ret = devm_request_threaded_irq(&pdev->dev, l2c->msix_ent.vector,
+ thunderx_l2c_isr,
+ thunderx_l2c_threaded_isr,
+ 0, "[EDAC] ThunderX L2C",
+ &l2c->msix_ent);
+ if (ret)
+ goto err_free;
+
+ edac_dev->dev = &pdev->dev;
+ edac_dev->dev_name = dev_name(&pdev->dev);
+ edac_dev->mod_name = "thunderx-l2c";
+ edac_dev->ctl_name = "thunderx-l2c";
+
+ ret = edac_device_add_device(edac_dev);
+ if (ret) {
+ dev_err(&pdev->dev, "Cannot add EDAC device: %d\n", ret);
+ goto err_free;
+ }
+
+ if (IS_ENABLED(CONFIG_EDAC_DEBUG)) {
+ l2c->debugfs = edac_debugfs_create_dir(pdev->dev.kobj.name);
+
+ thunderx_create_debugfs_nodes(l2c->debugfs, l2c_devattr,
+ l2c, dfs_entries);
+
+ if (ret != dfs_entries) {
+ dev_warn(&pdev->dev, "Error creating debugfs entries: %d%s\n",
+ ret, ret >= 0 ? " created" : "");
+ }
+ }
+
+ pci_set_drvdata(pdev, edac_dev);
+
+ writeq(reg_en_mask, l2c->regs + reg_en_offs);
+
+ return 0;
+
+err_free:
+ edac_device_free_ctl_info(edac_dev);
+
+ return ret;
+}
+
+static void thunderx_l2c_remove(struct pci_dev *pdev)
+{
+ struct edac_device_ctl_info *edac_dev = pci_get_drvdata(pdev);
+ struct thunderx_l2c *l2c = edac_dev->pvt_info;
+
+ switch (pdev->device) {
+ case PCI_DEVICE_ID_THUNDER_L2C_TAD:
+ writeq(L2C_TAD_INT_ENA_ALL, l2c->regs + L2C_TAD_INT_ENA_W1C);
+ break;
+ case PCI_DEVICE_ID_THUNDER_L2C_CBC:
+ writeq(L2C_CBC_INT_ENA_ALL, l2c->regs + L2C_CBC_INT_ENA_W1C);
+ break;
+ case PCI_DEVICE_ID_THUNDER_L2C_MCI:
+ writeq(L2C_MCI_INT_ENA_ALL, l2c->regs + L2C_MCI_INT_ENA_W1C);
+ break;
+ }
+
+ edac_debugfs_remove_recursive(l2c->debugfs);
+
+ edac_device_del_device(&pdev->dev);
+ edac_device_free_ctl_info(edac_dev);
+}
+
+MODULE_DEVICE_TABLE(pci, thunderx_l2c_pci_tbl);
+
+static struct pci_driver thunderx_l2c_driver = {
+ .name = "thunderx_l2c_edac",
+ .probe = thunderx_l2c_probe,
+ .remove = thunderx_l2c_remove,
+ .id_table = thunderx_l2c_pci_tbl,
+};
+
+static int __init thunderx_edac_init(void)
+{
+ int rc = 0;
+
+ rc = pci_register_driver(&thunderx_lmc_driver);
+ if (rc)
+ return rc;
+
+ rc = pci_register_driver(&thunderx_ocx_driver);
+ if (rc)
+ goto err_lmc;
+
+ rc = pci_register_driver(&thunderx_l2c_driver);
+ if (rc)
+ goto err_ocx;
+
+ return rc;
+err_ocx:
+ pci_unregister_driver(&thunderx_ocx_driver);
+err_lmc:
+ pci_unregister_driver(&thunderx_lmc_driver);
+
+ return rc;
+}
+
+static void __exit thunderx_edac_exit(void)
+{
+ pci_unregister_driver(&thunderx_l2c_driver);
+ pci_unregister_driver(&thunderx_ocx_driver);
+ pci_unregister_driver(&thunderx_lmc_driver);
+
+}
+
+module_init(thunderx_edac_init);
+module_exit(thunderx_edac_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Cavium, Inc.");
+MODULE_DESCRIPTION("EDAC Driver for Cavium ThunderX");
extcon_unregister_notifier(this->edev, this->id, this->nb);
}
+static void devm_extcon_dev_notifier_all_unreg(struct device *dev, void *res)
+{
+ struct extcon_dev_notifier_devres *this = res;
+
+ extcon_unregister_notifier_all(this->edev, this->nb);
+}
+
/**
* devm_extcon_dev_allocate - Allocate managed extcon device
* @dev: device owning the extcon device being created
devm_extcon_dev_match, edev));
}
EXPORT_SYMBOL(devm_extcon_unregister_notifier);
+
+/**
+ * devm_extcon_register_notifier_all()
+ * - Resource-managed extcon_register_notifier_all()
+ * @dev: device to allocate extcon device
+ * @edev: the extcon device that has the external connecotr.
+ * @nb: a notifier block to be registered.
+ *
+ * This function manages automatically the notifier of extcon device using
+ * device resource management and simplify the control of unregistering
+ * the notifier of extcon device. To get more information, refer that function.
+ *
+ * Returns 0 if success or negaive error number if failure.
+ */
+int devm_extcon_register_notifier_all(struct device *dev, struct extcon_dev *edev,
+ struct notifier_block *nb)
+{
+ struct extcon_dev_notifier_devres *ptr;
+ int ret;
+
+ ptr = devres_alloc(devm_extcon_dev_notifier_all_unreg, sizeof(*ptr),
+ GFP_KERNEL);
+ if (!ptr)
+ return -ENOMEM;
+
+ ret = extcon_register_notifier_all(edev, nb);
+ if (ret) {
+ devres_free(ptr);
+ return ret;
+ }
+
+ ptr->edev = edev;
+ ptr->nb = nb;
+ devres_add(dev, ptr);
+
+ return 0;
+}
+EXPORT_SYMBOL(devm_extcon_register_notifier_all);
+
+/**
+ * devm_extcon_unregister_notifier_all()
+ * - Resource-managed extcon_unregister_notifier_all()
+ * @dev: device to allocate extcon device
+ * @edev: the extcon device that has the external connecotr.
+ * @nb: a notifier block to be registered.
+ */
+void devm_extcon_unregister_notifier_all(struct device *dev,
+ struct extcon_dev *edev,
+ struct notifier_block *nb)
+{
+ WARN_ON(devres_release(dev, devm_extcon_dev_notifier_all_unreg,
+ devm_extcon_dev_match, edev));
+}
+EXPORT_SYMBOL(devm_extcon_unregister_notifier_all);
spin_lock_irqsave(&edev->lock, flags);
state = !!(edev->state & BIT(index));
+
+ /*
+ * Call functions in a raw notifier chain for the specific one
+ * external connector.
+ */
raw_notifier_call_chain(&edev->nh[index], state, edev);
+ /*
+ * Call functions in a raw notifier chain for the all supported
+ * external connectors.
+ */
+ raw_notifier_call_chain(&edev->nh_all, state, edev);
+
/* This could be in interrupt handler */
prop_buf = (char *)get_zeroed_page(GFP_ATOMIC);
if (!prop_buf) {
}
EXPORT_SYMBOL_GPL(extcon_unregister_notifier);
+/**
+ * extcon_register_notifier_all() - Register a notifier block for all connectors
+ * @edev: the extcon device that has the external connecotr.
+ * @nb: a notifier block to be registered.
+ *
+ * This fucntion registers a notifier block in order to receive the state
+ * change of all supported external connectors from extcon device.
+ * And The second parameter given to the callback of nb (val) is
+ * the current state and third parameter is the edev pointer.
+ *
+ * Returns 0 if success or error number if fail
+ */
+int extcon_register_notifier_all(struct extcon_dev *edev,
+ struct notifier_block *nb)
+{
+ unsigned long flags;
+ int ret;
+
+ if (!edev || !nb)
+ return -EINVAL;
+
+ spin_lock_irqsave(&edev->lock, flags);
+ ret = raw_notifier_chain_register(&edev->nh_all, nb);
+ spin_unlock_irqrestore(&edev->lock, flags);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(extcon_register_notifier_all);
+
+/**
+ * extcon_unregister_notifier_all() - Unregister a notifier block from extcon.
+ * @edev: the extcon device that has the external connecotr.
+ * @nb: a notifier block to be registered.
+ *
+ * Returns 0 if success or error number if fail
+ */
+int extcon_unregister_notifier_all(struct extcon_dev *edev,
+ struct notifier_block *nb)
+{
+ unsigned long flags;
+ int ret;
+
+ if (!edev || !nb)
+ return -EINVAL;
+
+ spin_lock_irqsave(&edev->lock, flags);
+ ret = raw_notifier_chain_unregister(&edev->nh_all, nb);
+ spin_unlock_irqrestore(&edev->lock, flags);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(extcon_unregister_notifier_all);
+
static struct attribute *extcon_attrs[] = {
&dev_attr_state.attr,
&dev_attr_name.attr,
for (index = 0; index < edev->max_supported; index++)
RAW_INIT_NOTIFIER_HEAD(&edev->nh[index]);
+ RAW_INIT_NOTIFIER_HEAD(&edev->nh_all);
+
dev_set_drvdata(&edev->dev, edev);
edev->state = 0;
* @dev: Device of this extcon.
* @state: Attach/detach state of this extcon. Do not provide at
* register-time.
+ * @nh_all: Notifier for the state change events for all supported
+ * external connectors from this extcon.
* @nh: Notifier for the state change events from this extcon
* @entry: To support list of extcon devices so that users can
* search for extcon devices based on the extcon name.
/* Internal data. Please do not set. */
struct device dev;
+ struct raw_notifier_head nh_all;
struct raw_notifier_head *nh;
struct list_head entry;
int max_supported;
#
KASAN_SANITIZE_runtime-wrappers.o := n
+obj-$(CONFIG_ACPI_BGRT) += efi-bgrt.o
obj-$(CONFIG_EFI) += efi.o vars.o reboot.o memattr.o
obj-$(CONFIG_EFI) += capsule.o memmap.o
obj-$(CONFIG_EFI_VARS) += efivars.o
for (i = 0; i < DUMP_NAME_LEN; i++)
efi_name[i] = name[i];
- efivar_entry_set_safe(efi_name, vendor, PSTORE_EFI_ATTRIBUTES,
- !pstore_cannot_block_path(reason),
- size, psi->buf);
+ ret = efivar_entry_set_safe(efi_name, vendor, PSTORE_EFI_ATTRIBUTES,
+ !pstore_cannot_block_path(reason),
+ size, psi->buf);
if (reason == KMSG_DUMP_OOPS)
efivar_run_worker();
#include "efistub.h"
-bool __nokaslr;
+/*
+ * This is the base address at which to start allocating virtual memory ranges
+ * for UEFI Runtime Services. This is in the low TTBR0 range so that we can use
+ * any allocation we choose, and eliminate the risk of a conflict after kexec.
+ * The value chosen is the largest non-zero power of 2 suitable for this purpose
+ * both on 32-bit and 64-bit ARM CPUs, to maximize the likelihood that it can
+ * be mapped efficiently.
+ * Since 32-bit ARM could potentially execute with a 1G/3G user/kernel split,
+ * map everything below 1 GB. (512 MB is a reasonable upper bound for the
+ * entire footprint of the UEFI runtime services memory regions)
+ */
+#define EFI_RT_VIRTUAL_BASE SZ_512M
+#define EFI_RT_VIRTUAL_SIZE SZ_512M
+
+#ifdef CONFIG_ARM64
+# define EFI_RT_VIRTUAL_LIMIT TASK_SIZE_64
+#else
+# define EFI_RT_VIRTUAL_LIMIT TASK_SIZE
+#endif
+
+static u64 virtmap_base = EFI_RT_VIRTUAL_BASE;
efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg,
void *__image, void **__fh)
if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
goto fail;
- pr_efi(sys_table, "Booting Linux Kernel...\n");
-
status = check_platform_features(sys_table);
if (status != EFI_SUCCESS)
goto fail;
goto fail;
}
- /* check whether 'nokaslr' was passed on the command line */
- if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
- static const u8 default_cmdline[] = CONFIG_CMDLINE;
- const u8 *str, *cmdline = cmdline_ptr;
+ if (IS_ENABLED(CONFIG_CMDLINE_EXTEND) ||
+ IS_ENABLED(CONFIG_CMDLINE_FORCE) ||
+ cmdline_size == 0)
+ efi_parse_options(CONFIG_CMDLINE);
- if (IS_ENABLED(CONFIG_CMDLINE_FORCE))
- cmdline = default_cmdline;
- str = strstr(cmdline, "nokaslr");
- if (str == cmdline || (str > cmdline && *(str - 1) == ' '))
- __nokaslr = true;
- }
+ if (!IS_ENABLED(CONFIG_CMDLINE_FORCE) && cmdline_size > 0)
+ efi_parse_options(cmdline_ptr);
+
+ pr_efi(sys_table, "Booting Linux Kernel...\n");
si = setup_graphics(sys_table);
goto fail_free_cmdline;
}
- status = efi_parse_options(cmdline_ptr);
- if (status != EFI_SUCCESS)
- pr_efi_err(sys_table, "Failed to parse EFI cmdline options\n");
-
secure_boot = efi_get_secureboot(sys_table);
/*
if (!fdt_addr)
pr_efi(sys_table, "Generating empty DTB\n");
- status = handle_cmdline_files(sys_table, image, cmdline_ptr,
- "initrd=", dram_base + SZ_512M,
+ status = handle_cmdline_files(sys_table, image, cmdline_ptr, "initrd=",
+ efi_get_max_initrd_addr(dram_base,
+ *image_addr),
(unsigned long *)&initrd_addr,
(unsigned long *)&initrd_size);
if (status != EFI_SUCCESS)
efi_random_get_seed(sys_table);
+ if (!nokaslr()) {
+ /*
+ * Randomize the base of the UEFI runtime services region.
+ * Preserve the 2 MB alignment of the region by taking a
+ * shift of 21 bit positions into account when scaling
+ * the headroom value using a 32-bit random value.
+ */
+ static const u64 headroom = EFI_RT_VIRTUAL_LIMIT -
+ EFI_RT_VIRTUAL_BASE -
+ EFI_RT_VIRTUAL_SIZE;
+ u32 rnd;
+
+ status = efi_get_random_bytes(sys_table, sizeof(rnd),
+ (u8 *)&rnd);
+ if (status == EFI_SUCCESS) {
+ virtmap_base = EFI_RT_VIRTUAL_BASE +
+ (((headroom >> 21) * rnd) >> (32 - 21));
+ }
+ }
+
new_fdt_addr = fdt_addr;
status = allocate_new_fdt_and_exit_boot(sys_table, handle,
- &new_fdt_addr, dram_base + MAX_FDT_OFFSET,
+ &new_fdt_addr, efi_get_max_fdt_addr(dram_base),
initrd_addr, initrd_size, cmdline_ptr,
fdt_addr, fdt_size);
return EFI_ERROR;
}
-/*
- * This is the base address at which to start allocating virtual memory ranges
- * for UEFI Runtime Services. This is in the low TTBR0 range so that we can use
- * any allocation we choose, and eliminate the risk of a conflict after kexec.
- * The value chosen is the largest non-zero power of 2 suitable for this purpose
- * both on 32-bit and 64-bit ARM CPUs, to maximize the likelihood that it can
- * be mapped efficiently.
- * Since 32-bit ARM could potentially execute with a 1G/3G user/kernel split,
- * map everything below 1 GB.
- */
-#define EFI_RT_VIRTUAL_BASE SZ_512M
-
static int cmp_mem_desc(const void *l, const void *r)
{
const efi_memory_desc_t *left = l, *right = r;
unsigned long desc_size, efi_memory_desc_t *runtime_map,
int *count)
{
- u64 efi_virt_base = EFI_RT_VIRTUAL_BASE;
+ u64 efi_virt_base = virtmap_base;
efi_memory_desc_t *in, *prev = NULL, *out = runtime_map;
int l;
#include <linux/efi.h>
#include <asm/efi.h>
+#include "efistub.h"
+
efi_status_t check_platform_features(efi_system_table_t *sys_table_arg)
{
int block;
efi_call_early(free_pool, si);
}
+static efi_status_t reserve_kernel_base(efi_system_table_t *sys_table_arg,
+ unsigned long dram_base,
+ unsigned long *reserve_addr,
+ unsigned long *reserve_size)
+{
+ efi_physical_addr_t alloc_addr;
+ efi_memory_desc_t *memory_map;
+ unsigned long nr_pages, map_size, desc_size, buff_size;
+ efi_status_t status;
+ unsigned long l;
+
+ struct efi_boot_memmap map = {
+ .map = &memory_map,
+ .map_size = &map_size,
+ .desc_size = &desc_size,
+ .desc_ver = NULL,
+ .key_ptr = NULL,
+ .buff_size = &buff_size,
+ };
+
+ /*
+ * Reserve memory for the uncompressed kernel image. This is
+ * all that prevents any future allocations from conflicting
+ * with the kernel. Since we can't tell from the compressed
+ * image how much DRAM the kernel actually uses (due to BSS
+ * size uncertainty) we allocate the maximum possible size.
+ * Do this very early, as prints can cause memory allocations
+ * that may conflict with this.
+ */
+ alloc_addr = dram_base + MAX_UNCOMP_KERNEL_SIZE;
+ nr_pages = MAX_UNCOMP_KERNEL_SIZE / EFI_PAGE_SIZE;
+ status = efi_call_early(allocate_pages, EFI_ALLOCATE_MAX_ADDRESS,
+ EFI_BOOT_SERVICES_DATA, nr_pages, &alloc_addr);
+ if (status == EFI_SUCCESS) {
+ if (alloc_addr == dram_base) {
+ *reserve_addr = alloc_addr;
+ *reserve_size = MAX_UNCOMP_KERNEL_SIZE;
+ return EFI_SUCCESS;
+ }
+ /*
+ * If we end up here, the allocation succeeded but starts below
+ * dram_base. This can only occur if the real base of DRAM is
+ * not a multiple of 128 MB, in which case dram_base will have
+ * been rounded up. Since this implies that a part of the region
+ * was already occupied, we need to fall through to the code
+ * below to ensure that the existing allocations don't conflict.
+ * For this reason, we use EFI_BOOT_SERVICES_DATA above and not
+ * EFI_LOADER_DATA, which we wouldn't able to distinguish from
+ * allocations that we want to disallow.
+ */
+ }
+
+ /*
+ * If the allocation above failed, we may still be able to proceed:
+ * if the only allocations in the region are of types that will be
+ * released to the OS after ExitBootServices(), the decompressor can
+ * safely overwrite them.
+ */
+ status = efi_get_memory_map(sys_table_arg, &map);
+ if (status != EFI_SUCCESS) {
+ pr_efi_err(sys_table_arg,
+ "reserve_kernel_base(): Unable to retrieve memory map.\n");
+ return status;
+ }
+
+ for (l = 0; l < map_size; l += desc_size) {
+ efi_memory_desc_t *desc;
+ u64 start, end;
+
+ desc = (void *)memory_map + l;
+ start = desc->phys_addr;
+ end = start + desc->num_pages * EFI_PAGE_SIZE;
+
+ /* Skip if entry does not intersect with region */
+ if (start >= dram_base + MAX_UNCOMP_KERNEL_SIZE ||
+ end <= dram_base)
+ continue;
+
+ switch (desc->type) {
+ case EFI_BOOT_SERVICES_CODE:
+ case EFI_BOOT_SERVICES_DATA:
+ /* Ignore types that are released to the OS anyway */
+ continue;
+
+ case EFI_CONVENTIONAL_MEMORY:
+ /*
+ * Reserve the intersection between this entry and the
+ * region.
+ */
+ start = max(start, (u64)dram_base);
+ end = min(end, (u64)dram_base + MAX_UNCOMP_KERNEL_SIZE);
+
+ status = efi_call_early(allocate_pages,
+ EFI_ALLOCATE_ADDRESS,
+ EFI_LOADER_DATA,
+ (end - start) / EFI_PAGE_SIZE,
+ &start);
+ if (status != EFI_SUCCESS) {
+ pr_efi_err(sys_table_arg,
+ "reserve_kernel_base(): alloc failed.\n");
+ goto out;
+ }
+ break;
+
+ case EFI_LOADER_CODE:
+ case EFI_LOADER_DATA:
+ /*
+ * These regions may be released and reallocated for
+ * another purpose (including EFI_RUNTIME_SERVICE_DATA)
+ * at any time during the execution of the OS loader,
+ * so we cannot consider them as safe.
+ */
+ default:
+ /*
+ * Treat any other allocation in the region as unsafe */
+ status = EFI_OUT_OF_RESOURCES;
+ goto out;
+ }
+ }
+
+ status = EFI_SUCCESS;
+out:
+ efi_call_early(free_pool, memory_map);
+ return status;
+}
+
efi_status_t handle_kernel_image(efi_system_table_t *sys_table,
unsigned long *image_addr,
unsigned long *image_size,
unsigned long dram_base,
efi_loaded_image_t *image)
{
- unsigned long nr_pages;
efi_status_t status;
- /* Use alloc_addr to tranlsate between types */
- efi_physical_addr_t alloc_addr;
/*
* Verify that the DRAM base address is compatible with the ARM
*/
dram_base = round_up(dram_base, SZ_128M);
- /*
- * Reserve memory for the uncompressed kernel image. This is
- * all that prevents any future allocations from conflicting
- * with the kernel. Since we can't tell from the compressed
- * image how much DRAM the kernel actually uses (due to BSS
- * size uncertainty) we allocate the maximum possible size.
- * Do this very early, as prints can cause memory allocations
- * that may conflict with this.
- */
- alloc_addr = dram_base;
- *reserve_size = MAX_UNCOMP_KERNEL_SIZE;
- nr_pages = round_up(*reserve_size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
- status = sys_table->boottime->allocate_pages(EFI_ALLOCATE_ADDRESS,
- EFI_LOADER_DATA,
- nr_pages, &alloc_addr);
+ status = reserve_kernel_base(sys_table, dram_base, reserve_addr,
+ reserve_size);
if (status != EFI_SUCCESS) {
- *reserve_size = 0;
pr_efi_err(sys_table, "Unable to allocate memory for uncompressed kernel.\n");
return status;
}
- *reserve_addr = alloc_addr;
/*
* Relocate the zImage, so that it appears in the lowest 128 MB
#include "efistub.h"
-extern bool __nokaslr;
-
efi_status_t check_platform_features(efi_system_table_t *sys_table_arg)
{
u64 tg;
u64 phys_seed = 0;
if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
- if (!__nokaslr) {
+ if (!nokaslr()) {
status = efi_get_random_bytes(sys_table_arg,
sizeof(phys_seed),
(u8 *)&phys_seed);
static unsigned long __chunk_size = EFI_READ_CHUNK_SIZE;
+static int __section(.data) __nokaslr;
+static int __section(.data) __quiet;
+
+int __pure nokaslr(void)
+{
+ return __nokaslr;
+}
+int __pure is_quiet(void)
+{
+ return __quiet;
+}
+
#define EFI_MMAP_NR_SLACK_SLOTS 8
struct file_info {
* environments, first in the early boot environment of the EFI boot
* stub, and subsequently during the kernel boot.
*/
-efi_status_t efi_parse_options(char *cmdline)
+efi_status_t efi_parse_options(char const *cmdline)
{
char *str;
- /*
- * Currently, the only efi= option we look for is 'nochunk', which
- * is intended to work around known issues on certain x86 UEFI
- * versions. So ignore for now on other architectures.
- */
- if (!IS_ENABLED(CONFIG_X86))
- return EFI_SUCCESS;
+ str = strstr(cmdline, "nokaslr");
+ if (str == cmdline || (str && str > cmdline && *(str - 1) == ' '))
+ __nokaslr = 1;
+
+ str = strstr(cmdline, "quiet");
+ if (str == cmdline || (str && str > cmdline && *(str - 1) == ' '))
+ __quiet = 1;
/*
* If no EFI parameters were specified on the cmdline we've got
* Remember, because efi= is also used by the kernel we need to
* skip over arguments we don't understand.
*/
- while (*str) {
+ while (*str && *str != ' ') {
if (!strncmp(str, "nochunk", 7)) {
str += strlen("nochunk");
__chunk_size = -1UL;
}
/* Group words together, delimited by "," */
- while (*str && *str != ',')
+ while (*str && *str != ' ' && *str != ',')
str++;
if (*str == ',')
#define EFI_ALLOC_ALIGN EFI_PAGE_SIZE
#endif
+extern int __pure nokaslr(void);
+extern int __pure is_quiet(void);
+
+#define pr_efi(sys_table, msg) do { \
+ if (!is_quiet()) efi_printk(sys_table, "EFI stub: "msg); \
+} while (0)
+
+#define pr_efi_err(sys_table, msg) efi_printk(sys_table, "EFI stub: ERROR: "msg)
+
void efi_char16_printk(efi_system_table_t *, efi_char16_t *);
efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, void *__image,
return update_fdt_memmap(p->new_fdt_addr, map);
}
+#ifndef MAX_FDT_SIZE
+#define MAX_FDT_SIZE SZ_2M
+#endif
+
/*
* Allocate memory for a new FDT, then add EFI, commandline, and
* initrd related fields to the FDT. This routine increases the
u32 desc_ver;
unsigned long mmap_key;
efi_memory_desc_t *memory_map, *runtime_map;
- unsigned long new_fdt_size;
efi_status_t status;
int runtime_entry_count = 0;
struct efi_boot_memmap map;
"Exiting boot services and installing virtual address map...\n");
map.map = &memory_map;
+ status = efi_high_alloc(sys_table, MAX_FDT_SIZE, EFI_FDT_ALIGN,
+ new_fdt_addr, max_addr);
+ if (status != EFI_SUCCESS) {
+ pr_efi_err(sys_table,
+ "Unable to allocate memory for new device tree.\n");
+ goto fail;
+ }
+
/*
- * Estimate size of new FDT, and allocate memory for it. We
- * will allocate a bigger buffer if this ends up being too
- * small, so a rough guess is OK here.
+ * Now that we have done our final memory allocation (and free)
+ * we can get the memory map key needed for exit_boot_services().
*/
- new_fdt_size = fdt_size + EFI_PAGE_SIZE;
- while (1) {
- status = efi_high_alloc(sys_table, new_fdt_size, EFI_FDT_ALIGN,
- new_fdt_addr, max_addr);
- if (status != EFI_SUCCESS) {
- pr_efi_err(sys_table, "Unable to allocate memory for new device tree.\n");
- goto fail;
- }
-
- status = update_fdt(sys_table,
- (void *)fdt_addr, fdt_size,
- (void *)*new_fdt_addr, new_fdt_size,
- cmdline_ptr, initrd_addr, initrd_size);
+ status = efi_get_memory_map(sys_table, &map);
+ if (status != EFI_SUCCESS)
+ goto fail_free_new_fdt;
- /* Succeeding the first time is the expected case. */
- if (status == EFI_SUCCESS)
- break;
+ status = update_fdt(sys_table, (void *)fdt_addr, fdt_size,
+ (void *)*new_fdt_addr, MAX_FDT_SIZE, cmdline_ptr,
+ initrd_addr, initrd_size);
- if (status == EFI_BUFFER_TOO_SMALL) {
- /*
- * We need to allocate more space for the new
- * device tree, so free existing buffer that is
- * too small.
- */
- efi_free(sys_table, new_fdt_size, *new_fdt_addr);
- new_fdt_size += EFI_PAGE_SIZE;
- } else {
- pr_efi_err(sys_table, "Unable to construct new device tree.\n");
- goto fail_free_new_fdt;
- }
+ if (status != EFI_SUCCESS) {
+ pr_efi_err(sys_table, "Unable to construct new device tree.\n");
+ goto fail_free_new_fdt;
}
priv.runtime_map = runtime_map;
pr_efi_err(sys_table, "Exit boot services failed.\n");
fail_free_new_fdt:
- efi_free(sys_table, new_fdt_size, *new_fdt_addr);
+ efi_free(sys_table, MAX_FDT_SIZE, *new_fdt_addr);
fail:
sys_table->boottime->free_pool(runtime_map);
status = __gop_query32(sys_table_arg, gop32, &info, &size,
¤t_fb_base);
- if (status == EFI_SUCCESS && (!first_gop || conout_found)) {
+ if (status == EFI_SUCCESS && (!first_gop || conout_found) &&
+ info->pixel_format != PIXEL_BLT_ONLY) {
/*
* Systems that use the UEFI Console Splitter may
* provide multiple GOP devices, not all of which are
status = __gop_query64(sys_table_arg, gop64, &info, &size,
¤t_fb_base);
- if (status == EFI_SUCCESS && (!first_gop || conout_found)) {
+ if (status == EFI_SUCCESS && (!first_gop || conout_found) &&
+ info->pixel_format != PIXEL_BLT_ONLY) {
/*
* Systems that use the UEFI Console Splitter may
* provide multiple GOP devices, not all of which are
#include <linux/efi.h>
#include <asm/efi.h>
+#include "efistub.h"
+
/* BIOS variables */
static const efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID;
static const efi_char16_t const efi_SecureBoot_name[] = {
if (!fence) {
event_free(gpu, event);
ret = -ENOMEM;
- goto out_pm_put;
+ goto out_unlock;
}
gpu->event[event].fence = fence;
hangcheck_timer_reset(gpu);
ret = 0;
+out_unlock:
mutex_unlock(&gpu->lock);
out_pm_put:
{
int ret;
- if (vgpu->failsafe)
- return 0;
-
if (WARN_ON(bytes > 4))
return -EINVAL;
_EL_OFFSET_STATUS_PTR);
ctx_status_ptr.dw = vgpu_vreg(vgpu, ctx_status_ptr_reg);
- ctx_status_ptr.read_ptr = ctx_status_ptr.write_ptr = 0x7;
+ ctx_status_ptr.read_ptr = 0;
+ ctx_status_ptr.write_ptr = 0x7;
vgpu_vreg(vgpu, ctx_status_ptr_reg) = ctx_status_ptr.dw;
}
struct gvt_firmware_header *h;
void *firmware;
void *p;
- unsigned long size;
+ unsigned long size, crc32_start;
int i;
int ret;
- size = sizeof(*h) + info->mmio_size + info->cfg_space_size - 1;
+ size = sizeof(*h) + info->mmio_size + info->cfg_space_size;
firmware = vzalloc(size);
if (!firmware)
return -ENOMEM;
memcpy(gvt->firmware.mmio, p, info->mmio_size);
+ crc32_start = offsetof(struct gvt_firmware_header, crc32) + 4;
+ h->crc32 = crc32_le(0, firmware + crc32_start, size - crc32_start);
+
firmware_attr.size = size;
firmware_attr.private = firmware;
firmware->mmio = mem;
- sprintf(path, "%s/vid_0x%04x_did_0x%04x_rid_0x%04x.golden_hw_state",
+ sprintf(path, "%s/vid_0x%04x_did_0x%04x_rid_0x%02x.golden_hw_state",
GVT_FIRMWARE_PATH, pdev->vendor, pdev->device,
pdev->revision);
.vgpu_create = intel_gvt_create_vgpu,
.vgpu_destroy = intel_gvt_destroy_vgpu,
.vgpu_reset = intel_gvt_reset_vgpu,
+ .vgpu_activate = intel_gvt_activate_vgpu,
+ .vgpu_deactivate = intel_gvt_deactivate_vgpu,
};
/**
void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
unsigned int engine_mask);
void intel_gvt_reset_vgpu(struct intel_vgpu *vgpu);
-
+void intel_gvt_activate_vgpu(struct intel_vgpu *vgpu);
+void intel_gvt_deactivate_vgpu(struct intel_vgpu *vgpu);
/* validating GM functions */
#define vgpu_gmadr_is_aperture(vgpu, gmadr) \
struct intel_vgpu_type *);
void (*vgpu_destroy)(struct intel_vgpu *);
void (*vgpu_reset)(struct intel_vgpu *);
+ void (*vgpu_activate)(struct intel_vgpu *);
+ void (*vgpu_deactivate)(struct intel_vgpu *);
};
if (ret)
goto undo_group;
+ intel_gvt_ops->vgpu_activate(vgpu);
+
atomic_set(&vgpu->vdev.released, 0);
return ret;
if (atomic_cmpxchg(&vgpu->vdev.released, 0, 1))
return;
+ intel_gvt_ops->vgpu_deactivate(vgpu);
+
ret = vfio_unregister_notifier(mdev_dev(vgpu->vdev.mdev), VFIO_IOMMU_NOTIFY,
&vgpu->vdev.iommu_notifier);
WARN(ret, "vfio_unregister_notifier for iommu failed: %d\n", ret);
static bool kvmgt_guest_exit(struct kvmgt_guest_info *info)
{
- struct intel_vgpu *vgpu = info->vgpu;
-
- if (!info) {
- gvt_vgpu_err("kvmgt_guest_info invalid\n");
- return false;
- }
-
kvm_page_track_unregister_notifier(info->kvm, &info->track_node);
kvm_put_kvm(info->kvm);
kvmgt_protect_table_destroy(info);
char *name;
} vgpu_types[] = {
/* Fixed vGPU type table */
- { MB_TO_BYTES(64), MB_TO_BYTES(512), 4, GVT_EDID_1024_768, "8" },
+ { MB_TO_BYTES(64), MB_TO_BYTES(384), 4, GVT_EDID_1024_768, "8" },
{ MB_TO_BYTES(128), MB_TO_BYTES(512), 4, GVT_EDID_1920_1200, "4" },
{ MB_TO_BYTES(256), MB_TO_BYTES(1024), 4, GVT_EDID_1920_1200, "2" },
{ MB_TO_BYTES(512), MB_TO_BYTES(2048), 4, GVT_EDID_1920_1200, "1" },
}
/**
- * intel_gvt_destroy_vgpu - destroy a virtual GPU
+ * intel_gvt_active_vgpu - activate a virtual GPU
* @vgpu: virtual GPU
*
- * This function is called when user wants to destroy a virtual GPU.
+ * This function is called when user wants to activate a virtual GPU.
*
*/
-void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu)
+void intel_gvt_activate_vgpu(struct intel_vgpu *vgpu)
+{
+ mutex_lock(&vgpu->gvt->lock);
+ vgpu->active = true;
+ mutex_unlock(&vgpu->gvt->lock);
+}
+
+/**
+ * intel_gvt_deactive_vgpu - deactivate a virtual GPU
+ * @vgpu: virtual GPU
+ *
+ * This function is called when user wants to deactivate a virtual GPU.
+ * All virtual GPU runtime information will be destroyed.
+ *
+ */
+void intel_gvt_deactivate_vgpu(struct intel_vgpu *vgpu)
{
struct intel_gvt *gvt = vgpu->gvt;
mutex_lock(&gvt->lock);
vgpu->active = false;
- idr_remove(&gvt->vgpu_idr, vgpu->id);
if (atomic_read(&vgpu->running_workload_num)) {
mutex_unlock(&gvt->lock);
}
intel_vgpu_stop_schedule(vgpu);
+
+ mutex_unlock(&gvt->lock);
+}
+
+/**
+ * intel_gvt_destroy_vgpu - destroy a virtual GPU
+ * @vgpu: virtual GPU
+ *
+ * This function is called when user wants to destroy a virtual GPU.
+ *
+ */
+void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu)
+{
+ struct intel_gvt *gvt = vgpu->gvt;
+
+ mutex_lock(&gvt->lock);
+
+ WARN(vgpu->active, "vGPU is still active!\n");
+
+ idr_remove(&gvt->vgpu_idr, vgpu->id);
intel_vgpu_clean_sched_policy(vgpu);
intel_vgpu_clean_gvt_context(vgpu);
intel_vgpu_clean_execlist(vgpu);
if (ret)
goto out_clean_shadow_ctx;
- vgpu->active = true;
mutex_unlock(&gvt->lock);
return vgpu;
goto out;
}
- intel_guc_suspend(dev_priv);
-
intel_display_suspend(dev);
intel_dp_mst_suspend(dev);
func(has_resource_streamer); \
func(has_runtime_pm); \
func(has_snoop); \
+ func(unfenced_needs_alignment); \
func(cursor_needs_physical); \
func(hws_needs_physical); \
func(overlay_needs_physical); \
i915_gem_context_lost(dev_priv);
mutex_unlock(&dev->struct_mutex);
+ intel_guc_suspend(dev_priv);
+
cancel_delayed_work_sync(&dev_priv->gpu_error.hangcheck_work);
cancel_delayed_work_sync(&dev_priv->gt.retire_work);
struct list_head ordered_vmas;
struct list_head pinned_vmas;
bool has_fenced_gpu_access = INTEL_GEN(engine->i915) < 4;
+ bool needs_unfenced_map = INTEL_INFO(engine->i915)->unfenced_needs_alignment;
int retry;
vm = list_first_entry(vmas, struct i915_vma, exec_list)->vm;
if (!has_fenced_gpu_access)
entry->flags &= ~EXEC_OBJECT_NEEDS_FENCE;
need_fence =
- entry->flags & EXEC_OBJECT_NEEDS_FENCE &&
+ (entry->flags & EXEC_OBJECT_NEEDS_FENCE ||
+ needs_unfenced_map) &&
i915_gem_object_is_tiled(obj);
need_mappable = need_fence || need_reloc_mappable(vma);
struct i915_ggtt *ggtt = &dev_priv->ggtt;
if (unlikely(ggtt->do_idle_maps)) {
- if (i915_gem_wait_for_idle(dev_priv, I915_WAIT_LOCKED)) {
+ if (i915_gem_wait_for_idle(dev_priv, 0)) {
DRM_ERROR("Failed to wait for idle; VT'd may hang.\n");
/* Wait a bit, in hopes it avoids the hang */
udelay(10);
static const char *i915_fence_get_timeline_name(struct dma_fence *fence)
{
+ /* The timeline struct (as part of the ppgtt underneath a context)
+ * may be freed when the request is no longer in use by the GPU.
+ * We could extend the life of a context to beyond that of all
+ * fences, possibly keeping the hw resource around indefinitely,
+ * or we just give them a false name. Since
+ * dma_fence_ops.get_timeline_name is a debug feature, the occasional
+ * lie seems justifiable.
+ */
+ if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
+ return "signaled";
+
return to_request(fence)->timeline->common->name;
}
BUG();
}
+static void i915_gem_shrinker_unlock(struct drm_device *dev, bool unlock)
+{
+ if (!unlock)
+ return;
+
+ mutex_unlock(&dev->struct_mutex);
+
+ /* expedite the RCU grace period to free some request slabs */
+ synchronize_rcu_expedited();
+}
+
static bool any_vma_pinned(struct drm_i915_gem_object *obj)
{
struct i915_vma *vma;
intel_runtime_pm_put(dev_priv);
i915_gem_retire_requests(dev_priv);
- if (unlock)
- mutex_unlock(&dev_priv->drm.struct_mutex);
- /* expedite the RCU grace period to free some request slabs */
- synchronize_rcu_expedited();
+ i915_gem_shrinker_unlock(&dev_priv->drm, unlock);
return count;
}
count += obj->base.size >> PAGE_SHIFT;
}
- if (unlock)
- mutex_unlock(&dev->struct_mutex);
+ i915_gem_shrinker_unlock(dev, unlock);
return count;
}
sc->nr_to_scan - freed,
I915_SHRINK_BOUND |
I915_SHRINK_UNBOUND);
- if (unlock)
- mutex_unlock(&dev->struct_mutex);
+
+ i915_gem_shrinker_unlock(dev, unlock);
return freed;
}
struct shrinker_lock_uninterruptible *slu)
{
dev_priv->mm.interruptible = slu->was_interruptible;
- if (slu->unlock)
- mutex_unlock(&dev_priv->drm.struct_mutex);
+ i915_gem_shrinker_unlock(&dev_priv->drm, slu->unlock);
}
static int
.has_overlay = 1, .overlay_needs_physical = 1, \
.has_gmch_display = 1, \
.hws_needs_physical = 1, \
+ .unfenced_needs_alignment = 1, \
.ring_mask = RENDER_RING, \
GEN_DEFAULT_PIPEOFFSETS, \
CURSOR_OFFSETS
.platform = INTEL_I915G, .cursor_needs_physical = 1,
.has_overlay = 1, .overlay_needs_physical = 1,
.hws_needs_physical = 1,
+ .unfenced_needs_alignment = 1,
};
static const struct intel_device_info intel_i915gm_info = {
.supports_tv = 1,
.has_fbc = 1,
.hws_needs_physical = 1,
+ .unfenced_needs_alignment = 1,
};
static const struct intel_device_info intel_i945g_info = {
.has_hotplug = 1, .cursor_needs_physical = 1,
.has_overlay = 1, .overlay_needs_physical = 1,
.hws_needs_physical = 1,
+ .unfenced_needs_alignment = 1,
};
static const struct intel_device_info intel_i945gm_info = {
.supports_tv = 1,
.has_fbc = 1,
.hws_needs_physical = 1,
+ .unfenced_needs_alignment = 1,
};
static const struct intel_device_info intel_g33_info = {
*/
if (WARN_ON(stream->sample_flags != props->sample_flags)) {
ret = -ENODEV;
- goto err_alloc;
+ goto err_flags;
}
list_add(&stream->link, &dev_priv->perf.streams);
err_open:
list_del(&stream->link);
+err_flags:
if (stream->ops->destroy)
stream->ops->destroy(stream);
err_alloc:
if (ret)
return ret;
+ if (id == 0 || id >= DRM_I915_PERF_PROP_MAX) {
+ DRM_DEBUG("Unknown i915 perf property ID\n");
+ return -EINVAL;
+ }
+
switch ((enum drm_i915_perf_property_id)id) {
case DRM_I915_PERF_PROP_CTX_HANDLE:
props->single_context = 1;
props->oa_periodic = true;
props->oa_period_exponent = value;
break;
- default:
+ case DRM_I915_PERF_PROP_MAX:
MISSING_CASE(id);
- DRM_DEBUG("Unknown i915 perf property ID\n");
return -EINVAL;
}
static struct intel_engine_cs *
pt_lock_engine(struct i915_priotree *pt, struct intel_engine_cs *locked)
{
- struct intel_engine_cs *engine;
+ struct intel_engine_cs *engine =
+ container_of(pt, struct drm_i915_gem_request, priotree)->engine;
+
+ GEM_BUG_ON(!locked);
- engine = container_of(pt,
- struct drm_i915_gem_request,
- priotree)->engine;
if (engine != locked) {
- if (locked)
- spin_unlock_irq(&locked->timeline->lock);
- spin_lock_irq(&engine->timeline->lock);
+ spin_unlock(&locked->timeline->lock);
+ spin_lock(&engine->timeline->lock);
}
return engine;
static void execlists_schedule(struct drm_i915_gem_request *request, int prio)
{
- struct intel_engine_cs *engine = NULL;
+ struct intel_engine_cs *engine;
struct i915_dependency *dep, *p;
struct i915_dependency stack;
LIST_HEAD(dfs);
list_for_each_entry_safe(dep, p, &dfs, dfs_link) {
struct i915_priotree *pt = dep->signaler;
- list_for_each_entry(p, &pt->signalers_list, signal_link)
+ /* Within an engine, there can be no cycle, but we may
+ * refer to the same dependency chain multiple times
+ * (redundant dependencies are not eliminated) and across
+ * engines.
+ */
+ list_for_each_entry(p, &pt->signalers_list, signal_link) {
+ GEM_BUG_ON(p->signaler->priority < pt->priority);
if (prio > READ_ONCE(p->signaler->priority))
list_move_tail(&p->dfs_link, &dfs);
+ }
list_safe_reset_next(dep, p, dfs_link);
- if (!RB_EMPTY_NODE(&pt->node))
- continue;
-
- engine = pt_lock_engine(pt, engine);
-
- /* If it is not already in the rbtree, we can update the
- * priority inplace and skip over it (and its dependencies)
- * if it is referenced *again* as we descend the dfs.
- */
- if (prio > pt->priority && RB_EMPTY_NODE(&pt->node)) {
- pt->priority = prio;
- list_del_init(&dep->dfs_link);
- }
}
+ engine = request->engine;
+ spin_lock_irq(&engine->timeline->lock);
+
/* Fifo and depth-first replacement ensure our deps execute before us */
list_for_each_entry_safe_reverse(dep, p, &dfs, dfs_link) {
struct i915_priotree *pt = dep->signaler;
if (prio <= pt->priority)
continue;
- GEM_BUG_ON(RB_EMPTY_NODE(&pt->node));
-
pt->priority = prio;
- rb_erase(&pt->node, &engine->execlist_queue);
- if (insert_request(pt, &engine->execlist_queue))
- engine->execlist_first = &pt->node;
+ if (!RB_EMPTY_NODE(&pt->node)) {
+ rb_erase(&pt->node, &engine->execlist_queue);
+ if (insert_request(pt, &engine->execlist_queue))
+ engine->execlist_first = &pt->node;
+ }
}
- if (engine)
- spin_unlock_irq(&engine->timeline->lock);
+ spin_unlock_irq(&engine->timeline->lock);
/* XXX Do we need to preempt to make room for us and our deps? */
}
GEM_BUG_ON(request->ctx != port[0].request->ctx);
/* Reset WaIdleLiteRestore:bdw,skl as well */
- request->tail = request->wa_tail - WA_TAIL_DWORDS * sizeof(u32);
+ request->tail =
+ intel_ring_wrap(request->ring,
+ request->wa_tail - WA_TAIL_DWORDS*sizeof(u32));
}
static int intel_logical_ring_emit_pdps(struct drm_i915_gem_request *req)
*/
}
+static inline u32
+intel_ring_wrap(const struct intel_ring *ring, u32 pos)
+{
+ return pos & (ring->size - 1);
+}
+
static inline u32 intel_ring_offset(struct intel_ring *ring, void *addr)
{
/* Don't write ring->size (equivalent to 0) as that hangs some GPUs. */
u32 offset = addr - ring->vaddr;
- return offset & (ring->size - 1);
+ return intel_ring_wrap(ring, offset);
}
int __intel_ring_space(int head, int tail, int size);
{
struct nv50_wndw_atom *asyw = nv50_wndw_atom(state);
__drm_atomic_helper_plane_destroy_state(&asyw->state);
- dma_fence_put(asyw->state.fence);
kfree(asyw);
}
if (!(asyw = kmalloc(sizeof(*asyw), GFP_KERNEL)))
return NULL;
__drm_atomic_helper_plane_duplicate_state(plane, &asyw->state);
- asyw->state.fence = NULL;
asyw->interval = 1;
asyw->sema = armw->sema;
asyw->ntfy = armw->ntfy;
u32 vbackp = (mode->vtotal - mode->vsync_end) * vscan / ilace;
u32 hfrontp = mode->hsync_start - mode->hdisplay;
u32 vfrontp = (mode->vsync_start - mode->vdisplay) * vscan / ilace;
+ u32 blankus;
struct nv50_head_mode *m = &asyh->mode;
m->h.active = mode->htotal;
m->v.blanks = m->v.active - vfrontp - 1;
/*XXX: Safe underestimate, even "0" works */
- m->v.blankus = (m->v.active - mode->vdisplay - 2) * m->h.active;
- m->v.blankus *= 1000;
- m->v.blankus /= mode->clock;
+ blankus = (m->v.active - mode->vdisplay - 2) * m->h.active;
+ blankus *= 1000;
+ blankus /= mode->clock;
+ m->v.blankus = blankus;
if (mode->flags & DRM_MODE_FLAG_INTERLACE) {
m->v.blank2e = m->v.active + m->v.synce + vbackp;
.i2c = nv04_i2c_new,
.imem = nv40_instmem_new,
.mc = nv44_mc_new,
- .mmu = nv44_mmu_new,
+ .mmu = nv04_mmu_new,
.pci = nv40_pci_new,
.therm = nv40_therm_new,
.timer = nv41_timer_new,
.fifo = gp100_fifo_new,
};
+static const struct nvkm_device_chip
+nv137_chipset = {
+ .name = "GP107",
+ .bar = gf100_bar_new,
+ .bios = nvkm_bios_new,
+ .bus = gf100_bus_new,
+ .devinit = gm200_devinit_new,
+ .fb = gp102_fb_new,
+ .fuse = gm107_fuse_new,
+ .gpio = gk104_gpio_new,
+ .i2c = gm200_i2c_new,
+ .ibus = gm200_ibus_new,
+ .imem = nv50_instmem_new,
+ .ltc = gp100_ltc_new,
+ .mc = gp100_mc_new,
+ .mmu = gf100_mmu_new,
+ .pci = gp100_pci_new,
+ .pmu = gp102_pmu_new,
+ .timer = gk20a_timer_new,
+ .top = gk104_top_new,
+ .ce[0] = gp102_ce_new,
+ .ce[1] = gp102_ce_new,
+ .ce[2] = gp102_ce_new,
+ .ce[3] = gp102_ce_new,
+ .disp = gp102_disp_new,
+ .dma = gf119_dma_new,
+ .fifo = gp100_fifo_new,
+};
+
static int
nvkm_device_event_ctor(struct nvkm_object *object, void *data, u32 size,
struct nvkm_notify *notify)
case 0x132: device->chip = &nv132_chipset; break;
case 0x134: device->chip = &nv134_chipset; break;
case 0x136: device->chip = &nv136_chipset; break;
+ case 0x137: device->chip = &nv137_chipset; break;
default:
nvdev_error(device, "unknown chipset (%08x)\n", boot0);
goto done;
}
if (type == 0x00000010) {
- if (!nv31_mpeg_mthd(mpeg, mthd, data))
+ if (nv31_mpeg_mthd(mpeg, mthd, data))
show &= ~0x01000000;
}
}
}
if (type == 0x00000010) {
- if (!nv44_mpeg_mthd(subdev->device, mthd, data))
+ if (nv44_mpeg_mthd(subdev->device, mthd, data))
show &= ~0x01000000;
}
}
#include <linux/slab.h>
#include <linux/fb.h>
#include <linux/prefetch.h>
+#include <asm/unaligned.h>
#include <drm/drmP.h>
#include "udl_drv.h"
const u8 *const start = pixel;
const uint16_t repeating_pixel_val16 = pixel_val16;
- *(uint16_t *)cmd = cpu_to_be16(pixel_val16);
+ put_unaligned_be16(pixel_val16, cmd);
cmd += 2;
pixel += bpp;
hid->group = HID_GROUP_WACOM;
break;
case USB_VENDOR_ID_SYNAPTICS:
- if (hid->group == HID_GROUP_GENERIC ||
- hid->group == HID_GROUP_MULTITOUCH_WIN_8)
+ if (hid->group == HID_GROUP_GENERIC)
if ((parser->scan_flags & HID_SCAN_FLAG_VENDOR_SPECIFIC)
&& (parser->scan_flags & HID_SCAN_FLAG_GD_POINTER))
/*
{ HID_USB_DEVICE(USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UGEE_TABLET_45) },
{ HID_USB_DEVICE(USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UCLOGIC_DRAWIMAGE_G3) },
{ HID_USB_DEVICE(USB_VENDOR_ID_UGTIZER, USB_DEVICE_ID_UGTIZER_TABLET_GP0610) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_TABLET_EX07S) },
{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP, USB_DEVICE_ID_SMARTJOY_PLUS) },
{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP, USB_DEVICE_ID_SUPER_JOY_BOX_3) },
{ HID_USB_DEVICE(USB_VENDOR_ID_WISEGROUP, USB_DEVICE_ID_DUAL_USB_JOYPAD) },
#define USB_DEVICE_ID_UGEE_TABLET_45 0x0045
#define USB_DEVICE_ID_YIYNOVA_TABLET 0x004d
+#define USB_VENDOR_ID_UGEE 0x28bd
+#define USB_DEVICE_ID_UGEE_TABLET_EX07S 0x0071
+
#define USB_VENDOR_ID_UNITEC 0x227d
#define USB_DEVICE_ID_UNITEC_USB_TOUCH_0709 0x0709
#define USB_DEVICE_ID_UNITEC_USB_TOUCH_0A19 0x0a19
}
break;
case USB_DEVICE_ID_UGTIZER_TABLET_GP0610:
+ case USB_DEVICE_ID_UGEE_TABLET_EX07S:
/* If this is the pen interface */
if (intf->cur_altsetting->desc.bInterfaceNumber == 1) {
rc = uclogic_tablet_enable(hdev);
{ HID_USB_DEVICE(USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UGEE_TABLET_45) },
{ HID_USB_DEVICE(USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_UCLOGIC_DRAWIMAGE_G3) },
{ HID_USB_DEVICE(USB_VENDOR_ID_UGTIZER, USB_DEVICE_ID_UGTIZER_TABLET_GP0610) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_TABLET_EX07S) },
{ }
};
MODULE_DEVICE_TABLE(hid, uclogic_devices);
return;
case HID_DG_TOOLSERIALNUMBER:
wacom_wac->serial[0] = (wacom_wac->serial[0] & ~0xFFFFFFFFULL);
- wacom_wac->serial[0] |= value;
+ wacom_wac->serial[0] |= (__u32)value;
return;
case WACOM_HID_WD_SENSE:
wacom_wac->hid_data.sense_state = value;
wacom_wac->hid_data.cc_index = field->index;
wacom_wac->hid_data.cc_value_index = usage->usage_index;
break;
+ case HID_DG_CONTACTID:
+ if ((field->logical_maximum - field->logical_minimum) < touch_max) {
+ /*
+ * The HID descriptor for G11 sensors leaves logical
+ * maximum set to '1' despite it being a multitouch
+ * device. Override to a sensible number.
+ */
+ field->logical_maximum = 255;
+ }
+ break;
}
}
goto drop;
/* Pad to 32-bits - FIXME: Revisit*/
if ((skb->len & 3) && skb_pad(skb, 4 - (skb->len & 3)))
- goto drop;
+ goto inc_dropped;
/*
* Modem sends Phonet messages over SSI with its own endianess...
drop2:
hsi_free_msg(msg);
drop:
- dev->stats.tx_dropped++;
dev_kfree_skb(skb);
+inc_dropped:
+ dev->stats.tx_dropped++;
return 0;
}
This driver can also be built as a module. If so, the module
will be called asb100.
+config SENSORS_ASPEED
+ tristate "ASPEED AST2400/AST2500 PWM and Fan tach driver"
+ help
+ This driver provides support for ASPEED AST2400/AST2500 PWM
+ and Fan Tacho controllers.
+
+ This driver can also be built as a module. If so, the module
+ will be called aspeed_pwm_tacho.
+
config SENSORS_ATXP1
tristate "Attansic ATXP1 VID controller"
depends on I2C
This driver can also be built as a module. If so, the module
will be called tmp421.
-config SENSORS_TWL4030_MADC
- tristate "Texas Instruments TWL4030 MADC Hwmon"
- depends on TWL4030_MADC
- help
- If you say yes here you get hwmon support for triton
- TWL4030-MADC.
-
- This driver can also be built as a module. If so it will be called
- twl4030-madc-hwmon.
-
config SENSORS_VEXPRESS
tristate "Versatile Express"
depends on VEXPRESS_CONFIG
obj-$(CONFIG_SENSORS_APPLESMC) += applesmc.o
obj-$(CONFIG_SENSORS_ARM_SCPI) += scpi-hwmon.o
obj-$(CONFIG_SENSORS_ASC7621) += asc7621.o
+obj-$(CONFIG_SENSORS_ASPEED) += aspeed-pwm-tacho.o
obj-$(CONFIG_SENSORS_ATXP1) += atxp1.o
obj-$(CONFIG_SENSORS_CORETEMP) += coretemp.o
obj-$(CONFIG_SENSORS_DA9052_ADC)+= da9052-hwmon.o
obj-$(CONFIG_SENSORS_TMP108) += tmp108.o
obj-$(CONFIG_SENSORS_TMP401) += tmp401.o
obj-$(CONFIG_SENSORS_TMP421) += tmp421.o
-obj-$(CONFIG_SENSORS_TWL4030_MADC)+= twl4030-madc-hwmon.o
obj-$(CONFIG_SENSORS_VEXPRESS) += vexpress-hwmon.o
obj-$(CONFIG_SENSORS_VIA_CPUTEMP)+= via-cputemp.o
obj-$(CONFIG_SENSORS_VIA686A) += via686a.o
};
MODULE_DEVICE_TABLE(i2c, ad7414_id);
+static const struct of_device_id ad7414_of_match[] = {
+ { .compatible = "ad,ad7414" },
+ { },
+};
+MODULE_DEVICE_TABLE(of, ad7414_of_match);
+
static struct i2c_driver ad7414_driver = {
.driver = {
.name = "ad7414",
+ .of_match_table = of_match_ptr(ad7414_of_match),
},
.probe = ad7414_probe,
.id_table = ad7414_id,
};
MODULE_DEVICE_TABLE(i2c, adc128_id);
+static const struct of_device_id adc128_of_match[] = {
+ { .compatible = "ti,adc128d818" },
+ { },
+};
+MODULE_DEVICE_TABLE(of, adc128_of_match);
+
static struct i2c_driver adc128_driver = {
.class = I2C_CLASS_HWMON,
.driver = {
.name = "adc128d818",
+ .of_match_table = of_match_ptr(adc128_of_match),
},
.probe = adc128_probe,
.remove = adc128_remove,
#include <linux/hwmon-sysfs.h>
#include <linux/err.h>
#include <linux/mutex.h>
+#include <linux/of_device.h>
#include <linux/of.h>
#include <linux/i2c/ads1015.h>
GFP_KERNEL);
if (!data)
return -ENOMEM;
- data->id = id->driver_data;
+
+ if (client->dev.of_node)
+ data->id = (enum ads1015_chips)
+ of_device_get_match_data(&client->dev);
+ else
+ data->id = id->driver_data;
i2c_set_clientdata(client, data);
mutex_init(&data->update_lock);
};
MODULE_DEVICE_TABLE(i2c, ads1015_id);
+static const struct of_device_id ads1015_of_match[] = {
+ {
+ .compatible = "ti,ads1015",
+ .data = (void *)ads1015
+ },
+ {
+ .compatible = "ti,ads1115",
+ .data = (void *)ads1115
+ },
+ { },
+};
+MODULE_DEVICE_TABLE(of, ads1015_of_match);
+
static struct i2c_driver ads1015_driver = {
.driver = {
.name = "ads1015",
+ .of_match_table = of_match_ptr(ads1015_of_match),
},
.probe = ads1015_probe,
.remove = ads1015_remove,
#include <linux/i2c.h>
#include <linux/init.h>
#include <linux/module.h>
+#include <linux/of_device.h>
#include <linux/platform_data/ads7828.h>
#include <linux/regmap.h>
#include <linux/slab.h>
+#include <linux/regulator/consumer.h>
/* The ADS7828 registers */
#define ADS7828_CMD_SD_SE 0x80 /* Single ended inputs */
struct ads7828_data *data;
struct device *hwmon_dev;
unsigned int vref_mv = ADS7828_INT_VREF_MV;
+ unsigned int vref_uv;
bool diff_input = false;
bool ext_vref = false;
unsigned int regval;
+ enum ads7828_chips chip;
+ struct regulator *reg;
data = devm_kzalloc(dev, sizeof(struct ads7828_data), GFP_KERNEL);
if (!data)
ext_vref = pdata->ext_vref;
if (ext_vref && pdata->vref_mv)
vref_mv = pdata->vref_mv;
+ } else if (dev->of_node) {
+ diff_input = of_property_read_bool(dev->of_node,
+ "ti,differential-input");
+ reg = devm_regulator_get_optional(dev, "vref");
+ if (!IS_ERR(reg)) {
+ vref_uv = regulator_get_voltage(reg);
+ vref_mv = DIV_ROUND_CLOSEST(vref_uv, 1000);
+ if (vref_mv < ADS7828_EXT_VREF_MV_MIN ||
+ vref_mv > ADS7828_EXT_VREF_MV_MAX)
+ return -EINVAL;
+ ext_vref = true;
+ }
}
+ if (client->dev.of_node)
+ chip = (enum ads7828_chips)
+ of_device_get_match_data(&client->dev);
+ else
+ chip = id->driver_data;
+
/* Bound Vref with min/max values */
vref_mv = clamp_val(vref_mv, ADS7828_EXT_VREF_MV_MIN,
ADS7828_EXT_VREF_MV_MAX);
/* ADS7828 uses 12-bit samples, while ADS7830 is 8-bit */
- if (id->driver_data == ads7828) {
+ if (chip == ads7828) {
data->lsb_resol = DIV_ROUND_CLOSEST(vref_mv * 1000, 4096);
data->regmap = devm_regmap_init_i2c(client,
&ads2828_regmap_config);
};
MODULE_DEVICE_TABLE(i2c, ads7828_device_ids);
+static const struct of_device_id ads7828_of_match[] = {
+ {
+ .compatible = "ti,ads7828",
+ .data = (void *)ads7828
+ },
+ {
+ .compatible = "ti,ads7830",
+ .data = (void *)ads7830
+ },
+ { },
+};
+MODULE_DEVICE_TABLE(of, ads7828_of_match);
+
static struct i2c_driver ads7828_driver = {
.driver = {
.name = "ads7828",
+ .of_match_table = of_match_ptr(ads7828_of_match),
},
.id_table = ads7828_device_ids,
*/
#include <linux/module.h>
+#include <linux/of_device.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/i2c.h>
#define REG_VENDID 0x3E
#define REG_DEVID2 0x3F
+#define REG_CONFIG1 0x40
+
#define REG_STATUS1 0x41
#define REG_STATUS2 0x42
};
MODULE_DEVICE_TABLE(i2c, adt7475_id);
+static const struct of_device_id adt7475_of_match[] = {
+ {
+ .compatible = "adi,adt7473",
+ .data = (void *)adt7473
+ },
+ {
+ .compatible = "adi,adt7475",
+ .data = (void *)adt7475
+ },
+ {
+ .compatible = "adi,adt7476",
+ .data = (void *)adt7476
+ },
+ {
+ .compatible = "adi,adt7490",
+ .data = (void *)adt7490
+ },
+ { },
+};
+MODULE_DEVICE_TABLE(of, adt7475_of_match);
+
struct adt7475_data {
struct device *hwmon_dev;
struct mutex lock;
static int adt7475_probe(struct i2c_client *client,
const struct i2c_device_id *id)
{
+ enum chips chip;
static const char * const names[] = {
[adt7473] = "ADT7473",
[adt7475] = "ADT7475",
mutex_init(&data->lock);
i2c_set_clientdata(client, data);
+ if (client->dev.of_node)
+ chip = (enum chips)of_device_get_match_data(&client->dev);
+ else
+ chip = id->driver_data;
+
/* Initialize device-specific values */
- switch (id->driver_data) {
+ switch (chip) {
case adt7476:
data->has_voltage = 0x0e; /* in1 to in3 */
revision = adt7475_read(REG_DEVID2) & 0x07;
for (i = 0; i < ADT7475_PWM_COUNT; i++)
adt7475_read_pwm(client, i);
+ /* Start monitoring */
+ switch (chip) {
+ case adt7475:
+ case adt7476:
+ i2c_smbus_write_byte_data(client, REG_CONFIG1,
+ adt7475_read(REG_CONFIG1) | 0x01);
+ break;
+ default:
+ break;
+ }
+
ret = sysfs_create_group(&client->dev.kobj, &adt7475_attr_group);
if (ret)
return ret;
.class = I2C_CLASS_HWMON,
.driver = {
.name = "adt7475",
+ .of_match_table = of_match_ptr(adt7475_of_match),
},
.probe = adt7475_probe,
.remove = adt7475_remove,
--- /dev/null
+/*
+ * Copyright (c) 2016 Google, Inc
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 or later as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/clk.h>
+#include <linux/gpio/consumer.h>
+#include <linux/delay.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/sysfs.h>
+#include <linux/regmap.h>
+
+/* ASPEED PWM & FAN Tach Register Definition */
+#define ASPEED_PTCR_CTRL 0x00
+#define ASPEED_PTCR_CLK_CTRL 0x04
+#define ASPEED_PTCR_DUTY0_CTRL 0x08
+#define ASPEED_PTCR_DUTY1_CTRL 0x0c
+#define ASPEED_PTCR_TYPEM_CTRL 0x10
+#define ASPEED_PTCR_TYPEM_CTRL1 0x14
+#define ASPEED_PTCR_TYPEN_CTRL 0x18
+#define ASPEED_PTCR_TYPEN_CTRL1 0x1c
+#define ASPEED_PTCR_TACH_SOURCE 0x20
+#define ASPEED_PTCR_TRIGGER 0x28
+#define ASPEED_PTCR_RESULT 0x2c
+#define ASPEED_PTCR_INTR_CTRL 0x30
+#define ASPEED_PTCR_INTR_STS 0x34
+#define ASPEED_PTCR_TYPEM_LIMIT 0x38
+#define ASPEED_PTCR_TYPEN_LIMIT 0x3C
+#define ASPEED_PTCR_CTRL_EXT 0x40
+#define ASPEED_PTCR_CLK_CTRL_EXT 0x44
+#define ASPEED_PTCR_DUTY2_CTRL 0x48
+#define ASPEED_PTCR_DUTY3_CTRL 0x4c
+#define ASPEED_PTCR_TYPEO_CTRL 0x50
+#define ASPEED_PTCR_TYPEO_CTRL1 0x54
+#define ASPEED_PTCR_TACH_SOURCE_EXT 0x60
+#define ASPEED_PTCR_TYPEO_LIMIT 0x78
+
+/* ASPEED_PTCR_CTRL : 0x00 - General Control Register */
+#define ASPEED_PTCR_CTRL_SET_PWMD_TYPE_PART1 15
+#define ASPEED_PTCR_CTRL_SET_PWMD_TYPE_PART2 6
+#define ASPEED_PTCR_CTRL_SET_PWMD_TYPE_MASK (BIT(7) | BIT(15))
+
+#define ASPEED_PTCR_CTRL_SET_PWMC_TYPE_PART1 14
+#define ASPEED_PTCR_CTRL_SET_PWMC_TYPE_PART2 5
+#define ASPEED_PTCR_CTRL_SET_PWMC_TYPE_MASK (BIT(6) | BIT(14))
+
+#define ASPEED_PTCR_CTRL_SET_PWMB_TYPE_PART1 13
+#define ASPEED_PTCR_CTRL_SET_PWMB_TYPE_PART2 4
+#define ASPEED_PTCR_CTRL_SET_PWMB_TYPE_MASK (BIT(5) | BIT(13))
+
+#define ASPEED_PTCR_CTRL_SET_PWMA_TYPE_PART1 12
+#define ASPEED_PTCR_CTRL_SET_PWMA_TYPE_PART2 3
+#define ASPEED_PTCR_CTRL_SET_PWMA_TYPE_MASK (BIT(4) | BIT(12))
+
+#define ASPEED_PTCR_CTRL_FAN_NUM_EN(x) BIT(16 + (x))
+
+#define ASPEED_PTCR_CTRL_PWMD_EN BIT(11)
+#define ASPEED_PTCR_CTRL_PWMC_EN BIT(10)
+#define ASPEED_PTCR_CTRL_PWMB_EN BIT(9)
+#define ASPEED_PTCR_CTRL_PWMA_EN BIT(8)
+
+#define ASPEED_PTCR_CTRL_CLK_SRC BIT(1)
+#define ASPEED_PTCR_CTRL_CLK_EN BIT(0)
+
+/* ASPEED_PTCR_CLK_CTRL : 0x04 - Clock Control Register */
+/* TYPE N */
+#define ASPEED_PTCR_CLK_CTRL_TYPEN_MASK GENMASK(31, 16)
+#define ASPEED_PTCR_CLK_CTRL_TYPEN_UNIT 24
+#define ASPEED_PTCR_CLK_CTRL_TYPEN_H 20
+#define ASPEED_PTCR_CLK_CTRL_TYPEN_L 16
+/* TYPE M */
+#define ASPEED_PTCR_CLK_CTRL_TYPEM_MASK GENMASK(15, 0)
+#define ASPEED_PTCR_CLK_CTRL_TYPEM_UNIT 8
+#define ASPEED_PTCR_CLK_CTRL_TYPEM_H 4
+#define ASPEED_PTCR_CLK_CTRL_TYPEM_L 0
+
+/*
+ * ASPEED_PTCR_DUTY_CTRL/1/2/3 : 0x08/0x0C/0x48/0x4C - PWM-FAN duty control
+ * 0/1/2/3 register
+ */
+#define DUTY_CTRL_PWM2_FALL_POINT 24
+#define DUTY_CTRL_PWM2_RISE_POINT 16
+#define DUTY_CTRL_PWM2_RISE_FALL_MASK GENMASK(31, 16)
+#define DUTY_CTRL_PWM1_FALL_POINT 8
+#define DUTY_CTRL_PWM1_RISE_POINT 0
+#define DUTY_CTRL_PWM1_RISE_FALL_MASK GENMASK(15, 0)
+
+/* ASPEED_PTCR_TYPEM_CTRL : 0x10/0x18/0x50 - Type M/N/O Ctrl 0 Register */
+#define TYPE_CTRL_FAN_MASK (GENMASK(5, 1) | GENMASK(31, 16))
+#define TYPE_CTRL_FAN1_MASK GENMASK(31, 0)
+#define TYPE_CTRL_FAN_PERIOD 16
+#define TYPE_CTRL_FAN_MODE 4
+#define TYPE_CTRL_FAN_DIVISION 1
+#define TYPE_CTRL_FAN_TYPE_EN 1
+
+/* ASPEED_PTCR_TACH_SOURCE : 0x20/0x60 - Tach Source Register */
+/* bit [0,1] at 0x20, bit [2] at 0x60 */
+#define TACH_PWM_SOURCE_BIT01(x) ((x) * 2)
+#define TACH_PWM_SOURCE_BIT2(x) ((x) * 2)
+#define TACH_PWM_SOURCE_MASK_BIT01(x) (0x3 << ((x) * 2))
+#define TACH_PWM_SOURCE_MASK_BIT2(x) BIT((x) * 2)
+
+/* ASPEED_PTCR_RESULT : 0x2c - Result Register */
+#define RESULT_STATUS_MASK BIT(31)
+#define RESULT_VALUE_MASK 0xfffff
+
+/* ASPEED_PTCR_CTRL_EXT : 0x40 - General Control Extension #1 Register */
+#define ASPEED_PTCR_CTRL_SET_PWMH_TYPE_PART1 15
+#define ASPEED_PTCR_CTRL_SET_PWMH_TYPE_PART2 6
+#define ASPEED_PTCR_CTRL_SET_PWMH_TYPE_MASK (BIT(7) | BIT(15))
+
+#define ASPEED_PTCR_CTRL_SET_PWMG_TYPE_PART1 14
+#define ASPEED_PTCR_CTRL_SET_PWMG_TYPE_PART2 5
+#define ASPEED_PTCR_CTRL_SET_PWMG_TYPE_MASK (BIT(6) | BIT(14))
+
+#define ASPEED_PTCR_CTRL_SET_PWMF_TYPE_PART1 13
+#define ASPEED_PTCR_CTRL_SET_PWMF_TYPE_PART2 4
+#define ASPEED_PTCR_CTRL_SET_PWMF_TYPE_MASK (BIT(5) | BIT(13))
+
+#define ASPEED_PTCR_CTRL_SET_PWME_TYPE_PART1 12
+#define ASPEED_PTCR_CTRL_SET_PWME_TYPE_PART2 3
+#define ASPEED_PTCR_CTRL_SET_PWME_TYPE_MASK (BIT(4) | BIT(12))
+
+#define ASPEED_PTCR_CTRL_PWMH_EN BIT(11)
+#define ASPEED_PTCR_CTRL_PWMG_EN BIT(10)
+#define ASPEED_PTCR_CTRL_PWMF_EN BIT(9)
+#define ASPEED_PTCR_CTRL_PWME_EN BIT(8)
+
+/* ASPEED_PTCR_CLK_EXT_CTRL : 0x44 - Clock Control Extension #1 Register */
+/* TYPE O */
+#define ASPEED_PTCR_CLK_CTRL_TYPEO_MASK GENMASK(15, 0)
+#define ASPEED_PTCR_CLK_CTRL_TYPEO_UNIT 8
+#define ASPEED_PTCR_CLK_CTRL_TYPEO_H 4
+#define ASPEED_PTCR_CLK_CTRL_TYPEO_L 0
+
+#define PWM_MAX 255
+
+#define M_PWM_DIV_H 0x00
+#define M_PWM_DIV_L 0x05
+#define M_PWM_PERIOD 0x5F
+#define M_TACH_CLK_DIV 0x00
+#define M_TACH_MODE 0x00
+#define M_TACH_UNIT 0x1000
+#define INIT_FAN_CTRL 0xFF
+
+struct aspeed_pwm_tacho_data {
+ struct regmap *regmap;
+ unsigned long clk_freq;
+ bool pwm_present[8];
+ bool fan_tach_present[16];
+ u8 type_pwm_clock_unit[3];
+ u8 type_pwm_clock_division_h[3];
+ u8 type_pwm_clock_division_l[3];
+ u8 type_fan_tach_clock_division[3];
+ u16 type_fan_tach_unit[3];
+ u8 pwm_port_type[8];
+ u8 pwm_port_fan_ctrl[8];
+ u8 fan_tach_ch_source[16];
+ const struct attribute_group *groups[3];
+};
+
+enum type { TYPEM, TYPEN, TYPEO };
+
+struct type_params {
+ u32 l_value;
+ u32 h_value;
+ u32 unit_value;
+ u32 clk_ctrl_mask;
+ u32 clk_ctrl_reg;
+ u32 ctrl_reg;
+ u32 ctrl_reg1;
+};
+
+static const struct type_params type_params[] = {
+ [TYPEM] = {
+ .l_value = ASPEED_PTCR_CLK_CTRL_TYPEM_L,
+ .h_value = ASPEED_PTCR_CLK_CTRL_TYPEM_H,
+ .unit_value = ASPEED_PTCR_CLK_CTRL_TYPEM_UNIT,
+ .clk_ctrl_mask = ASPEED_PTCR_CLK_CTRL_TYPEM_MASK,
+ .clk_ctrl_reg = ASPEED_PTCR_CLK_CTRL,
+ .ctrl_reg = ASPEED_PTCR_TYPEM_CTRL,
+ .ctrl_reg1 = ASPEED_PTCR_TYPEM_CTRL1,
+ },
+ [TYPEN] = {
+ .l_value = ASPEED_PTCR_CLK_CTRL_TYPEN_L,
+ .h_value = ASPEED_PTCR_CLK_CTRL_TYPEN_H,
+ .unit_value = ASPEED_PTCR_CLK_CTRL_TYPEN_UNIT,
+ .clk_ctrl_mask = ASPEED_PTCR_CLK_CTRL_TYPEN_MASK,
+ .clk_ctrl_reg = ASPEED_PTCR_CLK_CTRL,
+ .ctrl_reg = ASPEED_PTCR_TYPEN_CTRL,
+ .ctrl_reg1 = ASPEED_PTCR_TYPEN_CTRL1,
+ },
+ [TYPEO] = {
+ .l_value = ASPEED_PTCR_CLK_CTRL_TYPEO_L,
+ .h_value = ASPEED_PTCR_CLK_CTRL_TYPEO_H,
+ .unit_value = ASPEED_PTCR_CLK_CTRL_TYPEO_UNIT,
+ .clk_ctrl_mask = ASPEED_PTCR_CLK_CTRL_TYPEO_MASK,
+ .clk_ctrl_reg = ASPEED_PTCR_CLK_CTRL_EXT,
+ .ctrl_reg = ASPEED_PTCR_TYPEO_CTRL,
+ .ctrl_reg1 = ASPEED_PTCR_TYPEO_CTRL1,
+ }
+};
+
+enum pwm_port { PWMA, PWMB, PWMC, PWMD, PWME, PWMF, PWMG, PWMH };
+
+struct pwm_port_params {
+ u32 pwm_en;
+ u32 ctrl_reg;
+ u32 type_part1;
+ u32 type_part2;
+ u32 type_mask;
+ u32 duty_ctrl_rise_point;
+ u32 duty_ctrl_fall_point;
+ u32 duty_ctrl_reg;
+ u32 duty_ctrl_rise_fall_mask;
+};
+
+static const struct pwm_port_params pwm_port_params[] = {
+ [PWMA] = {
+ .pwm_en = ASPEED_PTCR_CTRL_PWMA_EN,
+ .ctrl_reg = ASPEED_PTCR_CTRL,
+ .type_part1 = ASPEED_PTCR_CTRL_SET_PWMA_TYPE_PART1,
+ .type_part2 = ASPEED_PTCR_CTRL_SET_PWMA_TYPE_PART2,
+ .type_mask = ASPEED_PTCR_CTRL_SET_PWMA_TYPE_MASK,
+ .duty_ctrl_rise_point = DUTY_CTRL_PWM1_RISE_POINT,
+ .duty_ctrl_fall_point = DUTY_CTRL_PWM1_FALL_POINT,
+ .duty_ctrl_reg = ASPEED_PTCR_DUTY0_CTRL,
+ .duty_ctrl_rise_fall_mask = DUTY_CTRL_PWM1_RISE_FALL_MASK,
+ },
+ [PWMB] = {
+ .pwm_en = ASPEED_PTCR_CTRL_PWMB_EN,
+ .ctrl_reg = ASPEED_PTCR_CTRL,
+ .type_part1 = ASPEED_PTCR_CTRL_SET_PWMB_TYPE_PART1,
+ .type_part2 = ASPEED_PTCR_CTRL_SET_PWMB_TYPE_PART2,
+ .type_mask = ASPEED_PTCR_CTRL_SET_PWMB_TYPE_MASK,
+ .duty_ctrl_rise_point = DUTY_CTRL_PWM2_RISE_POINT,
+ .duty_ctrl_fall_point = DUTY_CTRL_PWM2_FALL_POINT,
+ .duty_ctrl_reg = ASPEED_PTCR_DUTY0_CTRL,
+ .duty_ctrl_rise_fall_mask = DUTY_CTRL_PWM2_RISE_FALL_MASK,
+ },
+ [PWMC] = {
+ .pwm_en = ASPEED_PTCR_CTRL_PWMC_EN,
+ .ctrl_reg = ASPEED_PTCR_CTRL,
+ .type_part1 = ASPEED_PTCR_CTRL_SET_PWMC_TYPE_PART1,
+ .type_part2 = ASPEED_PTCR_CTRL_SET_PWMC_TYPE_PART2,
+ .type_mask = ASPEED_PTCR_CTRL_SET_PWMC_TYPE_MASK,
+ .duty_ctrl_rise_point = DUTY_CTRL_PWM1_RISE_POINT,
+ .duty_ctrl_fall_point = DUTY_CTRL_PWM1_FALL_POINT,
+ .duty_ctrl_reg = ASPEED_PTCR_DUTY1_CTRL,
+ .duty_ctrl_rise_fall_mask = DUTY_CTRL_PWM1_RISE_FALL_MASK,
+ },
+ [PWMD] = {
+ .pwm_en = ASPEED_PTCR_CTRL_PWMD_EN,
+ .ctrl_reg = ASPEED_PTCR_CTRL,
+ .type_part1 = ASPEED_PTCR_CTRL_SET_PWMD_TYPE_PART1,
+ .type_part2 = ASPEED_PTCR_CTRL_SET_PWMD_TYPE_PART2,
+ .type_mask = ASPEED_PTCR_CTRL_SET_PWMD_TYPE_MASK,
+ .duty_ctrl_rise_point = DUTY_CTRL_PWM2_RISE_POINT,
+ .duty_ctrl_fall_point = DUTY_CTRL_PWM2_FALL_POINT,
+ .duty_ctrl_reg = ASPEED_PTCR_DUTY1_CTRL,
+ .duty_ctrl_rise_fall_mask = DUTY_CTRL_PWM2_RISE_FALL_MASK,
+ },
+ [PWME] = {
+ .pwm_en = ASPEED_PTCR_CTRL_PWME_EN,
+ .ctrl_reg = ASPEED_PTCR_CTRL_EXT,
+ .type_part1 = ASPEED_PTCR_CTRL_SET_PWME_TYPE_PART1,
+ .type_part2 = ASPEED_PTCR_CTRL_SET_PWME_TYPE_PART2,
+ .type_mask = ASPEED_PTCR_CTRL_SET_PWME_TYPE_MASK,
+ .duty_ctrl_rise_point = DUTY_CTRL_PWM1_RISE_POINT,
+ .duty_ctrl_fall_point = DUTY_CTRL_PWM1_FALL_POINT,
+ .duty_ctrl_reg = ASPEED_PTCR_DUTY2_CTRL,
+ .duty_ctrl_rise_fall_mask = DUTY_CTRL_PWM1_RISE_FALL_MASK,
+ },
+ [PWMF] = {
+ .pwm_en = ASPEED_PTCR_CTRL_PWMF_EN,
+ .ctrl_reg = ASPEED_PTCR_CTRL_EXT,
+ .type_part1 = ASPEED_PTCR_CTRL_SET_PWMF_TYPE_PART1,
+ .type_part2 = ASPEED_PTCR_CTRL_SET_PWMF_TYPE_PART2,
+ .type_mask = ASPEED_PTCR_CTRL_SET_PWMF_TYPE_MASK,
+ .duty_ctrl_rise_point = DUTY_CTRL_PWM2_RISE_POINT,
+ .duty_ctrl_fall_point = DUTY_CTRL_PWM2_FALL_POINT,
+ .duty_ctrl_reg = ASPEED_PTCR_DUTY2_CTRL,
+ .duty_ctrl_rise_fall_mask = DUTY_CTRL_PWM2_RISE_FALL_MASK,
+ },
+ [PWMG] = {
+ .pwm_en = ASPEED_PTCR_CTRL_PWMG_EN,
+ .ctrl_reg = ASPEED_PTCR_CTRL_EXT,
+ .type_part1 = ASPEED_PTCR_CTRL_SET_PWMG_TYPE_PART1,
+ .type_part2 = ASPEED_PTCR_CTRL_SET_PWMG_TYPE_PART2,
+ .type_mask = ASPEED_PTCR_CTRL_SET_PWMG_TYPE_MASK,
+ .duty_ctrl_rise_point = DUTY_CTRL_PWM1_RISE_POINT,
+ .duty_ctrl_fall_point = DUTY_CTRL_PWM1_FALL_POINT,
+ .duty_ctrl_reg = ASPEED_PTCR_DUTY3_CTRL,
+ .duty_ctrl_rise_fall_mask = DUTY_CTRL_PWM1_RISE_FALL_MASK,
+ },
+ [PWMH] = {
+ .pwm_en = ASPEED_PTCR_CTRL_PWMH_EN,
+ .ctrl_reg = ASPEED_PTCR_CTRL_EXT,
+ .type_part1 = ASPEED_PTCR_CTRL_SET_PWMH_TYPE_PART1,
+ .type_part2 = ASPEED_PTCR_CTRL_SET_PWMH_TYPE_PART2,
+ .type_mask = ASPEED_PTCR_CTRL_SET_PWMH_TYPE_MASK,
+ .duty_ctrl_rise_point = DUTY_CTRL_PWM2_RISE_POINT,
+ .duty_ctrl_fall_point = DUTY_CTRL_PWM2_FALL_POINT,
+ .duty_ctrl_reg = ASPEED_PTCR_DUTY3_CTRL,
+ .duty_ctrl_rise_fall_mask = DUTY_CTRL_PWM2_RISE_FALL_MASK,
+ }
+};
+
+static int regmap_aspeed_pwm_tacho_reg_write(void *context, unsigned int reg,
+ unsigned int val)
+{
+ void __iomem *regs = (void __iomem *)context;
+
+ writel(val, regs + reg);
+ return 0;
+}
+
+static int regmap_aspeed_pwm_tacho_reg_read(void *context, unsigned int reg,
+ unsigned int *val)
+{
+ void __iomem *regs = (void __iomem *)context;
+
+ *val = readl(regs + reg);
+ return 0;
+}
+
+static const struct regmap_config aspeed_pwm_tacho_regmap_config = {
+ .reg_bits = 32,
+ .val_bits = 32,
+ .reg_stride = 4,
+ .max_register = ASPEED_PTCR_TYPEO_LIMIT,
+ .reg_write = regmap_aspeed_pwm_tacho_reg_write,
+ .reg_read = regmap_aspeed_pwm_tacho_reg_read,
+ .fast_io = true,
+};
+
+static void aspeed_set_clock_enable(struct regmap *regmap, bool val)
+{
+ regmap_update_bits(regmap, ASPEED_PTCR_CTRL,
+ ASPEED_PTCR_CTRL_CLK_EN,
+ val ? ASPEED_PTCR_CTRL_CLK_EN : 0);
+}
+
+static void aspeed_set_clock_source(struct regmap *regmap, int val)
+{
+ regmap_update_bits(regmap, ASPEED_PTCR_CTRL,
+ ASPEED_PTCR_CTRL_CLK_SRC,
+ val ? ASPEED_PTCR_CTRL_CLK_SRC : 0);
+}
+
+static void aspeed_set_pwm_clock_values(struct regmap *regmap, u8 type,
+ u8 div_high, u8 div_low, u8 unit)
+{
+ u32 reg_value = ((div_high << type_params[type].h_value) |
+ (div_low << type_params[type].l_value) |
+ (unit << type_params[type].unit_value));
+
+ regmap_update_bits(regmap, type_params[type].clk_ctrl_reg,
+ type_params[type].clk_ctrl_mask, reg_value);
+}
+
+static void aspeed_set_pwm_port_enable(struct regmap *regmap, u8 pwm_port,
+ bool enable)
+{
+ regmap_update_bits(regmap, pwm_port_params[pwm_port].ctrl_reg,
+ pwm_port_params[pwm_port].pwm_en,
+ enable ? pwm_port_params[pwm_port].pwm_en : 0);
+}
+
+static void aspeed_set_pwm_port_type(struct regmap *regmap,
+ u8 pwm_port, u8 type)
+{
+ u32 reg_value = (type & 0x1) << pwm_port_params[pwm_port].type_part1;
+
+ reg_value |= (type & 0x2) << pwm_port_params[pwm_port].type_part2;
+
+ regmap_update_bits(regmap, pwm_port_params[pwm_port].ctrl_reg,
+ pwm_port_params[pwm_port].type_mask, reg_value);
+}
+
+static void aspeed_set_pwm_port_duty_rising_falling(struct regmap *regmap,
+ u8 pwm_port, u8 rising,
+ u8 falling)
+{
+ u32 reg_value = (rising <<
+ pwm_port_params[pwm_port].duty_ctrl_rise_point);
+ reg_value |= (falling <<
+ pwm_port_params[pwm_port].duty_ctrl_fall_point);
+
+ regmap_update_bits(regmap, pwm_port_params[pwm_port].duty_ctrl_reg,
+ pwm_port_params[pwm_port].duty_ctrl_rise_fall_mask,
+ reg_value);
+}
+
+static void aspeed_set_tacho_type_enable(struct regmap *regmap, u8 type,
+ bool enable)
+{
+ regmap_update_bits(regmap, type_params[type].ctrl_reg,
+ TYPE_CTRL_FAN_TYPE_EN,
+ enable ? TYPE_CTRL_FAN_TYPE_EN : 0);
+}
+
+static void aspeed_set_tacho_type_values(struct regmap *regmap, u8 type,
+ u8 mode, u16 unit, u8 division)
+{
+ u32 reg_value = ((mode << TYPE_CTRL_FAN_MODE) |
+ (unit << TYPE_CTRL_FAN_PERIOD) |
+ (division << TYPE_CTRL_FAN_DIVISION));
+
+ regmap_update_bits(regmap, type_params[type].ctrl_reg,
+ TYPE_CTRL_FAN_MASK, reg_value);
+ regmap_update_bits(regmap, type_params[type].ctrl_reg1,
+ TYPE_CTRL_FAN1_MASK, unit << 16);
+}
+
+static void aspeed_set_fan_tach_ch_enable(struct regmap *regmap, u8 fan_tach_ch,
+ bool enable)
+{
+ regmap_update_bits(regmap, ASPEED_PTCR_CTRL,
+ ASPEED_PTCR_CTRL_FAN_NUM_EN(fan_tach_ch),
+ enable ?
+ ASPEED_PTCR_CTRL_FAN_NUM_EN(fan_tach_ch) : 0);
+}
+
+static void aspeed_set_fan_tach_ch_source(struct regmap *regmap, u8 fan_tach_ch,
+ u8 fan_tach_ch_source)
+{
+ u32 reg_value1 = ((fan_tach_ch_source & 0x3) <<
+ TACH_PWM_SOURCE_BIT01(fan_tach_ch));
+ u32 reg_value2 = (((fan_tach_ch_source & 0x4) >> 2) <<
+ TACH_PWM_SOURCE_BIT2(fan_tach_ch));
+
+ regmap_update_bits(regmap, ASPEED_PTCR_TACH_SOURCE,
+ TACH_PWM_SOURCE_MASK_BIT01(fan_tach_ch),
+ reg_value1);
+
+ regmap_update_bits(regmap, ASPEED_PTCR_TACH_SOURCE_EXT,
+ TACH_PWM_SOURCE_MASK_BIT2(fan_tach_ch),
+ reg_value2);
+}
+
+static void aspeed_set_pwm_port_fan_ctrl(struct aspeed_pwm_tacho_data *priv,
+ u8 index, u8 fan_ctrl)
+{
+ u16 period, dc_time_on;
+
+ period = priv->type_pwm_clock_unit[priv->pwm_port_type[index]];
+ period += 1;
+ dc_time_on = (fan_ctrl * period) / PWM_MAX;
+
+ if (dc_time_on == 0) {
+ aspeed_set_pwm_port_enable(priv->regmap, index, false);
+ } else {
+ if (dc_time_on == period)
+ dc_time_on = 0;
+
+ aspeed_set_pwm_port_duty_rising_falling(priv->regmap, index, 0,
+ dc_time_on);
+ aspeed_set_pwm_port_enable(priv->regmap, index, true);
+ }
+}
+
+static u32 aspeed_get_fan_tach_ch_measure_period(struct aspeed_pwm_tacho_data
+ *priv, u8 type)
+{
+ u32 clk;
+ u16 tacho_unit;
+ u8 clk_unit, div_h, div_l, tacho_div;
+
+ clk = priv->clk_freq;
+ clk_unit = priv->type_pwm_clock_unit[type];
+ div_h = priv->type_pwm_clock_division_h[type];
+ div_h = 0x1 << div_h;
+ div_l = priv->type_pwm_clock_division_l[type];
+ if (div_l == 0)
+ div_l = 1;
+ else
+ div_l = div_l * 2;
+
+ tacho_unit = priv->type_fan_tach_unit[type];
+ tacho_div = priv->type_fan_tach_clock_division[type];
+
+ tacho_div = 0x4 << (tacho_div * 2);
+ return clk / (clk_unit * div_h * div_l * tacho_div * tacho_unit);
+}
+
+static u32 aspeed_get_fan_tach_ch_rpm(struct aspeed_pwm_tacho_data *priv,
+ u8 fan_tach_ch)
+{
+ u32 raw_data, tach_div, clk_source, sec, val;
+ u8 fan_tach_ch_source, type;
+
+ regmap_write(priv->regmap, ASPEED_PTCR_TRIGGER, 0);
+ regmap_write(priv->regmap, ASPEED_PTCR_TRIGGER, 0x1 << fan_tach_ch);
+
+ fan_tach_ch_source = priv->fan_tach_ch_source[fan_tach_ch];
+ type = priv->pwm_port_type[fan_tach_ch_source];
+
+ sec = (1000 / aspeed_get_fan_tach_ch_measure_period(priv, type));
+ msleep(sec);
+
+ regmap_read(priv->regmap, ASPEED_PTCR_RESULT, &val);
+ raw_data = val & RESULT_VALUE_MASK;
+ tach_div = priv->type_fan_tach_clock_division[type];
+ tach_div = 0x4 << (tach_div * 2);
+ clk_source = priv->clk_freq;
+
+ if (raw_data == 0)
+ return 0;
+
+ return (clk_source * 60) / (2 * raw_data * tach_div);
+}
+
+static ssize_t set_pwm(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
+ int index = sensor_attr->index;
+ int ret;
+ struct aspeed_pwm_tacho_data *priv = dev_get_drvdata(dev);
+ long fan_ctrl;
+
+ ret = kstrtol(buf, 10, &fan_ctrl);
+ if (ret != 0)
+ return ret;
+
+ if (fan_ctrl < 0 || fan_ctrl > PWM_MAX)
+ return -EINVAL;
+
+ if (priv->pwm_port_fan_ctrl[index] == fan_ctrl)
+ return count;
+
+ priv->pwm_port_fan_ctrl[index] = fan_ctrl;
+ aspeed_set_pwm_port_fan_ctrl(priv, index, fan_ctrl);
+
+ return count;
+}
+
+static ssize_t show_pwm(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
+ int index = sensor_attr->index;
+ struct aspeed_pwm_tacho_data *priv = dev_get_drvdata(dev);
+
+ return sprintf(buf, "%u\n", priv->pwm_port_fan_ctrl[index]);
+}
+
+static ssize_t show_rpm(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
+ int index = sensor_attr->index;
+ u32 rpm;
+ struct aspeed_pwm_tacho_data *priv = dev_get_drvdata(dev);
+
+ rpm = aspeed_get_fan_tach_ch_rpm(priv, index);
+
+ return sprintf(buf, "%u\n", rpm);
+}
+
+static umode_t pwm_is_visible(struct kobject *kobj,
+ struct attribute *a, int index)
+{
+ struct device *dev = container_of(kobj, struct device, kobj);
+ struct aspeed_pwm_tacho_data *priv = dev_get_drvdata(dev);
+
+ if (!priv->pwm_present[index])
+ return 0;
+ return a->mode;
+}
+
+static umode_t fan_dev_is_visible(struct kobject *kobj,
+ struct attribute *a, int index)
+{
+ struct device *dev = container_of(kobj, struct device, kobj);
+ struct aspeed_pwm_tacho_data *priv = dev_get_drvdata(dev);
+
+ if (!priv->fan_tach_present[index])
+ return 0;
+ return a->mode;
+}
+
+static SENSOR_DEVICE_ATTR(pwm0, 0644,
+ show_pwm, set_pwm, 0);
+static SENSOR_DEVICE_ATTR(pwm1, 0644,
+ show_pwm, set_pwm, 1);
+static SENSOR_DEVICE_ATTR(pwm2, 0644,
+ show_pwm, set_pwm, 2);
+static SENSOR_DEVICE_ATTR(pwm3, 0644,
+ show_pwm, set_pwm, 3);
+static SENSOR_DEVICE_ATTR(pwm4, 0644,
+ show_pwm, set_pwm, 4);
+static SENSOR_DEVICE_ATTR(pwm5, 0644,
+ show_pwm, set_pwm, 5);
+static SENSOR_DEVICE_ATTR(pwm6, 0644,
+ show_pwm, set_pwm, 6);
+static SENSOR_DEVICE_ATTR(pwm7, 0644,
+ show_pwm, set_pwm, 7);
+static struct attribute *pwm_dev_attrs[] = {
+ &sensor_dev_attr_pwm0.dev_attr.attr,
+ &sensor_dev_attr_pwm1.dev_attr.attr,
+ &sensor_dev_attr_pwm2.dev_attr.attr,
+ &sensor_dev_attr_pwm3.dev_attr.attr,
+ &sensor_dev_attr_pwm4.dev_attr.attr,
+ &sensor_dev_attr_pwm5.dev_attr.attr,
+ &sensor_dev_attr_pwm6.dev_attr.attr,
+ &sensor_dev_attr_pwm7.dev_attr.attr,
+ NULL,
+};
+
+static const struct attribute_group pwm_dev_group = {
+ .attrs = pwm_dev_attrs,
+ .is_visible = pwm_is_visible,
+};
+
+static SENSOR_DEVICE_ATTR(fan0_input, 0444,
+ show_rpm, NULL, 0);
+static SENSOR_DEVICE_ATTR(fan1_input, 0444,
+ show_rpm, NULL, 1);
+static SENSOR_DEVICE_ATTR(fan2_input, 0444,
+ show_rpm, NULL, 2);
+static SENSOR_DEVICE_ATTR(fan3_input, 0444,
+ show_rpm, NULL, 3);
+static SENSOR_DEVICE_ATTR(fan4_input, 0444,
+ show_rpm, NULL, 4);
+static SENSOR_DEVICE_ATTR(fan5_input, 0444,
+ show_rpm, NULL, 5);
+static SENSOR_DEVICE_ATTR(fan6_input, 0444,
+ show_rpm, NULL, 6);
+static SENSOR_DEVICE_ATTR(fan7_input, 0444,
+ show_rpm, NULL, 7);
+static SENSOR_DEVICE_ATTR(fan8_input, 0444,
+ show_rpm, NULL, 8);
+static SENSOR_DEVICE_ATTR(fan9_input, 0444,
+ show_rpm, NULL, 9);
+static SENSOR_DEVICE_ATTR(fan10_input, 0444,
+ show_rpm, NULL, 10);
+static SENSOR_DEVICE_ATTR(fan11_input, 0444,
+ show_rpm, NULL, 11);
+static SENSOR_DEVICE_ATTR(fan12_input, 0444,
+ show_rpm, NULL, 12);
+static SENSOR_DEVICE_ATTR(fan13_input, 0444,
+ show_rpm, NULL, 13);
+static SENSOR_DEVICE_ATTR(fan14_input, 0444,
+ show_rpm, NULL, 14);
+static SENSOR_DEVICE_ATTR(fan15_input, 0444,
+ show_rpm, NULL, 15);
+static struct attribute *fan_dev_attrs[] = {
+ &sensor_dev_attr_fan0_input.dev_attr.attr,
+ &sensor_dev_attr_fan1_input.dev_attr.attr,
+ &sensor_dev_attr_fan2_input.dev_attr.attr,
+ &sensor_dev_attr_fan3_input.dev_attr.attr,
+ &sensor_dev_attr_fan4_input.dev_attr.attr,
+ &sensor_dev_attr_fan5_input.dev_attr.attr,
+ &sensor_dev_attr_fan6_input.dev_attr.attr,
+ &sensor_dev_attr_fan7_input.dev_attr.attr,
+ &sensor_dev_attr_fan8_input.dev_attr.attr,
+ &sensor_dev_attr_fan9_input.dev_attr.attr,
+ &sensor_dev_attr_fan10_input.dev_attr.attr,
+ &sensor_dev_attr_fan11_input.dev_attr.attr,
+ &sensor_dev_attr_fan12_input.dev_attr.attr,
+ &sensor_dev_attr_fan13_input.dev_attr.attr,
+ &sensor_dev_attr_fan14_input.dev_attr.attr,
+ &sensor_dev_attr_fan15_input.dev_attr.attr,
+ NULL
+};
+
+static const struct attribute_group fan_dev_group = {
+ .attrs = fan_dev_attrs,
+ .is_visible = fan_dev_is_visible,
+};
+
+/*
+ * The clock type is type M :
+ * The PWM frequency = 24MHz / (type M clock division L bit *
+ * type M clock division H bit * (type M PWM period bit + 1))
+ */
+static void aspeed_create_type(struct aspeed_pwm_tacho_data *priv)
+{
+ priv->type_pwm_clock_division_h[TYPEM] = M_PWM_DIV_H;
+ priv->type_pwm_clock_division_l[TYPEM] = M_PWM_DIV_L;
+ priv->type_pwm_clock_unit[TYPEM] = M_PWM_PERIOD;
+ aspeed_set_pwm_clock_values(priv->regmap, TYPEM, M_PWM_DIV_H,
+ M_PWM_DIV_L, M_PWM_PERIOD);
+ aspeed_set_tacho_type_enable(priv->regmap, TYPEM, true);
+ priv->type_fan_tach_clock_division[TYPEM] = M_TACH_CLK_DIV;
+ priv->type_fan_tach_unit[TYPEM] = M_TACH_UNIT;
+ aspeed_set_tacho_type_values(priv->regmap, TYPEM, M_TACH_MODE,
+ M_TACH_UNIT, M_TACH_CLK_DIV);
+}
+
+static void aspeed_create_pwm_port(struct aspeed_pwm_tacho_data *priv,
+ u8 pwm_port)
+{
+ aspeed_set_pwm_port_enable(priv->regmap, pwm_port, true);
+ priv->pwm_present[pwm_port] = true;
+
+ priv->pwm_port_type[pwm_port] = TYPEM;
+ aspeed_set_pwm_port_type(priv->regmap, pwm_port, TYPEM);
+
+ priv->pwm_port_fan_ctrl[pwm_port] = INIT_FAN_CTRL;
+ aspeed_set_pwm_port_fan_ctrl(priv, pwm_port, INIT_FAN_CTRL);
+}
+
+static void aspeed_create_fan_tach_channel(struct aspeed_pwm_tacho_data *priv,
+ u8 *fan_tach_ch,
+ int count,
+ u8 pwm_source)
+{
+ u8 val, index;
+
+ for (val = 0; val < count; val++) {
+ index = fan_tach_ch[val];
+ aspeed_set_fan_tach_ch_enable(priv->regmap, index, true);
+ priv->fan_tach_present[index] = true;
+ priv->fan_tach_ch_source[index] = pwm_source;
+ aspeed_set_fan_tach_ch_source(priv->regmap, index, pwm_source);
+ }
+}
+
+static int aspeed_create_fan(struct device *dev,
+ struct device_node *child,
+ struct aspeed_pwm_tacho_data *priv)
+{
+ u8 *fan_tach_ch;
+ u32 pwm_port;
+ int ret, count;
+
+ ret = of_property_read_u32(child, "reg", &pwm_port);
+ if (ret)
+ return ret;
+ aspeed_create_pwm_port(priv, (u8)pwm_port);
+
+ count = of_property_count_u8_elems(child, "aspeed,fan-tach-ch");
+ if (count < 1)
+ return -EINVAL;
+ fan_tach_ch = devm_kzalloc(dev, sizeof(*fan_tach_ch) * count,
+ GFP_KERNEL);
+ if (!fan_tach_ch)
+ return -ENOMEM;
+ ret = of_property_read_u8_array(child, "aspeed,fan-tach-ch",
+ fan_tach_ch, count);
+ if (ret)
+ return ret;
+ aspeed_create_fan_tach_channel(priv, fan_tach_ch, count, pwm_port);
+
+ return 0;
+}
+
+static int aspeed_pwm_tacho_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct device_node *np, *child;
+ struct aspeed_pwm_tacho_data *priv;
+ void __iomem *regs;
+ struct resource *res;
+ struct device *hwmon;
+ struct clk *clk;
+ int ret;
+
+ np = dev->of_node;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res)
+ return -ENOENT;
+ regs = devm_ioremap_resource(dev, res);
+ if (IS_ERR(regs))
+ return PTR_ERR(regs);
+ priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+ if (!priv)
+ return -ENOMEM;
+ priv->regmap = devm_regmap_init(dev, NULL, (__force void *)regs,
+ &aspeed_pwm_tacho_regmap_config);
+ if (IS_ERR(priv->regmap))
+ return PTR_ERR(priv->regmap);
+ regmap_write(priv->regmap, ASPEED_PTCR_TACH_SOURCE, 0);
+ regmap_write(priv->regmap, ASPEED_PTCR_TACH_SOURCE_EXT, 0);
+
+ clk = devm_clk_get(dev, NULL);
+ if (IS_ERR(clk))
+ return -ENODEV;
+ priv->clk_freq = clk_get_rate(clk);
+ aspeed_set_clock_enable(priv->regmap, true);
+ aspeed_set_clock_source(priv->regmap, 0);
+
+ aspeed_create_type(priv);
+
+ for_each_child_of_node(np, child) {
+ ret = aspeed_create_fan(dev, child, priv);
+ of_node_put(child);
+ if (ret)
+ return ret;
+ }
+ of_node_put(np);
+
+ priv->groups[0] = &pwm_dev_group;
+ priv->groups[1] = &fan_dev_group;
+ priv->groups[2] = NULL;
+ hwmon = devm_hwmon_device_register_with_groups(dev,
+ "aspeed_pwm_tacho",
+ priv, priv->groups);
+ return PTR_ERR_OR_ZERO(hwmon);
+}
+
+static const struct of_device_id of_pwm_tacho_match_table[] = {
+ { .compatible = "aspeed,ast2400-pwm-tacho", },
+ { .compatible = "aspeed,ast2500-pwm-tacho", },
+ {},
+};
+MODULE_DEVICE_TABLE(of, of_pwm_tacho_match_table);
+
+static struct platform_driver aspeed_pwm_tacho_driver = {
+ .probe = aspeed_pwm_tacho_probe,
+ .driver = {
+ .name = "aspeed_pwm_tacho",
+ .of_match_table = of_pwm_tacho_match_table,
+ },
+};
+
+module_platform_driver(aspeed_pwm_tacho_driver);
+
+MODULE_AUTHOR("Jaghathiswari Rankappagounder Natarajan <jaghu@google.com>");
+MODULE_DESCRIPTION("ASPEED PWM and Fan Tacho device driver");
+MODULE_LICENSE("GPL");
},
.driver_data = (void *)&i8k_config_data[DELL_XPS],
},
+ {
+ .ident = "Dell XPS 15 9560",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "XPS 15 9560"),
+ },
+ },
{ }
};
char *buf)
{
struct hwmon_device_attribute *hattr = to_hwmon_attr(devattr);
- char *s;
+ const char *s;
int ret;
ret = hattr->ops->read_string(dev, hattr->type, hattr->attr,
case INA209_SHUNT_VOLTAGE_POS_WARN:
case INA209_SHUNT_VOLTAGE_NEG_WARN:
/* LSB=10 uV. Convert to mV. */
- return DIV_ROUND_CLOSEST(val, 100);
+ return DIV_ROUND_CLOSEST((s16)val, 100);
case INA209_BUS_VOLTAGE:
case INA209_BUS_VOLTAGE_MAX_PEAK:
case INA209_CURRENT:
/* LSB=1 mA (selected). Is in mA */
- return val;
+ return (s16)val;
}
/* programmer goofed */
};
MODULE_DEVICE_TABLE(i2c, ina209_id);
+static const struct of_device_id ina209_of_match[] = {
+ { .compatible = "ti,ina209" },
+ { },
+};
+MODULE_DEVICE_TABLE(of, ina209_of_match);
+
/* This is the driver that will be inserted */
static struct i2c_driver ina209_driver = {
.class = I2C_CLASS_HWMON,
.driver = {
.name = "ina209",
+ .of_match_table = of_match_ptr(ina209_of_match),
},
.probe = ina209_probe,
.remove = ina209_remove,
#include <linux/hwmon.h>
#include <linux/hwmon-sysfs.h>
#include <linux/jiffies.h>
+#include <linux/of_device.h>
#include <linux/of.h>
#include <linux/delay.h>
#include <linux/util_macros.h>
struct device *hwmon_dev;
u32 val;
int ret, group = 0;
+ enum ina2xx_ids chip;
+
+ if (client->dev.of_node)
+ chip = (enum ina2xx_ids)of_device_get_match_data(&client->dev);
+ else
+ chip = id->driver_data;
data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
if (!data)
return -ENOMEM;
/* set the device type */
- data->config = &ina2xx_config[id->driver_data];
+ data->config = &ina2xx_config[chip];
if (of_property_read_u32(dev->of_node, "shunt-resistor", &val) < 0) {
struct ina2xx_platform_data *pdata = dev_get_platdata(dev);
};
MODULE_DEVICE_TABLE(i2c, ina2xx_id);
+static const struct of_device_id ina2xx_of_match[] = {
+ {
+ .compatible = "ti,ina219",
+ .data = (void *)ina219
+ },
+ {
+ .compatible = "ti,ina220",
+ .data = (void *)ina219
+ },
+ {
+ .compatible = "ti,ina226",
+ .data = (void *)ina226
+ },
+ {
+ .compatible = "ti,ina230",
+ .data = (void *)ina226
+ },
+ {
+ .compatible = "ti,ina231",
+ .data = (void *)ina226
+ },
+ { },
+};
+MODULE_DEVICE_TABLE(of, ina2xx_of_match);
+
static struct i2c_driver ina2xx_driver = {
.driver = {
.name = "ina2xx",
+ .of_match_table = of_match_ptr(ina2xx_of_match),
},
.probe = ina2xx_probe,
.id_table = ina2xx_id,
#include <linux/hwmon.h>
#include <linux/err.h>
#include <linux/mutex.h>
+#include <linux/of_device.h>
#include <linux/sysfs.h>
#include <linux/types.h>
mutex_init(&data->update_lock);
/* Set the device type */
+ if (client->dev.of_node)
+ data->kind = (enum chips)of_device_get_match_data(&client->dev);
+ else
+ data->kind = id->driver_data;
data->kind = id->driver_data;
if (data->kind == lm64)
data->temp2_offset = 16000;
};
MODULE_DEVICE_TABLE(i2c, lm63_id);
+static const struct of_device_id lm63_of_match[] = {
+ {
+ .compatible = "national,lm63",
+ .data = (void *)lm63
+ },
+ {
+ .compatible = "national,lm64",
+ .data = (void *)lm64
+ },
+ {
+ .compatible = "national,lm96163",
+ .data = (void *)lm96163
+ },
+ { },
+};
+MODULE_DEVICE_TABLE(of, lm63_of_match);
+
static struct i2c_driver lm63_driver = {
.class = I2C_CLASS_HWMON,
.driver = {
.name = "lm63",
+ .of_match_table = of_match_ptr(lm63_of_match),
},
.probe = lm63_probe,
.id_table = lm63_id,
#include <linux/hwmon.h>
#include <linux/hwmon-sysfs.h>
#include <linux/err.h>
+#include <linux/of_device.h>
#include <linux/of.h>
#include <linux/regmap.h>
#include "lm75.h"
int status, err;
u8 set_mask, clr_mask;
int new;
- enum lm75_type kind = id->driver_data;
+ enum lm75_type kind;
+
+ if (client->dev.of_node)
+ kind = (enum lm75_type)of_device_get_match_data(&client->dev);
+ else
+ kind = id->driver_data;
if (!i2c_check_functionality(client->adapter,
I2C_FUNC_SMBUS_BYTE_DATA | I2C_FUNC_SMBUS_WORD_DATA))
};
MODULE_DEVICE_TABLE(i2c, lm75_ids);
+static const struct of_device_id lm75_of_match[] = {
+ {
+ .compatible = "adi,adt75",
+ .data = (void *)adt75
+ },
+ {
+ .compatible = "dallas,ds1775",
+ .data = (void *)ds1775
+ },
+ {
+ .compatible = "dallas,ds75",
+ .data = (void *)ds75
+ },
+ {
+ .compatible = "dallas,ds7505",
+ .data = (void *)ds7505
+ },
+ {
+ .compatible = "gmt,g751",
+ .data = (void *)g751
+ },
+ {
+ .compatible = "national,lm75",
+ .data = (void *)lm75
+ },
+ {
+ .compatible = "national,lm75a",
+ .data = (void *)lm75a
+ },
+ {
+ .compatible = "national,lm75b",
+ .data = (void *)lm75b
+ },
+ {
+ .compatible = "maxim,max6625",
+ .data = (void *)max6625
+ },
+ {
+ .compatible = "maxim,max6626",
+ .data = (void *)max6626
+ },
+ {
+ .compatible = "maxim,mcp980x",
+ .data = (void *)mcp980x
+ },
+ {
+ .compatible = "st,stds75",
+ .data = (void *)stds75
+ },
+ {
+ .compatible = "microchip,tcn75",
+ .data = (void *)tcn75
+ },
+ {
+ .compatible = "ti,tmp100",
+ .data = (void *)tmp100
+ },
+ {
+ .compatible = "ti,tmp101",
+ .data = (void *)tmp101
+ },
+ {
+ .compatible = "ti,tmp105",
+ .data = (void *)tmp105
+ },
+ {
+ .compatible = "ti,tmp112",
+ .data = (void *)tmp112
+ },
+ {
+ .compatible = "ti,tmp175",
+ .data = (void *)tmp175
+ },
+ {
+ .compatible = "ti,tmp275",
+ .data = (void *)tmp275
+ },
+ {
+ .compatible = "ti,tmp75",
+ .data = (void *)tmp75
+ },
+ {
+ .compatible = "ti,tmp75c",
+ .data = (void *)tmp75c
+ },
+ { },
+};
+MODULE_DEVICE_TABLE(of, lm75_of_match);
+
#define LM75A_ID 0xA1
/* Return 0 if detection is successful, -ENODEV otherwise */
.class = I2C_CLASS_HWMON,
.driver = {
.name = "lm75",
+ .of_match_table = of_match_ptr(lm75_of_match),
.pm = LM75_DEV_PM_OPS,
},
.probe = lm75_probe,
*/
#include <linux/module.h>
+#include <linux/of_device.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/jiffies.h>
return -ENOMEM;
data->client = client;
- data->type = id->driver_data;
+ if (client->dev.of_node)
+ data->type = (enum chips)of_device_get_match_data(&client->dev);
+ else
+ data->type = id->driver_data;
mutex_init(&data->update_lock);
/* Fill in the chip specific driver values */
};
MODULE_DEVICE_TABLE(i2c, lm85_id);
+static const struct of_device_id lm85_of_match[] = {
+ {
+ .compatible = "adi,adm1027",
+ .data = (void *)adm1027
+ },
+ {
+ .compatible = "adi,adt7463",
+ .data = (void *)adt7463
+ },
+ {
+ .compatible = "adi,adt7468",
+ .data = (void *)adt7468
+ },
+ {
+ .compatible = "national,lm85",
+ .data = (void *)lm85
+ },
+ {
+ .compatible = "national,lm85b",
+ .data = (void *)lm85
+ },
+ {
+ .compatible = "national,lm85c",
+ .data = (void *)lm85
+ },
+ {
+ .compatible = "smsc,emc6d100",
+ .data = (void *)emc6d100
+ },
+ {
+ .compatible = "smsc,emc6d101",
+ .data = (void *)emc6d100
+ },
+ {
+ .compatible = "smsc,emc6d102",
+ .data = (void *)emc6d102
+ },
+ {
+ .compatible = "smsc,emc6d103",
+ .data = (void *)emc6d103
+ },
+ {
+ .compatible = "smsc,emc6d103s",
+ .data = (void *)emc6d103s
+ },
+ { },
+};
+MODULE_DEVICE_TABLE(of, lm85_of_match);
+
static struct i2c_driver lm85_driver = {
.class = I2C_CLASS_HWMON,
.driver = {
.name = "lm85",
+ .of_match_table = of_match_ptr(lm85_of_match),
},
.probe = lm85_probe,
.id_table = lm85_id,
#include <linux/hwmon-vid.h>
#include <linux/err.h>
#include <linux/mutex.h>
+#include <linux/regulator/consumer.h>
/*
* Addresses to scan
static const unsigned short normal_i2c[] = { 0x2c, 0x2d, 0x2e, I2C_CLIENT_END };
-enum chips { lm87, adm1024 };
-
/*
* The LM87 registers
*/
{
struct lm87_data *data = i2c_get_clientdata(client);
int rc;
-
- if (dev_get_platdata(&client->dev)) {
+ struct device_node *of_node = client->dev.of_node;
+ u8 val = 0;
+ struct regulator *vcc = NULL;
+
+ if (of_node) {
+ if (of_property_read_bool(of_node, "has-temp3"))
+ val |= CHAN_TEMP3;
+ if (of_property_read_bool(of_node, "has-in6"))
+ val |= CHAN_NO_FAN(0);
+ if (of_property_read_bool(of_node, "has-in7"))
+ val |= CHAN_NO_FAN(1);
+ vcc = devm_regulator_get_optional(&client->dev, "vcc");
+ if (!IS_ERR(vcc)) {
+ if (regulator_get_voltage(vcc) == 5000000)
+ val |= CHAN_VCC_5V;
+ }
+ data->channel = val;
+ lm87_write_value(client,
+ LM87_REG_CHANNEL_MODE, data->channel);
+ } else if (dev_get_platdata(&client->dev)) {
data->channel = *(u8 *)dev_get_platdata(&client->dev);
lm87_write_value(client,
LM87_REG_CHANNEL_MODE, data->channel);
*/
static const struct i2c_device_id lm87_id[] = {
- { "lm87", lm87 },
- { "adm1024", adm1024 },
+ { "lm87", 0 },
+ { "adm1024", 0 },
{ }
};
MODULE_DEVICE_TABLE(i2c, lm87_id);
+static const struct of_device_id lm87_of_match[] = {
+ { .compatible = "ti,lm87" },
+ { .compatible = "adi,adm1024" },
+ { },
+};
+MODULE_DEVICE_TABLE(of, lm87_of_match);
+
static struct i2c_driver lm87_driver = {
.class = I2C_CLASS_HWMON,
.driver = {
.name = "lm87",
+ .of_match_table = lm87_of_match,
},
.probe = lm87_probe,
.id_table = lm87_id,
#include <linux/hwmon.h>
#include <linux/err.h>
#include <linux/mutex.h>
+#include <linux/of_device.h>
#include <linux/sysfs.h>
#include <linux/interrupt.h>
#include <linux/regulator/consumer.h>
};
MODULE_DEVICE_TABLE(i2c, lm90_id);
+static const struct of_device_id lm90_of_match[] = {
+ {
+ .compatible = "adi,adm1032",
+ .data = (void *)adm1032
+ },
+ {
+ .compatible = "adi,adt7461",
+ .data = (void *)adt7461
+ },
+ {
+ .compatible = "adi,adt7461a",
+ .data = (void *)adt7461
+ },
+ {
+ .compatible = "gmt,g781",
+ .data = (void *)g781
+ },
+ {
+ .compatible = "national,lm90",
+ .data = (void *)lm90
+ },
+ {
+ .compatible = "national,lm86",
+ .data = (void *)lm86
+ },
+ {
+ .compatible = "national,lm89",
+ .data = (void *)lm86
+ },
+ {
+ .compatible = "national,lm99",
+ .data = (void *)lm99
+ },
+ {
+ .compatible = "dallas,max6646",
+ .data = (void *)max6646
+ },
+ {
+ .compatible = "dallas,max6647",
+ .data = (void *)max6646
+ },
+ {
+ .compatible = "dallas,max6649",
+ .data = (void *)max6646
+ },
+ {
+ .compatible = "dallas,max6657",
+ .data = (void *)max6657
+ },
+ {
+ .compatible = "dallas,max6658",
+ .data = (void *)max6657
+ },
+ {
+ .compatible = "dallas,max6659",
+ .data = (void *)max6659
+ },
+ {
+ .compatible = "dallas,max6680",
+ .data = (void *)max6680
+ },
+ {
+ .compatible = "dallas,max6681",
+ .data = (void *)max6680
+ },
+ {
+ .compatible = "dallas,max6695",
+ .data = (void *)max6696
+ },
+ {
+ .compatible = "dallas,max6696",
+ .data = (void *)max6696
+ },
+ {
+ .compatible = "onnn,nct1008",
+ .data = (void *)adt7461
+ },
+ {
+ .compatible = "winbond,w83l771",
+ .data = (void *)w83l771
+ },
+ {
+ .compatible = "nxp,sa56004",
+ .data = (void *)sa56004
+ },
+ {
+ .compatible = "ti,tmp451",
+ .data = (void *)tmp451
+ },
+ { },
+};
+MODULE_DEVICE_TABLE(of, lm90_of_match);
+
/*
* chip type specific parameters
*/
mutex_init(&data->update_lock);
/* Set the device type */
- data->kind = id->driver_data;
+ if (client->dev.of_node)
+ data->kind = (enum chips)of_device_get_match_data(&client->dev);
+ else
+ data->kind = id->driver_data;
if (data->kind == adm1032) {
if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE))
client->flags &= ~I2C_CLIENT_PEC;
.class = I2C_CLASS_HWMON,
.driver = {
.name = "lm90",
+ .of_match_table = of_match_ptr(lm90_of_match),
},
.probe = lm90_probe,
.alert = lm90_alert,
};
MODULE_DEVICE_TABLE(i2c, lm95245_id);
+static const struct of_device_id lm95245_of_match[] = {
+ { .compatible = "national,lm95235" },
+ { .compatible = "national,lm95245" },
+ { },
+};
+MODULE_DEVICE_TABLE(of, lm95245_of_match);
+
static struct i2c_driver lm95245_driver = {
.class = I2C_CLASS_HWMON,
.driver = {
.name = "lm95245",
+ .of_match_table = of_match_ptr(lm95245_of_match),
},
.probe = lm95245_probe,
.id_table = lm95245_id,
#include <linux/hwmon-sysfs.h>
#include <linux/err.h>
#include <linux/mutex.h>
+#include <linux/of_device.h>
#include <linux/of.h>
#include <linux/platform_data/max6697.h>
if (!data)
return -ENOMEM;
- data->type = id->driver_data;
+ if (client->dev.of_node)
+ data->type = (enum chips)of_device_get_match_data(&client->dev);
+ else
+ data->type = id->driver_data;
data->chip = &max6697_chip_data[data->type];
data->client = client;
mutex_init(&data->update_lock);
};
MODULE_DEVICE_TABLE(i2c, max6697_id);
+static const struct of_device_id max6697_of_match[] = {
+ {
+ .compatible = "maxim,max6581",
+ .data = (void *)max6581
+ },
+ {
+ .compatible = "maxim,max6602",
+ .data = (void *)max6602
+ },
+ {
+ .compatible = "maxim,max6622",
+ .data = (void *)max6622
+ },
+ {
+ .compatible = "maxim,max6636",
+ .data = (void *)max6636
+ },
+ {
+ .compatible = "maxim,max6689",
+ .data = (void *)max6689
+ },
+ {
+ .compatible = "maxim,max6693",
+ .data = (void *)max6693
+ },
+ {
+ .compatible = "maxim,max6694",
+ .data = (void *)max6694
+ },
+ {
+ .compatible = "maxim,max6697",
+ .data = (void *)max6697
+ },
+ {
+ .compatible = "maxim,max6698",
+ .data = (void *)max6698
+ },
+ {
+ .compatible = "maxim,max6699",
+ .data = (void *)max6699
+ },
+ { },
+};
+MODULE_DEVICE_TABLE(of, max6697_of_match);
+
static struct i2c_driver max6697_driver = {
.class = I2C_CLASS_HWMON,
.driver = {
.name = "max6697",
+ .of_match_table = of_match_ptr(max6697_of_match),
},
.probe = max6697_probe,
.id_table = max6697_id,
[0] = { 27169, 0, -1 }, /* voltage */
[1] = { 806, 20475, -1 }, /* current, irange25 */
[2] = { 404, 20475, -1 }, /* current, irange50 */
- [3] = { 0, -1, 8549 }, /* power, irange25 */
- [4] = { 0, -1, 4279 }, /* power, irange50 */
+ [3] = { 8549, 0, -1 }, /* power, irange25 */
+ [4] = { 4279, 0, -1 }, /* power, irange50 */
};
static const struct coefficients adm1275_coefficients[] = {
#include <linux/kernel.h>
#include <linux/module.h>
+#include <linux/of_device.h>
#include <linux/init.h>
#include <linux/err.h>
#include <linux/slab.h>
};
MODULE_DEVICE_TABLE(i2c, ucd9000_id);
+static const struct of_device_id ucd9000_of_match[] = {
+ {
+ .compatible = "ti,ucd9000",
+ .data = (void *)ucd9000
+ },
+ {
+ .compatible = "ti,ucd90120",
+ .data = (void *)ucd90120
+ },
+ {
+ .compatible = "ti,ucd90124",
+ .data = (void *)ucd90124
+ },
+ {
+ .compatible = "ti,ucd90160",
+ .data = (void *)ucd90160
+ },
+ {
+ .compatible = "ti,ucd9090",
+ .data = (void *)ucd9090
+ },
+ {
+ .compatible = "ti,ucd90910",
+ .data = (void *)ucd90910
+ },
+ { },
+};
+MODULE_DEVICE_TABLE(of, ucd9000_of_match);
+
static int ucd9000_probe(struct i2c_client *client,
const struct i2c_device_id *id)
{
struct ucd9000_data *data;
struct pmbus_driver_info *info;
const struct i2c_device_id *mid;
+ enum chips chip;
int i, ret;
if (!i2c_check_functionality(client->adapter,
return -ENODEV;
}
- if (id->driver_data != ucd9000 && id->driver_data != mid->driver_data)
+ if (client->dev.of_node)
+ chip = (enum chips)of_device_get_match_data(&client->dev);
+ else
+ chip = id->driver_data;
+
+ if (chip != ucd9000 && chip != mid->driver_data)
dev_notice(&client->dev,
"Device mismatch: Configured %s, detected %s\n",
id->name, mid->name);
static struct i2c_driver ucd9000_driver = {
.driver = {
.name = "ucd9000",
+ .of_match_table = of_match_ptr(ucd9000_of_match),
},
.probe = ucd9000_probe,
.remove = pmbus_do_remove,
#include <linux/kernel.h>
#include <linux/module.h>
+#include <linux/of_device.h>
#include <linux/init.h>
#include <linux/err.h>
#include <linux/slab.h>
};
MODULE_DEVICE_TABLE(i2c, ucd9200_id);
+static const struct of_device_id ucd9200_of_match[] = {
+ {
+ .compatible = "ti,cd9200",
+ .data = (void *)ucd9200
+ },
+ {
+ .compatible = "ti,cd9220",
+ .data = (void *)ucd9220
+ },
+ {
+ .compatible = "ti,cd9222",
+ .data = (void *)ucd9222
+ },
+ {
+ .compatible = "ti,cd9224",
+ .data = (void *)ucd9224
+ },
+ {
+ .compatible = "ti,cd9240",
+ .data = (void *)ucd9240
+ },
+ {
+ .compatible = "ti,cd9244",
+ .data = (void *)ucd9244
+ },
+ {
+ .compatible = "ti,cd9246",
+ .data = (void *)ucd9246
+ },
+ {
+ .compatible = "ti,cd9248",
+ .data = (void *)ucd9248
+ },
+ { },
+};
+MODULE_DEVICE_TABLE(of, ucd9200_of_match);
+
static int ucd9200_probe(struct i2c_client *client,
const struct i2c_device_id *id)
{
u8 block_buffer[I2C_SMBUS_BLOCK_MAX + 1];
struct pmbus_driver_info *info;
const struct i2c_device_id *mid;
+ enum chips chip;
int i, j, ret;
if (!i2c_check_functionality(client->adapter,
dev_err(&client->dev, "Unsupported device\n");
return -ENODEV;
}
- if (id->driver_data != ucd9200 && id->driver_data != mid->driver_data)
+
+ if (client->dev.of_node)
+ chip = (enum chips)of_device_get_match_data(&client->dev);
+ else
+ chip = id->driver_data;
+
+ if (chip != ucd9200 && chip != mid->driver_data)
dev_notice(&client->dev,
"Device mismatch: Configured %s, detected %s\n",
id->name, mid->name);
static struct i2c_driver ucd9200_driver = {
.driver = {
.name = "ucd9200",
+ .of_match_table = of_match_ptr(ucd9200_of_match),
},
.probe = ucd9200_probe,
.remove = pmbus_do_remove,
{ }
};
+static const struct of_device_id stts751_of_match[] = {
+ { .compatible = "stts751" },
+ { },
+};
+MODULE_DEVICE_TABLE(of, stts751_of_match);
+
struct stts751_priv {
struct device *dev;
struct i2c_client *client;
.class = I2C_CLASS_HWMON,
.driver = {
.name = DEVNAME,
+ .of_match_table = of_match_ptr(stts751_of_match),
},
.probe = stts751_probe,
.id_table = stts751_id,
};
MODULE_DEVICE_TABLE(i2c, tmp102_id);
+static const struct of_device_id tmp102_of_match[] = {
+ { .compatible = "ti,tmp102" },
+ { },
+};
+MODULE_DEVICE_TABLE(of, tmp102_of_match);
+
static struct i2c_driver tmp102_driver = {
.driver.name = DRIVER_NAME,
+ .driver.of_match_table = of_match_ptr(tmp102_of_match),
.driver.pm = &tmp102_dev_pm_ops,
.probe = tmp102_probe,
.id_table = tmp102_id,
return PTR_ERR_OR_ZERO(hwmon_dev);
}
-#ifdef CONFIG_PM
-static int tmp103_suspend(struct device *dev)
+static int __maybe_unused tmp103_suspend(struct device *dev)
{
struct regmap *regmap = dev_get_drvdata(dev);
TMP103_CONF_SD_MASK, 0);
}
-static int tmp103_resume(struct device *dev)
+static int __maybe_unused tmp103_resume(struct device *dev)
{
struct regmap *regmap = dev_get_drvdata(dev);
TMP103_CONF_SD_MASK, TMP103_CONF_SD);
}
-static const struct dev_pm_ops tmp103_dev_pm_ops = {
- .suspend = tmp103_suspend,
- .resume = tmp103_resume,
-};
-
-#define TMP103_DEV_PM_OPS (&tmp103_dev_pm_ops)
-#else
-#define TMP103_DEV_PM_OPS NULL
-#endif /* CONFIG_PM */
+static SIMPLE_DEV_PM_OPS(tmp103_dev_pm_ops, tmp103_suspend, tmp103_resume);
static const struct i2c_device_id tmp103_id[] = {
{ "tmp103", 0 },
};
MODULE_DEVICE_TABLE(i2c, tmp103_id);
+static const struct of_device_id tmp103_of_match[] = {
+ { .compatible = "ti,tmp103" },
+ { },
+};
+MODULE_DEVICE_TABLE(of, tmp103_of_match);
+
static struct i2c_driver tmp103_driver = {
.driver = {
.name = "tmp103",
- .pm = TMP103_DEV_PM_OPS,
+ .of_match_table = of_match_ptr(tmp103_of_match),
+ .pm = &tmp103_dev_pm_ops,
},
.probe = tmp103_probe,
.id_table = tmp103_id,
#include <linux/hwmon-sysfs.h>
#include <linux/err.h>
#include <linux/mutex.h>
+#include <linux/of_device.h>
#include <linux/sysfs.h>
/* Addresses to scan */
};
MODULE_DEVICE_TABLE(i2c, tmp421_id);
+static const struct of_device_id tmp421_of_match[] = {
+ {
+ .compatible = "ti,tmp421",
+ .data = (void *)2
+ },
+ {
+ .compatible = "ti,tmp422",
+ .data = (void *)3
+ },
+ {
+ .compatible = "ti,tmp423",
+ .data = (void *)4
+ },
+ {
+ .compatible = "ti,tmp441",
+ .data = (void *)2
+ },
+ {
+ .compatible = "ti,tmp422",
+ .data = (void *)3
+ },
+ { },
+};
+MODULE_DEVICE_TABLE(of, tmp421_of_match);
+
struct tmp421_data {
struct i2c_client *client;
struct mutex update_lock;
struct hwmon_chip_info chip;
char valid;
unsigned long last_updated;
- int channels;
+ unsigned long channels;
u8 config;
s16 temp[4];
};
return -ENOMEM;
mutex_init(&data->update_lock);
- data->channels = id->driver_data;
+ if (client->dev.of_node)
+ data->channels = (unsigned long)
+ of_device_get_match_data(&client->dev);
+ else
+ data->channels = id->driver_data;
data->client = client;
err = tmp421_init_client(client);
.class = I2C_CLASS_HWMON,
.driver = {
.name = "tmp421",
+ .of_match_table = of_match_ptr(tmp421_of_match),
},
.probe = tmp421_probe,
.id_table = tmp421_id,
+++ /dev/null
-/*
- *
- * TWL4030 MADC Hwmon driver-This driver monitors the real time
- * conversion of analog signals like battery temperature,
- * battery type, battery level etc. User can ask for the conversion on a
- * particular channel using the sysfs nodes.
- *
- * Copyright (C) 2011 Texas Instruments Incorporated - http://www.ti.com/
- * J Keerthy <j-keerthy@ti.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
- *
- */
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/i2c/twl.h>
-#include <linux/device.h>
-#include <linux/platform_device.h>
-#include <linux/i2c/twl4030-madc.h>
-#include <linux/hwmon.h>
-#include <linux/hwmon-sysfs.h>
-#include <linux/stddef.h>
-#include <linux/sysfs.h>
-#include <linux/err.h>
-#include <linux/types.h>
-
-/*
- * sysfs hook function
- */
-static ssize_t madc_read(struct device *dev,
- struct device_attribute *devattr, char *buf)
-{
- struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
- struct twl4030_madc_request req = {
- .channels = 1 << attr->index,
- .method = TWL4030_MADC_SW2,
- .type = TWL4030_MADC_WAIT,
- };
- long val;
-
- val = twl4030_madc_conversion(&req);
- if (val < 0)
- return val;
-
- return sprintf(buf, "%d\n", req.rbuf[attr->index]);
-}
-
-/* sysfs nodes to read individual channels from user side */
-static SENSOR_DEVICE_ATTR(in0_input, S_IRUGO, madc_read, NULL, 0);
-static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, madc_read, NULL, 1);
-static SENSOR_DEVICE_ATTR(in2_input, S_IRUGO, madc_read, NULL, 2);
-static SENSOR_DEVICE_ATTR(in3_input, S_IRUGO, madc_read, NULL, 3);
-static SENSOR_DEVICE_ATTR(in4_input, S_IRUGO, madc_read, NULL, 4);
-static SENSOR_DEVICE_ATTR(in5_input, S_IRUGO, madc_read, NULL, 5);
-static SENSOR_DEVICE_ATTR(in6_input, S_IRUGO, madc_read, NULL, 6);
-static SENSOR_DEVICE_ATTR(in7_input, S_IRUGO, madc_read, NULL, 7);
-static SENSOR_DEVICE_ATTR(in8_input, S_IRUGO, madc_read, NULL, 8);
-static SENSOR_DEVICE_ATTR(in9_input, S_IRUGO, madc_read, NULL, 9);
-static SENSOR_DEVICE_ATTR(curr10_input, S_IRUGO, madc_read, NULL, 10);
-static SENSOR_DEVICE_ATTR(in11_input, S_IRUGO, madc_read, NULL, 11);
-static SENSOR_DEVICE_ATTR(in12_input, S_IRUGO, madc_read, NULL, 12);
-static SENSOR_DEVICE_ATTR(in15_input, S_IRUGO, madc_read, NULL, 15);
-
-static struct attribute *twl4030_madc_attrs[] = {
- &sensor_dev_attr_in0_input.dev_attr.attr,
- &sensor_dev_attr_temp1_input.dev_attr.attr,
- &sensor_dev_attr_in2_input.dev_attr.attr,
- &sensor_dev_attr_in3_input.dev_attr.attr,
- &sensor_dev_attr_in4_input.dev_attr.attr,
- &sensor_dev_attr_in5_input.dev_attr.attr,
- &sensor_dev_attr_in6_input.dev_attr.attr,
- &sensor_dev_attr_in7_input.dev_attr.attr,
- &sensor_dev_attr_in8_input.dev_attr.attr,
- &sensor_dev_attr_in9_input.dev_attr.attr,
- &sensor_dev_attr_curr10_input.dev_attr.attr,
- &sensor_dev_attr_in11_input.dev_attr.attr,
- &sensor_dev_attr_in12_input.dev_attr.attr,
- &sensor_dev_attr_in15_input.dev_attr.attr,
- NULL
-};
-ATTRIBUTE_GROUPS(twl4030_madc);
-
-static int twl4030_madc_hwmon_probe(struct platform_device *pdev)
-{
- struct device *hwmon;
-
- hwmon = devm_hwmon_device_register_with_groups(&pdev->dev,
- "twl4030_madc", NULL,
- twl4030_madc_groups);
- return PTR_ERR_OR_ZERO(hwmon);
-}
-
-static struct platform_driver twl4030_madc_hwmon_driver = {
- .probe = twl4030_madc_hwmon_probe,
- .driver = {
- .name = "twl4030_madc_hwmon",
- },
-};
-
-module_platform_driver(twl4030_madc_hwmon_driver);
-
-MODULE_DESCRIPTION("TWL4030 ADC Hwmon driver");
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("J Keerthy");
-MODULE_ALIAS("platform:twl4030_madc_hwmon");
outb(ld, ioreg + 1);
}
-static inline void
+static inline int
superio_enter(int ioreg)
{
+ if (!request_muxed_region(ioreg, 2, DRVNAME))
+ return -EBUSY;
+
outb(0x87, ioreg);
outb(0x87, ioreg);
+
+ return 0;
}
static inline void
outb(0xaa, ioreg);
outb(0x02, ioreg);
outb(0x02, ioreg + 1);
+ release_region(ioreg, 2);
}
/*
return;
}
- superio_enter(sio_data->sioreg);
-
/* fan4 and fan5 share some pins with the GPIO and serial flash */
if (sio_data->kind == nct6775) {
/* On NCT6775, fan4 shares pins with the fdc interface */
fan4min = fan4pin;
}
- superio_exit(sio_data->sioreg);
-
data->has_fan = data->has_fan_min = 0x03; /* fan1 and fan2 */
data->has_fan |= (fan3pin << 2);
data->has_fan_min |= (fan3pin << 2);
w83627ehf_init_device(data, sio_data->kind);
data->vrm = vid_which_vrm();
- superio_enter(sio_data->sioreg);
+
+ err = superio_enter(sio_data->sioreg);
+ if (err)
+ goto exit_release;
+
/* Read VID value */
if (sio_data->kind == w83667hg || sio_data->kind == w83667hg_b ||
sio_data->kind == nct6775 || sio_data->kind == nct6776) {
superio_select(sio_data->sioreg, W83667HG_LD_VID);
data->vid = superio_inb(sio_data->sioreg, 0xe3);
err = device_create_file(dev, &dev_attr_cpu0_vid);
- if (err)
+ if (err) {
+ superio_exit(sio_data->sioreg);
goto exit_release;
+ }
} else if (sio_data->kind != w83627uhg) {
superio_select(sio_data->sioreg, W83627EHF_LD_HWM);
if (superio_inb(sio_data->sioreg, SIO_REG_VID_CTRL) & 0x80) {
data->vid &= 0x3f;
err = device_create_file(dev, &dev_attr_cpu0_vid);
- if (err)
+ if (err) {
+ superio_exit(sio_data->sioreg);
goto exit_release;
+ }
} else {
dev_info(dev,
"VID pins in output mode, CPU VID not available\n");
pr_info("Enabled fan debounce for chip %s\n", data->name);
}
- superio_exit(sio_data->sioreg);
-
w83627ehf_check_fan_inputs(sio_data, data);
+ superio_exit(sio_data->sioreg);
+
/* Read fan clock dividers immediately */
w83627ehf_update_fan_div_common(dev, data);
u16 val;
const char *sio_name;
+ int err;
- superio_enter(sioaddr);
+ err = superio_enter(sioaddr);
+ if (err)
+ return err;
if (force_id)
val = force_id;
static unsigned long etb_reset_buffer(struct coresight_device *csdev,
struct perf_output_handle *handle,
- void *sink_config, bool *lost)
+ void *sink_config)
{
unsigned long size = 0;
struct cs_buffers *buf = sink_config;
* resetting parameters here and squaring off with the ring
* buffer API in the tracer PMU is fine.
*/
- *lost = !!local_xchg(&buf->lost, 0);
size = local_xchg(&buf->data_size, 0);
}
(unsigned long)write_ptr);
write_ptr &= ~(ETB_FRAME_SIZE_WORDS - 1);
- local_inc(&buf->lost);
+ perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
}
/*
*/
status = readl_relaxed(drvdata->base + ETB_STATUS_REG);
if (status & ETB_STATUS_RAM_FULL) {
- local_inc(&buf->lost);
+ perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
to_read = capacity;
read_ptr = write_ptr;
} else {
if (read_ptr > (drvdata->buffer_depth - 1))
read_ptr -= drvdata->buffer_depth;
/* let the decoder know we've skipped ahead */
- local_inc(&buf->lost);
+ perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
}
/* finally tell HW where we want to start reading from */
return;
fail_end_stop:
- perf_aux_output_end(handle, 0, true);
+ perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
+ perf_aux_output_end(handle, 0);
fail:
event->hw.state = PERF_HES_STOPPED;
goto out;
static void etm_event_stop(struct perf_event *event, int mode)
{
- bool lost;
int cpu = smp_processor_id();
unsigned long size;
struct coresight_device *sink, *csdev = per_cpu(csdev_src, cpu);
return;
size = sink_ops(sink)->reset_buffer(sink, handle,
- event_data->snk_config,
- &lost);
+ event_data->snk_config);
- perf_aux_output_end(handle, size, lost);
+ perf_aux_output_end(handle, size);
}
/* Disabling the path make its elements available to other sessions */
* @nr_pages: max number of pages granted to us
* @offset: offset within the current buffer
* @data_size: how much we collected in this run
- * @lost: other than zero if we had a HW buffer wrap around
* @snapshot: is this run in snapshot mode
* @data_pages: a handle the ring buffer
*/
unsigned int nr_pages;
unsigned long offset;
local_t data_size;
- local_t lost;
bool snapshot;
void **data_pages;
};
static unsigned long tmc_reset_etf_buffer(struct coresight_device *csdev,
struct perf_output_handle *handle,
- void *sink_config, bool *lost)
+ void *sink_config)
{
long size = 0;
struct cs_buffers *buf = sink_config;
* resetting parameters here and squaring off with the ring
* buffer API in the tracer PMU is fine.
*/
- *lost = !!local_xchg(&buf->lost, 0);
size = local_xchg(&buf->data_size, 0);
}
*/
status = readl_relaxed(drvdata->base + TMC_STS);
if (status & TMC_STS_FULL) {
- local_inc(&buf->lost);
+ perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
to_read = drvdata->size;
} else {
to_read = CIRC_CNT(write_ptr, read_ptr, drvdata->size);
read_ptr -= drvdata->size;
/* Tell the HW */
writel_relaxed(read_ptr, drvdata->base + TMC_RRP);
- local_inc(&buf->lost);
+ perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED);
}
cur = buf->cur;
memcpy(scsi_req(rq)->cmd, pc->c, 12);
if (drive->media == ide_tape)
scsi_req(rq)->cmd[13] = REQ_IDETAPE_PC1;
- error = blk_execute_rq(drive->queue, disk, rq, 0);
+ blk_execute_rq(drive->queue, disk, rq, 0);
+ error = scsi_req(rq)->result ? -EIO : 0;
put_req:
blk_put_request(rq);
return error;
debug_log("%s: I/O error\n", drive->name);
if (drive->media != ide_tape)
- pc->rq->errors++;
+ scsi_req(pc->rq)->result++;
if (scsi_req(rq)->cmd[0] == REQUEST_SENSE) {
printk(KERN_ERR PFX "%s: I/O error in request "
drive->failed_pc = NULL;
if (ata_misc_request(rq)) {
- rq->errors = 0;
+ scsi_req(rq)->result = 0;
error = 0;
} else {
if (blk_rq_is_passthrough(rq) && uptodate <= 0) {
- if (rq->errors == 0)
- rq->errors = -EIO;
+ if (scsi_req(rq)->result == 0)
+ scsi_req(rq)->result = -EIO;
}
error = uptodate ? 0 : -EIO;
struct cdrom_info *info = drive->driver_data;
- if (!rq->errors)
+ if (!scsi_req(rq)->result)
info->write_timeout = jiffies + ATAPI_WAIT_WRITE_BUSY;
- rq->errors = 1;
+ scsi_req(rq)->result = 1;
if (time_after(jiffies, info->write_timeout))
return 0;
}
/* if we have an error, pass CHECK_CONDITION as the SCSI status byte */
- if (blk_rq_is_scsi(rq) && !rq->errors)
- rq->errors = SAM_STAT_CHECK_CONDITION;
+ if (blk_rq_is_scsi(rq) && !scsi_req(rq)->result)
+ scsi_req(rq)->result = SAM_STAT_CHECK_CONDITION;
if (blk_noretry_request(rq))
do_end_request = 1;
* Arrange to retry the request but be sure to give up if we've
* retried too many times.
*/
- if (++rq->errors > ERROR_MAX)
+ if (++scsi_req(rq)->result > ERROR_MAX)
do_end_request = 1;
break;
case ILLEGAL_REQUEST:
/* go to the default handler for other errors */
ide_error(drive, "cdrom_decode_status", stat);
return 1;
- } else if (++rq->errors > ERROR_MAX)
+ } else if (++scsi_req(rq)->result > ERROR_MAX)
/* we've racked up too many retries, abort */
do_end_request = 1;
}
}
}
- error = blk_execute_rq(drive->queue, info->disk, rq, 0);
+ blk_execute_rq(drive->queue, info->disk, rq, 0);
+ error = scsi_req(rq)->result ? -EIO : 0;
if (buffer)
*bufflen = scsi_req(rq)->resid_len;
if (cmd->nleft == 0)
uptodate = 1;
} else {
- if (uptodate <= 0 && rq->errors == 0)
- rq->errors = -EIO;
+ if (uptodate <= 0 && scsi_req(rq)->result == 0)
+ scsi_req(rq)->result = -EIO;
}
if (uptodate == 0 && rq->bio)
* appropriate action
*/
if (c[0] == MODE_SENSE || c[0] == MODE_SELECT) {
- rq->errors = ILLEGAL_REQUEST;
+ scsi_req(rq)->result = ILLEGAL_REQUEST;
return BLKPREP_KILL;
}
scsi_req_init(rq);
ide_req(rq)->type = ATA_PRIV_MISC;
rq->rq_flags = RQF_QUIET;
- ret = blk_execute_rq(drive->queue, cd->disk, rq, 0);
+ blk_execute_rq(drive->queue, cd->disk, rq, 0);
+ ret = scsi_req(rq)->result ? -EIO : 0;
blk_put_request(rq);
/*
* A reset will unlock the door. If it was previously locked,
*(int *)&scsi_req(rq)->cmd[1] = arg;
rq->special = setting->set;
- if (blk_execute_rq(q, NULL, rq, 0))
- ret = rq->errors;
+ blk_execute_rq(q, NULL, rq, 0);
+ ret = scsi_req(rq)->result;
blk_put_request(rq);
return ret;
err = setfunc(drive, *(int *)&scsi_req(rq)->cmd[1]);
if (err)
- rq->errors = err;
- ide_complete_rq(drive, err, blk_rq_bytes(rq));
+ scsi_req(rq)->result = err;
+ ide_complete_rq(drive, 0, blk_rq_bytes(rq));
return ide_stopped;
}
static int set_multcount(ide_drive_t *drive, int arg)
{
struct request *rq;
- int error;
if (arg < 0 || arg > (drive->id[ATA_ID_MAX_MULTSECT] & 0xff))
return -EINVAL;
drive->mult_req = arg;
drive->special_flags |= IDE_SFLAG_SET_MULTMODE;
- error = blk_execute_rq(drive->queue, NULL, rq, 0);
+ blk_execute_rq(drive->queue, NULL, rq, 0);
blk_put_request(rq);
return (drive->mult_count == arg) ? 0 : -EIO;
* make sure request is sane
*/
if (hwif->rq)
- hwif->rq->errors = 0;
+ scsi_req(hwif->rq)->result = 0;
return ret;
}
if ((stat & ATA_BUSY) ||
((stat & ATA_DF) && (drive->dev_flags & IDE_DFLAG_NOWERR) == 0)) {
/* other bits are useless when BUSY */
- rq->errors |= ERROR_RESET;
+ scsi_req(rq)->result |= ERROR_RESET;
} else if (stat & ATA_ERR) {
/* err has different meaning on cdrom and tape */
if (err == ATA_ABORTED) {
drive->crc_count++;
} else if (err & (ATA_BBK | ATA_UNC)) {
/* retries won't help these */
- rq->errors = ERROR_MAX;
+ scsi_req(rq)->result = ERROR_MAX;
} else if (err & ATA_TRK0NF) {
/* help it find track zero */
- rq->errors |= ERROR_RECAL;
+ scsi_req(rq)->result |= ERROR_RECAL;
}
}
ide_pad_transfer(drive, READ, nsect * SECTOR_SIZE);
}
- if (rq->errors >= ERROR_MAX || blk_noretry_request(rq)) {
+ if (scsi_req(rq)->result >= ERROR_MAX || blk_noretry_request(rq)) {
ide_kill_rq(drive, rq);
return ide_stopped;
}
if (hwif->tp_ops->read_status(hwif) & (ATA_BUSY | ATA_DRQ))
- rq->errors |= ERROR_RESET;
+ scsi_req(rq)->result |= ERROR_RESET;
- if ((rq->errors & ERROR_RESET) == ERROR_RESET) {
- ++rq->errors;
+ if ((scsi_req(rq)->result & ERROR_RESET) == ERROR_RESET) {
+ ++scsi_req(rq)->result;
return ide_do_reset(drive);
}
- if ((rq->errors & ERROR_RECAL) == ERROR_RECAL)
+ if ((scsi_req(rq)->result & ERROR_RECAL) == ERROR_RECAL)
drive->special_flags |= IDE_SFLAG_RECALIBRATE;
- ++rq->errors;
+ ++scsi_req(rq)->result;
return ide_stopped;
}
if ((stat & ATA_BUSY) ||
((stat & ATA_DF) && (drive->dev_flags & IDE_DFLAG_NOWERR) == 0)) {
/* other bits are useless when BUSY */
- rq->errors |= ERROR_RESET;
+ scsi_req(rq)->result |= ERROR_RESET;
} else {
/* add decoding error stuff */
}
/* force an abort */
hwif->tp_ops->exec_command(hwif, ATA_CMD_IDLEIMMEDIATE);
- if (rq->errors >= ERROR_MAX) {
+ if (scsi_req(rq)->result >= ERROR_MAX) {
ide_kill_rq(drive, rq);
} else {
- if ((rq->errors & ERROR_RESET) == ERROR_RESET) {
- ++rq->errors;
+ if ((scsi_req(rq)->result & ERROR_RESET) == ERROR_RESET) {
+ ++scsi_req(rq)->result;
return ide_do_reset(drive);
}
- ++rq->errors;
+ ++scsi_req(rq)->result;
}
return ide_stopped;
if (cmd)
ide_complete_cmd(drive, cmd, stat, err);
} else if (ata_pm_request(rq)) {
- rq->errors = 1;
+ scsi_req(rq)->result = 1;
ide_complete_pm_rq(drive, rq);
return ide_stopped;
}
- rq->errors = err;
+ scsi_req(rq)->result = err;
ide_complete_rq(drive, err ? -EIO : 0, blk_rq_bytes(rq));
return ide_stopped;
}
if (rq && ata_misc_request(rq) &&
scsi_req(rq)->cmd[0] == REQ_DRIVE_RESET) {
- if (err <= 0 && rq->errors == 0)
- rq->errors = -EIO;
+ if (err <= 0 && scsi_req(rq)->result == 0)
+ scsi_req(rq)->result = -EIO;
ide_complete_rq(drive, err ? err : 0, blk_rq_bytes(rq));
}
}
}
if (ata_misc_request(rq))
- rq->errors = uptodate ? 0 : IDE_DRV_ERROR_GENERAL;
+ scsi_req(rq)->result = uptodate ? 0 : IDE_DRV_ERROR_GENERAL;
return uptodate;
}
? rq->rq_disk->disk_name
: "dev?"));
- if (rq->errors >= ERROR_MAX) {
+ if (scsi_req(rq)->result >= ERROR_MAX) {
if (drive->failed_pc) {
ide_floppy_report_error(floppy, drive->failed_pc);
drive->failed_pc = NULL;
printk(KERN_ERR PFX "%s: I/O error\n", drive->name);
if (ata_misc_request(rq)) {
- rq->errors = 0;
+ scsi_req(rq)->result = 0;
ide_complete_rq(drive, 0, blk_rq_bytes(rq));
return ide_stopped;
} else
return ide_floppy_issue_pc(drive, &cmd, pc);
out_end:
drive->failed_pc = NULL;
- if (blk_rq_is_passthrough(rq) && rq->errors == 0)
- rq->errors = -EIO;
+ if (blk_rq_is_passthrough(rq) && scsi_req(rq)->result == 0)
+ scsi_req(rq)->result = -EIO;
ide_complete_rq(drive, -EIO, blk_rq_bytes(rq));
return ide_stopped;
}
drive->failed_pc = NULL;
if ((media == ide_floppy || media == ide_tape) && drv_req) {
- rq->errors = 0;
+ scsi_req(rq)->result = 0;
} else {
if (media == ide_tape)
- rq->errors = IDE_DRV_ERROR_GENERAL;
- else if (blk_rq_is_passthrough(rq) && rq->errors == 0)
- rq->errors = -EIO;
+ scsi_req(rq)->result = IDE_DRV_ERROR_GENERAL;
+ else if (blk_rq_is_passthrough(rq) && scsi_req(rq)->result == 0)
+ scsi_req(rq)->result = -EIO;
}
ide_complete_rq(drive, -EIO, blk_rq_bytes(rq));
#ifdef DEBUG
printk("%s: DRIVE_CMD (null)\n", drive->name);
#endif
- rq->errors = 0;
+ scsi_req(rq)->result = 0;
ide_complete_rq(drive, 0, blk_rq_bytes(rq));
return ide_stopped;
rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
scsi_req_init(rq);
ide_req(rq)->type = ATA_PRIV_TASKFILE;
- err = blk_execute_rq(drive->queue, NULL, rq, 0);
+ blk_execute_rq(drive->queue, NULL, rq, 0);
+ err = scsi_req(rq)->result ? -EIO : 0;
blk_put_request(rq);
return err;
ide_req(rq)->type = ATA_PRIV_MISC;
scsi_req(rq)->cmd_len = 1;
scsi_req(rq)->cmd[0] = REQ_DRIVE_RESET;
- if (blk_execute_rq(drive->queue, NULL, rq, 1))
- ret = rq->errors;
+ blk_execute_rq(drive->queue, NULL, rq, 1);
+ ret = scsi_req(rq)->result;
blk_put_request(rq);
return ret;
}
scsi_req(rq)->cmd_len = 1;
ide_req(rq)->type = ATA_PRIV_MISC;
rq->special = &timeout;
- rc = blk_execute_rq(q, NULL, rq, 1);
+ blk_execute_rq(q, NULL, rq, 1);
+ rc = scsi_req(rq)->result ? -EIO : 0;
blk_put_request(rq);
if (rc)
goto out;
mesg.event = PM_EVENT_FREEZE;
rqpm.pm_state = mesg.event;
- ret = blk_execute_rq(drive->queue, NULL, rq, 0);
+ blk_execute_rq(drive->queue, NULL, rq, 0);
+ ret = scsi_req(rq)->result ? -EIO : 0;
blk_put_request(rq);
if (ret == 0 && ide_port_acpi(hwif)) {
spin_lock_irq(q->queue_lock);
if (unlikely(blk_queue_dying(q))) {
rq->rq_flags |= RQF_QUIET;
- rq->errors = -ENXIO;
- __blk_end_request_all(rq, rq->errors);
+ scsi_req(rq)->result = -ENXIO;
+ __blk_end_request_all(rq, 0);
spin_unlock_irq(q->queue_lock);
return -ENXIO;
}
wait_for_completion_io(&wait);
- return rq->errors ? -EIO : 0;
+ return scsi_req(rq)->result ? -EIO : 0;
}
int generic_ide_resume(struct device *dev)
err = pc->error;
}
}
- rq->errors = err;
+ scsi_req(rq)->result = err;
return uptodate;
}
tape->valid = 0;
ret = size;
- if (rq->errors == IDE_DRV_ERROR_GENERAL)
+ if (scsi_req(rq)->result == IDE_DRV_ERROR_GENERAL)
ret = -EIO;
out_put:
blk_put_request(rq);
u8 saved_io_32bit = drive->io_32bit;
if (cmd->tf_flags & IDE_TFLAG_FS)
- cmd->rq->errors = 0;
+ scsi_req(cmd->rq)->result = 0;
if (cmd->tf_flags & IDE_TFLAG_IO_16BIT)
drive->io_32bit = 0;
u8 set_xfer = !!(cmd->tf_flags & IDE_TFLAG_SET_XFER);
ide_complete_cmd(drive, cmd, stat, err);
- rq->errors = err;
+ scsi_req(rq)->result = err;
if (err == 0 && set_xfer) {
ide_set_xfer_rate(drive, nsect);
rq->special = cmd;
cmd->rq = rq;
- error = blk_execute_rq(drive->queue, NULL, rq, 0);
-
+ blk_execute_rq(drive->queue, NULL, rq, 0);
+ error = scsi_req(rq)->result ? -EIO : 0;
put_req:
blk_put_request(rq);
return error;
name = "accel_3d";
channel_spec = accel_3d_channels;
channel_size = sizeof(accel_3d_channels);
+ indio_dev->num_channels = ARRAY_SIZE(accel_3d_channels);
} else {
name = "gravity";
channel_spec = gravity_channels;
channel_size = sizeof(gravity_channels);
+ indio_dev->num_channels = ARRAY_SIZE(gravity_channels);
}
ret = hid_sensor_parse_common_attributes(hsdev, hsdev->usage,
&accel_state->common_attributes);
goto error_free_dev_mem;
}
- indio_dev->num_channels = ARRAY_SIZE(accel_3d_channels);
indio_dev->dev.parent = &pdev->dev;
indio_dev->info = &accel_3d_info;
indio_dev->name = name;
ret = st->core.read_ec_sensors_data(indio_dev, 1 << idx, &data);
if (ret < 0)
break;
-
+ ret = IIO_VAL_INT;
*val = data;
break;
case IIO_CHAN_INFO_CALIBBIAS:
for (i = CROS_EC_SENSOR_X; i < CROS_EC_SENSOR_MAX_AXIS; i++)
st->core.calib[i] =
st->core.resp->sensor_offset.offset[i];
-
+ ret = IIO_VAL_INT;
*val = st->core.calib[idx];
break;
case IIO_CHAN_INFO_SCALE:
{
struct hid_sensor_hub_attribute_info timestamp;
+ s32 value;
+ int ret;
hid_sensor_get_reporting_interval(hsdev, usage_id, st);
st->sensitivity.index, st->sensitivity.report_id,
timestamp.index, timestamp.report_id);
+ ret = sensor_hub_get_feature(hsdev,
+ st->power_state.report_id,
+ st->power_state.index, sizeof(value), &value);
+ if (ret < 0)
+ return ret;
+ if (value < 0)
+ return -EINVAL;
+
return 0;
}
EXPORT_SYMBOL(hid_sensor_parse_common_attributes);
#include <linux/iio/trigger_consumer.h>
#include <linux/iio/triggered_buffer.h>
#include <linux/regmap.h>
+#include <linux/delay.h>
#include "bmg160.h"
#define BMG160_IRQ_NAME "bmg160_event"
#define BMG160_DEF_BW 100
#define BMG160_REG_PMU_BW_RES BIT(7)
+#define BMG160_GYRO_REG_RESET 0x14
+#define BMG160_GYRO_RESET_VAL 0xb6
+
#define BMG160_REG_INT_MAP_0 0x17
#define BMG160_INT_MAP_0_BIT_ANY BIT(1)
int ret;
unsigned int val;
+ /*
+ * Reset chip to get it in a known good state. A delay of 30ms after
+ * reset is required according to the datasheet.
+ */
+ regmap_write(data->regmap, BMG160_GYRO_REG_RESET,
+ BMG160_GYRO_RESET_VAL);
+ usleep_range(30000, 30700);
+
ret = regmap_read(data->regmap, BMG160_REG_CHIP_ID, &val);
if (ret < 0) {
dev_err(dev, "Error reading reg_chip_id\n");
tmp0 = (int)div_s64_rem(tmp, 1000000000, &tmp1);
return snprintf(buf, len, "%d.%09u", tmp0, abs(tmp1));
case IIO_VAL_FRACTIONAL_LOG2:
- tmp = (s64)vals[0] * 1000000000LL >> vals[1];
- tmp1 = do_div(tmp, 1000000000LL);
- tmp0 = tmp;
- return snprintf(buf, len, "%d.%09u", tmp0, tmp1);
+ tmp = shift_right((s64)vals[0] * 1000000000LL, vals[1]);
+ tmp0 = (int)div_s64_rem(tmp, 1000000000LL, &tmp1);
+ return snprintf(buf, len, "%d.%09u", tmp0, abs(tmp1));
case IIO_VAL_INT_MULTIPLE:
{
int i;
.addr_stat_drdy = ST_SENSORS_DEFAULT_STAT_ADDR,
},
.multi_read_bit = true,
+ .bootime = 2,
},
};
rx_wr->sg_list = &rx_desc->rx_sg;
rx_wr->num_sge = 1;
rx_wr->next = rx_wr + 1;
+ rx_desc->in_use = false;
}
rx_wr--;
rx_wr->next = NULL; /* mark end of work requests list */
struct ib_recv_wr *rx_wr_failed, rx_wr;
int ret;
+ if (!rx_desc->in_use) {
+ /*
+ * if the descriptor is not in-use we already reposted it
+ * for recv, so just silently return
+ */
+ return 0;
+ }
+
+ rx_desc->in_use = false;
rx_wr.wr_cqe = &rx_desc->rx_cqe;
rx_wr.sg_list = &rx_desc->rx_sg;
rx_wr.num_sge = 1;
return;
}
+ rx_desc->in_use = true;
+
ib_dma_sync_single_for_cpu(ib_dev, rx_desc->dma_addr,
ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE);
ret = isert_check_pi_status(cmd, isert_cmd->rw.sig->sig_mr);
isert_rdma_rw_ctx_destroy(isert_cmd, isert_conn);
- if (ret)
- transport_send_check_condition_and_sense(cmd, cmd->pi_err, 0);
- else
- isert_put_response(isert_conn->conn, isert_cmd->iscsi_cmd);
+ if (ret) {
+ /*
+ * transport_generic_request_failure() expects to have
+ * plus two references to handle queue-full, so re-add
+ * one here as target-core will have already dropped
+ * it after the first isert_put_datain() callback.
+ */
+ kref_get(&cmd->cmd_kref);
+ transport_generic_request_failure(cmd, cmd->pi_err);
+ } else {
+ /*
+ * XXX: isert_put_response() failure is not retried.
+ */
+ ret = isert_put_response(isert_conn->conn, isert_cmd->iscsi_cmd);
+ if (ret)
+ pr_warn_ratelimited("isert_put_response() ret: %d\n", ret);
+ }
}
static void
cmd->i_state = ISTATE_RECEIVED_LAST_DATAOUT;
spin_unlock_bh(&cmd->istate_lock);
- if (ret) {
- target_put_sess_cmd(se_cmd);
- transport_send_check_condition_and_sense(se_cmd,
- se_cmd->pi_err, 0);
- } else {
+ /*
+ * transport_generic_request_failure() will drop the extra
+ * se_cmd->cmd_kref reference after T10-PI error, and handle
+ * any non-zero ->queue_status() callback error retries.
+ */
+ if (ret)
+ transport_generic_request_failure(se_cmd, se_cmd->pi_err);
+ else
target_execute_cmd(se_cmd);
- }
}
static void
chain_wr = &isert_cmd->tx_desc.send_wr;
}
- isert_rdma_rw_ctx_post(isert_cmd, isert_conn, cqe, chain_wr);
- isert_dbg("Cmd: %p posted RDMA_WRITE for iSER Data READ\n", isert_cmd);
- return 1;
+ rc = isert_rdma_rw_ctx_post(isert_cmd, isert_conn, cqe, chain_wr);
+ isert_dbg("Cmd: %p posted RDMA_WRITE for iSER Data READ rc: %d\n",
+ isert_cmd, rc);
+ return rc;
}
static int
isert_get_dataout(struct iscsi_conn *conn, struct iscsi_cmd *cmd, bool recovery)
{
struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd);
+ int ret;
isert_dbg("Cmd: %p RDMA_READ data_length: %u write_data_done: %u\n",
isert_cmd, cmd->se_cmd.data_length, cmd->write_data_done);
isert_cmd->tx_desc.tx_cqe.done = isert_rdma_read_done;
- isert_rdma_rw_ctx_post(isert_cmd, conn->context,
- &isert_cmd->tx_desc.tx_cqe, NULL);
+ ret = isert_rdma_rw_ctx_post(isert_cmd, conn->context,
+ &isert_cmd->tx_desc.tx_cqe, NULL);
- isert_dbg("Cmd: %p posted RDMA_READ memory for ISER Data WRITE\n",
- isert_cmd);
- return 0;
+ isert_dbg("Cmd: %p posted RDMA_READ memory for ISER Data WRITE rc: %d\n",
+ isert_cmd, ret);
+ return ret;
}
static int
#define ISER_RX_PAD_SIZE (ISCSI_DEF_MAX_RECV_SEG_LEN + 4096 - \
(ISER_RX_PAYLOAD_SIZE + sizeof(u64) + sizeof(struct ib_sge) + \
- sizeof(struct ib_cqe)))
+ sizeof(struct ib_cqe) + sizeof(bool)))
#define ISCSI_ISER_SG_TABLESIZE 256
u64 dma_addr;
struct ib_sge rx_sg;
struct ib_cqe rx_cqe;
+ bool in_use;
char pad[ISER_RX_PAD_SIZE];
} __packed;
{ 0x1430, 0x8888, "TX6500+ Dance Pad (first generation)", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX },
{ 0x146b, 0x0601, "BigBen Interactive XBOX 360 Controller", 0, XTYPE_XBOX360 },
{ 0x1532, 0x0037, "Razer Sabertooth", 0, XTYPE_XBOX360 },
+ { 0x1532, 0x0a03, "Razer Wildcat", 0, XTYPE_XBOXONE },
{ 0x15e4, 0x3f00, "Power A Mini Pro Elite", 0, XTYPE_XBOX360 },
{ 0x15e4, 0x3f0a, "Xbox Airflo wired controller", 0, XTYPE_XBOX360 },
{ 0x15e4, 0x3f10, "Batarang Xbox 360 controller", 0, XTYPE_XBOX360 },
XPAD_XBOX360_VENDOR(0x1430), /* RedOctane X-Box 360 controllers */
XPAD_XBOX360_VENDOR(0x146b), /* BigBen Interactive Controllers */
XPAD_XBOX360_VENDOR(0x1532), /* Razer Sabertooth */
+ XPAD_XBOXONE_VENDOR(0x1532), /* Razer Wildcat */
XPAD_XBOX360_VENDOR(0x15e4), /* Numark X-Box 360 controllers */
XPAD_XBOX360_VENDOR(0x162e), /* Joytech X-Box 360 controllers */
XPAD_XBOX360_VENDOR(0x1689), /* Razer Onza */
* Asus UX32VD 0x361f02 00, 15, 0e clickpad
* Avatar AVIU-145A2 0x361f00 ? clickpad
* Fujitsu LIFEBOOK E544 0x470f00 d0, 12, 09 2 hw buttons
+ * Fujitsu LIFEBOOK E547 0x470f00 50, 12, 09 2 hw buttons
* Fujitsu LIFEBOOK E554 0x570f01 40, 14, 0c 2 hw buttons
* Fujitsu T725 0x470f01 05, 12, 09 2 hw buttons
* Fujitsu H730 0x570f00 c0, 14, 0c 3 hw buttons (**)
},
},
{
+ /* Fujitsu LIFEBOOK E547 does not work with crc_enabled == 0 */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E547"),
+ },
+ },
+ {
/* Fujitsu LIFEBOOK E554 does not work with crc_enabled == 0 */
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
DMI_MATCH(DMI_PRODUCT_NAME, "20046"),
},
},
+ {
+ /* Clevo P650RS, 650RP6, Sager NP8152-S, and others */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Notebook"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "P65xRP"),
+ },
+ },
{ }
};
build_inv_iommu_pages(&cmd, address, size, domain->id, pde);
- for (i = 0; i < amd_iommus_present; ++i) {
+ for (i = 0; i < amd_iommu_get_num_iommus(); ++i) {
if (!domain->dev_iommu[i])
continue;
{
int i;
- for (i = 0; i < amd_iommus_present; ++i) {
+ for (i = 0; i < amd_iommu_get_num_iommus(); ++i) {
if (domain && !domain->dev_iommu[i])
continue;
* IOMMU TLB needs to be flushed before Device TLB to
* prevent device TLB refill from IOMMU TLB
*/
- for (i = 0; i < amd_iommus_present; ++i) {
+ for (i = 0; i < amd_iommu_get_num_iommus(); ++i) {
if (domain->dev_iommu[i] == 0)
continue;
/* Array to assign indices to IOMMUs*/
struct amd_iommu *amd_iommus[MAX_IOMMUS];
-int amd_iommus_present;
+
+/* Number of IOMMUs present in the system */
+static int amd_iommus_present;
/* IOMMUs have a non-present cache? */
bool amd_iommu_np_cache __read_mostly;
static int __init iommu_go_to_state(enum iommu_init_state state);
static void init_device_table_dma(void);
-static int iommu_pc_get_set_reg_val(struct amd_iommu *iommu,
- u8 bank, u8 cntr, u8 fxn,
- u64 *value, bool is_write);
-
static inline void update_last_devid(u16 devid)
{
if (devid > amd_iommu_last_bdf)
return 1UL << shift;
}
+int amd_iommu_get_num_iommus(void)
+{
+ return amd_iommus_present;
+}
+
/* Access to l1 and l2 indexed register spaces */
static u32 iommu_read_l1(struct amd_iommu *iommu, u16 l1, u8 address)
/* Add IOMMU to internal data structures */
list_add_tail(&iommu->list, &amd_iommu_list);
- iommu->index = amd_iommus_present++;
+ iommu->index = amd_iommus_present++;
if (unlikely(iommu->index >= MAX_IOMMUS)) {
WARN(1, "AMD-Vi: System has more IOMMUs than supported by this driver\n");
return 0;
}
+static int iommu_pc_get_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
+ u8 fxn, u64 *value, bool is_write);
static void init_iommu_perf_ctr(struct amd_iommu *iommu)
{
amd_iommu_pc_present = true;
/* Check if the performance counters can be written to */
- if ((0 != iommu_pc_get_set_reg_val(iommu, 0, 0, 0, &val, true)) ||
- (0 != iommu_pc_get_set_reg_val(iommu, 0, 0, 0, &val2, false)) ||
+ if ((iommu_pc_get_set_reg(iommu, 0, 0, 0, &val, true)) ||
+ (iommu_pc_get_set_reg(iommu, 0, 0, 0, &val2, false)) ||
(val != val2)) {
pr_err("AMD-Vi: Unable to write to IOMMU perf counter.\n");
amd_iommu_pc_present = false;
}
EXPORT_SYMBOL(amd_iommu_v2_supported);
+struct amd_iommu *get_amd_iommu(unsigned int idx)
+{
+ unsigned int i = 0;
+ struct amd_iommu *iommu;
+
+ for_each_iommu(iommu)
+ if (i++ == idx)
+ return iommu;
+ return NULL;
+}
+EXPORT_SYMBOL(get_amd_iommu);
+
/****************************************************************************
*
* IOMMU EFR Performance Counter support functionality. This code allows
*
****************************************************************************/
-u8 amd_iommu_pc_get_max_banks(u16 devid)
+u8 amd_iommu_pc_get_max_banks(unsigned int idx)
{
- struct amd_iommu *iommu;
- u8 ret = 0;
+ struct amd_iommu *iommu = get_amd_iommu(idx);
- /* locate the iommu governing the devid */
- iommu = amd_iommu_rlookup_table[devid];
if (iommu)
- ret = iommu->max_banks;
+ return iommu->max_banks;
- return ret;
+ return 0;
}
EXPORT_SYMBOL(amd_iommu_pc_get_max_banks);
}
EXPORT_SYMBOL(amd_iommu_pc_supported);
-u8 amd_iommu_pc_get_max_counters(u16 devid)
+u8 amd_iommu_pc_get_max_counters(unsigned int idx)
{
- struct amd_iommu *iommu;
- u8 ret = 0;
+ struct amd_iommu *iommu = get_amd_iommu(idx);
- /* locate the iommu governing the devid */
- iommu = amd_iommu_rlookup_table[devid];
if (iommu)
- ret = iommu->max_counters;
+ return iommu->max_counters;
- return ret;
+ return 0;
}
EXPORT_SYMBOL(amd_iommu_pc_get_max_counters);
-static int iommu_pc_get_set_reg_val(struct amd_iommu *iommu,
- u8 bank, u8 cntr, u8 fxn,
- u64 *value, bool is_write)
+static int iommu_pc_get_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
+ u8 fxn, u64 *value, bool is_write)
{
u32 offset;
u32 max_offset_lim;
+ /* Make sure the IOMMU PC resource is available */
+ if (!amd_iommu_pc_present)
+ return -ENODEV;
+
/* Check for valid iommu and pc register indexing */
- if (WARN_ON((fxn > 0x28) || (fxn & 7)))
+ if (WARN_ON(!iommu || (fxn > 0x28) || (fxn & 7)))
return -ENODEV;
- offset = (u32)(((0x40|bank) << 12) | (cntr << 8) | fxn);
+ offset = (u32)(((0x40 | bank) << 12) | (cntr << 8) | fxn);
/* Limit the offset to the hw defined mmio region aperture */
- max_offset_lim = (u32)(((0x40|iommu->max_banks) << 12) |
+ max_offset_lim = (u32)(((0x40 | iommu->max_banks) << 12) |
(iommu->max_counters << 8) | 0x28);
if ((offset < MMIO_CNTR_REG_OFFSET) ||
(offset > max_offset_lim))
return -EINVAL;
if (is_write) {
- writel((u32)*value, iommu->mmio_base + offset);
- writel((*value >> 32), iommu->mmio_base + offset + 4);
+ u64 val = *value & GENMASK_ULL(47, 0);
+
+ writel((u32)val, iommu->mmio_base + offset);
+ writel((val >> 32), iommu->mmio_base + offset + 4);
} else {
*value = readl(iommu->mmio_base + offset + 4);
*value <<= 32;
- *value = readl(iommu->mmio_base + offset);
+ *value |= readl(iommu->mmio_base + offset);
+ *value &= GENMASK_ULL(47, 0);
}
return 0;
}
-EXPORT_SYMBOL(amd_iommu_pc_get_set_reg_val);
-int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn,
- u64 *value, bool is_write)
+int amd_iommu_pc_get_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, u8 fxn, u64 *value)
{
- struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
+ if (!iommu)
+ return -EINVAL;
- /* Make sure the IOMMU PC resource is available */
- if (!amd_iommu_pc_present || iommu == NULL)
- return -ENODEV;
+ return iommu_pc_get_set_reg(iommu, bank, cntr, fxn, value, false);
+}
+EXPORT_SYMBOL(amd_iommu_pc_get_reg);
+
+int amd_iommu_pc_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, u8 fxn, u64 *value)
+{
+ if (!iommu)
+ return -EINVAL;
- return iommu_pc_get_set_reg_val(iommu, bank, cntr, fxn,
- value, is_write);
+ return iommu_pc_get_set_reg(iommu, bank, cntr, fxn, value, true);
}
+EXPORT_SYMBOL(amd_iommu_pc_set_reg);
#include "amd_iommu_types.h"
+extern int amd_iommu_get_num_iommus(void);
extern int amd_iommu_init_dma_ops(void);
extern int amd_iommu_init_passthrough(void);
extern irqreturn_t amd_iommu_int_thread(int irq, void *data);
extern int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, int pasid);
extern struct iommu_domain *amd_iommu_get_v2_domain(struct pci_dev *pdev);
-/* IOMMU Performance Counter functions */
-extern bool amd_iommu_pc_supported(void);
-extern u8 amd_iommu_pc_get_max_banks(u16 devid);
-extern u8 amd_iommu_pc_get_max_counters(u16 devid);
-extern int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn,
- u64 *value, bool is_write);
-
#ifdef CONFIG_IRQ_REMAP
extern int amd_iommu_create_irq_domain(struct amd_iommu *iommu);
#else
*/
extern struct amd_iommu *amd_iommus[MAX_IOMMUS];
-/* Number of IOMMUs present in the system */
-extern int amd_iommus_present;
-
/*
* Declarations for the global list of all protection domains
*/
select GENERIC_IRQ_CHIP
select IRQ_DOMAIN
+config FARADAY_FTINTC010
+ bool
+ select IRQ_DOMAIN
+ select MULTI_IRQ_HANDLER
+ select SPARSE_IRQ
+
config HISILICON_IRQ_MBIGEN
bool
select ARM_GIC_V3
obj-$(CONFIG_ARCH_BCM2835) += irq-bcm2835.o
obj-$(CONFIG_ARCH_BCM2835) += irq-bcm2836.o
obj-$(CONFIG_ARCH_EXYNOS) += exynos-combiner.o
-obj-$(CONFIG_ARCH_GEMINI) += irq-gemini.o
+obj-$(CONFIG_FARADAY_FTINTC010) += irq-ftintc010.o
obj-$(CONFIG_ARCH_HIP04) += irq-hip04.o
obj-$(CONFIG_ARCH_LPC32XX) += irq-lpc32xx.o
obj-$(CONFIG_ARCH_MMP) += irq-mmp.o
obj-$(CONFIG_DW_APB_ICTL) += irq-dw-apb-ictl.o
obj-$(CONFIG_METAG) += irq-metag-ext.o
obj-$(CONFIG_METAG_PERFCOUNTER_IRQS) += irq-metag.o
-obj-$(CONFIG_ARCH_MOXART) += irq-moxart.o
obj-$(CONFIG_CLPS711X_IRQCHIP) += irq-clps711x.o
obj-$(CONFIG_OR1K_PIC) += irq-or1k-pic.o
obj-$(CONFIG_ORION_IRQCHIP) += irq-orion.o
obj-$(CONFIG_BRCMSTB_L2_IRQ) += irq-brcmstb-l2.o
obj-$(CONFIG_KEYSTONE_IRQ) += irq-keystone.o
obj-$(CONFIG_MIPS_GIC) += irq-mips-gic.o
-obj-$(CONFIG_ARCH_MEDIATEK) += irq-mtk-sysirq.o
+obj-$(CONFIG_ARCH_MEDIATEK) += irq-mtk-sysirq.o irq-mtk-cirq.o
obj-$(CONFIG_ARCH_DIGICOLOR) += irq-digicolor.o
obj-$(CONFIG_RENESAS_H8300H_INTC) += irq-renesas-h8300h.o
obj-$(CONFIG_RENESAS_H8S_INTC) += irq-renesas-h8s.o
}
#ifdef CONFIG_PM
+static u32 *smr_cache;
+
static void aic5_suspend(struct irq_data *d)
{
struct irq_domain *domain = d->domain;
int i;
u32 mask;
+ if (smr_cache)
+ for (i = 0; i < domain->revmap_size; i++) {
+ irq_reg_writel(bgc, i, AT91_AIC5_SSR);
+ smr_cache[i] = irq_reg_readl(bgc, AT91_AIC5_SMR);
+ }
+
irq_gc_lock(bgc);
for (i = 0; i < dgc->irqs_per_chip; i++) {
mask = 1 << i;
u32 mask;
irq_gc_lock(bgc);
+
+ if (smr_cache) {
+ irq_reg_writel(bgc, 0xffffffff, AT91_AIC5_SPU);
+ for (i = 0; i < domain->revmap_size; i++) {
+ irq_reg_writel(bgc, i, AT91_AIC5_SSR);
+ irq_reg_writel(bgc, i, AT91_AIC5_SVR);
+ irq_reg_writel(bgc, smr_cache[i], AT91_AIC5_SMR);
+ }
+ }
+
for (i = 0; i < dgc->irqs_per_chip; i++) {
mask = 1 << i;
- if ((mask & gc->mask_cache) == (mask & gc->wake_active))
+
+ if (!smr_cache &&
+ ((mask & gc->mask_cache) == (mask & gc->wake_active)))
continue;
irq_reg_writel(bgc, i + gc->irq_base, AT91_AIC5_SSR);
static int __init sama5d2_aic5_of_init(struct device_node *node,
struct device_node *parent)
{
+#ifdef CONFIG_PM
+ smr_cache = kcalloc(DIV_ROUND_UP(NR_SAMA5D2_IRQS, 32) * 32,
+ sizeof(*smr_cache), GFP_KERNEL);
+ if (!smr_cache)
+ return -ENOMEM;
+#endif
+
return aic5_of_init(node, parent, NR_SAMA5D2_IRQS);
}
IRQCHIP_DECLARE(sama5d2_aic5, "atmel,sama5d2-aic", sama5d2_aic5_of_init);
--- /dev/null
+/*
+ * irqchip for the Faraday Technology FTINTC010 Copyright (C) 2017 Linus
+ * Walleij <linus.walleij@linaro.org>
+ *
+ * Based on arch/arm/mach-gemini/irq.c
+ * Copyright (C) 2001-2006 Storlink, Corp.
+ * Copyright (C) 2008-2009 Paulius Zaleckas <paulius.zaleckas@gmail.com>
+ */
+#include <linux/bitops.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/irqchip.h>
+#include <linux/irqchip/versatile-fpga.h>
+#include <linux/irqdomain.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/cpu.h>
+
+#include <asm/exception.h>
+#include <asm/mach/irq.h>
+
+#define FT010_NUM_IRQS 32
+
+#define FT010_IRQ_SOURCE(base_addr) (base_addr + 0x00)
+#define FT010_IRQ_MASK(base_addr) (base_addr + 0x04)
+#define FT010_IRQ_CLEAR(base_addr) (base_addr + 0x08)
+/* Selects level- or edge-triggered */
+#define FT010_IRQ_MODE(base_addr) (base_addr + 0x0C)
+/* Selects active low/high or falling/rising edge */
+#define FT010_IRQ_POLARITY(base_addr) (base_addr + 0x10)
+#define FT010_IRQ_STATUS(base_addr) (base_addr + 0x14)
+#define FT010_FIQ_SOURCE(base_addr) (base_addr + 0x20)
+#define FT010_FIQ_MASK(base_addr) (base_addr + 0x24)
+#define FT010_FIQ_CLEAR(base_addr) (base_addr + 0x28)
+#define FT010_FIQ_MODE(base_addr) (base_addr + 0x2C)
+#define FT010_FIQ_POLARITY(base_addr) (base_addr + 0x30)
+#define FT010_FIQ_STATUS(base_addr) (base_addr + 0x34)
+
+/**
+ * struct ft010_irq_data - irq data container for the Faraday IRQ controller
+ * @base: memory offset in virtual memory
+ * @chip: chip container for this instance
+ * @domain: IRQ domain for this instance
+ */
+struct ft010_irq_data {
+ void __iomem *base;
+ struct irq_chip chip;
+ struct irq_domain *domain;
+};
+
+static void ft010_irq_mask(struct irq_data *d)
+{
+ struct ft010_irq_data *f = irq_data_get_irq_chip_data(d);
+ unsigned int mask;
+
+ mask = readl(FT010_IRQ_MASK(f->base));
+ mask &= ~BIT(irqd_to_hwirq(d));
+ writel(mask, FT010_IRQ_MASK(f->base));
+}
+
+static void ft010_irq_unmask(struct irq_data *d)
+{
+ struct ft010_irq_data *f = irq_data_get_irq_chip_data(d);
+ unsigned int mask;
+
+ mask = readl(FT010_IRQ_MASK(f->base));
+ mask |= BIT(irqd_to_hwirq(d));
+ writel(mask, FT010_IRQ_MASK(f->base));
+}
+
+static void ft010_irq_ack(struct irq_data *d)
+{
+ struct ft010_irq_data *f = irq_data_get_irq_chip_data(d);
+
+ writel(BIT(irqd_to_hwirq(d)), FT010_IRQ_CLEAR(f->base));
+}
+
+static int ft010_irq_set_type(struct irq_data *d, unsigned int trigger)
+{
+ struct ft010_irq_data *f = irq_data_get_irq_chip_data(d);
+ int offset = irqd_to_hwirq(d);
+ u32 mode, polarity;
+
+ mode = readl(FT010_IRQ_MODE(f->base));
+ polarity = readl(FT010_IRQ_POLARITY(f->base));
+
+ if (trigger & (IRQ_TYPE_LEVEL_LOW)) {
+ irq_set_handler_locked(d, handle_level_irq);
+ mode &= ~BIT(offset);
+ polarity |= BIT(offset);
+ } else if (trigger & (IRQ_TYPE_LEVEL_HIGH)) {
+ irq_set_handler_locked(d, handle_level_irq);
+ mode &= ~BIT(offset);
+ polarity &= ~BIT(offset);
+ } else if (trigger & IRQ_TYPE_EDGE_FALLING) {
+ irq_set_handler_locked(d, handle_edge_irq);
+ mode |= BIT(offset);
+ polarity |= BIT(offset);
+ } else if (trigger & IRQ_TYPE_EDGE_RISING) {
+ irq_set_handler_locked(d, handle_edge_irq);
+ mode |= BIT(offset);
+ polarity &= ~BIT(offset);
+ } else {
+ irq_set_handler_locked(d, handle_bad_irq);
+ pr_warn("Faraday IRQ: no supported trigger selected for line %d\n",
+ offset);
+ }
+
+ writel(mode, FT010_IRQ_MODE(f->base));
+ writel(polarity, FT010_IRQ_POLARITY(f->base));
+
+ return 0;
+}
+
+static struct irq_chip ft010_irq_chip = {
+ .name = "FTINTC010",
+ .irq_ack = ft010_irq_ack,
+ .irq_mask = ft010_irq_mask,
+ .irq_unmask = ft010_irq_unmask,
+ .irq_set_type = ft010_irq_set_type,
+};
+
+/* Local static for the IRQ entry call */
+static struct ft010_irq_data firq;
+
+asmlinkage void __exception_irq_entry ft010_irqchip_handle_irq(struct pt_regs *regs)
+{
+ struct ft010_irq_data *f = &firq;
+ int irq;
+ u32 status;
+
+ while ((status = readl(FT010_IRQ_STATUS(f->base)))) {
+ irq = ffs(status) - 1;
+ handle_domain_irq(f->domain, irq, regs);
+ }
+}
+
+static int ft010_irqdomain_map(struct irq_domain *d, unsigned int irq,
+ irq_hw_number_t hwirq)
+{
+ struct ft010_irq_data *f = d->host_data;
+
+ irq_set_chip_data(irq, f);
+ /* All IRQs should set up their type, flags as bad by default */
+ irq_set_chip_and_handler(irq, &ft010_irq_chip, handle_bad_irq);
+ irq_set_probe(irq);
+
+ return 0;
+}
+
+static void ft010_irqdomain_unmap(struct irq_domain *d, unsigned int irq)
+{
+ irq_set_chip_and_handler(irq, NULL, NULL);
+ irq_set_chip_data(irq, NULL);
+}
+
+static const struct irq_domain_ops ft010_irqdomain_ops = {
+ .map = ft010_irqdomain_map,
+ .unmap = ft010_irqdomain_unmap,
+ .xlate = irq_domain_xlate_onetwocell,
+};
+
+int __init ft010_of_init_irq(struct device_node *node,
+ struct device_node *parent)
+{
+ struct ft010_irq_data *f = &firq;
+
+ /*
+ * Disable the idle handler by default since it is buggy
+ * For more info see arch/arm/mach-gemini/idle.c
+ */
+ cpu_idle_poll_ctrl(true);
+
+ f->base = of_iomap(node, 0);
+ WARN(!f->base, "unable to map gemini irq registers\n");
+
+ /* Disable all interrupts */
+ writel(0, FT010_IRQ_MASK(f->base));
+ writel(0, FT010_FIQ_MASK(f->base));
+
+ f->domain = irq_domain_add_simple(node, FT010_NUM_IRQS, 0,
+ &ft010_irqdomain_ops, f);
+ set_handle_irq(ft010_irqchip_handle_irq);
+
+ return 0;
+}
+IRQCHIP_DECLARE(faraday, "faraday,ftintc010",
+ ft010_of_init_irq);
+IRQCHIP_DECLARE(gemini, "cortina,gemini-interrupt-controller",
+ ft010_of_init_irq);
+IRQCHIP_DECLARE(moxa, "moxa,moxart-ic",
+ ft010_of_init_irq);
+++ /dev/null
-/*
- * irqchip for the Cortina Systems Gemini Copyright (C) 2017 Linus
- * Walleij <linus.walleij@linaro.org>
- *
- * Based on arch/arm/mach-gemini/irq.c
- * Copyright (C) 2001-2006 Storlink, Corp.
- * Copyright (C) 2008-2009 Paulius Zaleckas <paulius.zaleckas@teltonika.lt>
- */
-#include <linux/bitops.h>
-#include <linux/irq.h>
-#include <linux/io.h>
-#include <linux/irqchip.h>
-#include <linux/irqchip/versatile-fpga.h>
-#include <linux/irqdomain.h>
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-#include <linux/cpu.h>
-
-#include <asm/exception.h>
-#include <asm/mach/irq.h>
-
-#define GEMINI_NUM_IRQS 32
-
-#define GEMINI_IRQ_SOURCE(base_addr) (base_addr + 0x00)
-#define GEMINI_IRQ_MASK(base_addr) (base_addr + 0x04)
-#define GEMINI_IRQ_CLEAR(base_addr) (base_addr + 0x08)
-#define GEMINI_IRQ_MODE(base_addr) (base_addr + 0x0C)
-#define GEMINI_IRQ_POLARITY(base_addr) (base_addr + 0x10)
-#define GEMINI_IRQ_STATUS(base_addr) (base_addr + 0x14)
-#define GEMINI_FIQ_SOURCE(base_addr) (base_addr + 0x20)
-#define GEMINI_FIQ_MASK(base_addr) (base_addr + 0x24)
-#define GEMINI_FIQ_CLEAR(base_addr) (base_addr + 0x28)
-#define GEMINI_FIQ_MODE(base_addr) (base_addr + 0x2C)
-#define GEMINI_FIQ_POLARITY(base_addr) (base_addr + 0x30)
-#define GEMINI_FIQ_STATUS(base_addr) (base_addr + 0x34)
-
-/**
- * struct gemini_irq_data - irq data container for the Gemini IRQ controller
- * @base: memory offset in virtual memory
- * @chip: chip container for this instance
- * @domain: IRQ domain for this instance
- */
-struct gemini_irq_data {
- void __iomem *base;
- struct irq_chip chip;
- struct irq_domain *domain;
-};
-
-static void gemini_irq_mask(struct irq_data *d)
-{
- struct gemini_irq_data *g = irq_data_get_irq_chip_data(d);
- unsigned int mask;
-
- mask = readl(GEMINI_IRQ_MASK(g->base));
- mask &= ~BIT(irqd_to_hwirq(d));
- writel(mask, GEMINI_IRQ_MASK(g->base));
-}
-
-static void gemini_irq_unmask(struct irq_data *d)
-{
- struct gemini_irq_data *g = irq_data_get_irq_chip_data(d);
- unsigned int mask;
-
- mask = readl(GEMINI_IRQ_MASK(g->base));
- mask |= BIT(irqd_to_hwirq(d));
- writel(mask, GEMINI_IRQ_MASK(g->base));
-}
-
-static void gemini_irq_ack(struct irq_data *d)
-{
- struct gemini_irq_data *g = irq_data_get_irq_chip_data(d);
-
- writel(BIT(irqd_to_hwirq(d)), GEMINI_IRQ_CLEAR(g->base));
-}
-
-static int gemini_irq_set_type(struct irq_data *d, unsigned int trigger)
-{
- struct gemini_irq_data *g = irq_data_get_irq_chip_data(d);
- int offset = irqd_to_hwirq(d);
- u32 mode, polarity;
-
- mode = readl(GEMINI_IRQ_MODE(g->base));
- polarity = readl(GEMINI_IRQ_POLARITY(g->base));
-
- if (trigger & (IRQ_TYPE_LEVEL_HIGH)) {
- irq_set_handler_locked(d, handle_level_irq);
- /* Disable edge detection */
- mode &= ~BIT(offset);
- polarity &= ~BIT(offset);
- } else if (trigger & IRQ_TYPE_EDGE_RISING) {
- irq_set_handler_locked(d, handle_edge_irq);
- mode |= BIT(offset);
- polarity |= BIT(offset);
- } else if (trigger & IRQ_TYPE_EDGE_FALLING) {
- irq_set_handler_locked(d, handle_edge_irq);
- mode |= BIT(offset);
- polarity &= ~BIT(offset);
- } else {
- irq_set_handler_locked(d, handle_bad_irq);
- pr_warn("GEMINI IRQ: no supported trigger selected for line %d\n",
- offset);
- }
-
- writel(mode, GEMINI_IRQ_MODE(g->base));
- writel(polarity, GEMINI_IRQ_POLARITY(g->base));
-
- return 0;
-}
-
-static struct irq_chip gemini_irq_chip = {
- .name = "GEMINI",
- .irq_ack = gemini_irq_ack,
- .irq_mask = gemini_irq_mask,
- .irq_unmask = gemini_irq_unmask,
- .irq_set_type = gemini_irq_set_type,
-};
-
-/* Local static for the IRQ entry call */
-static struct gemini_irq_data girq;
-
-asmlinkage void __exception_irq_entry gemini_irqchip_handle_irq(struct pt_regs *regs)
-{
- struct gemini_irq_data *g = &girq;
- int irq;
- u32 status;
-
- while ((status = readl(GEMINI_IRQ_STATUS(g->base)))) {
- irq = ffs(status) - 1;
- handle_domain_irq(g->domain, irq, regs);
- }
-}
-
-static int gemini_irqdomain_map(struct irq_domain *d, unsigned int irq,
- irq_hw_number_t hwirq)
-{
- struct gemini_irq_data *g = d->host_data;
-
- irq_set_chip_data(irq, g);
- /* All IRQs should set up their type, flags as bad by default */
- irq_set_chip_and_handler(irq, &gemini_irq_chip, handle_bad_irq);
- irq_set_probe(irq);
-
- return 0;
-}
-
-static void gemini_irqdomain_unmap(struct irq_domain *d, unsigned int irq)
-{
- irq_set_chip_and_handler(irq, NULL, NULL);
- irq_set_chip_data(irq, NULL);
-}
-
-static const struct irq_domain_ops gemini_irqdomain_ops = {
- .map = gemini_irqdomain_map,
- .unmap = gemini_irqdomain_unmap,
- .xlate = irq_domain_xlate_onetwocell,
-};
-
-int __init gemini_of_init_irq(struct device_node *node,
- struct device_node *parent)
-{
- struct gemini_irq_data *g = &girq;
-
- /*
- * Disable the idle handler by default since it is buggy
- * For more info see arch/arm/mach-gemini/idle.c
- */
- cpu_idle_poll_ctrl(true);
-
- g->base = of_iomap(node, 0);
- WARN(!g->base, "unable to map gemini irq registers\n");
-
- /* Disable all interrupts */
- writel(0, GEMINI_IRQ_MASK(g->base));
- writel(0, GEMINI_FIQ_MASK(g->base));
-
- g->domain = irq_domain_add_simple(node, GEMINI_NUM_IRQS, 0,
- &gemini_irqdomain_ops, g);
- set_handle_irq(gemini_irqchip_handle_irq);
-
- return 0;
-}
-IRQCHIP_DECLARE(gemini, "cortina,gemini-interrupt-controller",
- gemini_of_init_irq);
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/acpi_iort.h>
#include <linux/device.h>
#include <linux/msi.h>
#include <linux/of.h>
.name = "ITS-pMSI",
};
-static int its_pmsi_prepare(struct irq_domain *domain, struct device *dev,
- int nvec, msi_alloc_info_t *info)
+static int of_pmsi_get_dev_id(struct irq_domain *domain, struct device *dev,
+ u32 *dev_id)
{
- struct msi_domain_info *msi_info;
- u32 dev_id;
int ret, index = 0;
- msi_info = msi_get_domain_info(domain->parent);
-
/* Suck the DeviceID out of the msi-parent property */
do {
struct of_phandle_args args;
if (args.np == irq_domain_get_of_node(domain)) {
if (WARN_ON(args.args_count != 1))
return -EINVAL;
- dev_id = args.args[0];
+ *dev_id = args.args[0];
break;
}
} while (!ret);
+ return ret;
+}
+
+int __weak iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id)
+{
+ return -1;
+}
+
+static int its_pmsi_prepare(struct irq_domain *domain, struct device *dev,
+ int nvec, msi_alloc_info_t *info)
+{
+ struct msi_domain_info *msi_info;
+ u32 dev_id;
+ int ret;
+
+ msi_info = msi_get_domain_info(domain->parent);
+
+ if (dev->of_node)
+ ret = of_pmsi_get_dev_id(domain, dev, &dev_id);
+ else
+ ret = iort_pmsi_get_dev_id(dev, &dev_id);
if (ret)
return ret;
{},
};
-static int __init its_pmsi_init(void)
+static int __init its_pmsi_init_one(struct fwnode_handle *fwnode,
+ const char *name)
{
- struct device_node *np;
struct irq_domain *parent;
+ parent = irq_find_matching_fwnode(fwnode, DOMAIN_BUS_NEXUS);
+ if (!parent || !msi_get_domain_info(parent)) {
+ pr_err("%s: unable to locate ITS domain\n", name);
+ return -ENXIO;
+ }
+
+ if (!platform_msi_create_irq_domain(fwnode, &its_pmsi_domain_info,
+ parent)) {
+ pr_err("%s: unable to create platform domain\n", name);
+ return -ENXIO;
+ }
+
+ pr_info("Platform MSI: %s domain created\n", name);
+ return 0;
+}
+
+#ifdef CONFIG_ACPI
+static int __init
+its_pmsi_parse_madt(struct acpi_subtable_header *header,
+ const unsigned long end)
+{
+ struct acpi_madt_generic_translator *its_entry;
+ struct fwnode_handle *domain_handle;
+ const char *node_name;
+ int err = -ENXIO;
+
+ its_entry = (struct acpi_madt_generic_translator *)header;
+ node_name = kasprintf(GFP_KERNEL, "ITS@0x%lx",
+ (long)its_entry->base_address);
+ domain_handle = iort_find_domain_token(its_entry->translation_id);
+ if (!domain_handle) {
+ pr_err("%s: Unable to locate ITS domain handle\n", node_name);
+ goto out;
+ }
+
+ err = its_pmsi_init_one(domain_handle, node_name);
+
+out:
+ kfree(node_name);
+ return err;
+}
+
+static void __init its_pmsi_acpi_init(void)
+{
+ acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_TRANSLATOR,
+ its_pmsi_parse_madt, 0);
+}
+#else
+static inline void its_pmsi_acpi_init(void) { }
+#endif
+
+static void __init its_pmsi_of_init(void)
+{
+ struct device_node *np;
+
for (np = of_find_matching_node(NULL, its_device_id); np;
np = of_find_matching_node(np, its_device_id)) {
if (!of_property_read_bool(np, "msi-controller"))
continue;
- parent = irq_find_matching_host(np, DOMAIN_BUS_NEXUS);
- if (!parent || !msi_get_domain_info(parent)) {
- pr_err("%s: unable to locate ITS domain\n",
- np->full_name);
- continue;
- }
-
- if (!platform_msi_create_irq_domain(of_node_to_fwnode(np),
- &its_pmsi_domain_info,
- parent)) {
- pr_err("%s: unable to create platform domain\n",
- np->full_name);
- continue;
- }
-
- pr_info("Platform MSI: %s domain created\n", np->full_name);
+ its_pmsi_init_one(of_node_to_fwnode(np), np->full_name);
}
+}
+static int __init its_pmsi_init(void)
+{
+ its_pmsi_of_init();
+ its_pmsi_acpi_init();
return 0;
}
early_initcall(its_pmsi_init);
*/
#include <linux/acpi.h>
+#include <linux/acpi_iort.h>
#include <linux/bitmap.h>
#include <linux/cpu.h>
#include <linux/delay.h>
#include <linux/dma-iommu.h>
#include <linux/interrupt.h>
#include <linux/irqdomain.h>
-#include <linux/acpi_iort.h>
#include <linux/log2.h>
#include <linux/mm.h>
#include <linux/msi.h>
return -ENOMEM;
}
+ raw_spin_lock_init(&cd->rlock);
+
cd->gpc_base = of_iomap(node, 0);
if (!cd->gpc_base) {
pr_err("fsl-gpcv2: unable to map gpc registers\n");
imx_gpcv2_instance = cd;
register_syscore_ops(&imx_gpcv2_syscore_ops);
+ /*
+ * Clear the OF_POPULATED flag set in of_irq_init so that
+ * later the GPC power domain driver will not be skipped.
+ */
+ of_node_clear_flag(node, OF_POPULATED);
return 0;
}
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/acpi.h>
#include <linux/interrupt.h>
#include <linux/irqchip.h>
#include <linux/module.h>
unsigned long *hwirq,
unsigned int *type)
{
- if (is_of_node(fwspec->fwnode)) {
+ if (is_of_node(fwspec->fwnode) || is_acpi_device_node(fwspec->fwnode)) {
if (fwspec->param_count != 2)
return -EINVAL;
.free = irq_domain_free_irqs_common,
};
-static int mbigen_device_probe(struct platform_device *pdev)
+static int mbigen_of_create_domain(struct platform_device *pdev,
+ struct mbigen_device *mgn_chip)
{
- struct mbigen_device *mgn_chip;
+ struct device *parent;
struct platform_device *child;
struct irq_domain *domain;
struct device_node *np;
- struct device *parent;
- struct resource *res;
u32 num_pins;
- mgn_chip = devm_kzalloc(&pdev->dev, sizeof(*mgn_chip), GFP_KERNEL);
- if (!mgn_chip)
- return -ENOMEM;
-
- mgn_chip->pdev = pdev;
-
- res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- mgn_chip->base = devm_ioremap_resource(&pdev->dev, res);
- if (IS_ERR(mgn_chip->base))
- return PTR_ERR(mgn_chip->base);
-
for_each_child_of_node(pdev->dev.of_node, np) {
if (!of_property_read_bool(np, "interrupt-controller"))
continue;
return -ENOMEM;
}
+ return 0;
+}
+
+#ifdef CONFIG_ACPI
+static int mbigen_acpi_create_domain(struct platform_device *pdev,
+ struct mbigen_device *mgn_chip)
+{
+ struct irq_domain *domain;
+ u32 num_pins = 0;
+ int ret;
+
+ /*
+ * "num-pins" is the total number of interrupt pins implemented in
+ * this mbigen instance, and mbigen is an interrupt controller
+ * connected to ITS converting wired interrupts into MSI, so we
+ * use "num-pins" to alloc MSI vectors which are needed by client
+ * devices connected to it.
+ *
+ * Here is the DSDT device node used for mbigen in firmware:
+ * Device(MBI0) {
+ * Name(_HID, "HISI0152")
+ * Name(_UID, Zero)
+ * Name(_CRS, ResourceTemplate() {
+ * Memory32Fixed(ReadWrite, 0xa0080000, 0x10000)
+ * })
+ *
+ * Name(_DSD, Package () {
+ * ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+ * Package () {
+ * Package () {"num-pins", 378}
+ * }
+ * })
+ * }
+ */
+ ret = device_property_read_u32(&pdev->dev, "num-pins", &num_pins);
+ if (ret || num_pins == 0)
+ return -EINVAL;
+
+ domain = platform_msi_create_device_domain(&pdev->dev, num_pins,
+ mbigen_write_msg,
+ &mbigen_domain_ops,
+ mgn_chip);
+ if (!domain)
+ return -ENOMEM;
+
+ return 0;
+}
+#else
+static inline int mbigen_acpi_create_domain(struct platform_device *pdev,
+ struct mbigen_device *mgn_chip)
+{
+ return -ENODEV;
+}
+#endif
+
+static int mbigen_device_probe(struct platform_device *pdev)
+{
+ struct mbigen_device *mgn_chip;
+ struct resource *res;
+ int err;
+
+ mgn_chip = devm_kzalloc(&pdev->dev, sizeof(*mgn_chip), GFP_KERNEL);
+ if (!mgn_chip)
+ return -ENOMEM;
+
+ mgn_chip->pdev = pdev;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ mgn_chip->base = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(mgn_chip->base))
+ return PTR_ERR(mgn_chip->base);
+
+ if (IS_ENABLED(CONFIG_OF) && pdev->dev.of_node)
+ err = mbigen_of_create_domain(pdev, mgn_chip);
+ else if (ACPI_COMPANION(&pdev->dev))
+ err = mbigen_acpi_create_domain(pdev, mgn_chip);
+ else
+ err = -EINVAL;
+
+ if (err) {
+ dev_err(&pdev->dev, "Failed to create mbi-gen@%p irqdomain",
+ mgn_chip->base);
+ return err;
+ }
+
platform_set_drvdata(pdev, mgn_chip);
return 0;
}
};
MODULE_DEVICE_TABLE(of, mbigen_of_match);
+static const struct acpi_device_id mbigen_acpi_match[] = {
+ { "HISI0152", 0 },
+ {}
+};
+MODULE_DEVICE_TABLE(acpi, mbigen_acpi_match);
+
static struct platform_driver mbigen_platform_driver = {
.driver = {
.name = "Hisilicon MBIGEN-V2",
- .owner = THIS_MODULE,
.of_match_table = mbigen_of_match,
+ .acpi_match_table = ACPI_PTR(mbigen_acpi_match),
},
.probe = mbigen_device_probe,
};
DECLARE_BITMAP(pcpu_mask, GIC_MAX_INTRS);
};
-struct gic_irq_spec {
- enum {
- GIC_DEVICE,
- GIC_IPI
- } type;
-
- union {
- struct cpumask *ipimask;
- unsigned int hwirq;
- };
-};
-
static unsigned long __gic_base_addr;
static void __iomem *gic_base;
static struct gic_pcpu_mask pcpu_masks[NR_CPUS];
static DEFINE_SPINLOCK(gic_lock);
static struct irq_domain *gic_irq_domain;
-static struct irq_domain *gic_dev_domain;
static struct irq_domain *gic_ipi_domain;
static int gic_shared_intrs;
static int gic_vpes;
static unsigned int timer_cpu_pin;
static struct irq_chip gic_level_irq_controller, gic_edge_irq_controller;
DECLARE_BITMAP(ipi_resrv, GIC_MAX_INTRS);
+DECLARE_BITMAP(ipi_available, GIC_MAX_INTRS);
static void __gic_irq_dispatch(void);
return 0;
}
-static int gic_setup_dev_chip(struct irq_domain *d, unsigned int virq,
- unsigned int hwirq)
-{
- struct irq_chip *chip;
- int err;
-
- if (hwirq >= GIC_SHARED_HWIRQ_BASE) {
- err = irq_domain_set_hwirq_and_chip(d, virq, hwirq,
- &gic_level_irq_controller,
- NULL);
- } else {
- switch (GIC_HWIRQ_TO_LOCAL(hwirq)) {
- case GIC_LOCAL_INT_TIMER:
- case GIC_LOCAL_INT_PERFCTR:
- case GIC_LOCAL_INT_FDC:
- /*
- * HACK: These are all really percpu interrupts, but
- * the rest of the MIPS kernel code does not use the
- * percpu IRQ API for them.
- */
- chip = &gic_all_vpes_local_irq_controller;
- irq_set_handler(virq, handle_percpu_irq);
- break;
-
- default:
- chip = &gic_local_irq_controller;
- irq_set_handler(virq, handle_percpu_devid_irq);
- irq_set_percpu_devid(virq);
- break;
- }
-
- err = irq_domain_set_hwirq_and_chip(d, virq, hwirq,
- chip, NULL);
- }
-
- return err;
-}
-
-static int gic_irq_domain_alloc(struct irq_domain *d, unsigned int virq,
- unsigned int nr_irqs, void *arg)
-{
- struct gic_irq_spec *spec = arg;
- irq_hw_number_t hwirq, base_hwirq;
- int cpu, ret, i;
-
- if (spec->type == GIC_DEVICE) {
- /* verify that shared irqs don't conflict with an IPI irq */
- if ((spec->hwirq >= GIC_SHARED_HWIRQ_BASE) &&
- test_bit(GIC_HWIRQ_TO_SHARED(spec->hwirq), ipi_resrv))
- return -EBUSY;
-
- return gic_setup_dev_chip(d, virq, spec->hwirq);
- } else {
- base_hwirq = find_first_bit(ipi_resrv, gic_shared_intrs);
- if (base_hwirq == gic_shared_intrs) {
- return -ENOMEM;
- }
-
- /* check that we have enough space */
- for (i = base_hwirq; i < nr_irqs; i++) {
- if (!test_bit(i, ipi_resrv))
- return -EBUSY;
- }
- bitmap_clear(ipi_resrv, base_hwirq, nr_irqs);
-
- /* map the hwirq for each cpu consecutively */
- i = 0;
- for_each_cpu(cpu, spec->ipimask) {
- hwirq = GIC_SHARED_TO_HWIRQ(base_hwirq + i);
-
- ret = irq_domain_set_hwirq_and_chip(d, virq + i, hwirq,
- &gic_level_irq_controller,
- NULL);
- if (ret)
- goto error;
-
- irq_set_handler(virq + i, handle_level_irq);
-
- ret = gic_shared_irq_domain_map(d, virq + i, hwirq, cpu);
- if (ret)
- goto error;
-
- i++;
- }
-
- /*
- * tell the parent about the base hwirq we allocated so it can
- * set its own domain data
- */
- spec->hwirq = base_hwirq;
- }
-
- return 0;
-error:
- bitmap_set(ipi_resrv, base_hwirq, nr_irqs);
- return ret;
-}
-
-void gic_irq_domain_free(struct irq_domain *d, unsigned int virq,
- unsigned int nr_irqs)
-{
- irq_hw_number_t base_hwirq;
- struct irq_data *data;
-
- data = irq_get_irq_data(virq);
- if (!data)
- return;
-
- base_hwirq = GIC_HWIRQ_TO_SHARED(irqd_to_hwirq(data));
- bitmap_set(ipi_resrv, base_hwirq, nr_irqs);
-}
-
-int gic_irq_domain_match(struct irq_domain *d, struct device_node *node,
- enum irq_domain_bus_token bus_token)
-{
- /* this domain should'nt be accessed directly */
- return 0;
-}
-
-static const struct irq_domain_ops gic_irq_domain_ops = {
- .alloc = gic_irq_domain_alloc,
- .free = gic_irq_domain_free,
- .match = gic_irq_domain_match,
-};
-
-static int gic_dev_domain_xlate(struct irq_domain *d, struct device_node *ctrlr,
+static int gic_irq_domain_xlate(struct irq_domain *d, struct device_node *ctrlr,
const u32 *intspec, unsigned int intsize,
irq_hw_number_t *out_hwirq,
unsigned int *out_type)
return 0;
}
-static int gic_dev_domain_alloc(struct irq_domain *d, unsigned int virq,
- unsigned int nr_irqs, void *arg)
+static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq,
+ irq_hw_number_t hwirq)
{
- struct irq_fwspec *fwspec = arg;
- struct gic_irq_spec spec = {
- .type = GIC_DEVICE,
- };
- int i, ret;
+ int err;
- if (fwspec->param[0] == GIC_SHARED)
- spec.hwirq = GIC_SHARED_TO_HWIRQ(fwspec->param[1]);
- else
- spec.hwirq = GIC_LOCAL_TO_HWIRQ(fwspec->param[1]);
+ if (hwirq >= GIC_SHARED_HWIRQ_BASE) {
+ /* verify that shared irqs don't conflict with an IPI irq */
+ if (test_bit(GIC_HWIRQ_TO_SHARED(hwirq), ipi_resrv))
+ return -EBUSY;
- ret = irq_domain_alloc_irqs_parent(d, virq, nr_irqs, &spec);
- if (ret)
- return ret;
+ err = irq_domain_set_hwirq_and_chip(d, virq, hwirq,
+ &gic_level_irq_controller,
+ NULL);
+ if (err)
+ return err;
- for (i = 0; i < nr_irqs; i++) {
- ret = gic_setup_dev_chip(d, virq + i, spec.hwirq + i);
- if (ret)
- goto error;
+ return gic_shared_irq_domain_map(d, virq, hwirq, 0);
}
- return 0;
+ switch (GIC_HWIRQ_TO_LOCAL(hwirq)) {
+ case GIC_LOCAL_INT_TIMER:
+ case GIC_LOCAL_INT_PERFCTR:
+ case GIC_LOCAL_INT_FDC:
+ /*
+ * HACK: These are all really percpu interrupts, but
+ * the rest of the MIPS kernel code does not use the
+ * percpu IRQ API for them.
+ */
+ err = irq_domain_set_hwirq_and_chip(d, virq, hwirq,
+ &gic_all_vpes_local_irq_controller,
+ NULL);
+ if (err)
+ return err;
-error:
- irq_domain_free_irqs_parent(d, virq, nr_irqs);
- return ret;
+ irq_set_handler(virq, handle_percpu_irq);
+ break;
+
+ default:
+ err = irq_domain_set_hwirq_and_chip(d, virq, hwirq,
+ &gic_local_irq_controller,
+ NULL);
+ if (err)
+ return err;
+
+ irq_set_handler(virq, handle_percpu_devid_irq);
+ irq_set_percpu_devid(virq);
+ break;
+ }
+
+ return gic_local_irq_domain_map(d, virq, hwirq);
}
-void gic_dev_domain_free(struct irq_domain *d, unsigned int virq,
- unsigned int nr_irqs)
+static int gic_irq_domain_alloc(struct irq_domain *d, unsigned int virq,
+ unsigned int nr_irqs, void *arg)
{
- /* no real allocation is done for dev irqs, so no need to free anything */
- return;
+ struct irq_fwspec *fwspec = arg;
+ irq_hw_number_t hwirq;
+
+ if (fwspec->param[0] == GIC_SHARED)
+ hwirq = GIC_SHARED_TO_HWIRQ(fwspec->param[1]);
+ else
+ hwirq = GIC_LOCAL_TO_HWIRQ(fwspec->param[1]);
+
+ return gic_irq_domain_map(d, virq, hwirq);
}
-static void gic_dev_domain_activate(struct irq_domain *domain,
- struct irq_data *d)
+void gic_irq_domain_free(struct irq_domain *d, unsigned int virq,
+ unsigned int nr_irqs)
{
- if (GIC_HWIRQ_TO_LOCAL(d->hwirq) < GIC_NUM_LOCAL_INTRS)
- gic_local_irq_domain_map(domain, d->irq, d->hwirq);
- else
- gic_shared_irq_domain_map(domain, d->irq, d->hwirq, 0);
}
-static struct irq_domain_ops gic_dev_domain_ops = {
- .xlate = gic_dev_domain_xlate,
- .alloc = gic_dev_domain_alloc,
- .free = gic_dev_domain_free,
- .activate = gic_dev_domain_activate,
+static const struct irq_domain_ops gic_irq_domain_ops = {
+ .xlate = gic_irq_domain_xlate,
+ .alloc = gic_irq_domain_alloc,
+ .free = gic_irq_domain_free,
+ .map = gic_irq_domain_map,
};
static int gic_ipi_domain_xlate(struct irq_domain *d, struct device_node *ctrlr,
unsigned int nr_irqs, void *arg)
{
struct cpumask *ipimask = arg;
- struct gic_irq_spec spec = {
- .type = GIC_IPI,
- .ipimask = ipimask
- };
- int ret, i;
-
- ret = irq_domain_alloc_irqs_parent(d, virq, nr_irqs, &spec);
- if (ret)
- return ret;
-
- /* the parent should have set spec.hwirq to the base_hwirq it allocated */
- for (i = 0; i < nr_irqs; i++) {
- ret = irq_domain_set_hwirq_and_chip(d, virq + i,
- GIC_SHARED_TO_HWIRQ(spec.hwirq + i),
+ irq_hw_number_t hwirq, base_hwirq;
+ int cpu, ret, i;
+
+ base_hwirq = find_first_bit(ipi_available, gic_shared_intrs);
+ if (base_hwirq == gic_shared_intrs)
+ return -ENOMEM;
+
+ /* check that we have enough space */
+ for (i = base_hwirq; i < nr_irqs; i++) {
+ if (!test_bit(i, ipi_available))
+ return -EBUSY;
+ }
+ bitmap_clear(ipi_available, base_hwirq, nr_irqs);
+
+ /* map the hwirq for each cpu consecutively */
+ i = 0;
+ for_each_cpu(cpu, ipimask) {
+ hwirq = GIC_SHARED_TO_HWIRQ(base_hwirq + i);
+
+ ret = irq_domain_set_hwirq_and_chip(d, virq + i, hwirq,
+ &gic_edge_irq_controller,
+ NULL);
+ if (ret)
+ goto error;
+
+ ret = irq_domain_set_hwirq_and_chip(d->parent, virq + i, hwirq,
&gic_edge_irq_controller,
NULL);
if (ret)
ret = irq_set_irq_type(virq + i, IRQ_TYPE_EDGE_RISING);
if (ret)
goto error;
+
+ ret = gic_shared_irq_domain_map(d, virq + i, hwirq, cpu);
+ if (ret)
+ goto error;
+
+ i++;
}
return 0;
error:
- irq_domain_free_irqs_parent(d, virq, nr_irqs);
+ bitmap_set(ipi_available, base_hwirq, nr_irqs);
return ret;
}
void gic_ipi_domain_free(struct irq_domain *d, unsigned int virq,
unsigned int nr_irqs)
{
- irq_domain_free_irqs_parent(d, virq, nr_irqs);
+ irq_hw_number_t base_hwirq;
+ struct irq_data *data;
+
+ data = irq_get_irq_data(virq);
+ if (!data)
+ return;
+
+ base_hwirq = GIC_HWIRQ_TO_SHARED(irqd_to_hwirq(data));
+ bitmap_set(ipi_available, base_hwirq, nr_irqs);
}
int gic_ipi_domain_match(struct irq_domain *d, struct device_node *node,
.match = gic_ipi_domain_match,
};
-static void __init gic_map_single_int(struct device_node *node,
- unsigned int irq)
-{
- unsigned int linux_irq;
- struct irq_fwspec local_int_fwspec = {
- .fwnode = &node->fwnode,
- .param_count = 3,
- .param = {
- [0] = GIC_LOCAL,
- [1] = irq,
- [2] = IRQ_TYPE_NONE,
- },
- };
-
- if (!gic_local_irq_is_routable(irq))
- return;
-
- linux_irq = irq_create_fwspec_mapping(&local_int_fwspec);
- WARN_ON(!linux_irq);
-}
-
-static void __init gic_map_interrupts(struct device_node *node)
-{
- gic_map_single_int(node, GIC_LOCAL_INT_WD);
- gic_map_single_int(node, GIC_LOCAL_INT_COMPARE);
- gic_map_single_int(node, GIC_LOCAL_INT_TIMER);
- gic_map_single_int(node, GIC_LOCAL_INT_PERFCTR);
- gic_map_single_int(node, GIC_LOCAL_INT_SWINT0);
- gic_map_single_int(node, GIC_LOCAL_INT_SWINT1);
- gic_map_single_int(node, GIC_LOCAL_INT_FDC);
-}
-
static void __init __gic_init(unsigned long gic_base_addr,
unsigned long gic_addrspace_size,
unsigned int cpu_vec, unsigned int irqbase,
panic("Failed to add GIC IRQ domain");
gic_irq_domain->name = "mips-gic-irq";
- gic_dev_domain = irq_domain_add_hierarchy(gic_irq_domain, 0,
- GIC_NUM_LOCAL_INTRS + gic_shared_intrs,
- node, &gic_dev_domain_ops, NULL);
- if (!gic_dev_domain)
- panic("Failed to add GIC DEV domain");
- gic_dev_domain->name = "mips-gic-dev";
-
gic_ipi_domain = irq_domain_add_hierarchy(gic_irq_domain,
IRQ_DOMAIN_FLAG_IPI_PER_CPU,
GIC_NUM_LOCAL_INTRS + gic_shared_intrs,
2 * gic_vpes);
}
+ bitmap_copy(ipi_available, ipi_resrv, GIC_MAX_INTRS);
gic_basic_init();
- gic_map_interrupts(node);
}
void __init gic_init(unsigned long gic_base_addr,
+++ /dev/null
-/*
- * MOXA ART SoCs IRQ chip driver.
- *
- * Copyright (C) 2013 Jonas Jensen
- *
- * Jonas Jensen <jonas.jensen@gmail.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#include <linux/io.h>
-#include <linux/irq.h>
-#include <linux/irqchip.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-#include <linux/irqdomain.h>
-
-#include <asm/exception.h>
-
-#define IRQ_SOURCE_REG 0
-#define IRQ_MASK_REG 0x04
-#define IRQ_CLEAR_REG 0x08
-#define IRQ_MODE_REG 0x0c
-#define IRQ_LEVEL_REG 0x10
-#define IRQ_STATUS_REG 0x14
-
-#define FIQ_SOURCE_REG 0x20
-#define FIQ_MASK_REG 0x24
-#define FIQ_CLEAR_REG 0x28
-#define FIQ_MODE_REG 0x2c
-#define FIQ_LEVEL_REG 0x30
-#define FIQ_STATUS_REG 0x34
-
-
-struct moxart_irq_data {
- void __iomem *base;
- struct irq_domain *domain;
- unsigned int interrupt_mask;
-};
-
-static struct moxart_irq_data intc;
-
-static void __exception_irq_entry handle_irq(struct pt_regs *regs)
-{
- u32 irqstat;
- int hwirq;
-
- irqstat = readl(intc.base + IRQ_STATUS_REG);
-
- while (irqstat) {
- hwirq = ffs(irqstat) - 1;
- handle_IRQ(irq_linear_revmap(intc.domain, hwirq), regs);
- irqstat &= ~(1 << hwirq);
- }
-}
-
-static int __init moxart_of_intc_init(struct device_node *node,
- struct device_node *parent)
-{
- unsigned int clr = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN;
- int ret;
- struct irq_chip_generic *gc;
-
- intc.base = of_iomap(node, 0);
- if (!intc.base) {
- pr_err("%s: unable to map IC registers\n",
- node->full_name);
- return -EINVAL;
- }
-
- intc.domain = irq_domain_add_linear(node, 32, &irq_generic_chip_ops,
- intc.base);
- if (!intc.domain) {
- pr_err("%s: unable to create IRQ domain\n", node->full_name);
- return -EINVAL;
- }
-
- ret = irq_alloc_domain_generic_chips(intc.domain, 32, 1,
- "MOXARTINTC", handle_edge_irq,
- clr, 0, IRQ_GC_INIT_MASK_CACHE);
- if (ret) {
- pr_err("%s: could not allocate generic chip\n",
- node->full_name);
- irq_domain_remove(intc.domain);
- return -EINVAL;
- }
-
- ret = of_property_read_u32(node, "interrupt-mask",
- &intc.interrupt_mask);
- if (ret)
- pr_err("%s: could not read interrupt-mask DT property\n",
- node->full_name);
-
- gc = irq_get_domain_generic_chip(intc.domain, 0);
-
- gc->reg_base = intc.base;
- gc->chip_types[0].regs.mask = IRQ_MASK_REG;
- gc->chip_types[0].regs.ack = IRQ_CLEAR_REG;
- gc->chip_types[0].chip.irq_ack = irq_gc_ack_set_bit;
- gc->chip_types[0].chip.irq_mask = irq_gc_mask_clr_bit;
- gc->chip_types[0].chip.irq_unmask = irq_gc_mask_set_bit;
-
- writel(0, intc.base + IRQ_MASK_REG);
- writel(0xffffffff, intc.base + IRQ_CLEAR_REG);
-
- writel(intc.interrupt_mask, intc.base + IRQ_MODE_REG);
- writel(intc.interrupt_mask, intc.base + IRQ_LEVEL_REG);
-
- set_handle_irq(handle_irq);
-
- return 0;
-}
-IRQCHIP_DECLARE(moxa_moxart_ic, "moxa,moxart-ic", moxart_of_intc_init);
--- /dev/null
+/*
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Youlin.Pei <youlin.pei@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <linux/irqdomain.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+#include <linux/syscore_ops.h>
+
+#define CIRQ_ACK 0x40
+#define CIRQ_MASK_SET 0xc0
+#define CIRQ_MASK_CLR 0x100
+#define CIRQ_SENS_SET 0x180
+#define CIRQ_SENS_CLR 0x1c0
+#define CIRQ_POL_SET 0x240
+#define CIRQ_POL_CLR 0x280
+#define CIRQ_CONTROL 0x300
+
+#define CIRQ_EN 0x1
+#define CIRQ_EDGE 0x2
+#define CIRQ_FLUSH 0x4
+
+struct mtk_cirq_chip_data {
+ void __iomem *base;
+ unsigned int ext_irq_start;
+ unsigned int ext_irq_end;
+ struct irq_domain *domain;
+};
+
+static struct mtk_cirq_chip_data *cirq_data;
+
+static void mtk_cirq_write_mask(struct irq_data *data, unsigned int offset)
+{
+ struct mtk_cirq_chip_data *chip_data = data->chip_data;
+ unsigned int cirq_num = data->hwirq;
+ u32 mask = 1 << (cirq_num % 32);
+
+ writel_relaxed(mask, chip_data->base + offset + (cirq_num / 32) * 4);
+}
+
+static void mtk_cirq_mask(struct irq_data *data)
+{
+ mtk_cirq_write_mask(data, CIRQ_MASK_SET);
+ irq_chip_mask_parent(data);
+}
+
+static void mtk_cirq_unmask(struct irq_data *data)
+{
+ mtk_cirq_write_mask(data, CIRQ_MASK_CLR);
+ irq_chip_unmask_parent(data);
+}
+
+static int mtk_cirq_set_type(struct irq_data *data, unsigned int type)
+{
+ int ret;
+
+ switch (type & IRQ_TYPE_SENSE_MASK) {
+ case IRQ_TYPE_EDGE_FALLING:
+ mtk_cirq_write_mask(data, CIRQ_POL_CLR);
+ mtk_cirq_write_mask(data, CIRQ_SENS_CLR);
+ break;
+ case IRQ_TYPE_EDGE_RISING:
+ mtk_cirq_write_mask(data, CIRQ_POL_SET);
+ mtk_cirq_write_mask(data, CIRQ_SENS_CLR);
+ break;
+ case IRQ_TYPE_LEVEL_LOW:
+ mtk_cirq_write_mask(data, CIRQ_POL_CLR);
+ mtk_cirq_write_mask(data, CIRQ_SENS_SET);
+ break;
+ case IRQ_TYPE_LEVEL_HIGH:
+ mtk_cirq_write_mask(data, CIRQ_POL_SET);
+ mtk_cirq_write_mask(data, CIRQ_SENS_SET);
+ break;
+ default:
+ break;
+ }
+
+ data = data->parent_data;
+ ret = data->chip->irq_set_type(data, type);
+ return ret;
+}
+
+static struct irq_chip mtk_cirq_chip = {
+ .name = "MT_CIRQ",
+ .irq_mask = mtk_cirq_mask,
+ .irq_unmask = mtk_cirq_unmask,
+ .irq_eoi = irq_chip_eoi_parent,
+ .irq_set_type = mtk_cirq_set_type,
+ .irq_retrigger = irq_chip_retrigger_hierarchy,
+#ifdef CONFIG_SMP
+ .irq_set_affinity = irq_chip_set_affinity_parent,
+#endif
+};
+
+static int mtk_cirq_domain_translate(struct irq_domain *d,
+ struct irq_fwspec *fwspec,
+ unsigned long *hwirq,
+ unsigned int *type)
+{
+ if (is_of_node(fwspec->fwnode)) {
+ if (fwspec->param_count != 3)
+ return -EINVAL;
+
+ /* No PPI should point to this domain */
+ if (fwspec->param[0] != 0)
+ return -EINVAL;
+
+ /* cirq support irq number check */
+ if (fwspec->param[1] < cirq_data->ext_irq_start ||
+ fwspec->param[1] > cirq_data->ext_irq_end)
+ return -EINVAL;
+
+ *hwirq = fwspec->param[1] - cirq_data->ext_irq_start;
+ *type = fwspec->param[2] & IRQ_TYPE_SENSE_MASK;
+ return 0;
+ }
+
+ return -EINVAL;
+}
+
+static int mtk_cirq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+ unsigned int nr_irqs, void *arg)
+{
+ int ret;
+ irq_hw_number_t hwirq;
+ unsigned int type;
+ struct irq_fwspec *fwspec = arg;
+ struct irq_fwspec parent_fwspec = *fwspec;
+
+ ret = mtk_cirq_domain_translate(domain, fwspec, &hwirq, &type);
+ if (ret)
+ return ret;
+
+ if (WARN_ON(nr_irqs != 1))
+ return -EINVAL;
+
+ irq_domain_set_hwirq_and_chip(domain, virq, hwirq,
+ &mtk_cirq_chip,
+ domain->host_data);
+
+ parent_fwspec.fwnode = domain->parent->fwnode;
+ return irq_domain_alloc_irqs_parent(domain, virq, nr_irqs,
+ &parent_fwspec);
+}
+
+static const struct irq_domain_ops cirq_domain_ops = {
+ .translate = mtk_cirq_domain_translate,
+ .alloc = mtk_cirq_domain_alloc,
+ .free = irq_domain_free_irqs_common,
+};
+
+#ifdef CONFIG_PM_SLEEP
+static int mtk_cirq_suspend(void)
+{
+ u32 value, mask;
+ unsigned int irq, hwirq_num;
+ bool pending, masked;
+ int i, pendret, maskret;
+
+ /*
+ * When external interrupts happened, CIRQ will record the status
+ * even CIRQ is not enabled. When execute flush command, CIRQ will
+ * resend the signals according to the status. So if don't clear the
+ * status, CIRQ will resend the wrong signals.
+ *
+ * arch_suspend_disable_irqs() will be called before CIRQ suspend
+ * callback. If clear all the status simply, the external interrupts
+ * which happened between arch_suspend_disable_irqs and CIRQ suspend
+ * callback will be lost. Using following steps to avoid this issue;
+ *
+ * - Iterate over all the CIRQ supported interrupts;
+ * - For each interrupt, inspect its pending and masked status at GIC
+ * level;
+ * - If pending and unmasked, it happened between
+ * arch_suspend_disable_irqs and CIRQ suspend callback, don't ACK
+ * it. Otherwise, ACK it.
+ */
+ hwirq_num = cirq_data->ext_irq_end - cirq_data->ext_irq_start + 1;
+ for (i = 0; i < hwirq_num; i++) {
+ irq = irq_find_mapping(cirq_data->domain, i);
+ if (irq) {
+ pendret = irq_get_irqchip_state(irq,
+ IRQCHIP_STATE_PENDING,
+ &pending);
+
+ maskret = irq_get_irqchip_state(irq,
+ IRQCHIP_STATE_MASKED,
+ &masked);
+
+ if (pendret == 0 && maskret == 0 &&
+ (pending && !masked))
+ continue;
+ }
+
+ mask = 1 << (i % 32);
+ writel_relaxed(mask, cirq_data->base + CIRQ_ACK + (i / 32) * 4);
+ }
+
+ /* set edge_only mode, record edge-triggerd interrupts */
+ /* enable cirq */
+ value = readl_relaxed(cirq_data->base + CIRQ_CONTROL);
+ value |= (CIRQ_EDGE | CIRQ_EN);
+ writel_relaxed(value, cirq_data->base + CIRQ_CONTROL);
+
+ return 0;
+}
+
+static void mtk_cirq_resume(void)
+{
+ u32 value;
+
+ /* flush recored interrupts, will send signals to parent controller */
+ value = readl_relaxed(cirq_data->base + CIRQ_CONTROL);
+ writel_relaxed(value | CIRQ_FLUSH, cirq_data->base + CIRQ_CONTROL);
+
+ /* disable cirq */
+ value = readl_relaxed(cirq_data->base + CIRQ_CONTROL);
+ value &= ~(CIRQ_EDGE | CIRQ_EN);
+ writel_relaxed(value, cirq_data->base + CIRQ_CONTROL);
+}
+
+static struct syscore_ops mtk_cirq_syscore_ops = {
+ .suspend = mtk_cirq_suspend,
+ .resume = mtk_cirq_resume,
+};
+
+static void mtk_cirq_syscore_init(void)
+{
+ register_syscore_ops(&mtk_cirq_syscore_ops);
+}
+#else
+static inline void mtk_cirq_syscore_init(void) {}
+#endif
+
+static int __init mtk_cirq_of_init(struct device_node *node,
+ struct device_node *parent)
+{
+ struct irq_domain *domain, *domain_parent;
+ unsigned int irq_num;
+ int ret;
+
+ domain_parent = irq_find_host(parent);
+ if (!domain_parent) {
+ pr_err("mtk_cirq: interrupt-parent not found\n");
+ return -EINVAL;
+ }
+
+ cirq_data = kzalloc(sizeof(*cirq_data), GFP_KERNEL);
+ if (!cirq_data)
+ return -ENOMEM;
+
+ cirq_data->base = of_iomap(node, 0);
+ if (!cirq_data->base) {
+ pr_err("mtk_cirq: unable to map cirq register\n");
+ ret = -ENXIO;
+ goto out_free;
+ }
+
+ ret = of_property_read_u32_index(node, "mediatek,ext-irq-range", 0,
+ &cirq_data->ext_irq_start);
+ if (ret)
+ goto out_unmap;
+
+ ret = of_property_read_u32_index(node, "mediatek,ext-irq-range", 1,
+ &cirq_data->ext_irq_end);
+ if (ret)
+ goto out_unmap;
+
+ irq_num = cirq_data->ext_irq_end - cirq_data->ext_irq_start + 1;
+ domain = irq_domain_add_hierarchy(domain_parent, 0,
+ irq_num, node,
+ &cirq_domain_ops, cirq_data);
+ if (!domain) {
+ ret = -ENOMEM;
+ goto out_unmap;
+ }
+ cirq_data->domain = domain;
+
+ mtk_cirq_syscore_init();
+
+ return 0;
+
+out_unmap:
+ iounmap(cirq_data->base);
+out_free:
+ kfree(cirq_data);
+ return ret;
+}
+
+IRQCHIP_DECLARE(mtk_cirq, "mediatek,mtk-cirq", mtk_cirq_of_init);
struct mtk_sysirq_chip_data {
spinlock_t lock;
- void __iomem *intpol_base;
+ u32 nr_intpol_bases;
+ void __iomem **intpol_bases;
+ u32 *intpol_words;
+ u8 *intpol_idx;
+ u16 *which_word;
};
static int mtk_sysirq_set_type(struct irq_data *data, unsigned int type)
{
irq_hw_number_t hwirq = data->hwirq;
struct mtk_sysirq_chip_data *chip_data = data->chip_data;
+ u8 intpol_idx = chip_data->intpol_idx[hwirq];
+ void __iomem *base;
u32 offset, reg_index, value;
unsigned long flags;
int ret;
+ base = chip_data->intpol_bases[intpol_idx];
+ reg_index = chip_data->which_word[hwirq];
offset = hwirq & 0x1f;
- reg_index = hwirq >> 5;
spin_lock_irqsave(&chip_data->lock, flags);
- value = readl_relaxed(chip_data->intpol_base + reg_index * 4);
+ value = readl_relaxed(base + reg_index * 4);
if (type == IRQ_TYPE_LEVEL_LOW || type == IRQ_TYPE_EDGE_FALLING) {
if (type == IRQ_TYPE_LEVEL_LOW)
type = IRQ_TYPE_LEVEL_HIGH;
} else {
value &= ~(1 << offset);
}
- writel(value, chip_data->intpol_base + reg_index * 4);
+
+ writel_relaxed(value, base + reg_index * 4);
data = data->parent_data;
ret = data->chip->irq_set_type(data, type);
{
struct irq_domain *domain, *domain_parent;
struct mtk_sysirq_chip_data *chip_data;
- int ret, size, intpol_num;
- struct resource res;
+ int ret, size, intpol_num = 0, nr_intpol_bases = 0, i = 0;
domain_parent = irq_find_host(parent);
if (!domain_parent) {
return -EINVAL;
}
- ret = of_address_to_resource(node, 0, &res);
- if (ret)
- return ret;
-
chip_data = kzalloc(sizeof(*chip_data), GFP_KERNEL);
if (!chip_data)
return -ENOMEM;
- size = resource_size(&res);
- intpol_num = size * 8;
- chip_data->intpol_base = ioremap(res.start, size);
- if (!chip_data->intpol_base) {
- pr_err("mtk_sysirq: unable to map sysirq register\n");
- ret = -ENXIO;
- goto out_free;
+ while (of_get_address(node, i++, NULL, NULL))
+ nr_intpol_bases++;
+
+ if (nr_intpol_bases == 0) {
+ pr_err("mtk_sysirq: base address not specified\n");
+ ret = -EINVAL;
+ goto out_free_chip;
+ }
+
+ chip_data->intpol_words = kcalloc(nr_intpol_bases,
+ sizeof(*chip_data->intpol_words),
+ GFP_KERNEL);
+ if (!chip_data->intpol_words) {
+ ret = -ENOMEM;
+ goto out_free_chip;
+ }
+
+ chip_data->intpol_bases = kcalloc(nr_intpol_bases,
+ sizeof(*chip_data->intpol_bases),
+ GFP_KERNEL);
+ if (!chip_data->intpol_bases) {
+ ret = -ENOMEM;
+ goto out_free_intpol_words;
+ }
+
+ for (i = 0; i < nr_intpol_bases; i++) {
+ struct resource res;
+
+ ret = of_address_to_resource(node, i, &res);
+ size = resource_size(&res);
+ intpol_num += size * 8;
+ chip_data->intpol_words[i] = size / 4;
+ chip_data->intpol_bases[i] = of_iomap(node, i);
+ if (ret || !chip_data->intpol_bases[i]) {
+ pr_err("%s: couldn't map region %d\n",
+ node->full_name, i);
+ ret = -ENODEV;
+ goto out_free_intpol;
+ }
+ }
+
+ chip_data->intpol_idx = kcalloc(intpol_num,
+ sizeof(*chip_data->intpol_idx),
+ GFP_KERNEL);
+ if (!chip_data->intpol_idx) {
+ ret = -ENOMEM;
+ goto out_free_intpol;
+ }
+
+ chip_data->which_word = kcalloc(intpol_num,
+ sizeof(*chip_data->which_word),
+ GFP_KERNEL);
+ if (!chip_data->which_word) {
+ ret = -ENOMEM;
+ goto out_free_intpol_idx;
+ }
+
+ /*
+ * assign an index of the intpol_bases for each irq
+ * to set it fast later
+ */
+ for (i = 0; i < intpol_num ; i++) {
+ u32 word = i / 32, j;
+
+ for (j = 0; word >= chip_data->intpol_words[j] ; j++)
+ word -= chip_data->intpol_words[j];
+
+ chip_data->intpol_idx[i] = j;
+ chip_data->which_word[i] = word;
}
domain = irq_domain_add_hierarchy(domain_parent, 0, intpol_num, node,
&sysirq_domain_ops, chip_data);
if (!domain) {
ret = -ENOMEM;
- goto out_unmap;
+ goto out_free_which_word;
}
spin_lock_init(&chip_data->lock);
return 0;
-out_unmap:
- iounmap(chip_data->intpol_base);
-out_free:
+out_free_which_word:
+ kfree(chip_data->which_word);
+out_free_intpol_idx:
+ kfree(chip_data->intpol_idx);
+out_free_intpol:
+ for (i = 0; i < nr_intpol_bases; i++)
+ if (chip_data->intpol_bases[i])
+ iounmap(chip_data->intpol_bases[i]);
+ kfree(chip_data->intpol_bases);
+out_free_intpol_words:
+ kfree(chip_data->intpol_words);
+out_free_chip:
kfree(chip_data);
return ret;
}
sizeof(avmb1_carddef))))
return -EFAULT;
cdef.cardtype = AVM_CARDTYPE_B1;
+ cdef.cardnr = 0;
} else {
if ((retval = copy_from_user(&cdef, data,
sizeof(avmb1_extcarddef))))
This option enables support for LEDs connected to the BCM6358
LED HW controller accessed via MMIO registers.
+config LEDS_CPCAP
+ tristate "LED Support for Motorola CPCAP"
+ depends on LEDS_CLASS
+ depends on MFD_CPCAP
+ depends on OF
+ help
+ This option enables support for LEDs offered by Motorola's
+ CPCAP PMIC.
+
config LEDS_LM3530
tristate "LCD Backlight driver for LM3530"
depends on LEDS_CLASS
This option enables support for the so called "User LED" of
Mikrotik's Routerboard 532.
+config LEDS_MT6323
+ tristate "LED Support for Mediatek MT6323 PMIC"
+ depends on LEDS_CLASS
+ depends on MFD_MT6397
+ help
+ This option enables support for on-chip LED drivers found on
+ Mediatek MT6323 PMIC.
+
config LEDS_S3C24XX
tristate "LED Support for Samsung S3C24XX GPIO LEDs"
depends on LEDS_CLASS
tristate "LED Support for TI LP3952 2 channel LED driver"
depends on LEDS_CLASS
depends on I2C
- depends on ACPI
depends on GPIOLIB
select REGMAP_I2C
help
To compile this driver as a module, choose M here: the module will
be called leds-adp5520.
-config LEDS_DELL_NETBOOKS
- tristate "External LED on Dell Business Netbooks"
- depends on LEDS_CLASS
- depends on X86 && ACPI_WMI
- depends on DELL_SMBIOS
- help
- This adds support for the Latitude 2100 and similar
- notebooks that have an external LED.
-
config LEDS_MC13783
tristate "LED Support for MC13XXX PMIC"
depends on LEDS_CLASS
obj-$(CONFIG_LEDS_BCM6328) += leds-bcm6328.o
obj-$(CONFIG_LEDS_BCM6358) += leds-bcm6358.o
obj-$(CONFIG_LEDS_BD2802) += leds-bd2802.o
+obj-$(CONFIG_LEDS_CPCAP) += leds-cpcap.o
obj-$(CONFIG_LEDS_LOCOMO) += leds-locomo.o
obj-$(CONFIG_LEDS_LM3530) += leds-lm3530.o
obj-$(CONFIG_LEDS_LM3533) += leds-lm3533.o
obj-$(CONFIG_LEDS_INTEL_SS4200) += leds-ss4200.o
obj-$(CONFIG_LEDS_LT3593) += leds-lt3593.o
obj-$(CONFIG_LEDS_ADP5520) += leds-adp5520.o
-obj-$(CONFIG_LEDS_DELL_NETBOOKS) += dell-led.o
obj-$(CONFIG_LEDS_MC13783) += leds-mc13783.o
obj-$(CONFIG_LEDS_NS2) += leds-ns2.o
obj-$(CONFIG_LEDS_NETXBIG) += leds-netxbig.o
obj-$(CONFIG_LEDS_PM8058) += leds-pm8058.o
obj-$(CONFIG_LEDS_MLXCPLD) += leds-mlxcpld.o
obj-$(CONFIG_LEDS_NIC78BX) += leds-nic78bx.o
+obj-$(CONFIG_LEDS_MT6323) += leds-mt6323.o
# LED SPI Drivers
obj-$(CONFIG_LEDS_DAC124S085) += leds-dac124s085.o
}
/**
- * led_classdev_register - register a new object of led_classdev class.
- * @parent: The device to register.
+ * of_led_classdev_register - register a new object of led_classdev class.
+ *
+ * @parent: parent of LED device
* @led_cdev: the led_classdev structure for this device.
+ * @np: DT node describing this LED
*/
-int led_classdev_register(struct device *parent, struct led_classdev *led_cdev)
+int of_led_classdev_register(struct device *parent, struct device_node *np,
+ struct led_classdev *led_cdev)
{
char name[LED_MAX_NAME_SIZE];
int ret;
led_cdev, led_cdev->groups, "%s", name);
if (IS_ERR(led_cdev->dev))
return PTR_ERR(led_cdev->dev);
+ led_cdev->dev->of_node = np;
if (ret)
dev_warn(parent, "Led %s renamed to %s due to name collision",
return 0;
}
-EXPORT_SYMBOL_GPL(led_classdev_register);
+EXPORT_SYMBOL_GPL(of_led_classdev_register);
/**
* led_classdev_unregister - unregisters a object of led_properties class.
}
/**
- * devm_led_classdev_register - resource managed led_classdev_register()
- * @parent: The device to register.
+ * devm_of_led_classdev_register - resource managed led_classdev_register()
+ *
+ * @parent: parent of LED device
* @led_cdev: the led_classdev structure for this device.
*/
-int devm_led_classdev_register(struct device *parent,
- struct led_classdev *led_cdev)
+int devm_of_led_classdev_register(struct device *parent,
+ struct device_node *np,
+ struct led_classdev *led_cdev)
{
struct led_classdev **dr;
int rc;
if (!dr)
return -ENOMEM;
- rc = led_classdev_register(parent, led_cdev);
+ rc = of_led_classdev_register(parent, np, led_cdev);
if (rc) {
devres_free(dr);
return rc;
return 0;
}
-EXPORT_SYMBOL_GPL(devm_led_classdev_register);
+EXPORT_SYMBOL_GPL(devm_of_led_classdev_register);
static int devm_led_classdev_match(struct device *dev, void *res, void *data)
{
--- /dev/null
+/*
+ * Copyright (c) 2017 Sebastian Reichel <sre@kernel.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 or
+ * later as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/leds.h>
+#include <linux/mfd/motorola-cpcap.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
+
+#define CPCAP_LED_NO_CURRENT 0x0001
+
+struct cpcap_led_info {
+ u16 reg;
+ u16 mask;
+ u16 limit;
+ u16 init_mask;
+ u16 init_val;
+};
+
+static const struct cpcap_led_info cpcap_led_red = {
+ .reg = CPCAP_REG_REDC,
+ .mask = 0x03FF,
+ .limit = 31,
+};
+
+static const struct cpcap_led_info cpcap_led_green = {
+ .reg = CPCAP_REG_GREENC,
+ .mask = 0x03FF,
+ .limit = 31,
+};
+
+static const struct cpcap_led_info cpcap_led_blue = {
+ .reg = CPCAP_REG_BLUEC,
+ .mask = 0x03FF,
+ .limit = 31,
+};
+
+/* aux display light */
+static const struct cpcap_led_info cpcap_led_adl = {
+ .reg = CPCAP_REG_ADLC,
+ .mask = 0x000F,
+ .limit = 1,
+ .init_mask = 0x7FFF,
+ .init_val = 0x5FF0,
+};
+
+/* camera privacy led */
+static const struct cpcap_led_info cpcap_led_cp = {
+ .reg = CPCAP_REG_CLEDC,
+ .mask = 0x0007,
+ .limit = 1,
+ .init_mask = 0x03FF,
+ .init_val = 0x0008,
+};
+
+struct cpcap_led {
+ struct led_classdev led;
+ const struct cpcap_led_info *info;
+ struct device *dev;
+ struct regmap *regmap;
+ struct mutex update_lock;
+ struct regulator *vdd;
+ bool powered;
+
+ u32 current_limit;
+};
+
+static u16 cpcap_led_val(u8 current_limit, u8 duty_cycle)
+{
+ current_limit &= 0x1f; /* 5 bit */
+ duty_cycle &= 0x0f; /* 4 bit */
+
+ return current_limit << 4 | duty_cycle;
+}
+
+static int cpcap_led_set_power(struct cpcap_led *led, bool status)
+{
+ int err;
+
+ if (status == led->powered)
+ return 0;
+
+ if (status)
+ err = regulator_enable(led->vdd);
+ else
+ err = regulator_disable(led->vdd);
+
+ if (err) {
+ dev_err(led->dev, "regulator failure: %d", err);
+ return err;
+ }
+
+ led->powered = status;
+
+ return 0;
+}
+
+static int cpcap_led_set(struct led_classdev *ledc, enum led_brightness value)
+{
+ struct cpcap_led *led = container_of(ledc, struct cpcap_led, led);
+ int brightness;
+ int err;
+
+ mutex_lock(&led->update_lock);
+
+ if (value > LED_OFF) {
+ err = cpcap_led_set_power(led, true);
+ if (err)
+ goto exit;
+ }
+
+ if (value == LED_OFF) {
+ /* Avoid HW issue by turning off current before duty cycle */
+ err = regmap_update_bits(led->regmap,
+ led->info->reg, led->info->mask, CPCAP_LED_NO_CURRENT);
+ if (err) {
+ dev_err(led->dev, "regmap failed: %d", err);
+ goto exit;
+ }
+
+ brightness = cpcap_led_val(value, LED_OFF);
+ } else {
+ brightness = cpcap_led_val(value, LED_ON);
+ }
+
+ err = regmap_update_bits(led->regmap, led->info->reg, led->info->mask,
+ brightness);
+ if (err) {
+ dev_err(led->dev, "regmap failed: %d", err);
+ goto exit;
+ }
+
+ if (value == LED_OFF) {
+ err = cpcap_led_set_power(led, false);
+ if (err)
+ goto exit;
+ }
+
+exit:
+ mutex_unlock(&led->update_lock);
+ return err;
+}
+
+static const struct of_device_id cpcap_led_of_match[] = {
+ { .compatible = "motorola,cpcap-led-red", .data = &cpcap_led_red },
+ { .compatible = "motorola,cpcap-led-green", .data = &cpcap_led_green },
+ { .compatible = "motorola,cpcap-led-blue", .data = &cpcap_led_blue },
+ { .compatible = "motorola,cpcap-led-adl", .data = &cpcap_led_adl },
+ { .compatible = "motorola,cpcap-led-cp", .data = &cpcap_led_cp },
+ {},
+};
+MODULE_DEVICE_TABLE(of, cpcap_led_of_match);
+
+static int cpcap_led_probe(struct platform_device *pdev)
+{
+ const struct of_device_id *match;
+ struct cpcap_led *led;
+ int err;
+
+ match = of_match_device(of_match_ptr(cpcap_led_of_match), &pdev->dev);
+ if (!match || !match->data)
+ return -EINVAL;
+
+ led = devm_kzalloc(&pdev->dev, sizeof(*led), GFP_KERNEL);
+ if (!led)
+ return -ENOMEM;
+ platform_set_drvdata(pdev, led);
+ led->info = match->data;
+ led->dev = &pdev->dev;
+
+ if (led->info->reg == 0x0000) {
+ dev_err(led->dev, "Unsupported LED");
+ return -ENODEV;
+ }
+
+ led->regmap = dev_get_regmap(pdev->dev.parent, NULL);
+ if (!led->regmap)
+ return -ENODEV;
+
+ led->vdd = devm_regulator_get(&pdev->dev, "vdd");
+ if (IS_ERR(led->vdd)) {
+ err = PTR_ERR(led->vdd);
+ dev_err(led->dev, "Couldn't get regulator: %d", err);
+ return err;
+ }
+
+ err = device_property_read_string(&pdev->dev, "label", &led->led.name);
+ if (err) {
+ dev_err(led->dev, "Couldn't read LED label: %d", err);
+ return err;
+ }
+
+ if (led->info->init_mask) {
+ err = regmap_update_bits(led->regmap, led->info->reg,
+ led->info->init_mask, led->info->init_val);
+ if (err) {
+ dev_err(led->dev, "regmap failed: %d", err);
+ return err;
+ }
+ }
+
+ mutex_init(&led->update_lock);
+
+ led->led.max_brightness = led->info->limit;
+ led->led.brightness_set_blocking = cpcap_led_set;
+ err = devm_led_classdev_register(&pdev->dev, &led->led);
+ if (err) {
+ dev_err(led->dev, "Couldn't register LED: %d", err);
+ return err;
+ }
+
+ return 0;
+}
+
+static struct platform_driver cpcap_led_driver = {
+ .probe = cpcap_led_probe,
+ .driver = {
+ .name = "cpcap-led",
+ .of_match_table = cpcap_led_of_match,
+ },
+};
+module_platform_driver(cpcap_led_driver);
+
+MODULE_DESCRIPTION("CPCAP LED driver");
+MODULE_AUTHOR("Sebastian Reichel <sre@kernel.org>");
+MODULE_LICENSE("GPL");
static int create_gpio_led(const struct gpio_led *template,
struct gpio_led_data *led_dat, struct device *parent,
- gpio_blink_set_t blink_set)
+ struct device_node *np, gpio_blink_set_t blink_set)
{
int ret, state;
if (ret < 0)
return ret;
- return devm_led_classdev_register(parent, &led_dat->cdev);
+ return devm_of_led_classdev_register(parent, np, &led_dat->cdev);
}
struct gpio_leds_priv {
if (fwnode_property_present(child, "panic-indicator"))
led.panic_indicator = 1;
- ret = create_gpio_led(&led, led_dat, dev, NULL);
+ ret = create_gpio_led(&led, led_dat, dev, np, NULL);
if (ret < 0) {
fwnode_handle_put(child);
return ERR_PTR(ret);
priv->num_leds = pdata->num_leds;
for (i = 0; i < priv->num_leds; i++) {
- ret = create_gpio_led(&pdata->leds[i],
- &priv->leds[i],
- &pdev->dev, pdata->gpio_blink_set);
+ ret = create_gpio_led(&pdata->leds[i], &priv->leds[i],
+ &pdev->dev, NULL,
+ pdata->gpio_blink_set);
if (ret < 0)
return ret;
}
*
*/
-#include <linux/acpi.h>
#include <linux/delay.h>
#include <linux/gpio.h>
#include <linux/i2c.h>
const char *str;
ret = device_property_read_string(dev, label, &str);
- if (!ret)
- strncpy(dest, str, LP3952_LABEL_MAX_LEN);
+ if (ret)
+ return ret;
- return ret;
+ strncpy(dest, str, LP3952_LABEL_MAX_LEN);
+ return 0;
}
static int lp3952_register_led_classdev(struct lp3952_led_array *priv)
};
MODULE_DEVICE_TABLE(i2c, lp3952_id);
-#ifdef CONFIG_ACPI
-static const struct acpi_device_id lp3952_acpi_match[] = {
- {"TXNW3952", 0},
- {}
-};
-
-MODULE_DEVICE_TABLE(acpi, lp3952_acpi_match);
-#endif
-
static struct i2c_driver lp3952_i2c_driver = {
.driver = {
.name = LP3952_NAME,
- .acpi_match_table = ACPI_PTR(lp3952_acpi_match),
},
.probe = lp3952_probe,
.remove = lp3952_remove,
--- /dev/null
+/*
+ * LED driver for Mediatek MT6323 PMIC
+ *
+ * Copyright (C) 2017 Sean Wang <sean.wang@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+#include <linux/kernel.h>
+#include <linux/leds.h>
+#include <linux/mfd/mt6323/registers.h>
+#include <linux/mfd/mt6397/core.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+/*
+ * Register field for MT6323_TOP_CKPDN0 to enable
+ * 32K clock common for LED device.
+ */
+#define MT6323_RG_DRV_32K_CK_PDN BIT(11)
+#define MT6323_RG_DRV_32K_CK_PDN_MASK BIT(11)
+
+/*
+ * Register field for MT6323_TOP_CKPDN2 to enable
+ * individual clock for LED device.
+ */
+#define MT6323_RG_ISINK_CK_PDN(i) BIT(i)
+#define MT6323_RG_ISINK_CK_PDN_MASK(i) BIT(i)
+
+/*
+ * Register field for MT6323_TOP_CKCON1 to select
+ * clock source.
+ */
+#define MT6323_RG_ISINK_CK_SEL_MASK(i) (BIT(10) << (i))
+
+/*
+ * Register for MT6323_ISINK_CON0 to setup the
+ * duty cycle of the blink.
+ */
+#define MT6323_ISINK_CON0(i) (MT6323_ISINK0_CON0 + 0x8 * (i))
+#define MT6323_ISINK_DIM_DUTY_MASK (0x1f << 8)
+#define MT6323_ISINK_DIM_DUTY(i) (((i) << 8) & \
+ MT6323_ISINK_DIM_DUTY_MASK)
+
+/* Register to setup the period of the blink. */
+#define MT6323_ISINK_CON1(i) (MT6323_ISINK0_CON1 + 0x8 * (i))
+#define MT6323_ISINK_DIM_FSEL_MASK (0xffff)
+#define MT6323_ISINK_DIM_FSEL(i) ((i) & MT6323_ISINK_DIM_FSEL_MASK)
+
+/* Register to control the brightness. */
+#define MT6323_ISINK_CON2(i) (MT6323_ISINK0_CON2 + 0x8 * (i))
+#define MT6323_ISINK_CH_STEP_SHIFT 12
+#define MT6323_ISINK_CH_STEP_MASK (0x7 << 12)
+#define MT6323_ISINK_CH_STEP(i) (((i) << 12) & \
+ MT6323_ISINK_CH_STEP_MASK)
+#define MT6323_ISINK_SFSTR0_TC_MASK (0x3 << 1)
+#define MT6323_ISINK_SFSTR0_TC(i) (((i) << 1) & \
+ MT6323_ISINK_SFSTR0_TC_MASK)
+#define MT6323_ISINK_SFSTR0_EN_MASK BIT(0)
+#define MT6323_ISINK_SFSTR0_EN BIT(0)
+
+/* Register to LED channel enablement. */
+#define MT6323_ISINK_CH_EN_MASK(i) BIT(i)
+#define MT6323_ISINK_CH_EN(i) BIT(i)
+
+#define MT6323_MAX_PERIOD 10000
+#define MT6323_MAX_LEDS 4
+#define MT6323_MAX_BRIGHTNESS 6
+#define MT6323_UNIT_DUTY 3125
+#define MT6323_CAL_HW_DUTY(o, p) DIV_ROUND_CLOSEST((o) * 100000ul,\
+ (p) * MT6323_UNIT_DUTY)
+
+struct mt6323_leds;
+
+/**
+ * struct mt6323_led - state container for the LED device
+ * @id: the identifier in MT6323 LED device
+ * @parent: the pointer to MT6323 LED controller
+ * @cdev: LED class device for this LED device
+ * @current_brightness: current state of the LED device
+ */
+struct mt6323_led {
+ int id;
+ struct mt6323_leds *parent;
+ struct led_classdev cdev;
+ enum led_brightness current_brightness;
+};
+
+/**
+ * struct mt6323_leds - state container for holding LED controller
+ * of the driver
+ * @dev: the device pointer
+ * @hw: the underlying hardware providing shared
+ * bus for the register operations
+ * @lock: the lock among process context
+ * @led: the array that contains the state of individual
+ * LED device
+ */
+struct mt6323_leds {
+ struct device *dev;
+ struct mt6397_chip *hw;
+ /* protect among process context */
+ struct mutex lock;
+ struct mt6323_led *led[MT6323_MAX_LEDS];
+};
+
+static int mt6323_led_hw_brightness(struct led_classdev *cdev,
+ enum led_brightness brightness)
+{
+ struct mt6323_led *led = container_of(cdev, struct mt6323_led, cdev);
+ struct mt6323_leds *leds = led->parent;
+ struct regmap *regmap = leds->hw->regmap;
+ u32 con2_mask = 0, con2_val = 0;
+ int ret;
+
+ /*
+ * Setup current output for the corresponding
+ * brightness level.
+ */
+ con2_mask |= MT6323_ISINK_CH_STEP_MASK |
+ MT6323_ISINK_SFSTR0_TC_MASK |
+ MT6323_ISINK_SFSTR0_EN_MASK;
+ con2_val |= MT6323_ISINK_CH_STEP(brightness - 1) |
+ MT6323_ISINK_SFSTR0_TC(2) |
+ MT6323_ISINK_SFSTR0_EN;
+
+ ret = regmap_update_bits(regmap, MT6323_ISINK_CON2(led->id),
+ con2_mask, con2_val);
+ return ret;
+}
+
+static int mt6323_led_hw_off(struct led_classdev *cdev)
+{
+ struct mt6323_led *led = container_of(cdev, struct mt6323_led, cdev);
+ struct mt6323_leds *leds = led->parent;
+ struct regmap *regmap = leds->hw->regmap;
+ unsigned int status;
+ int ret;
+
+ status = MT6323_ISINK_CH_EN(led->id);
+ ret = regmap_update_bits(regmap, MT6323_ISINK_EN_CTRL,
+ MT6323_ISINK_CH_EN_MASK(led->id), ~status);
+ if (ret < 0)
+ return ret;
+
+ usleep_range(100, 300);
+ ret = regmap_update_bits(regmap, MT6323_TOP_CKPDN2,
+ MT6323_RG_ISINK_CK_PDN_MASK(led->id),
+ MT6323_RG_ISINK_CK_PDN(led->id));
+ if (ret < 0)
+ return ret;
+
+ return 0;
+}
+
+static enum led_brightness
+mt6323_get_led_hw_brightness(struct led_classdev *cdev)
+{
+ struct mt6323_led *led = container_of(cdev, struct mt6323_led, cdev);
+ struct mt6323_leds *leds = led->parent;
+ struct regmap *regmap = leds->hw->regmap;
+ unsigned int status;
+ int ret;
+
+ ret = regmap_read(regmap, MT6323_TOP_CKPDN2, &status);
+ if (ret < 0)
+ return ret;
+
+ if (status & MT6323_RG_ISINK_CK_PDN_MASK(led->id))
+ return 0;
+
+ ret = regmap_read(regmap, MT6323_ISINK_EN_CTRL, &status);
+ if (ret < 0)
+ return ret;
+
+ if (!(status & MT6323_ISINK_CH_EN(led->id)))
+ return 0;
+
+ ret = regmap_read(regmap, MT6323_ISINK_CON2(led->id), &status);
+ if (ret < 0)
+ return ret;
+
+ return ((status & MT6323_ISINK_CH_STEP_MASK)
+ >> MT6323_ISINK_CH_STEP_SHIFT) + 1;
+}
+
+static int mt6323_led_hw_on(struct led_classdev *cdev,
+ enum led_brightness brightness)
+{
+ struct mt6323_led *led = container_of(cdev, struct mt6323_led, cdev);
+ struct mt6323_leds *leds = led->parent;
+ struct regmap *regmap = leds->hw->regmap;
+ unsigned int status;
+ int ret;
+
+ /*
+ * Setup required clock source, enable the corresponding
+ * clock and channel and let work with continuous blink as
+ * the default.
+ */
+ ret = regmap_update_bits(regmap, MT6323_TOP_CKCON1,
+ MT6323_RG_ISINK_CK_SEL_MASK(led->id), 0);
+ if (ret < 0)
+ return ret;
+
+ status = MT6323_RG_ISINK_CK_PDN(led->id);
+ ret = regmap_update_bits(regmap, MT6323_TOP_CKPDN2,
+ MT6323_RG_ISINK_CK_PDN_MASK(led->id),
+ ~status);
+ if (ret < 0)
+ return ret;
+
+ usleep_range(100, 300);
+
+ ret = regmap_update_bits(regmap, MT6323_ISINK_EN_CTRL,
+ MT6323_ISINK_CH_EN_MASK(led->id),
+ MT6323_ISINK_CH_EN(led->id));
+ if (ret < 0)
+ return ret;
+
+ ret = mt6323_led_hw_brightness(cdev, brightness);
+ if (ret < 0)
+ return ret;
+
+ ret = regmap_update_bits(regmap, MT6323_ISINK_CON0(led->id),
+ MT6323_ISINK_DIM_DUTY_MASK,
+ MT6323_ISINK_DIM_DUTY(31));
+ if (ret < 0)
+ return ret;
+
+ ret = regmap_update_bits(regmap, MT6323_ISINK_CON1(led->id),
+ MT6323_ISINK_DIM_FSEL_MASK,
+ MT6323_ISINK_DIM_FSEL(1000));
+ if (ret < 0)
+ return ret;
+
+ return 0;
+}
+
+static int mt6323_led_set_blink(struct led_classdev *cdev,
+ unsigned long *delay_on,
+ unsigned long *delay_off)
+{
+ struct mt6323_led *led = container_of(cdev, struct mt6323_led, cdev);
+ struct mt6323_leds *leds = led->parent;
+ struct regmap *regmap = leds->hw->regmap;
+ unsigned long period;
+ u8 duty_hw;
+ int ret;
+
+ /*
+ * Units are in ms, if over the hardware able
+ * to support, fallback into software blink
+ */
+ period = *delay_on + *delay_off;
+
+ if (period > MT6323_MAX_PERIOD)
+ return -EINVAL;
+
+ /*
+ * LED subsystem requires a default user
+ * friendly blink pattern for the LED so using
+ * 1Hz duty cycle 50% here if without specific
+ * value delay_on and delay off being assigned.
+ */
+ if (!*delay_on && !*delay_off) {
+ *delay_on = 500;
+ *delay_off = 500;
+ }
+
+ /*
+ * Calculate duty_hw based on the percentage of period during
+ * which the led is ON.
+ */
+ duty_hw = MT6323_CAL_HW_DUTY(*delay_on, period);
+
+ /* hardware doesn't support zero duty cycle. */
+ if (!duty_hw)
+ return -EINVAL;
+
+ mutex_lock(&leds->lock);
+ /*
+ * Set max_brightness as the software blink behavior
+ * when no blink brightness.
+ */
+ if (!led->current_brightness) {
+ ret = mt6323_led_hw_on(cdev, cdev->max_brightness);
+ if (ret < 0)
+ goto out;
+ led->current_brightness = cdev->max_brightness;
+ }
+
+ ret = regmap_update_bits(regmap, MT6323_ISINK_CON0(led->id),
+ MT6323_ISINK_DIM_DUTY_MASK,
+ MT6323_ISINK_DIM_DUTY(duty_hw - 1));
+ if (ret < 0)
+ goto out;
+
+ ret = regmap_update_bits(regmap, MT6323_ISINK_CON1(led->id),
+ MT6323_ISINK_DIM_FSEL_MASK,
+ MT6323_ISINK_DIM_FSEL(period - 1));
+out:
+ mutex_unlock(&leds->lock);
+
+ return ret;
+}
+
+static int mt6323_led_set_brightness(struct led_classdev *cdev,
+ enum led_brightness brightness)
+{
+ struct mt6323_led *led = container_of(cdev, struct mt6323_led, cdev);
+ struct mt6323_leds *leds = led->parent;
+ int ret;
+
+ mutex_lock(&leds->lock);
+
+ if (!led->current_brightness && brightness) {
+ ret = mt6323_led_hw_on(cdev, brightness);
+ if (ret < 0)
+ goto out;
+ } else if (brightness) {
+ ret = mt6323_led_hw_brightness(cdev, brightness);
+ if (ret < 0)
+ goto out;
+ } else {
+ ret = mt6323_led_hw_off(cdev);
+ if (ret < 0)
+ goto out;
+ }
+
+ led->current_brightness = brightness;
+out:
+ mutex_unlock(&leds->lock);
+
+ return ret;
+}
+
+static int mt6323_led_set_dt_default(struct led_classdev *cdev,
+ struct device_node *np)
+{
+ struct mt6323_led *led = container_of(cdev, struct mt6323_led, cdev);
+ const char *state;
+ int ret = 0;
+
+ led->cdev.name = of_get_property(np, "label", NULL) ? : np->name;
+ led->cdev.default_trigger = of_get_property(np,
+ "linux,default-trigger",
+ NULL);
+
+ state = of_get_property(np, "default-state", NULL);
+ if (state) {
+ if (!strcmp(state, "keep")) {
+ ret = mt6323_get_led_hw_brightness(cdev);
+ if (ret < 0)
+ return ret;
+ led->current_brightness = ret;
+ ret = 0;
+ } else if (!strcmp(state, "on")) {
+ ret =
+ mt6323_led_set_brightness(cdev, cdev->max_brightness);
+ } else {
+ ret = mt6323_led_set_brightness(cdev, LED_OFF);
+ }
+ }
+
+ return ret;
+}
+
+static int mt6323_led_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct device_node *np = pdev->dev.of_node;
+ struct device_node *child;
+ struct mt6397_chip *hw = dev_get_drvdata(pdev->dev.parent);
+ struct mt6323_leds *leds;
+ struct mt6323_led *led;
+ int ret;
+ unsigned int status;
+ u32 reg;
+
+ leds = devm_kzalloc(dev, sizeof(*leds), GFP_KERNEL);
+ if (!leds)
+ return -ENOMEM;
+
+ platform_set_drvdata(pdev, leds);
+ leds->dev = dev;
+
+ /*
+ * leds->hw points to the underlying bus for the register
+ * controlled.
+ */
+ leds->hw = hw;
+ mutex_init(&leds->lock);
+
+ status = MT6323_RG_DRV_32K_CK_PDN;
+ ret = regmap_update_bits(leds->hw->regmap, MT6323_TOP_CKPDN0,
+ MT6323_RG_DRV_32K_CK_PDN_MASK, ~status);
+ if (ret < 0) {
+ dev_err(leds->dev,
+ "Failed to update MT6323_TOP_CKPDN0 Register\n");
+ return ret;
+ }
+
+ for_each_available_child_of_node(np, child) {
+ ret = of_property_read_u32(child, "reg", ®);
+ if (ret) {
+ dev_err(dev, "Failed to read led 'reg' property\n");
+ goto put_child_node;
+ }
+
+ if (reg >= MT6323_MAX_LEDS || leds->led[reg]) {
+ dev_err(dev, "Invalid led reg %u\n", reg);
+ ret = -EINVAL;
+ goto put_child_node;
+ }
+
+ led = devm_kzalloc(dev, sizeof(*led), GFP_KERNEL);
+ if (!led) {
+ ret = -ENOMEM;
+ goto put_child_node;
+ }
+
+ leds->led[reg] = led;
+ leds->led[reg]->id = reg;
+ leds->led[reg]->cdev.max_brightness = MT6323_MAX_BRIGHTNESS;
+ leds->led[reg]->cdev.brightness_set_blocking =
+ mt6323_led_set_brightness;
+ leds->led[reg]->cdev.blink_set = mt6323_led_set_blink;
+ leds->led[reg]->cdev.brightness_get =
+ mt6323_get_led_hw_brightness;
+ leds->led[reg]->parent = leds;
+
+ ret = mt6323_led_set_dt_default(&leds->led[reg]->cdev, child);
+ if (ret < 0) {
+ dev_err(leds->dev,
+ "Failed to LED set default from devicetree\n");
+ goto put_child_node;
+ }
+
+ ret = devm_led_classdev_register(dev, &leds->led[reg]->cdev);
+ if (ret) {
+ dev_err(&pdev->dev, "Failed to register LED: %d\n",
+ ret);
+ goto put_child_node;
+ }
+ leds->led[reg]->cdev.dev->of_node = child;
+ }
+
+ return 0;
+
+put_child_node:
+ of_node_put(child);
+ return ret;
+}
+
+static int mt6323_led_remove(struct platform_device *pdev)
+{
+ struct mt6323_leds *leds = platform_get_drvdata(pdev);
+ int i;
+
+ /* Turn the LEDs off on driver removal. */
+ for (i = 0 ; leds->led[i] ; i++)
+ mt6323_led_hw_off(&leds->led[i]->cdev);
+
+ regmap_update_bits(leds->hw->regmap, MT6323_TOP_CKPDN0,
+ MT6323_RG_DRV_32K_CK_PDN_MASK,
+ MT6323_RG_DRV_32K_CK_PDN);
+
+ mutex_destroy(&leds->lock);
+
+ return 0;
+}
+
+static const struct of_device_id mt6323_led_dt_match[] = {
+ { .compatible = "mediatek,mt6323-led" },
+ {},
+};
+MODULE_DEVICE_TABLE(of, mt6323_led_dt_match);
+
+static struct platform_driver mt6323_led_driver = {
+ .probe = mt6323_led_probe,
+ .remove = mt6323_led_remove,
+ .driver = {
+ .name = "mt6323-led",
+ .of_match_table = mt6323_led_dt_match,
+ },
+};
+
+module_platform_driver(mt6323_led_driver);
+
+MODULE_DESCRIPTION("LED driver for Mediatek MT6323 PMIC");
+MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
+MODULE_LICENSE("GPL");
mutex_unlock(&data->update_lock);
}
+static enum pca9532_state pca9532_getled(struct pca9532_led *led)
+{
+ struct i2c_client *client = led->client;
+ struct pca9532_data *data = i2c_get_clientdata(client);
+ u8 maxleds = data->chip_info->num_leds;
+ char reg;
+ enum pca9532_state ret;
+
+ mutex_lock(&data->update_lock);
+ reg = i2c_smbus_read_byte_data(client, LED_REG(maxleds, led->id));
+ ret = reg >> LED_NUM(led->id)/2;
+ mutex_unlock(&data->update_lock);
+ return ret;
+}
+
#ifdef CONFIG_LEDS_PCA9532_GPIO
static int pca9532_gpio_request_pin(struct gpio_chip *gc, unsigned offset)
{
gpios++;
break;
case PCA9532_TYPE_LED:
- led->state = pled->state;
+ if (pled->state == PCA9532_KEEP)
+ led->state = pca9532_getled(led);
+ else
+ led->state = pled->state;
led->name = pled->name;
led->ldev.name = led->name;
led->ldev.default_trigger = pled->default_trigger;
const struct of_device_id *match;
int devid, maxleds;
int i = 0;
+ const char *state;
match = of_match_device(of_pca9532_leds_match, dev);
if (!match)
of_property_read_u32(child, "type", &pdata->leds[i].type);
of_property_read_string(child, "linux,default-trigger",
&pdata->leds[i].default_trigger);
+ if (!of_property_read_string(child, "default-state", &state)) {
+ if (!strcmp(state, "on"))
+ pdata->leds[i].state = PCA9532_ON;
+ else if (!strcmp(state, "keep"))
+ pdata->leds[i].state = PCA9532_KEEP;
+ }
if (++i >= maxleds) {
of_node_put(child);
break;
#define MAX_NAME_LEN 8
struct led_trigger_cpu {
+ bool is_active;
char name[MAX_NAME_LEN];
struct led_trigger *_trig;
};
static DEFINE_PER_CPU(struct led_trigger_cpu, cpu_trig);
+static struct led_trigger *trig_cpu_all;
+static atomic_t num_active_cpus = ATOMIC_INIT(0);
+
/**
* ledtrig_cpu - emit a CPU event as a trigger
* @evt: CPU event to be emitted
void ledtrig_cpu(enum cpu_led_event ledevt)
{
struct led_trigger_cpu *trig = this_cpu_ptr(&cpu_trig);
+ bool is_active = trig->is_active;
/* Locate the correct CPU LED */
switch (ledevt) {
case CPU_LED_IDLE_END:
case CPU_LED_START:
/* Will turn the LED on, max brightness */
- led_trigger_event(trig->_trig, LED_FULL);
+ is_active = true;
break;
case CPU_LED_IDLE_START:
case CPU_LED_STOP:
case CPU_LED_HALTED:
/* Will turn the LED off */
- led_trigger_event(trig->_trig, LED_OFF);
+ is_active = false;
break;
default:
/* Will leave the LED as it is */
break;
}
+
+ if (is_active != trig->is_active) {
+ unsigned int active_cpus;
+ unsigned int total_cpus;
+
+ /* Update trigger state */
+ trig->is_active = is_active;
+ atomic_add(is_active ? 1 : -1, &num_active_cpus);
+ active_cpus = atomic_read(&num_active_cpus);
+ total_cpus = num_present_cpus();
+
+ led_trigger_event(trig->_trig,
+ is_active ? LED_FULL : LED_OFF);
+
+
+ led_trigger_event(trig_cpu_all,
+ DIV_ROUND_UP(LED_FULL * active_cpus, total_cpus));
+
+ }
}
EXPORT_SYMBOL(ledtrig_cpu);
BUILD_BUG_ON(CONFIG_NR_CPUS > 9999);
/*
+ * Registering a trigger for all CPUs.
+ */
+ led_trigger_register_simple("cpu", &trig_cpu_all);
+
+ /*
* Registering CPU led trigger for each CPU core here
* ignores CPU hotplug, but after this CPU hotplug works
* fine with this trigger.
host. The target is implemented using a linear mapping table and
cost-based garbage collection. It is optimized for 4K IO sizes.
+config NVM_PBLK
+ tristate "Physical Block Device Open-Channel SSD target"
+ ---help---
+ Allows an open-channel SSD to be exposed as a block device to the
+ host. The target assumes the device exposes raw flash and must be
+ explicitly managed by the host.
+
+ Please note the disk format is considered EXPERIMENTAL for now.
+
endif # NVM
obj-$(CONFIG_NVM) := core.o
obj-$(CONFIG_NVM_RRPC) += rrpc.o
+obj-$(CONFIG_NVM_PBLK) += pblk.o
+pblk-y := pblk-init.o pblk-core.o pblk-rb.o \
+ pblk-write.o pblk-cache.o pblk-read.o \
+ pblk-gc.o pblk-recovery.o pblk-map.o \
+ pblk-rl.o pblk-sysfs.o
WARN_ON(!test_and_clear_bit(i, dev->lun_map));
}
-static void nvm_remove_tgt_dev(struct nvm_tgt_dev *tgt_dev)
+static void nvm_remove_tgt_dev(struct nvm_tgt_dev *tgt_dev, int clear)
{
struct nvm_dev *dev = tgt_dev->parent;
struct nvm_dev_map *dev_map = tgt_dev->map;
int *lun_offs = ch_map->lun_offs;
int ch = i + ch_map->ch_off;
- for (j = 0; j < ch_map->nr_luns; j++) {
- int lun = j + lun_offs[j];
- int lunid = (ch * dev->geo.luns_per_chnl) + lun;
+ if (clear) {
+ for (j = 0; j < ch_map->nr_luns; j++) {
+ int lun = j + lun_offs[j];
+ int lunid = (ch * dev->geo.luns_per_chnl) + lun;
- WARN_ON(!test_and_clear_bit(lunid, dev->lun_map));
+ WARN_ON(!test_and_clear_bit(lunid,
+ dev->lun_map));
+ }
}
kfree(ch_map->lun_offs);
struct nvm_target *t;
struct nvm_tgt_dev *tgt_dev;
void *targetdata;
+ int ret;
tt = nvm_find_target_type(create->tgttype, 1);
if (!tt) {
return -ENOMEM;
t = kmalloc(sizeof(struct nvm_target), GFP_KERNEL);
- if (!t)
+ if (!t) {
+ ret = -ENOMEM;
goto err_reserve;
+ }
tgt_dev = nvm_create_tgt_dev(dev, s->lun_begin, s->lun_end);
if (!tgt_dev) {
pr_err("nvm: could not create target device\n");
+ ret = -ENOMEM;
goto err_t;
}
- tqueue = blk_alloc_queue_node(GFP_KERNEL, dev->q->node);
- if (!tqueue)
+ tdisk = alloc_disk(0);
+ if (!tdisk) {
+ ret = -ENOMEM;
goto err_dev;
- blk_queue_make_request(tqueue, tt->make_rq);
+ }
- tdisk = alloc_disk(0);
- if (!tdisk)
- goto err_queue;
+ tqueue = blk_alloc_queue_node(GFP_KERNEL, dev->q->node);
+ if (!tqueue) {
+ ret = -ENOMEM;
+ goto err_disk;
+ }
+ blk_queue_make_request(tqueue, tt->make_rq);
- sprintf(tdisk->disk_name, "%s", create->tgtname);
+ strlcpy(tdisk->disk_name, create->tgtname, sizeof(tdisk->disk_name));
tdisk->flags = GENHD_FL_EXT_DEVT;
tdisk->major = 0;
tdisk->first_minor = 0;
tdisk->fops = &nvm_fops;
tdisk->queue = tqueue;
- targetdata = tt->init(tgt_dev, tdisk);
- if (IS_ERR(targetdata))
+ targetdata = tt->init(tgt_dev, tdisk, create->flags);
+ if (IS_ERR(targetdata)) {
+ ret = PTR_ERR(targetdata);
goto err_init;
+ }
tdisk->private_data = targetdata;
tqueue->queuedata = targetdata;
set_capacity(tdisk, tt->capacity(targetdata));
add_disk(tdisk);
- if (tt->sysfs_init && tt->sysfs_init(tdisk))
+ if (tt->sysfs_init && tt->sysfs_init(tdisk)) {
+ ret = -ENOMEM;
goto err_sysfs;
+ }
t->type = tt;
t->disk = tdisk;
if (tt->exit)
tt->exit(targetdata);
err_init:
- put_disk(tdisk);
-err_queue:
blk_cleanup_queue(tqueue);
+ tdisk->queue = NULL;
+err_disk:
+ put_disk(tdisk);
err_dev:
- nvm_remove_tgt_dev(tgt_dev);
+ nvm_remove_tgt_dev(tgt_dev, 0);
err_t:
kfree(t);
err_reserve:
nvm_release_luns_err(dev, s->lun_begin, s->lun_end);
- return -ENOMEM;
+ return ret;
}
static void __nvm_remove_target(struct nvm_target *t)
if (tt->exit)
tt->exit(tdisk->private_data);
- nvm_remove_tgt_dev(t->dev);
+ nvm_remove_tgt_dev(t->dev, 1);
put_disk(tdisk);
list_del(&t->list);
return -ENOMEM;
}
+static void nvm_unregister_map(struct nvm_dev *dev)
+{
+ struct nvm_dev_map *rmap = dev->rmap;
+ int i;
+
+ for (i = 0; i < dev->geo.nr_chnls; i++)
+ kfree(rmap->chnls[i].lun_offs);
+
+ kfree(rmap->chnls);
+ kfree(rmap);
+}
+
static void nvm_map_to_dev(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *p)
{
struct nvm_dev_map *dev_map = tgt_dev->map;
int *lun_roffs;
struct ppa_addr gaddr;
u64 pba = le64_to_cpu(entries[i]);
- int off;
u64 diff;
if (!pba)
ch_rmap = &dev_rmap->chnls[gaddr.g.ch];
lun_roffs = ch_rmap->lun_offs;
- off = gaddr.g.ch * geo->luns_per_chnl + gaddr.g.lun;
-
diff = ((ch_rmap->ch_off * geo->luns_per_chnl) +
(lun_roffs[gaddr.g.lun])) * geo->sec_per_lun;
memset(&rqd, 0, sizeof(struct nvm_rq));
- nvm_set_rqd_ppalist(dev, &rqd, ppas, nr_ppas, 1);
+ nvm_set_rqd_ppalist(tgt_dev, &rqd, ppas, nr_ppas, 1);
nvm_rq_tgt_to_dev(tgt_dev, &rqd);
ret = dev->ops->set_bb_tbl(dev, &rqd.ppa_addr, rqd.nr_ppas, type);
- nvm_free_rqd_ppalist(dev, &rqd);
+ nvm_free_rqd_ppalist(tgt_dev, &rqd);
if (ret) {
pr_err("nvm: failed bb mark\n");
return -EINVAL;
}
EXPORT_SYMBOL(nvm_submit_io);
-int nvm_erase_blk(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *ppas, int flags)
+static void nvm_end_io_sync(struct nvm_rq *rqd)
{
- struct nvm_dev *dev = tgt_dev->parent;
- struct nvm_rq rqd;
- int ret;
+ struct completion *waiting = rqd->private;
- if (!dev->ops->erase_block)
- return 0;
+ complete(waiting);
+}
- nvm_map_to_dev(tgt_dev, ppas);
+int nvm_erase_sync(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *ppas,
+ int nr_ppas)
+{
+ struct nvm_geo *geo = &tgt_dev->geo;
+ struct nvm_rq rqd;
+ int ret;
+ DECLARE_COMPLETION_ONSTACK(wait);
memset(&rqd, 0, sizeof(struct nvm_rq));
- ret = nvm_set_rqd_ppalist(dev, &rqd, ppas, 1, 1);
+ rqd.opcode = NVM_OP_ERASE;
+ rqd.end_io = nvm_end_io_sync;
+ rqd.private = &wait;
+ rqd.flags = geo->plane_mode >> 1;
+
+ ret = nvm_set_rqd_ppalist(tgt_dev, &rqd, ppas, nr_ppas, 1);
if (ret)
return ret;
- nvm_rq_tgt_to_dev(tgt_dev, &rqd);
-
- rqd.flags = flags;
-
- ret = dev->ops->erase_block(dev, &rqd);
+ ret = nvm_submit_io(tgt_dev, &rqd);
+ if (ret) {
+ pr_err("rrpr: erase I/O submission failed: %d\n", ret);
+ goto free_ppa_list;
+ }
+ wait_for_completion_io(&wait);
- nvm_free_rqd_ppalist(dev, &rqd);
+free_ppa_list:
+ nvm_free_rqd_ppalist(tgt_dev, &rqd);
return ret;
}
-EXPORT_SYMBOL(nvm_erase_blk);
+EXPORT_SYMBOL(nvm_erase_sync);
int nvm_get_l2p_tbl(struct nvm_tgt_dev *tgt_dev, u64 slba, u32 nlb,
nvm_l2p_update_fn *update_l2p, void *priv)
}
EXPORT_SYMBOL(nvm_put_area);
-int nvm_set_rqd_ppalist(struct nvm_dev *dev, struct nvm_rq *rqd,
+int nvm_set_rqd_ppalist(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd,
const struct ppa_addr *ppas, int nr_ppas, int vblk)
{
- struct nvm_geo *geo = &dev->geo;
+ struct nvm_dev *dev = tgt_dev->parent;
+ struct nvm_geo *geo = &tgt_dev->geo;
int i, plane_cnt, pl_idx;
struct ppa_addr ppa;
}
EXPORT_SYMBOL(nvm_set_rqd_ppalist);
-void nvm_free_rqd_ppalist(struct nvm_dev *dev, struct nvm_rq *rqd)
+void nvm_free_rqd_ppalist(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd)
{
if (!rqd->ppa_list)
return;
- nvm_dev_dma_free(dev, rqd->ppa_list, rqd->dma_ppa_list);
+ nvm_dev_dma_free(tgt_dev->parent, rqd->ppa_list, rqd->dma_ppa_list);
}
EXPORT_SYMBOL(nvm_free_rqd_ppalist);
return ret;
}
-void nvm_free(struct nvm_dev *dev)
+static void nvm_free(struct nvm_dev *dev)
{
if (!dev)
return;
if (dev->dma_pool)
dev->ops->destroy_dma_pool(dev->dma_pool);
- kfree(dev->rmap);
+ nvm_unregister_map(dev);
kfree(dev->lptbl);
kfree(dev->lun_map);
kfree(dev);
list_for_each_entry(dev, &nvm_devices, devices) {
struct nvm_ioctl_device_info *info = &devices->info[i];
- sprintf(info->devname, "%s", dev->name);
+ strlcpy(info->devname, dev->name, sizeof(info->devname));
/* kept for compatibility */
info->bmversion[0] = 1;
info->bmversion[1] = 0;
info->bmversion[2] = 0;
- sprintf(info->bmname, "%s", "gennvm");
+ strlcpy(info->bmname, "gennvm", sizeof(info->bmname));
i++;
if (i > 31) {
create.tgtname[DISK_NAME_LEN - 1] = '\0';
if (create.flags != 0) {
- pr_err("nvm: no flags supported\n");
- return -EINVAL;
+ __u32 flags = create.flags;
+
+ /* Check for valid flags */
+ if (flags & NVM_TARGET_FACTORY)
+ flags &= ~NVM_TARGET_FACTORY;
+
+ if (flags) {
+ pr_err("nvm: flag not supported\n");
+ return -EINVAL;
+ }
}
return __nvm_configure_create(&create);
--- /dev/null
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ * Matias Bjorling <matias@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * pblk-cache.c - pblk's write cache
+ */
+
+#include "pblk.h"
+
+int pblk_write_to_cache(struct pblk *pblk, struct bio *bio, unsigned long flags)
+{
+ struct pblk_w_ctx w_ctx;
+ sector_t lba = pblk_get_lba(bio);
+ unsigned int bpos, pos;
+ int nr_entries = pblk_get_secs(bio);
+ int i, ret;
+
+ /* Update the write buffer head (mem) with the entries that we can
+ * write. The write in itself cannot fail, so there is no need to
+ * rollback from here on.
+ */
+retry:
+ ret = pblk_rb_may_write_user(&pblk->rwb, bio, nr_entries, &bpos);
+ if (ret == NVM_IO_REQUEUE) {
+ io_schedule();
+ goto retry;
+ }
+
+ if (unlikely(!bio_has_data(bio)))
+ goto out;
+
+ w_ctx.flags = flags;
+ pblk_ppa_set_empty(&w_ctx.ppa);
+
+ for (i = 0; i < nr_entries; i++) {
+ void *data = bio_data(bio);
+
+ w_ctx.lba = lba + i;
+
+ pos = pblk_rb_wrap_pos(&pblk->rwb, bpos + i);
+ pblk_rb_write_entry_user(&pblk->rwb, data, w_ctx, pos);
+
+ bio_advance(bio, PBLK_EXPOSED_PAGE_SIZE);
+ }
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_add(nr_entries, &pblk->inflight_writes);
+ atomic_long_add(nr_entries, &pblk->req_writes);
+#endif
+
+out:
+ pblk_write_should_kick(pblk);
+ return ret;
+}
+
+/*
+ * On GC the incoming lbas are not necessarily sequential. Also, some of the
+ * lbas might not be valid entries, which are marked as empty by the GC thread
+ */
+int pblk_write_gc_to_cache(struct pblk *pblk, void *data, u64 *lba_list,
+ unsigned int nr_entries, unsigned int nr_rec_entries,
+ struct pblk_line *gc_line, unsigned long flags)
+{
+ struct pblk_w_ctx w_ctx;
+ unsigned int bpos, pos;
+ int i, valid_entries;
+
+ /* Update the write buffer head (mem) with the entries that we can
+ * write. The write in itself cannot fail, so there is no need to
+ * rollback from here on.
+ */
+retry:
+ if (!pblk_rb_may_write_gc(&pblk->rwb, nr_rec_entries, &bpos)) {
+ io_schedule();
+ goto retry;
+ }
+
+ w_ctx.flags = flags;
+ pblk_ppa_set_empty(&w_ctx.ppa);
+
+ for (i = 0, valid_entries = 0; i < nr_entries; i++) {
+ if (lba_list[i] == ADDR_EMPTY)
+ continue;
+
+ w_ctx.lba = lba_list[i];
+
+ pos = pblk_rb_wrap_pos(&pblk->rwb, bpos + valid_entries);
+ pblk_rb_write_entry_gc(&pblk->rwb, data, w_ctx, gc_line, pos);
+
+ data += PBLK_EXPOSED_PAGE_SIZE;
+ valid_entries++;
+ }
+
+ WARN_ONCE(nr_rec_entries != valid_entries,
+ "pblk: inconsistent GC write\n");
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_add(valid_entries, &pblk->inflight_writes);
+ atomic_long_add(valid_entries, &pblk->recov_gc_writes);
+#endif
+
+ pblk_write_should_kick(pblk);
+ return NVM_IO_OK;
+}
--- /dev/null
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ * Matias Bjorling <matias@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * pblk-core.c - pblk's core functionality
+ *
+ */
+
+#include "pblk.h"
+#include <linux/time.h>
+
+static void pblk_mark_bb(struct pblk *pblk, struct pblk_line *line,
+ struct ppa_addr *ppa)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ int pos = pblk_dev_ppa_to_pos(geo, *ppa);
+
+ pr_debug("pblk: erase failed: line:%d, pos:%d\n", line->id, pos);
+ atomic_long_inc(&pblk->erase_failed);
+
+ atomic_dec(&line->blk_in_line);
+ if (test_and_set_bit(pos, line->blk_bitmap))
+ pr_err("pblk: attempted to erase bb: line:%d, pos:%d\n",
+ line->id, pos);
+
+ pblk_line_run_ws(pblk, NULL, ppa, pblk_line_mark_bb);
+}
+
+static void __pblk_end_io_erase(struct pblk *pblk, struct nvm_rq *rqd)
+{
+ struct pblk_line *line;
+
+ line = &pblk->lines[pblk_dev_ppa_to_line(rqd->ppa_addr)];
+ atomic_dec(&line->left_seblks);
+
+ if (rqd->error) {
+ struct ppa_addr *ppa;
+
+ ppa = kmalloc(sizeof(struct ppa_addr), GFP_ATOMIC);
+ if (!ppa)
+ return;
+
+ *ppa = rqd->ppa_addr;
+ pblk_mark_bb(pblk, line, ppa);
+ }
+}
+
+/* Erase completion assumes that only one block is erased at the time */
+static void pblk_end_io_erase(struct nvm_rq *rqd)
+{
+ struct pblk *pblk = rqd->private;
+
+ up(&pblk->erase_sem);
+ __pblk_end_io_erase(pblk, rqd);
+ mempool_free(rqd, pblk->r_rq_pool);
+}
+
+static void __pblk_map_invalidate(struct pblk *pblk, struct pblk_line *line,
+ u64 paddr)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct list_head *move_list = NULL;
+
+ /* Lines being reclaimed (GC'ed) cannot be invalidated. Before the L2P
+ * table is modified with reclaimed sectors, a check is done to endure
+ * that newer updates are not overwritten.
+ */
+ spin_lock(&line->lock);
+ if (line->state == PBLK_LINESTATE_GC ||
+ line->state == PBLK_LINESTATE_FREE) {
+ spin_unlock(&line->lock);
+ return;
+ }
+
+ if (test_and_set_bit(paddr, line->invalid_bitmap)) {
+ WARN_ONCE(1, "pblk: double invalidate\n");
+ spin_unlock(&line->lock);
+ return;
+ }
+ line->vsc--;
+
+ if (line->state == PBLK_LINESTATE_CLOSED)
+ move_list = pblk_line_gc_list(pblk, line);
+ spin_unlock(&line->lock);
+
+ if (move_list) {
+ spin_lock(&l_mg->gc_lock);
+ spin_lock(&line->lock);
+ /* Prevent moving a line that has just been chosen for GC */
+ if (line->state == PBLK_LINESTATE_GC ||
+ line->state == PBLK_LINESTATE_FREE) {
+ spin_unlock(&line->lock);
+ spin_unlock(&l_mg->gc_lock);
+ return;
+ }
+ spin_unlock(&line->lock);
+
+ list_move_tail(&line->list, move_list);
+ spin_unlock(&l_mg->gc_lock);
+ }
+}
+
+void pblk_map_invalidate(struct pblk *pblk, struct ppa_addr ppa)
+{
+ struct pblk_line *line;
+ u64 paddr;
+ int line_id;
+
+#ifdef CONFIG_NVM_DEBUG
+ /* Callers must ensure that the ppa points to a device address */
+ BUG_ON(pblk_addr_in_cache(ppa));
+ BUG_ON(pblk_ppa_empty(ppa));
+#endif
+
+ line_id = pblk_tgt_ppa_to_line(ppa);
+ line = &pblk->lines[line_id];
+ paddr = pblk_dev_ppa_to_line_addr(pblk, ppa);
+
+ __pblk_map_invalidate(pblk, line, paddr);
+}
+
+void pblk_map_pad_invalidate(struct pblk *pblk, struct pblk_line *line,
+ u64 paddr)
+{
+ __pblk_map_invalidate(pblk, line, paddr);
+
+ pblk_rb_sync_init(&pblk->rwb, NULL);
+ line->left_ssecs--;
+ if (!line->left_ssecs)
+ pblk_line_run_ws(pblk, line, NULL, pblk_line_close_ws);
+ pblk_rb_sync_end(&pblk->rwb, NULL);
+}
+
+static void pblk_invalidate_range(struct pblk *pblk, sector_t slba,
+ unsigned int nr_secs)
+{
+ sector_t lba;
+
+ spin_lock(&pblk->trans_lock);
+ for (lba = slba; lba < slba + nr_secs; lba++) {
+ struct ppa_addr ppa;
+
+ ppa = pblk_trans_map_get(pblk, lba);
+
+ if (!pblk_addr_in_cache(ppa) && !pblk_ppa_empty(ppa))
+ pblk_map_invalidate(pblk, ppa);
+
+ pblk_ppa_set_empty(&ppa);
+ pblk_trans_map_set(pblk, lba, ppa);
+ }
+ spin_unlock(&pblk->trans_lock);
+}
+
+struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int rw)
+{
+ mempool_t *pool;
+ struct nvm_rq *rqd;
+ int rq_size;
+
+ if (rw == WRITE) {
+ pool = pblk->w_rq_pool;
+ rq_size = pblk_w_rq_size;
+ } else {
+ pool = pblk->r_rq_pool;
+ rq_size = pblk_r_rq_size;
+ }
+
+ rqd = mempool_alloc(pool, GFP_KERNEL);
+ memset(rqd, 0, rq_size);
+
+ return rqd;
+}
+
+void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int rw)
+{
+ mempool_t *pool;
+
+ if (rw == WRITE)
+ pool = pblk->w_rq_pool;
+ else
+ pool = pblk->r_rq_pool;
+
+ mempool_free(rqd, pool);
+}
+
+void pblk_bio_free_pages(struct pblk *pblk, struct bio *bio, int off,
+ int nr_pages)
+{
+ struct bio_vec bv;
+ int i;
+
+ WARN_ON(off + nr_pages != bio->bi_vcnt);
+
+ bio_advance(bio, off * PBLK_EXPOSED_PAGE_SIZE);
+ for (i = off; i < nr_pages + off; i++) {
+ bv = bio->bi_io_vec[i];
+ mempool_free(bv.bv_page, pblk->page_pool);
+ }
+}
+
+int pblk_bio_add_pages(struct pblk *pblk, struct bio *bio, gfp_t flags,
+ int nr_pages)
+{
+ struct request_queue *q = pblk->dev->q;
+ struct page *page;
+ int i, ret;
+
+ for (i = 0; i < nr_pages; i++) {
+ page = mempool_alloc(pblk->page_pool, flags);
+ if (!page)
+ goto err;
+
+ ret = bio_add_pc_page(q, bio, page, PBLK_EXPOSED_PAGE_SIZE, 0);
+ if (ret != PBLK_EXPOSED_PAGE_SIZE) {
+ pr_err("pblk: could not add page to bio\n");
+ mempool_free(page, pblk->page_pool);
+ goto err;
+ }
+ }
+
+ return 0;
+err:
+ pblk_bio_free_pages(pblk, bio, 0, i - 1);
+ return -1;
+}
+
+static void pblk_write_kick(struct pblk *pblk)
+{
+ wake_up_process(pblk->writer_ts);
+ mod_timer(&pblk->wtimer, jiffies + msecs_to_jiffies(1000));
+}
+
+void pblk_write_timer_fn(unsigned long data)
+{
+ struct pblk *pblk = (struct pblk *)data;
+
+ /* kick the write thread every tick to flush outstanding data */
+ pblk_write_kick(pblk);
+}
+
+void pblk_write_should_kick(struct pblk *pblk)
+{
+ unsigned int secs_avail = pblk_rb_read_count(&pblk->rwb);
+
+ if (secs_avail >= pblk->min_write_pgs)
+ pblk_write_kick(pblk);
+}
+
+void pblk_end_bio_sync(struct bio *bio)
+{
+ struct completion *waiting = bio->bi_private;
+
+ complete(waiting);
+}
+
+void pblk_end_io_sync(struct nvm_rq *rqd)
+{
+ struct completion *waiting = rqd->private;
+
+ complete(waiting);
+}
+
+void pblk_flush_writer(struct pblk *pblk)
+{
+ struct bio *bio;
+ int ret;
+ DECLARE_COMPLETION_ONSTACK(wait);
+
+ bio = bio_alloc(GFP_KERNEL, 1);
+ if (!bio)
+ return;
+
+ bio->bi_iter.bi_sector = 0; /* internal bio */
+ bio_set_op_attrs(bio, REQ_OP_WRITE, REQ_OP_FLUSH);
+ bio->bi_private = &wait;
+ bio->bi_end_io = pblk_end_bio_sync;
+
+ ret = pblk_write_to_cache(pblk, bio, 0);
+ if (ret == NVM_IO_OK) {
+ if (!wait_for_completion_io_timeout(&wait,
+ msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+ pr_err("pblk: flush cache timed out\n");
+ }
+ } else if (ret != NVM_IO_DONE) {
+ pr_err("pblk: tear down bio failed\n");
+ }
+
+ if (bio->bi_error)
+ pr_err("pblk: flush sync write failed (%u)\n", bio->bi_error);
+
+ bio_put(bio);
+}
+
+struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line)
+{
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct list_head *move_list = NULL;
+
+ if (!line->vsc) {
+ if (line->gc_group != PBLK_LINEGC_FULL) {
+ line->gc_group = PBLK_LINEGC_FULL;
+ move_list = &l_mg->gc_full_list;
+ }
+ } else if (line->vsc < lm->mid_thrs) {
+ if (line->gc_group != PBLK_LINEGC_HIGH) {
+ line->gc_group = PBLK_LINEGC_HIGH;
+ move_list = &l_mg->gc_high_list;
+ }
+ } else if (line->vsc < lm->high_thrs) {
+ if (line->gc_group != PBLK_LINEGC_MID) {
+ line->gc_group = PBLK_LINEGC_MID;
+ move_list = &l_mg->gc_mid_list;
+ }
+ } else if (line->vsc < line->sec_in_line) {
+ if (line->gc_group != PBLK_LINEGC_LOW) {
+ line->gc_group = PBLK_LINEGC_LOW;
+ move_list = &l_mg->gc_low_list;
+ }
+ } else if (line->vsc == line->sec_in_line) {
+ if (line->gc_group != PBLK_LINEGC_EMPTY) {
+ line->gc_group = PBLK_LINEGC_EMPTY;
+ move_list = &l_mg->gc_empty_list;
+ }
+ } else {
+ line->state = PBLK_LINESTATE_CORRUPT;
+ line->gc_group = PBLK_LINEGC_NONE;
+ move_list = &l_mg->corrupt_list;
+ pr_err("pblk: corrupted vsc for line %d, vsc:%d (%d/%d/%d)\n",
+ line->id, line->vsc,
+ line->sec_in_line,
+ lm->high_thrs, lm->mid_thrs);
+ }
+
+ return move_list;
+}
+
+void pblk_discard(struct pblk *pblk, struct bio *bio)
+{
+ sector_t slba = pblk_get_lba(bio);
+ sector_t nr_secs = pblk_get_secs(bio);
+
+ pblk_invalidate_range(pblk, slba, nr_secs);
+}
+
+struct ppa_addr pblk_get_lba_map(struct pblk *pblk, sector_t lba)
+{
+ struct ppa_addr ppa;
+
+ spin_lock(&pblk->trans_lock);
+ ppa = pblk_trans_map_get(pblk, lba);
+ spin_unlock(&pblk->trans_lock);
+
+ return ppa;
+}
+
+void pblk_log_write_err(struct pblk *pblk, struct nvm_rq *rqd)
+{
+ atomic_long_inc(&pblk->write_failed);
+#ifdef CONFIG_NVM_DEBUG
+ pblk_print_failed_rqd(pblk, rqd, rqd->error);
+#endif
+}
+
+void pblk_log_read_err(struct pblk *pblk, struct nvm_rq *rqd)
+{
+ /* Empty page read is not necessarily an error (e.g., L2P recovery) */
+ if (rqd->error == NVM_RSP_ERR_EMPTYPAGE) {
+ atomic_long_inc(&pblk->read_empty);
+ return;
+ }
+
+ switch (rqd->error) {
+ case NVM_RSP_WARN_HIGHECC:
+ atomic_long_inc(&pblk->read_high_ecc);
+ break;
+ case NVM_RSP_ERR_FAILECC:
+ case NVM_RSP_ERR_FAILCRC:
+ atomic_long_inc(&pblk->read_failed);
+ break;
+ default:
+ pr_err("pblk: unknown read error:%d\n", rqd->error);
+ }
+#ifdef CONFIG_NVM_DEBUG
+ pblk_print_failed_rqd(pblk, rqd, rqd->error);
+#endif
+}
+
+int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+
+#ifdef CONFIG_NVM_DEBUG
+ struct ppa_addr *ppa_list;
+
+ ppa_list = (rqd->nr_ppas > 1) ? rqd->ppa_list : &rqd->ppa_addr;
+ if (pblk_boundary_ppa_checks(dev, ppa_list, rqd->nr_ppas)) {
+ WARN_ON(1);
+ return -EINVAL;
+ }
+
+ if (rqd->opcode == NVM_OP_PWRITE) {
+ struct pblk_line *line;
+ struct ppa_addr ppa;
+ int i;
+
+ for (i = 0; i < rqd->nr_ppas; i++) {
+ ppa = ppa_list[i];
+ line = &pblk->lines[pblk_dev_ppa_to_line(ppa)];
+
+ spin_lock(&line->lock);
+ if (line->state != PBLK_LINESTATE_OPEN) {
+ pr_err("pblk: bad ppa: line:%d,state:%d\n",
+ line->id, line->state);
+ WARN_ON(1);
+ spin_unlock(&line->lock);
+ return -EINVAL;
+ }
+ spin_unlock(&line->lock);
+ }
+ }
+#endif
+ return nvm_submit_io(dev, rqd);
+}
+
+struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data,
+ unsigned int nr_secs, unsigned int len,
+ gfp_t gfp_mask)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ void *kaddr = data;
+ struct page *page;
+ struct bio *bio;
+ int i, ret;
+
+ if (l_mg->emeta_alloc_type == PBLK_KMALLOC_META)
+ return bio_map_kern(dev->q, kaddr, len, gfp_mask);
+
+ bio = bio_kmalloc(gfp_mask, nr_secs);
+ if (!bio)
+ return ERR_PTR(-ENOMEM);
+
+ for (i = 0; i < nr_secs; i++) {
+ page = vmalloc_to_page(kaddr);
+ if (!page) {
+ pr_err("pblk: could not map vmalloc bio\n");
+ bio_put(bio);
+ bio = ERR_PTR(-ENOMEM);
+ goto out;
+ }
+
+ ret = bio_add_pc_page(dev->q, bio, page, PAGE_SIZE, 0);
+ if (ret != PAGE_SIZE) {
+ pr_err("pblk: could not add page to bio\n");
+ bio_put(bio);
+ bio = ERR_PTR(-ENOMEM);
+ goto out;
+ }
+
+ kaddr += PAGE_SIZE;
+ }
+out:
+ return bio;
+}
+
+int pblk_calc_secs(struct pblk *pblk, unsigned long secs_avail,
+ unsigned long secs_to_flush)
+{
+ int max = pblk->max_write_pgs;
+ int min = pblk->min_write_pgs;
+ int secs_to_sync = 0;
+
+ if (secs_avail >= max)
+ secs_to_sync = max;
+ else if (secs_avail >= min)
+ secs_to_sync = min * (secs_avail / min);
+ else if (secs_to_flush)
+ secs_to_sync = min;
+
+ return secs_to_sync;
+}
+
+static u64 __pblk_alloc_page(struct pblk *pblk, struct pblk_line *line,
+ int nr_secs)
+{
+ u64 addr;
+ int i;
+
+ /* logic error: ppa out-of-bounds. Prevent generating bad address */
+ if (line->cur_sec + nr_secs > pblk->lm.sec_per_line) {
+ WARN(1, "pblk: page allocation out of bounds\n");
+ nr_secs = pblk->lm.sec_per_line - line->cur_sec;
+ }
+
+ line->cur_sec = addr = find_next_zero_bit(line->map_bitmap,
+ pblk->lm.sec_per_line, line->cur_sec);
+ for (i = 0; i < nr_secs; i++, line->cur_sec++)
+ WARN_ON(test_and_set_bit(line->cur_sec, line->map_bitmap));
+
+ return addr;
+}
+
+u64 pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs)
+{
+ u64 addr;
+
+ /* Lock needed in case a write fails and a recovery needs to remap
+ * failed write buffer entries
+ */
+ spin_lock(&line->lock);
+ addr = __pblk_alloc_page(pblk, line, nr_secs);
+ line->left_msecs -= nr_secs;
+ WARN(line->left_msecs < 0, "pblk: page allocation out of bounds\n");
+ spin_unlock(&line->lock);
+
+ return addr;
+}
+
+/*
+ * Submit emeta to one LUN in the raid line at the time to avoid a deadlock when
+ * taking the per LUN semaphore.
+ */
+static int pblk_line_submit_emeta_io(struct pblk *pblk, struct pblk_line *line,
+ u64 paddr, int dir)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct bio *bio;
+ struct nvm_rq rqd;
+ struct ppa_addr *ppa_list;
+ dma_addr_t dma_ppa_list;
+ void *emeta = line->emeta;
+ int min = pblk->min_write_pgs;
+ int left_ppas = lm->emeta_sec;
+ int id = line->id;
+ int rq_ppas, rq_len;
+ int cmd_op, bio_op;
+ int flags;
+ int i, j;
+ int ret;
+ DECLARE_COMPLETION_ONSTACK(wait);
+
+ if (dir == WRITE) {
+ bio_op = REQ_OP_WRITE;
+ cmd_op = NVM_OP_PWRITE;
+ flags = pblk_set_progr_mode(pblk, WRITE);
+ } else if (dir == READ) {
+ bio_op = REQ_OP_READ;
+ cmd_op = NVM_OP_PREAD;
+ flags = pblk_set_read_mode(pblk);
+ } else
+ return -EINVAL;
+
+ ppa_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, &dma_ppa_list);
+ if (!ppa_list)
+ return -ENOMEM;
+
+next_rq:
+ memset(&rqd, 0, sizeof(struct nvm_rq));
+
+ rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
+ rq_len = rq_ppas * geo->sec_size;
+
+ bio = pblk_bio_map_addr(pblk, emeta, rq_ppas, rq_len, GFP_KERNEL);
+ if (IS_ERR(bio)) {
+ ret = PTR_ERR(bio);
+ goto free_rqd_dma;
+ }
+
+ bio->bi_iter.bi_sector = 0; /* internal bio */
+ bio_set_op_attrs(bio, bio_op, 0);
+
+ rqd.bio = bio;
+ rqd.opcode = cmd_op;
+ rqd.flags = flags;
+ rqd.nr_ppas = rq_ppas;
+ rqd.ppa_list = ppa_list;
+ rqd.dma_ppa_list = dma_ppa_list;
+ rqd.end_io = pblk_end_io_sync;
+ rqd.private = &wait;
+
+ if (dir == WRITE) {
+ for (i = 0; i < rqd.nr_ppas; ) {
+ spin_lock(&line->lock);
+ paddr = __pblk_alloc_page(pblk, line, min);
+ spin_unlock(&line->lock);
+ for (j = 0; j < min; j++, i++, paddr++)
+ rqd.ppa_list[i] =
+ addr_to_gen_ppa(pblk, paddr, id);
+ }
+ } else {
+ for (i = 0; i < rqd.nr_ppas; ) {
+ struct ppa_addr ppa = addr_to_gen_ppa(pblk, paddr, id);
+ int pos = pblk_dev_ppa_to_pos(geo, ppa);
+
+ while (test_bit(pos, line->blk_bitmap)) {
+ paddr += min;
+ if (pblk_boundary_paddr_checks(pblk, paddr)) {
+ pr_err("pblk: corrupt emeta line:%d\n",
+ line->id);
+ bio_put(bio);
+ ret = -EINTR;
+ goto free_rqd_dma;
+ }
+
+ ppa = addr_to_gen_ppa(pblk, paddr, id);
+ pos = pblk_dev_ppa_to_pos(geo, ppa);
+ }
+
+ if (pblk_boundary_paddr_checks(pblk, paddr + min)) {
+ pr_err("pblk: corrupt emeta line:%d\n",
+ line->id);
+ bio_put(bio);
+ ret = -EINTR;
+ goto free_rqd_dma;
+ }
+
+ for (j = 0; j < min; j++, i++, paddr++)
+ rqd.ppa_list[i] =
+ addr_to_gen_ppa(pblk, paddr, line->id);
+ }
+ }
+
+ ret = pblk_submit_io(pblk, &rqd);
+ if (ret) {
+ pr_err("pblk: emeta I/O submission failed: %d\n", ret);
+ bio_put(bio);
+ goto free_rqd_dma;
+ }
+
+ if (!wait_for_completion_io_timeout(&wait,
+ msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+ pr_err("pblk: emeta I/O timed out\n");
+ }
+ reinit_completion(&wait);
+
+ bio_put(bio);
+
+ if (rqd.error) {
+ if (dir == WRITE)
+ pblk_log_write_err(pblk, &rqd);
+ else
+ pblk_log_read_err(pblk, &rqd);
+ }
+
+ emeta += rq_len;
+ left_ppas -= rq_ppas;
+ if (left_ppas)
+ goto next_rq;
+free_rqd_dma:
+ nvm_dev_dma_free(dev->parent, ppa_list, dma_ppa_list);
+ return ret;
+}
+
+u64 pblk_line_smeta_start(struct pblk *pblk, struct pblk_line *line)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_line_meta *lm = &pblk->lm;
+ int bit;
+
+ /* This usually only happens on bad lines */
+ bit = find_first_zero_bit(line->blk_bitmap, lm->blk_per_line);
+ if (bit >= lm->blk_per_line)
+ return -1;
+
+ return bit * geo->sec_per_pl;
+}
+
+static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line,
+ u64 paddr, int dir)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct bio *bio;
+ struct nvm_rq rqd;
+ __le64 *lba_list = NULL;
+ int i, ret;
+ int cmd_op, bio_op;
+ int flags;
+ DECLARE_COMPLETION_ONSTACK(wait);
+
+ if (dir == WRITE) {
+ bio_op = REQ_OP_WRITE;
+ cmd_op = NVM_OP_PWRITE;
+ flags = pblk_set_progr_mode(pblk, WRITE);
+ lba_list = pblk_line_emeta_to_lbas(line->emeta);
+ } else if (dir == READ) {
+ bio_op = REQ_OP_READ;
+ cmd_op = NVM_OP_PREAD;
+ flags = pblk_set_read_mode(pblk);
+ } else
+ return -EINVAL;
+
+ memset(&rqd, 0, sizeof(struct nvm_rq));
+
+ rqd.ppa_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL,
+ &rqd.dma_ppa_list);
+ if (!rqd.ppa_list)
+ return -ENOMEM;
+
+ bio = bio_map_kern(dev->q, line->smeta, lm->smeta_len, GFP_KERNEL);
+ if (IS_ERR(bio)) {
+ ret = PTR_ERR(bio);
+ goto free_ppa_list;
+ }
+
+ bio->bi_iter.bi_sector = 0; /* internal bio */
+ bio_set_op_attrs(bio, bio_op, 0);
+
+ rqd.bio = bio;
+ rqd.opcode = cmd_op;
+ rqd.flags = flags;
+ rqd.nr_ppas = lm->smeta_sec;
+ rqd.end_io = pblk_end_io_sync;
+ rqd.private = &wait;
+
+ for (i = 0; i < lm->smeta_sec; i++, paddr++) {
+ rqd.ppa_list[i] = addr_to_gen_ppa(pblk, paddr, line->id);
+ if (dir == WRITE)
+ lba_list[paddr] = cpu_to_le64(ADDR_EMPTY);
+ }
+
+ /*
+ * This I/O is sent by the write thread when a line is replace. Since
+ * the write thread is the only one sending write and erase commands,
+ * there is no need to take the LUN semaphore.
+ */
+ ret = pblk_submit_io(pblk, &rqd);
+ if (ret) {
+ pr_err("pblk: smeta I/O submission failed: %d\n", ret);
+ bio_put(bio);
+ goto free_ppa_list;
+ }
+
+ if (!wait_for_completion_io_timeout(&wait,
+ msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+ pr_err("pblk: smeta I/O timed out\n");
+ }
+
+ if (rqd.error) {
+ if (dir == WRITE)
+ pblk_log_write_err(pblk, &rqd);
+ else
+ pblk_log_read_err(pblk, &rqd);
+ }
+
+free_ppa_list:
+ nvm_dev_dma_free(dev->parent, rqd.ppa_list, rqd.dma_ppa_list);
+
+ return ret;
+}
+
+int pblk_line_read_smeta(struct pblk *pblk, struct pblk_line *line)
+{
+ u64 bpaddr = pblk_line_smeta_start(pblk, line);
+
+ return pblk_line_submit_smeta_io(pblk, line, bpaddr, READ);
+}
+
+int pblk_line_read_emeta(struct pblk *pblk, struct pblk_line *line)
+{
+ return pblk_line_submit_emeta_io(pblk, line, line->emeta_ssec, READ);
+}
+
+static void pblk_setup_e_rq(struct pblk *pblk, struct nvm_rq *rqd,
+ struct ppa_addr ppa)
+{
+ rqd->opcode = NVM_OP_ERASE;
+ rqd->ppa_addr = ppa;
+ rqd->nr_ppas = 1;
+ rqd->flags = pblk_set_progr_mode(pblk, ERASE);
+ rqd->bio = NULL;
+}
+
+static int pblk_blk_erase_sync(struct pblk *pblk, struct ppa_addr ppa)
+{
+ struct nvm_rq rqd;
+ int ret;
+ DECLARE_COMPLETION_ONSTACK(wait);
+
+ memset(&rqd, 0, sizeof(struct nvm_rq));
+
+ pblk_setup_e_rq(pblk, &rqd, ppa);
+
+ rqd.end_io = pblk_end_io_sync;
+ rqd.private = &wait;
+
+ /* The write thread schedules erases so that it minimizes disturbances
+ * with writes. Thus, there is no need to take the LUN semaphore.
+ */
+ ret = pblk_submit_io(pblk, &rqd);
+ if (ret) {
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+
+ pr_err("pblk: could not sync erase line:%d,blk:%d\n",
+ pblk_dev_ppa_to_line(ppa),
+ pblk_dev_ppa_to_pos(geo, ppa));
+
+ rqd.error = ret;
+ goto out;
+ }
+
+ if (!wait_for_completion_io_timeout(&wait,
+ msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+ pr_err("pblk: sync erase timed out\n");
+ }
+
+out:
+ rqd.private = pblk;
+ __pblk_end_io_erase(pblk, &rqd);
+
+ return 0;
+}
+
+int pblk_line_erase(struct pblk *pblk, struct pblk_line *line)
+{
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct ppa_addr ppa;
+ int bit = -1;
+
+ /* Erase only good blocks, one at a time */
+ do {
+ spin_lock(&line->lock);
+ bit = find_next_zero_bit(line->erase_bitmap, lm->blk_per_line,
+ bit + 1);
+ if (bit >= lm->blk_per_line) {
+ spin_unlock(&line->lock);
+ break;
+ }
+
+ ppa = pblk->luns[bit].bppa; /* set ch and lun */
+ ppa.g.blk = line->id;
+
+ atomic_dec(&line->left_eblks);
+ WARN_ON(test_and_set_bit(bit, line->erase_bitmap));
+ spin_unlock(&line->lock);
+
+ if (pblk_blk_erase_sync(pblk, ppa)) {
+ pr_err("pblk: failed to erase line %d\n", line->id);
+ return -ENOMEM;
+ }
+ } while (1);
+
+ return 0;
+}
+
+/* For now lines are always assumed full lines. Thus, smeta former and current
+ * lun bitmaps are omitted.
+ */
+static int pblk_line_set_metadata(struct pblk *pblk, struct pblk_line *line,
+ struct pblk_line *cur)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct line_smeta *smeta = line->smeta;
+ struct line_emeta *emeta = line->emeta;
+ int nr_blk_line;
+
+ /* After erasing the line, new bad blocks might appear and we risk
+ * having an invalid line
+ */
+ nr_blk_line = lm->blk_per_line -
+ bitmap_weight(line->blk_bitmap, lm->blk_per_line);
+ if (nr_blk_line < lm->min_blk_line) {
+ spin_lock(&l_mg->free_lock);
+ spin_lock(&line->lock);
+ line->state = PBLK_LINESTATE_BAD;
+ spin_unlock(&line->lock);
+
+ list_add_tail(&line->list, &l_mg->bad_list);
+ spin_unlock(&l_mg->free_lock);
+
+ pr_debug("pblk: line %d is bad\n", line->id);
+
+ return 0;
+ }
+
+ /* Run-time metadata */
+ line->lun_bitmap = ((void *)(smeta)) + sizeof(struct line_smeta);
+
+ /* Mark LUNs allocated in this line (all for now) */
+ bitmap_set(line->lun_bitmap, 0, lm->lun_bitmap_len);
+
+ smeta->header.identifier = cpu_to_le32(PBLK_MAGIC);
+ memcpy(smeta->header.uuid, pblk->instance_uuid, 16);
+ smeta->header.id = cpu_to_le32(line->id);
+ smeta->header.type = cpu_to_le16(line->type);
+ smeta->header.version = cpu_to_le16(1);
+
+ /* Start metadata */
+ smeta->seq_nr = cpu_to_le64(line->seq_nr);
+ smeta->window_wr_lun = cpu_to_le32(geo->nr_luns);
+
+ /* Fill metadata among lines */
+ if (cur) {
+ memcpy(line->lun_bitmap, cur->lun_bitmap, lm->lun_bitmap_len);
+ smeta->prev_id = cpu_to_le32(cur->id);
+ cur->emeta->next_id = cpu_to_le32(line->id);
+ } else {
+ smeta->prev_id = cpu_to_le32(PBLK_LINE_EMPTY);
+ }
+
+ /* All smeta must be set at this point */
+ smeta->header.crc = cpu_to_le32(pblk_calc_meta_header_crc(pblk, smeta));
+ smeta->crc = cpu_to_le32(pblk_calc_smeta_crc(pblk, smeta));
+
+ /* End metadata */
+ memcpy(&emeta->header, &smeta->header, sizeof(struct line_header));
+ emeta->seq_nr = cpu_to_le64(line->seq_nr);
+ emeta->nr_lbas = cpu_to_le64(line->sec_in_line);
+ emeta->nr_valid_lbas = cpu_to_le64(0);
+ emeta->next_id = cpu_to_le32(PBLK_LINE_EMPTY);
+ emeta->crc = cpu_to_le32(0);
+ emeta->prev_id = smeta->prev_id;
+
+ return 1;
+}
+
+/* For now lines are always assumed full lines. Thus, smeta former and current
+ * lun bitmaps are omitted.
+ */
+static int pblk_line_init_bb(struct pblk *pblk, struct pblk_line *line,
+ int init)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ int nr_bb = 0;
+ u64 off;
+ int bit = -1;
+
+ line->sec_in_line = lm->sec_per_line;
+
+ /* Capture bad block information on line mapping bitmaps */
+ while ((bit = find_next_bit(line->blk_bitmap, lm->blk_per_line,
+ bit + 1)) < lm->blk_per_line) {
+ off = bit * geo->sec_per_pl;
+ bitmap_shift_left(l_mg->bb_aux, l_mg->bb_template, off,
+ lm->sec_per_line);
+ bitmap_or(line->map_bitmap, line->map_bitmap, l_mg->bb_aux,
+ lm->sec_per_line);
+ line->sec_in_line -= geo->sec_per_blk;
+ if (bit >= lm->emeta_bb)
+ nr_bb++;
+ }
+
+ /* Mark smeta metadata sectors as bad sectors */
+ bit = find_first_zero_bit(line->blk_bitmap, lm->blk_per_line);
+ off = bit * geo->sec_per_pl;
+retry_smeta:
+ bitmap_set(line->map_bitmap, off, lm->smeta_sec);
+ line->sec_in_line -= lm->smeta_sec;
+ line->smeta_ssec = off;
+ line->cur_sec = off + lm->smeta_sec;
+
+ if (init && pblk_line_submit_smeta_io(pblk, line, off, WRITE)) {
+ pr_debug("pblk: line smeta I/O failed. Retry\n");
+ off += geo->sec_per_pl;
+ goto retry_smeta;
+ }
+
+ bitmap_copy(line->invalid_bitmap, line->map_bitmap, lm->sec_per_line);
+
+ /* Mark emeta metadata sectors as bad sectors. We need to consider bad
+ * blocks to make sure that there are enough sectors to store emeta
+ */
+ bit = lm->sec_per_line;
+ off = lm->sec_per_line - lm->emeta_sec;
+ bitmap_set(line->invalid_bitmap, off, lm->emeta_sec);
+ while (nr_bb) {
+ off -= geo->sec_per_pl;
+ if (!test_bit(off, line->invalid_bitmap)) {
+ bitmap_set(line->invalid_bitmap, off, geo->sec_per_pl);
+ nr_bb--;
+ }
+ }
+
+ line->sec_in_line -= lm->emeta_sec;
+ line->emeta_ssec = off;
+ line->vsc = line->left_ssecs = line->left_msecs = line->sec_in_line;
+
+ if (lm->sec_per_line - line->sec_in_line !=
+ bitmap_weight(line->invalid_bitmap, lm->sec_per_line)) {
+ spin_lock(&line->lock);
+ line->state = PBLK_LINESTATE_BAD;
+ spin_unlock(&line->lock);
+
+ list_add_tail(&line->list, &l_mg->bad_list);
+ pr_err("pblk: unexpected line %d is bad\n", line->id);
+
+ return 0;
+ }
+
+ return 1;
+}
+
+static int pblk_line_prepare(struct pblk *pblk, struct pblk_line *line)
+{
+ struct pblk_line_meta *lm = &pblk->lm;
+ int blk_in_line = atomic_read(&line->blk_in_line);
+
+ line->map_bitmap = mempool_alloc(pblk->line_meta_pool, GFP_ATOMIC);
+ if (!line->map_bitmap)
+ return -ENOMEM;
+ memset(line->map_bitmap, 0, lm->sec_bitmap_len);
+
+ /* invalid_bitmap is special since it is used when line is closed. No
+ * need to zeroized; it will be initialized using bb info form
+ * map_bitmap
+ */
+ line->invalid_bitmap = mempool_alloc(pblk->line_meta_pool, GFP_ATOMIC);
+ if (!line->invalid_bitmap) {
+ mempool_free(line->map_bitmap, pblk->line_meta_pool);
+ return -ENOMEM;
+ }
+
+ spin_lock(&line->lock);
+ if (line->state != PBLK_LINESTATE_FREE) {
+ spin_unlock(&line->lock);
+ WARN(1, "pblk: corrupted line state\n");
+ return -EINTR;
+ }
+ line->state = PBLK_LINESTATE_OPEN;
+
+ atomic_set(&line->left_eblks, blk_in_line);
+ atomic_set(&line->left_seblks, blk_in_line);
+ spin_unlock(&line->lock);
+
+ /* Bad blocks do not need to be erased */
+ bitmap_copy(line->erase_bitmap, line->blk_bitmap, lm->blk_per_line);
+
+ kref_init(&line->ref);
+
+ return 0;
+}
+
+int pblk_line_recov_alloc(struct pblk *pblk, struct pblk_line *line)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ int ret;
+
+ spin_lock(&l_mg->free_lock);
+ l_mg->data_line = line;
+ list_del(&line->list);
+
+ ret = pblk_line_prepare(pblk, line);
+ if (ret) {
+ list_add(&line->list, &l_mg->free_list);
+ spin_unlock(&l_mg->free_lock);
+ return ret;
+ }
+ spin_unlock(&l_mg->free_lock);
+
+ pblk_rl_free_lines_dec(&pblk->rl, line);
+
+ if (!pblk_line_init_bb(pblk, line, 0)) {
+ list_add(&line->list, &l_mg->free_list);
+ return -EINTR;
+ }
+
+ return 0;
+}
+
+void pblk_line_recov_close(struct pblk *pblk, struct pblk_line *line)
+{
+ mempool_free(line->map_bitmap, pblk->line_meta_pool);
+ line->map_bitmap = NULL;
+ line->smeta = NULL;
+ line->emeta = NULL;
+}
+
+struct pblk_line *pblk_line_get(struct pblk *pblk)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_line *line = NULL;
+ int bit;
+
+ lockdep_assert_held(&l_mg->free_lock);
+
+retry_get:
+ if (list_empty(&l_mg->free_list)) {
+ pr_err("pblk: no free lines\n");
+ goto out;
+ }
+
+ line = list_first_entry(&l_mg->free_list, struct pblk_line, list);
+ list_del(&line->list);
+ l_mg->nr_free_lines--;
+
+ bit = find_first_zero_bit(line->blk_bitmap, lm->blk_per_line);
+ if (unlikely(bit >= lm->blk_per_line)) {
+ spin_lock(&line->lock);
+ line->state = PBLK_LINESTATE_BAD;
+ spin_unlock(&line->lock);
+
+ list_add_tail(&line->list, &l_mg->bad_list);
+
+ pr_debug("pblk: line %d is bad\n", line->id);
+ goto retry_get;
+ }
+
+ if (pblk_line_prepare(pblk, line)) {
+ pr_err("pblk: failed to prepare line %d\n", line->id);
+ list_add(&line->list, &l_mg->free_list);
+ return NULL;
+ }
+
+out:
+ return line;
+}
+
+static struct pblk_line *pblk_line_retry(struct pblk *pblk,
+ struct pblk_line *line)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct pblk_line *retry_line;
+
+ spin_lock(&l_mg->free_lock);
+ retry_line = pblk_line_get(pblk);
+ if (!retry_line) {
+ l_mg->data_line = NULL;
+ spin_unlock(&l_mg->free_lock);
+ return NULL;
+ }
+
+ retry_line->smeta = line->smeta;
+ retry_line->emeta = line->emeta;
+ retry_line->meta_line = line->meta_line;
+
+ pblk_line_free(pblk, line);
+ l_mg->data_line = retry_line;
+ spin_unlock(&l_mg->free_lock);
+
+ if (pblk_line_erase(pblk, retry_line)) {
+ spin_lock(&l_mg->free_lock);
+ l_mg->data_line = NULL;
+ spin_unlock(&l_mg->free_lock);
+ return NULL;
+ }
+
+ pblk_rl_free_lines_dec(&pblk->rl, retry_line);
+
+ return retry_line;
+}
+
+struct pblk_line *pblk_line_get_first_data(struct pblk *pblk)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct pblk_line *line;
+ int meta_line;
+ int is_next = 0;
+
+ spin_lock(&l_mg->free_lock);
+ line = pblk_line_get(pblk);
+ if (!line) {
+ spin_unlock(&l_mg->free_lock);
+ return NULL;
+ }
+
+ line->seq_nr = l_mg->d_seq_nr++;
+ line->type = PBLK_LINETYPE_DATA;
+ l_mg->data_line = line;
+
+ meta_line = find_first_zero_bit(&l_mg->meta_bitmap, PBLK_DATA_LINES);
+ set_bit(meta_line, &l_mg->meta_bitmap);
+ line->smeta = l_mg->sline_meta[meta_line].meta;
+ line->emeta = l_mg->eline_meta[meta_line].meta;
+ line->meta_line = meta_line;
+
+ /* Allocate next line for preparation */
+ l_mg->data_next = pblk_line_get(pblk);
+ if (l_mg->data_next) {
+ l_mg->data_next->seq_nr = l_mg->d_seq_nr++;
+ l_mg->data_next->type = PBLK_LINETYPE_DATA;
+ is_next = 1;
+ }
+ spin_unlock(&l_mg->free_lock);
+
+ pblk_rl_free_lines_dec(&pblk->rl, line);
+ if (is_next)
+ pblk_rl_free_lines_dec(&pblk->rl, l_mg->data_next);
+
+ if (pblk_line_erase(pblk, line))
+ return NULL;
+
+retry_setup:
+ if (!pblk_line_set_metadata(pblk, line, NULL)) {
+ line = pblk_line_retry(pblk, line);
+ if (!line)
+ return NULL;
+
+ goto retry_setup;
+ }
+
+ if (!pblk_line_init_bb(pblk, line, 1)) {
+ line = pblk_line_retry(pblk, line);
+ if (!line)
+ return NULL;
+
+ goto retry_setup;
+ }
+
+ return line;
+}
+
+struct pblk_line *pblk_line_replace_data(struct pblk *pblk)
+{
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct pblk_line *cur, *new;
+ unsigned int left_seblks;
+ int meta_line;
+ int is_next = 0;
+
+ cur = l_mg->data_line;
+ new = l_mg->data_next;
+ if (!new)
+ return NULL;
+ l_mg->data_line = new;
+
+retry_line:
+ left_seblks = atomic_read(&new->left_seblks);
+ if (left_seblks) {
+ /* If line is not fully erased, erase it */
+ if (atomic_read(&new->left_eblks)) {
+ if (pblk_line_erase(pblk, new))
+ return NULL;
+ } else {
+ io_schedule();
+ }
+ goto retry_line;
+ }
+
+ spin_lock(&l_mg->free_lock);
+ /* Allocate next line for preparation */
+ l_mg->data_next = pblk_line_get(pblk);
+ if (l_mg->data_next) {
+ l_mg->data_next->seq_nr = l_mg->d_seq_nr++;
+ l_mg->data_next->type = PBLK_LINETYPE_DATA;
+ is_next = 1;
+ }
+
+retry_meta:
+ meta_line = find_first_zero_bit(&l_mg->meta_bitmap, PBLK_DATA_LINES);
+ if (meta_line == PBLK_DATA_LINES) {
+ spin_unlock(&l_mg->free_lock);
+ io_schedule();
+ spin_lock(&l_mg->free_lock);
+ goto retry_meta;
+ }
+
+ set_bit(meta_line, &l_mg->meta_bitmap);
+ new->smeta = l_mg->sline_meta[meta_line].meta;
+ new->emeta = l_mg->eline_meta[meta_line].meta;
+ new->meta_line = meta_line;
+
+ memset(new->smeta, 0, lm->smeta_len);
+ memset(new->emeta, 0, lm->emeta_len);
+ spin_unlock(&l_mg->free_lock);
+
+ if (is_next)
+ pblk_rl_free_lines_dec(&pblk->rl, l_mg->data_next);
+
+retry_setup:
+ if (!pblk_line_set_metadata(pblk, new, cur)) {
+ new = pblk_line_retry(pblk, new);
+ if (!new)
+ return NULL;
+
+ goto retry_setup;
+ }
+
+ if (!pblk_line_init_bb(pblk, new, 1)) {
+ new = pblk_line_retry(pblk, new);
+ if (!new)
+ return NULL;
+
+ goto retry_setup;
+ }
+
+ return new;
+}
+
+void pblk_line_free(struct pblk *pblk, struct pblk_line *line)
+{
+ if (line->map_bitmap)
+ mempool_free(line->map_bitmap, pblk->line_meta_pool);
+ if (line->invalid_bitmap)
+ mempool_free(line->invalid_bitmap, pblk->line_meta_pool);
+
+ line->map_bitmap = NULL;
+ line->invalid_bitmap = NULL;
+ line->smeta = NULL;
+ line->emeta = NULL;
+}
+
+void pblk_line_put(struct kref *ref)
+{
+ struct pblk_line *line = container_of(ref, struct pblk_line, ref);
+ struct pblk *pblk = line->pblk;
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+
+ spin_lock(&line->lock);
+ WARN_ON(line->state != PBLK_LINESTATE_GC);
+ line->state = PBLK_LINESTATE_FREE;
+ line->gc_group = PBLK_LINEGC_NONE;
+ pblk_line_free(pblk, line);
+ spin_unlock(&line->lock);
+
+ spin_lock(&l_mg->free_lock);
+ list_add_tail(&line->list, &l_mg->free_list);
+ l_mg->nr_free_lines++;
+ spin_unlock(&l_mg->free_lock);
+
+ pblk_rl_free_lines_inc(&pblk->rl, line);
+}
+
+int pblk_blk_erase_async(struct pblk *pblk, struct ppa_addr ppa)
+{
+ struct nvm_rq *rqd;
+ int err;
+
+ rqd = mempool_alloc(pblk->r_rq_pool, GFP_KERNEL);
+ memset(rqd, 0, pblk_r_rq_size);
+
+ pblk_setup_e_rq(pblk, rqd, ppa);
+
+ rqd->end_io = pblk_end_io_erase;
+ rqd->private = pblk;
+
+ /* The write thread schedules erases so that it minimizes disturbances
+ * with writes. Thus, there is no need to take the LUN semaphore.
+ */
+ err = pblk_submit_io(pblk, rqd);
+ if (err) {
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+
+ pr_err("pblk: could not async erase line:%d,blk:%d\n",
+ pblk_dev_ppa_to_line(ppa),
+ pblk_dev_ppa_to_pos(geo, ppa));
+ }
+
+ return err;
+}
+
+struct pblk_line *pblk_line_get_data(struct pblk *pblk)
+{
+ return pblk->l_mg.data_line;
+}
+
+struct pblk_line *pblk_line_get_data_next(struct pblk *pblk)
+{
+ return pblk->l_mg.data_next;
+}
+
+int pblk_line_is_full(struct pblk_line *line)
+{
+ return (line->left_msecs == 0);
+}
+
+void pblk_line_close(struct pblk *pblk, struct pblk_line *line)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct list_head *move_list;
+
+ line->emeta->crc = cpu_to_le32(pblk_calc_emeta_crc(pblk, line->emeta));
+
+ if (pblk_line_submit_emeta_io(pblk, line, line->cur_sec, WRITE))
+ pr_err("pblk: line %d close I/O failed\n", line->id);
+
+ WARN(!bitmap_full(line->map_bitmap, line->sec_in_line),
+ "pblk: corrupt closed line %d\n", line->id);
+
+ spin_lock(&l_mg->free_lock);
+ WARN_ON(!test_and_clear_bit(line->meta_line, &l_mg->meta_bitmap));
+ spin_unlock(&l_mg->free_lock);
+
+ spin_lock(&l_mg->gc_lock);
+ spin_lock(&line->lock);
+ WARN_ON(line->state != PBLK_LINESTATE_OPEN);
+ line->state = PBLK_LINESTATE_CLOSED;
+ move_list = pblk_line_gc_list(pblk, line);
+
+ list_add_tail(&line->list, move_list);
+
+ mempool_free(line->map_bitmap, pblk->line_meta_pool);
+ line->map_bitmap = NULL;
+ line->smeta = NULL;
+ line->emeta = NULL;
+
+ spin_unlock(&line->lock);
+ spin_unlock(&l_mg->gc_lock);
+}
+
+void pblk_line_close_ws(struct work_struct *work)
+{
+ struct pblk_line_ws *line_ws = container_of(work, struct pblk_line_ws,
+ ws);
+ struct pblk *pblk = line_ws->pblk;
+ struct pblk_line *line = line_ws->line;
+
+ pblk_line_close(pblk, line);
+ mempool_free(line_ws, pblk->line_ws_pool);
+}
+
+void pblk_line_mark_bb(struct work_struct *work)
+{
+ struct pblk_line_ws *line_ws = container_of(work, struct pblk_line_ws,
+ ws);
+ struct pblk *pblk = line_ws->pblk;
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct ppa_addr *ppa = line_ws->priv;
+ int ret;
+
+ ret = nvm_set_tgt_bb_tbl(dev, ppa, 1, NVM_BLK_T_GRWN_BAD);
+ if (ret) {
+ struct pblk_line *line;
+ int pos;
+
+ line = &pblk->lines[pblk_dev_ppa_to_line(*ppa)];
+ pos = pblk_dev_ppa_to_pos(&dev->geo, *ppa);
+
+ pr_err("pblk: failed to mark bb, line:%d, pos:%d\n",
+ line->id, pos);
+ }
+
+ kfree(ppa);
+ mempool_free(line_ws, pblk->line_ws_pool);
+}
+
+void pblk_line_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv,
+ void (*work)(struct work_struct *))
+{
+ struct pblk_line_ws *line_ws;
+
+ line_ws = mempool_alloc(pblk->line_ws_pool, GFP_ATOMIC);
+ if (!line_ws)
+ return;
+
+ line_ws->pblk = pblk;
+ line_ws->line = line;
+ line_ws->priv = priv;
+
+ INIT_WORK(&line_ws->ws, work);
+ queue_work(pblk->kw_wq, &line_ws->ws);
+}
+
+void pblk_down_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas,
+ unsigned long *lun_bitmap)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_lun *rlun;
+ int lun_id = ppa_list[0].g.ch * geo->luns_per_chnl + ppa_list[0].g.lun;
+ int ret;
+
+ /*
+ * Only send one inflight I/O per LUN. Since we map at a page
+ * granurality, all ppas in the I/O will map to the same LUN
+ */
+#ifdef CONFIG_NVM_DEBUG
+ int i;
+
+ for (i = 1; i < nr_ppas; i++)
+ WARN_ON(ppa_list[0].g.lun != ppa_list[i].g.lun ||
+ ppa_list[0].g.ch != ppa_list[i].g.ch);
+#endif
+ /* If the LUN has been locked for this same request, do no attempt to
+ * lock it again
+ */
+ if (test_and_set_bit(lun_id, lun_bitmap))
+ return;
+
+ rlun = &pblk->luns[lun_id];
+ ret = down_timeout(&rlun->wr_sem, msecs_to_jiffies(5000));
+ if (ret) {
+ switch (ret) {
+ case -ETIME:
+ pr_err("pblk: lun semaphore timed out\n");
+ break;
+ case -EINTR:
+ pr_err("pblk: lun semaphore timed out\n");
+ break;
+ }
+ }
+}
+
+void pblk_up_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas,
+ unsigned long *lun_bitmap)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_lun *rlun;
+ int nr_luns = geo->nr_luns;
+ int bit = -1;
+
+ while ((bit = find_next_bit(lun_bitmap, nr_luns, bit + 1)) < nr_luns) {
+ rlun = &pblk->luns[bit];
+ up(&rlun->wr_sem);
+ }
+
+ kfree(lun_bitmap);
+}
+
+void pblk_update_map(struct pblk *pblk, sector_t lba, struct ppa_addr ppa)
+{
+ struct ppa_addr l2p_ppa;
+
+ /* logic error: lba out-of-bounds. Ignore update */
+ if (!(lba < pblk->rl.nr_secs)) {
+ WARN(1, "pblk: corrupted L2P map request\n");
+ return;
+ }
+
+ spin_lock(&pblk->trans_lock);
+ l2p_ppa = pblk_trans_map_get(pblk, lba);
+
+ if (!pblk_addr_in_cache(l2p_ppa) && !pblk_ppa_empty(l2p_ppa))
+ pblk_map_invalidate(pblk, l2p_ppa);
+
+ pblk_trans_map_set(pblk, lba, ppa);
+ spin_unlock(&pblk->trans_lock);
+}
+
+void pblk_update_map_cache(struct pblk *pblk, sector_t lba, struct ppa_addr ppa)
+{
+#ifdef CONFIG_NVM_DEBUG
+ /* Callers must ensure that the ppa points to a cache address */
+ BUG_ON(!pblk_addr_in_cache(ppa));
+ BUG_ON(pblk_rb_pos_oob(&pblk->rwb, pblk_addr_to_cacheline(ppa)));
+#endif
+
+ pblk_update_map(pblk, lba, ppa);
+}
+
+int pblk_update_map_gc(struct pblk *pblk, sector_t lba, struct ppa_addr ppa,
+ struct pblk_line *gc_line)
+{
+ struct ppa_addr l2p_ppa;
+ int ret = 1;
+
+#ifdef CONFIG_NVM_DEBUG
+ /* Callers must ensure that the ppa points to a cache address */
+ BUG_ON(!pblk_addr_in_cache(ppa));
+ BUG_ON(pblk_rb_pos_oob(&pblk->rwb, pblk_addr_to_cacheline(ppa)));
+#endif
+
+ /* logic error: lba out-of-bounds. Ignore update */
+ if (!(lba < pblk->rl.nr_secs)) {
+ WARN(1, "pblk: corrupted L2P map request\n");
+ return 0;
+ }
+
+ spin_lock(&pblk->trans_lock);
+ l2p_ppa = pblk_trans_map_get(pblk, lba);
+
+ /* Prevent updated entries to be overwritten by GC */
+ if (pblk_addr_in_cache(l2p_ppa) || pblk_ppa_empty(l2p_ppa) ||
+ pblk_tgt_ppa_to_line(l2p_ppa) != gc_line->id) {
+ ret = 0;
+ goto out;
+ }
+
+ pblk_trans_map_set(pblk, lba, ppa);
+out:
+ spin_unlock(&pblk->trans_lock);
+ return ret;
+}
+
+void pblk_update_map_dev(struct pblk *pblk, sector_t lba, struct ppa_addr ppa,
+ struct ppa_addr entry_line)
+{
+ struct ppa_addr l2p_line;
+
+#ifdef CONFIG_NVM_DEBUG
+ /* Callers must ensure that the ppa points to a device address */
+ BUG_ON(pblk_addr_in_cache(ppa));
+#endif
+ /* Invalidate and discard padded entries */
+ if (lba == ADDR_EMPTY) {
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_inc(&pblk->padded_wb);
+#endif
+ pblk_map_invalidate(pblk, ppa);
+ return;
+ }
+
+ /* logic error: lba out-of-bounds. Ignore update */
+ if (!(lba < pblk->rl.nr_secs)) {
+ WARN(1, "pblk: corrupted L2P map request\n");
+ return;
+ }
+
+ spin_lock(&pblk->trans_lock);
+ l2p_line = pblk_trans_map_get(pblk, lba);
+
+ /* Do not update L2P if the cacheline has been updated. In this case,
+ * the mapped ppa must be invalidated
+ */
+ if (l2p_line.ppa != entry_line.ppa) {
+ if (!pblk_ppa_empty(ppa))
+ pblk_map_invalidate(pblk, ppa);
+ goto out;
+ }
+
+#ifdef CONFIG_NVM_DEBUG
+ WARN_ON(!pblk_addr_in_cache(l2p_line) && !pblk_ppa_empty(l2p_line));
+#endif
+
+ pblk_trans_map_set(pblk, lba, ppa);
+out:
+ spin_unlock(&pblk->trans_lock);
+}
+
+void pblk_lookup_l2p_seq(struct pblk *pblk, struct ppa_addr *ppas,
+ sector_t blba, int nr_secs)
+{
+ int i;
+
+ spin_lock(&pblk->trans_lock);
+ for (i = 0; i < nr_secs; i++)
+ ppas[i] = pblk_trans_map_get(pblk, blba + i);
+ spin_unlock(&pblk->trans_lock);
+}
+
+void pblk_lookup_l2p_rand(struct pblk *pblk, struct ppa_addr *ppas,
+ u64 *lba_list, int nr_secs)
+{
+ sector_t lba;
+ int i;
+
+ spin_lock(&pblk->trans_lock);
+ for (i = 0; i < nr_secs; i++) {
+ lba = lba_list[i];
+ if (lba == ADDR_EMPTY) {
+ ppas[i].ppa = ADDR_EMPTY;
+ } else {
+ /* logic error: lba out-of-bounds. Ignore update */
+ if (!(lba < pblk->rl.nr_secs)) {
+ WARN(1, "pblk: corrupted L2P map request\n");
+ continue;
+ }
+ ppas[i] = pblk_trans_map_get(pblk, lba);
+ }
+ }
+ spin_unlock(&pblk->trans_lock);
+}
--- /dev/null
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ * Matias Bjorling <matias@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * pblk-gc.c - pblk's garbage collector
+ */
+
+#include "pblk.h"
+#include <linux/delay.h>
+
+static void pblk_gc_free_gc_rq(struct pblk_gc_rq *gc_rq)
+{
+ kfree(gc_rq->data);
+ kfree(gc_rq->lba_list);
+ kfree(gc_rq);
+}
+
+static int pblk_gc_write(struct pblk *pblk)
+{
+ struct pblk_gc *gc = &pblk->gc;
+ struct pblk_gc_rq *gc_rq, *tgc_rq;
+ LIST_HEAD(w_list);
+
+ spin_lock(&gc->w_lock);
+ if (list_empty(&gc->w_list)) {
+ spin_unlock(&gc->w_lock);
+ return 1;
+ }
+
+ list_for_each_entry_safe(gc_rq, tgc_rq, &gc->w_list, list) {
+ list_move_tail(&gc_rq->list, &w_list);
+ gc->w_entries--;
+ }
+ spin_unlock(&gc->w_lock);
+
+ list_for_each_entry_safe(gc_rq, tgc_rq, &w_list, list) {
+ pblk_write_gc_to_cache(pblk, gc_rq->data, gc_rq->lba_list,
+ gc_rq->nr_secs, gc_rq->secs_to_gc,
+ gc_rq->line, PBLK_IOTYPE_GC);
+
+ kref_put(&gc_rq->line->ref, pblk_line_put);
+
+ list_del(&gc_rq->list);
+ pblk_gc_free_gc_rq(gc_rq);
+ }
+
+ return 0;
+}
+
+static void pblk_gc_writer_kick(struct pblk_gc *gc)
+{
+ wake_up_process(gc->gc_writer_ts);
+}
+
+/*
+ * Responsible for managing all memory related to a gc request. Also in case of
+ * failure
+ */
+static int pblk_gc_move_valid_secs(struct pblk *pblk, struct pblk_line *line,
+ u64 *lba_list, unsigned int nr_secs)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_gc *gc = &pblk->gc;
+ struct pblk_gc_rq *gc_rq;
+ void *data;
+ unsigned int secs_to_gc;
+ int ret = NVM_IO_OK;
+
+ data = kmalloc(nr_secs * geo->sec_size, GFP_KERNEL);
+ if (!data) {
+ ret = NVM_IO_ERR;
+ goto free_lba_list;
+ }
+
+ /* Read from GC victim block */
+ if (pblk_submit_read_gc(pblk, lba_list, data, nr_secs,
+ &secs_to_gc, line)) {
+ ret = NVM_IO_ERR;
+ goto free_data;
+ }
+
+ if (!secs_to_gc)
+ goto free_data;
+
+ gc_rq = kmalloc(sizeof(struct pblk_gc_rq), GFP_KERNEL);
+ if (!gc_rq) {
+ ret = NVM_IO_ERR;
+ goto free_data;
+ }
+
+ gc_rq->line = line;
+ gc_rq->data = data;
+ gc_rq->lba_list = lba_list;
+ gc_rq->nr_secs = nr_secs;
+ gc_rq->secs_to_gc = secs_to_gc;
+
+ kref_get(&line->ref);
+
+retry:
+ spin_lock(&gc->w_lock);
+ if (gc->w_entries > 256) {
+ spin_unlock(&gc->w_lock);
+ usleep_range(256, 1024);
+ goto retry;
+ }
+ gc->w_entries++;
+ list_add_tail(&gc_rq->list, &gc->w_list);
+ spin_unlock(&gc->w_lock);
+
+ pblk_gc_writer_kick(&pblk->gc);
+
+ return NVM_IO_OK;
+
+free_data:
+ kfree(data);
+free_lba_list:
+ kfree(lba_list);
+
+ return ret;
+}
+
+static void pblk_put_line_back(struct pblk *pblk, struct pblk_line *line)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct list_head *move_list;
+
+ spin_lock(&line->lock);
+ WARN_ON(line->state != PBLK_LINESTATE_GC);
+ line->state = PBLK_LINESTATE_CLOSED;
+ move_list = pblk_line_gc_list(pblk, line);
+ spin_unlock(&line->lock);
+
+ if (move_list) {
+ spin_lock(&l_mg->gc_lock);
+ list_add_tail(&line->list, move_list);
+ spin_unlock(&l_mg->gc_lock);
+ }
+}
+
+static void pblk_gc_line_ws(struct work_struct *work)
+{
+ struct pblk_line_ws *line_ws = container_of(work, struct pblk_line_ws,
+ ws);
+ struct pblk *pblk = line_ws->pblk;
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct pblk_line *line = line_ws->line;
+ struct pblk_line_meta *lm = &pblk->lm;
+ __le64 *lba_list = line_ws->priv;
+ u64 *gc_list;
+ int sec_left;
+ int nr_ppas, bit;
+ int put_line = 1;
+
+ pr_debug("pblk: line '%d' being reclaimed for GC\n", line->id);
+
+ spin_lock(&line->lock);
+ sec_left = line->vsc;
+ if (!sec_left) {
+ /* Lines are erased before being used (l_mg->data_/log_next) */
+ spin_unlock(&line->lock);
+ goto out;
+ }
+ spin_unlock(&line->lock);
+
+ if (sec_left < 0) {
+ pr_err("pblk: corrupted GC line (%d)\n", line->id);
+ put_line = 0;
+ pblk_put_line_back(pblk, line);
+ goto out;
+ }
+
+ bit = -1;
+next_rq:
+ gc_list = kmalloc_array(pblk->max_write_pgs, sizeof(u64), GFP_KERNEL);
+ if (!gc_list) {
+ put_line = 0;
+ pblk_put_line_back(pblk, line);
+ goto out;
+ }
+
+ nr_ppas = 0;
+ do {
+ bit = find_next_zero_bit(line->invalid_bitmap, lm->sec_per_line,
+ bit + 1);
+ if (bit > line->emeta_ssec)
+ break;
+
+ gc_list[nr_ppas++] = le64_to_cpu(lba_list[bit]);
+ } while (nr_ppas < pblk->max_write_pgs);
+
+ if (unlikely(!nr_ppas)) {
+ kfree(gc_list);
+ goto out;
+ }
+
+ if (pblk_gc_move_valid_secs(pblk, line, gc_list, nr_ppas)) {
+ pr_err("pblk: could not GC all sectors: line:%d (%d/%d/%d)\n",
+ line->id, line->vsc,
+ nr_ppas, nr_ppas);
+ put_line = 0;
+ pblk_put_line_back(pblk, line);
+ goto out;
+ }
+
+ sec_left -= nr_ppas;
+ if (sec_left > 0)
+ goto next_rq;
+
+out:
+ pblk_mfree(line->emeta, l_mg->emeta_alloc_type);
+ mempool_free(line_ws, pblk->line_ws_pool);
+ atomic_dec(&pblk->gc.inflight_gc);
+ if (put_line)
+ kref_put(&line->ref, pblk_line_put);
+}
+
+static int pblk_gc_line(struct pblk *pblk, struct pblk_line *line)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_line_ws *line_ws;
+ __le64 *lba_list;
+ int ret;
+
+ line_ws = mempool_alloc(pblk->line_ws_pool, GFP_KERNEL);
+ line->emeta = pblk_malloc(lm->emeta_len, l_mg->emeta_alloc_type,
+ GFP_KERNEL);
+ if (!line->emeta) {
+ pr_err("pblk: cannot use GC emeta\n");
+ goto fail_free_ws;
+ }
+
+ ret = pblk_line_read_emeta(pblk, line);
+ if (ret) {
+ pr_err("pblk: line %d read emeta failed (%d)\n", line->id, ret);
+ goto fail_free_emeta;
+ }
+
+ /* If this read fails, it means that emeta is corrupted. For now, leave
+ * the line untouched. TODO: Implement a recovery routine that scans and
+ * moves all sectors on the line.
+ */
+ lba_list = pblk_recov_get_lba_list(pblk, line->emeta);
+ if (!lba_list) {
+ pr_err("pblk: could not interpret emeta (line %d)\n", line->id);
+ goto fail_free_emeta;
+ }
+
+ line_ws->pblk = pblk;
+ line_ws->line = line;
+ line_ws->priv = lba_list;
+
+ INIT_WORK(&line_ws->ws, pblk_gc_line_ws);
+ queue_work(pblk->gc.gc_reader_wq, &line_ws->ws);
+
+ return 0;
+
+fail_free_emeta:
+ pblk_mfree(line->emeta, l_mg->emeta_alloc_type);
+fail_free_ws:
+ mempool_free(line_ws, pblk->line_ws_pool);
+ pblk_put_line_back(pblk, line);
+
+ return 1;
+}
+
+static void pblk_gc_lines(struct pblk *pblk, struct list_head *gc_list)
+{
+ struct pblk_line *line, *tline;
+
+ list_for_each_entry_safe(line, tline, gc_list, list) {
+ if (pblk_gc_line(pblk, line))
+ pr_err("pblk: failed to GC line %d\n", line->id);
+ list_del(&line->list);
+ }
+}
+
+/*
+ * Lines with no valid sectors will be returned to the free list immediately. If
+ * GC is activated - either because the free block count is under the determined
+ * threshold, or because it is being forced from user space - only lines with a
+ * high count of invalid sectors will be recycled.
+ */
+static void pblk_gc_run(struct pblk *pblk)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct pblk_gc *gc = &pblk->gc;
+ struct pblk_line *line, *tline;
+ unsigned int nr_blocks_free, nr_blocks_need;
+ struct list_head *group_list;
+ int run_gc, gc_group = 0;
+ int prev_gc = 0;
+ int inflight_gc = atomic_read(&gc->inflight_gc);
+ LIST_HEAD(gc_list);
+
+ spin_lock(&l_mg->gc_lock);
+ list_for_each_entry_safe(line, tline, &l_mg->gc_full_list, list) {
+ spin_lock(&line->lock);
+ WARN_ON(line->state != PBLK_LINESTATE_CLOSED);
+ line->state = PBLK_LINESTATE_GC;
+ spin_unlock(&line->lock);
+
+ list_del(&line->list);
+ kref_put(&line->ref, pblk_line_put);
+ }
+ spin_unlock(&l_mg->gc_lock);
+
+ nr_blocks_need = pblk_rl_gc_thrs(&pblk->rl);
+ nr_blocks_free = pblk_rl_nr_free_blks(&pblk->rl);
+ run_gc = (nr_blocks_need > nr_blocks_free || gc->gc_forced);
+
+next_gc_group:
+ group_list = l_mg->gc_lists[gc_group++];
+ spin_lock(&l_mg->gc_lock);
+ while (run_gc && !list_empty(group_list)) {
+ /* No need to queue up more GC lines than we can handle */
+ if (!run_gc || inflight_gc > gc->gc_jobs_active) {
+ spin_unlock(&l_mg->gc_lock);
+ pblk_gc_lines(pblk, &gc_list);
+ return;
+ }
+
+ line = list_first_entry(group_list, struct pblk_line, list);
+ nr_blocks_free += atomic_read(&line->blk_in_line);
+
+ spin_lock(&line->lock);
+ WARN_ON(line->state != PBLK_LINESTATE_CLOSED);
+ line->state = PBLK_LINESTATE_GC;
+ list_move_tail(&line->list, &gc_list);
+ atomic_inc(&gc->inflight_gc);
+ inflight_gc++;
+ spin_unlock(&line->lock);
+
+ prev_gc = 1;
+ run_gc = (nr_blocks_need > nr_blocks_free || gc->gc_forced);
+ }
+ spin_unlock(&l_mg->gc_lock);
+
+ pblk_gc_lines(pblk, &gc_list);
+
+ if (!prev_gc && pblk->rl.rb_state > gc_group &&
+ gc_group < PBLK_NR_GC_LISTS)
+ goto next_gc_group;
+}
+
+
+static void pblk_gc_kick(struct pblk *pblk)
+{
+ struct pblk_gc *gc = &pblk->gc;
+
+ wake_up_process(gc->gc_ts);
+ pblk_gc_writer_kick(gc);
+ mod_timer(&gc->gc_timer, jiffies + msecs_to_jiffies(GC_TIME_MSECS));
+}
+
+static void pblk_gc_timer(unsigned long data)
+{
+ struct pblk *pblk = (struct pblk *)data;
+
+ pblk_gc_kick(pblk);
+}
+
+static int pblk_gc_ts(void *data)
+{
+ struct pblk *pblk = data;
+
+ while (!kthread_should_stop()) {
+ pblk_gc_run(pblk);
+ set_current_state(TASK_INTERRUPTIBLE);
+ io_schedule();
+ }
+
+ return 0;
+}
+
+static int pblk_gc_writer_ts(void *data)
+{
+ struct pblk *pblk = data;
+
+ while (!kthread_should_stop()) {
+ if (!pblk_gc_write(pblk))
+ continue;
+ set_current_state(TASK_INTERRUPTIBLE);
+ io_schedule();
+ }
+
+ return 0;
+}
+
+static void pblk_gc_start(struct pblk *pblk)
+{
+ pblk->gc.gc_active = 1;
+
+ pr_debug("pblk: gc start\n");
+}
+
+int pblk_gc_status(struct pblk *pblk)
+{
+ struct pblk_gc *gc = &pblk->gc;
+ int ret;
+
+ spin_lock(&gc->lock);
+ ret = gc->gc_active;
+ spin_unlock(&gc->lock);
+
+ return ret;
+}
+
+static void __pblk_gc_should_start(struct pblk *pblk)
+{
+ struct pblk_gc *gc = &pblk->gc;
+
+ lockdep_assert_held(&gc->lock);
+
+ if (gc->gc_enabled && !gc->gc_active)
+ pblk_gc_start(pblk);
+}
+
+void pblk_gc_should_start(struct pblk *pblk)
+{
+ struct pblk_gc *gc = &pblk->gc;
+
+ spin_lock(&gc->lock);
+ __pblk_gc_should_start(pblk);
+ spin_unlock(&gc->lock);
+}
+
+/*
+ * If flush_wq == 1 then no lock should be held by the caller since
+ * flush_workqueue can sleep
+ */
+static void pblk_gc_stop(struct pblk *pblk, int flush_wq)
+{
+ spin_lock(&pblk->gc.lock);
+ pblk->gc.gc_active = 0;
+ spin_unlock(&pblk->gc.lock);
+
+ pr_debug("pblk: gc stop\n");
+}
+
+void pblk_gc_should_stop(struct pblk *pblk)
+{
+ struct pblk_gc *gc = &pblk->gc;
+
+ if (gc->gc_active && !gc->gc_forced)
+ pblk_gc_stop(pblk, 0);
+}
+
+void pblk_gc_sysfs_state_show(struct pblk *pblk, int *gc_enabled,
+ int *gc_active)
+{
+ struct pblk_gc *gc = &pblk->gc;
+
+ spin_lock(&gc->lock);
+ *gc_enabled = gc->gc_enabled;
+ *gc_active = gc->gc_active;
+ spin_unlock(&gc->lock);
+}
+
+void pblk_gc_sysfs_force(struct pblk *pblk, int force)
+{
+ struct pblk_gc *gc = &pblk->gc;
+ int rsv = 0;
+
+ spin_lock(&gc->lock);
+ if (force) {
+ gc->gc_enabled = 1;
+ rsv = 64;
+ }
+ pblk_rl_set_gc_rsc(&pblk->rl, rsv);
+ gc->gc_forced = force;
+ __pblk_gc_should_start(pblk);
+ spin_unlock(&gc->lock);
+}
+
+int pblk_gc_init(struct pblk *pblk)
+{
+ struct pblk_gc *gc = &pblk->gc;
+ int ret;
+
+ gc->gc_ts = kthread_create(pblk_gc_ts, pblk, "pblk-gc-ts");
+ if (IS_ERR(gc->gc_ts)) {
+ pr_err("pblk: could not allocate GC main kthread\n");
+ return PTR_ERR(gc->gc_ts);
+ }
+
+ gc->gc_writer_ts = kthread_create(pblk_gc_writer_ts, pblk,
+ "pblk-gc-writer-ts");
+ if (IS_ERR(gc->gc_writer_ts)) {
+ pr_err("pblk: could not allocate GC writer kthread\n");
+ ret = PTR_ERR(gc->gc_writer_ts);
+ goto fail_free_main_kthread;
+ }
+
+ setup_timer(&gc->gc_timer, pblk_gc_timer, (unsigned long)pblk);
+ mod_timer(&gc->gc_timer, jiffies + msecs_to_jiffies(GC_TIME_MSECS));
+
+ gc->gc_active = 0;
+ gc->gc_forced = 0;
+ gc->gc_enabled = 1;
+ gc->gc_jobs_active = 8;
+ gc->w_entries = 0;
+ atomic_set(&gc->inflight_gc, 0);
+
+ gc->gc_reader_wq = alloc_workqueue("pblk-gc-reader-wq",
+ WQ_MEM_RECLAIM | WQ_UNBOUND, gc->gc_jobs_active);
+ if (!gc->gc_reader_wq) {
+ pr_err("pblk: could not allocate GC reader workqueue\n");
+ ret = -ENOMEM;
+ goto fail_free_writer_kthread;
+ }
+
+ spin_lock_init(&gc->lock);
+ spin_lock_init(&gc->w_lock);
+ INIT_LIST_HEAD(&gc->w_list);
+
+ return 0;
+
+fail_free_writer_kthread:
+ kthread_stop(gc->gc_writer_ts);
+fail_free_main_kthread:
+ kthread_stop(gc->gc_ts);
+
+ return ret;
+}
+
+void pblk_gc_exit(struct pblk *pblk)
+{
+ struct pblk_gc *gc = &pblk->gc;
+
+ flush_workqueue(gc->gc_reader_wq);
+
+ del_timer(&gc->gc_timer);
+ pblk_gc_stop(pblk, 1);
+
+ if (gc->gc_ts)
+ kthread_stop(gc->gc_ts);
+
+ if (pblk->gc.gc_reader_wq)
+ destroy_workqueue(pblk->gc.gc_reader_wq);
+
+ if (gc->gc_writer_ts)
+ kthread_stop(gc->gc_writer_ts);
+}
--- /dev/null
+/*
+ * Copyright (C) 2015 IT University of Copenhagen (rrpc.c)
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ * Matias Bjorling <matias@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * Implementation of a physical block-device target for Open-channel SSDs.
+ *
+ * pblk-init.c - pblk's initialization.
+ */
+
+#include "pblk.h"
+
+static struct kmem_cache *pblk_blk_ws_cache, *pblk_rec_cache, *pblk_r_rq_cache,
+ *pblk_w_rq_cache, *pblk_line_meta_cache;
+static DECLARE_RWSEM(pblk_lock);
+
+static int pblk_rw_io(struct request_queue *q, struct pblk *pblk,
+ struct bio *bio)
+{
+ int ret;
+
+ /* Read requests must be <= 256kb due to NVMe's 64 bit completion bitmap
+ * constraint. Writes can be of arbitrary size.
+ */
+ if (bio_data_dir(bio) == READ) {
+ blk_queue_split(q, &bio, q->bio_split);
+ ret = pblk_submit_read(pblk, bio);
+ if (ret == NVM_IO_DONE && bio_flagged(bio, BIO_CLONED))
+ bio_put(bio);
+
+ return ret;
+ }
+
+ /* Prevent deadlock in the case of a modest LUN configuration and large
+ * user I/Os. Unless stalled, the rate limiter leaves at least 256KB
+ * available for user I/O.
+ */
+ if (unlikely(pblk_get_secs(bio) >= pblk_rl_sysfs_rate_show(&pblk->rl)))
+ blk_queue_split(q, &bio, q->bio_split);
+
+ return pblk_write_to_cache(pblk, bio, PBLK_IOTYPE_USER);
+}
+
+static blk_qc_t pblk_make_rq(struct request_queue *q, struct bio *bio)
+{
+ struct pblk *pblk = q->queuedata;
+
+ if (bio_op(bio) == REQ_OP_DISCARD) {
+ pblk_discard(pblk, bio);
+ if (!(bio->bi_opf & REQ_PREFLUSH)) {
+ bio_endio(bio);
+ return BLK_QC_T_NONE;
+ }
+ }
+
+ switch (pblk_rw_io(q, pblk, bio)) {
+ case NVM_IO_ERR:
+ bio_io_error(bio);
+ break;
+ case NVM_IO_DONE:
+ bio_endio(bio);
+ break;
+ }
+
+ return BLK_QC_T_NONE;
+}
+
+static void pblk_l2p_free(struct pblk *pblk)
+{
+ vfree(pblk->trans_map);
+}
+
+static int pblk_l2p_init(struct pblk *pblk)
+{
+ sector_t i;
+ struct ppa_addr ppa;
+ int entry_size = 8;
+
+ if (pblk->ppaf_bitsize < 32)
+ entry_size = 4;
+
+ pblk->trans_map = vmalloc(entry_size * pblk->rl.nr_secs);
+ if (!pblk->trans_map)
+ return -ENOMEM;
+
+ pblk_ppa_set_empty(&ppa);
+
+ for (i = 0; i < pblk->rl.nr_secs; i++)
+ pblk_trans_map_set(pblk, i, ppa);
+
+ return 0;
+}
+
+static void pblk_rwb_free(struct pblk *pblk)
+{
+ if (pblk_rb_tear_down_check(&pblk->rwb))
+ pr_err("pblk: write buffer error on tear down\n");
+
+ pblk_rb_data_free(&pblk->rwb);
+ vfree(pblk_rb_entries_ref(&pblk->rwb));
+}
+
+static int pblk_rwb_init(struct pblk *pblk)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_rb_entry *entries;
+ unsigned long nr_entries;
+ unsigned int power_size, power_seg_sz;
+
+ nr_entries = pblk_rb_calculate_size(pblk->pgs_in_buffer);
+
+ entries = vzalloc(nr_entries * sizeof(struct pblk_rb_entry));
+ if (!entries)
+ return -ENOMEM;
+
+ power_size = get_count_order(nr_entries);
+ power_seg_sz = get_count_order(geo->sec_size);
+
+ return pblk_rb_init(&pblk->rwb, entries, power_size, power_seg_sz);
+}
+
+/* Minimum pages needed within a lun */
+#define PAGE_POOL_SIZE 16
+#define ADDR_POOL_SIZE 64
+
+static int pblk_set_ppaf(struct pblk *pblk)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct nvm_addr_format ppaf = geo->ppaf;
+ int power_len;
+
+ /* Re-calculate channel and lun format to adapt to configuration */
+ power_len = get_count_order(geo->nr_chnls);
+ if (1 << power_len != geo->nr_chnls) {
+ pr_err("pblk: supports only power-of-two channel config.\n");
+ return -EINVAL;
+ }
+ ppaf.ch_len = power_len;
+
+ power_len = get_count_order(geo->luns_per_chnl);
+ if (1 << power_len != geo->luns_per_chnl) {
+ pr_err("pblk: supports only power-of-two LUN config.\n");
+ return -EINVAL;
+ }
+ ppaf.lun_len = power_len;
+
+ pblk->ppaf.sec_offset = 0;
+ pblk->ppaf.pln_offset = ppaf.sect_len;
+ pblk->ppaf.ch_offset = pblk->ppaf.pln_offset + ppaf.pln_len;
+ pblk->ppaf.lun_offset = pblk->ppaf.ch_offset + ppaf.ch_len;
+ pblk->ppaf.pg_offset = pblk->ppaf.lun_offset + ppaf.lun_len;
+ pblk->ppaf.blk_offset = pblk->ppaf.pg_offset + ppaf.pg_len;
+ pblk->ppaf.sec_mask = (1ULL << ppaf.sect_len) - 1;
+ pblk->ppaf.pln_mask = ((1ULL << ppaf.pln_len) - 1) <<
+ pblk->ppaf.pln_offset;
+ pblk->ppaf.ch_mask = ((1ULL << ppaf.ch_len) - 1) <<
+ pblk->ppaf.ch_offset;
+ pblk->ppaf.lun_mask = ((1ULL << ppaf.lun_len) - 1) <<
+ pblk->ppaf.lun_offset;
+ pblk->ppaf.pg_mask = ((1ULL << ppaf.pg_len) - 1) <<
+ pblk->ppaf.pg_offset;
+ pblk->ppaf.blk_mask = ((1ULL << ppaf.blk_len) - 1) <<
+ pblk->ppaf.blk_offset;
+
+ pblk->ppaf_bitsize = pblk->ppaf.blk_offset + ppaf.blk_len;
+
+ return 0;
+}
+
+static int pblk_init_global_caches(struct pblk *pblk)
+{
+ char cache_name[PBLK_CACHE_NAME_LEN];
+
+ down_write(&pblk_lock);
+ pblk_blk_ws_cache = kmem_cache_create("pblk_blk_ws",
+ sizeof(struct pblk_line_ws), 0, 0, NULL);
+ if (!pblk_blk_ws_cache) {
+ up_write(&pblk_lock);
+ return -ENOMEM;
+ }
+
+ pblk_rec_cache = kmem_cache_create("pblk_rec",
+ sizeof(struct pblk_rec_ctx), 0, 0, NULL);
+ if (!pblk_rec_cache) {
+ kmem_cache_destroy(pblk_blk_ws_cache);
+ up_write(&pblk_lock);
+ return -ENOMEM;
+ }
+
+ pblk_r_rq_cache = kmem_cache_create("pblk_r_rq", pblk_r_rq_size,
+ 0, 0, NULL);
+ if (!pblk_r_rq_cache) {
+ kmem_cache_destroy(pblk_blk_ws_cache);
+ kmem_cache_destroy(pblk_rec_cache);
+ up_write(&pblk_lock);
+ return -ENOMEM;
+ }
+
+ pblk_w_rq_cache = kmem_cache_create("pblk_w_rq", pblk_w_rq_size,
+ 0, 0, NULL);
+ if (!pblk_w_rq_cache) {
+ kmem_cache_destroy(pblk_blk_ws_cache);
+ kmem_cache_destroy(pblk_rec_cache);
+ kmem_cache_destroy(pblk_r_rq_cache);
+ up_write(&pblk_lock);
+ return -ENOMEM;
+ }
+
+ snprintf(cache_name, sizeof(cache_name), "pblk_line_m_%s",
+ pblk->disk->disk_name);
+ pblk_line_meta_cache = kmem_cache_create(cache_name,
+ pblk->lm.sec_bitmap_len, 0, 0, NULL);
+ if (!pblk_line_meta_cache) {
+ kmem_cache_destroy(pblk_blk_ws_cache);
+ kmem_cache_destroy(pblk_rec_cache);
+ kmem_cache_destroy(pblk_r_rq_cache);
+ kmem_cache_destroy(pblk_w_rq_cache);
+ up_write(&pblk_lock);
+ return -ENOMEM;
+ }
+ up_write(&pblk_lock);
+
+ return 0;
+}
+
+static int pblk_core_init(struct pblk *pblk)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ int max_write_ppas;
+ int mod;
+
+ pblk->min_write_pgs = geo->sec_per_pl * (geo->sec_size / PAGE_SIZE);
+ max_write_ppas = pblk->min_write_pgs * geo->nr_luns;
+ pblk->max_write_pgs = (max_write_ppas < nvm_max_phys_sects(dev)) ?
+ max_write_ppas : nvm_max_phys_sects(dev);
+ pblk->pgs_in_buffer = NVM_MEM_PAGE_WRITE * geo->sec_per_pg *
+ geo->nr_planes * geo->nr_luns;
+
+ if (pblk->max_write_pgs > PBLK_MAX_REQ_ADDRS) {
+ pr_err("pblk: cannot support device max_phys_sect\n");
+ return -EINVAL;
+ }
+
+ div_u64_rem(geo->sec_per_blk, pblk->min_write_pgs, &mod);
+ if (mod) {
+ pr_err("pblk: bad configuration of sectors/pages\n");
+ return -EINVAL;
+ }
+
+ if (pblk_init_global_caches(pblk))
+ return -ENOMEM;
+
+ pblk->page_pool = mempool_create_page_pool(PAGE_POOL_SIZE, 0);
+ if (!pblk->page_pool)
+ return -ENOMEM;
+
+ pblk->line_ws_pool = mempool_create_slab_pool(geo->nr_luns,
+ pblk_blk_ws_cache);
+ if (!pblk->line_ws_pool)
+ goto free_page_pool;
+
+ pblk->rec_pool = mempool_create_slab_pool(geo->nr_luns, pblk_rec_cache);
+ if (!pblk->rec_pool)
+ goto free_blk_ws_pool;
+
+ pblk->r_rq_pool = mempool_create_slab_pool(64, pblk_r_rq_cache);
+ if (!pblk->r_rq_pool)
+ goto free_rec_pool;
+
+ pblk->w_rq_pool = mempool_create_slab_pool(64, pblk_w_rq_cache);
+ if (!pblk->w_rq_pool)
+ goto free_r_rq_pool;
+
+ pblk->line_meta_pool =
+ mempool_create_slab_pool(16, pblk_line_meta_cache);
+ if (!pblk->line_meta_pool)
+ goto free_w_rq_pool;
+
+ pblk->kw_wq = alloc_workqueue("pblk-aux-wq",
+ WQ_MEM_RECLAIM | WQ_UNBOUND, 1);
+ if (!pblk->kw_wq)
+ goto free_line_meta_pool;
+
+ if (pblk_set_ppaf(pblk))
+ goto free_kw_wq;
+
+ if (pblk_rwb_init(pblk))
+ goto free_kw_wq;
+
+ INIT_LIST_HEAD(&pblk->compl_list);
+ return 0;
+
+free_kw_wq:
+ destroy_workqueue(pblk->kw_wq);
+free_line_meta_pool:
+ mempool_destroy(pblk->line_meta_pool);
+free_w_rq_pool:
+ mempool_destroy(pblk->w_rq_pool);
+free_r_rq_pool:
+ mempool_destroy(pblk->r_rq_pool);
+free_rec_pool:
+ mempool_destroy(pblk->rec_pool);
+free_blk_ws_pool:
+ mempool_destroy(pblk->line_ws_pool);
+free_page_pool:
+ mempool_destroy(pblk->page_pool);
+ return -ENOMEM;
+}
+
+static void pblk_core_free(struct pblk *pblk)
+{
+ if (pblk->kw_wq)
+ destroy_workqueue(pblk->kw_wq);
+
+ mempool_destroy(pblk->page_pool);
+ mempool_destroy(pblk->line_ws_pool);
+ mempool_destroy(pblk->rec_pool);
+ mempool_destroy(pblk->r_rq_pool);
+ mempool_destroy(pblk->w_rq_pool);
+ mempool_destroy(pblk->line_meta_pool);
+
+ kmem_cache_destroy(pblk_blk_ws_cache);
+ kmem_cache_destroy(pblk_rec_cache);
+ kmem_cache_destroy(pblk_r_rq_cache);
+ kmem_cache_destroy(pblk_w_rq_cache);
+ kmem_cache_destroy(pblk_line_meta_cache);
+}
+
+static void pblk_luns_free(struct pblk *pblk)
+{
+ kfree(pblk->luns);
+}
+
+static void pblk_lines_free(struct pblk *pblk)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct pblk_line *line;
+ int i;
+
+ spin_lock(&l_mg->free_lock);
+ for (i = 0; i < l_mg->nr_lines; i++) {
+ line = &pblk->lines[i];
+
+ pblk_line_free(pblk, line);
+ kfree(line->blk_bitmap);
+ kfree(line->erase_bitmap);
+ }
+ spin_unlock(&l_mg->free_lock);
+}
+
+static void pblk_line_meta_free(struct pblk *pblk)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ int i;
+
+ kfree(l_mg->bb_template);
+ kfree(l_mg->bb_aux);
+
+ for (i = 0; i < PBLK_DATA_LINES; i++) {
+ pblk_mfree(l_mg->sline_meta[i].meta, l_mg->smeta_alloc_type);
+ pblk_mfree(l_mg->eline_meta[i].meta, l_mg->emeta_alloc_type);
+ }
+
+ kfree(pblk->lines);
+}
+
+static int pblk_bb_discovery(struct nvm_tgt_dev *dev, struct pblk_lun *rlun)
+{
+ struct nvm_geo *geo = &dev->geo;
+ struct ppa_addr ppa;
+ u8 *blks;
+ int nr_blks, ret;
+
+ nr_blks = geo->blks_per_lun * geo->plane_mode;
+ blks = kmalloc(nr_blks, GFP_KERNEL);
+ if (!blks)
+ return -ENOMEM;
+
+ ppa.ppa = 0;
+ ppa.g.ch = rlun->bppa.g.ch;
+ ppa.g.lun = rlun->bppa.g.lun;
+
+ ret = nvm_get_tgt_bb_tbl(dev, ppa, blks);
+ if (ret)
+ goto out;
+
+ nr_blks = nvm_bb_tbl_fold(dev->parent, blks, nr_blks);
+ if (nr_blks < 0) {
+ ret = nr_blks;
+ goto out;
+ }
+
+ rlun->bb_list = blks;
+
+ return 0;
+out:
+ kfree(blks);
+ return ret;
+}
+
+static int pblk_bb_line(struct pblk *pblk, struct pblk_line *line)
+{
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_lun *rlun;
+ int bb_cnt = 0;
+ int i;
+
+ line->blk_bitmap = kzalloc(lm->blk_bitmap_len, GFP_KERNEL);
+ if (!line->blk_bitmap)
+ return -ENOMEM;
+
+ line->erase_bitmap = kzalloc(lm->blk_bitmap_len, GFP_KERNEL);
+ if (!line->erase_bitmap) {
+ kfree(line->blk_bitmap);
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < lm->blk_per_line; i++) {
+ rlun = &pblk->luns[i];
+ if (rlun->bb_list[line->id] == NVM_BLK_T_FREE)
+ continue;
+
+ set_bit(i, line->blk_bitmap);
+ bb_cnt++;
+ }
+
+ return bb_cnt;
+}
+
+static int pblk_luns_init(struct pblk *pblk, struct ppa_addr *luns)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_lun *rlun;
+ int i, ret;
+
+ /* TODO: Implement unbalanced LUN support */
+ if (geo->luns_per_chnl < 0) {
+ pr_err("pblk: unbalanced LUN config.\n");
+ return -EINVAL;
+ }
+
+ pblk->luns = kcalloc(geo->nr_luns, sizeof(struct pblk_lun), GFP_KERNEL);
+ if (!pblk->luns)
+ return -ENOMEM;
+
+ for (i = 0; i < geo->nr_luns; i++) {
+ /* Stripe across channels */
+ int ch = i % geo->nr_chnls;
+ int lun_raw = i / geo->nr_chnls;
+ int lunid = lun_raw + ch * geo->luns_per_chnl;
+
+ rlun = &pblk->luns[i];
+ rlun->bppa = luns[lunid];
+
+ sema_init(&rlun->wr_sem, 1);
+
+ ret = pblk_bb_discovery(dev, rlun);
+ if (ret) {
+ while (--i >= 0)
+ kfree(pblk->luns[i].bb_list);
+ return ret;
+ }
+ }
+
+ return 0;
+}
+
+static int pblk_lines_configure(struct pblk *pblk, int flags)
+{
+ struct pblk_line *line = NULL;
+ int ret = 0;
+
+ if (!(flags & NVM_TARGET_FACTORY)) {
+ line = pblk_recov_l2p(pblk);
+ if (IS_ERR(line)) {
+ pr_err("pblk: could not recover l2p table\n");
+ ret = -EFAULT;
+ }
+ }
+
+ if (!line) {
+ /* Configure next line for user data */
+ line = pblk_line_get_first_data(pblk);
+ if (!line) {
+ pr_err("pblk: line list corrupted\n");
+ ret = -EFAULT;
+ }
+ }
+
+ return ret;
+}
+
+/* See comment over struct line_emeta definition */
+static unsigned int calc_emeta_len(struct pblk *pblk, struct pblk_line_meta *lm)
+{
+ return (sizeof(struct line_emeta) +
+ ((lm->sec_per_line - lm->emeta_sec) * sizeof(u64)) +
+ (pblk->l_mg.nr_lines * sizeof(u32)) +
+ lm->blk_bitmap_len);
+}
+
+static void pblk_set_provision(struct pblk *pblk, long nr_free_blks)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ sector_t provisioned;
+
+ pblk->over_pct = 20;
+
+ provisioned = nr_free_blks;
+ provisioned *= (100 - pblk->over_pct);
+ sector_div(provisioned, 100);
+
+ /* Internally pblk manages all free blocks, but all calculations based
+ * on user capacity consider only provisioned blocks
+ */
+ pblk->rl.total_blocks = nr_free_blks;
+ pblk->rl.nr_secs = nr_free_blks * geo->sec_per_blk;
+ pblk->capacity = provisioned * geo->sec_per_blk;
+ atomic_set(&pblk->rl.free_blocks, nr_free_blks);
+}
+
+static int pblk_lines_init(struct pblk *pblk)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_line *line;
+ unsigned int smeta_len, emeta_len;
+ long nr_bad_blks, nr_meta_blks, nr_free_blks;
+ int bb_distance;
+ int i;
+ int ret;
+
+ lm->sec_per_line = geo->sec_per_blk * geo->nr_luns;
+ lm->blk_per_line = geo->nr_luns;
+ lm->blk_bitmap_len = BITS_TO_LONGS(geo->nr_luns) * sizeof(long);
+ lm->sec_bitmap_len = BITS_TO_LONGS(lm->sec_per_line) * sizeof(long);
+ lm->lun_bitmap_len = BITS_TO_LONGS(geo->nr_luns) * sizeof(long);
+ lm->high_thrs = lm->sec_per_line / 2;
+ lm->mid_thrs = lm->sec_per_line / 4;
+
+ /* Calculate necessary pages for smeta. See comment over struct
+ * line_smeta definition
+ */
+ lm->smeta_len = sizeof(struct line_smeta) +
+ PBLK_LINE_NR_LUN_BITMAP * lm->lun_bitmap_len;
+
+ i = 1;
+add_smeta_page:
+ lm->smeta_sec = i * geo->sec_per_pl;
+ lm->smeta_len = lm->smeta_sec * geo->sec_size;
+
+ smeta_len = sizeof(struct line_smeta) +
+ PBLK_LINE_NR_LUN_BITMAP * lm->lun_bitmap_len;
+ if (smeta_len > lm->smeta_len) {
+ i++;
+ goto add_smeta_page;
+ }
+
+ /* Calculate necessary pages for emeta. See comment over struct
+ * line_emeta definition
+ */
+ i = 1;
+add_emeta_page:
+ lm->emeta_sec = i * geo->sec_per_pl;
+ lm->emeta_len = lm->emeta_sec * geo->sec_size;
+
+ emeta_len = calc_emeta_len(pblk, lm);
+ if (emeta_len > lm->emeta_len) {
+ i++;
+ goto add_emeta_page;
+ }
+ lm->emeta_bb = geo->nr_luns - i;
+
+ nr_meta_blks = (lm->smeta_sec + lm->emeta_sec +
+ (geo->sec_per_blk / 2)) / geo->sec_per_blk;
+ lm->min_blk_line = nr_meta_blks + 1;
+
+ l_mg->nr_lines = geo->blks_per_lun;
+ l_mg->log_line = l_mg->data_line = NULL;
+ l_mg->l_seq_nr = l_mg->d_seq_nr = 0;
+ l_mg->nr_free_lines = 0;
+ bitmap_zero(&l_mg->meta_bitmap, PBLK_DATA_LINES);
+
+ /* smeta is always small enough to fit on a kmalloc memory allocation,
+ * emeta depends on the number of LUNs allocated to the pblk instance
+ */
+ l_mg->smeta_alloc_type = PBLK_KMALLOC_META;
+ for (i = 0; i < PBLK_DATA_LINES; i++) {
+ l_mg->sline_meta[i].meta = kmalloc(lm->smeta_len, GFP_KERNEL);
+ if (!l_mg->sline_meta[i].meta)
+ while (--i >= 0) {
+ kfree(l_mg->sline_meta[i].meta);
+ ret = -ENOMEM;
+ goto fail;
+ }
+ }
+
+ if (lm->emeta_len > KMALLOC_MAX_CACHE_SIZE) {
+ l_mg->emeta_alloc_type = PBLK_VMALLOC_META;
+
+ for (i = 0; i < PBLK_DATA_LINES; i++) {
+ l_mg->eline_meta[i].meta = vmalloc(lm->emeta_len);
+ if (!l_mg->eline_meta[i].meta)
+ while (--i >= 0) {
+ vfree(l_mg->eline_meta[i].meta);
+ ret = -ENOMEM;
+ goto fail;
+ }
+ }
+ } else {
+ l_mg->emeta_alloc_type = PBLK_KMALLOC_META;
+
+ for (i = 0; i < PBLK_DATA_LINES; i++) {
+ l_mg->eline_meta[i].meta =
+ kmalloc(lm->emeta_len, GFP_KERNEL);
+ if (!l_mg->eline_meta[i].meta)
+ while (--i >= 0) {
+ kfree(l_mg->eline_meta[i].meta);
+ ret = -ENOMEM;
+ goto fail;
+ }
+ }
+ }
+
+ l_mg->bb_template = kzalloc(lm->sec_bitmap_len, GFP_KERNEL);
+ if (!l_mg->bb_template) {
+ ret = -ENOMEM;
+ goto fail_free_meta;
+ }
+
+ l_mg->bb_aux = kzalloc(lm->sec_bitmap_len, GFP_KERNEL);
+ if (!l_mg->bb_aux) {
+ ret = -ENOMEM;
+ goto fail_free_bb_template;
+ }
+
+ bb_distance = (geo->nr_luns) * geo->sec_per_pl;
+ for (i = 0; i < lm->sec_per_line; i += bb_distance)
+ bitmap_set(l_mg->bb_template, i, geo->sec_per_pl);
+
+ INIT_LIST_HEAD(&l_mg->free_list);
+ INIT_LIST_HEAD(&l_mg->corrupt_list);
+ INIT_LIST_HEAD(&l_mg->bad_list);
+ INIT_LIST_HEAD(&l_mg->gc_full_list);
+ INIT_LIST_HEAD(&l_mg->gc_high_list);
+ INIT_LIST_HEAD(&l_mg->gc_mid_list);
+ INIT_LIST_HEAD(&l_mg->gc_low_list);
+ INIT_LIST_HEAD(&l_mg->gc_empty_list);
+
+ l_mg->gc_lists[0] = &l_mg->gc_high_list;
+ l_mg->gc_lists[1] = &l_mg->gc_mid_list;
+ l_mg->gc_lists[2] = &l_mg->gc_low_list;
+
+ spin_lock_init(&l_mg->free_lock);
+ spin_lock_init(&l_mg->gc_lock);
+
+ pblk->lines = kcalloc(l_mg->nr_lines, sizeof(struct pblk_line),
+ GFP_KERNEL);
+ if (!pblk->lines) {
+ ret = -ENOMEM;
+ goto fail_free_bb_aux;
+ }
+
+ nr_free_blks = 0;
+ for (i = 0; i < l_mg->nr_lines; i++) {
+ int blk_in_line;
+
+ line = &pblk->lines[i];
+
+ line->pblk = pblk;
+ line->id = i;
+ line->type = PBLK_LINETYPE_FREE;
+ line->state = PBLK_LINESTATE_FREE;
+ line->gc_group = PBLK_LINEGC_NONE;
+ spin_lock_init(&line->lock);
+
+ nr_bad_blks = pblk_bb_line(pblk, line);
+ if (nr_bad_blks < 0 || nr_bad_blks > lm->blk_per_line) {
+ ret = -EINVAL;
+ goto fail_free_lines;
+ }
+
+ blk_in_line = lm->blk_per_line - nr_bad_blks;
+ if (blk_in_line < lm->min_blk_line) {
+ line->state = PBLK_LINESTATE_BAD;
+ list_add_tail(&line->list, &l_mg->bad_list);
+ continue;
+ }
+
+ nr_free_blks += blk_in_line;
+ atomic_set(&line->blk_in_line, blk_in_line);
+
+ l_mg->nr_free_lines++;
+ list_add_tail(&line->list, &l_mg->free_list);
+ }
+
+ pblk_set_provision(pblk, nr_free_blks);
+
+ sema_init(&pblk->erase_sem, 1);
+
+ /* Cleanup per-LUN bad block lists - managed within lines on run-time */
+ for (i = 0; i < geo->nr_luns; i++)
+ kfree(pblk->luns[i].bb_list);
+
+ return 0;
+fail_free_lines:
+ kfree(pblk->lines);
+fail_free_bb_aux:
+ kfree(l_mg->bb_aux);
+fail_free_bb_template:
+ kfree(l_mg->bb_template);
+fail_free_meta:
+ for (i = 0; i < PBLK_DATA_LINES; i++) {
+ pblk_mfree(l_mg->sline_meta[i].meta, l_mg->smeta_alloc_type);
+ pblk_mfree(l_mg->eline_meta[i].meta, l_mg->emeta_alloc_type);
+ }
+fail:
+ for (i = 0; i < geo->nr_luns; i++)
+ kfree(pblk->luns[i].bb_list);
+
+ return ret;
+}
+
+static int pblk_writer_init(struct pblk *pblk)
+{
+ setup_timer(&pblk->wtimer, pblk_write_timer_fn, (unsigned long)pblk);
+ mod_timer(&pblk->wtimer, jiffies + msecs_to_jiffies(100));
+
+ pblk->writer_ts = kthread_create(pblk_write_ts, pblk, "pblk-writer-t");
+ if (IS_ERR(pblk->writer_ts)) {
+ pr_err("pblk: could not allocate writer kthread\n");
+ return PTR_ERR(pblk->writer_ts);
+ }
+
+ return 0;
+}
+
+static void pblk_writer_stop(struct pblk *pblk)
+{
+ if (pblk->writer_ts)
+ kthread_stop(pblk->writer_ts);
+ del_timer(&pblk->wtimer);
+}
+
+static void pblk_free(struct pblk *pblk)
+{
+ pblk_luns_free(pblk);
+ pblk_lines_free(pblk);
+ pblk_line_meta_free(pblk);
+ pblk_core_free(pblk);
+ pblk_l2p_free(pblk);
+
+ kfree(pblk);
+}
+
+static void pblk_tear_down(struct pblk *pblk)
+{
+ pblk_flush_writer(pblk);
+ pblk_writer_stop(pblk);
+ pblk_rb_sync_l2p(&pblk->rwb);
+ pblk_recov_pad(pblk);
+ pblk_rwb_free(pblk);
+ pblk_rl_free(&pblk->rl);
+
+ pr_debug("pblk: consistent tear down\n");
+}
+
+static void pblk_exit(void *private)
+{
+ struct pblk *pblk = private;
+
+ down_write(&pblk_lock);
+ pblk_gc_exit(pblk);
+ pblk_tear_down(pblk);
+ pblk_free(pblk);
+ up_write(&pblk_lock);
+}
+
+static sector_t pblk_capacity(void *private)
+{
+ struct pblk *pblk = private;
+
+ return pblk->capacity * NR_PHY_IN_LOG;
+}
+
+static void *pblk_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk,
+ int flags)
+{
+ struct nvm_geo *geo = &dev->geo;
+ struct request_queue *bqueue = dev->q;
+ struct request_queue *tqueue = tdisk->queue;
+ struct pblk *pblk;
+ int ret;
+
+ if (dev->identity.dom & NVM_RSP_L2P) {
+ pr_err("pblk: device-side L2P table not supported. (%x)\n",
+ dev->identity.dom);
+ return ERR_PTR(-EINVAL);
+ }
+
+ pblk = kzalloc(sizeof(struct pblk), GFP_KERNEL);
+ if (!pblk)
+ return ERR_PTR(-ENOMEM);
+
+ pblk->dev = dev;
+ pblk->disk = tdisk;
+
+ spin_lock_init(&pblk->trans_lock);
+ spin_lock_init(&pblk->lock);
+
+ if (flags & NVM_TARGET_FACTORY)
+ pblk_setup_uuid(pblk);
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_set(&pblk->inflight_writes, 0);
+ atomic_long_set(&pblk->padded_writes, 0);
+ atomic_long_set(&pblk->padded_wb, 0);
+ atomic_long_set(&pblk->nr_flush, 0);
+ atomic_long_set(&pblk->req_writes, 0);
+ atomic_long_set(&pblk->sub_writes, 0);
+ atomic_long_set(&pblk->sync_writes, 0);
+ atomic_long_set(&pblk->compl_writes, 0);
+ atomic_long_set(&pblk->inflight_reads, 0);
+ atomic_long_set(&pblk->sync_reads, 0);
+ atomic_long_set(&pblk->recov_writes, 0);
+ atomic_long_set(&pblk->recov_writes, 0);
+ atomic_long_set(&pblk->recov_gc_writes, 0);
+#endif
+
+ atomic_long_set(&pblk->read_failed, 0);
+ atomic_long_set(&pblk->read_empty, 0);
+ atomic_long_set(&pblk->read_high_ecc, 0);
+ atomic_long_set(&pblk->read_failed_gc, 0);
+ atomic_long_set(&pblk->write_failed, 0);
+ atomic_long_set(&pblk->erase_failed, 0);
+
+ ret = pblk_luns_init(pblk, dev->luns);
+ if (ret) {
+ pr_err("pblk: could not initialize luns\n");
+ goto fail;
+ }
+
+ ret = pblk_lines_init(pblk);
+ if (ret) {
+ pr_err("pblk: could not initialize lines\n");
+ goto fail_free_luns;
+ }
+
+ ret = pblk_core_init(pblk);
+ if (ret) {
+ pr_err("pblk: could not initialize core\n");
+ goto fail_free_line_meta;
+ }
+
+ ret = pblk_l2p_init(pblk);
+ if (ret) {
+ pr_err("pblk: could not initialize maps\n");
+ goto fail_free_core;
+ }
+
+ ret = pblk_lines_configure(pblk, flags);
+ if (ret) {
+ pr_err("pblk: could not configure lines\n");
+ goto fail_free_l2p;
+ }
+
+ ret = pblk_writer_init(pblk);
+ if (ret) {
+ pr_err("pblk: could not initialize write thread\n");
+ goto fail_free_lines;
+ }
+
+ ret = pblk_gc_init(pblk);
+ if (ret) {
+ pr_err("pblk: could not initialize gc\n");
+ goto fail_stop_writer;
+ }
+
+ /* inherit the size from the underlying device */
+ blk_queue_logical_block_size(tqueue, queue_physical_block_size(bqueue));
+ blk_queue_max_hw_sectors(tqueue, queue_max_hw_sectors(bqueue));
+
+ blk_queue_write_cache(tqueue, true, false);
+
+ tqueue->limits.discard_granularity = geo->pgs_per_blk * geo->pfpg_size;
+ tqueue->limits.discard_alignment = 0;
+ blk_queue_max_discard_sectors(tqueue, UINT_MAX >> 9);
+ queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, tqueue);
+
+ pr_info("pblk init: luns:%u, lines:%d, secs:%llu, buf entries:%u\n",
+ geo->nr_luns, pblk->l_mg.nr_lines,
+ (unsigned long long)pblk->rl.nr_secs,
+ pblk->rwb.nr_entries);
+
+ wake_up_process(pblk->writer_ts);
+ return pblk;
+
+fail_stop_writer:
+ pblk_writer_stop(pblk);
+fail_free_lines:
+ pblk_lines_free(pblk);
+fail_free_l2p:
+ pblk_l2p_free(pblk);
+fail_free_core:
+ pblk_core_free(pblk);
+fail_free_line_meta:
+ pblk_line_meta_free(pblk);
+fail_free_luns:
+ pblk_luns_free(pblk);
+fail:
+ kfree(pblk);
+ return ERR_PTR(ret);
+}
+
+/* physical block device target */
+static struct nvm_tgt_type tt_pblk = {
+ .name = "pblk",
+ .version = {1, 0, 0},
+
+ .make_rq = pblk_make_rq,
+ .capacity = pblk_capacity,
+
+ .init = pblk_init,
+ .exit = pblk_exit,
+
+ .sysfs_init = pblk_sysfs_init,
+ .sysfs_exit = pblk_sysfs_exit,
+};
+
+static int __init pblk_module_init(void)
+{
+ return nvm_register_tgt_type(&tt_pblk);
+}
+
+static void pblk_module_exit(void)
+{
+ nvm_unregister_tgt_type(&tt_pblk);
+}
+
+module_init(pblk_module_init);
+module_exit(pblk_module_exit);
+MODULE_AUTHOR("Javier Gonzalez <javier@cnexlabs.com>");
+MODULE_AUTHOR("Matias Bjorling <matias@cnexlabs.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Physical Block-Device for Open-Channel SSDs");
--- /dev/null
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ * Matias Bjorling <matias@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * pblk-map.c - pblk's lba-ppa mapping strategy
+ *
+ */
+
+#include "pblk.h"
+
+static void pblk_map_page_data(struct pblk *pblk, unsigned int sentry,
+ struct ppa_addr *ppa_list,
+ unsigned long *lun_bitmap,
+ struct pblk_sec_meta *meta_list,
+ unsigned int valid_secs)
+{
+ struct pblk_line *line = pblk_line_get_data(pblk);
+ struct line_emeta *emeta = line->emeta;
+ struct pblk_w_ctx *w_ctx;
+ __le64 *lba_list = pblk_line_emeta_to_lbas(emeta);
+ u64 paddr;
+ int nr_secs = pblk->min_write_pgs;
+ int i;
+
+ paddr = pblk_alloc_page(pblk, line, nr_secs);
+
+ for (i = 0; i < nr_secs; i++, paddr++) {
+ /* ppa to be sent to the device */
+ ppa_list[i] = addr_to_gen_ppa(pblk, paddr, line->id);
+
+ /* Write context for target bio completion on write buffer. Note
+ * that the write buffer is protected by the sync backpointer,
+ * and a single writer thread have access to each specific entry
+ * at a time. Thus, it is safe to modify the context for the
+ * entry we are setting up for submission without taking any
+ * lock or memory barrier.
+ */
+ if (i < valid_secs) {
+ kref_get(&line->ref);
+ w_ctx = pblk_rb_w_ctx(&pblk->rwb, sentry + i);
+ w_ctx->ppa = ppa_list[i];
+ meta_list[i].lba = cpu_to_le64(w_ctx->lba);
+ lba_list[paddr] = cpu_to_le64(w_ctx->lba);
+ le64_add_cpu(&line->emeta->nr_valid_lbas, 1);
+ } else {
+ meta_list[i].lba = cpu_to_le64(ADDR_EMPTY);
+ lba_list[paddr] = cpu_to_le64(ADDR_EMPTY);
+ pblk_map_pad_invalidate(pblk, line, paddr);
+ }
+ }
+
+ if (pblk_line_is_full(line)) {
+ line = pblk_line_replace_data(pblk);
+ if (!line)
+ return;
+ }
+
+ pblk_down_rq(pblk, ppa_list, nr_secs, lun_bitmap);
+}
+
+void pblk_map_rq(struct pblk *pblk, struct nvm_rq *rqd, unsigned int sentry,
+ unsigned long *lun_bitmap, unsigned int valid_secs,
+ unsigned int off)
+{
+ struct pblk_sec_meta *meta_list = rqd->meta_list;
+ unsigned int map_secs;
+ int min = pblk->min_write_pgs;
+ int i;
+
+ for (i = off; i < rqd->nr_ppas; i += min) {
+ map_secs = (i + min > valid_secs) ? (valid_secs % min) : min;
+ pblk_map_page_data(pblk, sentry + i, &rqd->ppa_list[i],
+ lun_bitmap, &meta_list[i], map_secs);
+ }
+}
+
+/* only if erase_ppa is set, acquire erase semaphore */
+void pblk_map_erase_rq(struct pblk *pblk, struct nvm_rq *rqd,
+ unsigned int sentry, unsigned long *lun_bitmap,
+ unsigned int valid_secs, struct ppa_addr *erase_ppa)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_line *e_line = pblk_line_get_data_next(pblk);
+ struct pblk_sec_meta *meta_list = rqd->meta_list;
+ unsigned int map_secs;
+ int min = pblk->min_write_pgs;
+ int i, erase_lun;
+
+ for (i = 0; i < rqd->nr_ppas; i += min) {
+ map_secs = (i + min > valid_secs) ? (valid_secs % min) : min;
+ pblk_map_page_data(pblk, sentry + i, &rqd->ppa_list[i],
+ lun_bitmap, &meta_list[i], map_secs);
+
+ erase_lun = rqd->ppa_list[i].g.lun * geo->nr_chnls +
+ rqd->ppa_list[i].g.ch;
+
+ if (!test_bit(erase_lun, e_line->erase_bitmap)) {
+ if (down_trylock(&pblk->erase_sem))
+ continue;
+
+ set_bit(erase_lun, e_line->erase_bitmap);
+ atomic_dec(&e_line->left_eblks);
+ *erase_ppa = rqd->ppa_list[i];
+ erase_ppa->g.blk = e_line->id;
+
+ /* Avoid evaluating e_line->left_eblks */
+ return pblk_map_rq(pblk, rqd, sentry, lun_bitmap,
+ valid_secs, i + min);
+ }
+ }
+
+ /* Erase blocks that are bad in this line but might not be in next */
+ if (unlikely(ppa_empty(*erase_ppa))) {
+ struct pblk_line_meta *lm = &pblk->lm;
+
+ i = find_first_zero_bit(e_line->erase_bitmap, lm->blk_per_line);
+ if (i == lm->blk_per_line)
+ return;
+
+ set_bit(i, e_line->erase_bitmap);
+ atomic_dec(&e_line->left_eblks);
+ *erase_ppa = pblk->luns[i].bppa; /* set ch and lun */
+ erase_ppa->g.blk = e_line->id;
+ }
+}
--- /dev/null
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ *
+ * Based upon the circular ringbuffer.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * pblk-rb.c - pblk's write buffer
+ */
+
+#include <linux/circ_buf.h>
+
+#include "pblk.h"
+
+static DECLARE_RWSEM(pblk_rb_lock);
+
+void pblk_rb_data_free(struct pblk_rb *rb)
+{
+ struct pblk_rb_pages *p, *t;
+
+ down_write(&pblk_rb_lock);
+ list_for_each_entry_safe(p, t, &rb->pages, list) {
+ free_pages((unsigned long)page_address(p->pages), p->order);
+ list_del(&p->list);
+ kfree(p);
+ }
+ up_write(&pblk_rb_lock);
+}
+
+/*
+ * Initialize ring buffer. The data and metadata buffers must be previously
+ * allocated and their size must be a power of two
+ * (Documentation/circular-buffers.txt)
+ */
+int pblk_rb_init(struct pblk_rb *rb, struct pblk_rb_entry *rb_entry_base,
+ unsigned int power_size, unsigned int power_seg_sz)
+{
+ struct pblk *pblk = container_of(rb, struct pblk, rwb);
+ unsigned int init_entry = 0;
+ unsigned int alloc_order = power_size;
+ unsigned int max_order = MAX_ORDER - 1;
+ unsigned int order, iter;
+
+ down_write(&pblk_rb_lock);
+ rb->entries = rb_entry_base;
+ rb->seg_size = (1 << power_seg_sz);
+ rb->nr_entries = (1 << power_size);
+ rb->mem = rb->subm = rb->sync = rb->l2p_update = 0;
+ rb->sync_point = EMPTY_ENTRY;
+
+ spin_lock_init(&rb->w_lock);
+ spin_lock_init(&rb->s_lock);
+
+ INIT_LIST_HEAD(&rb->pages);
+
+ if (alloc_order >= max_order) {
+ order = max_order;
+ iter = (1 << (alloc_order - max_order));
+ } else {
+ order = alloc_order;
+ iter = 1;
+ }
+
+ do {
+ struct pblk_rb_entry *entry;
+ struct pblk_rb_pages *page_set;
+ void *kaddr;
+ unsigned long set_size;
+ int i;
+
+ page_set = kmalloc(sizeof(struct pblk_rb_pages), GFP_KERNEL);
+ if (!page_set) {
+ up_write(&pblk_rb_lock);
+ return -ENOMEM;
+ }
+
+ page_set->order = order;
+ page_set->pages = alloc_pages(GFP_KERNEL, order);
+ if (!page_set->pages) {
+ kfree(page_set);
+ pblk_rb_data_free(rb);
+ up_write(&pblk_rb_lock);
+ return -ENOMEM;
+ }
+ kaddr = page_address(page_set->pages);
+
+ entry = &rb->entries[init_entry];
+ entry->data = kaddr;
+ entry->cacheline = pblk_cacheline_to_addr(init_entry++);
+ entry->w_ctx.flags = PBLK_WRITABLE_ENTRY;
+
+ set_size = (1 << order);
+ for (i = 1; i < set_size; i++) {
+ entry = &rb->entries[init_entry];
+ entry->cacheline = pblk_cacheline_to_addr(init_entry++);
+ entry->data = kaddr + (i * rb->seg_size);
+ entry->w_ctx.flags = PBLK_WRITABLE_ENTRY;
+ bio_list_init(&entry->w_ctx.bios);
+ }
+
+ list_add_tail(&page_set->list, &rb->pages);
+ iter--;
+ } while (iter > 0);
+ up_write(&pblk_rb_lock);
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_set(&rb->inflight_sync_point, 0);
+#endif
+
+ /*
+ * Initialize rate-limiter, which controls access to the write buffer
+ * but user and GC I/O
+ */
+ pblk_rl_init(&pblk->rl, rb->nr_entries);
+
+ return 0;
+}
+
+/*
+ * pblk_rb_calculate_size -- calculate the size of the write buffer
+ */
+unsigned int pblk_rb_calculate_size(unsigned int nr_entries)
+{
+ /* Alloc a write buffer that can at least fit 128 entries */
+ return (1 << max(get_count_order(nr_entries), 7));
+}
+
+void *pblk_rb_entries_ref(struct pblk_rb *rb)
+{
+ return rb->entries;
+}
+
+static void clean_wctx(struct pblk_w_ctx *w_ctx)
+{
+ int flags;
+
+try:
+ flags = READ_ONCE(w_ctx->flags);
+ if (!(flags & PBLK_SUBMITTED_ENTRY))
+ goto try;
+
+ /* Release flags on context. Protect from writes and reads */
+ smp_store_release(&w_ctx->flags, PBLK_WRITABLE_ENTRY);
+ pblk_ppa_set_empty(&w_ctx->ppa);
+}
+
+#define pblk_rb_ring_count(head, tail, size) CIRC_CNT(head, tail, size)
+#define pblk_rb_ring_space(rb, head, tail, size) \
+ (CIRC_SPACE(head, tail, size))
+
+/*
+ * Buffer space is calculated with respect to the back pointer signaling
+ * synchronized entries to the media.
+ */
+static unsigned int pblk_rb_space(struct pblk_rb *rb)
+{
+ unsigned int mem = READ_ONCE(rb->mem);
+ unsigned int sync = READ_ONCE(rb->sync);
+
+ return pblk_rb_ring_space(rb, mem, sync, rb->nr_entries);
+}
+
+/*
+ * Buffer count is calculated with respect to the submission entry signaling the
+ * entries that are available to send to the media
+ */
+unsigned int pblk_rb_read_count(struct pblk_rb *rb)
+{
+ unsigned int mem = READ_ONCE(rb->mem);
+ unsigned int subm = READ_ONCE(rb->subm);
+
+ return pblk_rb_ring_count(mem, subm, rb->nr_entries);
+}
+
+unsigned int pblk_rb_read_commit(struct pblk_rb *rb, unsigned int nr_entries)
+{
+ unsigned int subm;
+
+ subm = READ_ONCE(rb->subm);
+ /* Commit read means updating submission pointer */
+ smp_store_release(&rb->subm,
+ (subm + nr_entries) & (rb->nr_entries - 1));
+
+ return subm;
+}
+
+static int __pblk_rb_update_l2p(struct pblk_rb *rb, unsigned int *l2p_upd,
+ unsigned int to_update)
+{
+ struct pblk *pblk = container_of(rb, struct pblk, rwb);
+ struct pblk_line *line;
+ struct pblk_rb_entry *entry;
+ struct pblk_w_ctx *w_ctx;
+ unsigned int i;
+
+ for (i = 0; i < to_update; i++) {
+ entry = &rb->entries[*l2p_upd];
+ w_ctx = &entry->w_ctx;
+
+ pblk_update_map_dev(pblk, w_ctx->lba, w_ctx->ppa,
+ entry->cacheline);
+
+ line = &pblk->lines[pblk_tgt_ppa_to_line(w_ctx->ppa)];
+ kref_put(&line->ref, pblk_line_put);
+ clean_wctx(w_ctx);
+ *l2p_upd = (*l2p_upd + 1) & (rb->nr_entries - 1);
+ }
+
+ return 0;
+}
+
+/*
+ * When we move the l2p_update pointer, we update the l2p table - lookups will
+ * point to the physical address instead of to the cacheline in the write buffer
+ * from this moment on.
+ */
+static int pblk_rb_update_l2p(struct pblk_rb *rb, unsigned int nr_entries,
+ unsigned int mem, unsigned int sync)
+{
+ unsigned int space, count;
+ int ret = 0;
+
+ lockdep_assert_held(&rb->w_lock);
+
+ /* Update l2p only as buffer entries are being overwritten */
+ space = pblk_rb_ring_space(rb, mem, rb->l2p_update, rb->nr_entries);
+ if (space > nr_entries)
+ goto out;
+
+ count = nr_entries - space;
+ /* l2p_update used exclusively under rb->w_lock */
+ ret = __pblk_rb_update_l2p(rb, &rb->l2p_update, count);
+
+out:
+ return ret;
+}
+
+/*
+ * Update the l2p entry for all sectors stored on the write buffer. This means
+ * that all future lookups to the l2p table will point to a device address, not
+ * to the cacheline in the write buffer.
+ */
+void pblk_rb_sync_l2p(struct pblk_rb *rb)
+{
+ unsigned int sync;
+ unsigned int to_update;
+
+ spin_lock(&rb->w_lock);
+
+ /* Protect from reads and writes */
+ sync = smp_load_acquire(&rb->sync);
+
+ to_update = pblk_rb_ring_count(sync, rb->l2p_update, rb->nr_entries);
+ __pblk_rb_update_l2p(rb, &rb->l2p_update, to_update);
+
+ spin_unlock(&rb->w_lock);
+}
+
+/*
+ * Write @nr_entries to ring buffer from @data buffer if there is enough space.
+ * Typically, 4KB data chunks coming from a bio will be copied to the ring
+ * buffer, thus the write will fail if not all incoming data can be copied.
+ *
+ */
+static void __pblk_rb_write_entry(struct pblk_rb *rb, void *data,
+ struct pblk_w_ctx w_ctx,
+ struct pblk_rb_entry *entry)
+{
+ memcpy(entry->data, data, rb->seg_size);
+
+ entry->w_ctx.lba = w_ctx.lba;
+ entry->w_ctx.ppa = w_ctx.ppa;
+}
+
+void pblk_rb_write_entry_user(struct pblk_rb *rb, void *data,
+ struct pblk_w_ctx w_ctx, unsigned int ring_pos)
+{
+ struct pblk *pblk = container_of(rb, struct pblk, rwb);
+ struct pblk_rb_entry *entry;
+ int flags;
+
+ entry = &rb->entries[ring_pos];
+ flags = READ_ONCE(entry->w_ctx.flags);
+#ifdef CONFIG_NVM_DEBUG
+ /* Caller must guarantee that the entry is free */
+ BUG_ON(!(flags & PBLK_WRITABLE_ENTRY));
+#endif
+
+ __pblk_rb_write_entry(rb, data, w_ctx, entry);
+
+ pblk_update_map_cache(pblk, w_ctx.lba, entry->cacheline);
+ flags = w_ctx.flags | PBLK_WRITTEN_DATA;
+
+ /* Release flags on write context. Protect from writes */
+ smp_store_release(&entry->w_ctx.flags, flags);
+}
+
+void pblk_rb_write_entry_gc(struct pblk_rb *rb, void *data,
+ struct pblk_w_ctx w_ctx, struct pblk_line *gc_line,
+ unsigned int ring_pos)
+{
+ struct pblk *pblk = container_of(rb, struct pblk, rwb);
+ struct pblk_rb_entry *entry;
+ int flags;
+
+ entry = &rb->entries[ring_pos];
+ flags = READ_ONCE(entry->w_ctx.flags);
+#ifdef CONFIG_NVM_DEBUG
+ /* Caller must guarantee that the entry is free */
+ BUG_ON(!(flags & PBLK_WRITABLE_ENTRY));
+#endif
+
+ __pblk_rb_write_entry(rb, data, w_ctx, entry);
+
+ if (!pblk_update_map_gc(pblk, w_ctx.lba, entry->cacheline, gc_line))
+ entry->w_ctx.lba = ADDR_EMPTY;
+
+ flags = w_ctx.flags | PBLK_WRITTEN_DATA;
+
+ /* Release flags on write context. Protect from writes */
+ smp_store_release(&entry->w_ctx.flags, flags);
+}
+
+static int pblk_rb_sync_point_set(struct pblk_rb *rb, struct bio *bio,
+ unsigned int pos)
+{
+ struct pblk_rb_entry *entry;
+ unsigned int subm, sync_point;
+ int flags;
+
+ subm = READ_ONCE(rb->subm);
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_inc(&rb->inflight_sync_point);
+#endif
+
+ if (pos == subm)
+ return 0;
+
+ sync_point = (pos == 0) ? (rb->nr_entries - 1) : (pos - 1);
+ entry = &rb->entries[sync_point];
+
+ flags = READ_ONCE(entry->w_ctx.flags);
+ flags |= PBLK_FLUSH_ENTRY;
+
+ /* Release flags on context. Protect from writes */
+ smp_store_release(&entry->w_ctx.flags, flags);
+
+ /* Protect syncs */
+ smp_store_release(&rb->sync_point, sync_point);
+
+ spin_lock_irq(&rb->s_lock);
+ bio_list_add(&entry->w_ctx.bios, bio);
+ spin_unlock_irq(&rb->s_lock);
+
+ return 1;
+}
+
+static int __pblk_rb_may_write(struct pblk_rb *rb, unsigned int nr_entries,
+ unsigned int *pos)
+{
+ unsigned int mem;
+ unsigned int sync;
+
+ sync = READ_ONCE(rb->sync);
+ mem = READ_ONCE(rb->mem);
+
+ if (pblk_rb_ring_space(rb, mem, sync, rb->nr_entries) < nr_entries)
+ return 0;
+
+ if (pblk_rb_update_l2p(rb, nr_entries, mem, sync))
+ return 0;
+
+ *pos = mem;
+
+ return 1;
+}
+
+static int pblk_rb_may_write(struct pblk_rb *rb, unsigned int nr_entries,
+ unsigned int *pos)
+{
+ if (!__pblk_rb_may_write(rb, nr_entries, pos))
+ return 0;
+
+ /* Protect from read count */
+ smp_store_release(&rb->mem, (*pos + nr_entries) & (rb->nr_entries - 1));
+ return 1;
+}
+
+static int pblk_rb_may_write_flush(struct pblk_rb *rb, unsigned int nr_entries,
+ unsigned int *pos, struct bio *bio,
+ int *io_ret)
+{
+ unsigned int mem;
+
+ if (!__pblk_rb_may_write(rb, nr_entries, pos))
+ return 0;
+
+ mem = (*pos + nr_entries) & (rb->nr_entries - 1);
+ *io_ret = NVM_IO_DONE;
+
+ if (bio->bi_opf & REQ_PREFLUSH) {
+ struct pblk *pblk = container_of(rb, struct pblk, rwb);
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_inc(&pblk->nr_flush);
+#endif
+ if (pblk_rb_sync_point_set(&pblk->rwb, bio, mem))
+ *io_ret = NVM_IO_OK;
+ }
+
+ /* Protect from read count */
+ smp_store_release(&rb->mem, mem);
+ return 1;
+}
+
+/*
+ * Atomically check that (i) there is space on the write buffer for the
+ * incoming I/O, and (ii) the current I/O type has enough budget in the write
+ * buffer (rate-limiter).
+ */
+int pblk_rb_may_write_user(struct pblk_rb *rb, struct bio *bio,
+ unsigned int nr_entries, unsigned int *pos)
+{
+ struct pblk *pblk = container_of(rb, struct pblk, rwb);
+ int flush_done;
+
+ spin_lock(&rb->w_lock);
+ if (!pblk_rl_user_may_insert(&pblk->rl, nr_entries)) {
+ spin_unlock(&rb->w_lock);
+ return NVM_IO_REQUEUE;
+ }
+
+ if (!pblk_rb_may_write_flush(rb, nr_entries, pos, bio, &flush_done)) {
+ spin_unlock(&rb->w_lock);
+ return NVM_IO_REQUEUE;
+ }
+
+ pblk_rl_user_in(&pblk->rl, nr_entries);
+ spin_unlock(&rb->w_lock);
+
+ return flush_done;
+}
+
+/*
+ * Look at pblk_rb_may_write_user comment
+ */
+int pblk_rb_may_write_gc(struct pblk_rb *rb, unsigned int nr_entries,
+ unsigned int *pos)
+{
+ struct pblk *pblk = container_of(rb, struct pblk, rwb);
+
+ spin_lock(&rb->w_lock);
+ if (!pblk_rl_gc_may_insert(&pblk->rl, nr_entries)) {
+ spin_unlock(&rb->w_lock);
+ return 0;
+ }
+
+ if (!pblk_rb_may_write(rb, nr_entries, pos)) {
+ spin_unlock(&rb->w_lock);
+ return 0;
+ }
+
+ pblk_rl_gc_in(&pblk->rl, nr_entries);
+ spin_unlock(&rb->w_lock);
+
+ return 1;
+}
+
+/*
+ * The caller of this function must ensure that the backpointer will not
+ * overwrite the entries passed on the list.
+ */
+unsigned int pblk_rb_read_to_bio_list(struct pblk_rb *rb, struct bio *bio,
+ struct list_head *list,
+ unsigned int max)
+{
+ struct pblk_rb_entry *entry, *tentry;
+ struct page *page;
+ unsigned int read = 0;
+ int ret;
+
+ list_for_each_entry_safe(entry, tentry, list, index) {
+ if (read > max) {
+ pr_err("pblk: too many entries on list\n");
+ goto out;
+ }
+
+ page = virt_to_page(entry->data);
+ if (!page) {
+ pr_err("pblk: could not allocate write bio page\n");
+ goto out;
+ }
+
+ ret = bio_add_page(bio, page, rb->seg_size, 0);
+ if (ret != rb->seg_size) {
+ pr_err("pblk: could not add page to write bio\n");
+ goto out;
+ }
+
+ list_del(&entry->index);
+ read++;
+ }
+
+out:
+ return read;
+}
+
+/*
+ * Read available entries on rb and add them to the given bio. To avoid a memory
+ * copy, a page reference to the write buffer is used to be added to the bio.
+ *
+ * This function is used by the write thread to form the write bio that will
+ * persist data on the write buffer to the media.
+ */
+unsigned int pblk_rb_read_to_bio(struct pblk_rb *rb, struct bio *bio,
+ struct pblk_c_ctx *c_ctx,
+ unsigned int pos,
+ unsigned int nr_entries,
+ unsigned int count)
+{
+ struct pblk *pblk = container_of(rb, struct pblk, rwb);
+ struct pblk_rb_entry *entry;
+ struct page *page;
+ unsigned int pad = 0, read = 0, to_read = nr_entries;
+ unsigned int user_io = 0, gc_io = 0;
+ unsigned int i;
+ int flags;
+ int ret;
+
+ if (count < nr_entries) {
+ pad = nr_entries - count;
+ to_read = count;
+ }
+
+ c_ctx->sentry = pos;
+ c_ctx->nr_valid = to_read;
+ c_ctx->nr_padded = pad;
+
+ for (i = 0; i < to_read; i++) {
+ entry = &rb->entries[pos];
+
+ /* A write has been allowed into the buffer, but data is still
+ * being copied to it. It is ok to busy wait.
+ */
+try:
+ flags = READ_ONCE(entry->w_ctx.flags);
+ if (!(flags & PBLK_WRITTEN_DATA))
+ goto try;
+
+ if (flags & PBLK_IOTYPE_USER)
+ user_io++;
+ else if (flags & PBLK_IOTYPE_GC)
+ gc_io++;
+ else
+ WARN(1, "pblk: unknown IO type\n");
+
+ page = virt_to_page(entry->data);
+ if (!page) {
+ pr_err("pblk: could not allocate write bio page\n");
+ flags &= ~PBLK_WRITTEN_DATA;
+ flags |= PBLK_SUBMITTED_ENTRY;
+ /* Release flags on context. Protect from writes */
+ smp_store_release(&entry->w_ctx.flags, flags);
+ goto out;
+ }
+
+ ret = bio_add_page(bio, page, rb->seg_size, 0);
+ if (ret != rb->seg_size) {
+ pr_err("pblk: could not add page to write bio\n");
+ flags &= ~PBLK_WRITTEN_DATA;
+ flags |= PBLK_SUBMITTED_ENTRY;
+ /* Release flags on context. Protect from writes */
+ smp_store_release(&entry->w_ctx.flags, flags);
+ goto out;
+ }
+
+ if (flags & PBLK_FLUSH_ENTRY) {
+ unsigned int sync_point;
+
+ sync_point = READ_ONCE(rb->sync_point);
+ if (sync_point == pos) {
+ /* Protect syncs */
+ smp_store_release(&rb->sync_point, EMPTY_ENTRY);
+ }
+
+ flags &= ~PBLK_FLUSH_ENTRY;
+#ifdef CONFIG_NVM_DEBUG
+ atomic_dec(&rb->inflight_sync_point);
+#endif
+ }
+
+ flags &= ~PBLK_WRITTEN_DATA;
+ flags |= PBLK_SUBMITTED_ENTRY;
+
+ /* Release flags on context. Protect from writes */
+ smp_store_release(&entry->w_ctx.flags, flags);
+
+ pos = (pos + 1) & (rb->nr_entries - 1);
+ }
+
+ read = to_read;
+ pblk_rl_out(&pblk->rl, user_io, gc_io);
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_add(pad, &((struct pblk *)
+ (container_of(rb, struct pblk, rwb)))->padded_writes);
+#endif
+out:
+ return read;
+}
+
+/*
+ * Copy to bio only if the lba matches the one on the given cache entry.
+ * Otherwise, it means that the entry has been overwritten, and the bio should
+ * be directed to disk.
+ */
+int pblk_rb_copy_to_bio(struct pblk_rb *rb, struct bio *bio, sector_t lba,
+ u64 pos, int bio_iter)
+{
+ struct pblk_rb_entry *entry;
+ struct pblk_w_ctx *w_ctx;
+ void *data;
+ int flags;
+ int ret = 1;
+
+ spin_lock(&rb->w_lock);
+
+#ifdef CONFIG_NVM_DEBUG
+ /* Caller must ensure that the access will not cause an overflow */
+ BUG_ON(pos >= rb->nr_entries);
+#endif
+ entry = &rb->entries[pos];
+ w_ctx = &entry->w_ctx;
+ flags = READ_ONCE(w_ctx->flags);
+
+ /* Check if the entry has been overwritten or is scheduled to be */
+ if (w_ctx->lba != lba || flags & PBLK_WRITABLE_ENTRY) {
+ ret = 0;
+ goto out;
+ }
+
+ /* Only advance the bio if it hasn't been advanced already. If advanced,
+ * this bio is at least a partial bio (i.e., it has partially been
+ * filled with data from the cache). If part of the data resides on the
+ * media, we will read later on
+ */
+ if (unlikely(!bio->bi_iter.bi_idx))
+ bio_advance(bio, bio_iter * PBLK_EXPOSED_PAGE_SIZE);
+
+ data = bio_data(bio);
+ memcpy(data, entry->data, rb->seg_size);
+
+out:
+ spin_unlock(&rb->w_lock);
+ return ret;
+}
+
+struct pblk_w_ctx *pblk_rb_w_ctx(struct pblk_rb *rb, unsigned int pos)
+{
+ unsigned int entry = pos & (rb->nr_entries - 1);
+
+ return &rb->entries[entry].w_ctx;
+}
+
+unsigned int pblk_rb_sync_init(struct pblk_rb *rb, unsigned long *flags)
+ __acquires(&rb->s_lock)
+{
+ if (flags)
+ spin_lock_irqsave(&rb->s_lock, *flags);
+ else
+ spin_lock_irq(&rb->s_lock);
+
+ return rb->sync;
+}
+
+void pblk_rb_sync_end(struct pblk_rb *rb, unsigned long *flags)
+ __releases(&rb->s_lock)
+{
+ lockdep_assert_held(&rb->s_lock);
+
+ if (flags)
+ spin_unlock_irqrestore(&rb->s_lock, *flags);
+ else
+ spin_unlock_irq(&rb->s_lock);
+}
+
+unsigned int pblk_rb_sync_advance(struct pblk_rb *rb, unsigned int nr_entries)
+{
+ unsigned int sync;
+ unsigned int i;
+
+ lockdep_assert_held(&rb->s_lock);
+
+ sync = READ_ONCE(rb->sync);
+
+ for (i = 0; i < nr_entries; i++)
+ sync = (sync + 1) & (rb->nr_entries - 1);
+
+ /* Protect from counts */
+ smp_store_release(&rb->sync, sync);
+
+ return sync;
+}
+
+unsigned int pblk_rb_sync_point_count(struct pblk_rb *rb)
+{
+ unsigned int subm, sync_point;
+ unsigned int count;
+
+ /* Protect syncs */
+ sync_point = smp_load_acquire(&rb->sync_point);
+ if (sync_point == EMPTY_ENTRY)
+ return 0;
+
+ subm = READ_ONCE(rb->subm);
+
+ /* The sync point itself counts as a sector to sync */
+ count = pblk_rb_ring_count(sync_point, subm, rb->nr_entries) + 1;
+
+ return count;
+}
+
+/*
+ * Scan from the current position of the sync pointer to find the entry that
+ * corresponds to the given ppa. This is necessary since write requests can be
+ * completed out of order. The assumption is that the ppa is close to the sync
+ * pointer thus the search will not take long.
+ *
+ * The caller of this function must guarantee that the sync pointer will no
+ * reach the entry while it is using the metadata associated with it. With this
+ * assumption in mind, there is no need to take the sync lock.
+ */
+struct pblk_rb_entry *pblk_rb_sync_scan_entry(struct pblk_rb *rb,
+ struct ppa_addr *ppa)
+{
+ unsigned int sync, subm, count;
+ unsigned int i;
+
+ sync = READ_ONCE(rb->sync);
+ subm = READ_ONCE(rb->subm);
+ count = pblk_rb_ring_count(subm, sync, rb->nr_entries);
+
+ for (i = 0; i < count; i++)
+ sync = (sync + 1) & (rb->nr_entries - 1);
+
+ return NULL;
+}
+
+int pblk_rb_tear_down_check(struct pblk_rb *rb)
+{
+ struct pblk_rb_entry *entry;
+ int i;
+ int ret = 0;
+
+ spin_lock(&rb->w_lock);
+ spin_lock_irq(&rb->s_lock);
+
+ if ((rb->mem == rb->subm) && (rb->subm == rb->sync) &&
+ (rb->sync == rb->l2p_update) &&
+ (rb->sync_point == EMPTY_ENTRY)) {
+ goto out;
+ }
+
+ if (!rb->entries) {
+ ret = 1;
+ goto out;
+ }
+
+ for (i = 0; i < rb->nr_entries; i++) {
+ entry = &rb->entries[i];
+
+ if (!entry->data) {
+ ret = 1;
+ goto out;
+ }
+ }
+
+out:
+ spin_unlock(&rb->w_lock);
+ spin_unlock_irq(&rb->s_lock);
+
+ return ret;
+}
+
+unsigned int pblk_rb_wrap_pos(struct pblk_rb *rb, unsigned int pos)
+{
+ return (pos & (rb->nr_entries - 1));
+}
+
+int pblk_rb_pos_oob(struct pblk_rb *rb, u64 pos)
+{
+ return (pos >= rb->nr_entries);
+}
+
+ssize_t pblk_rb_sysfs(struct pblk_rb *rb, char *buf)
+{
+ struct pblk *pblk = container_of(rb, struct pblk, rwb);
+ struct pblk_c_ctx *c;
+ ssize_t offset;
+ int queued_entries = 0;
+
+ spin_lock_irq(&rb->s_lock);
+ list_for_each_entry(c, &pblk->compl_list, list)
+ queued_entries++;
+ spin_unlock_irq(&rb->s_lock);
+
+ if (rb->sync_point != EMPTY_ENTRY)
+ offset = scnprintf(buf, PAGE_SIZE,
+ "%u\t%u\t%u\t%u\t%u\t%u\t%u - %u/%u/%u - %d\n",
+ rb->nr_entries,
+ rb->mem,
+ rb->subm,
+ rb->sync,
+ rb->l2p_update,
+#ifdef CONFIG_NVM_DEBUG
+ atomic_read(&rb->inflight_sync_point),
+#else
+ 0,
+#endif
+ rb->sync_point,
+ pblk_rb_read_count(rb),
+ pblk_rb_space(rb),
+ pblk_rb_sync_point_count(rb),
+ queued_entries);
+ else
+ offset = scnprintf(buf, PAGE_SIZE,
+ "%u\t%u\t%u\t%u\t%u\t%u\tNULL - %u/%u/%u - %d\n",
+ rb->nr_entries,
+ rb->mem,
+ rb->subm,
+ rb->sync,
+ rb->l2p_update,
+#ifdef CONFIG_NVM_DEBUG
+ atomic_read(&rb->inflight_sync_point),
+#else
+ 0,
+#endif
+ pblk_rb_read_count(rb),
+ pblk_rb_space(rb),
+ pblk_rb_sync_point_count(rb),
+ queued_entries);
+
+ return offset;
+}
--- /dev/null
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ * Matias Bjorling <matias@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * pblk-read.c - pblk's read path
+ */
+
+#include "pblk.h"
+
+/*
+ * There is no guarantee that the value read from cache has not been updated and
+ * resides at another location in the cache. We guarantee though that if the
+ * value is read from the cache, it belongs to the mapped lba. In order to
+ * guarantee and order between writes and reads are ordered, a flush must be
+ * issued.
+ */
+static int pblk_read_from_cache(struct pblk *pblk, struct bio *bio,
+ sector_t lba, struct ppa_addr ppa,
+ int bio_iter)
+{
+#ifdef CONFIG_NVM_DEBUG
+ /* Callers must ensure that the ppa points to a cache address */
+ BUG_ON(pblk_ppa_empty(ppa));
+ BUG_ON(!pblk_addr_in_cache(ppa));
+#endif
+
+ return pblk_rb_copy_to_bio(&pblk->rwb, bio, lba,
+ pblk_addr_to_cacheline(ppa), bio_iter);
+}
+
+static void pblk_read_ppalist_rq(struct pblk *pblk, struct nvm_rq *rqd,
+ unsigned long *read_bitmap)
+{
+ struct bio *bio = rqd->bio;
+ struct ppa_addr ppas[PBLK_MAX_REQ_ADDRS];
+ sector_t blba = pblk_get_lba(bio);
+ int nr_secs = rqd->nr_ppas;
+ int advanced_bio = 0;
+ int i, j = 0;
+
+ /* logic error: lba out-of-bounds. Ignore read request */
+ if (blba + nr_secs >= pblk->rl.nr_secs) {
+ WARN(1, "pblk: read lbas out of bounds\n");
+ return;
+ }
+
+ pblk_lookup_l2p_seq(pblk, ppas, blba, nr_secs);
+
+ for (i = 0; i < nr_secs; i++) {
+ struct ppa_addr p = ppas[i];
+ sector_t lba = blba + i;
+
+retry:
+ if (pblk_ppa_empty(p)) {
+ WARN_ON(test_and_set_bit(i, read_bitmap));
+ continue;
+ }
+
+ /* Try to read from write buffer. The address is later checked
+ * on the write buffer to prevent retrieving overwritten data.
+ */
+ if (pblk_addr_in_cache(p)) {
+ if (!pblk_read_from_cache(pblk, bio, lba, p, i)) {
+ pblk_lookup_l2p_seq(pblk, &p, lba, 1);
+ goto retry;
+ }
+ WARN_ON(test_and_set_bit(i, read_bitmap));
+ advanced_bio = 1;
+ } else {
+ /* Read from media non-cached sectors */
+ rqd->ppa_list[j++] = p;
+ }
+
+ if (advanced_bio)
+ bio_advance(bio, PBLK_EXPOSED_PAGE_SIZE);
+ }
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_add(nr_secs, &pblk->inflight_reads);
+#endif
+}
+
+static int pblk_submit_read_io(struct pblk *pblk, struct nvm_rq *rqd)
+{
+ int err;
+
+ rqd->flags = pblk_set_read_mode(pblk);
+
+ err = pblk_submit_io(pblk, rqd);
+ if (err)
+ return NVM_IO_ERR;
+
+ return NVM_IO_OK;
+}
+
+static void pblk_end_io_read(struct nvm_rq *rqd)
+{
+ struct pblk *pblk = rqd->private;
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct pblk_r_ctx *r_ctx = nvm_rq_to_pdu(rqd);
+ struct bio *bio = rqd->bio;
+
+ if (rqd->error)
+ pblk_log_read_err(pblk, rqd);
+#ifdef CONFIG_NVM_DEBUG
+ else
+ WARN_ONCE(bio->bi_error, "pblk: corrupted read error\n");
+#endif
+
+ if (rqd->nr_ppas > 1)
+ nvm_dev_dma_free(dev->parent, rqd->ppa_list, rqd->dma_ppa_list);
+
+ bio_put(bio);
+ if (r_ctx->orig_bio) {
+#ifdef CONFIG_NVM_DEBUG
+ WARN_ONCE(r_ctx->orig_bio->bi_error,
+ "pblk: corrupted read bio\n");
+#endif
+ bio_endio(r_ctx->orig_bio);
+ bio_put(r_ctx->orig_bio);
+ }
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_add(rqd->nr_ppas, &pblk->sync_reads);
+ atomic_long_sub(rqd->nr_ppas, &pblk->inflight_reads);
+#endif
+
+ pblk_free_rqd(pblk, rqd, READ);
+}
+
+static int pblk_fill_partial_read_bio(struct pblk *pblk, struct nvm_rq *rqd,
+ unsigned int bio_init_idx,
+ unsigned long *read_bitmap)
+{
+ struct bio *new_bio, *bio = rqd->bio;
+ struct bio_vec src_bv, dst_bv;
+ void *ppa_ptr = NULL;
+ void *src_p, *dst_p;
+ dma_addr_t dma_ppa_list = 0;
+ int nr_secs = rqd->nr_ppas;
+ int nr_holes = nr_secs - bitmap_weight(read_bitmap, nr_secs);
+ int i, ret, hole;
+ DECLARE_COMPLETION_ONSTACK(wait);
+
+ new_bio = bio_alloc(GFP_KERNEL, nr_holes);
+ if (!new_bio) {
+ pr_err("pblk: could not alloc read bio\n");
+ return NVM_IO_ERR;
+ }
+
+ if (pblk_bio_add_pages(pblk, new_bio, GFP_KERNEL, nr_holes))
+ goto err;
+
+ if (nr_holes != new_bio->bi_vcnt) {
+ pr_err("pblk: malformed bio\n");
+ goto err;
+ }
+
+ new_bio->bi_iter.bi_sector = 0; /* internal bio */
+ bio_set_op_attrs(new_bio, REQ_OP_READ, 0);
+ new_bio->bi_private = &wait;
+ new_bio->bi_end_io = pblk_end_bio_sync;
+
+ rqd->bio = new_bio;
+ rqd->nr_ppas = nr_holes;
+ rqd->end_io = NULL;
+
+ if (unlikely(nr_secs > 1 && nr_holes == 1)) {
+ ppa_ptr = rqd->ppa_list;
+ dma_ppa_list = rqd->dma_ppa_list;
+ rqd->ppa_addr = rqd->ppa_list[0];
+ }
+
+ ret = pblk_submit_read_io(pblk, rqd);
+ if (ret) {
+ bio_put(rqd->bio);
+ pr_err("pblk: read IO submission failed\n");
+ goto err;
+ }
+
+ if (!wait_for_completion_io_timeout(&wait,
+ msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+ pr_err("pblk: partial read I/O timed out\n");
+ }
+
+ if (rqd->error) {
+ atomic_long_inc(&pblk->read_failed);
+#ifdef CONFIG_NVM_DEBUG
+ pblk_print_failed_rqd(pblk, rqd, rqd->error);
+#endif
+ }
+
+ if (unlikely(nr_secs > 1 && nr_holes == 1)) {
+ rqd->ppa_list = ppa_ptr;
+ rqd->dma_ppa_list = dma_ppa_list;
+ }
+
+ /* Fill the holes in the original bio */
+ i = 0;
+ hole = find_first_zero_bit(read_bitmap, nr_secs);
+ do {
+ src_bv = new_bio->bi_io_vec[i++];
+ dst_bv = bio->bi_io_vec[bio_init_idx + hole];
+
+ src_p = kmap_atomic(src_bv.bv_page);
+ dst_p = kmap_atomic(dst_bv.bv_page);
+
+ memcpy(dst_p + dst_bv.bv_offset,
+ src_p + src_bv.bv_offset,
+ PBLK_EXPOSED_PAGE_SIZE);
+
+ kunmap_atomic(src_p);
+ kunmap_atomic(dst_p);
+
+ mempool_free(src_bv.bv_page, pblk->page_pool);
+
+ hole = find_next_zero_bit(read_bitmap, nr_secs, hole + 1);
+ } while (hole < nr_secs);
+
+ bio_put(new_bio);
+
+ /* Complete the original bio and associated request */
+ rqd->bio = bio;
+ rqd->nr_ppas = nr_secs;
+ rqd->private = pblk;
+
+ bio_endio(bio);
+ pblk_end_io_read(rqd);
+ return NVM_IO_OK;
+
+err:
+ /* Free allocated pages in new bio */
+ pblk_bio_free_pages(pblk, bio, 0, new_bio->bi_vcnt);
+ rqd->private = pblk;
+ pblk_end_io_read(rqd);
+ return NVM_IO_ERR;
+}
+
+static void pblk_read_rq(struct pblk *pblk, struct nvm_rq *rqd,
+ unsigned long *read_bitmap)
+{
+ struct bio *bio = rqd->bio;
+ struct ppa_addr ppa;
+ sector_t lba = pblk_get_lba(bio);
+
+ /* logic error: lba out-of-bounds. Ignore read request */
+ if (lba >= pblk->rl.nr_secs) {
+ WARN(1, "pblk: read lba out of bounds\n");
+ return;
+ }
+
+ pblk_lookup_l2p_seq(pblk, &ppa, lba, 1);
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_inc(&pblk->inflight_reads);
+#endif
+
+retry:
+ if (pblk_ppa_empty(ppa)) {
+ WARN_ON(test_and_set_bit(0, read_bitmap));
+ return;
+ }
+
+ /* Try to read from write buffer. The address is later checked on the
+ * write buffer to prevent retrieving overwritten data.
+ */
+ if (pblk_addr_in_cache(ppa)) {
+ if (!pblk_read_from_cache(pblk, bio, lba, ppa, 0)) {
+ pblk_lookup_l2p_seq(pblk, &ppa, lba, 1);
+ goto retry;
+ }
+ WARN_ON(test_and_set_bit(0, read_bitmap));
+ } else {
+ rqd->ppa_addr = ppa;
+ }
+}
+
+int pblk_submit_read(struct pblk *pblk, struct bio *bio)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ unsigned int nr_secs = pblk_get_secs(bio);
+ struct nvm_rq *rqd;
+ unsigned long read_bitmap; /* Max 64 ppas per request */
+ unsigned int bio_init_idx;
+ int ret = NVM_IO_ERR;
+
+ if (nr_secs > PBLK_MAX_REQ_ADDRS)
+ return NVM_IO_ERR;
+
+ bitmap_zero(&read_bitmap, nr_secs);
+
+ rqd = pblk_alloc_rqd(pblk, READ);
+ if (IS_ERR(rqd)) {
+ pr_err_ratelimited("pblk: not able to alloc rqd");
+ return NVM_IO_ERR;
+ }
+
+ rqd->opcode = NVM_OP_PREAD;
+ rqd->bio = bio;
+ rqd->nr_ppas = nr_secs;
+ rqd->private = pblk;
+ rqd->end_io = pblk_end_io_read;
+
+ /* Save the index for this bio's start. This is needed in case
+ * we need to fill a partial read.
+ */
+ bio_init_idx = pblk_get_bi_idx(bio);
+
+ if (nr_secs > 1) {
+ rqd->ppa_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL,
+ &rqd->dma_ppa_list);
+ if (!rqd->ppa_list) {
+ pr_err("pblk: not able to allocate ppa list\n");
+ goto fail_rqd_free;
+ }
+
+ pblk_read_ppalist_rq(pblk, rqd, &read_bitmap);
+ } else {
+ pblk_read_rq(pblk, rqd, &read_bitmap);
+ }
+
+ bio_get(bio);
+ if (bitmap_full(&read_bitmap, nr_secs)) {
+ bio_endio(bio);
+ pblk_end_io_read(rqd);
+ return NVM_IO_OK;
+ }
+
+ /* All sectors are to be read from the device */
+ if (bitmap_empty(&read_bitmap, rqd->nr_ppas)) {
+ struct bio *int_bio = NULL;
+ struct pblk_r_ctx *r_ctx = nvm_rq_to_pdu(rqd);
+
+ /* Clone read bio to deal with read errors internally */
+ int_bio = bio_clone_bioset(bio, GFP_KERNEL, fs_bio_set);
+ if (!int_bio) {
+ pr_err("pblk: could not clone read bio\n");
+ return NVM_IO_ERR;
+ }
+
+ rqd->bio = int_bio;
+ r_ctx->orig_bio = bio;
+
+ ret = pblk_submit_read_io(pblk, rqd);
+ if (ret) {
+ pr_err("pblk: read IO submission failed\n");
+ if (int_bio)
+ bio_put(int_bio);
+ return ret;
+ }
+
+ return NVM_IO_OK;
+ }
+
+ /* The read bio request could be partially filled by the write buffer,
+ * but there are some holes that need to be read from the drive.
+ */
+ ret = pblk_fill_partial_read_bio(pblk, rqd, bio_init_idx, &read_bitmap);
+ if (ret) {
+ pr_err("pblk: failed to perform partial read\n");
+ return ret;
+ }
+
+ return NVM_IO_OK;
+
+fail_rqd_free:
+ pblk_free_rqd(pblk, rqd, READ);
+ return ret;
+}
+
+static int read_ppalist_rq_gc(struct pblk *pblk, struct nvm_rq *rqd,
+ struct pblk_line *line, u64 *lba_list,
+ unsigned int nr_secs)
+{
+ struct ppa_addr ppas[PBLK_MAX_REQ_ADDRS];
+ int valid_secs = 0;
+ int i;
+
+ pblk_lookup_l2p_rand(pblk, ppas, lba_list, nr_secs);
+
+ for (i = 0; i < nr_secs; i++) {
+ if (pblk_addr_in_cache(ppas[i]) || ppas[i].g.blk != line->id ||
+ pblk_ppa_empty(ppas[i])) {
+ lba_list[i] = ADDR_EMPTY;
+ continue;
+ }
+
+ rqd->ppa_list[valid_secs++] = ppas[i];
+ }
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_add(valid_secs, &pblk->inflight_reads);
+#endif
+ return valid_secs;
+}
+
+static int read_rq_gc(struct pblk *pblk, struct nvm_rq *rqd,
+ struct pblk_line *line, sector_t lba)
+{
+ struct ppa_addr ppa;
+ int valid_secs = 0;
+
+ if (lba == ADDR_EMPTY)
+ goto out;
+
+ /* logic error: lba out-of-bounds */
+ if (lba >= pblk->rl.nr_secs) {
+ WARN(1, "pblk: read lba out of bounds\n");
+ goto out;
+ }
+
+ spin_lock(&pblk->trans_lock);
+ ppa = pblk_trans_map_get(pblk, lba);
+ spin_unlock(&pblk->trans_lock);
+
+ /* Ignore updated values until the moment */
+ if (pblk_addr_in_cache(ppa) || ppa.g.blk != line->id ||
+ pblk_ppa_empty(ppa))
+ goto out;
+
+ rqd->ppa_addr = ppa;
+ valid_secs = 1;
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_inc(&pblk->inflight_reads);
+#endif
+
+out:
+ return valid_secs;
+}
+
+int pblk_submit_read_gc(struct pblk *pblk, u64 *lba_list, void *data,
+ unsigned int nr_secs, unsigned int *secs_to_gc,
+ struct pblk_line *line)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct request_queue *q = dev->q;
+ struct bio *bio;
+ struct nvm_rq rqd;
+ int ret, data_len;
+ DECLARE_COMPLETION_ONSTACK(wait);
+
+ memset(&rqd, 0, sizeof(struct nvm_rq));
+
+ if (nr_secs > 1) {
+ rqd.ppa_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL,
+ &rqd.dma_ppa_list);
+ if (!rqd.ppa_list)
+ return NVM_IO_ERR;
+
+ *secs_to_gc = read_ppalist_rq_gc(pblk, &rqd, line, lba_list,
+ nr_secs);
+ if (*secs_to_gc == 1) {
+ struct ppa_addr ppa;
+
+ ppa = rqd.ppa_list[0];
+ nvm_dev_dma_free(dev->parent, rqd.ppa_list,
+ rqd.dma_ppa_list);
+ rqd.ppa_addr = ppa;
+ }
+ } else {
+ *secs_to_gc = read_rq_gc(pblk, &rqd, line, lba_list[0]);
+ }
+
+ if (!(*secs_to_gc))
+ goto out;
+
+ data_len = (*secs_to_gc) * geo->sec_size;
+ bio = bio_map_kern(q, data, data_len, GFP_KERNEL);
+ if (IS_ERR(bio)) {
+ pr_err("pblk: could not allocate GC bio (%lu)\n", PTR_ERR(bio));
+ goto err_free_dma;
+ }
+
+ bio->bi_iter.bi_sector = 0; /* internal bio */
+ bio_set_op_attrs(bio, REQ_OP_READ, 0);
+
+ rqd.opcode = NVM_OP_PREAD;
+ rqd.end_io = pblk_end_io_sync;
+ rqd.private = &wait;
+ rqd.nr_ppas = *secs_to_gc;
+ rqd.bio = bio;
+
+ ret = pblk_submit_read_io(pblk, &rqd);
+ if (ret) {
+ bio_endio(bio);
+ pr_err("pblk: GC read request failed\n");
+ goto err_free_dma;
+ }
+
+ if (!wait_for_completion_io_timeout(&wait,
+ msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+ pr_err("pblk: GC read I/O timed out\n");
+ }
+
+ if (rqd.error) {
+ atomic_long_inc(&pblk->read_failed_gc);
+#ifdef CONFIG_NVM_DEBUG
+ pblk_print_failed_rqd(pblk, &rqd, rqd.error);
+#endif
+ }
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_add(*secs_to_gc, &pblk->sync_reads);
+ atomic_long_add(*secs_to_gc, &pblk->recov_gc_reads);
+ atomic_long_sub(*secs_to_gc, &pblk->inflight_reads);
+#endif
+
+out:
+ if (rqd.nr_ppas > 1)
+ nvm_dev_dma_free(dev->parent, rqd.ppa_list, rqd.dma_ppa_list);
+ return NVM_IO_OK;
+
+err_free_dma:
+ if (rqd.nr_ppas > 1)
+ nvm_dev_dma_free(dev->parent, rqd.ppa_list, rqd.dma_ppa_list);
+ return NVM_IO_ERR;
+}
--- /dev/null
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial: Javier Gonzalez <javier@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * pblk-recovery.c - pblk's recovery path
+ */
+
+#include "pblk.h"
+
+void pblk_submit_rec(struct work_struct *work)
+{
+ struct pblk_rec_ctx *recovery =
+ container_of(work, struct pblk_rec_ctx, ws_rec);
+ struct pblk *pblk = recovery->pblk;
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_rq *rqd = recovery->rqd;
+ struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd);
+ int max_secs = nvm_max_phys_sects(dev);
+ struct bio *bio;
+ unsigned int nr_rec_secs;
+ unsigned int pgs_read;
+ int ret;
+
+ nr_rec_secs = bitmap_weight((unsigned long int *)&rqd->ppa_status,
+ max_secs);
+
+ bio = bio_alloc(GFP_KERNEL, nr_rec_secs);
+ if (!bio) {
+ pr_err("pblk: not able to create recovery bio\n");
+ return;
+ }
+
+ bio->bi_iter.bi_sector = 0;
+ bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+ rqd->bio = bio;
+ rqd->nr_ppas = nr_rec_secs;
+
+ pgs_read = pblk_rb_read_to_bio_list(&pblk->rwb, bio, &recovery->failed,
+ nr_rec_secs);
+ if (pgs_read != nr_rec_secs) {
+ pr_err("pblk: could not read recovery entries\n");
+ goto err;
+ }
+
+ if (pblk_setup_w_rec_rq(pblk, rqd, c_ctx)) {
+ pr_err("pblk: could not setup recovery request\n");
+ goto err;
+ }
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_add(nr_rec_secs, &pblk->recov_writes);
+#endif
+
+ ret = pblk_submit_io(pblk, rqd);
+ if (ret) {
+ pr_err("pblk: I/O submission failed: %d\n", ret);
+ goto err;
+ }
+
+ mempool_free(recovery, pblk->rec_pool);
+ return;
+
+err:
+ bio_put(bio);
+ pblk_free_rqd(pblk, rqd, WRITE);
+}
+
+int pblk_recov_setup_rq(struct pblk *pblk, struct pblk_c_ctx *c_ctx,
+ struct pblk_rec_ctx *recovery, u64 *comp_bits,
+ unsigned int comp)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ int max_secs = nvm_max_phys_sects(dev);
+ struct nvm_rq *rec_rqd;
+ struct pblk_c_ctx *rec_ctx;
+ int nr_entries = c_ctx->nr_valid + c_ctx->nr_padded;
+
+ rec_rqd = pblk_alloc_rqd(pblk, WRITE);
+ if (IS_ERR(rec_rqd)) {
+ pr_err("pblk: could not create recovery req.\n");
+ return -ENOMEM;
+ }
+
+ rec_ctx = nvm_rq_to_pdu(rec_rqd);
+
+ /* Copy completion bitmap, but exclude the first X completed entries */
+ bitmap_shift_right((unsigned long int *)&rec_rqd->ppa_status,
+ (unsigned long int *)comp_bits,
+ comp, max_secs);
+
+ /* Save the context for the entries that need to be re-written and
+ * update current context with the completed entries.
+ */
+ rec_ctx->sentry = pblk_rb_wrap_pos(&pblk->rwb, c_ctx->sentry + comp);
+ if (comp >= c_ctx->nr_valid) {
+ rec_ctx->nr_valid = 0;
+ rec_ctx->nr_padded = nr_entries - comp;
+
+ c_ctx->nr_padded = comp - c_ctx->nr_valid;
+ } else {
+ rec_ctx->nr_valid = c_ctx->nr_valid - comp;
+ rec_ctx->nr_padded = c_ctx->nr_padded;
+
+ c_ctx->nr_valid = comp;
+ c_ctx->nr_padded = 0;
+ }
+
+ recovery->rqd = rec_rqd;
+ recovery->pblk = pblk;
+
+ return 0;
+}
+
+__le64 *pblk_recov_get_lba_list(struct pblk *pblk, struct line_emeta *emeta)
+{
+ u32 crc;
+
+ crc = pblk_calc_emeta_crc(pblk, emeta);
+ if (le32_to_cpu(emeta->crc) != crc)
+ return NULL;
+
+ if (le32_to_cpu(emeta->header.identifier) != PBLK_MAGIC)
+ return NULL;
+
+ return pblk_line_emeta_to_lbas(emeta);
+}
+
+static int pblk_recov_l2p_from_emeta(struct pblk *pblk, struct pblk_line *line)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct line_emeta *emeta = line->emeta;
+ __le64 *lba_list;
+ int data_start;
+ int nr_data_lbas, nr_valid_lbas, nr_lbas = 0;
+ int i;
+
+ lba_list = pblk_recov_get_lba_list(pblk, emeta);
+ if (!lba_list)
+ return 1;
+
+ data_start = pblk_line_smeta_start(pblk, line) + lm->smeta_sec;
+ nr_data_lbas = lm->sec_per_line - lm->emeta_sec;
+ nr_valid_lbas = le64_to_cpu(emeta->nr_valid_lbas);
+
+ for (i = data_start; i < nr_data_lbas && nr_lbas < nr_valid_lbas; i++) {
+ struct ppa_addr ppa;
+ int pos;
+
+ ppa = addr_to_pblk_ppa(pblk, i, line->id);
+ pos = pblk_ppa_to_pos(geo, ppa);
+
+ /* Do not update bad blocks */
+ if (test_bit(pos, line->blk_bitmap))
+ continue;
+
+ if (le64_to_cpu(lba_list[i]) == ADDR_EMPTY) {
+ spin_lock(&line->lock);
+ if (test_and_set_bit(i, line->invalid_bitmap))
+ WARN_ONCE(1, "pblk: rec. double invalidate:\n");
+ else
+ line->vsc--;
+ spin_unlock(&line->lock);
+
+ continue;
+ }
+
+ pblk_update_map(pblk, le64_to_cpu(lba_list[i]), ppa);
+ nr_lbas++;
+ }
+
+ if (nr_valid_lbas != nr_lbas)
+ pr_err("pblk: line %d - inconsistent lba list(%llu/%d)\n",
+ line->id, line->emeta->nr_valid_lbas, nr_lbas);
+
+ line->left_msecs = 0;
+
+ return 0;
+}
+
+static int pblk_calc_sec_in_line(struct pblk *pblk, struct pblk_line *line)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_line_meta *lm = &pblk->lm;
+ int nr_bb = bitmap_weight(line->blk_bitmap, lm->blk_per_line);
+
+ return lm->sec_per_line - lm->smeta_sec - lm->emeta_sec -
+ nr_bb * geo->sec_per_blk;
+}
+
+struct pblk_recov_alloc {
+ struct ppa_addr *ppa_list;
+ struct pblk_sec_meta *meta_list;
+ struct nvm_rq *rqd;
+ void *data;
+ dma_addr_t dma_ppa_list;
+ dma_addr_t dma_meta_list;
+};
+
+static int pblk_recov_read_oob(struct pblk *pblk, struct pblk_line *line,
+ struct pblk_recov_alloc p, u64 r_ptr)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct ppa_addr *ppa_list;
+ struct pblk_sec_meta *meta_list;
+ struct nvm_rq *rqd;
+ struct bio *bio;
+ void *data;
+ dma_addr_t dma_ppa_list, dma_meta_list;
+ u64 r_ptr_int;
+ int left_ppas;
+ int rq_ppas, rq_len;
+ int i, j;
+ int ret = 0;
+ DECLARE_COMPLETION_ONSTACK(wait);
+
+ ppa_list = p.ppa_list;
+ meta_list = p.meta_list;
+ rqd = p.rqd;
+ data = p.data;
+ dma_ppa_list = p.dma_ppa_list;
+ dma_meta_list = p.dma_meta_list;
+
+ left_ppas = line->cur_sec - r_ptr;
+ if (!left_ppas)
+ return 0;
+
+ r_ptr_int = r_ptr;
+
+next_read_rq:
+ memset(rqd, 0, pblk_r_rq_size);
+
+ rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
+ if (!rq_ppas)
+ rq_ppas = pblk->min_write_pgs;
+ rq_len = rq_ppas * geo->sec_size;
+
+ bio = bio_map_kern(dev->q, data, rq_len, GFP_KERNEL);
+ if (IS_ERR(bio))
+ return PTR_ERR(bio);
+
+ bio->bi_iter.bi_sector = 0; /* internal bio */
+ bio_set_op_attrs(bio, REQ_OP_READ, 0);
+
+ rqd->bio = bio;
+ rqd->opcode = NVM_OP_PREAD;
+ rqd->flags = pblk_set_read_mode(pblk);
+ rqd->meta_list = meta_list;
+ rqd->nr_ppas = rq_ppas;
+ rqd->ppa_list = ppa_list;
+ rqd->dma_ppa_list = dma_ppa_list;
+ rqd->dma_meta_list = dma_meta_list;
+ rqd->end_io = pblk_end_io_sync;
+ rqd->private = &wait;
+
+ for (i = 0; i < rqd->nr_ppas; ) {
+ struct ppa_addr ppa;
+ int pos;
+
+ ppa = addr_to_gen_ppa(pblk, r_ptr_int, line->id);
+ pos = pblk_dev_ppa_to_pos(geo, ppa);
+
+ while (test_bit(pos, line->blk_bitmap)) {
+ r_ptr_int += pblk->min_write_pgs;
+ ppa = addr_to_gen_ppa(pblk, r_ptr_int, line->id);
+ pos = pblk_dev_ppa_to_pos(geo, ppa);
+ }
+
+ for (j = 0; j < pblk->min_write_pgs; j++, i++, r_ptr_int++)
+ rqd->ppa_list[i] =
+ addr_to_gen_ppa(pblk, r_ptr_int, line->id);
+ }
+
+ /* If read fails, more padding is needed */
+ ret = pblk_submit_io(pblk, rqd);
+ if (ret) {
+ pr_err("pblk: I/O submission failed: %d\n", ret);
+ return ret;
+ }
+
+ if (!wait_for_completion_io_timeout(&wait,
+ msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+ pr_err("pblk: L2P recovery read timed out\n");
+ return -EINTR;
+ }
+
+ reinit_completion(&wait);
+
+ /* At this point, the read should not fail. If it does, it is a problem
+ * we cannot recover from here. Need FTL log.
+ */
+ if (rqd->error) {
+ pr_err("pblk: L2P recovery failed (%d)\n", rqd->error);
+ return -EINTR;
+ }
+
+ for (i = 0; i < rqd->nr_ppas; i++) {
+ u64 lba = le64_to_cpu(meta_list[i].lba);
+
+ if (lba == ADDR_EMPTY || lba > pblk->rl.nr_secs)
+ continue;
+
+ pblk_update_map(pblk, lba, rqd->ppa_list[i]);
+ }
+
+ left_ppas -= rq_ppas;
+ if (left_ppas > 0)
+ goto next_read_rq;
+
+ return 0;
+}
+
+static int pblk_recov_pad_oob(struct pblk *pblk, struct pblk_line *line,
+ struct pblk_recov_alloc p, int left_ppas)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct ppa_addr *ppa_list;
+ struct pblk_sec_meta *meta_list;
+ struct nvm_rq *rqd;
+ struct bio *bio;
+ void *data;
+ dma_addr_t dma_ppa_list, dma_meta_list;
+ __le64 *lba_list = pblk_line_emeta_to_lbas(line->emeta);
+ u64 w_ptr = line->cur_sec;
+ int left_line_ppas = line->left_msecs;
+ int rq_ppas, rq_len;
+ int i, j;
+ int ret = 0;
+ DECLARE_COMPLETION_ONSTACK(wait);
+
+ ppa_list = p.ppa_list;
+ meta_list = p.meta_list;
+ rqd = p.rqd;
+ data = p.data;
+ dma_ppa_list = p.dma_ppa_list;
+ dma_meta_list = p.dma_meta_list;
+
+next_pad_rq:
+ rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
+ if (!rq_ppas)
+ rq_ppas = pblk->min_write_pgs;
+ rq_len = rq_ppas * geo->sec_size;
+
+ bio = bio_map_kern(dev->q, data, rq_len, GFP_KERNEL);
+ if (IS_ERR(bio))
+ return PTR_ERR(bio);
+
+ bio->bi_iter.bi_sector = 0; /* internal bio */
+ bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+
+ memset(rqd, 0, pblk_r_rq_size);
+
+ rqd->bio = bio;
+ rqd->opcode = NVM_OP_PWRITE;
+ rqd->flags = pblk_set_progr_mode(pblk, WRITE);
+ rqd->meta_list = meta_list;
+ rqd->nr_ppas = rq_ppas;
+ rqd->ppa_list = ppa_list;
+ rqd->dma_ppa_list = dma_ppa_list;
+ rqd->dma_meta_list = dma_meta_list;
+ rqd->end_io = pblk_end_io_sync;
+ rqd->private = &wait;
+
+ for (i = 0; i < rqd->nr_ppas; ) {
+ struct ppa_addr ppa;
+ int pos;
+
+ w_ptr = pblk_alloc_page(pblk, line, pblk->min_write_pgs);
+ ppa = addr_to_pblk_ppa(pblk, w_ptr, line->id);
+ pos = pblk_ppa_to_pos(geo, ppa);
+
+ while (test_bit(pos, line->blk_bitmap)) {
+ w_ptr += pblk->min_write_pgs;
+ ppa = addr_to_pblk_ppa(pblk, w_ptr, line->id);
+ pos = pblk_ppa_to_pos(geo, ppa);
+ }
+
+ for (j = 0; j < pblk->min_write_pgs; j++, i++, w_ptr++) {
+ struct ppa_addr dev_ppa;
+
+ dev_ppa = addr_to_gen_ppa(pblk, w_ptr, line->id);
+
+ pblk_map_invalidate(pblk, dev_ppa);
+ meta_list[i].lba = cpu_to_le64(ADDR_EMPTY);
+ lba_list[w_ptr] = cpu_to_le64(ADDR_EMPTY);
+ rqd->ppa_list[i] = dev_ppa;
+ }
+ }
+
+ ret = pblk_submit_io(pblk, rqd);
+ if (ret) {
+ pr_err("pblk: I/O submission failed: %d\n", ret);
+ return ret;
+ }
+
+ if (!wait_for_completion_io_timeout(&wait,
+ msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+ pr_err("pblk: L2P recovery write timed out\n");
+ }
+ reinit_completion(&wait);
+
+ left_line_ppas -= rq_ppas;
+ left_ppas -= rq_ppas;
+ if (left_ppas > 0 && left_line_ppas)
+ goto next_pad_rq;
+
+ return 0;
+}
+
+/* When this function is called, it means that not all upper pages have been
+ * written in a page that contains valid data. In order to recover this data, we
+ * first find the write pointer on the device, then we pad all necessary
+ * sectors, and finally attempt to read the valid data
+ */
+static int pblk_recov_scan_all_oob(struct pblk *pblk, struct pblk_line *line,
+ struct pblk_recov_alloc p)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct ppa_addr *ppa_list;
+ struct pblk_sec_meta *meta_list;
+ struct nvm_rq *rqd;
+ struct bio *bio;
+ void *data;
+ dma_addr_t dma_ppa_list, dma_meta_list;
+ u64 w_ptr = 0, r_ptr;
+ int rq_ppas, rq_len;
+ int i, j;
+ int ret = 0;
+ int rec_round;
+ int left_ppas = pblk_calc_sec_in_line(pblk, line) - line->cur_sec;
+ DECLARE_COMPLETION_ONSTACK(wait);
+
+ ppa_list = p.ppa_list;
+ meta_list = p.meta_list;
+ rqd = p.rqd;
+ data = p.data;
+ dma_ppa_list = p.dma_ppa_list;
+ dma_meta_list = p.dma_meta_list;
+
+ /* we could recover up until the line write pointer */
+ r_ptr = line->cur_sec;
+ rec_round = 0;
+
+next_rq:
+ memset(rqd, 0, pblk_r_rq_size);
+
+ rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
+ if (!rq_ppas)
+ rq_ppas = pblk->min_write_pgs;
+ rq_len = rq_ppas * geo->sec_size;
+
+ bio = bio_map_kern(dev->q, data, rq_len, GFP_KERNEL);
+ if (IS_ERR(bio))
+ return PTR_ERR(bio);
+
+ bio->bi_iter.bi_sector = 0; /* internal bio */
+ bio_set_op_attrs(bio, REQ_OP_READ, 0);
+
+ rqd->bio = bio;
+ rqd->opcode = NVM_OP_PREAD;
+ rqd->flags = pblk_set_read_mode(pblk);
+ rqd->meta_list = meta_list;
+ rqd->nr_ppas = rq_ppas;
+ rqd->ppa_list = ppa_list;
+ rqd->dma_ppa_list = dma_ppa_list;
+ rqd->dma_meta_list = dma_meta_list;
+ rqd->end_io = pblk_end_io_sync;
+ rqd->private = &wait;
+
+ for (i = 0; i < rqd->nr_ppas; ) {
+ struct ppa_addr ppa;
+ int pos;
+
+ w_ptr = pblk_alloc_page(pblk, line, pblk->min_write_pgs);
+ ppa = addr_to_gen_ppa(pblk, w_ptr, line->id);
+ pos = pblk_dev_ppa_to_pos(geo, ppa);
+
+ while (test_bit(pos, line->blk_bitmap)) {
+ w_ptr += pblk->min_write_pgs;
+ ppa = addr_to_gen_ppa(pblk, w_ptr, line->id);
+ pos = pblk_dev_ppa_to_pos(geo, ppa);
+ }
+
+ for (j = 0; j < pblk->min_write_pgs; j++, i++, w_ptr++)
+ rqd->ppa_list[i] =
+ addr_to_gen_ppa(pblk, w_ptr, line->id);
+ }
+
+ ret = pblk_submit_io(pblk, rqd);
+ if (ret) {
+ pr_err("pblk: I/O submission failed: %d\n", ret);
+ return ret;
+ }
+
+ if (!wait_for_completion_io_timeout(&wait,
+ msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+ pr_err("pblk: L2P recovery read timed out\n");
+ }
+ reinit_completion(&wait);
+
+ /* This should not happen since the read failed during normal recovery,
+ * but the media works funny sometimes...
+ */
+ if (!rec_round++ && !rqd->error) {
+ rec_round = 0;
+ for (i = 0; i < rqd->nr_ppas; i++, r_ptr++) {
+ u64 lba = le64_to_cpu(meta_list[i].lba);
+
+ if (lba == ADDR_EMPTY || lba > pblk->rl.nr_secs)
+ continue;
+
+ pblk_update_map(pblk, lba, rqd->ppa_list[i]);
+ }
+ }
+
+ /* Reached the end of the written line */
+ if (rqd->error == NVM_RSP_ERR_EMPTYPAGE) {
+ int pad_secs, nr_error_bits, bit;
+ int ret;
+
+ bit = find_first_bit((void *)&rqd->ppa_status, rqd->nr_ppas);
+ nr_error_bits = rqd->nr_ppas - bit;
+
+ /* Roll back failed sectors */
+ line->cur_sec -= nr_error_bits;
+ line->left_msecs += nr_error_bits;
+ bitmap_clear(line->map_bitmap, line->cur_sec, nr_error_bits);
+
+ pad_secs = pblk_pad_distance(pblk);
+ if (pad_secs > line->left_msecs)
+ pad_secs = line->left_msecs;
+
+ ret = pblk_recov_pad_oob(pblk, line, p, pad_secs);
+ if (ret)
+ pr_err("pblk: OOB padding failed (err:%d)\n", ret);
+
+ ret = pblk_recov_read_oob(pblk, line, p, r_ptr);
+ if (ret)
+ pr_err("pblk: OOB read failed (err:%d)\n", ret);
+
+ line->left_ssecs = line->left_msecs;
+ left_ppas = 0;
+ }
+
+ left_ppas -= rq_ppas;
+ if (left_ppas > 0)
+ goto next_rq;
+
+ return ret;
+}
+
+static int pblk_recov_scan_oob(struct pblk *pblk, struct pblk_line *line,
+ struct pblk_recov_alloc p, int *done)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct ppa_addr *ppa_list;
+ struct pblk_sec_meta *meta_list;
+ struct nvm_rq *rqd;
+ struct bio *bio;
+ void *data;
+ dma_addr_t dma_ppa_list, dma_meta_list;
+ u64 paddr;
+ int rq_ppas, rq_len;
+ int i, j;
+ int ret = 0;
+ int left_ppas = pblk_calc_sec_in_line(pblk, line);
+ DECLARE_COMPLETION_ONSTACK(wait);
+
+ ppa_list = p.ppa_list;
+ meta_list = p.meta_list;
+ rqd = p.rqd;
+ data = p.data;
+ dma_ppa_list = p.dma_ppa_list;
+ dma_meta_list = p.dma_meta_list;
+
+ *done = 1;
+
+next_rq:
+ memset(rqd, 0, pblk_r_rq_size);
+
+ rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
+ if (!rq_ppas)
+ rq_ppas = pblk->min_write_pgs;
+ rq_len = rq_ppas * geo->sec_size;
+
+ bio = bio_map_kern(dev->q, data, rq_len, GFP_KERNEL);
+ if (IS_ERR(bio))
+ return PTR_ERR(bio);
+
+ bio->bi_iter.bi_sector = 0; /* internal bio */
+ bio_set_op_attrs(bio, REQ_OP_READ, 0);
+
+ rqd->bio = bio;
+ rqd->opcode = NVM_OP_PREAD;
+ rqd->flags = pblk_set_read_mode(pblk);
+ rqd->meta_list = meta_list;
+ rqd->nr_ppas = rq_ppas;
+ rqd->ppa_list = ppa_list;
+ rqd->dma_ppa_list = dma_ppa_list;
+ rqd->dma_meta_list = dma_meta_list;
+ rqd->end_io = pblk_end_io_sync;
+ rqd->private = &wait;
+
+ for (i = 0; i < rqd->nr_ppas; ) {
+ struct ppa_addr ppa;
+ int pos;
+
+ paddr = pblk_alloc_page(pblk, line, pblk->min_write_pgs);
+ ppa = addr_to_gen_ppa(pblk, paddr, line->id);
+ pos = pblk_dev_ppa_to_pos(geo, ppa);
+
+ while (test_bit(pos, line->blk_bitmap)) {
+ paddr += pblk->min_write_pgs;
+ ppa = addr_to_gen_ppa(pblk, paddr, line->id);
+ pos = pblk_dev_ppa_to_pos(geo, ppa);
+ }
+
+ for (j = 0; j < pblk->min_write_pgs; j++, i++, paddr++)
+ rqd->ppa_list[i] =
+ addr_to_gen_ppa(pblk, paddr, line->id);
+ }
+
+ ret = pblk_submit_io(pblk, rqd);
+ if (ret) {
+ pr_err("pblk: I/O submission failed: %d\n", ret);
+ bio_put(bio);
+ return ret;
+ }
+
+ if (!wait_for_completion_io_timeout(&wait,
+ msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+ pr_err("pblk: L2P recovery read timed out\n");
+ }
+ reinit_completion(&wait);
+
+ /* Reached the end of the written line */
+ if (rqd->error) {
+ int nr_error_bits, bit;
+
+ bit = find_first_bit((void *)&rqd->ppa_status, rqd->nr_ppas);
+ nr_error_bits = rqd->nr_ppas - bit;
+
+ /* Roll back failed sectors */
+ line->cur_sec -= nr_error_bits;
+ line->left_msecs += nr_error_bits;
+ line->left_ssecs = line->left_msecs;
+ bitmap_clear(line->map_bitmap, line->cur_sec, nr_error_bits);
+
+ left_ppas = 0;
+ rqd->nr_ppas = bit;
+
+ if (rqd->error != NVM_RSP_ERR_EMPTYPAGE)
+ *done = 0;
+ }
+
+ for (i = 0; i < rqd->nr_ppas; i++) {
+ u64 lba = le64_to_cpu(meta_list[i].lba);
+
+ if (lba == ADDR_EMPTY || lba > pblk->rl.nr_secs)
+ continue;
+
+ pblk_update_map(pblk, lba, rqd->ppa_list[i]);
+ }
+
+ left_ppas -= rq_ppas;
+ if (left_ppas > 0)
+ goto next_rq;
+
+ return ret;
+}
+
+/* Scan line for lbas on out of bound area */
+static int pblk_recov_l2p_from_oob(struct pblk *pblk, struct pblk_line *line)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct nvm_rq *rqd;
+ struct ppa_addr *ppa_list;
+ struct pblk_sec_meta *meta_list;
+ struct pblk_recov_alloc p;
+ void *data;
+ dma_addr_t dma_ppa_list, dma_meta_list;
+ int done, ret = 0;
+
+ rqd = pblk_alloc_rqd(pblk, READ);
+ if (IS_ERR(rqd))
+ return PTR_ERR(rqd);
+
+ meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, &dma_meta_list);
+ if (!meta_list) {
+ ret = -ENOMEM;
+ goto free_rqd;
+ }
+
+ ppa_list = (void *)(meta_list) + pblk_dma_meta_size;
+ dma_ppa_list = dma_meta_list + pblk_dma_meta_size;
+
+ data = kcalloc(pblk->max_write_pgs, geo->sec_size, GFP_KERNEL);
+ if (!data) {
+ ret = -ENOMEM;
+ goto free_meta_list;
+ }
+
+ p.ppa_list = ppa_list;
+ p.meta_list = meta_list;
+ p.rqd = rqd;
+ p.data = data;
+ p.dma_ppa_list = dma_ppa_list;
+ p.dma_meta_list = dma_meta_list;
+
+ ret = pblk_recov_scan_oob(pblk, line, p, &done);
+ if (ret) {
+ pr_err("pblk: could not recover L2P from OOB\n");
+ goto out;
+ }
+
+ if (!done) {
+ ret = pblk_recov_scan_all_oob(pblk, line, p);
+ if (ret) {
+ pr_err("pblk: could not recover L2P from OOB\n");
+ goto out;
+ }
+ }
+
+ if (pblk_line_is_full(line))
+ pblk_line_recov_close(pblk, line);
+
+out:
+ kfree(data);
+free_meta_list:
+ nvm_dev_dma_free(dev->parent, meta_list, dma_meta_list);
+free_rqd:
+ pblk_free_rqd(pblk, rqd, READ);
+
+ return ret;
+}
+
+/* Insert lines ordered by sequence number (seq_num) on list */
+static void pblk_recov_line_add_ordered(struct list_head *head,
+ struct pblk_line *line)
+{
+ struct pblk_line *t = NULL;
+
+ list_for_each_entry(t, head, list)
+ if (t->seq_nr > line->seq_nr)
+ break;
+
+ __list_add(&line->list, t->list.prev, &t->list);
+}
+
+struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct pblk_line *line, *tline, *data_line = NULL;
+ struct line_smeta *smeta;
+ struct line_emeta *emeta;
+ int found_lines = 0, recovered_lines = 0, open_lines = 0;
+ int is_next = 0;
+ int meta_line;
+ int i, valid_uuid = 0;
+ LIST_HEAD(recov_list);
+
+ /* TODO: Implement FTL snapshot */
+
+ /* Scan recovery - takes place when FTL snapshot fails */
+ spin_lock(&l_mg->free_lock);
+ meta_line = find_first_zero_bit(&l_mg->meta_bitmap, PBLK_DATA_LINES);
+ set_bit(meta_line, &l_mg->meta_bitmap);
+ smeta = l_mg->sline_meta[meta_line].meta;
+ emeta = l_mg->eline_meta[meta_line].meta;
+ spin_unlock(&l_mg->free_lock);
+
+ /* Order data lines using their sequence number */
+ for (i = 0; i < l_mg->nr_lines; i++) {
+ u32 crc;
+
+ line = &pblk->lines[i];
+
+ memset(smeta, 0, lm->smeta_len);
+ line->smeta = smeta;
+ line->lun_bitmap = ((void *)(smeta)) +
+ sizeof(struct line_smeta);
+
+ /* Lines that cannot be read are assumed as not written here */
+ if (pblk_line_read_smeta(pblk, line))
+ continue;
+
+ crc = pblk_calc_smeta_crc(pblk, smeta);
+ if (le32_to_cpu(smeta->crc) != crc)
+ continue;
+
+ if (le32_to_cpu(smeta->header.identifier) != PBLK_MAGIC)
+ continue;
+
+ if (le16_to_cpu(smeta->header.version) != 1) {
+ pr_err("pblk: found incompatible line version %u\n",
+ smeta->header.version);
+ return ERR_PTR(-EINVAL);
+ }
+
+ /* The first valid instance uuid is used for initialization */
+ if (!valid_uuid) {
+ memcpy(pblk->instance_uuid, smeta->header.uuid, 16);
+ valid_uuid = 1;
+ }
+
+ if (memcmp(pblk->instance_uuid, smeta->header.uuid, 16)) {
+ pr_debug("pblk: ignore line %u due to uuid mismatch\n",
+ i);
+ continue;
+ }
+
+ /* Update line metadata */
+ spin_lock(&line->lock);
+ line->id = le32_to_cpu(line->smeta->header.id);
+ line->type = le16_to_cpu(line->smeta->header.type);
+ line->seq_nr = le64_to_cpu(line->smeta->seq_nr);
+ spin_unlock(&line->lock);
+
+ /* Update general metadata */
+ spin_lock(&l_mg->free_lock);
+ if (line->seq_nr >= l_mg->d_seq_nr)
+ l_mg->d_seq_nr = line->seq_nr + 1;
+ l_mg->nr_free_lines--;
+ spin_unlock(&l_mg->free_lock);
+
+ if (pblk_line_recov_alloc(pblk, line))
+ goto out;
+
+ pblk_recov_line_add_ordered(&recov_list, line);
+ found_lines++;
+ pr_debug("pblk: recovering data line %d, seq:%llu\n",
+ line->id, smeta->seq_nr);
+ }
+
+ if (!found_lines) {
+ pblk_setup_uuid(pblk);
+
+ spin_lock(&l_mg->free_lock);
+ WARN_ON_ONCE(!test_and_clear_bit(meta_line,
+ &l_mg->meta_bitmap));
+ spin_unlock(&l_mg->free_lock);
+
+ goto out;
+ }
+
+ /* Verify closed blocks and recover this portion of L2P table*/
+ list_for_each_entry_safe(line, tline, &recov_list, list) {
+ int off, nr_bb;
+
+ recovered_lines++;
+ /* Calculate where emeta starts based on the line bb */
+ off = lm->sec_per_line - lm->emeta_sec;
+ nr_bb = bitmap_weight(line->blk_bitmap, lm->blk_per_line);
+ off -= nr_bb * geo->sec_per_pl;
+
+ memset(emeta, 0, lm->emeta_len);
+ line->emeta = emeta;
+ line->emeta_ssec = off;
+
+ if (pblk_line_read_emeta(pblk, line)) {
+ pblk_recov_l2p_from_oob(pblk, line);
+ goto next;
+ }
+
+ if (pblk_recov_l2p_from_emeta(pblk, line))
+ pblk_recov_l2p_from_oob(pblk, line);
+
+next:
+ if (pblk_line_is_full(line)) {
+ struct list_head *move_list;
+
+ spin_lock(&line->lock);
+ line->state = PBLK_LINESTATE_CLOSED;
+ move_list = pblk_line_gc_list(pblk, line);
+ spin_unlock(&line->lock);
+
+ spin_lock(&l_mg->gc_lock);
+ list_move_tail(&line->list, move_list);
+ spin_unlock(&l_mg->gc_lock);
+
+ mempool_free(line->map_bitmap, pblk->line_meta_pool);
+ line->map_bitmap = NULL;
+ line->smeta = NULL;
+ line->emeta = NULL;
+ } else {
+ if (open_lines > 1)
+ pr_err("pblk: failed to recover L2P\n");
+
+ open_lines++;
+ line->meta_line = meta_line;
+ data_line = line;
+ }
+ }
+
+ spin_lock(&l_mg->free_lock);
+ if (!open_lines) {
+ WARN_ON_ONCE(!test_and_clear_bit(meta_line,
+ &l_mg->meta_bitmap));
+ pblk_line_replace_data(pblk);
+ } else {
+ /* Allocate next line for preparation */
+ l_mg->data_next = pblk_line_get(pblk);
+ if (l_mg->data_next) {
+ l_mg->data_next->seq_nr = l_mg->d_seq_nr++;
+ l_mg->data_next->type = PBLK_LINETYPE_DATA;
+ is_next = 1;
+ }
+ }
+ spin_unlock(&l_mg->free_lock);
+
+ if (is_next) {
+ pblk_line_erase(pblk, l_mg->data_next);
+ pblk_rl_free_lines_dec(&pblk->rl, l_mg->data_next);
+ }
+
+out:
+ if (found_lines != recovered_lines)
+ pr_err("pblk: failed to recover all found lines %d/%d\n",
+ found_lines, recovered_lines);
+
+ return data_line;
+}
+
+/*
+ * Pad until smeta can be read on current data line
+ */
+void pblk_recov_pad(struct pblk *pblk)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_line *line;
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct nvm_rq *rqd;
+ struct pblk_recov_alloc p;
+ struct ppa_addr *ppa_list;
+ struct pblk_sec_meta *meta_list;
+ void *data;
+ dma_addr_t dma_ppa_list, dma_meta_list;
+
+ spin_lock(&l_mg->free_lock);
+ line = l_mg->data_line;
+ spin_unlock(&l_mg->free_lock);
+
+ rqd = pblk_alloc_rqd(pblk, READ);
+ if (IS_ERR(rqd))
+ return;
+
+ meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, &dma_meta_list);
+ if (!meta_list)
+ goto free_rqd;
+
+ ppa_list = (void *)(meta_list) + pblk_dma_meta_size;
+ dma_ppa_list = dma_meta_list + pblk_dma_meta_size;
+
+ data = kcalloc(pblk->max_write_pgs, geo->sec_size, GFP_KERNEL);
+ if (!data)
+ goto free_meta_list;
+
+ p.ppa_list = ppa_list;
+ p.meta_list = meta_list;
+ p.rqd = rqd;
+ p.data = data;
+ p.dma_ppa_list = dma_ppa_list;
+ p.dma_meta_list = dma_meta_list;
+
+ if (pblk_recov_pad_oob(pblk, line, p, line->left_msecs)) {
+ pr_err("pblk: Tear down padding failed\n");
+ goto free_data;
+ }
+
+ pblk_line_close(pblk, line);
+
+free_data:
+ kfree(data);
+free_meta_list:
+ nvm_dev_dma_free(dev->parent, meta_list, dma_meta_list);
+free_rqd:
+ pblk_free_rqd(pblk, rqd, READ);
+}
--- /dev/null
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ * Matias Bjorling <matias@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * pblk-rl.c - pblk's rate limiter for user I/O
+ *
+ */
+
+#include "pblk.h"
+
+static void pblk_rl_kick_u_timer(struct pblk_rl *rl)
+{
+ mod_timer(&rl->u_timer, jiffies + msecs_to_jiffies(5000));
+}
+
+int pblk_rl_user_may_insert(struct pblk_rl *rl, int nr_entries)
+{
+ int rb_user_cnt = atomic_read(&rl->rb_user_cnt);
+
+ return (!(rb_user_cnt + nr_entries > rl->rb_user_max));
+}
+
+int pblk_rl_gc_may_insert(struct pblk_rl *rl, int nr_entries)
+{
+ int rb_gc_cnt = atomic_read(&rl->rb_gc_cnt);
+ int rb_user_active;
+
+ /* If there is no user I/O let GC take over space on the write buffer */
+ rb_user_active = READ_ONCE(rl->rb_user_active);
+ return (!(rb_gc_cnt + nr_entries > rl->rb_gc_max && rb_user_active));
+}
+
+void pblk_rl_user_in(struct pblk_rl *rl, int nr_entries)
+{
+ atomic_add(nr_entries, &rl->rb_user_cnt);
+
+ /* Release user I/O state. Protect from GC */
+ smp_store_release(&rl->rb_user_active, 1);
+ pblk_rl_kick_u_timer(rl);
+}
+
+void pblk_rl_gc_in(struct pblk_rl *rl, int nr_entries)
+{
+ atomic_add(nr_entries, &rl->rb_gc_cnt);
+}
+
+void pblk_rl_out(struct pblk_rl *rl, int nr_user, int nr_gc)
+{
+ atomic_sub(nr_user, &rl->rb_user_cnt);
+ atomic_sub(nr_gc, &rl->rb_gc_cnt);
+}
+
+unsigned long pblk_rl_nr_free_blks(struct pblk_rl *rl)
+{
+ return atomic_read(&rl->free_blocks);
+}
+
+/*
+ * We check for (i) the number of free blocks in the current LUN and (ii) the
+ * total number of free blocks in the pblk instance. This is to even out the
+ * number of free blocks on each LUN when GC kicks in.
+ *
+ * Only the total number of free blocks is used to configure the rate limiter.
+ */
+static int pblk_rl_update_rates(struct pblk_rl *rl, unsigned long max)
+{
+ unsigned long free_blocks = pblk_rl_nr_free_blks(rl);
+
+ if (free_blocks >= rl->high) {
+ rl->rb_user_max = max - rl->rb_gc_rsv;
+ rl->rb_gc_max = rl->rb_gc_rsv;
+ rl->rb_state = PBLK_RL_HIGH;
+ } else if (free_blocks < rl->high) {
+ int shift = rl->high_pw - rl->rb_windows_pw;
+ int user_windows = free_blocks >> shift;
+ int user_max = user_windows << PBLK_MAX_REQ_ADDRS_PW;
+ int gc_max;
+
+ rl->rb_user_max = user_max;
+ gc_max = max - rl->rb_user_max;
+ rl->rb_gc_max = max(gc_max, rl->rb_gc_rsv);
+
+ if (free_blocks > rl->low)
+ rl->rb_state = PBLK_RL_MID;
+ else
+ rl->rb_state = PBLK_RL_LOW;
+ }
+
+ return rl->rb_state;
+}
+
+void pblk_rl_set_gc_rsc(struct pblk_rl *rl, int rsv)
+{
+ rl->rb_gc_rsv = rl->rb_gc_max = rsv;
+}
+
+void pblk_rl_free_lines_inc(struct pblk_rl *rl, struct pblk_line *line)
+{
+ struct pblk *pblk = container_of(rl, struct pblk, rl);
+ int blk_in_line = atomic_read(&line->blk_in_line);
+ int ret;
+
+ atomic_add(blk_in_line, &rl->free_blocks);
+ /* Rates will not change that often - no need to lock update */
+ ret = pblk_rl_update_rates(rl, rl->rb_budget);
+
+ if (ret == (PBLK_RL_MID | PBLK_RL_LOW))
+ pblk_gc_should_start(pblk);
+ else
+ pblk_gc_should_stop(pblk);
+}
+
+void pblk_rl_free_lines_dec(struct pblk_rl *rl, struct pblk_line *line)
+{
+ struct pblk *pblk = container_of(rl, struct pblk, rl);
+ int blk_in_line = atomic_read(&line->blk_in_line);
+ int ret;
+
+ atomic_sub(blk_in_line, &rl->free_blocks);
+
+ /* Rates will not change that often - no need to lock update */
+ ret = pblk_rl_update_rates(rl, rl->rb_budget);
+ if (ret == (PBLK_RL_MID | PBLK_RL_LOW))
+ pblk_gc_should_start(pblk);
+ else
+ pblk_gc_should_stop(pblk);
+}
+
+int pblk_rl_gc_thrs(struct pblk_rl *rl)
+{
+ return rl->high;
+}
+
+int pblk_rl_sysfs_rate_show(struct pblk_rl *rl)
+{
+ return rl->rb_user_max;
+}
+
+static void pblk_rl_u_timer(unsigned long data)
+{
+ struct pblk_rl *rl = (struct pblk_rl *)data;
+
+ /* Release user I/O state. Protect from GC */
+ smp_store_release(&rl->rb_user_active, 0);
+}
+
+void pblk_rl_free(struct pblk_rl *rl)
+{
+ del_timer(&rl->u_timer);
+}
+
+void pblk_rl_init(struct pblk_rl *rl, int budget)
+{
+ unsigned int rb_windows;
+
+ rl->high = rl->total_blocks / PBLK_USER_HIGH_THRS;
+ rl->low = rl->total_blocks / PBLK_USER_LOW_THRS;
+ rl->high_pw = get_count_order(rl->high);
+
+ /* This will always be a power-of-2 */
+ rb_windows = budget / PBLK_MAX_REQ_ADDRS;
+ rl->rb_windows_pw = get_count_order(rb_windows) + 1;
+
+ /* To start with, all buffer is available to user I/O writers */
+ rl->rb_budget = budget;
+ rl->rb_user_max = budget;
+ atomic_set(&rl->rb_user_cnt, 0);
+ rl->rb_gc_max = 0;
+ rl->rb_state = PBLK_RL_HIGH;
+ atomic_set(&rl->rb_gc_cnt, 0);
+
+ setup_timer(&rl->u_timer, pblk_rl_u_timer, (unsigned long)rl);
+ rl->rb_user_active = 0;
+}
--- /dev/null
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ * Matias Bjorling <matias@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * Implementation of a physical block-device target for Open-channel SSDs.
+ *
+ * pblk-sysfs.c - pblk's sysfs
+ *
+ */
+
+#include "pblk.h"
+
+static ssize_t pblk_sysfs_luns_show(struct pblk *pblk, char *page)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_lun *rlun;
+ ssize_t sz = 0;
+ int i;
+
+ for (i = 0; i < geo->nr_luns; i++) {
+ int active = 1;
+
+ rlun = &pblk->luns[i];
+ if (!down_trylock(&rlun->wr_sem)) {
+ active = 0;
+ up(&rlun->wr_sem);
+ }
+ sz += snprintf(page + sz, PAGE_SIZE - sz,
+ "pblk: pos:%d, ch:%d, lun:%d - %d\n",
+ i,
+ rlun->bppa.g.ch,
+ rlun->bppa.g.lun,
+ active);
+ }
+
+ return sz;
+}
+
+static ssize_t pblk_sysfs_rate_limiter(struct pblk *pblk, char *page)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ int free_blocks, total_blocks;
+ int rb_user_max, rb_user_cnt;
+ int rb_gc_max, rb_gc_rsv, rb_gc_cnt, rb_budget, rb_state;
+
+ free_blocks = atomic_read(&pblk->rl.free_blocks);
+ rb_user_max = pblk->rl.rb_user_max;
+ rb_user_cnt = atomic_read(&pblk->rl.rb_user_cnt);
+ rb_gc_max = pblk->rl.rb_gc_max;
+ rb_gc_rsv = pblk->rl.rb_gc_rsv;
+ rb_gc_cnt = atomic_read(&pblk->rl.rb_gc_cnt);
+ rb_budget = pblk->rl.rb_budget;
+ rb_state = pblk->rl.rb_state;
+
+ total_blocks = geo->blks_per_lun * geo->nr_luns;
+
+ return snprintf(page, PAGE_SIZE,
+ "u:%u/%u,gc:%u/%u/%u(%u/%u)(stop:<%u,full:>%u,free:%d/%d)-%d\n",
+ rb_user_cnt,
+ rb_user_max,
+ rb_gc_cnt,
+ rb_gc_max,
+ rb_gc_rsv,
+ rb_state,
+ rb_budget,
+ pblk->rl.low,
+ pblk->rl.high,
+ free_blocks,
+ total_blocks,
+ READ_ONCE(pblk->rl.rb_user_active));
+}
+
+static ssize_t pblk_sysfs_gc_state_show(struct pblk *pblk, char *page)
+{
+ int gc_enabled, gc_active;
+
+ pblk_gc_sysfs_state_show(pblk, &gc_enabled, &gc_active);
+ return snprintf(page, PAGE_SIZE, "gc_enabled=%d, gc_active=%d\n",
+ gc_enabled, gc_active);
+}
+
+static ssize_t pblk_sysfs_stats(struct pblk *pblk, char *page)
+{
+ ssize_t sz;
+
+ sz = snprintf(page, PAGE_SIZE,
+ "read_failed=%lu, read_high_ecc=%lu, read_empty=%lu, read_failed_gc=%lu, write_failed=%lu, erase_failed=%lu\n",
+ atomic_long_read(&pblk->read_failed),
+ atomic_long_read(&pblk->read_high_ecc),
+ atomic_long_read(&pblk->read_empty),
+ atomic_long_read(&pblk->read_failed_gc),
+ atomic_long_read(&pblk->write_failed),
+ atomic_long_read(&pblk->erase_failed));
+
+ return sz;
+}
+
+static ssize_t pblk_sysfs_write_buffer(struct pblk *pblk, char *page)
+{
+ return pblk_rb_sysfs(&pblk->rwb, page);
+}
+
+static ssize_t pblk_sysfs_ppaf(struct pblk *pblk, char *page)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ ssize_t sz = 0;
+
+ sz = snprintf(page, PAGE_SIZE - sz,
+ "g:(b:%d)blk:%d/%d,pg:%d/%d,lun:%d/%d,ch:%d/%d,pl:%d/%d,sec:%d/%d\n",
+ pblk->ppaf_bitsize,
+ pblk->ppaf.blk_offset, geo->ppaf.blk_len,
+ pblk->ppaf.pg_offset, geo->ppaf.pg_len,
+ pblk->ppaf.lun_offset, geo->ppaf.lun_len,
+ pblk->ppaf.ch_offset, geo->ppaf.ch_len,
+ pblk->ppaf.pln_offset, geo->ppaf.pln_len,
+ pblk->ppaf.sec_offset, geo->ppaf.sect_len);
+
+ sz += snprintf(page + sz, PAGE_SIZE - sz,
+ "d:blk:%d/%d,pg:%d/%d,lun:%d/%d,ch:%d/%d,pl:%d/%d,sec:%d/%d\n",
+ geo->ppaf.blk_offset, geo->ppaf.blk_len,
+ geo->ppaf.pg_offset, geo->ppaf.pg_len,
+ geo->ppaf.lun_offset, geo->ppaf.lun_len,
+ geo->ppaf.ch_offset, geo->ppaf.ch_len,
+ geo->ppaf.pln_offset, geo->ppaf.pln_len,
+ geo->ppaf.sect_offset, geo->ppaf.sect_len);
+
+ return sz;
+}
+
+static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct pblk_line *line;
+ ssize_t sz = 0;
+ int nr_free_lines;
+ int cur_data, cur_log;
+ int free_line_cnt = 0, closed_line_cnt = 0;
+ int d_line_cnt = 0, l_line_cnt = 0;
+ int gc_full = 0, gc_high = 0, gc_mid = 0, gc_low = 0, gc_empty = 0;
+ int free = 0, bad = 0, cor = 0;
+ int msecs = 0, ssecs = 0, cur_sec = 0, vsc = 0, sec_in_line = 0;
+ int map_weight = 0, meta_weight = 0;
+
+ spin_lock(&l_mg->free_lock);
+ cur_data = (l_mg->data_line) ? l_mg->data_line->id : -1;
+ cur_log = (l_mg->log_line) ? l_mg->log_line->id : -1;
+ nr_free_lines = l_mg->nr_free_lines;
+
+ list_for_each_entry(line, &l_mg->free_list, list)
+ free_line_cnt++;
+ spin_unlock(&l_mg->free_lock);
+
+ spin_lock(&l_mg->gc_lock);
+ list_for_each_entry(line, &l_mg->gc_full_list, list) {
+ if (line->type == PBLK_LINETYPE_DATA)
+ d_line_cnt++;
+ else if (line->type == PBLK_LINETYPE_LOG)
+ l_line_cnt++;
+ closed_line_cnt++;
+ gc_full++;
+ }
+
+ list_for_each_entry(line, &l_mg->gc_high_list, list) {
+ if (line->type == PBLK_LINETYPE_DATA)
+ d_line_cnt++;
+ else if (line->type == PBLK_LINETYPE_LOG)
+ l_line_cnt++;
+ closed_line_cnt++;
+ gc_high++;
+ }
+
+ list_for_each_entry(line, &l_mg->gc_mid_list, list) {
+ if (line->type == PBLK_LINETYPE_DATA)
+ d_line_cnt++;
+ else if (line->type == PBLK_LINETYPE_LOG)
+ l_line_cnt++;
+ closed_line_cnt++;
+ gc_mid++;
+ }
+
+ list_for_each_entry(line, &l_mg->gc_low_list, list) {
+ if (line->type == PBLK_LINETYPE_DATA)
+ d_line_cnt++;
+ else if (line->type == PBLK_LINETYPE_LOG)
+ l_line_cnt++;
+ closed_line_cnt++;
+ gc_low++;
+ }
+
+ list_for_each_entry(line, &l_mg->gc_empty_list, list) {
+ if (line->type == PBLK_LINETYPE_DATA)
+ d_line_cnt++;
+ else if (line->type == PBLK_LINETYPE_LOG)
+ l_line_cnt++;
+ closed_line_cnt++;
+ gc_empty++;
+ }
+
+ list_for_each_entry(line, &l_mg->free_list, list)
+ free++;
+ list_for_each_entry(line, &l_mg->bad_list, list)
+ bad++;
+ list_for_each_entry(line, &l_mg->corrupt_list, list)
+ cor++;
+ spin_unlock(&l_mg->gc_lock);
+
+ spin_lock(&l_mg->free_lock);
+ if (l_mg->data_line) {
+ cur_sec = l_mg->data_line->cur_sec;
+ msecs = l_mg->data_line->left_msecs;
+ ssecs = l_mg->data_line->left_ssecs;
+ vsc = l_mg->data_line->vsc;
+ sec_in_line = l_mg->data_line->sec_in_line;
+ meta_weight = bitmap_weight(&l_mg->meta_bitmap,
+ PBLK_DATA_LINES);
+ map_weight = bitmap_weight(l_mg->data_line->map_bitmap,
+ lm->sec_per_line);
+ }
+ spin_unlock(&l_mg->free_lock);
+
+ if (nr_free_lines != free_line_cnt)
+ pr_err("pblk: corrupted free line list\n");
+
+ sz = snprintf(page, PAGE_SIZE - sz,
+ "line: nluns:%d, nblks:%d, nsecs:%d\n",
+ geo->nr_luns, lm->blk_per_line, lm->sec_per_line);
+
+ sz += snprintf(page + sz, PAGE_SIZE - sz,
+ "lines:d:%d,l:%d-f:%d(%d),b:%d,co:%d,c:%d(d:%d,l:%d)t:%d\n",
+ cur_data, cur_log,
+ free, nr_free_lines, bad, cor,
+ closed_line_cnt,
+ d_line_cnt, l_line_cnt,
+ l_mg->nr_lines);
+
+ sz += snprintf(page + sz, PAGE_SIZE - sz,
+ "GC: full:%d, high:%d, mid:%d, low:%d, empty:%d, queue:%d\n",
+ gc_full, gc_high, gc_mid, gc_low, gc_empty,
+ atomic_read(&pblk->gc.inflight_gc));
+
+ sz += snprintf(page + sz, PAGE_SIZE - sz,
+ "data (%d) cur:%d, left:%d/%d, vsc:%d, s:%d, map:%d/%d (%d)\n",
+ cur_data, cur_sec, msecs, ssecs, vsc, sec_in_line,
+ map_weight, lm->sec_per_line, meta_weight);
+
+ return sz;
+}
+
+static ssize_t pblk_sysfs_lines_info(struct pblk *pblk, char *page)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_line_meta *lm = &pblk->lm;
+ ssize_t sz = 0;
+
+ sz = snprintf(page, PAGE_SIZE - sz,
+ "smeta - len:%d, secs:%d\n",
+ lm->smeta_len, lm->smeta_sec);
+ sz += snprintf(page + sz, PAGE_SIZE - sz,
+ "emeta - len:%d, sec:%d, bb_start:%d\n",
+ lm->emeta_len, lm->emeta_sec,
+ lm->emeta_bb);
+ sz += snprintf(page + sz, PAGE_SIZE - sz,
+ "bitmap lengths: sec:%d, blk:%d, lun:%d\n",
+ lm->sec_bitmap_len,
+ lm->blk_bitmap_len,
+ lm->lun_bitmap_len);
+ sz += snprintf(page + sz, PAGE_SIZE - sz,
+ "blk_line:%d, sec_line:%d, sec_blk:%d\n",
+ lm->blk_per_line,
+ lm->sec_per_line,
+ geo->sec_per_blk);
+
+ return sz;
+}
+
+#ifdef CONFIG_NVM_DEBUG
+static ssize_t pblk_sysfs_stats_debug(struct pblk *pblk, char *page)
+{
+ return snprintf(page, PAGE_SIZE,
+ "%lu\t%lu\t%lu\t%lu\t%lu\t%lu\t%lu\t%lu\t%lu\t%lu\t%lu\t%lu\t%lu\n",
+ atomic_long_read(&pblk->inflight_writes),
+ atomic_long_read(&pblk->inflight_reads),
+ atomic_long_read(&pblk->req_writes),
+ atomic_long_read(&pblk->nr_flush),
+ atomic_long_read(&pblk->padded_writes),
+ atomic_long_read(&pblk->padded_wb),
+ atomic_long_read(&pblk->sub_writes),
+ atomic_long_read(&pblk->sync_writes),
+ atomic_long_read(&pblk->compl_writes),
+ atomic_long_read(&pblk->recov_writes),
+ atomic_long_read(&pblk->recov_gc_writes),
+ atomic_long_read(&pblk->recov_gc_reads),
+ atomic_long_read(&pblk->sync_reads));
+}
+#endif
+
+static ssize_t pblk_sysfs_rate_store(struct pblk *pblk, const char *page,
+ size_t len)
+{
+ struct pblk_gc *gc = &pblk->gc;
+ size_t c_len;
+ int value;
+
+ c_len = strcspn(page, "\n");
+ if (c_len >= len)
+ return -EINVAL;
+
+ if (kstrtouint(page, 0, &value))
+ return -EINVAL;
+
+ spin_lock(&gc->lock);
+ pblk_rl_set_gc_rsc(&pblk->rl, value);
+ spin_unlock(&gc->lock);
+
+ return len;
+}
+
+static ssize_t pblk_sysfs_gc_force(struct pblk *pblk, const char *page,
+ size_t len)
+{
+ size_t c_len;
+ int force;
+
+ c_len = strcspn(page, "\n");
+ if (c_len >= len)
+ return -EINVAL;
+
+ if (kstrtouint(page, 0, &force))
+ return -EINVAL;
+
+ if (force < 0 || force > 1)
+ return -EINVAL;
+
+ pblk_gc_sysfs_force(pblk, force);
+
+ return len;
+}
+
+static struct attribute sys_write_luns = {
+ .name = "write_luns",
+ .mode = 0444,
+};
+
+static struct attribute sys_rate_limiter_attr = {
+ .name = "rate_limiter",
+ .mode = 0444,
+};
+
+static struct attribute sys_gc_state = {
+ .name = "gc_state",
+ .mode = 0444,
+};
+
+static struct attribute sys_errors_attr = {
+ .name = "errors",
+ .mode = 0444,
+};
+
+static struct attribute sys_rb_attr = {
+ .name = "write_buffer",
+ .mode = 0444,
+};
+
+static struct attribute sys_stats_ppaf_attr = {
+ .name = "ppa_format",
+ .mode = 0444,
+};
+
+static struct attribute sys_lines_attr = {
+ .name = "lines",
+ .mode = 0444,
+};
+
+static struct attribute sys_lines_info_attr = {
+ .name = "lines_info",
+ .mode = 0444,
+};
+
+static struct attribute sys_gc_force = {
+ .name = "gc_force",
+ .mode = 0200,
+};
+
+static struct attribute sys_gc_rl_max = {
+ .name = "gc_rl_max",
+ .mode = 0200,
+};
+
+#ifdef CONFIG_NVM_DEBUG
+static struct attribute sys_stats_debug_attr = {
+ .name = "stats",
+ .mode = 0444,
+};
+#endif
+
+static struct attribute *pblk_attrs[] = {
+ &sys_write_luns,
+ &sys_rate_limiter_attr,
+ &sys_errors_attr,
+ &sys_gc_state,
+ &sys_gc_force,
+ &sys_gc_rl_max,
+ &sys_rb_attr,
+ &sys_stats_ppaf_attr,
+ &sys_lines_attr,
+ &sys_lines_info_attr,
+#ifdef CONFIG_NVM_DEBUG
+ &sys_stats_debug_attr,
+#endif
+ NULL,
+};
+
+static ssize_t pblk_sysfs_show(struct kobject *kobj, struct attribute *attr,
+ char *buf)
+{
+ struct pblk *pblk = container_of(kobj, struct pblk, kobj);
+
+ if (strcmp(attr->name, "rate_limiter") == 0)
+ return pblk_sysfs_rate_limiter(pblk, buf);
+ else if (strcmp(attr->name, "write_luns") == 0)
+ return pblk_sysfs_luns_show(pblk, buf);
+ else if (strcmp(attr->name, "gc_state") == 0)
+ return pblk_sysfs_gc_state_show(pblk, buf);
+ else if (strcmp(attr->name, "errors") == 0)
+ return pblk_sysfs_stats(pblk, buf);
+ else if (strcmp(attr->name, "write_buffer") == 0)
+ return pblk_sysfs_write_buffer(pblk, buf);
+ else if (strcmp(attr->name, "ppa_format") == 0)
+ return pblk_sysfs_ppaf(pblk, buf);
+ else if (strcmp(attr->name, "lines") == 0)
+ return pblk_sysfs_lines(pblk, buf);
+ else if (strcmp(attr->name, "lines_info") == 0)
+ return pblk_sysfs_lines_info(pblk, buf);
+#ifdef CONFIG_NVM_DEBUG
+ else if (strcmp(attr->name, "stats") == 0)
+ return pblk_sysfs_stats_debug(pblk, buf);
+#endif
+ return 0;
+}
+
+static ssize_t pblk_sysfs_store(struct kobject *kobj, struct attribute *attr,
+ const char *buf, size_t len)
+{
+ struct pblk *pblk = container_of(kobj, struct pblk, kobj);
+
+ if (strcmp(attr->name, "gc_rl_max") == 0)
+ return pblk_sysfs_rate_store(pblk, buf, len);
+ else if (strcmp(attr->name, "gc_force") == 0)
+ return pblk_sysfs_gc_force(pblk, buf, len);
+
+ return 0;
+}
+
+static const struct sysfs_ops pblk_sysfs_ops = {
+ .show = pblk_sysfs_show,
+ .store = pblk_sysfs_store,
+};
+
+static struct kobj_type pblk_ktype = {
+ .sysfs_ops = &pblk_sysfs_ops,
+ .default_attrs = pblk_attrs,
+};
+
+int pblk_sysfs_init(struct gendisk *tdisk)
+{
+ struct pblk *pblk = tdisk->private_data;
+ struct device *parent_dev = disk_to_dev(pblk->disk);
+ int ret;
+
+ ret = kobject_init_and_add(&pblk->kobj, &pblk_ktype,
+ kobject_get(&parent_dev->kobj),
+ "%s", "pblk");
+ if (ret) {
+ pr_err("pblk: could not register %s/pblk\n",
+ tdisk->disk_name);
+ return ret;
+ }
+
+ kobject_uevent(&pblk->kobj, KOBJ_ADD);
+ return 0;
+}
+
+void pblk_sysfs_exit(struct gendisk *tdisk)
+{
+ struct pblk *pblk = tdisk->private_data;
+
+ kobject_uevent(&pblk->kobj, KOBJ_REMOVE);
+ kobject_del(&pblk->kobj);
+ kobject_put(&pblk->kobj);
+}
--- /dev/null
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ * Matias Bjorling <matias@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * pblk-write.c - pblk's write path from write buffer to media
+ */
+
+#include "pblk.h"
+
+static void pblk_sync_line(struct pblk *pblk, struct pblk_line *line)
+{
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_inc(&pblk->sync_writes);
+#endif
+
+ /* Counter protected by rb sync lock */
+ line->left_ssecs--;
+ if (!line->left_ssecs)
+ pblk_line_run_ws(pblk, line, NULL, pblk_line_close_ws);
+}
+
+static unsigned long pblk_end_w_bio(struct pblk *pblk, struct nvm_rq *rqd,
+ struct pblk_c_ctx *c_ctx)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct bio *original_bio;
+ unsigned long ret;
+ int i;
+
+ for (i = 0; i < c_ctx->nr_valid; i++) {
+ struct pblk_w_ctx *w_ctx;
+ struct ppa_addr p;
+ struct pblk_line *line;
+
+ w_ctx = pblk_rb_w_ctx(&pblk->rwb, c_ctx->sentry + i);
+
+ p = rqd->ppa_list[i];
+ line = &pblk->lines[pblk_dev_ppa_to_line(p)];
+ pblk_sync_line(pblk, line);
+
+ while ((original_bio = bio_list_pop(&w_ctx->bios)))
+ bio_endio(original_bio);
+ }
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_add(c_ctx->nr_valid, &pblk->compl_writes);
+#endif
+
+ ret = pblk_rb_sync_advance(&pblk->rwb, c_ctx->nr_valid);
+
+ if (rqd->meta_list)
+ nvm_dev_dma_free(dev->parent, rqd->meta_list,
+ rqd->dma_meta_list);
+
+ bio_put(rqd->bio);
+ pblk_free_rqd(pblk, rqd, WRITE);
+
+ return ret;
+}
+
+static unsigned long pblk_end_queued_w_bio(struct pblk *pblk,
+ struct nvm_rq *rqd,
+ struct pblk_c_ctx *c_ctx)
+{
+ list_del(&c_ctx->list);
+ return pblk_end_w_bio(pblk, rqd, c_ctx);
+}
+
+static void pblk_complete_write(struct pblk *pblk, struct nvm_rq *rqd,
+ struct pblk_c_ctx *c_ctx)
+{
+ struct pblk_c_ctx *c, *r;
+ unsigned long flags;
+ unsigned long pos;
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_sub(c_ctx->nr_valid, &pblk->inflight_writes);
+#endif
+
+ pblk_up_rq(pblk, rqd->ppa_list, rqd->nr_ppas, c_ctx->lun_bitmap);
+
+ pos = pblk_rb_sync_init(&pblk->rwb, &flags);
+ if (pos == c_ctx->sentry) {
+ pos = pblk_end_w_bio(pblk, rqd, c_ctx);
+
+retry:
+ list_for_each_entry_safe(c, r, &pblk->compl_list, list) {
+ rqd = nvm_rq_from_c_ctx(c);
+ if (c->sentry == pos) {
+ pos = pblk_end_queued_w_bio(pblk, rqd, c);
+ goto retry;
+ }
+ }
+ } else {
+ WARN_ON(nvm_rq_from_c_ctx(c_ctx) != rqd);
+ list_add_tail(&c_ctx->list, &pblk->compl_list);
+ }
+ pblk_rb_sync_end(&pblk->rwb, &flags);
+}
+
+/* When a write fails, we are not sure whether the block has grown bad or a page
+ * range is more susceptible to write errors. If a high number of pages fail, we
+ * assume that the block is bad and we mark it accordingly. In all cases, we
+ * remap and resubmit the failed entries as fast as possible; if a flush is
+ * waiting on a completion, the whole stack would stall otherwise.
+ */
+static void pblk_end_w_fail(struct pblk *pblk, struct nvm_rq *rqd)
+{
+ void *comp_bits = &rqd->ppa_status;
+ struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd);
+ struct pblk_rec_ctx *recovery;
+ struct ppa_addr *ppa_list = rqd->ppa_list;
+ int nr_ppas = rqd->nr_ppas;
+ unsigned int c_entries;
+ int bit, ret;
+
+ if (unlikely(nr_ppas == 1))
+ ppa_list = &rqd->ppa_addr;
+
+ recovery = mempool_alloc(pblk->rec_pool, GFP_ATOMIC);
+ if (!recovery) {
+ pr_err("pblk: could not allocate recovery context\n");
+ return;
+ }
+ INIT_LIST_HEAD(&recovery->failed);
+
+ bit = -1;
+ while ((bit = find_next_bit(comp_bits, nr_ppas, bit + 1)) < nr_ppas) {
+ struct pblk_rb_entry *entry;
+ struct ppa_addr ppa;
+
+ /* Logic error */
+ if (bit > c_ctx->nr_valid) {
+ WARN_ONCE(1, "pblk: corrupted write request\n");
+ mempool_free(recovery, pblk->rec_pool);
+ goto out;
+ }
+
+ ppa = ppa_list[bit];
+ entry = pblk_rb_sync_scan_entry(&pblk->rwb, &ppa);
+ if (!entry) {
+ pr_err("pblk: could not scan entry on write failure\n");
+ mempool_free(recovery, pblk->rec_pool);
+ goto out;
+ }
+
+ /* The list is filled first and emptied afterwards. No need for
+ * protecting it with a lock
+ */
+ list_add_tail(&entry->index, &recovery->failed);
+ }
+
+ c_entries = find_first_bit(comp_bits, nr_ppas);
+ ret = pblk_recov_setup_rq(pblk, c_ctx, recovery, comp_bits, c_entries);
+ if (ret) {
+ pr_err("pblk: could not recover from write failure\n");
+ mempool_free(recovery, pblk->rec_pool);
+ goto out;
+ }
+
+ INIT_WORK(&recovery->ws_rec, pblk_submit_rec);
+ queue_work(pblk->kw_wq, &recovery->ws_rec);
+
+out:
+ pblk_complete_write(pblk, rqd, c_ctx);
+}
+
+static void pblk_end_io_write(struct nvm_rq *rqd)
+{
+ struct pblk *pblk = rqd->private;
+ struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd);
+
+ if (rqd->error) {
+ pblk_log_write_err(pblk, rqd);
+ return pblk_end_w_fail(pblk, rqd);
+ }
+#ifdef CONFIG_NVM_DEBUG
+ else
+ WARN_ONCE(rqd->bio->bi_error, "pblk: corrupted write error\n");
+#endif
+
+ pblk_complete_write(pblk, rqd, c_ctx);
+}
+
+static int pblk_alloc_w_rq(struct pblk *pblk, struct nvm_rq *rqd,
+ unsigned int nr_secs)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+
+ /* Setup write request */
+ rqd->opcode = NVM_OP_PWRITE;
+ rqd->nr_ppas = nr_secs;
+ rqd->flags = pblk_set_progr_mode(pblk, WRITE);
+ rqd->private = pblk;
+ rqd->end_io = pblk_end_io_write;
+
+ rqd->meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL,
+ &rqd->dma_meta_list);
+ if (!rqd->meta_list)
+ return -ENOMEM;
+
+ if (unlikely(nr_secs == 1))
+ return 0;
+
+ rqd->ppa_list = rqd->meta_list + pblk_dma_meta_size;
+ rqd->dma_ppa_list = rqd->dma_meta_list + pblk_dma_meta_size;
+
+ return 0;
+}
+
+static int pblk_setup_w_rq(struct pblk *pblk, struct nvm_rq *rqd,
+ struct pblk_c_ctx *c_ctx)
+{
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_line *e_line = pblk_line_get_data_next(pblk);
+ struct ppa_addr erase_ppa;
+ unsigned int valid = c_ctx->nr_valid;
+ unsigned int padded = c_ctx->nr_padded;
+ unsigned int nr_secs = valid + padded;
+ unsigned long *lun_bitmap;
+ int ret = 0;
+
+ lun_bitmap = kzalloc(lm->lun_bitmap_len, GFP_KERNEL);
+ if (!lun_bitmap) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ c_ctx->lun_bitmap = lun_bitmap;
+
+ ret = pblk_alloc_w_rq(pblk, rqd, nr_secs);
+ if (ret) {
+ kfree(lun_bitmap);
+ goto out;
+ }
+
+ ppa_set_empty(&erase_ppa);
+ if (likely(!e_line || !atomic_read(&e_line->left_eblks)))
+ pblk_map_rq(pblk, rqd, c_ctx->sentry, lun_bitmap, valid, 0);
+ else
+ pblk_map_erase_rq(pblk, rqd, c_ctx->sentry, lun_bitmap,
+ valid, &erase_ppa);
+
+out:
+ if (unlikely(e_line && !ppa_empty(erase_ppa))) {
+ if (pblk_blk_erase_async(pblk, erase_ppa)) {
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ int bit;
+
+ atomic_inc(&e_line->left_eblks);
+ bit = erase_ppa.g.lun * geo->nr_chnls + erase_ppa.g.ch;
+ WARN_ON(!test_and_clear_bit(bit, e_line->erase_bitmap));
+ up(&pblk->erase_sem);
+ }
+ }
+
+ return ret;
+}
+
+int pblk_setup_w_rec_rq(struct pblk *pblk, struct nvm_rq *rqd,
+ struct pblk_c_ctx *c_ctx)
+{
+ struct pblk_line_meta *lm = &pblk->lm;
+ unsigned long *lun_bitmap;
+ int ret;
+
+ lun_bitmap = kzalloc(lm->lun_bitmap_len, GFP_KERNEL);
+ if (!lun_bitmap)
+ return -ENOMEM;
+
+ c_ctx->lun_bitmap = lun_bitmap;
+
+ ret = pblk_alloc_w_rq(pblk, rqd, rqd->nr_ppas);
+ if (ret)
+ return ret;
+
+ pblk_map_rq(pblk, rqd, c_ctx->sentry, lun_bitmap, c_ctx->nr_valid, 0);
+
+ rqd->ppa_status = (u64)0;
+ rqd->flags = pblk_set_progr_mode(pblk, WRITE);
+
+ return ret;
+}
+
+static int pblk_calc_secs_to_sync(struct pblk *pblk, unsigned int secs_avail,
+ unsigned int secs_to_flush)
+{
+ int secs_to_sync;
+
+ secs_to_sync = pblk_calc_secs(pblk, secs_avail, secs_to_flush);
+
+#ifdef CONFIG_NVM_DEBUG
+ if ((!secs_to_sync && secs_to_flush)
+ || (secs_to_sync < 0)
+ || (secs_to_sync > secs_avail && !secs_to_flush)) {
+ pr_err("pblk: bad sector calculation (a:%d,s:%d,f:%d)\n",
+ secs_avail, secs_to_sync, secs_to_flush);
+ }
+#endif
+
+ return secs_to_sync;
+}
+
+static int pblk_submit_write(struct pblk *pblk)
+{
+ struct bio *bio;
+ struct nvm_rq *rqd;
+ struct pblk_c_ctx *c_ctx;
+ unsigned int pgs_read;
+ unsigned int secs_avail, secs_to_sync, secs_to_com;
+ unsigned int secs_to_flush;
+ unsigned long pos;
+ int err;
+
+ /* If there are no sectors in the cache, flushes (bios without data)
+ * will be cleared on the cache threads
+ */
+ secs_avail = pblk_rb_read_count(&pblk->rwb);
+ if (!secs_avail)
+ return 1;
+
+ secs_to_flush = pblk_rb_sync_point_count(&pblk->rwb);
+ if (!secs_to_flush && secs_avail < pblk->min_write_pgs)
+ return 1;
+
+ rqd = pblk_alloc_rqd(pblk, WRITE);
+ if (IS_ERR(rqd)) {
+ pr_err("pblk: cannot allocate write req.\n");
+ return 1;
+ }
+ c_ctx = nvm_rq_to_pdu(rqd);
+
+ bio = bio_alloc(GFP_KERNEL, pblk->max_write_pgs);
+ if (!bio) {
+ pr_err("pblk: cannot allocate write bio\n");
+ goto fail_free_rqd;
+ }
+ bio->bi_iter.bi_sector = 0; /* internal bio */
+ bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+ rqd->bio = bio;
+
+ secs_to_sync = pblk_calc_secs_to_sync(pblk, secs_avail, secs_to_flush);
+ if (secs_to_sync > pblk->max_write_pgs) {
+ pr_err("pblk: bad buffer sync calculation\n");
+ goto fail_put_bio;
+ }
+
+ secs_to_com = (secs_to_sync > secs_avail) ? secs_avail : secs_to_sync;
+ pos = pblk_rb_read_commit(&pblk->rwb, secs_to_com);
+
+ pgs_read = pblk_rb_read_to_bio(&pblk->rwb, bio, c_ctx, pos,
+ secs_to_sync, secs_avail);
+ if (!pgs_read) {
+ pr_err("pblk: corrupted write bio\n");
+ goto fail_put_bio;
+ }
+
+ if (c_ctx->nr_padded)
+ if (pblk_bio_add_pages(pblk, bio, GFP_KERNEL, c_ctx->nr_padded))
+ goto fail_put_bio;
+
+ /* Assign lbas to ppas and populate request structure */
+ err = pblk_setup_w_rq(pblk, rqd, c_ctx);
+ if (err) {
+ pr_err("pblk: could not setup write request\n");
+ goto fail_free_bio;
+ }
+
+ err = pblk_submit_io(pblk, rqd);
+ if (err) {
+ pr_err("pblk: I/O submission failed: %d\n", err);
+ goto fail_free_bio;
+ }
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_add(secs_to_sync, &pblk->sub_writes);
+#endif
+
+ return 0;
+
+fail_free_bio:
+ if (c_ctx->nr_padded)
+ pblk_bio_free_pages(pblk, bio, secs_to_sync, c_ctx->nr_padded);
+fail_put_bio:
+ bio_put(bio);
+fail_free_rqd:
+ pblk_free_rqd(pblk, rqd, WRITE);
+
+ return 1;
+}
+
+int pblk_write_ts(void *data)
+{
+ struct pblk *pblk = data;
+
+ while (!kthread_should_stop()) {
+ if (!pblk_submit_write(pblk))
+ continue;
+ set_current_state(TASK_INTERRUPTIBLE);
+ io_schedule();
+ }
+
+ return 0;
+}
--- /dev/null
+/*
+ * Copyright (C) 2015 IT University of Copenhagen (rrpc.h)
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Matias Bjorling <matias@cnexlabs.com>
+ * Write buffering: Javier Gonzalez <javier@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * Implementation of a Physical Block-device target for Open-channel SSDs.
+ *
+ */
+
+#ifndef PBLK_H_
+#define PBLK_H_
+
+#include <linux/blkdev.h>
+#include <linux/blk-mq.h>
+#include <linux/bio.h>
+#include <linux/module.h>
+#include <linux/kthread.h>
+#include <linux/vmalloc.h>
+#include <linux/crc32.h>
+#include <linux/uuid.h>
+
+#include <linux/lightnvm.h>
+
+/* Run only GC if less than 1/X blocks are free */
+#define GC_LIMIT_INVERSE 5
+#define GC_TIME_MSECS 1000
+
+#define PBLK_SECTOR (512)
+#define PBLK_EXPOSED_PAGE_SIZE (4096)
+#define PBLK_MAX_REQ_ADDRS (64)
+#define PBLK_MAX_REQ_ADDRS_PW (6)
+
+#define PBLK_CACHE_NAME_LEN (DISK_NAME_LEN + 16)
+
+#define PBLK_COMMAND_TIMEOUT_MS 30000
+
+/* Max 512 LUNs per device */
+#define PBLK_MAX_LUNS_BITMAP (4)
+
+#define NR_PHY_IN_LOG (PBLK_EXPOSED_PAGE_SIZE / PBLK_SECTOR)
+
+#define pblk_for_each_lun(pblk, rlun, i) \
+ for ((i) = 0, rlun = &(pblk)->luns[0]; \
+ (i) < (pblk)->nr_luns; (i)++, rlun = &(pblk)->luns[(i)])
+
+#define ERASE 2 /* READ = 0, WRITE = 1 */
+
+enum {
+ /* IO Types */
+ PBLK_IOTYPE_USER = 1 << 0,
+ PBLK_IOTYPE_GC = 1 << 1,
+
+ /* Write buffer flags */
+ PBLK_FLUSH_ENTRY = 1 << 2,
+ PBLK_WRITTEN_DATA = 1 << 3,
+ PBLK_SUBMITTED_ENTRY = 1 << 4,
+ PBLK_WRITABLE_ENTRY = 1 << 5,
+};
+
+enum {
+ PBLK_BLK_ST_OPEN = 0x1,
+ PBLK_BLK_ST_CLOSED = 0x2,
+};
+
+/* The number of GC lists and the rate-limiter states go together. This way the
+ * rate-limiter can dictate how much GC is needed based on resource utilization.
+ */
+#define PBLK_NR_GC_LISTS 3
+#define PBLK_MAX_GC_JOBS 32
+
+enum {
+ PBLK_RL_HIGH = 1,
+ PBLK_RL_MID = 2,
+ PBLK_RL_LOW = 3,
+};
+
+struct pblk_sec_meta {
+ u64 reserved;
+ __le64 lba;
+};
+
+#define pblk_dma_meta_size (sizeof(struct pblk_sec_meta) * PBLK_MAX_REQ_ADDRS)
+
+/* write completion context */
+struct pblk_c_ctx {
+ struct list_head list; /* Head for out-of-order completion */
+
+ unsigned long *lun_bitmap; /* Luns used on current request */
+ unsigned int sentry;
+ unsigned int nr_valid;
+ unsigned int nr_padded;
+};
+
+/* Read context */
+struct pblk_r_ctx {
+ struct bio *orig_bio;
+};
+
+/* Recovery context */
+struct pblk_rec_ctx {
+ struct pblk *pblk;
+ struct nvm_rq *rqd;
+ struct list_head failed;
+ struct work_struct ws_rec;
+};
+
+/* Write context */
+struct pblk_w_ctx {
+ struct bio_list bios; /* Original bios - used for completion
+ * in REQ_FUA, REQ_FLUSH case
+ */
+ u64 lba; /* Logic addr. associated with entry */
+ struct ppa_addr ppa; /* Physic addr. associated with entry */
+ int flags; /* Write context flags */
+};
+
+struct pblk_rb_entry {
+ struct ppa_addr cacheline; /* Cacheline for this entry */
+ void *data; /* Pointer to data on this entry */
+ struct pblk_w_ctx w_ctx; /* Context for this entry */
+ struct list_head index; /* List head to enable indexes */
+};
+
+#define EMPTY_ENTRY (~0U)
+
+struct pblk_rb_pages {
+ struct page *pages;
+ int order;
+ struct list_head list;
+};
+
+struct pblk_rb {
+ struct pblk_rb_entry *entries; /* Ring buffer entries */
+ unsigned int mem; /* Write offset - points to next
+ * writable entry in memory
+ */
+ unsigned int subm; /* Read offset - points to last entry
+ * that has been submitted to the media
+ * to be persisted
+ */
+ unsigned int sync; /* Synced - backpointer that signals
+ * the last submitted entry that has
+ * been successfully persisted to media
+ */
+ unsigned int sync_point; /* Sync point - last entry that must be
+ * flushed to the media. Used with
+ * REQ_FLUSH and REQ_FUA
+ */
+ unsigned int l2p_update; /* l2p update point - next entry for
+ * which l2p mapping will be updated to
+ * contain a device ppa address (instead
+ * of a cacheline
+ */
+ unsigned int nr_entries; /* Number of entries in write buffer -
+ * must be a power of two
+ */
+ unsigned int seg_size; /* Size of the data segments being
+ * stored on each entry. Typically this
+ * will be 4KB
+ */
+
+ struct list_head pages; /* List of data pages */
+
+ spinlock_t w_lock; /* Write lock */
+ spinlock_t s_lock; /* Sync lock */
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_t inflight_sync_point; /* Not served REQ_FLUSH | REQ_FUA */
+#endif
+};
+
+#define PBLK_RECOVERY_SECTORS 16
+
+struct pblk_lun {
+ struct ppa_addr bppa;
+
+ u8 *bb_list; /* Bad block list for LUN. Only used on
+ * bring up. Bad blocks are managed
+ * within lines on run-time.
+ */
+
+ struct semaphore wr_sem;
+};
+
+struct pblk_gc_rq {
+ struct pblk_line *line;
+ void *data;
+ u64 *lba_list;
+ int nr_secs;
+ int secs_to_gc;
+ struct list_head list;
+};
+
+struct pblk_gc {
+ int gc_active;
+ int gc_enabled;
+ int gc_forced;
+ int gc_jobs_active;
+ atomic_t inflight_gc;
+
+ struct task_struct *gc_ts;
+ struct task_struct *gc_writer_ts;
+ struct workqueue_struct *gc_reader_wq;
+ struct timer_list gc_timer;
+
+ int w_entries;
+ struct list_head w_list;
+
+ spinlock_t lock;
+ spinlock_t w_lock;
+};
+
+struct pblk_rl {
+ unsigned int high; /* Upper threshold for rate limiter (free run -
+ * user I/O rate limiter
+ */
+ unsigned int low; /* Lower threshold for rate limiter (user I/O
+ * rate limiter - stall)
+ */
+ unsigned int high_pw; /* High rounded up as a power of 2 */
+
+#define PBLK_USER_HIGH_THRS 2 /* Begin write limit at 50 percent
+ * available blks
+ */
+#define PBLK_USER_LOW_THRS 20 /* Aggressive GC at 5% available blocks */
+
+ int rb_windows_pw; /* Number of rate windows in the write buffer
+ * given as a power-of-2. This guarantees that
+ * when user I/O is being rate limited, there
+ * will be reserved enough space for the GC to
+ * place its payload. A window is of
+ * pblk->max_write_pgs size, which in NVMe is
+ * 64, i.e., 256kb.
+ */
+ int rb_budget; /* Total number of entries available for I/O */
+ int rb_user_max; /* Max buffer entries available for user I/O */
+ atomic_t rb_user_cnt; /* User I/O buffer counter */
+ int rb_gc_max; /* Max buffer entries available for GC I/O */
+ int rb_gc_rsv; /* Reserved buffer entries for GC I/O */
+ int rb_state; /* Rate-limiter current state */
+ atomic_t rb_gc_cnt; /* GC I/O buffer counter */
+
+ int rb_user_active;
+ struct timer_list u_timer;
+
+ unsigned long long nr_secs;
+ unsigned long total_blocks;
+ atomic_t free_blocks;
+};
+
+#define PBLK_LINE_NR_LUN_BITMAP 2
+#define PBLK_LINE_NR_SEC_BITMAP 2
+#define PBLK_LINE_EMPTY (~0U)
+
+enum {
+ /* Line Types */
+ PBLK_LINETYPE_FREE = 0,
+ PBLK_LINETYPE_LOG = 1,
+ PBLK_LINETYPE_DATA = 2,
+
+ /* Line state */
+ PBLK_LINESTATE_FREE = 10,
+ PBLK_LINESTATE_OPEN = 11,
+ PBLK_LINESTATE_CLOSED = 12,
+ PBLK_LINESTATE_GC = 13,
+ PBLK_LINESTATE_BAD = 14,
+ PBLK_LINESTATE_CORRUPT = 15,
+
+ /* GC group */
+ PBLK_LINEGC_NONE = 20,
+ PBLK_LINEGC_EMPTY = 21,
+ PBLK_LINEGC_LOW = 22,
+ PBLK_LINEGC_MID = 23,
+ PBLK_LINEGC_HIGH = 24,
+ PBLK_LINEGC_FULL = 25,
+};
+
+#define PBLK_MAGIC 0x70626c6b /*pblk*/
+
+struct line_header {
+ __le32 crc;
+ __le32 identifier; /* pblk identifier */
+ __u8 uuid[16]; /* instance uuid */
+ __le16 type; /* line type */
+ __le16 version; /* type version */
+ __le32 id; /* line id for current line */
+};
+
+struct line_smeta {
+ struct line_header header;
+
+ __le32 crc; /* Full structure including struct crc */
+ /* Previous line metadata */
+ __le32 prev_id; /* Line id for previous line */
+
+ /* Current line metadata */
+ __le64 seq_nr; /* Sequence number for current line */
+
+ /* Active writers */
+ __le32 window_wr_lun; /* Number of parallel LUNs to write */
+
+ __le32 rsvd[2];
+};
+
+/*
+ * Metadata Layout:
+ * 1. struct pblk_emeta
+ * 2. nr_lbas u64 forming lba list
+ * 3. nr_lines (all) u32 valid sector count (vsc) (~0U: non-alloc line)
+ * 4. nr_luns bits (u64 format) forming line bad block bitmap
+ *
+ * 3. and 4. will be part of FTL log
+ */
+struct line_emeta {
+ struct line_header header;
+
+ __le32 crc; /* Full structure including struct crc */
+
+ /* Previous line metadata */
+ __le32 prev_id; /* Line id for prev line */
+
+ /* Current line metadata */
+ __le64 seq_nr; /* Sequence number for current line */
+
+ /* Active writers */
+ __le32 window_wr_lun; /* Number of parallel LUNs to write */
+
+ /* Bookkeeping for recovery */
+ __le32 next_id; /* Line id for next line */
+ __le64 nr_lbas; /* Number of lbas mapped in line */
+ __le64 nr_valid_lbas; /* Number of valid lbas mapped in line */
+};
+
+struct pblk_line {
+ struct pblk *pblk;
+ unsigned int id; /* Line number corresponds to the
+ * block line
+ */
+ unsigned int seq_nr; /* Unique line sequence number */
+
+ int state; /* PBLK_LINESTATE_X */
+ int type; /* PBLK_LINETYPE_X */
+ int gc_group; /* PBLK_LINEGC_X */
+ struct list_head list; /* Free, GC lists */
+
+ unsigned long *lun_bitmap; /* Bitmap for LUNs mapped in line */
+
+ struct line_smeta *smeta; /* Start metadata */
+ struct line_emeta *emeta; /* End metadata */
+ int meta_line; /* Metadata line id */
+ u64 smeta_ssec; /* Sector where smeta starts */
+ u64 emeta_ssec; /* Sector where emeta starts */
+
+ unsigned int sec_in_line; /* Number of usable secs in line */
+
+ atomic_t blk_in_line; /* Number of good blocks in line */
+ unsigned long *blk_bitmap; /* Bitmap for valid/invalid blocks */
+ unsigned long *erase_bitmap; /* Bitmap for erased blocks */
+
+ unsigned long *map_bitmap; /* Bitmap for mapped sectors in line */
+ unsigned long *invalid_bitmap; /* Bitmap for invalid sectors in line */
+
+ atomic_t left_eblks; /* Blocks left for erasing */
+ atomic_t left_seblks; /* Blocks left for sync erasing */
+
+ int left_msecs; /* Sectors left for mapping */
+ int left_ssecs; /* Sectors left to sync */
+ unsigned int cur_sec; /* Sector map pointer */
+ unsigned int vsc; /* Valid sector count in line */
+
+ struct kref ref; /* Write buffer L2P references */
+
+ spinlock_t lock; /* Necessary for invalid_bitmap only */
+};
+
+#define PBLK_DATA_LINES 4
+
+enum{
+ PBLK_KMALLOC_META = 1,
+ PBLK_VMALLOC_META = 2,
+};
+
+struct pblk_line_metadata {
+ void *meta;
+};
+
+struct pblk_line_mgmt {
+ int nr_lines; /* Total number of full lines */
+ int nr_free_lines; /* Number of full lines in free list */
+
+ /* Free lists - use free_lock */
+ struct list_head free_list; /* Full lines ready to use */
+ struct list_head corrupt_list; /* Full lines corrupted */
+ struct list_head bad_list; /* Full lines bad */
+
+ /* GC lists - use gc_lock */
+ struct list_head *gc_lists[PBLK_NR_GC_LISTS];
+ struct list_head gc_high_list; /* Full lines ready to GC, high isc */
+ struct list_head gc_mid_list; /* Full lines ready to GC, mid isc */
+ struct list_head gc_low_list; /* Full lines ready to GC, low isc */
+
+ struct list_head gc_full_list; /* Full lines ready to GC, no valid */
+ struct list_head gc_empty_list; /* Full lines close, all valid */
+
+ struct pblk_line *log_line; /* Current FTL log line */
+ struct pblk_line *data_line; /* Current data line */
+ struct pblk_line *log_next; /* Next FTL log line */
+ struct pblk_line *data_next; /* Next data line */
+
+ /* Metadata allocation type: VMALLOC | KMALLOC */
+ int smeta_alloc_type;
+ int emeta_alloc_type;
+
+ /* Pre-allocated metadata for data lines */
+ struct pblk_line_metadata sline_meta[PBLK_DATA_LINES];
+ struct pblk_line_metadata eline_meta[PBLK_DATA_LINES];
+ unsigned long meta_bitmap;
+
+ /* Helpers for fast bitmap calculations */
+ unsigned long *bb_template;
+ unsigned long *bb_aux;
+
+ unsigned long d_seq_nr; /* Data line unique sequence number */
+ unsigned long l_seq_nr; /* Log line unique sequence number */
+
+ spinlock_t free_lock;
+ spinlock_t gc_lock;
+};
+
+struct pblk_line_meta {
+ unsigned int smeta_len; /* Total length for smeta */
+ unsigned int smeta_sec; /* Sectors needed for smeta*/
+ unsigned int emeta_len; /* Total length for emeta */
+ unsigned int emeta_sec; /* Sectors needed for emeta*/
+ unsigned int emeta_bb; /* Boundary for bb that affects emeta */
+ unsigned int sec_bitmap_len; /* Length for sector bitmap in line */
+ unsigned int blk_bitmap_len; /* Length for block bitmap in line */
+ unsigned int lun_bitmap_len; /* Length for lun bitmap in line */
+
+ unsigned int blk_per_line; /* Number of blocks in a full line */
+ unsigned int sec_per_line; /* Number of sectors in a line */
+ unsigned int min_blk_line; /* Min. number of good blocks in line */
+
+ unsigned int mid_thrs; /* Threshold for GC mid list */
+ unsigned int high_thrs; /* Threshold for GC high list */
+};
+
+struct pblk_addr_format {
+ u64 ch_mask;
+ u64 lun_mask;
+ u64 pln_mask;
+ u64 blk_mask;
+ u64 pg_mask;
+ u64 sec_mask;
+ u8 ch_offset;
+ u8 lun_offset;
+ u8 pln_offset;
+ u8 blk_offset;
+ u8 pg_offset;
+ u8 sec_offset;
+};
+
+struct pblk {
+ struct nvm_tgt_dev *dev;
+ struct gendisk *disk;
+
+ struct kobject kobj;
+
+ struct pblk_lun *luns;
+
+ struct pblk_line *lines; /* Line array */
+ struct pblk_line_mgmt l_mg; /* Line management */
+ struct pblk_line_meta lm; /* Line metadata */
+
+ int ppaf_bitsize;
+ struct pblk_addr_format ppaf;
+
+ struct pblk_rb rwb;
+
+ int min_write_pgs; /* Minimum amount of pages required by controller */
+ int max_write_pgs; /* Maximum amount of pages supported by controller */
+ int pgs_in_buffer; /* Number of pages that need to be held in buffer to
+ * guarantee successful reads.
+ */
+
+ sector_t capacity; /* Device capacity when bad blocks are subtracted */
+ int over_pct; /* Percentage of device used for over-provisioning */
+
+ /* pblk provisioning values. Used by rate limiter */
+ struct pblk_rl rl;
+
+ struct semaphore erase_sem;
+
+ unsigned char instance_uuid[16];
+#ifdef CONFIG_NVM_DEBUG
+ /* All debug counters apply to 4kb sector I/Os */
+ atomic_long_t inflight_writes; /* Inflight writes (user and gc) */
+ atomic_long_t padded_writes; /* Sectors padded due to flush/fua */
+ atomic_long_t padded_wb; /* Sectors padded in write buffer */
+ atomic_long_t nr_flush; /* Number of flush/fua I/O */
+ atomic_long_t req_writes; /* Sectors stored on write buffer */
+ atomic_long_t sub_writes; /* Sectors submitted from buffer */
+ atomic_long_t sync_writes; /* Sectors synced to media */
+ atomic_long_t compl_writes; /* Sectors completed in write bio */
+ atomic_long_t inflight_reads; /* Inflight sector read requests */
+ atomic_long_t sync_reads; /* Completed sector read requests */
+ atomic_long_t recov_writes; /* Sectors submitted from recovery */
+ atomic_long_t recov_gc_writes; /* Sectors submitted from write GC */
+ atomic_long_t recov_gc_reads; /* Sectors submitted from read GC */
+#endif
+
+ spinlock_t lock;
+
+ atomic_long_t read_failed;
+ atomic_long_t read_empty;
+ atomic_long_t read_high_ecc;
+ atomic_long_t read_failed_gc;
+ atomic_long_t write_failed;
+ atomic_long_t erase_failed;
+
+ struct task_struct *writer_ts;
+
+ /* Simple translation map of logical addresses to physical addresses.
+ * The logical addresses is known by the host system, while the physical
+ * addresses are used when writing to the disk block device.
+ */
+ unsigned char *trans_map;
+ spinlock_t trans_lock;
+
+ struct list_head compl_list;
+
+ mempool_t *page_pool;
+ mempool_t *line_ws_pool;
+ mempool_t *rec_pool;
+ mempool_t *r_rq_pool;
+ mempool_t *w_rq_pool;
+ mempool_t *line_meta_pool;
+
+ struct workqueue_struct *kw_wq;
+ struct timer_list wtimer;
+
+ struct pblk_gc gc;
+};
+
+struct pblk_line_ws {
+ struct pblk *pblk;
+ struct pblk_line *line;
+ void *priv;
+ struct work_struct ws;
+};
+
+#define pblk_r_rq_size (sizeof(struct nvm_rq) + sizeof(struct pblk_r_ctx))
+#define pblk_w_rq_size (sizeof(struct nvm_rq) + sizeof(struct pblk_c_ctx))
+
+/*
+ * pblk ring buffer operations
+ */
+int pblk_rb_init(struct pblk_rb *rb, struct pblk_rb_entry *rb_entry_base,
+ unsigned int power_size, unsigned int power_seg_sz);
+unsigned int pblk_rb_calculate_size(unsigned int nr_entries);
+void *pblk_rb_entries_ref(struct pblk_rb *rb);
+int pblk_rb_may_write_user(struct pblk_rb *rb, struct bio *bio,
+ unsigned int nr_entries, unsigned int *pos);
+int pblk_rb_may_write_gc(struct pblk_rb *rb, unsigned int nr_entries,
+ unsigned int *pos);
+void pblk_rb_write_entry_user(struct pblk_rb *rb, void *data,
+ struct pblk_w_ctx w_ctx, unsigned int pos);
+void pblk_rb_write_entry_gc(struct pblk_rb *rb, void *data,
+ struct pblk_w_ctx w_ctx, struct pblk_line *gc_line,
+ unsigned int pos);
+struct pblk_w_ctx *pblk_rb_w_ctx(struct pblk_rb *rb, unsigned int pos);
+
+void pblk_rb_sync_l2p(struct pblk_rb *rb);
+unsigned int pblk_rb_read_to_bio(struct pblk_rb *rb, struct bio *bio,
+ struct pblk_c_ctx *c_ctx,
+ unsigned int pos,
+ unsigned int nr_entries,
+ unsigned int count);
+unsigned int pblk_rb_read_to_bio_list(struct pblk_rb *rb, struct bio *bio,
+ struct list_head *list,
+ unsigned int max);
+int pblk_rb_copy_to_bio(struct pblk_rb *rb, struct bio *bio, sector_t lba,
+ u64 pos, int bio_iter);
+unsigned int pblk_rb_read_commit(struct pblk_rb *rb, unsigned int entries);
+
+unsigned int pblk_rb_sync_init(struct pblk_rb *rb, unsigned long *flags);
+unsigned int pblk_rb_sync_advance(struct pblk_rb *rb, unsigned int nr_entries);
+struct pblk_rb_entry *pblk_rb_sync_scan_entry(struct pblk_rb *rb,
+ struct ppa_addr *ppa);
+void pblk_rb_sync_end(struct pblk_rb *rb, unsigned long *flags);
+unsigned int pblk_rb_sync_point_count(struct pblk_rb *rb);
+
+unsigned int pblk_rb_read_count(struct pblk_rb *rb);
+unsigned int pblk_rb_wrap_pos(struct pblk_rb *rb, unsigned int pos);
+
+int pblk_rb_tear_down_check(struct pblk_rb *rb);
+int pblk_rb_pos_oob(struct pblk_rb *rb, u64 pos);
+void pblk_rb_data_free(struct pblk_rb *rb);
+ssize_t pblk_rb_sysfs(struct pblk_rb *rb, char *buf);
+
+/*
+ * pblk core
+ */
+struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int rw);
+int pblk_setup_w_rec_rq(struct pblk *pblk, struct nvm_rq *rqd,
+ struct pblk_c_ctx *c_ctx);
+void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int rw);
+void pblk_flush_writer(struct pblk *pblk);
+struct ppa_addr pblk_get_lba_map(struct pblk *pblk, sector_t lba);
+void pblk_discard(struct pblk *pblk, struct bio *bio);
+void pblk_log_write_err(struct pblk *pblk, struct nvm_rq *rqd);
+void pblk_log_read_err(struct pblk *pblk, struct nvm_rq *rqd);
+int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd);
+struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data,
+ unsigned int nr_secs, unsigned int len,
+ gfp_t gfp_mask);
+struct pblk_line *pblk_line_get(struct pblk *pblk);
+struct pblk_line *pblk_line_get_first_data(struct pblk *pblk);
+struct pblk_line *pblk_line_replace_data(struct pblk *pblk);
+int pblk_line_recov_alloc(struct pblk *pblk, struct pblk_line *line);
+void pblk_line_recov_close(struct pblk *pblk, struct pblk_line *line);
+struct pblk_line *pblk_line_get_data(struct pblk *pblk);
+struct pblk_line *pblk_line_get_data_next(struct pblk *pblk);
+int pblk_line_erase(struct pblk *pblk, struct pblk_line *line);
+int pblk_line_is_full(struct pblk_line *line);
+void pblk_line_free(struct pblk *pblk, struct pblk_line *line);
+void pblk_line_close_ws(struct work_struct *work);
+void pblk_line_close(struct pblk *pblk, struct pblk_line *line);
+void pblk_line_mark_bb(struct work_struct *work);
+void pblk_line_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv,
+ void (*work)(struct work_struct *));
+u64 pblk_line_smeta_start(struct pblk *pblk, struct pblk_line *line);
+int pblk_line_read_smeta(struct pblk *pblk, struct pblk_line *line);
+int pblk_line_read_emeta(struct pblk *pblk, struct pblk_line *line);
+int pblk_blk_erase_async(struct pblk *pblk, struct ppa_addr erase_ppa);
+void pblk_line_put(struct kref *ref);
+struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line);
+u64 pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs);
+int pblk_calc_secs(struct pblk *pblk, unsigned long secs_avail,
+ unsigned long secs_to_flush);
+void pblk_down_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas,
+ unsigned long *lun_bitmap);
+void pblk_up_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas,
+ unsigned long *lun_bitmap);
+void pblk_end_bio_sync(struct bio *bio);
+void pblk_end_io_sync(struct nvm_rq *rqd);
+int pblk_bio_add_pages(struct pblk *pblk, struct bio *bio, gfp_t flags,
+ int nr_pages);
+void pblk_map_pad_invalidate(struct pblk *pblk, struct pblk_line *line,
+ u64 paddr);
+void pblk_bio_free_pages(struct pblk *pblk, struct bio *bio, int off,
+ int nr_pages);
+void pblk_map_invalidate(struct pblk *pblk, struct ppa_addr ppa);
+void pblk_update_map(struct pblk *pblk, sector_t lba, struct ppa_addr ppa);
+void pblk_update_map_cache(struct pblk *pblk, sector_t lba,
+ struct ppa_addr ppa);
+void pblk_update_map_dev(struct pblk *pblk, sector_t lba,
+ struct ppa_addr ppa, struct ppa_addr entry_line);
+int pblk_update_map_gc(struct pblk *pblk, sector_t lba, struct ppa_addr ppa,
+ struct pblk_line *gc_line);
+void pblk_lookup_l2p_rand(struct pblk *pblk, struct ppa_addr *ppas,
+ u64 *lba_list, int nr_secs);
+void pblk_lookup_l2p_seq(struct pblk *pblk, struct ppa_addr *ppas,
+ sector_t blba, int nr_secs);
+
+/*
+ * pblk user I/O write path
+ */
+int pblk_write_to_cache(struct pblk *pblk, struct bio *bio,
+ unsigned long flags);
+int pblk_write_gc_to_cache(struct pblk *pblk, void *data, u64 *lba_list,
+ unsigned int nr_entries, unsigned int nr_rec_entries,
+ struct pblk_line *gc_line, unsigned long flags);
+
+/*
+ * pblk map
+ */
+void pblk_map_erase_rq(struct pblk *pblk, struct nvm_rq *rqd,
+ unsigned int sentry, unsigned long *lun_bitmap,
+ unsigned int valid_secs, struct ppa_addr *erase_ppa);
+void pblk_map_rq(struct pblk *pblk, struct nvm_rq *rqd, unsigned int sentry,
+ unsigned long *lun_bitmap, unsigned int valid_secs,
+ unsigned int off);
+
+/*
+ * pblk write thread
+ */
+int pblk_write_ts(void *data);
+void pblk_write_timer_fn(unsigned long data);
+void pblk_write_should_kick(struct pblk *pblk);
+
+/*
+ * pblk read path
+ */
+int pblk_submit_read(struct pblk *pblk, struct bio *bio);
+int pblk_submit_read_gc(struct pblk *pblk, u64 *lba_list, void *data,
+ unsigned int nr_secs, unsigned int *secs_to_gc,
+ struct pblk_line *line);
+/*
+ * pblk recovery
+ */
+void pblk_submit_rec(struct work_struct *work);
+struct pblk_line *pblk_recov_l2p(struct pblk *pblk);
+void pblk_recov_pad(struct pblk *pblk);
+__le64 *pblk_recov_get_lba_list(struct pblk *pblk, struct line_emeta *emeta);
+int pblk_recov_setup_rq(struct pblk *pblk, struct pblk_c_ctx *c_ctx,
+ struct pblk_rec_ctx *recovery, u64 *comp_bits,
+ unsigned int comp);
+
+/*
+ * pblk gc
+ */
+#define PBLK_GC_TRIES 3
+
+int pblk_gc_init(struct pblk *pblk);
+void pblk_gc_exit(struct pblk *pblk);
+void pblk_gc_should_start(struct pblk *pblk);
+void pblk_gc_should_stop(struct pblk *pblk);
+int pblk_gc_status(struct pblk *pblk);
+void pblk_gc_sysfs_state_show(struct pblk *pblk, int *gc_enabled,
+ int *gc_active);
+void pblk_gc_sysfs_force(struct pblk *pblk, int force);
+
+/*
+ * pblk rate limiter
+ */
+void pblk_rl_init(struct pblk_rl *rl, int budget);
+void pblk_rl_free(struct pblk_rl *rl);
+int pblk_rl_gc_thrs(struct pblk_rl *rl);
+unsigned long pblk_rl_nr_free_blks(struct pblk_rl *rl);
+int pblk_rl_user_may_insert(struct pblk_rl *rl, int nr_entries);
+void pblk_rl_user_in(struct pblk_rl *rl, int nr_entries);
+int pblk_rl_gc_may_insert(struct pblk_rl *rl, int nr_entries);
+void pblk_rl_gc_in(struct pblk_rl *rl, int nr_entries);
+void pblk_rl_out(struct pblk_rl *rl, int nr_user, int nr_gc);
+void pblk_rl_set_gc_rsc(struct pblk_rl *rl, int rsv);
+int pblk_rl_sysfs_rate_show(struct pblk_rl *rl);
+void pblk_rl_free_lines_inc(struct pblk_rl *rl, struct pblk_line *line);
+void pblk_rl_free_lines_dec(struct pblk_rl *rl, struct pblk_line *line);
+
+/*
+ * pblk sysfs
+ */
+int pblk_sysfs_init(struct gendisk *tdisk);
+void pblk_sysfs_exit(struct gendisk *tdisk);
+
+static inline void *pblk_malloc(size_t size, int type, gfp_t flags)
+{
+ if (type == PBLK_KMALLOC_META)
+ return kmalloc(size, flags);
+ return vmalloc(size);
+}
+
+static inline void pblk_mfree(void *ptr, int type)
+{
+ if (type == PBLK_KMALLOC_META)
+ kfree(ptr);
+ else
+ vfree(ptr);
+}
+
+static inline struct nvm_rq *nvm_rq_from_c_ctx(void *c_ctx)
+{
+ return c_ctx - sizeof(struct nvm_rq);
+}
+
+static inline void *pblk_line_emeta_to_lbas(struct line_emeta *emeta)
+{
+ return (emeta) + 1;
+}
+
+#define NVM_MEM_PAGE_WRITE (8)
+
+static inline int pblk_pad_distance(struct pblk *pblk)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+
+ return NVM_MEM_PAGE_WRITE * geo->nr_luns * geo->sec_per_pl;
+}
+
+static inline int pblk_dev_ppa_to_line(struct ppa_addr p)
+{
+ return p.g.blk;
+}
+
+static inline int pblk_tgt_ppa_to_line(struct ppa_addr p)
+{
+ return p.g.blk;
+}
+
+static inline int pblk_ppa_to_pos(struct nvm_geo *geo, struct ppa_addr p)
+{
+ return p.g.lun * geo->nr_chnls + p.g.ch;
+}
+
+/* A block within a line corresponds to the lun */
+static inline int pblk_dev_ppa_to_pos(struct nvm_geo *geo, struct ppa_addr p)
+{
+ return p.g.lun * geo->nr_chnls + p.g.ch;
+}
+
+static inline struct ppa_addr pblk_ppa32_to_ppa64(struct pblk *pblk, u32 ppa32)
+{
+ struct ppa_addr ppa64;
+
+ ppa64.ppa = 0;
+
+ if (ppa32 == -1) {
+ ppa64.ppa = ADDR_EMPTY;
+ } else if (ppa32 & (1U << 31)) {
+ ppa64.c.line = ppa32 & ((~0U) >> 1);
+ ppa64.c.is_cached = 1;
+ } else {
+ ppa64.g.blk = (ppa32 & pblk->ppaf.blk_mask) >>
+ pblk->ppaf.blk_offset;
+ ppa64.g.pg = (ppa32 & pblk->ppaf.pg_mask) >>
+ pblk->ppaf.pg_offset;
+ ppa64.g.lun = (ppa32 & pblk->ppaf.lun_mask) >>
+ pblk->ppaf.lun_offset;
+ ppa64.g.ch = (ppa32 & pblk->ppaf.ch_mask) >>
+ pblk->ppaf.ch_offset;
+ ppa64.g.pl = (ppa32 & pblk->ppaf.pln_mask) >>
+ pblk->ppaf.pln_offset;
+ ppa64.g.sec = (ppa32 & pblk->ppaf.sec_mask) >>
+ pblk->ppaf.sec_offset;
+ }
+
+ return ppa64;
+}
+
+static inline struct ppa_addr pblk_trans_map_get(struct pblk *pblk,
+ sector_t lba)
+{
+ struct ppa_addr ppa;
+
+ if (pblk->ppaf_bitsize < 32) {
+ u32 *map = (u32 *)pblk->trans_map;
+
+ ppa = pblk_ppa32_to_ppa64(pblk, map[lba]);
+ } else {
+ struct ppa_addr *map = (struct ppa_addr *)pblk->trans_map;
+
+ ppa = map[lba];
+ }
+
+ return ppa;
+}
+
+static inline u32 pblk_ppa64_to_ppa32(struct pblk *pblk, struct ppa_addr ppa64)
+{
+ u32 ppa32 = 0;
+
+ if (ppa64.ppa == ADDR_EMPTY) {
+ ppa32 = ~0U;
+ } else if (ppa64.c.is_cached) {
+ ppa32 |= ppa64.c.line;
+ ppa32 |= 1U << 31;
+ } else {
+ ppa32 |= ppa64.g.blk << pblk->ppaf.blk_offset;
+ ppa32 |= ppa64.g.pg << pblk->ppaf.pg_offset;
+ ppa32 |= ppa64.g.lun << pblk->ppaf.lun_offset;
+ ppa32 |= ppa64.g.ch << pblk->ppaf.ch_offset;
+ ppa32 |= ppa64.g.pl << pblk->ppaf.pln_offset;
+ ppa32 |= ppa64.g.sec << pblk->ppaf.sec_offset;
+ }
+
+ return ppa32;
+}
+
+static inline void pblk_trans_map_set(struct pblk *pblk, sector_t lba,
+ struct ppa_addr ppa)
+{
+ if (pblk->ppaf_bitsize < 32) {
+ u32 *map = (u32 *)pblk->trans_map;
+
+ map[lba] = pblk_ppa64_to_ppa32(pblk, ppa);
+ } else {
+ u64 *map = (u64 *)pblk->trans_map;
+
+ map[lba] = ppa.ppa;
+ }
+}
+
+static inline u64 pblk_dev_ppa_to_line_addr(struct pblk *pblk,
+ struct ppa_addr p)
+{
+ u64 paddr;
+
+ paddr = 0;
+ paddr |= (u64)p.g.pg << pblk->ppaf.pg_offset;
+ paddr |= (u64)p.g.lun << pblk->ppaf.lun_offset;
+ paddr |= (u64)p.g.ch << pblk->ppaf.ch_offset;
+ paddr |= (u64)p.g.pl << pblk->ppaf.pln_offset;
+ paddr |= (u64)p.g.sec << pblk->ppaf.sec_offset;
+
+ return paddr;
+}
+
+static inline int pblk_ppa_empty(struct ppa_addr ppa_addr)
+{
+ return (ppa_addr.ppa == ADDR_EMPTY);
+}
+
+static inline void pblk_ppa_set_empty(struct ppa_addr *ppa_addr)
+{
+ ppa_addr->ppa = ADDR_EMPTY;
+}
+
+static inline int pblk_addr_in_cache(struct ppa_addr ppa)
+{
+ return (ppa.ppa != ADDR_EMPTY && ppa.c.is_cached);
+}
+
+static inline int pblk_addr_to_cacheline(struct ppa_addr ppa)
+{
+ return ppa.c.line;
+}
+
+static inline struct ppa_addr pblk_cacheline_to_addr(int addr)
+{
+ struct ppa_addr p;
+
+ p.c.line = addr;
+ p.c.is_cached = 1;
+
+ return p;
+}
+
+static inline struct ppa_addr addr_to_gen_ppa(struct pblk *pblk, u64 paddr,
+ u64 line_id)
+{
+ struct ppa_addr ppa;
+
+ ppa.ppa = 0;
+ ppa.g.blk = line_id;
+ ppa.g.pg = (paddr & pblk->ppaf.pg_mask) >> pblk->ppaf.pg_offset;
+ ppa.g.lun = (paddr & pblk->ppaf.lun_mask) >> pblk->ppaf.lun_offset;
+ ppa.g.ch = (paddr & pblk->ppaf.ch_mask) >> pblk->ppaf.ch_offset;
+ ppa.g.pl = (paddr & pblk->ppaf.pln_mask) >> pblk->ppaf.pln_offset;
+ ppa.g.sec = (paddr & pblk->ppaf.sec_mask) >> pblk->ppaf.sec_offset;
+
+ return ppa;
+}
+
+static inline struct ppa_addr addr_to_pblk_ppa(struct pblk *pblk, u64 paddr,
+ u64 line_id)
+{
+ struct ppa_addr ppa;
+
+ ppa = addr_to_gen_ppa(pblk, paddr, line_id);
+
+ return ppa;
+}
+
+static inline u32 pblk_calc_meta_header_crc(struct pblk *pblk,
+ struct line_smeta *smeta)
+{
+ u32 crc = ~(u32)0;
+
+ crc = crc32_le(crc, (unsigned char *)smeta + sizeof(crc),
+ sizeof(struct line_header) - sizeof(crc));
+
+ return crc;
+}
+
+static inline u32 pblk_calc_smeta_crc(struct pblk *pblk,
+ struct line_smeta *smeta)
+{
+ struct pblk_line_meta *lm = &pblk->lm;
+ u32 crc = ~(u32)0;
+
+ crc = crc32_le(crc, (unsigned char *)smeta +
+ sizeof(struct line_header) + sizeof(crc),
+ lm->smeta_len -
+ sizeof(struct line_header) - sizeof(crc));
+
+ return crc;
+}
+
+static inline u32 pblk_calc_emeta_crc(struct pblk *pblk,
+ struct line_emeta *emeta)
+{
+ struct pblk_line_meta *lm = &pblk->lm;
+ u32 crc = ~(u32)0;
+
+ crc = crc32_le(crc, (unsigned char *)emeta +
+ sizeof(struct line_header) + sizeof(crc),
+ lm->emeta_len -
+ sizeof(struct line_header) - sizeof(crc));
+
+ return crc;
+}
+
+static inline int pblk_set_progr_mode(struct pblk *pblk, int type)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ int flags;
+
+ flags = geo->plane_mode >> 1;
+
+ if (type == WRITE)
+ flags |= NVM_IO_SCRAMBLE_ENABLE;
+
+ return flags;
+}
+
+static inline int pblk_set_read_mode(struct pblk *pblk)
+{
+ return NVM_IO_SNGL_ACCESS | NVM_IO_SUSPEND | NVM_IO_SCRAMBLE_ENABLE;
+}
+
+#ifdef CONFIG_NVM_DEBUG
+static inline void print_ppa(struct ppa_addr *p, char *msg, int error)
+{
+ if (p->c.is_cached) {
+ pr_err("ppa: (%s: %x) cache line: %llu\n",
+ msg, error, (u64)p->c.line);
+ } else {
+ pr_err("ppa: (%s: %x):ch:%d,lun:%d,blk:%d,pg:%d,pl:%d,sec:%d\n",
+ msg, error,
+ p->g.ch, p->g.lun, p->g.blk,
+ p->g.pg, p->g.pl, p->g.sec);
+ }
+}
+
+static inline void pblk_print_failed_rqd(struct pblk *pblk, struct nvm_rq *rqd,
+ int error)
+{
+ int bit = -1;
+
+ if (rqd->nr_ppas == 1) {
+ print_ppa(&rqd->ppa_addr, "rqd", error);
+ return;
+ }
+
+ while ((bit = find_next_bit((void *)&rqd->ppa_status, rqd->nr_ppas,
+ bit + 1)) < rqd->nr_ppas) {
+ print_ppa(&rqd->ppa_list[bit], "rqd", error);
+ }
+
+ pr_err("error:%d, ppa_status:%llx\n", error, rqd->ppa_status);
+}
+#endif
+
+static inline int pblk_boundary_ppa_checks(struct nvm_tgt_dev *tgt_dev,
+ struct ppa_addr *ppas, int nr_ppas)
+{
+ struct nvm_geo *geo = &tgt_dev->geo;
+ struct ppa_addr *ppa;
+ int i;
+
+ for (i = 0; i < nr_ppas; i++) {
+ ppa = &ppas[i];
+
+ if (!ppa->c.is_cached &&
+ ppa->g.ch < geo->nr_chnls &&
+ ppa->g.lun < geo->luns_per_chnl &&
+ ppa->g.pl < geo->nr_planes &&
+ ppa->g.blk < geo->blks_per_lun &&
+ ppa->g.pg < geo->pgs_per_blk &&
+ ppa->g.sec < geo->sec_per_pg)
+ continue;
+
+#ifdef CONFIG_NVM_DEBUG
+ print_ppa(ppa, "boundary", i);
+#endif
+ return 1;
+ }
+ return 0;
+}
+
+static inline int pblk_boundary_paddr_checks(struct pblk *pblk, u64 paddr)
+{
+ struct pblk_line_meta *lm = &pblk->lm;
+
+ if (paddr > lm->sec_per_line)
+ return 1;
+
+ return 0;
+}
+
+static inline unsigned int pblk_get_bi_idx(struct bio *bio)
+{
+ return bio->bi_iter.bi_idx;
+}
+
+static inline sector_t pblk_get_lba(struct bio *bio)
+{
+ return bio->bi_iter.bi_sector / NR_PHY_IN_LOG;
+}
+
+static inline unsigned int pblk_get_secs(struct bio *bio)
+{
+ return bio->bi_iter.bi_size / PBLK_EXPOSED_PAGE_SIZE;
+}
+
+static inline sector_t pblk_get_sector(sector_t lba)
+{
+ return lba * NR_PHY_IN_LOG;
+}
+
+static inline void pblk_setup_uuid(struct pblk *pblk)
+{
+ uuid_le uuid;
+
+ uuid_le_gen(&uuid);
+ memcpy(pblk->instance_uuid, uuid.b, 16);
+}
+#endif /* PBLK_H_ */
}
page = mempool_alloc(rrpc->page_pool, GFP_NOIO);
- if (!page) {
- bio_put(bio);
- return -ENOMEM;
- }
while ((slot = find_first_zero_bit(rblk->invalid_pages,
nr_sec_per_blk)) < nr_sec_per_blk) {
struct rrpc *rrpc = gcb->rrpc;
struct rrpc_block *rblk = gcb->rblk;
struct rrpc_lun *rlun = rblk->rlun;
- struct nvm_tgt_dev *dev = rrpc->dev;
struct ppa_addr ppa;
mempool_free(gcb, rrpc->gcb_pool);
ppa.g.lun = rlun->bppa.g.lun;
ppa.g.blk = rblk->id;
- if (nvm_erase_blk(dev, &ppa, 0))
+ if (nvm_erase_sync(rrpc->dev, &ppa, 1))
goto put_back;
rrpc_put_blk(rrpc, rblk);
for (i = 0; i < npages; i++) {
/* We assume that mapping occurs at 4KB granularity */
- BUG_ON(!(laddr + i >= 0 && laddr + i < rrpc->nr_sects));
+ BUG_ON(!(laddr + i < rrpc->nr_sects));
gp = &rrpc->trans_map[laddr + i];
if (gp->rblk) {
if (!is_gc && rrpc_lock_rq(rrpc, bio, rqd))
return NVM_IO_REQUEUE;
- BUG_ON(!(laddr >= 0 && laddr < rrpc->nr_sects));
+ BUG_ON(!(laddr < rrpc->nr_sects));
gp = &rrpc->trans_map[laddr];
if (gp->rblk) {
}
rqd = mempool_alloc(rrpc->rq_pool, GFP_KERNEL);
- if (!rqd) {
- pr_err_ratelimited("rrpc: not able to queue bio.");
- bio_io_error(bio);
- return BLK_QC_T_NONE;
- }
memset(rqd, 0, sizeof(struct nvm_rq));
err = rrpc_submit_io(rrpc, bio, rqd, NVM_IOTYPE_NONE);
}
nr_blks = nvm_bb_tbl_fold(dev->parent, blks, nr_blks);
- if (nr_blks < 0)
- return nr_blks;
+ if (nr_blks < 0) {
+ ret = nr_blks;
+ goto out;
+ }
for (i = 0; i < nr_blks; i++) {
if (blks[i] == NVM_BLK_T_FREE)
static struct nvm_tgt_type tt_rrpc;
-static void *rrpc_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk)
+static void *rrpc_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk,
+ int flags)
{
struct request_queue *bqueue = dev->q;
struct request_queue *tqueue = tdisk->queue;
want to use the APM X-Gene SLIMpro IPCM support.
config BCM_PDC_MBOX
- tristate "Broadcom PDC Mailbox"
- depends on ARM64 || COMPILE_TEST
+ tristate "Broadcom FlexSparx DMA Mailbox"
+ depends on ARCH_BCM_IPROC || COMPILE_TEST
depends on HAS_DMA
+ help
+ Mailbox implementation for the Broadcom FlexSparx DMA ring manager,
+ which provides access to various offload engines on Broadcom
+ SoCs, including FA2/FA+ on Northstar Plus and PDC on Northstar 2.
+
+config BCM_FLEXRM_MBOX
+ tristate "Broadcom FlexRM Mailbox"
+ depends on ARM64
+ depends on HAS_DMA
+ select GENERIC_MSI_IRQ_DOMAIN
default ARCH_BCM_IPROC
help
- Mailbox implementation for the Broadcom PDC ring manager,
+ Mailbox implementation of the Broadcom FlexRM ring manager,
which provides access to various offload engines on Broadcom
- SoCs. Say Y here if you want to use the Broadcom PDC.
+ SoCs. Say Y here if you want to use the Broadcom FlexRM.
endif
obj-$(CONFIG_BCM_PDC_MBOX) += bcm-pdc-mailbox.o
+obj-$(CONFIG_BCM_FLEXRM_MBOX) += bcm-flexrm-mailbox.o
+
obj-$(CONFIG_TEGRA_HSP_MBOX) += tegra-hsp.o
--- /dev/null
+/* Broadcom FlexRM Mailbox Driver
+ *
+ * Copyright (C) 2017 Broadcom
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Each Broadcom FlexSparx4 offload engine is implemented as an
+ * extension to Broadcom FlexRM ring manager. The FlexRM ring
+ * manager provides a set of rings which can be used to submit
+ * work to a FlexSparx4 offload engine.
+ *
+ * This driver creates a mailbox controller using a set of FlexRM
+ * rings where each mailbox channel represents a separate FlexRM ring.
+ */
+
+#include <asm/barrier.h>
+#include <asm/byteorder.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/err.h>
+#include <linux/idr.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/mailbox_controller.h>
+#include <linux/mailbox_client.h>
+#include <linux/mailbox/brcm-message.h>
+#include <linux/module.h>
+#include <linux/msi.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock.h>
+
+/* ====== FlexRM register defines ===== */
+
+/* FlexRM configuration */
+#define RING_REGS_SIZE 0x10000
+#define RING_DESC_SIZE 8
+#define RING_DESC_INDEX(offset) \
+ ((offset) / RING_DESC_SIZE)
+#define RING_DESC_OFFSET(index) \
+ ((index) * RING_DESC_SIZE)
+#define RING_MAX_REQ_COUNT 1024
+#define RING_BD_ALIGN_ORDER 12
+#define RING_BD_ALIGN_CHECK(addr) \
+ (!((addr) & ((0x1 << RING_BD_ALIGN_ORDER) - 1)))
+#define RING_BD_TOGGLE_INVALID(offset) \
+ (((offset) >> RING_BD_ALIGN_ORDER) & 0x1)
+#define RING_BD_TOGGLE_VALID(offset) \
+ (!RING_BD_TOGGLE_INVALID(offset))
+#define RING_BD_DESC_PER_REQ 32
+#define RING_BD_DESC_COUNT \
+ (RING_MAX_REQ_COUNT * RING_BD_DESC_PER_REQ)
+#define RING_BD_SIZE \
+ (RING_BD_DESC_COUNT * RING_DESC_SIZE)
+#define RING_CMPL_ALIGN_ORDER 13
+#define RING_CMPL_DESC_COUNT RING_MAX_REQ_COUNT
+#define RING_CMPL_SIZE \
+ (RING_CMPL_DESC_COUNT * RING_DESC_SIZE)
+#define RING_VER_MAGIC 0x76303031
+
+/* Per-Ring register offsets */
+#define RING_VER 0x000
+#define RING_BD_START_ADDR 0x004
+#define RING_BD_READ_PTR 0x008
+#define RING_BD_WRITE_PTR 0x00c
+#define RING_BD_READ_PTR_DDR_LS 0x010
+#define RING_BD_READ_PTR_DDR_MS 0x014
+#define RING_CMPL_START_ADDR 0x018
+#define RING_CMPL_WRITE_PTR 0x01c
+#define RING_NUM_REQ_RECV_LS 0x020
+#define RING_NUM_REQ_RECV_MS 0x024
+#define RING_NUM_REQ_TRANS_LS 0x028
+#define RING_NUM_REQ_TRANS_MS 0x02c
+#define RING_NUM_REQ_OUTSTAND 0x030
+#define RING_CONTROL 0x034
+#define RING_FLUSH_DONE 0x038
+#define RING_MSI_ADDR_LS 0x03c
+#define RING_MSI_ADDR_MS 0x040
+#define RING_MSI_CONTROL 0x048
+#define RING_BD_READ_PTR_DDR_CONTROL 0x04c
+#define RING_MSI_DATA_VALUE 0x064
+
+/* Register RING_BD_START_ADDR fields */
+#define BD_LAST_UPDATE_HW_SHIFT 28
+#define BD_LAST_UPDATE_HW_MASK 0x1
+#define BD_START_ADDR_VALUE(pa) \
+ ((u32)((((dma_addr_t)(pa)) >> RING_BD_ALIGN_ORDER) & 0x0fffffff))
+#define BD_START_ADDR_DECODE(val) \
+ ((dma_addr_t)((val) & 0x0fffffff) << RING_BD_ALIGN_ORDER)
+
+/* Register RING_CMPL_START_ADDR fields */
+#define CMPL_START_ADDR_VALUE(pa) \
+ ((u32)((((u64)(pa)) >> RING_CMPL_ALIGN_ORDER) & 0x03ffffff))
+
+/* Register RING_CONTROL fields */
+#define CONTROL_MASK_DISABLE_CONTROL 12
+#define CONTROL_FLUSH_SHIFT 5
+#define CONTROL_ACTIVE_SHIFT 4
+#define CONTROL_RATE_ADAPT_MASK 0xf
+#define CONTROL_RATE_DYNAMIC 0x0
+#define CONTROL_RATE_FAST 0x8
+#define CONTROL_RATE_MEDIUM 0x9
+#define CONTROL_RATE_SLOW 0xa
+#define CONTROL_RATE_IDLE 0xb
+
+/* Register RING_FLUSH_DONE fields */
+#define FLUSH_DONE_MASK 0x1
+
+/* Register RING_MSI_CONTROL fields */
+#define MSI_TIMER_VAL_SHIFT 16
+#define MSI_TIMER_VAL_MASK 0xffff
+#define MSI_ENABLE_SHIFT 15
+#define MSI_ENABLE_MASK 0x1
+#define MSI_COUNT_SHIFT 0
+#define MSI_COUNT_MASK 0x3ff
+
+/* Register RING_BD_READ_PTR_DDR_CONTROL fields */
+#define BD_READ_PTR_DDR_TIMER_VAL_SHIFT 16
+#define BD_READ_PTR_DDR_TIMER_VAL_MASK 0xffff
+#define BD_READ_PTR_DDR_ENABLE_SHIFT 15
+#define BD_READ_PTR_DDR_ENABLE_MASK 0x1
+
+/* ====== FlexRM ring descriptor defines ===== */
+
+/* Completion descriptor format */
+#define CMPL_OPAQUE_SHIFT 0
+#define CMPL_OPAQUE_MASK 0xffff
+#define CMPL_ENGINE_STATUS_SHIFT 16
+#define CMPL_ENGINE_STATUS_MASK 0xffff
+#define CMPL_DME_STATUS_SHIFT 32
+#define CMPL_DME_STATUS_MASK 0xffff
+#define CMPL_RM_STATUS_SHIFT 48
+#define CMPL_RM_STATUS_MASK 0xffff
+
+/* Completion DME status code */
+#define DME_STATUS_MEM_COR_ERR BIT(0)
+#define DME_STATUS_MEM_UCOR_ERR BIT(1)
+#define DME_STATUS_FIFO_UNDERFLOW BIT(2)
+#define DME_STATUS_FIFO_OVERFLOW BIT(3)
+#define DME_STATUS_RRESP_ERR BIT(4)
+#define DME_STATUS_BRESP_ERR BIT(5)
+#define DME_STATUS_ERROR_MASK (DME_STATUS_MEM_COR_ERR | \
+ DME_STATUS_MEM_UCOR_ERR | \
+ DME_STATUS_FIFO_UNDERFLOW | \
+ DME_STATUS_FIFO_OVERFLOW | \
+ DME_STATUS_RRESP_ERR | \
+ DME_STATUS_BRESP_ERR)
+
+/* Completion RM status code */
+#define RM_STATUS_CODE_SHIFT 0
+#define RM_STATUS_CODE_MASK 0x3ff
+#define RM_STATUS_CODE_GOOD 0x0
+#define RM_STATUS_CODE_AE_TIMEOUT 0x3ff
+
+/* General descriptor format */
+#define DESC_TYPE_SHIFT 60
+#define DESC_TYPE_MASK 0xf
+#define DESC_PAYLOAD_SHIFT 0
+#define DESC_PAYLOAD_MASK 0x0fffffffffffffff
+
+/* Null descriptor format */
+#define NULL_TYPE 0
+#define NULL_TOGGLE_SHIFT 58
+#define NULL_TOGGLE_MASK 0x1
+
+/* Header descriptor format */
+#define HEADER_TYPE 1
+#define HEADER_TOGGLE_SHIFT 58
+#define HEADER_TOGGLE_MASK 0x1
+#define HEADER_ENDPKT_SHIFT 57
+#define HEADER_ENDPKT_MASK 0x1
+#define HEADER_STARTPKT_SHIFT 56
+#define HEADER_STARTPKT_MASK 0x1
+#define HEADER_BDCOUNT_SHIFT 36
+#define HEADER_BDCOUNT_MASK 0x1f
+#define HEADER_BDCOUNT_MAX HEADER_BDCOUNT_MASK
+#define HEADER_FLAGS_SHIFT 16
+#define HEADER_FLAGS_MASK 0xffff
+#define HEADER_OPAQUE_SHIFT 0
+#define HEADER_OPAQUE_MASK 0xffff
+
+/* Source (SRC) descriptor format */
+#define SRC_TYPE 2
+#define SRC_LENGTH_SHIFT 44
+#define SRC_LENGTH_MASK 0xffff
+#define SRC_ADDR_SHIFT 0
+#define SRC_ADDR_MASK 0x00000fffffffffff
+
+/* Destination (DST) descriptor format */
+#define DST_TYPE 3
+#define DST_LENGTH_SHIFT 44
+#define DST_LENGTH_MASK 0xffff
+#define DST_ADDR_SHIFT 0
+#define DST_ADDR_MASK 0x00000fffffffffff
+
+/* Immediate (IMM) descriptor format */
+#define IMM_TYPE 4
+#define IMM_DATA_SHIFT 0
+#define IMM_DATA_MASK 0x0fffffffffffffff
+
+/* Next pointer (NPTR) descriptor format */
+#define NPTR_TYPE 5
+#define NPTR_TOGGLE_SHIFT 58
+#define NPTR_TOGGLE_MASK 0x1
+#define NPTR_ADDR_SHIFT 0
+#define NPTR_ADDR_MASK 0x00000fffffffffff
+
+/* Mega source (MSRC) descriptor format */
+#define MSRC_TYPE 6
+#define MSRC_LENGTH_SHIFT 44
+#define MSRC_LENGTH_MASK 0xffff
+#define MSRC_ADDR_SHIFT 0
+#define MSRC_ADDR_MASK 0x00000fffffffffff
+
+/* Mega destination (MDST) descriptor format */
+#define MDST_TYPE 7
+#define MDST_LENGTH_SHIFT 44
+#define MDST_LENGTH_MASK 0xffff
+#define MDST_ADDR_SHIFT 0
+#define MDST_ADDR_MASK 0x00000fffffffffff
+
+/* Source with tlast (SRCT) descriptor format */
+#define SRCT_TYPE 8
+#define SRCT_LENGTH_SHIFT 44
+#define SRCT_LENGTH_MASK 0xffff
+#define SRCT_ADDR_SHIFT 0
+#define SRCT_ADDR_MASK 0x00000fffffffffff
+
+/* Destination with tlast (DSTT) descriptor format */
+#define DSTT_TYPE 9
+#define DSTT_LENGTH_SHIFT 44
+#define DSTT_LENGTH_MASK 0xffff
+#define DSTT_ADDR_SHIFT 0
+#define DSTT_ADDR_MASK 0x00000fffffffffff
+
+/* Immediate with tlast (IMMT) descriptor format */
+#define IMMT_TYPE 10
+#define IMMT_DATA_SHIFT 0
+#define IMMT_DATA_MASK 0x0fffffffffffffff
+
+/* Descriptor helper macros */
+#define DESC_DEC(_d, _s, _m) (((_d) >> (_s)) & (_m))
+#define DESC_ENC(_d, _v, _s, _m) \
+ do { \
+ (_d) &= ~((u64)(_m) << (_s)); \
+ (_d) |= (((u64)(_v) & (_m)) << (_s)); \
+ } while (0)
+
+/* ====== FlexRM data structures ===== */
+
+struct flexrm_ring {
+ /* Unprotected members */
+ int num;
+ struct flexrm_mbox *mbox;
+ void __iomem *regs;
+ bool irq_requested;
+ unsigned int irq;
+ unsigned int msi_timer_val;
+ unsigned int msi_count_threshold;
+ struct ida requests_ida;
+ struct brcm_message *requests[RING_MAX_REQ_COUNT];
+ void *bd_base;
+ dma_addr_t bd_dma_base;
+ u32 bd_write_offset;
+ void *cmpl_base;
+ dma_addr_t cmpl_dma_base;
+ /* Protected members */
+ spinlock_t lock;
+ struct brcm_message *last_pending_msg;
+ u32 cmpl_read_offset;
+};
+
+struct flexrm_mbox {
+ struct device *dev;
+ void __iomem *regs;
+ u32 num_rings;
+ struct flexrm_ring *rings;
+ struct dma_pool *bd_pool;
+ struct dma_pool *cmpl_pool;
+ struct mbox_controller controller;
+};
+
+/* ====== FlexRM ring descriptor helper routines ===== */
+
+static u64 flexrm_read_desc(void *desc_ptr)
+{
+ return le64_to_cpu(*((u64 *)desc_ptr));
+}
+
+static void flexrm_write_desc(void *desc_ptr, u64 desc)
+{
+ *((u64 *)desc_ptr) = cpu_to_le64(desc);
+}
+
+static u32 flexrm_cmpl_desc_to_reqid(u64 cmpl_desc)
+{
+ return (u32)(cmpl_desc & CMPL_OPAQUE_MASK);
+}
+
+static int flexrm_cmpl_desc_to_error(u64 cmpl_desc)
+{
+ u32 status;
+
+ status = DESC_DEC(cmpl_desc, CMPL_DME_STATUS_SHIFT,
+ CMPL_DME_STATUS_MASK);
+ if (status & DME_STATUS_ERROR_MASK)
+ return -EIO;
+
+ status = DESC_DEC(cmpl_desc, CMPL_RM_STATUS_SHIFT,
+ CMPL_RM_STATUS_MASK);
+ status &= RM_STATUS_CODE_MASK;
+ if (status == RM_STATUS_CODE_AE_TIMEOUT)
+ return -ETIMEDOUT;
+
+ return 0;
+}
+
+static bool flexrm_is_next_table_desc(void *desc_ptr)
+{
+ u64 desc = flexrm_read_desc(desc_ptr);
+ u32 type = DESC_DEC(desc, DESC_TYPE_SHIFT, DESC_TYPE_MASK);
+
+ return (type == NPTR_TYPE) ? true : false;
+}
+
+static u64 flexrm_next_table_desc(u32 toggle, dma_addr_t next_addr)
+{
+ u64 desc = 0;
+
+ DESC_ENC(desc, NPTR_TYPE, DESC_TYPE_SHIFT, DESC_TYPE_MASK);
+ DESC_ENC(desc, toggle, NPTR_TOGGLE_SHIFT, NPTR_TOGGLE_MASK);
+ DESC_ENC(desc, next_addr, NPTR_ADDR_SHIFT, NPTR_ADDR_MASK);
+
+ return desc;
+}
+
+static u64 flexrm_null_desc(u32 toggle)
+{
+ u64 desc = 0;
+
+ DESC_ENC(desc, NULL_TYPE, DESC_TYPE_SHIFT, DESC_TYPE_MASK);
+ DESC_ENC(desc, toggle, NULL_TOGGLE_SHIFT, NULL_TOGGLE_MASK);
+
+ return desc;
+}
+
+static u32 flexrm_estimate_header_desc_count(u32 nhcnt)
+{
+ u32 hcnt = nhcnt / HEADER_BDCOUNT_MAX;
+
+ if (!(nhcnt % HEADER_BDCOUNT_MAX))
+ hcnt += 1;
+
+ return hcnt;
+}
+
+static void flexrm_flip_header_toogle(void *desc_ptr)
+{
+ u64 desc = flexrm_read_desc(desc_ptr);
+
+ if (desc & ((u64)0x1 << HEADER_TOGGLE_SHIFT))
+ desc &= ~((u64)0x1 << HEADER_TOGGLE_SHIFT);
+ else
+ desc |= ((u64)0x1 << HEADER_TOGGLE_SHIFT);
+
+ flexrm_write_desc(desc_ptr, desc);
+}
+
+static u64 flexrm_header_desc(u32 toggle, u32 startpkt, u32 endpkt,
+ u32 bdcount, u32 flags, u32 opaque)
+{
+ u64 desc = 0;
+
+ DESC_ENC(desc, HEADER_TYPE, DESC_TYPE_SHIFT, DESC_TYPE_MASK);
+ DESC_ENC(desc, toggle, HEADER_TOGGLE_SHIFT, HEADER_TOGGLE_MASK);
+ DESC_ENC(desc, startpkt, HEADER_STARTPKT_SHIFT, HEADER_STARTPKT_MASK);
+ DESC_ENC(desc, endpkt, HEADER_ENDPKT_SHIFT, HEADER_ENDPKT_MASK);
+ DESC_ENC(desc, bdcount, HEADER_BDCOUNT_SHIFT, HEADER_BDCOUNT_MASK);
+ DESC_ENC(desc, flags, HEADER_FLAGS_SHIFT, HEADER_FLAGS_MASK);
+ DESC_ENC(desc, opaque, HEADER_OPAQUE_SHIFT, HEADER_OPAQUE_MASK);
+
+ return desc;
+}
+
+static void flexrm_enqueue_desc(u32 nhpos, u32 nhcnt, u32 reqid,
+ u64 desc, void **desc_ptr, u32 *toggle,
+ void *start_desc, void *end_desc)
+{
+ u64 d;
+ u32 nhavail, _toggle, _startpkt, _endpkt, _bdcount;
+
+ /* Sanity check */
+ if (nhcnt <= nhpos)
+ return;
+
+ /*
+ * Each request or packet start with a HEADER descriptor followed
+ * by one or more non-HEADER descriptors (SRC, SRCT, MSRC, DST,
+ * DSTT, MDST, IMM, and IMMT). The number of non-HEADER descriptors
+ * following a HEADER descriptor is represented by BDCOUNT field
+ * of HEADER descriptor. The max value of BDCOUNT field is 31 which
+ * means we can only have 31 non-HEADER descriptors following one
+ * HEADER descriptor.
+ *
+ * In general use, number of non-HEADER descriptors can easily go
+ * beyond 31. To tackle this situation, we have packet (or request)
+ * extenstion bits (STARTPKT and ENDPKT) in the HEADER descriptor.
+ *
+ * To use packet extension, the first HEADER descriptor of request
+ * (or packet) will have STARTPKT=1 and ENDPKT=0. The intermediate
+ * HEADER descriptors will have STARTPKT=0 and ENDPKT=0. The last
+ * HEADER descriptor will have STARTPKT=0 and ENDPKT=1. Also, the
+ * TOGGLE bit of the first HEADER will be set to invalid state to
+ * ensure that FlexRM does not start fetching descriptors till all
+ * descriptors are enqueued. The user of this function will flip
+ * the TOGGLE bit of first HEADER after all descriptors are
+ * enqueued.
+ */
+
+ if ((nhpos % HEADER_BDCOUNT_MAX == 0) && (nhcnt - nhpos)) {
+ /* Prepare the header descriptor */
+ nhavail = (nhcnt - nhpos);
+ _toggle = (nhpos == 0) ? !(*toggle) : (*toggle);
+ _startpkt = (nhpos == 0) ? 0x1 : 0x0;
+ _endpkt = (nhavail <= HEADER_BDCOUNT_MAX) ? 0x1 : 0x0;
+ _bdcount = (nhavail <= HEADER_BDCOUNT_MAX) ?
+ nhavail : HEADER_BDCOUNT_MAX;
+ if (nhavail <= HEADER_BDCOUNT_MAX)
+ _bdcount = nhavail;
+ else
+ _bdcount = HEADER_BDCOUNT_MAX;
+ d = flexrm_header_desc(_toggle, _startpkt, _endpkt,
+ _bdcount, 0x0, reqid);
+
+ /* Write header descriptor */
+ flexrm_write_desc(*desc_ptr, d);
+
+ /* Point to next descriptor */
+ *desc_ptr += sizeof(desc);
+ if (*desc_ptr == end_desc)
+ *desc_ptr = start_desc;
+
+ /* Skip next pointer descriptors */
+ while (flexrm_is_next_table_desc(*desc_ptr)) {
+ *toggle = (*toggle) ? 0 : 1;
+ *desc_ptr += sizeof(desc);
+ if (*desc_ptr == end_desc)
+ *desc_ptr = start_desc;
+ }
+ }
+
+ /* Write desired descriptor */
+ flexrm_write_desc(*desc_ptr, desc);
+
+ /* Point to next descriptor */
+ *desc_ptr += sizeof(desc);
+ if (*desc_ptr == end_desc)
+ *desc_ptr = start_desc;
+
+ /* Skip next pointer descriptors */
+ while (flexrm_is_next_table_desc(*desc_ptr)) {
+ *toggle = (*toggle) ? 0 : 1;
+ *desc_ptr += sizeof(desc);
+ if (*desc_ptr == end_desc)
+ *desc_ptr = start_desc;
+ }
+}
+
+static u64 flexrm_src_desc(dma_addr_t addr, unsigned int length)
+{
+ u64 desc = 0;
+
+ DESC_ENC(desc, SRC_TYPE, DESC_TYPE_SHIFT, DESC_TYPE_MASK);
+ DESC_ENC(desc, length, SRC_LENGTH_SHIFT, SRC_LENGTH_MASK);
+ DESC_ENC(desc, addr, SRC_ADDR_SHIFT, SRC_ADDR_MASK);
+
+ return desc;
+}
+
+static u64 flexrm_msrc_desc(dma_addr_t addr, unsigned int length_div_16)
+{
+ u64 desc = 0;
+
+ DESC_ENC(desc, MSRC_TYPE, DESC_TYPE_SHIFT, DESC_TYPE_MASK);
+ DESC_ENC(desc, length_div_16, MSRC_LENGTH_SHIFT, MSRC_LENGTH_MASK);
+ DESC_ENC(desc, addr, MSRC_ADDR_SHIFT, MSRC_ADDR_MASK);
+
+ return desc;
+}
+
+static u64 flexrm_dst_desc(dma_addr_t addr, unsigned int length)
+{
+ u64 desc = 0;
+
+ DESC_ENC(desc, DST_TYPE, DESC_TYPE_SHIFT, DESC_TYPE_MASK);
+ DESC_ENC(desc, length, DST_LENGTH_SHIFT, DST_LENGTH_MASK);
+ DESC_ENC(desc, addr, DST_ADDR_SHIFT, DST_ADDR_MASK);
+
+ return desc;
+}
+
+static u64 flexrm_mdst_desc(dma_addr_t addr, unsigned int length_div_16)
+{
+ u64 desc = 0;
+
+ DESC_ENC(desc, MDST_TYPE, DESC_TYPE_SHIFT, DESC_TYPE_MASK);
+ DESC_ENC(desc, length_div_16, MDST_LENGTH_SHIFT, MDST_LENGTH_MASK);
+ DESC_ENC(desc, addr, MDST_ADDR_SHIFT, MDST_ADDR_MASK);
+
+ return desc;
+}
+
+static u64 flexrm_imm_desc(u64 data)
+{
+ u64 desc = 0;
+
+ DESC_ENC(desc, IMM_TYPE, DESC_TYPE_SHIFT, DESC_TYPE_MASK);
+ DESC_ENC(desc, data, IMM_DATA_SHIFT, IMM_DATA_MASK);
+
+ return desc;
+}
+
+static u64 flexrm_srct_desc(dma_addr_t addr, unsigned int length)
+{
+ u64 desc = 0;
+
+ DESC_ENC(desc, SRCT_TYPE, DESC_TYPE_SHIFT, DESC_TYPE_MASK);
+ DESC_ENC(desc, length, SRCT_LENGTH_SHIFT, SRCT_LENGTH_MASK);
+ DESC_ENC(desc, addr, SRCT_ADDR_SHIFT, SRCT_ADDR_MASK);
+
+ return desc;
+}
+
+static u64 flexrm_dstt_desc(dma_addr_t addr, unsigned int length)
+{
+ u64 desc = 0;
+
+ DESC_ENC(desc, DSTT_TYPE, DESC_TYPE_SHIFT, DESC_TYPE_MASK);
+ DESC_ENC(desc, length, DSTT_LENGTH_SHIFT, DSTT_LENGTH_MASK);
+ DESC_ENC(desc, addr, DSTT_ADDR_SHIFT, DSTT_ADDR_MASK);
+
+ return desc;
+}
+
+static u64 flexrm_immt_desc(u64 data)
+{
+ u64 desc = 0;
+
+ DESC_ENC(desc, IMMT_TYPE, DESC_TYPE_SHIFT, DESC_TYPE_MASK);
+ DESC_ENC(desc, data, IMMT_DATA_SHIFT, IMMT_DATA_MASK);
+
+ return desc;
+}
+
+static bool flexrm_spu_sanity_check(struct brcm_message *msg)
+{
+ struct scatterlist *sg;
+
+ if (!msg->spu.src || !msg->spu.dst)
+ return false;
+ for (sg = msg->spu.src; sg; sg = sg_next(sg)) {
+ if (sg->length & 0xf) {
+ if (sg->length > SRC_LENGTH_MASK)
+ return false;
+ } else {
+ if (sg->length > (MSRC_LENGTH_MASK * 16))
+ return false;
+ }
+ }
+ for (sg = msg->spu.dst; sg; sg = sg_next(sg)) {
+ if (sg->length & 0xf) {
+ if (sg->length > DST_LENGTH_MASK)
+ return false;
+ } else {
+ if (sg->length > (MDST_LENGTH_MASK * 16))
+ return false;
+ }
+ }
+
+ return true;
+}
+
+static u32 flexrm_spu_estimate_nonheader_desc_count(struct brcm_message *msg)
+{
+ u32 cnt = 0;
+ unsigned int dst_target = 0;
+ struct scatterlist *src_sg = msg->spu.src, *dst_sg = msg->spu.dst;
+
+ while (src_sg || dst_sg) {
+ if (src_sg) {
+ cnt++;
+ dst_target = src_sg->length;
+ src_sg = sg_next(src_sg);
+ } else
+ dst_target = UINT_MAX;
+
+ while (dst_target && dst_sg) {
+ cnt++;
+ if (dst_sg->length < dst_target)
+ dst_target -= dst_sg->length;
+ else
+ dst_target = 0;
+ dst_sg = sg_next(dst_sg);
+ }
+ }
+
+ return cnt;
+}
+
+static int flexrm_spu_dma_map(struct device *dev, struct brcm_message *msg)
+{
+ int rc;
+
+ rc = dma_map_sg(dev, msg->spu.src, sg_nents(msg->spu.src),
+ DMA_TO_DEVICE);
+ if (rc < 0)
+ return rc;
+
+ rc = dma_map_sg(dev, msg->spu.dst, sg_nents(msg->spu.dst),
+ DMA_FROM_DEVICE);
+ if (rc < 0) {
+ dma_unmap_sg(dev, msg->spu.src, sg_nents(msg->spu.src),
+ DMA_TO_DEVICE);
+ return rc;
+ }
+
+ return 0;
+}
+
+static void flexrm_spu_dma_unmap(struct device *dev, struct brcm_message *msg)
+{
+ dma_unmap_sg(dev, msg->spu.dst, sg_nents(msg->spu.dst),
+ DMA_FROM_DEVICE);
+ dma_unmap_sg(dev, msg->spu.src, sg_nents(msg->spu.src),
+ DMA_TO_DEVICE);
+}
+
+static void *flexrm_spu_write_descs(struct brcm_message *msg, u32 nhcnt,
+ u32 reqid, void *desc_ptr, u32 toggle,
+ void *start_desc, void *end_desc)
+{
+ u64 d;
+ u32 nhpos = 0;
+ void *orig_desc_ptr = desc_ptr;
+ unsigned int dst_target = 0;
+ struct scatterlist *src_sg = msg->spu.src, *dst_sg = msg->spu.dst;
+
+ while (src_sg || dst_sg) {
+ if (src_sg) {
+ if (sg_dma_len(src_sg) & 0xf)
+ d = flexrm_src_desc(sg_dma_address(src_sg),
+ sg_dma_len(src_sg));
+ else
+ d = flexrm_msrc_desc(sg_dma_address(src_sg),
+ sg_dma_len(src_sg)/16);
+ flexrm_enqueue_desc(nhpos, nhcnt, reqid,
+ d, &desc_ptr, &toggle,
+ start_desc, end_desc);
+ nhpos++;
+ dst_target = sg_dma_len(src_sg);
+ src_sg = sg_next(src_sg);
+ } else
+ dst_target = UINT_MAX;
+
+ while (dst_target && dst_sg) {
+ if (sg_dma_len(dst_sg) & 0xf)
+ d = flexrm_dst_desc(sg_dma_address(dst_sg),
+ sg_dma_len(dst_sg));
+ else
+ d = flexrm_mdst_desc(sg_dma_address(dst_sg),
+ sg_dma_len(dst_sg)/16);
+ flexrm_enqueue_desc(nhpos, nhcnt, reqid,
+ d, &desc_ptr, &toggle,
+ start_desc, end_desc);
+ nhpos++;
+ if (sg_dma_len(dst_sg) < dst_target)
+ dst_target -= sg_dma_len(dst_sg);
+ else
+ dst_target = 0;
+ dst_sg = sg_next(dst_sg);
+ }
+ }
+
+ /* Null descriptor with invalid toggle bit */
+ flexrm_write_desc(desc_ptr, flexrm_null_desc(!toggle));
+
+ /* Ensure that descriptors have been written to memory */
+ wmb();
+
+ /* Flip toggle bit in header */
+ flexrm_flip_header_toogle(orig_desc_ptr);
+
+ return desc_ptr;
+}
+
+static bool flexrm_sba_sanity_check(struct brcm_message *msg)
+{
+ u32 i;
+
+ if (!msg->sba.cmds || !msg->sba.cmds_count)
+ return false;
+
+ for (i = 0; i < msg->sba.cmds_count; i++) {
+ if (((msg->sba.cmds[i].flags & BRCM_SBA_CMD_TYPE_B) ||
+ (msg->sba.cmds[i].flags & BRCM_SBA_CMD_TYPE_C)) &&
+ (msg->sba.cmds[i].flags & BRCM_SBA_CMD_HAS_OUTPUT))
+ return false;
+ if ((msg->sba.cmds[i].flags & BRCM_SBA_CMD_TYPE_B) &&
+ (msg->sba.cmds[i].data_len > SRCT_LENGTH_MASK))
+ return false;
+ if ((msg->sba.cmds[i].flags & BRCM_SBA_CMD_TYPE_C) &&
+ (msg->sba.cmds[i].data_len > SRCT_LENGTH_MASK))
+ return false;
+ if ((msg->sba.cmds[i].flags & BRCM_SBA_CMD_HAS_RESP) &&
+ (msg->sba.cmds[i].resp_len > DSTT_LENGTH_MASK))
+ return false;
+ if ((msg->sba.cmds[i].flags & BRCM_SBA_CMD_HAS_OUTPUT) &&
+ (msg->sba.cmds[i].data_len > DSTT_LENGTH_MASK))
+ return false;
+ }
+
+ return true;
+}
+
+static u32 flexrm_sba_estimate_nonheader_desc_count(struct brcm_message *msg)
+{
+ u32 i, cnt;
+
+ cnt = 0;
+ for (i = 0; i < msg->sba.cmds_count; i++) {
+ cnt++;
+
+ if ((msg->sba.cmds[i].flags & BRCM_SBA_CMD_TYPE_B) ||
+ (msg->sba.cmds[i].flags & BRCM_SBA_CMD_TYPE_C))
+ cnt++;
+
+ if (msg->sba.cmds[i].flags & BRCM_SBA_CMD_HAS_RESP)
+ cnt++;
+
+ if (msg->sba.cmds[i].flags & BRCM_SBA_CMD_HAS_OUTPUT)
+ cnt++;
+ }
+
+ return cnt;
+}
+
+static void *flexrm_sba_write_descs(struct brcm_message *msg, u32 nhcnt,
+ u32 reqid, void *desc_ptr, u32 toggle,
+ void *start_desc, void *end_desc)
+{
+ u64 d;
+ u32 i, nhpos = 0;
+ struct brcm_sba_command *c;
+ void *orig_desc_ptr = desc_ptr;
+
+ /* Convert SBA commands into descriptors */
+ for (i = 0; i < msg->sba.cmds_count; i++) {
+ c = &msg->sba.cmds[i];
+
+ if ((c->flags & BRCM_SBA_CMD_HAS_RESP) &&
+ (c->flags & BRCM_SBA_CMD_HAS_OUTPUT)) {
+ /* Destination response descriptor */
+ d = flexrm_dst_desc(c->resp, c->resp_len);
+ flexrm_enqueue_desc(nhpos, nhcnt, reqid,
+ d, &desc_ptr, &toggle,
+ start_desc, end_desc);
+ nhpos++;
+ } else if (c->flags & BRCM_SBA_CMD_HAS_RESP) {
+ /* Destination response with tlast descriptor */
+ d = flexrm_dstt_desc(c->resp, c->resp_len);
+ flexrm_enqueue_desc(nhpos, nhcnt, reqid,
+ d, &desc_ptr, &toggle,
+ start_desc, end_desc);
+ nhpos++;
+ }
+
+ if (c->flags & BRCM_SBA_CMD_HAS_OUTPUT) {
+ /* Destination with tlast descriptor */
+ d = flexrm_dstt_desc(c->data, c->data_len);
+ flexrm_enqueue_desc(nhpos, nhcnt, reqid,
+ d, &desc_ptr, &toggle,
+ start_desc, end_desc);
+ nhpos++;
+ }
+
+ if (c->flags & BRCM_SBA_CMD_TYPE_B) {
+ /* Command as immediate descriptor */
+ d = flexrm_imm_desc(c->cmd);
+ flexrm_enqueue_desc(nhpos, nhcnt, reqid,
+ d, &desc_ptr, &toggle,
+ start_desc, end_desc);
+ nhpos++;
+ } else {
+ /* Command as immediate descriptor with tlast */
+ d = flexrm_immt_desc(c->cmd);
+ flexrm_enqueue_desc(nhpos, nhcnt, reqid,
+ d, &desc_ptr, &toggle,
+ start_desc, end_desc);
+ nhpos++;
+ }
+
+ if ((c->flags & BRCM_SBA_CMD_TYPE_B) ||
+ (c->flags & BRCM_SBA_CMD_TYPE_C)) {
+ /* Source with tlast descriptor */
+ d = flexrm_srct_desc(c->data, c->data_len);
+ flexrm_enqueue_desc(nhpos, nhcnt, reqid,
+ d, &desc_ptr, &toggle,
+ start_desc, end_desc);
+ nhpos++;
+ }
+ }
+
+ /* Null descriptor with invalid toggle bit */
+ flexrm_write_desc(desc_ptr, flexrm_null_desc(!toggle));
+
+ /* Ensure that descriptors have been written to memory */
+ wmb();
+
+ /* Flip toggle bit in header */
+ flexrm_flip_header_toogle(orig_desc_ptr);
+
+ return desc_ptr;
+}
+
+static bool flexrm_sanity_check(struct brcm_message *msg)
+{
+ if (!msg)
+ return false;
+
+ switch (msg->type) {
+ case BRCM_MESSAGE_SPU:
+ return flexrm_spu_sanity_check(msg);
+ case BRCM_MESSAGE_SBA:
+ return flexrm_sba_sanity_check(msg);
+ default:
+ return false;
+ };
+}
+
+static u32 flexrm_estimate_nonheader_desc_count(struct brcm_message *msg)
+{
+ if (!msg)
+ return 0;
+
+ switch (msg->type) {
+ case BRCM_MESSAGE_SPU:
+ return flexrm_spu_estimate_nonheader_desc_count(msg);
+ case BRCM_MESSAGE_SBA:
+ return flexrm_sba_estimate_nonheader_desc_count(msg);
+ default:
+ return 0;
+ };
+}
+
+static int flexrm_dma_map(struct device *dev, struct brcm_message *msg)
+{
+ if (!dev || !msg)
+ return -EINVAL;
+
+ switch (msg->type) {
+ case BRCM_MESSAGE_SPU:
+ return flexrm_spu_dma_map(dev, msg);
+ default:
+ break;
+ }
+
+ return 0;
+}
+
+static void flexrm_dma_unmap(struct device *dev, struct brcm_message *msg)
+{
+ if (!dev || !msg)
+ return;
+
+ switch (msg->type) {
+ case BRCM_MESSAGE_SPU:
+ flexrm_spu_dma_unmap(dev, msg);
+ break;
+ default:
+ break;
+ }
+}
+
+static void *flexrm_write_descs(struct brcm_message *msg, u32 nhcnt,
+ u32 reqid, void *desc_ptr, u32 toggle,
+ void *start_desc, void *end_desc)
+{
+ if (!msg || !desc_ptr || !start_desc || !end_desc)
+ return ERR_PTR(-ENOTSUPP);
+
+ if ((desc_ptr < start_desc) || (end_desc <= desc_ptr))
+ return ERR_PTR(-ERANGE);
+
+ switch (msg->type) {
+ case BRCM_MESSAGE_SPU:
+ return flexrm_spu_write_descs(msg, nhcnt, reqid,
+ desc_ptr, toggle,
+ start_desc, end_desc);
+ case BRCM_MESSAGE_SBA:
+ return flexrm_sba_write_descs(msg, nhcnt, reqid,
+ desc_ptr, toggle,
+ start_desc, end_desc);
+ default:
+ return ERR_PTR(-ENOTSUPP);
+ };
+}
+
+/* ====== FlexRM driver helper routines ===== */
+
+static int flexrm_new_request(struct flexrm_ring *ring,
+ struct brcm_message *batch_msg,
+ struct brcm_message *msg)
+{
+ void *next;
+ unsigned long flags;
+ u32 val, count, nhcnt;
+ u32 read_offset, write_offset;
+ bool exit_cleanup = false;
+ int ret = 0, reqid;
+
+ /* Do sanity check on message */
+ if (!flexrm_sanity_check(msg))
+ return -EIO;
+ msg->error = 0;
+
+ /* If no requests possible then save data pointer and goto done. */
+ reqid = ida_simple_get(&ring->requests_ida, 0,
+ RING_MAX_REQ_COUNT, GFP_KERNEL);
+ if (reqid < 0) {
+ spin_lock_irqsave(&ring->lock, flags);
+ if (batch_msg)
+ ring->last_pending_msg = batch_msg;
+ else
+ ring->last_pending_msg = msg;
+ spin_unlock_irqrestore(&ring->lock, flags);
+ return 0;
+ }
+ ring->requests[reqid] = msg;
+
+ /* Do DMA mappings for the message */
+ ret = flexrm_dma_map(ring->mbox->dev, msg);
+ if (ret < 0) {
+ ring->requests[reqid] = NULL;
+ ida_simple_remove(&ring->requests_ida, reqid);
+ return ret;
+ }
+
+ /* If last_pending_msg is already set then goto done with error */
+ spin_lock_irqsave(&ring->lock, flags);
+ if (ring->last_pending_msg)
+ ret = -ENOSPC;
+ spin_unlock_irqrestore(&ring->lock, flags);
+ if (ret < 0) {
+ dev_warn(ring->mbox->dev, "no space in ring %d\n", ring->num);
+ exit_cleanup = true;
+ goto exit;
+ }
+
+ /* Determine current HW BD read offset */
+ read_offset = readl_relaxed(ring->regs + RING_BD_READ_PTR);
+ val = readl_relaxed(ring->regs + RING_BD_START_ADDR);
+ read_offset *= RING_DESC_SIZE;
+ read_offset += (u32)(BD_START_ADDR_DECODE(val) - ring->bd_dma_base);
+
+ /*
+ * Number required descriptors = number of non-header descriptors +
+ * number of header descriptors +
+ * 1x null descriptor
+ */
+ nhcnt = flexrm_estimate_nonheader_desc_count(msg);
+ count = flexrm_estimate_header_desc_count(nhcnt) + nhcnt + 1;
+
+ /* Check for available descriptor space. */
+ write_offset = ring->bd_write_offset;
+ while (count) {
+ if (!flexrm_is_next_table_desc(ring->bd_base + write_offset))
+ count--;
+ write_offset += RING_DESC_SIZE;
+ if (write_offset == RING_BD_SIZE)
+ write_offset = 0x0;
+ if (write_offset == read_offset)
+ break;
+ }
+ if (count) {
+ spin_lock_irqsave(&ring->lock, flags);
+ if (batch_msg)
+ ring->last_pending_msg = batch_msg;
+ else
+ ring->last_pending_msg = msg;
+ spin_unlock_irqrestore(&ring->lock, flags);
+ ret = 0;
+ exit_cleanup = true;
+ goto exit;
+ }
+
+ /* Write descriptors to ring */
+ next = flexrm_write_descs(msg, nhcnt, reqid,
+ ring->bd_base + ring->bd_write_offset,
+ RING_BD_TOGGLE_VALID(ring->bd_write_offset),
+ ring->bd_base, ring->bd_base + RING_BD_SIZE);
+ if (IS_ERR(next)) {
+ ret = PTR_ERR(next);
+ exit_cleanup = true;
+ goto exit;
+ }
+
+ /* Save ring BD write offset */
+ ring->bd_write_offset = (unsigned long)(next - ring->bd_base);
+
+exit:
+ /* Update error status in message */
+ msg->error = ret;
+
+ /* Cleanup if we failed */
+ if (exit_cleanup) {
+ flexrm_dma_unmap(ring->mbox->dev, msg);
+ ring->requests[reqid] = NULL;
+ ida_simple_remove(&ring->requests_ida, reqid);
+ }
+
+ return ret;
+}
+
+static int flexrm_process_completions(struct flexrm_ring *ring)
+{
+ u64 desc;
+ int err, count = 0;
+ unsigned long flags;
+ struct brcm_message *msg = NULL;
+ u32 reqid, cmpl_read_offset, cmpl_write_offset;
+ struct mbox_chan *chan = &ring->mbox->controller.chans[ring->num];
+
+ spin_lock_irqsave(&ring->lock, flags);
+
+ /* Check last_pending_msg */
+ if (ring->last_pending_msg) {
+ msg = ring->last_pending_msg;
+ ring->last_pending_msg = NULL;
+ }
+
+ /*
+ * Get current completion read and write offset
+ *
+ * Note: We should read completion write pointer atleast once
+ * after we get a MSI interrupt because HW maintains internal
+ * MSI status which will allow next MSI interrupt only after
+ * completion write pointer is read.
+ */
+ cmpl_write_offset = readl_relaxed(ring->regs + RING_CMPL_WRITE_PTR);
+ cmpl_write_offset *= RING_DESC_SIZE;
+ cmpl_read_offset = ring->cmpl_read_offset;
+ ring->cmpl_read_offset = cmpl_write_offset;
+
+ spin_unlock_irqrestore(&ring->lock, flags);
+
+ /* If last_pending_msg was set then queue it back */
+ if (msg)
+ mbox_send_message(chan, msg);
+
+ /* For each completed request notify mailbox clients */
+ reqid = 0;
+ while (cmpl_read_offset != cmpl_write_offset) {
+ /* Dequeue next completion descriptor */
+ desc = *((u64 *)(ring->cmpl_base + cmpl_read_offset));
+
+ /* Next read offset */
+ cmpl_read_offset += RING_DESC_SIZE;
+ if (cmpl_read_offset == RING_CMPL_SIZE)
+ cmpl_read_offset = 0;
+
+ /* Decode error from completion descriptor */
+ err = flexrm_cmpl_desc_to_error(desc);
+ if (err < 0) {
+ dev_warn(ring->mbox->dev,
+ "got completion desc=0x%lx with error %d",
+ (unsigned long)desc, err);
+ }
+
+ /* Determine request id from completion descriptor */
+ reqid = flexrm_cmpl_desc_to_reqid(desc);
+
+ /* Determine message pointer based on reqid */
+ msg = ring->requests[reqid];
+ if (!msg) {
+ dev_warn(ring->mbox->dev,
+ "null msg pointer for completion desc=0x%lx",
+ (unsigned long)desc);
+ continue;
+ }
+
+ /* Release reqid for recycling */
+ ring->requests[reqid] = NULL;
+ ida_simple_remove(&ring->requests_ida, reqid);
+
+ /* Unmap DMA mappings */
+ flexrm_dma_unmap(ring->mbox->dev, msg);
+
+ /* Give-back message to mailbox client */
+ msg->error = err;
+ mbox_chan_received_data(chan, msg);
+
+ /* Increment number of completions processed */
+ count++;
+ }
+
+ return count;
+}
+
+/* ====== FlexRM interrupt handler ===== */
+
+static irqreturn_t flexrm_irq_event(int irq, void *dev_id)
+{
+ /* We only have MSI for completions so just wakeup IRQ thread */
+ /* Ring related errors will be informed via completion descriptors */
+
+ return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t flexrm_irq_thread(int irq, void *dev_id)
+{
+ flexrm_process_completions(dev_id);
+
+ return IRQ_HANDLED;
+}
+
+/* ====== FlexRM mailbox callbacks ===== */
+
+static int flexrm_send_data(struct mbox_chan *chan, void *data)
+{
+ int i, rc;
+ struct flexrm_ring *ring = chan->con_priv;
+ struct brcm_message *msg = data;
+
+ if (msg->type == BRCM_MESSAGE_BATCH) {
+ for (i = msg->batch.msgs_queued;
+ i < msg->batch.msgs_count; i++) {
+ rc = flexrm_new_request(ring, msg,
+ &msg->batch.msgs[i]);
+ if (rc) {
+ msg->error = rc;
+ return rc;
+ }
+ msg->batch.msgs_queued++;
+ }
+ return 0;
+ }
+
+ return flexrm_new_request(ring, NULL, data);
+}
+
+static bool flexrm_peek_data(struct mbox_chan *chan)
+{
+ int cnt = flexrm_process_completions(chan->con_priv);
+
+ return (cnt > 0) ? true : false;
+}
+
+static int flexrm_startup(struct mbox_chan *chan)
+{
+ u64 d;
+ u32 val, off;
+ int ret = 0;
+ dma_addr_t next_addr;
+ struct flexrm_ring *ring = chan->con_priv;
+
+ /* Allocate BD memory */
+ ring->bd_base = dma_pool_alloc(ring->mbox->bd_pool,
+ GFP_KERNEL, &ring->bd_dma_base);
+ if (!ring->bd_base) {
+ dev_err(ring->mbox->dev, "can't allocate BD memory\n");
+ ret = -ENOMEM;
+ goto fail;
+ }
+
+ /* Configure next table pointer entries in BD memory */
+ for (off = 0; off < RING_BD_SIZE; off += RING_DESC_SIZE) {
+ next_addr = off + RING_DESC_SIZE;
+ if (next_addr == RING_BD_SIZE)
+ next_addr = 0;
+ next_addr += ring->bd_dma_base;
+ if (RING_BD_ALIGN_CHECK(next_addr))
+ d = flexrm_next_table_desc(RING_BD_TOGGLE_VALID(off),
+ next_addr);
+ else
+ d = flexrm_null_desc(RING_BD_TOGGLE_INVALID(off));
+ flexrm_write_desc(ring->bd_base + off, d);
+ }
+
+ /* Allocate completion memory */
+ ring->cmpl_base = dma_pool_alloc(ring->mbox->cmpl_pool,
+ GFP_KERNEL, &ring->cmpl_dma_base);
+ if (!ring->cmpl_base) {
+ dev_err(ring->mbox->dev, "can't allocate completion memory\n");
+ ret = -ENOMEM;
+ goto fail_free_bd_memory;
+ }
+ memset(ring->cmpl_base, 0, RING_CMPL_SIZE);
+
+ /* Request IRQ */
+ if (ring->irq == UINT_MAX) {
+ dev_err(ring->mbox->dev, "ring IRQ not available\n");
+ ret = -ENODEV;
+ goto fail_free_cmpl_memory;
+ }
+ ret = request_threaded_irq(ring->irq,
+ flexrm_irq_event,
+ flexrm_irq_thread,
+ 0, dev_name(ring->mbox->dev), ring);
+ if (ret) {
+ dev_err(ring->mbox->dev, "failed to request ring IRQ\n");
+ goto fail_free_cmpl_memory;
+ }
+ ring->irq_requested = true;
+
+ /* Disable/inactivate ring */
+ writel_relaxed(0x0, ring->regs + RING_CONTROL);
+
+ /* Program BD start address */
+ val = BD_START_ADDR_VALUE(ring->bd_dma_base);
+ writel_relaxed(val, ring->regs + RING_BD_START_ADDR);
+
+ /* BD write pointer will be same as HW write pointer */
+ ring->bd_write_offset =
+ readl_relaxed(ring->regs + RING_BD_WRITE_PTR);
+ ring->bd_write_offset *= RING_DESC_SIZE;
+
+ /* Program completion start address */
+ val = CMPL_START_ADDR_VALUE(ring->cmpl_dma_base);
+ writel_relaxed(val, ring->regs + RING_CMPL_START_ADDR);
+
+ /* Ensure last pending message is cleared */
+ ring->last_pending_msg = NULL;
+
+ /* Completion read pointer will be same as HW write pointer */
+ ring->cmpl_read_offset =
+ readl_relaxed(ring->regs + RING_CMPL_WRITE_PTR);
+ ring->cmpl_read_offset *= RING_DESC_SIZE;
+
+ /* Read ring Tx, Rx, and Outstanding counts to clear */
+ readl_relaxed(ring->regs + RING_NUM_REQ_RECV_LS);
+ readl_relaxed(ring->regs + RING_NUM_REQ_RECV_MS);
+ readl_relaxed(ring->regs + RING_NUM_REQ_TRANS_LS);
+ readl_relaxed(ring->regs + RING_NUM_REQ_TRANS_MS);
+ readl_relaxed(ring->regs + RING_NUM_REQ_OUTSTAND);
+
+ /* Configure RING_MSI_CONTROL */
+ val = 0;
+ val |= (ring->msi_timer_val << MSI_TIMER_VAL_SHIFT);
+ val |= BIT(MSI_ENABLE_SHIFT);
+ val |= (ring->msi_count_threshold & MSI_COUNT_MASK) << MSI_COUNT_SHIFT;
+ writel_relaxed(val, ring->regs + RING_MSI_CONTROL);
+
+ /* Enable/activate ring */
+ val = BIT(CONTROL_ACTIVE_SHIFT);
+ writel_relaxed(val, ring->regs + RING_CONTROL);
+
+ return 0;
+
+fail_free_cmpl_memory:
+ dma_pool_free(ring->mbox->cmpl_pool,
+ ring->cmpl_base, ring->cmpl_dma_base);
+ ring->cmpl_base = NULL;
+fail_free_bd_memory:
+ dma_pool_free(ring->mbox->bd_pool,
+ ring->bd_base, ring->bd_dma_base);
+ ring->bd_base = NULL;
+fail:
+ return ret;
+}
+
+static void flexrm_shutdown(struct mbox_chan *chan)
+{
+ u32 reqid;
+ unsigned int timeout;
+ struct brcm_message *msg;
+ struct flexrm_ring *ring = chan->con_priv;
+
+ /* Disable/inactivate ring */
+ writel_relaxed(0x0, ring->regs + RING_CONTROL);
+
+ /* Flush ring with timeout of 1s */
+ timeout = 1000;
+ writel_relaxed(BIT(CONTROL_FLUSH_SHIFT),
+ ring->regs + RING_CONTROL);
+ do {
+ if (readl_relaxed(ring->regs + RING_FLUSH_DONE) &
+ FLUSH_DONE_MASK)
+ break;
+ mdelay(1);
+ } while (timeout--);
+
+ /* Abort all in-flight requests */
+ for (reqid = 0; reqid < RING_MAX_REQ_COUNT; reqid++) {
+ msg = ring->requests[reqid];
+ if (!msg)
+ continue;
+
+ /* Release reqid for recycling */
+ ring->requests[reqid] = NULL;
+ ida_simple_remove(&ring->requests_ida, reqid);
+
+ /* Unmap DMA mappings */
+ flexrm_dma_unmap(ring->mbox->dev, msg);
+
+ /* Give-back message to mailbox client */
+ msg->error = -EIO;
+ mbox_chan_received_data(chan, msg);
+ }
+
+ /* Release IRQ */
+ if (ring->irq_requested) {
+ free_irq(ring->irq, ring);
+ ring->irq_requested = false;
+ }
+
+ /* Free-up completion descriptor ring */
+ if (ring->cmpl_base) {
+ dma_pool_free(ring->mbox->cmpl_pool,
+ ring->cmpl_base, ring->cmpl_dma_base);
+ ring->cmpl_base = NULL;
+ }
+
+ /* Free-up BD descriptor ring */
+ if (ring->bd_base) {
+ dma_pool_free(ring->mbox->bd_pool,
+ ring->bd_base, ring->bd_dma_base);
+ ring->bd_base = NULL;
+ }
+}
+
+static bool flexrm_last_tx_done(struct mbox_chan *chan)
+{
+ bool ret;
+ unsigned long flags;
+ struct flexrm_ring *ring = chan->con_priv;
+
+ spin_lock_irqsave(&ring->lock, flags);
+ ret = (ring->last_pending_msg) ? false : true;
+ spin_unlock_irqrestore(&ring->lock, flags);
+
+ return ret;
+}
+
+static const struct mbox_chan_ops flexrm_mbox_chan_ops = {
+ .send_data = flexrm_send_data,
+ .startup = flexrm_startup,
+ .shutdown = flexrm_shutdown,
+ .last_tx_done = flexrm_last_tx_done,
+ .peek_data = flexrm_peek_data,
+};
+
+static struct mbox_chan *flexrm_mbox_of_xlate(struct mbox_controller *cntlr,
+ const struct of_phandle_args *pa)
+{
+ struct mbox_chan *chan;
+ struct flexrm_ring *ring;
+
+ if (pa->args_count < 3)
+ return ERR_PTR(-EINVAL);
+
+ if (pa->args[0] >= cntlr->num_chans)
+ return ERR_PTR(-ENOENT);
+
+ if (pa->args[1] > MSI_COUNT_MASK)
+ return ERR_PTR(-EINVAL);
+
+ if (pa->args[2] > MSI_TIMER_VAL_MASK)
+ return ERR_PTR(-EINVAL);
+
+ chan = &cntlr->chans[pa->args[0]];
+ ring = chan->con_priv;
+ ring->msi_count_threshold = pa->args[1];
+ ring->msi_timer_val = pa->args[2];
+
+ return chan;
+}
+
+/* ====== FlexRM platform driver ===== */
+
+static void flexrm_mbox_msi_write(struct msi_desc *desc, struct msi_msg *msg)
+{
+ struct device *dev = msi_desc_to_dev(desc);
+ struct flexrm_mbox *mbox = dev_get_drvdata(dev);
+ struct flexrm_ring *ring = &mbox->rings[desc->platform.msi_index];
+
+ /* Configure per-Ring MSI registers */
+ writel_relaxed(msg->address_lo, ring->regs + RING_MSI_ADDR_LS);
+ writel_relaxed(msg->address_hi, ring->regs + RING_MSI_ADDR_MS);
+ writel_relaxed(msg->data, ring->regs + RING_MSI_DATA_VALUE);
+}
+
+static int flexrm_mbox_probe(struct platform_device *pdev)
+{
+ int index, ret = 0;
+ void __iomem *regs;
+ void __iomem *regs_end;
+ struct msi_desc *desc;
+ struct resource *iomem;
+ struct flexrm_ring *ring;
+ struct flexrm_mbox *mbox;
+ struct device *dev = &pdev->dev;
+
+ /* Allocate driver mailbox struct */
+ mbox = devm_kzalloc(dev, sizeof(*mbox), GFP_KERNEL);
+ if (!mbox) {
+ ret = -ENOMEM;
+ goto fail;
+ }
+ mbox->dev = dev;
+ platform_set_drvdata(pdev, mbox);
+
+ /* Get resource for registers */
+ iomem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!iomem || (resource_size(iomem) < RING_REGS_SIZE)) {
+ ret = -ENODEV;
+ goto fail;
+ }
+
+ /* Map registers of all rings */
+ mbox->regs = devm_ioremap_resource(&pdev->dev, iomem);
+ if (IS_ERR(mbox->regs)) {
+ ret = PTR_ERR(mbox->regs);
+ dev_err(&pdev->dev, "Failed to remap mailbox regs: %d\n", ret);
+ goto fail;
+ }
+ regs_end = mbox->regs + resource_size(iomem);
+
+ /* Scan and count available rings */
+ mbox->num_rings = 0;
+ for (regs = mbox->regs; regs < regs_end; regs += RING_REGS_SIZE) {
+ if (readl_relaxed(regs + RING_VER) == RING_VER_MAGIC)
+ mbox->num_rings++;
+ }
+ if (!mbox->num_rings) {
+ ret = -ENODEV;
+ goto fail;
+ }
+
+ /* Allocate driver ring structs */
+ ring = devm_kcalloc(dev, mbox->num_rings, sizeof(*ring), GFP_KERNEL);
+ if (!ring) {
+ ret = -ENOMEM;
+ goto fail;
+ }
+ mbox->rings = ring;
+
+ /* Initialize members of driver ring structs */
+ regs = mbox->regs;
+ for (index = 0; index < mbox->num_rings; index++) {
+ ring = &mbox->rings[index];
+ ring->num = index;
+ ring->mbox = mbox;
+ while ((regs < regs_end) &&
+ (readl_relaxed(regs + RING_VER) != RING_VER_MAGIC))
+ regs += RING_REGS_SIZE;
+ if (regs_end <= regs) {
+ ret = -ENODEV;
+ goto fail;
+ }
+ ring->regs = regs;
+ regs += RING_REGS_SIZE;
+ ring->irq = UINT_MAX;
+ ring->irq_requested = false;
+ ring->msi_timer_val = MSI_TIMER_VAL_MASK;
+ ring->msi_count_threshold = 0x1;
+ ida_init(&ring->requests_ida);
+ memset(ring->requests, 0, sizeof(ring->requests));
+ ring->bd_base = NULL;
+ ring->bd_dma_base = 0;
+ ring->cmpl_base = NULL;
+ ring->cmpl_dma_base = 0;
+ spin_lock_init(&ring->lock);
+ ring->last_pending_msg = NULL;
+ ring->cmpl_read_offset = 0;
+ }
+
+ /* FlexRM is capable of 40-bit physical addresses only */
+ ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(40));
+ if (ret) {
+ ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
+ if (ret)
+ goto fail;
+ }
+
+ /* Create DMA pool for ring BD memory */
+ mbox->bd_pool = dma_pool_create("bd", dev, RING_BD_SIZE,
+ 1 << RING_BD_ALIGN_ORDER, 0);
+ if (!mbox->bd_pool) {
+ ret = -ENOMEM;
+ goto fail;
+ }
+
+ /* Create DMA pool for ring completion memory */
+ mbox->cmpl_pool = dma_pool_create("cmpl", dev, RING_CMPL_SIZE,
+ 1 << RING_CMPL_ALIGN_ORDER, 0);
+ if (!mbox->cmpl_pool) {
+ ret = -ENOMEM;
+ goto fail_destroy_bd_pool;
+ }
+
+ /* Allocate platform MSIs for each ring */
+ ret = platform_msi_domain_alloc_irqs(dev, mbox->num_rings,
+ flexrm_mbox_msi_write);
+ if (ret)
+ goto fail_destroy_cmpl_pool;
+
+ /* Save alloced IRQ numbers for each ring */
+ for_each_msi_entry(desc, dev) {
+ ring = &mbox->rings[desc->platform.msi_index];
+ ring->irq = desc->irq;
+ }
+
+ /* Initialize mailbox controller */
+ mbox->controller.txdone_irq = false;
+ mbox->controller.txdone_poll = true;
+ mbox->controller.txpoll_period = 1;
+ mbox->controller.ops = &flexrm_mbox_chan_ops;
+ mbox->controller.dev = dev;
+ mbox->controller.num_chans = mbox->num_rings;
+ mbox->controller.of_xlate = flexrm_mbox_of_xlate;
+ mbox->controller.chans = devm_kcalloc(dev, mbox->num_rings,
+ sizeof(*mbox->controller.chans), GFP_KERNEL);
+ if (!mbox->controller.chans) {
+ ret = -ENOMEM;
+ goto fail_free_msis;
+ }
+ for (index = 0; index < mbox->num_rings; index++)
+ mbox->controller.chans[index].con_priv = &mbox->rings[index];
+
+ /* Register mailbox controller */
+ ret = mbox_controller_register(&mbox->controller);
+ if (ret)
+ goto fail_free_msis;
+
+ dev_info(dev, "registered flexrm mailbox with %d channels\n",
+ mbox->controller.num_chans);
+
+ return 0;
+
+fail_free_msis:
+ platform_msi_domain_free_irqs(dev);
+fail_destroy_cmpl_pool:
+ dma_pool_destroy(mbox->cmpl_pool);
+fail_destroy_bd_pool:
+ dma_pool_destroy(mbox->bd_pool);
+fail:
+ return ret;
+}
+
+static int flexrm_mbox_remove(struct platform_device *pdev)
+{
+ int index;
+ struct device *dev = &pdev->dev;
+ struct flexrm_ring *ring;
+ struct flexrm_mbox *mbox = platform_get_drvdata(pdev);
+
+ mbox_controller_unregister(&mbox->controller);
+
+ platform_msi_domain_free_irqs(dev);
+
+ dma_pool_destroy(mbox->cmpl_pool);
+ dma_pool_destroy(mbox->bd_pool);
+
+ for (index = 0; index < mbox->num_rings; index++) {
+ ring = &mbox->rings[index];
+ ida_destroy(&ring->requests_ida);
+ }
+
+ return 0;
+}
+
+static const struct of_device_id flexrm_mbox_of_match[] = {
+ { .compatible = "brcm,iproc-flexrm-mbox", },
+ {},
+};
+MODULE_DEVICE_TABLE(of, flexrm_mbox_of_match);
+
+static struct platform_driver flexrm_mbox_driver = {
+ .driver = {
+ .name = "brcm-flexrm-mbox",
+ .of_match_table = flexrm_mbox_of_match,
+ },
+ .probe = flexrm_mbox_probe,
+ .remove = flexrm_mbox_remove,
+};
+module_platform_driver(flexrm_mbox_driver);
+
+MODULE_AUTHOR("Anup Patel <anup.patel@broadcom.com>");
+MODULE_DESCRIPTION("Broadcom FlexRM mailbox driver");
+MODULE_LICENSE("GPL v2");
* Broadcom PDC Mailbox Driver
* The PDC provides a ring based programming interface to one or more hardware
* offload engines. For example, the PDC driver works with both SPU-M and SPU2
- * cryptographic offload hardware. In some chips the PDC is referred to as MDE.
+ * cryptographic offload hardware. In some chips the PDC is referred to as MDE,
+ * and in others the FA2/FA+ hardware is used with this PDC driver.
*
* The PDC driver registers with the Linux mailbox framework as a mailbox
* controller, once for each PDC instance. Ring 0 for each PDC is registered as
#define PDC_INTMASK_OFFSET 0x24
#define PDC_INTSTATUS_OFFSET 0x20
#define PDC_RCVLAZY0_OFFSET (0x30 + 4 * PDC_RINGSET)
+#define FA_RCVLAZY0_OFFSET 0x100
/*
* For SPU2, configure MDE_CKSUM_CONTROL to write 17 bytes of metadata
/* Maximum size buffer the DMA engine can handle */
#define PDC_DMA_BUF_MAX 16384
+enum pdc_hw {
+ FA_HW, /* FA2/FA+ hardware (i.e. Northstar Plus) */
+ PDC_HW /* PDC/MDE hardware (i.e. Northstar 2, Pegasus) */
+};
+
struct pdc_dma_map {
void *ctx; /* opaque context associated with frame */
};
u32 gptimer; /* 0x028 */
u32 PAD;
- u32 intrcvlazy_0; /* 0x030 */
- u32 intrcvlazy_1; /* 0x034 */
- u32 intrcvlazy_2; /* 0x038 */
- u32 intrcvlazy_3; /* 0x03c */
+ u32 intrcvlazy_0; /* 0x030 (Only in PDC, not FA2) */
+ u32 intrcvlazy_1; /* 0x034 (Only in PDC, not FA2) */
+ u32 intrcvlazy_2; /* 0x038 (Only in PDC, not FA2) */
+ u32 intrcvlazy_3; /* 0x03c (Only in PDC, not FA2) */
u32 PAD[48];
- u32 removed_intrecvlazy; /* 0x100 */
+ u32 fa_intrecvlazy; /* 0x100 (Only in FA2, not PDC) */
u32 flowctlthresh; /* 0x104 */
u32 wrrthresh; /* 0x108 */
u32 gmac_idle_cnt_thresh; /* 0x10c */
u32 serdes_status1; /* 0x1b0 */
u32 PAD[11]; /* 0x1b4-1dc */
u32 clk_ctl_st; /* 0x1e0 */
- u32 hw_war; /* 0x1e4 */
+ u32 hw_war; /* 0x1e4 (Only in PDC, not FA2) */
u32 pwrctl; /* 0x1e8 */
u32 PAD[5];
u32 txnobuf; /* unable to create tx descriptor */
u32 rxnobuf; /* unable to create rx descriptor */
u32 rx_oflow; /* count of rx overflows */
+
+ /* hardware type - FA2 or PDC/MDE */
+ enum pdc_hw hw_type;
};
/* Global variables */
/* interrupt configuration */
iowrite32(PDC_INTMASK, pdcs->pdc_reg_vbase + PDC_INTMASK_OFFSET);
- iowrite32(PDC_LAZY_INT, pdcs->pdc_reg_vbase + PDC_RCVLAZY0_OFFSET);
+
+ if (pdcs->hw_type == FA_HW)
+ iowrite32(PDC_LAZY_INT, pdcs->pdc_reg_vbase +
+ FA_RCVLAZY0_OFFSET);
+ else
+ iowrite32(PDC_LAZY_INT, pdcs->pdc_reg_vbase +
+ PDC_RCVLAZY0_OFFSET);
/* read irq from device tree */
pdcs->pdc_irq = irq_of_parse_and_map(dn, 0);
return 0;
}
+/* Device tree API */
+static const int pdc_hw = PDC_HW;
+static const int fa_hw = FA_HW;
+
+static const struct of_device_id pdc_mbox_of_match[] = {
+ {.compatible = "brcm,iproc-pdc-mbox", .data = &pdc_hw},
+ {.compatible = "brcm,iproc-fa2-mbox", .data = &fa_hw},
+ { /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, pdc_mbox_of_match);
+
/**
* pdc_dt_read() - Read application-specific data from device tree.
* @pdev: Platform device
{
struct device *dev = &pdev->dev;
struct device_node *dn = pdev->dev.of_node;
+ const struct of_device_id *match;
+ const int *hw_type;
int err;
err = of_property_read_u32(dn, "brcm,rx-status-len",
pdcs->use_bcm_hdr = of_property_read_bool(dn, "brcm,use-bcm-hdr");
+ pdcs->hw_type = PDC_HW;
+
+ match = of_match_device(of_match_ptr(pdc_mbox_of_match), dev);
+ if (match != NULL) {
+ hw_type = match->data;
+ pdcs->hw_type = *hw_type;
+ }
+
return 0;
}
pdcs->pdc_idx = pdcg.num_spu;
pdcg.num_spu++;
- err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
+ err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(39));
if (err) {
dev_warn(dev, "PDC device cannot perform DMA. Error %d.", err);
goto cleanup;
return 0;
}
-static const struct of_device_id pdc_mbox_of_match[] = {
- {.compatible = "brcm,iproc-pdc-mbox"},
- { /* sentinel */ }
-};
-MODULE_DEVICE_TABLE(of, pdc_mbox_of_match);
-
static struct platform_driver pdc_mbox_driver = {
.probe = pdc_probe,
.remove = pdc_remove,
mbox->irq_map_chan[mchan->ack_irq] = NULL;
}
-static struct mbox_chan_ops hi6220_mbox_ops = {
+static const struct mbox_chan_ops hi6220_mbox_ops = {
.send_data = hi6220_mbox_send_data,
.startup = hi6220_mbox_startup,
.shutdown = hi6220_mbox_shutdown,
devm_free_irq(mb_chan->dev, mb_chan->irq, mb_chan);
}
-static struct mbox_chan_ops slimpro_mbox_ops = {
+static const struct mbox_chan_ops slimpro_mbox_ops = {
.send_data = slimpro_mbox_send_data,
.startup = slimpro_mbox_startup,
.shutdown = slimpro_mbox_shutdown,
/* Submit next message */
msg_submit(chan);
+ if (!mssg)
+ return;
+
/* Notify the client */
- if (mssg && chan->cl->tx_done)
+ if (chan->cl->tx_done)
chan->cl->tx_done(chan->cl, mssg, r);
- if (chan->cl->tx_block)
+ if (r != -ETIME && chan->cl->tx_block)
complete(&chan->tx_complete);
}
msg_submit(chan);
- if (chan->cl->tx_block && chan->active_req) {
+ if (chan->cl->tx_block) {
unsigned long wait;
int ret;
ret = wait_for_completion_timeout(&chan->tx_complete, wait);
if (ret == 0) {
- t = -EIO;
- tx_tick(chan, -EIO);
+ t = -ETIME;
+ tx_tick(chan, t);
}
}
txdone = TXDONE_BY_ACK;
if (txdone == TXDONE_BY_POLL) {
+
+ if (!mbox->ops->last_tx_done) {
+ dev_err(mbox->dev, "last_tx_done method is absent\n");
+ return -EINVAL;
+ }
+
hrtimer_init(&mbox->poll_hrt, CLOCK_MONOTONIC,
HRTIMER_MODE_REL);
mbox->poll_hrt.function = txdone_hrtimer;
*result = true;
r = dm_bitset_cursor_begin(&cmd->dirty_info, cmd->dirty_root,
- from_cblock(begin), &cmd->dirty_cursor);
+ from_cblock(cmd->cache_blocks), &cmd->dirty_cursor);
if (r) {
DMERR("%s: dm_bitset_cursor_begin for dirty failed", __func__);
return r;
return 0;
}
+ begin = to_cblock(from_cblock(begin) + 1);
+ if (begin == end)
+ break;
+
r = dm_bitset_cursor_next(&cmd->dirty_cursor);
if (r) {
DMERR("%s: dm_bitset_cursor_next for dirty failed", __func__);
dm_bitset_cursor_end(&cmd->dirty_cursor);
return r;
}
-
- begin = to_cblock(from_cblock(begin) + 1);
}
dm_bitset_cursor_end(&cmd->dirty_cursor);
ti->num_discard_bios = 1;
ti->discards_supported = true;
- ti->discard_zeroes_data_unsupported = true;
ti->split_discard_bios = false;
cache->features = ca->features;
void dm_init_normal_md_queue(struct mapped_device *md);
int md_in_flight(struct mapped_device *md);
void disable_write_same(struct mapped_device *md);
+void disable_write_zeroes(struct mapped_device *md);
static inline struct completion *dm_get_completion_from_kobject(struct kobject *kobj)
{
wake_up_process(cc->write_thread);
ti->num_flush_bios = 1;
- ti->discard_zeroes_data_unsupported = true;
return 0;
*/
if (op == REQ_OP_DISCARD)
special_cmd_max_sectors = q->limits.max_discard_sectors;
+ else if (op == REQ_OP_WRITE_ZEROES)
+ special_cmd_max_sectors = q->limits.max_write_zeroes_sectors;
else if (op == REQ_OP_WRITE_SAME)
special_cmd_max_sectors = q->limits.max_write_same_sectors;
- if ((op == REQ_OP_DISCARD || op == REQ_OP_WRITE_SAME) &&
+ if ((op == REQ_OP_DISCARD || op == REQ_OP_WRITE_ZEROES ||
+ op == REQ_OP_WRITE_SAME) &&
special_cmd_max_sectors == 0) {
dec_count(io, region, -EOPNOTSUPP);
return;
/*
* Allocate a suitably sized-bio.
*/
- if ((op == REQ_OP_DISCARD) || (op == REQ_OP_WRITE_SAME))
+ switch (op) {
+ case REQ_OP_DISCARD:
+ case REQ_OP_WRITE_ZEROES:
+ num_bvecs = 0;
+ break;
+ case REQ_OP_WRITE_SAME:
num_bvecs = 1;
- else
+ break;
+ default:
num_bvecs = min_t(int, BIO_MAX_PAGES,
dm_sector_div_up(remaining, (PAGE_SIZE >> SECTOR_SHIFT)));
+ }
bio = bio_alloc_bioset(GFP_NOIO, num_bvecs, io->client->bios);
bio->bi_iter.bi_sector = where->sector + (where->count - remaining);
bio_set_op_attrs(bio, op, op_flags);
store_io_and_region_in_bio(bio, io, region);
- if (op == REQ_OP_DISCARD) {
+ if (op == REQ_OP_DISCARD || op == REQ_OP_WRITE_ZEROES) {
num_sectors = min_t(sector_t, special_cmd_max_sectors, remaining);
bio->bi_iter.bi_size = num_sectors << SECTOR_SHIFT;
remaining -= num_sectors;
job->pages = &zero_page_list;
/*
- * Use WRITE SAME to optimize zeroing if all dests support it.
+ * Use WRITE ZEROES to optimize zeroing if all dests support it.
*/
- job->rw = REQ_OP_WRITE_SAME;
+ job->rw = REQ_OP_WRITE_ZEROES;
for (i = 0; i < job->num_dests; i++)
- if (!bdev_write_same(job->dests[i].bdev)) {
+ if (!bdev_write_zeroes_sectors(job->dests[i].bdev)) {
job->rw = WRITE;
break;
}
ti->num_flush_bios = 1;
ti->num_discard_bios = 1;
ti->num_write_same_bios = 1;
+ ti->num_write_zeroes_bios = 1;
ti->private = lc;
return 0;
ti->num_flush_bios = 1;
ti->num_discard_bios = 1;
ti->num_write_same_bios = 1;
+ ti->num_write_zeroes_bios = 1;
if (m->queue_mode == DM_TYPE_BIO_BASED)
ti->per_io_data_size = multipath_per_bio_data_size();
else
*/
int r = DM_ENDIO_REQUEUE;
- if (!error && !clone->errors)
+ if (!error)
return 0; /* I/O complete */
if (noretry_error(error))
/* Assume discards not supported until after checks below. */
ti->discards_supported = false;
- /* RAID level 4,5,6 require discard_zeroes_data for data integrity! */
+ /*
+ * XXX: RAID level 4,5,6 require zeroing for safety.
+ */
raid456 = (rs->md.level == 4 || rs->md.level == 5 || rs->md.level == 6);
for (i = 0; i < rs->raid_disks; i++) {
return;
if (raid456) {
- if (!q->limits.discard_zeroes_data)
- return;
if (!devices_handle_discard_safely) {
DMERR("raid456 discard support disabled due to discard_zeroes_data uncertainty.");
DMERR("Set dm-raid.devices_handle_discard_safely=Y to override.");
return r;
/* Resize bitmap to adjust to changed region size (aka MD bitmap chunksize) */
- if (test_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags) &&
+ if (test_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags) && mddev->bitmap &&
mddev->bitmap_info.chunksize != to_bytes(rs->requested_bitmap_chunk_sectors)) {
r = bitmap_resize(mddev->bitmap, mddev->dev_sectors,
to_bytes(rs->requested_bitmap_chunk_sectors), 0);
ti->num_flush_bios = 1;
ti->num_discard_bios = 1;
ti->per_io_data_size = sizeof(struct dm_raid1_bio_record);
- ti->discard_zeroes_data_unsupported = true;
ms->kmirrord_wq = alloc_workqueue("kmirrord", WQ_MEM_RECLAIM, 0);
if (!ms->kmirrord_wq) {
r = rq_end_io(tio->ti, clone, error, &tio->info);
}
- if (unlikely(r == -EREMOTEIO && (req_op(clone) == REQ_OP_WRITE_SAME) &&
- !clone->q->limits.max_write_same_sectors))
- disable_write_same(tio->md);
+ if (unlikely(r == -EREMOTEIO)) {
+ if (req_op(clone) == REQ_OP_WRITE_SAME &&
+ !clone->q->limits.max_write_same_sectors)
+ disable_write_same(tio->md);
+ if (req_op(clone) == REQ_OP_WRITE_ZEROES &&
+ !clone->q->limits.max_write_zeroes_sectors)
+ disable_write_zeroes(tio->md);
+ }
if (r <= 0)
/* The target wants to complete the I/O */
if (!rq->q->mq_ops)
blk_complete_request(rq);
else
- blk_mq_complete_request(rq, error);
+ blk_mq_complete_request(rq);
}
/*
/* Undo dm_start_request() before requeuing */
rq_end_stats(md, rq);
rq_completed(md, rq_data_dir(rq), false);
+ blk_mq_delay_run_hw_queue(hctx, 100/*ms*/);
return BLK_MQ_RQ_QUEUE_BUSY;
}
return BLK_MQ_RQ_QUEUE_OK;
}
-static struct blk_mq_ops dm_mq_ops = {
+static const struct blk_mq_ops dm_mq_ops = {
.queue_rq = dm_mq_queue_rq,
.complete = dm_softirq_done,
.init_request = dm_mq_init_request,
ti->num_flush_bios = stripes;
ti->num_discard_bios = stripes;
ti->num_write_same_bios = stripes;
+ ti->num_write_zeroes_bios = stripes;
sc->chunk_size = chunk_size;
if (chunk_size & (chunk_size - 1))
return DM_MAPIO_REMAPPED;
}
if (unlikely(bio_op(bio) == REQ_OP_DISCARD) ||
+ unlikely(bio_op(bio) == REQ_OP_WRITE_ZEROES) ||
unlikely(bio_op(bio) == REQ_OP_WRITE_SAME)) {
target_bio_nr = dm_bio_get_target_bio_nr(bio);
BUG_ON(target_bio_nr >= sc->stripes);
return false;
}
-static bool dm_table_discard_zeroes_data(struct dm_table *t)
-{
- struct dm_target *ti;
- unsigned i = 0;
-
- /* Ensure that all targets supports discard_zeroes_data. */
- while (i < dm_table_get_num_targets(t)) {
- ti = dm_table_get_target(t, i++);
-
- if (ti->discard_zeroes_data_unsupported)
- return false;
- }
-
- return true;
-}
-
static int device_is_nonrot(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
return true;
}
+static int device_not_write_zeroes_capable(struct dm_target *ti, struct dm_dev *dev,
+ sector_t start, sector_t len, void *data)
+{
+ struct request_queue *q = bdev_get_queue(dev->bdev);
+
+ return q && !q->limits.max_write_zeroes_sectors;
+}
+
+static bool dm_table_supports_write_zeroes(struct dm_table *t)
+{
+ struct dm_target *ti;
+ unsigned i = 0;
+
+ while (i < dm_table_get_num_targets(t)) {
+ ti = dm_table_get_target(t, i++);
+
+ if (!ti->num_write_zeroes_bios)
+ return false;
+
+ if (!ti->type->iterate_devices ||
+ ti->type->iterate_devices(ti, device_not_write_zeroes_capable, NULL))
+ return false;
+ }
+
+ return true;
+}
+
+
static int device_discard_capable(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
}
blk_queue_write_cache(q, wc, fua);
- if (!dm_table_discard_zeroes_data(t))
- q->limits.discard_zeroes_data = 0;
-
/* Ensure that all underlying devices are non-rotational. */
if (dm_table_all_devices_attribute(t, device_is_nonrot))
queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q);
if (!dm_table_supports_write_same(t))
q->limits.max_write_same_sectors = 0;
+ if (!dm_table_supports_write_zeroes(t))
+ q->limits.max_write_zeroes_sectors = 0;
if (dm_table_all_devices_attribute(t, queue_supports_sg_merge))
queue_flag_clear_unlocked(QUEUE_FLAG_NO_SG_MERGE, q);
* them down to the data device. The thin device's discard
* processing will cause mappings to be removed from the btree.
*/
- ti->discard_zeroes_data_unsupported = true;
if (pf.discard_enabled && pf.discard_passdown) {
ti->num_discard_bios = 1;
ti->per_io_data_size = sizeof(struct dm_thin_endio_hook);
/* In case the pool supports discards, pass them on. */
- ti->discard_zeroes_data_unsupported = true;
if (tc->pool->pf.discard_enabled) {
ti->discards_supported = true;
ti->num_discard_bios = 1;
block = fec_buffer_rs_block(v, fio, n, i);
res = fec_decode_rs8(v, fio, block, &par[offset], neras);
if (res < 0) {
- dm_bufio_release(buf);
-
r = res;
goto error;
}
done:
r = corrected;
error:
+ dm_bufio_release(buf);
+
if (r < 0 && neras)
DMERR_LIMIT("%s: FEC %llu: failed to correct: %d",
v->data_dev->name, (unsigned long long)rsb, r);
&is_zero) == 0) {
/* skip known zero blocks entirely */
if (is_zero)
- continue;
+ goto done;
/*
* skip if we have already found the theoretical
if (!verity_fec_is_enabled(v))
return -EOPNOTSUPP;
+ if (fio->level >= DM_VERITY_FEC_MAX_RECURSION) {
+ DMWARN_LIMIT("%s: FEC: recursion too deep", v->data_dev->name);
+ return -EIO;
+ }
+
+ fio->level++;
+
if (type == DM_VERITY_BLOCK_TYPE_METADATA)
block += v->data_blocks;
if (r < 0) {
r = fec_decode_rsb(v, io, fio, rsb, offset, true);
if (r < 0)
- return r;
+ goto done;
}
if (dest)
r = verity_for_bv_block(v, io, iter, fec_bv_copy);
}
+done:
+ fio->level--;
return r;
}
memset(fio->bufs, 0, sizeof(fio->bufs));
fio->nbufs = 0;
fio->output = NULL;
+ fio->level = 0;
}
/*
#define DM_VERITY_FEC_BUF_MAX \
(1 << (PAGE_SHIFT - DM_VERITY_FEC_BUF_RS_BITS))
+/* maximum recursion level for verity_fec_decode */
+#define DM_VERITY_FEC_MAX_RECURSION 4
+
#define DM_VERITY_OPT_FEC_DEV "use_fec_from_device"
#define DM_VERITY_OPT_FEC_BLOCKS "fec_blocks"
#define DM_VERITY_OPT_FEC_START "fec_start"
unsigned nbufs; /* number of buffers allocated */
u8 *output; /* buffer for corrected output */
size_t output_pos;
+ unsigned level; /* recursion level */
};
#ifdef CONFIG_DM_VERITY_FEC
queue_io(md, bio);
} else {
/* done with normal IO or empty flush */
- trace_block_bio_complete(md->queue, bio, io_error);
bio->bi_error = io_error;
bio_endio(bio);
}
limits->max_write_same_sectors = 0;
}
+void disable_write_zeroes(struct mapped_device *md)
+{
+ struct queue_limits *limits = dm_get_queue_limits(md);
+
+ /* device doesn't really support WRITE ZEROES, disable it */
+ limits->max_write_zeroes_sectors = 0;
+}
+
static void clone_endio(struct bio *bio)
{
int error = bio->bi_error;
}
}
- if (unlikely(r == -EREMOTEIO && (bio_op(bio) == REQ_OP_WRITE_SAME) &&
- !bdev_get_queue(bio->bi_bdev)->limits.max_write_same_sectors))
- disable_write_same(md);
+ if (unlikely(r == -EREMOTEIO)) {
+ if (bio_op(bio) == REQ_OP_WRITE_SAME &&
+ !bdev_get_queue(bio->bi_bdev)->limits.max_write_same_sectors)
+ disable_write_same(md);
+ if (bio_op(bio) == REQ_OP_WRITE_ZEROES &&
+ !bdev_get_queue(bio->bi_bdev)->limits.max_write_zeroes_sectors)
+ disable_write_zeroes(md);
+ }
free_tio(tio);
dec_pending(io, error);
return ti->num_write_same_bios;
}
+static unsigned get_num_write_zeroes_bios(struct dm_target *ti)
+{
+ return ti->num_write_zeroes_bios;
+}
+
typedef bool (*is_split_required_fn)(struct dm_target *ti);
static bool is_split_required_for_discard(struct dm_target *ti)
return __send_changing_extent_only(ci, get_num_write_same_bios, NULL);
}
+static int __send_write_zeroes(struct clone_info *ci)
+{
+ return __send_changing_extent_only(ci, get_num_write_zeroes_bios, NULL);
+}
+
/*
* Select the correct strategy for processing a non-flush bio.
*/
return __send_discard(ci);
else if (unlikely(bio_op(bio) == REQ_OP_WRITE_SAME))
return __send_write_same(ci);
+ else if (unlikely(bio_op(bio) == REQ_OP_WRITE_ZEROES))
+ return __send_write_zeroes(ci);
ti = dm_table_find_target(ci->map, ci->sector);
if (!dm_target_is_valid(ti))
split, disk_devt(mddev->gendisk),
bio_sector);
mddev_check_writesame(mddev, split);
+ mddev_check_write_zeroes(mddev, split);
generic_make_request(split);
}
} while (split != bio);
!bdev_get_queue(bio->bi_bdev)->limits.max_write_same_sectors)
mddev->queue->limits.max_write_same_sectors = 0;
}
+
+static inline void mddev_check_write_zeroes(struct mddev *mddev, struct bio *bio)
+{
+ if (bio_op(bio) == REQ_OP_WRITE_ZEROES &&
+ !bdev_get_queue(bio->bi_bdev)->limits.max_write_zeroes_sectors)
+ mddev->queue->limits.max_write_zeroes_sectors = 0;
+}
#endif /* _MD_MD_H */
mp_bh->bio.bi_end_io = multipath_end_request;
mp_bh->bio.bi_private = mp_bh;
mddev_check_writesame(mddev, &mp_bh->bio);
+ mddev_check_write_zeroes(mddev, &mp_bh->bio);
generic_make_request(&mp_bh->bio);
return;
}
blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors);
+ blk_queue_max_write_zeroes_sectors(mddev->queue, mddev->chunk_sectors);
blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors);
blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
split, disk_devt(mddev->gendisk),
bio_sector);
mddev_check_writesame(mddev, split);
+ mddev_check_write_zeroes(mddev, split);
generic_make_request(split);
}
} while (split != bio);
if (IS_ERR(conf))
return PTR_ERR(conf);
- if (mddev->queue)
+ if (mddev->queue) {
blk_queue_max_write_same_sectors(mddev->queue, 0);
+ blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
+ }
rdev_for_each(rdev, mddev) {
if (!mddev->gendisk)
blk_queue_max_discard_sectors(mddev->queue,
mddev->chunk_sectors);
blk_queue_max_write_same_sectors(mddev->queue, 0);
+ blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
blk_queue_io_min(mddev->queue, chunk_size);
if (conf->geo.raid_disks % conf->geo.near_copies)
blk_queue_io_opt(mddev->queue, chunk_size * conf->geo.raid_disks);
rdev_dec_pending(rdev, conf->mddev);
if (!error) {
- trace_block_bio_complete(bdev_get_queue(raid_bi->bi_bdev),
- raid_bi, 0);
bio_endio(raid_bi);
if (atomic_dec_and_test(&conf->active_aligned_reads))
wake_up(&conf->wait_for_quiescent);
if (mddev->queue) {
int chunk_size;
- bool discard_supported = true;
/* read-ahead size must cover two whole stripes, which
* is 2 * (datadisks) * chunksize where 'n' is the
* number of raid devices
blk_queue_max_discard_sectors(mddev->queue,
0xfffe * STRIPE_SECTORS);
- /*
- * unaligned part of discard request will be ignored, so can't
- * guarantee discard_zeroes_data
- */
- mddev->queue->limits.discard_zeroes_data = 0;
-
blk_queue_max_write_same_sectors(mddev->queue, 0);
+ blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
rdev_for_each(rdev, mddev) {
disk_stack_limits(mddev->gendisk, rdev->bdev,
rdev->data_offset << 9);
disk_stack_limits(mddev->gendisk, rdev->bdev,
rdev->new_data_offset << 9);
- /*
- * discard_zeroes_data is required, otherwise data
- * could be lost. Consider a scenario: discard a stripe
- * (the stripe could be inconsistent if
- * discard_zeroes_data is 0); write one disk of the
- * stripe (the stripe could be inconsistent again
- * depending on which disks are used to calculate
- * parity); the disk is broken; The stripe data of this
- * disk is lost.
- */
- if (!blk_queue_discard(bdev_get_queue(rdev->bdev)) ||
- !bdev_get_queue(rdev->bdev)->
- limits.discard_zeroes_data)
- discard_supported = false;
- /* Unfortunately, discard_zeroes_data is not currently
- * a guarantee - just a hint. So we only allow DISCARD
- * if the sysadmin has confirmed that only safe devices
- * are in use by setting a module parameter.
- */
- if (!devices_handle_discard_safely) {
- if (discard_supported) {
- pr_info("md/raid456: discard support disabled due to uncertainty.\n");
- pr_info("Set raid456.devices_handle_discard_safely=Y to override.\n");
- }
- discard_supported = false;
- }
}
- if (discard_supported &&
+ /*
+ * zeroing is required, otherwise data
+ * could be lost. Consider a scenario: discard a stripe
+ * (the stripe could be inconsistent if
+ * discard_zeroes_data is 0); write one disk of the
+ * stripe (the stripe could be inconsistent again
+ * depending on which disks are used to calculate
+ * parity); the disk is broken; The stripe data of this
+ * disk is lost.
+ *
+ * We only allow DISCARD if the sysadmin has confirmed that
+ * only safe devices are in use by setting a module parameter.
+ * A better idea might be to turn DISCARD into WRITE_ZEROES
+ * requests, as that is required to be safe.
+ */
+ if (devices_handle_discard_safely &&
mddev->queue->limits.max_discard_sectors >= (stripe >> 9) &&
mddev->queue->limits.discard_granularity >= stripe)
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD,
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
blk_queue_max_discard_sectors(q, max_discard);
- if (card->erased_byte == 0 && !mmc_can_discard(card))
- q->limits.discard_zeroes_data = 1;
q->limits.discard_granularity = card->pref_erase << 9;
/* granularity must not be greater than max. discard */
if (card->pref_erase > max_discard)
sdio_free_func_cis(func);
kfree(func->info);
-
+ kfree(func->tmpbuf);
kfree(func);
}
if (!func)
return ERR_PTR(-ENOMEM);
+ /*
+ * allocate buffer separately to make sure it's properly aligned for
+ * DMA usage (incl. 64 bit DMA)
+ */
+ func->tmpbuf = kmalloc(4, GFP_KERNEL);
+ if (!func->tmpbuf) {
+ kfree(func);
+ return ERR_PTR(-ENOMEM);
+ }
+
func->card = card;
device_initialize(&func->dev);
#include <linux/ioport.h>
#include <linux/module.h>
#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/stat.h>
if (card->type == MMC_TYPE_SDIO ||
card->type == MMC_TYPE_SD_COMBO) {
- set_bit(DW_MMC_CARD_NO_LOW_PWR, &slot->flags);
+ if (!test_bit(DW_MMC_CARD_NO_LOW_PWR, &slot->flags)) {
+ pm_runtime_get_noresume(mmc->parent);
+ set_bit(DW_MMC_CARD_NO_LOW_PWR, &slot->flags);
+ }
clk_en_a = clk_en_a_old & ~clken_low_pwr;
} else {
- clear_bit(DW_MMC_CARD_NO_LOW_PWR, &slot->flags);
+ if (test_bit(DW_MMC_CARD_NO_LOW_PWR, &slot->flags)) {
+ pm_runtime_put_noidle(mmc->parent);
+ clear_bit(DW_MMC_CARD_NO_LOW_PWR, &slot->flags);
+ }
clk_en_a = clk_en_a_old | clken_low_pwr;
}
switch (uhs) {
case MMC_TIMING_UHS_SDR50:
+ case MMC_TIMING_UHS_DDR50:
pinctrl = imx_data->pins_100mhz;
break;
case MMC_TIMING_UHS_SDR104:
#include "mtdcore.h"
-static struct backing_dev_info *mtd_bdi;
+struct backing_dev_info *mtd_bdi;
#ifdef CONFIG_PM_SLEEP
* mtd_device_parse_register() multiple times on the same master MTD,
* especially with CONFIG_MTD_PARTITIONED_MASTER=y.
*/
- if (WARN_ONCE(mtd->backing_dev_info, "MTD already registered\n"))
+ if (WARN_ONCE(mtd->dev.type, "MTD already registered\n"))
return -EEXIST;
- mtd->backing_dev_info = mtd_bdi;
-
BUG_ON(mtd->writesize == 0);
mutex_lock(&mtd_table_mutex);
struct backing_dev_info *bdi;
int ret;
- bdi = kzalloc(sizeof(*bdi), GFP_KERNEL);
+ bdi = bdi_alloc(GFP_KERNEL);
if (!bdi)
return ERR_PTR(-ENOMEM);
- ret = bdi_setup_and_register(bdi, name);
+ bdi->name = name;
+ /*
+ * We put '-0' suffix to the name to get the same name format as we
+ * used to get. Since this is called only once, we get a unique name.
+ */
+ ret = bdi_register(bdi, "%.28s-0", name);
if (ret)
- kfree(bdi);
+ bdi_put(bdi);
return ret ? ERR_PTR(ret) : bdi;
}
out_procfs:
if (proc_mtd)
remove_proc_entry("mtd", NULL);
- bdi_destroy(mtd_bdi);
- kfree(mtd_bdi);
+ bdi_put(mtd_bdi);
err_bdi:
class_unregister(&mtd_class);
err_reg:
if (proc_mtd)
remove_proc_entry("mtd", NULL);
class_unregister(&mtd_class);
- bdi_destroy(mtd_bdi);
- kfree(mtd_bdi);
+ bdi_put(mtd_bdi);
idr_destroy(&mtd_idr);
}
#include <linux/ctype.h>
#include <linux/slab.h>
#include <linux/major.h>
+#include <linux/backing-dev.h>
/*
* compare superblocks to see if they're equivalent
return 0;
}
+extern struct backing_dev_info *mtd_bdi;
+
/*
* mark the superblock by the MTD device it is using
* - set the device number to be the correct MTD block device for pesuperstence
sb->s_mtd = mtd;
sb->s_dev = MKDEV(MTD_BLOCK_MAJOR, mtd->index);
- sb->s_bdi = mtd->backing_dev_info;
+ sb->s_bdi = bdi_get(mtd_bdi);
+
return 0;
}
return 0;
}
-static struct blk_mq_ops ubiblock_mq_ops = {
+static const struct blk_mq_ops ubiblock_mq_ops = {
.queue_rq = ubiblock_queue_rq,
.init_request = ubiblock_init_request,
};
return err;
}
- if (bytes == 0) {
- err = ubi_wl_flush(ubi, UBI_ALL, UBI_ALL);
- if (err)
- return err;
+ err = ubi_wl_flush(ubi, UBI_ALL, UBI_ALL);
+ if (err)
+ return err;
+ if (bytes == 0) {
err = clear_update_marker(ubi, vol, 0);
if (err)
return err;
gso_max_size = min(gso_max_size, slave->dev->gso_max_size);
gso_max_segs = min(gso_max_segs, slave->dev->gso_max_segs);
}
+ bond_dev->hard_header_len = max_hard_header_len;
done:
bond_dev->vlan_features = vlan_features;
bond_dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL;
- bond_dev->hard_header_len = max_hard_header_len;
bond_dev->gso_max_segs = gso_max_segs;
netif_set_gso_max_size(bond_dev, gso_max_size);
int work_done = 0;
u32 stcmd = readl(priv->base + IFI_CANFD_STCMD);
- u32 rxstcmd = readl(priv->base + IFI_CANFD_STCMD);
+ u32 rxstcmd = readl(priv->base + IFI_CANFD_RXSTCMD);
u32 errctr = readl(priv->base + IFI_CANFD_ERROR_CTR);
/* Handle bus state changes */
devm_can_led_init(ndev);
- dev_info(&pdev->dev, "device registered (regs @ %p, IRQ%d)\n",
- priv->regs, ndev->irq);
+ dev_info(&pdev->dev, "device registered (IRQ%d)\n", ndev->irq);
return 0;
fail_candev:
PCAN-USB Pro dual CAN 2.0b channels USB adapter
PCAN-USB FD single CAN-FD channel USB adapter
PCAN-USB Pro FD dual CAN-FD channels USB adapter
+ PCAN-Chip USB CAN-FD to USB stamp module
+ PCAN-USB X6 6 CAN-FD channels USB adapter
(see also http://www.peak-system.com).
static int gs_usb_set_identify(struct net_device *netdev, bool do_identify)
{
struct gs_can *dev = netdev_priv(netdev);
- struct gs_identify_mode imode;
+ struct gs_identify_mode *imode;
int rc;
+ imode = kmalloc(sizeof(*imode), GFP_KERNEL);
+
+ if (!imode)
+ return -ENOMEM;
+
if (do_identify)
- imode.mode = GS_CAN_IDENTIFY_ON;
+ imode->mode = GS_CAN_IDENTIFY_ON;
else
- imode.mode = GS_CAN_IDENTIFY_OFF;
+ imode->mode = GS_CAN_IDENTIFY_OFF;
rc = usb_control_msg(interface_to_usbdev(dev->iface),
usb_sndctrlpipe(interface_to_usbdev(dev->iface),
USB_RECIP_INTERFACE,
dev->channel,
0,
- &imode,
- sizeof(imode),
+ imode,
+ sizeof(*imode),
100);
+ kfree(imode);
+
return (rc > 0) ? 0 : rc;
}
{USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBPRO_PRODUCT_ID)},
{USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBFD_PRODUCT_ID)},
{USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBPROFD_PRODUCT_ID)},
+ {USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBCHIP_PRODUCT_ID)},
{USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBX6_PRODUCT_ID)},
{} /* Terminating entry */
};
&pcan_usb_pro,
&pcan_usb_fd,
&pcan_usb_pro_fd,
+ &pcan_usb_chip,
&pcan_usb_x6,
};
#define PCAN_USBPRO_PRODUCT_ID 0x000d
#define PCAN_USBPROFD_PRODUCT_ID 0x0011
#define PCAN_USBFD_PRODUCT_ID 0x0012
+#define PCAN_USBCHIP_PRODUCT_ID 0x0013
#define PCAN_USBX6_PRODUCT_ID 0x0014
#define PCAN_USB_DRIVER_NAME "peak_usb"
extern const struct peak_usb_adapter pcan_usb;
extern const struct peak_usb_adapter pcan_usb_pro;
extern const struct peak_usb_adapter pcan_usb_fd;
+extern const struct peak_usb_adapter pcan_usb_chip;
extern const struct peak_usb_adapter pcan_usb_pro_fd;
extern const struct peak_usb_adapter pcan_usb_x6;
.do_get_berr_counter = pcan_usb_fd_get_berr_counter,
};
+/* describes the PCAN-CHIP USB */
+static const struct can_bittiming_const pcan_usb_chip_const = {
+ .name = "pcan_chip_usb",
+ .tseg1_min = 1,
+ .tseg1_max = (1 << PUCAN_TSLOW_TSGEG1_BITS),
+ .tseg2_min = 1,
+ .tseg2_max = (1 << PUCAN_TSLOW_TSGEG2_BITS),
+ .sjw_max = (1 << PUCAN_TSLOW_SJW_BITS),
+ .brp_min = 1,
+ .brp_max = (1 << PUCAN_TSLOW_BRP_BITS),
+ .brp_inc = 1,
+};
+
+static const struct can_bittiming_const pcan_usb_chip_data_const = {
+ .name = "pcan_chip_usb",
+ .tseg1_min = 1,
+ .tseg1_max = (1 << PUCAN_TFAST_TSGEG1_BITS),
+ .tseg2_min = 1,
+ .tseg2_max = (1 << PUCAN_TFAST_TSGEG2_BITS),
+ .sjw_max = (1 << PUCAN_TFAST_SJW_BITS),
+ .brp_min = 1,
+ .brp_max = (1 << PUCAN_TFAST_BRP_BITS),
+ .brp_inc = 1,
+};
+
+const struct peak_usb_adapter pcan_usb_chip = {
+ .name = "PCAN-Chip USB",
+ .device_id = PCAN_USBCHIP_PRODUCT_ID,
+ .ctrl_count = PCAN_USBFD_CHANNEL_COUNT,
+ .ctrlmode_supported = CAN_CTRLMODE_FD |
+ CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_LISTENONLY,
+ .clock = {
+ .freq = PCAN_UFD_CRYSTAL_HZ,
+ },
+ .bittiming_const = &pcan_usb_chip_const,
+ .data_bittiming_const = &pcan_usb_chip_data_const,
+
+ /* size of device private data */
+ .sizeof_dev_private = sizeof(struct pcan_usb_fd_device),
+
+ /* timestamps usage */
+ .ts_used_bits = 32,
+ .ts_period = 1000000, /* calibration period in ts. */
+ .us_per_ts_scale = 1, /* us = (ts * scale) >> shift */
+ .us_per_ts_shift = 0,
+
+ /* give here messages in/out endpoints */
+ .ep_msg_in = PCAN_USBPRO_EP_MSGIN,
+ .ep_msg_out = {PCAN_USBPRO_EP_MSGOUT_0},
+
+ /* size of rx/tx usb buffers */
+ .rx_buffer_size = PCAN_UFD_RX_BUFFER_SIZE,
+ .tx_buffer_size = PCAN_UFD_TX_BUFFER_SIZE,
+
+ /* device callbacks */
+ .intf_probe = pcan_usb_pro_probe, /* same as PCAN-USB Pro */
+ .dev_init = pcan_usb_fd_init,
+
+ .dev_exit = pcan_usb_fd_exit,
+ .dev_free = pcan_usb_fd_free,
+ .dev_set_bus = pcan_usb_fd_set_bus,
+ .dev_set_bittiming = pcan_usb_fd_set_bittiming_slow,
+ .dev_set_data_bittiming = pcan_usb_fd_set_bittiming_fast,
+ .dev_decode_buf = pcan_usb_fd_decode_buf,
+ .dev_start = pcan_usb_fd_start,
+ .dev_stop = pcan_usb_fd_stop,
+ .dev_restart_async = pcan_usb_fd_restart_async,
+ .dev_encode_msg = pcan_usb_fd_encode_msg,
+
+ .do_get_berr_counter = pcan_usb_fd_get_berr_counter,
+};
+
/* describes the PCAN-USB Pro FD adapter */
static const struct can_bittiming_const pcan_usb_pro_fd_const = {
.name = "pcan_usb_pro_fd",
static void b53_set_forwarding(struct b53_device *dev, int enable)
{
+ struct dsa_switch *ds = dev->ds;
u8 mgmt;
b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, &mgmt);
mgmt &= ~SM_SW_FWD_EN;
b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, mgmt);
+
+ /* Include IMP port in dumb forwarding mode when no tagging protocol is
+ * set
+ */
+ if (ds->ops->get_tag_protocol(ds) == DSA_TAG_PROTO_NONE) {
+ b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_CTRL, &mgmt);
+ mgmt |= B53_MII_DUMB_FWDG_EN;
+ b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_CTRL, mgmt);
+ }
}
static void b53_enable_vlan(struct b53_device *dev, bool enable)
static int b53_switch_reset(struct b53_device *dev)
{
- u8 mgmt;
+ unsigned int timeout = 1000;
+ u8 mgmt, reg;
b53_switch_reset_gpio(dev);
b53_write8(dev, B53_CTRL_PAGE, B53_SOFTRESET, 0x00);
}
+ /* This is specific to 58xx devices here, do not use is58xx() which
+ * covers the larger Starfigther 2 family, including 7445/7278 which
+ * still use this driver as a library and need to perform the reset
+ * earlier.
+ */
+ if (dev->chip_id == BCM58XX_DEVICE_ID) {
+ b53_read8(dev, B53_CTRL_PAGE, B53_SOFTRESET, ®);
+ reg |= SW_RST | EN_SW_RST | EN_CH_RST;
+ b53_write8(dev, B53_CTRL_PAGE, B53_SOFTRESET, reg);
+
+ do {
+ b53_read8(dev, B53_CTRL_PAGE, B53_SOFTRESET, ®);
+ if (!(reg & SW_RST))
+ break;
+
+ usleep_range(1000, 2000);
+ } while (timeout-- > 0);
+
+ if (timeout == 0)
+ return -ETIMEDOUT;
+ }
+
b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, &mgmt);
if (!(mgmt & SM_SW_FWD_EN)) {
.vlans = 4096,
.enabled_ports = 0x1ff,
.arl_entries = 4,
- .cpu_port = B53_CPU_PORT_25,
+ .cpu_port = B53_CPU_PORT,
.vta_regs = B53_VTA_REGS,
.duplex_reg = B53_DUPLEX_STAT_GE,
.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
#define B53_UC_FWD_EN BIT(6)
#define B53_MC_FWD_EN BIT(7)
+/* Switch control (8 bit) */
+#define B53_SWITCH_CTRL 0x22
+#define B53_MII_DUMB_FWDG_EN BIT(6)
+
/* (16 bit) */
#define B53_UC_FLOOD_MASK 0x32
#define B53_MC_FLOOD_MASK 0x34
/* Software reset register (8 bit) */
#define B53_SOFTRESET 0x79
#define SW_RST BIT(7)
+#define EN_CH_RST BIT(6)
#define EN_SW_RST BIT(4)
/* Fast Aging Control register (8 bit) */
goto err_exit;
ndev->mtu = new_mtu;
- if (netif_running(ndev)) {
- aq_ndev_close(ndev);
- aq_ndev_open(ndev);
- }
-
err_exit:
return err;
}
dx_buff->mss = skb_shinfo(skb)->gso_size;
dx_buff->is_txc = 1U;
+ dx_buff->is_ipv6 =
+ (ip_hdr(skb)->version == 6) ? 1U : 0U;
+
dx = aq_ring_next_dx(ring, dx);
dx_buff = &ring->buff_ring[dx];
++ret;
if (skb->ip_summed == CHECKSUM_PARTIAL) {
dx_buff->is_ip_cso = (htons(ETH_P_IP) == skb->protocol) ?
1U : 0U;
- dx_buff->is_tcp_cso =
- (ip_hdr(skb)->protocol == IPPROTO_TCP) ? 1U : 0U;
- dx_buff->is_udp_cso =
- (ip_hdr(skb)->protocol == IPPROTO_UDP) ? 1U : 0U;
+
+ if (ip_hdr(skb)->version == 4) {
+ dx_buff->is_tcp_cso =
+ (ip_hdr(skb)->protocol == IPPROTO_TCP) ?
+ 1U : 0U;
+ dx_buff->is_udp_cso =
+ (ip_hdr(skb)->protocol == IPPROTO_UDP) ?
+ 1U : 0U;
+ } else if (ip_hdr(skb)->version == 6) {
+ dx_buff->is_tcp_cso =
+ (ipv6_hdr(skb)->nexthdr == NEXTHDR_TCP) ?
+ 1U : 0U;
+ dx_buff->is_udp_cso =
+ (ipv6_hdr(skb)->nexthdr == NEXTHDR_UDP) ?
+ 1U : 0U;
+ }
}
for (; nr_frags--; ++frag_count) {
self->hw_head = 0;
self->sw_head = 0;
self->sw_tail = 0;
+ spin_lock_init(&self->header.lock);
return 0;
}
u8 len_l2;
u8 len_l3;
u8 len_l4;
- u8 rsvd2;
+ u8 is_ipv6:1;
+ u8 rsvd2:7;
u32 len_pkt;
};
};
buff->len_l3 +
buff->len_l2);
is_gso = true;
+
+ if (buff->is_ipv6)
+ txd->ctl |= HW_ATL_A0_TXD_CTL_CMD_IPV6;
} else {
buff_pa_len = buff->len;
if (unlikely(buff->is_eop)) {
txd->ctl |= HW_ATL_A0_TXD_CTL_EOP;
txd->ctl |= HW_ATL_A0_TXD_CTL_CMD_WB;
+ is_gso = false;
}
}
buff->len_l3 +
buff->len_l2);
is_gso = true;
+
+ if (buff->is_ipv6)
+ txd->ctl |= HW_ATL_B0_TXD_CTL_CMD_IPV6;
} else {
buff_pa_len = buff->len;
if (unlikely(buff->is_eop)) {
txd->ctl |= HW_ATL_B0_TXD_CTL_EOP;
txd->ctl |= HW_ATL_B0_TXD_CTL_CMD_WB;
+ is_gso = false;
}
}
GENERAL_ATTEN_OFFSET(LATCHED_ATTN_RBCP) | \
GENERAL_ATTEN_OFFSET(LATCHED_ATTN_RSVD_GRC))
-#define HW_INTERRUT_ASSERT_SET_0 \
+#define HW_INTERRUPT_ASSERT_SET_0 \
(AEU_INPUTS_ATTN_BITS_TSDM_HW_INTERRUPT | \
AEU_INPUTS_ATTN_BITS_TCM_HW_INTERRUPT | \
AEU_INPUTS_ATTN_BITS_TSEMI_HW_INTERRUPT | \
AEU_INPUTS_ATTN_BITS_TSEMI_PARITY_ERROR |\
AEU_INPUTS_ATTN_BITS_TCM_PARITY_ERROR |\
AEU_INPUTS_ATTN_BITS_PBCLIENT_PARITY_ERROR)
-#define HW_INTERRUT_ASSERT_SET_1 \
+#define HW_INTERRUPT_ASSERT_SET_1 \
(AEU_INPUTS_ATTN_BITS_QM_HW_INTERRUPT | \
AEU_INPUTS_ATTN_BITS_TIMERS_HW_INTERRUPT | \
AEU_INPUTS_ATTN_BITS_XSDM_HW_INTERRUPT | \
AEU_INPUTS_ATTN_BITS_UPB_PARITY_ERROR | \
AEU_INPUTS_ATTN_BITS_CSDM_PARITY_ERROR |\
AEU_INPUTS_ATTN_BITS_CCM_PARITY_ERROR)
-#define HW_INTERRUT_ASSERT_SET_2 \
+#define HW_INTERRUPT_ASSERT_SET_2 \
(AEU_INPUTS_ATTN_BITS_CSEMI_HW_INTERRUPT | \
AEU_INPUTS_ATTN_BITS_CDU_HW_INTERRUPT | \
AEU_INPUTS_ATTN_BITS_DMAE_HW_INTERRUPT | \
bnx2x_release_phy_lock(bp);
}
- if (attn & HW_INTERRUT_ASSERT_SET_0) {
+ if (attn & HW_INTERRUPT_ASSERT_SET_0) {
val = REG_RD(bp, reg_offset);
- val &= ~(attn & HW_INTERRUT_ASSERT_SET_0);
+ val &= ~(attn & HW_INTERRUPT_ASSERT_SET_0);
REG_WR(bp, reg_offset, val);
BNX2X_ERR("FATAL HW block attention set0 0x%x\n",
- (u32)(attn & HW_INTERRUT_ASSERT_SET_0));
+ (u32)(attn & HW_INTERRUPT_ASSERT_SET_0));
bnx2x_panic();
}
}
BNX2X_ERR("FATAL error from DORQ\n");
}
- if (attn & HW_INTERRUT_ASSERT_SET_1) {
+ if (attn & HW_INTERRUPT_ASSERT_SET_1) {
int port = BP_PORT(bp);
int reg_offset;
MISC_REG_AEU_ENABLE1_FUNC_0_OUT_1);
val = REG_RD(bp, reg_offset);
- val &= ~(attn & HW_INTERRUT_ASSERT_SET_1);
+ val &= ~(attn & HW_INTERRUPT_ASSERT_SET_1);
REG_WR(bp, reg_offset, val);
BNX2X_ERR("FATAL HW block attention set1 0x%x\n",
- (u32)(attn & HW_INTERRUT_ASSERT_SET_1));
+ (u32)(attn & HW_INTERRUPT_ASSERT_SET_1));
bnx2x_panic();
}
}
}
}
- if (attn & HW_INTERRUT_ASSERT_SET_2) {
+ if (attn & HW_INTERRUPT_ASSERT_SET_2) {
int port = BP_PORT(bp);
int reg_offset;
MISC_REG_AEU_ENABLE1_FUNC_0_OUT_2);
val = REG_RD(bp, reg_offset);
- val &= ~(attn & HW_INTERRUT_ASSERT_SET_2);
+ val &= ~(attn & HW_INTERRUPT_ASSERT_SET_2);
REG_WR(bp, reg_offset, val);
BNX2X_ERR("FATAL HW block attention set2 0x%x\n",
- (u32)(attn & HW_INTERRUT_ASSERT_SET_2));
+ (u32)(attn & HW_INTERRUPT_ASSERT_SET_2));
bnx2x_panic();
}
}
for (j = 0; j < max_idx; j++) {
struct bnxt_sw_rx_bd *rx_buf = &rxr->rx_buf_ring[j];
+ dma_addr_t mapping = rx_buf->mapping;
void *data = rx_buf->data;
if (!data)
continue;
- dma_unmap_single(&pdev->dev, rx_buf->mapping,
- bp->rx_buf_use_size, bp->rx_dir);
-
rx_buf->data = NULL;
- if (BNXT_RX_PAGE_MODE(bp))
+ if (BNXT_RX_PAGE_MODE(bp)) {
+ mapping -= bp->rx_dma_offset;
+ dma_unmap_page(&pdev->dev, mapping,
+ PAGE_SIZE, bp->rx_dir);
__free_page(data);
- else
+ } else {
+ dma_unmap_single(&pdev->dev, mapping,
+ bp->rx_buf_use_size,
+ bp->rx_dir);
kfree(data);
+ }
}
for (j = 0; j < max_agg_idx; j++) {
return 0;
}
+static void bnxt_init_cp_rings(struct bnxt *bp)
+{
+ int i;
+
+ for (i = 0; i < bp->cp_nr_rings; i++) {
+ struct bnxt_cp_ring_info *cpr = &bp->bnapi[i]->cp_ring;
+ struct bnxt_ring_struct *ring = &cpr->cp_ring_struct;
+
+ ring->fw_ring_id = INVALID_HW_RING_ID;
+ }
+}
+
static int bnxt_init_rx_rings(struct bnxt *bp)
{
int i, rc = 0;
rc = bnxt_hwrm_vnic_set_tpa(bp, i, tpa_flags);
if (rc) {
netdev_err(bp->dev, "hwrm vnic set tpa failure rc for vnic %d: %x\n",
- rc, i);
+ i, rc);
return rc;
}
}
static int bnxt_init_nic(struct bnxt *bp, bool irq_re_init)
{
+ bnxt_init_cp_rings(bp);
bnxt_init_rx_rings(bp);
bnxt_init_tx_rings(bp);
bnxt_init_ring_grps(bp, irq_re_init);
bfa_ioc_send_enable(struct bfa_ioc *ioc)
{
struct bfi_ioc_ctrl_req enable_req;
- struct timeval tv;
bfi_h2i_set(enable_req.mh, BFI_MC_IOC, BFI_IOC_H2I_ENABLE_REQ,
bfa_ioc_portid(ioc));
enable_req.clscode = htons(ioc->clscode);
- do_gettimeofday(&tv);
- enable_req.tv_sec = ntohl(tv.tv_sec);
+ enable_req.rsvd = htons(0);
+ /* overflow in 2106 */
+ enable_req.tv_sec = ntohl(ktime_get_real_seconds());
bfa_ioc_mbox_send(ioc, &enable_req, sizeof(struct bfi_ioc_ctrl_req));
}
bfi_h2i_set(disable_req.mh, BFI_MC_IOC, BFI_IOC_H2I_DISABLE_REQ,
bfa_ioc_portid(ioc));
+ disable_req.clscode = htons(ioc->clscode);
+ disable_req.rsvd = htons(0);
+ /* overflow in 2106 */
+ disable_req.tv_sec = ntohl(ktime_get_real_seconds());
bfa_ioc_mbox_send(ioc, &disable_req, sizeof(struct bfi_ioc_ctrl_req));
}
pci_read_config_word(pdev, PCI_SUBSYSTEM_ID, &sdevid);
switch (sdevid) {
case PCI_SUBSYS_DEVID_81XX_BGX:
+ case PCI_SUBSYS_DEVID_81XX_RGX:
max_bgx_per_node = MAX_BGX_PER_CN81XX;
break;
case PCI_SUBSYS_DEVID_83XX_BGX:
/* Subsystem device IDs */
#define PCI_SUBSYS_DEVID_88XX_BGX 0xA126
#define PCI_SUBSYS_DEVID_81XX_BGX 0xA226
+#define PCI_SUBSYS_DEVID_81XX_RGX 0xA254
#define PCI_SUBSYS_DEVID_83XX_BGX 0xA326
#define MAX_BGX_THUNDER 8 /* Max 2 nodes, 4 per node */
__be_cmd_set_logical_link_config(struct be_adapter *adapter,
int link_state, int version, u8 domain)
{
- struct be_mcc_wrb *wrb;
struct be_cmd_req_set_ll_link *req;
+ struct be_mcc_wrb *wrb;
+ u32 link_config = 0;
int status;
mutex_lock(&adapter->mcc_lock);
if (link_state == IFLA_VF_LINK_STATE_ENABLE ||
link_state == IFLA_VF_LINK_STATE_AUTO)
- req->link_config |= PLINK_ENABLE;
+ link_config |= PLINK_ENABLE;
if (link_state == IFLA_VF_LINK_STATE_AUTO)
- req->link_config |= PLINK_TRACK;
+ link_config |= PLINK_TRACK;
+
+ req->link_config = cpu_to_le32(link_config);
status = be_mcc_notify_wait(adapter);
err:
nps_enet_tx_handler(ndev);
work_done = nps_enet_rx_handler(ndev);
- if (work_done < budget) {
+ if ((work_done < budget) && napi_complete_done(napi, work_done)) {
u32 buf_int_enable_value = 0;
- napi_complete_done(napi, work_done);
-
/* set tx_done and rx_rdy bits */
buf_int_enable_value |= NPS_ENET_ENABLE << RX_RDY_SHIFT;
buf_int_enable_value |= NPS_ENET_ENABLE << TX_DONE_SHIFT;
#include <linux/io.h>
#include <linux/module.h>
#include <linux/netdevice.h>
+#include <linux/of.h>
#include <linux/phy.h>
#include <linux/platform_device.h>
+#include <linux/property.h>
#include <net/ip.h>
#include <net/ncsi.h>
else
*link_status = 0;
- ret = mac_cb->dsaf_dev->misc_op->get_sfp_prsnt(mac_cb, &sfp_prsnt);
- if (!ret)
- *link_status = *link_status && sfp_prsnt;
+ if (mac_cb->media_type == HNAE_MEDIA_TYPE_FIBER) {
+ ret = mac_cb->dsaf_dev->misc_op->get_sfp_prsnt(mac_cb,
+ &sfp_prsnt);
+ if (!ret)
+ *link_status = *link_status && sfp_prsnt;
+ }
mac_cb->link = *link_status;
}
of_node_put(np);
np = of_parse_phandle(to_of_node(mac_cb->fw_port),
- "serdes-syscon", 0);
+ "serdes-syscon", 0);
syscon = syscon_node_to_regmap(np);
of_node_put(np);
if (IS_ERR_OR_NULL(syscon)) {
mac_key->high.bits.mac_3 = addr[3];
mac_key->low.bits.mac_4 = addr[4];
mac_key->low.bits.mac_5 = addr[5];
+ mac_key->low.bits.port_vlan = 0;
dsaf_set_field(mac_key->low.bits.port_vlan, DSAF_TBL_TCAM_KEY_VLAN_M,
DSAF_TBL_TCAM_KEY_VLAN_S, vlan_id);
dsaf_set_field(mac_key->low.bits.port_vlan, DSAF_TBL_TCAM_KEY_PORT_M,
/* find the tcam entry index for promisc */
entry_index = dsaf_promisc_tcam_entry(port);
+ memset(&tbl_tcam_data, 0, sizeof(tbl_tcam_data));
+ memset(&tbl_tcam_mask, 0, sizeof(tbl_tcam_mask));
+
/* config key mask */
if (enable) {
- memset(&tbl_tcam_data, 0, sizeof(tbl_tcam_data));
- memset(&tbl_tcam_mask, 0, sizeof(tbl_tcam_mask));
dsaf_set_field(tbl_tcam_data.low.bits.port_vlan,
DSAF_TBL_TCAM_KEY_PORT_M,
DSAF_TBL_TCAM_KEY_PORT_S, port);
return 0;
}
+int hns_mac_get_sfp_prsnt_acpi(struct hns_mac_cb *mac_cb, int *sfp_prsnt)
+{
+ union acpi_object *obj;
+ union acpi_object obj_args, argv4;
+
+ obj_args.integer.type = ACPI_TYPE_INTEGER;
+ obj_args.integer.value = mac_cb->mac_id;
+
+ argv4.type = ACPI_TYPE_PACKAGE,
+ argv4.package.count = 1,
+ argv4.package.elements = &obj_args,
+
+ obj = acpi_evaluate_dsm(ACPI_HANDLE(mac_cb->dev),
+ hns_dsaf_acpi_dsm_uuid, 0,
+ HNS_OP_GET_SFP_STAT_FUNC, &argv4);
+
+ if (!obj || obj->type != ACPI_TYPE_INTEGER)
+ return -ENODEV;
+
+ *sfp_prsnt = obj->integer.value;
+
+ ACPI_FREE(obj);
+
+ return 0;
+}
+
/**
* hns_mac_config_sds_loopback - set loop back for serdes
* @mac_cb: mac control block
misc_op->hns_dsaf_roce_srst = hns_dsaf_roce_srst_acpi;
misc_op->get_phy_if = hns_mac_get_phy_if_acpi;
- misc_op->get_sfp_prsnt = hns_mac_get_sfp_prsnt;
+ misc_op->get_sfp_prsnt = hns_mac_get_sfp_prsnt_acpi;
misc_op->cfg_serdes_loopback = hns_mac_config_sds_loopback_acpi;
} else {
/* Quiesce the device without resetting the hardware */
e1000e_down(adapter, false);
e1000_free_irq(adapter);
- e1000e_reset_interrupt_capability(adapter);
}
+ e1000e_reset_interrupt_capability(adapter);
/* Allow time for pending master requests to run */
e1000e_disable_pcie_master(&adapter->hw);
if (!vsi->netdev)
return;
- for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++)
- napi_enable(&vsi->q_vectors[q_idx]->napi);
+ for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) {
+ struct i40e_q_vector *q_vector = vsi->q_vectors[q_idx];
+
+ if (q_vector->rx.ring || q_vector->tx.ring)
+ napi_enable(&q_vector->napi);
+ }
}
/**
if (!vsi->netdev)
return;
- for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++)
- napi_disable(&vsi->q_vectors[q_idx]->napi);
+ for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) {
+ struct i40e_q_vector *q_vector = vsi->q_vectors[q_idx];
+
+ if (q_vector->rx.ring || q_vector->tx.ring)
+ napi_disable(&q_vector->napi);
+ }
}
/**
struct mtk_mac *mac = netdev_priv(dev);
struct mtk_eth *eth = mac->hw;
struct mtk_tx_dma *itxd, *txd;
- struct mtk_tx_buf *tx_buf;
+ struct mtk_tx_buf *itx_buf, *tx_buf;
dma_addr_t mapped_addr;
unsigned int nr_frags;
int i, n_desc = 1;
fport = (mac->id + 1) << TX_DMA_FPORT_SHIFT;
txd4 |= fport;
- tx_buf = mtk_desc_to_tx_buf(ring, itxd);
- memset(tx_buf, 0, sizeof(*tx_buf));
+ itx_buf = mtk_desc_to_tx_buf(ring, itxd);
+ memset(itx_buf, 0, sizeof(*itx_buf));
if (gso)
txd4 |= TX_DMA_TSO;
return -ENOMEM;
WRITE_ONCE(itxd->txd1, mapped_addr);
- tx_buf->flags |= MTK_TX_FLAGS_SINGLE0;
- dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr);
- dma_unmap_len_set(tx_buf, dma_len0, skb_headlen(skb));
+ itx_buf->flags |= MTK_TX_FLAGS_SINGLE0;
+ itx_buf->flags |= (!mac->id) ? MTK_TX_FLAGS_FPORT0 :
+ MTK_TX_FLAGS_FPORT1;
+ dma_unmap_addr_set(itx_buf, dma_addr0, mapped_addr);
+ dma_unmap_len_set(itx_buf, dma_len0, skb_headlen(skb));
/* TX SG offload */
txd = itxd;
last_frag * TX_DMA_LS0));
WRITE_ONCE(txd->txd4, fport);
- tx_buf->skb = (struct sk_buff *)MTK_DMA_DUMMY_DESC;
tx_buf = mtk_desc_to_tx_buf(ring, txd);
memset(tx_buf, 0, sizeof(*tx_buf));
-
+ tx_buf->skb = (struct sk_buff *)MTK_DMA_DUMMY_DESC;
tx_buf->flags |= MTK_TX_FLAGS_PAGE0;
+ tx_buf->flags |= (!mac->id) ? MTK_TX_FLAGS_FPORT0 :
+ MTK_TX_FLAGS_FPORT1;
+
dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr);
dma_unmap_len_set(tx_buf, dma_len0, frag_map_size);
frag_size -= frag_map_size;
}
/* store skb to cleanup */
- tx_buf->skb = skb;
+ itx_buf->skb = skb;
WRITE_ONCE(itxd->txd4, txd4);
WRITE_ONCE(itxd->txd3, (TX_DMA_SWC | TX_DMA_PLEN0(skb_headlen(skb)) |
while ((cpu != dma) && budget) {
u32 next_cpu = desc->txd2;
- int mac;
+ int mac = 0;
desc = mtk_qdma_phys_to_virt(ring, desc->txd2);
if ((desc->txd3 & TX_DMA_OWNER_CPU) == 0)
break;
- mac = (desc->txd4 >> TX_DMA_FPORT_SHIFT) &
- TX_DMA_FPORT_MASK;
- mac--;
-
tx_buf = mtk_desc_to_tx_buf(ring, desc);
+ if (tx_buf->flags & MTK_TX_FLAGS_FPORT1)
+ mac = 1;
+
skb = tx_buf->skb;
if (!skb) {
condition = 1;
struct u64_stats_sync syncp;
};
-/* PDMA descriptor can point at 1-2 segments. This enum allows us to track how
- * memory was allocated so that it can be freed properly
- */
enum mtk_tx_flags {
+ /* PDMA descriptor can point at 1-2 segments. This enum allows us to
+ * track how memory was allocated so that it can be freed properly.
+ */
MTK_TX_FLAGS_SINGLE0 = 0x01,
MTK_TX_FLAGS_PAGE0 = 0x02,
+
+ /* MTK_TX_FLAGS_FPORTx allows tracking which port the transmitted
+ * SKB out instead of looking up through hardware TX descriptor.
+ */
+ MTK_TX_FLAGS_FPORT0 = 0x04,
+ MTK_TX_FLAGS_FPORT1 = 0x08,
};
/* This enum allows us to identify how the clock is defined on the array of the
#define MLX5E_VALID_NUM_MTTS(num_mtts) (MLX5_MTT_OCTW(num_mtts) - 1 <= U16_MAX)
#define MLX5_UMR_ALIGN (2048)
-#define MLX5_MPWRQ_SMALL_PACKET_THRESHOLD (128)
+#define MLX5_MPWRQ_SMALL_PACKET_THRESHOLD (256)
#define MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ (64 * 1024)
#define MLX5E_DEFAULT_LRO_TIMEOUT 32
int idx = 0;
int err = 0;
+ info->data = MAX_NUM_OF_ETHTOOL_RULES;
while ((!err || err == -ENOENT) && idx < info->rule_cnt) {
err = mlx5e_ethtool_get_flow(priv, info, location);
if (!err)
static void mlx5e_update_sw_counters(struct mlx5e_priv *priv)
{
- struct mlx5e_sw_stats *s = &priv->stats.sw;
+ struct mlx5e_sw_stats temp, *s = &temp;
struct mlx5e_rq_stats *rq_stats;
struct mlx5e_sq_stats *sq_stats;
u64 tx_offload_none = 0;
s->link_down_events_phy = MLX5_GET(ppcnt_reg,
priv->stats.pport.phy_counters,
counter_set.phys_layer_cntrs.link_down_events);
+ memcpy(&priv->stats.sw, s, sizeof(*s));
}
static void mlx5e_update_vport_counters(struct mlx5e_priv *priv)
MLX5_SET(query_vport_counter_in, in, op_mod, 0);
MLX5_SET(query_vport_counter_in, in, other_vport, 0);
- memset(out, 0, outlen);
mlx5_cmd_exec(mdev, in, sizeof(in), out, outlen);
}
if (!err && (flow->flags & MLX5E_TC_FLOW_ESWITCH) &&
rep->vport != FDB_UPLINK_VPORT) {
- if (min_inline > esw->offloads.inline_mode) {
+ if (esw->offloads.inline_mode != MLX5_INLINE_MODE_NONE &&
+ esw->offloads.inline_mode < min_inline) {
netdev_warn(priv->netdev,
"Flow is not offloaded due to min inline setting, required %d actual %d\n",
min_inline, esw->offloads.inline_mode);
return 0;
}
-static int gen_vxlan_header_ipv4(struct net_device *out_dev,
- char buf[],
- unsigned char h_dest[ETH_ALEN],
- int ttl,
- __be32 daddr,
- __be32 saddr,
- __be16 udp_dst_port,
- __be32 vx_vni)
+static void gen_vxlan_header_ipv4(struct net_device *out_dev,
+ char buf[], int encap_size,
+ unsigned char h_dest[ETH_ALEN],
+ int ttl,
+ __be32 daddr,
+ __be32 saddr,
+ __be16 udp_dst_port,
+ __be32 vx_vni)
{
- int encap_size = VXLAN_HLEN + sizeof(struct iphdr) + ETH_HLEN;
struct ethhdr *eth = (struct ethhdr *)buf;
struct iphdr *ip = (struct iphdr *)((char *)eth + sizeof(struct ethhdr));
struct udphdr *udp = (struct udphdr *)((char *)ip + sizeof(struct iphdr));
udp->dest = udp_dst_port;
vxh->vx_flags = VXLAN_HF_VNI;
vxh->vx_vni = vxlan_vni_field(vx_vni);
-
- return encap_size;
}
-static int gen_vxlan_header_ipv6(struct net_device *out_dev,
- char buf[],
- unsigned char h_dest[ETH_ALEN],
- int ttl,
- struct in6_addr *daddr,
- struct in6_addr *saddr,
- __be16 udp_dst_port,
- __be32 vx_vni)
+static void gen_vxlan_header_ipv6(struct net_device *out_dev,
+ char buf[], int encap_size,
+ unsigned char h_dest[ETH_ALEN],
+ int ttl,
+ struct in6_addr *daddr,
+ struct in6_addr *saddr,
+ __be16 udp_dst_port,
+ __be32 vx_vni)
{
- int encap_size = VXLAN_HLEN + sizeof(struct ipv6hdr) + ETH_HLEN;
struct ethhdr *eth = (struct ethhdr *)buf;
struct ipv6hdr *ip6h = (struct ipv6hdr *)((char *)eth + sizeof(struct ethhdr));
struct udphdr *udp = (struct udphdr *)((char *)ip6h + sizeof(struct ipv6hdr));
udp->dest = udp_dst_port;
vxh->vx_flags = VXLAN_HF_VNI;
vxh->vx_vni = vxlan_vni_field(vx_vni);
-
- return encap_size;
}
static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
struct net_device **out_dev)
{
int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
+ int ipv4_encap_size = ETH_HLEN + sizeof(struct iphdr) + VXLAN_HLEN;
struct ip_tunnel_key *tun_key = &e->tun_info.key;
- int encap_size, ttl, err;
struct neighbour *n = NULL;
struct flowi4 fl4 = {};
char *encap_header;
+ int ttl, err;
+
+ if (max_encap_size < ipv4_encap_size) {
+ mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
+ ipv4_encap_size, max_encap_size);
+ return -EOPNOTSUPP;
+ }
- encap_header = kzalloc(max_encap_size, GFP_KERNEL);
+ encap_header = kzalloc(ipv4_encap_size, GFP_KERNEL);
if (!encap_header)
return -ENOMEM;
switch (e->tunnel_type) {
case MLX5_HEADER_TYPE_VXLAN:
- encap_size = gen_vxlan_header_ipv4(*out_dev, encap_header,
- e->h_dest, ttl,
- fl4.daddr,
- fl4.saddr, tun_key->tp_dst,
- tunnel_id_to_key32(tun_key->tun_id));
+ gen_vxlan_header_ipv4(*out_dev, encap_header,
+ ipv4_encap_size, e->h_dest, ttl,
+ fl4.daddr,
+ fl4.saddr, tun_key->tp_dst,
+ tunnel_id_to_key32(tun_key->tun_id));
break;
default:
err = -EOPNOTSUPP;
}
err = mlx5_encap_alloc(priv->mdev, e->tunnel_type,
- encap_size, encap_header, &e->encap_id);
+ ipv4_encap_size, encap_header, &e->encap_id);
out:
if (err && n)
neigh_release(n);
{
int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
+ int ipv6_encap_size = ETH_HLEN + sizeof(struct ipv6hdr) + VXLAN_HLEN;
struct ip_tunnel_key *tun_key = &e->tun_info.key;
- int encap_size, err, ttl = 0;
struct neighbour *n = NULL;
struct flowi6 fl6 = {};
char *encap_header;
+ int err, ttl = 0;
+
+ if (max_encap_size < ipv6_encap_size) {
+ mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
+ ipv6_encap_size, max_encap_size);
+ return -EOPNOTSUPP;
+ }
- encap_header = kzalloc(max_encap_size, GFP_KERNEL);
+ encap_header = kzalloc(ipv6_encap_size, GFP_KERNEL);
if (!encap_header)
return -ENOMEM;
switch (e->tunnel_type) {
case MLX5_HEADER_TYPE_VXLAN:
- encap_size = gen_vxlan_header_ipv6(*out_dev, encap_header,
- e->h_dest, ttl,
- &fl6.daddr,
- &fl6.saddr, tun_key->tp_dst,
- tunnel_id_to_key32(tun_key->tun_id));
+ gen_vxlan_header_ipv6(*out_dev, encap_header,
+ ipv6_encap_size, e->h_dest, ttl,
+ &fl6.daddr,
+ &fl6.saddr, tun_key->tp_dst,
+ tunnel_id_to_key32(tun_key->tun_id));
break;
default:
err = -EOPNOTSUPP;
}
err = mlx5_encap_alloc(priv->mdev, e->tunnel_type,
- encap_size, encap_header, &e->encap_id);
+ ipv6_encap_size, encap_header, &e->encap_id);
out:
if (err && n)
neigh_release(n);
struct mlx5_core_dev *dev = devlink_priv(devlink);
struct mlx5_eswitch *esw = dev->priv.eswitch;
int num_vports = esw->enabled_vports;
- int err;
- int vport;
+ int err, vport;
u8 mlx5_mode;
if (!MLX5_CAP_GEN(dev, vport_group_manager))
if (esw->mode == SRIOV_NONE)
return -EOPNOTSUPP;
- if (MLX5_CAP_ETH(dev, wqe_inline_mode) !=
- MLX5_CAP_INLINE_MODE_VPORT_CONTEXT)
+ switch (MLX5_CAP_ETH(dev, wqe_inline_mode)) {
+ case MLX5_CAP_INLINE_MODE_NOT_REQUIRED:
+ if (mode == DEVLINK_ESWITCH_INLINE_MODE_NONE)
+ return 0;
+ /* fall through */
+ case MLX5_CAP_INLINE_MODE_L2:
+ esw_warn(dev, "Inline mode can't be set\n");
return -EOPNOTSUPP;
+ case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT:
+ break;
+ }
if (esw->offloads.num_flows > 0) {
esw_warn(dev, "Can't set inline mode when flows are configured\n");
if (esw->mode == SRIOV_NONE)
return -EOPNOTSUPP;
- if (MLX5_CAP_ETH(dev, wqe_inline_mode) !=
- MLX5_CAP_INLINE_MODE_VPORT_CONTEXT)
- return -EOPNOTSUPP;
-
return esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode);
}
int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode)
{
+ u8 prev_mlx5_mode, mlx5_mode = MLX5_INLINE_MODE_L2;
struct mlx5_core_dev *dev = esw->dev;
int vport;
- u8 prev_mlx5_mode, mlx5_mode = MLX5_INLINE_MODE_L2;
if (!MLX5_CAP_GEN(dev, vport_group_manager))
return -EOPNOTSUPP;
if (esw->mode == SRIOV_NONE)
return -EOPNOTSUPP;
- if (MLX5_CAP_ETH(dev, wqe_inline_mode) !=
- MLX5_CAP_INLINE_MODE_VPORT_CONTEXT)
- return -EOPNOTSUPP;
+ switch (MLX5_CAP_ETH(dev, wqe_inline_mode)) {
+ case MLX5_CAP_INLINE_MODE_NOT_REQUIRED:
+ mlx5_mode = MLX5_INLINE_MODE_NONE;
+ goto out;
+ case MLX5_CAP_INLINE_MODE_L2:
+ mlx5_mode = MLX5_INLINE_MODE_L2;
+ goto out;
+ case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT:
+ goto query_vports;
+ }
+query_vports:
for (vport = 1; vport <= nvfs; vport++) {
mlx5_query_nic_vport_min_inline(dev, vport, &mlx5_mode);
if (vport > 1 && prev_mlx5_mode != mlx5_mode)
prev_mlx5_mode = mlx5_mode;
}
+out:
*mode = mlx5_mode;
return 0;
}
struct netdev_notifier_changeupper_info *info)
{
struct net_device *upper = info->upper_dev, *ndev_tmp;
- struct netdev_lag_upper_info *lag_upper_info;
+ struct netdev_lag_upper_info *lag_upper_info = NULL;
bool is_bonded;
int bond_status = 0;
int num_slaves = 0;
if (!netif_is_lag_master(upper))
return 0;
- lag_upper_info = info->upper_info;
+ if (info->linking)
+ lag_upper_info = info->upper_info;
/* The event may still be of interest if the slave does not belong to
* us, but is enslaved to a master which has one or more of our netdevs
if (err) {
dev_err(&dev->pdev->dev, "Firmware over %d MS in initializing state, aborting\n",
FW_INIT_TIMEOUT_MILI);
- goto out_err;
+ goto err_cmd_cleanup;
}
err = mlx5_core_enable_hca(dev, 0);
struct mlx5_uars_page *up = container_of(kref, struct mlx5_uars_page, ref_count);
list_del(&up->list);
+ iounmap(up->map);
if (mlx5_cmd_free_uar(up->mdev, up->index))
mlx5_core_warn(up->mdev, "failed to free uar index %d\n", up->index);
kfree(up->reg_bitmap);
#include <linux/of_irq.h>
#include <linux/crc32.h>
#include <linux/crc32c.h>
+#include <linux/circ_buf.h>
#include "moxart_ether.h"
return rx;
}
+static int moxart_tx_queue_space(struct net_device *ndev)
+{
+ struct moxart_mac_priv_t *priv = netdev_priv(ndev);
+
+ return CIRC_SPACE(priv->tx_head, priv->tx_tail, TX_DESC_NUM);
+}
+
static void moxart_tx_finished(struct net_device *ndev)
{
struct moxart_mac_priv_t *priv = netdev_priv(ndev);
tx_tail = TX_NEXT(tx_tail);
}
priv->tx_tail = tx_tail;
+ if (netif_queue_stopped(ndev) &&
+ moxart_tx_queue_space(ndev) >= TX_WAKE_THRESHOLD)
+ netif_wake_queue(ndev);
}
static irqreturn_t moxart_mac_interrupt(int irq, void *dev_id)
struct moxart_mac_priv_t *priv = netdev_priv(ndev);
void *desc;
unsigned int len;
- unsigned int tx_head = priv->tx_head;
+ unsigned int tx_head;
u32 txdes1;
int ret = NETDEV_TX_BUSY;
+ spin_lock_irq(&priv->txlock);
+
+ tx_head = priv->tx_head;
desc = priv->tx_desc_base + (TX_REG_DESC_SIZE * tx_head);
- spin_lock_irq(&priv->txlock);
+ if (moxart_tx_queue_space(ndev) == 1)
+ netif_stop_queue(ndev);
+
if (moxart_desc_read(desc + TX_REG_OFFSET_DESC0) & TX_DESC0_DMA_OWN) {
net_dbg_ratelimited("no TX space for packet\n");
priv->stats.tx_dropped++;
#define TX_NEXT(N) (((N) + 1) & (TX_DESC_NUM_MASK))
#define TX_BUF_SIZE 1600
#define TX_BUF_SIZE_MAX (TX_DESC1_BUF_SIZE_MASK+1)
+#define TX_WAKE_THRESHOLD 16
#define RX_DESC_NUM 64
#define RX_DESC_NUM_MASK (RX_DESC_NUM-1)
{
struct nfp_net *nn = netdev_priv(netdev);
+ unregister_netdev(nn->netdev);
+
if (nn->xdp_prog)
bpf_prog_put(nn->xdp_prog);
if (nn->bpf_offload_xdp)
nfp_net_xdp_offload(nn, NULL);
- unregister_netdev(nn->netdev);
}
((u32)(prio_tc_tbl >> ((7 - prio) * 4)) & 0x7)
static const struct qed_dcbx_app_metadata qed_dcbx_app_update[] = {
- {DCBX_PROTOCOL_ISCSI, "ISCSI", QED_PCI_DEFAULT},
- {DCBX_PROTOCOL_FCOE, "FCOE", QED_PCI_DEFAULT},
- {DCBX_PROTOCOL_ROCE, "ROCE", QED_PCI_DEFAULT},
- {DCBX_PROTOCOL_ROCE_V2, "ROCE_V2", QED_PCI_DEFAULT},
- {DCBX_PROTOCOL_ETH, "ETH", QED_PCI_ETH}
+ {DCBX_PROTOCOL_ISCSI, "ISCSI", QED_PCI_ISCSI},
+ {DCBX_PROTOCOL_FCOE, "FCOE", QED_PCI_FCOE},
+ {DCBX_PROTOCOL_ROCE, "ROCE", QED_PCI_ETH_ROCE},
+ {DCBX_PROTOCOL_ROCE_V2, "ROCE_V2", QED_PCI_ETH_ROCE},
+ {DCBX_PROTOCOL_ETH, "ETH", QED_PCI_ETH},
};
static bool qed_dcbx_app_ethtype(u32 app_info_bitmap)
p_params->ets_cbs,
p_ets->pri_tc_tbl[0], p_params->max_ets_tc);
+ if (p_params->ets_enabled && !p_params->max_ets_tc) {
+ p_params->max_ets_tc = QED_MAX_PFC_PRIORITIES;
+ DP_VERBOSE(p_hwfn, QED_MSG_DCB,
+ "ETS params: max_ets_tc is forced to %d\n",
+ p_params->max_ets_tc);
+ }
+
/* 8 bit tsa and bw data corresponding to each of the 8 TC's are
* encoded in a type u32 array of size 2.
*/
u8 pfc_map = 0;
int i;
+ *pfc &= ~DCBX_PFC_ERROR_MASK;
+
if (p_params->pfc.willing)
*pfc |= DCBX_PFC_WILLING_MASK;
else
{
struct qed_dcbx_get *dcbx_info;
- dcbx_info = kzalloc(sizeof(*dcbx_info), GFP_KERNEL);
+ dcbx_info = kmalloc(sizeof(*dcbx_info), GFP_ATOMIC);
if (!dcbx_info)
return NULL;
for (i = 0; i < QED_MAX_PFC_PRIORITIES; i++)
dcbx_set.config.params.pfc.prio[i] = !!(pfc->pfc_en & BIT(i));
+ dcbx_set.config.params.pfc.max_tc = pfc->pfc_cap;
+
ptt = qed_ptt_acquire(hwfn);
if (!ptt)
return -EINVAL;
spin_unlock_irqrestore(&priv->lock, flags);
return NETDEV_TX_BUSY;
}
- entry = priv->cur_tx[q] % (priv->num_tx_ring[q] * NUM_TX_DESC);
- priv->tx_skb[q][entry / NUM_TX_DESC] = skb;
if (skb_put_padto(skb, ETH_ZLEN))
- goto drop;
+ goto exit;
+
+ entry = priv->cur_tx[q] % (priv->num_tx_ring[q] * NUM_TX_DESC);
+ priv->tx_skb[q][entry / NUM_TX_DESC] = skb;
buffer = PTR_ALIGN(priv->tx_align[q], DPTR_ALIGN) +
entry / NUM_TX_DESC * DPTR_ALIGN;
.get_mdio_data = sh_get_mdio,
};
+/* free Tx skb function */
+static int sh_eth_tx_free(struct net_device *ndev, bool sent_only)
+{
+ struct sh_eth_private *mdp = netdev_priv(ndev);
+ struct sh_eth_txdesc *txdesc;
+ int free_num = 0;
+ int entry;
+ bool sent;
+
+ for (; mdp->cur_tx - mdp->dirty_tx > 0; mdp->dirty_tx++) {
+ entry = mdp->dirty_tx % mdp->num_tx_ring;
+ txdesc = &mdp->tx_ring[entry];
+ sent = !(txdesc->status & cpu_to_le32(TD_TACT));
+ if (sent_only && !sent)
+ break;
+ /* TACT bit must be checked before all the following reads */
+ dma_rmb();
+ netif_info(mdp, tx_done, ndev,
+ "tx entry %d status 0x%08x\n",
+ entry, le32_to_cpu(txdesc->status));
+ /* Free the original skb. */
+ if (mdp->tx_skbuff[entry]) {
+ dma_unmap_single(&ndev->dev, le32_to_cpu(txdesc->addr),
+ le32_to_cpu(txdesc->len) >> 16,
+ DMA_TO_DEVICE);
+ dev_kfree_skb_irq(mdp->tx_skbuff[entry]);
+ mdp->tx_skbuff[entry] = NULL;
+ free_num++;
+ }
+ txdesc->status = cpu_to_le32(TD_TFP);
+ if (entry >= mdp->num_tx_ring - 1)
+ txdesc->status |= cpu_to_le32(TD_TDLE);
+
+ if (sent) {
+ ndev->stats.tx_packets++;
+ ndev->stats.tx_bytes += le32_to_cpu(txdesc->len) >> 16;
+ }
+ }
+ return free_num;
+}
+
/* free skb and descriptor buffer */
static void sh_eth_ring_free(struct net_device *ndev)
{
struct sh_eth_private *mdp = netdev_priv(ndev);
int ringsize, i;
+ if (mdp->rx_ring) {
+ for (i = 0; i < mdp->num_rx_ring; i++) {
+ if (mdp->rx_skbuff[i]) {
+ struct sh_eth_rxdesc *rxdesc = &mdp->rx_ring[i];
+
+ dma_unmap_single(&ndev->dev,
+ le32_to_cpu(rxdesc->addr),
+ ALIGN(mdp->rx_buf_sz, 32),
+ DMA_FROM_DEVICE);
+ }
+ }
+ ringsize = sizeof(struct sh_eth_rxdesc) * mdp->num_rx_ring;
+ dma_free_coherent(NULL, ringsize, mdp->rx_ring,
+ mdp->rx_desc_dma);
+ mdp->rx_ring = NULL;
+ }
+
/* Free Rx skb ringbuffer */
if (mdp->rx_skbuff) {
for (i = 0; i < mdp->num_rx_ring; i++)
kfree(mdp->rx_skbuff);
mdp->rx_skbuff = NULL;
- /* Free Tx skb ringbuffer */
- if (mdp->tx_skbuff) {
- for (i = 0; i < mdp->num_tx_ring; i++)
- dev_kfree_skb(mdp->tx_skbuff[i]);
- }
- kfree(mdp->tx_skbuff);
- mdp->tx_skbuff = NULL;
-
- if (mdp->rx_ring) {
- ringsize = sizeof(struct sh_eth_rxdesc) * mdp->num_rx_ring;
- dma_free_coherent(NULL, ringsize, mdp->rx_ring,
- mdp->rx_desc_dma);
- mdp->rx_ring = NULL;
- }
-
if (mdp->tx_ring) {
+ sh_eth_tx_free(ndev, false);
+
ringsize = sizeof(struct sh_eth_txdesc) * mdp->num_tx_ring;
dma_free_coherent(NULL, ringsize, mdp->tx_ring,
mdp->tx_desc_dma);
mdp->tx_ring = NULL;
}
+
+ /* Free Tx skb ringbuffer */
+ kfree(mdp->tx_skbuff);
+ mdp->tx_skbuff = NULL;
}
/* format skb and descriptor buffer */
update_mac_address(ndev);
}
-/* free Tx skb function */
-static int sh_eth_txfree(struct net_device *ndev)
-{
- struct sh_eth_private *mdp = netdev_priv(ndev);
- struct sh_eth_txdesc *txdesc;
- int free_num = 0;
- int entry;
-
- for (; mdp->cur_tx - mdp->dirty_tx > 0; mdp->dirty_tx++) {
- entry = mdp->dirty_tx % mdp->num_tx_ring;
- txdesc = &mdp->tx_ring[entry];
- if (txdesc->status & cpu_to_le32(TD_TACT))
- break;
- /* TACT bit must be checked before all the following reads */
- dma_rmb();
- netif_info(mdp, tx_done, ndev,
- "tx entry %d status 0x%08x\n",
- entry, le32_to_cpu(txdesc->status));
- /* Free the original skb. */
- if (mdp->tx_skbuff[entry]) {
- dma_unmap_single(&ndev->dev, le32_to_cpu(txdesc->addr),
- le32_to_cpu(txdesc->len) >> 16,
- DMA_TO_DEVICE);
- dev_kfree_skb_irq(mdp->tx_skbuff[entry]);
- mdp->tx_skbuff[entry] = NULL;
- free_num++;
- }
- txdesc->status = cpu_to_le32(TD_TFP);
- if (entry >= mdp->num_tx_ring - 1)
- txdesc->status |= cpu_to_le32(TD_TDLE);
-
- ndev->stats.tx_packets++;
- ndev->stats.tx_bytes += le32_to_cpu(txdesc->len) >> 16;
- }
- return free_num;
-}
-
/* Packet receive function */
static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
{
intr_status, mdp->cur_tx, mdp->dirty_tx,
(u32)ndev->state, edtrr);
/* dirty buffer free */
- sh_eth_txfree(ndev);
+ sh_eth_tx_free(ndev, true);
/* SH7712 BUG */
if (edtrr ^ sh_eth_get_edtrr_trns(mdp)) {
/* Clear Tx interrupts */
sh_eth_write(ndev, intr_status & cd->tx_check, EESR);
- sh_eth_txfree(ndev);
+ sh_eth_tx_free(ndev, true);
netif_wake_queue(ndev);
}
spin_lock_irqsave(&mdp->lock, flags);
if ((mdp->cur_tx - mdp->dirty_tx) >= (mdp->num_tx_ring - 4)) {
- if (!sh_eth_txfree(ndev)) {
+ if (!sh_eth_tx_free(ndev, true)) {
netif_warn(mdp, tx_queued, ndev, "TxFD exhausted.\n");
netif_stop_queue(ndev);
spin_unlock_irqrestore(&mdp->lock, flags);
{
bool want[OFDPA_CTRL_MAX] = { 0, };
bool prev_ctrls[OFDPA_CTRL_MAX];
- u8 uninitialized_var(prev_state);
+ u8 prev_state;
int err;
int i;
- if (switchdev_trans_ph_prepare(trans)) {
- memcpy(prev_ctrls, ofdpa_port->ctrls, sizeof(prev_ctrls));
- prev_state = ofdpa_port->stp_state;
- }
-
- if (ofdpa_port->stp_state == state)
+ prev_state = ofdpa_port->stp_state;
+ if (prev_state == state)
return 0;
+ memcpy(prev_ctrls, ofdpa_port->ctrls, sizeof(prev_ctrls));
ofdpa_port->stp_state = state;
switch (state) {
free_cpumask_var(thread_mask);
}
+ if (count > EFX_MAX_RX_QUEUES) {
+ netif_cond_dbg(efx, probe, efx->net_dev, !rss_cpus, warn,
+ "Reducing number of rx queues from %u to %u.\n",
+ count, EFX_MAX_RX_QUEUES);
+ count = EFX_MAX_RX_QUEUES;
+ }
+
/* If RSS is requested for the PF *and* VFs then we can't write RSS
* table entries that are inaccessible to VFs
*/
#define EFX_RXQ_MIN_ENT 128U
#define EFX_TXQ_MIN_ENT(efx) (2 * efx_tx_max_skb_descs(efx))
-#define EFX_TXQ_MAX_ENT(efx) (EFX_WORKAROUND_35388(efx) ? \
+/* All EF10 architecture NICs steal one bit of the DMAQ size for various
+ * other purposes when counting TxQ entries, so we halve the queue size.
+ */
+#define EFX_TXQ_MAX_ENT(efx) (EFX_WORKAROUND_EF10(efx) ? \
EFX_MAX_DMAQ_SIZE / 2 : EFX_MAX_DMAQ_SIZE)
static inline bool efx_rss_enabled(struct efx_nic *efx)
free_cpumask_var(thread_mask);
}
+ if (count > EF4_MAX_RX_QUEUES) {
+ netif_cond_dbg(efx, probe, efx->net_dev, !rss_cpus, warn,
+ "Reducing number of rx queues from %u to %u.\n",
+ count, EF4_MAX_RX_QUEUES);
+ count = EF4_MAX_RX_QUEUES;
+ }
+
return count;
}
*/
#define EFX_WORKAROUND_SIENA(efx) (efx_nic_rev(efx) == EFX_REV_SIENA_A0)
+#define EFX_WORKAROUND_EF10(efx) (efx_nic_rev(efx) >= EFX_REV_HUNT_A0)
#define EFX_WORKAROUND_10G(efx) 1
/* Bit-bashed I2C reads cause performance drop */
config TI_CPTS
bool "TI Common Platform Time Sync (CPTS) Support"
depends on TI_CPSW || TI_KEYSTONE_NETCP
- depends on PTP_1588_CLOCK
+ depends on POSIX_TIMERS
---help---
This driver supports the Common Platform Time Sync unit of
the CPSW Ethernet Switch and Keystone 2 1g/10g Switch Subsystem.
tristate
depends on TI_CPTS
default y if TI_CPSW=y || TI_KEYSTONE_NETCP=y
+ select NET_PTP_CLASSIFY
+ imply PTP_1588_CLOCK
default m
config TI_KEYSTONE_NETCP
static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv)
{
u32 slave_port;
+ struct phy_device *phy;
struct cpsw_common *cpsw = priv->cpsw;
soft_reset_slave(slave);
1 << slave_port, 0, 0, ALE_MCAST_FWD_2);
if (slave->data->phy_node) {
- slave->phy = of_phy_connect(priv->ndev, slave->data->phy_node,
+ phy = of_phy_connect(priv->ndev, slave->data->phy_node,
&cpsw_adjust_link, 0, slave->data->phy_if);
- if (!slave->phy) {
+ if (!phy) {
dev_err(priv->dev, "phy \"%s\" not found on slave %d\n",
slave->data->phy_node->full_name,
slave->slave_num);
return;
}
} else {
- slave->phy = phy_connect(priv->ndev, slave->data->phy_id,
+ phy = phy_connect(priv->ndev, slave->data->phy_id,
&cpsw_adjust_link, slave->data->phy_if);
- if (IS_ERR(slave->phy)) {
+ if (IS_ERR(phy)) {
dev_err(priv->dev,
"phy \"%s\" not found on slave %d, err %ld\n",
slave->data->phy_id, slave->slave_num,
- PTR_ERR(slave->phy));
- slave->phy = NULL;
+ PTR_ERR(phy));
return;
}
}
+ slave->phy = phy;
+
phy_attached_info(slave->phy);
phy_start(slave->phy);
}
cpsw_intr_enable(cpsw);
+ netif_trans_update(ndev);
+ netif_tx_wake_all_queues(ndev);
}
static int cpsw_ndo_set_mac_address(struct net_device *ndev, void *p)
BUG_ON(lp->tx_skbs[i].skb != skb);
#endif
if (skb) {
- dev_kfree_skb(skb);
pci_unmap_single(lp->pci_dev, lp->tx_skbs[i].skb_dma, skb->len, PCI_DMA_TODEVICE);
+ dev_kfree_skb(skb);
lp->tx_skbs[i].skb = NULL;
lp->tx_skbs[i].skb_dma = 0;
}
u32 send_section_cnt;
u32 send_section_size;
unsigned long *send_section_map;
- int map_words;
/* Used for NetVSP initialization protocol */
struct completion channel_init_wait;
struct netvsc_device *net_device;
struct nvsp_message *init_packet;
struct net_device *ndev;
+ size_t map_words;
int node;
net_device = get_outbound_net_device(device);
net_device->send_section_size, net_device->send_section_cnt);
/* Setup state for managing the send buffer. */
- net_device->map_words = DIV_ROUND_UP(net_device->send_section_cnt,
- BITS_PER_LONG);
+ map_words = DIV_ROUND_UP(net_device->send_section_cnt, BITS_PER_LONG);
- net_device->send_section_map = kcalloc(net_device->map_words,
- sizeof(ulong), GFP_KERNEL);
+ net_device->send_section_map = kcalloc(map_words, sizeof(ulong), GFP_KERNEL);
if (net_device->send_section_map == NULL) {
ret = -ENOMEM;
goto cleanup;
unsigned long *map_addr = net_device->send_section_map;
unsigned int i;
- for_each_clear_bit(i, map_addr, net_device->map_words) {
+ for_each_clear_bit(i, map_addr, net_device->send_section_cnt) {
if (sync_test_and_set_bit(i, map_addr) == 0)
return i;
}
memset(rd, 0, sizeof(*rd));
rd->hw = hwmap + i;
rd->buf = kmalloc(len, GFP_KERNEL|GFP_DMA);
- if (rd->buf == NULL ||
- !(busaddr = pci_map_single(pdev, rd->buf, len, dir))) {
+ if (rd->buf)
+ busaddr = pci_map_single(pdev, rd->buf, len, dir);
+ if (rd->buf == NULL || pci_dma_mapping_error(pdev, busaddr)) {
if (rd->buf) {
net_err_ratelimited("%s: failed to create PCI-MAP for %p\n",
__func__, rd->buf);
rd = r->rd + j;
busaddr = rd_get_addr(rd);
rd_set_addr_status(rd, 0, 0);
- if (busaddr)
- pci_unmap_single(pdev, busaddr, len, dir);
+ pci_unmap_single(pdev, busaddr, len, dir);
kfree(rd->buf);
rd->buf = NULL;
}
static struct aead_request *macsec_alloc_req(struct crypto_aead *tfm,
unsigned char **iv,
- struct scatterlist **sg)
+ struct scatterlist **sg,
+ int num_frags)
{
size_t size, iv_offset, sg_offset;
struct aead_request *req;
size = ALIGN(size, __alignof__(struct scatterlist));
sg_offset = size;
- size += sizeof(struct scatterlist) * (MAX_SKB_FRAGS + 1);
+ size += sizeof(struct scatterlist) * num_frags;
tmp = kmalloc(size, GFP_ATOMIC);
if (!tmp)
{
int ret;
struct scatterlist *sg;
+ struct sk_buff *trailer;
unsigned char *iv;
struct ethhdr *eth;
struct macsec_eth_header *hh;
return ERR_PTR(-EINVAL);
}
- req = macsec_alloc_req(tx_sa->key.tfm, &iv, &sg);
+ ret = skb_cow_data(skb, 0, &trailer);
+ if (unlikely(ret < 0)) {
+ macsec_txsa_put(tx_sa);
+ kfree_skb(skb);
+ return ERR_PTR(ret);
+ }
+
+ req = macsec_alloc_req(tx_sa->key.tfm, &iv, &sg, ret);
if (!req) {
macsec_txsa_put(tx_sa);
kfree_skb(skb);
macsec_fill_iv(iv, secy->sci, pn);
- sg_init_table(sg, MAX_SKB_FRAGS + 1);
+ sg_init_table(sg, ret);
skb_to_sgvec(skb, sg, 0, skb->len);
if (tx_sc->encrypt) {
{
int ret;
struct scatterlist *sg;
+ struct sk_buff *trailer;
unsigned char *iv;
struct aead_request *req;
struct macsec_eth_header *hdr;
if (!skb)
return ERR_PTR(-ENOMEM);
- req = macsec_alloc_req(rx_sa->key.tfm, &iv, &sg);
+ ret = skb_cow_data(skb, 0, &trailer);
+ if (unlikely(ret < 0)) {
+ kfree_skb(skb);
+ return ERR_PTR(ret);
+ }
+ req = macsec_alloc_req(rx_sa->key.tfm, &iv, &sg, ret);
if (!req) {
kfree_skb(skb);
return ERR_PTR(-ENOMEM);
hdr = (struct macsec_eth_header *)skb->data;
macsec_fill_iv(iv, sci, ntohl(hdr->packet_number));
- sg_init_table(sg, MAX_SKB_FRAGS + 1);
+ sg_init_table(sg, ret);
skb_to_sgvec(skb, sg, 0, skb->len);
if (hdr->tci_an & MACSEC_TCI_E) {
static void macvlan_port_destroy(struct net_device *dev)
{
struct macvlan_port *port = macvlan_port_get_rtnl(dev);
+ struct sk_buff *skb;
dev->priv_flags &= ~IFF_MACVLAN_PORT;
netdev_rx_handler_unregister(dev);
* but we need to cancel it and purge left skbs if any.
*/
cancel_work_sync(&port->bc_work);
- __skb_queue_purge(&port->bc_queue);
+
+ while ((skb = __skb_dequeue(&port->bc_queue))) {
+ const struct macvlan_dev *src = MACVLAN_SKB_CB(skb)->src;
+
+ if (src)
+ dev_put(src->dev);
+
+ kfree_skb(skb);
+ }
kfree(port);
}
skb_info->tmo = jiffies + SKB_TIMESTAMP_TIMEOUT;
skb_queue_tail(&dp83640->rx_queue, skb);
schedule_delayed_work(&dp83640->ts_work, SKB_TIMESTAMP_TIMEOUT);
- } else {
- netif_rx_ni(skb);
}
return true;
return 0;
}
+EXPORT_SYMBOL(mdiobus_register_board_info);
if (priv->led_mode >= 0)
kszphy_setup_led(phydev, type->led_mode_reg, priv->led_mode);
- if (phy_interrupt_is_valid(phydev)) {
- int ctl = phy_read(phydev, MII_BMCR);
-
- if (ctl < 0)
- return ctl;
-
- ret = phy_write(phydev, MII_BMCR, ctl & ~BMCR_ANENABLE);
- if (ret < 0)
- return ret;
- }
-
return 0;
}
.read_status = genphy_read_status,
.ack_interrupt = kszphy_ack_interrupt,
.config_intr = kszphy_config_intr,
- .get_sset_count = kszphy_get_sset_count,
- .get_strings = kszphy_get_strings,
- .get_stats = kszphy_get_stats,
.suspend = genphy_suspend,
.resume = genphy_resume,
}, {
.read_status = genphy_read_status,
.ack_interrupt = kszphy_ack_interrupt,
.config_intr = kszphy_config_intr,
- .get_sset_count = kszphy_get_sset_count,
- .get_strings = kszphy_get_strings,
- .get_stats = kszphy_get_stats,
.suspend = genphy_suspend,
.resume = genphy_resume,
}, {
.features = PHY_GBIT_FEATURES,
.flags = PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT,
.driver_data = &ksz9021_type,
+ .probe = kszphy_probe,
.config_init = ksz9021_config_init,
.config_aneg = genphy_config_aneg,
.read_status = genphy_read_status,
.features = PHY_GBIT_FEATURES,
.flags = PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT,
.driver_data = &ksz9021_type,
+ .probe = kszphy_probe,
.config_init = ksz9031_config_init,
.config_aneg = genphy_config_aneg,
.read_status = ksz9031_read_status,
.config_init = kszphy_config_init,
.config_aneg = ksz8873mll_config_aneg,
.read_status = ksz8873mll_read_status,
- .get_sset_count = kszphy_get_sset_count,
- .get_strings = kszphy_get_strings,
- .get_stats = kszphy_get_stats,
.suspend = genphy_suspend,
.resume = genphy_resume,
}, {
.config_init = kszphy_config_init,
.config_aneg = genphy_config_aneg,
.read_status = genphy_read_status,
- .get_sset_count = kszphy_get_sset_count,
- .get_strings = kszphy_get_strings,
- .get_stats = kszphy_get_stats,
.suspend = genphy_suspend,
.resume = genphy_resume,
}, {
.config_init = kszphy_config_init,
.config_aneg = ksz8873mll_config_aneg,
.read_status = ksz8873mll_read_status,
- .get_sset_count = kszphy_get_sset_count,
- .get_strings = kszphy_get_strings,
- .get_stats = kszphy_get_stats,
.suspend = genphy_suspend,
.resume = genphy_resume,
} };
EXPORT_SYMBOL(phy_mii_ioctl);
/**
- * phy_start_aneg - start auto-negotiation for this PHY device
+ * phy_start_aneg_priv - start auto-negotiation for this PHY device
* @phydev: the phy_device struct
+ * @sync: indicate whether we should wait for the workqueue cancelation
*
* Description: Sanitizes the settings (if we're not autonegotiating
* them), and then calls the driver's config_aneg function.
* If the PHYCONTROL Layer is operating, we change the state to
* reflect the beginning of Auto-negotiation or forcing.
*/
-int phy_start_aneg(struct phy_device *phydev)
+static int phy_start_aneg_priv(struct phy_device *phydev, bool sync)
{
+ bool trigger = 0;
int err;
if (!phydev->drv)
}
}
+ /* Re-schedule a PHY state machine to check PHY status because
+ * negotiation may already be done and aneg interrupt may not be
+ * generated.
+ */
+ if (phy_interrupt_is_valid(phydev) && (phydev->state == PHY_AN)) {
+ err = phy_aneg_done(phydev);
+ if (err > 0) {
+ trigger = true;
+ err = 0;
+ }
+ }
+
out_unlock:
mutex_unlock(&phydev->lock);
+
+ if (trigger)
+ phy_trigger_machine(phydev, sync);
+
return err;
}
+
+/**
+ * phy_start_aneg - start auto-negotiation for this PHY device
+ * @phydev: the phy_device struct
+ *
+ * Description: Sanitizes the settings (if we're not autonegotiating
+ * them), and then calls the driver's config_aneg function.
+ * If the PHYCONTROL Layer is operating, we change the state to
+ * reflect the beginning of Auto-negotiation or forcing.
+ */
+int phy_start_aneg(struct phy_device *phydev)
+{
+ return phy_start_aneg_priv(phydev, true);
+}
EXPORT_SYMBOL(phy_start_aneg);
/**
* state machine runs.
*/
-static void phy_trigger_machine(struct phy_device *phydev, bool sync)
+void phy_trigger_machine(struct phy_device *phydev, bool sync)
{
if (sync)
cancel_delayed_work_sync(&phydev->state_queue);
cancel_delayed_work_sync(&phydev->state_queue);
mutex_lock(&phydev->lock);
- if (phydev->state > PHY_UP)
+ if (phydev->state > PHY_UP && phydev->state != PHY_HALTED)
phydev->state = PHY_UP;
mutex_unlock(&phydev->lock);
}
mutex_unlock(&phydev->lock);
if (needs_aneg)
- err = phy_start_aneg(phydev);
+ err = phy_start_aneg_priv(phydev, false);
else if (do_suspend)
phy_suspend(phydev);
#define TEAM_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \
NETIF_F_RXCSUM | NETIF_F_ALL_TSO)
-static void ___team_compute_features(struct team *team)
+static void __team_compute_features(struct team *team)
{
struct team_port *port;
u32 vlan_features = TEAM_VLAN_FEATURES & NETIF_F_ALL_FOR_ALL;
team->dev->priv_flags |= IFF_XMIT_DST_RELEASE;
}
-static void __team_compute_features(struct team *team)
-{
- ___team_compute_features(team);
- netdev_change_features(team->dev);
-}
-
static void team_compute_features(struct team *team)
{
mutex_lock(&team->lock);
- ___team_compute_features(team);
+ __team_compute_features(team);
mutex_unlock(&team->lock);
netdev_change_features(team->dev);
}
team_notify_peers_fini(team);
team_queue_override_fini(team);
mutex_unlock(&team->lock);
+ netdev_change_features(dev);
}
static void team_destructor(struct net_device *dev)
mutex_lock(&team->lock);
err = team_port_add(team, port_dev);
mutex_unlock(&team->lock);
+
+ if (!err)
+ netdev_change_features(dev);
+
return err;
}
mutex_lock(&team->lock);
err = team_port_del(team, port_dev);
mutex_unlock(&team->lock);
+
+ if (!err)
+ netdev_change_features(dev);
+
return err;
}
hdr = genlmsg_put(skb, portid, seq, &team_nl_family, flags | NLM_F_MULTI,
TEAM_CMD_OPTIONS_GET);
- if (!hdr)
+ if (!hdr) {
+ nlmsg_free(skb);
return -EMSGSIZE;
+ }
if (nla_put_u32(skb, TEAM_ATTR_TEAM_IFINDEX, team->dev->ifindex))
goto nla_put_failure;
hdr = genlmsg_put(skb, portid, seq, &team_nl_family, flags | NLM_F_MULTI,
TEAM_CMD_PORT_LIST_GET);
- if (!hdr)
+ if (!hdr) {
+ nlmsg_free(skb);
return -EMSGSIZE;
+ }
if (nla_put_u32(skb, TEAM_ATTR_TEAM_IFINDEX, team->dev->ifindex))
goto nla_put_failure;
optionally with LEDs that indicate traffic
config USB_NET_PLUSB
- tristate "Prolific PL-2301/2302/25A1 based cables"
+ tristate "Prolific PL-2301/2302/25A1/27A1 based cables"
# if the handshake/init/reset problems, from original 'plusb',
# are ever resolved ... then remove "experimental"
depends on USB_USBNET
#define LENOVO_VENDOR_ID 0x17ef
#define NVIDIA_VENDOR_ID 0x0955
#define HP_VENDOR_ID 0x03f0
+#define MICROSOFT_VENDOR_ID 0x045e
static const struct usb_device_id products[] = {
/* BLACKLIST !!
.driver_info = 0,
},
+/* Microsoft Surface 2 dock (based on Realtek RTL8152) */
+{
+ USB_DEVICE_AND_INTERFACE_INFO(MICROSOFT_VENDOR_ID, 0x07ab, USB_CLASS_COMM,
+ USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+ .driver_info = 0,
+},
+
+/* Microsoft Surface 3 dock (based on Realtek RTL8153) */
+{
+ USB_DEVICE_AND_INTERFACE_INFO(MICROSOFT_VENDOR_ID, 0x07c6, USB_CLASS_COMM,
+ USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+ .driver_info = 0,
+},
+
/* WHITELIST!!!
*
* CDC Ether uses two interfaces, not necessarily consecutive.
tx_overhead = 0x40;
len = skb->len;
- if (skb_headroom(skb) < tx_overhead) {
- struct sk_buff *skb2;
-
- skb2 = skb_copy_expand(skb, tx_overhead, 0, flags);
+ if (skb_cow_head(skb, tx_overhead)) {
dev_kfree_skb_any(skb);
- skb = skb2;
- if (!skb)
- return NULL;
+ return NULL;
}
__skb_push(skb, tx_overhead);
{
int len = skb->len;
- if (skb_headroom(skb) < 2) {
- struct sk_buff *skb2 = skb_copy_expand(skb, 2, 0, flags);
+ if (skb_cow_head(skb, 2)) {
dev_kfree_skb_any(skb);
- skb = skb2;
- if (!skb)
- return NULL;
+ return NULL;
}
skb_push(skb, 2);
SET_NETDEV_DEV(net, &interface->dev);
SET_NETDEV_DEVTYPE(net, &hso_type);
- /* registering our net device */
- result = register_netdev(net);
- if (result) {
- dev_err(&interface->dev, "Failed to register device\n");
- goto exit;
- }
-
/* start allocating */
for (i = 0; i < MUX_BULK_RX_BUF_COUNT; i++) {
hso_net->mux_bulk_rx_urb_pool[i] = usb_alloc_urb(0, GFP_KERNEL);
add_net_device(hso_dev);
+ /* registering our net device */
+ result = register_netdev(net);
+ if (result) {
+ dev_err(&interface->dev, "Failed to register device\n");
+ goto exit;
+ }
+
hso_log_port(hso_dev);
hso_create_rfkill(hso_dev, interface);
pr_info("unloaded\n");
tty_unregister_driver(tty_drv);
- put_tty_driver(tty_drv);
/* deregister the usb driver */
usb_deregister(&hso_driver);
+ put_tty_driver(tty_drv);
}
/* Module definitions */
}
/* We now decide whether we can put our special header into the sk_buff */
- if (skb_cloned(skb) || skb_headroom(skb) < 2) {
- /* no such luck - we make our own */
- struct sk_buff *copied_skb;
- copied_skb = skb_copy_expand(skb, 2, 0, GFP_ATOMIC);
- dev_kfree_skb_irq(skb);
- skb = copied_skb;
- if (!copied_skb) {
- kaweth->stats.tx_errors++;
- netif_start_queue(net);
- spin_unlock_irq(&kaweth->device_lock);
- return NETDEV_TX_OK;
- }
+ if (skb_cow_head(skb, 2)) {
+ kaweth->stats.tx_errors++;
+ netif_start_queue(net);
+ spin_unlock_irq(&kaweth->device_lock);
+ dev_kfree_skb_any(skb);
+ return NETDEV_TX_OK;
}
private_header = (__le16 *)__skb_push(skb, 2);
{
u32 tx_cmd_a, tx_cmd_b;
- if (skb_headroom(skb) < TX_OVERHEAD) {
- struct sk_buff *skb2;
-
- skb2 = skb_copy_expand(skb, TX_OVERHEAD, 0, flags);
+ if (skb_cow_head(skb, TX_OVERHEAD)) {
dev_kfree_skb_any(skb);
- skb = skb2;
- if (!skb)
- return NULL;
+ return NULL;
}
if (lan78xx_linearize(skb) < 0)
}
static const struct driver_info prolific_info = {
- .description = "Prolific PL-2301/PL-2302/PL-25A1",
+ .description = "Prolific PL-2301/PL-2302/PL-25A1/PL-27A1",
.flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT,
/* some PL-2302 versions seem to fail usb_set_interface() */
.reset = pl_reset,
* Host-to-Host Cable
*/
.driver_info = (unsigned long) &prolific_info,
+
+},
+
+/* super speed cables */
+{
+ USB_DEVICE(0x067b, 0x27a1), /* PL-27A1, no eeprom
+ * also: goobay Active USB 3.0
+ * Data Link,
+ * Unitek Y-3501
+ */
+ .driver_info = (unsigned long) &prolific_info,
},
{ }, // END
module_usb_driver(plusb_driver);
MODULE_AUTHOR("David Brownell");
-MODULE_DESCRIPTION("Prolific PL-2301/2302/25A1 USB Host to Host Link Driver");
+MODULE_DESCRIPTION("Prolific PL-2301/2302/25A1/27A1 USB Host to Host Link Driver");
MODULE_LICENSE("GPL");
{QMI_FIXED_INTF(0x2357, 0x9000, 4)}, /* TP-LINK MA260 */
{QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)}, /* Telit LE922A */
{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */
- {QMI_FIXED_INTF(0x1bc7, 0x1201, 2)}, /* Telit LE920 */
+ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1201, 2)}, /* Telit LE920, LE920A4 */
{QMI_FIXED_INTF(0x1c9e, 0x9b01, 3)}, /* XS Stick W100-2 from 4G Systems */
{QMI_FIXED_INTF(0x0b3c, 0xc000, 4)}, /* Olivetti Olicard 100 */
{QMI_FIXED_INTF(0x0b3c, 0xc001, 4)}, /* Olivetti Olicard 120 */
/* Define these values to match your device */
#define VENDOR_ID_REALTEK 0x0bda
+#define VENDOR_ID_MICROSOFT 0x045e
#define VENDOR_ID_SAMSUNG 0x04e8
#define VENDOR_ID_LENOVO 0x17ef
#define VENDOR_ID_NVIDIA 0x0955
}
} else {
if (netif_carrier_ok(tp->netdev)) {
+ netif_stop_queue(tp->netdev);
set_bit(RTL8152_LINK_CHG, &tp->flags);
schedule_delayed_work(&tp->schedule, 0);
}
napi_enable(&tp->napi);
netif_wake_queue(netdev);
netif_info(tp, link, netdev, "carrier on\n");
+ } else if (netif_queue_stopped(netdev) &&
+ skb_queue_len(&tp->tx_queue) < tp->tx_qlen) {
+ netif_wake_queue(netdev);
}
} else {
if (netif_carrier_ok(netdev)) {
tp->rtl_ops.autosuspend_en(tp, false);
napi_disable(&tp->napi);
set_bit(WORK_ENABLE, &tp->flags);
- if (netif_carrier_ok(tp->netdev))
- rtl_start_rx(tp);
+
+ if (netif_carrier_ok(tp->netdev)) {
+ if (rtl8152_get_speed(tp) & LINK_STATUS) {
+ rtl_start_rx(tp);
+ } else {
+ netif_carrier_off(tp->netdev);
+ tp->rtl_ops.disable(tp);
+ netif_info(tp, link, tp->netdev,
+ "linking down\n");
+ }
+ }
+
napi_enable(&tp->napi);
clear_bit(SELECTIVE_SUSPEND, &tp->flags);
smp_mb__after_atomic();
static struct usb_device_id rtl8152_table[] = {
{REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, 0x8152)},
{REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, 0x8153)},
+ {REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07ab)},
+ {REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07c6)},
{REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101)},
{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x304f)},
{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x3062)},
{
u32 tx_cmd_a, tx_cmd_b;
- if (skb_headroom(skb) < SMSC75XX_TX_OVERHEAD) {
- struct sk_buff *skb2 =
- skb_copy_expand(skb, SMSC75XX_TX_OVERHEAD, 0, flags);
+ if (skb_cow_head(skb, SMSC75XX_TX_OVERHEAD)) {
dev_kfree_skb_any(skb);
- skb = skb2;
- if (!skb)
- return NULL;
+ return NULL;
}
tx_cmd_a = (u32)(skb->len & TX_CMD_A_LEN) | TX_CMD_A_FCS;
/* We do not advertise SG, so skbs should be already linearized */
BUG_ON(skb_shinfo(skb)->nr_frags);
- if (skb_headroom(skb) < overhead) {
- struct sk_buff *skb2 = skb_copy_expand(skb,
- overhead, 0, flags);
+ /* Make writable and expand header space by overhead if required */
+ if (skb_cow_head(skb, overhead)) {
+ /* Must deallocate here as returning NULL to indicate error
+ * means the skb won't be deallocated in the caller.
+ */
dev_kfree_skb_any(skb);
- skb = skb2;
- if (!skb)
- return NULL;
+ return NULL;
}
if (csum) {
len = skb->len;
- if (skb_headroom(skb) < SR_TX_OVERHEAD) {
- struct sk_buff *skb2;
-
- skb2 = skb_copy_expand(skb, SR_TX_OVERHEAD, 0, flags);
+ if (skb_cow_head(skb, SR_TX_OVERHEAD)) {
dev_kfree_skb_any(skb);
- skb = skb2;
- if (!skb)
- return NULL;
+ return NULL;
}
__skb_push(skb, SR_TX_OVERHEAD);
" value=0x%04x index=0x%04x size=%d\n",
cmd, reqtype, value, index, size);
- if (data) {
+ if (size) {
buf = kmalloc(size, GFP_KERNEL);
if (!buf)
goto out;
err = usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0),
cmd, reqtype, value, index, buf, size,
USB_CTRL_GET_TIMEOUT);
- if (err > 0 && err <= size)
- memcpy(data, buf, err);
+ if (err > 0 && err <= size) {
+ if (data)
+ memcpy(data, buf, err);
+ else
+ netdev_dbg(dev->net,
+ "Huh? Data requested but thrown away.\n");
+ }
kfree(buf);
out:
return err;
buf = kmemdup(data, size, GFP_KERNEL);
if (!buf)
goto out;
- }
+ } else {
+ if (size) {
+ WARN_ON_ONCE(1);
+ err = -EINVAL;
+ goto out;
+ }
+ }
err = usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0),
cmd, reqtype, value, index, buf, size,
#define MIN_MTU ETH_MIN_MTU
#define MAX_MTU ETH_MAX_MTU
-static int virtnet_probe(struct virtio_device *vdev)
+static int virtnet_validate(struct virtio_device *vdev)
{
- int i, err;
- struct net_device *dev;
- struct virtnet_info *vi;
- u16 max_queue_pairs;
- int mtu;
-
if (!vdev->config->get) {
dev_err(&vdev->dev, "%s failure: config access disabled\n",
__func__);
if (!virtnet_validate_features(vdev))
return -EINVAL;
+ if (virtio_has_feature(vdev, VIRTIO_NET_F_MTU)) {
+ int mtu = virtio_cread16(vdev,
+ offsetof(struct virtio_net_config,
+ mtu));
+ if (mtu < MIN_MTU)
+ __virtio_clear_bit(vdev, VIRTIO_NET_F_MTU);
+ }
+
+ return 0;
+}
+
+static int virtnet_probe(struct virtio_device *vdev)
+{
+ int i, err;
+ struct net_device *dev;
+ struct virtnet_info *vi;
+ u16 max_queue_pairs;
+ int mtu;
+
/* Find if host supports multiqueue virtio_net device */
err = virtio_cread_feature(vdev, VIRTIO_NET_F_MQ,
struct virtio_net_config,
offsetof(struct virtio_net_config,
mtu));
if (mtu < dev->min_mtu) {
- __virtio_clear_bit(vdev, VIRTIO_NET_F_MTU);
- } else {
- dev->mtu = mtu;
- dev->max_mtu = mtu;
+ /* Should never trigger: MTU was previously validated
+ * in virtnet_validate.
+ */
+ dev_err(&vdev->dev, "device MTU appears to have changed "
+ "it is now %d < %d", mtu, dev->min_mtu);
+ goto free_stats;
}
+
+ dev->mtu = mtu;
+ dev->max_mtu = mtu;
+
+ /* TODO: size buffers correctly in this case. */
+ if (dev->mtu > ETH_DATA_LEN)
+ vi->big_packets = true;
}
if (vi->any_header_sg)
.driver.name = KBUILD_MODNAME,
.driver.owner = THIS_MODULE,
.id_table = id_table,
+ .validate = virtnet_validate,
.probe = virtnet_probe,
.remove = virtnet_remove,
.config_changed = virtnet_config_changed,
goto nla_put_failure;
/* rule only needs to appear once */
- nlh->nlmsg_flags &= NLM_F_EXCL;
+ nlh->nlmsg_flags |= NLM_F_EXCL;
frh = nlmsg_data(nlh);
memset(frh, 0, sizeof(*frh));
struct brcmf_cfg80211_info *cfg = wiphy_priv(wiphy);
struct brcmf_p2p_info *p2p = &cfg->p2p;
struct brcmf_cfg80211_vif *vif;
+ enum nl80211_iftype iftype;
bool wait_for_disable = false;
int err;
brcmf_dbg(TRACE, "delete P2P vif\n");
vif = container_of(wdev, struct brcmf_cfg80211_vif, wdev);
+ iftype = vif->wdev.iftype;
brcmf_cfg80211_arm_vif_event(cfg, vif);
- switch (vif->wdev.iftype) {
+ switch (iftype) {
case NL80211_IFTYPE_P2P_CLIENT:
if (test_bit(BRCMF_VIF_STATUS_DISCONNECTING, &vif->sme_state))
wait_for_disable = true;
BRCMF_P2P_DISABLE_TIMEOUT);
err = 0;
- if (vif->wdev.iftype != NL80211_IFTYPE_P2P_DEVICE) {
+ if (iftype != NL80211_IFTYPE_P2P_DEVICE) {
brcmf_vif_clear_mgmt_ies(vif);
err = brcmf_p2p_release_p2p_if(vif);
}
brcmf_remove_interface(vif->ifp, true);
brcmf_cfg80211_arm_vif_event(cfg, NULL);
- if (vif->wdev.iftype != NL80211_IFTYPE_P2P_DEVICE)
+ if (iftype != NL80211_IFTYPE_P2P_DEVICE)
p2p->bss_idx[P2PAPI_BSSCFG_CONNECTION].vif = NULL;
return err;
if (ret)
return ret;
+ if (count == 0)
+ return 0;
iwl_mvm_fw_dbg_collect(mvm, FW_DBG_TRIGGER_USER, buf,
(count - 1), NULL);
qmask |= BIT(vif->hw_queue[ac]);
}
- if (vif->type == NL80211_IFTYPE_AP)
+ if (vif->type == NL80211_IFTYPE_AP ||
+ vif->type == NL80211_IFTYPE_ADHOC)
qmask |= BIT(vif->cab_queue);
return qmask;
return;
rcu_read_lock();
- sta = mvm->fw_id_to_mac_id[notif->sta_id];
+ sta = rcu_dereference(mvm->fw_id_to_mac_id[notif->sta_id]);
if (WARN_ON(IS_ERR_OR_NULL(sta))) {
rcu_read_unlock();
return;
iwl_mvm_get_wd_timeout(mvm, vif, false, false);
int queue;
- if (vif->type == NL80211_IFTYPE_AP)
+ if (vif->type == NL80211_IFTYPE_AP ||
+ vif->type == NL80211_IFTYPE_ADHOC)
queue = IWL_MVM_DQA_AP_PROBE_RESP_QUEUE;
else if (vif->type == NL80211_IFTYPE_P2P_DEVICE)
queue = IWL_MVM_DQA_P2P_DEVICE_QUEUE;
* enabled-cab_queue to the mask)
*/
if (iwl_mvm_is_dqa_supported(mvm) &&
- vif->type == NL80211_IFTYPE_AP) {
+ (vif->type == NL80211_IFTYPE_AP ||
+ vif->type == NL80211_IFTYPE_ADHOC)) {
struct iwl_trans_txq_scd_cfg cfg = {
.fifo = IWL_MVM_TX_FIFO_MCAST,
.sta_id = mvmvif->bcast_sta.sta_id,
lockdep_assert_held(&mvm->mutex);
- if (vif->type == NL80211_IFTYPE_AP)
+ if (vif->type == NL80211_IFTYPE_AP ||
+ vif->type == NL80211_IFTYPE_ADHOC)
iwl_mvm_disable_txq(mvm, vif->cab_queue, vif->cab_queue,
IWL_MAX_TID_COUNT, 0);
switch (info->control.vif->type) {
case NL80211_IFTYPE_AP:
+ case NL80211_IFTYPE_ADHOC:
/*
* Handle legacy hostapd as well, where station may be added
* only after assoc. Take care of the case where we send a
if (info->hw_queue == info->control.vif->cab_queue)
return info->hw_queue;
- WARN_ONCE(1, "fc=0x%02x", le16_to_cpu(fc));
+ WARN_ONCE(info->control.vif->type != NL80211_IFTYPE_ADHOC,
+ "fc=0x%02x", le16_to_cpu(fc));
return IWL_MVM_DQA_AP_PROBE_RESP_QUEUE;
case NL80211_IFTYPE_P2P_DEVICE:
if (ieee80211_is_mgmt(fc))
iwl_mvm_vif_from_mac80211(info.control.vif);
if (info.control.vif->type == NL80211_IFTYPE_P2P_DEVICE ||
- info.control.vif->type == NL80211_IFTYPE_AP) {
+ info.control.vif->type == NL80211_IFTYPE_AP ||
+ info.control.vif->type == NL80211_IFTYPE_ADHOC) {
sta_id = mvmvif->bcast_sta.sta_id;
queue = iwl_mvm_get_ctrl_vif_queue(mvm, &info,
hdr->frame_control);
unsigned long flags;
struct rtl_c2hcmd *c2hcmd;
- c2hcmd = kmalloc(sizeof(*c2hcmd), GFP_KERNEL);
+ c2hcmd = kmalloc(sizeof(*c2hcmd),
+ in_interrupt() ? GFP_ATOMIC : GFP_KERNEL);
if (!c2hcmd)
goto label_err;
- c2hcmd->val = kmalloc(len, GFP_KERNEL);
+ c2hcmd->val = kmalloc(len,
+ in_interrupt() ? GFP_ATOMIC : GFP_KERNEL);
if (!c2hcmd->val)
goto label_err2;
rc = nd_desc->ndctl(nd_desc, nvdimm, cmd, buf, buf_len, NULL);
if (rc < 0)
goto out_unlock;
+ nvdimm_bus_unlock(&nvdimm_bus->dev);
+
if (copy_to_user(p, buf, buf_len))
rc = -EFAULT;
+
+ vfree(buf);
+ return rc;
+
out_unlock:
nvdimm_bus_unlock(&nvdimm_bus->dev);
out:
}
if (unlikely(is_bad_pmem(&nsio->bb, sector, sz_align))) {
- if (IS_ALIGNED(offset, 512) && IS_ALIGNED(size, 512)) {
+ /*
+ * FIXME: nsio_rw_bytes() may be called from atomic
+ * context in the btt case and nvdimm_clear_poison()
+ * takes a sleeping lock. Until the locking can be
+ * reworked this capability requires that the namespace
+ * is not claimed by btt.
+ */
+ if (IS_ALIGNED(offset, 512) && IS_ALIGNED(size, 512)
+ && (!ndns->claim || !is_nd_btt(ndns->claim))) {
long cleared;
cleared = nvdimm_clear_poison(&ndns->dev, offset, size);
int alias_dpa_busy(struct device *dev, void *data)
{
- resource_size_t map_end, blk_start, new, busy;
+ resource_size_t map_end, blk_start, new;
struct blk_alloc_info *info = data;
struct nd_mapping *nd_mapping;
struct nd_region *nd_region;
retry:
/*
* Find the free dpa from the end of the last pmem allocation to
- * the end of the interleave-set mapping that is not already
- * covered by a blk allocation.
+ * the end of the interleave-set mapping.
*/
- busy = 0;
for_each_dpa_resource(ndd, res) {
+ if (strncmp(res->name, "pmem", 4) != 0)
+ continue;
if ((res->start >= blk_start && res->start < map_end)
|| (res->end >= blk_start
&& res->end <= map_end)) {
- if (strncmp(res->name, "pmem", 4) == 0) {
- new = max(blk_start, min(map_end + 1,
- res->end + 1));
- if (new != blk_start) {
- blk_start = new;
- goto retry;
- }
- } else
- busy += min(map_end, res->end)
- - max(nd_mapping->start, res->start) + 1;
- } else if (nd_mapping->start > res->start
- && map_end < res->end) {
- /* total eclipse of the PMEM region mapping */
- busy += nd_mapping->size;
- break;
+ new = max(blk_start, min(map_end + 1, res->end + 1));
+ if (new != blk_start) {
+ blk_start = new;
+ goto retry;
+ }
}
}
return 1;
}
- info->available -= blk_start - nd_mapping->start + busy;
+ info->available -= blk_start - nd_mapping->start;
return 0;
}
-static int blk_dpa_busy(struct device *dev, void *data)
-{
- struct blk_alloc_info *info = data;
- struct nd_mapping *nd_mapping;
- struct nd_region *nd_region;
- resource_size_t map_end;
- int i;
-
- if (!is_nd_pmem(dev))
- return 0;
-
- nd_region = to_nd_region(dev);
- for (i = 0; i < nd_region->ndr_mappings; i++) {
- nd_mapping = &nd_region->mapping[i];
- if (nd_mapping->nvdimm == info->nd_mapping->nvdimm)
- break;
- }
-
- if (i >= nd_region->ndr_mappings)
- return 0;
-
- map_end = nd_mapping->start + nd_mapping->size - 1;
- if (info->res->start >= nd_mapping->start
- && info->res->start < map_end) {
- if (info->res->end <= map_end) {
- info->busy = 0;
- return 1;
- } else {
- info->busy -= info->res->end - map_end;
- return 0;
- }
- } else if (info->res->end >= nd_mapping->start
- && info->res->end <= map_end) {
- info->busy -= nd_mapping->start - info->res->start;
- return 0;
- } else {
- info->busy -= nd_mapping->size;
- return 0;
- }
-}
-
/**
* nd_blk_available_dpa - account the unused dpa of BLK region
* @nd_mapping: container of dpa-resource-root + labels
for_each_dpa_resource(ndd, res) {
if (strncmp(res->name, "blk", 3) != 0)
continue;
-
- info.res = res;
- info.busy = resource_size(res);
- device_for_each_child(&nvdimm_bus->dev, &info, blk_dpa_busy);
- info.available -= info.busy;
+ info.available -= resource_size(res);
}
return info.available;
module_param(shutdown_timeout, byte, 0644);
MODULE_PARM_DESC(shutdown_timeout, "timeout in seconds for controller shutdown");
-unsigned int nvme_max_retries = 5;
-module_param_named(max_retries, nvme_max_retries, uint, 0644);
+static u8 nvme_max_retries = 5;
+module_param_named(max_retries, nvme_max_retries, byte, 0644);
MODULE_PARM_DESC(max_retries, "max number of retries a command may have");
-EXPORT_SYMBOL_GPL(nvme_max_retries);
static int nvme_char_major;
module_param(nvme_char_major, int, 0);
MODULE_PARM_DESC(default_ps_max_latency_us,
"max power saving latency for new devices; use PM QOS to change per device");
+static bool force_apst;
+module_param(force_apst, bool, 0644);
+MODULE_PARM_DESC(force_apst, "allow APST for newly enumerated devices even if quirked off");
+
static LIST_HEAD(nvme_ctrl_list);
static DEFINE_SPINLOCK(dev_list_lock);
static struct class *nvme_class;
+static int nvme_error_status(struct request *req)
+{
+ switch (nvme_req(req)->status & 0x7ff) {
+ case NVME_SC_SUCCESS:
+ return 0;
+ case NVME_SC_CAP_EXCEEDED:
+ return -ENOSPC;
+ default:
+ return -EIO;
+
+ /*
+ * XXX: these errors are a nasty side-band protocol to
+ * drivers/md/dm-mpath.c:noretry_error() that aren't documented
+ * anywhere..
+ */
+ case NVME_SC_CMD_SEQ_ERROR:
+ return -EILSEQ;
+ case NVME_SC_ONCS_NOT_SUPPORTED:
+ return -EOPNOTSUPP;
+ case NVME_SC_WRITE_FAULT:
+ case NVME_SC_READ_ERROR:
+ case NVME_SC_UNWRITTEN_BLOCK:
+ return -ENODATA;
+ }
+}
+
+static inline bool nvme_req_needs_retry(struct request *req)
+{
+ if (blk_noretry_request(req))
+ return false;
+ if (nvme_req(req)->status & NVME_SC_DNR)
+ return false;
+ if (jiffies - req->start_time >= req->timeout)
+ return false;
+ if (nvme_req(req)->retries >= nvme_max_retries)
+ return false;
+ return true;
+}
+
+void nvme_complete_rq(struct request *req)
+{
+ if (unlikely(nvme_req(req)->status && nvme_req_needs_retry(req))) {
+ nvme_req(req)->retries++;
+ blk_mq_requeue_request(req, !blk_mq_queue_stopped(req->q));
+ return;
+ }
+
+ blk_mq_end_request(req, nvme_error_status(req));
+}
+EXPORT_SYMBOL_GPL(nvme_complete_rq);
+
void nvme_cancel_request(struct request *req, void *data, bool reserved)
{
int status;
status = NVME_SC_ABORT_REQ;
if (blk_queue_dying(req->q))
status |= NVME_SC_DNR;
- blk_mq_complete_request(req, status);
+ nvme_req(req)->status = status;
+ blk_mq_complete_request(req);
+
}
EXPORT_SYMBOL_GPL(nvme_cancel_request);
return NULL;
}
-void nvme_requeue_req(struct request *req)
-{
- blk_mq_requeue_request(req, !blk_mq_queue_stopped(req->q));
-}
-EXPORT_SYMBOL_GPL(nvme_requeue_req);
-
struct request *nvme_alloc_request(struct request_queue *q,
struct nvme_command *cmd, unsigned int flags, int qid)
{
memset(cmnd, 0, sizeof(*cmnd));
cmnd->dsm.opcode = nvme_cmd_dsm;
cmnd->dsm.nsid = cpu_to_le32(ns->ns_id);
- cmnd->dsm.nr = segments - 1;
+ cmnd->dsm.nr = cpu_to_le32(segments - 1);
cmnd->dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD);
req->special_vec.bv_page = virt_to_page(range);
{
int ret = BLK_MQ_RQ_QUEUE_OK;
+ if (!(req->rq_flags & RQF_DONTPREP)) {
+ nvme_req(req)->retries = 0;
+ nvme_req(req)->flags = 0;
+ req->rq_flags |= RQF_DONTPREP;
+ }
+
switch (req_op(req)) {
case REQ_OP_DRV_IN:
case REQ_OP_DRV_OUT:
case REQ_OP_FLUSH:
nvme_setup_flush(ns, cmd);
break;
+ case REQ_OP_WRITE_ZEROES:
+ /* currently only aliased to deallocate for a few ctrls: */
case REQ_OP_DISCARD:
ret = nvme_setup_discard(ns, req, cmd);
break;
blk_execute_rq(req->q, NULL, req, at_head);
if (result)
*result = nvme_req(req)->result;
- ret = req->errors;
+ if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
+ ret = -EINTR;
+ else
+ ret = nvme_req(req)->status;
out:
blk_mq_free_request(req);
return ret;
}
submit:
blk_execute_rq(req->q, disk, req, 0);
- ret = req->errors;
+ if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
+ ret = -EINTR;
+ else
+ ret = nvme_req(req)->status;
if (result)
*result = le32_to_cpu(nvme_req(req)->result.u32);
if (meta && !ret && !write) {
BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) <
NVME_DSM_MAX_RANGES);
- if (ctrl->quirks & NVME_QUIRK_DISCARD_ZEROES)
- ns->queue->limits.discard_zeroes_data = 1;
- else
- ns->queue->limits.discard_zeroes_data = 0;
-
ns->queue->limits.discard_alignment = logical_block_size;
ns->queue->limits.discard_granularity = logical_block_size;
blk_queue_max_discard_sectors(ns->queue, UINT_MAX);
blk_queue_max_discard_segments(ns->queue, NVME_DSM_MAX_RANGES);
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue);
+
+ if (ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
+ blk_queue_max_write_zeroes_sectors(ns->queue, UINT_MAX);
}
static int nvme_revalidate_ns(struct nvme_ns *ns, struct nvme_id_ns **id)
* heuristic: we are willing to spend at most 2% of the time
* transitioning between power states. Therefore, when running
* in any given state, we will enter the next lower-power
- * non-operational state after waiting 100 * (enlat + exlat)
+ * non-operational state after waiting 50 * (enlat + exlat)
* microseconds, as long as that state's total latency is under
* the requested maximum latency.
*
unsigned apste;
struct nvme_feat_auto_pst *table;
+ u64 max_lat_us = 0;
+ int max_ps = -1;
int ret;
/*
if (ctrl->ps_max_latency_us == 0) {
/* Turn off APST. */
apste = 0;
+ dev_dbg(ctrl->device, "APST disabled\n");
} else {
__le64 target = cpu_to_le64(0);
int state;
table->entries[state] = target;
/*
+ * Don't allow transitions to the deepest state
+ * if it's quirked off.
+ */
+ if (state == ctrl->npss &&
+ (ctrl->quirks & NVME_QUIRK_NO_DEEPEST_PS))
+ continue;
+
+ /*
* Is this state a useful non-operational state for
* higher-power states to autonomously transition to?
*/
target = cpu_to_le64((state << 3) |
(transition_ms << 8));
+
+ if (max_ps == -1)
+ max_ps = state;
+
+ if (total_latency_us > max_lat_us)
+ max_lat_us = total_latency_us;
}
apste = 1;
+
+ if (max_ps == -1) {
+ dev_dbg(ctrl->device, "APST enabled but no non-operational states are available\n");
+ } else {
+ dev_dbg(ctrl->device, "APST enabled: max PS = %d, max round-trip latency = %lluus, table = %*phN\n",
+ max_ps, max_lat_us, (int)sizeof(*table), table);
+ }
}
ret = nvme_set_features(ctrl, NVME_FEAT_AUTO_PST, apste,
};
static const struct nvme_core_quirk_entry core_quirks[] = {
- /*
- * Seen on a Samsung "SM951 NVMe SAMSUNG 256GB": using APST causes
- * the controller to go out to lunch. It dies when the watchdog
- * timer reads CSTS and gets 0xffffffff.
- */
{
- .vid = 0x144d,
- .fr = "BXW75D0Q",
+ /*
+ * This Toshiba device seems to die using any APST states. See:
+ * https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1678184/comments/11
+ */
+ .vid = 0x1179,
+ .mn = "THNSF5256GPUK TOSHIBA",
.quirks = NVME_QUIRK_NO_APST,
- },
+ }
};
/* match is null-terminated but idstr is space-padded. */
}
}
+ if (force_apst && (ctrl->quirks & NVME_QUIRK_NO_DEEPEST_PS)) {
+ dev_warn(ctrl->dev, "forcibly allowing all power states due to nvme_core.force_apst -- use at your own risk\n");
+ ctrl->quirks &= ~NVME_QUIRK_NO_DEEPEST_PS;
+ }
+
ctrl->oacs = le16_to_cpu(id->oacs);
ctrl->vid = le16_to_cpu(id->vid);
ctrl->oncs = le16_to_cpup(&id->oncs);
ctrl->npss = id->npss;
prev_apsta = ctrl->apsta;
- ctrl->apsta = (ctrl->quirks & NVME_QUIRK_NO_APST) ? 0 : id->apsta;
+ if (ctrl->quirks & NVME_QUIRK_NO_APST) {
+ if (force_apst && id->apsta) {
+ dev_warn(ctrl->dev, "forcibly allowing APST due to nvme_core.force_apst -- use at your own risk\n");
+ ctrl->apsta = 1;
+ } else {
+ ctrl->apsta = 0;
+ }
+ } else {
+ ctrl->apsta = id->apsta;
+ }
memcpy(ctrl->psd, id->psd, sizeof(ctrl->psd));
if (ctrl->ops->is_fabrics) {
mutex_lock(&ctrl->namespaces_mutex);
list_for_each_entry(ns, &ctrl->namespaces, list)
- blk_mq_freeze_queue_start(ns->queue);
+ blk_freeze_queue_start(ns->queue);
mutex_unlock(&ctrl->namespaces_mutex);
}
EXPORT_SYMBOL_GPL(nvme_start_freeze);
}
EXPORT_SYMBOL_GPL(nvmf_connect_io_queue);
+bool nvmf_should_reconnect(struct nvme_ctrl *ctrl)
+{
+ if (ctrl->opts->max_reconnects != -1 &&
+ ctrl->opts->nr_reconnects < ctrl->opts->max_reconnects)
+ return true;
+
+ return false;
+}
+EXPORT_SYMBOL_GPL(nvmf_should_reconnect);
+
/**
* nvmf_register_transport() - NVMe Fabrics Library registration function.
* @ops: Transport ops instance to be registered to the
{ NVMF_OPT_QUEUE_SIZE, "queue_size=%d" },
{ NVMF_OPT_NR_IO_QUEUES, "nr_io_queues=%d" },
{ NVMF_OPT_RECONNECT_DELAY, "reconnect_delay=%d" },
+ { NVMF_OPT_CTRL_LOSS_TMO, "ctrl_loss_tmo=%d" },
{ NVMF_OPT_KATO, "keep_alive_tmo=%d" },
{ NVMF_OPT_HOSTNQN, "hostnqn=%s" },
{ NVMF_OPT_HOST_TRADDR, "host_traddr=%s" },
char *options, *o, *p;
int token, ret = 0;
size_t nqnlen = 0;
+ int ctrl_loss_tmo = NVMF_DEF_CTRL_LOSS_TMO;
/* Set defaults */
opts->queue_size = NVMF_DEF_QUEUE_SIZE;
}
opts->kato = token;
break;
+ case NVMF_OPT_CTRL_LOSS_TMO:
+ if (match_int(args, &token)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (token < 0)
+ pr_warn("ctrl_loss_tmo < 0 will reconnect forever\n");
+ ctrl_loss_tmo = token;
+ break;
case NVMF_OPT_HOSTNQN:
if (opts->host) {
pr_err("hostnqn already user-assigned: %s\n",
}
}
+ if (ctrl_loss_tmo < 0)
+ opts->max_reconnects = -1;
+ else
+ opts->max_reconnects = DIV_ROUND_UP(ctrl_loss_tmo,
+ opts->reconnect_delay);
+
if (!opts->host) {
kref_get(&nvmf_default_host->ref);
opts->host = nvmf_default_host;
#define NVMF_MAX_QUEUE_SIZE 1024
#define NVMF_DEF_QUEUE_SIZE 128
#define NVMF_DEF_RECONNECT_DELAY 10
+/* default to 600 seconds of reconnect attempts before giving up */
+#define NVMF_DEF_CTRL_LOSS_TMO 600
/*
* Define a host as seen by the target. We allocate one at boot, but also
NVMF_OPT_HOSTNQN = 1 << 8,
NVMF_OPT_RECONNECT_DELAY = 1 << 9,
NVMF_OPT_HOST_TRADDR = 1 << 10,
+ NVMF_OPT_CTRL_LOSS_TMO = 1 << 11,
};
/**
* @discovery_nqn: indicates if the subsysnqn is the well-known discovery NQN.
* @kato: Keep-alive timeout.
* @host: Virtual NVMe host, contains the NQN and Host ID.
+ * @nr_reconnects: number of reconnect attempted since the last ctrl failure
+ * @max_reconnects: maximum number of allowed reconnect attempts before removing
+ * the controller, (-1) means reconnect forever, zero means remove
+ * immediately;
*/
struct nvmf_ctrl_options {
unsigned mask;
bool discovery_nqn;
unsigned int kato;
struct nvmf_host *host;
+ int nr_reconnects;
+ int max_reconnects;
};
/*
void nvmf_free_options(struct nvmf_ctrl_options *opts);
const char *nvmf_get_subsysnqn(struct nvme_ctrl *ctrl);
int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size);
+bool nvmf_should_reconnect(struct nvme_ctrl *ctrl);
#endif /* _NVME_FABRICS_H */
#include <linux/parser.h>
#include <uapi/scsi/fc/fc_fs.h>
#include <uapi/scsi/fc/fc_els.h>
+#include <linux/delay.h>
#include "nvme.h"
#include "fabrics.h"
#define NVMEFC_QUEUE_DELAY 3 /* ms units */
+#define NVME_FC_MAX_CONNECT_ATTEMPTS 1
+
struct nvme_fc_queue {
struct nvme_fc_ctrl *ctrl;
struct device *dev;
unsigned long flags;
} __aligned(sizeof(u64)); /* alignment for other things alloc'd with */
+enum nvme_fcop_flags {
+ FCOP_FLAGS_TERMIO = (1 << 0),
+ FCOP_FLAGS_RELEASED = (1 << 1),
+ FCOP_FLAGS_COMPLETE = (1 << 2),
+ FCOP_FLAGS_AEN = (1 << 3),
+};
+
struct nvmefc_ls_req_op {
struct nvmefc_ls_req ls_req;
- struct nvme_fc_ctrl *ctrl;
+ struct nvme_fc_rport *rport;
struct nvme_fc_queue *queue;
struct request *rq;
+ u32 flags;
int ls_error;
struct completion ls_done;
- struct list_head lsreq_list; /* ctrl->ls_req_list */
+ struct list_head lsreq_list; /* rport->ls_req_list */
bool req_queued;
};
FCPOP_STATE_IDLE = 1,
FCPOP_STATE_ACTIVE = 2,
FCPOP_STATE_ABORTED = 3,
+ FCPOP_STATE_COMPLETE = 4,
};
struct nvme_fc_fcp_op {
struct request *rq;
atomic_t state;
+ u32 flags;
u32 rqno;
u32 nents;
struct list_head endp_list; /* for lport->endp_list */
struct list_head ctrl_list;
+ struct list_head ls_req_list;
+ struct device *dev; /* physical device for dma */
+ struct nvme_fc_lport *lport;
spinlock_t lock;
struct kref ref;
} __aligned(sizeof(u64)); /* alignment for other things alloc'd with */
-enum nvme_fcctrl_state {
- FCCTRL_INIT = 0,
- FCCTRL_ACTIVE = 1,
+enum nvme_fcctrl_flags {
+ FCCTRL_TERMIO = (1 << 0),
};
struct nvme_fc_ctrl {
spinlock_t lock;
struct nvme_fc_queue *queues;
- u32 queue_count;
-
struct device *dev;
struct nvme_fc_lport *lport;
struct nvme_fc_rport *rport;
+ u32 queue_count;
u32 cnum;
u64 association_id;
u64 cap;
struct list_head ctrl_list; /* rport->ctrl_list */
- struct list_head ls_req_list;
struct blk_mq_tag_set admin_tag_set;
struct blk_mq_tag_set tag_set;
struct work_struct delete_work;
+ struct work_struct reset_work;
+ struct delayed_work connect_work;
+ int reconnect_delay;
+ int connect_attempts;
+
struct kref ref;
- int state;
+ u32 flags;
+ u32 iocnt;
struct nvme_fc_fcp_op aen_ops[NVME_FC_NR_AEN_COMMANDS];
INIT_LIST_HEAD(&newrec->endp_list);
INIT_LIST_HEAD(&newrec->ctrl_list);
+ INIT_LIST_HEAD(&newrec->ls_req_list);
kref_init(&newrec->ref);
spin_lock_init(&newrec->lock);
newrec->remoteport.localport = &lport->localport;
+ newrec->dev = lport->dev;
+ newrec->lport = lport;
newrec->remoteport.private = &newrec[1];
newrec->remoteport.port_role = pinfo->port_role;
newrec->remoteport.node_name = pinfo->node_name;
out_reghost_failed:
*portptr = NULL;
return ret;
-
}
EXPORT_SYMBOL_GPL(nvme_fc_register_remoteport);
return kref_get_unless_zero(&rport->ref);
}
+static int
+nvme_fc_abort_lsops(struct nvme_fc_rport *rport)
+{
+ struct nvmefc_ls_req_op *lsop;
+ unsigned long flags;
+
+restart:
+ spin_lock_irqsave(&rport->lock, flags);
+
+ list_for_each_entry(lsop, &rport->ls_req_list, lsreq_list) {
+ if (!(lsop->flags & FCOP_FLAGS_TERMIO)) {
+ lsop->flags |= FCOP_FLAGS_TERMIO;
+ spin_unlock_irqrestore(&rport->lock, flags);
+ rport->lport->ops->ls_abort(&rport->lport->localport,
+ &rport->remoteport,
+ &lsop->ls_req);
+ goto restart;
+ }
+ }
+ spin_unlock_irqrestore(&rport->lock, flags);
+
+ return 0;
+}
+
/**
* nvme_fc_unregister_remoteport - transport entry point called by an
* LLDD to deregister/remove a previously
spin_unlock_irqrestore(&rport->lock, flags);
+ nvme_fc_abort_lsops(rport);
+
nvme_fc_rport_put(rport);
return 0;
}
static void
-__nvme_fc_finish_ls_req(struct nvme_fc_ctrl *ctrl,
- struct nvmefc_ls_req_op *lsop)
+__nvme_fc_finish_ls_req(struct nvmefc_ls_req_op *lsop)
{
+ struct nvme_fc_rport *rport = lsop->rport;
struct nvmefc_ls_req *lsreq = &lsop->ls_req;
unsigned long flags;
- spin_lock_irqsave(&ctrl->lock, flags);
+ spin_lock_irqsave(&rport->lock, flags);
if (!lsop->req_queued) {
- spin_unlock_irqrestore(&ctrl->lock, flags);
+ spin_unlock_irqrestore(&rport->lock, flags);
return;
}
lsop->req_queued = false;
- spin_unlock_irqrestore(&ctrl->lock, flags);
+ spin_unlock_irqrestore(&rport->lock, flags);
- fc_dma_unmap_single(ctrl->dev, lsreq->rqstdma,
+ fc_dma_unmap_single(rport->dev, lsreq->rqstdma,
(lsreq->rqstlen + lsreq->rsplen),
DMA_BIDIRECTIONAL);
- nvme_fc_ctrl_put(ctrl);
+ nvme_fc_rport_put(rport);
}
static int
-__nvme_fc_send_ls_req(struct nvme_fc_ctrl *ctrl,
+__nvme_fc_send_ls_req(struct nvme_fc_rport *rport,
struct nvmefc_ls_req_op *lsop,
void (*done)(struct nvmefc_ls_req *req, int status))
{
struct nvmefc_ls_req *lsreq = &lsop->ls_req;
unsigned long flags;
- int ret;
+ int ret = 0;
- if (!nvme_fc_ctrl_get(ctrl))
+ if (rport->remoteport.port_state != FC_OBJSTATE_ONLINE)
+ return -ECONNREFUSED;
+
+ if (!nvme_fc_rport_get(rport))
return -ESHUTDOWN;
lsreq->done = done;
- lsop->ctrl = ctrl;
+ lsop->rport = rport;
lsop->req_queued = false;
INIT_LIST_HEAD(&lsop->lsreq_list);
init_completion(&lsop->ls_done);
- lsreq->rqstdma = fc_dma_map_single(ctrl->dev, lsreq->rqstaddr,
+ lsreq->rqstdma = fc_dma_map_single(rport->dev, lsreq->rqstaddr,
lsreq->rqstlen + lsreq->rsplen,
DMA_BIDIRECTIONAL);
- if (fc_dma_mapping_error(ctrl->dev, lsreq->rqstdma)) {
- nvme_fc_ctrl_put(ctrl);
- dev_err(ctrl->dev,
- "els request command failed EFAULT.\n");
- return -EFAULT;
+ if (fc_dma_mapping_error(rport->dev, lsreq->rqstdma)) {
+ ret = -EFAULT;
+ goto out_putrport;
}
lsreq->rspdma = lsreq->rqstdma + lsreq->rqstlen;
- spin_lock_irqsave(&ctrl->lock, flags);
+ spin_lock_irqsave(&rport->lock, flags);
- list_add_tail(&lsop->lsreq_list, &ctrl->ls_req_list);
+ list_add_tail(&lsop->lsreq_list, &rport->ls_req_list);
lsop->req_queued = true;
- spin_unlock_irqrestore(&ctrl->lock, flags);
+ spin_unlock_irqrestore(&rport->lock, flags);
- ret = ctrl->lport->ops->ls_req(&ctrl->lport->localport,
- &ctrl->rport->remoteport, lsreq);
+ ret = rport->lport->ops->ls_req(&rport->lport->localport,
+ &rport->remoteport, lsreq);
if (ret)
- lsop->ls_error = ret;
+ goto out_unlink;
+
+ return 0;
+
+out_unlink:
+ lsop->ls_error = ret;
+ spin_lock_irqsave(&rport->lock, flags);
+ lsop->req_queued = false;
+ list_del(&lsop->lsreq_list);
+ spin_unlock_irqrestore(&rport->lock, flags);
+ fc_dma_unmap_single(rport->dev, lsreq->rqstdma,
+ (lsreq->rqstlen + lsreq->rsplen),
+ DMA_BIDIRECTIONAL);
+out_putrport:
+ nvme_fc_rport_put(rport);
return ret;
}
}
static int
-nvme_fc_send_ls_req(struct nvme_fc_ctrl *ctrl, struct nvmefc_ls_req_op *lsop)
+nvme_fc_send_ls_req(struct nvme_fc_rport *rport, struct nvmefc_ls_req_op *lsop)
{
struct nvmefc_ls_req *lsreq = &lsop->ls_req;
struct fcnvme_ls_rjt *rjt = lsreq->rspaddr;
int ret;
- ret = __nvme_fc_send_ls_req(ctrl, lsop, nvme_fc_send_ls_req_done);
+ ret = __nvme_fc_send_ls_req(rport, lsop, nvme_fc_send_ls_req_done);
- if (!ret)
+ if (!ret) {
/*
* No timeout/not interruptible as we need the struct
* to exist until the lldd calls us back. Thus mandate
*/
wait_for_completion(&lsop->ls_done);
- __nvme_fc_finish_ls_req(ctrl, lsop);
+ __nvme_fc_finish_ls_req(lsop);
- if (ret) {
- dev_err(ctrl->dev,
- "ls request command failed (%d).\n", ret);
- return ret;
+ ret = lsop->ls_error;
}
+ if (ret)
+ return ret;
+
/* ACC or RJT payload ? */
if (rjt->w0.ls_cmd == FCNVME_LS_RJT)
return -ENXIO;
return 0;
}
-static void
-nvme_fc_send_ls_req_async(struct nvme_fc_ctrl *ctrl,
+static int
+nvme_fc_send_ls_req_async(struct nvme_fc_rport *rport,
struct nvmefc_ls_req_op *lsop,
void (*done)(struct nvmefc_ls_req *req, int status))
{
- int ret;
-
- ret = __nvme_fc_send_ls_req(ctrl, lsop, done);
-
/* don't wait for completion */
- if (ret)
- done(&lsop->ls_req, ret);
+ return __nvme_fc_send_ls_req(rport, lsop, done);
}
/* Validation Error indexes into the string table below */
lsreq->rsplen = sizeof(*assoc_acc);
lsreq->timeout = NVME_FC_CONNECT_TIMEOUT_SEC;
- ret = nvme_fc_send_ls_req(ctrl, lsop);
+ ret = nvme_fc_send_ls_req(ctrl->rport, lsop);
if (ret)
goto out_free_buffer;
/* validate the ACC response */
if (assoc_acc->hdr.w0.ls_cmd != FCNVME_LS_ACC)
fcret = VERR_LSACC;
- if (assoc_acc->hdr.desc_list_len !=
+ else if (assoc_acc->hdr.desc_list_len !=
fcnvme_lsdesc_len(
sizeof(struct fcnvme_ls_cr_assoc_acc)))
fcret = VERR_CR_ASSOC_ACC_LEN;
- if (assoc_acc->hdr.rqst.desc_tag != cpu_to_be32(FCNVME_LSDESC_RQST))
+ else if (assoc_acc->hdr.rqst.desc_tag !=
+ cpu_to_be32(FCNVME_LSDESC_RQST))
fcret = VERR_LSDESC_RQST;
else if (assoc_acc->hdr.rqst.desc_len !=
fcnvme_lsdesc_len(sizeof(struct fcnvme_lsdesc_rqst)))
lsreq->rsplen = sizeof(*conn_acc);
lsreq->timeout = NVME_FC_CONNECT_TIMEOUT_SEC;
- ret = nvme_fc_send_ls_req(ctrl, lsop);
+ ret = nvme_fc_send_ls_req(ctrl->rport, lsop);
if (ret)
goto out_free_buffer;
/* validate the ACC response */
if (conn_acc->hdr.w0.ls_cmd != FCNVME_LS_ACC)
fcret = VERR_LSACC;
- if (conn_acc->hdr.desc_list_len !=
+ else if (conn_acc->hdr.desc_list_len !=
fcnvme_lsdesc_len(sizeof(struct fcnvme_ls_cr_conn_acc)))
fcret = VERR_CR_CONN_ACC_LEN;
- if (conn_acc->hdr.rqst.desc_tag != cpu_to_be32(FCNVME_LSDESC_RQST))
+ else if (conn_acc->hdr.rqst.desc_tag != cpu_to_be32(FCNVME_LSDESC_RQST))
fcret = VERR_LSDESC_RQST;
else if (conn_acc->hdr.rqst.desc_len !=
fcnvme_lsdesc_len(sizeof(struct fcnvme_lsdesc_rqst)))
nvme_fc_disconnect_assoc_done(struct nvmefc_ls_req *lsreq, int status)
{
struct nvmefc_ls_req_op *lsop = ls_req_to_lsop(lsreq);
- struct nvme_fc_ctrl *ctrl = lsop->ctrl;
- __nvme_fc_finish_ls_req(ctrl, lsop);
-
- if (status)
- dev_err(ctrl->dev,
- "disconnect assoc ls request command failed (%d).\n",
- status);
+ __nvme_fc_finish_ls_req(lsop);
/* fc-nvme iniator doesn't care about success or failure of cmd */
struct fcnvme_ls_disconnect_acc *discon_acc;
struct nvmefc_ls_req_op *lsop;
struct nvmefc_ls_req *lsreq;
+ int ret;
lsop = kzalloc((sizeof(*lsop) +
ctrl->lport->ops->lsrqst_priv_sz +
lsreq->rsplen = sizeof(*discon_acc);
lsreq->timeout = NVME_FC_CONNECT_TIMEOUT_SEC;
- nvme_fc_send_ls_req_async(ctrl, lsop, nvme_fc_disconnect_assoc_done);
+ ret = nvme_fc_send_ls_req_async(ctrl->rport, lsop,
+ nvme_fc_disconnect_assoc_done);
+ if (ret)
+ kfree(lsop);
/* only meaningful part to terminating the association */
ctrl->association_id = 0;
/* *********************** NVME Ctrl Routines **************************** */
+static void __nvme_fc_final_op_cleanup(struct request *rq);
static int
nvme_fc_reinit_request(void *data, struct request *rq)
return __nvme_fc_exit_request(data, op);
}
+static int
+__nvme_fc_abort_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_fcp_op *op)
+{
+ int state;
+
+ state = atomic_xchg(&op->state, FCPOP_STATE_ABORTED);
+ if (state != FCPOP_STATE_ACTIVE) {
+ atomic_set(&op->state, state);
+ return -ECANCELED;
+ }
+
+ ctrl->lport->ops->fcp_abort(&ctrl->lport->localport,
+ &ctrl->rport->remoteport,
+ op->queue->lldd_handle,
+ &op->fcp_req);
+
+ return 0;
+}
+
static void
-nvme_fc_exit_aen_ops(struct nvme_fc_ctrl *ctrl)
+nvme_fc_abort_aen_ops(struct nvme_fc_ctrl *ctrl)
{
struct nvme_fc_fcp_op *aen_op = ctrl->aen_ops;
- int i;
+ unsigned long flags;
+ int i, ret;
for (i = 0; i < NVME_FC_NR_AEN_COMMANDS; i++, aen_op++) {
- if (atomic_read(&aen_op->state) == FCPOP_STATE_UNINIT)
+ if (atomic_read(&aen_op->state) != FCPOP_STATE_ACTIVE)
continue;
- __nvme_fc_exit_request(ctrl, aen_op);
- nvme_fc_ctrl_put(ctrl);
+
+ spin_lock_irqsave(&ctrl->lock, flags);
+ if (ctrl->flags & FCCTRL_TERMIO) {
+ ctrl->iocnt++;
+ aen_op->flags |= FCOP_FLAGS_TERMIO;
+ }
+ spin_unlock_irqrestore(&ctrl->lock, flags);
+
+ ret = __nvme_fc_abort_op(ctrl, aen_op);
+ if (ret) {
+ /*
+ * if __nvme_fc_abort_op failed the io wasn't
+ * active. Thus this call path is running in
+ * parallel to the io complete. Treat as non-error.
+ */
+
+ /* back out the flags/counters */
+ spin_lock_irqsave(&ctrl->lock, flags);
+ if (ctrl->flags & FCCTRL_TERMIO)
+ ctrl->iocnt--;
+ aen_op->flags &= ~FCOP_FLAGS_TERMIO;
+ spin_unlock_irqrestore(&ctrl->lock, flags);
+ return;
+ }
+ }
+}
+
+static inline int
+__nvme_fc_fcpop_chk_teardowns(struct nvme_fc_ctrl *ctrl,
+ struct nvme_fc_fcp_op *op)
+{
+ unsigned long flags;
+ bool complete_rq = false;
+
+ spin_lock_irqsave(&ctrl->lock, flags);
+ if (unlikely(op->flags & FCOP_FLAGS_TERMIO)) {
+ if (ctrl->flags & FCCTRL_TERMIO)
+ ctrl->iocnt--;
}
+ if (op->flags & FCOP_FLAGS_RELEASED)
+ complete_rq = true;
+ else
+ op->flags |= FCOP_FLAGS_COMPLETE;
+ spin_unlock_irqrestore(&ctrl->lock, flags);
+
+ return complete_rq;
}
-void
+static void
nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
{
struct nvme_fc_fcp_op *op = fcp_req_to_fcp_op(req);
struct nvme_fc_ctrl *ctrl = op->ctrl;
struct nvme_fc_queue *queue = op->queue;
struct nvme_completion *cqe = &op->rsp_iu.cqe;
- u16 status;
+ struct nvme_command *sqe = &op->cmd_iu.sqe;
+ __le16 status = cpu_to_le16(NVME_SC_SUCCESS << 1);
+ union nvme_result result;
+ bool complete_rq;
/*
* WARNING:
sizeof(op->rsp_iu), DMA_FROM_DEVICE);
if (atomic_read(&op->state) == FCPOP_STATE_ABORTED)
- status = NVME_SC_ABORT_REQ | NVME_SC_DNR;
- else
- status = freq->status;
+ status = cpu_to_le16((NVME_SC_ABORT_REQ | NVME_SC_DNR) << 1);
+ else if (freq->status)
+ status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
/*
* For the linux implementation, if we have an unsuccesful
*/
if (freq->transferred_length !=
be32_to_cpu(op->cmd_iu.data_len)) {
- status = -EIO;
+ status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
goto done;
}
- op->nreq.result.u64 = 0;
+ result.u64 = 0;
break;
case sizeof(struct nvme_fc_ersp_iu):
(freq->rcv_rsplen / 4) ||
be32_to_cpu(op->rsp_iu.xfrd_len) !=
freq->transferred_length ||
- op->rqno != le16_to_cpu(cqe->command_id))) {
- status = -EIO;
+ op->rsp_iu.status_code ||
+ sqe->common.command_id != cqe->command_id)) {
+ status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
goto done;
}
- op->nreq.result = cqe->result;
- status = le16_to_cpu(cqe->status) >> 1;
+ result = cqe->result;
+ status = cqe->status;
break;
default:
- status = -EIO;
+ status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
goto done;
}
done:
- if (!queue->qnum && op->rqno >= AEN_CMDID_BASE) {
- nvme_complete_async_event(&queue->ctrl->ctrl, status,
- &op->nreq.result);
+ if (op->flags & FCOP_FLAGS_AEN) {
+ nvme_complete_async_event(&queue->ctrl->ctrl, status, &result);
+ complete_rq = __nvme_fc_fcpop_chk_teardowns(ctrl, op);
+ atomic_set(&op->state, FCPOP_STATE_IDLE);
+ op->flags = FCOP_FLAGS_AEN; /* clear other flags */
nvme_fc_ctrl_put(ctrl);
return;
}
- blk_mq_complete_request(rq, status);
+ complete_rq = __nvme_fc_fcpop_chk_teardowns(ctrl, op);
+ if (!complete_rq) {
+ if (unlikely(op->flags & FCOP_FLAGS_TERMIO)) {
+ status = cpu_to_le16(NVME_SC_ABORT_REQ);
+ if (blk_queue_dying(rq->q))
+ status |= cpu_to_le16(NVME_SC_DNR);
+ }
+ nvme_end_request(rq, status, result);
+ } else
+ __nvme_fc_final_op_cleanup(rq);
}
static int
struct nvme_fc_fcp_op *aen_op;
struct nvme_fc_cmd_iu *cmdiu;
struct nvme_command *sqe;
+ void *private;
int i, ret;
aen_op = ctrl->aen_ops;
for (i = 0; i < NVME_FC_NR_AEN_COMMANDS; i++, aen_op++) {
+ private = kzalloc(ctrl->lport->ops->fcprqst_priv_sz,
+ GFP_KERNEL);
+ if (!private)
+ return -ENOMEM;
+
cmdiu = &aen_op->cmd_iu;
sqe = &cmdiu->sqe;
ret = __nvme_fc_init_request(ctrl, &ctrl->queues[0],
aen_op, (struct request *)NULL,
(AEN_CMDID_BASE + i));
- if (ret)
+ if (ret) {
+ kfree(private);
return ret;
+ }
+
+ aen_op->flags = FCOP_FLAGS_AEN;
+ aen_op->fcp_req.first_sgl = NULL; /* no sg list */
+ aen_op->fcp_req.private = private;
memset(sqe, 0, sizeof(*sqe));
sqe->common.opcode = nvme_admin_async_event;
+ /* Note: core layer may overwrite the sqe.command_id value */
sqe->common.command_id = AEN_CMDID_BASE + i;
}
return 0;
}
+static void
+nvme_fc_term_aen_ops(struct nvme_fc_ctrl *ctrl)
+{
+ struct nvme_fc_fcp_op *aen_op;
+ int i;
+
+ aen_op = ctrl->aen_ops;
+ for (i = 0; i < NVME_FC_NR_AEN_COMMANDS; i++, aen_op++) {
+ if (!aen_op->fcp_req.private)
+ continue;
+
+ __nvme_fc_exit_request(ctrl, aen_op);
+
+ kfree(aen_op->fcp_req.private);
+ aen_op->fcp_req.private = NULL;
+ }
+}
static inline void
__nvme_fc_init_hctx(struct blk_mq_hw_ctx *hctx, struct nvme_fc_ctrl *ctrl,
}
static void
-nvme_fc_destroy_admin_queue(struct nvme_fc_ctrl *ctrl)
-{
- __nvme_fc_delete_hw_queue(ctrl, &ctrl->queues[0], 0);
- blk_cleanup_queue(ctrl->ctrl.admin_q);
- blk_mq_free_tag_set(&ctrl->admin_tag_set);
- nvme_fc_free_queue(&ctrl->queues[0]);
-}
-
-static void
nvme_fc_free_io_queues(struct nvme_fc_ctrl *ctrl)
{
int i;
container_of(ref, struct nvme_fc_ctrl, ref);
unsigned long flags;
- if (ctrl->state != FCCTRL_INIT) {
- /* remove from rport list */
- spin_lock_irqsave(&ctrl->rport->lock, flags);
- list_del(&ctrl->ctrl_list);
- spin_unlock_irqrestore(&ctrl->rport->lock, flags);
+ if (ctrl->ctrl.tagset) {
+ blk_cleanup_queue(ctrl->ctrl.connect_q);
+ blk_mq_free_tag_set(&ctrl->tag_set);
}
+ /* remove from rport list */
+ spin_lock_irqsave(&ctrl->rport->lock, flags);
+ list_del(&ctrl->ctrl_list);
+ spin_unlock_irqrestore(&ctrl->rport->lock, flags);
+
+ blk_cleanup_queue(ctrl->ctrl.admin_q);
+ blk_mq_free_tag_set(&ctrl->admin_tag_set);
+
+ kfree(ctrl->queues);
+
put_device(ctrl->dev);
nvme_fc_rport_put(ctrl->rport);
- kfree(ctrl->queues);
ida_simple_remove(&nvme_fc_ctrl_cnt, ctrl->cnum);
- nvmf_free_options(ctrl->ctrl.opts);
+ if (ctrl->ctrl.opts)
+ nvmf_free_options(ctrl->ctrl.opts);
kfree(ctrl);
}
* controller. Called after last nvme_put_ctrl() call
*/
static void
-nvme_fc_free_nvme_ctrl(struct nvme_ctrl *nctrl)
+nvme_fc_nvme_ctrl_freed(struct nvme_ctrl *nctrl)
{
struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
WARN_ON(nctrl != &ctrl->ctrl);
- /*
- * Tear down the association, which will generate link
- * traffic to terminate connections
- */
-
- if (ctrl->state != FCCTRL_INIT) {
- /* send a Disconnect(association) LS to fc-nvme target */
- nvme_fc_xmt_disconnect_assoc(ctrl);
-
- if (ctrl->ctrl.tagset) {
- blk_cleanup_queue(ctrl->ctrl.connect_q);
- blk_mq_free_tag_set(&ctrl->tag_set);
- nvme_fc_delete_hw_io_queues(ctrl);
- nvme_fc_free_io_queues(ctrl);
- }
-
- nvme_fc_exit_aen_ops(ctrl);
-
- nvme_fc_destroy_admin_queue(ctrl);
- }
-
nvme_fc_ctrl_put(ctrl);
}
-
-static int
-__nvme_fc_abort_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_fcp_op *op)
+static void
+nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg)
{
- int state;
+ dev_warn(ctrl->ctrl.device,
+ "NVME-FC{%d}: transport association error detected: %s\n",
+ ctrl->cnum, errmsg);
+ dev_info(ctrl->ctrl.device,
+ "NVME-FC{%d}: resetting controller\n", ctrl->cnum);
- state = atomic_xchg(&op->state, FCPOP_STATE_ABORTED);
- if (state != FCPOP_STATE_ACTIVE) {
- atomic_set(&op->state, state);
- return -ECANCELED; /* fail */
+ if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RECONNECTING)) {
+ dev_err(ctrl->ctrl.device,
+ "NVME-FC{%d}: error_recovery: Couldn't change state "
+ "to RECONNECTING\n", ctrl->cnum);
+ return;
}
- ctrl->lport->ops->fcp_abort(&ctrl->lport->localport,
- &ctrl->rport->remoteport,
- op->queue->lldd_handle,
- &op->fcp_req);
-
- return 0;
+ if (!queue_work(nvme_fc_wq, &ctrl->reset_work))
+ dev_err(ctrl->ctrl.device,
+ "NVME-FC{%d}: error_recovery: Failed to schedule "
+ "reset work\n", ctrl->cnum);
}
-enum blk_eh_timer_return
+static enum blk_eh_timer_return
nvme_fc_timeout(struct request *rq, bool reserved)
{
struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq);
return BLK_EH_HANDLED;
/*
- * TODO: force a controller reset
- * when that happens, queues will be torn down and outstanding
- * ios will be terminated, and the above abort, on a single io
- * will no longer be needed.
+ * we can't individually ABTS an io without affecting the queue,
+ * thus killing the queue, adn thus the association.
+ * So resolve by performing a controller reset, which will stop
+ * the host/io stack, terminate the association on the link,
+ * and recreate an association on the link.
*/
+ nvme_fc_error_recovery(ctrl, "io timeout error");
return BLK_EH_HANDLED;
}
u32 csn;
int ret;
+ /*
+ * before attempting to send the io, check to see if we believe
+ * the target device is present
+ */
+ if (ctrl->rport->remoteport.port_state != FC_OBJSTATE_ONLINE)
+ return BLK_MQ_RQ_QUEUE_ERROR;
+
if (!nvme_fc_ctrl_get(ctrl))
return BLK_MQ_RQ_QUEUE_ERROR;
op->fcp_req.io_dir = io_dir;
op->fcp_req.transferred_length = 0;
op->fcp_req.rcv_rsplen = 0;
- op->fcp_req.status = 0;
+ op->fcp_req.status = NVME_SC_SUCCESS;
op->fcp_req.sqid = cpu_to_le16(queue->qnum);
/*
sqe->rw.dptr.sgl.length = cpu_to_le32(data_len);
sqe->rw.dptr.sgl.addr = 0;
- /* odd that we set the command_id - should come from nvme-fabrics */
- WARN_ON_ONCE(sqe->common.command_id != cpu_to_le16(op->rqno));
-
- if (op->rq) { /* skipped on aens */
+ if (!(op->flags & FCOP_FLAGS_AEN)) {
ret = nvme_fc_map_data(ctrl, op->rq, op);
if (ret < 0) {
- dev_err(queue->ctrl->ctrl.device,
- "Failed to map data (%d)\n", ret);
nvme_cleanup_cmd(op->rq);
nvme_fc_ctrl_put(ctrl);
return (ret == -ENOMEM || ret == -EAGAIN) ?
atomic_set(&op->state, FCPOP_STATE_ACTIVE);
- if (op->rq)
+ if (!(op->flags & FCOP_FLAGS_AEN))
blk_mq_start_request(op->rq);
ret = ctrl->lport->ops->fcp_io(&ctrl->lport->localport,
queue->lldd_handle, &op->fcp_req);
if (ret) {
- dev_err(ctrl->dev,
- "Send nvme command failed - lldd returned %d.\n", ret);
-
if (op->rq) { /* normal request */
nvme_fc_unmap_data(ctrl, op->rq, op);
nvme_cleanup_cmd(op->rq);
struct nvme_fc_fcp_op *op;
req = blk_mq_tag_to_rq(nvme_fc_tagset(queue), tag);
- if (!req) {
- dev_err(queue->ctrl->ctrl.device,
- "tag 0x%x on QNum %#x not found\n",
- tag, queue->qnum);
+ if (!req)
return 0;
- }
op = blk_mq_rq_to_pdu(req);
{
struct nvme_fc_ctrl *ctrl = to_fc_ctrl(arg);
struct nvme_fc_fcp_op *aen_op;
+ unsigned long flags;
+ bool terminating = false;
int ret;
if (aer_idx > NVME_FC_NR_AEN_COMMANDS)
return;
+ spin_lock_irqsave(&ctrl->lock, flags);
+ if (ctrl->flags & FCCTRL_TERMIO)
+ terminating = true;
+ spin_unlock_irqrestore(&ctrl->lock, flags);
+
+ if (terminating)
+ return;
+
aen_op = &ctrl->aen_ops[aer_idx];
ret = nvme_fc_start_fcp_op(ctrl, aen_op->queue, aen_op, 0,
}
static void
-nvme_fc_complete_rq(struct request *rq)
+__nvme_fc_final_op_cleanup(struct request *rq)
{
struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq);
struct nvme_fc_ctrl *ctrl = op->ctrl;
- int error = 0, state;
- state = atomic_xchg(&op->state, FCPOP_STATE_IDLE);
+ atomic_set(&op->state, FCPOP_STATE_IDLE);
+ op->flags &= ~(FCOP_FLAGS_TERMIO | FCOP_FLAGS_RELEASED |
+ FCOP_FLAGS_COMPLETE);
nvme_cleanup_cmd(rq);
-
nvme_fc_unmap_data(ctrl, rq, op);
+ nvme_complete_rq(rq);
+ nvme_fc_ctrl_put(ctrl);
- if (unlikely(rq->errors)) {
- if (nvme_req_needs_retry(rq, rq->errors)) {
- nvme_requeue_req(rq);
- return;
- }
+}
- if (blk_rq_is_passthrough(rq))
- error = rq->errors;
- else
- error = nvme_error_status(rq->errors);
+static void
+nvme_fc_complete_rq(struct request *rq)
+{
+ struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq);
+ struct nvme_fc_ctrl *ctrl = op->ctrl;
+ unsigned long flags;
+ bool completed = false;
+
+ /*
+ * the core layer, on controller resets after calling
+ * nvme_shutdown_ctrl(), calls complete_rq without our
+ * calling blk_mq_complete_request(), thus there may still
+ * be live i/o outstanding with the LLDD. Means transport has
+ * to track complete calls vs fcpio_done calls to know what
+ * path to take on completes and dones.
+ */
+ spin_lock_irqsave(&ctrl->lock, flags);
+ if (op->flags & FCOP_FLAGS_COMPLETE)
+ completed = true;
+ else
+ op->flags |= FCOP_FLAGS_RELEASED;
+ spin_unlock_irqrestore(&ctrl->lock, flags);
+
+ if (completed)
+ __nvme_fc_final_op_cleanup(rq);
+}
+
+/*
+ * This routine is used by the transport when it needs to find active
+ * io on a queue that is to be terminated. The transport uses
+ * blk_mq_tagset_busy_itr() to find the busy requests, which then invoke
+ * this routine to kill them on a 1 by 1 basis.
+ *
+ * As FC allocates FC exchange for each io, the transport must contact
+ * the LLDD to terminate the exchange, thus releasing the FC exchange.
+ * After terminating the exchange the LLDD will call the transport's
+ * normal io done path for the request, but it will have an aborted
+ * status. The done path will return the io request back to the block
+ * layer with an error status.
+ */
+static void
+nvme_fc_terminate_exchange(struct request *req, void *data, bool reserved)
+{
+ struct nvme_ctrl *nctrl = data;
+ struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
+ struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(req);
+ unsigned long flags;
+ int status;
+
+ if (!blk_mq_request_started(req))
+ return;
+
+ spin_lock_irqsave(&ctrl->lock, flags);
+ if (ctrl->flags & FCCTRL_TERMIO) {
+ ctrl->iocnt++;
+ op->flags |= FCOP_FLAGS_TERMIO;
}
+ spin_unlock_irqrestore(&ctrl->lock, flags);
- nvme_fc_ctrl_put(ctrl);
+ status = __nvme_fc_abort_op(ctrl, op);
+ if (status) {
+ /*
+ * if __nvme_fc_abort_op failed the io wasn't
+ * active. Thus this call path is running in
+ * parallel to the io complete. Treat as non-error.
+ */
- blk_mq_end_request(rq, error);
+ /* back out the flags/counters */
+ spin_lock_irqsave(&ctrl->lock, flags);
+ if (ctrl->flags & FCCTRL_TERMIO)
+ ctrl->iocnt--;
+ op->flags &= ~FCOP_FLAGS_TERMIO;
+ spin_unlock_irqrestore(&ctrl->lock, flags);
+ return;
+ }
}
-static struct blk_mq_ops nvme_fc_mq_ops = {
+
+static const struct blk_mq_ops nvme_fc_mq_ops = {
.queue_rq = nvme_fc_queue_rq,
.complete = nvme_fc_complete_rq,
.init_request = nvme_fc_init_request,
.timeout = nvme_fc_timeout,
};
-static struct blk_mq_ops nvme_fc_admin_mq_ops = {
- .queue_rq = nvme_fc_queue_rq,
- .complete = nvme_fc_complete_rq,
- .init_request = nvme_fc_init_admin_request,
- .exit_request = nvme_fc_exit_request,
- .reinit_request = nvme_fc_reinit_request,
- .init_hctx = nvme_fc_init_admin_hctx,
- .timeout = nvme_fc_timeout,
-};
-
static int
-nvme_fc_configure_admin_queue(struct nvme_fc_ctrl *ctrl)
+nvme_fc_create_io_queues(struct nvme_fc_ctrl *ctrl)
{
- u32 segs;
- int error;
+ struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
+ int ret;
- nvme_fc_init_queue(ctrl, 0, NVME_FC_AQ_BLKMQ_DEPTH);
+ ret = nvme_set_queue_count(&ctrl->ctrl, &opts->nr_io_queues);
+ if (ret) {
+ dev_info(ctrl->ctrl.device,
+ "set_queue_count failed: %d\n", ret);
+ return ret;
+ }
- error = nvme_fc_connect_admin_queue(ctrl, &ctrl->queues[0],
- NVME_FC_AQ_BLKMQ_DEPTH,
- (NVME_FC_AQ_BLKMQ_DEPTH / 4));
- if (error)
- return error;
+ ctrl->queue_count = opts->nr_io_queues + 1;
+ if (!opts->nr_io_queues)
+ return 0;
- memset(&ctrl->admin_tag_set, 0, sizeof(ctrl->admin_tag_set));
- ctrl->admin_tag_set.ops = &nvme_fc_admin_mq_ops;
- ctrl->admin_tag_set.queue_depth = NVME_FC_AQ_BLKMQ_DEPTH;
- ctrl->admin_tag_set.reserved_tags = 2; /* fabric connect + Keep-Alive */
- ctrl->admin_tag_set.numa_node = NUMA_NO_NODE;
- ctrl->admin_tag_set.cmd_size = sizeof(struct nvme_fc_fcp_op) +
+ dev_info(ctrl->ctrl.device, "creating %d I/O queues.\n",
+ opts->nr_io_queues);
+
+ nvme_fc_init_io_queues(ctrl);
+
+ memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set));
+ ctrl->tag_set.ops = &nvme_fc_mq_ops;
+ ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size;
+ ctrl->tag_set.reserved_tags = 1; /* fabric connect */
+ ctrl->tag_set.numa_node = NUMA_NO_NODE;
+ ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
+ ctrl->tag_set.cmd_size = sizeof(struct nvme_fc_fcp_op) +
(SG_CHUNK_SIZE *
sizeof(struct scatterlist)) +
ctrl->lport->ops->fcprqst_priv_sz;
- ctrl->admin_tag_set.driver_data = ctrl;
- ctrl->admin_tag_set.nr_hw_queues = 1;
- ctrl->admin_tag_set.timeout = ADMIN_TIMEOUT;
+ ctrl->tag_set.driver_data = ctrl;
+ ctrl->tag_set.nr_hw_queues = ctrl->queue_count - 1;
+ ctrl->tag_set.timeout = NVME_IO_TIMEOUT;
- error = blk_mq_alloc_tag_set(&ctrl->admin_tag_set);
- if (error)
- goto out_free_queue;
+ ret = blk_mq_alloc_tag_set(&ctrl->tag_set);
+ if (ret)
+ return ret;
- ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set);
- if (IS_ERR(ctrl->ctrl.admin_q)) {
- error = PTR_ERR(ctrl->ctrl.admin_q);
- goto out_free_tagset;
+ ctrl->ctrl.tagset = &ctrl->tag_set;
+
+ ctrl->ctrl.connect_q = blk_mq_init_queue(&ctrl->tag_set);
+ if (IS_ERR(ctrl->ctrl.connect_q)) {
+ ret = PTR_ERR(ctrl->ctrl.connect_q);
+ goto out_free_tag_set;
}
- error = __nvme_fc_create_hw_queue(ctrl, &ctrl->queues[0], 0,
+ ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.opts->queue_size);
+ if (ret)
+ goto out_cleanup_blk_queue;
+
+ ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.opts->queue_size);
+ if (ret)
+ goto out_delete_hw_queues;
+
+ return 0;
+
+out_delete_hw_queues:
+ nvme_fc_delete_hw_io_queues(ctrl);
+out_cleanup_blk_queue:
+ nvme_stop_keep_alive(&ctrl->ctrl);
+ blk_cleanup_queue(ctrl->ctrl.connect_q);
+out_free_tag_set:
+ blk_mq_free_tag_set(&ctrl->tag_set);
+ nvme_fc_free_io_queues(ctrl);
+
+ /* force put free routine to ignore io queues */
+ ctrl->ctrl.tagset = NULL;
+
+ return ret;
+}
+
+static int
+nvme_fc_reinit_io_queues(struct nvme_fc_ctrl *ctrl)
+{
+ struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
+ int ret;
+
+ ret = nvme_set_queue_count(&ctrl->ctrl, &opts->nr_io_queues);
+ if (ret) {
+ dev_info(ctrl->ctrl.device,
+ "set_queue_count failed: %d\n", ret);
+ return ret;
+ }
+
+ /* check for io queues existing */
+ if (ctrl->queue_count == 1)
+ return 0;
+
+ dev_info(ctrl->ctrl.device, "Recreating %d I/O queues.\n",
+ opts->nr_io_queues);
+
+ nvme_fc_init_io_queues(ctrl);
+
+ ret = blk_mq_reinit_tagset(&ctrl->tag_set);
+ if (ret)
+ goto out_free_io_queues;
+
+ ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.opts->queue_size);
+ if (ret)
+ goto out_free_io_queues;
+
+ ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.opts->queue_size);
+ if (ret)
+ goto out_delete_hw_queues;
+
+ return 0;
+
+out_delete_hw_queues:
+ nvme_fc_delete_hw_io_queues(ctrl);
+out_free_io_queues:
+ nvme_fc_free_io_queues(ctrl);
+ return ret;
+}
+
+/*
+ * This routine restarts the controller on the host side, and
+ * on the link side, recreates the controller association.
+ */
+static int
+nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
+{
+ struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
+ u32 segs;
+ int ret;
+ bool changed;
+
+ ctrl->connect_attempts++;
+
+ /*
+ * Create the admin queue
+ */
+
+ nvme_fc_init_queue(ctrl, 0, NVME_FC_AQ_BLKMQ_DEPTH);
+
+ ret = __nvme_fc_create_hw_queue(ctrl, &ctrl->queues[0], 0,
NVME_FC_AQ_BLKMQ_DEPTH);
- if (error)
- goto out_cleanup_queue;
+ if (ret)
+ goto out_free_queue;
- error = nvmf_connect_admin_queue(&ctrl->ctrl);
- if (error)
+ ret = nvme_fc_connect_admin_queue(ctrl, &ctrl->queues[0],
+ NVME_FC_AQ_BLKMQ_DEPTH,
+ (NVME_FC_AQ_BLKMQ_DEPTH / 4));
+ if (ret)
goto out_delete_hw_queue;
- error = nvmf_reg_read64(&ctrl->ctrl, NVME_REG_CAP, &ctrl->cap);
- if (error) {
+ if (ctrl->ctrl.state != NVME_CTRL_NEW)
+ blk_mq_start_stopped_hw_queues(ctrl->ctrl.admin_q, true);
+
+ ret = nvmf_connect_admin_queue(&ctrl->ctrl);
+ if (ret)
+ goto out_disconnect_admin_queue;
+
+ /*
+ * Check controller capabilities
+ *
+ * todo:- add code to check if ctrl attributes changed from
+ * prior connection values
+ */
+
+ ret = nvmf_reg_read64(&ctrl->ctrl, NVME_REG_CAP, &ctrl->cap);
+ if (ret) {
dev_err(ctrl->ctrl.device,
"prop_get NVME_REG_CAP failed\n");
- goto out_delete_hw_queue;
+ goto out_disconnect_admin_queue;
}
ctrl->ctrl.sqsize =
min_t(int, NVME_CAP_MQES(ctrl->cap) + 1, ctrl->ctrl.sqsize);
- error = nvme_enable_ctrl(&ctrl->ctrl, ctrl->cap);
- if (error)
- goto out_delete_hw_queue;
+ ret = nvme_enable_ctrl(&ctrl->ctrl, ctrl->cap);
+ if (ret)
+ goto out_disconnect_admin_queue;
segs = min_t(u32, NVME_FC_MAX_SEGMENTS,
ctrl->lport->ops->max_sgl_segments);
ctrl->ctrl.max_hw_sectors = (segs - 1) << (PAGE_SHIFT - 9);
- error = nvme_init_identify(&ctrl->ctrl);
- if (error)
- goto out_delete_hw_queue;
+ ret = nvme_init_identify(&ctrl->ctrl);
+ if (ret)
+ goto out_disconnect_admin_queue;
+
+ /* sanity checks */
+
+ /* FC-NVME does not have other data in the capsule */
+ if (ctrl->ctrl.icdoff) {
+ dev_err(ctrl->ctrl.device, "icdoff %d is not supported!\n",
+ ctrl->ctrl.icdoff);
+ goto out_disconnect_admin_queue;
+ }
nvme_start_keep_alive(&ctrl->ctrl);
- return 0;
+ /* FC-NVME supports normal SGL Data Block Descriptors */
+
+ if (opts->queue_size > ctrl->ctrl.maxcmd) {
+ /* warn if maxcmd is lower than queue_size */
+ dev_warn(ctrl->ctrl.device,
+ "queue_size %zu > ctrl maxcmd %u, reducing "
+ "to queue_size\n",
+ opts->queue_size, ctrl->ctrl.maxcmd);
+ opts->queue_size = ctrl->ctrl.maxcmd;
+ }
+
+ ret = nvme_fc_init_aen_ops(ctrl);
+ if (ret)
+ goto out_term_aen_ops;
+
+ /*
+ * Create the io queues
+ */
+
+ if (ctrl->queue_count > 1) {
+ if (ctrl->ctrl.state == NVME_CTRL_NEW)
+ ret = nvme_fc_create_io_queues(ctrl);
+ else
+ ret = nvme_fc_reinit_io_queues(ctrl);
+ if (ret)
+ goto out_term_aen_ops;
+ }
+
+ changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
+ WARN_ON_ONCE(!changed);
+ ctrl->connect_attempts = 0;
+
+ kref_get(&ctrl->ctrl.kref);
+
+ if (ctrl->queue_count > 1) {
+ nvme_start_queues(&ctrl->ctrl);
+ nvme_queue_scan(&ctrl->ctrl);
+ nvme_queue_async_events(&ctrl->ctrl);
+ }
+
+ return 0; /* Success */
+
+out_term_aen_ops:
+ nvme_fc_term_aen_ops(ctrl);
+ nvme_stop_keep_alive(&ctrl->ctrl);
+out_disconnect_admin_queue:
+ /* send a Disconnect(association) LS to fc-nvme target */
+ nvme_fc_xmt_disconnect_assoc(ctrl);
out_delete_hw_queue:
__nvme_fc_delete_hw_queue(ctrl, &ctrl->queues[0], 0);
-out_cleanup_queue:
- blk_cleanup_queue(ctrl->ctrl.admin_q);
-out_free_tagset:
- blk_mq_free_tag_set(&ctrl->admin_tag_set);
out_free_queue:
nvme_fc_free_queue(&ctrl->queues[0]);
- return error;
+
+ return ret;
}
/*
- * This routine is used by the transport when it needs to find active
- * io on a queue that is to be terminated. The transport uses
- * blk_mq_tagset_busy_itr() to find the busy requests, which then invoke
- * this routine to kill them on a 1 by 1 basis.
- *
- * As FC allocates FC exchange for each io, the transport must contact
- * the LLDD to terminate the exchange, thus releasing the FC exchange.
- * After terminating the exchange the LLDD will call the transport's
- * normal io done path for the request, but it will have an aborted
- * status. The done path will return the io request back to the block
- * layer with an error status.
+ * This routine stops operation of the controller on the host side.
+ * On the host os stack side: Admin and IO queues are stopped,
+ * outstanding ios on them terminated via FC ABTS.
+ * On the link side: the association is terminated.
*/
static void
-nvme_fc_terminate_exchange(struct request *req, void *data, bool reserved)
+nvme_fc_delete_association(struct nvme_fc_ctrl *ctrl)
{
- struct nvme_ctrl *nctrl = data;
- struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
- struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(req);
-int status;
-
- if (!blk_mq_request_started(req))
- return;
+ unsigned long flags;
- /* this performs an ABTS-LS on the FC exchange for the io */
- status = __nvme_fc_abort_op(ctrl, op);
- /*
- * if __nvme_fc_abort_op failed: io wasn't active to abort
- * consider it done. Assume completion path already completing
- * in parallel
- */
- if (status)
- /* io wasn't active to abort consider it done */
- /* assume completion path already completing in parallel */
- return;
-}
+ nvme_stop_keep_alive(&ctrl->ctrl);
+ spin_lock_irqsave(&ctrl->lock, flags);
+ ctrl->flags |= FCCTRL_TERMIO;
+ ctrl->iocnt = 0;
+ spin_unlock_irqrestore(&ctrl->lock, flags);
-/*
- * This routine stops operation of the controller. Admin and IO queues
- * are stopped, outstanding ios on them terminated, and the nvme ctrl
- * is shutdown.
- */
-static void
-nvme_fc_shutdown_ctrl(struct nvme_fc_ctrl *ctrl)
-{
/*
* If io queues are present, stop them and terminate all outstanding
* ios on them. As FC allocates FC exchange for each io, the
nvme_fc_terminate_exchange, &ctrl->ctrl);
}
- if (ctrl->ctrl.state == NVME_CTRL_LIVE)
- nvme_shutdown_ctrl(&ctrl->ctrl);
+ /*
+ * Other transports, which don't have link-level contexts bound
+ * to sqe's, would try to gracefully shutdown the controller by
+ * writing the registers for shutdown and polling (call
+ * nvme_shutdown_ctrl()). Given a bunch of i/o was potentially
+ * just aborted and we will wait on those contexts, and given
+ * there was no indication of how live the controlelr is on the
+ * link, don't send more io to create more contexts for the
+ * shutdown. Let the controller fail via keepalive failure if
+ * its still present.
+ */
/*
- * now clean up the admin queue. Same thing as above.
+ * clean up the admin queue. Same thing as above.
* use blk_mq_tagset_busy_itr() and the transport routine to
* terminate the exchanges.
*/
blk_mq_stop_hw_queues(ctrl->ctrl.admin_q);
blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
nvme_fc_terminate_exchange, &ctrl->ctrl);
+
+ /* kill the aens as they are a separate path */
+ nvme_fc_abort_aen_ops(ctrl);
+
+ /* wait for all io that had to be aborted */
+ spin_lock_irqsave(&ctrl->lock, flags);
+ while (ctrl->iocnt) {
+ spin_unlock_irqrestore(&ctrl->lock, flags);
+ msleep(1000);
+ spin_lock_irqsave(&ctrl->lock, flags);
+ }
+ ctrl->flags &= ~FCCTRL_TERMIO;
+ spin_unlock_irqrestore(&ctrl->lock, flags);
+
+ nvme_fc_term_aen_ops(ctrl);
+
+ /*
+ * send a Disconnect(association) LS to fc-nvme target
+ * Note: could have been sent at top of process, but
+ * cleaner on link traffic if after the aborts complete.
+ * Note: if association doesn't exist, association_id will be 0
+ */
+ if (ctrl->association_id)
+ nvme_fc_xmt_disconnect_assoc(ctrl);
+
+ if (ctrl->ctrl.tagset) {
+ nvme_fc_delete_hw_io_queues(ctrl);
+ nvme_fc_free_io_queues(ctrl);
+ }
+
+ __nvme_fc_delete_hw_queue(ctrl, &ctrl->queues[0], 0);
+ nvme_fc_free_queue(&ctrl->queues[0]);
}
-/*
- * Called to teardown an association.
- * May be called with association fully in place or partially in place.
- */
static void
-__nvme_fc_remove_ctrl(struct nvme_fc_ctrl *ctrl)
+nvme_fc_delete_ctrl_work(struct work_struct *work)
{
- nvme_stop_keep_alive(&ctrl->ctrl);
+ struct nvme_fc_ctrl *ctrl =
+ container_of(work, struct nvme_fc_ctrl, delete_work);
- /* stop and terminate ios on admin and io queues */
- nvme_fc_shutdown_ctrl(ctrl);
+ cancel_work_sync(&ctrl->reset_work);
+ cancel_delayed_work_sync(&ctrl->connect_work);
+
+ /*
+ * kill the association on the link side. this will block
+ * waiting for io to terminate
+ */
+ nvme_fc_delete_association(ctrl);
/*
* tear down the controller
* This will result in the last reference on the nvme ctrl to
- * expire, calling the transport nvme_fc_free_nvme_ctrl() callback.
+ * expire, calling the transport nvme_fc_nvme_ctrl_freed() callback.
* From there, the transport will tear down it's logical queues and
* association.
*/
nvme_put_ctrl(&ctrl->ctrl);
}
-static void
-nvme_fc_del_ctrl_work(struct work_struct *work)
-{
- struct nvme_fc_ctrl *ctrl =
- container_of(work, struct nvme_fc_ctrl, delete_work);
-
- __nvme_fc_remove_ctrl(ctrl);
-}
-
static int
__nvme_fc_del_ctrl(struct nvme_fc_ctrl *ctrl)
{
nvme_fc_del_nvme_ctrl(struct nvme_ctrl *nctrl)
{
struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
- struct nvme_fc_rport *rport = ctrl->rport;
- unsigned long flags;
int ret;
- spin_lock_irqsave(&rport->lock, flags);
+ if (!kref_get_unless_zero(&ctrl->ctrl.kref))
+ return -EBUSY;
+
ret = __nvme_fc_del_ctrl(ctrl);
- spin_unlock_irqrestore(&rport->lock, flags);
- if (ret)
- return ret;
- flush_work(&ctrl->delete_work);
+ if (!ret)
+ flush_workqueue(nvme_fc_wq);
- return 0;
+ nvme_put_ctrl(&ctrl->ctrl);
+
+ return ret;
}
+static void
+nvme_fc_reset_ctrl_work(struct work_struct *work)
+{
+ struct nvme_fc_ctrl *ctrl =
+ container_of(work, struct nvme_fc_ctrl, reset_work);
+ int ret;
+
+ /* will block will waiting for io to terminate */
+ nvme_fc_delete_association(ctrl);
+
+ ret = nvme_fc_create_association(ctrl);
+ if (ret) {
+ dev_warn(ctrl->ctrl.device,
+ "NVME-FC{%d}: reset: Reconnect attempt failed (%d)\n",
+ ctrl->cnum, ret);
+ if (ctrl->connect_attempts >= NVME_FC_MAX_CONNECT_ATTEMPTS) {
+ dev_warn(ctrl->ctrl.device,
+ "NVME-FC{%d}: Max reconnect attempts (%d) "
+ "reached. Removing controller\n",
+ ctrl->cnum, ctrl->connect_attempts);
+
+ if (!nvme_change_ctrl_state(&ctrl->ctrl,
+ NVME_CTRL_DELETING)) {
+ dev_err(ctrl->ctrl.device,
+ "NVME-FC{%d}: failed to change state "
+ "to DELETING\n", ctrl->cnum);
+ return;
+ }
+
+ WARN_ON(!queue_work(nvme_fc_wq, &ctrl->delete_work));
+ return;
+ }
+
+ dev_warn(ctrl->ctrl.device,
+ "NVME-FC{%d}: Reconnect attempt in %d seconds.\n",
+ ctrl->cnum, ctrl->reconnect_delay);
+ queue_delayed_work(nvme_fc_wq, &ctrl->connect_work,
+ ctrl->reconnect_delay * HZ);
+ } else
+ dev_info(ctrl->ctrl.device,
+ "NVME-FC{%d}: controller reset complete\n", ctrl->cnum);
+}
+
+/*
+ * called by the nvme core layer, for sysfs interface that requests
+ * a reset of the nvme controller
+ */
static int
nvme_fc_reset_nvme_ctrl(struct nvme_ctrl *nctrl)
{
- return -EIO;
+ struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
+
+ dev_warn(ctrl->ctrl.device,
+ "NVME-FC{%d}: admin requested controller reset\n", ctrl->cnum);
+
+ if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING))
+ return -EBUSY;
+
+ if (!queue_work(nvme_fc_wq, &ctrl->reset_work))
+ return -EBUSY;
+
+ flush_work(&ctrl->reset_work);
+
+ return 0;
}
static const struct nvme_ctrl_ops nvme_fc_ctrl_ops = {
.reg_read64 = nvmf_reg_read64,
.reg_write32 = nvmf_reg_write32,
.reset_ctrl = nvme_fc_reset_nvme_ctrl,
- .free_ctrl = nvme_fc_free_nvme_ctrl,
+ .free_ctrl = nvme_fc_nvme_ctrl_freed,
.submit_async_event = nvme_fc_submit_async_event,
.delete_ctrl = nvme_fc_del_nvme_ctrl,
.get_subsysnqn = nvmf_get_subsysnqn,
.get_address = nvmf_get_address,
};
-static int
-nvme_fc_create_io_queues(struct nvme_fc_ctrl *ctrl)
+static void
+nvme_fc_connect_ctrl_work(struct work_struct *work)
{
- struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
int ret;
- ret = nvme_set_queue_count(&ctrl->ctrl, &opts->nr_io_queues);
- if (ret) {
- dev_info(ctrl->ctrl.device,
- "set_queue_count failed: %d\n", ret);
- return ret;
- }
-
- ctrl->queue_count = opts->nr_io_queues + 1;
- if (!opts->nr_io_queues)
- return 0;
-
- dev_info(ctrl->ctrl.device, "creating %d I/O queues.\n",
- opts->nr_io_queues);
-
- nvme_fc_init_io_queues(ctrl);
-
- memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set));
- ctrl->tag_set.ops = &nvme_fc_mq_ops;
- ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size;
- ctrl->tag_set.reserved_tags = 1; /* fabric connect */
- ctrl->tag_set.numa_node = NUMA_NO_NODE;
- ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
- ctrl->tag_set.cmd_size = sizeof(struct nvme_fc_fcp_op) +
- (SG_CHUNK_SIZE *
- sizeof(struct scatterlist)) +
- ctrl->lport->ops->fcprqst_priv_sz;
- ctrl->tag_set.driver_data = ctrl;
- ctrl->tag_set.nr_hw_queues = ctrl->queue_count - 1;
- ctrl->tag_set.timeout = NVME_IO_TIMEOUT;
-
- ret = blk_mq_alloc_tag_set(&ctrl->tag_set);
- if (ret)
- return ret;
-
- ctrl->ctrl.tagset = &ctrl->tag_set;
-
- ctrl->ctrl.connect_q = blk_mq_init_queue(&ctrl->tag_set);
- if (IS_ERR(ctrl->ctrl.connect_q)) {
- ret = PTR_ERR(ctrl->ctrl.connect_q);
- goto out_free_tag_set;
- }
-
- ret = nvme_fc_create_hw_io_queues(ctrl, ctrl->ctrl.opts->queue_size);
- if (ret)
- goto out_cleanup_blk_queue;
+ struct nvme_fc_ctrl *ctrl =
+ container_of(to_delayed_work(work),
+ struct nvme_fc_ctrl, connect_work);
- ret = nvme_fc_connect_io_queues(ctrl, ctrl->ctrl.opts->queue_size);
- if (ret)
- goto out_delete_hw_queues;
+ ret = nvme_fc_create_association(ctrl);
+ if (ret) {
+ dev_warn(ctrl->ctrl.device,
+ "NVME-FC{%d}: Reconnect attempt failed (%d)\n",
+ ctrl->cnum, ret);
+ if (ctrl->connect_attempts >= NVME_FC_MAX_CONNECT_ATTEMPTS) {
+ dev_warn(ctrl->ctrl.device,
+ "NVME-FC{%d}: Max reconnect attempts (%d) "
+ "reached. Removing controller\n",
+ ctrl->cnum, ctrl->connect_attempts);
+
+ if (!nvme_change_ctrl_state(&ctrl->ctrl,
+ NVME_CTRL_DELETING)) {
+ dev_err(ctrl->ctrl.device,
+ "NVME-FC{%d}: failed to change state "
+ "to DELETING\n", ctrl->cnum);
+ return;
+ }
- return 0;
+ WARN_ON(!queue_work(nvme_fc_wq, &ctrl->delete_work));
+ return;
+ }
-out_delete_hw_queues:
- nvme_fc_delete_hw_io_queues(ctrl);
-out_cleanup_blk_queue:
- nvme_stop_keep_alive(&ctrl->ctrl);
- blk_cleanup_queue(ctrl->ctrl.connect_q);
-out_free_tag_set:
- blk_mq_free_tag_set(&ctrl->tag_set);
- nvme_fc_free_io_queues(ctrl);
+ dev_warn(ctrl->ctrl.device,
+ "NVME-FC{%d}: Reconnect attempt in %d seconds.\n",
+ ctrl->cnum, ctrl->reconnect_delay);
+ queue_delayed_work(nvme_fc_wq, &ctrl->connect_work,
+ ctrl->reconnect_delay * HZ);
+ } else
+ dev_info(ctrl->ctrl.device,
+ "NVME-FC{%d}: controller reconnect complete\n",
+ ctrl->cnum);
+}
- /* force put free routine to ignore io queues */
- ctrl->ctrl.tagset = NULL;
- return ret;
-}
+static const struct blk_mq_ops nvme_fc_admin_mq_ops = {
+ .queue_rq = nvme_fc_queue_rq,
+ .complete = nvme_fc_complete_rq,
+ .init_request = nvme_fc_init_admin_request,
+ .exit_request = nvme_fc_exit_request,
+ .reinit_request = nvme_fc_reinit_request,
+ .init_hctx = nvme_fc_init_admin_hctx,
+ .timeout = nvme_fc_timeout,
+};
static struct nvme_ctrl *
-__nvme_fc_create_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
+nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
struct nvme_fc_lport *lport, struct nvme_fc_rport *rport)
{
struct nvme_fc_ctrl *ctrl;
unsigned long flags;
int ret, idx;
- bool changed;
ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL);
if (!ctrl) {
ctrl->ctrl.opts = opts;
INIT_LIST_HEAD(&ctrl->ctrl_list);
- INIT_LIST_HEAD(&ctrl->ls_req_list);
ctrl->lport = lport;
ctrl->rport = rport;
ctrl->dev = lport->dev;
- ctrl->state = FCCTRL_INIT;
ctrl->cnum = idx;
- ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_fc_ctrl_ops, 0);
- if (ret)
- goto out_free_ida;
-
get_device(ctrl->dev);
kref_init(&ctrl->ref);
- INIT_WORK(&ctrl->delete_work, nvme_fc_del_ctrl_work);
+ INIT_WORK(&ctrl->delete_work, nvme_fc_delete_ctrl_work);
+ INIT_WORK(&ctrl->reset_work, nvme_fc_reset_ctrl_work);
+ INIT_DELAYED_WORK(&ctrl->connect_work, nvme_fc_connect_ctrl_work);
+ ctrl->reconnect_delay = opts->reconnect_delay;
spin_lock_init(&ctrl->lock);
/* io queue count */
ctrl->queues = kcalloc(ctrl->queue_count, sizeof(struct nvme_fc_queue),
GFP_KERNEL);
if (!ctrl->queues)
- goto out_uninit_ctrl;
-
- ret = nvme_fc_configure_admin_queue(ctrl);
- if (ret)
- goto out_uninit_ctrl;
-
- /* sanity checks */
-
- /* FC-NVME does not have other data in the capsule */
- if (ctrl->ctrl.icdoff) {
- dev_err(ctrl->ctrl.device, "icdoff %d is not supported!\n",
- ctrl->ctrl.icdoff);
- goto out_remove_admin_queue;
- }
-
- /* FC-NVME supports normal SGL Data Block Descriptors */
+ goto out_free_ida;
- if (opts->queue_size > ctrl->ctrl.maxcmd) {
- /* warn if maxcmd is lower than queue_size */
- dev_warn(ctrl->ctrl.device,
- "queue_size %zu > ctrl maxcmd %u, reducing "
- "to queue_size\n",
- opts->queue_size, ctrl->ctrl.maxcmd);
- opts->queue_size = ctrl->ctrl.maxcmd;
- }
+ memset(&ctrl->admin_tag_set, 0, sizeof(ctrl->admin_tag_set));
+ ctrl->admin_tag_set.ops = &nvme_fc_admin_mq_ops;
+ ctrl->admin_tag_set.queue_depth = NVME_FC_AQ_BLKMQ_DEPTH;
+ ctrl->admin_tag_set.reserved_tags = 2; /* fabric connect + Keep-Alive */
+ ctrl->admin_tag_set.numa_node = NUMA_NO_NODE;
+ ctrl->admin_tag_set.cmd_size = sizeof(struct nvme_fc_fcp_op) +
+ (SG_CHUNK_SIZE *
+ sizeof(struct scatterlist)) +
+ ctrl->lport->ops->fcprqst_priv_sz;
+ ctrl->admin_tag_set.driver_data = ctrl;
+ ctrl->admin_tag_set.nr_hw_queues = 1;
+ ctrl->admin_tag_set.timeout = ADMIN_TIMEOUT;
- ret = nvme_fc_init_aen_ops(ctrl);
+ ret = blk_mq_alloc_tag_set(&ctrl->admin_tag_set);
if (ret)
- goto out_exit_aen_ops;
+ goto out_free_queues;
- if (ctrl->queue_count > 1) {
- ret = nvme_fc_create_io_queues(ctrl);
- if (ret)
- goto out_exit_aen_ops;
+ ctrl->ctrl.admin_q = blk_mq_init_queue(&ctrl->admin_tag_set);
+ if (IS_ERR(ctrl->ctrl.admin_q)) {
+ ret = PTR_ERR(ctrl->ctrl.admin_q);
+ goto out_free_admin_tag_set;
}
- spin_lock_irqsave(&ctrl->lock, flags);
- ctrl->state = FCCTRL_ACTIVE;
- spin_unlock_irqrestore(&ctrl->lock, flags);
-
- changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
- WARN_ON_ONCE(!changed);
+ /*
+ * Would have been nice to init io queues tag set as well.
+ * However, we require interaction from the controller
+ * for max io queue count before we can do so.
+ * Defer this to the connect path.
+ */
- dev_info(ctrl->ctrl.device,
- "NVME-FC{%d}: new ctrl: NQN \"%s\"\n",
- ctrl->cnum, ctrl->ctrl.opts->subsysnqn);
+ ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_fc_ctrl_ops, 0);
+ if (ret)
+ goto out_cleanup_admin_q;
- kref_get(&ctrl->ctrl.kref);
+ /* at this point, teardown path changes to ref counting on nvme ctrl */
spin_lock_irqsave(&rport->lock, flags);
list_add_tail(&ctrl->ctrl_list, &rport->ctrl_list);
spin_unlock_irqrestore(&rport->lock, flags);
- if (opts->nr_io_queues) {
- nvme_queue_scan(&ctrl->ctrl);
- nvme_queue_async_events(&ctrl->ctrl);
+ ret = nvme_fc_create_association(ctrl);
+ if (ret) {
+ ctrl->ctrl.opts = NULL;
+ /* initiate nvme ctrl ref counting teardown */
+ nvme_uninit_ctrl(&ctrl->ctrl);
+ nvme_put_ctrl(&ctrl->ctrl);
+
+ /* as we're past the point where we transition to the ref
+ * counting teardown path, if we return a bad pointer here,
+ * the calling routine, thinking it's prior to the
+ * transition, will do an rport put. Since the teardown
+ * path also does a rport put, we do an extra get here to
+ * so proper order/teardown happens.
+ */
+ nvme_fc_rport_get(rport);
+
+ if (ret > 0)
+ ret = -EIO;
+ return ERR_PTR(ret);
}
- return &ctrl->ctrl;
+ dev_info(ctrl->ctrl.device,
+ "NVME-FC{%d}: new ctrl: NQN \"%s\"\n",
+ ctrl->cnum, ctrl->ctrl.opts->subsysnqn);
-out_exit_aen_ops:
- nvme_fc_exit_aen_ops(ctrl);
-out_remove_admin_queue:
- /* send a Disconnect(association) LS to fc-nvme target */
- nvme_fc_xmt_disconnect_assoc(ctrl);
- nvme_stop_keep_alive(&ctrl->ctrl);
- nvme_fc_destroy_admin_queue(ctrl);
-out_uninit_ctrl:
- nvme_uninit_ctrl(&ctrl->ctrl);
- nvme_put_ctrl(&ctrl->ctrl);
- if (ret > 0)
- ret = -EIO;
- /* exit via here will follow ctlr ref point callbacks to free */
- return ERR_PTR(ret);
+ return &ctrl->ctrl;
+out_cleanup_admin_q:
+ blk_cleanup_queue(ctrl->ctrl.admin_q);
+out_free_admin_tag_set:
+ blk_mq_free_tag_set(&ctrl->admin_tag_set);
+out_free_queues:
+ kfree(ctrl->queues);
out_free_ida:
+ put_device(ctrl->dev);
ida_simple_remove(&nvme_fc_ctrl_cnt, ctrl->cnum);
out_free_ctrl:
kfree(ctrl);
out_fail:
- nvme_fc_rport_put(rport);
/* exit via here doesn't follow ctlr ref points */
return ERR_PTR(ret);
}
{
struct nvme_fc_lport *lport;
struct nvme_fc_rport *rport;
+ struct nvme_ctrl *ctrl;
struct nvmet_fc_traddr laddr = { 0L, 0L };
struct nvmet_fc_traddr raddr = { 0L, 0L };
unsigned long flags;
spin_unlock_irqrestore(&nvme_fc_lock, flags);
- return __nvme_fc_create_ctrl(dev, opts, lport, rport);
+ ctrl = nvme_fc_init_ctrl(dev, opts, lport, rport);
+ if (IS_ERR(ctrl))
+ nvme_fc_rport_put(rport);
+ return ctrl;
}
}
spin_unlock_irqrestore(&nvme_fc_lock, flags);
static int __init nvme_fc_init_module(void)
{
+ int ret;
+
nvme_fc_wq = create_workqueue("nvme_fc_wq");
if (!nvme_fc_wq)
return -ENOMEM;
- return nvmf_register_transport(&nvme_fc_transport);
+ ret = nvmf_register_transport(&nvme_fc_transport);
+ if (ret)
+ goto err;
+
+ return 0;
+err:
+ destroy_workqueue(nvme_fc_wq);
+ return ret;
}
static void __exit nvme_fc_exit_module(void)
BUILD_BUG_ON(sizeof(struct nvme_nvm_l2ptbl) != 64);
BUILD_BUG_ON(sizeof(struct nvme_nvm_erase_blk) != 64);
BUILD_BUG_ON(sizeof(struct nvme_nvm_id_group) != 960);
- BUILD_BUG_ON(sizeof(struct nvme_nvm_addr_format) != 128);
+ BUILD_BUG_ON(sizeof(struct nvme_nvm_addr_format) != 16);
BUILD_BUG_ON(sizeof(struct nvme_nvm_id) != 4096);
- BUILD_BUG_ON(sizeof(struct nvme_nvm_bb_tbl) != 512);
+ BUILD_BUG_ON(sizeof(struct nvme_nvm_bb_tbl) != 64);
}
static int init_grps(struct nvm_id *nvm_id, struct nvme_nvm_id *nvme_nvm_id)
nvm_id->cap = le32_to_cpu(nvme_nvm_id->cap);
nvm_id->dom = le32_to_cpu(nvme_nvm_id->dom);
memcpy(&nvm_id->ppaf, &nvme_nvm_id->ppaf,
- sizeof(struct nvme_nvm_addr_format));
+ sizeof(struct nvm_addr_format));
ret = init_grps(nvm_id, nvme_nvm_id);
out:
{
struct nvm_rq *rqd = rq->end_io_data;
- rqd->ppa_status = nvme_req(rq)->result.u64;
- rqd->error = error;
+ rqd->ppa_status = le64_to_cpu(nvme_req(rq)->result.u64);
+ rqd->error = nvme_req(rq)->status;
nvm_end_io(rqd);
kfree(nvme_req(rq)->cmd);
}
rq->cmd_flags &= ~REQ_FAILFAST_DRIVER;
- rq->ioprio = bio_prio(bio);
- if (bio_has_data(bio))
- rq->nr_phys_segments = bio_phys_segments(q, bio);
-
- rq->__data_len = bio->bi_iter.bi_size;
- rq->bio = rq->biotail = bio;
+ if (bio) {
+ blk_init_request_from_bio(rq, bio);
+ } else {
+ rq->ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
+ rq->__data_len = 0;
+ }
nvme_nvm_rqtocmd(rq, rqd, ns, cmd);
return 0;
}
-static int nvme_nvm_erase_block(struct nvm_dev *dev, struct nvm_rq *rqd)
-{
- struct request_queue *q = dev->q;
- struct nvme_ns *ns = q->queuedata;
- struct nvme_nvm_command c = {};
-
- c.erase.opcode = NVM_OP_ERASE;
- c.erase.nsid = cpu_to_le32(ns->ns_id);
- c.erase.spba = cpu_to_le64(rqd->ppa_addr.ppa);
- c.erase.length = cpu_to_le16(rqd->nr_ppas - 1);
- c.erase.control = cpu_to_le16(rqd->flags);
-
- return nvme_submit_sync_cmd(q, (struct nvme_command *)&c, NULL, 0);
-}
-
static void *nvme_nvm_create_dma_pool(struct nvm_dev *nvmdev, char *name)
{
struct nvme_ns *ns = nvmdev->q->queuedata;
.set_bb_tbl = nvme_nvm_set_bb_tbl,
.submit_io = nvme_nvm_submit_io,
- .erase_block = nvme_nvm_erase_block,
.create_dma_pool = nvme_nvm_create_dma_pool,
.destroy_dma_pool = nvme_nvm_destroy_dma_pool,
__le64 *metadata = NULL;
dma_addr_t metadata_dma;
DECLARE_COMPLETION_ONSTACK(wait);
- int ret;
+ int ret = 0;
rq = nvme_alloc_request(q, (struct nvme_command *)vcmd, 0,
NVME_QID_ANY);
wait_for_completion_io(&wait);
- ret = nvme_error_status(rq->errors);
+ if (nvme_req(rq)->flags & NVME_REQ_CANCELLED)
+ ret = -EINTR;
+ else if (nvme_req(rq)->status & 0x7ff)
+ ret = -EIO;
if (result)
- *result = rq->errors & 0x7ff;
+ *result = nvme_req(rq)->status & 0x7ff;
if (status)
*status = le64_to_cpu(nvme_req(rq)->result.u64);
c.common.cdw2[1] = cpu_to_le32(vcmd.cdw3);
/* cdw11-12 */
c.ph_rw.length = cpu_to_le16(vcmd.nppas);
- c.ph_rw.control = cpu_to_le32(vcmd.control);
+ c.ph_rw.control = cpu_to_le16(vcmd.control);
c.common.cdw10[3] = cpu_to_le32(vcmd.cdw13);
c.common.cdw10[4] = cpu_to_le32(vcmd.cdw14);
c.common.cdw10[5] = cpu_to_le32(vcmd.cdw15);
struct request_queue *q = ns->queue;
struct nvm_dev *dev;
+ _nvme_nvm_check_size();
+
dev = nvm_alloc_dev(node);
if (!dev)
return -ENOMEM;
#include <linux/lightnvm.h>
#include <linux/sed-opal.h>
-enum {
- /*
- * Driver internal status code for commands that were cancelled due
- * to timeouts or controller shutdown. The value is negative so
- * that it a) doesn't overlap with the unsigned hardware error codes,
- * and b) can easily be tested for.
- */
- NVME_SC_CANCELLED = -EINTR,
-};
-
extern unsigned char nvme_io_timeout;
#define NVME_IO_TIMEOUT (nvme_io_timeout * HZ)
#define NVME_DEFAULT_KATO 5
#define NVME_KATO_GRACE 10
-extern unsigned int nvme_max_retries;
-
enum {
NVME_NS_LBA = 0,
NVME_NS_LIGHTNVM = 1,
NVME_QUIRK_IDENTIFY_CNS = (1 << 1),
/*
- * The controller deterministically returns O's on reads to discarded
- * logical blocks.
+ * The controller deterministically returns O's on reads to
+ * logical blocks that deallocate was called on.
*/
- NVME_QUIRK_DISCARD_ZEROES = (1 << 2),
+ NVME_QUIRK_DEALLOCATE_ZEROES = (1 << 2),
/*
* The controller needs a delay before starts checking the device
* APST should not be used.
*/
NVME_QUIRK_NO_APST = (1 << 4),
+
+ /*
+ * The deepest sleep state should not be used.
+ */
+ NVME_QUIRK_NO_DEEPEST_PS = (1 << 5),
};
/*
struct nvme_request {
struct nvme_command *cmd;
union nvme_result result;
+ u8 retries;
+ u8 flags;
+ u16 status;
+};
+
+enum {
+ NVME_REQ_CANCELLED = (1 << 0),
};
static inline struct nvme_request *nvme_req(struct request *req)
}
}
-static inline int nvme_error_status(u16 status)
+static inline void nvme_end_request(struct request *req, __le16 status,
+ union nvme_result result)
{
- switch (status & 0x7ff) {
- case NVME_SC_SUCCESS:
- return 0;
- case NVME_SC_CAP_EXCEEDED:
- return -ENOSPC;
- default:
- return -EIO;
- }
-}
+ struct nvme_request *rq = nvme_req(req);
-static inline bool nvme_req_needs_retry(struct request *req, u16 status)
-{
- return !(status & NVME_SC_DNR || blk_noretry_request(req)) &&
- (jiffies - req->start_time) < req->timeout &&
- req->retries < nvme_max_retries;
+ rq->status = le16_to_cpu(status) >> 1;
+ rq->result = result;
+ blk_mq_complete_request(req);
}
+void nvme_complete_rq(struct request *req);
void nvme_cancel_request(struct request *req, void *data, bool reserved);
bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
enum nvme_ctrl_state new_state);
#define NVME_QID_ANY -1
struct request *nvme_alloc_request(struct request_queue *q,
struct nvme_command *cmd, unsigned int flags, int qid);
-void nvme_requeue_req(struct request *req);
int nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
struct nvme_command *cmd);
int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
#include <linux/blk-mq-pci.h>
#include <linux/cpu.h>
#include <linux/delay.h>
+#include <linux/dmi.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/genhd.h>
u32 cmbloc;
struct nvme_ctrl ctrl;
struct completion ioq_wait;
+ u32 *dbbuf_dbs;
+ dma_addr_t dbbuf_dbs_dma_addr;
+ u32 *dbbuf_eis;
+ dma_addr_t dbbuf_eis_dma_addr;
};
+static inline unsigned int sq_idx(unsigned int qid, u32 stride)
+{
+ return qid * 2 * stride;
+}
+
+static inline unsigned int cq_idx(unsigned int qid, u32 stride)
+{
+ return (qid * 2 + 1) * stride;
+}
+
static inline struct nvme_dev *to_nvme_dev(struct nvme_ctrl *ctrl)
{
return container_of(ctrl, struct nvme_dev, ctrl);
u16 qid;
u8 cq_phase;
u8 cqe_seen;
+ u32 *dbbuf_sq_db;
+ u32 *dbbuf_cq_db;
+ u32 *dbbuf_sq_ei;
+ u32 *dbbuf_cq_ei;
};
/*
BUILD_BUG_ON(sizeof(struct nvme_id_ns) != 4096);
BUILD_BUG_ON(sizeof(struct nvme_lba_range_type) != 64);
BUILD_BUG_ON(sizeof(struct nvme_smart_log) != 512);
+ BUILD_BUG_ON(sizeof(struct nvme_dbbuf) != 64);
+}
+
+static inline unsigned int nvme_dbbuf_size(u32 stride)
+{
+ return ((num_possible_cpus() + 1) * 8 * stride);
+}
+
+static int nvme_dbbuf_dma_alloc(struct nvme_dev *dev)
+{
+ unsigned int mem_size = nvme_dbbuf_size(dev->db_stride);
+
+ if (dev->dbbuf_dbs)
+ return 0;
+
+ dev->dbbuf_dbs = dma_alloc_coherent(dev->dev, mem_size,
+ &dev->dbbuf_dbs_dma_addr,
+ GFP_KERNEL);
+ if (!dev->dbbuf_dbs)
+ return -ENOMEM;
+ dev->dbbuf_eis = dma_alloc_coherent(dev->dev, mem_size,
+ &dev->dbbuf_eis_dma_addr,
+ GFP_KERNEL);
+ if (!dev->dbbuf_eis) {
+ dma_free_coherent(dev->dev, mem_size,
+ dev->dbbuf_dbs, dev->dbbuf_dbs_dma_addr);
+ dev->dbbuf_dbs = NULL;
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static void nvme_dbbuf_dma_free(struct nvme_dev *dev)
+{
+ unsigned int mem_size = nvme_dbbuf_size(dev->db_stride);
+
+ if (dev->dbbuf_dbs) {
+ dma_free_coherent(dev->dev, mem_size,
+ dev->dbbuf_dbs, dev->dbbuf_dbs_dma_addr);
+ dev->dbbuf_dbs = NULL;
+ }
+ if (dev->dbbuf_eis) {
+ dma_free_coherent(dev->dev, mem_size,
+ dev->dbbuf_eis, dev->dbbuf_eis_dma_addr);
+ dev->dbbuf_eis = NULL;
+ }
+}
+
+static void nvme_dbbuf_init(struct nvme_dev *dev,
+ struct nvme_queue *nvmeq, int qid)
+{
+ if (!dev->dbbuf_dbs || !qid)
+ return;
+
+ nvmeq->dbbuf_sq_db = &dev->dbbuf_dbs[sq_idx(qid, dev->db_stride)];
+ nvmeq->dbbuf_cq_db = &dev->dbbuf_dbs[cq_idx(qid, dev->db_stride)];
+ nvmeq->dbbuf_sq_ei = &dev->dbbuf_eis[sq_idx(qid, dev->db_stride)];
+ nvmeq->dbbuf_cq_ei = &dev->dbbuf_eis[cq_idx(qid, dev->db_stride)];
+}
+
+static void nvme_dbbuf_set(struct nvme_dev *dev)
+{
+ struct nvme_command c;
+
+ if (!dev->dbbuf_dbs)
+ return;
+
+ memset(&c, 0, sizeof(c));
+ c.dbbuf.opcode = nvme_admin_dbbuf;
+ c.dbbuf.prp1 = cpu_to_le64(dev->dbbuf_dbs_dma_addr);
+ c.dbbuf.prp2 = cpu_to_le64(dev->dbbuf_eis_dma_addr);
+
+ if (nvme_submit_sync_cmd(dev->ctrl.admin_q, &c, NULL, 0)) {
+ dev_warn(dev->dev, "unable to set dbbuf\n");
+ /* Free memory and continue on */
+ nvme_dbbuf_dma_free(dev);
+ }
+}
+
+static inline int nvme_dbbuf_need_event(u16 event_idx, u16 new_idx, u16 old)
+{
+ return (u16)(new_idx - event_idx - 1) < (u16)(new_idx - old);
+}
+
+/* Update dbbuf and return true if an MMIO is required */
+static bool nvme_dbbuf_update_and_check_event(u16 value, u32 *dbbuf_db,
+ volatile u32 *dbbuf_ei)
+{
+ if (dbbuf_db) {
+ u16 old_value;
+
+ /*
+ * Ensure that the queue is written before updating
+ * the doorbell in memory
+ */
+ wmb();
+
+ old_value = *dbbuf_db;
+ *dbbuf_db = value;
+
+ if (!nvme_dbbuf_need_event(*dbbuf_ei, value, old_value))
+ return false;
+ }
+
+ return true;
}
/*
if (++tail == nvmeq->q_depth)
tail = 0;
- writel(tail, nvmeq->q_db);
+ if (nvme_dbbuf_update_and_check_event(tail, nvmeq->dbbuf_sq_db,
+ nvmeq->dbbuf_sq_ei))
+ writel(tail, nvmeq->q_db);
nvmeq->sq_tail = tail;
}
iod->nents = 0;
iod->length = size;
- if (!(rq->rq_flags & RQF_DONTPREP)) {
- rq->retries = 0;
- rq->rq_flags |= RQF_DONTPREP;
- }
return BLK_MQ_RQ_QUEUE_OK;
}
return ret;
}
-static void nvme_complete_rq(struct request *req)
+static void nvme_pci_complete_rq(struct request *req)
{
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
- struct nvme_dev *dev = iod->nvmeq->dev;
- int error = 0;
-
- nvme_unmap_data(dev, req);
- if (unlikely(req->errors)) {
- if (nvme_req_needs_retry(req, req->errors)) {
- req->retries++;
- nvme_requeue_req(req);
- return;
- }
-
- if (blk_rq_is_passthrough(req))
- error = req->errors;
- else
- error = nvme_error_status(req->errors);
- }
-
- if (unlikely(iod->aborted)) {
- dev_warn(dev->ctrl.device,
- "completing aborted command with status: %04x\n",
- req->errors);
- }
-
- blk_mq_end_request(req, error);
+ nvme_unmap_data(iod->nvmeq->dev, req);
+ nvme_complete_rq(req);
}
/* We read the CQE phase first to check if the rest of the entry is valid */
}
req = blk_mq_tag_to_rq(*nvmeq->tags, cqe.command_id);
- nvme_req(req)->result = cqe.result;
- blk_mq_complete_request(req, le16_to_cpu(cqe.status) >> 1);
+ nvme_end_request(req, cqe.status, cqe.result);
}
if (head == nvmeq->cq_head && phase == nvmeq->cq_phase)
return;
if (likely(nvmeq->cq_vector >= 0))
- writel(head, nvmeq->q_db + nvmeq->dev->db_stride);
+ if (nvme_dbbuf_update_and_check_event(head, nvmeq->dbbuf_cq_db,
+ nvmeq->dbbuf_cq_ei))
+ writel(head, nvmeq->q_db + nvmeq->dev->db_stride);
nvmeq->cq_head = head;
nvmeq->cq_phase = phase;
return IRQ_NONE;
}
-static int nvme_poll(struct blk_mq_hw_ctx *hctx, unsigned int tag)
+static int __nvme_poll(struct nvme_queue *nvmeq, unsigned int tag)
{
- struct nvme_queue *nvmeq = hctx->driver_data;
-
if (nvme_cqe_valid(nvmeq, nvmeq->cq_head, nvmeq->cq_phase)) {
spin_lock_irq(&nvmeq->q_lock);
__nvme_process_cq(nvmeq, &tag);
return 0;
}
+static int nvme_poll(struct blk_mq_hw_ctx *hctx, unsigned int tag)
+{
+ struct nvme_queue *nvmeq = hctx->driver_data;
+
+ return __nvme_poll(nvmeq, tag);
+}
+
static void nvme_pci_submit_async_event(struct nvme_ctrl *ctrl, int aer_idx)
{
struct nvme_dev *dev = to_nvme_dev(ctrl);
struct nvme_queue *nvmeq)
{
struct nvme_command c;
- int flags = NVME_QUEUE_PHYS_CONTIG | NVME_SQ_PRIO_MEDIUM;
+ int flags = NVME_QUEUE_PHYS_CONTIG;
/*
* Note: we (ab)use the fact the the prp fields survive if no data
{
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
struct nvme_queue *nvmeq = iod->nvmeq;
- u16 status = req->errors;
- dev_warn(nvmeq->dev->ctrl.device, "Abort status: 0x%x", status);
+ dev_warn(nvmeq->dev->ctrl.device,
+ "Abort status: 0x%x", nvme_req(req)->status);
atomic_inc(&nvmeq->dev->ctrl.abort_limit);
blk_mq_free_request(req);
}
struct nvme_command cmd;
/*
+ * Did we miss an interrupt?
+ */
+ if (__nvme_poll(nvmeq, req->tag)) {
+ dev_warn(dev->ctrl.device,
+ "I/O %d QID %d timeout, completion polled\n",
+ req->tag, nvmeq->qid);
+ return BLK_EH_HANDLED;
+ }
+
+ /*
* Shutdown immediately if controller times out while starting. The
* reset work will see the pci device disabled when it gets the forced
* cancellation error. All outstanding requests are completed on
"I/O %d QID %d timeout, disable controller\n",
req->tag, nvmeq->qid);
nvme_dev_disable(dev, false);
- req->errors = NVME_SC_CANCELLED;
+ nvme_req(req)->flags |= NVME_REQ_CANCELLED;
return BLK_EH_HANDLED;
}
* Mark the request as handled, since the inline shutdown
* forces all outstanding requests to complete.
*/
- req->errors = NVME_SC_CANCELLED;
+ nvme_req(req)->flags |= NVME_REQ_CANCELLED;
return BLK_EH_HANDLED;
}
nvmeq->cq_phase = 1;
nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
memset((void *)nvmeq->cqes, 0, CQ_SIZE(nvmeq->q_depth));
+ nvme_dbbuf_init(dev, nvmeq, qid);
dev->online_queues++;
spin_unlock_irq(&nvmeq->q_lock);
}
return result;
}
-static struct blk_mq_ops nvme_mq_admin_ops = {
+static const struct blk_mq_ops nvme_mq_admin_ops = {
.queue_rq = nvme_queue_rq,
- .complete = nvme_complete_rq,
+ .complete = nvme_pci_complete_rq,
.init_hctx = nvme_admin_init_hctx,
.exit_hctx = nvme_admin_exit_hctx,
.init_request = nvme_admin_init_request,
.timeout = nvme_timeout,
};
-static struct blk_mq_ops nvme_mq_ops = {
+static const struct blk_mq_ops nvme_mq_ops = {
.queue_rq = nvme_queue_rq,
- .complete = nvme_complete_rq,
+ .complete = nvme_pci_complete_rq,
.init_hctx = nvme_init_hctx,
.init_request = nvme_init_request,
.map_queues = nvme_pci_map_queues,
if (blk_mq_alloc_tag_set(&dev->tagset))
return 0;
dev->ctrl.tagset = &dev->tagset;
+
+ nvme_dbbuf_set(dev);
} else {
blk_mq_update_nr_hw_queues(&dev->tagset, dev->online_queues - 1);
{
struct nvme_dev *dev = to_nvme_dev(ctrl);
+ nvme_dbbuf_dma_free(dev);
put_device(dev->dev);
if (dev->tagset.tags)
blk_mq_free_tag_set(&dev->tagset);
dev->ctrl.opal_dev = NULL;
}
+ if (dev->ctrl.oacs & NVME_CTRL_OACS_DBBUF_SUPP) {
+ result = nvme_dbbuf_dma_alloc(dev);
+ if (result)
+ dev_warn(dev->dev,
+ "unable to allocate dma for dbbuf\n");
+ }
+
result = nvme_setup_io_queues(dev);
if (result)
goto out;
return -ENODEV;
}
+static unsigned long check_dell_samsung_bug(struct pci_dev *pdev)
+{
+ if (pdev->vendor == 0x144d && pdev->device == 0xa802) {
+ /*
+ * Several Samsung devices seem to drop off the PCIe bus
+ * randomly when APST is on and uses the deepest sleep state.
+ * This has been observed on a Samsung "SM951 NVMe SAMSUNG
+ * 256GB", a "PM951 NVMe SAMSUNG 512GB", and a "Samsung SSD
+ * 950 PRO 256GB", but it seems to be restricted to two Dell
+ * laptops.
+ */
+ if (dmi_match(DMI_SYS_VENDOR, "Dell Inc.") &&
+ (dmi_match(DMI_PRODUCT_NAME, "XPS 15 9550") ||
+ dmi_match(DMI_PRODUCT_NAME, "Precision 5510")))
+ return NVME_QUIRK_NO_DEEPEST_PS;
+ }
+
+ return 0;
+}
+
static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
int node, result = -ENOMEM;
struct nvme_dev *dev;
+ unsigned long quirks = id->driver_data;
node = dev_to_node(&pdev->dev);
if (node == NUMA_NO_NODE)
if (result)
goto put_pci;
+ quirks |= check_dell_samsung_bug(pdev);
+
result = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops,
- id->driver_data);
+ quirks);
if (result)
goto release_pools;
static const struct pci_device_id nvme_id_table[] = {
{ PCI_VDEVICE(INTEL, 0x0953),
.driver_data = NVME_QUIRK_STRIPE_SIZE |
- NVME_QUIRK_DISCARD_ZEROES, },
+ NVME_QUIRK_DEALLOCATE_ZEROES, },
{ PCI_VDEVICE(INTEL, 0x0a53),
.driver_data = NVME_QUIRK_STRIPE_SIZE |
- NVME_QUIRK_DISCARD_ZEROES, },
+ NVME_QUIRK_DEALLOCATE_ZEROES, },
{ PCI_VDEVICE(INTEL, 0x0a54),
.driver_data = NVME_QUIRK_STRIPE_SIZE |
- NVME_QUIRK_DISCARD_ZEROES, },
+ NVME_QUIRK_DEALLOCATE_ZEROES, },
{ PCI_VDEVICE(INTEL, 0x5845), /* Qemu emulated controller */
.driver_data = NVME_QUIRK_IDENTIFY_CNS, },
{ PCI_DEVICE(0x1c58, 0x0003), /* HGST adapter */
#include "fabrics.h"
-#define NVME_RDMA_CONNECT_TIMEOUT_MS 1000 /* 1 second */
+#define NVME_RDMA_CONNECT_TIMEOUT_MS 3000 /* 3 second */
#define NVME_RDMA_MAX_SEGMENT_SIZE 0xffffff /* 24-bit SGL field */
struct nvme_rdma_qe async_event_sqe;
- int reconnect_delay;
struct delayed_work reconnect_work;
struct list_head list;
u64 cap;
u32 max_fr_pages;
- union {
- struct sockaddr addr;
- struct sockaddr_in addr_in;
- };
- union {
- struct sockaddr src_addr;
- struct sockaddr_in src_addr_in;
- };
+ struct sockaddr_storage addr;
+ struct sockaddr_storage src_addr;
struct nvme_ctrl ctrl;
};
return PTR_ERR(queue->cm_id);
}
- queue->cm_error = -ETIMEDOUT;
if (ctrl->ctrl.opts->mask & NVMF_OPT_HOST_TRADDR)
- src_addr = &ctrl->src_addr;
+ src_addr = (struct sockaddr *)&ctrl->src_addr;
- ret = rdma_resolve_addr(queue->cm_id, src_addr, &ctrl->addr,
+ queue->cm_error = -ETIMEDOUT;
+ ret = rdma_resolve_addr(queue->cm_id, src_addr,
+ (struct sockaddr *)&ctrl->addr,
NVME_RDMA_CONNECT_TIMEOUT_MS);
if (ret) {
dev_info(ctrl->ctrl.device,
kfree(ctrl);
}
+static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl)
+{
+ /* If we are resetting/deleting then do nothing */
+ if (ctrl->ctrl.state != NVME_CTRL_RECONNECTING) {
+ WARN_ON_ONCE(ctrl->ctrl.state == NVME_CTRL_NEW ||
+ ctrl->ctrl.state == NVME_CTRL_LIVE);
+ return;
+ }
+
+ if (nvmf_should_reconnect(&ctrl->ctrl)) {
+ dev_info(ctrl->ctrl.device, "Reconnecting in %d seconds...\n",
+ ctrl->ctrl.opts->reconnect_delay);
+ queue_delayed_work(nvme_rdma_wq, &ctrl->reconnect_work,
+ ctrl->ctrl.opts->reconnect_delay * HZ);
+ } else {
+ dev_info(ctrl->ctrl.device, "Removing controller...\n");
+ queue_work(nvme_rdma_wq, &ctrl->delete_work);
+ }
+}
+
static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
{
struct nvme_rdma_ctrl *ctrl = container_of(to_delayed_work(work),
bool changed;
int ret;
+ ++ctrl->ctrl.opts->nr_reconnects;
+
if (ctrl->queue_count > 1) {
nvme_rdma_free_io_queues(ctrl);
changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
WARN_ON_ONCE(!changed);
+ ctrl->ctrl.opts->nr_reconnects = 0;
if (ctrl->queue_count > 1) {
nvme_start_queues(&ctrl->ctrl);
stop_admin_q:
blk_mq_stop_hw_queues(ctrl->ctrl.admin_q);
requeue:
- /* Make sure we are not resetting/deleting */
- if (ctrl->ctrl.state == NVME_CTRL_RECONNECTING) {
- dev_info(ctrl->ctrl.device,
- "Failed reconnect attempt, requeueing...\n");
- queue_delayed_work(nvme_rdma_wq, &ctrl->reconnect_work,
- ctrl->reconnect_delay * HZ);
- }
+ dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d\n",
+ ctrl->ctrl.opts->nr_reconnects);
+ nvme_rdma_reconnect_or_remove(ctrl);
}
static void nvme_rdma_error_recovery_work(struct work_struct *work)
blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
nvme_cancel_request, &ctrl->ctrl);
- dev_info(ctrl->ctrl.device, "reconnecting in %d seconds\n",
- ctrl->reconnect_delay);
-
- queue_delayed_work(nvme_rdma_wq, &ctrl->reconnect_work,
- ctrl->reconnect_delay * HZ);
+ nvme_rdma_reconnect_or_remove(ctrl);
}
static void nvme_rdma_error_recovery(struct nvme_rdma_ctrl *ctrl)
wc->ex.invalidate_rkey == req->mr->rkey)
req->mr->need_inval = false;
- req->req.result = cqe->result;
- blk_mq_complete_request(rq, le16_to_cpu(cqe->status) >> 1);
+ nvme_end_request(rq, cqe->status, cqe->result);
return ret;
}
nvme_rdma_error_recovery(req->queue->ctrl);
/* fail with DNR on cmd timeout */
- rq->errors = NVME_SC_ABORT_REQ | NVME_SC_DNR;
+ nvme_req(rq)->status = NVME_SC_ABORT_REQ | NVME_SC_DNR;
return BLK_EH_HANDLED;
}
static void nvme_rdma_complete_rq(struct request *rq)
{
struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
- struct nvme_rdma_queue *queue = req->queue;
- int error = 0;
-
- nvme_rdma_unmap_data(queue, rq);
- if (unlikely(rq->errors)) {
- if (nvme_req_needs_retry(rq, rq->errors)) {
- nvme_requeue_req(rq);
- return;
- }
-
- if (blk_rq_is_passthrough(rq))
- error = rq->errors;
- else
- error = nvme_error_status(rq->errors);
- }
-
- blk_mq_end_request(rq, error);
+ nvme_rdma_unmap_data(req->queue, rq);
+ nvme_complete_rq(rq);
}
-static struct blk_mq_ops nvme_rdma_mq_ops = {
+static const struct blk_mq_ops nvme_rdma_mq_ops = {
.queue_rq = nvme_rdma_queue_rq,
.complete = nvme_rdma_complete_rq,
.init_request = nvme_rdma_init_request,
.timeout = nvme_rdma_timeout,
};
-static struct blk_mq_ops nvme_rdma_admin_mq_ops = {
+static const struct blk_mq_ops nvme_rdma_admin_mq_ops = {
.queue_rq = nvme_rdma_queue_rq,
.complete = nvme_rdma_complete_rq,
.init_request = nvme_rdma_init_admin_request,
}
ctrl->ctrl.sqsize =
- min_t(int, NVME_CAP_MQES(ctrl->cap) + 1, ctrl->ctrl.sqsize);
+ min_t(int, NVME_CAP_MQES(ctrl->cap), ctrl->ctrl.sqsize);
error = nvme_enable_ctrl(&ctrl->ctrl, ctrl->cap);
if (error)
return ret;
}
-static int nvme_rdma_parse_ipaddr(struct sockaddr_in *in_addr, char *p)
-{
- u8 *addr = (u8 *)&in_addr->sin_addr.s_addr;
- size_t buflen = strlen(p);
-
- /* XXX: handle IPv6 addresses */
-
- if (buflen > INET_ADDRSTRLEN)
- return -EINVAL;
- if (in4_pton(p, buflen, addr, '\0', NULL) == 0)
- return -EINVAL;
- in_addr->sin_family = AF_INET;
- return 0;
-}
-
static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
struct nvmf_ctrl_options *opts)
{
struct nvme_rdma_ctrl *ctrl;
int ret;
bool changed;
+ char *port;
ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL);
if (!ctrl)
ctrl->ctrl.opts = opts;
INIT_LIST_HEAD(&ctrl->list);
- ret = nvme_rdma_parse_ipaddr(&ctrl->addr_in, opts->traddr);
+ if (opts->mask & NVMF_OPT_TRSVCID)
+ port = opts->trsvcid;
+ else
+ port = __stringify(NVME_RDMA_IP_PORT);
+
+ ret = inet_pton_with_scope(&init_net, AF_UNSPEC,
+ opts->traddr, port, &ctrl->addr);
if (ret) {
- pr_err("malformed IP address passed: %s\n", opts->traddr);
+ pr_err("malformed address passed: %s:%s\n", opts->traddr, port);
goto out_free_ctrl;
}
if (opts->mask & NVMF_OPT_HOST_TRADDR) {
- ret = nvme_rdma_parse_ipaddr(&ctrl->src_addr_in,
- opts->host_traddr);
+ ret = inet_pton_with_scope(&init_net, AF_UNSPEC,
+ opts->host_traddr, NULL, &ctrl->src_addr);
if (ret) {
- pr_err("malformed src IP address passed: %s\n",
+ pr_err("malformed src address passed: %s\n",
opts->host_traddr);
goto out_free_ctrl;
}
}
- if (opts->mask & NVMF_OPT_TRSVCID) {
- u16 port;
-
- ret = kstrtou16(opts->trsvcid, 0, &port);
- if (ret)
- goto out_free_ctrl;
-
- ctrl->addr_in.sin_port = cpu_to_be16(port);
- } else {
- ctrl->addr_in.sin_port = cpu_to_be16(NVME_RDMA_IP_PORT);
- }
-
ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_rdma_ctrl_ops,
0 /* no quirks, we're perfect! */);
if (ret)
goto out_free_ctrl;
- ctrl->reconnect_delay = opts->reconnect_delay;
INIT_DELAYED_WORK(&ctrl->reconnect_work,
nvme_rdma_reconnect_ctrl_work);
INIT_WORK(&ctrl->err_work, nvme_rdma_error_recovery_work);
changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
WARN_ON_ONCE(!changed);
- dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISp\n",
+ dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs\n",
ctrl->ctrl.opts->subsysnqn, &ctrl->addr);
kref_get(&ctrl->ctrl.kref);
.name = "rdma",
.required_opts = NVMF_OPT_TRADDR,
.allowed_opts = NVMF_OPT_TRSVCID | NVMF_OPT_RECONNECT_DELAY |
- NVMF_OPT_HOST_TRADDR,
+ NVMF_OPT_HOST_TRADDR | NVMF_OPT_CTRL_LOSS_TMO,
.create_ctrl = nvme_rdma_create_ctrl,
};
return -ENOMEM;
ret = ib_register_client(&nvme_rdma_ib_client);
- if (ret) {
- destroy_workqueue(nvme_rdma_wq);
- return ret;
- }
+ if (ret)
+ goto err_destroy_wq;
+
+ ret = nvmf_register_transport(&nvme_rdma_transport);
+ if (ret)
+ goto err_unreg_client;
+
+ return 0;
- return nvmf_register_transport(&nvme_rdma_transport);
+err_unreg_client:
+ ib_unregister_client(&nvme_rdma_ib_client);
+err_destroy_wq:
+ destroy_workqueue(nvme_rdma_wq);
+ return ret;
}
static void __exit nvme_rdma_cleanup_module(void)
struct nvme_command c;
u8 opcode = (is_write ? nvme_cmd_write : nvme_cmd_read);
u16 control;
- u32 max_blocks = queue_max_hw_sectors(ns->queue);
+ u32 max_blocks = queue_max_hw_sectors(ns->queue) >> (ns->lba_shift - 9);
num_cmds = nvme_trans_io_get_num_cmds(hdr, cdb_info, max_blocks);
return res;
}
-static int nvme_trans_security_protocol(struct nvme_ns *ns,
- struct sg_io_hdr *hdr,
- u8 *cmd)
-{
- return nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST, SCSI_ASC_ILLEGAL_COMMAND,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
-}
-
static int nvme_trans_synchronize_cache(struct nvme_ns *ns,
struct sg_io_hdr *hdr)
{
case REQUEST_SENSE:
retcode = nvme_trans_request_sense(ns, hdr, cmd);
break;
- case SECURITY_PROTOCOL_IN:
- case SECURITY_PROTOCOL_OUT:
- retcode = nvme_trans_security_protocol(ns, hdr, cmd);
- break;
case SYNCHRONIZE_CACHE:
retcode = nvme_trans_synchronize_cache(ns, hdr);
break;
u16 status;
WARN_ON(req == NULL || slog == NULL);
- if (req->cmd->get_log_page.nsid == 0xFFFFFFFF)
+ if (req->cmd->get_log_page.nsid == cpu_to_le32(0xFFFFFFFF))
status = nvmet_get_smart_log_all(req, slog);
else
status = nvmet_get_smart_log_nsid(req, slog);
}
switch (req->cmd->get_log_page.lid) {
- case 0x01:
+ case NVME_LOG_ERROR:
/*
* We currently never set the More bit in the status field,
* so all error log entries are invalid and can be zeroed out.
* mandatory log page.
*/
break;
- case 0x02:
+ case NVME_LOG_SMART:
/*
* XXX: fill out actual smart log
*
goto err;
}
break;
- case 0x03:
+ case NVME_LOG_FW_SLOT:
/*
* We only support a single firmware slot which always is
* active, so we can zero out the whole firmware slot log and
nvmet_req_complete(req, 0);
}
-int nvmet_parse_admin_cmd(struct nvmet_req *req)
+u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
{
struct nvme_command *cmd = req->cmd;
+ u16 ret;
req->ns = NULL;
- if (unlikely(!(req->sq->ctrl->cc & NVME_CC_ENABLE))) {
- pr_err("nvmet: got admin cmd %d while CC.EN == 0\n",
- cmd->common.opcode);
- return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
- }
- if (unlikely(!(req->sq->ctrl->csts & NVME_CSTS_RDY))) {
- pr_err("nvmet: got admin cmd %d while CSTS.RDY == 0\n",
- cmd->common.opcode);
- return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
- }
+ ret = nvmet_check_ctrl_status(req, cmd);
+ if (unlikely(ret))
+ return ret;
switch (cmd->common.opcode) {
case nvme_admin_get_log_page:
req->data_len = nvmet_get_log_page_len(cmd);
switch (cmd->get_log_page.lid) {
- case 0x01:
- case 0x02:
- case 0x03:
+ case NVME_LOG_ERROR:
+ case NVME_LOG_SMART:
+ case NVME_LOG_FW_SLOT:
req->execute = nvmet_execute_get_log_page;
return 0;
}
return 0;
}
- pr_err("nvmet: unhandled cmd %d\n", cmd->common.opcode);
+ pr_err("unhandled cmd %d on qid %d\n", cmd->common.opcode,
+ req->sq->qid);
return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
}
ns->bdev = blkdev_get_by_path(ns->device_path, FMODE_READ | FMODE_WRITE,
NULL);
if (IS_ERR(ns->bdev)) {
- pr_err("nvmet: failed to open block device %s: (%ld)\n",
- ns->device_path, PTR_ERR(ns->bdev));
+ pr_err("failed to open block device %s: (%ld)\n",
+ ns->device_path, PTR_ERR(ns->bdev));
ret = PTR_ERR(ns->bdev);
ns->bdev = NULL;
goto out_unlock;
return status;
}
+u16 nvmet_check_ctrl_status(struct nvmet_req *req, struct nvme_command *cmd)
+{
+ if (unlikely(!(req->sq->ctrl->cc & NVME_CC_ENABLE))) {
+ pr_err("got io cmd %d while CC.EN == 0 on qid = %d\n",
+ cmd->common.opcode, req->sq->qid);
+ return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
+ }
+
+ if (unlikely(!(req->sq->ctrl->csts & NVME_CSTS_RDY))) {
+ pr_err("got io cmd %d while CSTS.RDY == 0 on qid = %d\n",
+ cmd->common.opcode, req->sq->qid);
+ req->ns = NULL;
+ return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
+ }
+ return 0;
+}
+
static bool __nvmet_host_allowed(struct nvmet_subsys *subsys,
const char *hostnqn)
{
nvmet_req_complete(req, status);
}
-int nvmet_parse_discovery_cmd(struct nvmet_req *req)
+u16 nvmet_parse_discovery_cmd(struct nvmet_req *req)
{
struct nvme_command *cmd = req->cmd;
req->ns = NULL;
if (unlikely(!(req->sq->ctrl->csts & NVME_CSTS_RDY))) {
- pr_err("nvmet: got cmd %d while not ready\n",
- cmd->common.opcode);
+ pr_err("got cmd %d while not ready\n",
+ cmd->common.opcode);
return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
}
req->execute = nvmet_execute_get_disc_log_page;
return 0;
default:
- pr_err("nvmet: unsupported get_log_page lid %d\n",
- cmd->get_log_page.lid);
+ pr_err("unsupported get_log_page lid %d\n",
+ cmd->get_log_page.lid);
return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
}
case nvme_admin_identify:
nvmet_execute_identify_disc_ctrl;
return 0;
default:
- pr_err("nvmet: unsupported identify cns %d\n",
- cmd->identify.cns);
+ pr_err("unsupported identify cns %d\n",
+ cmd->identify.cns);
return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
}
default:
- pr_err("nvmet: unsupported cmd %d\n",
- cmd->common.opcode);
+ pr_err("unsupported cmd %d\n", cmd->common.opcode);
return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
}
- pr_err("nvmet: unhandled cmd %d\n", cmd->common.opcode);
+ pr_err("unhandled cmd %d\n", cmd->common.opcode);
return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
}
nvmet_req_complete(req, status);
}
-int nvmet_parse_fabrics_cmd(struct nvmet_req *req)
+u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req)
{
struct nvme_command *cmd = req->cmd;
struct nvmet_ctrl *ctrl = NULL;
u16 status = 0;
- d = kmap(sg_page(req->sg)) + req->sg->offset;
+ d = kmalloc(sizeof(*d), GFP_KERNEL);
+ if (!d) {
+ status = NVME_SC_INTERNAL;
+ goto complete;
+ }
+
+ status = nvmet_copy_from_sgl(req, 0, d, sizeof(*d));
+ if (status)
+ goto out;
/* zero out initial completion result, assign values as needed */
req->rsp->result.u32 = 0;
}
status = nvmet_alloc_ctrl(d->subsysnqn, d->hostnqn, req,
- le32_to_cpu(c->kato), &ctrl);
+ le32_to_cpu(c->kato), &ctrl);
if (status)
goto out;
req->rsp->result.u16 = cpu_to_le16(ctrl->cntlid);
out:
- kunmap(sg_page(req->sg));
+ kfree(d);
+complete:
nvmet_req_complete(req, status);
}
u16 qid = le16_to_cpu(c->qid);
u16 status = 0;
- d = kmap(sg_page(req->sg)) + req->sg->offset;
+ d = kmalloc(sizeof(*d), GFP_KERNEL);
+ if (!d) {
+ status = NVME_SC_INTERNAL;
+ goto complete;
+ }
+
+ status = nvmet_copy_from_sgl(req, 0, d, sizeof(*d));
+ if (status)
+ goto out;
/* zero out initial completion result, assign values as needed */
req->rsp->result.u32 = 0;
}
status = nvmet_ctrl_find_get(d->subsysnqn, d->hostnqn,
- le16_to_cpu(d->cntlid),
- req, &ctrl);
+ le16_to_cpu(d->cntlid),
+ req, &ctrl);
if (status)
goto out;
pr_info("adding queue %d to ctrl %d.\n", qid, ctrl->cntlid);
out:
- kunmap(sg_page(req->sg));
+ kfree(d);
+complete:
nvmet_req_complete(req, status);
return;
goto out;
}
-int nvmet_parse_connect_cmd(struct nvmet_req *req)
+u16 nvmet_parse_connect_cmd(struct nvmet_req *req)
{
struct nvme_command *cmd = req->cmd;
enum nvmet_fcp_datadir io_dir;
bool active;
bool abort;
+ bool aborted;
+ bool writedataactive;
spinlock_t flock;
struct nvmet_req req;
struct work_struct work;
+ struct work_struct done_work;
struct nvmet_fc_tgtport *tgtport;
struct nvmet_fc_tgt_queue *queue;
u16 qid;
u16 sqsize;
u16 ersp_ratio;
- u16 sqhd;
+ __le16 sqhd;
int cpu;
atomic_t connected;
atomic_t sqtail;
static void nvmet_fc_handle_ls_rqst_work(struct work_struct *work);
static void nvmet_fc_handle_fcp_rqst_work(struct work_struct *work);
+static void nvmet_fc_fcp_rqst_op_done_work(struct work_struct *work);
static void nvmet_fc_tgt_a_put(struct nvmet_fc_tgt_assoc *assoc);
static int nvmet_fc_tgt_a_get(struct nvmet_fc_tgt_assoc *assoc);
static void nvmet_fc_tgt_q_put(struct nvmet_fc_tgt_queue *queue);
for (i = 0; i < queue->sqsize; fod++, i++) {
INIT_WORK(&fod->work, nvmet_fc_handle_fcp_rqst_work);
+ INIT_WORK(&fod->done_work, nvmet_fc_fcp_rqst_op_done_work);
fod->tgtport = tgtport;
fod->queue = queue;
fod->active = false;
+ fod->abort = false;
+ fod->aborted = false;
+ fod->fcpreq = NULL;
list_add_tail(&fod->fcp_list, &queue->fod_list);
spin_lock_init(&fod->flock);
if (fod) {
list_del(&fod->fcp_list);
fod->active = true;
- fod->abort = false;
/*
* no queue reference is taken, as it was taken by the
* queue lookup just prior to the allocation. The iod
nvmet_fc_free_fcp_iod(struct nvmet_fc_tgt_queue *queue,
struct nvmet_fc_fcp_iod *fod)
{
+ struct nvmefc_tgt_fcp_req *fcpreq = fod->fcpreq;
+ struct nvmet_fc_tgtport *tgtport = fod->tgtport;
unsigned long flags;
+ fc_dma_sync_single_for_cpu(tgtport->dev, fod->rspdma,
+ sizeof(fod->rspiubuf), DMA_TO_DEVICE);
+
+ fcpreq->nvmet_fc_private = NULL;
+
spin_lock_irqsave(&queue->qlock, flags);
list_add_tail(&fod->fcp_list, &fod->queue->fod_list);
fod->active = false;
+ fod->abort = false;
+ fod->aborted = false;
+ fod->writedataactive = false;
+ fod->fcpreq = NULL;
spin_unlock_irqrestore(&queue->qlock, flags);
/*
* release the reference taken at queue lookup and fod allocation
*/
nvmet_fc_tgt_q_put(queue);
+
+ tgtport->ops->fcp_req_release(&tgtport->fc_target_port, fcpreq);
}
static int
static void
-nvmet_fc_abort_op(struct nvmet_fc_tgtport *tgtport,
- struct nvmefc_tgt_fcp_req *fcpreq)
-{
- int ret;
-
- fcpreq->op = NVMET_FCOP_ABORT;
- fcpreq->offset = 0;
- fcpreq->timeout = 0;
- fcpreq->transfer_length = 0;
- fcpreq->transferred_length = 0;
- fcpreq->fcp_error = 0;
- fcpreq->sg_cnt = 0;
-
- ret = tgtport->ops->fcp_op(&tgtport->fc_target_port, fcpreq);
- if (ret)
- /* should never reach here !! */
- WARN_ON(1);
-}
-
-
-static void
nvmet_fc_delete_target_queue(struct nvmet_fc_tgt_queue *queue)
{
+ struct nvmet_fc_tgtport *tgtport = queue->assoc->tgtport;
struct nvmet_fc_fcp_iod *fod = queue->fod;
unsigned long flags;
- int i;
+ int i, writedataactive;
bool disconnect;
disconnect = atomic_xchg(&queue->connected, 0);
if (fod->active) {
spin_lock(&fod->flock);
fod->abort = true;
+ writedataactive = fod->writedataactive;
spin_unlock(&fod->flock);
+ /*
+ * only call lldd abort routine if waiting for
+ * writedata. other outstanding ops should finish
+ * on their own.
+ */
+ if (writedataactive) {
+ spin_lock(&fod->flock);
+ fod->aborted = true;
+ spin_unlock(&fod->flock);
+ tgtport->ops->fcp_abort(
+ &tgtport->fc_target_port, fod->fcpreq);
+ }
}
}
spin_unlock_irqrestore(&queue->qlock, flags);
int ret, idx;
if (!template->xmt_ls_rsp || !template->fcp_op ||
- !template->targetport_delete ||
+ !template->fcp_abort ||
+ !template->fcp_req_release || !template->targetport_delete ||
!template->max_hw_queues || !template->max_sgl_segments ||
!template->max_dif_sgl_segments || !template->dma_boundary) {
ret = -EINVAL;
static void
-nvmet_fc_format_rsp_hdr(void *buf, u8 ls_cmd, u32 desc_len, u8 rqst_ls_cmd)
+nvmet_fc_format_rsp_hdr(void *buf, u8 ls_cmd, __be32 desc_len, u8 rqst_ls_cmd)
{
struct fcnvme_ls_acc_hdr *acc = buf;
validation_errors[ret]);
iod->lsreq->rsplen = nvmet_fc_format_rjt(acc,
NVME_FC_MAX_LS_BUFFER_SIZE, rqst->w0.ls_cmd,
- ELS_RJT_LOGIC,
- ELS_EXPL_NONE, 0);
+ FCNVME_RJT_RC_LOGIC,
+ FCNVME_RJT_EXP_NONE, 0);
return;
}
iod->lsreq->rsplen = nvmet_fc_format_rjt(acc,
NVME_FC_MAX_LS_BUFFER_SIZE, rqst->w0.ls_cmd,
(ret == VERR_NO_ASSOC) ?
- ELS_RJT_PROT : ELS_RJT_LOGIC,
- ELS_EXPL_NONE, 0);
+ FCNVME_RJT_RC_INV_ASSOC :
+ FCNVME_RJT_RC_LOGIC,
+ FCNVME_RJT_EXP_NONE, 0);
return;
}
validation_errors[ret]);
iod->lsreq->rsplen = nvmet_fc_format_rjt(acc,
NVME_FC_MAX_LS_BUFFER_SIZE, rqst->w0.ls_cmd,
- (ret == 8) ? ELS_RJT_PROT : ELS_RJT_LOGIC,
- ELS_EXPL_NONE, 0);
+ (ret == VERR_NO_ASSOC) ?
+ FCNVME_RJT_RC_INV_ASSOC :
+ (ret == VERR_NO_CONN) ?
+ FCNVME_RJT_RC_INV_CONN :
+ FCNVME_RJT_RC_LOGIC,
+ FCNVME_RJT_EXP_NONE, 0);
return;
}
default:
iod->lsreq->rsplen = nvmet_fc_format_rjt(iod->rspbuf,
NVME_FC_MAX_LS_BUFFER_SIZE, w0->ls_cmd,
- ELS_RJT_INVAL, ELS_EXPL_NONE, 0);
+ FCNVME_RJT_RC_INVAL, FCNVME_RJT_EXP_NONE, 0);
}
nvmet_fc_xmt_ls_rsp(tgtport, iod);
for_each_sg(fod->data_sg, sg, fod->data_sg_cnt, count)
__free_page(sg_page(sg));
kfree(fod->data_sg);
+ fod->data_sg = NULL;
+ fod->data_sg_cnt = 0;
}
xfr_length != fod->total_length ||
(le16_to_cpu(cqe->status) & 0xFFFE) || cqewd[0] || cqewd[1] ||
(sqe->flags & (NVME_CMD_FUSE_FIRST | NVME_CMD_FUSE_SECOND)) ||
- queue_90percent_full(fod->queue, cqe->sq_head))
+ queue_90percent_full(fod->queue, le16_to_cpu(cqe->sq_head)))
send_ersp = true;
/* re-set the fields */
static void nvmet_fc_xmt_fcp_op_done(struct nvmefc_tgt_fcp_req *fcpreq);
static void
+nvmet_fc_abort_op(struct nvmet_fc_tgtport *tgtport,
+ struct nvmet_fc_fcp_iod *fod)
+{
+ struct nvmefc_tgt_fcp_req *fcpreq = fod->fcpreq;
+
+ /* data no longer needed */
+ nvmet_fc_free_tgt_pgs(fod);
+
+ /*
+ * if an ABTS was received or we issued the fcp_abort early
+ * don't call abort routine again.
+ */
+ /* no need to take lock - lock was taken earlier to get here */
+ if (!fod->aborted)
+ tgtport->ops->fcp_abort(&tgtport->fc_target_port, fcpreq);
+
+ nvmet_fc_free_fcp_iod(fod->queue, fod);
+}
+
+static void
nvmet_fc_xmt_fcp_rsp(struct nvmet_fc_tgtport *tgtport,
struct nvmet_fc_fcp_iod *fod)
{
ret = tgtport->ops->fcp_op(&tgtport->fc_target_port, fod->fcpreq);
if (ret)
- nvmet_fc_abort_op(tgtport, fod->fcpreq);
+ nvmet_fc_abort_op(tgtport, fod);
}
static void
{
struct nvmefc_tgt_fcp_req *fcpreq = fod->fcpreq;
struct scatterlist *sg, *datasg;
+ unsigned long flags;
u32 tlen, sg_off;
int ret;
*/
fod->abort = true;
- if (op == NVMET_FCOP_WRITEDATA)
+ if (op == NVMET_FCOP_WRITEDATA) {
+ spin_lock_irqsave(&fod->flock, flags);
+ fod->writedataactive = false;
+ spin_unlock_irqrestore(&fod->flock, flags);
nvmet_req_complete(&fod->req,
NVME_SC_FC_TRANSPORT_ERROR);
- else /* NVMET_FCOP_READDATA or NVMET_FCOP_READDATA_RSP */ {
+ } else /* NVMET_FCOP_READDATA or NVMET_FCOP_READDATA_RSP */ {
fcpreq->fcp_error = ret;
fcpreq->transferred_length = 0;
nvmet_fc_xmt_fcp_op_done(fod->fcpreq);
}
}
+static inline bool
+__nvmet_fc_fod_op_abort(struct nvmet_fc_fcp_iod *fod, bool abort)
+{
+ struct nvmefc_tgt_fcp_req *fcpreq = fod->fcpreq;
+ struct nvmet_fc_tgtport *tgtport = fod->tgtport;
+
+ /* if in the middle of an io and we need to tear down */
+ if (abort) {
+ if (fcpreq->op == NVMET_FCOP_WRITEDATA) {
+ nvmet_req_complete(&fod->req,
+ NVME_SC_FC_TRANSPORT_ERROR);
+ return true;
+ }
+
+ nvmet_fc_abort_op(tgtport, fod);
+ return true;
+ }
+
+ return false;
+}
+
+/*
+ * actual done handler for FCP operations when completed by the lldd
+ */
static void
-nvmet_fc_xmt_fcp_op_done(struct nvmefc_tgt_fcp_req *fcpreq)
+nvmet_fc_fod_op_done(struct nvmet_fc_fcp_iod *fod)
{
- struct nvmet_fc_fcp_iod *fod = fcpreq->nvmet_fc_private;
+ struct nvmefc_tgt_fcp_req *fcpreq = fod->fcpreq;
struct nvmet_fc_tgtport *tgtport = fod->tgtport;
unsigned long flags;
bool abort;
spin_lock_irqsave(&fod->flock, flags);
abort = fod->abort;
+ fod->writedataactive = false;
spin_unlock_irqrestore(&fod->flock, flags);
- /* if in the middle of an io and we need to tear down */
- if (abort && fcpreq->op != NVMET_FCOP_ABORT) {
- /* data no longer needed */
- nvmet_fc_free_tgt_pgs(fod);
-
- nvmet_req_complete(&fod->req, fcpreq->fcp_error);
- return;
- }
-
switch (fcpreq->op) {
case NVMET_FCOP_WRITEDATA:
+ if (__nvmet_fc_fod_op_abort(fod, abort))
+ return;
if (fcpreq->fcp_error ||
fcpreq->transferred_length != fcpreq->transfer_length) {
+ spin_lock(&fod->flock);
+ fod->abort = true;
+ spin_unlock(&fod->flock);
+
nvmet_req_complete(&fod->req,
NVME_SC_FC_TRANSPORT_ERROR);
return;
fod->offset += fcpreq->transferred_length;
if (fod->offset != fod->total_length) {
+ spin_lock_irqsave(&fod->flock, flags);
+ fod->writedataactive = true;
+ spin_unlock_irqrestore(&fod->flock, flags);
+
/* transfer the next chunk */
nvmet_fc_transfer_fcp_data(tgtport, fod,
NVMET_FCOP_WRITEDATA);
case NVMET_FCOP_READDATA:
case NVMET_FCOP_READDATA_RSP:
+ if (__nvmet_fc_fod_op_abort(fod, abort))
+ return;
if (fcpreq->fcp_error ||
fcpreq->transferred_length != fcpreq->transfer_length) {
- /* data no longer needed */
- nvmet_fc_free_tgt_pgs(fod);
-
- nvmet_fc_abort_op(tgtport, fod->fcpreq);
+ nvmet_fc_abort_op(tgtport, fod);
return;
}
if (fcpreq->op == NVMET_FCOP_READDATA_RSP) {
/* data no longer needed */
nvmet_fc_free_tgt_pgs(fod);
- fc_dma_sync_single_for_cpu(tgtport->dev, fod->rspdma,
- sizeof(fod->rspiubuf), DMA_TO_DEVICE);
nvmet_fc_free_fcp_iod(fod->queue, fod);
return;
}
break;
case NVMET_FCOP_RSP:
- case NVMET_FCOP_ABORT:
- fc_dma_sync_single_for_cpu(tgtport->dev, fod->rspdma,
- sizeof(fod->rspiubuf), DMA_TO_DEVICE);
+ if (__nvmet_fc_fod_op_abort(fod, abort))
+ return;
nvmet_fc_free_fcp_iod(fod->queue, fod);
break;
default:
- nvmet_fc_free_tgt_pgs(fod);
- nvmet_fc_abort_op(tgtport, fod->fcpreq);
break;
}
}
+static void
+nvmet_fc_fcp_rqst_op_done_work(struct work_struct *work)
+{
+ struct nvmet_fc_fcp_iod *fod =
+ container_of(work, struct nvmet_fc_fcp_iod, done_work);
+
+ nvmet_fc_fod_op_done(fod);
+}
+
+static void
+nvmet_fc_xmt_fcp_op_done(struct nvmefc_tgt_fcp_req *fcpreq)
+{
+ struct nvmet_fc_fcp_iod *fod = fcpreq->nvmet_fc_private;
+ struct nvmet_fc_tgt_queue *queue = fod->queue;
+
+ if (fod->tgtport->ops->target_features & NVMET_FCTGTFEAT_OPDONE_IN_ISR)
+ /* context switch so completion is not in ISR context */
+ queue_work_on(queue->cpu, queue->work_q, &fod->done_work);
+ else
+ nvmet_fc_fod_op_done(fod);
+}
+
/*
* actual completion handler after execution by the nvmet layer
*/
fod->queue->sqhd = cqe->sq_head;
if (abort) {
- /* data no longer needed */
- nvmet_fc_free_tgt_pgs(fod);
-
- nvmet_fc_abort_op(tgtport, fod->fcpreq);
+ nvmet_fc_abort_op(tgtport, fod);
return;
}
/*
* Actual processing routine for received FC-NVME LS Requests from the LLD
*/
-void
+static void
nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport,
struct nvmet_fc_fcp_iod *fod)
{
&fod->queue->nvme_cq,
&fod->queue->nvme_sq,
&nvmet_fc_tgt_fcp_ops);
- if (!ret) { /* bad SQE content */
- nvmet_fc_abort_op(tgtport, fod->fcpreq);
+ if (!ret) { /* bad SQE content or invalid ctrl state */
+ nvmet_fc_abort_op(tgtport, fod);
return;
}
return;
transport_error:
- nvmet_fc_abort_op(tgtport, fod->fcpreq);
+ nvmet_fc_abort_op(tgtport, fod);
}
/*
* If this routine returns error, the lldd should abort the exchange.
*
* @target_port: pointer to the (registered) target port the FCP CMD IU
- * was receive on.
+ * was received on.
* @fcpreq: pointer to a fcpreq request structure to be used to reference
* the exchange corresponding to the FCP Exchange.
* @cmdiubuf: pointer to the buffer containing the FCP CMD IU
(be16_to_cpu(cmdiu->iu_len) != (sizeof(*cmdiu)/4)))
return -EIO;
-
queue = nvmet_fc_find_target_queue(tgtport,
be64_to_cpu(cmdiu->connection_id));
if (!queue)
((queue->qid - 1) % tgtport->ops->max_hw_queues) : 0;
memcpy(&fod->cmdiubuf, cmdiubuf, cmdiubuf_len);
- queue_work_on(queue->cpu, queue->work_q, &fod->work);
+ if (tgtport->ops->target_features & NVMET_FCTGTFEAT_CMD_IN_ISR)
+ queue_work_on(queue->cpu, queue->work_q, &fod->work);
+ else
+ nvmet_fc_handle_fcp_rqst(tgtport, fod);
return 0;
}
EXPORT_SYMBOL_GPL(nvmet_fc_rcv_fcp_req);
+/**
+ * nvmet_fc_rcv_fcp_abort - transport entry point called by an LLDD
+ * upon the reception of an ABTS for a FCP command
+ *
+ * Notify the transport that an ABTS has been received for a FCP command
+ * that had been given to the transport via nvmet_fc_rcv_fcp_req(). The
+ * LLDD believes the command is still being worked on
+ * (template_ops->fcp_req_release() has not been called).
+ *
+ * The transport will wait for any outstanding work (an op to the LLDD,
+ * which the lldd should complete with error due to the ABTS; or the
+ * completion from the nvmet layer of the nvme command), then will
+ * stop processing and call the nvmet_fc_rcv_fcp_req() callback to
+ * return the i/o context to the LLDD. The LLDD may send the BA_ACC
+ * to the ABTS either after return from this function (assuming any
+ * outstanding op work has been terminated) or upon the callback being
+ * called.
+ *
+ * @target_port: pointer to the (registered) target port the FCP CMD IU
+ * was received on.
+ * @fcpreq: pointer to the fcpreq request structure that corresponds
+ * to the exchange that received the ABTS.
+ */
+void
+nvmet_fc_rcv_fcp_abort(struct nvmet_fc_target_port *target_port,
+ struct nvmefc_tgt_fcp_req *fcpreq)
+{
+ struct nvmet_fc_fcp_iod *fod = fcpreq->nvmet_fc_private;
+ struct nvmet_fc_tgt_queue *queue;
+ unsigned long flags;
+
+ if (!fod || fod->fcpreq != fcpreq)
+ /* job appears to have already completed, ignore abort */
+ return;
+
+ queue = fod->queue;
+
+ spin_lock_irqsave(&queue->qlock, flags);
+ if (fod->active) {
+ /*
+ * mark as abort. The abort handler, invoked upon completion
+ * of any work, will detect the aborted status and do the
+ * callback.
+ */
+ spin_lock(&fod->flock);
+ fod->abort = true;
+ fod->aborted = true;
+ spin_unlock(&fod->flock);
+ }
+ spin_unlock_irqrestore(&queue->qlock, flags);
+}
+EXPORT_SYMBOL_GPL(nvmet_fc_rcv_fcp_abort);
+
enum {
FCT_TRADDR_ERR = 0,
FCT_TRADDR_WWNN = 1 << 0,
if (!options)
return -ENOMEM;
- while ((p = strsep(&o, ",\n")) != NULL) {
+ while ((p = strsep(&o, ":\n")) != NULL) {
if (!*p)
continue;
if (!tgtport->port) {
tgtport->port = port;
port->priv = tgtport;
+ nvmet_fc_tgtport_get(tgtport);
ret = 0;
} else
ret = -EALREADY;
struct fcloop_fcpreq {
struct fcloop_tport *tport;
struct nvmefc_fcp_req *fcpreq;
+ spinlock_t reqlock;
u16 status;
+ bool active;
+ bool aborted;
struct work_struct work;
struct nvmefc_tgt_fcp_req tgt_fcp_req;
};
+struct fcloop_ini_fcpreq {
+ struct nvmefc_fcp_req *fcpreq;
+ struct fcloop_fcpreq *tfcp_req;
+ struct work_struct iniwork;
+};
static inline struct fcloop_lsreq *
tgt_ls_req_to_lsreq(struct nvmefc_tgt_ls_req *tgt_lsreq)
}
/*
- * FCP IO operation done. call back up initiator "done" flows.
+ * FCP IO operation done by initiator abort.
+ * call back up initiator "done" flows.
+ */
+static void
+fcloop_tgt_fcprqst_ini_done_work(struct work_struct *work)
+{
+ struct fcloop_ini_fcpreq *inireq =
+ container_of(work, struct fcloop_ini_fcpreq, iniwork);
+
+ inireq->fcpreq->done(inireq->fcpreq);
+}
+
+/*
+ * FCP IO operation done by target completion.
+ * call back up initiator "done" flows.
*/
static void
fcloop_tgt_fcprqst_done_work(struct work_struct *work)
struct fcloop_fcpreq *tfcp_req =
container_of(work, struct fcloop_fcpreq, work);
struct fcloop_tport *tport = tfcp_req->tport;
- struct nvmefc_fcp_req *fcpreq = tfcp_req->fcpreq;
+ struct nvmefc_fcp_req *fcpreq;
- if (tport->remoteport) {
+ spin_lock(&tfcp_req->reqlock);
+ fcpreq = tfcp_req->fcpreq;
+ spin_unlock(&tfcp_req->reqlock);
+
+ if (tport->remoteport && fcpreq) {
fcpreq->status = tfcp_req->status;
fcpreq->done(fcpreq);
}
+
+ kfree(tfcp_req);
}
void *hw_queue_handle,
struct nvmefc_fcp_req *fcpreq)
{
- struct fcloop_fcpreq *tfcp_req = fcpreq->private;
struct fcloop_rport *rport = remoteport->private;
+ struct fcloop_ini_fcpreq *inireq = fcpreq->private;
+ struct fcloop_fcpreq *tfcp_req;
int ret = 0;
- INIT_WORK(&tfcp_req->work, fcloop_tgt_fcprqst_done_work);
+ if (!rport->targetport)
+ return -ECONNREFUSED;
- if (!rport->targetport) {
- tfcp_req->status = NVME_SC_FC_TRANSPORT_ERROR;
- schedule_work(&tfcp_req->work);
- return ret;
- }
+ tfcp_req = kzalloc(sizeof(*tfcp_req), GFP_KERNEL);
+ if (!tfcp_req)
+ return -ENOMEM;
+ inireq->fcpreq = fcpreq;
+ inireq->tfcp_req = tfcp_req;
+ INIT_WORK(&inireq->iniwork, fcloop_tgt_fcprqst_ini_done_work);
tfcp_req->fcpreq = fcpreq;
tfcp_req->tport = rport->targetport->private;
+ spin_lock_init(&tfcp_req->reqlock);
+ INIT_WORK(&tfcp_req->work, fcloop_tgt_fcprqst_done_work);
ret = nvmet_fc_rcv_fcp_req(rport->targetport, &tfcp_req->tgt_fcp_req,
fcpreq->cmdaddr, fcpreq->cmdlen);
struct nvmefc_tgt_fcp_req *tgt_fcpreq)
{
struct fcloop_fcpreq *tfcp_req = tgt_fcp_req_to_fcpreq(tgt_fcpreq);
- struct nvmefc_fcp_req *fcpreq = tfcp_req->fcpreq;
+ struct nvmefc_fcp_req *fcpreq;
u32 rsplen = 0, xfrlen = 0;
- int fcp_err = 0;
+ int fcp_err = 0, active, aborted;
u8 op = tgt_fcpreq->op;
+ spin_lock(&tfcp_req->reqlock);
+ fcpreq = tfcp_req->fcpreq;
+ active = tfcp_req->active;
+ aborted = tfcp_req->aborted;
+ tfcp_req->active = true;
+ spin_unlock(&tfcp_req->reqlock);
+
+ if (unlikely(active))
+ /* illegal - call while i/o active */
+ return -EALREADY;
+
+ if (unlikely(aborted)) {
+ /* target transport has aborted i/o prior */
+ spin_lock(&tfcp_req->reqlock);
+ tfcp_req->active = false;
+ spin_unlock(&tfcp_req->reqlock);
+ tgt_fcpreq->transferred_length = 0;
+ tgt_fcpreq->fcp_error = -ECANCELED;
+ tgt_fcpreq->done(tgt_fcpreq);
+ return 0;
+ }
+
+ /*
+ * if fcpreq is NULL, the I/O has been aborted (from
+ * initiator side). For the target side, act as if all is well
+ * but don't actually move data.
+ */
+
switch (op) {
case NVMET_FCOP_WRITEDATA:
xfrlen = tgt_fcpreq->transfer_length;
- fcloop_fcp_copy_data(op, tgt_fcpreq->sg, fcpreq->first_sgl,
- tgt_fcpreq->offset, xfrlen);
- fcpreq->transferred_length += xfrlen;
+ if (fcpreq) {
+ fcloop_fcp_copy_data(op, tgt_fcpreq->sg,
+ fcpreq->first_sgl, tgt_fcpreq->offset,
+ xfrlen);
+ fcpreq->transferred_length += xfrlen;
+ }
break;
case NVMET_FCOP_READDATA:
case NVMET_FCOP_READDATA_RSP:
xfrlen = tgt_fcpreq->transfer_length;
- fcloop_fcp_copy_data(op, tgt_fcpreq->sg, fcpreq->first_sgl,
- tgt_fcpreq->offset, xfrlen);
- fcpreq->transferred_length += xfrlen;
+ if (fcpreq) {
+ fcloop_fcp_copy_data(op, tgt_fcpreq->sg,
+ fcpreq->first_sgl, tgt_fcpreq->offset,
+ xfrlen);
+ fcpreq->transferred_length += xfrlen;
+ }
if (op == NVMET_FCOP_READDATA)
break;
/* Fall-Thru to RSP handling */
case NVMET_FCOP_RSP:
- rsplen = ((fcpreq->rsplen < tgt_fcpreq->rsplen) ?
- fcpreq->rsplen : tgt_fcpreq->rsplen);
- memcpy(fcpreq->rspaddr, tgt_fcpreq->rspaddr, rsplen);
- if (rsplen < tgt_fcpreq->rsplen)
- fcp_err = -E2BIG;
- fcpreq->rcv_rsplen = rsplen;
- fcpreq->status = 0;
+ if (fcpreq) {
+ rsplen = ((fcpreq->rsplen < tgt_fcpreq->rsplen) ?
+ fcpreq->rsplen : tgt_fcpreq->rsplen);
+ memcpy(fcpreq->rspaddr, tgt_fcpreq->rspaddr, rsplen);
+ if (rsplen < tgt_fcpreq->rsplen)
+ fcp_err = -E2BIG;
+ fcpreq->rcv_rsplen = rsplen;
+ fcpreq->status = 0;
+ }
tfcp_req->status = 0;
break;
- case NVMET_FCOP_ABORT:
- tfcp_req->status = NVME_SC_FC_TRANSPORT_ABORTED;
- break;
-
default:
fcp_err = -EINVAL;
break;
}
+ spin_lock(&tfcp_req->reqlock);
+ tfcp_req->active = false;
+ spin_unlock(&tfcp_req->reqlock);
+
tgt_fcpreq->transferred_length = xfrlen;
tgt_fcpreq->fcp_error = fcp_err;
tgt_fcpreq->done(tgt_fcpreq);
- if ((!fcp_err) && (op == NVMET_FCOP_RSP ||
- op == NVMET_FCOP_READDATA_RSP ||
- op == NVMET_FCOP_ABORT))
- schedule_work(&tfcp_req->work);
-
return 0;
}
static void
+fcloop_tgt_fcp_abort(struct nvmet_fc_target_port *tgtport,
+ struct nvmefc_tgt_fcp_req *tgt_fcpreq)
+{
+ struct fcloop_fcpreq *tfcp_req = tgt_fcp_req_to_fcpreq(tgt_fcpreq);
+ int active;
+
+ /*
+ * mark aborted only in case there were 2 threads in transport
+ * (one doing io, other doing abort) and only kills ops posted
+ * after the abort request
+ */
+ spin_lock(&tfcp_req->reqlock);
+ active = tfcp_req->active;
+ tfcp_req->aborted = true;
+ spin_unlock(&tfcp_req->reqlock);
+
+ tfcp_req->status = NVME_SC_FC_TRANSPORT_ABORTED;
+
+ /*
+ * nothing more to do. If io wasn't active, the transport should
+ * immediately call the req_release. If it was active, the op
+ * will complete, and the lldd should call req_release.
+ */
+}
+
+static void
+fcloop_fcp_req_release(struct nvmet_fc_target_port *tgtport,
+ struct nvmefc_tgt_fcp_req *tgt_fcpreq)
+{
+ struct fcloop_fcpreq *tfcp_req = tgt_fcp_req_to_fcpreq(tgt_fcpreq);
+
+ schedule_work(&tfcp_req->work);
+}
+
+static void
fcloop_ls_abort(struct nvme_fc_local_port *localport,
struct nvme_fc_remote_port *remoteport,
struct nvmefc_ls_req *lsreq)
void *hw_queue_handle,
struct nvmefc_fcp_req *fcpreq)
{
+ struct fcloop_rport *rport = remoteport->private;
+ struct fcloop_ini_fcpreq *inireq = fcpreq->private;
+ struct fcloop_fcpreq *tfcp_req = inireq->tfcp_req;
+
+ if (!tfcp_req)
+ /* abort has already been called */
+ return;
+
+ if (rport->targetport)
+ nvmet_fc_rcv_fcp_abort(rport->targetport,
+ &tfcp_req->tgt_fcp_req);
+
+ /* break initiator/target relationship for io */
+ spin_lock(&tfcp_req->reqlock);
+ inireq->tfcp_req = NULL;
+ tfcp_req->fcpreq = NULL;
+ spin_unlock(&tfcp_req->reqlock);
+
+ /* post the aborted io completion */
+ fcpreq->status = -ECANCELED;
+ schedule_work(&inireq->iniwork);
}
static void
#define FCLOOP_SGL_SEGS 256
#define FCLOOP_DMABOUND_4G 0xFFFFFFFF
-struct nvme_fc_port_template fctemplate = {
+static struct nvme_fc_port_template fctemplate = {
.localport_delete = fcloop_localport_delete,
.remoteport_delete = fcloop_remoteport_delete,
.create_queue = fcloop_create_queue,
.local_priv_sz = sizeof(struct fcloop_lport),
.remote_priv_sz = sizeof(struct fcloop_rport),
.lsrqst_priv_sz = sizeof(struct fcloop_lsreq),
- .fcprqst_priv_sz = sizeof(struct fcloop_fcpreq),
+ .fcprqst_priv_sz = sizeof(struct fcloop_ini_fcpreq),
};
-struct nvmet_fc_target_template tgttemplate = {
+static struct nvmet_fc_target_template tgttemplate = {
.targetport_delete = fcloop_targetport_delete,
.xmt_ls_rsp = fcloop_xmt_ls_rsp,
.fcp_op = fcloop_fcp_op,
+ .fcp_abort = fcloop_tgt_fcp_abort,
+ .fcp_req_release = fcloop_fcp_req_release,
.max_hw_queues = FCLOOP_HW_QUEUES,
.max_sgl_segments = FCLOOP_SGL_SEGS,
.max_dif_sgl_segments = FCLOOP_SGL_SEGS,
.dma_boundary = FCLOOP_DMABOUND_4G,
/* optional features */
- .target_features = NVMET_FCTGTFEAT_READDATA_RSP |
- NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED,
+ .target_features = NVMET_FCTGTFEAT_CMD_IN_ISR |
+ NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED |
+ NVMET_FCTGTFEAT_OPDONE_IN_ISR,
/* sizes of additional private data for data structures */
.target_priv_sz = sizeof(struct fcloop_tport),
};
sector = le64_to_cpu(write_zeroes->slba) <<
(req->ns->blksize_shift - 9);
- nr_sector = (((sector_t)le32_to_cpu(write_zeroes->length)) <<
+ nr_sector = (((sector_t)le16_to_cpu(write_zeroes->length)) <<
(req->ns->blksize_shift - 9)) + 1;
if (__blkdev_issue_zeroout(req->ns->bdev, sector, nr_sector,
- GFP_KERNEL, &bio, true))
+ GFP_KERNEL, &bio, 0))
status = NVME_SC_INTERNAL | NVME_SC_DNR;
if (bio) {
}
}
-int nvmet_parse_io_cmd(struct nvmet_req *req)
+u16 nvmet_parse_io_cmd(struct nvmet_req *req)
{
struct nvme_command *cmd = req->cmd;
+ u16 ret;
- if (unlikely(!(req->sq->ctrl->cc & NVME_CC_ENABLE))) {
- pr_err("nvmet: got io cmd %d while CC.EN == 0\n",
- cmd->common.opcode);
+ ret = nvmet_check_ctrl_status(req, cmd);
+ if (unlikely(ret)) {
req->ns = NULL;
- return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
- }
-
- if (unlikely(!(req->sq->ctrl->csts & NVME_CSTS_RDY))) {
- pr_err("nvmet: got io cmd %d while CSTS.RDY == 0\n",
- cmd->common.opcode);
- req->ns = NULL;
- return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
+ return ret;
}
req->ns = nvmet_find_namespace(req->sq->ctrl, cmd->rw.nsid);
- if (!req->ns)
+ if (unlikely(!req->ns))
return NVME_SC_INVALID_NS | NVME_SC_DNR;
switch (cmd->common.opcode) {
return 0;
case nvme_cmd_dsm:
req->execute = nvmet_execute_dsm;
- req->data_len = le32_to_cpu(cmd->dsm.nr + 1) *
+ req->data_len = (le32_to_cpu(cmd->dsm.nr) + 1) *
sizeof(struct nvme_dsm_range);
return 0;
case nvme_cmd_write_zeroes:
req->execute = nvmet_execute_write_zeroes;
return 0;
default:
- pr_err("nvmet: unhandled cmd %d\n", cmd->common.opcode);
+ pr_err("unhandled cmd %d on qid %d\n", cmd->common.opcode,
+ req->sq->qid);
return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
}
}
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/scatterlist.h>
-#include <linux/delay.h>
#include <linux/blk-mq.h>
#include <linux/nvme.h>
#include <linux/module.h>
#include <linux/parser.h>
-#include <linux/t10-pi.h>
#include "nvmet.h"
#include "../host/nvme.h"
#include "../host/fabrics.h"
static void nvme_loop_complete_rq(struct request *req)
{
struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(req);
- int error = 0;
nvme_cleanup_cmd(req);
sg_free_table_chained(&iod->sg_table, true);
+ nvme_complete_rq(req);
+}
- if (unlikely(req->errors)) {
- if (nvme_req_needs_retry(req, req->errors)) {
- nvme_requeue_req(req);
- return;
- }
-
- if (blk_rq_is_passthrough(req))
- error = req->errors;
- else
- error = nvme_error_status(req->errors);
- }
+static struct blk_mq_tags *nvme_loop_tagset(struct nvme_loop_queue *queue)
+{
+ u32 queue_idx = nvme_loop_queue_idx(queue);
- blk_mq_end_request(req, error);
+ if (queue_idx == 0)
+ return queue->ctrl->admin_tag_set.tags[queue_idx];
+ return queue->ctrl->tag_set.tags[queue_idx - 1];
}
static void nvme_loop_queue_response(struct nvmet_req *req)
{
- struct nvme_loop_iod *iod =
- container_of(req, struct nvme_loop_iod, req);
- struct nvme_completion *cqe = &iod->rsp;
+ struct nvme_loop_queue *queue =
+ container_of(req->sq, struct nvme_loop_queue, nvme_sq);
+ struct nvme_completion *cqe = req->rsp;
/*
* AEN requests are special as they don't time out and can
* aborts. We don't even bother to allocate a struct request
* for them but rather special case them here.
*/
- if (unlikely(nvme_loop_queue_idx(iod->queue) == 0 &&
+ if (unlikely(nvme_loop_queue_idx(queue) == 0 &&
cqe->command_id >= NVME_LOOP_AQ_BLKMQ_DEPTH)) {
- nvme_complete_async_event(&iod->queue->ctrl->ctrl, cqe->status,
+ nvme_complete_async_event(&queue->ctrl->ctrl, cqe->status,
&cqe->result);
} else {
- struct request *rq = blk_mq_rq_from_pdu(iod);
+ struct request *rq;
+
+ rq = blk_mq_tag_to_rq(nvme_loop_tagset(queue), cqe->command_id);
+ if (!rq) {
+ dev_err(queue->ctrl->ctrl.device,
+ "tag 0x%x on queue %d not found\n",
+ cqe->command_id, nvme_loop_queue_idx(queue));
+ return;
+ }
- iod->nvme_req.result = cqe->result;
- blk_mq_complete_request(rq, le16_to_cpu(cqe->status) >> 1);
+ nvme_end_request(rq, cqe->status, cqe->result);
}
}
schedule_work(&iod->queue->ctrl->reset_work);
/* fail with DNR on admin cmd timeout */
- rq->errors = NVME_SC_ABORT_REQ | NVME_SC_DNR;
+ nvme_req(rq)->status = NVME_SC_ABORT_REQ | NVME_SC_DNR;
return BLK_EH_HANDLED;
}
return 0;
}
-static struct blk_mq_ops nvme_loop_mq_ops = {
+static const struct blk_mq_ops nvme_loop_mq_ops = {
.queue_rq = nvme_loop_queue_rq,
.complete = nvme_loop_complete_rq,
.init_request = nvme_loop_init_request,
.timeout = nvme_loop_timeout,
};
-static struct blk_mq_ops nvme_loop_admin_mq_ops = {
+static const struct blk_mq_ops nvme_loop_admin_mq_ops = {
.queue_rq = nvme_loop_queue_rq,
.complete = nvme_loop_complete_rq,
.init_request = nvme_loop_init_admin_request,
return ret;
}
+static int nvme_loop_connect_io_queues(struct nvme_loop_ctrl *ctrl)
+{
+ int i, ret;
+
+ for (i = 1; i < ctrl->queue_count; i++) {
+ ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
{
int error;
}
ctrl->ctrl.sqsize =
- min_t(int, NVME_CAP_MQES(ctrl->cap) + 1, ctrl->ctrl.sqsize);
+ min_t(int, NVME_CAP_MQES(ctrl->cap), ctrl->ctrl.sqsize);
error = nvme_enable_ctrl(&ctrl->ctrl, ctrl->cap);
if (error)
struct nvme_loop_ctrl *ctrl = container_of(work,
struct nvme_loop_ctrl, reset_work);
bool changed;
- int i, ret;
+ int ret;
nvme_loop_shutdown_ctrl(ctrl);
if (ret)
goto out_destroy_admin;
- for (i = 1; i < ctrl->queue_count; i++) {
- ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
- if (ret)
- goto out_destroy_io;
- }
+ ret = nvme_loop_connect_io_queues(ctrl);
+ if (ret)
+ goto out_destroy_io;
changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
WARN_ON_ONCE(!changed);
static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl)
{
- int ret, i;
+ int ret;
ret = nvme_loop_init_io_queues(ctrl);
if (ret)
goto out_free_tagset;
}
- for (i = 1; i < ctrl->queue_count; i++) {
- ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
- if (ret)
- goto out_cleanup_connect_q;
- }
+ ret = nvme_loop_connect_io_queues(ctrl);
+ if (ret)
+ goto out_cleanup_connect_q;
return 0;
ret = nvmet_register_transport(&nvme_loop_ops);
if (ret)
return ret;
- return nvmf_register_transport(&nvme_loop_transport);
+
+ ret = nvmf_register_transport(&nvme_loop_transport);
+ if (ret)
+ nvmet_unregister_transport(&nvme_loop_ops);
+
+ return ret;
}
static void __exit nvme_loop_cleanup_module(void)
u8 log_page;
};
-int nvmet_parse_connect_cmd(struct nvmet_req *req);
-int nvmet_parse_io_cmd(struct nvmet_req *req);
-int nvmet_parse_admin_cmd(struct nvmet_req *req);
-int nvmet_parse_discovery_cmd(struct nvmet_req *req);
-int nvmet_parse_fabrics_cmd(struct nvmet_req *req);
+u16 nvmet_parse_connect_cmd(struct nvmet_req *req);
+u16 nvmet_parse_io_cmd(struct nvmet_req *req);
+u16 nvmet_parse_admin_cmd(struct nvmet_req *req);
+u16 nvmet_parse_discovery_cmd(struct nvmet_req *req);
+u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req);
bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
struct nvmet_sq *sq, struct nvmet_fabrics_ops *ops);
u16 nvmet_ctrl_find_get(const char *subsysnqn, const char *hostnqn, u16 cntlid,
struct nvmet_req *req, struct nvmet_ctrl **ret);
void nvmet_ctrl_put(struct nvmet_ctrl *ctrl);
+u16 nvmet_check_ctrl_status(struct nvmet_req *req, struct nvme_command *cmd);
struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn,
enum nvme_subsys_type type);
}
queue->port = cm_id->context;
+ if (queue->host_qid == 0) {
+ /* Let inflight controller teardown complete */
+ flush_scheduled_work();
+ }
+
ret = nvmet_rdma_cm_accept(cm_id, queue, &event->param.conn);
if (ret)
goto release_queue;
static int nvmet_rdma_add_port(struct nvmet_port *port)
{
struct rdma_cm_id *cm_id;
- struct sockaddr_in addr_in;
- u16 port_in;
+ struct sockaddr_storage addr = { };
+ __kernel_sa_family_t af;
int ret;
switch (port->disc_addr.adrfam) {
case NVMF_ADDR_FAMILY_IP4:
+ af = AF_INET;
+ break;
+ case NVMF_ADDR_FAMILY_IP6:
+ af = AF_INET6;
break;
default:
pr_err("address family %d not supported\n",
return -EINVAL;
}
- ret = kstrtou16(port->disc_addr.trsvcid, 0, &port_in);
- if (ret)
+ ret = inet_pton_with_scope(&init_net, af, port->disc_addr.traddr,
+ port->disc_addr.trsvcid, &addr);
+ if (ret) {
+ pr_err("malformed ip/port passed: %s:%s\n",
+ port->disc_addr.traddr, port->disc_addr.trsvcid);
return ret;
-
- addr_in.sin_family = AF_INET;
- addr_in.sin_addr.s_addr = in_aton(port->disc_addr.traddr);
- addr_in.sin_port = htons(port_in);
+ }
cm_id = rdma_create_id(&init_net, nvmet_rdma_cm_handler, port,
RDMA_PS_TCP, IB_QPT_RC);
return PTR_ERR(cm_id);
}
- ret = rdma_bind_addr(cm_id, (struct sockaddr *)&addr_in);
+ /*
+ * Allow both IPv4 and IPv6 sockets to bind a single port
+ * at the same time.
+ */
+ ret = rdma_set_afonly(cm_id, 1);
+ if (ret) {
+ pr_err("rdma_set_afonly failed (%d)\n", ret);
+ goto out_destroy_id;
+ }
+
+ ret = rdma_bind_addr(cm_id, (struct sockaddr *)&addr);
if (ret) {
- pr_err("binding CM ID to %pISpc failed (%d)\n", &addr_in, ret);
+ pr_err("binding CM ID to %pISpcs failed (%d)\n",
+ (struct sockaddr *)&addr, ret);
goto out_destroy_id;
}
ret = rdma_listen(cm_id, 128);
if (ret) {
- pr_err("listening to %pISpc failed (%d)\n", &addr_in, ret);
+ pr_err("listening to %pISpcs failed (%d)\n",
+ (struct sockaddr *)&addr, ret);
goto out_destroy_id;
}
- pr_info("enabling port %d (%pISpc)\n",
- le16_to_cpu(port->disc_addr.portid), &addr_in);
+ pr_info("enabling port %d (%pISpcs)\n",
+ le16_to_cpu(port->disc_addr.portid), (struct sockaddr *)&addr);
port->priv = cm_id;
return 0;
depends on PCI_MSI_IRQ_DOMAIN
select PCIEPORTBUS
select PCIE_DW_HOST
+ select PCI_HOST_COMMON
help
Say Y here if you want PCIe controller support on HiSilicon
Hip05 and Hip06 SoCs
return 0;
}
+static const struct dw_pcie_ops dw_pcie_ops = {
+};
+
static int artpec6_pcie_probe(struct platform_device *pdev)
{
struct device *dev = &pdev->dev;
return -ENOMEM;
pci->dev = dev;
+ pci->ops = &dw_pcie_ops;
artpec6_pcie->pci = pci;
return 0;
}
+static const struct dw_pcie_ops dw_pcie_ops = {
+};
+
static int dw_plat_pcie_probe(struct platform_device *pdev)
{
struct device *dev = &pdev->dev;
return -ENOMEM;
pci->dev = dev;
+ pci->ops = &dw_pcie_ops;
dw_plat_pcie->pci = pci;
static const struct of_device_id hisi_pcie_almost_ecam_of_match[] = {
{
- .compatible = "hisilicon,pcie-almost-ecam",
+ .compatible = "hisilicon,hip06-pcie-ecam",
.data = (void *) &hisi_pcie_platform_ops,
},
+ {
+ .compatible = "hisilicon,hip07-pcie-ecam",
+ .data = (void *) &hisi_pcie_platform_ops,
+ },
{},
};
index -= node * PEM_MAX_DOM_IN_NODE;
res_pem->start = PEM_RES_BASE | FIELD_PREP(PEM_NODE_MASK, node) |
FIELD_PREP(PEM_INDX_MASK, index);
- res_pem->end = res_pem->start + SZ_16M - 1;
res_pem->flags = IORESOURCE_MEM;
}
*/
if (ret) {
thunder_pem_legacy_fw(root, res_pem);
- /* Reserve PEM-specific resources and PCI configuration space */
+ /*
+ * Reserve 64K size PEM specific resources. The full 16M range
+ * size is required for thunder_pem_init() call.
+ */
+ res_pem->end = res_pem->start + SZ_64K - 1;
thunder_pem_reserve_range(dev, root->segment, res_pem);
+ res_pem->end = res_pem->start + SZ_16M - 1;
+
+ /* Reserve PCI configuration space as well. */
thunder_pem_reserve_range(dev, root->segment, &cfg->res);
}
return ERR_PTR(ret);
}
-static int pinctrl_create_and_start(struct pinctrl_dev *pctldev)
+static int pinctrl_claim_hogs(struct pinctrl_dev *pctldev)
{
pctldev->p = create_pinctrl(pctldev->dev, pctldev);
- if (!IS_ERR(pctldev->p)) {
- kref_get(&pctldev->p->users);
- pctldev->hog_default =
- pinctrl_lookup_state(pctldev->p, PINCTRL_STATE_DEFAULT);
- if (IS_ERR(pctldev->hog_default)) {
- dev_dbg(pctldev->dev,
- "failed to lookup the default state\n");
- } else {
- if (pinctrl_select_state(pctldev->p,
- pctldev->hog_default))
- dev_err(pctldev->dev,
- "failed to select default state\n");
- }
+ if (PTR_ERR(pctldev->p) == -ENODEV) {
+ dev_dbg(pctldev->dev, "no hogs found\n");
- pctldev->hog_sleep =
- pinctrl_lookup_state(pctldev->p,
- PINCTRL_STATE_SLEEP);
- if (IS_ERR(pctldev->hog_sleep))
- dev_dbg(pctldev->dev,
- "failed to lookup the sleep state\n");
+ return 0;
+ }
+
+ if (IS_ERR(pctldev->p)) {
+ dev_err(pctldev->dev, "error claiming hogs: %li\n",
+ PTR_ERR(pctldev->p));
+
+ return PTR_ERR(pctldev->p);
+ }
+
+ kref_get(&pctldev->p->users);
+ pctldev->hog_default =
+ pinctrl_lookup_state(pctldev->p, PINCTRL_STATE_DEFAULT);
+ if (IS_ERR(pctldev->hog_default)) {
+ dev_dbg(pctldev->dev,
+ "failed to lookup the default state\n");
+ } else {
+ if (pinctrl_select_state(pctldev->p,
+ pctldev->hog_default))
+ dev_err(pctldev->dev,
+ "failed to select default state\n");
+ }
+
+ pctldev->hog_sleep =
+ pinctrl_lookup_state(pctldev->p,
+ PINCTRL_STATE_SLEEP);
+ if (IS_ERR(pctldev->hog_sleep))
+ dev_dbg(pctldev->dev,
+ "failed to lookup the sleep state\n");
+
+ return 0;
+}
+
+int pinctrl_enable(struct pinctrl_dev *pctldev)
+{
+ int error;
+
+ error = pinctrl_claim_hogs(pctldev);
+ if (error) {
+ dev_err(pctldev->dev, "could not claim hogs: %i\n",
+ error);
+ mutex_destroy(&pctldev->mutex);
+ kfree(pctldev);
+
+ return error;
}
mutex_lock(&pinctrldev_list_mutex);
return 0;
}
+EXPORT_SYMBOL_GPL(pinctrl_enable);
/**
* pinctrl_register() - register a pin controller device
if (IS_ERR(pctldev))
return pctldev;
- error = pinctrl_create_and_start(pctldev);
- if (error) {
- mutex_destroy(&pctldev->mutex);
- kfree(pctldev);
-
+ error = pinctrl_enable(pctldev);
+ if (error)
return ERR_PTR(error);
- }
return pctldev;
}
EXPORT_SYMBOL_GPL(pinctrl_register);
+/**
+ * pinctrl_register_and_init() - register and init pin controller device
+ * @pctldesc: descriptor for this pin controller
+ * @dev: parent device for this pin controller
+ * @driver_data: private pin controller data for this pin controller
+ * @pctldev: pin controller device
+ *
+ * Note that pinctrl_enable() still needs to be manually called after
+ * this once the driver is ready.
+ */
int pinctrl_register_and_init(struct pinctrl_desc *pctldesc,
struct device *dev, void *driver_data,
struct pinctrl_dev **pctldev)
{
struct pinctrl_dev *p;
- int error;
p = pinctrl_init_controller(pctldesc, dev, driver_data);
if (IS_ERR(p))
*/
*pctldev = p;
- error = pinctrl_create_and_start(p);
- if (error) {
- mutex_destroy(&p->mutex);
- kfree(p);
- *pctldev = NULL;
-
- return error;
- }
-
return 0;
}
EXPORT_SYMBOL_GPL(pinctrl_register_and_init);
dev_info(&pdev->dev, "initialized IMX pinctrl driver\n");
- return 0;
+ return pinctrl_enable(ipctl->pctl);
free:
imx_free_resources(ipctl);
* published by the Free Software Foundation.
*/
+#include <linux/dmi.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
chained_irq_exit(chip, desc);
}
+/*
+ * Certain machines seem to hardcode Linux IRQ numbers in their ACPI
+ * tables. Since we leave GPIOs that are not capable of generating
+ * interrupts out of the irqdomain the numbering will be different and
+ * cause devices using the hardcoded IRQ numbers fail. In order not to
+ * break such machines we will only mask pins from irqdomain if the machine
+ * is not listed below.
+ */
+static const struct dmi_system_id chv_no_valid_mask[] = {
+ {
+ /* See https://bugzilla.kernel.org/show_bug.cgi?id=194945 */
+ .ident = "Acer Chromebook (CYAN)",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Edgar"),
+ DMI_MATCH(DMI_BIOS_DATE, "05/21/2016"),
+ },
+ }
+};
+
static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq)
{
const struct chv_gpio_pinrange *range;
struct gpio_chip *chip = &pctrl->chip;
+ bool need_valid_mask = !dmi_check_system(chv_no_valid_mask);
int ret, i, offset;
*chip = chv_gpio_chip;
chip->label = dev_name(pctrl->dev);
chip->parent = pctrl->dev;
chip->base = -1;
- chip->irq_need_valid_mask = true;
+ chip->irq_need_valid_mask = need_valid_mask;
ret = devm_gpiochip_add_data(pctrl->dev, chip, pctrl);
if (ret) {
intsel &= CHV_PADCTRL0_INTSEL_MASK;
intsel >>= CHV_PADCTRL0_INTSEL_SHIFT;
- if (intsel >= pctrl->community->nirqs)
+ if (need_valid_mask && intsel >= pctrl->community->nirqs)
clear_bit(i, chip->irq_valid_mask);
}
dev_info(pcs->dev, "%i pins at pa %p size %u\n",
pcs->desc.npins, pcs->base, pcs->size);
- return 0;
+ return pinctrl_enable(pcs->pctl);
free:
pcs_free_resources(pcs);
/* pin banks of exynos5433 pin-controller - ALIVE */
static const struct samsung_pin_bank_data exynos5433_pin_banks0[] __initconst = {
- EXYNOS_PIN_BANK_EINTW(8, 0x000, "gpa0", 0x00),
- EXYNOS_PIN_BANK_EINTW(8, 0x020, "gpa1", 0x04),
- EXYNOS_PIN_BANK_EINTW(8, 0x040, "gpa2", 0x08),
- EXYNOS_PIN_BANK_EINTW(8, 0x060, "gpa3", 0x0c),
- EXYNOS_PIN_BANK_EINTW_EXT(8, 0x020, "gpf1", 0x1004, 1),
- EXYNOS_PIN_BANK_EINTW_EXT(4, 0x040, "gpf2", 0x1008, 1),
- EXYNOS_PIN_BANK_EINTW_EXT(4, 0x060, "gpf3", 0x100c, 1),
- EXYNOS_PIN_BANK_EINTW_EXT(8, 0x080, "gpf4", 0x1010, 1),
- EXYNOS_PIN_BANK_EINTW_EXT(8, 0x0a0, "gpf5", 0x1014, 1),
+ EXYNOS5433_PIN_BANK_EINTW(8, 0x000, "gpa0", 0x00),
+ EXYNOS5433_PIN_BANK_EINTW(8, 0x020, "gpa1", 0x04),
+ EXYNOS5433_PIN_BANK_EINTW(8, 0x040, "gpa2", 0x08),
+ EXYNOS5433_PIN_BANK_EINTW(8, 0x060, "gpa3", 0x0c),
+ EXYNOS5433_PIN_BANK_EINTW_EXT(8, 0x020, "gpf1", 0x1004, 1),
+ EXYNOS5433_PIN_BANK_EINTW_EXT(4, 0x040, "gpf2", 0x1008, 1),
+ EXYNOS5433_PIN_BANK_EINTW_EXT(4, 0x060, "gpf3", 0x100c, 1),
+ EXYNOS5433_PIN_BANK_EINTW_EXT(8, 0x080, "gpf4", 0x1010, 1),
+ EXYNOS5433_PIN_BANK_EINTW_EXT(8, 0x0a0, "gpf5", 0x1014, 1),
};
/* pin banks of exynos5433 pin-controller - AUD */
static const struct samsung_pin_bank_data exynos5433_pin_banks1[] __initconst = {
- EXYNOS_PIN_BANK_EINTG(7, 0x000, "gpz0", 0x00),
- EXYNOS_PIN_BANK_EINTG(4, 0x020, "gpz1", 0x04),
+ EXYNOS5433_PIN_BANK_EINTG(7, 0x000, "gpz0", 0x00),
+ EXYNOS5433_PIN_BANK_EINTG(4, 0x020, "gpz1", 0x04),
};
/* pin banks of exynos5433 pin-controller - CPIF */
static const struct samsung_pin_bank_data exynos5433_pin_banks2[] __initconst = {
- EXYNOS_PIN_BANK_EINTG(2, 0x000, "gpv6", 0x00),
+ EXYNOS5433_PIN_BANK_EINTG(2, 0x000, "gpv6", 0x00),
};
/* pin banks of exynos5433 pin-controller - eSE */
static const struct samsung_pin_bank_data exynos5433_pin_banks3[] __initconst = {
- EXYNOS_PIN_BANK_EINTG(3, 0x000, "gpj2", 0x00),
+ EXYNOS5433_PIN_BANK_EINTG(3, 0x000, "gpj2", 0x00),
};
/* pin banks of exynos5433 pin-controller - FINGER */
static const struct samsung_pin_bank_data exynos5433_pin_banks4[] __initconst = {
- EXYNOS_PIN_BANK_EINTG(4, 0x000, "gpd5", 0x00),
+ EXYNOS5433_PIN_BANK_EINTG(4, 0x000, "gpd5", 0x00),
};
/* pin banks of exynos5433 pin-controller - FSYS */
static const struct samsung_pin_bank_data exynos5433_pin_banks5[] __initconst = {
- EXYNOS_PIN_BANK_EINTG(6, 0x000, "gph1", 0x00),
- EXYNOS_PIN_BANK_EINTG(7, 0x020, "gpr4", 0x04),
- EXYNOS_PIN_BANK_EINTG(5, 0x040, "gpr0", 0x08),
- EXYNOS_PIN_BANK_EINTG(8, 0x060, "gpr1", 0x0c),
- EXYNOS_PIN_BANK_EINTG(2, 0x080, "gpr2", 0x10),
- EXYNOS_PIN_BANK_EINTG(8, 0x0a0, "gpr3", 0x14),
+ EXYNOS5433_PIN_BANK_EINTG(6, 0x000, "gph1", 0x00),
+ EXYNOS5433_PIN_BANK_EINTG(7, 0x020, "gpr4", 0x04),
+ EXYNOS5433_PIN_BANK_EINTG(5, 0x040, "gpr0", 0x08),
+ EXYNOS5433_PIN_BANK_EINTG(8, 0x060, "gpr1", 0x0c),
+ EXYNOS5433_PIN_BANK_EINTG(2, 0x080, "gpr2", 0x10),
+ EXYNOS5433_PIN_BANK_EINTG(8, 0x0a0, "gpr3", 0x14),
};
/* pin banks of exynos5433 pin-controller - IMEM */
static const struct samsung_pin_bank_data exynos5433_pin_banks6[] __initconst = {
- EXYNOS_PIN_BANK_EINTG(8, 0x000, "gpf0", 0x00),
+ EXYNOS5433_PIN_BANK_EINTG(8, 0x000, "gpf0", 0x00),
};
/* pin banks of exynos5433 pin-controller - NFC */
static const struct samsung_pin_bank_data exynos5433_pin_banks7[] __initconst = {
- EXYNOS_PIN_BANK_EINTG(3, 0x000, "gpj0", 0x00),
+ EXYNOS5433_PIN_BANK_EINTG(3, 0x000, "gpj0", 0x00),
};
/* pin banks of exynos5433 pin-controller - PERIC */
static const struct samsung_pin_bank_data exynos5433_pin_banks8[] __initconst = {
- EXYNOS_PIN_BANK_EINTG(6, 0x000, "gpv7", 0x00),
- EXYNOS_PIN_BANK_EINTG(5, 0x020, "gpb0", 0x04),
- EXYNOS_PIN_BANK_EINTG(8, 0x040, "gpc0", 0x08),
- EXYNOS_PIN_BANK_EINTG(2, 0x060, "gpc1", 0x0c),
- EXYNOS_PIN_BANK_EINTG(6, 0x080, "gpc2", 0x10),
- EXYNOS_PIN_BANK_EINTG(8, 0x0a0, "gpc3", 0x14),
- EXYNOS_PIN_BANK_EINTG(2, 0x0c0, "gpg0", 0x18),
- EXYNOS_PIN_BANK_EINTG(4, 0x0e0, "gpd0", 0x1c),
- EXYNOS_PIN_BANK_EINTG(6, 0x100, "gpd1", 0x20),
- EXYNOS_PIN_BANK_EINTG(8, 0x120, "gpd2", 0x24),
- EXYNOS_PIN_BANK_EINTG(5, 0x140, "gpd4", 0x28),
- EXYNOS_PIN_BANK_EINTG(2, 0x160, "gpd8", 0x2c),
- EXYNOS_PIN_BANK_EINTG(7, 0x180, "gpd6", 0x30),
- EXYNOS_PIN_BANK_EINTG(3, 0x1a0, "gpd7", 0x34),
- EXYNOS_PIN_BANK_EINTG(5, 0x1c0, "gpg1", 0x38),
- EXYNOS_PIN_BANK_EINTG(2, 0x1e0, "gpg2", 0x3c),
- EXYNOS_PIN_BANK_EINTG(8, 0x200, "gpg3", 0x40),
+ EXYNOS5433_PIN_BANK_EINTG(6, 0x000, "gpv7", 0x00),
+ EXYNOS5433_PIN_BANK_EINTG(5, 0x020, "gpb0", 0x04),
+ EXYNOS5433_PIN_BANK_EINTG(8, 0x040, "gpc0", 0x08),
+ EXYNOS5433_PIN_BANK_EINTG(2, 0x060, "gpc1", 0x0c),
+ EXYNOS5433_PIN_BANK_EINTG(6, 0x080, "gpc2", 0x10),
+ EXYNOS5433_PIN_BANK_EINTG(8, 0x0a0, "gpc3", 0x14),
+ EXYNOS5433_PIN_BANK_EINTG(2, 0x0c0, "gpg0", 0x18),
+ EXYNOS5433_PIN_BANK_EINTG(4, 0x0e0, "gpd0", 0x1c),
+ EXYNOS5433_PIN_BANK_EINTG(6, 0x100, "gpd1", 0x20),
+ EXYNOS5433_PIN_BANK_EINTG(8, 0x120, "gpd2", 0x24),
+ EXYNOS5433_PIN_BANK_EINTG(5, 0x140, "gpd4", 0x28),
+ EXYNOS5433_PIN_BANK_EINTG(2, 0x160, "gpd8", 0x2c),
+ EXYNOS5433_PIN_BANK_EINTG(7, 0x180, "gpd6", 0x30),
+ EXYNOS5433_PIN_BANK_EINTG(3, 0x1a0, "gpd7", 0x34),
+ EXYNOS5433_PIN_BANK_EINTG(5, 0x1c0, "gpg1", 0x38),
+ EXYNOS5433_PIN_BANK_EINTG(2, 0x1e0, "gpg2", 0x3c),
+ EXYNOS5433_PIN_BANK_EINTG(8, 0x200, "gpg3", 0x40),
};
/* pin banks of exynos5433 pin-controller - TOUCH */
static const struct samsung_pin_bank_data exynos5433_pin_banks9[] __initconst = {
- EXYNOS_PIN_BANK_EINTG(3, 0x000, "gpj1", 0x00),
+ EXYNOS5433_PIN_BANK_EINTG(3, 0x000, "gpj1", 0x00),
};
/*
.name = id \
}
-#define EXYNOS_PIN_BANK_EINTW_EXT(pins, reg, id, offs, pctl_idx) \
- { \
- .type = &bank_type_alive, \
- .pctl_offset = reg, \
- .nr_pins = pins, \
- .eint_type = EINT_TYPE_WKUP, \
- .eint_offset = offs, \
- .name = id, \
- .pctl_res_idx = pctl_idx, \
- } \
-
#define EXYNOS5433_PIN_BANK_EINTG(pins, reg, id, offs) \
{ \
.type = &exynos5433_bank_type_off, \
pmx->pctl_desc.pins = pmx->pins;
pmx->pctl_desc.npins = pfc->info->nr_pins;
- return devm_pinctrl_register_and_init(pfc->dev, &pmx->pctl_desc, pmx,
- &pmx->pctl);
+ ret = devm_pinctrl_register_and_init(pfc->dev, &pmx->pctl_desc, pmx,
+ &pmx->pctl);
+ if (ret) {
+ dev_err(pfc->dev, "could not register: %i\n", ret);
+
+ return ret;
+ }
+
+ return pinctrl_enable(pmx->pctl);
}
platform_set_drvdata(pdev, iod);
+ return pinctrl_enable(iod->pctl);
+
exit_out:
of_node_put(np);
return ret;
To compile this driver as a module, choose M here: the module will
be called dell-wmi-aio.
+config DELL_WMI_LED
+ tristate "External LED on Dell Business Netbooks"
+ depends on LEDS_CLASS
+ depends on ACPI_WMI
+ help
+ This adds support for the Latitude 2100 and similar
+ notebooks that have an external LED.
+
config DELL_SMO8800
tristate "Dell Latitude freefall driver (ACPI SMO88XX)"
depends on ACPI
obj-$(CONFIG_DELL_LAPTOP) += dell-laptop.o
obj-$(CONFIG_DELL_WMI) += dell-wmi.o
obj-$(CONFIG_DELL_WMI_AIO) += dell-wmi-aio.o
+obj-$(CONFIG_DELL_WMI_LED) += dell-wmi-led.o
obj-$(CONFIG_DELL_SMO8800) += dell-smo8800.o
obj-$(CONFIG_DELL_RBTN) += dell-rbtn.o
obj-$(CONFIG_ACER_WMI) += acer-wmi.o
#include <linux/mm.h>
#include <linux/i8042.h>
#include <linux/debugfs.h>
+#include <linux/dell-led.h>
#include <linux/seq_file.h>
#include <acpi/video.h>
#include "dell-rbtn.h"
#define KBD_LED_AUTO_50_TOKEN 0x02EB
#define KBD_LED_AUTO_75_TOKEN 0x02EC
#define KBD_LED_AUTO_100_TOKEN 0x02F6
+#define GLOBAL_MIC_MUTE_ENABLE 0x0364
+#define GLOBAL_MIC_MUTE_DISABLE 0x0365
struct quirk_entry {
u8 touchpad_led;
led_classdev_unregister(&kbd_led);
}
+int dell_micmute_led_set(int state)
+{
+ struct calling_interface_buffer *buffer;
+ struct calling_interface_token *token;
+
+ if (state == 0)
+ token = dell_smbios_find_token(GLOBAL_MIC_MUTE_DISABLE);
+ else if (state == 1)
+ token = dell_smbios_find_token(GLOBAL_MIC_MUTE_ENABLE);
+ else
+ return -EINVAL;
+
+ if (!token)
+ return -ENODEV;
+
+ buffer = dell_smbios_get_buffer();
+ buffer->input[0] = token->location;
+ buffer->input[1] = token->value;
+ dell_smbios_send_request(1, 0);
+ dell_smbios_release_buffer();
+
+ return state;
+}
+EXPORT_SYMBOL_GPL(dell_micmute_led_set);
+
static int __init dell_init(void)
{
struct calling_interface_buffer *buffer;
/*
- * dell_led.c - Dell LED Driver
- *
* Copyright (C) 2010 Dell Inc.
* Louis Davis <louis_davis@dell.com>
* Jim Dailey <jim_dailey@dell.com>
#include <linux/leds.h>
#include <linux/slab.h>
#include <linux/module.h>
-#include <linux/dmi.h>
-#include <linux/dell-led.h>
-#include "../platform/x86/dell-smbios.h"
MODULE_AUTHOR("Louis Davis/Jim Dailey");
MODULE_DESCRIPTION("Dell LED Control Driver");
MODULE_LICENSE("GPL");
#define DELL_LED_BIOS_GUID "F6E4FE6E-909D-47cb-8BAB-C9F6F2F8D396"
-#define DELL_APP_GUID "A80593CE-A997-11DA-B012-B622A1EF5492"
MODULE_ALIAS("wmi:" DELL_LED_BIOS_GUID);
/* Error Result Codes: */
#define CMD_LED_OFF 17
#define CMD_LED_BLINK 18
-#define GLOBAL_MIC_MUTE_ENABLE 0x364
-#define GLOBAL_MIC_MUTE_DISABLE 0x365
-
-static int dell_micmute_led_set(int state)
-{
- struct calling_interface_buffer *buffer;
- struct calling_interface_token *token;
-
- if (!wmi_has_guid(DELL_APP_GUID))
- return -ENODEV;
-
- if (state == 0)
- token = dell_smbios_find_token(GLOBAL_MIC_MUTE_DISABLE);
- else if (state == 1)
- token = dell_smbios_find_token(GLOBAL_MIC_MUTE_ENABLE);
- else
- return -EINVAL;
-
- if (!token)
- return -ENODEV;
-
- buffer = dell_smbios_get_buffer();
- buffer->input[0] = token->location;
- buffer->input[1] = token->value;
- dell_smbios_send_request(1, 0);
- dell_smbios_release_buffer();
-
- return state;
-}
-
-int dell_app_wmi_led_set(int whichled, int on)
-{
- int state = 0;
-
- switch (whichled) {
- case DELL_LED_MICMUTE:
- state = dell_micmute_led_set(on);
- break;
- default:
- pr_warn("led type %x is not supported\n", whichled);
- break;
- }
-
- return state;
-}
-EXPORT_SYMBOL_GPL(dell_app_wmi_led_set);
-
struct bios_args {
unsigned char length;
unsigned char result_code;
unsigned char off_time;
};
-static int dell_led_perform_fn(u8 length,
- u8 result_code,
- u8 device_id,
- u8 command,
- u8 on_time,
- u8 off_time)
+static int dell_led_perform_fn(u8 length, u8 result_code, u8 device_id,
+ u8 command, u8 on_time, u8 off_time)
{
- struct bios_args *bios_return;
- u8 return_code;
- union acpi_object *obj;
struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL };
+ struct bios_args *bios_return;
struct acpi_buffer input;
+ union acpi_object *obj;
acpi_status status;
+ u8 return_code;
- struct bios_args args;
- args.length = length;
- args.result_code = result_code;
- args.device_id = device_id;
- args.command = command;
- args.on_time = on_time;
- args.off_time = off_time;
+ struct bios_args args = {
+ .length = length,
+ .result_code = result_code,
+ .device_id = device_id,
+ .command = command,
+ .on_time = on_time,
+ .off_time = off_time
+ };
input.length = sizeof(struct bios_args);
input.pointer = &args;
- status = wmi_evaluate_method(DELL_LED_BIOS_GUID,
- 1,
- 1,
- &input,
- &output);
-
+ status = wmi_evaluate_method(DELL_LED_BIOS_GUID, 1, 1, &input, &output);
if (ACPI_FAILURE(status))
return status;
if (!obj)
return -EINVAL;
- else if (obj->type != ACPI_TYPE_BUFFER) {
+ if (obj->type != ACPI_TYPE_BUFFER) {
kfree(obj);
return -EINVAL;
}
0); /* not used */
}
-static int led_blink(unsigned char on_eighths,
- unsigned char off_eighths)
+static int led_blink(unsigned char on_eighths, unsigned char off_eighths)
{
return dell_led_perform_fn(5, /* Length of command */
INTERFACE_ERROR, /* Init to INTERFACE_ERROR */
}
static void dell_led_set(struct led_classdev *led_cdev,
- enum led_brightness value)
+ enum led_brightness value)
{
if (value == LED_OFF)
led_off();
}
static int dell_led_blink(struct led_classdev *led_cdev,
- unsigned long *delay_on,
- unsigned long *delay_off)
+ unsigned long *delay_on, unsigned long *delay_off)
{
unsigned long on_eighths;
unsigned long off_eighths;
- /* The Dell LED delay is based on 125ms intervals.
- Need to round up to next interval. */
+ /*
+ * The Dell LED delay is based on 125ms intervals.
+ * Need to round up to next interval.
+ */
- on_eighths = (*delay_on + 124) / 125;
- if (0 == on_eighths)
- on_eighths = 1;
- if (on_eighths > 255)
- on_eighths = 255;
+ on_eighths = DIV_ROUND_UP(*delay_on, 125);
+ on_eighths = clamp_t(unsigned long, on_eighths, 1, 255);
*delay_on = on_eighths * 125;
- off_eighths = (*delay_off + 124) / 125;
- if (0 == off_eighths)
- off_eighths = 1;
- if (off_eighths > 255)
- off_eighths = 255;
+ off_eighths = DIV_ROUND_UP(*delay_off, 125);
+ off_eighths = clamp_t(unsigned long, off_eighths, 1, 255);
*delay_off = off_eighths * 125;
led_blink(on_eighths, off_eighths);
{
int error = 0;
- if (!wmi_has_guid(DELL_LED_BIOS_GUID) && !wmi_has_guid(DELL_APP_GUID))
+ if (!wmi_has_guid(DELL_LED_BIOS_GUID))
return -ENODEV;
- if (wmi_has_guid(DELL_LED_BIOS_GUID)) {
- error = led_off();
- if (error != 0)
- return -ENODEV;
-
- error = led_classdev_register(NULL, &dell_led);
- }
+ error = led_off();
+ if (error != 0)
+ return -ENODEV;
- return error;
+ return led_classdev_register(NULL, &dell_led);
}
static void __exit dell_led_exit(void)
{
- int error = 0;
+ led_classdev_unregister(&dell_led);
- if (wmi_has_guid(DELL_LED_BIOS_GUID)) {
- error = led_off();
- if (error == 0)
- led_classdev_unregister(&dell_led);
- }
+ led_off();
}
module_init(dell_led_init);
#define RK3288_SOC_CON2_FLASH0 BIT(7)
#define RK3288_SOC_FLASH_SUPPLY_NUM 2
+#define RK3328_SOC_CON4 0x410
+#define RK3328_SOC_CON4_VCCIO2 BIT(7)
+#define RK3328_SOC_VCCIO2_SUPPLY_NUM 1
+
#define RK3368_SOC_CON15 0x43c
#define RK3368_SOC_CON15_FLASH0 BIT(14)
#define RK3368_SOC_FLASH_SUPPLY_NUM 2
dev_warn(iod->dev, "couldn't update flash0 ctrl\n");
}
+static void rk3328_iodomain_init(struct rockchip_iodomain *iod)
+{
+ int ret;
+ u32 val;
+
+ /* if no vccio2 supply we should leave things alone */
+ if (!iod->supplies[RK3328_SOC_VCCIO2_SUPPLY_NUM].reg)
+ return;
+
+ /*
+ * set vccio2 iodomain to also use this framework
+ * instead of a special gpio.
+ */
+ val = RK3328_SOC_CON4_VCCIO2 | (RK3328_SOC_CON4_VCCIO2 << 16);
+ ret = regmap_write(iod->grf, RK3328_SOC_CON4, val);
+ if (ret < 0)
+ dev_warn(iod->dev, "couldn't update vccio2 vsel ctrl\n");
+}
+
static void rk3368_iodomain_init(struct rockchip_iodomain *iod)
{
int ret;
.init = rk3288_iodomain_init,
};
+static const struct rockchip_iodomain_soc_data soc_data_rk3328 = {
+ .grf_offset = 0x410,
+ .supply_names = {
+ "vccio1",
+ "vccio2",
+ "vccio3",
+ "vccio4",
+ "vccio5",
+ "vccio6",
+ "pmuio",
+ },
+ .init = rk3328_iodomain_init,
+};
+
static const struct rockchip_iodomain_soc_data soc_data_rk3368 = {
.grf_offset = 0x900,
.supply_names = {
.data = (void *)&soc_data_rk3288
},
{
+ .compatible = "rockchip,rk3328-io-voltage-domain",
+ .data = (void *)&soc_data_rk3328
+ },
+ {
.compatible = "rockchip,rk3368-io-voltage-domain",
.data = (void *)&soc_data_rk3368
},
Say Y here if you have a Broadcom STB board and you wish
to have restart support.
+config POWER_RESET_GEMINI_POWEROFF
+ bool "Cortina Gemini power-off driver"
+ depends on ARCH_GEMINI || COMPILE_TEST
+ depends on OF && HAS_IOMEM
+ default ARCH_GEMINI
+ help
+ This driver supports turning off the Cortina Gemini SoC.
+ Select this if you're building a kernel with Gemini SoC support.
+
config POWER_RESET_GPIO
bool "GPIO power-off driver"
depends on OF_GPIO
obj-$(CONFIG_POWER_RESET_AXXIA) += axxia-reset.o
obj-$(CONFIG_POWER_RESET_BRCMKONA) += brcm-kona-reset.o
obj-$(CONFIG_POWER_RESET_BRCMSTB) += brcmstb-reboot.o
+obj-$(CONFIG_POWER_RESET_GEMINI_POWEROFF) += gemini-poweroff.o
obj-$(CONFIG_POWER_RESET_GPIO) += gpio-poweroff.o
obj-$(CONFIG_POWER_RESET_GPIO_RESTART) += gpio-restart.o
obj-$(CONFIG_POWER_RESET_HISI) += hisi-reboot.o
--- /dev/null
+/*
+ * Gemini power management controller
+ * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org>
+ *
+ * Inspired by code from the SL3516 board support by Jason Lee
+ * Inspired by code from Janos Laube <janos.dev@gmail.com>
+ */
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/bitops.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/reboot.h>
+
+#define GEMINI_PWC_ID 0x00010500
+#define GEMINI_PWC_IDREG 0x00
+#define GEMINI_PWC_CTRLREG 0x04
+#define GEMINI_PWC_STATREG 0x08
+
+#define GEMINI_CTRL_SHUTDOWN BIT(0)
+#define GEMINI_CTRL_ENABLE BIT(1)
+#define GEMINI_CTRL_IRQ_CLR BIT(2)
+
+#define GEMINI_STAT_CIR BIT(4)
+#define GEMINI_STAT_RTC BIT(5)
+#define GEMINI_STAT_POWERBUTTON BIT(6)
+
+struct gemini_powercon {
+ struct device *dev;
+ void __iomem *base;
+};
+
+static irqreturn_t gemini_powerbutton_interrupt(int irq, void *data)
+{
+ struct gemini_powercon *gpw = data;
+ u32 val;
+
+ /* ACK the IRQ */
+ val = readl(gpw->base + GEMINI_PWC_CTRLREG);
+ val |= GEMINI_CTRL_IRQ_CLR;
+ writel(val, gpw->base + GEMINI_PWC_CTRLREG);
+
+ val = readl(gpw->base + GEMINI_PWC_STATREG);
+ val &= 0x70U;
+ switch (val) {
+ case GEMINI_STAT_CIR:
+ dev_info(gpw->dev, "infrared poweroff\n");
+ orderly_poweroff(true);
+ break;
+ case GEMINI_STAT_RTC:
+ dev_info(gpw->dev, "RTC poweroff\n");
+ orderly_poweroff(true);
+ break;
+ case GEMINI_STAT_POWERBUTTON:
+ dev_info(gpw->dev, "poweroff button pressed\n");
+ orderly_poweroff(true);
+ break;
+ default:
+ dev_info(gpw->dev, "other power management IRQ\n");
+ break;
+ }
+
+ return IRQ_HANDLED;
+}
+
+/* This callback needs this static local as it has void as argument */
+static struct gemini_powercon *gpw_poweroff;
+
+static void gemini_poweroff(void)
+{
+ struct gemini_powercon *gpw = gpw_poweroff;
+ u32 val;
+
+ dev_crit(gpw->dev, "Gemini power off\n");
+ val = readl(gpw->base + GEMINI_PWC_CTRLREG);
+ val |= GEMINI_CTRL_ENABLE | GEMINI_CTRL_IRQ_CLR;
+ writel(val, gpw->base + GEMINI_PWC_CTRLREG);
+
+ val &= ~GEMINI_CTRL_ENABLE;
+ val |= GEMINI_CTRL_SHUTDOWN;
+ writel(val, gpw->base + GEMINI_PWC_CTRLREG);
+}
+
+static int gemini_poweroff_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct resource *res;
+ struct gemini_powercon *gpw;
+ u32 val;
+ int irq;
+ int ret;
+
+ gpw = devm_kzalloc(dev, sizeof(*gpw), GFP_KERNEL);
+ if (!gpw)
+ return -ENOMEM;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ gpw->base = devm_ioremap_resource(dev, res);
+ if (IS_ERR(gpw->base))
+ return PTR_ERR(gpw->base);
+
+ irq = platform_get_irq(pdev, 0);
+ if (!irq)
+ return -EINVAL;
+
+ gpw->dev = dev;
+
+ val = readl(gpw->base + GEMINI_PWC_IDREG);
+ val &= 0xFFFFFF00U;
+ if (val != GEMINI_PWC_ID) {
+ dev_err(dev, "wrong power controller ID: %08x\n",
+ val);
+ return -ENODEV;
+ }
+
+ /* Clear the power management IRQ */
+ val = readl(gpw->base + GEMINI_PWC_CTRLREG);
+ val |= GEMINI_CTRL_IRQ_CLR;
+ writel(val, gpw->base + GEMINI_PWC_CTRLREG);
+
+ ret = devm_request_irq(dev, irq, gemini_powerbutton_interrupt, 0,
+ "poweroff", gpw);
+ if (ret)
+ return ret;
+
+ pm_power_off = gemini_poweroff;
+ gpw_poweroff = gpw;
+
+ /*
+ * Enable the power controller. This is crucial on Gemini
+ * systems: if this is not done, pressing the power button
+ * will result in unconditional poweroff without any warning.
+ * This makes the kernel handle the poweroff.
+ */
+ val = readl(gpw->base + GEMINI_PWC_CTRLREG);
+ val |= GEMINI_CTRL_ENABLE;
+ writel(val, gpw->base + GEMINI_PWC_CTRLREG);
+
+ dev_info(dev, "Gemini poweroff driver registered\n");
+
+ return 0;
+}
+
+static const struct of_device_id gemini_poweroff_of_match[] = {
+ {
+ .compatible = "cortina,gemini-power-controller",
+ },
+ {}
+};
+
+static struct platform_driver gemini_poweroff_driver = {
+ .probe = gemini_poweroff_probe,
+ .driver = {
+ .name = "gemini-poweroff",
+ .of_match_table = gemini_poweroff_of_match,
+ },
+};
+builtin_platform_driver(gemini_poweroff_driver);
static struct regmap *map;
static u32 offset;
+static u32 value;
static u32 mask;
static void syscon_poweroff(void)
{
/* Issue the poweroff */
- regmap_write(map, offset, mask);
+ regmap_update_bits(map, offset, mask, value);
mdelay(1000);
static int syscon_poweroff_probe(struct platform_device *pdev)
{
char symname[KSYM_NAME_LEN];
+ int mask_err, value_err;
map = syscon_regmap_lookup_by_phandle(pdev->dev.of_node, "regmap");
if (IS_ERR(map)) {
return -EINVAL;
}
- if (of_property_read_u32(pdev->dev.of_node, "mask", &mask)) {
- dev_err(&pdev->dev, "unable to read 'mask'");
+ value_err = of_property_read_u32(pdev->dev.of_node, "value", &value);
+ mask_err = of_property_read_u32(pdev->dev.of_node, "mask", &mask);
+ if (value_err && mask_err) {
+ dev_err(&pdev->dev, "unable to read 'value' and 'mask'");
return -EINVAL;
}
+ if (value_err) {
+ /* support old binding */
+ value = mask;
+ mask = 0xFFFFFFFF;
+ } else if (mask_err) {
+ /* support value without mask*/
+ mask = 0xFFFFFFFF;
+ }
+
if (pm_power_off) {
lookup_symbol_name((ulong)pm_power_off, symname);
dev_err(&pdev->dev,
Say Y here to enable support for the DS2782/DS2786 standalone battery
gas-gauge.
+config BATTERY_LEGO_EV3
+ tristate "LEGO MINDSTORMS EV3 battery"
+ depends on OF && IIO && GPIOLIB
+ help
+ Say Y here to enable support for the LEGO MINDSTORMS EV3 battery.
+
config BATTERY_PMU
tristate "Apple PMU battery"
depends on PPC32 && ADB_PMU
Say Y here to enable support for battery information on Nokia
RX-51, also known as N900 tablet.
+config CHARGER_CPCAP
+ tristate "CPCAP PMIC Charger Driver"
+ depends on MFD_CPCAP && IIO
+ default MFD_CPCAP
+ help
+ Say Y to enable support for CPCAP PMIC charger driver for Motorola
+ mobile devices such as Droid 4.
+
config CHARGER_ISP1704
tristate "ISP1704 USB Charger Detection"
depends on USB_PHY
config CHARGER_BQ24190
tristate "TI BQ24190 battery charger driver"
depends on I2C
+ depends on EXTCON
depends on GPIOLIB || COMPILE_TEST
help
Say Y to enable support for the TI BQ24190 battery charger.
obj-$(CONFIG_BATTERY_DS2782) += ds2782_battery.o
obj-$(CONFIG_BATTERY_GAUGE_LTC2941) += ltc2941-battery-gauge.o
obj-$(CONFIG_BATTERY_GOLDFISH) += goldfish_battery.o
+obj-$(CONFIG_BATTERY_LEGO_EV3) += lego_ev3_battery.o
obj-$(CONFIG_BATTERY_PMU) += pmu_battery.o
obj-$(CONFIG_BATTERY_OLPC) += olpc_battery.o
obj-$(CONFIG_BATTERY_TOSA) += tosa_battery.o
obj-$(CONFIG_BATTERY_JZ4740) += jz4740-battery.o
obj-$(CONFIG_BATTERY_RX51) += rx51_battery.o
obj-$(CONFIG_AB8500_BM) += ab8500_bmdata.o ab8500_charger.o ab8500_fg.o ab8500_btemp.o abx500_chargalg.o pm2301_charger.o
+obj-$(CONFIG_CHARGER_CPCAP) += cpcap-charger.o
obj-$(CONFIG_CHARGER_ISP1704) += isp1704_charger.o
obj-$(CONFIG_CHARGER_MAX8903) += max8903_charger.o
obj-$(CONFIG_CHARGER_TWL4030) += twl4030_charger.o
};
static const struct abx500_maxim_parameters abx540_maxi_params = {
- .ena_maxi = true,
- .chg_curr = 3000,
- .wait_cycles = 10,
- .charger_curr_step = 200,
+ .ena_maxi = true,
+ .chg_curr = 3000,
+ .wait_cycles = 10,
+ .charger_curr_step = 200,
};
static const struct abx500_bm_charger_parameters chg = {
* GNU General Public License for more details.
*/
+#include <linux/acpi.h>
#include <linux/module.h>
#include <linux/device.h>
#include <linux/regmap.h>
#define ILIM_3000MA 3000 /* 3000mA */
#define AXP288_EXTCON_DEV_NAME "axp288_extcon"
-#define USB_HOST_EXTCON_DEV_NAME "INT3496:00"
+#define USB_HOST_EXTCON_HID "INT3496"
+#define USB_HOST_EXTCON_NAME "INT3496:00"
static const unsigned int cable_ids[] =
{ EXTCON_CHG_USB_SDP, EXTCON_CHG_USB_CDP, EXTCON_CHG_USB_DCP };
return -EPROBE_DEFER;
}
- info->otg.cable = extcon_get_extcon_dev(USB_HOST_EXTCON_DEV_NAME);
- if (info->otg.cable == NULL) {
- dev_dbg(dev, "EXTCON_USB_HOST is not ready, probe deferred\n");
- return -EPROBE_DEFER;
+ if (acpi_dev_present(USB_HOST_EXTCON_HID, NULL, -1)) {
+ info->otg.cable = extcon_get_extcon_dev(USB_HOST_EXTCON_NAME);
+ if (info->otg.cable == NULL) {
+ dev_dbg(dev, "EXTCON_USB_HOST is not ready, probe deferred\n");
+ return -EPROBE_DEFER;
+ }
+ dev_info(&pdev->dev,
+ "Using " USB_HOST_EXTCON_HID " extcon for usb-id\n");
}
platform_set_drvdata(pdev, info);
/* Register for OTG notification */
INIT_WORK(&info->otg.work, axp288_charger_otg_evt_worker);
info->otg.id_nb.notifier_call = axp288_charger_handle_otg_evt;
- ret = devm_extcon_register_notifier(&pdev->dev, info->otg.cable,
+ if (info->otg.cable) {
+ ret = devm_extcon_register_notifier(&pdev->dev, info->otg.cable,
EXTCON_USB_HOST, &info->otg.id_nb);
- if (ret) {
- dev_err(dev, "failed to register EXTCON_USB_HOST notifier\n");
- return ret;
+ if (ret) {
+ dev_err(dev, "failed to register EXTCON_USB_HOST notifier\n");
+ return ret;
+ }
+ schedule_work(&info->otg.work);
}
- schedule_work(&info->otg.work);
/* Register charger interrupts */
for (i = 0; i < CHRG_INTR_END; i++) {
#include <linux/module.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
+#include <linux/extcon.h>
#include <linux/of_irq.h>
#include <linux/of_device.h>
#include <linux/pm_runtime.h>
#include <linux/power_supply.h>
+#include <linux/workqueue.h>
#include <linux/gpio.h>
#include <linux/i2c.h>
-#include <linux/power/bq24190_charger.h>
-
-
#define BQ24190_MANUFACTURER "Texas Instruments"
#define BQ24190_REG_ISC 0x00 /* Input Source Control */
#define BQ24190_REG_POC_WDT_RESET_SHIFT 6
#define BQ24190_REG_POC_CHG_CONFIG_MASK (BIT(5) | BIT(4))
#define BQ24190_REG_POC_CHG_CONFIG_SHIFT 4
+#define BQ24190_REG_POC_CHG_CONFIG_DISABLE 0x0
+#define BQ24190_REG_POC_CHG_CONFIG_CHARGE 0x1
+#define BQ24190_REG_POC_CHG_CONFIG_OTG 0x2
#define BQ24190_REG_POC_SYS_MIN_MASK (BIT(3) | BIT(2) | BIT(1))
#define BQ24190_REG_POC_SYS_MIN_SHIFT 1
#define BQ24190_REG_POC_BOOST_LIM_MASK BIT(0)
struct device *dev;
struct power_supply *charger;
struct power_supply *battery;
+ struct extcon_dev *extcon;
+ struct notifier_block extcon_nb;
+ struct delayed_work extcon_work;
char model_name[I2C_NAME_SIZE];
- kernel_ulong_t model;
- unsigned int gpio_int;
- unsigned int irq;
+ bool initialized;
+ bool irq_event;
struct mutex f_reg_lock;
u8 f_reg;
u8 ss_reg;
* number at that index in the array is the real-world value that it
* represents.
*/
+
+/* REG00[2:0] (IINLIM) in uAh */
+static const int bq24190_isc_iinlim_values[] = {
+ 100000, 150000, 500000, 900000, 1200000, 1500000, 2000000, 3000000
+};
+
/* REG02[7:2] (ICHG) in uAh */
static const int bq24190_ccc_ichg_values[] = {
512000, 576000, 640000, 704000, 768000, 832000, 896000, 960000,
struct power_supply *psy = dev_get_drvdata(dev);
struct bq24190_dev_info *bdi = power_supply_get_drvdata(psy);
struct bq24190_sysfs_field_info *info;
+ ssize_t count;
int ret;
u8 v;
if (!info)
return -EINVAL;
+ ret = pm_runtime_get_sync(bdi->dev);
+ if (ret < 0)
+ return ret;
+
ret = bq24190_read_mask(bdi, info->reg, info->mask, info->shift, &v);
if (ret)
- return ret;
+ count = ret;
+ else
+ count = scnprintf(buf, PAGE_SIZE, "%hhx\n", v);
+
+ pm_runtime_mark_last_busy(bdi->dev);
+ pm_runtime_put_autosuspend(bdi->dev);
- return scnprintf(buf, PAGE_SIZE, "%hhx\n", v);
+ return count;
}
static ssize_t bq24190_sysfs_store(struct device *dev,
if (ret < 0)
return ret;
+ ret = pm_runtime_get_sync(bdi->dev);
+ if (ret < 0)
+ return ret;
+
ret = bq24190_write_mask(bdi, info->reg, info->mask, info->shift, v);
if (ret)
- return ret;
+ count = ret;
+
+ pm_runtime_mark_last_busy(bdi->dev);
+ pm_runtime_put_autosuspend(bdi->dev);
return count;
}
if (ret < 0)
return ret;
- if (!v)
- break;
+ if (v == 0)
+ return 0;
- udelay(10);
+ usleep_range(100, 200);
} while (--limit);
- if (!limit)
- return -EIO;
-
- return 0;
+ return -EIO;
}
/* Charger power supply property routines */
dev_dbg(bdi->dev, "prop: %d\n", psp);
- pm_runtime_get_sync(bdi->dev);
+ ret = pm_runtime_get_sync(bdi->dev);
+ if (ret < 0)
+ return ret;
switch (psp) {
case POWER_SUPPLY_PROP_CHARGE_TYPE:
ret = -ENODATA;
}
- pm_runtime_put_sync(bdi->dev);
+ pm_runtime_mark_last_busy(bdi->dev);
+ pm_runtime_put_autosuspend(bdi->dev);
+
return ret;
}
dev_dbg(bdi->dev, "prop: %d\n", psp);
- pm_runtime_get_sync(bdi->dev);
+ ret = pm_runtime_get_sync(bdi->dev);
+ if (ret < 0)
+ return ret;
switch (psp) {
case POWER_SUPPLY_PROP_CHARGE_TYPE:
ret = -EINVAL;
}
- pm_runtime_put_sync(bdi->dev);
+ pm_runtime_mark_last_busy(bdi->dev);
+ pm_runtime_put_autosuspend(bdi->dev);
+
return ret;
}
dev_dbg(bdi->dev, "prop: %d\n", psp);
- pm_runtime_get_sync(bdi->dev);
+ ret = pm_runtime_get_sync(bdi->dev);
+ if (ret < 0)
+ return ret;
switch (psp) {
case POWER_SUPPLY_PROP_STATUS:
ret = -ENODATA;
}
- pm_runtime_put_sync(bdi->dev);
+ pm_runtime_mark_last_busy(bdi->dev);
+ pm_runtime_put_autosuspend(bdi->dev);
+
return ret;
}
dev_dbg(bdi->dev, "prop: %d\n", psp);
- pm_runtime_get_sync(bdi->dev);
+ ret = pm_runtime_get_sync(bdi->dev);
+ if (ret < 0)
+ return ret;
switch (psp) {
case POWER_SUPPLY_PROP_ONLINE:
ret = -EINVAL;
}
- pm_runtime_put_sync(bdi->dev);
+ pm_runtime_mark_last_busy(bdi->dev);
+ pm_runtime_put_autosuspend(bdi->dev);
+
return ret;
}
.property_is_writeable = bq24190_battery_property_is_writeable,
};
-static irqreturn_t bq24190_irq_handler_thread(int irq, void *data)
+static void bq24190_check_status(struct bq24190_dev_info *bdi)
{
- struct bq24190_dev_info *bdi = data;
const u8 battery_mask_ss = BQ24190_REG_SS_CHRG_STAT_MASK;
const u8 battery_mask_f = BQ24190_REG_F_BAT_FAULT_MASK
| BQ24190_REG_F_NTC_FAULT_MASK;
u8 ss_reg = 0, f_reg = 0;
int i, ret;
- pm_runtime_get_sync(bdi->dev);
-
ret = bq24190_read(bdi, BQ24190_REG_SS, &ss_reg);
if (ret < 0) {
dev_err(bdi->dev, "Can't read SS reg: %d\n", ret);
- goto out;
+ return;
}
i = 0;
ret = bq24190_read(bdi, BQ24190_REG_F, &f_reg);
if (ret < 0) {
dev_err(bdi->dev, "Can't read F reg: %d\n", ret);
- goto out;
+ return;
}
} while (f_reg && ++i < 2);
+ /* ignore over/under voltage fault after disconnect */
+ if (f_reg == (1 << BQ24190_REG_F_CHRG_FAULT_SHIFT) &&
+ !(ss_reg & BQ24190_REG_SS_PG_STAT_MASK))
+ f_reg = 0;
+
if (f_reg != bdi->f_reg) {
- dev_info(bdi->dev,
+ dev_warn(bdi->dev,
"Fault: boost %d, charge %d, battery %d, ntc %d\n",
!!(f_reg & BQ24190_REG_F_BOOST_FAULT_MASK),
!!(f_reg & BQ24190_REG_F_CHRG_FAULT_MASK),
if (alert_battery)
power_supply_changed(bdi->battery);
-out:
- pm_runtime_put_sync(bdi->dev);
-
dev_dbg(bdi->dev, "ss_reg: 0x%02x, f_reg: 0x%02x\n", ss_reg, f_reg);
+}
+
+static irqreturn_t bq24190_irq_handler_thread(int irq, void *data)
+{
+ struct bq24190_dev_info *bdi = data;
+ int error;
+
+ bdi->irq_event = true;
+ error = pm_runtime_get_sync(bdi->dev);
+ if (error < 0) {
+ dev_warn(bdi->dev, "pm_runtime_get failed: %i\n", error);
+ pm_runtime_put_noidle(bdi->dev);
+ return IRQ_NONE;
+ }
+ bq24190_check_status(bdi);
+ pm_runtime_mark_last_busy(bdi->dev);
+ pm_runtime_put_autosuspend(bdi->dev);
+ bdi->irq_event = false;
return IRQ_HANDLED;
}
-static int bq24190_hw_init(struct bq24190_dev_info *bdi)
+static void bq24190_extcon_work(struct work_struct *work)
{
+ struct bq24190_dev_info *bdi =
+ container_of(work, struct bq24190_dev_info, extcon_work.work);
+ int error, iinlim = 0;
u8 v;
- int ret;
-
- pm_runtime_get_sync(bdi->dev);
- /* First check that the device really is what its supposed to be */
- ret = bq24190_read_mask(bdi, BQ24190_REG_VPRS,
- BQ24190_REG_VPRS_PN_MASK,
- BQ24190_REG_VPRS_PN_SHIFT,
- &v);
- if (ret < 0)
- goto out;
+ error = pm_runtime_get_sync(bdi->dev);
+ if (error < 0) {
+ dev_warn(bdi->dev, "pm_runtime_get failed: %i\n", error);
+ pm_runtime_put_noidle(bdi->dev);
+ return;
+ }
- if (v != bdi->model) {
- ret = -ENODEV;
- goto out;
+ if (extcon_get_state(bdi->extcon, EXTCON_CHG_USB_SDP) == 1)
+ iinlim = 500000;
+ else if (extcon_get_state(bdi->extcon, EXTCON_CHG_USB_CDP) == 1 ||
+ extcon_get_state(bdi->extcon, EXTCON_CHG_USB_ACA) == 1)
+ iinlim = 1500000;
+ else if (extcon_get_state(bdi->extcon, EXTCON_CHG_USB_DCP) == 1)
+ iinlim = 2000000;
+
+ if (iinlim) {
+ error = bq24190_set_field_val(bdi, BQ24190_REG_ISC,
+ BQ24190_REG_ISC_IINLIM_MASK,
+ BQ24190_REG_ISC_IINLIM_SHIFT,
+ bq24190_isc_iinlim_values,
+ ARRAY_SIZE(bq24190_isc_iinlim_values),
+ iinlim);
+ if (error < 0)
+ dev_err(bdi->dev, "Can't set IINLIM: %d\n", error);
}
- ret = bq24190_register_reset(bdi);
- if (ret < 0)
- goto out;
+ /* if no charger found and in USB host mode, set OTG 5V boost, else normal */
+ if (!iinlim && extcon_get_state(bdi->extcon, EXTCON_USB_HOST) == 1)
+ v = BQ24190_REG_POC_CHG_CONFIG_OTG;
+ else
+ v = BQ24190_REG_POC_CHG_CONFIG_CHARGE;
- ret = bq24190_set_mode_host(bdi);
- if (ret < 0)
- goto out;
+ error = bq24190_write_mask(bdi, BQ24190_REG_POC,
+ BQ24190_REG_POC_CHG_CONFIG_MASK,
+ BQ24190_REG_POC_CHG_CONFIG_SHIFT,
+ v);
+ if (error < 0)
+ dev_err(bdi->dev, "Can't set CHG_CONFIG: %d\n", error);
- ret = bq24190_read(bdi, BQ24190_REG_SS, &bdi->ss_reg);
-out:
- pm_runtime_put_sync(bdi->dev);
- return ret;
+ pm_runtime_mark_last_busy(bdi->dev);
+ pm_runtime_put_autosuspend(bdi->dev);
}
-#ifdef CONFIG_OF
-static int bq24190_setup_dt(struct bq24190_dev_info *bdi)
+static int bq24190_extcon_event(struct notifier_block *nb, unsigned long event,
+ void *param)
{
- bdi->irq = irq_of_parse_and_map(bdi->dev->of_node, 0);
- if (bdi->irq <= 0)
- return -1;
+ struct bq24190_dev_info *bdi =
+ container_of(nb, struct bq24190_dev_info, extcon_nb);
- return 0;
-}
-#else
-static int bq24190_setup_dt(struct bq24190_dev_info *bdi)
-{
- return -1;
+ /*
+ * The Power-Good detection may take up to 220ms, sometimes
+ * the external charger detection is quicker, and the bq24190 will
+ * reset to iinlim based on its own charger detection (which is not
+ * hooked up when using external charger detection) resulting in
+ * a too low default 500mA iinlim. Delay applying the extcon value
+ * for 300ms to avoid this.
+ */
+ queue_delayed_work(system_wq, &bdi->extcon_work, msecs_to_jiffies(300));
+
+ return NOTIFY_OK;
}
-#endif
-static int bq24190_setup_pdata(struct bq24190_dev_info *bdi,
- struct bq24190_platform_data *pdata)
+static int bq24190_hw_init(struct bq24190_dev_info *bdi)
{
+ u8 v;
int ret;
- if (!gpio_is_valid(pdata->gpio_int))
- return -1;
-
- ret = gpio_request(pdata->gpio_int, dev_name(bdi->dev));
+ /* First check that the device really is what its supposed to be */
+ ret = bq24190_read_mask(bdi, BQ24190_REG_VPRS,
+ BQ24190_REG_VPRS_PN_MASK,
+ BQ24190_REG_VPRS_PN_SHIFT,
+ &v);
if (ret < 0)
- return -1;
+ return ret;
- ret = gpio_direction_input(pdata->gpio_int);
- if (ret < 0)
- goto out;
+ if (v != BQ24190_REG_VPRS_PN_24190 &&
+ v != BQ24190_REG_VPRS_PN_24192I) {
+ dev_err(bdi->dev, "Error unknown model: 0x%02x\n", v);
+ return -ENODEV;
+ }
- bdi->irq = gpio_to_irq(pdata->gpio_int);
- if (!bdi->irq)
- goto out;
+ ret = bq24190_register_reset(bdi);
+ if (ret < 0)
+ return ret;
- bdi->gpio_int = pdata->gpio_int;
- return 0;
+ ret = bq24190_set_mode_host(bdi);
+ if (ret < 0)
+ return ret;
-out:
- gpio_free(pdata->gpio_int);
- return -1;
+ return bq24190_read(bdi, BQ24190_REG_SS, &bdi->ss_reg);
}
static int bq24190_probe(struct i2c_client *client,
{
struct i2c_adapter *adapter = to_i2c_adapter(client->dev.parent);
struct device *dev = &client->dev;
- struct bq24190_platform_data *pdata = client->dev.platform_data;
struct power_supply_config charger_cfg = {}, battery_cfg = {};
struct bq24190_dev_info *bdi;
+ const char *name;
int ret;
if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA)) {
bdi->client = client;
bdi->dev = dev;
- bdi->model = id->driver_data;
strncpy(bdi->model_name, id->name, I2C_NAME_SIZE);
mutex_init(&bdi->f_reg_lock);
bdi->f_reg = 0;
i2c_set_clientdata(client, bdi);
- if (dev->of_node)
- ret = bq24190_setup_dt(bdi);
- else
- ret = bq24190_setup_pdata(bdi, pdata);
-
- if (ret) {
+ if (!client->irq) {
dev_err(dev, "Can't get irq info\n");
return -EINVAL;
}
+ /*
+ * Devicetree platforms should get extcon via phandle (not yet supported).
+ * On ACPI platforms, extcon clients may invoke us with:
+ * struct property_entry pe[] =
+ * { PROPERTY_ENTRY_STRING("extcon-name", client_name), ... };
+ * struct i2c_board_info bi =
+ * { .type = "bq24190", .addr = 0x6b, .properties = pe, .irq = irq };
+ * struct i2c_adapter ad = { ... };
+ * i2c_add_adapter(&ad);
+ * i2c_new_device(&ad, &bi);
+ */
+ if (device_property_read_string(dev, "extcon-name", &name) == 0) {
+ bdi->extcon = extcon_get_extcon_dev(name);
+ if (!bdi->extcon)
+ return -EPROBE_DEFER;
+
+ dev_info(bdi->dev, "using extcon device %s\n", name);
+ }
+
pm_runtime_enable(dev);
- pm_runtime_resume(dev);
+ pm_runtime_use_autosuspend(dev);
+ pm_runtime_set_autosuspend_delay(dev, 600);
+ ret = pm_runtime_get_sync(dev);
+ if (ret < 0) {
+ dev_err(dev, "pm_runtime_get failed: %i\n", ret);
+ goto out_pmrt;
+ }
ret = bq24190_hw_init(bdi);
if (ret < 0) {
dev_err(dev, "Hardware init failed\n");
- goto out1;
+ goto out_pmrt;
}
charger_cfg.drv_data = bdi;
if (IS_ERR(bdi->charger)) {
dev_err(dev, "Can't register charger\n");
ret = PTR_ERR(bdi->charger);
- goto out1;
+ goto out_pmrt;
}
battery_cfg.drv_data = bdi;
if (IS_ERR(bdi->battery)) {
dev_err(dev, "Can't register battery\n");
ret = PTR_ERR(bdi->battery);
- goto out2;
+ goto out_charger;
}
ret = bq24190_sysfs_create_group(bdi);
if (ret) {
dev_err(dev, "Can't create sysfs entries\n");
- goto out3;
+ goto out_battery;
}
- ret = devm_request_threaded_irq(dev, bdi->irq, NULL,
+ bdi->initialized = true;
+
+ ret = devm_request_threaded_irq(dev, client->irq, NULL,
bq24190_irq_handler_thread,
IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
"bq24190-charger", bdi);
if (ret < 0) {
dev_err(dev, "Can't set up irq handler\n");
- goto out4;
+ goto out_sysfs;
+ }
+
+ if (bdi->extcon) {
+ INIT_DELAYED_WORK(&bdi->extcon_work, bq24190_extcon_work);
+ bdi->extcon_nb.notifier_call = bq24190_extcon_event;
+ ret = devm_extcon_register_notifier_all(dev, bdi->extcon,
+ &bdi->extcon_nb);
+ if (ret) {
+ dev_err(dev, "Can't register extcon\n");
+ goto out_sysfs;
+ }
+
+ /* Sync initial cable state */
+ queue_delayed_work(system_wq, &bdi->extcon_work, 0);
}
+ enable_irq_wake(client->irq);
+
+ pm_runtime_mark_last_busy(dev);
+ pm_runtime_put_autosuspend(dev);
+
return 0;
-out4:
+out_sysfs:
bq24190_sysfs_remove_group(bdi);
-out3:
+out_battery:
power_supply_unregister(bdi->battery);
-out2:
+out_charger:
power_supply_unregister(bdi->charger);
-out1:
+out_pmrt:
+ pm_runtime_put_sync(dev);
+ pm_runtime_dont_use_autosuspend(dev);
pm_runtime_disable(dev);
- if (bdi->gpio_int)
- gpio_free(bdi->gpio_int);
return ret;
}
static int bq24190_remove(struct i2c_client *client)
{
struct bq24190_dev_info *bdi = i2c_get_clientdata(client);
+ int error;
- pm_runtime_get_sync(bdi->dev);
- bq24190_register_reset(bdi);
- pm_runtime_put_sync(bdi->dev);
+ error = pm_runtime_get_sync(bdi->dev);
+ if (error < 0) {
+ dev_warn(bdi->dev, "pm_runtime_get failed: %i\n", error);
+ pm_runtime_put_noidle(bdi->dev);
+ }
+ bq24190_register_reset(bdi);
bq24190_sysfs_remove_group(bdi);
power_supply_unregister(bdi->battery);
power_supply_unregister(bdi->charger);
+ if (error >= 0)
+ pm_runtime_put_sync(bdi->dev);
+ pm_runtime_dont_use_autosuspend(bdi->dev);
pm_runtime_disable(bdi->dev);
- if (bdi->gpio_int)
- gpio_free(bdi->gpio_int);
+ return 0;
+}
+
+static __maybe_unused int bq24190_runtime_suspend(struct device *dev)
+{
+ struct i2c_client *client = to_i2c_client(dev);
+ struct bq24190_dev_info *bdi = i2c_get_clientdata(client);
+
+ if (!bdi->initialized)
+ return 0;
+
+ dev_dbg(bdi->dev, "%s\n", __func__);
+
+ return 0;
+}
+
+static __maybe_unused int bq24190_runtime_resume(struct device *dev)
+{
+ struct i2c_client *client = to_i2c_client(dev);
+ struct bq24190_dev_info *bdi = i2c_get_clientdata(client);
+
+ if (!bdi->initialized)
+ return 0;
+
+ if (!bdi->irq_event) {
+ dev_dbg(bdi->dev, "checking events on possible wakeirq\n");
+ bq24190_check_status(bdi);
+ }
return 0;
}
-#ifdef CONFIG_PM_SLEEP
-static int bq24190_pm_suspend(struct device *dev)
+static __maybe_unused int bq24190_pm_suspend(struct device *dev)
{
struct i2c_client *client = to_i2c_client(dev);
struct bq24190_dev_info *bdi = i2c_get_clientdata(client);
+ int error;
+
+ error = pm_runtime_get_sync(bdi->dev);
+ if (error < 0) {
+ dev_warn(bdi->dev, "pm_runtime_get failed: %i\n", error);
+ pm_runtime_put_noidle(bdi->dev);
+ }
- pm_runtime_get_sync(bdi->dev);
bq24190_register_reset(bdi);
- pm_runtime_put_sync(bdi->dev);
+
+ if (error >= 0) {
+ pm_runtime_mark_last_busy(bdi->dev);
+ pm_runtime_put_autosuspend(bdi->dev);
+ }
return 0;
}
-static int bq24190_pm_resume(struct device *dev)
+static __maybe_unused int bq24190_pm_resume(struct device *dev)
{
struct i2c_client *client = to_i2c_client(dev);
struct bq24190_dev_info *bdi = i2c_get_clientdata(client);
+ int error;
bdi->f_reg = 0;
bdi->ss_reg = BQ24190_REG_SS_VBUS_STAT_MASK; /* impossible state */
- pm_runtime_get_sync(bdi->dev);
+ error = pm_runtime_get_sync(bdi->dev);
+ if (error < 0) {
+ dev_warn(bdi->dev, "pm_runtime_get failed: %i\n", error);
+ pm_runtime_put_noidle(bdi->dev);
+ }
+
bq24190_register_reset(bdi);
bq24190_set_mode_host(bdi);
bq24190_read(bdi, BQ24190_REG_SS, &bdi->ss_reg);
- pm_runtime_put_sync(bdi->dev);
+
+ if (error >= 0) {
+ pm_runtime_mark_last_busy(bdi->dev);
+ pm_runtime_put_autosuspend(bdi->dev);
+ }
/* Things may have changed while suspended so alert upper layer */
power_supply_changed(bdi->charger);
return 0;
}
-#endif
-static SIMPLE_DEV_PM_OPS(bq24190_pm_ops, bq24190_pm_suspend, bq24190_pm_resume);
+static const struct dev_pm_ops bq24190_pm_ops = {
+ SET_RUNTIME_PM_OPS(bq24190_runtime_suspend, bq24190_runtime_resume,
+ NULL)
+ SET_SYSTEM_SLEEP_PM_OPS(bq24190_pm_suspend, bq24190_pm_resume)
+};
-/*
- * Only support the bq24190 right now. The bq24192, bq24192i, and bq24193
- * are similar but not identical so the driver needs to be extended to
- * support them.
- */
static const struct i2c_device_id bq24190_i2c_ids[] = {
- { "bq24190", BQ24190_REG_VPRS_PN_24190 },
+ { "bq24190" },
+ { "bq24192i" },
{ },
};
MODULE_DEVICE_TABLE(i2c, bq24190_i2c_ids);
{
struct gpio_desc *irq;
- irq = devm_gpiod_get_index(bq->dev, BQ25890_IRQ_PIN, 0, GPIOD_IN);
+ irq = devm_gpiod_get(bq->dev, BQ25890_IRQ_PIN, GPIOD_IN);
if (IS_ERR(irq)) {
dev_err(bq->dev, "Could not probe irq pin.\n");
return PTR_ERR(irq);
static int charger_extcon_init(struct charger_manager *cm,
struct charger_cable *cable)
{
- int ret = 0;
+ int ret;
/*
* Charger manager use Extcon framework to identify
{
struct charger_desc *desc = cm->desc;
struct charger_regulator *charger;
- int ret = 0;
+ int ret;
int i;
int j;
if (ret < 0) {
dev_err(cm->dev, "Cannot initialize charger(%s)\n",
charger->regulator_name);
- goto err;
+ return ret;
}
cable->charger = charger;
cable->cm = cm;
}
}
-err:
- return ret;
+ return 0;
}
/* help function of sysfs node to control charger(regulator) */
int chargers_externally_control = 1;
char buf[11];
char *str;
- int ret = 0;
+ int ret;
int i;
/* Create sysfs entry to control charger(regulator) */
snprintf(buf, 10, "charger.%d", i);
str = devm_kzalloc(cm->dev,
sizeof(char) * (strlen(buf) + 1), GFP_KERNEL);
- if (!str) {
- ret = -ENOMEM;
- goto err;
- }
+ if (!str)
+ return -ENOMEM;
+
strcpy(str, buf);
charger->attrs[0] = &charger->attr_name.attr;
if (ret < 0) {
dev_err(cm->dev, "Cannot create sysfs entry of %s regulator\n",
charger->regulator_name);
- ret = -EINVAL;
- goto err;
+ return ret;
}
}
if (chargers_externally_control) {
dev_err(cm->dev, "Cannot register regulator because charger-manager must need at least one charger for charging battery\n");
- ret = -EINVAL;
- goto err;
+ return -EINVAL;
}
-err:
- return ret;
+ return 0;
}
static int cm_init_thermal_data(struct charger_manager *cm,
{
struct charger_desc *desc = cm_get_drv_data(pdev);
struct charger_manager *cm;
- int ret = 0, i = 0;
+ int ret, i = 0;
int j = 0;
union power_supply_propval val;
struct power_supply *fuel_gauge;
static int cm_suspend_noirq(struct device *dev)
{
- int ret = 0;
-
if (device_may_wakeup(dev)) {
device_set_wakeup_capable(dev, false);
- ret = -EAGAIN;
+ return -EAGAIN;
}
- return ret;
+ return 0;
}
static bool cm_need_to_awake(void)
--- /dev/null
+/*
+ * Motorola CPCAP PMIC battery charger driver
+ *
+ * Copyright (C) 2017 Tony Lindgren <tony@atomide.com>
+ *
+ * Rewritten for Linux power framework with some parts based on
+ * on earlier driver found in the Motorola Linux kernel:
+ *
+ * Copyright (C) 2009-2010 Motorola, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/atomic.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/notifier.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/power_supply.h>
+#include <linux/regmap.h>
+
+#include <linux/gpio/consumer.h>
+#include <linux/usb/phy_companion.h>
+#include <linux/phy/omap_usb.h>
+#include <linux/usb/otg.h>
+#include <linux/iio/consumer.h>
+#include <linux/mfd/motorola-cpcap.h>
+
+/* CPCAP_REG_CRM register bits */
+#define CPCAP_REG_CRM_UNUSED_641_15 BIT(15) /* 641 = register number */
+#define CPCAP_REG_CRM_UNUSED_641_14 BIT(14) /* 641 = register number */
+#define CPCAP_REG_CRM_CHRG_LED_EN BIT(13)
+#define CPCAP_REG_CRM_RVRSMODE BIT(12)
+#define CPCAP_REG_CRM_ICHRG_TR1 BIT(11)
+#define CPCAP_REG_CRM_ICHRG_TR0 BIT(10)
+#define CPCAP_REG_CRM_FET_OVRD BIT(9)
+#define CPCAP_REG_CRM_FET_CTRL BIT(8)
+#define CPCAP_REG_CRM_VCHRG3 BIT(7)
+#define CPCAP_REG_CRM_VCHRG2 BIT(6)
+#define CPCAP_REG_CRM_VCHRG1 BIT(5)
+#define CPCAP_REG_CRM_VCHRG0 BIT(4)
+#define CPCAP_REG_CRM_ICHRG3 BIT(3)
+#define CPCAP_REG_CRM_ICHRG2 BIT(2)
+#define CPCAP_REG_CRM_ICHRG1 BIT(1)
+#define CPCAP_REG_CRM_ICHRG0 BIT(0)
+
+/* CPCAP_REG_CRM trickle charge voltages */
+#define CPCAP_REG_CRM_TR(val) (((val) & 0x3) << 10)
+#define CPCAP_REG_CRM_TR_0A00 CPCAP_REG_CRM_TR(0x0)
+#define CPCAP_REG_CRM_TR_0A24 CPCAP_REG_CRM_TR(0x1)
+#define CPCAP_REG_CRM_TR_0A48 CPCAP_REG_CRM_TR(0x2)
+#define CPCAP_REG_CRM_TR_0A72 CPCAP_REG_CRM_TR(0x4)
+
+/* CPCAP_REG_CRM charge voltages */
+#define CPCAP_REG_CRM_VCHRG(val) (((val) & 0xf) << 4)
+#define CPCAP_REG_CRM_VCHRG_3V80 CPCAP_REG_CRM_VCHRG(0x0)
+#define CPCAP_REG_CRM_VCHRG_4V10 CPCAP_REG_CRM_VCHRG(0x1)
+#define CPCAP_REG_CRM_VCHRG_4V15 CPCAP_REG_CRM_VCHRG(0x2)
+#define CPCAP_REG_CRM_VCHRG_4V20 CPCAP_REG_CRM_VCHRG(0x3)
+#define CPCAP_REG_CRM_VCHRG_4V22 CPCAP_REG_CRM_VCHRG(0x4)
+#define CPCAP_REG_CRM_VCHRG_4V24 CPCAP_REG_CRM_VCHRG(0x5)
+#define CPCAP_REG_CRM_VCHRG_4V26 CPCAP_REG_CRM_VCHRG(0x6)
+#define CPCAP_REG_CRM_VCHRG_4V28 CPCAP_REG_CRM_VCHRG(0x7)
+#define CPCAP_REG_CRM_VCHRG_4V30 CPCAP_REG_CRM_VCHRG(0x8)
+#define CPCAP_REG_CRM_VCHRG_4V32 CPCAP_REG_CRM_VCHRG(0x9)
+#define CPCAP_REG_CRM_VCHRG_4V34 CPCAP_REG_CRM_VCHRG(0xa)
+#define CPCAP_REG_CRM_VCHRG_4V36 CPCAP_REG_CRM_VCHRG(0xb)
+#define CPCAP_REG_CRM_VCHRG_4V38 CPCAP_REG_CRM_VCHRG(0xc)
+#define CPCAP_REG_CRM_VCHRG_4V40 CPCAP_REG_CRM_VCHRG(0xd)
+#define CPCAP_REG_CRM_VCHRG_4V42 CPCAP_REG_CRM_VCHRG(0xe)
+#define CPCAP_REG_CRM_VCHRG_4V44 CPCAP_REG_CRM_VCHRG(0xf)
+
+/* CPCAP_REG_CRM charge currents */
+#define CPCAP_REG_CRM_ICHRG(val) (((val) & 0xf) << 0)
+#define CPCAP_REG_CRM_ICHRG_0A000 CPCAP_REG_CRM_ICHRG(0x0)
+#define CPCAP_REG_CRM_ICHRG_0A070 CPCAP_REG_CRM_ICHRG(0x1)
+#define CPCAP_REG_CRM_ICHRG_0A176 CPCAP_REG_CRM_ICHRG(0x2)
+#define CPCAP_REG_CRM_ICHRG_0A264 CPCAP_REG_CRM_ICHRG(0x3)
+#define CPCAP_REG_CRM_ICHRG_0A352 CPCAP_REG_CRM_ICHRG(0x4)
+#define CPCAP_REG_CRM_ICHRG_0A440 CPCAP_REG_CRM_ICHRG(0x5)
+#define CPCAP_REG_CRM_ICHRG_0A528 CPCAP_REG_CRM_ICHRG(0x6)
+#define CPCAP_REG_CRM_ICHRG_0A616 CPCAP_REG_CRM_ICHRG(0x7)
+#define CPCAP_REG_CRM_ICHRG_0A704 CPCAP_REG_CRM_ICHRG(0x8)
+#define CPCAP_REG_CRM_ICHRG_0A792 CPCAP_REG_CRM_ICHRG(0x9)
+#define CPCAP_REG_CRM_ICHRG_0A880 CPCAP_REG_CRM_ICHRG(0xa)
+#define CPCAP_REG_CRM_ICHRG_0A968 CPCAP_REG_CRM_ICHRG(0xb)
+#define CPCAP_REG_CRM_ICHRG_1A056 CPCAP_REG_CRM_ICHRG(0xc)
+#define CPCAP_REG_CRM_ICHRG_1A144 CPCAP_REG_CRM_ICHRG(0xd)
+#define CPCAP_REG_CRM_ICHRG_1A584 CPCAP_REG_CRM_ICHRG(0xe)
+#define CPCAP_REG_CRM_ICHRG_NO_LIMIT CPCAP_REG_CRM_ICHRG(0xf)
+
+enum {
+ CPCAP_CHARGER_IIO_BATTDET,
+ CPCAP_CHARGER_IIO_VOLTAGE,
+ CPCAP_CHARGER_IIO_VBUS,
+ CPCAP_CHARGER_IIO_CHRG_CURRENT,
+ CPCAP_CHARGER_IIO_BATT_CURRENT,
+ CPCAP_CHARGER_IIO_NR,
+};
+
+struct cpcap_charger_ddata {
+ struct device *dev;
+ struct regmap *reg;
+ struct list_head irq_list;
+ struct delayed_work detect_work;
+ struct delayed_work vbus_work;
+ struct gpio_desc *gpio[2]; /* gpio_reven0 & 1 */
+
+ struct iio_channel *channels[CPCAP_CHARGER_IIO_NR];
+
+ struct power_supply *usb;
+
+ struct phy_companion comparator; /* For USB VBUS */
+ bool vbus_enabled;
+ atomic_t active;
+
+ int status;
+};
+
+struct cpcap_interrupt_desc {
+ int irq;
+ struct list_head node;
+ const char *name;
+};
+
+struct cpcap_charger_ints_state {
+ bool chrg_det;
+ bool rvrs_chrg;
+ bool vbusov;
+
+ bool chrg_se1b;
+ bool rvrs_mode;
+ bool chrgcurr1;
+ bool vbusvld;
+
+ bool battdetb;
+};
+
+static enum power_supply_property cpcap_charger_props[] = {
+ POWER_SUPPLY_PROP_STATUS,
+ POWER_SUPPLY_PROP_ONLINE,
+ POWER_SUPPLY_PROP_VOLTAGE_NOW,
+ POWER_SUPPLY_PROP_CURRENT_NOW,
+};
+
+static bool cpcap_charger_battery_found(struct cpcap_charger_ddata *ddata)
+{
+ struct iio_channel *channel;
+ int error, value;
+
+ channel = ddata->channels[CPCAP_CHARGER_IIO_BATTDET];
+ error = iio_read_channel_raw(channel, &value);
+ if (error < 0) {
+ dev_warn(ddata->dev, "%s failed: %i\n", __func__, error);
+
+ return false;
+ }
+
+ return value == 1;
+}
+
+static int cpcap_charger_get_charge_voltage(struct cpcap_charger_ddata *ddata)
+{
+ struct iio_channel *channel;
+ int error, value = 0;
+
+ channel = ddata->channels[CPCAP_CHARGER_IIO_VOLTAGE];
+ error = iio_read_channel_processed(channel, &value);
+ if (error < 0) {
+ dev_warn(ddata->dev, "%s failed: %i\n", __func__, error);
+
+ return 0;
+ }
+
+ return value;
+}
+
+static int cpcap_charger_get_charge_current(struct cpcap_charger_ddata *ddata)
+{
+ struct iio_channel *channel;
+ int error, value = 0;
+
+ channel = ddata->channels[CPCAP_CHARGER_IIO_CHRG_CURRENT];
+ error = iio_read_channel_processed(channel, &value);
+ if (error < 0) {
+ dev_warn(ddata->dev, "%s failed: %i\n", __func__, error);
+
+ return 0;
+ }
+
+ return value;
+}
+
+static int cpcap_charger_get_property(struct power_supply *psy,
+ enum power_supply_property psp,
+ union power_supply_propval *val)
+{
+ struct cpcap_charger_ddata *ddata = dev_get_drvdata(psy->dev.parent);
+
+ switch (psp) {
+ case POWER_SUPPLY_PROP_STATUS:
+ val->intval = ddata->status;
+ break;
+ case POWER_SUPPLY_PROP_VOLTAGE_NOW:
+ if (ddata->status == POWER_SUPPLY_STATUS_CHARGING)
+ val->intval = cpcap_charger_get_charge_voltage(ddata) *
+ 1000;
+ else
+ val->intval = 0;
+ break;
+ case POWER_SUPPLY_PROP_CURRENT_NOW:
+ if (ddata->status == POWER_SUPPLY_STATUS_CHARGING)
+ val->intval = cpcap_charger_get_charge_current(ddata) *
+ 1000;
+ else
+ val->intval = 0;
+ break;
+ case POWER_SUPPLY_PROP_ONLINE:
+ val->intval = ddata->status == POWER_SUPPLY_STATUS_CHARGING;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static void cpcap_charger_set_cable_path(struct cpcap_charger_ddata *ddata,
+ bool enabled)
+{
+ if (!ddata->gpio[0])
+ return;
+
+ gpiod_set_value(ddata->gpio[0], enabled);
+}
+
+static void cpcap_charger_set_inductive_path(struct cpcap_charger_ddata *ddata,
+ bool enabled)
+{
+ if (!ddata->gpio[1])
+ return;
+
+ gpiod_set_value(ddata->gpio[1], enabled);
+}
+
+static int cpcap_charger_set_state(struct cpcap_charger_ddata *ddata,
+ int max_voltage, int charge_current,
+ int trickle_current)
+{
+ bool enable;
+ int error;
+
+ enable = max_voltage && (charge_current || trickle_current);
+ dev_dbg(ddata->dev, "%s enable: %i\n", __func__, enable);
+
+ if (!enable) {
+ error = regmap_update_bits(ddata->reg, CPCAP_REG_CRM,
+ 0x3fff,
+ CPCAP_REG_CRM_FET_OVRD |
+ CPCAP_REG_CRM_FET_CTRL);
+ if (error) {
+ ddata->status = POWER_SUPPLY_STATUS_UNKNOWN;
+ goto out_err;
+ }
+
+ ddata->status = POWER_SUPPLY_STATUS_DISCHARGING;
+
+ return 0;
+ }
+
+ error = regmap_update_bits(ddata->reg, CPCAP_REG_CRM, 0x3fff,
+ CPCAP_REG_CRM_CHRG_LED_EN |
+ trickle_current |
+ CPCAP_REG_CRM_FET_OVRD |
+ CPCAP_REG_CRM_FET_CTRL |
+ max_voltage |
+ charge_current);
+ if (error) {
+ ddata->status = POWER_SUPPLY_STATUS_UNKNOWN;
+ goto out_err;
+ }
+
+ ddata->status = POWER_SUPPLY_STATUS_CHARGING;
+
+ return 0;
+
+out_err:
+ dev_err(ddata->dev, "%s failed with %i\n", __func__, error);
+
+ return error;
+}
+
+static bool cpcap_charger_vbus_valid(struct cpcap_charger_ddata *ddata)
+{
+ int error, value = 0;
+ struct iio_channel *channel =
+ ddata->channels[CPCAP_CHARGER_IIO_VBUS];
+
+ error = iio_read_channel_processed(channel, &value);
+ if (error >= 0)
+ return value > 3900 ? true : false;
+
+ dev_err(ddata->dev, "error reading VBUS: %i\n", error);
+
+ return false;
+}
+
+/* VBUS control functions for the USB PHY companion */
+
+static void cpcap_charger_vbus_work(struct work_struct *work)
+{
+ struct cpcap_charger_ddata *ddata;
+ bool vbus = false;
+ int error;
+
+ ddata = container_of(work, struct cpcap_charger_ddata,
+ vbus_work.work);
+
+ if (ddata->vbus_enabled) {
+ vbus = cpcap_charger_vbus_valid(ddata);
+ if (vbus) {
+ dev_info(ddata->dev, "VBUS already provided\n");
+
+ return;
+ }
+
+ cpcap_charger_set_cable_path(ddata, false);
+ cpcap_charger_set_inductive_path(ddata, false);
+
+ error = cpcap_charger_set_state(ddata, 0, 0, 0);
+ if (error)
+ goto out_err;
+
+ error = regmap_update_bits(ddata->reg, CPCAP_REG_CRM,
+ CPCAP_REG_CRM_RVRSMODE,
+ CPCAP_REG_CRM_RVRSMODE);
+ if (error)
+ goto out_err;
+ } else {
+ error = regmap_update_bits(ddata->reg, CPCAP_REG_CRM,
+ CPCAP_REG_CRM_RVRSMODE, 0);
+ if (error)
+ goto out_err;
+
+ cpcap_charger_set_cable_path(ddata, true);
+ cpcap_charger_set_inductive_path(ddata, true);
+ }
+
+ return;
+
+out_err:
+ dev_err(ddata->dev, "%s could not %s vbus: %i\n", __func__,
+ ddata->vbus_enabled ? "enable" : "disable", error);
+}
+
+static int cpcap_charger_set_vbus(struct phy_companion *comparator,
+ bool enabled)
+{
+ struct cpcap_charger_ddata *ddata =
+ container_of(comparator, struct cpcap_charger_ddata,
+ comparator);
+
+ ddata->vbus_enabled = enabled;
+ schedule_delayed_work(&ddata->vbus_work, 0);
+
+ return 0;
+}
+
+/* Charger interrupt handling functions */
+
+static int cpcap_charger_get_ints_state(struct cpcap_charger_ddata *ddata,
+ struct cpcap_charger_ints_state *s)
+{
+ int val, error;
+
+ error = regmap_read(ddata->reg, CPCAP_REG_INTS1, &val);
+ if (error)
+ return error;
+
+ s->chrg_det = val & BIT(13);
+ s->rvrs_chrg = val & BIT(12);
+ s->vbusov = val & BIT(11);
+
+ error = regmap_read(ddata->reg, CPCAP_REG_INTS2, &val);
+ if (error)
+ return error;
+
+ s->chrg_se1b = val & BIT(13);
+ s->rvrs_mode = val & BIT(6);
+ s->chrgcurr1 = val & BIT(4);
+ s->vbusvld = val & BIT(3);
+
+ error = regmap_read(ddata->reg, CPCAP_REG_INTS4, &val);
+ if (error)
+ return error;
+
+ s->battdetb = val & BIT(6);
+
+ return 0;
+}
+
+static void cpcap_usb_detect(struct work_struct *work)
+{
+ struct cpcap_charger_ddata *ddata;
+ struct cpcap_charger_ints_state s;
+ int error;
+
+ ddata = container_of(work, struct cpcap_charger_ddata,
+ detect_work.work);
+
+ error = cpcap_charger_get_ints_state(ddata, &s);
+ if (error)
+ return;
+
+ if (cpcap_charger_vbus_valid(ddata) && s.chrgcurr1) {
+ int max_current;
+
+ if (cpcap_charger_battery_found(ddata))
+ max_current = CPCAP_REG_CRM_ICHRG_1A584;
+ else
+ max_current = CPCAP_REG_CRM_ICHRG_0A528;
+
+ error = cpcap_charger_set_state(ddata,
+ CPCAP_REG_CRM_VCHRG_4V20,
+ max_current,
+ CPCAP_REG_CRM_TR_0A72);
+ if (error)
+ goto out_err;
+ } else {
+ error = cpcap_charger_set_state(ddata, 0, 0, 0);
+ if (error)
+ goto out_err;
+ }
+
+ return;
+
+out_err:
+ dev_err(ddata->dev, "%s failed with %i\n", __func__, error);
+}
+
+static irqreturn_t cpcap_charger_irq_thread(int irq, void *data)
+{
+ struct cpcap_charger_ddata *ddata = data;
+
+ if (!atomic_read(&ddata->active))
+ return IRQ_NONE;
+
+ schedule_delayed_work(&ddata->detect_work, 0);
+
+ return IRQ_HANDLED;
+}
+
+static int cpcap_usb_init_irq(struct platform_device *pdev,
+ struct cpcap_charger_ddata *ddata,
+ const char *name)
+{
+ struct cpcap_interrupt_desc *d;
+ int irq, error;
+
+ irq = platform_get_irq_byname(pdev, name);
+ if (!irq)
+ return -ENODEV;
+
+ error = devm_request_threaded_irq(ddata->dev, irq, NULL,
+ cpcap_charger_irq_thread,
+ IRQF_SHARED,
+ name, ddata);
+ if (error) {
+ dev_err(ddata->dev, "could not get irq %s: %i\n",
+ name, error);
+
+ return error;
+ }
+
+ d = devm_kzalloc(ddata->dev, sizeof(*d), GFP_KERNEL);
+ if (!d)
+ return -ENOMEM;
+
+ d->name = name;
+ d->irq = irq;
+ list_add(&d->node, &ddata->irq_list);
+
+ return 0;
+}
+
+static const char * const cpcap_charger_irqs[] = {
+ /* REG_INT_0 */
+ "chrg_det", "rvrs_chrg",
+
+ /* REG_INT1 */
+ "chrg_se1b", "se0conn", "rvrs_mode", "chrgcurr1", "vbusvld",
+
+ /* REG_INT_3 */
+ "battdetb",
+};
+
+static int cpcap_usb_init_interrupts(struct platform_device *pdev,
+ struct cpcap_charger_ddata *ddata)
+{
+ int i, error;
+
+ for (i = 0; i < ARRAY_SIZE(cpcap_charger_irqs); i++) {
+ error = cpcap_usb_init_irq(pdev, ddata, cpcap_charger_irqs[i]);
+ if (error)
+ return error;
+ }
+
+ return 0;
+}
+
+static void cpcap_charger_init_optional_gpios(struct cpcap_charger_ddata *ddata)
+{
+ int i;
+
+ for (i = 0; i < 2; i++) {
+ ddata->gpio[i] = devm_gpiod_get_index(ddata->dev, "mode",
+ i, GPIOD_OUT_HIGH);
+ if (IS_ERR(ddata->gpio[i])) {
+ dev_info(ddata->dev, "no mode change GPIO%i: %li\n",
+ i, PTR_ERR(ddata->gpio[i]));
+ ddata->gpio[i] = NULL;
+ }
+ }
+}
+
+static int cpcap_charger_init_iio(struct cpcap_charger_ddata *ddata)
+{
+ const char * const names[CPCAP_CHARGER_IIO_NR] = {
+ "battdetb", "battp", "vbus", "chg_isense", "batti",
+ };
+ int error, i;
+
+ for (i = 0; i < CPCAP_CHARGER_IIO_NR; i++) {
+ ddata->channels[i] = devm_iio_channel_get(ddata->dev,
+ names[i]);
+ if (IS_ERR(ddata->channels[i])) {
+ error = PTR_ERR(ddata->channels[i]);
+ goto out_err;
+ }
+
+ if (!ddata->channels[i]->indio_dev) {
+ error = -ENXIO;
+ goto out_err;
+ }
+ }
+
+ return 0;
+
+out_err:
+ dev_err(ddata->dev, "could not initialize VBUS or ID IIO: %i\n",
+ error);
+
+ return error;
+}
+
+static const struct power_supply_desc cpcap_charger_usb_desc = {
+ .name = "cpcap_usb",
+ .type = POWER_SUPPLY_TYPE_USB,
+ .properties = cpcap_charger_props,
+ .num_properties = ARRAY_SIZE(cpcap_charger_props),
+ .get_property = cpcap_charger_get_property,
+};
+
+#ifdef CONFIG_OF
+static const struct of_device_id cpcap_charger_id_table[] = {
+ {
+ .compatible = "motorola,mapphone-cpcap-charger",
+ },
+ {},
+};
+MODULE_DEVICE_TABLE(of, cpcap_charger_id_table);
+#endif
+
+static int cpcap_charger_probe(struct platform_device *pdev)
+{
+ struct cpcap_charger_ddata *ddata;
+ const struct of_device_id *of_id;
+ int error;
+
+ of_id = of_match_device(of_match_ptr(cpcap_charger_id_table),
+ &pdev->dev);
+ if (!of_id)
+ return -EINVAL;
+
+ ddata = devm_kzalloc(&pdev->dev, sizeof(*ddata), GFP_KERNEL);
+ if (!ddata)
+ return -ENOMEM;
+
+ ddata->dev = &pdev->dev;
+
+ ddata->reg = dev_get_regmap(ddata->dev->parent, NULL);
+ if (!ddata->reg)
+ return -ENODEV;
+
+ INIT_LIST_HEAD(&ddata->irq_list);
+ INIT_DELAYED_WORK(&ddata->detect_work, cpcap_usb_detect);
+ INIT_DELAYED_WORK(&ddata->vbus_work, cpcap_charger_vbus_work);
+ platform_set_drvdata(pdev, ddata);
+
+ error = cpcap_charger_init_iio(ddata);
+ if (error)
+ return error;
+
+ atomic_set(&ddata->active, 1);
+
+ ddata->usb = devm_power_supply_register(ddata->dev,
+ &cpcap_charger_usb_desc,
+ NULL);
+ if (IS_ERR(ddata->usb)) {
+ error = PTR_ERR(ddata->usb);
+ dev_err(ddata->dev, "failed to register USB charger: %i\n",
+ error);
+
+ return error;
+ }
+
+ error = cpcap_usb_init_interrupts(pdev, ddata);
+ if (error)
+ return error;
+
+ ddata->comparator.set_vbus = cpcap_charger_set_vbus;
+ error = omap_usb2_set_comparator(&ddata->comparator);
+ if (error == -ENODEV) {
+ dev_info(ddata->dev, "charger needs phy, deferring probe\n");
+ return -EPROBE_DEFER;
+ }
+
+ cpcap_charger_init_optional_gpios(ddata);
+
+ schedule_delayed_work(&ddata->detect_work, 0);
+
+ return 0;
+}
+
+static int cpcap_charger_remove(struct platform_device *pdev)
+{
+ struct cpcap_charger_ddata *ddata = platform_get_drvdata(pdev);
+ int error;
+
+ atomic_set(&ddata->active, 0);
+ error = omap_usb2_set_comparator(NULL);
+ if (error)
+ dev_warn(ddata->dev, "could not clear USB comparator: %i\n",
+ error);
+
+ error = cpcap_charger_set_state(ddata, 0, 0, 0);
+ if (error)
+ dev_warn(ddata->dev, "could not clear charger: %i\n",
+ error);
+ cancel_delayed_work_sync(&ddata->vbus_work);
+ cancel_delayed_work_sync(&ddata->detect_work);
+
+ return 0;
+}
+
+static struct platform_driver cpcap_charger_driver = {
+ .probe = cpcap_charger_probe,
+ .driver = {
+ .name = "cpcap-charger",
+ .of_match_table = of_match_ptr(cpcap_charger_id_table),
+ },
+ .remove = cpcap_charger_remove,
+};
+module_platform_driver(cpcap_charger_driver);
+
+MODULE_AUTHOR("Tony Lindgren <tony@atomide.com>");
+MODULE_DESCRIPTION("CPCAP Battery Charger Interface driver");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:cpcap-charger");
--- /dev/null
+/*
+ * Battery driver for LEGO MINDSTORMS EV3
+ *
+ * Copyright (C) 2017 David Lechner <david@lechnology.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/gpio/consumer.h>
+#include <linux/iio/consumer.h>
+#include <linux/iio/types.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/power_supply.h>
+
+struct lego_ev3_battery {
+ struct iio_channel *iio_v;
+ struct iio_channel *iio_i;
+ struct gpio_desc *rechargeable_gpio;
+ struct power_supply *psy;
+ int technology;
+ int v_max;
+ int v_min;
+};
+
+static int lego_ev3_battery_get_property(struct power_supply *psy,
+ enum power_supply_property psp,
+ union power_supply_propval *val)
+{
+ struct lego_ev3_battery *batt = power_supply_get_drvdata(psy);
+ int val2;
+
+ switch (psp) {
+ case POWER_SUPPLY_PROP_TECHNOLOGY:
+ val->intval = batt->technology;
+ break;
+ case POWER_SUPPLY_PROP_VOLTAGE_NOW:
+ /* battery voltage is iio channel * 2 + Vce of transistor */
+ iio_read_channel_processed(batt->iio_v, &val->intval);
+ val->intval *= 2000;
+ val->intval += 200000;
+ /* plus adjust for shunt resistor drop */
+ iio_read_channel_processed(batt->iio_i, &val2);
+ val2 *= 1000;
+ val2 /= 15;
+ val->intval += val2;
+ break;
+ case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN:
+ val->intval = batt->v_max;
+ break;
+ case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN:
+ val->intval = batt->v_min;
+ break;
+ case POWER_SUPPLY_PROP_CURRENT_NOW:
+ /* battery current is iio channel / 15 / 0.05 ohms */
+ iio_read_channel_processed(batt->iio_i, &val->intval);
+ val->intval *= 20000;
+ val->intval /= 15;
+ break;
+ case POWER_SUPPLY_PROP_SCOPE:
+ val->intval = POWER_SUPPLY_SCOPE_SYSTEM;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int lego_ev3_battery_set_property(struct power_supply *psy,
+ enum power_supply_property psp,
+ const union power_supply_propval *val)
+{
+ struct lego_ev3_battery *batt = power_supply_get_drvdata(psy);
+
+ switch (psp) {
+ case POWER_SUPPLY_PROP_TECHNOLOGY:
+ /*
+ * Only allow changing technology from Unknown to NiMH. Li-ion
+ * batteries are automatically detected and should not be
+ * overridden. Rechargeable AA batteries, on the other hand,
+ * cannot be automatically detected, and so must be manually
+ * specified. This should only be set once during system init,
+ * so there is no mechanism to go back to Unknown.
+ */
+ if (batt->technology != POWER_SUPPLY_TECHNOLOGY_UNKNOWN)
+ return -EINVAL;
+ switch (val->intval) {
+ case POWER_SUPPLY_TECHNOLOGY_NiMH:
+ batt->technology = POWER_SUPPLY_TECHNOLOGY_NiMH;
+ batt->v_max = 7800000;
+ batt->v_min = 5400000;
+ break;
+ default:
+ return -EINVAL;
+ }
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int lego_ev3_battery_property_is_writeable(struct power_supply *psy,
+ enum power_supply_property psp)
+{
+ struct lego_ev3_battery *batt = power_supply_get_drvdata(psy);
+
+ return psp == POWER_SUPPLY_PROP_TECHNOLOGY &&
+ batt->technology == POWER_SUPPLY_TECHNOLOGY_UNKNOWN;
+}
+
+static enum power_supply_property lego_ev3_battery_props[] = {
+ POWER_SUPPLY_PROP_TECHNOLOGY,
+ POWER_SUPPLY_PROP_VOLTAGE_NOW,
+ POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN,
+ POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN,
+ POWER_SUPPLY_PROP_CURRENT_NOW,
+ POWER_SUPPLY_PROP_SCOPE,
+};
+
+static const struct power_supply_desc lego_ev3_battery_desc = {
+ .name = "lego-ev3-battery",
+ .type = POWER_SUPPLY_TYPE_BATTERY,
+ .properties = lego_ev3_battery_props,
+ .num_properties = ARRAY_SIZE(lego_ev3_battery_props),
+ .get_property = lego_ev3_battery_get_property,
+ .set_property = lego_ev3_battery_set_property,
+ .property_is_writeable = lego_ev3_battery_property_is_writeable,
+};
+
+static int lego_ev3_battery_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct lego_ev3_battery *batt;
+ struct power_supply_config psy_cfg = {};
+ int err;
+
+ batt = devm_kzalloc(dev, sizeof(*batt), GFP_KERNEL);
+ if (!batt)
+ return -ENOMEM;
+
+ platform_set_drvdata(pdev, batt);
+
+ batt->iio_v = devm_iio_channel_get(dev, "voltage");
+ err = PTR_ERR_OR_ZERO(batt->iio_v);
+ if (err) {
+ if (err != -EPROBE_DEFER)
+ dev_err(dev, "Failed to get voltage iio channel\n");
+ return err;
+ }
+
+ batt->iio_i = devm_iio_channel_get(dev, "current");
+ err = PTR_ERR_OR_ZERO(batt->iio_i);
+ if (err) {
+ if (err != -EPROBE_DEFER)
+ dev_err(dev, "Failed to get current iio channel\n");
+ return err;
+ }
+
+ batt->rechargeable_gpio = devm_gpiod_get(dev, "rechargeable", GPIOD_IN);
+ err = PTR_ERR_OR_ZERO(batt->rechargeable_gpio);
+ if (err) {
+ if (err != -EPROBE_DEFER)
+ dev_err(dev, "Failed to get rechargeable gpio\n");
+ return err;
+ }
+
+ /*
+ * The rechargeable battery indication switch cannot be changed without
+ * removing the battery, so we only need to read it once.
+ */
+ if (gpiod_get_value(batt->rechargeable_gpio)) {
+ /* 2-cell Li-ion, 7.4V nominal */
+ batt->technology = POWER_SUPPLY_TECHNOLOGY_LION;
+ batt->v_max = 84000000;
+ batt->v_min = 60000000;
+ } else {
+ /* 6x AA Alkaline, 9V nominal */
+ batt->technology = POWER_SUPPLY_TECHNOLOGY_UNKNOWN;
+ batt->v_max = 90000000;
+ batt->v_min = 48000000;
+ }
+
+ psy_cfg.of_node = pdev->dev.of_node;
+ psy_cfg.drv_data = batt;
+
+ batt->psy = devm_power_supply_register(dev, &lego_ev3_battery_desc,
+ &psy_cfg);
+ err = PTR_ERR_OR_ZERO(batt->psy);
+ if (err) {
+ dev_err(dev, "failed to register power supply\n");
+ return err;
+ }
+
+ return 0;
+}
+
+static const struct of_device_id of_lego_ev3_battery_match[] = {
+ { .compatible = "lego,ev3-battery", },
+ { }
+};
+MODULE_DEVICE_TABLE(of, of_lego_ev3_battery_match);
+
+static struct platform_driver lego_ev3_battery_driver = {
+ .driver = {
+ .name = "lego-ev3-battery",
+ .of_match_table = of_lego_ev3_battery_match,
+ },
+ .probe = lego_ev3_battery_probe,
+};
+module_platform_driver(lego_ev3_battery_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("David Lechner <david@lechnology.com>");
+MODULE_DESCRIPTION("LEGO MINDSTORMS EV3 Battery Driver");
{
struct lp8788_charger *pchg = dev_get_drvdata(dev);
char *stime[] = { "400ms", "5min", "10min", "15min",
- "20min", "25min", "30min" "No timeout" };
+ "20min", "25min", "30min", "No timeout" };
u8 val;
lp8788_read_byte(pchg->lp, LP8788_CHG_EOC, &val);
*/
#include <linux/kernel.h>
#include <linux/module.h>
+#include <linux/of_device.h>
#include <linux/types.h>
#include <linux/errno.h>
#include <linux/swab.h>
struct power_supply *supply; /* Supply pointer */
struct power_supply_desc supply_desc; /* Supply description */
struct delayed_work work; /* Work scheduler */
- int num_regs; /* Number of registers (chip type) */
+ unsigned long num_regs; /* Number of registers (chip type) */
int charge; /* Last charge register content */
int r_sense; /* mOhm */
int Qlsb; /* nAh */
np = of_node_get(client->dev.of_node);
- info->num_regs = id->driver_data;
+ info->num_regs = (unsigned long)of_device_get_match_data(&client->dev);
info->supply_desc.name = np->name;
/* r_sense can be negative, when sense+ is connected to the battery
};
MODULE_DEVICE_TABLE(i2c, ltc294x_i2c_id);
+static const struct of_device_id ltc294x_i2c_of_match[] = {
+ {
+ .compatible = "lltc,ltc2941",
+ .data = (void *)LTC2941_NUM_REGS
+ },
+ {
+ .compatible = "lltc,ltc2943",
+ .data = (void *)LTC2943_NUM_REGS
+ },
+ { },
+};
+MODULE_DEVICE_TABLE(of, ltc294x_i2c_of_match);
+
static struct i2c_driver ltc294x_driver = {
.driver = {
.name = "LTC2941",
+ .of_match_table = ltc294x_i2c_of_match,
.pm = LTC294X_PM_OPS,
},
.probe = ltc294x_i2c_probe,
};
MODULE_DEVICE_TABLE(i2c, max17040_id);
+static const struct of_device_id max17040_of_match[] = {
+ { .compatible = "maxim,max17040" },
+ { .compatible = "maxim,max77836-battery" },
+ { },
+};
+MODULE_DEVICE_TABLE(of, max17040_of_match);
+
static struct i2c_driver max17040_i2c_driver = {
.driver = {
.name = "max17040",
+ .of_match_table = max17040_of_match,
.pm = MAX17040_PM_OPS,
},
.probe = max17040_probe,
static bool sbs_readable_reg(struct device *dev, unsigned int reg)
{
- if (reg < SBS_CHARGER_REG_SPEC_INFO)
- return false;
- else
- return true;
+ return reg >= SBS_CHARGER_REG_SPEC_INFO;
}
static bool sbs_volatile_reg(struct device *dev, unsigned int reg)
{
int ret;
- dev_dbg(charger->dev, "%s\n", __func__);
-
/*
* tps65217 rev. G, p. 31 (see p. 32 for NTC schematic)
*
int ret;
int i;
- dev_dbg(&pdev->dev, "%s\n", __func__);
-
charger = devm_kzalloc(&pdev->dev, sizeof(*charger), GFP_KERNEL);
if (!charger)
return -ENOMEM;
return ret;
}
-static int __exit twl4030_bci_remove(struct platform_device *pdev)
+static int twl4030_bci_remove(struct platform_device *pdev)
{
struct twl4030_bci *bci = platform_get_drvdata(pdev);
static struct platform_driver twl4030_bci_driver = {
.probe = twl4030_bci_probe,
+ .remove = twl4030_bci_remove,
.driver = {
.name = "twl4030_bci",
.of_match_table = of_match_ptr(twl_bci_of_match),
},
- .remove = __exit_p(twl4030_bci_remove),
};
module_platform_driver(twl4030_bci_driver);
/* posix clock implementation */
-static int ptp_clock_getres(struct posix_clock *pc, struct timespec *tp)
+static int ptp_clock_getres(struct posix_clock *pc, struct timespec64 *tp)
{
tp->tv_sec = 0;
tp->tv_nsec = 1;
return 0;
}
-static int ptp_clock_settime(struct posix_clock *pc, const struct timespec *tp)
+static int ptp_clock_settime(struct posix_clock *pc, const struct timespec64 *tp)
{
struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
- struct timespec64 ts = timespec_to_timespec64(*tp);
- return ptp->info->settime64(ptp->info, &ts);
+ return ptp->info->settime64(ptp->info, tp);
}
-static int ptp_clock_gettime(struct posix_clock *pc, struct timespec *tp)
+static int ptp_clock_gettime(struct posix_clock *pc, struct timespec64 *tp)
{
struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
- struct timespec64 ts;
int err;
- err = ptp->info->gettime64(ptp->info, &ts);
- if (!err)
- *tp = timespec64_to_timespec(ts);
+ err = ptp->info->gettime64(ptp->info, tp);
return err;
}
ops = ptp->info;
if (tx->modes & ADJ_SETOFFSET) {
- struct timespec ts;
+ struct timespec64 ts;
ktime_t kt;
s64 delta;
if ((unsigned long) ts.tv_nsec >= NSEC_PER_SEC)
return -EINVAL;
- kt = timespec_to_ktime(ts);
+ kt = timespec64_to_ktime(ts);
delta = ktime_to_ns(kt);
err = ops->adjtime(ops, delta);
} else if (tx->modes & ADJ_FREQUENCY) {
.clk_rate = 19200000,
.npwm = 4,
.base_unit_bits = 22,
+ .bypass = true,
+};
+
+/* Tangier */
+static const struct pwm_lpss_boardinfo pwm_lpss_tng_info = {
+ .clk_rate = 19200000,
+ .npwm = 4,
+ .base_unit_bits = 22,
};
static int pwm_lpss_probe_pci(struct pci_dev *pdev,
{ PCI_VDEVICE(INTEL, 0x0ac8), (unsigned long)&pwm_lpss_bxt_info},
{ PCI_VDEVICE(INTEL, 0x0f08), (unsigned long)&pwm_lpss_byt_info},
{ PCI_VDEVICE(INTEL, 0x0f09), (unsigned long)&pwm_lpss_byt_info},
- { PCI_VDEVICE(INTEL, 0x11a5), (unsigned long)&pwm_lpss_bxt_info},
+ { PCI_VDEVICE(INTEL, 0x11a5), (unsigned long)&pwm_lpss_tng_info},
{ PCI_VDEVICE(INTEL, 0x1ac8), (unsigned long)&pwm_lpss_bxt_info},
{ PCI_VDEVICE(INTEL, 0x2288), (unsigned long)&pwm_lpss_bsw_info},
{ PCI_VDEVICE(INTEL, 0x2289), (unsigned long)&pwm_lpss_bsw_info},
.clk_rate = 19200000,
.npwm = 4,
.base_unit_bits = 22,
+ .bypass = true,
};
static int pwm_lpss_probe_platform(struct platform_device *pdev)
writel(value, lpwm->regs + pwm->hwpwm * PWM_SIZE + PWM);
}
-static int pwm_lpss_update(struct pwm_device *pwm)
+static int pwm_lpss_wait_for_update(struct pwm_device *pwm)
{
struct pwm_lpss_chip *lpwm = to_lpwm(pwm->chip);
const void __iomem *addr = lpwm->regs + pwm->hwpwm * PWM_SIZE + PWM;
u32 val;
int err;
- pwm_lpss_write(pwm, pwm_lpss_read(pwm) | PWM_SW_UPDATE);
-
/*
* PWM Configuration register has SW_UPDATE bit that is set when a new
* configuration is written to the register. The bit is automatically
pwm_lpss_write(pwm, ctrl);
}
+static inline void pwm_lpss_cond_enable(struct pwm_device *pwm, bool cond)
+{
+ if (cond)
+ pwm_lpss_write(pwm, pwm_lpss_read(pwm) | PWM_ENABLE);
+}
+
static int pwm_lpss_apply(struct pwm_chip *chip, struct pwm_device *pwm,
struct pwm_state *state)
{
return ret;
}
pwm_lpss_prepare(lpwm, pwm, state->duty_cycle, state->period);
- ret = pwm_lpss_update(pwm);
+ pwm_lpss_write(pwm, pwm_lpss_read(pwm) | PWM_SW_UPDATE);
+ pwm_lpss_cond_enable(pwm, lpwm->info->bypass == false);
+ ret = pwm_lpss_wait_for_update(pwm);
if (ret) {
pm_runtime_put(chip->dev);
return ret;
}
- pwm_lpss_write(pwm, pwm_lpss_read(pwm) | PWM_ENABLE);
+ pwm_lpss_cond_enable(pwm, lpwm->info->bypass == true);
} else {
ret = pwm_lpss_is_updating(pwm);
if (ret)
return ret;
pwm_lpss_prepare(lpwm, pwm, state->duty_cycle, state->period);
- return pwm_lpss_update(pwm);
+ pwm_lpss_write(pwm, pwm_lpss_read(pwm) | PWM_SW_UPDATE);
+ return pwm_lpss_wait_for_update(pwm);
}
} else if (pwm_is_enabled(pwm)) {
pwm_lpss_write(pwm, pwm_lpss_read(pwm) & ~PWM_ENABLE);
unsigned long clk_rate;
unsigned int npwm;
unsigned long base_unit_bits;
+ bool bypass;
};
struct pwm_lpss_chip *pwm_lpss_probe(struct device *dev, struct resource *r,
return 0;
}
+static int rockchip_pwm_enable(struct pwm_chip *chip,
+ struct pwm_device *pwm,
+ bool enable,
+ enum pwm_polarity polarity)
+{
+ struct rockchip_pwm_chip *pc = to_rockchip_pwm_chip(chip);
+ int ret;
+
+ if (enable) {
+ ret = clk_enable(pc->clk);
+ if (ret)
+ return ret;
+ }
+
+ pc->data->set_enable(chip, pwm, enable, polarity);
+
+ if (!enable)
+ clk_disable(pc->clk);
+
+ return 0;
+}
+
static int rockchip_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
struct pwm_state *state)
{
return ret;
if (state->polarity != curstate.polarity && enabled) {
- pc->data->set_enable(chip, pwm, false, state->polarity);
+ ret = rockchip_pwm_enable(chip, pwm, false, state->polarity);
+ if (ret)
+ goto out;
enabled = false;
}
ret = rockchip_pwm_config(chip, pwm, state->duty_cycle, state->period);
if (ret) {
if (enabled != curstate.enabled)
- pc->data->set_enable(chip, pwm, !enabled,
- state->polarity);
-
+ rockchip_pwm_enable(chip, pwm, !enabled,
+ state->polarity);
goto out;
}
- if (state->enabled != enabled)
- pc->data->set_enable(chip, pwm, state->enabled,
- state->polarity);
+ if (state->enabled != enabled) {
+ ret = rockchip_pwm_enable(chip, pwm, state->enabled,
+ state->polarity);
+ if (ret)
+ goto out;
+ }
/*
* Update the state with the real hardware, which can differ a bit
-obj-$(CONFIG_RAS) += ras.o debugfs.o
+obj-$(CONFIG_RAS) += ras.o debugfs.o
+obj-$(CONFIG_RAS_CEC) += cec.o
--- /dev/null
+#include <linux/mm.h>
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+
+#include <asm/mce.h>
+
+#include "debugfs.h"
+
+/*
+ * RAS Correctable Errors Collector
+ *
+ * This is a simple gadget which collects correctable errors and counts their
+ * occurrence per physical page address.
+ *
+ * We've opted for possibly the simplest data structure to collect those - an
+ * array of the size of a memory page. It stores 512 u64's with the following
+ * structure:
+ *
+ * [63 ... PFN ... 12 | 11 ... generation ... 10 | 9 ... count ... 0]
+ *
+ * The generation in the two highest order bits is two bits which are set to 11b
+ * on every insertion. During the course of each entry's existence, the
+ * generation field gets decremented during spring cleaning to 10b, then 01b and
+ * then 00b.
+ *
+ * This way we're employing the natural numeric ordering to make sure that newly
+ * inserted/touched elements have higher 12-bit counts (which we've manufactured)
+ * and thus iterating over the array initially won't kick out those elements
+ * which were inserted last.
+ *
+ * Spring cleaning is what we do when we reach a certain number CLEAN_ELEMS of
+ * elements entered into the array, during which, we're decaying all elements.
+ * If, after decay, an element gets inserted again, its generation is set to 11b
+ * to make sure it has higher numerical count than other, older elements and
+ * thus emulate an an LRU-like behavior when deleting elements to free up space
+ * in the page.
+ *
+ * When an element reaches it's max count of count_threshold, we try to poison
+ * it by assuming that errors triggered count_threshold times in a single page
+ * are excessive and that page shouldn't be used anymore. count_threshold is
+ * initialized to COUNT_MASK which is the maximum.
+ *
+ * That error event entry causes cec_add_elem() to return !0 value and thus
+ * signal to its callers to log the error.
+ *
+ * To the question why we've chosen a page and moving elements around with
+ * memmove(), it is because it is a very simple structure to handle and max data
+ * movement is 4K which on highly optimized modern CPUs is almost unnoticeable.
+ * We wanted to avoid the pointer traversal of more complex structures like a
+ * linked list or some sort of a balancing search tree.
+ *
+ * Deleting an element takes O(n) but since it is only a single page, it should
+ * be fast enough and it shouldn't happen all too often depending on error
+ * patterns.
+ */
+
+#undef pr_fmt
+#define pr_fmt(fmt) "RAS: " fmt
+
+/*
+ * We use DECAY_BITS bits of PAGE_SHIFT bits for counting decay, i.e., how long
+ * elements have stayed in the array without having been accessed again.
+ */
+#define DECAY_BITS 2
+#define DECAY_MASK ((1ULL << DECAY_BITS) - 1)
+#define MAX_ELEMS (PAGE_SIZE / sizeof(u64))
+
+/*
+ * Threshold amount of inserted elements after which we start spring
+ * cleaning.
+ */
+#define CLEAN_ELEMS (MAX_ELEMS >> DECAY_BITS)
+
+/* Bits which count the number of errors happened in this 4K page. */
+#define COUNT_BITS (PAGE_SHIFT - DECAY_BITS)
+#define COUNT_MASK ((1ULL << COUNT_BITS) - 1)
+#define FULL_COUNT_MASK (PAGE_SIZE - 1)
+
+/*
+ * u64: [ 63 ... 12 | DECAY_BITS | COUNT_BITS ]
+ */
+
+#define PFN(e) ((e) >> PAGE_SHIFT)
+#define DECAY(e) (((e) >> COUNT_BITS) & DECAY_MASK)
+#define COUNT(e) ((unsigned int)(e) & COUNT_MASK)
+#define FULL_COUNT(e) ((e) & (PAGE_SIZE - 1))
+
+static struct ce_array {
+ u64 *array; /* container page */
+ unsigned int n; /* number of elements in the array */
+
+ unsigned int decay_count; /*
+ * number of element insertions/increments
+ * since the last spring cleaning.
+ */
+
+ u64 pfns_poisoned; /*
+ * number of PFNs which got poisoned.
+ */
+
+ u64 ces_entered; /*
+ * The number of correctable errors
+ * entered into the collector.
+ */
+
+ u64 decays_done; /*
+ * Times we did spring cleaning.
+ */
+
+ union {
+ struct {
+ __u32 disabled : 1, /* cmdline disabled */
+ __resv : 31;
+ };
+ __u32 flags;
+ };
+} ce_arr;
+
+static DEFINE_MUTEX(ce_mutex);
+static u64 dfs_pfn;
+
+/* Amount of errors after which we offline */
+static unsigned int count_threshold = COUNT_MASK;
+
+/*
+ * The timer "decays" element count each timer_interval which is 24hrs by
+ * default.
+ */
+
+#define CEC_TIMER_DEFAULT_INTERVAL 24 * 60 * 60 /* 24 hrs */
+#define CEC_TIMER_MIN_INTERVAL 1 * 60 * 60 /* 1h */
+#define CEC_TIMER_MAX_INTERVAL 30 * 24 * 60 * 60 /* one month */
+static struct timer_list cec_timer;
+static u64 timer_interval = CEC_TIMER_DEFAULT_INTERVAL;
+
+/*
+ * Decrement decay value. We're using DECAY_BITS bits to denote decay of an
+ * element in the array. On insertion and any access, it gets reset to max.
+ */
+static void do_spring_cleaning(struct ce_array *ca)
+{
+ int i;
+
+ for (i = 0; i < ca->n; i++) {
+ u8 decay = DECAY(ca->array[i]);
+
+ if (!decay)
+ continue;
+
+ decay--;
+
+ ca->array[i] &= ~(DECAY_MASK << COUNT_BITS);
+ ca->array[i] |= (decay << COUNT_BITS);
+ }
+ ca->decay_count = 0;
+ ca->decays_done++;
+}
+
+/*
+ * @interval in seconds
+ */
+static void cec_mod_timer(struct timer_list *t, unsigned long interval)
+{
+ unsigned long iv;
+
+ iv = interval * HZ + jiffies;
+
+ mod_timer(t, round_jiffies(iv));
+}
+
+static void cec_timer_fn(unsigned long data)
+{
+ struct ce_array *ca = (struct ce_array *)data;
+
+ do_spring_cleaning(ca);
+
+ cec_mod_timer(&cec_timer, timer_interval);
+}
+
+/*
+ * @to: index of the smallest element which is >= then @pfn.
+ *
+ * Return the index of the pfn if found, otherwise negative value.
+ */
+static int __find_elem(struct ce_array *ca, u64 pfn, unsigned int *to)
+{
+ u64 this_pfn;
+ int min = 0, max = ca->n;
+
+ while (min < max) {
+ int tmp = (max + min) >> 1;
+
+ this_pfn = PFN(ca->array[tmp]);
+
+ if (this_pfn < pfn)
+ min = tmp + 1;
+ else if (this_pfn > pfn)
+ max = tmp;
+ else {
+ min = tmp;
+ break;
+ }
+ }
+
+ if (to)
+ *to = min;
+
+ this_pfn = PFN(ca->array[min]);
+
+ if (this_pfn == pfn)
+ return min;
+
+ return -ENOKEY;
+}
+
+static int find_elem(struct ce_array *ca, u64 pfn, unsigned int *to)
+{
+ WARN_ON(!to);
+
+ if (!ca->n) {
+ *to = 0;
+ return -ENOKEY;
+ }
+ return __find_elem(ca, pfn, to);
+}
+
+static void del_elem(struct ce_array *ca, int idx)
+{
+ /* Save us a function call when deleting the last element. */
+ if (ca->n - (idx + 1))
+ memmove((void *)&ca->array[idx],
+ (void *)&ca->array[idx + 1],
+ (ca->n - (idx + 1)) * sizeof(u64));
+
+ ca->n--;
+}
+
+static u64 del_lru_elem_unlocked(struct ce_array *ca)
+{
+ unsigned int min = FULL_COUNT_MASK;
+ int i, min_idx = 0;
+
+ for (i = 0; i < ca->n; i++) {
+ unsigned int this = FULL_COUNT(ca->array[i]);
+
+ if (min > this) {
+ min = this;
+ min_idx = i;
+ }
+ }
+
+ del_elem(ca, min_idx);
+
+ return PFN(ca->array[min_idx]);
+}
+
+/*
+ * We return the 0th pfn in the error case under the assumption that it cannot
+ * be poisoned and excessive CEs in there are a serious deal anyway.
+ */
+static u64 __maybe_unused del_lru_elem(void)
+{
+ struct ce_array *ca = &ce_arr;
+ u64 pfn;
+
+ if (!ca->n)
+ return 0;
+
+ mutex_lock(&ce_mutex);
+ pfn = del_lru_elem_unlocked(ca);
+ mutex_unlock(&ce_mutex);
+
+ return pfn;
+}
+
+
+int cec_add_elem(u64 pfn)
+{
+ struct ce_array *ca = &ce_arr;
+ unsigned int to;
+ int count, ret = 0;
+
+ /*
+ * We can be called very early on the identify_cpu() path where we are
+ * not initialized yet. We ignore the error for simplicity.
+ */
+ if (!ce_arr.array || ce_arr.disabled)
+ return -ENODEV;
+
+ ca->ces_entered++;
+
+ mutex_lock(&ce_mutex);
+
+ if (ca->n == MAX_ELEMS)
+ WARN_ON(!del_lru_elem_unlocked(ca));
+
+ ret = find_elem(ca, pfn, &to);
+ if (ret < 0) {
+ /*
+ * Shift range [to-end] to make room for one more element.
+ */
+ memmove((void *)&ca->array[to + 1],
+ (void *)&ca->array[to],
+ (ca->n - to) * sizeof(u64));
+
+ ca->array[to] = (pfn << PAGE_SHIFT) |
+ (DECAY_MASK << COUNT_BITS) | 1;
+
+ ca->n++;
+
+ ret = 0;
+
+ goto decay;
+ }
+
+ count = COUNT(ca->array[to]);
+
+ if (count < count_threshold) {
+ ca->array[to] |= (DECAY_MASK << COUNT_BITS);
+ ca->array[to]++;
+
+ ret = 0;
+ } else {
+ u64 pfn = ca->array[to] >> PAGE_SHIFT;
+
+ if (!pfn_valid(pfn)) {
+ pr_warn("CEC: Invalid pfn: 0x%llx\n", pfn);
+ } else {
+ /* We have reached max count for this page, soft-offline it. */
+ pr_err("Soft-offlining pfn: 0x%llx\n", pfn);
+ memory_failure_queue(pfn, 0, MF_SOFT_OFFLINE);
+ ca->pfns_poisoned++;
+ }
+
+ del_elem(ca, to);
+
+ /*
+ * Return a >0 value to denote that we've reached the offlining
+ * threshold.
+ */
+ ret = 1;
+
+ goto unlock;
+ }
+
+decay:
+ ca->decay_count++;
+
+ if (ca->decay_count >= CLEAN_ELEMS)
+ do_spring_cleaning(ca);
+
+unlock:
+ mutex_unlock(&ce_mutex);
+
+ return ret;
+}
+
+static int u64_get(void *data, u64 *val)
+{
+ *val = *(u64 *)data;
+
+ return 0;
+}
+
+static int pfn_set(void *data, u64 val)
+{
+ *(u64 *)data = val;
+
+ return cec_add_elem(val);
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(pfn_ops, u64_get, pfn_set, "0x%llx\n");
+
+static int decay_interval_set(void *data, u64 val)
+{
+ *(u64 *)data = val;
+
+ if (val < CEC_TIMER_MIN_INTERVAL)
+ return -EINVAL;
+
+ if (val > CEC_TIMER_MAX_INTERVAL)
+ return -EINVAL;
+
+ timer_interval = val;
+
+ cec_mod_timer(&cec_timer, timer_interval);
+ return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(decay_interval_ops, u64_get, decay_interval_set, "%lld\n");
+
+static int count_threshold_set(void *data, u64 val)
+{
+ *(u64 *)data = val;
+
+ if (val > COUNT_MASK)
+ val = COUNT_MASK;
+
+ count_threshold = val;
+
+ return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(count_threshold_ops, u64_get, count_threshold_set, "%lld\n");
+
+static int array_dump(struct seq_file *m, void *v)
+{
+ struct ce_array *ca = &ce_arr;
+ u64 prev = 0;
+ int i;
+
+ mutex_lock(&ce_mutex);
+
+ seq_printf(m, "{ n: %d\n", ca->n);
+ for (i = 0; i < ca->n; i++) {
+ u64 this = PFN(ca->array[i]);
+
+ seq_printf(m, " %03d: [%016llx|%03llx]\n", i, this, FULL_COUNT(ca->array[i]));
+
+ WARN_ON(prev > this);
+
+ prev = this;
+ }
+
+ seq_printf(m, "}\n");
+
+ seq_printf(m, "Stats:\nCEs: %llu\nofflined pages: %llu\n",
+ ca->ces_entered, ca->pfns_poisoned);
+
+ seq_printf(m, "Flags: 0x%x\n", ca->flags);
+
+ seq_printf(m, "Timer interval: %lld seconds\n", timer_interval);
+ seq_printf(m, "Decays: %lld\n", ca->decays_done);
+
+ seq_printf(m, "Action threshold: %d\n", count_threshold);
+
+ mutex_unlock(&ce_mutex);
+
+ return 0;
+}
+
+static int array_open(struct inode *inode, struct file *filp)
+{
+ return single_open(filp, array_dump, NULL);
+}
+
+static const struct file_operations array_ops = {
+ .owner = THIS_MODULE,
+ .open = array_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static int __init create_debugfs_nodes(void)
+{
+ struct dentry *d, *pfn, *decay, *count, *array;
+
+ d = debugfs_create_dir("cec", ras_debugfs_dir);
+ if (!d) {
+ pr_warn("Error creating cec debugfs node!\n");
+ return -1;
+ }
+
+ pfn = debugfs_create_file("pfn", S_IRUSR | S_IWUSR, d, &dfs_pfn, &pfn_ops);
+ if (!pfn) {
+ pr_warn("Error creating pfn debugfs node!\n");
+ goto err;
+ }
+
+ array = debugfs_create_file("array", S_IRUSR, d, NULL, &array_ops);
+ if (!array) {
+ pr_warn("Error creating array debugfs node!\n");
+ goto err;
+ }
+
+ decay = debugfs_create_file("decay_interval", S_IRUSR | S_IWUSR, d,
+ &timer_interval, &decay_interval_ops);
+ if (!decay) {
+ pr_warn("Error creating decay_interval debugfs node!\n");
+ goto err;
+ }
+
+ count = debugfs_create_file("count_threshold", S_IRUSR | S_IWUSR, d,
+ &count_threshold, &count_threshold_ops);
+ if (!decay) {
+ pr_warn("Error creating count_threshold debugfs node!\n");
+ goto err;
+ }
+
+
+ return 0;
+
+err:
+ debugfs_remove_recursive(d);
+
+ return 1;
+}
+
+void __init cec_init(void)
+{
+ if (ce_arr.disabled)
+ return;
+
+ ce_arr.array = (void *)get_zeroed_page(GFP_KERNEL);
+ if (!ce_arr.array) {
+ pr_err("Error allocating CE array page!\n");
+ return;
+ }
+
+ if (create_debugfs_nodes())
+ return;
+
+ setup_timer(&cec_timer, cec_timer_fn, (unsigned long)&ce_arr);
+ cec_mod_timer(&cec_timer, CEC_TIMER_DEFAULT_INTERVAL);
+
+ pr_info("Correctable Errors collector initialized.\n");
+}
+
+int __init parse_cec_param(char *str)
+{
+ if (!str)
+ return 0;
+
+ if (*str == '=')
+ str++;
+
+ if (!strncmp(str, "cec_disable", 7))
+ ce_arr.disabled = 1;
+ else
+ return 0;
+
+ return 1;
+}
#include <linux/debugfs.h>
-static struct dentry *ras_debugfs_dir;
+struct dentry *ras_debugfs_dir;
static atomic_t trace_count = ATOMIC_INIT(0);
--- /dev/null
+#ifndef __RAS_DEBUGFS_H__
+#define __RAS_DEBUGFS_H__
+
+#include <linux/debugfs.h>
+
+extern struct dentry *ras_debugfs_dir;
+
+#endif /* __RAS_DEBUGFS_H__ */
EXPORT_TRACEPOINT_SYMBOL_GPL(extlog_mem_event);
#endif
EXPORT_TRACEPOINT_SYMBOL_GPL(mc_event);
+
+
+int __init parse_ras_param(char *str)
+{
+#ifdef CONFIG_RAS_CEC
+ parse_cec_param(str);
+#endif
+
+ return 1;
+}
+__setup("ras", parse_ras_param);
}
EXPORT_SYMBOL_GPL(reset_control_status);
-static struct reset_control *__reset_control_get(
+static struct reset_control *__reset_control_get_internal(
struct reset_controller_dev *rcdev,
unsigned int index, bool shared)
{
return rstc;
}
-static void __reset_control_put(struct reset_control *rstc)
+static void __reset_control_put_internal(struct reset_control *rstc)
{
lockdep_assert_held(&reset_list_mutex);
}
/* reset_list_mutex also protects the rcdev's reset_control list */
- rstc = __reset_control_get(rcdev, rstc_id, shared);
+ rstc = __reset_control_get_internal(rcdev, rstc_id, shared);
mutex_unlock(&reset_list_mutex);
}
EXPORT_SYMBOL_GPL(__of_reset_control_get);
+struct reset_control *__reset_control_get(struct device *dev, const char *id,
+ int index, bool shared, bool optional)
+{
+ if (dev->of_node)
+ return __of_reset_control_get(dev->of_node, id, index, shared,
+ optional);
+
+ return optional ? NULL : ERR_PTR(-EINVAL);
+}
+EXPORT_SYMBOL_GPL(__reset_control_get);
+
/**
* reset_control_put - free the reset controller
* @rstc: reset controller
return;
mutex_lock(&reset_list_mutex);
- __reset_control_put(rstc);
+ __reset_control_put_internal(rstc);
mutex_unlock(&reset_list_mutex);
}
EXPORT_SYMBOL_GPL(reset_control_put);
if (!ptr)
return ERR_PTR(-ENOMEM);
- rstc = __of_reset_control_get(dev ? dev->of_node : NULL,
- id, index, shared, optional);
+ rstc = __reset_control_get(dev, id, index, shared, optional);
if (!IS_ERR(rstc)) {
*ptr = rstc;
devres_add(dev, ptr);
int qeth_bridgeport_setrole(struct qeth_card *card, enum qeth_sbp_roles role);
int qeth_bridgeport_an_set(struct qeth_card *card, int enable);
int qeth_get_priority_queue(struct qeth_card *, struct sk_buff *, int, int);
-int qeth_get_elements_no(struct qeth_card *, struct sk_buff *, int);
+int qeth_get_elements_no(struct qeth_card *card, struct sk_buff *skb,
+ int extra_elems, int data_offset);
int qeth_get_elements_for_frags(struct sk_buff *);
int qeth_do_send_packet_fast(struct qeth_card *, struct qeth_qdio_out_q *,
struct sk_buff *, struct qeth_hdr *, int, int, int);
* @card: qeth card structure, to check max. elems.
* @skb: SKB address
* @extra_elems: extra elems needed, to check against max.
+ * @data_offset: range starts at skb->data + data_offset
*
* Returns the number of pages, and thus QDIO buffer elements, needed to cover
* skb data, including linear part and fragments. Checks if the result plus
* Note: extra_elems is not included in the returned result.
*/
int qeth_get_elements_no(struct qeth_card *card,
- struct sk_buff *skb, int extra_elems)
+ struct sk_buff *skb, int extra_elems, int data_offset)
{
int elements = qeth_get_elements_for_range(
- (addr_t)skb->data,
+ (addr_t)skb->data + data_offset,
(addr_t)skb->data + skb_headlen(skb)) +
qeth_get_elements_for_frags(skb);
* chaining we can not send long frag lists
*/
if ((card->info.type != QETH_CARD_TYPE_IQD) &&
- !qeth_get_elements_no(card, new_skb, 0)) {
+ !qeth_get_elements_no(card, new_skb, 0, 0)) {
int lin_rc = skb_linearize(new_skb);
if (card->options.performance_stats) {
}
}
- elements = qeth_get_elements_no(card, new_skb, elements_needed);
+ elements = qeth_get_elements_no(card, new_skb, elements_needed,
+ (data_offset > 0) ? data_offset : 0);
if (!elements) {
if (data_offset >= 0)
kmem_cache_free(qeth_core_header_cache, hdr);
char daddr[16];
struct af_iucv_trans_hdr *iucv_hdr;
- skb_pull(skb, 14);
- card->dev->header_ops->create(skb, card->dev, 0,
- card->dev->dev_addr, card->dev->dev_addr,
- card->dev->addr_len);
- skb_pull(skb, 14);
- iucv_hdr = (struct af_iucv_trans_hdr *)skb->data;
memset(hdr, 0, sizeof(struct qeth_hdr));
hdr->hdr.l3.id = QETH_HEADER_TYPE_LAYER3;
hdr->hdr.l3.ext_flags = 0;
- hdr->hdr.l3.length = skb->len;
+ hdr->hdr.l3.length = skb->len - ETH_HLEN;
hdr->hdr.l3.flags = QETH_HDR_IPV6 | QETH_CAST_UNICAST;
+
+ iucv_hdr = (struct af_iucv_trans_hdr *) (skb->data + ETH_HLEN);
memset(daddr, 0, sizeof(daddr));
daddr[0] = 0xfe;
daddr[1] = 0x80;
if ((card->info.type == QETH_CARD_TYPE_IQD) &&
!skb_is_nonlinear(skb)) {
new_skb = skb;
- if (new_skb->protocol == ETH_P_AF_IUCV)
- data_offset = 0;
- else
- data_offset = ETH_HLEN;
+ data_offset = ETH_HLEN;
hdr = kmem_cache_alloc(qeth_core_header_cache, GFP_ATOMIC);
if (!hdr)
goto tx_drop;
*/
if ((card->info.type != QETH_CARD_TYPE_IQD) &&
((use_tso && !qeth_l3_get_elements_no_tso(card, new_skb, 1)) ||
- (!use_tso && !qeth_get_elements_no(card, new_skb, 0)))) {
+ (!use_tso && !qeth_get_elements_no(card, new_skb, 0, 0)))) {
int lin_rc = skb_linearize(new_skb);
if (card->options.performance_stats) {
elements = use_tso ?
qeth_l3_get_elements_no_tso(card, new_skb, hdr_elements) :
- qeth_get_elements_no(card, new_skb, hdr_elements);
+ qeth_get_elements_no(card, new_skb, hdr_elements,
+ (data_offset > 0) ? data_offset : 0);
if (!elements) {
if (data_offset >= 0)
kmem_cache_free(qeth_core_header_cache, hdr);
}
}
-static void jsfd_do_request(struct request_queue *q)
+static int jsfd_queue;
+
+static struct request *jsfd_next_request(void)
+{
+ struct request_queue *q;
+ struct request *rq;
+ int old_pos = jsfd_queue;
+
+ do {
+ q = jsfd_disk[jsfd_queue]->queue;
+ if (++jsfd_queue == JSF_MAX)
+ jsfd_queue = 0;
+ if (q) {
+ rq = blk_fetch_request(q);
+ if (rq)
+ return rq;
+ }
+ } while (jsfd_queue != old_pos);
+
+ return NULL;
+}
+
+static void jsfd_request(void)
{
struct request *req;
- req = blk_fetch_request(q);
+ req = jsfd_next_request();
while (req) {
struct jsfd_part *jdp = req->rq_disk->private_data;
unsigned long offset = blk_rq_pos(req) << 9;
err = 0;
end:
if (!__blk_end_request_cur(req, err))
- req = blk_fetch_request(q);
+ req = jsfd_next_request();
}
}
+static void jsfd_do_request(struct request_queue *q)
+{
+ jsfd_request();
+}
+
/*
* The memory devices use the full 32/64 bits of the offset, and so we cannot
* check against negative addresses: they are ok. The return value is weird,
return 0;
}
-static struct request_queue *jsf_queue;
-
static int jsfd_init(void)
{
static DEFINE_SPINLOCK(lock);
struct gendisk *disk = alloc_disk(1);
if (!disk)
goto out;
+ disk->queue = blk_init_queue(jsfd_do_request, &lock);
+ if (!disk->queue) {
+ put_disk(disk);
+ goto out;
+ }
jsfd_disk[i] = disk;
}
goto out;
}
- jsf_queue = blk_init_queue(jsfd_do_request, &lock);
- if (!jsf_queue) {
- err = -ENOMEM;
- unregister_blkdev(JSFD_MAJOR, "jsfd");
- goto out;
- }
-
for (i = 0; i < JSF_MAX; i++) {
struct gendisk *disk = jsfd_disk[i];
if ((i & JSF_PART_MASK) >= JSF_NPART) continue;
disk->fops = &jsfd_fops;
set_capacity(disk, jdp->dsize >> 9);
disk->private_data = jdp;
- disk->queue = jsf_queue;
add_disk(disk);
set_disk_ro(disk, 1);
}
for (i = 0; i < JSF_MAX; i++) {
if ((i & JSF_PART_MASK) >= JSF_NPART) continue;
del_gendisk(jsfd_disk[i]);
+ blk_cleanup_queue(jsfd_disk[i]->queue);
put_disk(jsfd_disk[i]);
}
if (jsf0.busy)
misc_deregister(&jsf_dev);
unregister_blkdev(JSFD_MAJOR, "jsfd");
- blk_cleanup_queue(jsf_queue);
}
module_init(jsflash_init_module);
scsi_mod-$(CONFIG_SCSI_NETLINK) += scsi_netlink.o
scsi_mod-$(CONFIG_SYSCTL) += scsi_sysctl.o
scsi_mod-$(CONFIG_SCSI_PROC_FS) += scsi_proc.o
+scsi_mod-$(CONFIG_BLK_DEBUG_FS) += scsi_debugfs.o
scsi_mod-y += scsi_trace.o scsi_logging.o
scsi_mod-$(CONFIG_PM) += scsi_pm.o
scsi_mod-$(CONFIG_SCSI_DH) += scsi_dh.o
#define aac_adapter_sync_cmd(dev, command, p1, p2, p3, p4, p5, p6, status, r1, r2, r3, r4) \
(dev)->a_ops.adapter_sync_cmd(dev, command, p1, p2, p3, p4, p5, p6, status, r1, r2, r3, r4)
-#define aac_adapter_check_health(dev) \
- (dev)->a_ops.adapter_check_health(dev)
-
#define aac_adapter_restart(dev, bled, reset_type) \
((dev)->a_ops.adapter_restart(dev, bled, reset_type))
return capacity;
}
+static inline int aac_adapter_check_health(struct aac_dev *dev)
+{
+ if (unlikely(pci_channel_offline(dev->pdev)))
+ return -1;
+
+ return (dev)->a_ops.adapter_check_health(dev);
+}
+
/* SCp.phase values */
#define AAC_OWNER_MIDLEVEL 0x101
#define AAC_OWNER_LOWLEVEL 0x102
spin_unlock_irqrestore(&aac->fib_lock, flagv);
if (BlinkLED < 0) {
- printk(KERN_ERR "%s: Host adapter dead %d\n", aac->name, BlinkLED);
+ printk(KERN_ERR "%s: Host adapter is dead (or got a PCI error) %d\n",
+ aac->name, BlinkLED);
goto out;
}
|| (cmd > EXPRESS_IOCTL_MAX))
return -ENOTSUPP;
- if (!access_ok(VERIFY_WRITE, arg, sizeof(struct atto_express_ioctl))) {
+ ioctl = memdup_user(arg, sizeof(struct atto_express_ioctl));
+ if (IS_ERR(ioctl)) {
esas2r_log(ESAS2R_LOG_WARN,
"ioctl_handler access_ok failed for cmd %d, "
"address %p", cmd,
arg);
- return -EFAULT;
- }
-
- /* allocate a kernel memory buffer for the IOCTL data */
- ioctl = kzalloc(sizeof(struct atto_express_ioctl), GFP_KERNEL);
- if (ioctl == NULL) {
- esas2r_log(ESAS2R_LOG_WARN,
- "ioctl_handler kzalloc failed for %zu bytes",
- sizeof(struct atto_express_ioctl));
- return -ENOMEM;
- }
-
- err = __copy_from_user(ioctl, arg, sizeof(struct atto_express_ioctl));
- if (err != 0) {
- esas2r_log(ESAS2R_LOG_WARN,
- "copy_from_user didn't copy everything (err %d, cmd %d)",
- err,
- cmd);
- kfree(ioctl);
-
- return -EFAULT;
+ return PTR_ERR(ioctl);
}
/* verify the signature */
break;
case IPR_IOASC_MED_DO_NOT_REALLOC: /* prevent retries */
case IPR_IOASA_IR_DUAL_IOA_DISABLED:
- scsi_cmd->result |= (DID_PASSTHROUGH << 16);
+ /*
+ * exception: do not set DID_PASSTHROUGH on CHECK CONDITION
+ * so SCSI mid-layer and upper layers handle it accordingly.
+ */
+ if (scsi_cmd->result != SAM_STAT_CHECK_CONDITION)
+ scsi_cmd->result |= (DID_PASSTHROUGH << 16);
break;
case IPR_IOASC_BUS_WAS_RESET:
case IPR_IOASC_BUS_WAS_RESET_BY_OTHER:
rc = 0;
}
- tsk_restore_flags(current, pflags, PF_MEMALLOC);
+ current_restore_flags(pflags, PF_MEMALLOC);
return rc;
}
#define LPFC_MAX_SG_SEG_CNT 4096 /* sg element count per scsi cmnd */
#define LPFC_MAX_SGL_SEG_CNT 512 /* SGL element count per scsi cmnd */
#define LPFC_MAX_BPL_SEG_CNT 4096 /* BPL element count per scsi cmnd */
-#define LPFC_MIN_NVME_SEG_CNT 254
+#define LPFC_MAX_NVME_SEG_CNT 128 /* max SGL element cnt per NVME cmnd */
#define LPFC_MAX_SGE_SIZE 0x80000000 /* Maximum data allowed in a SGE */
#define LPFC_IOCB_LIST_CNT 2250 /* list of IOCBs for fast-path usage. */
unsigned long rcv_buffer_time_stamp;
uint32_t vport_flag;
#define STATIC_VPORT 1
+#define FAWWPN_SET 2
+#define FAWWPN_PARAM_CHG 4
uint16_t fdmi_num_disc;
uint32_t fdmi_hba_mask;
uint32_t cfg_nvmet_fb_size;
uint32_t cfg_total_seg_cnt;
uint32_t cfg_sg_seg_cnt;
+ uint32_t cfg_nvme_seg_cnt;
uint32_t cfg_sg_dma_buf_size;
uint64_t cfg_soft_wwnn;
uint64_t cfg_soft_wwpn;
struct lpfc_vport *vport = (struct lpfc_vport *) shost->hostdata;
struct lpfc_hba *phba = vport->phba;
unsigned int cnt = count;
+ uint8_t vvvl = vport->fc_sparam.cmn.valid_vendor_ver_level;
+ u32 *fawwpn_key = (uint32_t *)&vport->fc_sparam.un.vendorVersion[0];
/*
* We're doing a simple sanity check for soft_wwpn setting.
* here. The intent is to protect against the random user or
* application that is just writing attributes.
*/
+ if (vvvl == 1 && cpu_to_be32(*fawwpn_key) == FAPWWN_KEY_VENDOR) {
+ lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+ "0051 "LPFC_DRIVER_NAME" soft wwpn can not"
+ " be enabled: fawwpn is enabled\n");
+ return -EINVAL;
+ }
/* count may include a LF at end of string */
if (buf[cnt-1] == '\n')
* percentage will go to NVME.
*/
LPFC_ATTR_R(xri_split, 50, 10, 90,
- "Division of XRI resources between SCSI and NVME");
+ "Division of XRI resources between SCSI and NVME");
/*
# lpfc_log_verbose: Only turn this flag on if you are willing to risk being
mbox, *rpi);
else {
*rpi = lpfc_sli4_alloc_rpi(phba);
+ if (*rpi == LPFC_RPI_ALLOC_ERROR) {
+ mempool_free(mbox, phba->mbox_mem_pool);
+ return -EBUSY;
+ }
status = lpfc_reg_rpi(phba, phba->pport->vpi,
phba->pport->fc_myDID,
(uint8_t *)&phba->pport->fc_sparam,
struct fc_rport;
struct fc_frame_header;
+struct lpfc_nvmet_rcv_ctx;
void lpfc_down_link(struct lpfc_hba *, LPFC_MBOXQ_t *);
void lpfc_sli_read_link_ste(struct lpfc_hba *);
void lpfc_dump_mem(struct lpfc_hba *, LPFC_MBOXQ_t *, uint16_t, uint16_t);
int lpfc_check_sli_ndlp(struct lpfc_hba *, struct lpfc_sli_ring *,
struct lpfc_iocbq *, struct lpfc_nodelist *);
-void lpfc_nlp_init(struct lpfc_vport *, struct lpfc_nodelist *, uint32_t);
+struct lpfc_nodelist *lpfc_nlp_init(struct lpfc_vport *vport, uint32_t did);
struct lpfc_nodelist *lpfc_nlp_get(struct lpfc_nodelist *);
int lpfc_nlp_put(struct lpfc_nodelist *);
int lpfc_nlp_not_used(struct lpfc_nodelist *ndlp);
void lpfc_sli4_rb_free(struct lpfc_hba *, struct hbq_dmabuf *);
struct rqb_dmabuf *lpfc_sli4_nvmet_alloc(struct lpfc_hba *phba);
void lpfc_sli4_nvmet_free(struct lpfc_hba *phba, struct rqb_dmabuf *dmab);
+void lpfc_nvmet_rq_post(struct lpfc_hba *phba, struct lpfc_nvmet_rcv_ctx *ctxp,
+ struct lpfc_dmabuf *mp);
+int lpfc_nvmet_rcv_unsol_abort(struct lpfc_vport *vport,
+ struct fc_frame_header *fc_hdr);
void lpfc_sli4_build_dflt_fcf_record(struct lpfc_hba *, struct fcf_record *,
uint16_t);
int lpfc_sli4_rq_put(struct lpfc_queue *hq, struct lpfc_queue *dq,
void lpfc_sli_handle_slow_ring_event(struct lpfc_hba *,
struct lpfc_sli_ring *, uint32_t);
void lpfc_sli4_handle_received_buffer(struct lpfc_hba *, struct hbq_dmabuf *);
+void lpfc_sli4_seq_abort_rsp(struct lpfc_vport *vport,
+ struct fc_frame_header *fc_hdr, bool aborted);
void lpfc_sli_def_mbox_cmpl(struct lpfc_hba *, LPFC_MBOXQ_t *);
void lpfc_sli4_unreg_rpi_cmpl_clr(struct lpfc_hba *, LPFC_MBOXQ_t *);
int lpfc_sli_issue_iocb(struct lpfc_hba *, uint32_t,
}
}
+static void
+lpfc_ns_rsp_audit_did(struct lpfc_vport *vport, uint32_t Did, uint8_t fc4_type)
+{
+ struct lpfc_hba *phba = vport->phba;
+ struct lpfc_nodelist *ndlp = NULL;
+ struct Scsi_Host *shost = lpfc_shost_from_vport(vport);
+
+ /*
+ * To conserve rpi's, filter out addresses for other
+ * vports on the same physical HBAs.
+ */
+ if (Did != vport->fc_myDID &&
+ (!lpfc_find_vport_by_did(phba, Did) ||
+ vport->cfg_peer_port_login)) {
+ if (!phba->nvmet_support) {
+ /* FCPI/NVMEI path. Process Did */
+ lpfc_prep_node_fc4type(vport, Did, fc4_type);
+ return;
+ }
+ /* NVMET path. NVMET only cares about NVMEI nodes. */
+ list_for_each_entry(ndlp, &vport->fc_nodes, nlp_listp) {
+ if (ndlp->nlp_type != NLP_NVME_INITIATOR ||
+ ndlp->nlp_state != NLP_STE_UNMAPPED_NODE)
+ continue;
+ spin_lock_irq(shost->host_lock);
+ if (ndlp->nlp_DID == Did)
+ ndlp->nlp_flag &= ~NLP_NVMET_RECOV;
+ else
+ ndlp->nlp_flag |= NLP_NVMET_RECOV;
+ spin_unlock_irq(shost->host_lock);
+ }
+ }
+}
+
static int
lpfc_ns_rsp(struct lpfc_vport *vport, struct lpfc_dmabuf *mp, uint8_t fc4_type,
uint32_t Size)
{
- struct lpfc_hba *phba = vport->phba;
struct lpfc_sli_ct_request *Response =
(struct lpfc_sli_ct_request *) mp->virt;
- struct lpfc_nodelist *ndlp = NULL;
struct lpfc_dmabuf *mlast, *next_mp;
uint32_t *ctptr = (uint32_t *) & Response->un.gid.PortType;
uint32_t Did, CTentry;
int Cnt;
struct list_head head;
+ struct Scsi_Host *shost = lpfc_shost_from_vport(vport);
+ struct lpfc_nodelist *ndlp = NULL;
lpfc_set_disctmo(vport);
vport->num_disc_nodes = 0;
/* Get next DID from NameServer List */
CTentry = *ctptr++;
Did = ((be32_to_cpu(CTentry)) & Mask_DID);
-
- ndlp = NULL;
-
- /*
- * Check for rscn processing or not
- * To conserve rpi's, filter out addresses for other
- * vports on the same physical HBAs.
- */
- if ((Did != vport->fc_myDID) &&
- ((lpfc_find_vport_by_did(phba, Did) == NULL) ||
- vport->cfg_peer_port_login))
- lpfc_prep_node_fc4type(vport, Did, fc4_type);
-
+ lpfc_ns_rsp_audit_did(vport, Did, fc4_type);
if (CTentry & (cpu_to_be32(SLI_CT_LAST_ENTRY)))
goto nsout1;
}
+ /* All GID_FT entries processed. If the driver is running in
+ * in target mode, put impacted nodes into recovery and drop
+ * the RPI to flush outstanding IO.
+ */
+ if (vport->phba->nvmet_support) {
+ list_for_each_entry(ndlp, &vport->fc_nodes, nlp_listp) {
+ if (!(ndlp->nlp_flag & NLP_NVMET_RECOV))
+ continue;
+ lpfc_disc_state_machine(vport, ndlp, NULL,
+ NLP_EVT_DEVICE_RECOVERY);
+ spin_lock_irq(shost->host_lock);
+ ndlp->nlp_flag &= ~NLP_NVMET_RECOV;
+ spin_lock_irq(shost->host_lock);
+ }
+ }
+
nsout1:
list_del(&head);
return 0;
{
struct lpfc_hba *phba = vport->phba;
struct lpfc_nvmet_tgtport *tgtp;
+ struct lpfc_nvmet_rcv_ctx *ctxp, *next_ctxp;
int len = 0;
+ int cnt;
if (phba->nvmet_support) {
if (!phba->targetport)
return len;
tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
- len += snprintf(buf+len, size-len,
+ len += snprintf(buf + len, size - len,
"\nNVME Targetport Statistics\n");
- len += snprintf(buf+len, size-len,
+ len += snprintf(buf + len, size - len,
"LS: Rcv %08x Drop %08x Abort %08x\n",
atomic_read(&tgtp->rcv_ls_req_in),
atomic_read(&tgtp->rcv_ls_req_drop),
atomic_read(&tgtp->xmt_ls_abort));
if (atomic_read(&tgtp->rcv_ls_req_in) !=
atomic_read(&tgtp->rcv_ls_req_out)) {
- len += snprintf(buf+len, size-len,
+ len += snprintf(buf + len, size - len,
"Rcv LS: in %08x != out %08x\n",
atomic_read(&tgtp->rcv_ls_req_in),
atomic_read(&tgtp->rcv_ls_req_out));
}
- len += snprintf(buf+len, size-len,
+ len += snprintf(buf + len, size - len,
"LS: Xmt %08x Drop %08x Cmpl %08x Err %08x\n",
atomic_read(&tgtp->xmt_ls_rsp),
atomic_read(&tgtp->xmt_ls_drop),
atomic_read(&tgtp->xmt_ls_rsp_cmpl),
atomic_read(&tgtp->xmt_ls_rsp_error));
- len += snprintf(buf+len, size-len,
+ len += snprintf(buf + len, size - len,
"FCP: Rcv %08x Drop %08x\n",
atomic_read(&tgtp->rcv_fcp_cmd_in),
atomic_read(&tgtp->rcv_fcp_cmd_drop));
if (atomic_read(&tgtp->rcv_fcp_cmd_in) !=
atomic_read(&tgtp->rcv_fcp_cmd_out)) {
- len += snprintf(buf+len, size-len,
+ len += snprintf(buf + len, size - len,
"Rcv FCP: in %08x != out %08x\n",
atomic_read(&tgtp->rcv_fcp_cmd_in),
atomic_read(&tgtp->rcv_fcp_cmd_out));
}
- len += snprintf(buf+len, size-len,
- "FCP Rsp: read %08x readrsp %08x write %08x rsp %08x\n",
+ len += snprintf(buf + len, size - len,
+ "FCP Rsp: read %08x readrsp %08x "
+ "write %08x rsp %08x\n",
atomic_read(&tgtp->xmt_fcp_read),
atomic_read(&tgtp->xmt_fcp_read_rsp),
atomic_read(&tgtp->xmt_fcp_write),
atomic_read(&tgtp->xmt_fcp_rsp));
- len += snprintf(buf+len, size-len,
+ len += snprintf(buf + len, size - len,
"FCP Rsp: abort %08x drop %08x\n",
atomic_read(&tgtp->xmt_fcp_abort),
atomic_read(&tgtp->xmt_fcp_drop));
- len += snprintf(buf+len, size-len,
+ len += snprintf(buf + len, size - len,
"FCP Rsp Cmpl: %08x err %08x drop %08x\n",
atomic_read(&tgtp->xmt_fcp_rsp_cmpl),
atomic_read(&tgtp->xmt_fcp_rsp_error),
atomic_read(&tgtp->xmt_fcp_rsp_drop));
- len += snprintf(buf+len, size-len,
+ len += snprintf(buf + len, size - len,
"ABORT: Xmt %08x Err %08x Cmpl %08x",
atomic_read(&tgtp->xmt_abort_rsp),
atomic_read(&tgtp->xmt_abort_rsp_error),
atomic_read(&tgtp->xmt_abort_cmpl));
- len += snprintf(buf+len, size-len, "\n");
+ len += snprintf(buf + len, size - len, "\n");
+
+ cnt = 0;
+ spin_lock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+ list_for_each_entry_safe(ctxp, next_ctxp,
+ &phba->sli4_hba.lpfc_abts_nvmet_ctx_list,
+ list) {
+ cnt++;
+ }
+ spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+ if (cnt) {
+ len += snprintf(buf + len, size - len,
+ "ABORT: %d ctx entries\n", cnt);
+ spin_lock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+ list_for_each_entry_safe(ctxp, next_ctxp,
+ &phba->sli4_hba.lpfc_abts_nvmet_ctx_list,
+ list) {
+ if (len >= (size - LPFC_DEBUG_OUT_LINE_SZ))
+ break;
+ len += snprintf(buf + len, size - len,
+ "Entry: oxid %x state %x "
+ "flag %x\n",
+ ctxp->oxid, ctxp->state,
+ ctxp->flag);
+ }
+ spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+ }
} else {
if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME))
return len;
datqp->queue_id, datqp->entry_count,
datqp->entry_size, datqp->host_index,
datqp->hba_index);
- len += snprintf(pbuffer + len, LPFC_QUE_INFO_GET_BUF_SIZE - len, "\n");
-
return len;
}
#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
struct lpfc_hba *phba = vport->phba;
- if (vport->disc_trc) {
- kfree(vport->disc_trc);
- vport->disc_trc = NULL;
- }
+ kfree(vport->disc_trc);
+ vport->disc_trc = NULL;
debugfs_remove(vport->debug_disc_trc); /* discovery_trace */
vport->debug_disc_trc = NULL;
debugfs_remove(phba->debug_readRef); /* readRef */
phba->debug_readRef = NULL;
- if (phba->slow_ring_trc) {
- kfree(phba->slow_ring_trc);
- phba->slow_ring_trc = NULL;
- }
+ kfree(phba->slow_ring_trc);
+ phba->slow_ring_trc = NULL;
/* slow_ring_trace */
debugfs_remove(phba->debug_slow_ring_trc);
#define NLP_LOGO_SND 0x00000100 /* sent LOGO request for this entry */
#define NLP_RNID_SND 0x00000400 /* sent RNID request for this entry */
#define NLP_ELS_SND_MASK 0x000007e0 /* sent ELS request for this entry */
+#define NLP_NVMET_RECOV 0x00001000 /* NVMET auditing node for recovery. */
#define NLP_DEFER_RM 0x00010000 /* Remove this ndlp if no longer used */
#define NLP_DELAY_TMO 0x00020000 /* delay timeout is running for node */
#define NLP_NPR_2B_DISC 0x00040000 /* node is included in num_disc_nodes */
memcmp(&vport->fabric_portname, &sp->portName,
sizeof(struct lpfc_name)) ||
memcmp(&vport->fabric_nodename, &sp->nodeName,
- sizeof(struct lpfc_name)))
+ sizeof(struct lpfc_name)) ||
+ (vport->vport_flag & FAWWPN_PARAM_CHG)) {
fabric_param_changed = 1;
-
+ vport->vport_flag &= ~FAWWPN_PARAM_CHG;
+ }
/*
* Word 1 Bit 31 in common service parameter is overloaded.
* Word 1 Bit 31 in FLOGI request is multiple NPort request
* Cannot find existing Fabric ndlp, so allocate a
* new one
*/
- ndlp = mempool_alloc(phba->nlp_mem_pool, GFP_KERNEL);
+ ndlp = lpfc_nlp_init(vport, PT2PT_RemoteID);
if (!ndlp)
goto fail;
- lpfc_nlp_init(vport, ndlp, PT2PT_RemoteID);
} else if (!NLP_CHK_NODE_ACT(ndlp)) {
ndlp = lpfc_enable_node(vport, ndlp,
NLP_STE_UNUSED_NODE);
int
lpfc_initial_flogi(struct lpfc_vport *vport)
{
- struct lpfc_hba *phba = vport->phba;
struct lpfc_nodelist *ndlp;
vport->port_state = LPFC_FLOGI;
ndlp = lpfc_findnode_did(vport, Fabric_DID);
if (!ndlp) {
/* Cannot find existing Fabric ndlp, so allocate a new one */
- ndlp = mempool_alloc(phba->nlp_mem_pool, GFP_KERNEL);
+ ndlp = lpfc_nlp_init(vport, Fabric_DID);
if (!ndlp)
return 0;
- lpfc_nlp_init(vport, ndlp, Fabric_DID);
/* Set the node type */
ndlp->nlp_type |= NLP_FABRIC;
/* Put ndlp onto node list */
int
lpfc_initial_fdisc(struct lpfc_vport *vport)
{
- struct lpfc_hba *phba = vport->phba;
struct lpfc_nodelist *ndlp;
/* First look for the Fabric ndlp */
ndlp = lpfc_findnode_did(vport, Fabric_DID);
if (!ndlp) {
/* Cannot find existing Fabric ndlp, so allocate a new one */
- ndlp = mempool_alloc(phba->nlp_mem_pool, GFP_KERNEL);
+ ndlp = lpfc_nlp_init(vport, Fabric_DID);
if (!ndlp)
return 0;
- lpfc_nlp_init(vport, ndlp, Fabric_DID);
/* Put ndlp onto node list */
lpfc_enqueue_node(vport, ndlp);
} else if (!NLP_CHK_NODE_ACT(ndlp)) {
phba->active_rrq_pool);
return ndlp;
}
- new_ndlp = mempool_alloc(phba->nlp_mem_pool, GFP_ATOMIC);
+ new_ndlp = lpfc_nlp_init(vport, ndlp->nlp_DID);
if (!new_ndlp) {
if (active_rrqs_xri_bitmap)
mempool_free(active_rrqs_xri_bitmap,
phba->active_rrq_pool);
return ndlp;
}
- lpfc_nlp_init(vport, new_ndlp, ndlp->nlp_DID);
} else if (!NLP_CHK_NODE_ACT(new_ndlp)) {
rc = memcmp(&ndlp->nlp_portname, name,
sizeof(struct lpfc_name));
ndlp = lpfc_findnode_did(vport, nportid);
if (!ndlp) {
- ndlp = mempool_alloc(phba->nlp_mem_pool, GFP_KERNEL);
+ ndlp = lpfc_nlp_init(vport, nportid);
if (!ndlp)
return 1;
- lpfc_nlp_init(vport, ndlp, nportid);
lpfc_enqueue_node(vport, ndlp);
} else if (!NLP_CHK_NODE_ACT(ndlp)) {
ndlp = lpfc_enable_node(vport, ndlp, NLP_STE_UNUSED_NODE);
ndlp = lpfc_findnode_did(vport, nportid);
if (!ndlp) {
- ndlp = mempool_alloc(phba->nlp_mem_pool, GFP_KERNEL);
+ ndlp = lpfc_nlp_init(vport, nportid);
if (!ndlp)
return 1;
- lpfc_nlp_init(vport, ndlp, nportid);
lpfc_enqueue_node(vport, ndlp);
} else if (!NLP_CHK_NODE_ACT(ndlp)) {
ndlp = lpfc_enable_node(vport, ndlp, NLP_STE_UNUSED_NODE);
pcmd = (uint8_t *) (((struct lpfc_dmabuf *) elsiocb->context2)->virt);
memset(pcmd, 0, cmdsize);
- *((uint32_t *) (pcmd)) = (ELS_CMD_ACC | (ELS_CMD_PRLI & ~ELS_RSP_MASK));
+ *((uint32_t *)(pcmd)) = elsrspcmd;
pcmd += sizeof(uint32_t);
/* For PRLI, remainder of payload is PRLI parameter page */
(ndlp->nlp_state == NLP_STE_UNUSED_NODE) ||
!lpfc_rscn_payload_check(vport, ndlp->nlp_DID))
continue;
+
+ /* NVME Target mode does not do RSCN Recovery. */
if (vport->phba->nvmet_support)
continue;
+
lpfc_disc_state_machine(vport, ndlp, NULL,
NLP_EVT_DEVICE_RECOVERY);
lpfc_cancel_retry_delay_tmo(vport, ndlp);
lpfc_els_handle_rscn(struct lpfc_vport *vport)
{
struct lpfc_nodelist *ndlp;
- struct lpfc_hba *phba = vport->phba;
/* Ignore RSCN if the port is being torn down. */
if (vport->load_flag & FC_UNLOADING) {
ndlp = lpfc_findnode_did(vport, NameServer_DID);
if (ndlp && NLP_CHK_NODE_ACT(ndlp)
&& ndlp->nlp_state == NLP_STE_UNMAPPED_NODE) {
- /* Good ndlp, issue CT Request to NameServer */
+ /* Good ndlp, issue CT Request to NameServer. Need to
+ * know how many gidfts were issued. If none, then just
+ * flush the RSCN. Otherwise, the outstanding requests
+ * need to complete.
+ */
vport->gidft_inp = 0;
- if (lpfc_issue_gidft(vport) == 0)
- /* Wait for NameServer query cmpl before we can
- * continue
- */
+ if (lpfc_issue_gidft(vport) > 0)
return 1;
} else {
- /* If login to NameServer does not exist, issue one */
- /* Good status, issue PLOGI to NameServer */
- ndlp = lpfc_findnode_did(vport, NameServer_DID);
- if (ndlp && NLP_CHK_NODE_ACT(ndlp))
- /* Wait for NameServer login cmpl before we can
- continue */
- return 1;
-
+ /* Nameserver login in question. Revalidate. */
if (ndlp) {
ndlp = lpfc_enable_node(vport, ndlp,
NLP_STE_PLOGI_ISSUE);
}
ndlp->nlp_prev_state = NLP_STE_UNUSED_NODE;
} else {
- ndlp = mempool_alloc(phba->nlp_mem_pool, GFP_KERNEL);
+ ndlp = lpfc_nlp_init(vport, NameServer_DID);
if (!ndlp) {
lpfc_els_flush_rscn(vport);
return 0;
}
- lpfc_nlp_init(vport, ndlp, NameServer_DID);
ndlp->nlp_prev_state = ndlp->nlp_state;
lpfc_nlp_set_state(vport, ndlp, NLP_STE_PLOGI_ISSUE);
}
ndlp = lpfc_findnode_did(vport, did);
if (!ndlp) {
/* Cannot find existing Fabric ndlp, so allocate a new one */
- ndlp = mempool_alloc(phba->nlp_mem_pool, GFP_KERNEL);
+ ndlp = lpfc_nlp_init(vport, did);
if (!ndlp)
goto dropit;
-
- lpfc_nlp_init(vport, ndlp, did);
lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
newnode = 1;
if ((did & Fabric_DID_MASK) == Fabric_DID_MASK)
static void
lpfc_start_fdmi(struct lpfc_vport *vport)
{
- struct lpfc_hba *phba = vport->phba;
struct lpfc_nodelist *ndlp;
/* If this is the first time, allocate an ndlp and initialize
*/
ndlp = lpfc_findnode_did(vport, FDMI_DID);
if (!ndlp) {
- ndlp = mempool_alloc(phba->nlp_mem_pool, GFP_KERNEL);
+ ndlp = lpfc_nlp_init(vport, FDMI_DID);
if (ndlp) {
- lpfc_nlp_init(vport, ndlp, FDMI_DID);
ndlp->nlp_type |= NLP_FABRIC;
} else {
return;
ndlp = lpfc_findnode_did(vport, NameServer_DID);
if (!ndlp) {
- ndlp = mempool_alloc(phba->nlp_mem_pool, GFP_KERNEL);
+ ndlp = lpfc_nlp_init(vport, NameServer_DID);
if (!ndlp) {
if (phba->fc_topology == LPFC_TOPOLOGY_LOOP) {
lpfc_disc_start(vport);
"0251 NameServer login: no memory\n");
return;
}
- lpfc_nlp_init(vport, ndlp, NameServer_DID);
} else if (!NLP_CHK_NODE_ACT(ndlp)) {
ndlp = lpfc_enable_node(vport, ndlp, NLP_STE_UNUSED_NODE);
if (!ndlp) {
pcmd += sizeof(uint32_t); /* Node Name */
pcmd += sizeof(uint32_t); /* Node Name */
memcpy(pcmd, &vport->fc_nodename, 8);
-
+ memset(sp->un.vendorVersion, 0, sizeof(sp->un.vendorVersion));
lpfc_set_disctmo(vport);
phba->fc_stat.elsXmitFDISC++;
MAILBOX_t *mb = &pmb->u.mb;
struct lpfc_dmabuf *mp = (struct lpfc_dmabuf *) pmb->context1;
struct lpfc_vport *vport = pmb->vport;
+ struct Scsi_Host *shost = lpfc_shost_from_vport(vport);
struct serv_parm *sp = &vport->fc_sparam;
uint32_t ed_tov;
}
lpfc_update_vport_wwn(vport);
+ fc_host_port_name(shost) = wwn_to_u64(vport->fc_portname.u.wwn);
if (vport->port_type == LPFC_PHYSICAL_PORT) {
memcpy(&phba->wwnn, &vport->fc_nodename, sizeof(phba->wwnn));
memcpy(&phba->wwpn, &vport->fc_portname, sizeof(phba->wwnn));
struct lpfc_sli_ring *pring;
MAILBOX_t *mb = &pmb->u.mb;
struct lpfc_dmabuf *mp = (struct lpfc_dmabuf *) (pmb->context1);
+ uint8_t attn_type;
/* Unblock ELS traffic */
pring = lpfc_phba_elsring(phba);
}
la = (struct lpfc_mbx_read_top *) &pmb->u.mb.un.varReadTop;
+ attn_type = bf_get(lpfc_mbx_read_top_att_type, la);
memcpy(&phba->alpa_map[0], mp->virt, 128);
if (phba->fc_eventTag <= la->eventTag) {
phba->fc_stat.LinkMultiEvent++;
- if (bf_get(lpfc_mbx_read_top_att_type, la) == LPFC_ATT_LINK_UP)
+ if (attn_type == LPFC_ATT_LINK_UP)
if (phba->fc_eventTag != 0)
lpfc_linkdown(phba);
}
}
phba->link_events++;
- if ((bf_get(lpfc_mbx_read_top_att_type, la) == LPFC_ATT_LINK_UP) &&
+ if ((attn_type == LPFC_ATT_LINK_UP) &&
!(phba->sli.sli_flag & LPFC_MENLO_MAINT)) {
phba->fc_stat.LinkUp++;
if (phba->link_flag & LS_LOOPBACK_MODE) {
phba->wait_4_mlo_maint_flg);
}
lpfc_mbx_process_link_up(phba, la);
- } else if (bf_get(lpfc_mbx_read_top_att_type, la) ==
- LPFC_ATT_LINK_DOWN) {
+ } else if (attn_type == LPFC_ATT_LINK_DOWN ||
+ attn_type == LPFC_ATT_UNEXP_WWPN) {
phba->fc_stat.LinkDown++;
if (phba->link_flag & LS_LOOPBACK_MODE)
lpfc_printf_log(phba, KERN_ERR, LOG_LINK_EVENT,
"Data: x%x x%x x%x\n",
la->eventTag, phba->fc_eventTag,
phba->pport->port_state, vport->fc_flag);
+ else if (attn_type == LPFC_ATT_UNEXP_WWPN)
+ lpfc_printf_log(phba, KERN_ERR, LOG_LINK_EVENT,
+ "1313 Link Down UNEXP WWPN Event x%x received "
+ "Data: x%x x%x x%x x%x x%x\n",
+ la->eventTag, phba->fc_eventTag,
+ phba->pport->port_state, vport->fc_flag,
+ bf_get(lpfc_mbx_read_top_mm, la),
+ bf_get(lpfc_mbx_read_top_fa, la));
else
lpfc_printf_log(phba, KERN_ERR, LOG_LINK_EVENT,
"1305 Link Down Event x%x received "
bf_get(lpfc_mbx_read_top_fa, la));
lpfc_mbx_issue_link_down(phba);
}
- if ((phba->sli.sli_flag & LPFC_MENLO_MAINT) &&
- ((bf_get(lpfc_mbx_read_top_att_type, la) == LPFC_ATT_LINK_UP))) {
+ if (phba->sli.sli_flag & LPFC_MENLO_MAINT &&
+ attn_type == LPFC_ATT_LINK_UP) {
if (phba->link_state != LPFC_LINK_DOWN) {
phba->fc_stat.LinkDown++;
lpfc_printf_log(phba, KERN_ERR, LOG_LINK_EVENT,
int old_state, int new_state)
{
struct Scsi_Host *shost = lpfc_shost_from_vport(vport);
- struct lpfc_hba *phba = vport->phba;
if (new_state == NLP_STE_UNMAPPED_NODE) {
ndlp->nlp_flag &= ~NLP_NODEV_REMOVE;
lpfc_unregister_remote_port(ndlp);
}
- /* Notify the NVME transport of this rport's loss */
- if (((phba->cfg_enable_fc4_type == LPFC_ENABLE_BOTH) ||
- (phba->cfg_enable_fc4_type == LPFC_ENABLE_NVME)) &&
- (vport->phba->nvmet_support == 0) &&
- ((ndlp->nlp_fc4_type & NLP_FC4_NVME) ||
- (ndlp->nlp_DID == Fabric_DID))) {
+ /* Notify the NVME transport of this rport's loss on the
+ * Initiator. For NVME Target, should upcall transport
+ * in the else clause when API available.
+ */
+ if (ndlp->nlp_fc4_type & NLP_FC4_NVME) {
vport->phba->nport_event_cnt++;
- lpfc_nvme_unregister_port(vport, ndlp);
+ if (vport->phba->nvmet_support == 0)
+ lpfc_nvme_unregister_port(vport, ndlp);
}
}
uint32_t did;
unsigned long flags;
unsigned long *active_rrqs_xri_bitmap = NULL;
+ int rpi = LPFC_RPI_ALLOC_ERROR;
if (!ndlp)
return NULL;
+ if (phba->sli_rev == LPFC_SLI_REV4) {
+ rpi = lpfc_sli4_alloc_rpi(vport->phba);
+ if (rpi == LPFC_RPI_ALLOC_ERROR)
+ return NULL;
+ }
+
spin_lock_irqsave(&phba->ndlp_lock, flags);
/* The ndlp should not be in memory free mode */
if (NLP_CHK_FREE_REQ(ndlp)) {
"usgmap:x%x refcnt:%d\n",
(void *)ndlp, ndlp->nlp_usg_map,
kref_read(&ndlp->kref));
- return NULL;
+ goto free_rpi;
}
/* The ndlp should not already be in active mode */
if (NLP_CHK_NODE_ACT(ndlp)) {
"usgmap:x%x refcnt:%d\n",
(void *)ndlp, ndlp->nlp_usg_map,
kref_read(&ndlp->kref));
- return NULL;
+ goto free_rpi;
}
/* Keep the original DID */
spin_unlock_irqrestore(&phba->ndlp_lock, flags);
if (vport->phba->sli_rev == LPFC_SLI_REV4) {
- ndlp->nlp_rpi = lpfc_sli4_alloc_rpi(vport->phba);
+ ndlp->nlp_rpi = rpi;
lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE,
"0008 rpi:%x DID:%x flg:%x refcnt:%d "
"map:%x %p\n", ndlp->nlp_rpi, ndlp->nlp_DID,
"node enable: did:x%x",
ndlp->nlp_DID, 0, 0);
return ndlp;
+
+free_rpi:
+ if (phba->sli_rev == LPFC_SLI_REV4)
+ lpfc_sli4_free_rpi(vport->phba, rpi);
+ return NULL;
}
void
ndlp = lpfc_findnode_did(vport, did);
if (!ndlp) {
+ if (vport->phba->nvmet_support)
+ return NULL;
if ((vport->fc_flag & FC_RSCN_MODE) != 0 &&
lpfc_rscn_payload_check(vport, did) == 0)
return NULL;
- ndlp = (struct lpfc_nodelist *)
- mempool_alloc(vport->phba->nlp_mem_pool, GFP_KERNEL);
+ ndlp = lpfc_nlp_init(vport, did);
if (!ndlp)
return NULL;
- lpfc_nlp_init(vport, ndlp, did);
lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
- if (vport->phba->nvmet_support)
- return ndlp;
spin_lock_irq(shost->host_lock);
ndlp->nlp_flag |= NLP_NPR_2B_DISC;
spin_unlock_irq(shost->host_lock);
return ndlp;
} else if (!NLP_CHK_NODE_ACT(ndlp)) {
+ if (vport->phba->nvmet_support)
+ return NULL;
ndlp = lpfc_enable_node(vport, ndlp, NLP_STE_NPR_NODE);
if (!ndlp)
return NULL;
- if (vport->phba->nvmet_support)
- return ndlp;
spin_lock_irq(shost->host_lock);
ndlp->nlp_flag |= NLP_NPR_2B_DISC;
spin_unlock_irq(shost->host_lock);
return ndlp;
}
+ /* The NVME Target does not want to actively manage an rport.
+ * The goal is to allow the target to reset its state and clear
+ * pending IO in preparation for the initiator to recover.
+ */
if ((vport->fc_flag & FC_RSCN_MODE) &&
!(vport->fc_flag & FC_NDISC_ACTIVE)) {
if (lpfc_rscn_payload_check(vport, did)) {
- /* If we've already received a PLOGI from this NPort
- * we don't need to try to discover it again.
- */
- if (ndlp->nlp_flag & NLP_RCV_PLOGI)
- return NULL;
/* Since this node is marked for discovery,
* delay timeout is not needed.
*/
lpfc_cancel_retry_delay_tmo(vport, ndlp);
+
+ /* NVME Target mode waits until rport is known to be
+ * impacted by the RSCN before it transitions. No
+ * active management - just go to NPR provided the
+ * node had a valid login.
+ */
if (vport->phba->nvmet_support)
return ndlp;
+
+ /* If we've already received a PLOGI from this NPort
+ * we don't need to try to discover it again.
+ */
+ if (ndlp->nlp_flag & NLP_RCV_PLOGI)
+ return NULL;
+
spin_lock_irq(shost->host_lock);
ndlp->nlp_flag |= NLP_NPR_2B_DISC;
spin_unlock_irq(shost->host_lock);
} else
ndlp = NULL;
} else {
- /* If we've already received a PLOGI from this NPort,
- * or we are already in the process of discovery on it,
- * we don't need to try to discover it again.
+ /* If the initiator received a PLOGI from this NPort or if the
+ * initiator is already in the process of discovery on it,
+ * there's no need to try to discover it again.
*/
if (ndlp->nlp_state == NLP_STE_ADISC_ISSUE ||
ndlp->nlp_state == NLP_STE_PLOGI_ISSUE ||
- ndlp->nlp_flag & NLP_RCV_PLOGI)
+ (!vport->phba->nvmet_support &&
+ ndlp->nlp_flag & NLP_RCV_PLOGI))
return NULL;
- lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
+
if (vport->phba->nvmet_support)
return ndlp;
+
+ /* Moving to NPR state clears unsolicited flags and
+ * allows for rediscovery
+ */
+ lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE);
+
spin_lock_irq(shost->host_lock);
ndlp->nlp_flag |= NLP_NPR_2B_DISC;
spin_unlock_irq(shost->host_lock);
return NULL;
}
-void
-lpfc_nlp_init(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
- uint32_t did)
+struct lpfc_nodelist *
+lpfc_nlp_init(struct lpfc_vport *vport, uint32_t did)
{
+ struct lpfc_nodelist *ndlp;
+ int rpi = LPFC_RPI_ALLOC_ERROR;
+
+ if (vport->phba->sli_rev == LPFC_SLI_REV4) {
+ rpi = lpfc_sli4_alloc_rpi(vport->phba);
+ if (rpi == LPFC_RPI_ALLOC_ERROR)
+ return NULL;
+ }
+
+ ndlp = mempool_alloc(vport->phba->nlp_mem_pool, GFP_KERNEL);
+ if (!ndlp) {
+ if (vport->phba->sli_rev == LPFC_SLI_REV4)
+ lpfc_sli4_free_rpi(vport->phba, rpi);
+ return NULL;
+ }
+
memset(ndlp, 0, sizeof (struct lpfc_nodelist));
lpfc_initialize_node(vport, ndlp, did);
INIT_LIST_HEAD(&ndlp->nlp_listp);
if (vport->phba->sli_rev == LPFC_SLI_REV4) {
- ndlp->nlp_rpi = lpfc_sli4_alloc_rpi(vport->phba);
+ ndlp->nlp_rpi = rpi;
lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE,
"0007 rpi:%x DID:%x flg:%x refcnt:%d "
"map:%x %p\n", ndlp->nlp_rpi, ndlp->nlp_DID,
"node init: did:x%x",
ndlp->nlp_DID, 0, 0);
- return;
+ return ndlp;
}
/* This routine releases all resources associated with a specifc NPort's ndlp
uint8_t word3Reserved2; /* Fc Word 3, bit 0: 7 */
};
+#define FAPWWN_KEY_VENDOR 0x42524344 /*valid vendor version fawwpn key*/
+
struct serv_parm { /* Structure is in Big Endian format */
struct csp cmn;
struct lpfc_name portName;
#define LPFC_ATT_RESERVED 0x00 /* Reserved - attType */
#define LPFC_ATT_LINK_UP 0x01 /* Link is up */
#define LPFC_ATT_LINK_DOWN 0x02 /* Link is down */
+#define LPFC_ATT_UNEXP_WWPN 0x06 /* Link is down Unexpected WWWPN */
uint32_t word3;
#define lpfc_mbx_read_top_alpa_granted_SHIFT 24
#define lpfc_mbx_read_top_alpa_granted_MASK 0x000000FF
#define lpfc_mbx_rq_ftr_rq_ifip_SHIFT 7
#define lpfc_mbx_rq_ftr_rq_ifip_MASK 0x00000001
#define lpfc_mbx_rq_ftr_rq_ifip_WORD word2
+#define lpfc_mbx_rq_ftr_rq_iaar_SHIFT 9
+#define lpfc_mbx_rq_ftr_rq_iaar_MASK 0x00000001
+#define lpfc_mbx_rq_ftr_rq_iaar_WORD word2
#define lpfc_mbx_rq_ftr_rq_perfh_SHIFT 11
#define lpfc_mbx_rq_ftr_rq_perfh_MASK 0x00000001
#define lpfc_mbx_rq_ftr_rq_perfh_WORD word2
#define LPFC_FC_LA_TYPE_NO_HARD_ALPA 0x3
#define LPFC_FC_LA_TYPE_MDS_LINK_DOWN 0x4
#define LPFC_FC_LA_TYPE_MDS_LOOPBACK 0x5
+#define LPFC_FC_LA_TYPE_UNEXP_WWPN 0x6
#define lpfc_acqe_fc_la_port_type_SHIFT 6
#define lpfc_acqe_fc_la_port_type_MASK 0x00000003
#define lpfc_acqe_fc_la_port_type_WORD word0
#include <scsi/scsi_device.h>
#include <scsi/scsi_host.h>
#include <scsi/scsi_transport_fc.h>
+#include <scsi/scsi_tcq.h>
+#include <scsi/fc/fc_fs.h>
+
+#include <linux/nvme-fc-driver.h>
#include "lpfc_hw4.h"
#include "lpfc_hw.h"
#include "lpfc.h"
#include "lpfc_scsi.h"
#include "lpfc_nvme.h"
+#include "lpfc_nvmet.h"
#include "lpfc_logmsg.h"
#include "lpfc_crtn.h"
#include "lpfc_vport.h"
void
lpfc_update_vport_wwn(struct lpfc_vport *vport)
{
+ uint8_t vvvl = vport->fc_sparam.cmn.valid_vendor_ver_level;
+ u32 *fawwpn_key = (u32 *)&vport->fc_sparam.un.vendorVersion[0];
+
/* If the soft name exists then update it using the service params */
if (vport->phba->cfg_soft_wwnn)
u64_to_wwn(vport->phba->cfg_soft_wwnn,
memcpy(&vport->fc_sparam.nodeName, &vport->fc_nodename,
sizeof(struct lpfc_name));
- if (vport->fc_portname.u.wwn[0] == 0 || vport->phba->cfg_soft_wwpn)
+ /*
+ * If the port name has changed, then set the Param changes flag
+ * to unreg the login
+ */
+ if (vport->fc_portname.u.wwn[0] != 0 &&
+ memcmp(&vport->fc_portname, &vport->fc_sparam.portName,
+ sizeof(struct lpfc_name)))
+ vport->vport_flag |= FAWWPN_PARAM_CHG;
+
+ if (vport->fc_portname.u.wwn[0] == 0 ||
+ vport->phba->cfg_soft_wwpn ||
+ (vvvl == 1 && cpu_to_be32(*fawwpn_key) == FAPWWN_KEY_VENDOR) ||
+ vport->vport_flag & FAWWPN_SET) {
memcpy(&vport->fc_portname, &vport->fc_sparam.portName,
sizeof(struct lpfc_name));
+ vport->vport_flag &= ~FAWWPN_SET;
+ if (vvvl == 1 && cpu_to_be32(*fawwpn_key) == FAPWWN_KEY_VENDOR)
+ vport->vport_flag |= FAWWPN_SET;
+ }
else
memcpy(&vport->fc_sparam.portName, &vport->fc_portname,
sizeof(struct lpfc_name));
lpfc_hba_down_post_s4(struct lpfc_hba *phba)
{
struct lpfc_scsi_buf *psb, *psb_next;
+ struct lpfc_nvmet_rcv_ctx *ctxp, *ctxp_next;
LIST_HEAD(aborts);
LIST_HEAD(nvme_aborts);
+ LIST_HEAD(nvmet_aborts);
unsigned long iflag = 0;
struct lpfc_sglq *sglq_entry = NULL;
list_for_each_entry(sglq_entry,
&phba->sli4_hba.lpfc_abts_els_sgl_list, list)
sglq_entry->state = SGL_FREED;
- list_for_each_entry(sglq_entry,
- &phba->sli4_hba.lpfc_abts_nvmet_sgl_list, list)
- sglq_entry->state = SGL_FREED;
list_splice_init(&phba->sli4_hba.lpfc_abts_els_sgl_list,
&phba->sli4_hba.lpfc_els_sgl_list);
- if (phba->sli4_hba.nvme_wq)
- list_splice_init(&phba->sli4_hba.lpfc_abts_nvmet_sgl_list,
- &phba->sli4_hba.lpfc_nvmet_sgl_list);
spin_unlock(&phba->sli4_hba.sgl_list_lock);
/* abts_scsi_buf_list_lock required because worker thread uses this
spin_lock(&phba->sli4_hba.abts_nvme_buf_list_lock);
list_splice_init(&phba->sli4_hba.lpfc_abts_nvme_buf_list,
&nvme_aborts);
+ list_splice_init(&phba->sli4_hba.lpfc_abts_nvmet_ctx_list,
+ &nvmet_aborts);
spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock);
}
list_splice(&aborts, &phba->lpfc_scsi_buf_list_put);
spin_unlock_irqrestore(&phba->scsi_buf_list_put_lock, iflag);
- list_for_each_entry_safe(psb, psb_next, &nvme_aborts, list) {
- psb->pCmd = NULL;
- psb->status = IOSTAT_SUCCESS;
+ if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) {
+ list_for_each_entry_safe(psb, psb_next, &nvme_aborts, list) {
+ psb->pCmd = NULL;
+ psb->status = IOSTAT_SUCCESS;
+ }
+ spin_lock_irqsave(&phba->nvme_buf_list_put_lock, iflag);
+ list_splice(&nvme_aborts, &phba->lpfc_nvme_buf_list_put);
+ spin_unlock_irqrestore(&phba->nvme_buf_list_put_lock, iflag);
+
+ list_for_each_entry_safe(ctxp, ctxp_next, &nvmet_aborts, list) {
+ ctxp->flag &= ~(LPFC_NVMET_XBUSY | LPFC_NVMET_ABORT_OP);
+ lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
+ }
}
- spin_lock_irqsave(&phba->nvme_buf_list_put_lock, iflag);
- list_splice(&nvme_aborts, &phba->lpfc_nvme_buf_list_put);
- spin_unlock_irqrestore(&phba->nvme_buf_list_put_lock, iflag);
lpfc_sli4_free_sp_events(phba);
return 0;
{
struct lpfc_nodelist *ndlp, *next_ndlp;
struct lpfc_vport **vports;
- int i;
+ int i, rpi;
+ unsigned long flags;
if (phba->sli_rev != LPFC_SLI_REV4)
return;
vports = lpfc_create_vport_work_array(phba);
- if (vports != NULL) {
- for (i = 0; i <= phba->max_vports && vports[i] != NULL; i++) {
- if (vports[i]->load_flag & FC_UNLOADING)
- continue;
+ if (vports == NULL)
+ return;
- list_for_each_entry_safe(ndlp, next_ndlp,
- &vports[i]->fc_nodes,
- nlp_listp) {
- if (NLP_CHK_NODE_ACT(ndlp)) {
- ndlp->nlp_rpi =
- lpfc_sli4_alloc_rpi(phba);
- lpfc_printf_vlog(ndlp->vport, KERN_INFO,
- LOG_NODE,
- "0009 rpi:%x DID:%x "
- "flg:%x map:%x %p\n",
- ndlp->nlp_rpi,
- ndlp->nlp_DID,
- ndlp->nlp_flag,
- ndlp->nlp_usg_map,
- ndlp);
- }
+ for (i = 0; i <= phba->max_vports && vports[i] != NULL; i++) {
+ if (vports[i]->load_flag & FC_UNLOADING)
+ continue;
+
+ list_for_each_entry_safe(ndlp, next_ndlp,
+ &vports[i]->fc_nodes,
+ nlp_listp) {
+ if (!NLP_CHK_NODE_ACT(ndlp))
+ continue;
+ rpi = lpfc_sli4_alloc_rpi(phba);
+ if (rpi == LPFC_RPI_ALLOC_ERROR) {
+ spin_lock_irqsave(&phba->ndlp_lock, flags);
+ NLP_CLR_NODE_ACT(ndlp);
+ spin_unlock_irqrestore(&phba->ndlp_lock, flags);
+ continue;
}
+ ndlp->nlp_rpi = rpi;
+ lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE,
+ "0009 rpi:%x DID:%x "
+ "flg:%x map:%x %p\n", ndlp->nlp_rpi,
+ ndlp->nlp_DID, ndlp->nlp_flag,
+ ndlp->nlp_usg_map, ndlp);
}
}
lpfc_destroy_vport_work_array(phba, vports);
spin_unlock(&phba->scsi_buf_list_put_lock);
spin_unlock_irq(&phba->scsi_buf_list_get_lock);
+ lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
+ "6060 Current allocated SCSI xri-sgl count:%d, "
+ "maximum SCSI xri count:%d (split:%d)\n",
+ phba->sli4_hba.scsi_xri_cnt,
+ phba->sli4_hba.scsi_xri_max, phba->cfg_xri_split);
+
if (phba->sli4_hba.scsi_xri_cnt > phba->sli4_hba.scsi_xri_max) {
/* max scsi xri shrinked below the allocated scsi buffers */
scsi_xri_cnt = phba->sli4_hba.scsi_xri_cnt -
/* Parse and translate link attention fields */
la = (struct lpfc_mbx_read_top *)&pmb->u.mb.un.varReadTop;
la->eventTag = acqe_fc->event_tag;
- bf_set(lpfc_mbx_read_top_att_type, la,
- LPFC_FC_LA_TYPE_LINK_DOWN);
+ if (phba->sli4_hba.link_state.status ==
+ LPFC_FC_LA_TYPE_UNEXP_WWPN) {
+ bf_set(lpfc_mbx_read_top_att_type, la,
+ LPFC_FC_LA_TYPE_UNEXP_WWPN);
+ } else {
+ bf_set(lpfc_mbx_read_top_att_type, la,
+ LPFC_FC_LA_TYPE_LINK_DOWN);
+ }
/* Invoke the mailbox command callback function */
lpfc_mbx_cmpl_read_topology(phba, pmb);
ndlp = lpfc_findnode_did(vport, Fabric_DID);
if (!ndlp) {
/* Cannot find existing Fabric ndlp, so allocate a new one */
- ndlp = mempool_alloc(phba->nlp_mem_pool, GFP_KERNEL);
+ ndlp = lpfc_nlp_init(vport, Fabric_DID);
if (!ndlp)
return 0;
- lpfc_nlp_init(vport, ndlp, Fabric_DID);
/* Set the node type */
ndlp->nlp_type |= NLP_FABRIC;
/* Put ndlp onto node list */
/* Initialize the Abort nvme buffer list used by driver */
spin_lock_init(&phba->sli4_hba.abts_nvme_buf_list_lock);
INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_nvme_buf_list);
+ INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_nvmet_ctx_list);
/* Fast-path XRI aborted CQ Event work queue list */
INIT_LIST_HEAD(&phba->sli4_hba.sp_nvme_xri_aborted_work_queue);
}
INIT_LIST_HEAD(&phba->sli4_hba.lpfc_vfi_blk_list);
INIT_LIST_HEAD(&phba->lpfc_vpi_blk_list);
+ /* Initialize mboxq lists. If the early init routines fail
+ * these lists need to be correctly initialized.
+ */
+ INIT_LIST_HEAD(&phba->sli.mboxq);
+ INIT_LIST_HEAD(&phba->sli.mboxq_cmpl);
+
/* initialize optic_state to 0xFF */
phba->sli4_hba.lnk_info.optic_state = 0xff;
"READ_NV, mbxStatus x%x\n",
bf_get(lpfc_mqe_command, &mboxq->u.mqe),
bf_get(lpfc_mqe_status, &mboxq->u.mqe));
+ mempool_free(mboxq, phba->mbox_mem_pool);
rc = -EIO;
goto out_free_bsmbx;
}
INIT_LIST_HEAD(&phba->sli4_hba.lpfc_els_sgl_list);
INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_els_sgl_list);
INIT_LIST_HEAD(&phba->sli4_hba.lpfc_nvmet_sgl_list);
- INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_nvmet_sgl_list);
+ INIT_LIST_HEAD(&phba->sli4_hba.lpfc_abts_nvmet_ctx_list);
/* els xri-sgl book keeping */
phba->sli4_hba.els_xri_cnt = 0;
/* Create Fast Path FCP WQs */
wqesize = (phba->fcp_embed_io) ?
- LPFC_WQE128_SIZE : phba->sli4_hba.wq_esize;
+ LPFC_WQE128_SIZE : phba->sli4_hba.wq_esize;
qdesc = lpfc_sli4_queue_alloc(phba, wqesize, phba->sli4_hba.wq_ecount);
if (!qdesc) {
lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
lpfc_sli4_queue_create(struct lpfc_hba *phba)
{
struct lpfc_queue *qdesc;
- int idx, io_channel, max;
+ int idx, io_channel;
/*
* Create HBA Record arrays.
if (lpfc_alloc_nvme_wq_cq(phba, idx))
goto out_error;
- /* allocate MRQ CQs */
- max = phba->cfg_nvme_io_channel;
- if (max < phba->cfg_nvmet_mrq)
- max = phba->cfg_nvmet_mrq;
-
- for (idx = 0; idx < max; idx++)
- if (lpfc_alloc_nvme_wq_cq(phba, idx))
- goto out_error;
-
if (phba->nvmet_support) {
for (idx = 0; idx < phba->cfg_nvmet_mrq; idx++) {
qdesc = lpfc_sli4_queue_alloc(phba,
/* Release FCP cqs */
lpfc_sli4_release_queues(&phba->sli4_hba.fcp_cq,
- phba->cfg_fcp_io_channel);
+ phba->cfg_fcp_io_channel);
/* Release FCP wqs */
lpfc_sli4_release_queues(&phba->sli4_hba.fcp_wq,
- phba->cfg_fcp_io_channel);
+ phba->cfg_fcp_io_channel);
/* Release FCP CQ mapping array */
lpfc_sli4_release_queue_map(&phba->sli4_hba.fcp_cq_map);
lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
"0528 %s not allocated\n",
phba->sli4_hba.mbx_cq ?
- "Mailbox WQ" : "Mailbox CQ");
+ "Mailbox WQ" : "Mailbox CQ");
rc = -ENOMEM;
goto out_destroy;
}
rc = lpfc_create_wq_cq(phba, phba->sli4_hba.hba_eq[0],
- phba->sli4_hba.mbx_cq,
- phba->sli4_hba.mbx_wq,
- NULL, 0, LPFC_MBOX);
+ phba->sli4_hba.mbx_cq,
+ phba->sli4_hba.mbx_wq,
+ NULL, 0, LPFC_MBOX);
if (rc) {
lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
"0529 Failed setup of mailbox WQ/CQ: rc = 0x%x\n",
{
int wait_time = 0;
int nvme_xri_cmpl = 1;
+ int nvmet_xri_cmpl = 1;
int fcp_xri_cmpl = 1;
int els_xri_cmpl = list_empty(&phba->sli4_hba.lpfc_abts_els_sgl_list);
- int nvmet_xri_cmpl =
- list_empty(&phba->sli4_hba.lpfc_abts_nvmet_sgl_list);
if (phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP)
fcp_xri_cmpl =
list_empty(&phba->sli4_hba.lpfc_abts_scsi_buf_list);
- if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME)
+ if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) {
nvme_xri_cmpl =
list_empty(&phba->sli4_hba.lpfc_abts_nvme_buf_list);
+ nvmet_xri_cmpl =
+ list_empty(&phba->sli4_hba.lpfc_abts_nvmet_ctx_list);
+ }
while (!fcp_xri_cmpl || !els_xri_cmpl || !nvme_xri_cmpl ||
!nvmet_xri_cmpl) {
msleep(LPFC_XRI_EXCH_BUSY_WAIT_T1);
wait_time += LPFC_XRI_EXCH_BUSY_WAIT_T1;
}
- if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME)
+ if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) {
nvme_xri_cmpl = list_empty(
&phba->sli4_hba.lpfc_abts_nvme_buf_list);
+ nvmet_xri_cmpl = list_empty(
+ &phba->sli4_hba.lpfc_abts_nvmet_ctx_list);
+ }
if (phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP)
fcp_xri_cmpl = list_empty(
els_xri_cmpl =
list_empty(&phba->sli4_hba.lpfc_abts_els_sgl_list);
- nvmet_xri_cmpl =
- list_empty(&phba->sli4_hba.lpfc_abts_nvmet_sgl_list);
}
}
/* Stop kthread signal shall trigger work_done one more time */
kthread_stop(phba->worker_thread);
+ /* Unset the queues shared with the hardware then release all
+ * allocated resources.
+ */
+ lpfc_sli4_queue_unset(phba);
+ lpfc_sli4_queue_destroy(phba);
+
/* Reset SLI4 HBA FCoE function */
lpfc_pci_function_reset(phba);
- lpfc_sli4_queue_destroy(phba);
/* Stop the SLI4 device port */
phba->pport->work_port_events = 0;
}
/* Initialize and populate the iocb list per host */
+
error = lpfc_init_iocb_list(phba, LPFC_IOCB_LIST_CNT);
if (error) {
lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
struct lpfc_hba *phba;
struct lpfc_vport *vport = NULL;
struct Scsi_Host *shost = NULL;
- int error;
+ int error, cnt;
uint32_t cfg_mode, intr_mode;
/* Allocate memory for HBA structure */
goto out_unset_pci_mem_s4;
}
- /* Initialize and populate the iocb list per host */
+ cnt = phba->cfg_iocb_cnt * 1024;
+ if (phba->nvmet_support)
+ cnt += phba->cfg_nvmet_mrq_post * phba->cfg_nvmet_mrq;
+ /* Initialize and populate the iocb list per host */
lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
- "2821 initialize iocb list %d.\n",
- phba->cfg_iocb_cnt*1024);
- error = lpfc_init_iocb_list(phba, phba->cfg_iocb_cnt*1024);
+ "2821 initialize iocb list %d total %d\n",
+ phba->cfg_iocb_cnt, cnt);
+ error = lpfc_init_iocb_list(phba, cnt);
if (error) {
lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
if ((phba->nvmet_support == 0) &&
(phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME)) {
/* Create NVME binding with nvme_fc_transport. This
- * ensures the vport is initialized.
+ * ensures the vport is initialized. If the localport
+ * create fails, it should not unload the driver to
+ * support field issues.
*/
error = lpfc_nvme_create_localport(vport);
if (error) {
"6004 NVME registration failed, "
"error x%x\n",
error);
- goto out_disable_intr;
}
}
lpfc_fof_queue_create(struct lpfc_hba *phba)
{
struct lpfc_queue *qdesc;
+ uint32_t wqesize;
/* Create FOF EQ */
qdesc = lpfc_sli4_queue_alloc(phba, phba->sli4_hba.eq_esize,
phba->sli4_hba.oas_cq = qdesc;
/* Create OAS WQ */
- qdesc = lpfc_sli4_queue_alloc(phba, phba->sli4_hba.wq_esize,
+ wqesize = (phba->fcp_embed_io) ?
+ LPFC_WQE128_SIZE : phba->sli4_hba.wq_esize;
+ qdesc = lpfc_sli4_queue_alloc(phba, wqesize,
phba->sli4_hba.wq_ecount);
+
if (!qdesc)
goto out_error;
if (phba->max_vpi && phba->cfg_enable_npiv)
bf_set(lpfc_mbx_rq_ftr_rq_npiv, &mboxq->u.mqe.un.req_ftrs, 1);
- if (phba->nvmet_support)
+ if (phba->nvmet_support) {
bf_set(lpfc_mbx_rq_ftr_rq_mrqp, &mboxq->u.mqe.un.req_ftrs, 1);
-
+ /* iaab/iaar NOT set for now */
+ bf_set(lpfc_mbx_rq_ftr_rq_iaab, &mboxq->u.mqe.un.req_ftrs, 0);
+ bf_set(lpfc_mbx_rq_ftr_rq_iaar, &mboxq->u.mqe.un.req_ftrs, 0);
+ }
return;
}
case NLP_STE_PRLI_ISSUE:
case NLP_STE_UNMAPPED_NODE:
case NLP_STE_MAPPED_NODE:
- /* lpfc_plogi_confirm_nport skips fabric did, handle it here */
- if (!(ndlp->nlp_type & NLP_FABRIC)) {
+ /* For initiators, lpfc_plogi_confirm_nport skips fabric did.
+ * For target mode, execute implicit logo.
+ * Fabric nodes go into NPR.
+ */
+ if (!(ndlp->nlp_type & NLP_FABRIC) &&
+ !(phba->nvmet_support)) {
lpfc_els_rsp_acc(vport, ELS_CMD_PLOGI, cmdiocb,
ndlp, NULL);
return 1;
struct lpfc_nodelist *ndlp;
struct ulp_bde64 *bpl;
struct lpfc_dmabuf *bmp;
+ uint16_t ntype, nstate;
/* there are two dma buf in the request, actually there is one and
* the second one is just the start address + cmd size.
vport = lport->vport;
ndlp = lpfc_findnode_did(vport, pnvme_rport->port_id);
- if (!ndlp) {
- lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_DISC,
- "6043 Could not find node for DID %x\n",
+ if (!ndlp || !NLP_CHK_NODE_ACT(ndlp)) {
+ lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE | LOG_NVME_IOERR,
+ "6051 DID x%06x not an active rport.\n",
pnvme_rport->port_id);
- return 1;
+ return -ENODEV;
+ }
+
+ /* The remote node has to be a mapped nvme target or an
+ * unmapped nvme initiator or it's an error.
+ */
+ ntype = ndlp->nlp_type;
+ nstate = ndlp->nlp_state;
+ if ((ntype & NLP_NVME_TARGET && nstate != NLP_STE_MAPPED_NODE) ||
+ (ntype & NLP_NVME_INITIATOR && nstate != NLP_STE_UNMAPPED_NODE)) {
+ lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE | LOG_NVME_IOERR,
+ "6088 DID x%06x not ready for "
+ "IO. State x%x, Type x%x\n",
+ pnvme_rport->port_id,
+ ndlp->nlp_state, ndlp->nlp_type);
+ return -ENODEV;
}
bmp = kmalloc(sizeof(struct lpfc_dmabuf), GFP_KERNEL);
if (!bmp) {
/* Expand print to include key fields. */
lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC,
- "6051 ENTER. lport %p, rport %p lsreq%p rqstlen:%d "
+ "6149 ENTER. lport %p, rport %p lsreq%p rqstlen:%d "
"rsplen:%d %pad %pad\n",
pnvme_lport, pnvme_rport,
pnvme_lsreq, pnvme_lsreq->rqstlen,
struct nvme_fc_cmd_iu *cp;
struct lpfc_nvme_rport *rport;
struct lpfc_nodelist *ndlp;
+ struct lpfc_nvme_fcpreq_priv *freqpriv;
unsigned long flags;
uint32_t code;
uint16_t cid, sqhd, data;
ndlp = rport->ndlp;
if (!ndlp || !NLP_CHK_NODE_ACT(ndlp)) {
lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE | LOG_NVME_IOERR,
- "6061 rport %p, ndlp %p, DID x%06x ndlp "
- "not ready.\n",
- rport, ndlp, rport->remoteport->port_id);
+ "6061 rport %p, DID x%06x node not ready.\n",
+ rport, rport->remoteport->port_id);
ndlp = lpfc_findnode_did(vport, rport->remoteport->port_id);
if (!ndlp) {
break;
lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_IOERR,
"6081 NVME Completion Protocol Error: "
- "status x%x result x%x placed x%x\n",
+ "xri %x status x%x result x%x "
+ "placed x%x\n",
+ lpfc_ncmd->cur_iocbq.sli4_xritag,
lpfc_ncmd->status, lpfc_ncmd->result,
wcqe->total_data_placed);
break;
default:
out_err:
lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_IOERR,
- "6072 NVME Completion Error: "
+ "6072 NVME Completion Error: xri %x "
"status x%x result x%x placed x%x\n",
+ lpfc_ncmd->cur_iocbq.sli4_xritag,
lpfc_ncmd->status, lpfc_ncmd->result,
wcqe->total_data_placed);
nCmd->transferred_length = 0;
phba->cpucheck_cmpl_io[lpfc_ncmd->cpu]++;
}
#endif
+ freqpriv = nCmd->private;
+ freqpriv->nvme_buf = NULL;
nCmd->done(nCmd);
spin_lock_irqsave(&phba->hbalock, flags);
first_data_sgl = sgl;
lpfc_ncmd->seg_cnt = nCmd->sg_cnt;
- if (lpfc_ncmd->seg_cnt > phba->cfg_sg_seg_cnt) {
+ if (lpfc_ncmd->seg_cnt > phba->cfg_nvme_seg_cnt) {
lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
"6058 Too many sg segments from "
"NVME Transport. Max %d, "
"nvmeIO sg_cnt %d\n",
- phba->cfg_sg_seg_cnt,
+ phba->cfg_nvme_seg_cnt,
lpfc_ncmd->seg_cnt);
lpfc_ncmd->seg_cnt = 0;
return 1;
struct lpfc_nvme_buf *lpfc_ncmd;
struct lpfc_nvme_rport *rport;
struct lpfc_nvme_qhandle *lpfc_queue_info;
+ struct lpfc_nvme_fcpreq_priv *freqpriv = pnvme_fcreq->private;
#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
uint64_t start = 0;
#endif
* Do not let the IO hang out forever. There is no midlayer issuing
* an abort so inform the FW of the maximum IO pending time.
*/
- pnvme_fcreq->private = (void *)lpfc_ncmd;
+ freqpriv->nvme_buf = lpfc_ncmd;
lpfc_ncmd->nvmeCmd = pnvme_fcreq;
lpfc_ncmd->nrport = rport;
lpfc_ncmd->ndlp = ndlp;
struct lpfc_nvme_buf *lpfc_nbuf;
struct lpfc_iocbq *abts_buf;
struct lpfc_iocbq *nvmereq_wqe;
+ struct lpfc_nvme_fcpreq_priv *freqpriv = pnvme_fcreq->private;
union lpfc_wqe *abts_wqe;
unsigned long flags;
int ret_val;
phba = vport->phba;
/* Announce entry to new IO submit field. */
- lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS,
+ lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_ABTS,
"6002 Abort Request to rport DID x%06x "
"for nvme_fc_req %p\n",
pnvme_rport->port_id,
/* The remote node has to be ready to send an abort. */
if ((ndlp->nlp_state != NLP_STE_MAPPED_NODE) &&
!(ndlp->nlp_type & NLP_NVME_TARGET)) {
- lpfc_printf_vlog(vport, KERN_ERR, LOG_NODE | LOG_NVME_ABTS,
+ lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS,
"6048 rport %p, DID x%06x not ready for "
"IO. State x%x, Type x%x\n",
rport, pnvme_rport->port_id,
/* driver queued commands are in process of being flushed */
if (phba->hba_flag & HBA_NVME_IOQ_FLUSH) {
spin_unlock_irqrestore(&phba->hbalock, flags);
- lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+ lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS,
"6139 Driver in reset cleanup - flushing "
"NVME Req now. hba_flag x%x\n",
phba->hba_flag);
return;
}
- lpfc_nbuf = (struct lpfc_nvme_buf *)pnvme_fcreq->private;
+ lpfc_nbuf = freqpriv->nvme_buf;
if (!lpfc_nbuf) {
spin_unlock_irqrestore(&phba->hbalock, flags);
- lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+ lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS,
"6140 NVME IO req has no matching lpfc nvme "
"io buffer. Skipping abort req.\n");
return;
} else if (!lpfc_nbuf->nvmeCmd) {
spin_unlock_irqrestore(&phba->hbalock, flags);
- lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+ lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS,
"6141 lpfc NVME IO req has no nvme_fcreq "
"io buffer. Skipping abort req.\n");
return;
}
+ nvmereq_wqe = &lpfc_nbuf->cur_iocbq;
/*
* The lpfc_nbuf and the mapped nvme_fcreq in the driver's
*/
if (lpfc_nbuf->nvmeCmd != pnvme_fcreq) {
spin_unlock_irqrestore(&phba->hbalock, flags);
- lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+ lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS,
"6143 NVME req mismatch: "
"lpfc_nbuf %p nvmeCmd %p, "
- "pnvme_fcreq %p. Skipping Abort\n",
+ "pnvme_fcreq %p. Skipping Abort xri x%x\n",
lpfc_nbuf, lpfc_nbuf->nvmeCmd,
- pnvme_fcreq);
+ pnvme_fcreq, nvmereq_wqe->sli4_xritag);
return;
}
/* Don't abort IOs no longer on the pending queue. */
- nvmereq_wqe = &lpfc_nbuf->cur_iocbq;
if (!(nvmereq_wqe->iocb_flag & LPFC_IO_ON_TXCMPLQ)) {
spin_unlock_irqrestore(&phba->hbalock, flags);
- lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+ lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS,
"6142 NVME IO req %p not queued - skipping "
- "abort req\n",
- pnvme_fcreq);
+ "abort req xri x%x\n",
+ pnvme_fcreq, nvmereq_wqe->sli4_xritag);
return;
}
/* Outstanding abort is in progress */
if (nvmereq_wqe->iocb_flag & LPFC_DRIVER_ABORTED) {
spin_unlock_irqrestore(&phba->hbalock, flags);
- lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+ lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS,
"6144 Outstanding NVME I/O Abort Request "
"still pending on nvme_fcreq %p, "
- "lpfc_ncmd %p\n",
- pnvme_fcreq, lpfc_nbuf);
+ "lpfc_ncmd %p xri x%x\n",
+ pnvme_fcreq, lpfc_nbuf,
+ nvmereq_wqe->sli4_xritag);
return;
}
abts_buf = __lpfc_sli_get_iocbq(phba);
if (!abts_buf) {
spin_unlock_irqrestore(&phba->hbalock, flags);
- lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+ lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS,
"6136 No available abort wqes. Skipping "
- "Abts req for nvme_fcreq %p.\n",
- pnvme_fcreq);
+ "Abts req for nvme_fcreq %p xri x%x\n",
+ pnvme_fcreq, nvmereq_wqe->sli4_xritag);
return;
}
ret_val = lpfc_sli4_issue_wqe(phba, LPFC_FCP_RING, abts_buf);
spin_unlock_irqrestore(&phba->hbalock, flags);
if (ret_val == IOCB_ERROR) {
- lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
+ lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_ABTS,
"6137 Failed abts issue_wqe with status x%x "
"for nvme_fcreq %p.\n",
ret_val, pnvme_fcreq);
return;
}
- lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME,
- "6138 Transport Abort NVME Request Issued for\n"
+ lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_ABTS,
+ "6138 Transport Abort NVME Request Issued for "
"ox_id x%x on reqtag x%x\n",
nvmereq_wqe->sli4_xritag,
abts_buf->iotag);
.local_priv_sz = sizeof(struct lpfc_nvme_lport),
.remote_priv_sz = sizeof(struct lpfc_nvme_rport),
.lsrqst_priv_sz = 0,
- .fcprqst_priv_sz = 0,
+ .fcprqst_priv_sz = sizeof(struct lpfc_nvme_fcpreq_priv),
};
/**
if (lpfc_test_rrq_active(phba, ndlp,
lpfc_ncmd->cur_iocbq.sli4_lxritag))
continue;
- list_del(&lpfc_ncmd->list);
+ list_del_init(&lpfc_ncmd->list);
found = 1;
break;
}
if (lpfc_test_rrq_active(
phba, ndlp, lpfc_ncmd->cur_iocbq.sli4_lxritag))
continue;
- list_del(&lpfc_ncmd->list);
+ list_del_init(&lpfc_ncmd->list);
found = 1;
break;
}
lpfc_ncmd->nonsg_phys = 0;
if (lpfc_ncmd->flags & LPFC_SBUF_XBUSY) {
+ lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+ "6310 XB release deferred for "
+ "ox_id x%x on reqtag x%x\n",
+ lpfc_ncmd->cur_iocbq.sli4_xritag,
+ lpfc_ncmd->cur_iocbq.iotag);
+
spin_lock_irqsave(&phba->sli4_hba.abts_nvme_buf_list_lock,
iflag);
lpfc_ncmd->nvmeCmd = NULL;
nfcp_info.node_name = wwn_to_u64(vport->fc_nodename.u.wwn);
nfcp_info.port_name = wwn_to_u64(vport->fc_portname.u.wwn);
- /* For now need + 1 to get around NVME transport logic */
- lpfc_nvme_template.max_sgl_segments = phba->cfg_sg_seg_cnt + 1;
+ /* Limit to LPFC_MAX_NVME_SEG_CNT.
+ * For now need + 1 to get around NVME transport logic.
+ */
+ if (phba->cfg_sg_seg_cnt > LPFC_MAX_NVME_SEG_CNT) {
+ lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME | LOG_INIT,
+ "6300 Reducing sg segment cnt to %d\n",
+ LPFC_MAX_NVME_SEG_CNT);
+ phba->cfg_nvme_seg_cnt = LPFC_MAX_NVME_SEG_CNT;
+ } else {
+ phba->cfg_nvme_seg_cnt = phba->cfg_sg_seg_cnt;
+ }
+ lpfc_nvme_template.max_sgl_segments = phba->cfg_nvme_seg_cnt + 1;
lpfc_nvme_template.max_hw_queues = phba->cfg_nvme_io_channel;
/* localport is allocated from the stack, but the registration
void
lpfc_nvme_update_localport(struct lpfc_vport *vport)
{
+#if (IS_ENABLED(CONFIG_NVME_FC))
struct nvme_fc_local_port *localport;
struct lpfc_nvme_lport *lport;
localport = vport->localport;
+ if (!localport) {
+ lpfc_printf_vlog(vport, KERN_WARNING, LOG_NVME,
+ "6710 Update NVME fail. No localport\n");
+ return;
+ }
lport = (struct lpfc_nvme_lport *)localport->private;
-
+ if (!lport) {
+ lpfc_printf_vlog(vport, KERN_WARNING, LOG_NVME,
+ "6171 Update NVME fail. localP %p, No lport\n",
+ localport);
+ return;
+ }
lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME,
"6012 Update NVME lport %p did x%x\n",
localport, vport->fc_myDID);
lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_DISC,
"6030 bound lport %p to DID x%06x\n",
lport, localport->port_id);
-
+#endif
}
int
struct lpfc_nvme_lport *lport;
struct lpfc_nvme_rport *rport;
struct nvme_fc_remote_port *remoteport;
+ unsigned long wait_tmo;
localport = vport->localport;
* before proceeding. This guarantees the transport and driver
* have completed the unreg process.
*/
- ret = wait_for_completion_timeout(&rport->rport_unreg_done, 5);
+ wait_tmo = msecs_to_jiffies(5000);
+ ret = wait_for_completion_timeout(&rport->rport_unreg_done,
+ wait_tmo);
if (ret == 0) {
lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_DISC,
- "6169 Unreg nvme wait failed %d\n",
- ret);
+ "6169 Unreg nvme wait timeout\n");
}
}
return;
input_err:
#endif
lpfc_printf_vlog(vport, KERN_ERR, LOG_NVME_DISC,
- "6168: State error: lport %p, rport%p FCID x%06x\n",
+ "6168 State error: lport %p, rport%p FCID x%06x\n",
vport->localport, ndlp->rport, ndlp->nlp_DID);
}
&phba->sli4_hba.lpfc_abts_nvme_buf_list,
list) {
if (lpfc_ncmd->cur_iocbq.sli4_xritag == xri) {
- list_del(&lpfc_ncmd->list);
+ list_del_init(&lpfc_ncmd->list);
lpfc_ncmd->flags &= ~LPFC_SBUF_XBUSY;
lpfc_ncmd->status = IOSTAT_SUCCESS;
spin_unlock(
rxid, 1);
lpfc_sli4_abts_err_handler(phba, ndlp, axri);
}
+
+ lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+ "6311 XRI Aborted xri x%x tag x%x "
+ "released\n",
+ xri, lpfc_ncmd->cur_iocbq.iotag);
+
lpfc_release_nvme_buf(phba, lpfc_ncmd);
if (rrq_empty)
lpfc_worker_wake_up(phba);
}
spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock);
spin_unlock_irqrestore(&phba->hbalock, iflag);
+
+ lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+ "6312 XRI Aborted xri x%x not found\n", xri);
+
}
* included with this package. *
********************************************************************/
-#define LPFC_NVME_MIN_SEGS 16
-#define LPFC_NVME_DEFAULT_SEGS 66 /* 256K IOs - 64 + 2 */
-#define LPFC_NVME_MAX_SEGS 510
-#define LPFC_NVMET_MIN_POSTBUF 16
-#define LPFC_NVMET_DEFAULT_POSTBUF 1024
-#define LPFC_NVMET_MAX_POSTBUF 4096
+#define LPFC_NVME_DEFAULT_SEGS (64 + 1) /* 256K IOs */
#define LPFC_NVME_WQSIZE 256
#define LPFC_NVME_ERSP_LEN 0x20
uint64_t ts_data_nvme;
#endif
};
+
+struct lpfc_nvme_fcpreq_priv {
+ struct lpfc_nvme_buf *nvme_buf;
+};
struct lpfc_nvmet_rcv_ctx *,
uint32_t, uint16_t);
+void
+lpfc_nvmet_defer_release(struct lpfc_hba *phba, struct lpfc_nvmet_rcv_ctx *ctxp)
+{
+ unsigned long iflag;
+
+ lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
+ "6313 NVMET Defer ctx release xri x%x flg x%x\n",
+ ctxp->oxid, ctxp->flag);
+
+ spin_lock_irqsave(&phba->sli4_hba.abts_nvme_buf_list_lock, iflag);
+ if (ctxp->flag & LPFC_NVMET_CTX_RLS) {
+ spin_unlock_irqrestore(&phba->sli4_hba.abts_nvme_buf_list_lock,
+ iflag);
+ return;
+ }
+ ctxp->flag |= LPFC_NVMET_CTX_RLS;
+ list_add_tail(&ctxp->list, &phba->sli4_hba.lpfc_abts_nvmet_ctx_list);
+ spin_unlock_irqrestore(&phba->sli4_hba.abts_nvme_buf_list_lock, iflag);
+}
+
/**
* lpfc_nvmet_xmt_ls_rsp_cmp - Completion handler for LS Response
* @phba: Pointer to HBA context object.
struct lpfc_dmabuf *mp)
{
if (ctxp) {
+ if (ctxp->flag)
+ lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+ "6314 rq_post ctx xri x%x flag x%x\n",
+ ctxp->oxid, ctxp->flag);
+
if (ctxp->txrdy) {
pci_pool_free(phba->txrdy_payload_pool, ctxp->txrdy,
ctxp->txrdy_phys);
#endif
ctxp = cmdwqe->context2;
+ ctxp->flag &= ~LPFC_NVMET_IO_INP;
+
rsp = &ctxp->ctx.fcp_req;
op = rsp->op;
- ctxp->flag &= ~LPFC_NVMET_IO_INP;
status = bf_get(lpfc_wcqe_c_status, wcqe);
result = wcqe->parameter;
- if (!phba->targetport)
- goto out;
+ if (phba->targetport)
+ tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
+ else
+ tgtp = NULL;
lpfc_nvmeio_data(phba, "NVMET FCP CMPL: xri x%x op x%x status x%x\n",
ctxp->oxid, op, status);
- tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
if (status) {
rsp->fcp_error = NVME_SC_DATA_XFER_ERROR;
rsp->transferred_length = 0;
- atomic_inc(&tgtp->xmt_fcp_rsp_error);
+ if (tgtp)
+ atomic_inc(&tgtp->xmt_fcp_rsp_error);
+
+ /* pick up SLI4 exhange busy condition */
+ if (bf_get(lpfc_wcqe_c_xb, wcqe)) {
+ ctxp->flag |= LPFC_NVMET_XBUSY;
+
+ lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+ "6315 IO Cmpl XBUSY: xri x%x: %x/%x\n",
+ ctxp->oxid, status, result);
+ } else {
+ ctxp->flag &= ~LPFC_NVMET_XBUSY;
+ }
+
} else {
rsp->fcp_error = NVME_SC_SUCCESS;
if (op == NVMET_FCOP_RSP)
rsp->transferred_length = rsp->rsplen;
else
rsp->transferred_length = rsp->transfer_length;
- atomic_inc(&tgtp->xmt_fcp_rsp_cmpl);
+ if (tgtp)
+ atomic_inc(&tgtp->xmt_fcp_rsp_cmpl);
}
-out:
if ((op == NVMET_FCOP_READDATA_RSP) ||
(op == NVMET_FCOP_RSP)) {
/* Sanity check */
ctxp->state = LPFC_NVMET_STE_DONE;
ctxp->entry_cnt++;
+
#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
if (phba->ktime_on) {
if (rsp->op == NVMET_FCOP_READDATA_RSP) {
if (phba->ktime_on)
lpfc_nvmet_ktime(phba, ctxp);
#endif
- /* Let Abort cmpl repost the context */
- if (!(ctxp->flag & LPFC_NVMET_ABORT_OP))
- lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
+ /* lpfc_nvmet_xmt_fcp_release() will recycle the context */
} else {
ctxp->entry_cnt++;
start_clean = offsetof(struct lpfc_iocbq, wqe);
container_of(rsp, struct lpfc_nvmet_rcv_ctx, ctx.fcp_req);
struct lpfc_hba *phba = ctxp->phba;
struct lpfc_iocbq *nvmewqeq;
- unsigned long iflags;
int rc;
#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
}
#endif
- if (rsp->op == NVMET_FCOP_ABORT) {
- lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
- "6103 Abort op: oxri x%x %d cnt %d\n",
- ctxp->oxid, ctxp->state, ctxp->entry_cnt);
-
- lpfc_nvmeio_data(phba, "NVMET FCP ABRT: "
- "xri x%x state x%x cnt x%x\n",
- ctxp->oxid, ctxp->state, ctxp->entry_cnt);
-
- atomic_inc(&lpfc_nvmep->xmt_fcp_abort);
- ctxp->entry_cnt++;
- ctxp->flag |= LPFC_NVMET_ABORT_OP;
- if (ctxp->flag & LPFC_NVMET_IO_INP)
- lpfc_nvmet_sol_fcp_issue_abort(phba, ctxp, ctxp->sid,
- ctxp->oxid);
- else
- lpfc_nvmet_unsol_fcp_issue_abort(phba, ctxp, ctxp->sid,
- ctxp->oxid);
- return 0;
- }
-
/* Sanity check */
- if (ctxp->state == LPFC_NVMET_STE_ABORT) {
+ if ((ctxp->flag & LPFC_NVMET_ABTS_RCV) ||
+ (ctxp->state == LPFC_NVMET_STE_ABORT)) {
atomic_inc(&lpfc_nvmep->xmt_fcp_drop);
lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
- "6102 Bad state IO x%x aborted\n",
+ "6102 IO xri x%x aborted\n",
ctxp->oxid);
rc = -ENXIO;
goto aerr;
lpfc_nvmeio_data(phba, "NVMET FCP CMND: xri x%x op x%x len x%x\n",
ctxp->oxid, rsp->op, rsp->rsplen);
- /* For now we take hbalock */
- spin_lock_irqsave(&phba->hbalock, iflags);
rc = lpfc_sli4_issue_wqe(phba, LPFC_FCP_RING, nvmewqeq);
- spin_unlock_irqrestore(&phba->hbalock, iflags);
if (rc == WQE_SUCCESS) {
ctxp->flag |= LPFC_NVMET_IO_INP;
#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
complete(&tport->tport_unreg_done);
}
+static void
+lpfc_nvmet_xmt_fcp_abort(struct nvmet_fc_target_port *tgtport,
+ struct nvmefc_tgt_fcp_req *req)
+{
+ struct lpfc_nvmet_tgtport *lpfc_nvmep = tgtport->private;
+ struct lpfc_nvmet_rcv_ctx *ctxp =
+ container_of(req, struct lpfc_nvmet_rcv_ctx, ctx.fcp_req);
+ struct lpfc_hba *phba = ctxp->phba;
+ unsigned long flags;
+
+ lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+ "6103 Abort op: oxri x%x flg x%x cnt %d\n",
+ ctxp->oxid, ctxp->flag, ctxp->entry_cnt);
+
+ lpfc_nvmeio_data(phba, "NVMET FCP ABRT: "
+ "xri x%x flg x%x cnt x%x\n",
+ ctxp->oxid, ctxp->flag, ctxp->entry_cnt);
+
+ atomic_inc(&lpfc_nvmep->xmt_fcp_abort);
+ ctxp->entry_cnt++;
+ spin_lock_irqsave(&ctxp->ctxlock, flags);
+
+ /* Since iaab/iaar are NOT set, we need to check
+ * if the firmware is in process of aborting IO
+ */
+ if (ctxp->flag & LPFC_NVMET_XBUSY) {
+ spin_unlock_irqrestore(&ctxp->ctxlock, flags);
+ return;
+ }
+ ctxp->flag |= LPFC_NVMET_ABORT_OP;
+ if (ctxp->flag & LPFC_NVMET_IO_INP)
+ lpfc_nvmet_sol_fcp_issue_abort(phba, ctxp, ctxp->sid,
+ ctxp->oxid);
+ else
+ lpfc_nvmet_unsol_fcp_issue_abort(phba, ctxp, ctxp->sid,
+ ctxp->oxid);
+ spin_unlock_irqrestore(&ctxp->ctxlock, flags);
+}
+
+static void
+lpfc_nvmet_xmt_fcp_release(struct nvmet_fc_target_port *tgtport,
+ struct nvmefc_tgt_fcp_req *rsp)
+{
+ struct lpfc_nvmet_rcv_ctx *ctxp =
+ container_of(rsp, struct lpfc_nvmet_rcv_ctx, ctx.fcp_req);
+ struct lpfc_hba *phba = ctxp->phba;
+ unsigned long flags;
+ bool aborting = false;
+
+ spin_lock_irqsave(&ctxp->ctxlock, flags);
+ if ((ctxp->flag & LPFC_NVMET_ABORT_OP) ||
+ (ctxp->flag & LPFC_NVMET_XBUSY)) {
+ aborting = true;
+ /* let the abort path do the real release */
+ lpfc_nvmet_defer_release(phba, ctxp);
+ }
+ spin_unlock_irqrestore(&ctxp->ctxlock, flags);
+
+ lpfc_nvmeio_data(phba, "NVMET FCP FREE: xri x%x ste %d\n", ctxp->oxid,
+ ctxp->state, 0);
+
+ if (aborting)
+ return;
+
+ lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
+}
+
static struct nvmet_fc_target_template lpfc_tgttemplate = {
.targetport_delete = lpfc_nvmet_targetport_delete,
.xmt_ls_rsp = lpfc_nvmet_xmt_ls_rsp,
.fcp_op = lpfc_nvmet_xmt_fcp_op,
+ .fcp_abort = lpfc_nvmet_xmt_fcp_abort,
+ .fcp_req_release = lpfc_nvmet_xmt_fcp_release,
.max_hw_queues = 1,
.max_sgl_segments = LPFC_NVMET_DEFAULT_SEGS,
pinfo.port_name = wwn_to_u64(vport->fc_portname.u.wwn);
pinfo.port_id = vport->fc_myDID;
+ /* Limit to LPFC_MAX_NVME_SEG_CNT.
+ * For now need + 1 to get around NVME transport logic.
+ */
+ if (phba->cfg_sg_seg_cnt > LPFC_MAX_NVME_SEG_CNT) {
+ lpfc_printf_log(phba, KERN_INFO, LOG_NVME | LOG_INIT,
+ "6400 Reducing sg segment cnt to %d\n",
+ LPFC_MAX_NVME_SEG_CNT);
+ phba->cfg_nvme_seg_cnt = LPFC_MAX_NVME_SEG_CNT;
+ } else {
+ phba->cfg_nvme_seg_cnt = phba->cfg_sg_seg_cnt;
+ }
+ lpfc_tgttemplate.max_sgl_segments = phba->cfg_nvme_seg_cnt + 1;
lpfc_tgttemplate.max_hw_queues = phba->cfg_nvme_io_channel;
- lpfc_tgttemplate.max_sgl_segments = phba->cfg_sg_seg_cnt;
lpfc_tgttemplate.target_features = NVMET_FCTGTFEAT_READDATA_RSP |
- NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED;
+ NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED |
+ NVMET_FCTGTFEAT_CMD_IN_ISR |
+ NVMET_FCTGTFEAT_OPDONE_IN_ISR;
#if (IS_ENABLED(CONFIG_NVME_TARGET_FC))
error = nvmet_fc_register_targetport(&pinfo, &lpfc_tgttemplate,
lpfc_sli4_nvmet_xri_aborted(struct lpfc_hba *phba,
struct sli4_wcqe_xri_aborted *axri)
{
- /* TODO: work in progress */
+ uint16_t xri = bf_get(lpfc_wcqe_xa_xri, axri);
+ uint16_t rxid = bf_get(lpfc_wcqe_xa_remote_xid, axri);
+ struct lpfc_nvmet_rcv_ctx *ctxp, *next_ctxp;
+ struct lpfc_nodelist *ndlp;
+ unsigned long iflag = 0;
+ int rrq_empty = 0;
+ bool released = false;
+
+ lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+ "6317 XB aborted xri x%x rxid x%x\n", xri, rxid);
+
+ if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME))
+ return;
+ spin_lock_irqsave(&phba->hbalock, iflag);
+ spin_lock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+ list_for_each_entry_safe(ctxp, next_ctxp,
+ &phba->sli4_hba.lpfc_abts_nvmet_ctx_list,
+ list) {
+ if (ctxp->rqb_buffer->sglq->sli4_xritag != xri)
+ continue;
+
+ /* Check if we already received a free context call
+ * and we have completed processing an abort situation.
+ */
+ if (ctxp->flag & LPFC_NVMET_CTX_RLS &&
+ !(ctxp->flag & LPFC_NVMET_ABORT_OP)) {
+ list_del(&ctxp->list);
+ released = true;
+ }
+ ctxp->flag &= ~LPFC_NVMET_XBUSY;
+ spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+
+ rrq_empty = list_empty(&phba->active_rrq_list);
+ spin_unlock_irqrestore(&phba->hbalock, iflag);
+ ndlp = lpfc_findnode_did(phba->pport, ctxp->sid);
+ if (ndlp && NLP_CHK_NODE_ACT(ndlp) &&
+ (ndlp->nlp_state == NLP_STE_UNMAPPED_NODE ||
+ ndlp->nlp_state == NLP_STE_MAPPED_NODE)) {
+ lpfc_set_rrq_active(phba, ndlp,
+ ctxp->rqb_buffer->sglq->sli4_lxritag,
+ rxid, 1);
+ lpfc_sli4_abts_err_handler(phba, ndlp, axri);
+ }
+
+ lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+ "6318 XB aborted %x flg x%x (%x)\n",
+ ctxp->oxid, ctxp->flag, released);
+ if (released)
+ lpfc_nvmet_rq_post(phba, ctxp,
+ &ctxp->rqb_buffer->hbuf);
+ if (rrq_empty)
+ lpfc_worker_wake_up(phba);
+ return;
+ }
+ spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+ spin_unlock_irqrestore(&phba->hbalock, iflag);
+}
+
+int
+lpfc_nvmet_rcv_unsol_abort(struct lpfc_vport *vport,
+ struct fc_frame_header *fc_hdr)
+
+{
+#if (IS_ENABLED(CONFIG_NVME_TARGET_FC))
+ struct lpfc_hba *phba = vport->phba;
+ struct lpfc_nvmet_rcv_ctx *ctxp, *next_ctxp;
+ struct nvmefc_tgt_fcp_req *rsp;
+ uint16_t xri;
+ unsigned long iflag = 0;
+
+ xri = be16_to_cpu(fc_hdr->fh_ox_id);
+
+ spin_lock_irqsave(&phba->hbalock, iflag);
+ spin_lock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+ list_for_each_entry_safe(ctxp, next_ctxp,
+ &phba->sli4_hba.lpfc_abts_nvmet_ctx_list,
+ list) {
+ if (ctxp->rqb_buffer->sglq->sli4_xritag != xri)
+ continue;
+
+ spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+ spin_unlock_irqrestore(&phba->hbalock, iflag);
+
+ spin_lock_irqsave(&ctxp->ctxlock, iflag);
+ ctxp->flag |= LPFC_NVMET_ABTS_RCV;
+ spin_unlock_irqrestore(&ctxp->ctxlock, iflag);
+
+ lpfc_nvmeio_data(phba,
+ "NVMET ABTS RCV: xri x%x CPU %02x rjt %d\n",
+ xri, smp_processor_id(), 0);
+
+ lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+ "6319 NVMET Rcv ABTS:acc xri x%x\n", xri);
+
+ rsp = &ctxp->ctx.fcp_req;
+ nvmet_fc_rcv_fcp_abort(phba->targetport, rsp);
+
+ /* Respond with BA_ACC accordingly */
+ lpfc_sli4_seq_abort_rsp(vport, fc_hdr, 1);
+ return 0;
+ }
+ spin_unlock(&phba->sli4_hba.abts_nvme_buf_list_lock);
+ spin_unlock_irqrestore(&phba->hbalock, iflag);
+
+ lpfc_nvmeio_data(phba, "NVMET ABTS RCV: xri x%x CPU %02x rjt %d\n",
+ xri, smp_processor_id(), 1);
+
+ lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+ "6320 NVMET Rcv ABTS:rjt xri x%x\n", xri);
+
+ /* Respond with BA_RJT accordingly */
+ lpfc_sli4_seq_abort_rsp(vport, fc_hdr, 0);
+#endif
+ return 0;
}
void
ctxp->rqb_buffer = nvmebuf;
ctxp->entry_cnt = 1;
ctxp->flag = 0;
+ spin_lock_init(&ctxp->ctxlock);
#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
if (phba->ktime_on) {
}
#endif
- lpfc_nvmeio_data(phba, "NVMET FCP RCV: xri x%x sz %d from %06x\n",
- oxid, size, sid);
+ lpfc_nvmeio_data(phba, "NVMET FCP RCV: xri x%x sz %d CPU %02x\n",
+ oxid, size, smp_processor_id());
atomic_inc(&tgtp->rcv_fcp_cmd_in);
/*
return NULL;
}
- if (rsp->sg_cnt > phba->cfg_sg_seg_cnt) {
+ if (rsp->sg_cnt > phba->cfg_nvme_seg_cnt) {
lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
"6109 lpfc_nvmet_prep_fcp_wqe: seg cnt err: "
- "NPORT x%x oxid:x%x\n",
- ctxp->sid, ctxp->oxid);
+ "NPORT x%x oxid:x%x cnt %d\n",
+ ctxp->sid, ctxp->oxid, phba->cfg_nvme_seg_cnt);
return NULL;
}
struct lpfc_nvmet_rcv_ctx *ctxp;
struct lpfc_nvmet_tgtport *tgtp;
uint32_t status, result;
+ unsigned long flags;
+ bool released = false;
ctxp = cmdwqe->context2;
status = bf_get(lpfc_wcqe_c_status, wcqe);
tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
atomic_inc(&tgtp->xmt_abort_cmpl);
+ ctxp->state = LPFC_NVMET_STE_DONE;
+
+ /* Check if we already received a free context call
+ * and we have completed processing an abort situation.
+ */
+ spin_lock_irqsave(&ctxp->ctxlock, flags);
+ if ((ctxp->flag & LPFC_NVMET_CTX_RLS) &&
+ !(ctxp->flag & LPFC_NVMET_XBUSY)) {
+ list_del(&ctxp->list);
+ released = true;
+ }
+ ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
+ spin_unlock_irqrestore(&ctxp->ctxlock, flags);
+
lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
- "6165 Abort cmpl: xri x%x WCQE: %08x %08x %08x %08x\n",
- ctxp->oxid, wcqe->word0, wcqe->total_data_placed,
+ "6165 ABORT cmpl: xri x%x flg x%x (%d) "
+ "WCQE: %08x %08x %08x %08x\n",
+ ctxp->oxid, ctxp->flag, released,
+ wcqe->word0, wcqe->total_data_placed,
result, wcqe->word3);
- ctxp->state = LPFC_NVMET_STE_DONE;
- lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
+ /*
+ * if transport has released ctx, then can reuse it. Otherwise,
+ * will be recycled by transport release call.
+ */
+ if (released)
+ lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
cmdwqe->context2 = NULL;
cmdwqe->context3 = NULL;
lpfc_sli_release_iocbq(phba, cmdwqe);
+
+ /* Since iaab/iaar are NOT set, there is no work left.
+ * For LPFC_NVMET_XBUSY, lpfc_sli4_nvmet_xri_aborted
+ * should have been called already.
+ */
}
/**
- * lpfc_nvmet_xmt_fcp_abort_cmp - Completion handler for ABTS
+ * lpfc_nvmet_unsol_fcp_abort_cmp - Completion handler for ABTS
* @phba: Pointer to HBA context object.
* @cmdwqe: Pointer to driver command WQE object.
* @wcqe: Pointer to driver response CQE object.
* The function frees memory resources used for the NVME commands.
**/
static void
-lpfc_nvmet_xmt_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
- struct lpfc_wcqe_complete *wcqe)
+lpfc_nvmet_unsol_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
+ struct lpfc_wcqe_complete *wcqe)
{
struct lpfc_nvmet_rcv_ctx *ctxp;
struct lpfc_nvmet_tgtport *tgtp;
+ unsigned long flags;
uint32_t status, result;
+ bool released = false;
ctxp = cmdwqe->context2;
status = bf_get(lpfc_wcqe_c_status, wcqe);
tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
atomic_inc(&tgtp->xmt_abort_cmpl);
+ if (!ctxp) {
+ /* if context is clear, related io alrady complete */
+ lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+ "6070 ABTS cmpl: WCQE: %08x %08x %08x %08x\n",
+ wcqe->word0, wcqe->total_data_placed,
+ result, wcqe->word3);
+ return;
+ }
+
+ /* Sanity check */
+ if (ctxp->state != LPFC_NVMET_STE_ABORT) {
+ lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
+ "6112 ABTS Wrong state:%d oxid x%x\n",
+ ctxp->state, ctxp->oxid);
+ }
+
+ /* Check if we already received a free context call
+ * and we have completed processing an abort situation.
+ */
+ ctxp->state = LPFC_NVMET_STE_DONE;
+ spin_lock_irqsave(&ctxp->ctxlock, flags);
+ if ((ctxp->flag & LPFC_NVMET_CTX_RLS) &&
+ !(ctxp->flag & LPFC_NVMET_XBUSY)) {
+ list_del(&ctxp->list);
+ released = true;
+ }
+ ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
+ spin_unlock_irqrestore(&ctxp->ctxlock, flags);
+
lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
- "6070 Abort cmpl: ctx %p WCQE: %08x %08x %08x %08x\n",
- ctxp, wcqe->word0, wcqe->total_data_placed,
+ "6316 ABTS cmpl xri x%x flg x%x (%x) "
+ "WCQE: %08x %08x %08x %08x\n",
+ ctxp->oxid, ctxp->flag, released,
+ wcqe->word0, wcqe->total_data_placed,
result, wcqe->word3);
-
- if (ctxp) {
- /* Sanity check */
- if (ctxp->state != LPFC_NVMET_STE_ABORT) {
- lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
- "6112 ABORT Wrong state:%d oxid x%x\n",
- ctxp->state, ctxp->oxid);
- }
- ctxp->state = LPFC_NVMET_STE_DONE;
+ /*
+ * if transport has released ctx, then can reuse it. Otherwise,
+ * will be recycled by transport release call.
+ */
+ if (released)
lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
- cmdwqe->context2 = NULL;
- cmdwqe->context3 = NULL;
- }
+
+ cmdwqe->context2 = NULL;
+ cmdwqe->context3 = NULL;
+
+ /* Since iaab/iaar are NOT set, there is no work left.
+ * For LPFC_NVMET_XBUSY, lpfc_sli4_nvmet_xri_aborted
+ * should have been called already.
+ */
}
/**
struct lpfc_nodelist *ndlp;
lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
- "6067 Abort: sid %x xri x%x/x%x\n",
+ "6067 ABTS: sid %x xri x%x/x%x\n",
sid, xri, ctxp->wqeq->sli4_xritag);
tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
+ if (!ctxp->wqeq) {
+ ctxp->wqeq = ctxp->rqb_buffer->iocbq;
+ ctxp->wqeq->hba_wqidx = 0;
+ }
ndlp = lpfc_findnode_did(phba->pport, sid);
if (!ndlp || !NLP_CHK_NODE_ACT(ndlp) ||
(ndlp->nlp_state != NLP_STE_MAPPED_NODE))) {
atomic_inc(&tgtp->xmt_abort_rsp_error);
lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS,
- "6160 Drop ABTS - wrong NDLP state x%x.\n",
+ "6160 Drop ABORT - wrong NDLP state x%x.\n",
(ndlp) ? ndlp->nlp_state : NLP_STE_MAX_STATE);
/* No failure to an ABTS request. */
+ ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
return 0;
}
ctxp->abort_wqeq = lpfc_sli_get_iocbq(phba);
if (!ctxp->abort_wqeq) {
lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS,
- "6161 Abort failed: No wqeqs: "
+ "6161 ABORT failed: No wqeqs: "
"xri: x%x\n", ctxp->oxid);
/* No failure to an ABTS request. */
+ ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
return 0;
}
abts_wqeq = ctxp->abort_wqeq;
ctxp->state = LPFC_NVMET_STE_ABORT;
/* Announce entry to new IO submit field. */
- lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
- "6162 Abort Request to rport DID x%06x "
+ lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+ "6162 ABORT Request to rport DID x%06x "
"for xri x%x x%x\n",
ctxp->sid, ctxp->oxid, ctxp->wqeq->sli4_xritag);
"NVME Req now. hba_flag x%x oxid x%x\n",
phba->hba_flag, ctxp->oxid);
lpfc_sli_release_iocbq(phba, abts_wqeq);
+ ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
return 0;
}
"still pending on oxid x%x\n",
ctxp->oxid);
lpfc_sli_release_iocbq(phba, abts_wqeq);
+ ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
return 0;
}
if (rc == WQE_SUCCESS)
return 0;
+ ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
lpfc_sli_release_iocbq(phba, abts_wqeq);
- lpfc_printf_log(phba, KERN_ERR, LOG_NVME,
- "6166 Failed abts issue_wqe with status x%x "
+ lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
+ "6166 Failed ABORT issue_wqe with status x%x "
"for oxid x%x.\n",
rc, ctxp->oxid);
return 1;
spin_lock_irqsave(&phba->hbalock, flags);
abts_wqeq = ctxp->wqeq;
- abts_wqeq->wqe_cmpl = lpfc_nvmet_xmt_fcp_abort_cmp;
- abts_wqeq->iocb_cmpl = 0;
+ abts_wqeq->wqe_cmpl = lpfc_nvmet_unsol_fcp_abort_cmp;
+ abts_wqeq->iocb_cmpl = NULL;
abts_wqeq->iocb_flag |= LPFC_IO_NVMET;
rc = lpfc_sli4_issue_wqe(phba, LPFC_FCP_RING, abts_wqeq);
spin_unlock_irqrestore(&phba->hbalock, flags);
}
aerr:
- lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
+ ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
atomic_inc(&tgtp->xmt_abort_rsp_error);
lpfc_printf_log(phba, KERN_WARNING, LOG_NVME_ABTS,
"6135 Failed to Issue ABTS for oxid x%x. Status x%x\n",
* included with this package. *
********************************************************************/
-#define LPFC_NVMET_MIN_SEGS 16
-#define LPFC_NVMET_DEFAULT_SEGS 64 /* 256K IOs */
-#define LPFC_NVMET_MAX_SEGS 510
+#define LPFC_NVMET_DEFAULT_SEGS (64 + 1) /* 256K IOs */
#define LPFC_NVMET_SUCCESS_LEN 12
/* Used for NVME Target */
struct nvmefc_tgt_ls_req ls_req;
struct nvmefc_tgt_fcp_req fcp_req;
} ctx;
+ struct list_head list;
struct lpfc_hba *phba;
struct lpfc_iocbq *wqeq;
struct lpfc_iocbq *abort_wqeq;
dma_addr_t txrdy_phys;
+ spinlock_t ctxlock; /* protect flag access */
uint32_t *txrdy;
uint32_t sid;
uint32_t offset;
#define LPFC_NVMET_STE_RSP 4
#define LPFC_NVMET_STE_DONE 5
uint16_t flag;
-#define LPFC_NVMET_IO_INP 1
-#define LPFC_NVMET_ABORT_OP 2
+#define LPFC_NVMET_IO_INP 0x1 /* IO is in progress on exchange */
+#define LPFC_NVMET_ABORT_OP 0x2 /* Abort WQE issued on exchange */
+#define LPFC_NVMET_XBUSY 0x4 /* XB bit set on IO cmpl */
+#define LPFC_NVMET_CTX_RLS 0x8 /* ctx free requested */
+#define LPFC_NVMET_ABTS_RCV 0x10 /* ABTS received on exchange */
struct rqb_dmabuf *rqb_buffer;
#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
}
/**
- * lpfc_sli4_repost_sgl_list - Repsot the buffers sgl pages as block
+ * lpfc_sli4_repost_sgl_list - Repost the buffers sgl pages as block
* @phba: pointer to lpfc hba data structure.
* @pring: Pointer to driver SLI ring object.
* @sgl_list: linked link of sgl buffers to post
lpfc_free_rq_buffer(queue->phba, queue);
kfree(queue->rqbp);
}
- kfree(queue->pring);
+
+ if (!list_empty(&queue->wq_list))
+ list_del(&queue->wq_list);
+
kfree(queue);
return;
}
case LPFC_Q_CREATE_VERSION_1:
bf_set(lpfc_mbx_wq_create_wqe_count, &wq_create->u.request_1,
wq->entry_count);
+ bf_set(lpfc_mbox_hdr_version, &shdr->request,
+ LPFC_Q_CREATE_VERSION_1);
+
switch (wq->entry_size) {
default:
case 64:
}
/* Remove wq from any list */
list_del_init(&wq->list);
+ kfree(wq->pring);
+ wq->pring = NULL;
mempool_free(mbox, wq->phba->mbox_mem_pool);
return status;
}
* This function sends a basic response to a previous unsol sequence abort
* event after aborting the sequence handling.
**/
-static void
+void
lpfc_sli4_seq_abort_rsp(struct lpfc_vport *vport,
struct fc_frame_header *fc_hdr, bool aborted)
{
ndlp = lpfc_findnode_did(vport, sid);
if (!ndlp) {
- ndlp = mempool_alloc(phba->nlp_mem_pool, GFP_KERNEL);
+ ndlp = lpfc_nlp_init(vport, sid);
if (!ndlp) {
lpfc_printf_vlog(vport, KERN_WARNING, LOG_ELS,
"1268 Failed to allocate ndlp for "
"oxid:x%x SID:x%x\n", oxid, sid);
return;
}
- lpfc_nlp_init(vport, ndlp, sid);
/* Put ndlp onto pport node list */
lpfc_enqueue_node(vport, ndlp);
} else if (!NLP_CHK_NODE_ACT(ndlp)) {
}
lpfc_in_buf_free(phba, &dmabuf->dbuf);
+ if (phba->nvmet_support) {
+ lpfc_nvmet_rcv_unsol_abort(vport, &fc_hdr);
+ return;
+ }
+
/* Respond with BA_ACC or BA_RJT accordingly */
lpfc_sli4_seq_abort_rsp(vport, &fc_hdr, aborted);
}
struct list_head lpfc_els_sgl_list;
struct list_head lpfc_abts_els_sgl_list;
struct list_head lpfc_nvmet_sgl_list;
- struct list_head lpfc_abts_nvmet_sgl_list;
+ struct list_head lpfc_abts_nvmet_ctx_list;
struct list_head lpfc_abts_scsi_buf_list;
struct list_head lpfc_abts_nvme_buf_list;
struct lpfc_sglq **lpfc_sglq_active_list;
* included with this package. *
*******************************************************************/
-#define LPFC_DRIVER_VERSION "11.2.0.10"
+#define LPFC_DRIVER_VERSION "11.2.0.12"
#define LPFC_DRIVER_NAME "lpfc"
/* Used for SLI 2/3 */
ndlp = lpfc_findnode_did(vport, Fabric_DID);
if (!ndlp) {
/* Cannot find existing Fabric ndlp, allocate one */
- ndlp = mempool_alloc(phba->nlp_mem_pool, GFP_KERNEL);
+ ndlp = lpfc_nlp_init(vport, Fabric_DID);
if (!ndlp)
goto skip_logo;
- lpfc_nlp_init(vport, ndlp, Fabric_DID);
/* Indicate free memory when release */
NLP_SET_FREE_REQ(ndlp);
} else {
int error)
{
or->async_error = error;
- or->req_errors = req->errors ? : error;
+ or->req_errors = scsi_req(req)->result ? : error;
or->sense_len = scsi_req(req)->sense_len;
if (or->sense_len)
memcpy(or->sense, scsi_req(req)->sense, or->sense_len);
int osd_execute_request(struct osd_request *or)
{
- int error = blk_execute_rq(or->request->q, NULL, or->request, 0);
+ int error;
+
+ blk_execute_rq(or->request->q, NULL, or->request, 0);
+ error = scsi_req(or->request)->result ? -EIO : 0;
_set_error_resid(or, or->request, error);
return error;
req->rq_flags |= RQF_QUIET;
req->timeout = or->timeout;
- req->retries = or->retries;
+ scsi_req(req)->retries = or->retries;
if (has_out) {
or->out.req = req;
struct osst_tape *STp = SRpnt->stp;
struct rq_map_data *mdata = &SRpnt->stp->buffer->map_data;
- STp->buffer->cmdstat.midlevel_result = SRpnt->result = req->errors;
+ STp->buffer->cmdstat.midlevel_result = SRpnt->result = rq->result;
#if DEBUG
STp->write_pending = 0;
#endif
memset(rq->cmd, 0, BLK_MAX_CDB); /* ATAPI hates garbage after CDB */
memcpy(rq->cmd, cmd, rq->cmd_len);
req->timeout = timeout;
- req->retries = retries;
+ rq->retries = retries;
req->end_io_data = SRpnt;
blk_execute_rq_nowait(req->q, NULL, req, 1, osst_end_async);
qedf_set_vlan_id(qedf, vid);
/* Inform waiter that it's ok to call fcoe_ctlr_link up() */
- complete(&qedf->fipvlan_compl);
+ if (!completion_done(&qedf->fipvlan_compl))
+ complete(&qedf->fipvlan_compl);
}
}
atomic_set(&qedf->num_offloads, 0);
qedf->stop_io_on_error = false;
pci_set_drvdata(pdev, qedf);
+ init_completion(&qedf->fipvlan_compl);
QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_INFO,
"QLogic FastLinQ FCoE Module qedf %s, "
ql_log(ql_log_warn, vha, 0x7089,
"mbx abort_command "
"failed.\n");
- bsg_job->req->errors =
+ scsi_req(bsg_job->req)->result =
bsg_reply->result = -EIO;
} else {
ql_dbg(ql_dbg_user, vha, 0x708a,
"mbx abort_command "
"success.\n");
- bsg_job->req->errors =
+ scsi_req(bsg_job->req)->result =
bsg_reply->result = 0;
}
spin_lock_irqsave(&ha->hardware_lock, flags);
}
spin_unlock_irqrestore(&ha->hardware_lock, flags);
ql_log(ql_log_info, vha, 0x708b, "SRB not found to abort.\n");
- bsg_job->req->errors = bsg_reply->result = -ENXIO;
+ scsi_req(bsg_job->req)->result = bsg_reply->result = -ENXIO;
return 0;
done:
uint32_t qla2x00_isp_reg_stat(struct qla_hw_data *ha)
{
struct device_reg_24xx __iomem *reg = &ha->iobase->isp24;
+ struct device_reg_82xx __iomem *reg82 = &ha->iobase->isp82;
- return ((RD_REG_DWORD(®->host_status)) == ISP_REG_DISCONNECT);
+ if (IS_P3P_TYPE(ha))
+ return ((RD_REG_DWORD(®82->host_int)) == ISP_REG_DISCONNECT);
+ else
+ return ((RD_REG_DWORD(®->host_status)) ==
+ ISP_REG_DISCONNECT);
}
/**************************************************************************
--- /dev/null
+#include <linux/seq_file.h>
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_dbg.h>
+#include "scsi_debugfs.h"
+
+void scsi_show_rq(struct seq_file *m, struct request *rq)
+{
+ struct scsi_cmnd *cmd = container_of(scsi_req(rq), typeof(*cmd), req);
+ char buf[80];
+
+ __scsi_format_command(buf, sizeof(buf), cmd->cmnd, cmd->cmd_len);
+ seq_printf(m, ", .cmd=%s", buf);
+}
--- /dev/null
+struct request;
+struct seq_file;
+
+void scsi_show_rq(struct seq_file *m, struct request *rq);
req->rq_flags |= RQF_QUIET;
req->timeout = 10 * HZ;
- req->retries = 5;
+ rq->retries = 5;
blk_execute_rq_nowait(req->q, NULL, req, 1, eh_lock_door_done);
}
#include <trace/events/scsi.h>
+#include "scsi_debugfs.h"
#include "scsi_priv.h"
#include "scsi_logging.h"
* @rq_flags: flags for ->rq_flags
* @resid: optional residual length
*
- * returns the req->errors value which is the scsi_cmnd result
- * field.
+ * Returns the scsi_cmnd result field if a command was executed, or a negative
+ * Linux error code if we didn't get that far.
*/
int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
int data_direction, void *buffer, unsigned bufflen,
rq->cmd_len = COMMAND_SIZE(cmd[0]);
memcpy(rq->cmd, cmd, rq->cmd_len);
- req->retries = retries;
+ rq->retries = retries;
req->timeout = timeout;
req->cmd_flags |= flags;
req->rq_flags |= rq_flags | RQF_QUIET | RQF_PREEMPT;
memcpy(sense, rq->sense, SCSI_SENSE_BUFFERSIZE);
if (sshdr)
scsi_normalize_sense(rq->sense, rq->sense_len, sshdr);
- ret = req->errors;
+ ret = rq->result;
out:
blk_put_request(req);
scsi_starved_list_run(sdev->host);
if (q->mq_ops)
- blk_mq_start_stopped_hw_queues(q, false);
+ blk_mq_run_hw_queues(q, false);
else
blk_run_queue(q);
}
!list_empty(&sdev->host->starved_list))
kblockd_schedule_work(&sdev->requeue_work);
else
- blk_mq_start_stopped_hw_queues(q, true);
+ blk_mq_run_hw_queues(q, true);
} else {
unsigned long flags;
/*
* __scsi_error_from_host_byte may have reset the host_byte
*/
- req->errors = cmd->result;
-
+ scsi_req(req)->result = cmd->result;
scsi_req(req)->resid_len = scsi_get_resid(cmd);
if (scsi_bidi_cmnd(cmd)) {
/*
* Recovered errors need reporting, but they're always treated as
* success, so fiddle the result code here. For passthrough requests
- * we already took a copy of the original into rq->errors which
+ * we already took a copy of the original into sreq->result which
* is what gets returned to the user
*/
if (sense_valid && (sshdr.sense_key == RECOVERED_ERROR)) {
struct scsi_device *sdev = cmd->device;
struct request *rq = cmd->request;
bool is_mq = (rq->mq_ctx != NULL);
- int error;
+ int error = BLKPREP_KILL;
if (WARN_ON_ONCE(!blk_rq_nr_phys_segments(rq)))
- return -EINVAL;
+ goto err_exit;
error = scsi_init_sgtable(rq, &cmd->sdb);
if (error)
cmd->cmd_len = scsi_req(req)->cmd_len;
cmd->cmnd = scsi_req(req)->cmd;
cmd->transfersize = blk_rq_bytes(req);
- cmd->allowed = req->retries;
+ cmd->allowed = scsi_req(req)->retries;
return BLKPREP_OK;
}
switch (ret) {
case BLKPREP_KILL:
case BLKPREP_INVALID:
- req->errors = DID_NO_CONNECT << 16;
+ scsi_req(req)->result = DID_NO_CONNECT << 16;
/* release the command and kill it */
if (req->special) {
struct scsi_cmnd *cmd = req->special;
static void scsi_mq_done(struct scsi_cmnd *cmd)
{
trace_scsi_dispatch_cmd_done(cmd);
- blk_mq_complete_request(cmd->request, cmd->request->errors);
+ blk_mq_complete_request(cmd->request);
}
static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
case BLK_MQ_RQ_QUEUE_BUSY:
if (atomic_read(&sdev->device_busy) == 0 &&
!scsi_device_blocked(sdev))
- blk_mq_delay_queue(hctx, SCSI_QUEUE_DELAY);
+ blk_mq_delay_run_hw_queue(hctx, SCSI_QUEUE_DELAY);
break;
case BLK_MQ_RQ_QUEUE_ERROR:
/*
return q;
}
-static struct blk_mq_ops scsi_mq_ops = {
+static const struct blk_mq_ops scsi_mq_ops = {
.queue_rq = scsi_queue_rq,
.complete = scsi_softirq_done,
.timeout = scsi_timeout,
+#ifdef CONFIG_BLK_DEBUG_FS
+ .show_rq = scsi_show_rq,
+#endif
.init_request = scsi_init_request,
.exit_request = scsi_exit_request,
.map_queues = scsi_map_queues,
blk_rq_bytes(req->next_rq);
handler = to_sas_internal(shost->transportt)->f->smp_handler;
ret = handler(shost, rphy, req);
- req->errors = ret;
+ scsi_req(req)->result = ret;
- blk_end_request_all(req, ret);
+ blk_end_request_all(req, 0);
spin_lock_irq(q->queue_lock);
}
}
static DEVICE_ATTR_RW(provisioning_mode);
+static const char *zeroing_mode[] = {
+ [SD_ZERO_WRITE] = "write",
+ [SD_ZERO_WS] = "writesame",
+ [SD_ZERO_WS16_UNMAP] = "writesame_16_unmap",
+ [SD_ZERO_WS10_UNMAP] = "writesame_10_unmap",
+};
+
+static ssize_t
+zeroing_mode_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct scsi_disk *sdkp = to_scsi_disk(dev);
+
+ return snprintf(buf, 20, "%s\n", zeroing_mode[sdkp->zeroing_mode]);
+}
+
+static ssize_t
+zeroing_mode_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct scsi_disk *sdkp = to_scsi_disk(dev);
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
+
+ if (!strncmp(buf, zeroing_mode[SD_ZERO_WRITE], 20))
+ sdkp->zeroing_mode = SD_ZERO_WRITE;
+ else if (!strncmp(buf, zeroing_mode[SD_ZERO_WS], 20))
+ sdkp->zeroing_mode = SD_ZERO_WS;
+ else if (!strncmp(buf, zeroing_mode[SD_ZERO_WS16_UNMAP], 20))
+ sdkp->zeroing_mode = SD_ZERO_WS16_UNMAP;
+ else if (!strncmp(buf, zeroing_mode[SD_ZERO_WS10_UNMAP], 20))
+ sdkp->zeroing_mode = SD_ZERO_WS10_UNMAP;
+ else
+ return -EINVAL;
+
+ return count;
+}
+static DEVICE_ATTR_RW(zeroing_mode);
+
static ssize_t
max_medium_access_timeouts_show(struct device *dev,
struct device_attribute *attr, char *buf)
&dev_attr_app_tag_own.attr,
&dev_attr_thin_provisioning.attr,
&dev_attr_provisioning_mode.attr,
+ &dev_attr_zeroing_mode.attr,
&dev_attr_max_write_same_blocks.attr,
&dev_attr_max_medium_access_timeouts.attr,
NULL,
unsigned int logical_block_size = sdkp->device->sector_size;
unsigned int max_blocks = 0;
- q->limits.discard_zeroes_data = 0;
-
- /*
- * When LBPRZ is reported, discard alignment and granularity
- * must be fixed to the logical block size. Otherwise the block
- * layer will drop misaligned portions of the request which can
- * lead to data corruption. If LBPRZ is not set, we honor the
- * device preference.
- */
- if (sdkp->lbprz) {
- q->limits.discard_alignment = 0;
- q->limits.discard_granularity = logical_block_size;
- } else {
- q->limits.discard_alignment = sdkp->unmap_alignment *
- logical_block_size;
- q->limits.discard_granularity =
- max(sdkp->physical_block_size,
- sdkp->unmap_granularity * logical_block_size);
- }
-
+ q->limits.discard_alignment =
+ sdkp->unmap_alignment * logical_block_size;
+ q->limits.discard_granularity =
+ max(sdkp->physical_block_size,
+ sdkp->unmap_granularity * logical_block_size);
sdkp->provisioning_mode = mode;
switch (mode) {
case SD_LBP_WS16:
max_blocks = min_not_zero(sdkp->max_ws_blocks,
(u32)SD_MAX_WS16_BLOCKS);
- q->limits.discard_zeroes_data = sdkp->lbprz;
break;
case SD_LBP_WS10:
max_blocks = min_not_zero(sdkp->max_ws_blocks,
(u32)SD_MAX_WS10_BLOCKS);
- q->limits.discard_zeroes_data = sdkp->lbprz;
break;
case SD_LBP_ZERO:
max_blocks = min_not_zero(sdkp->max_ws_blocks,
(u32)SD_MAX_WS10_BLOCKS);
- q->limits.discard_zeroes_data = 1;
break;
}
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
}
-/**
- * sd_setup_discard_cmnd - unmap blocks on thinly provisioned device
- * @sdp: scsi device to operate on
- * @rq: Request to prepare
- *
- * Will issue either UNMAP or WRITE SAME(16) depending on preference
- * indicated by target device.
- **/
-static int sd_setup_discard_cmnd(struct scsi_cmnd *cmd)
+static int sd_setup_unmap_cmnd(struct scsi_cmnd *cmd)
{
- struct request *rq = cmd->request;
struct scsi_device *sdp = cmd->device;
- struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
- sector_t sector = blk_rq_pos(rq);
- unsigned int nr_sectors = blk_rq_sectors(rq);
- unsigned int len;
- int ret;
+ struct request *rq = cmd->request;
+ u64 sector = blk_rq_pos(rq) >> (ilog2(sdp->sector_size) - 9);
+ u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9);
+ unsigned int data_len = 24;
char *buf;
- struct page *page;
-
- sector >>= ilog2(sdp->sector_size) - 9;
- nr_sectors >>= ilog2(sdp->sector_size) - 9;
- page = alloc_page(GFP_ATOMIC | __GFP_ZERO);
- if (!page)
+ rq->special_vec.bv_page = alloc_page(GFP_ATOMIC | __GFP_ZERO);
+ if (!rq->special_vec.bv_page)
return BLKPREP_DEFER;
+ rq->special_vec.bv_offset = 0;
+ rq->special_vec.bv_len = data_len;
+ rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
- switch (sdkp->provisioning_mode) {
- case SD_LBP_UNMAP:
- buf = page_address(page);
+ cmd->cmd_len = 10;
+ cmd->cmnd[0] = UNMAP;
+ cmd->cmnd[8] = 24;
- cmd->cmd_len = 10;
- cmd->cmnd[0] = UNMAP;
- cmd->cmnd[8] = 24;
+ buf = page_address(rq->special_vec.bv_page);
+ put_unaligned_be16(6 + 16, &buf[0]);
+ put_unaligned_be16(16, &buf[2]);
+ put_unaligned_be64(sector, &buf[8]);
+ put_unaligned_be32(nr_sectors, &buf[16]);
- put_unaligned_be16(6 + 16, &buf[0]);
- put_unaligned_be16(16, &buf[2]);
- put_unaligned_be64(sector, &buf[8]);
- put_unaligned_be32(nr_sectors, &buf[16]);
+ cmd->allowed = SD_MAX_RETRIES;
+ cmd->transfersize = data_len;
+ rq->timeout = SD_TIMEOUT;
+ scsi_req(rq)->resid_len = data_len;
- len = 24;
- break;
+ return scsi_init_io(cmd);
+}
- case SD_LBP_WS16:
- cmd->cmd_len = 16;
- cmd->cmnd[0] = WRITE_SAME_16;
+static int sd_setup_write_same16_cmnd(struct scsi_cmnd *cmd, bool unmap)
+{
+ struct scsi_device *sdp = cmd->device;
+ struct request *rq = cmd->request;
+ u64 sector = blk_rq_pos(rq) >> (ilog2(sdp->sector_size) - 9);
+ u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9);
+ u32 data_len = sdp->sector_size;
+
+ rq->special_vec.bv_page = alloc_page(GFP_ATOMIC | __GFP_ZERO);
+ if (!rq->special_vec.bv_page)
+ return BLKPREP_DEFER;
+ rq->special_vec.bv_offset = 0;
+ rq->special_vec.bv_len = data_len;
+ rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
+
+ cmd->cmd_len = 16;
+ cmd->cmnd[0] = WRITE_SAME_16;
+ if (unmap)
cmd->cmnd[1] = 0x8; /* UNMAP */
- put_unaligned_be64(sector, &cmd->cmnd[2]);
- put_unaligned_be32(nr_sectors, &cmd->cmnd[10]);
+ put_unaligned_be64(sector, &cmd->cmnd[2]);
+ put_unaligned_be32(nr_sectors, &cmd->cmnd[10]);
- len = sdkp->device->sector_size;
- break;
+ cmd->allowed = SD_MAX_RETRIES;
+ cmd->transfersize = data_len;
+ rq->timeout = unmap ? SD_TIMEOUT : SD_WRITE_SAME_TIMEOUT;
+ scsi_req(rq)->resid_len = data_len;
- case SD_LBP_WS10:
- case SD_LBP_ZERO:
- cmd->cmd_len = 10;
- cmd->cmnd[0] = WRITE_SAME;
- if (sdkp->provisioning_mode == SD_LBP_WS10)
- cmd->cmnd[1] = 0x8; /* UNMAP */
- put_unaligned_be32(sector, &cmd->cmnd[2]);
- put_unaligned_be16(nr_sectors, &cmd->cmnd[7]);
+ return scsi_init_io(cmd);
+}
- len = sdkp->device->sector_size;
- break;
+static int sd_setup_write_same10_cmnd(struct scsi_cmnd *cmd, bool unmap)
+{
+ struct scsi_device *sdp = cmd->device;
+ struct request *rq = cmd->request;
+ u64 sector = blk_rq_pos(rq) >> (ilog2(sdp->sector_size) - 9);
+ u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9);
+ u32 data_len = sdp->sector_size;
- default:
- ret = BLKPREP_INVALID;
- goto out;
- }
+ rq->special_vec.bv_page = alloc_page(GFP_ATOMIC | __GFP_ZERO);
+ if (!rq->special_vec.bv_page)
+ return BLKPREP_DEFER;
+ rq->special_vec.bv_offset = 0;
+ rq->special_vec.bv_len = data_len;
+ rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
- rq->timeout = SD_TIMEOUT;
+ cmd->cmd_len = 10;
+ cmd->cmnd[0] = WRITE_SAME;
+ if (unmap)
+ cmd->cmnd[1] = 0x8; /* UNMAP */
+ put_unaligned_be32(sector, &cmd->cmnd[2]);
+ put_unaligned_be16(nr_sectors, &cmd->cmnd[7]);
- cmd->transfersize = len;
cmd->allowed = SD_MAX_RETRIES;
+ cmd->transfersize = data_len;
+ rq->timeout = unmap ? SD_TIMEOUT : SD_WRITE_SAME_TIMEOUT;
+ scsi_req(rq)->resid_len = data_len;
- rq->special_vec.bv_page = page;
- rq->special_vec.bv_offset = 0;
- rq->special_vec.bv_len = len;
+ return scsi_init_io(cmd);
+}
- rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
- scsi_req(rq)->resid_len = len;
+static int sd_setup_write_zeroes_cmnd(struct scsi_cmnd *cmd)
+{
+ struct request *rq = cmd->request;
+ struct scsi_device *sdp = cmd->device;
+ struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
+ u64 sector = blk_rq_pos(rq) >> (ilog2(sdp->sector_size) - 9);
+ u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9);
+
+ if (!(rq->cmd_flags & REQ_NOUNMAP)) {
+ switch (sdkp->zeroing_mode) {
+ case SD_ZERO_WS16_UNMAP:
+ return sd_setup_write_same16_cmnd(cmd, true);
+ case SD_ZERO_WS10_UNMAP:
+ return sd_setup_write_same10_cmnd(cmd, true);
+ }
+ }
- ret = scsi_init_io(cmd);
-out:
- if (ret != BLKPREP_OK)
- __free_page(page);
- return ret;
+ if (sdp->no_write_same)
+ return BLKPREP_INVALID;
+ if (sdkp->ws16 || sector > 0xffffffff || nr_sectors > 0xffff)
+ return sd_setup_write_same16_cmnd(cmd, false);
+ return sd_setup_write_same10_cmnd(cmd, false);
}
static void sd_config_write_same(struct scsi_disk *sdkp)
sdkp->max_ws_blocks = 0;
}
+ if (sdkp->lbprz && sdkp->lbpws)
+ sdkp->zeroing_mode = SD_ZERO_WS16_UNMAP;
+ else if (sdkp->lbprz && sdkp->lbpws10)
+ sdkp->zeroing_mode = SD_ZERO_WS10_UNMAP;
+ else if (sdkp->max_ws_blocks)
+ sdkp->zeroing_mode = SD_ZERO_WS;
+ else
+ sdkp->zeroing_mode = SD_ZERO_WRITE;
+
out:
blk_queue_max_write_same_sectors(q, sdkp->max_ws_blocks *
(logical_block_size >> 9));
+ blk_queue_max_write_zeroes_sectors(q, sdkp->max_ws_blocks *
+ (logical_block_size >> 9));
}
/**
switch (req_op(rq)) {
case REQ_OP_DISCARD:
- return sd_setup_discard_cmnd(cmd);
+ switch (scsi_disk(rq->rq_disk)->provisioning_mode) {
+ case SD_LBP_UNMAP:
+ return sd_setup_unmap_cmnd(cmd);
+ case SD_LBP_WS16:
+ return sd_setup_write_same16_cmnd(cmd, true);
+ case SD_LBP_WS10:
+ return sd_setup_write_same10_cmnd(cmd, true);
+ case SD_LBP_ZERO:
+ return sd_setup_write_same10_cmnd(cmd, false);
+ default:
+ return BLKPREP_INVALID;
+ }
+ case REQ_OP_WRITE_ZEROES:
+ return sd_setup_write_zeroes_cmnd(cmd);
case REQ_OP_WRITE_SAME:
return sd_setup_write_same_cmnd(cmd);
case REQ_OP_FLUSH:
switch (req_op(req)) {
case REQ_OP_DISCARD:
+ case REQ_OP_WRITE_ZEROES:
case REQ_OP_WRITE_SAME:
case REQ_OP_ZONE_RESET:
if (!result) {
#define READ_CAPACITY_RETRIES_ON_RESET 10
+/*
+ * Ensure that we don't overflow sector_t when CONFIG_LBDAF is not set
+ * and the reported logical block size is bigger than 512 bytes. Note
+ * that last_sector is a u64 and therefore logical_to_sectors() is not
+ * applicable.
+ */
+static bool sd_addressable_capacity(u64 lba, unsigned int sector_size)
+{
+ u64 last_sector = (lba + 1ULL) << (ilog2(sector_size) - 9);
+
+ if (sizeof(sector_t) == 4 && last_sector > U32_MAX)
+ return false;
+
+ return true;
+}
+
static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp,
unsigned char *buffer)
{
return -ENODEV;
}
- if ((sizeof(sdkp->capacity) == 4) && (lba >= 0xffffffffULL)) {
+ if (!sd_addressable_capacity(lba, sector_size)) {
sd_printk(KERN_ERR, sdkp, "Too big for this kernel. Use a "
"kernel compiled with support for large block "
"devices.\n");
return sector_size;
}
- if ((sizeof(sdkp->capacity) == 4) && (lba == 0xffffffff)) {
+ if (!sd_addressable_capacity(lba, sector_size)) {
sd_printk(KERN_ERR, sdkp, "Too big for this kernel. Use a "
"kernel compiled with support for large block "
"devices.\n");
sd_config_discard(sdkp, SD_LBP_WS16);
} else { /* LBP VPD page tells us what to use */
- if (sdkp->lbpu && sdkp->max_unmap_blocks && !sdkp->lbprz)
+ if (sdkp->lbpu && sdkp->max_unmap_blocks)
sd_config_discard(sdkp, SD_LBP_UNMAP);
else if (sdkp->lbpws)
sd_config_discard(sdkp, SD_LBP_WS16);
q->limits.io_opt = logical_to_bytes(sdp, sdkp->opt_xfer_blocks);
rw_max = logical_to_sectors(sdp, sdkp->opt_xfer_blocks);
} else
- rw_max = BLK_DEF_MAX_SECTORS;
+ rw_max = min_not_zero(logical_to_sectors(sdp, dev_max),
+ (sector_t)BLK_DEF_MAX_SECTORS);
/* Combine with controller limits */
q->limits.max_sectors = min(rw_max, queue_max_hw_sectors(q));
SD_LBP_DISABLE, /* Discard disabled due to failed cmd */
};
+enum {
+ SD_ZERO_WRITE = 0, /* Use WRITE(10/16) command */
+ SD_ZERO_WS, /* Use WRITE SAME(10/16) command */
+ SD_ZERO_WS16_UNMAP, /* Use WRITE SAME(16) with UNMAP */
+ SD_ZERO_WS10_UNMAP, /* Use WRITE SAME(10) with UNMAP */
+};
+
struct scsi_disk {
struct scsi_driver *driver; /* always &sd_template */
struct scsi_device *device;
u8 write_prot;
u8 protection_type;/* Data Integrity Field */
u8 provisioning_mode;
+ u8 zeroing_mode;
unsigned ATO : 1; /* state of disk ATO bit */
unsigned cache_override : 1; /* temp override of WCE,RCD */
unsigned WCE : 1; /* state of disk WCE bit */
switch (req_op(rq)) {
case REQ_OP_WRITE:
+ case REQ_OP_WRITE_ZEROES:
case REQ_OP_WRITE_SAME:
case REQ_OP_ZONE_RESET:
sg_io_hdr_t *hp;
unsigned char cmnd[SG_MAX_CDB_SIZE];
- if (unlikely(segment_eq(get_fs(), KERNEL_DS)))
+ if (unlikely(uaccess_kernel()))
return -EINVAL;
if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp)))
pr_info("%s: device detaching\n", __func__);
sense = req->sense;
- result = rq->errors;
+ result = req->result;
resid = req->resid_len;
SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sdp,
srp->rq = rq;
rq->end_io_data = srp;
- rq->retries = SG_DEFAULT_RETRIES;
+ req->retries = SG_DEFAULT_RETRIES;
if ((dxfer_len <= 0) || (dxfer_dir == SG_DXFER_NONE))
return 0;
unsigned char *buffer;
struct scsi_mode_data data;
struct scsi_sense_hdr sshdr;
+ unsigned int ms_len = 128;
int rc, n;
static const char *loadmech[] =
scsi_test_unit_ready(cd->device, SR_TIMEOUT, MAX_RETRIES, &sshdr);
/* ask for mode page 0x2a */
- rc = scsi_mode_sense(cd->device, 0, 0x2a, buffer, 128,
+ rc = scsi_mode_sense(cd->device, 0, 0x2a, buffer, ms_len,
SR_TIMEOUT, 3, &data, NULL);
- if (!scsi_status_is_good(rc)) {
+ if (!scsi_status_is_good(rc) || data.length > ms_len ||
+ data.header_length + data.block_descriptor_length > data.length) {
/* failed, drive doesn't have capabilities mode page */
cd->cdi.speed = 1;
cd->cdi.mask |= (CDC_CD_R | CDC_CD_RW | CDC_DVD_R |
atomic64_add(ktime_to_ns(now), &STp->stats->tot_write_time);
atomic64_add(ktime_to_ns(now), &STp->stats->tot_io_time);
atomic64_inc(&STp->stats->write_cnt);
- if (req->errors) {
+ if (scsi_req(req)->result) {
atomic64_add(atomic_read(&STp->stats->last_write_size)
- STp->buffer->cmdstat.residual,
&STp->stats->write_byte_cnt);
atomic64_add(ktime_to_ns(now), &STp->stats->tot_read_time);
atomic64_add(ktime_to_ns(now), &STp->stats->tot_io_time);
atomic64_inc(&STp->stats->read_cnt);
- if (req->errors) {
+ if (scsi_req(req)->result) {
atomic64_add(atomic_read(&STp->stats->last_read_size)
- STp->buffer->cmdstat.residual,
&STp->stats->read_byte_cnt);
struct scsi_tape *STp = SRpnt->stp;
struct bio *tmp;
- STp->buffer->cmdstat.midlevel_result = SRpnt->result = req->errors;
+ STp->buffer->cmdstat.midlevel_result = SRpnt->result = rq->result;
STp->buffer->cmdstat.residual = rq->resid_len;
st_do_stats(STp, req);
memset(rq->cmd, 0, BLK_MAX_CDB);
memcpy(rq->cmd, cmd, rq->cmd_len);
req->timeout = timeout;
- req->retries = retries;
+ rq->retries = retries;
req->end_io_data = SRpnt;
blk_execute_rq_nowait(req->q, NULL, req, 1, st_scsi_execute_end);
ret = PTR_ERR(vmfile);
goto out;
}
+ vmfile->f_mode |= FMODE_LSEEK;
asma->file = vmfile;
}
get_file(asma->file);
struct obd_export *lsi_osd_exp;
char lsi_osd_type[16];
char lsi_fstype[16];
- struct backing_dev_info lsi_bdi; /* each client mountpoint needs
- * own backing_dev_info
- */
};
#define LSI_UMOUNT_FAILOVER 0x00200000
-#define LSI_BDI_INITIALIZED 0x00400000
#define s2lsi(sb) ((struct lustre_sb_info *)((sb)->s_fs_info))
#define s2lsi_nocast(sb) ((sb)->s_fs_info)
mutex_init(&lli->lli_layout_mutex);
}
-static inline int ll_bdi_register(struct backing_dev_info *bdi)
-{
- static atomic_t ll_bdi_num = ATOMIC_INIT(0);
-
- bdi->name = "lustre";
- return bdi_register(bdi, NULL, "lustre-%d",
- atomic_inc_return(&ll_bdi_num));
-}
-
int ll_fill_super(struct super_block *sb, struct vfsmount *mnt)
{
struct lustre_profile *lprof = NULL;
char *profilenm = get_profile_name(sb);
struct config_llog_instance *cfg;
int err;
+ static atomic_t ll_bdi_num = ATOMIC_INIT(0);
CDEBUG(D_VFSTRACE, "VFS Op: sb %p\n", sb);
if (err)
goto out_free;
- err = bdi_init(&lsi->lsi_bdi);
- if (err)
- goto out_free;
- lsi->lsi_flags |= LSI_BDI_INITIALIZED;
- lsi->lsi_bdi.capabilities = 0;
- err = ll_bdi_register(&lsi->lsi_bdi);
+ err = super_setup_bdi_name(sb, "lustre-%d",
+ atomic_inc_return(&ll_bdi_num));
if (err)
goto out_free;
- sb->s_bdi = &lsi->lsi_bdi;
/* kernel >= 2.6.38 store dentry operations in sb->s_d_op. */
sb->s_d_op = &ll_d_ops;
if (profilenm)
class_del_profile(profilenm);
- if (lsi->lsi_flags & LSI_BDI_INITIALIZED) {
- bdi_destroy(&lsi->lsi_bdi);
- lsi->lsi_flags &= ~LSI_BDI_INITIALIZED;
- }
-
ll_free_sbi(sb);
lsi->lsi_llsbi = NULL;
int iscsit_queue_rsp(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
{
- iscsit_add_cmd_to_response_queue(cmd, cmd->conn, cmd->i_state);
- return 0;
+ return iscsit_add_cmd_to_response_queue(cmd, cmd->conn, cmd->i_state);
}
EXPORT_SYMBOL(iscsit_queue_rsp);
struct iscsi_portal_group *tpg;
struct iscsi_tpg_np *tpg_np;
char *str, *str2, *ip_str, *port_str;
- struct sockaddr_storage sockaddr;
- struct sockaddr_in *sock_in;
- struct sockaddr_in6 *sock_in6;
- unsigned long port;
+ struct sockaddr_storage sockaddr = { };
int ret;
char buf[MAX_PORTAL_LEN + 1];
memset(buf, 0, MAX_PORTAL_LEN + 1);
snprintf(buf, MAX_PORTAL_LEN + 1, "%s", name);
- memset(&sockaddr, 0, sizeof(struct sockaddr_storage));
-
str = strstr(buf, "[");
if (str) {
- const char *end;
-
str2 = strstr(str, "]");
if (!str2) {
pr_err("Unable to locate trailing \"]\""
" in IPv6 iSCSI network portal address\n");
return ERR_PTR(-EINVAL);
}
- str++; /* Skip over leading "[" */
+
+ ip_str = str + 1; /* Skip over leading "[" */
*str2 = '\0'; /* Terminate the unbracketed IPv6 address */
str2++; /* Skip over the \0 */
+
port_str = strstr(str2, ":");
if (!port_str) {
pr_err("Unable to locate \":port\""
}
*port_str = '\0'; /* Terminate string for IP */
port_str++; /* Skip over ":" */
-
- ret = kstrtoul(port_str, 0, &port);
- if (ret < 0) {
- pr_err("kstrtoul() failed for port_str: %d\n", ret);
- return ERR_PTR(ret);
- }
- sock_in6 = (struct sockaddr_in6 *)&sockaddr;
- sock_in6->sin6_family = AF_INET6;
- sock_in6->sin6_port = htons((unsigned short)port);
- ret = in6_pton(str, -1,
- (void *)&sock_in6->sin6_addr.in6_u, -1, &end);
- if (ret <= 0) {
- pr_err("in6_pton returned: %d\n", ret);
- return ERR_PTR(-EINVAL);
- }
} else {
- str = ip_str = &buf[0];
+ ip_str = &buf[0];
port_str = strstr(ip_str, ":");
if (!port_str) {
pr_err("Unable to locate \":port\""
}
*port_str = '\0'; /* Terminate string for IP */
port_str++; /* Skip over ":" */
+ }
- ret = kstrtoul(port_str, 0, &port);
- if (ret < 0) {
- pr_err("kstrtoul() failed for port_str: %d\n", ret);
- return ERR_PTR(ret);
- }
- sock_in = (struct sockaddr_in *)&sockaddr;
- sock_in->sin_family = AF_INET;
- sock_in->sin_port = htons((unsigned short)port);
- sock_in->sin_addr.s_addr = in_aton(ip_str);
+ ret = inet_pton_with_scope(&init_net, AF_UNSPEC, ip_str,
+ port_str, &sockaddr);
+ if (ret) {
+ pr_err("malformed ip/port passed: %s\n", name);
+ return ERR_PTR(ret);
}
+
tpg = container_of(se_tpg, struct iscsi_portal_group, tpg_se_tpg);
ret = iscsit_get_tpg(tpg);
if (ret < 0)
static int lio_queue_data_in(struct se_cmd *se_cmd)
{
struct iscsi_cmd *cmd = container_of(se_cmd, struct iscsi_cmd, se_cmd);
+ struct iscsi_conn *conn = cmd->conn;
cmd->i_state = ISTATE_SEND_DATAIN;
- cmd->conn->conn_transport->iscsit_queue_data_in(cmd->conn, cmd);
-
- return 0;
+ return conn->conn_transport->iscsit_queue_data_in(conn, cmd);
}
static int lio_write_pending(struct se_cmd *se_cmd)
static int lio_queue_status(struct se_cmd *se_cmd)
{
struct iscsi_cmd *cmd = container_of(se_cmd, struct iscsi_cmd, se_cmd);
+ struct iscsi_conn *conn = cmd->conn;
cmd->i_state = ISTATE_SEND_STATUS;
if (cmd->se_cmd.scsi_status || cmd->sense_reason) {
- iscsit_add_cmd_to_response_queue(cmd, cmd->conn, cmd->i_state);
- return 0;
+ return iscsit_add_cmd_to_response_queue(cmd, conn, cmd->i_state);
}
- cmd->conn->conn_transport->iscsit_queue_status(cmd->conn, cmd);
-
- return 0;
+ return conn->conn_transport->iscsit_queue_status(conn, cmd);
}
static void lio_queue_tm_rsp(struct se_cmd *se_cmd)
if (!strcmp(param->name, MAXRECVDATASEGMENTLENGTH))
SET_PSTATE_REPLY_OPTIONAL(param);
/*
- * The GlobalSAN iSCSI Initiator for MacOSX does
- * not respond to MaxBurstLength, FirstBurstLength,
- * DefaultTime2Wait or DefaultTime2Retain parameter keys.
- * So, we set them to 'reply optional' here, and assume the
- * the defaults from iscsi_parameters.h if the initiator
- * is not RFC compliant and the keys are not negotiated.
- */
- if (!strcmp(param->name, MAXBURSTLENGTH))
- SET_PSTATE_REPLY_OPTIONAL(param);
- if (!strcmp(param->name, FIRSTBURSTLENGTH))
- SET_PSTATE_REPLY_OPTIONAL(param);
- if (!strcmp(param->name, DEFAULTTIME2WAIT))
- SET_PSTATE_REPLY_OPTIONAL(param);
- if (!strcmp(param->name, DEFAULTTIME2RETAIN))
- SET_PSTATE_REPLY_OPTIONAL(param);
- /*
* Required for gPXE iSCSI boot client
*/
if (!strcmp(param->name, MAXCONNECTIONS))
}
}
-void iscsit_add_cmd_to_response_queue(
+int iscsit_add_cmd_to_response_queue(
struct iscsi_cmd *cmd,
struct iscsi_conn *conn,
u8 state)
if (!qr) {
pr_err("Unable to allocate memory for"
" struct iscsi_queue_req\n");
- return;
+ return -ENOMEM;
}
INIT_LIST_HEAD(&qr->qr_list);
qr->cmd = cmd;
spin_unlock_bh(&conn->response_queue_lock);
wake_up(&conn->queues_wq);
+ return 0;
}
struct iscsi_queue_req *iscsit_get_cmd_from_response_queue(struct iscsi_conn *conn)
{
struct se_cmd *se_cmd = NULL;
int rc;
+ bool op_scsi = false;
/*
* Determine if a struct se_cmd is associated with
* this struct iscsi_cmd.
*/
switch (cmd->iscsi_opcode) {
case ISCSI_OP_SCSI_CMD:
- se_cmd = &cmd->se_cmd;
- __iscsit_free_cmd(cmd, true, shutdown);
+ op_scsi = true;
/*
* Fallthrough
*/
case ISCSI_OP_SCSI_TMFUNC:
- rc = transport_generic_free_cmd(&cmd->se_cmd, shutdown);
- if (!rc && shutdown && se_cmd && se_cmd->se_sess) {
- __iscsit_free_cmd(cmd, true, shutdown);
+ se_cmd = &cmd->se_cmd;
+ __iscsit_free_cmd(cmd, op_scsi, shutdown);
+ rc = transport_generic_free_cmd(se_cmd, shutdown);
+ if (!rc && shutdown && se_cmd->se_sess) {
+ __iscsit_free_cmd(cmd, op_scsi, shutdown);
target_put_sess_cmd(se_cmd);
}
break;
struct iscsi_conn_recovery **, itt_t);
extern void iscsit_add_cmd_to_immediate_queue(struct iscsi_cmd *, struct iscsi_conn *, u8);
extern struct iscsi_queue_req *iscsit_get_cmd_from_immediate_queue(struct iscsi_conn *);
-extern void iscsit_add_cmd_to_response_queue(struct iscsi_cmd *, struct iscsi_conn *, u8);
+extern int iscsit_add_cmd_to_response_queue(struct iscsi_cmd *, struct iscsi_conn *, u8);
extern struct iscsi_queue_req *iscsit_get_cmd_from_response_queue(struct iscsi_conn *);
extern void iscsit_remove_cmd_from_tx_queues(struct iscsi_cmd *, struct iscsi_conn *);
extern bool iscsit_conn_all_queues_empty(struct iscsi_conn *);
/*
* Set the ASYMMETRIC ACCESS State
*/
- buf[off++] |= (atomic_read(
- &tg_pt_gp->tg_pt_gp_alua_access_state) & 0xff);
+ buf[off++] |= tg_pt_gp->tg_pt_gp_alua_access_state & 0xff;
/*
* Set supported ASYMMETRIC ACCESS State bits
*/
spin_lock(&lun->lun_tg_pt_gp_lock);
tg_pt_gp = lun->lun_tg_pt_gp;
- out_alua_state = atomic_read(&tg_pt_gp->tg_pt_gp_alua_access_state);
+ out_alua_state = tg_pt_gp->tg_pt_gp_alua_access_state;
nonop_delay_msecs = tg_pt_gp->tg_pt_gp_nonop_delay_msecs;
// XXX: keeps using tg_pt_gp witout reference after unlock
}
/*
- * Called with tg_pt_gp->tg_pt_gp_md_mutex held
+ * Called with tg_pt_gp->tg_pt_gp_transition_mutex held
*/
static int core_alua_update_tpg_primary_metadata(
struct t10_alua_tg_pt_gp *tg_pt_gp)
"alua_access_state=0x%02x\n"
"alua_access_status=0x%02x\n",
tg_pt_gp->tg_pt_gp_id,
- tg_pt_gp->tg_pt_gp_alua_pending_state,
+ tg_pt_gp->tg_pt_gp_alua_access_state,
tg_pt_gp->tg_pt_gp_alua_access_status);
snprintf(path, ALUA_METADATA_PATH_LEN,
spin_unlock(&tg_pt_gp->tg_pt_gp_lock);
}
-static void core_alua_do_transition_tg_pt_work(struct work_struct *work)
-{
- struct t10_alua_tg_pt_gp *tg_pt_gp = container_of(work,
- struct t10_alua_tg_pt_gp, tg_pt_gp_transition_work);
- struct se_device *dev = tg_pt_gp->tg_pt_gp_dev;
- bool explicit = (tg_pt_gp->tg_pt_gp_alua_access_status ==
- ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG);
-
- /*
- * Update the ALUA metadata buf that has been allocated in
- * core_alua_do_port_transition(), this metadata will be written
- * to struct file.
- *
- * Note that there is the case where we do not want to update the
- * metadata when the saved metadata is being parsed in userspace
- * when setting the existing port access state and access status.
- *
- * Also note that the failure to write out the ALUA metadata to
- * struct file does NOT affect the actual ALUA transition.
- */
- if (tg_pt_gp->tg_pt_gp_write_metadata) {
- mutex_lock(&tg_pt_gp->tg_pt_gp_md_mutex);
- core_alua_update_tpg_primary_metadata(tg_pt_gp);
- mutex_unlock(&tg_pt_gp->tg_pt_gp_md_mutex);
- }
- /*
- * Set the current primary ALUA access state to the requested new state
- */
- atomic_set(&tg_pt_gp->tg_pt_gp_alua_access_state,
- tg_pt_gp->tg_pt_gp_alua_pending_state);
-
- pr_debug("Successful %s ALUA transition TG PT Group: %s ID: %hu"
- " from primary access state %s to %s\n", (explicit) ? "explicit" :
- "implicit", config_item_name(&tg_pt_gp->tg_pt_gp_group.cg_item),
- tg_pt_gp->tg_pt_gp_id,
- core_alua_dump_state(tg_pt_gp->tg_pt_gp_alua_previous_state),
- core_alua_dump_state(tg_pt_gp->tg_pt_gp_alua_pending_state));
-
- core_alua_queue_state_change_ua(tg_pt_gp);
-
- spin_lock(&dev->t10_alua.tg_pt_gps_lock);
- atomic_dec(&tg_pt_gp->tg_pt_gp_ref_cnt);
- spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
-
- if (tg_pt_gp->tg_pt_gp_transition_complete)
- complete(tg_pt_gp->tg_pt_gp_transition_complete);
-}
-
static int core_alua_do_transition_tg_pt(
struct t10_alua_tg_pt_gp *tg_pt_gp,
int new_state,
int explicit)
{
- struct se_device *dev = tg_pt_gp->tg_pt_gp_dev;
- DECLARE_COMPLETION_ONSTACK(wait);
+ int prev_state;
+ mutex_lock(&tg_pt_gp->tg_pt_gp_transition_mutex);
/* Nothing to be done here */
- if (atomic_read(&tg_pt_gp->tg_pt_gp_alua_access_state) == new_state)
+ if (tg_pt_gp->tg_pt_gp_alua_access_state == new_state) {
+ mutex_unlock(&tg_pt_gp->tg_pt_gp_transition_mutex);
return 0;
+ }
- if (explicit && new_state == ALUA_ACCESS_STATE_TRANSITION)
+ if (explicit && new_state == ALUA_ACCESS_STATE_TRANSITION) {
+ mutex_unlock(&tg_pt_gp->tg_pt_gp_transition_mutex);
return -EAGAIN;
-
- /*
- * Flush any pending transitions
- */
- if (!explicit)
- flush_work(&tg_pt_gp->tg_pt_gp_transition_work);
+ }
/*
* Save the old primary ALUA access state, and set the current state
* to ALUA_ACCESS_STATE_TRANSITION.
*/
- atomic_set(&tg_pt_gp->tg_pt_gp_alua_access_state,
- ALUA_ACCESS_STATE_TRANSITION);
+ prev_state = tg_pt_gp->tg_pt_gp_alua_access_state;
+ tg_pt_gp->tg_pt_gp_alua_access_state = ALUA_ACCESS_STATE_TRANSITION;
tg_pt_gp->tg_pt_gp_alua_access_status = (explicit) ?
ALUA_STATUS_ALTERED_BY_EXPLICIT_STPG :
ALUA_STATUS_ALTERED_BY_IMPLICIT_ALUA;
core_alua_queue_state_change_ua(tg_pt_gp);
- if (new_state == ALUA_ACCESS_STATE_TRANSITION)
+ if (new_state == ALUA_ACCESS_STATE_TRANSITION) {
+ mutex_unlock(&tg_pt_gp->tg_pt_gp_transition_mutex);
return 0;
-
- tg_pt_gp->tg_pt_gp_alua_previous_state =
- atomic_read(&tg_pt_gp->tg_pt_gp_alua_access_state);
- tg_pt_gp->tg_pt_gp_alua_pending_state = new_state;
+ }
/*
* Check for the optional ALUA primary state transition delay
msleep_interruptible(tg_pt_gp->tg_pt_gp_trans_delay_msecs);
/*
- * Take a reference for workqueue item
+ * Set the current primary ALUA access state to the requested new state
*/
- spin_lock(&dev->t10_alua.tg_pt_gps_lock);
- atomic_inc(&tg_pt_gp->tg_pt_gp_ref_cnt);
- spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
+ tg_pt_gp->tg_pt_gp_alua_access_state = new_state;
- schedule_work(&tg_pt_gp->tg_pt_gp_transition_work);
- if (explicit) {
- tg_pt_gp->tg_pt_gp_transition_complete = &wait;
- wait_for_completion(&wait);
- tg_pt_gp->tg_pt_gp_transition_complete = NULL;
+ /*
+ * Update the ALUA metadata buf that has been allocated in
+ * core_alua_do_port_transition(), this metadata will be written
+ * to struct file.
+ *
+ * Note that there is the case where we do not want to update the
+ * metadata when the saved metadata is being parsed in userspace
+ * when setting the existing port access state and access status.
+ *
+ * Also note that the failure to write out the ALUA metadata to
+ * struct file does NOT affect the actual ALUA transition.
+ */
+ if (tg_pt_gp->tg_pt_gp_write_metadata) {
+ core_alua_update_tpg_primary_metadata(tg_pt_gp);
}
+ pr_debug("Successful %s ALUA transition TG PT Group: %s ID: %hu"
+ " from primary access state %s to %s\n", (explicit) ? "explicit" :
+ "implicit", config_item_name(&tg_pt_gp->tg_pt_gp_group.cg_item),
+ tg_pt_gp->tg_pt_gp_id,
+ core_alua_dump_state(prev_state),
+ core_alua_dump_state(new_state));
+
+ core_alua_queue_state_change_ua(tg_pt_gp);
+
+ mutex_unlock(&tg_pt_gp->tg_pt_gp_transition_mutex);
return 0;
}
}
INIT_LIST_HEAD(&tg_pt_gp->tg_pt_gp_list);
INIT_LIST_HEAD(&tg_pt_gp->tg_pt_gp_lun_list);
- mutex_init(&tg_pt_gp->tg_pt_gp_md_mutex);
+ mutex_init(&tg_pt_gp->tg_pt_gp_transition_mutex);
spin_lock_init(&tg_pt_gp->tg_pt_gp_lock);
atomic_set(&tg_pt_gp->tg_pt_gp_ref_cnt, 0);
- INIT_WORK(&tg_pt_gp->tg_pt_gp_transition_work,
- core_alua_do_transition_tg_pt_work);
tg_pt_gp->tg_pt_gp_dev = dev;
- atomic_set(&tg_pt_gp->tg_pt_gp_alua_access_state,
- ALUA_ACCESS_STATE_ACTIVE_OPTIMIZED);
+ tg_pt_gp->tg_pt_gp_alua_access_state =
+ ALUA_ACCESS_STATE_ACTIVE_OPTIMIZED;
/*
* Enable both explicit and implicit ALUA support by default
*/
dev->t10_alua.alua_tg_pt_gps_counter--;
spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
- flush_work(&tg_pt_gp->tg_pt_gp_transition_work);
-
/*
* Allow a struct t10_alua_tg_pt_gp_member * referenced by
* core_alua_get_tg_pt_gp_by_name() in
"Primary Access Status: %s\nTG Port Secondary Access"
" State: %s\nTG Port Secondary Access Status: %s\n",
config_item_name(tg_pt_ci), tg_pt_gp->tg_pt_gp_id,
- core_alua_dump_state(atomic_read(
- &tg_pt_gp->tg_pt_gp_alua_access_state)),
+ core_alua_dump_state(
+ tg_pt_gp->tg_pt_gp_alua_access_state),
core_alua_dump_status(
tg_pt_gp->tg_pt_gp_alua_access_status),
atomic_read(&lun->lun_tg_pt_secondary_offline) ?
char *page)
{
return sprintf(page, "%d\n",
- atomic_read(&to_tg_pt_gp(item)->tg_pt_gp_alua_access_state));
+ to_tg_pt_gp(item)->tg_pt_gp_alua_access_state);
}
static ssize_t target_tg_pt_gp_alua_access_state_store(struct config_item *item,
attrib->unmap_granularity = q->limits.discard_granularity / block_size;
attrib->unmap_granularity_alignment = q->limits.discard_alignment /
block_size;
- attrib->unmap_zeroes_data = q->limits.discard_zeroes_data;
+ attrib->unmap_zeroes_data = 0;
return true;
}
EXPORT_SYMBOL(target_configure_unmap_from_queue);
pr_err("Source se_lun->lun_se_dev does not exist\n");
return -EINVAL;
}
+ if (lun->lun_shutdown) {
+ pr_err("Unable to create mappedlun symlink because"
+ " lun->lun_shutdown=true\n");
+ return -EINVAL;
+ }
se_tpg = lun->lun_tpg;
nacl_ci = &lun_acl_ci->ci_parent->ci_group->cg_item;
req->timeout = PS_TIMEOUT_DISK;
else
req->timeout = PS_TIMEOUT_OTHER;
- req->retries = PS_RETRY;
+ scsi_req(req)->retries = PS_RETRY;
blk_execute_rq_nowait(pdv->pdv_sd->request_queue, NULL, req,
(cmd->sam_task_attr == TCM_HEAD_TAG),
struct se_cmd *cmd = req->end_io_data;
struct pscsi_plugin_task *pt = cmd->priv;
- pt->pscsi_result = req->errors;
+ pt->pscsi_result = scsi_req(req)->result;
pt->pscsi_resid = scsi_req(req)->resid_len;
cmd->scsi_status = status_byte(pt->pscsi_result) << 1;
*/
struct se_device *dev = rcu_dereference_raw(lun->lun_se_dev);
+ lun->lun_shutdown = true;
+
core_clear_lun_from_tpg(lun, tpg);
/*
* Wait for any active I/O references to percpu se_lun->lun_ref to
}
if (!(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE))
hlist_del_rcu(&lun->link);
+
+ lun->lun_shutdown = false;
mutex_unlock(&tpg->tpg_lun_mutex);
percpu_ref_exit(&lun->lun_ref);
struct kmem_cache *t10_alua_lba_map_mem_cache;
static void transport_complete_task_attr(struct se_cmd *cmd);
+static int translate_sense_reason(struct se_cmd *cmd, sense_reason_t reason);
static void transport_handle_queue_full(struct se_cmd *cmd,
- struct se_device *dev);
+ struct se_device *dev, int err, bool write_pending);
static int transport_put_cmd(struct se_cmd *cmd);
static void target_complete_ok_work(struct work_struct *work);
if (cmd->t_state == TRANSPORT_COMPLETE_QF_WP)
transport_write_pending_qf(cmd);
- else if (cmd->t_state == TRANSPORT_COMPLETE_QF_OK)
+ else if (cmd->t_state == TRANSPORT_COMPLETE_QF_OK ||
+ cmd->t_state == TRANSPORT_COMPLETE_QF_ERR)
transport_complete_qf(cmd);
}
}
}
trace_target_cmd_complete(cmd);
ret = cmd->se_tfo->queue_status(cmd);
- if (ret == -EAGAIN || ret == -ENOMEM)
+ if (ret)
goto queue_full;
goto check_stop;
default:
}
ret = transport_send_check_condition_and_sense(cmd, sense_reason, 0);
- if (ret == -EAGAIN || ret == -ENOMEM)
+ if (ret)
goto queue_full;
check_stop:
return;
queue_full:
- cmd->t_state = TRANSPORT_COMPLETE_QF_OK;
- transport_handle_queue_full(cmd, cmd->se_dev);
+ transport_handle_queue_full(cmd, cmd->se_dev, ret, false);
}
EXPORT_SYMBOL(transport_generic_request_failure);
int ret = 0;
transport_complete_task_attr(cmd);
+ /*
+ * If a fabric driver ->write_pending() or ->queue_data_in() callback
+ * has returned neither -ENOMEM or -EAGAIN, assume it's fatal and
+ * the same callbacks should not be retried. Return CHECK_CONDITION
+ * if a scsi_status is not already set.
+ *
+ * If a fabric driver ->queue_status() has returned non zero, always
+ * keep retrying no matter what..
+ */
+ if (cmd->t_state == TRANSPORT_COMPLETE_QF_ERR) {
+ if (cmd->scsi_status)
+ goto queue_status;
- if (cmd->se_cmd_flags & SCF_TRANSPORT_TASK_SENSE) {
- trace_target_cmd_complete(cmd);
- ret = cmd->se_tfo->queue_status(cmd);
- goto out;
+ cmd->se_cmd_flags |= SCF_EMULATED_TASK_SENSE;
+ cmd->scsi_status = SAM_STAT_CHECK_CONDITION;
+ cmd->scsi_sense_length = TRANSPORT_SENSE_BUFFER;
+ translate_sense_reason(cmd, TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE);
+ goto queue_status;
}
+ if (cmd->se_cmd_flags & SCF_TRANSPORT_TASK_SENSE)
+ goto queue_status;
+
switch (cmd->data_direction) {
case DMA_FROM_DEVICE:
if (cmd->scsi_status)
break;
}
-out:
if (ret < 0) {
- transport_handle_queue_full(cmd, cmd->se_dev);
+ transport_handle_queue_full(cmd, cmd->se_dev, ret, false);
return;
}
transport_lun_remove_cmd(cmd);
transport_cmd_check_stop_to_fabric(cmd);
}
-static void transport_handle_queue_full(
- struct se_cmd *cmd,
- struct se_device *dev)
+static void transport_handle_queue_full(struct se_cmd *cmd, struct se_device *dev,
+ int err, bool write_pending)
{
+ /*
+ * -EAGAIN or -ENOMEM signals retry of ->write_pending() and/or
+ * ->queue_data_in() callbacks from new process context.
+ *
+ * Otherwise for other errors, transport_complete_qf() will send
+ * CHECK_CONDITION via ->queue_status() instead of attempting to
+ * retry associated fabric driver data-transfer callbacks.
+ */
+ if (err == -EAGAIN || err == -ENOMEM) {
+ cmd->t_state = (write_pending) ? TRANSPORT_COMPLETE_QF_WP :
+ TRANSPORT_COMPLETE_QF_OK;
+ } else {
+ pr_warn_ratelimited("Got unknown fabric queue status: %d\n", err);
+ cmd->t_state = TRANSPORT_COMPLETE_QF_ERR;
+ }
+
spin_lock_irq(&dev->qf_cmd_lock);
list_add_tail(&cmd->se_qf_node, &cmd->se_dev->qf_cmd_list);
atomic_inc_mb(&dev->dev_qf_count);
WARN_ON(!cmd->scsi_status);
ret = transport_send_check_condition_and_sense(
cmd, 0, 1);
- if (ret == -EAGAIN || ret == -ENOMEM)
+ if (ret)
goto queue_full;
transport_lun_remove_cmd(cmd);
} else if (rc) {
ret = transport_send_check_condition_and_sense(cmd,
rc, 0);
- if (ret == -EAGAIN || ret == -ENOMEM)
+ if (ret)
goto queue_full;
transport_lun_remove_cmd(cmd);
if (target_read_prot_action(cmd)) {
ret = transport_send_check_condition_and_sense(cmd,
cmd->pi_err, 0);
- if (ret == -EAGAIN || ret == -ENOMEM)
+ if (ret)
goto queue_full;
transport_lun_remove_cmd(cmd);
trace_target_cmd_complete(cmd);
ret = cmd->se_tfo->queue_data_in(cmd);
- if (ret == -EAGAIN || ret == -ENOMEM)
+ if (ret)
goto queue_full;
break;
case DMA_TO_DEVICE:
atomic_long_add(cmd->data_length,
&cmd->se_lun->lun_stats.tx_data_octets);
ret = cmd->se_tfo->queue_data_in(cmd);
- if (ret == -EAGAIN || ret == -ENOMEM)
+ if (ret)
goto queue_full;
break;
}
queue_status:
trace_target_cmd_complete(cmd);
ret = cmd->se_tfo->queue_status(cmd);
- if (ret == -EAGAIN || ret == -ENOMEM)
+ if (ret)
goto queue_full;
break;
default:
queue_full:
pr_debug("Handling complete_ok QUEUE_FULL: se_cmd: %p,"
" data_direction: %d\n", cmd, cmd->data_direction);
- cmd->t_state = TRANSPORT_COMPLETE_QF_OK;
- transport_handle_queue_full(cmd, cmd->se_dev);
+
+ transport_handle_queue_full(cmd, cmd->se_dev, ret, false);
}
void target_free_sgl(struct scatterlist *sgl, int nents)
spin_unlock_irqrestore(&cmd->t_state_lock, flags);
ret = cmd->se_tfo->write_pending(cmd);
- if (ret == -EAGAIN || ret == -ENOMEM)
+ if (ret)
goto queue_full;
- /* fabric drivers should only return -EAGAIN or -ENOMEM as error */
- WARN_ON(ret);
-
- return (!ret) ? 0 : TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
+ return 0;
queue_full:
pr_debug("Handling write_pending QUEUE__FULL: se_cmd: %p\n", cmd);
- cmd->t_state = TRANSPORT_COMPLETE_QF_WP;
- transport_handle_queue_full(cmd, cmd->se_dev);
+ transport_handle_queue_full(cmd, cmd->se_dev, ret, true);
return 0;
}
EXPORT_SYMBOL(transport_generic_new_cmd);
int ret;
ret = cmd->se_tfo->write_pending(cmd);
- if (ret == -EAGAIN || ret == -ENOMEM) {
+ if (ret) {
pr_debug("Handling write_pending QUEUE__FULL: se_cmd: %p\n",
cmd);
- transport_handle_queue_full(cmd, cmd->se_dev);
+ transport_handle_queue_full(cmd, cmd->se_dev, ret, true);
}
}
__releases(&cmd->t_state_lock)
__acquires(&cmd->t_state_lock)
{
+ int ret;
+
assert_spin_locked(&cmd->t_state_lock);
WARN_ON_ONCE(!irqs_disabled());
trace_target_cmd_complete(cmd);
spin_unlock_irq(&cmd->t_state_lock);
- cmd->se_tfo->queue_status(cmd);
+ ret = cmd->se_tfo->queue_status(cmd);
+ if (ret)
+ transport_handle_queue_full(cmd, cmd->se_dev, ret, false);
spin_lock_irq(&cmd->t_state_lock);
return 1;
void transport_send_task_abort(struct se_cmd *cmd)
{
unsigned long flags;
+ int ret;
spin_lock_irqsave(&cmd->t_state_lock, flags);
if (cmd->se_cmd_flags & (SCF_SENT_CHECK_CONDITION)) {
cmd->t_task_cdb[0], cmd->tag);
trace_target_cmd_complete(cmd);
- cmd->se_tfo->queue_status(cmd);
+ ret = cmd->se_tfo->queue_status(cmd);
+ if (ret)
+ transport_handle_queue_full(cmd, cmd->se_dev, ret, false);
}
static void target_tmr_work(struct work_struct *work)
DATA_BLOCK_BITS);
}
-static void gather_data_area(struct tcmu_dev *udev, unsigned long *cmd_bitmap,
- struct scatterlist *data_sg, unsigned int data_nents)
+static void gather_data_area(struct tcmu_dev *udev, struct tcmu_cmd *cmd,
+ bool bidi)
{
+ struct se_cmd *se_cmd = cmd->se_cmd;
int i, block;
int block_remaining = 0;
void *from, *to;
size_t copy_bytes, from_offset;
- struct scatterlist *sg;
+ struct scatterlist *sg, *data_sg;
+ unsigned int data_nents;
+ DECLARE_BITMAP(bitmap, DATA_BLOCK_BITS);
+
+ bitmap_copy(bitmap, cmd->data_bitmap, DATA_BLOCK_BITS);
+
+ if (!bidi) {
+ data_sg = se_cmd->t_data_sg;
+ data_nents = se_cmd->t_data_nents;
+ } else {
+ uint32_t count;
+
+ /*
+ * For bidi case, the first count blocks are for Data-Out
+ * buffer blocks, and before gathering the Data-In buffer
+ * the Data-Out buffer blocks should be discarded.
+ */
+ count = DIV_ROUND_UP(se_cmd->data_length, DATA_BLOCK_SIZE);
+ while (count--) {
+ block = find_first_bit(bitmap, DATA_BLOCK_BITS);
+ clear_bit(block, bitmap);
+ }
+
+ data_sg = se_cmd->t_bidi_data_sg;
+ data_nents = se_cmd->t_bidi_data_nents;
+ }
for_each_sg(data_sg, sg, data_nents, i) {
int sg_remaining = sg->length;
to = kmap_atomic(sg_page(sg)) + sg->offset;
while (sg_remaining > 0) {
if (block_remaining == 0) {
- block = find_first_bit(cmd_bitmap,
+ block = find_first_bit(bitmap,
DATA_BLOCK_BITS);
block_remaining = DATA_BLOCK_SIZE;
- clear_bit(block, cmd_bitmap);
+ clear_bit(block, bitmap);
}
copy_bytes = min_t(size_t, sg_remaining,
block_remaining);
return true;
}
+static inline size_t tcmu_cmd_get_data_length(struct tcmu_cmd *tcmu_cmd)
+{
+ struct se_cmd *se_cmd = tcmu_cmd->se_cmd;
+ size_t data_length = round_up(se_cmd->data_length, DATA_BLOCK_SIZE);
+
+ if (se_cmd->se_cmd_flags & SCF_BIDI) {
+ BUG_ON(!(se_cmd->t_bidi_data_sg && se_cmd->t_bidi_data_nents));
+ data_length += round_up(se_cmd->t_bidi_data_sg->length,
+ DATA_BLOCK_SIZE);
+ }
+
+ return data_length;
+}
+
+static inline uint32_t tcmu_cmd_get_block_cnt(struct tcmu_cmd *tcmu_cmd)
+{
+ size_t data_length = tcmu_cmd_get_data_length(tcmu_cmd);
+
+ return data_length / DATA_BLOCK_SIZE;
+}
+
static sense_reason_t
tcmu_queue_cmd_ring(struct tcmu_cmd *tcmu_cmd)
{
uint32_t cmd_head;
uint64_t cdb_off;
bool copy_to_data_area;
- size_t data_length;
+ size_t data_length = tcmu_cmd_get_data_length(tcmu_cmd);
DECLARE_BITMAP(old_bitmap, DATA_BLOCK_BITS);
if (test_bit(TCMU_DEV_BIT_BROKEN, &udev->flags))
* expensive to tell how many regions are freed in the bitmap
*/
base_command_size = max(offsetof(struct tcmu_cmd_entry,
- req.iov[se_cmd->t_bidi_data_nents +
- se_cmd->t_data_nents]),
+ req.iov[tcmu_cmd_get_block_cnt(tcmu_cmd)]),
sizeof(struct tcmu_cmd_entry));
command_size = base_command_size
+ round_up(scsi_command_size(se_cmd->t_task_cdb), TCMU_OP_ALIGN_SIZE);
mb = udev->mb_addr;
cmd_head = mb->cmd_head % udev->cmdr_size; /* UAM */
- data_length = se_cmd->data_length;
- if (se_cmd->se_cmd_flags & SCF_BIDI) {
- BUG_ON(!(se_cmd->t_bidi_data_sg && se_cmd->t_bidi_data_nents));
- data_length += se_cmd->t_bidi_data_sg->length;
- }
if ((command_size > (udev->cmdr_size / 2)) ||
data_length > udev->data_size) {
pr_warn("TCMU: Request of size %zu/%zu is too big for %u/%zu "
entry->req.iov_dif_cnt = 0;
/* Handle BIDI commands */
- iov_cnt = 0;
- alloc_and_scatter_data_area(udev, se_cmd->t_bidi_data_sg,
- se_cmd->t_bidi_data_nents, &iov, &iov_cnt, false);
- entry->req.iov_bidi_cnt = iov_cnt;
-
+ if (se_cmd->se_cmd_flags & SCF_BIDI) {
+ iov_cnt = 0;
+ iov++;
+ alloc_and_scatter_data_area(udev, se_cmd->t_bidi_data_sg,
+ se_cmd->t_bidi_data_nents, &iov, &iov_cnt,
+ false);
+ entry->req.iov_bidi_cnt = iov_cnt;
+ }
/* cmd's data_bitmap is what changed in process */
bitmap_xor(tcmu_cmd->data_bitmap, old_bitmap, udev->data_bitmap,
DATA_BLOCK_BITS);
se_cmd->scsi_sense_length);
free_data_area(udev, cmd);
} else if (se_cmd->se_cmd_flags & SCF_BIDI) {
- DECLARE_BITMAP(bitmap, DATA_BLOCK_BITS);
-
/* Get Data-In buffer before clean up */
- bitmap_copy(bitmap, cmd->data_bitmap, DATA_BLOCK_BITS);
- gather_data_area(udev, bitmap,
- se_cmd->t_bidi_data_sg, se_cmd->t_bidi_data_nents);
+ gather_data_area(udev, cmd, true);
free_data_area(udev, cmd);
} else if (se_cmd->data_direction == DMA_FROM_DEVICE) {
- DECLARE_BITMAP(bitmap, DATA_BLOCK_BITS);
-
- bitmap_copy(bitmap, cmd->data_bitmap, DATA_BLOCK_BITS);
- gather_data_area(udev, bitmap,
- se_cmd->t_data_sg, se_cmd->t_data_nents);
+ gather_data_area(udev, cmd, false);
free_data_area(udev, cmd);
} else if (se_cmd->data_direction == DMA_TO_DEVICE) {
free_data_area(udev, cmd);
if (ret < 0)
return ret;
- if (!val) {
- pr_err("Illegal value for cmd_time_out\n");
- return -EINVAL;
- }
-
udev->cmd_time_out = val * MSEC_PER_SEC;
return count;
}
Enable this option if you want to have support for thermal management
controller present in Armada 370 and Armada XP SoC.
-config DB8500_CPUFREQ_COOLING
- tristate "DB8500 cpufreq cooling"
- depends on ARCH_U8500 || COMPILE_TEST
- depends on HAS_IOMEM
- depends on CPU_THERMAL
- default y
- help
- Adds DB8500 cpufreq cooling devices, and these cooling devices can be
- bound to thermal zone trip points. When a trip point reached, the
- bound cpufreq cooling device turns active to set CPU frequency low to
- cool down the CPU.
-
config INTEL_POWERCLAMP
tristate "Intel PowerClamp idle injection driver"
depends on THERMAL
obj-$(CONFIG_IMX_THERMAL) += imx_thermal.o
obj-$(CONFIG_MAX77620_THERMAL) += max77620_thermal.o
obj-$(CONFIG_QORIQ_THERMAL) += qoriq_thermal.o
-obj-$(CONFIG_DB8500_CPUFREQ_COOLING) += db8500_cpufreq_cooling.o
obj-$(CONFIG_INTEL_POWERCLAMP) += intel_powerclamp.o
obj-$(CONFIG_X86_PKG_TEMP_THERMAL) += x86_pkg_temp_thermal.o
obj-$(CONFIG_INTEL_SOC_DTS_IOSF_CORE) += intel_soc_dts_iosf.o
+++ /dev/null
-/*
- * db8500_cpufreq_cooling.c - DB8500 cpufreq works as cooling device.
- *
- * Copyright (C) 2012 ST-Ericsson
- * Copyright (C) 2012 Linaro Ltd.
- *
- * Author: Hongbo Zhang <hongbo.zhang@linaro.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- */
-
-#include <linux/cpu_cooling.h>
-#include <linux/err.h>
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/platform_device.h>
-#include <linux/slab.h>
-
-static int db8500_cpufreq_cooling_probe(struct platform_device *pdev)
-{
- struct thermal_cooling_device *cdev;
-
- cdev = cpufreq_cooling_register(cpu_present_mask);
- if (IS_ERR(cdev)) {
- int ret = PTR_ERR(cdev);
-
- if (ret != -EPROBE_DEFER)
- dev_err(&pdev->dev,
- "Failed to register cooling device %d\n",
- ret);
-
- return ret;
- }
-
- platform_set_drvdata(pdev, cdev);
-
- dev_info(&pdev->dev, "Cooling device registered: %s\n", cdev->type);
-
- return 0;
-}
-
-static int db8500_cpufreq_cooling_remove(struct platform_device *pdev)
-{
- struct thermal_cooling_device *cdev = platform_get_drvdata(pdev);
-
- cpufreq_cooling_unregister(cdev);
-
- return 0;
-}
-
-static int db8500_cpufreq_cooling_suspend(struct platform_device *pdev,
- pm_message_t state)
-{
- return -ENOSYS;
-}
-
-static int db8500_cpufreq_cooling_resume(struct platform_device *pdev)
-{
- return -ENOSYS;
-}
-
-#ifdef CONFIG_OF
-static const struct of_device_id db8500_cpufreq_cooling_match[] = {
- { .compatible = "stericsson,db8500-cpufreq-cooling" },
- {},
-};
-MODULE_DEVICE_TABLE(of, db8500_cpufreq_cooling_match);
-#endif
-
-static struct platform_driver db8500_cpufreq_cooling_driver = {
- .driver = {
- .name = "db8500-cpufreq-cooling",
- .of_match_table = of_match_ptr(db8500_cpufreq_cooling_match),
- },
- .probe = db8500_cpufreq_cooling_probe,
- .suspend = db8500_cpufreq_cooling_suspend,
- .resume = db8500_cpufreq_cooling_resume,
- .remove = db8500_cpufreq_cooling_remove,
-};
-
-static int __init db8500_cpufreq_cooling_init(void)
-{
- return platform_driver_register(&db8500_cpufreq_cooling_driver);
-}
-
-static void __exit db8500_cpufreq_cooling_exit(void)
-{
- platform_driver_unregister(&db8500_cpufreq_cooling_driver);
-}
-
-/* Should be later than db8500_cpufreq_register */
-late_initcall(db8500_cpufreq_cooling_init);
-module_exit(db8500_cpufreq_cooling_exit);
-
-MODULE_AUTHOR("Hongbo Zhang <hongbo.zhang@stericsson.com>");
-MODULE_DESCRIPTION("DB8500 cpufreq cooling driver");
-MODULE_LICENSE("GPL");
}
/**
+ * tty_ldisc_restore - helper for tty ldisc change
+ * @tty: tty to recover
+ * @old: previous ldisc
+ *
+ * Restore the previous line discipline or N_TTY when a line discipline
+ * change fails due to an open error
+ */
+
+static void tty_ldisc_restore(struct tty_struct *tty, struct tty_ldisc *old)
+{
+ struct tty_ldisc *new_ldisc;
+ int r;
+
+ /* There is an outstanding reference here so this is safe */
+ old = tty_ldisc_get(tty, old->ops->num);
+ WARN_ON(IS_ERR(old));
+ tty->ldisc = old;
+ tty_set_termios_ldisc(tty, old->ops->num);
+ if (tty_ldisc_open(tty, old) < 0) {
+ tty_ldisc_put(old);
+ /* This driver is always present */
+ new_ldisc = tty_ldisc_get(tty, N_TTY);
+ if (IS_ERR(new_ldisc))
+ panic("n_tty: get");
+ tty->ldisc = new_ldisc;
+ tty_set_termios_ldisc(tty, N_TTY);
+ r = tty_ldisc_open(tty, new_ldisc);
+ if (r < 0)
+ panic("Couldn't open N_TTY ldisc for "
+ "%s --- error %d.",
+ tty_name(tty), r);
+ }
+}
+
+/**
* tty_set_ldisc - set line discipline
* @tty: the terminal to set
* @ldisc: the line discipline
int tty_set_ldisc(struct tty_struct *tty, int disc)
{
- int retval, old_disc;
+ int retval;
+ struct tty_ldisc *old_ldisc, *new_ldisc;
+
+ new_ldisc = tty_ldisc_get(tty, disc);
+ if (IS_ERR(new_ldisc))
+ return PTR_ERR(new_ldisc);
tty_lock(tty);
retval = tty_ldisc_lock(tty, 5 * HZ);
}
/* Check the no-op case */
- old_disc = tty->ldisc->ops->num;
- if (old_disc == disc)
+ if (tty->ldisc->ops->num == disc)
goto out;
if (test_bit(TTY_HUPPED, &tty->flags)) {
goto out;
}
- retval = tty_ldisc_reinit(tty, disc);
+ old_ldisc = tty->ldisc;
+
+ /* Shutdown the old discipline. */
+ tty_ldisc_close(tty, old_ldisc);
+
+ /* Now set up the new line discipline. */
+ tty->ldisc = new_ldisc;
+ tty_set_termios_ldisc(tty, disc);
+
+ retval = tty_ldisc_open(tty, new_ldisc);
if (retval < 0) {
/* Back to the old one or N_TTY if we can't */
- if (tty_ldisc_reinit(tty, old_disc) < 0) {
- pr_err("tty: TIOCSETD failed, reinitializing N_TTY\n");
- if (tty_ldisc_reinit(tty, N_TTY) < 0) {
- /* At this point we have tty->ldisc == NULL. */
- pr_err("tty: reinitializing N_TTY failed\n");
- }
- }
+ tty_ldisc_put(new_ldisc);
+ tty_ldisc_restore(tty, old_ldisc);
}
- if (tty->ldisc && tty->ldisc->ops->num != old_disc &&
- tty->ops->set_ldisc) {
+ if (tty->ldisc->ops->num != old_ldisc->ops->num && tty->ops->set_ldisc) {
down_read(&tty->termios_rwsem);
tty->ops->set_ldisc(tty);
up_read(&tty->termios_rwsem);
}
+ /* At this point we hold a reference to the new ldisc and a
+ reference to the old ldisc, or we hold two references to
+ the old ldisc (if it was restored as part of error cleanup
+ above). In either case, releasing a single reference from
+ the old ldisc is correct. */
+ new_ldisc = old_ldisc;
out:
tty_ldisc_unlock(tty);
already running */
tty_buffer_restart_work(tty->port);
err:
+ tty_ldisc_put(new_ldisc); /* drop the extra reference */
tty_unlock(tty);
return retval;
}
int retval;
ld = tty_ldisc_get(tty, disc);
- if (IS_ERR(ld))
+ if (IS_ERR(ld)) {
+ BUG_ON(disc == N_TTY);
return PTR_ERR(ld);
+ }
if (tty->ldisc) {
tty_ldisc_close(tty, tty->ldisc);
tty_set_termios_ldisc(tty, disc);
retval = tty_ldisc_open(tty, tty->ldisc);
if (retval) {
- tty_ldisc_put(tty->ldisc);
- tty->ldisc = NULL;
+ if (!WARN_ON(disc == N_TTY)) {
+ tty_ldisc_put(tty->ldisc);
+ tty->ldisc = NULL;
+ }
}
return retval;
}
usb_ep_free_request(fu->ep_in, fu->bot_req_in);
usb_ep_free_request(fu->ep_out, fu->bot_req_out);
usb_ep_free_request(fu->ep_out, fu->cmd.req);
- usb_ep_free_request(fu->ep_out, fu->bot_status.req);
+ usb_ep_free_request(fu->ep_in, fu->bot_status.req);
kfree(fu->cmd.buf);
}
/*
- * If the GPIO is configured as input, change the direction to output
- * and set the GPIO as active.
+ * If the GPIO is not known to be already configured as output, that
+ * is, if gpiod_get_direction returns either GPIOF_DIR_IN or -EINVAL,
+ * change the direction to output and set the GPIO as active.
* Do not force the GPIO to active when it was already output as it
* could cause backlight flickering or we would enable the backlight too
* early. Leave the decision of the initial backlight state for later.
*/
if (pb->enable_gpio &&
- gpiod_get_direction(pb->enable_gpio) == GPIOF_DIR_IN)
+ gpiod_get_direction(pb->enable_gpio) != GPIOF_DIR_OUT)
gpiod_direction_output(pb->enable_gpio, 1);
pb->power_supply = devm_regulator_get(&pdev->dev, "power");
#include <linux/efi.h>
#include <linux/errno.h>
#include <linux/fb.h>
+#include <linux/pci.h>
#include <linux/platform_device.h>
#include <linux/screen_info.h>
#include <video/vga.h>
};
ATTRIBUTE_GROUPS(efifb);
+static bool pci_dev_disabled; /* FB base matches BAR of a disabled device */
+
static int efifb_probe(struct platform_device *dev)
{
struct fb_info *info;
unsigned int size_total;
char *option = NULL;
- if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI)
+ if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI || pci_dev_disabled)
return -ENODEV;
if (fb_get_options("efifb", &option))
};
builtin_platform_driver(efifb_driver);
+
+#if defined(CONFIG_PCI) && !defined(CONFIG_X86)
+
+static bool pci_bar_found; /* did we find a BAR matching the efifb base? */
+
+static void claim_efifb_bar(struct pci_dev *dev, int idx)
+{
+ u16 word;
+
+ pci_bar_found = true;
+
+ pci_read_config_word(dev, PCI_COMMAND, &word);
+ if (!(word & PCI_COMMAND_MEMORY)) {
+ pci_dev_disabled = true;
+ dev_err(&dev->dev,
+ "BAR %d: assigned to efifb but device is disabled!\n",
+ idx);
+ return;
+ }
+
+ if (pci_claim_resource(dev, idx)) {
+ pci_dev_disabled = true;
+ dev_err(&dev->dev,
+ "BAR %d: failed to claim resource for efifb!\n", idx);
+ return;
+ }
+
+ dev_info(&dev->dev, "BAR %d: assigned to efifb\n", idx);
+}
+
+static void efifb_fixup_resources(struct pci_dev *dev)
+{
+ u64 base = screen_info.lfb_base;
+ u64 size = screen_info.lfb_size;
+ int i;
+
+ if (pci_bar_found || screen_info.orig_video_isVGA != VIDEO_TYPE_EFI)
+ return;
+
+ if (screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE)
+ base |= (u64)screen_info.ext_lfb_base << 32;
+
+ if (!base)
+ return;
+
+ for (i = 0; i < PCI_STD_RESOURCE_END; i++) {
+ struct resource *res = &dev->resource[i];
+
+ if (!(res->flags & IORESOURCE_MEM))
+ continue;
+
+ if (res->start <= base && res->end >= base + size - 1) {
+ claim_efifb_bar(dev, i);
+ break;
+ }
+ }
+}
+DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_ANY_ID, PCI_ANY_ID, PCI_BASE_CLASS_DISPLAY,
+ 16, efifb_fixup_resources);
+
+#endif
return 0;
}
-static void check_required_callbacks(struct omapfb_device *fbdev)
-{
-#define _C(x) (fbdev->ctrl->x != NULL)
-#define _P(x) (fbdev->panel->x != NULL)
- BUG_ON(fbdev->ctrl == NULL || fbdev->panel == NULL);
- BUG_ON(!(_C(init) && _C(cleanup) && _C(get_caps) &&
- _C(set_update_mode) && _C(setup_plane) && _C(enable_plane) &&
- _P(init) && _P(cleanup) && _P(enable) && _P(disable) &&
- _P(get_caps)));
-#undef _P
-#undef _C
-}
-
/*
* Called by LDM binding to probe and attach a new device.
* Initialization sequence:
omapfb_ops.fb_mmap = omapfb_mmap;
init_state++;
- check_required_callbacks(fbdev);
-
r = planes_init(fbdev);
if (r)
goto cleanup;
par->vbat_reg = devm_regulator_get_optional(&client->dev, "vbat");
if (IS_ERR(par->vbat_reg)) {
- dev_err(&client->dev, "failed to get VBAT regulator: %ld\n",
- PTR_ERR(par->vbat_reg));
ret = PTR_ERR(par->vbat_reg);
- goto fb_alloc_error;
+ if (ret == -ENODEV) {
+ par->vbat_reg = NULL;
+ } else {
+ dev_err(&client->dev, "failed to get VBAT regulator: %d\n",
+ ret);
+ goto fb_alloc_error;
+ }
}
if (of_property_read_u32(node, "solomon,width", &par->width))
udelay(4);
}
- ret = regulator_enable(par->vbat_reg);
- if (ret) {
- dev_err(&client->dev, "failed to enable VBAT: %d\n", ret);
- goto reset_oled_error;
+ if (par->vbat_reg) {
+ ret = regulator_enable(par->vbat_reg);
+ if (ret) {
+ dev_err(&client->dev, "failed to enable VBAT: %d\n",
+ ret);
+ goto reset_oled_error;
+ }
}
ret = ssd1307fb_init(par);
pwm_put(par->pwm);
};
regulator_enable_error:
- regulator_disable(par->vbat_reg);
+ if (par->vbat_reg)
+ regulator_disable(par->vbat_reg);
reset_oled_error:
fb_deferred_io_cleanup(info);
fb_alloc_error:
break;
case XenbusStateInitWait:
-InitWait:
xenbus_switch_state(dev, XenbusStateConnected);
break;
* get Connected twice here.
*/
if (dev->state != XenbusStateConnected)
- goto InitWait; /* no InitWait seen yet, fudge it */
+ /* no InitWait seen yet, fudge it */
+ xenbus_switch_state(dev, XenbusStateConnected);
if (xenbus_read_unsigned(info->xbdev->otherend,
"request-update", 0))
if (device_features & (1ULL << i))
__virtio_set_bit(dev, i);
+ if (drv->validate) {
+ err = drv->validate(dev);
+ if (err)
+ goto err;
+ }
+
err = virtio_finalize_features(dev);
if (err)
goto err;
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
int i;
- synchronize_irq(pci_irq_vector(vp_dev->pci_dev, 0));
- for (i = 1; i < vp_dev->msix_vectors; i++)
+ if (vp_dev->intx_enabled)
+ synchronize_irq(vp_dev->pci_dev->irq);
+
+ for (i = 0; i < vp_dev->msix_vectors; ++i)
synchronize_irq(pci_irq_vector(vp_dev->pci_dev, i));
}
static irqreturn_t vp_vring_interrupt(int irq, void *opaque)
{
struct virtio_pci_device *vp_dev = opaque;
+ struct virtio_pci_vq_info *info;
irqreturn_t ret = IRQ_NONE;
- struct virtqueue *vq;
+ unsigned long flags;
- list_for_each_entry(vq, &vp_dev->vdev.vqs, list) {
- if (vq->callback && vring_interrupt(irq, vq) == IRQ_HANDLED)
+ spin_lock_irqsave(&vp_dev->lock, flags);
+ list_for_each_entry(info, &vp_dev->virtqueues, node) {
+ if (vring_interrupt(irq, info->vq) == IRQ_HANDLED)
ret = IRQ_HANDLED;
}
+ spin_unlock_irqrestore(&vp_dev->lock, flags);
return ret;
}
return vp_vring_interrupt(irq, opaque);
}
-static void vp_remove_vqs(struct virtio_device *vdev)
+static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors,
+ bool per_vq_vectors, struct irq_affinity *desc)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
- struct virtqueue *vq, *n;
+ const char *name = dev_name(&vp_dev->vdev.dev);
+ unsigned i, v;
+ int err = -ENOMEM;
- list_for_each_entry_safe(vq, n, &vdev->vqs, list) {
- if (vp_dev->msix_vector_map) {
- int v = vp_dev->msix_vector_map[vq->index];
+ vp_dev->msix_vectors = nvectors;
- if (v != VIRTIO_MSI_NO_VECTOR)
- free_irq(pci_irq_vector(vp_dev->pci_dev, v),
- vq);
- }
- vp_dev->del_vq(vq);
+ vp_dev->msix_names = kmalloc(nvectors * sizeof *vp_dev->msix_names,
+ GFP_KERNEL);
+ if (!vp_dev->msix_names)
+ goto error;
+ vp_dev->msix_affinity_masks
+ = kzalloc(nvectors * sizeof *vp_dev->msix_affinity_masks,
+ GFP_KERNEL);
+ if (!vp_dev->msix_affinity_masks)
+ goto error;
+ for (i = 0; i < nvectors; ++i)
+ if (!alloc_cpumask_var(&vp_dev->msix_affinity_masks[i],
+ GFP_KERNEL))
+ goto error;
+
+ err = pci_alloc_irq_vectors_affinity(vp_dev->pci_dev, nvectors,
+ nvectors, PCI_IRQ_MSIX |
+ (desc ? PCI_IRQ_AFFINITY : 0),
+ desc);
+ if (err < 0)
+ goto error;
+ vp_dev->msix_enabled = 1;
+
+ /* Set the vector used for configuration */
+ v = vp_dev->msix_used_vectors;
+ snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names,
+ "%s-config", name);
+ err = request_irq(pci_irq_vector(vp_dev->pci_dev, v),
+ vp_config_changed, 0, vp_dev->msix_names[v],
+ vp_dev);
+ if (err)
+ goto error;
+ ++vp_dev->msix_used_vectors;
+
+ v = vp_dev->config_vector(vp_dev, v);
+ /* Verify we had enough resources to assign the vector */
+ if (v == VIRTIO_MSI_NO_VECTOR) {
+ err = -EBUSY;
+ goto error;
}
+
+ if (!per_vq_vectors) {
+ /* Shared vector for all VQs */
+ v = vp_dev->msix_used_vectors;
+ snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names,
+ "%s-virtqueues", name);
+ err = request_irq(pci_irq_vector(vp_dev->pci_dev, v),
+ vp_vring_interrupt, 0, vp_dev->msix_names[v],
+ vp_dev);
+ if (err)
+ goto error;
+ ++vp_dev->msix_used_vectors;
+ }
+ return 0;
+error:
+ return err;
+}
+
+static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned index,
+ void (*callback)(struct virtqueue *vq),
+ const char *name,
+ u16 msix_vec)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ struct virtio_pci_vq_info *info = kmalloc(sizeof *info, GFP_KERNEL);
+ struct virtqueue *vq;
+ unsigned long flags;
+
+ /* fill out our structure that represents an active queue */
+ if (!info)
+ return ERR_PTR(-ENOMEM);
+
+ vq = vp_dev->setup_vq(vp_dev, info, index, callback, name,
+ msix_vec);
+ if (IS_ERR(vq))
+ goto out_info;
+
+ info->vq = vq;
+ if (callback) {
+ spin_lock_irqsave(&vp_dev->lock, flags);
+ list_add(&info->node, &vp_dev->virtqueues);
+ spin_unlock_irqrestore(&vp_dev->lock, flags);
+ } else {
+ INIT_LIST_HEAD(&info->node);
+ }
+
+ vp_dev->vqs[index] = info;
+ return vq;
+
+out_info:
+ kfree(info);
+ return vq;
+}
+
+static void vp_del_vq(struct virtqueue *vq)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
+ struct virtio_pci_vq_info *info = vp_dev->vqs[vq->index];
+ unsigned long flags;
+
+ spin_lock_irqsave(&vp_dev->lock, flags);
+ list_del(&info->node);
+ spin_unlock_irqrestore(&vp_dev->lock, flags);
+
+ vp_dev->del_vq(info);
+ kfree(info);
}
/* the config->del_vqs() implementation */
void vp_del_vqs(struct virtio_device *vdev)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ struct virtqueue *vq, *n;
int i;
- if (WARN_ON_ONCE(list_empty_careful(&vdev->vqs)))
- return;
+ list_for_each_entry_safe(vq, n, &vdev->vqs, list) {
+ if (vp_dev->per_vq_vectors) {
+ int v = vp_dev->vqs[vq->index]->msix_vector;
- vp_remove_vqs(vdev);
+ if (v != VIRTIO_MSI_NO_VECTOR) {
+ int irq = pci_irq_vector(vp_dev->pci_dev, v);
+
+ irq_set_affinity_hint(irq, NULL);
+ free_irq(irq, vq);
+ }
+ }
+ vp_del_vq(vq);
+ }
+ vp_dev->per_vq_vectors = false;
+
+ if (vp_dev->intx_enabled) {
+ free_irq(vp_dev->pci_dev->irq, vp_dev);
+ vp_dev->intx_enabled = 0;
+ }
- if (vp_dev->pci_dev->msix_enabled) {
- for (i = 0; i < vp_dev->msix_vectors; i++)
+ for (i = 0; i < vp_dev->msix_used_vectors; ++i)
+ free_irq(pci_irq_vector(vp_dev->pci_dev, i), vp_dev);
+
+ for (i = 0; i < vp_dev->msix_vectors; i++)
+ if (vp_dev->msix_affinity_masks[i])
free_cpumask_var(vp_dev->msix_affinity_masks[i]);
+ if (vp_dev->msix_enabled) {
/* Disable the vector used for configuration */
vp_dev->config_vector(vp_dev, VIRTIO_MSI_NO_VECTOR);
- kfree(vp_dev->msix_affinity_masks);
- kfree(vp_dev->msix_names);
- kfree(vp_dev->msix_vector_map);
+ pci_free_irq_vectors(vp_dev->pci_dev);
+ vp_dev->msix_enabled = 0;
}
- free_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_dev);
- pci_free_irq_vectors(vp_dev->pci_dev);
+ vp_dev->msix_vectors = 0;
+ vp_dev->msix_used_vectors = 0;
+ kfree(vp_dev->msix_names);
+ vp_dev->msix_names = NULL;
+ kfree(vp_dev->msix_affinity_masks);
+ vp_dev->msix_affinity_masks = NULL;
+ kfree(vp_dev->vqs);
+ vp_dev->vqs = NULL;
}
static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs,
struct virtqueue *vqs[], vq_callback_t *callbacks[],
- const char * const names[], struct irq_affinity *desc)
+ const char * const names[], bool per_vq_vectors,
+ struct irq_affinity *desc)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
- const char *name = dev_name(&vp_dev->vdev.dev);
- int i, j, err = -ENOMEM, allocated_vectors, nvectors;
- unsigned flags = PCI_IRQ_MSIX;
- bool shared = false;
u16 msix_vec;
+ int i, err, nvectors, allocated_vectors;
- if (desc) {
- flags |= PCI_IRQ_AFFINITY;
- desc->pre_vectors++; /* virtio config vector */
- }
-
- nvectors = 1;
- for (i = 0; i < nvqs; i++)
- if (callbacks[i])
- nvectors++;
-
- /* Try one vector per queue first. */
- err = pci_alloc_irq_vectors_affinity(vp_dev->pci_dev, nvectors,
- nvectors, flags, desc);
- if (err < 0) {
- /* Fallback to one vector for config, one shared for queues. */
- shared = true;
- err = pci_alloc_irq_vectors(vp_dev->pci_dev, 2, 2,
- PCI_IRQ_MSIX);
- if (err < 0)
- return err;
- }
- if (err < 0)
- return err;
-
- vp_dev->msix_vectors = nvectors;
- vp_dev->msix_names = kmalloc_array(nvectors,
- sizeof(*vp_dev->msix_names), GFP_KERNEL);
- if (!vp_dev->msix_names)
- goto out_free_irq_vectors;
-
- vp_dev->msix_affinity_masks = kcalloc(nvectors,
- sizeof(*vp_dev->msix_affinity_masks), GFP_KERNEL);
- if (!vp_dev->msix_affinity_masks)
- goto out_free_msix_names;
+ vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL);
+ if (!vp_dev->vqs)
+ return -ENOMEM;
- for (i = 0; i < nvectors; ++i) {
- if (!alloc_cpumask_var(&vp_dev->msix_affinity_masks[i],
- GFP_KERNEL))
- goto out_free_msix_affinity_masks;
+ if (per_vq_vectors) {
+ /* Best option: one for change interrupt, one per vq. */
+ nvectors = 1;
+ for (i = 0; i < nvqs; ++i)
+ if (callbacks[i])
+ ++nvectors;
+ } else {
+ /* Second best: one for change, shared for all vqs. */
+ nvectors = 2;
}
- /* Set the vector used for configuration */
- snprintf(vp_dev->msix_names[0], sizeof(*vp_dev->msix_names),
- "%s-config", name);
- err = request_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_config_changed,
- 0, vp_dev->msix_names[0], vp_dev);
+ err = vp_request_msix_vectors(vdev, nvectors, per_vq_vectors,
+ per_vq_vectors ? desc : NULL);
if (err)
- goto out_free_msix_affinity_masks;
+ goto error_find;
- /* Verify we had enough resources to assign the vector */
- if (vp_dev->config_vector(vp_dev, 0) == VIRTIO_MSI_NO_VECTOR) {
- err = -EBUSY;
- goto out_free_config_irq;
- }
-
- vp_dev->msix_vector_map = kmalloc_array(nvqs,
- sizeof(*vp_dev->msix_vector_map), GFP_KERNEL);
- if (!vp_dev->msix_vector_map)
- goto out_disable_config_irq;
-
- allocated_vectors = j = 1; /* vector 0 is the config interrupt */
+ vp_dev->per_vq_vectors = per_vq_vectors;
+ allocated_vectors = vp_dev->msix_used_vectors;
for (i = 0; i < nvqs; ++i) {
if (!names[i]) {
vqs[i] = NULL;
continue;
}
- if (callbacks[i])
- msix_vec = allocated_vectors;
- else
+ if (!callbacks[i])
msix_vec = VIRTIO_MSI_NO_VECTOR;
-
- vqs[i] = vp_dev->setup_vq(vp_dev, i, callbacks[i], names[i],
- msix_vec);
+ else if (vp_dev->per_vq_vectors)
+ msix_vec = allocated_vectors++;
+ else
+ msix_vec = VP_MSIX_VQ_VECTOR;
+ vqs[i] = vp_setup_vq(vdev, i, callbacks[i], names[i],
+ msix_vec);
if (IS_ERR(vqs[i])) {
err = PTR_ERR(vqs[i]);
- goto out_remove_vqs;
+ goto error_find;
}
- if (msix_vec == VIRTIO_MSI_NO_VECTOR) {
- vp_dev->msix_vector_map[i] = VIRTIO_MSI_NO_VECTOR;
+ if (!vp_dev->per_vq_vectors || msix_vec == VIRTIO_MSI_NO_VECTOR)
continue;
- }
- snprintf(vp_dev->msix_names[j],
- sizeof(*vp_dev->msix_names), "%s-%s",
+ /* allocate per-vq irq if available and necessary */
+ snprintf(vp_dev->msix_names[msix_vec],
+ sizeof *vp_dev->msix_names,
+ "%s-%s",
dev_name(&vp_dev->vdev.dev), names[i]);
err = request_irq(pci_irq_vector(vp_dev->pci_dev, msix_vec),
- vring_interrupt, IRQF_SHARED,
- vp_dev->msix_names[j], vqs[i]);
- if (err) {
- /* don't free this irq on error */
- vp_dev->msix_vector_map[i] = VIRTIO_MSI_NO_VECTOR;
- goto out_remove_vqs;
- }
- vp_dev->msix_vector_map[i] = msix_vec;
- j++;
-
- /*
- * Use a different vector for each queue if they are available,
- * else share the same vector for all VQs.
- */
- if (!shared)
- allocated_vectors++;
+ vring_interrupt, 0,
+ vp_dev->msix_names[msix_vec],
+ vqs[i]);
+ if (err)
+ goto error_find;
}
-
return 0;
-out_remove_vqs:
- vp_remove_vqs(vdev);
- kfree(vp_dev->msix_vector_map);
-out_disable_config_irq:
- vp_dev->config_vector(vp_dev, VIRTIO_MSI_NO_VECTOR);
-out_free_config_irq:
- free_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_dev);
-out_free_msix_affinity_masks:
- for (i = 0; i < nvectors; i++) {
- if (vp_dev->msix_affinity_masks[i])
- free_cpumask_var(vp_dev->msix_affinity_masks[i]);
- }
- kfree(vp_dev->msix_affinity_masks);
-out_free_msix_names:
- kfree(vp_dev->msix_names);
-out_free_irq_vectors:
- pci_free_irq_vectors(vp_dev->pci_dev);
+error_find:
+ vp_del_vqs(vdev);
return err;
}
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
int i, err;
+ vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL);
+ if (!vp_dev->vqs)
+ return -ENOMEM;
+
err = request_irq(vp_dev->pci_dev->irq, vp_interrupt, IRQF_SHARED,
dev_name(&vdev->dev), vp_dev);
if (err)
- return err;
+ goto out_del_vqs;
+ vp_dev->intx_enabled = 1;
+ vp_dev->per_vq_vectors = false;
for (i = 0; i < nvqs; ++i) {
if (!names[i]) {
vqs[i] = NULL;
continue;
}
- vqs[i] = vp_dev->setup_vq(vp_dev, i, callbacks[i], names[i],
- VIRTIO_MSI_NO_VECTOR);
+ vqs[i] = vp_setup_vq(vdev, i, callbacks[i], names[i],
+ VIRTIO_MSI_NO_VECTOR);
if (IS_ERR(vqs[i])) {
err = PTR_ERR(vqs[i]);
- goto out_remove_vqs;
+ goto out_del_vqs;
}
}
return 0;
-
-out_remove_vqs:
- vp_remove_vqs(vdev);
- free_irq(pci_irq_vector(vp_dev->pci_dev, 0), vp_dev);
+out_del_vqs:
+ vp_del_vqs(vdev);
return err;
}
{
int err;
- err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, desc);
+ /* Try MSI-X with one vector per queue. */
+ err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, true, desc);
if (!err)
return 0;
+ /* Fallback: MSI-X with one vector for config, one shared for queues. */
+ err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, false, desc);
+ if (!err)
+ return 0;
+ /* Finally fall back to regular interrupts. */
return vp_find_vqs_intx(vdev, nvqs, vqs, callbacks, names);
}
{
struct virtio_device *vdev = vq->vdev;
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ struct virtio_pci_vq_info *info = vp_dev->vqs[vq->index];
+ struct cpumask *mask;
+ unsigned int irq;
if (!vq->callback)
return -EINVAL;
- if (vp_dev->pci_dev->msix_enabled) {
- int vec = vp_dev->msix_vector_map[vq->index];
- struct cpumask *mask = vp_dev->msix_affinity_masks[vec];
- unsigned int irq = pci_irq_vector(vp_dev->pci_dev, vec);
-
+ if (vp_dev->msix_enabled) {
+ mask = vp_dev->msix_affinity_masks[info->msix_vector];
+ irq = pci_irq_vector(vp_dev->pci_dev, info->msix_vector);
if (cpu == -1)
irq_set_affinity_hint(irq, NULL);
else {
const struct cpumask *vp_get_vq_affinity(struct virtio_device *vdev, int index)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
- unsigned int *map = vp_dev->msix_vector_map;
- if (!map || map[index] == VIRTIO_MSI_NO_VECTOR)
+ if (!vp_dev->per_vq_vectors ||
+ vp_dev->vqs[index]->msix_vector == VIRTIO_MSI_NO_VECTOR)
return NULL;
- return pci_irq_get_affinity(vp_dev->pci_dev, map[index]);
+ return pci_irq_get_affinity(vp_dev->pci_dev,
+ vp_dev->vqs[index]->msix_vector);
}
#ifdef CONFIG_PM_SLEEP
vp_dev->vdev.dev.parent = &pci_dev->dev;
vp_dev->vdev.dev.release = virtio_pci_release_dev;
vp_dev->pci_dev = pci_dev;
+ INIT_LIST_HEAD(&vp_dev->virtqueues);
+ spin_lock_init(&vp_dev->lock);
/* enable the device */
rc = pci_enable_device(pci_dev);
#include <linux/highmem.h>
#include <linux/spinlock.h>
+struct virtio_pci_vq_info {
+ /* the actual virtqueue */
+ struct virtqueue *vq;
+
+ /* the list node for the virtqueues list */
+ struct list_head node;
+
+ /* MSI-X vector (or none) */
+ unsigned msix_vector;
+};
+
/* Our device structure */
struct virtio_pci_device {
struct virtio_device vdev;
/* the IO mapping for the PCI config space */
void __iomem *ioaddr;
+ /* a list of queues so we can dispatch IRQs */
+ spinlock_t lock;
+ struct list_head virtqueues;
+
+ /* array of all queues for house-keeping */
+ struct virtio_pci_vq_info **vqs;
+
+ /* MSI-X support */
+ int msix_enabled;
+ int intx_enabled;
cpumask_var_t *msix_affinity_masks;
/* Name strings for interrupts. This size should be enough,
* and I'm too lazy to allocate each name separately. */
char (*msix_names)[256];
- /* Total Number of MSI-X vectors (including per-VQ ones). */
- int msix_vectors;
- /* Map of per-VQ MSI-X vectors, may be NULL */
- unsigned *msix_vector_map;
+ /* Number of available vectors */
+ unsigned msix_vectors;
+ /* Vectors allocated, excluding per-vq vectors if any */
+ unsigned msix_used_vectors;
+
+ /* Whether we have vector per vq */
+ bool per_vq_vectors;
struct virtqueue *(*setup_vq)(struct virtio_pci_device *vp_dev,
+ struct virtio_pci_vq_info *info,
unsigned idx,
void (*callback)(struct virtqueue *vq),
const char *name,
u16 msix_vec);
- void (*del_vq)(struct virtqueue *vq);
+ void (*del_vq)(struct virtio_pci_vq_info *info);
u16 (*config_vector)(struct virtio_pci_device *vp_dev, u16 vector);
};
+/* Constants for MSI-X */
+/* Use first vector for configuration changes, second and the rest for
+ * virtqueues Thus, we need at least 2 vectors for MSI. */
+enum {
+ VP_MSIX_CONFIG_VECTOR = 0,
+ VP_MSIX_VQ_VECTOR = 1,
+};
+
/* Convert a generic virtio device to our structure */
static struct virtio_pci_device *to_vp_device(struct virtio_device *vdev)
{
}
static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
+ struct virtio_pci_vq_info *info,
unsigned index,
void (*callback)(struct virtqueue *vq),
const char *name,
if (!num || ioread32(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN))
return ERR_PTR(-ENOENT);
+ info->msix_vector = msix_vec;
+
/* create the vring */
vq = vring_create_virtqueue(index, num,
VIRTIO_PCI_VRING_ALIGN, &vp_dev->vdev,
return ERR_PTR(err);
}
-static void del_vq(struct virtqueue *vq)
+static void del_vq(struct virtio_pci_vq_info *info)
{
+ struct virtqueue *vq = info->vq;
struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
iowrite16(vq->index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
- if (vp_dev->pci_dev->msix_enabled) {
+ if (vp_dev->msix_enabled) {
iowrite16(VIRTIO_MSI_NO_VECTOR,
vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
/* Flush the write out to device */
}
static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
+ struct virtio_pci_vq_info *info,
unsigned index,
void (*callback)(struct virtqueue *vq),
const char *name,
/* get offset of notification word for this vq */
off = vp_ioread16(&cfg->queue_notify_off);
+ info->msix_vector = msix_vec;
+
/* create the vring */
vq = vring_create_virtqueue(index, num,
SMP_CACHE_BYTES, &vp_dev->vdev,
return 0;
}
-static void del_vq(struct virtqueue *vq)
+static void del_vq(struct virtio_pci_vq_info *info)
{
+ struct virtqueue *vq = info->vq;
struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
vp_iowrite16(vq->index, &vp_dev->common->queue_select);
- if (vp_dev->pci_dev->msix_enabled) {
+ if (vp_dev->msix_enabled) {
vp_iowrite16(VIRTIO_MSI_NO_VECTOR,
&vp_dev->common->queue_msix_vector);
/* Flush the write out to device */
return xenbus_command_reply(u, XS_ERROR, "ENOENT");
rc = xenbus_dev_request_and_reply(&u->u.msg, u);
- if (rc)
+ if (rc && trans) {
+ list_del(&trans->list);
kfree(trans);
+ }
out:
return rc;
goto err_names;
init_rwsem(&v9ses->rename_sem);
- rc = bdi_setup_and_register(&v9ses->bdi, "9p");
- if (rc)
- goto err_names;
-
v9ses->uid = INVALID_UID;
v9ses->dfltuid = V9FS_DEFUID;
v9ses->dfltgid = V9FS_DEFGID;
if (IS_ERR(v9ses->clnt)) {
rc = PTR_ERR(v9ses->clnt);
p9_debug(P9_DEBUG_ERROR, "problem initializing 9p client\n");
- goto err_bdi;
+ goto err_names;
}
v9ses->flags = V9FS_ACCESS_USER;
err_clnt:
p9_client_destroy(v9ses->clnt);
-err_bdi:
- bdi_destroy(&v9ses->bdi);
err_names:
kfree(v9ses->uname);
kfree(v9ses->aname);
kfree(v9ses->uname);
kfree(v9ses->aname);
- bdi_destroy(&v9ses->bdi);
-
spin_lock(&v9fs_sessionlist_lock);
list_del(&v9ses->slist);
spin_unlock(&v9fs_sessionlist_lock);
kuid_t uid; /* if ACCESS_SINGLE, the uid that has access */
struct p9_client *clnt; /* 9p client */
struct list_head slist; /* list of sessions registered with v9fs */
- struct backing_dev_info bdi;
struct rw_semaphore rename_sem;
};
*
*/
-static void
+static int
v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses,
int flags, void *data)
{
+ int ret;
+
sb->s_maxbytes = MAX_LFS_FILESIZE;
sb->s_blocksize_bits = fls(v9ses->maxdata - 1);
sb->s_blocksize = 1 << sb->s_blocksize_bits;
sb->s_xattr = v9fs_xattr_handlers;
} else
sb->s_op = &v9fs_super_ops;
- sb->s_bdi = &v9ses->bdi;
+
+ ret = super_setup_bdi(sb);
+ if (ret)
+ return ret;
+
if (v9ses->cache)
sb->s_bdi->ra_pages = (VM_MAX_READAHEAD * 1024)/PAGE_SIZE;
#endif
save_mount_options(sb, data);
+ return 0;
}
/**
retval = PTR_ERR(sb);
goto clunk_fid;
}
- v9fs_fill_super(sb, v9ses, flags, data);
+ retval = v9fs_fill_super(sb, v9ses, flags, data);
+ if (retval)
+ goto release_sb;
if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
sb->s_d_op = &v9fs_cached_dentry_operations;
unsigned short rjservers; /* number of servers discarded due to -ENOMEDIUM */
struct afs_server *servers[8]; /* servers on which volume resides (ordered) */
struct rw_semaphore server_sem; /* lock for accessing current server */
- struct backing_dev_info bdi;
};
/*
sb->s_blocksize_bits = PAGE_SHIFT;
sb->s_magic = AFS_FS_MAGIC;
sb->s_op = &afs_super_ops;
- sb->s_bdi = &as->volume->bdi;
+ ret = super_setup_bdi(sb);
+ if (ret)
+ return ret;
+ sb->s_bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_SIZE;
strlcpy(sb->s_id, as->volume->vlocation->vldb.name, sizeof(sb->s_id));
/* allocate the root inode and dentry */
volume->cell = params->cell;
volume->vid = vlocation->vldb.vid[params->type];
- volume->bdi.ra_pages = VM_MAX_READAHEAD*1024/PAGE_SIZE;
- ret = bdi_setup_and_register(&volume->bdi, "afs");
- if (ret)
- goto error_bdi;
-
init_rwsem(&volume->server_sem);
/* look up all the applicable server records */
return ERR_PTR(ret);
error_discard:
- bdi_destroy(&volume->bdi);
-error_bdi:
up_write(¶ms->cell->vl_sem);
for (loop = volume->nservers - 1; loop >= 0; loop--)
for (loop = volume->nservers - 1; loop >= 0; loop--)
afs_put_server(volume->servers[loop]);
- bdi_destroy(&volume->bdi);
kfree(volume);
_leave(" [destroyed]");
spin_lock(&bdev_lock);
list_del_init(&bdev->bd_list);
spin_unlock(&bdev_lock);
+ /* Detach inode from wb early as bdi_put() may free bdi->wb */
+ inode_detach_wb(inode);
if (bdev->bd_bdi != &noop_backing_dev_info) {
bdi_put(bdev->bd_bdi);
bdev->bd_bdi = &noop_backing_dev_info;
if (disk->fops->revalidate_disk)
ret = disk->fops->revalidate_disk(disk);
- blk_integrity_revalidate(disk);
bdev = bdget_disk(disk, 0);
if (!bdev)
return ret;
bdev->bd_disk = disk;
bdev->bd_queue = disk->queue;
bdev->bd_contains = bdev;
- if (bdev->bd_bdi == &noop_backing_dev_info)
- bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info);
if (!partno) {
ret = -ENXIO;
}
bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
}
+
+ if (bdev->bd_bdi == &noop_backing_dev_info)
+ bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info);
} else {
if (bdev->bd_contains == bdev) {
ret = 0;
bdev->bd_disk = NULL;
bdev->bd_part = NULL;
bdev->bd_queue = NULL;
- bdi_put(bdev->bd_bdi);
- bdev->bd_bdi = &noop_backing_dev_info;
if (bdev != bdev->bd_contains)
__blkdev_put(bdev->bd_contains, mode, 1);
bdev->bd_contains = NULL;
kill_bdev(bdev);
bdev_write_inode(bdev);
- /*
- * Detaching bdev inode from its wb in __destroy_inode()
- * is too late: the queue which embeds its bdi (along with
- * root wb) can be gone as soon as we put_disk() below.
- */
- inode_detach_wb(bdev->bd_inode);
}
if (bdev->bd_contains == bdev) {
if (disk->fops->release)
loff_t len)
{
struct block_device *bdev = I_BDEV(bdev_file_inode(file));
- struct request_queue *q = bdev_get_queue(bdev);
struct address_space *mapping;
loff_t end = start + len - 1;
loff_t isize;
case FALLOC_FL_ZERO_RANGE:
case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE:
error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
- GFP_KERNEL, false);
+ GFP_KERNEL, BLKDEV_ZERO_NOUNMAP);
break;
case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE:
- /* Only punch if the device can do zeroing discard. */
- if (!blk_queue_discard(q) || !q->limits.discard_zeroes_data)
- return -EOPNOTSUPP;
- error = blkdev_issue_discard(bdev, start >> 9, len >> 9,
- GFP_KERNEL, 0);
+ error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
+ GFP_KERNEL, BLKDEV_ZERO_NOFALLBACK);
break;
case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE:
- if (!blk_queue_discard(q))
- return -EOPNOTSUPP;
error = blkdev_issue_discard(bdev, start >> 9, len >> 9,
GFP_KERNEL, 0);
break;
struct btrfs_super_block *super_for_commit;
struct super_block *sb;
struct inode *btree_inode;
- struct backing_dev_info bdi;
struct mutex tree_log_mutex;
struct mutex transaction_kthread_mutex;
struct mutex cleaner_mutex;
return ret;
}
-static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi)
-{
- int err;
-
- err = bdi_setup_and_register(bdi, "btrfs");
- if (err)
- return err;
-
- bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_SIZE;
- bdi->congested_fn = btrfs_congested_fn;
- bdi->congested_data = info;
- bdi->capabilities |= BDI_CAP_CGROUP_WRITEBACK;
- return 0;
-}
-
/*
* called by the kthread helper functions to finally call the bio end_io
* functions. This is where read checksum verification actually happens
goto fail;
}
- ret = setup_bdi(fs_info, &fs_info->bdi);
- if (ret) {
- err = ret;
- goto fail_srcu;
- }
-
ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0, GFP_KERNEL);
if (ret) {
err = ret;
- goto fail_bdi;
+ goto fail_srcu;
}
fs_info->dirty_metadata_batch = PAGE_SIZE *
(1 + ilog2(nr_cpu_ids));
sb->s_blocksize = 4096;
sb->s_blocksize_bits = blksize_bits(4096);
- sb->s_bdi = &fs_info->bdi;
btrfs_init_btree_inode(fs_info);
goto fail_sb_buffer;
}
- fs_info->bdi.ra_pages *= btrfs_super_num_devices(disk_super);
- fs_info->bdi.ra_pages = max(fs_info->bdi.ra_pages,
- SZ_4M / PAGE_SIZE);
+ sb->s_bdi->congested_fn = btrfs_congested_fn;
+ sb->s_bdi->congested_data = fs_info;
+ sb->s_bdi->capabilities |= BDI_CAP_CGROUP_WRITEBACK;
+ sb->s_bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_SIZE;
+ sb->s_bdi->ra_pages *= btrfs_super_num_devices(disk_super);
+ sb->s_bdi->ra_pages = max(sb->s_bdi->ra_pages, SZ_4M / PAGE_SIZE);
sb->s_blocksize = sectorsize;
sb->s_blocksize_bits = blksize_bits(sectorsize);
percpu_counter_destroy(&fs_info->delalloc_bytes);
fail_dirty_metadata_bytes:
percpu_counter_destroy(&fs_info->dirty_metadata_bytes);
-fail_bdi:
- bdi_destroy(&fs_info->bdi);
fail_srcu:
cleanup_srcu_struct(&fs_info->subvol_srcu);
fail:
percpu_counter_destroy(&fs_info->dirty_metadata_bytes);
percpu_counter_destroy(&fs_info->delalloc_bytes);
percpu_counter_destroy(&fs_info->bio_counter);
- bdi_destroy(&fs_info->bdi);
cleanup_srcu_struct(&fs_info->subvol_srcu);
btrfs_free_stripe_hash_table(fs_info);
static void btrfs_retry_endio_nocsum(struct bio *bio)
{
struct btrfs_retry_complete *done = bio->bi_private;
- struct inode *inode;
struct bio_vec *bvec;
int i;
goto end;
ASSERT(bio->bi_vcnt == 1);
- inode = bio->bi_io_vec->bv_page->mapping->host;
- ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(inode));
+ ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(done->inode));
done->uptodate = 1;
bio_for_each_segment_all(bvec, bio, i)
- clean_io_failure(BTRFS_I(done->inode), done->start, bvec->bv_page, 0);
+ clean_io_failure(BTRFS_I(done->inode), done->start,
+ bvec->bv_page, 0);
end:
complete(&done->done);
bio_put(bio);
start += sectorsize;
- if (nr_sectors--) {
+ nr_sectors--;
+ if (nr_sectors) {
pgoff += sectorsize;
+ ASSERT(pgoff < PAGE_SIZE);
goto next_block_or_try_again;
}
}
{
struct btrfs_retry_complete *done = bio->bi_private;
struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
- struct inode *inode;
struct bio_vec *bvec;
- u64 start;
int uptodate;
int ret;
int i;
uptodate = 1;
- start = done->start;
-
ASSERT(bio->bi_vcnt == 1);
- inode = bio->bi_io_vec->bv_page->mapping->host;
- ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(inode));
+ ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(done->inode));
bio_for_each_segment_all(bvec, bio, i) {
ret = __readpage_endio_check(done->inode, io_bio, i,
ASSERT(nr_sectors);
- if (--nr_sectors) {
+ nr_sectors--;
+ if (nr_sectors) {
pgoff += sectorsize;
+ ASSERT(pgoff < PAGE_SIZE);
goto next_block;
}
}
struct btrfs_qgroup *qgroup,
u64 num_bytes)
{
- btrfs_warn(fs_info,
+#ifdef CONFIG_BTRFS_DEBUG
+ WARN_ON(qgroup->reserved < num_bytes);
+ btrfs_debug(fs_info,
"qgroup %llu reserved space underflow, have: %llu, to free: %llu",
qgroup->qgroupid, qgroup->reserved, num_bytes);
+#endif
qgroup->reserved = 0;
}
/*
qgroup->excl += sign * num_bytes;
qgroup->excl_cmpr += sign * num_bytes;
if (sign > 0) {
- if (WARN_ON(qgroup->reserved < num_bytes))
+ if (qgroup->reserved < num_bytes)
report_reserved_underflow(fs_info, qgroup, num_bytes);
else
qgroup->reserved -= num_bytes;
WARN_ON(sign < 0 && qgroup->excl < num_bytes);
qgroup->excl += sign * num_bytes;
if (sign > 0) {
- if (WARN_ON(qgroup->reserved < num_bytes))
+ if (qgroup->reserved < num_bytes)
report_reserved_underflow(fs_info, qgroup,
num_bytes);
else
qg = unode_aux_to_qgroup(unode);
- if (WARN_ON(qg->reserved < num_bytes))
+ if (qg->reserved < num_bytes)
report_reserved_underflow(fs_info, qg, num_bytes);
else
qg->reserved -= num_bytes;
case Opt_ssd:
btrfs_set_and_info(info, SSD,
"use ssd allocation scheme");
+ btrfs_clear_opt(info->mount_opt, NOSSD);
break;
case Opt_ssd_spread:
btrfs_set_and_info(info, SSD_SPREAD,
"use spread ssd allocation scheme");
btrfs_set_opt(info->mount_opt, SSD);
+ btrfs_clear_opt(info->mount_opt, NOSSD);
break;
case Opt_nossd:
btrfs_set_and_info(info, NOSSD,
"not using ssd allocation scheme");
btrfs_clear_opt(info->mount_opt, SSD);
+ btrfs_clear_opt(info->mount_opt, SSD_SPREAD);
break;
case Opt_barrier:
btrfs_clear_and_info(info, NOBARRIER,
#endif
sb->s_flags |= MS_I_VERSION;
sb->s_iflags |= SB_I_CGROUPWB;
+
+ err = super_setup_bdi(sb);
+ if (err) {
+ btrfs_err(fs_info, "super_setup_bdi failed");
+ return err;
+ }
+
err = open_ctree(sb, fs_devices, (char *)data);
if (err) {
btrfs_err(fs_info, "open_ctree failed");
for (dev_nr = 0; dev_nr < total_devs; dev_nr++) {
dev = bbio->stripes[dev_nr].dev;
if (!dev || !dev->bdev ||
- (bio_op(bio) == REQ_OP_WRITE && !dev->writeable)) {
+ (bio_op(first_bio) == REQ_OP_WRITE && !dev->writeable)) {
bbio_error(bbio, first_bio, logical);
continue;
}
writeback_stat = atomic_long_inc_return(&fsc->writeback_count);
if (writeback_stat >
CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))
- set_bdi_congested(&fsc->backing_dev_info, BLK_RW_ASYNC);
+ set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
set_page_writeback(page);
err = ceph_osdc_writepages(osdc, ceph_vino(inode),
if (atomic_long_dec_return(&fsc->writeback_count) <
CONGESTION_OFF_THRESH(
fsc->mount_options->congestion_kb))
- clear_bdi_congested(&fsc->backing_dev_info,
+ clear_bdi_congested(inode_to_bdi(inode),
BLK_RW_ASYNC);
if (rc < 0)
if (atomic_long_inc_return(&fsc->writeback_count) >
CONGESTION_ON_THRESH(
fsc->mount_options->congestion_kb)) {
- set_bdi_congested(&fsc->backing_dev_info,
+ set_bdi_congested(inode_to_bdi(inode),
BLK_RW_ASYNC);
}
goto out;
snprintf(name, sizeof(name), "../../bdi/%s",
- dev_name(fsc->backing_dev_info.dev));
+ dev_name(fsc->sb->s_bdi->dev));
fsc->debugfs_bdi =
debugfs_create_symlink("bdi",
fsc->client->debugfs_dir,
if (inode_dirty_flags)
__mark_inode_dirty(inode, inode_dirty_flags);
- if (ia_valid & ATTR_MODE) {
- err = posix_acl_chmod(inode, attr->ia_mode);
- if (err)
- goto out_put;
- }
if (mask) {
req->r_inode = inode;
ceph_cap_string(dirtied), mask);
ceph_mdsc_put_request(req);
- if (mask & CEPH_SETATTR_SIZE)
- __ceph_do_pending_vmtruncate(inode);
- ceph_free_cap_flush(prealloc_cf);
- return err;
-out_put:
- ceph_mdsc_put_request(req);
ceph_free_cap_flush(prealloc_cf);
+
+ if (err >= 0 && (mask & CEPH_SETATTR_SIZE))
+ __ceph_do_pending_vmtruncate(inode);
+
return err;
}
if (err != 0)
return err;
- return __ceph_setattr(inode, attr);
+ err = __ceph_setattr(inode, attr);
+
+ if (err >= 0 && (attr->ia_valid & ATTR_MODE))
+ err = posix_acl_chmod(inode, attr->ia_mode);
+
+ return err;
}
/*
atomic_long_set(&fsc->writeback_count, 0);
- err = bdi_init(&fsc->backing_dev_info);
- if (err < 0)
- goto fail_client;
-
err = -ENOMEM;
/*
* The number of concurrent works can be high but they don't need
*/
fsc->wb_wq = alloc_workqueue("ceph-writeback", 0, 1);
if (fsc->wb_wq == NULL)
- goto fail_bdi;
+ goto fail_client;
fsc->pg_inv_wq = alloc_workqueue("ceph-pg-invalid", 0, 1);
if (fsc->pg_inv_wq == NULL)
goto fail_wb_wq;
destroy_workqueue(fsc->pg_inv_wq);
fail_wb_wq:
destroy_workqueue(fsc->wb_wq);
-fail_bdi:
- bdi_destroy(&fsc->backing_dev_info);
fail_client:
ceph_destroy_client(fsc->client);
fail:
destroy_workqueue(fsc->pg_inv_wq);
destroy_workqueue(fsc->trunc_wq);
- bdi_destroy(&fsc->backing_dev_info);
-
mempool_destroy(fsc->wb_pagevec_pool);
destroy_mount_options(fsc->mount_options);
*/
static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
-static int ceph_register_bdi(struct super_block *sb,
- struct ceph_fs_client *fsc)
+static int ceph_setup_bdi(struct super_block *sb, struct ceph_fs_client *fsc)
{
int err;
+ err = super_setup_bdi_name(sb, "ceph-%ld",
+ atomic_long_inc_return(&bdi_seq));
+ if (err)
+ return err;
+
/* set ra_pages based on rasize mount option? */
if (fsc->mount_options->rasize >= PAGE_SIZE)
- fsc->backing_dev_info.ra_pages =
+ sb->s_bdi->ra_pages =
(fsc->mount_options->rasize + PAGE_SIZE - 1)
>> PAGE_SHIFT;
else
- fsc->backing_dev_info.ra_pages =
- VM_MAX_READAHEAD * 1024 / PAGE_SIZE;
+ sb->s_bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_SIZE;
if (fsc->mount_options->rsize > fsc->mount_options->rasize &&
fsc->mount_options->rsize >= PAGE_SIZE)
- fsc->backing_dev_info.io_pages =
+ sb->s_bdi->io_pages =
(fsc->mount_options->rsize + PAGE_SIZE - 1)
>> PAGE_SHIFT;
else if (fsc->mount_options->rsize == 0)
- fsc->backing_dev_info.io_pages = ULONG_MAX;
+ sb->s_bdi->io_pages = ULONG_MAX;
- err = bdi_register(&fsc->backing_dev_info, NULL, "ceph-%ld",
- atomic_long_inc_return(&bdi_seq));
- if (!err)
- sb->s_bdi = &fsc->backing_dev_info;
- return err;
+ return 0;
}
static struct dentry *ceph_mount(struct file_system_type *fs_type,
dout("get_sb got existing client %p\n", fsc);
} else {
dout("get_sb using new client %p\n", fsc);
- err = ceph_register_bdi(sb, fsc);
+ err = ceph_setup_bdi(sb, fsc);
if (err < 0) {
res = ERR_PTR(err);
goto out_splat;
struct workqueue_struct *trunc_wq;
atomic_long_t writeback_count;
- struct backing_dev_info backing_dev_info;
-
#ifdef CONFIG_DEBUG_FS
struct dentry *debugfs_dentry_lru, *debugfs_caps;
struct dentry *debugfs_congestion_kb;
umode_t mnt_dir_mode;
unsigned int mnt_cifs_flags;
char *mountdata; /* options received at mount time or via DFS refs */
- struct backing_dev_info bdi;
struct delayed_work prune_tlinks;
struct rcu_head rcu;
char *prepath;
sb->s_magic = CIFS_MAGIC_NUMBER;
sb->s_op = &cifs_super_ops;
sb->s_xattr = cifs_xattr_handlers;
- sb->s_bdi = &cifs_sb->bdi;
+ rc = super_setup_bdi(sb);
+ if (rc)
+ goto out_no_root;
+ /* tune readahead according to rsize */
+ sb->s_bdi->ra_pages = cifs_sb->rsize / PAGE_SIZE;
+
sb->s_blocksize = CIFS_MAX_MSGSIZE;
sb->s_blocksize_bits = 14; /* default 2**14 = CIFS_MAX_MSGSIZE */
inode = cifs_root_iget(sb);
return rc;
}
+ssize_t cifs_file_copychunk_range(unsigned int xid,
+ struct file *src_file, loff_t off,
+ struct file *dst_file, loff_t destoff,
+ size_t len, unsigned int flags)
+{
+ struct inode *src_inode = file_inode(src_file);
+ struct inode *target_inode = file_inode(dst_file);
+ struct cifsFileInfo *smb_file_src;
+ struct cifsFileInfo *smb_file_target;
+ struct cifs_tcon *src_tcon;
+ struct cifs_tcon *target_tcon;
+ ssize_t rc;
+
+ cifs_dbg(FYI, "copychunk range\n");
+
+ if (src_inode == target_inode) {
+ rc = -EINVAL;
+ goto out;
+ }
+
+ if (!src_file->private_data || !dst_file->private_data) {
+ rc = -EBADF;
+ cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n");
+ goto out;
+ }
+
+ rc = -EXDEV;
+ smb_file_target = dst_file->private_data;
+ smb_file_src = src_file->private_data;
+ src_tcon = tlink_tcon(smb_file_src->tlink);
+ target_tcon = tlink_tcon(smb_file_target->tlink);
+
+ if (src_tcon->ses != target_tcon->ses) {
+ cifs_dbg(VFS, "source and target of copy not on same server\n");
+ goto out;
+ }
+
+ /*
+ * Note: cifs case is easier than btrfs since server responsible for
+ * checks for proper open modes and file type and if it wants
+ * server could even support copy of range where source = target
+ */
+ lock_two_nondirectories(target_inode, src_inode);
+
+ cifs_dbg(FYI, "about to flush pages\n");
+ /* should we flush first and last page first */
+ truncate_inode_pages(&target_inode->i_data, 0);
+
+ if (target_tcon->ses->server->ops->copychunk_range)
+ rc = target_tcon->ses->server->ops->copychunk_range(xid,
+ smb_file_src, smb_file_target, off, len, destoff);
+ else
+ rc = -EOPNOTSUPP;
+
+ /* force revalidate of size and timestamps of target file now
+ * that target is updated on the server
+ */
+ CIFS_I(target_inode)->time = 0;
+ /* although unlocking in the reverse order from locking is not
+ * strictly necessary here it is a little cleaner to be consistent
+ */
+ unlock_two_nondirectories(src_inode, target_inode);
+
+out:
+ return rc;
+}
+
+static ssize_t cifs_copy_file_range(struct file *src_file, loff_t off,
+ struct file *dst_file, loff_t destoff,
+ size_t len, unsigned int flags)
+{
+ unsigned int xid = get_xid();
+ ssize_t rc;
+
+ rc = cifs_file_copychunk_range(xid, src_file, off, dst_file, destoff,
+ len, flags);
+ free_xid(xid);
+ return rc;
+}
+
const struct file_operations cifs_file_ops = {
.read_iter = cifs_loose_read_iter,
.write_iter = cifs_file_write_iter,
.splice_read = generic_file_splice_read,
.llseek = cifs_llseek,
.unlocked_ioctl = cifs_ioctl,
+ .copy_file_range = cifs_copy_file_range,
.clone_file_range = cifs_clone_file_range,
.setlease = cifs_setlease,
.fallocate = cifs_fallocate,
.splice_read = generic_file_splice_read,
.llseek = cifs_llseek,
.unlocked_ioctl = cifs_ioctl,
+ .copy_file_range = cifs_copy_file_range,
.clone_file_range = cifs_clone_file_range,
.setlease = cifs_setlease,
.fallocate = cifs_fallocate,
.mmap = cifs_file_mmap,
.splice_read = generic_file_splice_read,
.unlocked_ioctl = cifs_ioctl,
+ .copy_file_range = cifs_copy_file_range,
.clone_file_range = cifs_clone_file_range,
.llseek = cifs_llseek,
.setlease = cifs_setlease,
.splice_read = generic_file_splice_read,
.llseek = cifs_llseek,
.unlocked_ioctl = cifs_ioctl,
+ .copy_file_range = cifs_copy_file_range,
.clone_file_range = cifs_clone_file_range,
.setlease = cifs_setlease,
.fallocate = cifs_fallocate,
.splice_read = generic_file_splice_read,
.llseek = cifs_llseek,
.unlocked_ioctl = cifs_ioctl,
+ .copy_file_range = cifs_copy_file_range,
.clone_file_range = cifs_clone_file_range,
.setlease = cifs_setlease,
.fallocate = cifs_fallocate,
.mmap = cifs_file_mmap,
.splice_read = generic_file_splice_read,
.unlocked_ioctl = cifs_ioctl,
+ .copy_file_range = cifs_copy_file_range,
.clone_file_range = cifs_clone_file_range,
.llseek = cifs_llseek,
.setlease = cifs_setlease,
.release = cifs_closedir,
.read = generic_read_dir,
.unlocked_ioctl = cifs_ioctl,
+ .copy_file_range = cifs_copy_file_range,
.clone_file_range = cifs_clone_file_range,
.llseek = generic_file_llseek,
};
# define cifs_listxattr NULL
#endif
+extern ssize_t cifs_file_copychunk_range(unsigned int xid,
+ struct file *src_file, loff_t off,
+ struct file *dst_file, loff_t destoff,
+ size_t len, unsigned int flags);
+
extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
#ifdef CONFIG_CIFS_NFSD_EXPORT
extern const struct export_operations cifs_export_ops;
/* verify the message */
int (*check_message)(char *, unsigned int, struct TCP_Server_Info *);
bool (*is_oplock_break)(char *, struct TCP_Server_Info *);
+ int (*handle_cancelled_mid)(char *, struct TCP_Server_Info *);
void (*downgrade_oplock)(struct TCP_Server_Info *,
struct cifsInodeInfo *, bool);
/* process transaction2 response */
char * (*create_lease_buf)(u8 *, u8);
/* parse lease context buffer and return oplock/epoch info */
__u8 (*parse_lease_buf)(void *, unsigned int *);
- int (*clone_range)(const unsigned int, struct cifsFileInfo *src_file,
- struct cifsFileInfo *target_file, u64 src_off, u64 len,
- u64 dest_off);
+ ssize_t (*copychunk_range)(const unsigned int,
+ struct cifsFileInfo *src_file,
+ struct cifsFileInfo *target_file,
+ u64 src_off, u64 len, u64 dest_off);
int (*duplicate_extents)(const unsigned int, struct cifsFileInfo *src,
struct cifsFileInfo *target_file, u64 src_off, u64 len,
u64 dest_off);
bool use_persistent:1; /* use persistent instead of durable handles */
#ifdef CONFIG_CIFS_SMB2
bool print:1; /* set if connection to printer share */
- bool bad_network_name:1; /* set if ret status STATUS_BAD_NETWORK_NAME */
__le32 capabilities;
__u32 share_flags;
__u32 maximal_access;
void *callback_data; /* general purpose pointer for callback */
void *resp_buf; /* pointer to received SMB header */
int mid_state; /* wish this were enum but can not pass to wait_event */
+ unsigned int mid_flags;
__le16 command; /* smb command code */
bool large_buf:1; /* if valid response, is pointer to large buf */
bool multiRsp:1; /* multiple trans2 responses for one request */
bool decrypted:1; /* decrypted entry */
};
+struct close_cancelled_open {
+ struct cifs_fid fid;
+ struct cifs_tcon *tcon;
+ struct work_struct work;
+};
+
/* Make code in transport.c a little cleaner by moving
update of optional stats into function below */
#ifdef CONFIG_CIFS_STATS2
#define MID_RESPONSE_MALFORMED 0x10
#define MID_SHUTDOWN 0x20
+/* Flags */
+#define MID_WAIT_CANCELLED 1 /* Cancelled while waiting for response */
+
/* Types of response buffer returned from SendReceive2 */
#define CIFS_NO_BUFFER 0 /* Response buffer not returned */
#define CIFS_SMALL_BUFFER 1
length = cifs_discard_remaining_data(server);
dequeue_mid(mid, rdata->result);
+ mid->resp_buf = server->smallbuf;
+ server->smallbuf = NULL;
return length;
}
return cifs_readv_discard(server, mid);
dequeue_mid(mid, false);
+ mid->resp_buf = server->smallbuf;
+ server->smallbuf = NULL;
return length;
}
server->lstrp = jiffies;
if (mid_entry != NULL) {
+ if ((mid_entry->mid_flags & MID_WAIT_CANCELLED) &&
+ mid_entry->mid_state == MID_RESPONSE_RECEIVED &&
+ server->ops->handle_cancelled_mid)
+ server->ops->handle_cancelled_mid(
+ mid_entry->resp_buf,
+ server);
+
if (!mid_entry->multiRsp || mid_entry->multiEnd)
mid_entry->callback(mid_entry);
- } else if (!server->ops->is_oplock_break ||
- !server->ops->is_oplock_break(buf, server)) {
+ } else if (server->ops->is_oplock_break &&
+ server->ops->is_oplock_break(buf, server)) {
+ cifs_dbg(FYI, "Received oplock break\n");
+ } else {
cifs_dbg(VFS, "No task to wake, unknown frame received! NumMids %d\n",
atomic_read(&midCount));
cifs_dump_mem("Received Data is: ", buf,
int referral_walks_count = 0;
#endif
- rc = bdi_setup_and_register(&cifs_sb->bdi, "cifs");
- if (rc)
- return rc;
-
#ifdef CONFIG_CIFS_DFS_UPCALL
try_mount_again:
/* cleanup activities if we're chasing a referral */
server = cifs_get_tcp_session(volume_info);
if (IS_ERR(server)) {
rc = PTR_ERR(server);
- bdi_destroy(&cifs_sb->bdi);
goto out;
}
if ((volume_info->max_credits < 20) ||
if (IS_ERR(tcon)) {
rc = PTR_ERR(tcon);
tcon = NULL;
+ if (rc == -EACCES)
+ goto mount_fail_check;
+
goto remote_path_check;
}
cifs_sb->wsize = server->ops->negotiate_wsize(tcon, volume_info);
cifs_sb->rsize = server->ops->negotiate_rsize(tcon, volume_info);
- /* tune readahead according to rsize */
- cifs_sb->bdi.ra_pages = cifs_sb->rsize / PAGE_SIZE;
-
remote_path_check:
#ifdef CONFIG_CIFS_DFS_UPCALL
/*
cifs_put_smb_ses(ses);
else
cifs_put_tcp_session(server, 0);
- bdi_destroy(&cifs_sb->bdi);
}
out:
}
spin_unlock(&cifs_sb->tlink_tree_lock);
- bdi_destroy(&cifs_sb->bdi);
kfree(cifs_sb->mountdata);
kfree(cifs_sb->prepath);
call_rcu(&cifs_sb->rcu, delayed_free);
wdata->credits = credits;
if (!wdata->cfile->invalidHandle ||
- !cifs_reopen_file(wdata->cfile, false))
+ !(rc = cifs_reopen_file(wdata->cfile, false)))
rc = server->ops->async_writev(wdata,
cifs_uncached_writedata_release);
if (rc) {
rdata->credits = credits;
if (!rdata->cfile->invalidHandle ||
- !cifs_reopen_file(rdata->cfile, true))
+ !(rc = cifs_reopen_file(rdata->cfile, true)))
rc = server->ops->async_readv(rdata);
error:
if (rc) {
}
if (!rdata->cfile->invalidHandle ||
- !cifs_reopen_file(rdata->cfile, true))
+ !(rc = cifs_reopen_file(rdata->cfile, true)))
rc = server->ops->async_readv(rdata);
if (rc) {
add_credits_and_wake_if(server, rdata->credits, 0);
#include "cifs_ioctl.h"
#include <linux/btrfs.h>
-static int cifs_file_clone_range(unsigned int xid, struct file *src_file,
- struct file *dst_file)
-{
- struct inode *src_inode = file_inode(src_file);
- struct inode *target_inode = file_inode(dst_file);
- struct cifsFileInfo *smb_file_src;
- struct cifsFileInfo *smb_file_target;
- struct cifs_tcon *src_tcon;
- struct cifs_tcon *target_tcon;
- int rc;
-
- cifs_dbg(FYI, "ioctl clone range\n");
-
- if (!src_file->private_data || !dst_file->private_data) {
- rc = -EBADF;
- cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n");
- goto out;
- }
-
- rc = -EXDEV;
- smb_file_target = dst_file->private_data;
- smb_file_src = src_file->private_data;
- src_tcon = tlink_tcon(smb_file_src->tlink);
- target_tcon = tlink_tcon(smb_file_target->tlink);
-
- if (src_tcon->ses != target_tcon->ses) {
- cifs_dbg(VFS, "source and target of copy not on same server\n");
- goto out;
- }
-
- /*
- * Note: cifs case is easier than btrfs since server responsible for
- * checks for proper open modes and file type and if it wants
- * server could even support copy of range where source = target
- */
- lock_two_nondirectories(target_inode, src_inode);
-
- cifs_dbg(FYI, "about to flush pages\n");
- /* should we flush first and last page first */
- truncate_inode_pages(&target_inode->i_data, 0);
-
- if (target_tcon->ses->server->ops->clone_range)
- rc = target_tcon->ses->server->ops->clone_range(xid,
- smb_file_src, smb_file_target, 0, src_inode->i_size, 0);
- else
- rc = -EOPNOTSUPP;
-
- /* force revalidate of size and timestamps of target file now
- that target is updated on the server */
- CIFS_I(target_inode)->time = 0;
- /* although unlocking in the reverse order from locking is not
- strictly necessary here it is a little cleaner to be consistent */
- unlock_two_nondirectories(src_inode, target_inode);
-out:
- return rc;
-}
-
-static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file,
+static long cifs_ioctl_copychunk(unsigned int xid, struct file *dst_file,
unsigned long srcfd)
{
int rc;
struct fd src_file;
struct inode *src_inode;
- cifs_dbg(FYI, "ioctl clone range\n");
+ cifs_dbg(FYI, "ioctl copychunk range\n");
/* the destination must be opened for writing */
if (!(dst_file->f_mode & FMODE_WRITE)) {
cifs_dbg(FYI, "file target not open for write\n");
if (S_ISDIR(src_inode->i_mode))
goto out_fput;
- rc = cifs_file_clone_range(xid, src_file.file, dst_file);
+ rc = cifs_file_copychunk_range(xid, src_file.file, 0, dst_file, 0,
+ src_inode->i_size, 0);
out_fput:
fdput(src_file);
}
break;
case CIFS_IOC_COPYCHUNK_FILE:
- rc = cifs_ioctl_clone(xid, filep, arg);
+ rc = cifs_ioctl_copychunk(xid, filep, arg);
break;
case CIFS_IOC_SET_INTEGRITY:
if (pSMBFile == NULL)
return !cfile->srch_inf.endOfSearch && !cfile->invalidHandle;
}
+static bool
+cifs_can_echo(struct TCP_Server_Info *server)
+{
+ if (server->tcpStatus == CifsGood)
+ return true;
+
+ return false;
+}
+
struct smb_version_operations smb1_operations = {
.send_cancel = send_nt_cancel,
.compare_fids = cifs_compare_fids,
.get_dfs_refer = CIFSGetDFSRefer,
.qfs_tcon = cifs_qfs_tcon,
.is_path_accessible = cifs_is_path_accessible,
+ .can_echo = cifs_can_echo,
.query_path_info = cifs_query_path_info,
.query_file_info = cifs_query_file_info,
.get_srv_inum = cifs_get_srv_inum,
cifs_dbg(FYI, "Can not process oplock break for non-existent connection\n");
return false;
}
+
+void
+smb2_cancelled_close_fid(struct work_struct *work)
+{
+ struct close_cancelled_open *cancelled = container_of(work,
+ struct close_cancelled_open, work);
+
+ cifs_dbg(VFS, "Close unmatched open\n");
+
+ SMB2_close(0, cancelled->tcon, cancelled->fid.persistent_fid,
+ cancelled->fid.volatile_fid);
+ cifs_put_tcon(cancelled->tcon);
+ kfree(cancelled);
+}
+
+int
+smb2_handle_cancelled_mid(char *buffer, struct TCP_Server_Info *server)
+{
+ struct smb2_sync_hdr *sync_hdr = get_sync_hdr(buffer);
+ struct smb2_create_rsp *rsp = (struct smb2_create_rsp *)buffer;
+ struct cifs_tcon *tcon;
+ struct close_cancelled_open *cancelled;
+
+ if (sync_hdr->Command != SMB2_CREATE ||
+ sync_hdr->Status != STATUS_SUCCESS)
+ return 0;
+
+ cancelled = kzalloc(sizeof(*cancelled), GFP_KERNEL);
+ if (!cancelled)
+ return -ENOMEM;
+
+ tcon = smb2_find_smb_tcon(server, sync_hdr->SessionId,
+ sync_hdr->TreeId);
+ if (!tcon) {
+ kfree(cancelled);
+ return -ENOENT;
+ }
+
+ cancelled->fid.persistent_fid = rsp->PersistentFileId;
+ cancelled->fid.volatile_fid = rsp->VolatileFileId;
+ cancelled->tcon = tcon;
+ INIT_WORK(&cancelled->work, smb2_cancelled_close_fid);
+ queue_work(cifsiod_wq, &cancelled->work);
+
+ return 0;
+}
#include <linux/vfs.h>
#include <linux/falloc.h>
#include <linux/scatterlist.h>
+#include <linux/uuid.h>
#include <crypto/aead.h>
#include "cifsglob.h"
#include "smb2pdu.h"
return rc;
}
-static int
-smb2_clone_range(const unsigned int xid,
+static ssize_t
+smb2_copychunk_range(const unsigned int xid,
struct cifsFileInfo *srcfile,
struct cifsFileInfo *trgtfile, u64 src_off,
u64 len, u64 dest_off)
struct cifs_tcon *tcon;
int chunks_copied = 0;
bool chunk_sizes_updated = false;
+ ssize_t bytes_written, total_bytes_written = 0;
pcchunk = kmalloc(sizeof(struct copychunk_ioctl), GFP_KERNEL);
if (pcchunk == NULL)
return -ENOMEM;
- cifs_dbg(FYI, "in smb2_clone_range - about to call request res key\n");
+ cifs_dbg(FYI, "in smb2_copychunk_range - about to call request res key\n");
/* Request a key from the server to identify the source of the copy */
rc = SMB2_request_res_key(xid, tlink_tcon(srcfile->tlink),
srcfile->fid.persistent_fid,
}
chunks_copied++;
- src_off += le32_to_cpu(retbuf->TotalBytesWritten);
- dest_off += le32_to_cpu(retbuf->TotalBytesWritten);
- len -= le32_to_cpu(retbuf->TotalBytesWritten);
+ bytes_written = le32_to_cpu(retbuf->TotalBytesWritten);
+ src_off += bytes_written;
+ dest_off += bytes_written;
+ len -= bytes_written;
+ total_bytes_written += bytes_written;
- cifs_dbg(FYI, "Chunks %d PartialChunk %d Total %d\n",
+ cifs_dbg(FYI, "Chunks %d PartialChunk %d Total %zu\n",
le32_to_cpu(retbuf->ChunksWritten),
le32_to_cpu(retbuf->ChunkBytesWritten),
- le32_to_cpu(retbuf->TotalBytesWritten));
+ bytes_written);
} else if (rc == -EINVAL) {
if (ret_data_len != sizeof(struct copychunk_ioctl_rsp))
goto cchunk_out;
cchunk_out:
kfree(pcchunk);
kfree(retbuf);
- return rc;
+ if (rc)
+ return rc;
+ else
+ return total_bytes_written;
}
static int
.clear_stats = smb2_clear_stats,
.print_stats = smb2_print_stats,
.is_oplock_break = smb2_is_valid_oplock_break,
+ .handle_cancelled_mid = smb2_handle_cancelled_mid,
.downgrade_oplock = smb2_downgrade_oplock,
.need_neg = smb2_need_neg,
.negotiate = smb2_negotiate,
.set_oplock_level = smb2_set_oplock_level,
.create_lease_buf = smb2_create_lease_buf,
.parse_lease_buf = smb2_parse_lease_buf,
- .clone_range = smb2_clone_range,
+ .copychunk_range = smb2_copychunk_range,
.wp_retry_size = smb2_wp_retry_size,
.dir_needs_close = smb2_dir_needs_close,
.get_dfs_refer = smb2_get_dfs_refer,
.clear_stats = smb2_clear_stats,
.print_stats = smb2_print_stats,
.is_oplock_break = smb2_is_valid_oplock_break,
+ .handle_cancelled_mid = smb2_handle_cancelled_mid,
.downgrade_oplock = smb2_downgrade_oplock,
.need_neg = smb2_need_neg,
.negotiate = smb2_negotiate,
.set_oplock_level = smb21_set_oplock_level,
.create_lease_buf = smb2_create_lease_buf,
.parse_lease_buf = smb2_parse_lease_buf,
- .clone_range = smb2_clone_range,
+ .copychunk_range = smb2_copychunk_range,
.wp_retry_size = smb2_wp_retry_size,
.dir_needs_close = smb2_dir_needs_close,
.enum_snapshots = smb3_enum_snapshots,
.print_stats = smb2_print_stats,
.dump_share_caps = smb2_dump_share_caps,
.is_oplock_break = smb2_is_valid_oplock_break,
+ .handle_cancelled_mid = smb2_handle_cancelled_mid,
.downgrade_oplock = smb2_downgrade_oplock,
.need_neg = smb2_need_neg,
.negotiate = smb2_negotiate,
.set_oplock_level = smb3_set_oplock_level,
.create_lease_buf = smb3_create_lease_buf,
.parse_lease_buf = smb3_parse_lease_buf,
- .clone_range = smb2_clone_range,
+ .copychunk_range = smb2_copychunk_range,
.duplicate_extents = smb2_duplicate_extents,
.validate_negotiate = smb3_validate_negotiate,
.wp_retry_size = smb2_wp_retry_size,
.print_stats = smb2_print_stats,
.dump_share_caps = smb2_dump_share_caps,
.is_oplock_break = smb2_is_valid_oplock_break,
+ .handle_cancelled_mid = smb2_handle_cancelled_mid,
.downgrade_oplock = smb2_downgrade_oplock,
.need_neg = smb2_need_neg,
.negotiate = smb2_negotiate,
.set_oplock_level = smb3_set_oplock_level,
.create_lease_buf = smb3_create_lease_buf,
.parse_lease_buf = smb3_parse_lease_buf,
- .clone_range = smb2_clone_range,
+ .copychunk_range = smb2_copychunk_range,
.duplicate_extents = smb2_duplicate_extents,
/* .validate_negotiate = smb3_validate_negotiate, */ /* not used in 3.11 */
.wp_retry_size = smb2_wp_retry_size,
* but for time being this is our only auth choice so doesn't matter.
* We just found a server which sets blob length to zero expecting raw.
*/
- if (blob_length == 0)
+ if (blob_length == 0) {
cifs_dbg(FYI, "missing security blob on negprot\n");
+ server->sec_ntlmssp = true;
+ }
rc = cifs_enable_signing(server, ses->sign);
if (rc)
else
return -EIO;
- if (tcon && tcon->bad_network_name)
- return -ENOENT;
-
unc_path = kmalloc(MAX_SHARENAME_LENGTH * 2, GFP_KERNEL);
if (unc_path == NULL)
return -ENOMEM;
return -EINVAL;
}
+ /* SMB2 TREE_CONNECT request must be called with TreeId == 0 */
+ if (tcon)
+ tcon->tid = 0;
+
rc = small_smb2_init(SMB2_TREE_CONNECT, tcon, (void **) &req);
if (rc) {
kfree(unc_path);
tcon_error_exit:
if (rsp->hdr.sync_hdr.Status == STATUS_BAD_NETWORK_NAME) {
cifs_dbg(VFS, "BAD_NETWORK_NAME: %s\n", tree);
- if (tcon)
- tcon->bad_network_name = true;
}
goto tcon_exit;
}
struct cifs_tcon *tcon, *tcon2;
struct list_head tmp_list;
int tcon_exist = false;
+ int rc;
+ int resched = false;
+
/* Prevent simultaneous reconnects that can corrupt tcon->rlist list */
mutex_lock(&server->reconnect_mutex);
spin_unlock(&cifs_tcp_ses_lock);
list_for_each_entry_safe(tcon, tcon2, &tmp_list, rlist) {
- if (!smb2_reconnect(SMB2_INTERNAL_CMD, tcon))
+ rc = smb2_reconnect(SMB2_INTERNAL_CMD, tcon);
+ if (!rc)
cifs_reopen_persistent_handles(tcon);
+ else
+ resched = true;
list_del_init(&tcon->rlist);
cifs_put_tcon(tcon);
}
cifs_dbg(FYI, "Reconnecting tcons finished\n");
+ if (resched)
+ queue_delayed_work(cifsiod_wq, &server->reconnect, 2 * HZ);
mutex_unlock(&server->reconnect_mutex);
/* now we can safely release srv struct */
struct smb_rqst *rqst);
extern struct mid_q_entry *smb2_setup_async_request(
struct TCP_Server_Info *server, struct smb_rqst *rqst);
+extern struct cifs_ses *smb2_find_smb_ses(struct TCP_Server_Info *server,
+ __u64 ses_id);
+extern struct cifs_tcon *smb2_find_smb_tcon(struct TCP_Server_Info *server,
+ __u64 ses_id, __u32 tid);
extern int smb2_calc_signature(struct smb_rqst *rqst,
struct TCP_Server_Info *server);
extern int smb3_calc_signature(struct smb_rqst *rqst,
extern int SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon,
const u64 persistent_fid, const u64 volatile_fid,
const __u8 oplock_level);
+extern int smb2_handle_cancelled_mid(char *buffer,
+ struct TCP_Server_Info *server);
+void smb2_cancelled_close_fid(struct work_struct *work);
extern int SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
u64 persistent_file_id, u64 volatile_file_id,
struct kstatfs *FSData);
return 0;
}
-struct cifs_ses *
-smb2_find_smb_ses(struct TCP_Server_Info *server, __u64 ses_id)
+static struct cifs_ses *
+smb2_find_smb_ses_unlocked(struct TCP_Server_Info *server, __u64 ses_id)
{
struct cifs_ses *ses;
- spin_lock(&cifs_tcp_ses_lock);
list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
if (ses->Suid != ses_id)
continue;
- spin_unlock(&cifs_tcp_ses_lock);
return ses;
}
+
+ return NULL;
+}
+
+struct cifs_ses *
+smb2_find_smb_ses(struct TCP_Server_Info *server, __u64 ses_id)
+{
+ struct cifs_ses *ses;
+
+ spin_lock(&cifs_tcp_ses_lock);
+ ses = smb2_find_smb_ses_unlocked(server, ses_id);
spin_unlock(&cifs_tcp_ses_lock);
+ return ses;
+}
+
+static struct cifs_tcon *
+smb2_find_smb_sess_tcon_unlocked(struct cifs_ses *ses, __u32 tid)
+{
+ struct cifs_tcon *tcon;
+
+ list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
+ if (tcon->tid != tid)
+ continue;
+ ++tcon->tc_count;
+ return tcon;
+ }
+
return NULL;
}
+/*
+ * Obtain tcon corresponding to the tid in the given
+ * cifs_ses
+ */
+
+struct cifs_tcon *
+smb2_find_smb_tcon(struct TCP_Server_Info *server, __u64 ses_id, __u32 tid)
+{
+ struct cifs_ses *ses;
+ struct cifs_tcon *tcon;
+
+ spin_lock(&cifs_tcp_ses_lock);
+ ses = smb2_find_smb_ses_unlocked(server, ses_id);
+ if (!ses) {
+ spin_unlock(&cifs_tcp_ses_lock);
+ return NULL;
+ }
+ tcon = smb2_find_smb_sess_tcon_unlocked(ses, tid);
+ spin_unlock(&cifs_tcp_ses_lock);
+
+ return tcon;
+}
+
int
smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
{
rc = wait_for_response(ses->server, midQ);
if (rc != 0) {
+ cifs_dbg(FYI, "Cancelling wait for mid %llu\n", midQ->mid);
send_cancel(ses->server, rqst, midQ);
spin_lock(&GlobalMid_Lock);
if (midQ->mid_state == MID_REQUEST_SUBMITTED) {
+ midQ->mid_flags |= MID_WAIT_CANCELLED;
midQ->callback = DeleteMidQEntry;
spin_unlock(&GlobalMid_Lock);
add_credits(ses->server, 1, optype);
goto unlock_out;
}
- error = bdi_setup_and_register(&vc->bdi, "coda");
- if (error)
- goto unlock_out;
-
vc->vc_sb = sb;
mutex_unlock(&vc->vc_mutex);
sb->s_magic = CODA_SUPER_MAGIC;
sb->s_op = &coda_super_operations;
sb->s_d_op = &coda_dentry_operations;
- sb->s_bdi = &vc->bdi;
+
+ error = super_setup_bdi(sb);
+ if (error)
+ goto error;
/* get root fid from Venus: this needs the root inode */
error = venus_rootfid(sb, &fid);
error:
mutex_lock(&vc->vc_mutex);
- bdi_destroy(&vc->bdi);
vc->vc_sb = NULL;
sb->s_fs_info = NULL;
unlock_out:
{
struct venus_comm *vcp = coda_vcp(sb);
mutex_lock(&vcp->vc_mutex);
- bdi_destroy(&vcp->bdi);
vcp->vc_sb = NULL;
sb->s_fs_info = NULL;
mutex_unlock(&vcp->vc_mutex);
}
spin_lock_irq(&mapping->tree_lock);
+ if (!entry) {
+ /*
+ * We needed to drop the page_tree lock while calling
+ * radix_tree_preload() and we didn't have an entry to
+ * lock. See if another thread inserted an entry at
+ * our index during this time.
+ */
+ entry = __radix_tree_lookup(&mapping->page_tree, index,
+ NULL, &slot);
+ if (entry) {
+ radix_tree_preload_end();
+ spin_unlock_irq(&mapping->tree_lock);
+ goto restart;
+ }
+ }
+
if (pmd_downgrade) {
radix_tree_delete(&mapping->page_tree, index);
mapping->nrexceptional--;
if (err) {
spin_unlock_irq(&mapping->tree_lock);
/*
- * Someone already created the entry? This is a
- * normal failure when inserting PMDs in a range
- * that already contains PTEs. In that case we want
- * to return -EEXIST immediately.
- */
- if (err == -EEXIST && !(size_flag & RADIX_DAX_PMD))
- goto restart;
- /*
- * Our insertion of a DAX PMD entry failed, most
- * likely because it collided with a PTE sized entry
- * at a different index in the PMD range. We haven't
- * inserted anything into the radix tree and have no
- * waiters to wake.
+ * Our insertion of a DAX entry failed, most likely
+ * because we were inserting a PMD entry and it
+ * collided with a PTE sized entry at a different
+ * index in the PMD range. We haven't inserted
+ * anything into the radix tree and have no waiters to
+ * wake.
*/
return ERR_PTR(err);
}
sector_t start_sector = dax.sector + (offset >> 9);
return blkdev_issue_zeroout(bdev, start_sector,
- length >> 9, GFP_NOFS, true);
+ length >> 9, GFP_NOFS, 0);
} else {
if (dax_map_atomic(bdev, &dax) < 0)
return PTR_ERR(dax.addr);
struct ecryptfs_sb_info {
struct super_block *wsi_sb;
struct ecryptfs_mount_crypt_stat mount_crypt_stat;
- struct backing_dev_info bdi;
};
/* file private data. */
goto out;
}
- rc = bdi_setup_and_register(&sbi->bdi, "ecryptfs");
+ rc = super_setup_bdi(s);
if (rc)
goto out1;
ecryptfs_set_superblock_private(s, sbi);
- s->s_bdi = &sbi->bdi;
/* ->kill_sb() will take care of sbi after that point */
sbi = NULL;
if (!sb_info)
return;
ecryptfs_destroy_mount_crypt_stat(&sb_info->mount_crypt_stat);
- bdi_destroy(&sb_info->bdi);
kmem_cache_free(ecryptfs_sb_info_cache, sb_info);
}
else
set_dumpable(current->mm, suid_dumpable);
+ arch_setup_new_exec();
perf_event_exec();
__set_task_comm(current, kbasename(bprm->filename), true);
* our extension to the in-memory superblock
*/
struct exofs_sb_info {
- struct backing_dev_info bdi; /* register our bdi with VFS */
struct exofs_sb_stats s_ess; /* Written often, pre-allocate*/
int s_timeout; /* timeout for OSD operations */
uint64_t s_nextid; /* highest object ID used */
sbi->one_comp.obj.partition);
exofs_sysfs_sb_del(sbi);
- bdi_destroy(&sbi->bdi);
exofs_free_sbi(sbi);
sb->s_fs_info = NULL;
}
__sbi_read_stats(sbi);
/* set up operation vectors */
- sbi->bdi.ra_pages = __ra_pages(&sbi->layout);
- sb->s_bdi = &sbi->bdi;
+ ret = super_setup_bdi(sb);
+ if (ret) {
+ EXOFS_DBGMSG("Failed to super_setup_bdi\n");
+ goto free_sbi;
+ }
+ sb->s_bdi->ra_pages = __ra_pages(&sbi->layout);
sb->s_fs_info = sbi;
sb->s_op = &exofs_sops;
sb->s_export_op = &exofs_export_ops;
goto free_sbi;
}
- ret = bdi_setup_and_register(&sbi->bdi, "exofs");
- if (ret) {
- EXOFS_DBGMSG("Failed to bdi_setup_and_register\n");
- dput(sb->s_root);
- sb->s_root = NULL;
- goto free_sbi;
- }
-
exofs_sysfs_dbg_print();
_exofs_print_device("Mounting", opts->dev_name,
ore_comp_dev(&sbi->oc, 0),
extern int ext4_getattr(const struct path *, struct kstat *, u32, unsigned int);
extern void ext4_evict_inode(struct inode *);
extern void ext4_clear_inode(struct inode *);
+extern int ext4_file_getattr(const struct path *, struct kstat *, u32, unsigned int);
extern int ext4_sync_inode(handle_t *, struct inode *);
extern void ext4_dirty_inode(struct inode *, int);
extern int ext4_change_inode_journal_flag(struct inode *, int);
const struct inode_operations ext4_file_inode_operations = {
.setattr = ext4_setattr,
- .getattr = ext4_getattr,
+ .getattr = ext4_file_getattr,
.listxattr = ext4_listxattr,
.get_acl = ext4_get_acl,
.set_acl = ext4_set_acl,
int ext4_getattr(const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int query_flags)
{
- struct inode *inode;
- unsigned long long delalloc_blocks;
+ struct inode *inode = d_inode(path->dentry);
+ struct ext4_inode *raw_inode;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ unsigned int flags;
+
+ if (EXT4_FITS_IN_INODE(raw_inode, ei, i_crtime)) {
+ stat->result_mask |= STATX_BTIME;
+ stat->btime.tv_sec = ei->i_crtime.tv_sec;
+ stat->btime.tv_nsec = ei->i_crtime.tv_nsec;
+ }
+
+ flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
+ if (flags & EXT4_APPEND_FL)
+ stat->attributes |= STATX_ATTR_APPEND;
+ if (flags & EXT4_COMPR_FL)
+ stat->attributes |= STATX_ATTR_COMPRESSED;
+ if (flags & EXT4_ENCRYPT_FL)
+ stat->attributes |= STATX_ATTR_ENCRYPTED;
+ if (flags & EXT4_IMMUTABLE_FL)
+ stat->attributes |= STATX_ATTR_IMMUTABLE;
+ if (flags & EXT4_NODUMP_FL)
+ stat->attributes |= STATX_ATTR_NODUMP;
+
+ stat->attributes_mask |= (STATX_ATTR_APPEND |
+ STATX_ATTR_COMPRESSED |
+ STATX_ATTR_ENCRYPTED |
+ STATX_ATTR_IMMUTABLE |
+ STATX_ATTR_NODUMP);
- inode = d_inode(path->dentry);
generic_fillattr(inode, stat);
+ return 0;
+}
+
+int ext4_file_getattr(const struct path *path, struct kstat *stat,
+ u32 request_mask, unsigned int query_flags)
+{
+ struct inode *inode = d_inode(path->dentry);
+ u64 delalloc_blocks;
+
+ ext4_getattr(path, stat, request_mask, query_flags);
/*
* If there is inline data in the inode, the inode will normally not
.tmpfile = ext4_tmpfile,
.rename = ext4_rename2,
.setattr = ext4_setattr,
+ .getattr = ext4_getattr,
.listxattr = ext4_listxattr,
.get_acl = ext4_get_acl,
.set_acl = ext4_set_acl,
const struct inode_operations ext4_special_inode_operations = {
.setattr = ext4_setattr,
+ .getattr = ext4_getattr,
.listxattr = ext4_listxattr,
.get_acl = ext4_get_acl,
.set_acl = ext4_set_acl,
const struct inode_operations ext4_encrypted_symlink_inode_operations = {
.get_link = ext4_encrypted_get_link,
.setattr = ext4_setattr,
+ .getattr = ext4_getattr,
.listxattr = ext4_listxattr,
};
const struct inode_operations ext4_symlink_inode_operations = {
.get_link = page_get_link,
.setattr = ext4_setattr,
+ .getattr = ext4_getattr,
.listxattr = ext4_listxattr,
};
const struct inode_operations ext4_fast_symlink_inode_operations = {
.get_link = simple_get_link,
.setattr = ext4_setattr,
+ .getattr = ext4_getattr,
.listxattr = ext4_listxattr,
};
wake_up(&fc->blocked_waitq);
if (fc->num_background == fc->congestion_threshold &&
- fc->connected && fc->bdi_initialized) {
- clear_bdi_congested(&fc->bdi, BLK_RW_SYNC);
- clear_bdi_congested(&fc->bdi, BLK_RW_ASYNC);
+ fc->connected && fc->sb) {
+ clear_bdi_congested(fc->sb->s_bdi, BLK_RW_SYNC);
+ clear_bdi_congested(fc->sb->s_bdi, BLK_RW_ASYNC);
}
fc->num_background--;
fc->active_background--;
fc->num_background++;
if (fc->num_background == fc->max_background)
fc->blocked = 1;
- if (fc->num_background == fc->congestion_threshold &&
- fc->bdi_initialized) {
- set_bdi_congested(&fc->bdi, BLK_RW_SYNC);
- set_bdi_congested(&fc->bdi, BLK_RW_ASYNC);
+ if (fc->num_background == fc->congestion_threshold && fc->sb) {
+ set_bdi_congested(fc->sb->s_bdi, BLK_RW_SYNC);
+ set_bdi_congested(fc->sb->s_bdi, BLK_RW_ASYNC);
}
list_add_tail(&req->list, &fc->bg_queue);
flush_bg_queue(fc);
/** Filesystem supports NFS exporting. Only set in INIT */
unsigned export_support:1;
- /** Set if bdi is valid */
- unsigned bdi_initialized:1;
-
/** write-back cache policy (default is write-through) */
unsigned writeback_cache:1;
/** Negotiated minor version */
unsigned minor;
- /** Backing dev info */
- struct backing_dev_info bdi;
-
/** Entry on the fuse_conn_list */
struct list_head entry;
}
}
-static void fuse_bdi_destroy(struct fuse_conn *fc)
-{
- if (fc->bdi_initialized)
- bdi_destroy(&fc->bdi);
-}
-
static void fuse_put_super(struct super_block *sb)
{
struct fuse_conn *fc = get_fuse_conn_super(sb);
list_del(&fc->entry);
fuse_ctl_remove_conn(fc);
mutex_unlock(&fuse_mutex);
- fuse_bdi_destroy(fc);
fuse_conn_put(fc);
}
fc->no_flock = 1;
}
- fc->bdi.ra_pages = min(fc->bdi.ra_pages, ra_pages);
+ fc->sb->s_bdi->ra_pages =
+ min(fc->sb->s_bdi->ra_pages, ra_pages);
fc->minor = arg->minor;
fc->max_write = arg->minor < 5 ? 4096 : arg->max_write;
fc->max_write = max_t(unsigned, 4096, fc->max_write);
arg->major = FUSE_KERNEL_VERSION;
arg->minor = FUSE_KERNEL_MINOR_VERSION;
- arg->max_readahead = fc->bdi.ra_pages * PAGE_SIZE;
+ arg->max_readahead = fc->sb->s_bdi->ra_pages * PAGE_SIZE;
arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC |
FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK |
FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ |
static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb)
{
int err;
+ char *suffix = "";
- fc->bdi.name = "fuse";
- fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_SIZE;
- /* fuse does it's own writeback accounting */
- fc->bdi.capabilities = BDI_CAP_NO_ACCT_WB | BDI_CAP_STRICTLIMIT;
-
- err = bdi_init(&fc->bdi);
+ if (sb->s_bdev)
+ suffix = "-fuseblk";
+ err = super_setup_bdi_name(sb, "%u:%u%s", MAJOR(fc->dev),
+ MINOR(fc->dev), suffix);
if (err)
return err;
- fc->bdi_initialized = 1;
-
- if (sb->s_bdev) {
- err = bdi_register(&fc->bdi, NULL, "%u:%u-fuseblk",
- MAJOR(fc->dev), MINOR(fc->dev));
- } else {
- err = bdi_register_dev(&fc->bdi, fc->dev);
- }
-
- if (err)
- return err;
+ sb->s_bdi->ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_SIZE;
+ /* fuse does it's own writeback accounting */
+ sb->s_bdi->capabilities = BDI_CAP_NO_ACCT_WB | BDI_CAP_STRICTLIMIT;
/*
* For a single fuse filesystem use max 1% of dirty +
*
* /sys/class/bdi/<bdi>/max_ratio
*/
- bdi_set_max_ratio(&fc->bdi, 1);
+ bdi_set_max_ratio(sb->s_bdi, 1);
return 0;
}
if (err)
goto err_dev_free;
- sb->s_bdi = &fc->bdi;
-
/* Handle umasking inside the fuse code */
if (sb->s_flags & MS_POSIXACL)
fc->dont_mask = 1;
err_dev_free:
fuse_dev_free(fud);
err_put_conn:
- fuse_bdi_destroy(fc);
fuse_conn_put(fc);
err_fput:
fput(file);
#include <linux/quotaops.h>
#include <linux/lockdep.h>
#include <linux/module.h>
+#include <linux/backing-dev.h>
#include "gfs2.h"
#include "incore.h"
{
s->s_bdev = data;
s->s_dev = s->s_bdev->bd_dev;
-
- /*
- * We set the bdi here to the queue backing, file systems can
- * overwrite this in ->fill_super()
- */
- s->s_bdi = bdev_get_queue(s->s_bdev)->backing_dev_info;
+ s->s_bdi = bdi_get(s->s_bdev->bd_bdi);
return 0;
}
vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND;
vma->vm_ops = &hugetlb_vm_ops;
+ /*
+ * Offset passed to mmap (before page shift) could have been
+ * negative when represented as a (l)off_t.
+ */
+ if (((loff_t)vma->vm_pgoff << PAGE_SHIFT) < 0)
+ return -EINVAL;
+
if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))
return -EINVAL;
vma_len = (loff_t)(vma->vm_end - vma->vm_start);
+ len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
+ /* check for overflow */
+ if (len < vma_len)
+ return -EINVAL;
inode_lock(inode);
file_accessed(file);
ret = -ENOMEM;
- len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
-
if (hugetlb_reserve_pages(inode,
vma->vm_pgoff >> huge_page_order(h),
len >> huge_page_shift(h), vma,
ret = 0;
if (vma->vm_flags & VM_WRITE && inode->i_size < len)
- inode->i_size = len;
+ i_size_write(inode, len);
out:
inode_unlock(inode);
int retval = 0;
const char *s = nd->name->name;
+ if (!*s)
+ flags &= ~LOOKUP_RCU;
+
nd->last_type = LAST_ROOT; /* if there are only slashes... */
nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT;
nd->depth = 0;
sb->s_magic = NCP_SUPER_MAGIC;
sb->s_op = &ncp_sops;
sb->s_d_op = &ncp_dentry_operations;
- sb->s_bdi = &server->bdi;
server = NCP_SBP(sb);
memset(server, 0, sizeof(*server));
- error = bdi_setup_and_register(&server->bdi, "ncpfs");
+ error = super_setup_bdi(sb);
if (error)
goto out_fput;
if (data.info_fd != -1) {
struct socket *info_sock = sockfd_lookup(data.info_fd, &error);
if (!info_sock)
- goto out_bdi;
+ goto out_fput;
server->info_sock = info_sock;
error = -EBADFD;
if (info_sock->type != SOCK_STREAM)
out_fput2:
if (server->info_sock)
sockfd_put(server->info_sock);
-out_bdi:
- bdi_destroy(&server->bdi);
out_fput:
sockfd_put(sock);
out:
kill_pid(server->m.wdog_pid, SIGTERM, 1);
put_pid(server->m.wdog_pid);
- bdi_destroy(&server->bdi);
kfree(server->priv.data);
kfree(server->auth.object_name);
vfree(server->rxbuf);
size_t len;
__u8 data[128];
} unexpected_packet;
- struct backing_dev_info bdi;
};
extern void ncp_tcp_rcv_proc(struct work_struct *work);
server->rsize = NFS_MAX_FILE_IO_SIZE;
server->rpages = (server->rsize + PAGE_SIZE - 1) >> PAGE_SHIFT;
- server->backing_dev_info.name = "nfs";
- server->backing_dev_info.ra_pages = server->rpages * NFS_MAX_READAHEAD;
-
if (server->wsize > max_rpc_payload)
server->wsize = max_rpc_payload;
if (server->wsize > NFS_MAX_FILE_IO_SIZE)
return NULL;
}
- if (bdi_init(&server->backing_dev_info)) {
- nfs_free_iostats(server->io_stats);
- kfree(server);
- return NULL;
- }
-
ida_init(&server->openowner_id);
ida_init(&server->lockowner_id);
pnfs_init_server(server);
ida_destroy(&server->lockowner_id);
ida_destroy(&server->openowner_id);
nfs_free_iostats(server->io_stats);
- bdi_destroy(&server->backing_dev_info);
kfree(server);
nfs_release_automount_timer();
dprintk("<-- nfs_free_server()\n");
if (put_dreq(dreq))
nfs_direct_complete(dreq);
- return 0;
+ return requested_bytes;
}
/**
struct inode *inode = mapping->host;
struct nfs_direct_req *dreq;
struct nfs_lock_context *l_ctx;
- ssize_t result = -EINVAL;
+ ssize_t result = -EINVAL, requested;
size_t count = iov_iter_count(iter);
nfs_add_stats(mapping->host, NFSIOS_DIRECTREADBYTES, count);
nfs_start_io_direct(inode);
NFS_I(inode)->read_io += count;
- result = nfs_direct_read_schedule_iovec(dreq, iter, iocb->ki_pos);
+ requested = nfs_direct_read_schedule_iovec(dreq, iter, iocb->ki_pos);
nfs_end_io_direct(inode);
- if (!result) {
+ if (requested > 0) {
result = nfs_direct_wait(dreq);
- if (result > 0)
+ if (result > 0) {
+ requested -= result;
iocb->ki_pos += result;
+ }
+ iov_iter_revert(iter, requested);
+ } else {
+ result = requested;
}
out_release:
if (put_dreq(dreq))
nfs_direct_write_complete(dreq);
- return 0;
+ return requested_bytes;
}
/**
*/
ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
{
- ssize_t result = -EINVAL;
+ ssize_t result = -EINVAL, requested;
size_t count;
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
nfs_start_io_direct(inode);
- result = nfs_direct_write_schedule_iovec(dreq, iter, pos);
+ requested = nfs_direct_write_schedule_iovec(dreq, iter, pos);
if (mapping->nrpages) {
invalidate_inode_pages2_range(mapping,
nfs_end_io_direct(inode);
- if (!result) {
+ if (requested > 0) {
result = nfs_direct_wait(dreq);
if (result > 0) {
+ requested -= result;
iocb->ki_pos = pos + result;
/* XXX: should check the generic_write_sync retval */
generic_write_sync(iocb, result);
}
+ iov_iter_revert(iter, requested);
+ } else {
+ result = requested;
}
out_release:
nfs_direct_req_release(dreq);
};
struct nfs_mount_info {
- void (*fill_super)(struct super_block *, struct nfs_mount_info *);
+ int (*fill_super)(struct super_block *, struct nfs_mount_info *);
int (*set_security)(struct super_block *, struct dentry *, struct nfs_mount_info *);
struct nfs_parsed_mount_data *parsed;
struct nfs_clone_mount *cloned;
struct dentry * nfs_xdev_mount_common(struct file_system_type *, int,
const char *, struct nfs_mount_info *);
void nfs_kill_super(struct super_block *);
-void nfs_fill_super(struct super_block *, struct nfs_mount_info *);
+int nfs_fill_super(struct super_block *, struct nfs_mount_info *);
extern struct rpc_stat nfs_rpcstat;
extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio);
/* super.c */
-void nfs_clone_super(struct super_block *, struct nfs_mount_info *);
+int nfs_clone_super(struct super_block *, struct nfs_mount_info *);
void nfs_umount_begin(struct super_block *);
int nfs_statfs(struct dentry *, struct kstatfs *);
int nfs_show_options(struct seq_file *, struct dentry *);
sb->s_blocksize = nfs_block_bits(server->wsize,
&sb->s_blocksize_bits);
- sb->s_bdi = &server->backing_dev_info;
-
nfs_super_set_maxbytes(sb, server->maxfilesize);
}
/*
* Finish setting up an NFS2/3 superblock
*/
-void nfs_fill_super(struct super_block *sb, struct nfs_mount_info *mount_info)
+int nfs_fill_super(struct super_block *sb, struct nfs_mount_info *mount_info)
{
struct nfs_parsed_mount_data *data = mount_info->parsed;
struct nfs_server *server = NFS_SB(sb);
+ int ret;
sb->s_blocksize_bits = 0;
sb->s_blocksize = 0;
}
nfs_initialise_sb(sb);
+
+ ret = super_setup_bdi_name(sb, "%u:%u", MAJOR(server->s_dev),
+ MINOR(server->s_dev));
+ if (ret)
+ return ret;
+ sb->s_bdi->ra_pages = server->rpages * NFS_MAX_READAHEAD;
+ return 0;
+
}
EXPORT_SYMBOL_GPL(nfs_fill_super);
/*
* Finish setting up a cloned NFS2/3/4 superblock
*/
-void nfs_clone_super(struct super_block *sb, struct nfs_mount_info *mount_info)
+int nfs_clone_super(struct super_block *sb, struct nfs_mount_info *mount_info)
{
const struct super_block *old_sb = mount_info->cloned->sb;
struct nfs_server *server = NFS_SB(sb);
}
nfs_initialise_sb(sb);
+
+ sb->s_bdi = bdi_get(old_sb->s_bdi);
+
+ return 0;
}
static int nfs_compare_mount_options(const struct super_block *s, const struct nfs_server *b, int flags)
}
#endif
-static int nfs_bdi_register(struct nfs_server *server)
-{
- return bdi_register_dev(&server->backing_dev_info, server->s_dev);
-}
-
int nfs_set_sb_security(struct super_block *s, struct dentry *mntroot,
struct nfs_mount_info *mount_info)
{
nfs_free_server(server);
server = NULL;
} else {
- error = nfs_bdi_register(server);
- if (error) {
- mntroot = ERR_PTR(error);
- goto error_splat_super;
- }
server->super = s;
}
if (!s->s_root) {
/* initial superblock/root creation */
- mount_info->fill_super(s, mount_info);
+ error = mount_info->fill_super(s, mount_info);
+ if (error)
+ goto error_splat_super;
nfs_get_cache_cookie(s, mount_info->parsed, mount_info->cloned);
}
static void nfs_set_page_writeback(struct page *page)
{
- struct nfs_server *nfss = NFS_SERVER(page_file_mapping(page)->host);
+ struct inode *inode = page_file_mapping(page)->host;
+ struct nfs_server *nfss = NFS_SERVER(inode);
int ret = test_set_page_writeback(page);
WARN_ON_ONCE(ret != 0);
if (atomic_long_inc_return(&nfss->writeback) >
- NFS_CONGESTION_ON_THRESH) {
- set_bdi_congested(&nfss->backing_dev_info,
- BLK_RW_ASYNC);
- }
+ NFS_CONGESTION_ON_THRESH)
+ set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
}
static void nfs_end_page_writeback(struct nfs_page *req)
end_page_writeback(req->wb_page);
if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
- clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
+ clear_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
}
}
nfss = NFS_SERVER(data->inode);
if (atomic_long_read(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
- clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
+ clear_bdi_congested(inode_to_bdi(data->inode), BLK_RW_ASYNC);
nfs_init_cinfo(&cinfo, data->inode, data->dreq);
nfs_commit_end(cinfo.mds);
req->cmd[4] = bufflen & 0xff;
req->cmd_len = COMMAND_SIZE(INQUIRY);
- error = blk_execute_rq(rq->q, NULL, rq, 1);
- if (error) {
+ blk_execute_rq(rq->q, NULL, rq, 1);
+ if (req->result) {
pr_err("pNFS: INQUIRY 0x83 failed with: %x\n",
- rq->errors);
+ req->result);
+ error = -EIO;
goto out_put_request;
}
{
unsigned int len, v, hdr, dlen;
u32 max_blocksize = svc_max_payload(rqstp);
+ struct kvec *head = rqstp->rq_arg.head;
+ struct kvec *tail = rqstp->rq_arg.tail;
p = decode_fh(p, &args->fh);
if (!p)
args->count = ntohl(*p++);
args->stable = ntohl(*p++);
len = args->len = ntohl(*p++);
+ if ((void *)p > head->iov_base + head->iov_len)
+ return 0;
/*
* The count must equal the amount of data passed.
*/
* Check to make sure that we got the right number of
* bytes.
*/
- hdr = (void*)p - rqstp->rq_arg.head[0].iov_base;
- dlen = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len
- + rqstp->rq_arg.tail[0].iov_len - hdr;
+ hdr = (void*)p - head->iov_base;
+ dlen = head->iov_len + rqstp->rq_arg.page_len + tail->iov_len - hdr;
/*
* Round the length of the data which was specified up to
* the next multiple of XDR units and then compare that
len = args->len = max_blocksize;
}
rqstp->rq_vec[0].iov_base = (void*)p;
- rqstp->rq_vec[0].iov_len = rqstp->rq_arg.head[0].iov_len - hdr;
+ rqstp->rq_vec[0].iov_len = head->iov_len - hdr;
v = 0;
while (len > rqstp->rq_vec[v].iov_len) {
len -= rqstp->rq_vec[v].iov_len;
/* first copy and check from the first page */
old = (char*)p;
vec = &rqstp->rq_arg.head[0];
+ if ((void *)old > vec->iov_base + vec->iov_len)
+ return 0;
avail = vec->iov_len - (old - (char*)vec->iov_base);
while (len && avail && *old) {
*new++ = *old++;
int nfsd4_max_reply(struct svc_rqst *rqstp, struct nfsd4_op *op)
{
- if (op->opnum == OP_ILLEGAL)
+ if (op->opnum == OP_ILLEGAL || op->status == nfserr_notsupp)
return op_encode_hdr_size * sizeof(__be32);
BUG_ON(OPDESC(op)->op_rsize_bop == NULL);
return nfserr;
}
+/*
+ * A write procedure can have a large argument, and a read procedure can
+ * have a large reply, but no NFSv2 or NFSv3 procedure has argument and
+ * reply that can both be larger than a page. The xdr code has taken
+ * advantage of this assumption to be a sloppy about bounds checking in
+ * some cases. Pending a rewrite of the NFSv2/v3 xdr code to fix that
+ * problem, we enforce these assumptions here:
+ */
+static bool nfs_request_too_big(struct svc_rqst *rqstp,
+ struct svc_procedure *proc)
+{
+ /*
+ * The ACL code has more careful bounds-checking and is not
+ * susceptible to this problem:
+ */
+ if (rqstp->rq_prog != NFS_PROGRAM)
+ return false;
+ /*
+ * Ditto NFSv4 (which can in theory have argument and reply both
+ * more than a page):
+ */
+ if (rqstp->rq_vers >= 4)
+ return false;
+ /* The reply will be small, we're OK: */
+ if (proc->pc_xdrressize > 0 &&
+ proc->pc_xdrressize < XDR_QUADLEN(PAGE_SIZE))
+ return false;
+
+ return rqstp->rq_arg.len > PAGE_SIZE;
+}
+
int
nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
{
rqstp->rq_vers, rqstp->rq_proc);
proc = rqstp->rq_procinfo;
+ if (nfs_request_too_big(rqstp, proc)) {
+ dprintk("nfsd: NFSv%d argument too large\n", rqstp->rq_vers);
+ *statp = rpc_garbage_args;
+ return 1;
+ }
/*
* Give the xdr decoder a chance to change this if it wants
* (necessary in the NFSv4.0 compound case)
struct nfsd_writeargs *args)
{
unsigned int len, hdr, dlen;
+ struct kvec *head = rqstp->rq_arg.head;
int v;
p = decode_fh(p, &args->fh);
* Check to make sure that we got the right number of
* bytes.
*/
- hdr = (void*)p - rqstp->rq_arg.head[0].iov_base;
- dlen = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len
- - hdr;
+ hdr = (void*)p - head->iov_base;
+ if (hdr > head->iov_len)
+ return 0;
+ dlen = head->iov_len + rqstp->rq_arg.page_len - hdr;
/*
* Round the length of the data which was specified up to
return 0;
rqstp->rq_vec[0].iov_base = (void*)p;
- rqstp->rq_vec[0].iov_len = rqstp->rq_arg.head[0].iov_len - hdr;
+ rqstp->rq_vec[0].iov_len = head->iov_len - hdr;
v = 0;
while (len > rqstp->rq_vec[v].iov_len) {
len -= rqstp->rq_vec[v].iov_len;
else
err = nfserrno(host_err);
if (test_bit(RQ_LOCAL, &rqstp->rq_flags))
- tsk_restore_flags(current, pflags, PF_LESS_THROTTLE);
+ current_restore_flags(pflags, PF_LESS_THROTTLE);
return err;
}
sb->s_time_gran = 1;
sb->s_max_links = NILFS_LINK_MAX;
- sb->s_bdi = bdev_get_queue(sb->s_bdev)->backing_dev_info;
+ sb->s_bdi = bdi_get(sb->s_bdev->bd_bdi);
err = load_nilfs(nilfs, sb);
if (err)
return ERR_PTR(-ENOMEM);
}
d_instantiate(dentry, inode);
+ dentry->d_flags |= DCACHE_RCUACCESS;
dentry->d_fsdata = (void *)ns->ops;
d = atomic_long_cmpxchg(&ns->stashed, 0, (unsigned long)dentry);
if (d) {
static int o2net_set_nodelay(struct socket *sock)
{
- int ret, val = 1;
- mm_segment_t oldfs;
+ int val = 1;
- oldfs = get_fs();
- set_fs(KERNEL_DS);
-
- /*
- * Dear unsuspecting programmer,
- *
- * Don't use sock_setsockopt() for SOL_TCP. It doesn't check its level
- * argument and assumes SOL_SOCKET so, say, your TCP_NODELAY will
- * silently turn into SO_DEBUG.
- *
- * Yours,
- * Keeper of hilariously fragile interfaces.
- */
- ret = sock->ops->setsockopt(sock, SOL_TCP, TCP_NODELAY,
- (char __user *)&val, sizeof(val));
-
- set_fs(oldfs);
- return ret;
+ return kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY,
+ (void *)&val, sizeof(val));
}
static int o2net_set_usertimeout(struct socket *sock)
int user_timeout = O2NET_TCP_USER_TIMEOUT;
return kernel_setsockopt(sock, SOL_TCP, TCP_USER_TIMEOUT,
- (char *)&user_timeout, sizeof(user_timeout));
+ (void *)&user_timeout, sizeof(user_timeout));
}
static void o2net_initialize_handshake(void)
continue;
/*
* Skip ops whose filesystem we don't know about unless
- * it is being mounted.
+ * it is being mounted or unmounted. It is possible for
+ * a filesystem we don't know about to be unmounted if
+ * it fails to mount in the kernel after userspace has
+ * been sent the mount request.
*/
/* XXX: is there a better way to detect this? */
} else if (ret == -1 &&
!(op->upcall.type ==
ORANGEFS_VFS_OP_FS_MOUNT ||
op->upcall.type ==
- ORANGEFS_VFS_OP_GETATTR)) {
+ ORANGEFS_VFS_OP_GETATTR ||
+ op->upcall.type ==
+ ORANGEFS_VFS_OP_FS_UMOUNT)) {
gossip_debug(GOSSIP_DEV_DEBUG,
"orangefs: skipping op tag %llu %s\n",
llu(op->tag), get_opname_string(op));
size_t n = size;
if (n > PAGE_SIZE)
n = PAGE_SIZE;
- n = copy_page_from_iter(page, 0, n, iter);
- if (!n)
+ if (copy_page_from_iter(page, 0, n, iter) != n)
return -EFAULT;
size -= n;
}
return 0;
-
}
/*
char devname[ORANGEFS_MAX_SERVER_ADDR_LEN];
struct super_block *sb;
int mount_pending;
+ int no_list;
struct list_head list;
};
if (!new_op)
return -ENOMEM;
new_op->upcall.req.features.features = 0;
- ret = service_operation(new_op, "orangefs_features", 0);
- orangefs_features = new_op->downcall.resp.features.features;
+ ret = service_operation(new_op, "orangefs_features",
+ ORANGEFS_OP_PRIORITY | ORANGEFS_OP_NO_MUTEX);
+ if (!ret)
+ orangefs_features =
+ new_op->downcall.resp.features.features;
+ else
+ orangefs_features = 0;
op_release(new_op);
} else {
orangefs_features = 0;
if (ret) {
d = ERR_PTR(ret);
- goto free_op;
+ goto free_sb_and_op;
}
/*
spin_unlock(&orangefs_superblocks_lock);
op_release(new_op);
+ /* Must be removed from the list now. */
+ ORANGEFS_SB(sb)->no_list = 0;
+
if (orangefs_userspace_version >= 20906) {
new_op = op_alloc(ORANGEFS_VFS_OP_FEATURES);
if (!new_op)
return dget(sb->s_root);
+free_sb_and_op:
+ /* Will call orangefs_kill_sb with sb not in list. */
+ ORANGEFS_SB(sb)->no_list = 1;
+ deactivate_locked_super(sb);
free_op:
gossip_err("orangefs_mount: mount request failed with %d\n", ret);
if (ret == -EINVAL) {
*/
orangefs_unmount_sb(sb);
- /* remove the sb from our list of orangefs specific sb's */
-
- spin_lock(&orangefs_superblocks_lock);
- __list_del_entry(&ORANGEFS_SB(sb)->list); /* not list_del_init */
- ORANGEFS_SB(sb)->list.prev = NULL;
- spin_unlock(&orangefs_superblocks_lock);
+ if (!ORANGEFS_SB(sb)->no_list) {
+ /* remove the sb from our list of orangefs specific sb's */
+ spin_lock(&orangefs_superblocks_lock);
+ /* not list_del_init */
+ __list_del_entry(&ORANGEFS_SB(sb)->list);
+ ORANGEFS_SB(sb)->list.prev = NULL;
+ spin_unlock(&orangefs_superblocks_lock);
+ }
/*
* make sure that ORANGEFS_DEV_REMOUNT_ALL loop that might've seen us
if ((table->proc_handler == proc_dostring) ||
(table->proc_handler == proc_dointvec) ||
+ (table->proc_handler == proc_douintvec) ||
(table->proc_handler == proc_dointvec_minmax) ||
(table->proc_handler == proc_dointvec_jiffies) ||
(table->proc_handler == proc_dointvec_userhz_jiffies) ||
static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
unsigned long addr, pmd_t *pmdp)
{
- pmd_t pmd = pmdp_huge_get_and_clear(vma->vm_mm, addr, pmdp);
+ pmd_t pmd = *pmdp;
+
+ /* See comment in change_huge_pmd() */
+ pmdp_invalidate(vma, addr, pmdp);
+ if (pmd_dirty(*pmdp))
+ pmd = pmd_mkdirty(pmd);
+ if (pmd_young(*pmdp))
+ pmd = pmd_mkyoung(pmd);
pmd = pmd_wrprotect(pmd);
pmd = pmd_clear_soft_dirty(pmd);
int vfs_statx_fd(unsigned int fd, struct kstat *stat,
u32 request_mask, unsigned int query_flags)
{
- struct fd f = fdget_raw(fd);
+ struct fd f;
int error = -EBADF;
+ if (query_flags & ~KSTAT_QUERY_FLAGS)
+ return -EINVAL;
+
+ f = fdget_raw(fd);
if (f.file) {
error = vfs_getattr(&f.file->f_path, stat,
request_mask, query_flags);
* Additionally, the use of AT_SYMLINK_NOFOLLOW in flags will prevent a symlink
* at the given name from being referenced.
*
- * The caller must have preset stat->request_mask as for vfs_getattr(). The
- * flags are also used to load up stat->query_flags.
- *
* 0 will be returned on success, and a -ve error code if unsuccessful.
*/
int vfs_statx(int dfd, const char __user *filename, int flags,
}
#endif /* __ARCH_WANT_STAT64 || __ARCH_WANT_COMPAT_STAT64 */
-static inline int __put_timestamp(struct timespec *kts,
- struct statx_timestamp __user *uts)
-{
- return (__put_user(kts->tv_sec, &uts->tv_sec ) ||
- __put_user(kts->tv_nsec, &uts->tv_nsec ) ||
- __put_user(0, &uts->__reserved ));
-}
-
-/*
- * Set the statx results.
- */
-static long statx_set_result(struct kstat *stat, struct statx __user *buffer)
+static noinline_for_stack int
+cp_statx(const struct kstat *stat, struct statx __user *buffer)
{
- uid_t uid = from_kuid_munged(current_user_ns(), stat->uid);
- gid_t gid = from_kgid_munged(current_user_ns(), stat->gid);
-
- if (__put_user(stat->result_mask, &buffer->stx_mask ) ||
- __put_user(stat->mode, &buffer->stx_mode ) ||
- __clear_user(&buffer->__spare0, sizeof(buffer->__spare0)) ||
- __put_user(stat->nlink, &buffer->stx_nlink ) ||
- __put_user(uid, &buffer->stx_uid ) ||
- __put_user(gid, &buffer->stx_gid ) ||
- __put_user(stat->attributes, &buffer->stx_attributes ) ||
- __put_user(stat->blksize, &buffer->stx_blksize ) ||
- __put_user(MAJOR(stat->rdev), &buffer->stx_rdev_major ) ||
- __put_user(MINOR(stat->rdev), &buffer->stx_rdev_minor ) ||
- __put_user(MAJOR(stat->dev), &buffer->stx_dev_major ) ||
- __put_user(MINOR(stat->dev), &buffer->stx_dev_minor ) ||
- __put_timestamp(&stat->atime, &buffer->stx_atime ) ||
- __put_timestamp(&stat->btime, &buffer->stx_btime ) ||
- __put_timestamp(&stat->ctime, &buffer->stx_ctime ) ||
- __put_timestamp(&stat->mtime, &buffer->stx_mtime ) ||
- __put_user(stat->ino, &buffer->stx_ino ) ||
- __put_user(stat->size, &buffer->stx_size ) ||
- __put_user(stat->blocks, &buffer->stx_blocks ) ||
- __clear_user(&buffer->__spare1, sizeof(buffer->__spare1)) ||
- __clear_user(&buffer->__spare2, sizeof(buffer->__spare2)))
- return -EFAULT;
-
- return 0;
+ struct statx tmp;
+
+ memset(&tmp, 0, sizeof(tmp));
+
+ tmp.stx_mask = stat->result_mask;
+ tmp.stx_blksize = stat->blksize;
+ tmp.stx_attributes = stat->attributes;
+ tmp.stx_nlink = stat->nlink;
+ tmp.stx_uid = from_kuid_munged(current_user_ns(), stat->uid);
+ tmp.stx_gid = from_kgid_munged(current_user_ns(), stat->gid);
+ tmp.stx_mode = stat->mode;
+ tmp.stx_ino = stat->ino;
+ tmp.stx_size = stat->size;
+ tmp.stx_blocks = stat->blocks;
+ tmp.stx_attributes_mask = stat->attributes_mask;
+ tmp.stx_atime.tv_sec = stat->atime.tv_sec;
+ tmp.stx_atime.tv_nsec = stat->atime.tv_nsec;
+ tmp.stx_btime.tv_sec = stat->btime.tv_sec;
+ tmp.stx_btime.tv_nsec = stat->btime.tv_nsec;
+ tmp.stx_ctime.tv_sec = stat->ctime.tv_sec;
+ tmp.stx_ctime.tv_nsec = stat->ctime.tv_nsec;
+ tmp.stx_mtime.tv_sec = stat->mtime.tv_sec;
+ tmp.stx_mtime.tv_nsec = stat->mtime.tv_nsec;
+ tmp.stx_rdev_major = MAJOR(stat->rdev);
+ tmp.stx_rdev_minor = MINOR(stat->rdev);
+ tmp.stx_dev_major = MAJOR(stat->dev);
+ tmp.stx_dev_minor = MINOR(stat->dev);
+
+ return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0;
}
/**
* sys_statx - System call to get enhanced stats
* @dfd: Base directory to pathwalk from *or* fd to stat.
- * @filename: File to stat *or* NULL.
+ * @filename: File to stat or "" with AT_EMPTY_PATH
* @flags: AT_* flags to control pathwalk.
* @mask: Parts of statx struct actually required.
* @buffer: Result buffer.
*
- * Note that if filename is NULL, then it does the equivalent of fstat() using
- * dfd to indicate the file of interest.
+ * Note that fstat() can be emulated by setting dfd to the fd of interest,
+ * supplying "" as the filename and setting AT_EMPTY_PATH in the flags.
*/
SYSCALL_DEFINE5(statx,
int, dfd, const char __user *, filename, unsigned, flags,
struct kstat stat;
int error;
+ if (mask & STATX__RESERVED)
+ return -EINVAL;
if ((flags & AT_STATX_SYNC_TYPE) == AT_STATX_SYNC_TYPE)
return -EINVAL;
- if (!access_ok(VERIFY_WRITE, buffer, sizeof(*buffer)))
- return -EFAULT;
- if (filename)
- error = vfs_statx(dfd, filename, flags, &stat, mask);
- else
- error = vfs_statx_fd(dfd, &stat, mask, flags);
+ error = vfs_statx(dfd, filename, flags, &stat, mask);
if (error)
return error;
- return statx_set_result(&stat, buffer);
+
+ return cp_statx(&stat, buffer);
}
/* Caller is here responsible for sufficient locking (ie. inode->i_lock) */
hlist_del_init(&sb->s_instances);
spin_unlock(&sb_lock);
up_write(&sb->s_umount);
+ if (sb->s_bdi != &noop_backing_dev_info) {
+ bdi_put(sb->s_bdi);
+ sb->s_bdi = &noop_backing_dev_info;
+ }
}
EXPORT_SYMBOL(generic_shutdown_super);
{
s->s_bdev = data;
s->s_dev = s->s_bdev->bd_dev;
+ s->s_bdi = bdi_get(s->s_bdev->bd_bdi);
- /*
- * We set the bdi here to the queue backing, file systems can
- * overwrite this in ->fill_super()
- */
- s->s_bdi = bdev_get_queue(s->s_bdev)->backing_dev_info;
return 0;
}
}
/*
+ * Setup private BDI for given superblock. It gets automatically cleaned up
+ * in generic_shutdown_super().
+ */
+int super_setup_bdi_name(struct super_block *sb, char *fmt, ...)
+{
+ struct backing_dev_info *bdi;
+ int err;
+ va_list args;
+
+ bdi = bdi_alloc(GFP_KERNEL);
+ if (!bdi)
+ return -ENOMEM;
+
+ bdi->name = sb->s_type->name;
+
+ va_start(args, fmt);
+ err = bdi_register_va(bdi, fmt, args);
+ va_end(args);
+ if (err) {
+ bdi_put(bdi);
+ return err;
+ }
+ WARN_ON(sb->s_bdi != &noop_backing_dev_info);
+ sb->s_bdi = bdi;
+
+ return 0;
+}
+EXPORT_SYMBOL(super_setup_bdi_name);
+
+/*
+ * Setup private BDI for given superblock. I gets automatically cleaned up
+ * in generic_shutdown_super().
+ */
+int super_setup_bdi(struct super_block *sb)
+{
+ static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
+
+ return super_setup_bdi_name(sb, "%.28s-%ld", sb->s_type->name,
+ atomic_long_inc_return(&bdi_seq));
+}
+EXPORT_SYMBOL(super_setup_bdi);
+
+/*
* This is an internal function, please use sb_end_{write,pagefault,intwrite}
* instead.
*/
{
const struct sysfs_ops *ops = sysfs_file_ops(of->kn);
struct kobject *kobj = of->kn->parent->priv;
- size_t len;
+ ssize_t len;
/*
* If buf != of->prealloc_buf, we don't know how
if (WARN_ON_ONCE(buf != of->prealloc_buf))
return 0;
len = ops->show(kobj, of->kn->priv, buf);
+ if (len < 0)
+ return len;
if (pos) {
if (len <= pos)
return 0;
len -= pos;
memmove(buf, buf + pos, len);
}
- return min(count, len);
+ return min_t(ssize_t, count, len);
}
/* kernfs write callback for regular sysfs files */
#include <linux/math64.h>
#include <linux/uaccess.h>
#include <linux/random.h>
+#include <linux/ctype.h>
#include "ubifs.h"
static DEFINE_SPINLOCK(dbg_lock);
break;
}
- pr_err("\t%d: %s (%s)\n",
- count++, dent->name, get_dent_type(dent->type));
+ pr_err("\t%d: inode %llu, type %s, len %d\n",
+ count++, (unsigned long long) le64_to_cpu(dent->inum),
+ get_dent_type(dent->type),
+ le16_to_cpu(dent->nlen));
fname_name(&nm) = dent->name;
fname_len(&nm) = le16_to_cpu(dent->nlen);
pr_err("(bad name length, not printing, bad or corrupted node)");
else {
for (i = 0; i < nlen && dent->name[i]; i++)
- pr_cont("%c", dent->name[i]);
+ pr_cont("%c", isprint(dent->name[i]) ?
+ dent->name[i] : '?');
}
pr_cont("\n");
}
while (1) {
- dbg_gen("feed '%s', ino %llu, new f_pos %#x",
- dent->name, (unsigned long long)le64_to_cpu(dent->inum),
+ dbg_gen("ino %llu, new f_pos %#x",
+ (unsigned long long)le64_to_cpu(dent->inum),
key_hash_flash(c, &dent->key));
ubifs_assert(le64_to_cpu(dent->ch.sqnum) >
ubifs_inode(dir)->creat_sqnum);
goto out_fname;
lock_2_inodes(dir, inode);
+
+ /* Handle O_TMPFILE corner case, it is allowed to link a O_TMPFILE. */
+ if (inode->i_nlink == 0)
+ ubifs_delete_orphan(c, inode->i_ino);
+
inc_nlink(inode);
ihold(inode);
inode->i_ctime = ubifs_current_time(inode);
dir->i_size -= sz_change;
dir_ui->ui_size = dir->i_size;
drop_nlink(inode);
+ if (inode->i_nlink == 0)
+ ubifs_add_orphan(c, inode->i_ino);
unlock_2_inodes(dir, inode);
ubifs_release_budget(c, &req);
iput(inode);
}
err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm);
- if (err)
+ if (err) {
+ kfree(dev);
goto out_budg;
+ }
sz_change = CALC_DENT_SIZE(fname_len(&nm));
unsigned int uninitialized_var(saved_nlink);
struct fscrypt_name old_nm, new_nm;
- if (flags & ~RENAME_NOREPLACE)
- return -EINVAL;
-
/*
* Budget request settings: deletion direntry, new direntry, removing
* the old inode, and changing old and new parent directory inodes.
}
ubifs_umount(c);
- bdi_destroy(&c->bdi);
ubi_close_volume(c->ubi);
mutex_unlock(&c->umount_mutex);
}
goto out;
}
+ err = ubifs_parse_options(c, data, 0);
+ if (err)
+ goto out_close;
+
/*
* UBIFS provides 'backing_dev_info' in order to disable read-ahead. For
* UBIFS, I/O is not deferred, it is done immediately in readpage,
* which means the user would have to wait not just for their own I/O
* but the read-ahead I/O as well i.e. completely pointless.
*
- * Read-ahead will be disabled because @c->bdi.ra_pages is 0.
+ * Read-ahead will be disabled because @sb->s_bdi->ra_pages is 0. Also
+ * @sb->s_bdi->capabilities are initialized to 0 so there won't be any
+ * writeback happening.
*/
- c->bdi.name = "ubifs",
- c->bdi.capabilities = 0;
- err = bdi_init(&c->bdi);
+ err = super_setup_bdi_name(sb, "ubifs_%d_%d", c->vi.ubi_num,
+ c->vi.vol_id);
if (err)
goto out_close;
- err = bdi_register(&c->bdi, NULL, "ubifs_%d_%d",
- c->vi.ubi_num, c->vi.vol_id);
- if (err)
- goto out_bdi;
-
- err = ubifs_parse_options(c, data, 0);
- if (err)
- goto out_bdi;
- sb->s_bdi = &c->bdi;
sb->s_fs_info = c;
sb->s_magic = UBIFS_SUPER_MAGIC;
sb->s_blocksize = UBIFS_BLOCK_SIZE;
ubifs_umount(c);
out_unlock:
mutex_unlock(&c->umount_mutex);
-out_bdi:
- bdi_destroy(&c->bdi);
out_close:
ubi_close_volume(c->ubi);
out:
* struct ubifs_info - UBIFS file-system description data structure
* (per-superblock).
* @vfs_sb: VFS @struct super_block object
- * @bdi: backing device info object to make VFS happy and disable read-ahead
*
* @highest_inum: highest used inode number
* @max_sqnum: current global sequence number
*/
struct ubifs_info {
struct super_block *vfs_sb;
- struct backing_dev_info bdi;
ino_t highest_inum;
unsigned long long max_sqnum;
extern const struct file_operations ubifs_dir_operations;
extern const struct inode_operations ubifs_dir_inode_operations;
extern const struct inode_operations ubifs_symlink_inode_operations;
-extern struct backing_dev_info ubifs_backing_dev_info;
extern struct ubifs_compressor *ubifs_compressors[UBIFS_COMPR_TYPES_CNT];
/* io.c */
* protocols: aa:... bb:...
*/
seq_printf(m, "pending:\t%lu\ntotal:\t%lu\nAPI:\t%Lx:%x:%Lx\n",
- pending, total, UFFD_API, UFFD_API_FEATURES,
+ pending, total, UFFD_API, ctx->features,
UFFD_API_IOCTLS|UFFD_API_RANGE_IOCTLS);
}
#endif
extern int xfs_dir2_sf_lookup(struct xfs_da_args *args);
extern int xfs_dir2_sf_removename(struct xfs_da_args *args);
extern int xfs_dir2_sf_replace(struct xfs_da_args *args);
-extern int xfs_dir2_sf_verify(struct xfs_mount *mp, struct xfs_dir2_sf_hdr *sfp,
- int size);
+extern int xfs_dir2_sf_verify(struct xfs_inode *ip);
/* xfs_dir2_readdir.c */
extern int xfs_readdir(struct xfs_inode *dp, struct dir_context *ctx,
/* Verify the consistency of an inline directory. */
int
xfs_dir2_sf_verify(
- struct xfs_mount *mp,
- struct xfs_dir2_sf_hdr *sfp,
- int size)
+ struct xfs_inode *ip)
{
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_dir2_sf_hdr *sfp;
struct xfs_dir2_sf_entry *sfep;
struct xfs_dir2_sf_entry *next_sfep;
char *endp;
const struct xfs_dir_ops *dops;
+ struct xfs_ifork *ifp;
xfs_ino_t ino;
int i;
int i8count;
int offset;
+ int size;
+ int error;
__uint8_t filetype;
+ ASSERT(ip->i_d.di_format == XFS_DINODE_FMT_LOCAL);
+ /*
+ * xfs_iread calls us before xfs_setup_inode sets up ip->d_ops,
+ * so we can only trust the mountpoint to have the right pointer.
+ */
dops = xfs_dir_get_ops(mp, NULL);
+ ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
+ sfp = (struct xfs_dir2_sf_hdr *)ifp->if_u1.if_data;
+ size = ifp->if_bytes;
+
/*
* Give up if the directory is way too short.
*/
- XFS_WANT_CORRUPTED_RETURN(mp, size >
- offsetof(struct xfs_dir2_sf_hdr, parent));
- XFS_WANT_CORRUPTED_RETURN(mp, size >=
- xfs_dir2_sf_hdr_size(sfp->i8count));
+ if (size <= offsetof(struct xfs_dir2_sf_hdr, parent) ||
+ size < xfs_dir2_sf_hdr_size(sfp->i8count))
+ return -EFSCORRUPTED;
endp = (char *)sfp + size;
/* Check .. entry */
ino = dops->sf_get_parent_ino(sfp);
i8count = ino > XFS_DIR2_MAX_SHORT_INUM;
- XFS_WANT_CORRUPTED_RETURN(mp, !xfs_dir_ino_validate(mp, ino));
+ error = xfs_dir_ino_validate(mp, ino);
+ if (error)
+ return error;
offset = dops->data_first_offset;
/* Check all reported entries */
* Check the fixed-offset parts of the structure are
* within the data buffer.
*/
- XFS_WANT_CORRUPTED_RETURN(mp,
- ((char *)sfep + sizeof(*sfep)) < endp);
+ if (((char *)sfep + sizeof(*sfep)) >= endp)
+ return -EFSCORRUPTED;
/* Don't allow names with known bad length. */
- XFS_WANT_CORRUPTED_RETURN(mp, sfep->namelen > 0);
- XFS_WANT_CORRUPTED_RETURN(mp, sfep->namelen < MAXNAMELEN);
+ if (sfep->namelen == 0)
+ return -EFSCORRUPTED;
/*
* Check that the variable-length part of the structure is
* name component, so nextentry is an acceptable test.
*/
next_sfep = dops->sf_nextentry(sfp, sfep);
- XFS_WANT_CORRUPTED_RETURN(mp, endp >= (char *)next_sfep);
+ if (endp < (char *)next_sfep)
+ return -EFSCORRUPTED;
/* Check that the offsets always increase. */
- XFS_WANT_CORRUPTED_RETURN(mp,
- xfs_dir2_sf_get_offset(sfep) >= offset);
+ if (xfs_dir2_sf_get_offset(sfep) < offset)
+ return -EFSCORRUPTED;
/* Check the inode number. */
ino = dops->sf_get_ino(sfp, sfep);
i8count += ino > XFS_DIR2_MAX_SHORT_INUM;
- XFS_WANT_CORRUPTED_RETURN(mp, !xfs_dir_ino_validate(mp, ino));
+ error = xfs_dir_ino_validate(mp, ino);
+ if (error)
+ return error;
/* Check the file type. */
filetype = dops->sf_get_ftype(sfep);
- XFS_WANT_CORRUPTED_RETURN(mp, filetype < XFS_DIR3_FT_MAX);
+ if (filetype >= XFS_DIR3_FT_MAX)
+ return -EFSCORRUPTED;
offset = xfs_dir2_sf_get_offset(sfep) +
dops->data_entsize(sfep->namelen);
sfep = next_sfep;
}
- XFS_WANT_CORRUPTED_RETURN(mp, i8count == sfp->i8count);
- XFS_WANT_CORRUPTED_RETURN(mp, (void *)sfep == (void *)endp);
+ if (i8count != sfp->i8count)
+ return -EFSCORRUPTED;
+ if ((void *)sfep != (void *)endp)
+ return -EFSCORRUPTED;
/* Make sure this whole thing ought to be in local format. */
- XFS_WANT_CORRUPTED_RETURN(mp, offset +
- (sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t) +
- (uint)sizeof(xfs_dir2_block_tail_t) <= mp->m_dir_geo->blksize);
+ if (offset + (sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t) +
+ (uint)sizeof(xfs_dir2_block_tail_t) > mp->m_dir_geo->blksize)
+ return -EFSCORRUPTED;
return 0;
}
if (error)
return error;
+ /* Check inline dir contents. */
+ if (S_ISDIR(VFS_I(ip)->i_mode) &&
+ dip->di_format == XFS_DINODE_FMT_LOCAL) {
+ error = xfs_dir2_sf_verify(ip);
+ if (error) {
+ xfs_idestroy_fork(ip, XFS_DATA_FORK);
+ return error;
+ }
+ }
+
if (xfs_is_reflink_inode(ip)) {
ASSERT(ip->i_cowfp == NULL);
xfs_ifork_init_cow(ip);
int whichfork,
int size)
{
- int error;
-
/*
* If the size is unreasonable, then something
* is wrong and we just bail out rather than crash in
return -EFSCORRUPTED;
}
- if (S_ISDIR(VFS_I(ip)->i_mode) && whichfork == XFS_DATA_FORK) {
- error = xfs_dir2_sf_verify(ip->i_mount,
- (struct xfs_dir2_sf_hdr *)XFS_DFORK_DPTR(dip),
- size);
- if (error)
- return error;
- }
-
xfs_init_local_fork(ip, whichfork, XFS_DFORK_PTR(dip, whichfork), size);
return 0;
}
* In these cases, the format always takes precedence, because the
* format indicates the current state of the fork.
*/
-int
+void
xfs_iflush_fork(
xfs_inode_t *ip,
xfs_dinode_t *dip,
char *cp;
xfs_ifork_t *ifp;
xfs_mount_t *mp;
- int error;
static const short brootflag[2] =
{ XFS_ILOG_DBROOT, XFS_ILOG_ABROOT };
static const short dataflag[2] =
{ XFS_ILOG_DEXT, XFS_ILOG_AEXT };
if (!iip)
- return 0;
+ return;
ifp = XFS_IFORK_PTR(ip, whichfork);
/*
* This can happen if we gave up in iformat in an error path,
*/
if (!ifp) {
ASSERT(whichfork == XFS_ATTR_FORK);
- return 0;
+ return;
}
cp = XFS_DFORK_PTR(dip, whichfork);
mp = ip->i_mount;
switch (XFS_IFORK_FORMAT(ip, whichfork)) {
case XFS_DINODE_FMT_LOCAL:
- if (S_ISDIR(VFS_I(ip)->i_mode) && whichfork == XFS_DATA_FORK) {
- error = xfs_dir2_sf_verify(mp,
- (struct xfs_dir2_sf_hdr *)ifp->if_u1.if_data,
- ifp->if_bytes);
- if (error)
- return error;
- }
if ((iip->ili_fields & dataflag[whichfork]) &&
(ifp->if_bytes > 0)) {
ASSERT(ifp->if_u1.if_data != NULL);
ASSERT(0);
break;
}
- return 0;
}
/*
struct xfs_ifork *xfs_iext_state_to_fork(struct xfs_inode *ip, int state);
int xfs_iformat_fork(struct xfs_inode *, struct xfs_dinode *);
-int xfs_iflush_fork(struct xfs_inode *, struct xfs_dinode *,
+void xfs_iflush_fork(struct xfs_inode *, struct xfs_dinode *,
struct xfs_inode_log_item *, int);
void xfs_idestroy_fork(struct xfs_inode *, int);
void xfs_idata_realloc(struct xfs_inode *, int, int);
return blkdev_issue_zeroout(xfs_find_bdev_for_inode(VFS_I(ip)),
block << (mp->m_super->s_blocksize_bits - 9),
count_fsb << (mp->m_super->s_blocksize_bits - 9),
- GFP_NOFS, true);
+ GFP_NOFS, 0);
}
int
/*
* Now that we've unmap all full blocks we'll have to zero out any
* partial block at the beginning and/or end. xfs_zero_range is
- * smart enough to skip any holes, including those we just created.
+ * smart enough to skip any holes, including those we just created,
+ * but we must take care not to zero beyond EOF and enlarge i_size.
*/
+
+ if (offset >= XFS_ISIZE(ip))
+ return 0;
+
+ if (offset + len > XFS_ISIZE(ip))
+ len = XFS_ISIZE(ip) - offset;
+
return xfs_zero_range(ip, offset, len, NULL);
}
#include "xfs_log.h"
#include "xfs_bmap_btree.h"
#include "xfs_reflink.h"
+#include "xfs_dir2_priv.h"
kmem_zone_t *xfs_inode_zone;
struct xfs_inode_log_item *iip = ip->i_itemp;
struct xfs_dinode *dip;
struct xfs_mount *mp = ip->i_mount;
- int error;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
ASSERT(xfs_isiflocked(ip));
if (ip->i_d.di_version < 3)
ip->i_d.di_flushiter++;
+ /* Check the inline directory data. */
+ if (S_ISDIR(VFS_I(ip)->i_mode) &&
+ ip->i_d.di_format == XFS_DINODE_FMT_LOCAL &&
+ xfs_dir2_sf_verify(ip))
+ goto corrupt_out;
+
/*
* Copy the dirty parts of the inode into the on-disk inode. We always
* copy out the core of the inode, because if the inode is dirty at all
if (ip->i_d.di_flushiter == DI_MAX_FLUSH)
ip->i_d.di_flushiter = 0;
- error = xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK);
- if (error)
- return error;
- if (XFS_IFORK_Q(ip)) {
- error = xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK);
- if (error)
- return error;
- }
+ xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK);
+ if (XFS_IFORK_Q(ip))
+ xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK);
xfs_inobp_check(mp, bp);
/*
stat->blocks =
XFS_FSB_TO_BB(mp, ip->i_d.di_nblocks + ip->i_delayed_blks);
+ if (ip->i_d.di_version == 3) {
+ if (request_mask & STATX_BTIME) {
+ stat->result_mask |= STATX_BTIME;
+ stat->btime.tv_sec = ip->i_d.di_crtime.t_sec;
+ stat->btime.tv_nsec = ip->i_d.di_crtime.t_nsec;
+ }
+ }
+
+ if (ip->i_d.di_flags & XFS_DIFLAG_IMMUTABLE)
+ stat->attributes |= STATX_ATTR_IMMUTABLE;
+ if (ip->i_d.di_flags & XFS_DIFLAG_APPEND)
+ stat->attributes |= STATX_ATTR_APPEND;
+ if (ip->i_d.di_flags & XFS_DIFLAG_NODUMP)
+ stat->attributes |= STATX_ATTR_NODUMP;
switch (inode->i_mode & S_IFMT) {
case S_IFBLK:
return error;
bcount = MIN(left, (int)(PAGE_SIZE / sizeof(*buffer)));
- buffer = kmem_alloc(bcount * sizeof(*buffer), KM_SLEEP);
+ buffer = kmem_zalloc(bcount * sizeof(*buffer), KM_SLEEP);
do {
struct xfs_inobt_rec_incore r;
int stat;
}
bool acpi_dev_found(const char *hid);
+bool acpi_dev_present(const char *hid, const char *uid, s64 hrv);
#ifdef CONFIG_ACPI
const char *name;
acpi_handle handle;
struct fwnode_handle fwnode;
+ struct fwnode_handle *parent;
struct acpi_device_data data;
struct list_head sibling;
struct kobject kobj;
u32 highest_perf;
u32 nominal_perf;
u32 lowest_perf;
+ u32 lowest_nonlinear_perf;
};
struct cppc_perf_ctrls {
u64 reference;
u64 delivered;
u64 reference_perf;
- u64 ctr_wrap_time;
+ u64 wraparound_time;
};
/* Per CPU container for runtime CPPC management. */
--- /dev/null
+#ifndef __ASM_GENERIC_EXTABLE_H
+#define __ASM_GENERIC_EXTABLE_H
+
+/*
+ * The exception table consists of pairs of addresses: the first is the
+ * address of an instruction that is allowed to fault, and the second is
+ * the address at which the program should continue. No registers are
+ * modified, so it is entirely up to the continuation code to figure out
+ * what to do.
+ *
+ * All the routines below use bits of fixup code that are out of line
+ * with the main instruction path. This means when everything is well,
+ * we don't even have to jump over them. Further, they do not intrude
+ * on our cache or tlb entries.
+ */
+
+struct exception_table_entry
+{
+ unsigned long insn, fixup;
+};
+
+
+struct pt_regs;
+extern int fixup_exception(struct pt_regs *regs);
+
+#endif
* on any machine that has kernel and user data in the same
* address space, e.g. all NOMMU machines.
*/
-#include <linux/sched.h>
#include <linux/string.h>
#include <asm/segment.h>
#define segment_eq(a, b) ((a).seg == (b).seg)
#endif
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
#define access_ok(type, addr, size) __access_ok((unsigned long)(addr),(size))
/*
#endif
/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue. No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path. This means when everything is well,
- * we don't even have to jump over them. Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry
-{
- unsigned long insn, fixup;
-};
-
-/*
- * architectures with an MMU should override these two
- */
-#ifndef __copy_from_user
-static inline __must_check long __copy_from_user(void *to,
- const void __user * from, unsigned long n)
-{
- if (__builtin_constant_p(n)) {
- switch(n) {
- case 1:
- *(u8 *)to = *(u8 __force *)from;
- return 0;
- case 2:
- *(u16 *)to = *(u16 __force *)from;
- return 0;
- case 4:
- *(u32 *)to = *(u32 __force *)from;
- return 0;
-#ifdef CONFIG_64BIT
- case 8:
- *(u64 *)to = *(u64 __force *)from;
- return 0;
-#endif
- default:
- break;
- }
- }
-
- memcpy(to, (const void __force *)from, n);
- return 0;
-}
-#endif
-
-#ifndef __copy_to_user
-static inline __must_check long __copy_to_user(void __user *to,
- const void *from, unsigned long n)
-{
- if (__builtin_constant_p(n)) {
- switch(n) {
- case 1:
- *(u8 __force *)to = *(u8 *)from;
- return 0;
- case 2:
- *(u16 __force *)to = *(u16 *)from;
- return 0;
- case 4:
- *(u32 __force *)to = *(u32 *)from;
- return 0;
-#ifdef CONFIG_64BIT
- case 8:
- *(u64 __force *)to = *(u64 *)from;
- return 0;
-#endif
- default:
- break;
- }
- }
-
- memcpy((void __force *)to, from, n);
- return 0;
-}
-#endif
-
-/*
* These are the main single-value transfer routines. They automatically
* use the right size if we just have the right pointer type.
* This version just falls back to copy_{from,to}_user, which should
static inline int __put_user_fn(size_t size, void __user *ptr, void *x)
{
- size = __copy_to_user(ptr, x, size);
- return size ? -EFAULT : size;
+ return unlikely(raw_copy_to_user(ptr, x, size)) ? -EFAULT : 0;
}
#define __put_user_fn(sz, u, k) __put_user_fn(sz, u, k)
__chk_user_ptr(ptr); \
switch (sizeof(*(ptr))) { \
case 1: { \
- unsigned char __x; \
+ unsigned char __x = 0; \
__gu_err = __get_user_fn(sizeof (*(ptr)), \
ptr, &__x); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
break; \
}; \
case 2: { \
- unsigned short __x; \
+ unsigned short __x = 0; \
__gu_err = __get_user_fn(sizeof (*(ptr)), \
ptr, &__x); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
break; \
}; \
case 4: { \
- unsigned int __x; \
+ unsigned int __x = 0; \
__gu_err = __get_user_fn(sizeof (*(ptr)), \
ptr, &__x); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
break; \
}; \
case 8: { \
- unsigned long long __x; \
+ unsigned long long __x = 0; \
__gu_err = __get_user_fn(sizeof (*(ptr)), \
ptr, &__x); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
#ifndef __get_user_fn
static inline int __get_user_fn(size_t size, const void __user *ptr, void *x)
{
- size_t n = __copy_from_user(x, ptr, size);
- if (unlikely(n)) {
- memset(x + (size - n), 0, n);
- return -EFAULT;
- }
- return 0;
+ return unlikely(raw_copy_from_user(x, ptr, size)) ? -EFAULT : 0;
}
#define __get_user_fn(sz, u, k) __get_user_fn(sz, u, k)
extern int __get_user_bad(void) __attribute__((noreturn));
-#ifndef __copy_from_user_inatomic
-#define __copy_from_user_inatomic __copy_from_user
-#endif
-
-#ifndef __copy_to_user_inatomic
-#define __copy_to_user_inatomic __copy_to_user
-#endif
-
-static inline long copy_from_user(void *to,
- const void __user * from, unsigned long n)
-{
- unsigned long res = n;
- might_fault();
- if (likely(access_ok(VERIFY_READ, from, n)))
- res = __copy_from_user(to, from, n);
- if (unlikely(res))
- memset(to + (n - res), 0, res);
- return res;
-}
-
-static inline long copy_to_user(void __user *to,
- const void *from, unsigned long n)
-{
- might_fault();
- if (access_ok(VERIFY_WRITE, to, n))
- return __copy_to_user(to, from, n);
- else
- return n;
-}
-
/*
* Copy a null terminated string from userspace.
*/
return __clear_user(to, n);
}
+#include <asm/extable.h>
+
#endif /* __ASM_GENERIC_UACCESS_H */
*/
#ifndef RO_AFTER_INIT_DATA
#define RO_AFTER_INIT_DATA \
- __start_ro_after_init = .; \
+ VMLINUX_SYMBOL(__start_ro_after_init) = .; \
*(.data..ro_after_init) \
- __end_ro_after_init = .;
+ VMLINUX_SYMBOL(__end_ro_after_init) = .;
#endif
/*
#ifndef __CLKSOURCE_ARM_ARCH_TIMER_H
#define __CLKSOURCE_ARM_ARCH_TIMER_H
+#include <linux/bitops.h>
#include <linux/timecounter.h>
#include <linux/types.h>
+#define ARCH_TIMER_TYPE_CP15 BIT(0)
+#define ARCH_TIMER_TYPE_MEM BIT(1)
+
#define ARCH_TIMER_CTRL_ENABLE (1 << 0)
#define ARCH_TIMER_CTRL_IT_MASK (1 << 1)
#define ARCH_TIMER_CTRL_IT_STAT (1 << 2)
ARCH_TIMER_REG_TVAL,
};
+enum arch_timer_ppi_nr {
+ ARCH_TIMER_PHYS_SECURE_PPI,
+ ARCH_TIMER_PHYS_NONSECURE_PPI,
+ ARCH_TIMER_VIRT_PPI,
+ ARCH_TIMER_HYP_PPI,
+ ARCH_TIMER_MAX_TIMER_PPI
+};
+
+enum arch_timer_spi_nr {
+ ARCH_TIMER_PHYS_SPI,
+ ARCH_TIMER_VIRT_SPI,
+ ARCH_TIMER_MAX_TIMER_SPI
+};
+
#define ARCH_TIMER_PHYS_ACCESS 0
#define ARCH_TIMER_VIRT_ACCESS 1
#define ARCH_TIMER_MEM_PHYS_ACCESS 2
#define ARCH_TIMER_MEM_VIRT_ACCESS 3
+#define ARCH_TIMER_MEM_MAX_FRAMES 8
+
#define ARCH_TIMER_USR_PCT_ACCESS_EN (1 << 0) /* physical counter */
#define ARCH_TIMER_USR_VCT_ACCESS_EN (1 << 1) /* virtual counter */
#define ARCH_TIMER_VIRT_EVT_EN (1 << 2)
int virtual_irq;
};
+struct arch_timer_mem_frame {
+ bool valid;
+ phys_addr_t cntbase;
+ size_t size;
+ int phys_irq;
+ int virt_irq;
+};
+
+struct arch_timer_mem {
+ phys_addr_t cntctlbase;
+ size_t size;
+ struct arch_timer_mem_frame frame[ARCH_TIMER_MEM_MAX_FRAMES];
+};
+
#ifdef CONFIG_ARM_ARCH_TIMER
extern u32 arch_timer_get_rate(void);
return crypto_alloc_instance2(name, alg, ahash_instance_headroom());
}
+static inline void ahash_request_complete(struct ahash_request *req, int err)
+{
+ req->base.complete(&req->base, err);
+}
+
+static inline u32 ahash_request_flags(struct ahash_request *req)
+{
+ return req->base.flags;
+}
+
static inline struct crypto_ahash *crypto_spawn_ahash(
struct crypto_ahash_spawn *spawn)
{
void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu);
int kvm_vgic_map_resources(struct kvm *kvm);
int kvm_vgic_hyp_init(void);
+void kvm_vgic_init_cpu_hardware(void);
int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid,
bool level);
int acpi_table_init (void);
int acpi_table_parse(char *id, acpi_tbl_table_handler handler);
-int __init acpi_parse_entries(char *id, unsigned long table_size,
- acpi_tbl_entry_handler handler,
- struct acpi_table_header *table_header,
- int entry_id, unsigned int max_entries);
int __init acpi_table_parse_entries(char *id, unsigned long table_size,
int entry_id,
acpi_tbl_entry_handler handler,
int acpi_reconfig_notifier_register(struct notifier_block *nb);
int acpi_reconfig_notifier_unregister(struct notifier_block *nb);
+#ifdef CONFIG_ACPI_GTDT
+int acpi_gtdt_init(struct acpi_table_header *table, int *platform_timer_count);
+int acpi_gtdt_map_ppi(int type);
+bool acpi_gtdt_c3stop(int type);
+int acpi_arch_timer_mem_init(struct arch_timer_mem *timer_mem, int *timer_count);
+#endif
+
#else /* !CONFIG_ACPI */
#define acpi_disabled 1
return false;
}
+static inline bool acpi_dev_present(const char *hid, const char *uid, s64 hrv)
+{
+ return false;
+}
+
static inline bool is_acpi_node(struct fwnode_handle *fwnode)
{
return false;
int acpi_dev_prop_read(struct acpi_device *adev, const char *propname,
enum dev_prop_type proptype, void *val, size_t nval);
-struct fwnode_handle *acpi_get_next_subnode(struct device *dev,
- struct fwnode_handle *subnode);
+struct fwnode_handle *acpi_get_next_subnode(struct fwnode_handle *fwnode,
+ struct fwnode_handle *child);
+struct fwnode_handle *acpi_node_get_parent(struct fwnode_handle *fwnode);
+
+struct fwnode_handle *acpi_graph_get_next_endpoint(struct fwnode_handle *fwnode,
+ struct fwnode_handle *prev);
+int acpi_graph_get_remote_endpoint(struct fwnode_handle *fwnode,
+ struct fwnode_handle **remote,
+ struct fwnode_handle **port,
+ struct fwnode_handle **endpoint);
struct acpi_probe_entry;
typedef bool (*acpi_probe_entry_validate_subtbl)(struct acpi_subtable_header *,
return -ENXIO;
}
-static inline struct fwnode_handle *acpi_get_next_subnode(struct device *dev,
- struct fwnode_handle *subnode)
+static inline struct fwnode_handle *
+acpi_get_next_subnode(struct fwnode_handle *fwnode, struct fwnode_handle *child)
+{
+ return NULL;
+}
+
+static inline struct fwnode_handle *
+acpi_node_get_parent(struct fwnode_handle *fwnode)
{
return NULL;
}
+static inline struct fwnode_handle *
+acpi_graph_get_next_endpoint(struct fwnode_handle *fwnode,
+ struct fwnode_handle *prev)
+{
+ return ERR_PTR(-ENXIO);
+}
+
+static inline int
+acpi_graph_get_remote_endpoint(struct fwnode_handle *fwnode,
+ struct fwnode_handle **remote,
+ struct fwnode_handle **port,
+ struct fwnode_handle **endpoint)
+{
+ return -ENXIO;
+}
+
#define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, valid, data, fn) \
static const void * __acpi_table_##name[] \
__attribute__((unused)) \
return id[ATA_ID_SCT_CMD_XPORT] & (1 << 3) ? true : false;
}
-static inline bool ata_id_sct_write_same(const u16 *id)
-{
- return id[ATA_ID_SCT_CMD_XPORT] & (1 << 2) ? true : false;
-}
-
static inline bool ata_id_sct_long_sector_access(const u16 *id)
{
return id[ATA_ID_SCT_CMD_XPORT] & (1 << 1) ? true : false;
#endif
#endif /* atomic_cmpxchg_relaxed */
+#ifndef atomic_try_cmpxchg
+
+#define __atomic_try_cmpxchg(type, _p, _po, _n) \
+({ \
+ typeof(_po) __po = (_po); \
+ typeof(*(_po)) __r, __o = *__po; \
+ __r = atomic_cmpxchg##type((_p), __o, (_n)); \
+ if (unlikely(__r != __o)) \
+ *__po = __r; \
+ likely(__r == __o); \
+})
+
+#define atomic_try_cmpxchg(_p, _po, _n) __atomic_try_cmpxchg(, _p, _po, _n)
+#define atomic_try_cmpxchg_relaxed(_p, _po, _n) __atomic_try_cmpxchg(_relaxed, _p, _po, _n)
+#define atomic_try_cmpxchg_acquire(_p, _po, _n) __atomic_try_cmpxchg(_acquire, _p, _po, _n)
+#define atomic_try_cmpxchg_release(_p, _po, _n) __atomic_try_cmpxchg(_release, _p, _po, _n)
+
+#else /* atomic_try_cmpxchg */
+#define atomic_try_cmpxchg_relaxed atomic_try_cmpxchg
+#define atomic_try_cmpxchg_acquire atomic_try_cmpxchg
+#define atomic_try_cmpxchg_release atomic_try_cmpxchg
+#endif /* atomic_try_cmpxchg */
+
/* cmpxchg_relaxed */
#ifndef cmpxchg_relaxed
#define cmpxchg_relaxed cmpxchg
#endif
#endif /* atomic64_cmpxchg_relaxed */
+#ifndef atomic64_try_cmpxchg
+
+#define __atomic64_try_cmpxchg(type, _p, _po, _n) \
+({ \
+ typeof(_po) __po = (_po); \
+ typeof(*(_po)) __r, __o = *__po; \
+ __r = atomic64_cmpxchg##type((_p), __o, (_n)); \
+ if (unlikely(__r != __o)) \
+ *__po = __r; \
+ likely(__r == __o); \
+})
+
+#define atomic64_try_cmpxchg(_p, _po, _n) __atomic64_try_cmpxchg(, _p, _po, _n)
+#define atomic64_try_cmpxchg_relaxed(_p, _po, _n) __atomic64_try_cmpxchg(_relaxed, _p, _po, _n)
+#define atomic64_try_cmpxchg_acquire(_p, _po, _n) __atomic64_try_cmpxchg(_acquire, _p, _po, _n)
+#define atomic64_try_cmpxchg_release(_p, _po, _n) __atomic64_try_cmpxchg(_release, _p, _po, _n)
+
+#else /* atomic64_try_cmpxchg */
+#define atomic64_try_cmpxchg_relaxed atomic64_try_cmpxchg
+#define atomic64_try_cmpxchg_acquire atomic64_try_cmpxchg
+#define atomic64_try_cmpxchg_release atomic64_try_cmpxchg
+#endif /* atomic64_try_cmpxchg */
+
#ifndef atomic64_andnot
static inline void atomic64_andnot(long long i, atomic64_t *v)
{
*/
enum wb_state {
WB_registered, /* bdi_register() was done */
+ WB_shutting_down, /* wb_shutdown() in progress */
WB_writeback_running, /* Writeback is in progress */
WB_has_dirty_io, /* Dirty inodes on ->b_{dirty|io|more_io} */
};
atomic_t refcnt; /* nr of attached wb's and blkg */
#ifdef CONFIG_CGROUP_WRITEBACK
- struct backing_dev_info *bdi; /* the associated bdi */
+ struct backing_dev_info *__bdi; /* the associated bdi, set to NULL
+ * on bdi unregistration. For memcg-wb
+ * internal use only! */
int blkcg_id; /* ID of the associated blkcg */
struct rb_node rb_node; /* on bdi->cgwb_congestion_tree */
#endif
congested_fn *congested_fn; /* Function pointer if device is md/dm */
void *congested_data; /* Pointer to aux data for congested func */
- char *name;
+ const char *name;
struct kref refcnt; /* Reference counter for the structure */
unsigned int capabilities; /* Device capabilities */
#ifdef CONFIG_CGROUP_WRITEBACK
struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */
struct rb_root cgwb_congested_tree; /* their congested states */
- atomic_t usage_cnt; /* counts both cgwbs and cgwb_contested's */
#else
struct bdi_writeback_congested *wb_congested;
#endif
#include <linux/backing-dev-defs.h>
#include <linux/slab.h>
-int __must_check bdi_init(struct backing_dev_info *bdi);
-
static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi)
{
kref_get(&bdi->refcnt);
void bdi_put(struct backing_dev_info *bdi);
-__printf(3, 4)
-int bdi_register(struct backing_dev_info *bdi, struct device *parent,
- const char *fmt, ...);
-int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev);
+__printf(2, 3)
+int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...);
+int bdi_register_va(struct backing_dev_info *bdi, const char *fmt,
+ va_list args);
int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner);
void bdi_unregister(struct backing_dev_info *bdi);
-int __must_check bdi_setup_and_register(struct backing_dev_info *, char *);
-void bdi_destroy(struct backing_dev_info *bdi);
struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id);
+static inline struct backing_dev_info *bdi_alloc(gfp_t gfp_mask)
+{
+ return bdi_alloc_node(gfp_mask, NUMA_NO_NODE);
+}
void wb_start_writeback(struct bdi_writeback *wb, long nr_pages,
bool range_cyclic, enum wb_reason reason);
extern void bioset_free(struct bio_set *);
extern mempool_t *biovec_create_pool(int pool_entries);
-extern struct bio *bio_alloc_bioset(gfp_t, int, struct bio_set *);
+extern struct bio *bio_alloc_bioset(gfp_t, unsigned int, struct bio_set *);
extern void bio_put(struct bio *);
extern void __bio_clone_fast(struct bio *, struct bio *);
unsigned long state; /* BLK_MQ_S_* flags */
} ____cacheline_aligned_in_smp;
- struct work_struct run_work;
+ struct delayed_work run_work;
cpumask_var_t cpumask;
int next_cpu;
int next_cpu_batch;
atomic_t nr_active;
- struct delayed_work delay_work;
-
struct hlist_node cpuhp_dead;
struct kobject kobj;
struct blk_mq_queue_data {
struct request *rq;
- struct list_head *list;
bool last;
};
reinit_request_fn *reinit_request;
map_queues_fn *map_queues;
+
+#ifdef CONFIG_BLK_DEBUG_FS
+ /*
+ * Used by the debugfs implementation to show driver-specific
+ * information about a request.
+ */
+ void (*show_rq)(struct seq_file *m, struct request *rq);
+#endif
};
enum {
BLK_MQ_F_SHOULD_MERGE = 1 << 0,
BLK_MQ_F_TAG_SHARED = 1 << 1,
BLK_MQ_F_SG_MERGE = 1 << 2,
- BLK_MQ_F_DEFER_ISSUE = 1 << 4,
BLK_MQ_F_BLOCKING = 1 << 5,
BLK_MQ_F_NO_SCHED = 1 << 6,
BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
BLK_MQ_S_TAG_ACTIVE = 1,
BLK_MQ_S_SCHED_RESTART = 2,
BLK_MQ_S_TAG_WAITING = 3,
+ BLK_MQ_S_START_ON_RUN = 4,
BLK_MQ_MAX_DEPTH = 10240,
void blk_mq_kick_requeue_list(struct request_queue *q);
void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs);
void blk_mq_abort_requeue_list(struct request_queue *q);
-void blk_mq_complete_request(struct request *rq, int error);
+void blk_mq_complete_request(struct request *rq);
bool blk_mq_queue_stopped(struct request_queue *q);
void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx);
void blk_mq_start_hw_queues(struct request_queue *q);
void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async);
+void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
+void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
void blk_mq_run_hw_queues(struct request_queue *q, bool async);
void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
busy_tag_iter_fn *fn, void *priv);
void blk_mq_freeze_queue(struct request_queue *q);
void blk_mq_unfreeze_queue(struct request_queue *q);
-void blk_mq_freeze_queue_start(struct request_queue *q);
+void blk_freeze_queue_start(struct request_queue *q);
void blk_mq_freeze_queue_wait(struct request_queue *q);
int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
unsigned long timeout);
struct cgroup_subsys_state;
typedef void (bio_end_io_t) (struct bio *);
+struct blk_issue_stat {
+ u64 stat;
+};
+
/*
* main unit of I/O for the block layer and lower layers (ie drivers and
* stacking drivers)
* top bits REQ_OP. Use
* accessors.
*/
- unsigned short bi_flags; /* status, command, etc */
+ unsigned short bi_flags; /* status, etc and bvec pool number */
unsigned short bi_ioprio;
struct bvec_iter bi_iter;
*/
struct io_context *bi_ioc;
struct cgroup_subsys_state *bi_css;
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+ void *bi_cg_private;
+ struct blk_issue_stat bi_issue_stat;
+#endif
#endif
union {
#if defined(CONFIG_BLK_DEV_INTEGRITY)
#define BIO_REFFED 8 /* bio has elevated ->bi_cnt */
#define BIO_THROTTLED 9 /* This bio has already been subjected to
* throttling rules. Don't do it again. */
-
-/*
- * Flags starting here get preserved by bio_reset() - this includes
- * BVEC_POOL_IDX()
- */
-#define BIO_RESET_BITS 10
+#define BIO_TRACE_COMPLETION 10 /* bio_endio() should trace the final completion
+ * of this bio. */
+/* See BVEC_POOL_OFFSET below before adding new flags */
/*
* We support 6 different bvec pools, the last one is magic in that it
#define BVEC_POOL_MAX (BVEC_POOL_NR - 1)
/*
- * Top 4 bits of bio flags indicate the pool the bvecs came from. We add
+ * Top 3 bits of bio flags indicate the pool the bvecs came from. We add
* 1 to the actual index so that 0 indicates that there are no bvecs to be
* freed.
*/
-#define BVEC_POOL_BITS (4)
+#define BVEC_POOL_BITS (3)
#define BVEC_POOL_OFFSET (16 - BVEC_POOL_BITS)
#define BVEC_POOL_IDX(bio) ((bio)->bi_flags >> BVEC_POOL_OFFSET)
+#if (1<< BVEC_POOL_BITS) < (BVEC_POOL_NR+1)
+# error "BVEC_POOL_BITS is too small"
+#endif
+
+/*
+ * Flags starting here get preserved by bio_reset() - this includes
+ * only BVEC_POOL_IDX()
+ */
+#define BIO_RESET_BITS BVEC_POOL_OFFSET
/*
* Operations and flags common to the bio and request structures.
/* write the same sector many times */
REQ_OP_WRITE_SAME = 7,
/* write the zero filled sector many times */
- REQ_OP_WRITE_ZEROES = 8,
+ REQ_OP_WRITE_ZEROES = 9,
/* SCSI passthrough using struct scsi_request */
REQ_OP_SCSI_IN = 32,
__REQ_PREFLUSH, /* request for cache flush */
__REQ_RAHEAD, /* read ahead, can fail anytime */
__REQ_BACKGROUND, /* background IO */
+
+ /* command specific flags for REQ_OP_WRITE_ZEROES: */
+ __REQ_NOUNMAP, /* do not free blocks when zeroing */
+
__REQ_NR_BITS, /* stops here */
};
#define REQ_RAHEAD (1ULL << __REQ_RAHEAD)
#define REQ_BACKGROUND (1ULL << __REQ_BACKGROUND)
+#define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP)
+
#define REQ_FAILFAST_MASK \
(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
return (cookie & BLK_QC_T_INTERNAL) != 0;
}
-struct blk_issue_stat {
- u64 time;
-};
-
-#define BLK_RQ_STAT_BATCH 64
-
struct blk_rq_stat {
s64 mean;
u64 min;
s32 nr_samples;
s32 nr_batch;
u64 batch;
- s64 time;
};
#endif /* __LINUX_BLK_TYPES_H */
struct blk_flush_queue;
struct pr_ops;
struct rq_wb;
+struct blk_queue_stats;
+struct blk_stat_callback;
#define BLKDEV_MIN_RQ 4
#define BLKDEV_MAX_RQ 128 /* Default maximum */
+/* Must be consisitent with blk_mq_poll_stats_bkt() */
+#define BLK_MQ_POLL_STATS_BKTS 16
+
/*
* Maximum number of blkcg policies allowed to be registered concurrently.
* Defined here to simplify include dependency.
*/
-#define BLKCG_MAX_POLS 2
+#define BLKCG_MAX_POLS 3
typedef void (rq_end_io_fn)(struct request *, int);
struct rb_node rb_node; /* sort/lookup */
struct bio_vec special_vec;
void *completion_data;
+ int error_count; /* for legacy drivers, don't use */
};
/*
unsigned short ioprio;
- void *special; /* opaque pointer available for LLD use */
+ unsigned int timeout;
- int errors;
+ void *special; /* opaque pointer available for LLD use */
unsigned int extra_len; /* length of alignment and padding */
unsigned long deadline;
struct list_head timeout_list;
- unsigned int timeout;
- int retries;
/*
* completion callback.
unsigned char misaligned;
unsigned char discard_misaligned;
unsigned char cluster;
- unsigned char discard_zeroes_data;
unsigned char raid_partial_stripes_expensive;
enum blk_zoned_model zoned;
};
int nr_rqs[2]; /* # allocated [a]sync rqs */
int nr_rqs_elvpriv; /* # allocated rqs w/ elvpriv */
+ struct blk_queue_stats *stats;
struct rq_wb *rq_wb;
/*
unsigned int nr_sorted;
unsigned int in_flight[2];
- struct blk_rq_stat rq_stats[2];
-
/*
* Number of active block driver functions for which blk_drain_queue()
* must wait. Must be incremented around functions that unlock the
unsigned int rq_timeout;
int poll_nsec;
+
+ struct blk_stat_callback *poll_cb;
+ struct blk_rq_stat poll_stat[BLK_MQ_POLL_STATS_BKTS];
+
struct timer_list timeout;
struct work_struct timeout_work;
struct list_head timeout_list;
#define QUEUE_FLAG_FLUSH_NQ 25 /* flush not queueuable */
#define QUEUE_FLAG_DAX 26 /* device supports DAX */
#define QUEUE_FLAG_STATS 27 /* track rq completion times */
-#define QUEUE_FLAG_RESTART 28 /* queue needs restart at completion */
+#define QUEUE_FLAG_POLL_STATS 28 /* collecting stats for hybrid polling */
+#define QUEUE_FLAG_REGISTERED 29 /* queue has been registered to a disk */
#define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \
(1 << QUEUE_FLAG_STACKABLE) | \
extern void blk_unregister_queue(struct gendisk *disk);
extern blk_qc_t generic_make_request(struct bio *bio);
extern void blk_rq_init(struct request_queue *q, struct request *rq);
+extern void blk_init_request_from_bio(struct request *req, struct bio *bio);
extern void blk_put_request(struct request *);
extern void __blk_put_request(struct request_queue *, struct request *);
extern struct request *blk_get_request(struct request_queue *, int, gfp_t);
extern int blk_rq_map_user_iov(struct request_queue *, struct request *,
struct rq_map_data *, const struct iov_iter *,
gfp_t);
-extern int blk_execute_rq(struct request_queue *, struct gendisk *,
+extern void blk_execute_rq(struct request_queue *, struct gendisk *,
struct request *, int);
extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *,
struct request *, int, rq_end_io_fn *);
}
/*
- * blk_rq_set_prio - associate a request with prio from ioc
- * @rq: request of interest
- * @ioc: target iocontext
- *
- * Assocate request prio with ioc prio so request based drivers
- * can leverage priority information.
- */
-static inline void blk_rq_set_prio(struct request *rq, struct io_context *ioc)
-{
- if (ioc)
- rq->ioprio = ioc->ioprio;
-}
-
-/*
* Request issue related functions.
*/
extern struct request *blk_peek_request(struct request_queue *q);
extern bool blk_end_request(struct request *rq, int error,
unsigned int nr_bytes);
extern void blk_end_request_all(struct request *rq, int error);
-extern bool blk_end_request_cur(struct request *rq, int error);
-extern bool blk_end_request_err(struct request *rq, int error);
extern bool __blk_end_request(struct request *rq, int error,
unsigned int nr_bytes);
extern void __blk_end_request_all(struct request *rq, int error);
extern bool __blk_end_request_cur(struct request *rq, int error);
-extern bool __blk_end_request_err(struct request *rq, int error);
extern void blk_complete_request(struct request *);
extern void __blk_complete_request(struct request *);
return bqt->tag_index[tag];
}
+extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *);
+extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
+ sector_t nr_sects, gfp_t gfp_mask, struct page *page);
#define BLKDEV_DISCARD_SECURE (1 << 0) /* issue a secure erase */
-#define BLKDEV_DISCARD_ZERO (1 << 1) /* must reliably zero data */
-extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *);
extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask, unsigned long flags);
extern int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask, int flags,
struct bio **biop);
-extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
- sector_t nr_sects, gfp_t gfp_mask, struct page *page);
+
+#define BLKDEV_ZERO_NOUNMAP (1 << 0) /* do not free blocks */
+#define BLKDEV_ZERO_NOFALLBACK (1 << 1) /* don't write explicit zeroes */
+
extern int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask, struct bio **biop,
- bool discard);
+ unsigned flags);
extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
- sector_t nr_sects, gfp_t gfp_mask, bool discard);
+ sector_t nr_sects, gfp_t gfp_mask, unsigned flags);
+
static inline int sb_issue_discard(struct super_block *sb, sector_t block,
sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags)
{
return blkdev_issue_zeroout(sb->s_bdev,
block << (sb->s_blocksize_bits - 9),
nr_blocks << (sb->s_blocksize_bits - 9),
- gfp_mask, true);
+ gfp_mask, 0);
}
extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm);
return q->limits.discard_alignment;
}
-static inline unsigned int queue_discard_zeroes_data(struct request_queue *q)
-{
- if (q->limits.max_discard_sectors && q->limits.discard_zeroes_data == 1)
- return 1;
-
- return 0;
-}
-
-static inline unsigned int bdev_discard_zeroes_data(struct block_device *bdev)
-{
- return queue_discard_zeroes_data(bdev_get_queue(bdev));
-}
-
static inline unsigned int bdev_write_same(struct block_device *bdev)
{
struct request_queue *q = bdev_get_queue(bdev);
return true;
}
-static inline bool bio_will_gap(struct request_queue *q, struct bio *prev,
- struct bio *next)
+static inline bool bio_will_gap(struct request_queue *q,
+ struct request *prev_rq,
+ struct bio *prev,
+ struct bio *next)
{
if (bio_has_data(prev) && queue_virt_boundary(q)) {
struct bio_vec pb, nb;
+ /*
+ * don't merge if the 1st bio starts with non-zero
+ * offset, otherwise it is quite difficult to respect
+ * sg gap limit. We work hard to merge a huge number of small
+ * single bios in case of mkfs.
+ */
+ if (prev_rq)
+ bio_get_first_bvec(prev_rq->bio, &pb);
+ else
+ bio_get_first_bvec(prev, &pb);
+ if (pb.bv_offset)
+ return true;
+
+ /*
+ * We don't need to worry about the situation that the
+ * merged segment ends in unaligned virt boundary:
+ *
+ * - if 'pb' ends aligned, the merged segment ends aligned
+ * - if 'pb' ends unaligned, the next bio must include
+ * one single bvec of 'nb', otherwise the 'nb' can't
+ * merge with 'pb'
+ */
bio_get_last_bvec(prev, &pb);
bio_get_first_bvec(next, &nb);
static inline bool req_gap_back_merge(struct request *req, struct bio *bio)
{
- return bio_will_gap(req->q, req->biotail, bio);
+ return bio_will_gap(req->q, req, req->biotail, bio);
}
static inline bool req_gap_front_merge(struct request *req, struct bio *bio)
{
- return bio_will_gap(req->q, bio, req->bio);
+ return bio_will_gap(req->q, NULL, bio, req->bio);
}
int kblockd_schedule_work(struct work_struct *work);
int kblockd_schedule_work_on(int cpu, struct work_struct *work);
int kblockd_schedule_delayed_work(struct delayed_work *dwork, unsigned long delay);
int kblockd_schedule_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay);
+int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay);
#ifdef CONFIG_BLK_CGROUP
/*
#include <linux/wait.h>
#include <linux/mutex.h>
#include <linux/rcupdate.h>
+#include <linux/refcount.h>
#include <linux/percpu-refcount.h>
#include <linux/percpu-rwsem.h>
#include <linux/workqueue.h>
/* reference count - access via css_[try]get() and css_put() */
struct percpu_ref refcnt;
- /* PI: the parent css */
- struct cgroup_subsys_state *parent;
-
/* siblings list anchored at the parent's ->children */
struct list_head sibling;
struct list_head children;
/* percpu_ref killing and RCU release */
struct rcu_head rcu_head;
struct work_struct destroy_work;
+
+ /*
+ * PI: the parent css. Placed here for cache proximity to following
+ * fields of the containing structure.
+ */
+ struct cgroup_subsys_state *parent;
};
/*
struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT];
/* reference count */
- atomic_t refcount;
+ refcount_t refcount;
/* the default cgroup associated with this css_set */
struct cgroup *dfl_cgrp;
#include <linux/seq_file.h>
#include <linux/kernfs.h>
#include <linux/jump_label.h>
-#include <linux/nsproxy.h>
#include <linux/types.h>
#include <linux/ns_common.h>
#include <linux/nsproxy.h>
#include <linux/user_namespace.h>
+#include <linux/refcount.h>
#include <linux/cgroup-defs.h>
pr_cont_kernfs_path(cgrp->kn);
}
+static inline void cgroup_init_kthreadd(void)
+{
+ /*
+ * kthreadd is inherited by all kthreads, keep it in the root so
+ * that the new kthreads are guaranteed to stay in the root until
+ * initialization is finished.
+ */
+ current->no_cgroup_migration = 1;
+}
+
+static inline void cgroup_kthread_ready(void)
+{
+ /*
+ * This kthread finished initialization. The creator should have
+ * set PF_NO_SETAFFINITY if this kthread should stay in the root.
+ */
+ current->no_cgroup_migration = 0;
+}
+
#else /* !CONFIG_CGROUPS */
struct cgroup_subsys_state;
static inline int cgroup_init_early(void) { return 0; }
static inline int cgroup_init(void) { return 0; }
+static inline void cgroup_init_kthreadd(void) {}
+static inline void cgroup_kthread_ready(void) {}
static inline bool task_under_cgroup_hierarchy(struct task_struct *task,
struct cgroup *ancestor)
#endif /* CONFIG_CGROUP_DATA */
struct cgroup_namespace {
- atomic_t count;
+ refcount_t count;
struct ns_common ns;
struct user_namespace *user_ns;
struct ucounts *ucounts;
static inline void get_cgroup_ns(struct cgroup_namespace *ns)
{
if (ns)
- atomic_inc(&ns->count);
+ refcount_inc(&ns->count);
}
static inline void put_cgroup_ns(struct cgroup_namespace *ns)
{
- if (ns && atomic_dec_and_test(&ns->count))
+ if (ns && refcount_dec_and_test(&ns->count))
free_cgroup_ns(ns);
}
extern void clockevents_register_device(struct clock_event_device *dev);
extern int clockevents_unbind_device(struct clock_event_device *ced, int cpu);
-extern void clockevents_config(struct clock_event_device *dev, u32 freq);
extern void clockevents_config_and_register(struct clock_event_device *dev,
u32 freq, unsigned long min_delta,
unsigned long max_delta);
#define CLOCK_SOURCE_RESELECT 0x100
/* simplify initialization of mask field */
-#define CLOCKSOURCE_MASK(bits) (u64)((bits) < 64 ? ((1ULL<<(bits))-1) : -1)
+#define CLOCKSOURCE_MASK(bits) GENMASK_ULL((bits) - 1, 0)
static inline u32 clocksource_freq2mult(u32 freq, u32 shift_constant, u64 from)
{
struct list_head vc_processing;
int vc_inuse;
struct super_block *vc_sb;
- struct backing_dev_info bdi;
struct mutex vc_mutex;
};
asmlinkage long compat_sys_fanotify_mark(int, unsigned int, __u32, __u32,
int, const char __user *);
+asmlinkage long compat_sys_arch_prctl(int option, unsigned long arg2);
+
/*
* For most but not all architectures, "am I in a compat syscall?" and
* "am I a compat task?" are the same question. For architectures on which
void *sink_config);
unsigned long (*reset_buffer)(struct coresight_device *csdev,
struct perf_output_handle *handle,
- void *sink_config, bool *lost);
+ void *sink_config);
void (*update_buffer)(struct coresight_device *csdev,
struct perf_output_handle *handle,
void *sink_config);
bool fast_switch_possible;
bool fast_switch_enabled;
+ /*
+ * Preferred average time interval between consecutive invocations of
+ * the driver to set the frequency for this policy. To be set by the
+ * scaling driver (0, which is the default, means no preference).
+ */
+ unsigned int transition_delay_us;
+
/* Cached frequency lookup from cpufreq_driver_resolve_freq. */
unsigned int cached_target_freq;
int cached_resolved_idx;
void free_cpumask_var(cpumask_var_t mask);
void free_bootmem_cpumask_var(cpumask_var_t mask);
+static inline bool cpumask_available(cpumask_var_t mask)
+{
+ return mask != NULL;
+}
+
#else
typedef struct cpumask cpumask_var_t[1];
static inline void free_bootmem_cpumask_var(cpumask_var_t mask)
{
}
+
+static inline bool cpumask_available(cpumask_var_t mask)
+{
+ return true;
+}
#endif /* CONFIG_CPUMASK_OFFSTACK */
/* It's common to want to use cpu_all_mask in struct member initializers,
extern int cpuset_init(void);
extern void cpuset_init_smp(void);
-extern void cpuset_update_active_cpus(bool cpu_online);
+extern void cpuset_update_active_cpus(void);
extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);
extern void cpuset_cpus_allowed_fallback(struct task_struct *p);
extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
static inline int cpuset_init(void) { return 0; }
static inline void cpuset_init_smp(void) {}
-static inline void cpuset_update_active_cpus(bool cpu_online)
+static inline void cpuset_update_active_cpus(void)
{
partition_sched_domains(1, NULL, NULL);
}
#ifndef __DELL_LED_H__
#define __DELL_LED_H__
-enum {
- DELL_LED_MICMUTE,
-};
-
-int dell_app_wmi_led_set(int whichled, int on);
+int dell_micmute_led_set(int on);
#endif
#define DEVFREQ_POSTCHANGE (1)
struct devfreq;
+struct devfreq_governor;
/**
* struct devfreq_dev_status - Data given from devfreq user device to
};
/**
- * struct devfreq_governor - Devfreq policy governor
- * @node: list node - contains registered devfreq governors
- * @name: Governor's name
- * @immutable: Immutable flag for governor. If the value is 1,
- * this govenror is never changeable to other governor.
- * @get_target_freq: Returns desired operating frequency for the device.
- * Basically, get_target_freq will run
- * devfreq_dev_profile.get_dev_status() to get the
- * status of the device (load = busy_time / total_time).
- * If no_central_polling is set, this callback is called
- * only with update_devfreq() notified by OPP.
- * @event_handler: Callback for devfreq core framework to notify events
- * to governors. Events include per device governor
- * init and exit, opp changes out of devfreq, suspend
- * and resume of per device devfreq during device idle.
- *
- * Note that the callbacks are called with devfreq->lock locked by devfreq.
- */
-struct devfreq_governor {
- struct list_head node;
-
- const char name[DEVFREQ_NAME_LEN];
- const unsigned int immutable;
- int (*get_target_freq)(struct devfreq *this, unsigned long *freq);
- int (*event_handler)(struct devfreq *devfreq,
- unsigned int event, void *data);
-};
-
-/**
* struct devfreq - Device devfreq structure
* @node: list node - contains the devices with devfreq that have been
* registered.
unsigned num_write_same_bios;
/*
+ * The number of WRITE ZEROES bios that will be submitted to the target.
+ * The bio number can be accessed with dm_bio_get_target_bio_nr.
+ */
+ unsigned num_write_zeroes_bios;
+
+ /*
* The minimum number of extra bytes allocated in each io for the
* target to use.
*/
* on max_io_len boundary.
*/
bool split_discard_bios:1;
-
- /*
- * Set if this target does not return zeroes on discarded blocks.
- */
- bool discard_zeroes_data_unsupported:1;
};
/* Each target can link one of these into the table */
#define EDAC_OPSTATE_INT 2
extern int edac_op_state;
-extern int edac_err_assert;
-extern atomic_t edac_handlers;
-extern int edac_handler_set(void);
-extern void edac_atomic_assert_error(void);
-extern struct bus_type *edac_get_sysfs_subsys(void);
+struct bus_type *edac_get_sysfs_subsys(void);
+int edac_get_report_status(void);
+void edac_set_report_status(int new);
enum {
EDAC_REPORTING_ENABLED,
EDAC_REPORTING_FORCE
};
-extern int edac_report_status;
-#ifdef CONFIG_EDAC
-static inline int get_edac_report_status(void)
-{
- return edac_report_status;
-}
-
-static inline void set_edac_report_status(int new)
-{
- edac_report_status = new;
-}
-#else
-static inline int get_edac_report_status(void)
-{
- return EDAC_REPORTING_DISABLED;
-}
-
-static inline void set_edac_report_status(int new)
-{
-}
-#endif
-
static inline void opstate_init(void)
{
switch (edac_op_state) {
#ifdef CONFIG_ACPI_BGRT
void efi_bgrt_init(struct acpi_table_header *table);
+int __init acpi_parse_bgrt(struct acpi_table_header *table);
/* The BGRT data itself; only valid if bgrt_image != NULL. */
extern size_t bgrt_image_size;
#else /* !CONFIG_ACPI_BGRT */
static inline void efi_bgrt_init(struct acpi_table_header *table) {}
+static inline int __init acpi_parse_bgrt(struct acpi_table_header *table)
+{
+ return 0;
+}
#endif /* !CONFIG_ACPI_BGRT */
/* prototypes shared between arch specific and generic stub code */
-#define pr_efi(sys_table, msg) efi_printk(sys_table, "EFI stub: "msg)
-#define pr_efi_err(sys_table, msg) efi_printk(sys_table, "EFI stub: ERROR: "msg)
-
void efi_printk(efi_system_table_t *sys_table_arg, char *str);
void efi_free(efi_system_table_t *sys_table_arg, unsigned long size,
unsigned long *load_addr,
unsigned long *load_size);
-efi_status_t efi_parse_options(char *cmdline);
+efi_status_t efi_parse_options(char const *cmdline);
efi_status_t efi_setup_gop(efi_system_table_t *sys_table_arg,
struct screen_info *si, efi_guid_t *proto,
struct elevator_mq_ops {
int (*init_sched)(struct request_queue *, struct elevator_type *);
void (*exit_sched)(struct elevator_queue *);
+ int (*init_hctx)(struct blk_mq_hw_ctx *, unsigned int);
+ void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int);
bool (*allow_merge)(struct request_queue *, struct request *, struct bio *);
bool (*bio_merge)(struct blk_mq_hw_ctx *, struct bio *);
void (*insert_requests)(struct blk_mq_hw_ctx *, struct list_head *, bool);
struct request *(*dispatch_request)(struct blk_mq_hw_ctx *);
bool (*has_work)(struct blk_mq_hw_ctx *);
- void (*completed_request)(struct blk_mq_hw_ctx *, struct request *);
+ void (*completed_request)(struct request *);
void (*started_request)(struct request *);
void (*requeue_request)(struct request *);
struct request *(*former_request)(struct request_queue *, struct request *);
extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t);
extern int elevator_init(struct request_queue *, char *);
-extern void elevator_exit(struct elevator_queue *);
+extern void elevator_exit(struct request_queue *, struct elevator_queue *);
extern int elevator_change(struct request_queue *, const char *);
extern bool elv_bio_merge_ok(struct request *, struct bio *);
extern struct elevator_queue *elevator_alloc(struct request_queue *,
unsigned int id, unsigned int prop);
/*
- * Following APIs are to monitor every action of a notifier.
- * Registrar gets notified for every external port of a connection device.
- * Probably this could be used to debug an action of notifier; however,
- * we do not recommend to use this for normal 'notifiee' device drivers who
- * want to be notified by a specific external port of the notifier.
+ * Following APIs are to monitor the status change of the external connectors.
+ * extcon_register_notifier(*edev, id, *nb) : Register a notifier block
+ * for specific external connector of the extcon.
+ * extcon_register_notifier_all(*edev, *nb) : Register a notifier block
+ * for all supported external connectors of the extcon.
*/
extern int extcon_register_notifier(struct extcon_dev *edev, unsigned int id,
struct notifier_block *nb);
struct extcon_dev *edev, unsigned int id,
struct notifier_block *nb);
+extern int extcon_register_notifier_all(struct extcon_dev *edev,
+ struct notifier_block *nb);
+extern int extcon_unregister_notifier_all(struct extcon_dev *edev,
+ struct notifier_block *nb);
+extern int devm_extcon_register_notifier_all(struct device *dev,
+ struct extcon_dev *edev,
+ struct notifier_block *nb);
+extern void devm_extcon_unregister_notifier_all(struct device *dev,
+ struct extcon_dev *edev,
+ struct notifier_block *nb);
+
/*
* Following API get the extcon device from devicetree.
* This function use phandle of devicetree to get extcon device directly.
extern int freeze_super(struct super_block *super);
extern int thaw_super(struct super_block *super);
extern bool our_mnt(struct vfsmount *mnt);
+extern __printf(2, 3)
+int super_setup_bdi_name(struct super_block *sb, char *fmt, ...);
+extern int super_setup_bdi(struct super_block *sb);
extern int current_umask(void);
struct fwnode_handle *secondary;
};
+/**
+ * struct fwnode_endpoint - Fwnode graph endpoint
+ * @port: Port number
+ * @id: Endpoint id
+ * @local_fwnode: reference to the related fwnode
+ */
+struct fwnode_endpoint {
+ unsigned int port;
+ unsigned int id;
+ const struct fwnode_handle *local_fwnode;
+};
+
#endif
#if defined(CONFIG_BLK_DEV_INTEGRITY)
struct blk_integrity {
- struct blk_integrity_profile *profile;
- unsigned char flags;
- unsigned char tuple_size;
- unsigned char interval_exp;
- unsigned char tag_size;
+ const struct blk_integrity_profile *profile;
+ unsigned char flags;
+ unsigned char tuple_size;
+ unsigned char interval_exp;
+ unsigned char tag_size;
};
#endif /* CONFIG_BLK_DEV_INTEGRITY */
#if defined(CONFIG_BLK_DEV_INTEGRITY)
extern void blk_integrity_add(struct gendisk *);
extern void blk_integrity_del(struct gendisk *);
-extern void blk_integrity_revalidate(struct gendisk *);
#else /* CONFIG_BLK_DEV_INTEGRITY */
static inline void blk_integrity_add(struct gendisk *disk) { }
static inline void blk_integrity_del(struct gendisk *disk) { }
-static inline void blk_integrity_revalidate(struct gendisk *disk) { }
#endif /* CONFIG_BLK_DEV_INTEGRITY */
#else /* CONFIG_BLOCK */
return timer->base->cpu_base->hres_active;
}
-extern void hrtimer_peek_ahead_timers(void);
-
/*
* The resolution of the clocks. The resolution value is returned in
* the clock_getres() system call to give application programmers an
#define hrtimer_resolution (unsigned int)LOW_RES_NSEC
-static inline void hrtimer_peek_ahead_timers(void) { }
-
static inline int hrtimer_is_hres_active(struct hrtimer *timer)
{
return 0;
}
/* Precise sleep: */
-extern long hrtimer_nanosleep(struct timespec *rqtp,
+extern long hrtimer_nanosleep(struct timespec64 *rqtp,
struct timespec __user *rmtp,
const enum hrtimer_mode mode,
const clockid_t clockid);
int (*read)(struct device *dev, enum hwmon_sensor_types type,
u32 attr, int channel, long *val);
int (*read_string)(struct device *dev, enum hwmon_sensor_types type,
- u32 attr, int channel, char **str);
+ u32 attr, int channel, const char **str);
int (*write)(struct device *dev, enum hwmon_sensor_types type,
u32 attr, int channel, long val);
};
ide_req(rq)->type == ATA_PRIV_PM_RESUME);
}
-/* Error codes returned in rq->errors to the higher part of the driver. */
+/* Error codes returned in result to the higher part of the driver. */
enum {
IDE_DRV_ERROR_GENERAL = 101,
IDE_DRV_ERROR_FILEMARK = 102,
#define _LINUX_INET_H
#include <linux/types.h>
+#include <net/net_namespace.h>
+#include <linux/socket.h>
/*
* These mimic similar macros defined in user-space for inet_ntop(3).
extern __be32 in_aton(const char *str);
extern int in4_pton(const char *src, int srclen, u8 *dst, int delim, const char **end);
extern int in6_pton(const char *src, int srclen, u8 *dst, int delim, const char **end);
+
+extern int inet_pton_with_scope(struct net *net, unsigned short af,
+ const char *src, const char *port, struct sockaddr_storage *addr);
+
#endif /* _LINUX_INET_H */
#ifdef CONFIG_RT_MUTEXES
# define INIT_RT_MUTEXES(tsk) \
.pi_waiters = RB_ROOT, \
+ .pi_top_task = NULL, \
.pi_waiters_leftmost = NULL,
#else
# define INIT_RT_MUTEXES(tsk)
#define GICH_MISR_EOI (1 << 0)
#define GICH_MISR_U (1 << 1)
+#define GICV_PMR_PRIORITY_SHIFT 3
+#define GICV_PMR_PRIORITY_MASK (0x1f << GICV_PMR_PRIORITY_SHIFT)
+
#ifndef __ASSEMBLY__
#include <linux/irqdomain.h>
extern void gic_init(unsigned long gic_base_addr,
unsigned long gic_addrspace_size, unsigned int cpu_vec,
unsigned int irqbase);
-extern void gic_clocksource_init(unsigned int);
extern u64 gic_read_count(void);
extern unsigned int gic_get_count_width(void);
extern u64 gic_read_compare(void);
extern char *get_options(const char *str, int nints, int *ints);
extern unsigned long long memparse(const char *ptr, char **retptr);
extern bool parse_option_str(const char *str, const char *option);
+extern char *next_arg(char *args, char **param, char **val);
extern int core_kernel_text(unsigned long addr);
extern int core_kernel_data(unsigned long addr);
extern int __must_check kobject_move(struct kobject *, struct kobject *);
extern struct kobject *kobject_get(struct kobject *kobj);
+extern struct kobject * __must_check kobject_get_unless_zero(
+ struct kobject *kobj);
extern void kobject_put(struct kobject *kobj);
extern const void *kobject_namespace(struct kobject *kobj);
extern void show_registers(struct pt_regs *regs);
extern void kprobes_inc_nmissed_count(struct kprobe *p);
extern bool arch_within_kprobe_blacklist(unsigned long addr);
+extern bool arch_function_offset_within_entry(unsigned long offset);
+extern bool function_offset_within_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset);
extern bool within_kprobe_blacklist(unsigned long addr);
PCA9532_OFF = 0x0,
PCA9532_ON = 0x1,
PCA9532_PWM0 = 0x2,
- PCA9532_PWM1 = 0x3
+ PCA9532_PWM1 = 0x3,
+ PCA9532_KEEP = 0xff,
};
struct pca9532_led {
};
#endif /* __LINUX_PCA9532_H */
-
struct mutex led_access;
};
-extern int led_classdev_register(struct device *parent,
- struct led_classdev *led_cdev);
-extern int devm_led_classdev_register(struct device *parent,
- struct led_classdev *led_cdev);
+extern int of_led_classdev_register(struct device *parent,
+ struct device_node *np,
+ struct led_classdev *led_cdev);
+#define led_classdev_register(parent, led_cdev) \
+ of_led_classdev_register(parent, NULL, led_cdev)
+extern int devm_of_led_classdev_register(struct device *parent,
+ struct device_node *np,
+ struct led_classdev *led_cdev);
+#define devm_led_classdev_register(parent, led_cdev) \
+ devm_of_led_classdev_register(parent, NULL, led_cdev)
extern void led_classdev_unregister(struct led_classdev *led_cdev);
extern void devm_led_classdev_unregister(struct device *parent,
struct led_classdev *led_cdev);
typedef int (nvm_op_bb_tbl_fn)(struct nvm_dev *, struct ppa_addr, u8 *);
typedef int (nvm_op_set_bb_fn)(struct nvm_dev *, struct ppa_addr *, int, int);
typedef int (nvm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *);
-typedef int (nvm_erase_blk_fn)(struct nvm_dev *, struct nvm_rq *);
typedef void *(nvm_create_dma_pool_fn)(struct nvm_dev *, char *);
typedef void (nvm_destroy_dma_pool_fn)(void *);
typedef void *(nvm_dev_dma_alloc_fn)(struct nvm_dev *, void *, gfp_t,
nvm_op_set_bb_fn *set_bb_tbl;
nvm_submit_io_fn *submit_io;
- nvm_erase_blk_fn *erase_block;
nvm_create_dma_pool_fn *create_dma_pool;
nvm_destroy_dma_pool_fn *destroy_dma_pool;
/* NAND Access Modes */
NVM_IO_SUSPEND = 0x80,
NVM_IO_SLC_MODE = 0x100,
- NVM_IO_SCRAMBLE_DISABLE = 0x200,
+ NVM_IO_SCRAMBLE_ENABLE = 0x200,
/* Block Types */
NVM_BLK_T_FREE = 0x0,
typedef blk_qc_t (nvm_tgt_make_rq_fn)(struct request_queue *, struct bio *);
typedef sector_t (nvm_tgt_capacity_fn)(void *);
-typedef void *(nvm_tgt_init_fn)(struct nvm_tgt_dev *, struct gendisk *);
+typedef void *(nvm_tgt_init_fn)(struct nvm_tgt_dev *, struct gendisk *,
+ int flags);
typedef void (nvm_tgt_exit_fn)(void *);
typedef int (nvm_tgt_sysfs_init_fn)(struct gendisk *);
typedef void (nvm_tgt_sysfs_exit_fn)(struct gendisk *);
int, int);
extern int nvm_max_phys_sects(struct nvm_tgt_dev *);
extern int nvm_submit_io(struct nvm_tgt_dev *, struct nvm_rq *);
-extern int nvm_set_rqd_ppalist(struct nvm_dev *, struct nvm_rq *,
+extern int nvm_erase_sync(struct nvm_tgt_dev *, struct ppa_addr *, int);
+extern int nvm_set_rqd_ppalist(struct nvm_tgt_dev *, struct nvm_rq *,
const struct ppa_addr *, int, int);
-extern void nvm_free_rqd_ppalist(struct nvm_dev *, struct nvm_rq *);
-extern int nvm_erase_blk(struct nvm_tgt_dev *, struct ppa_addr *, int);
+extern void nvm_free_rqd_ppalist(struct nvm_tgt_dev *, struct nvm_rq *);
extern int nvm_get_l2p_tbl(struct nvm_tgt_dev *, u64, u32, nvm_l2p_update_fn *,
void *);
extern int nvm_get_area(struct nvm_tgt_dev *, sector_t *, sector_t);
lock_set_class(lock, lock->name, lock->key, subclass, ip);
}
+extern void lock_downgrade(struct lockdep_map *lock, unsigned long ip);
+
extern void lockdep_set_current_reclaim_state(gfp_t gfp_mask);
extern void lockdep_clear_current_reclaim_state(void);
extern void lockdep_trace_alloc(gfp_t mask);
# define lock_acquire(l, s, t, r, c, n, i) do { } while (0)
# define lock_release(l, n, i) do { } while (0)
+# define lock_downgrade(l, i) do { } while (0)
# define lock_set_class(l, n, k, s, i) do { } while (0)
# define lock_set_subclass(l, s, i) do { } while (0)
# define lockdep_set_current_reclaim_state(g) do { } while (0)
enum brcm_message_type {
BRCM_MESSAGE_UNKNOWN = 0,
+ BRCM_MESSAGE_BATCH,
BRCM_MESSAGE_SPU,
BRCM_MESSAGE_SBA,
BRCM_MESSAGE_MAX,
struct brcm_sba_command {
u64 cmd;
+ u64 *cmd_dma;
+ dma_addr_t cmd_dma_addr;
#define BRCM_SBA_CMD_TYPE_A BIT(0)
#define BRCM_SBA_CMD_TYPE_B BIT(1)
#define BRCM_SBA_CMD_TYPE_C BIT(2)
#define BRCM_SBA_CMD_HAS_RESP BIT(3)
#define BRCM_SBA_CMD_HAS_OUTPUT BIT(4)
u64 flags;
- dma_addr_t input;
- size_t input_len;
dma_addr_t resp;
size_t resp_len;
- dma_addr_t output;
- size_t output_len;
+ dma_addr_t data;
+ size_t data_len;
};
struct brcm_message {
enum brcm_message_type type;
union {
struct {
+ struct brcm_message *msgs;
+ unsigned int msgs_queued;
+ unsigned int msgs_count;
+ } batch;
+ struct {
struct scatterlist *src;
struct scatterlist *dst;
} spu;
* Max bus-specific overhead incurred by request/responses.
* I2C requires 1 additional byte for requests.
* I2C requires 2 additional bytes for responses.
+ * SPI requires up to 32 additional bytes for responses.
* */
#define EC_PROTO_VERSION_UNKNOWN 0
#define EC_MAX_REQUEST_OVERHEAD 1
-#define EC_MAX_RESPONSE_OVERHEAD 2
+#define EC_MAX_RESPONSE_OVERHEAD 32
/*
* Command interface between EC and AP, for LPC, I2C and SPI interfaces.
* published by the Free Software Foundation.
*/
+#include <linux/device.h>
+#include <linux/regmap.h>
+
#define CPCAP_VENDOR_ST 0
#define CPCAP_VENDOR_TI 1
+++ /dev/null
-/*
- * include/linux/mg_disk.c
- *
- * Private data for mflash platform driver
- *
- * (c) 2008 mGine Co.,LTD
- * (c) 2008 unsik Kim <donari75@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef __MG_DISK_H__
-#define __MG_DISK_H__
-
-/* name for platform device */
-#define MG_DEV_NAME "mg_disk"
-
-/* names of GPIO resource */
-#define MG_RST_PIN "mg_rst"
-/* except MG_BOOT_DEV, reset-out pin should be assigned */
-#define MG_RSTOUT_PIN "mg_rstout"
-
-/* device attribution */
-/* use mflash as boot device */
-#define MG_BOOT_DEV (1 << 0)
-/* use mflash as storage device */
-#define MG_STORAGE_DEV (1 << 1)
-/* same as MG_STORAGE_DEV, but bootloader already done reset sequence */
-#define MG_STORAGE_DEV_SKIP_RST (1 << 2)
-
-/* private driver data */
-struct mg_drv_data {
- /* disk resource */
- u32 use_polling;
-
- /* device attribution */
- u32 dev_attr;
-
- /* internally used */
- void *host;
-};
-
-#endif
unsigned int state; /* function state */
#define SDIO_STATE_PRESENT (1<<0) /* present in sysfs */
- u8 tmpbuf[4]; /* DMA:able scratch buffer */
+ u8 *tmpbuf; /* DMA:able scratch buffer */
unsigned num_info; /* number of info strings */
const char **info; /* info strings */
___pud; \
})
-#define pmdp_huge_get_and_clear_notify(__mm, __haddr, __pmd) \
-({ \
- unsigned long ___haddr = __haddr & HPAGE_PMD_MASK; \
- pmd_t ___pmd; \
- \
- ___pmd = pmdp_huge_get_and_clear(__mm, __haddr, __pmd); \
- mmu_notifier_invalidate_range(__mm, ___haddr, \
- ___haddr + HPAGE_PMD_SIZE); \
- \
- ___pmd; \
-})
-
/*
* set_pte_at_notify() sets the pte _after_ running the notifier.
* This is safe to start by updating the secondary MMUs, because the primary MMU
#define ptep_clear_flush_notify ptep_clear_flush
#define pmdp_huge_clear_flush_notify pmdp_huge_clear_flush
#define pudp_huge_clear_flush_notify pudp_huge_clear_flush
-#define pmdp_huge_get_and_clear_notify pmdp_huge_get_and_clear
#define set_pte_at_notify set_pte_at
#endif /* CONFIG_MMU_NOTIFIER */
struct module *__module_text_address(unsigned long addr);
struct module *__module_address(unsigned long addr);
bool is_module_address(unsigned long addr);
+bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr);
bool is_module_percpu_address(unsigned long addr);
bool is_module_text_address(unsigned long addr);
return false;
}
+static inline bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr)
+{
+ return false;
+}
+
static inline bool is_module_text_address(unsigned long addr)
{
return false;
int (*_get_device) (struct mtd_info *mtd);
void (*_put_device) (struct mtd_info *mtd);
- /* Backing device capabilities for this device
- * - provides mmap capabilities
- */
- struct backing_dev_info *backing_dev_info;
-
struct notifier_block reboot_notifier; /* default mode before reboot */
/* ECC status information */
struct rpc_clnt * client_acl; /* ACL RPC client handle */
struct nlm_host *nlm_host; /* NLM client handle */
struct nfs_iostats __percpu *io_stats; /* I/O statistics */
- struct backing_dev_info backing_dev_info;
atomic_long_t writeback; /* number of writeback pages */
int flags; /* various flags */
unsigned int caps; /* server capabilities */
* transferred. Should equal payload_length on success.
* @rcv_rsplen: length, in bytes, of the FCP RSP IU received.
* @status: Completion status of the FCP operation. must be 0 upon success,
- * NVME_SC_FC_xxx value upon failure. Note: this is NOT a
- * reflection of the NVME CQE completion status. Only the status
- * of the FCP operation at the NVME-FC level.
+ * negative errno value upon failure (ex: -EIO). Note: this is
+ * NOT a reflection of the NVME CQE completion status. Only the
+ * status of the FCP operation at the NVME-FC level.
*/
struct nvmefc_fcp_req {
void *cmdaddr;
* rsp as well
*/
NVMET_FCOP_RSP = 4, /* send rsp frame */
- NVMET_FCOP_ABORT = 5, /* abort exchange via ABTS */
- NVMET_FCOP_BA_ACC = 6, /* send BA_ACC */
- NVMET_FCOP_BA_RJT = 7, /* send BA_RJT */
};
/**
* upon compeletion of the operation. The nvmet-fc layer will also set a
* private pointer for its own use in the done routine.
*
- * Note: the LLDD must never fail a NVMET_FCOP_ABORT request !!
- *
* Values set by the NVMET-FC layer prior to calling the LLDD fcp_op
* entrypoint.
* @op: Indicates the FCP IU operation to perform (see NVMET_FCOP_xxx)
* on. The transport should pick a cpu to schedule the work
* on.
*/
+ NVMET_FCTGTFEAT_CMD_IN_ISR = (1 << 2),
+ /* Bit 2: When 0, the LLDD is calling the cmd rcv handler
+ * in a non-isr context, allowing the transport to finish
+ * op completion in the calling context. When 1, the LLDD
+ * is calling the cmd rcv handler in an ISR context,
+ * requiring the transport to transition to a workqueue
+ * for op completion.
+ */
+ NVMET_FCTGTFEAT_OPDONE_IN_ISR = (1 << 3),
+ /* Bit 3: When 0, the LLDD is calling the op done handler
+ * in a non-isr context, allowing the transport to finish
+ * op completion in the calling context. When 1, the LLDD
+ * is calling the op done handler in an ISR context,
+ * requiring the transport to transition to a workqueue
+ * for op completion.
+ */
};
* be freed/released.
* Entrypoint is Mandatory.
*
- * @fcp_op: Called to perform a data transfer, transmit a response, or
- * abort an FCP opertion. The nvmefc_tgt_fcp_req structure is the same
- * LLDD-supplied exchange structure specified in the
- * nvmet_fc_rcv_fcp_req() call made when the FCP CMD IU was received.
- * The op field in the structure shall indicate the operation for
- * the LLDD to perform relative to the io.
+ * @fcp_op: Called to perform a data transfer or transmit a response.
+ * The nvmefc_tgt_fcp_req structure is the same LLDD-supplied
+ * exchange structure specified in the nvmet_fc_rcv_fcp_req() call
+ * made when the FCP CMD IU was received. The op field in the
+ * structure shall indicate the operation for the LLDD to perform
+ * relative to the io.
* NVMET_FCOP_READDATA operation: the LLDD is to send the
* payload data (described by sglist) to the host in 1 or
* more FC sequences (preferrably 1). Note: the fc-nvme layer
* successfully, the LLDD is to update the nvmefc_tgt_fcp_req
* transferred_length field and may subsequently transmit the
* FCP_RSP iu payload (described by rspbuf, rspdma, rsplen).
- * The LLDD is to await FCP_CONF reception to confirm the RSP
- * reception by the host. The LLDD may retramsit the FCP_RSP iu
- * if necessary per FC-NVME. Upon reception of FCP_CONF, or upon
- * FCP_CONF failure, the LLDD is to set the nvmefc_tgt_fcp_req
- * fcp_error field and consider the operation complete..
+ * If FCP_CONF is supported, the LLDD is to await FCP_CONF
+ * reception to confirm the RSP reception by the host. The LLDD
+ * may retramsit the FCP_RSP iu if necessary per FC-NVME. Upon
+ * transmission of the FCP_RSP iu if FCP_CONF is not supported,
+ * or upon success/failure of FCP_CONF if it is supported, the
+ * LLDD is to set the nvmefc_tgt_fcp_req fcp_error field and
+ * consider the operation complete.
* NVMET_FCOP_RSP: the LLDD is to transmit the FCP_RSP iu payload
- * (described by rspbuf, rspdma, rsplen). The LLDD is to await
- * FCP_CONF reception to confirm the RSP reception by the host.
- * The LLDD may retramsit the FCP_RSP iu if necessary per FC-NVME.
- * Upon reception of FCP_CONF, or upon FCP_CONF failure, the
+ * (described by rspbuf, rspdma, rsplen). If FCP_CONF is
+ * supported, the LLDD is to await FCP_CONF reception to confirm
+ * the RSP reception by the host. The LLDD may retramsit the
+ * FCP_RSP iu if FCP_CONF is not received per FC-NVME. Upon
+ * transmission of the FCP_RSP iu if FCP_CONF is not supported,
+ * or upon success/failure of FCP_CONF if it is supported, the
* LLDD is to set the nvmefc_tgt_fcp_req fcp_error field and
- * consider the operation complete..
- * NVMET_FCOP_ABORT: the LLDD is to terminate the exchange
- * corresponding to the fcp operation. The LLDD shall send
- * ABTS and follow FC exchange abort-multi rules, including
- * ABTS retries and possible logout.
+ * consider the operation complete.
* Upon completing the indicated operation, the LLDD is to set the
* status fields for the operation (tranferred_length and fcp_error
- * status) in the request, then all the "done" routine
- * indicated in the fcp request. Upon return from the "done"
- * routine for either a NVMET_FCOP_RSP or NVMET_FCOP_ABORT operation
- * the fc-nvme layer will not longer reference the fcp request,
- * allowing the LLDD to free/release the fcp request.
+ * status) in the request, then call the "done" routine
+ * indicated in the fcp request. After the operation completes,
+ * regardless of whether the FCP_RSP iu was successfully transmit,
+ * the LLDD-supplied exchange structure must remain valid until the
+ * transport calls the fcp_req_release() callback to return ownership
+ * of the exchange structure back to the LLDD so that it may be used
+ * for another fcp command.
* Note: when calling the done routine for READDATA or WRITEDATA
* operations, the fc-nvme layer may immediate convert, in the same
* thread and before returning to the LLDD, the fcp operation to
* Returns 0 on success, -<errno> on failure (Ex: -EIO)
* Entrypoint is Mandatory.
*
+ * @fcp_abort: Called by the transport to abort an active command.
+ * The command may be in-between operations (nothing active in LLDD)
+ * or may have an active WRITEDATA operation pending. The LLDD is to
+ * initiate the ABTS process for the command and return from the
+ * callback. The ABTS does not need to be complete on the command.
+ * The fcp_abort callback inherently cannot fail. After the
+ * fcp_abort() callback completes, the transport will wait for any
+ * outstanding operation (if there was one) to complete, then will
+ * call the fcp_req_release() callback to return the command's
+ * exchange context back to the LLDD.
+ *
+ * @fcp_req_release: Called by the transport to return a nvmefc_tgt_fcp_req
+ * to the LLDD after all operations on the fcp operation are complete.
+ * This may be due to the command completing or upon completion of
+ * abort cleanup.
+ *
* @max_hw_queues: indicates the maximum number of hw queues the LLDD
* supports for cpu affinitization.
* Value is Mandatory. Must be at least 1.
int (*xmt_ls_rsp)(struct nvmet_fc_target_port *tgtport,
struct nvmefc_tgt_ls_req *tls_req);
int (*fcp_op)(struct nvmet_fc_target_port *tgtport,
- struct nvmefc_tgt_fcp_req *);
+ struct nvmefc_tgt_fcp_req *fcpreq);
+ void (*fcp_abort)(struct nvmet_fc_target_port *tgtport,
+ struct nvmefc_tgt_fcp_req *fcpreq);
+ void (*fcp_req_release)(struct nvmet_fc_target_port *tgtport,
+ struct nvmefc_tgt_fcp_req *fcpreq);
u32 max_hw_queues;
u16 max_sgl_segments;
struct nvmefc_tgt_fcp_req *fcpreq,
void *cmdiubuf, u32 cmdiubuf_len);
+void nvmet_fc_rcv_fcp_abort(struct nvmet_fc_target_port *tgtport,
+ struct nvmefc_tgt_fcp_req *fcpreq);
+
#endif /* _NVME_FC_DRIVER_H */
*/
/*
- * This file contains definitions relative to FC-NVME r1.11 and a few
- * newer items
+ * This file contains definitions relative to FC-NVME r1.14 (16-020vB).
*/
#ifndef _NVME_FC_H
#define NVME_FC_SIZEOF_ZEROS_RSP 12
+enum {
+ FCNVME_SC_SUCCESS = 0,
+ FCNVME_SC_INVALID_FIELD = 1,
+ FCNVME_SC_INVALID_CONNID = 2,
+};
+
struct nvme_fc_ersp_iu {
- __u8 rsvd0[2];
+ __u8 status_code;
+ __u8 rsvd1;
__be16 iu_len;
__be32 rsn;
__be32 xfrd_len;
};
-/* FC-NVME r1.03/16-119v0 NVME Link Services */
+/* FC-NVME Link Services */
enum {
FCNVME_LS_RSVD = 0,
FCNVME_LS_RJT = 1,
FCNVME_LS_DISCONNECT = 5,
};
-/* FC-NVME r1.03/16-119v0 NVME Link Service Descriptors */
+/* FC-NVME Link Service Descriptors */
enum {
FCNVME_LSDESC_RSVD = 0x0,
FCNVME_LSDESC_RQST = 0x1,
return cpu_to_be32(sz - (2 * sizeof(u32)));
}
-
struct fcnvme_ls_rqst_w0 {
u8 ls_cmd; /* FCNVME_LS_xxx */
u8 zeros[3];
__be32 rsvd12;
};
+/* FC-NVME LS RJT reason_code values */
+enum fcnvme_ls_rjt_reason {
+ FCNVME_RJT_RC_NONE = 0,
+ /* no reason - not to be sent */
+
+ FCNVME_RJT_RC_INVAL = 0x01,
+ /* invalid NVMe_LS command code */
+
+ FCNVME_RJT_RC_LOGIC = 0x03,
+ /* logical error */
+
+ FCNVME_RJT_RC_UNAB = 0x09,
+ /* unable to perform command request */
+
+ FCNVME_RJT_RC_UNSUP = 0x0b,
+ /* command not supported */
+
+ FCNVME_RJT_RC_INPROG = 0x0e,
+ /* command already in progress */
+ FCNVME_RJT_RC_INV_ASSOC = 0x40,
+ /* Invalid Association ID*/
+ FCNVME_RJT_RC_INV_CONN = 0x41,
+ /* Invalid Connection ID*/
+
+ FCNVME_RJT_RC_VENDOR = 0xff,
+ /* vendor specific error */
+};
+
+/* FC-NVME LS RJT reason_explanation values */
+enum fcnvme_ls_rjt_explan {
+ FCNVME_RJT_EXP_NONE = 0x00,
+ /* No additional explanation */
+
+ FCNVME_RJT_EXP_OXID_RXID = 0x17,
+ /* invalid OX_ID-RX_ID combination */
+
+ FCNVME_RJT_EXP_INSUF_RES = 0x29,
+ /* insufficient resources */
+
+ FCNVME_RJT_EXP_UNAB_DATA = 0x2a,
+ /* unable to supply requested data */
+
+ FCNVME_RJT_EXP_INV_LEN = 0x2d,
+ /* Invalid payload length */
+};
/* FCNVME_LSDESC_RJT */
struct fcnvme_lsdesc_rjt {
* Reject reason and explanaction codes are generic
* to ELs's from LS-3.
*/
- u8 reason_code;
- u8 reason_explanation;
+ u8 reason_code; /* fcnvme_ls_rjt_reason */
+ u8 reason_explanation; /* fcnvme_ls_rjt_explan */
u8 vendor;
__be32 rsvd12;
};
-#define FCNVME_ASSOC_HOSTID_LEN 64
+#define FCNVME_ASSOC_HOSTID_LEN 16
#define FCNVME_ASSOC_HOSTNQN_LEN 256
#define FCNVME_ASSOC_SUBNQN_LEN 256
* RDMA_QPTYPE field
*/
enum {
- NVMF_RDMA_QPTYPE_CONNECTED = 0, /* Reliable Connected */
- NVMF_RDMA_QPTYPE_DATAGRAM = 1, /* Reliable Datagram */
+ NVMF_RDMA_QPTYPE_CONNECTED = 1, /* Reliable Connected */
+ NVMF_RDMA_QPTYPE_DATAGRAM = 2, /* Reliable Datagram */
};
/* RDMA QP Service Type codes for Discovery Log Page entry TSAS
* RDMA_QPTYPE field
*/
enum {
- NVMF_RDMA_PRTYPE_NOT_SPECIFIED = 0, /* No Provider Specified */
- NVMF_RDMA_PRTYPE_IB = 1, /* InfiniBand */
- NVMF_RDMA_PRTYPE_ROCE = 2, /* InfiniBand RoCE */
- NVMF_RDMA_PRTYPE_ROCEV2 = 3, /* InfiniBand RoCEV2 */
- NVMF_RDMA_PRTYPE_IWARP = 4, /* IWARP */
+ NVMF_RDMA_PRTYPE_NOT_SPECIFIED = 1, /* No Provider Specified */
+ NVMF_RDMA_PRTYPE_IB = 2, /* InfiniBand */
+ NVMF_RDMA_PRTYPE_ROCE = 3, /* InfiniBand RoCE */
+ NVMF_RDMA_PRTYPE_ROCEV2 = 4, /* InfiniBand RoCEV2 */
+ NVMF_RDMA_PRTYPE_IWARP = 5, /* IWARP */
};
/* RDMA Connection Management Service Type codes for Discovery Log Page
* entry TSAS RDMA_CMS field
*/
enum {
- NVMF_RDMA_CMS_RDMA_CM = 0, /* Sockets based enpoint addressing */
+ NVMF_RDMA_CMS_RDMA_CM = 1, /* Sockets based endpoint addressing */
};
#define NVMF_AQ_DEPTH 32
NVME_CTRL_ONCS_WRITE_ZEROES = 1 << 3,
NVME_CTRL_VWC_PRESENT = 1 << 0,
NVME_CTRL_OACS_SEC_SUPP = 1 << 0,
+ NVME_CTRL_OACS_DBBUF_SUPP = 1 << 7,
};
struct nvme_lbaf {
nvme_admin_download_fw = 0x11,
nvme_admin_ns_attach = 0x15,
nvme_admin_keep_alive = 0x18,
+ nvme_admin_dbbuf = 0x7C,
nvme_admin_format_nvm = 0x80,
nvme_admin_security_send = 0x81,
nvme_admin_security_recv = 0x82,
__u8 resv4[16];
};
+struct nvme_dbbuf {
+ __u8 opcode;
+ __u8 flags;
+ __u16 command_id;
+ __u32 rsvd1[5];
+ __le64 prp1;
+ __le64 prp2;
+ __u32 rsvd12[6];
+};
+
struct nvme_command {
union {
struct nvme_common_command common;
struct nvmf_connect_command connect;
struct nvmf_property_set_command prop_set;
struct nvmf_property_get_command prop_get;
+ struct nvme_dbbuf dbbuf;
};
};
container_of(fwnode, struct device_node, fwnode) : NULL;
}
+#define of_fwnode_handle(node) (&(node)->fwnode)
+
static inline bool of_have_populated_dt(void)
{
return of_root != NULL;
return NULL;
}
+#define of_fwnode_handle(node) NULL
+
static inline bool of_have_populated_dt(void)
{
return false;
#endif
extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align);
+extern bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr);
extern bool is_kernel_percpu_address(unsigned long addr);
#if !defined(CONFIG_SMP) || !defined(CONFIG_HAVE_SETUP_PER_CPU_AREA)
struct list_head bp_list;
};
#endif
+ struct { /* amd_iommu */
+ u8 iommu_bank;
+ u8 iommu_cntr;
+ u16 padding;
+ u64 conf;
+ u64 conf1;
+ };
};
/*
* If the event is a per task event, this will point to the task in
struct ring_buffer *rb;
unsigned long wakeup;
unsigned long size;
+ u64 aux_flags;
union {
void *addr;
unsigned long head;
extern void *perf_aux_output_begin(struct perf_output_handle *handle,
struct perf_event *event);
extern void perf_aux_output_end(struct perf_output_handle *handle,
- unsigned long size, bool truncated);
+ unsigned long size);
extern int perf_aux_output_skip(struct perf_output_handle *handle,
unsigned long size);
extern void *perf_get_aux(struct perf_output_handle *handle);
+extern void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags);
extern int perf_pmu_register(struct pmu *pmu, const char *name, int type);
extern void perf_pmu_unregister(struct pmu *pmu);
extern void perf_event_exec(void);
extern void perf_event_comm(struct task_struct *tsk, bool exec);
+extern void perf_event_namespaces(struct task_struct *tsk);
extern void perf_event_fork(struct task_struct *tsk);
/* Callchains */
perf_aux_output_begin(struct perf_output_handle *handle,
struct perf_event *event) { return NULL; }
static inline void
-perf_aux_output_end(struct perf_output_handle *handle, unsigned long size,
- bool truncated) { }
+perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
+ { }
static inline int
perf_aux_output_skip(struct perf_output_handle *handle,
unsigned long size) { return -EINVAL; }
static inline void perf_event_mmap(struct vm_area_struct *vma) { }
static inline void perf_event_exec(void) { }
static inline void perf_event_comm(struct task_struct *tsk, bool exec) { }
+static inline void perf_event_namespaces(struct task_struct *tsk) { }
static inline void perf_event_fork(struct task_struct *tsk) { }
static inline void perf_event_init(void) { }
static inline int perf_swevent_get_recursion_context(void) { return -1; }
void phy_mac_interrupt(struct phy_device *phydev, int new_link);
void phy_start_machine(struct phy_device *phydev);
void phy_stop_machine(struct phy_device *phydev);
+void phy_trigger_machine(struct phy_device *phydev, bool sync);
int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd);
int phy_ethtool_gset(struct phy_device *phydev, struct ethtool_cmd *cmd);
int phy_ethtool_ksettings_get(struct phy_device *phydev,
extern int pinctrl_register_and_init(struct pinctrl_desc *pctldesc,
struct device *dev, void *driver_data,
struct pinctrl_dev **pctldev);
+extern int pinctrl_enable(struct pinctrl_dev *pctldev);
-/* Please use pinctrl_register_and_init() instead */
+/* Please use pinctrl_register_and_init() and pinctrl_enable() instead */
extern struct pinctrl_dev *pinctrl_register(struct pinctrl_desc *pctldesc,
struct device *dev, void *driver_data);
/* Defines used for the flags field in the struct generic_pm_domain */
#define GENPD_FLAG_PM_CLK (1U << 0) /* PM domain uses PM clk */
#define GENPD_FLAG_IRQ_SAFE (1U << 1) /* PM domain operates in atomic */
+#define GENPD_FLAG_ALWAYS_ON (1U << 2) /* PM domain is always powered on */
enum gpd_status {
GPD_STATE_ACTIVE = 0, /* PM domain is active */
int (*clock_adjtime)(struct posix_clock *pc, struct timex *tx);
- int (*clock_gettime)(struct posix_clock *pc, struct timespec *ts);
+ int (*clock_gettime)(struct posix_clock *pc, struct timespec64 *ts);
- int (*clock_getres) (struct posix_clock *pc, struct timespec *ts);
+ int (*clock_getres) (struct posix_clock *pc, struct timespec64 *ts);
int (*clock_settime)(struct posix_clock *pc,
- const struct timespec *ts);
+ const struct timespec64 *ts);
int (*timer_create) (struct posix_clock *pc, struct k_itimer *kit);
int (*timer_delete) (struct posix_clock *pc, struct k_itimer *kit);
void (*timer_gettime)(struct posix_clock *pc,
- struct k_itimer *kit, struct itimerspec *tsp);
+ struct k_itimer *kit, struct itimerspec64 *tsp);
int (*timer_settime)(struct posix_clock *pc,
struct k_itimer *kit, int flags,
- struct itimerspec *tsp, struct itimerspec *old);
+ struct itimerspec64 *tsp, struct itimerspec64 *old);
/*
* Optional character device methods:
*/
};
struct k_clock {
- int (*clock_getres) (const clockid_t which_clock, struct timespec *tp);
+ int (*clock_getres) (const clockid_t which_clock, struct timespec64 *tp);
int (*clock_set) (const clockid_t which_clock,
- const struct timespec *tp);
- int (*clock_get) (const clockid_t which_clock, struct timespec * tp);
+ const struct timespec64 *tp);
+ int (*clock_get) (const clockid_t which_clock, struct timespec64 *tp);
int (*clock_adj) (const clockid_t which_clock, struct timex *tx);
int (*timer_create) (struct k_itimer *timer);
int (*nsleep) (const clockid_t which_clock, int flags,
- struct timespec *, struct timespec __user *);
+ struct timespec64 *, struct timespec __user *);
long (*nsleep_restart) (struct restart_block *restart_block);
- int (*timer_set) (struct k_itimer * timr, int flags,
- struct itimerspec * new_setting,
- struct itimerspec * old_setting);
- int (*timer_del) (struct k_itimer * timr);
+ int (*timer_set) (struct k_itimer *timr, int flags,
+ struct itimerspec64 *new_setting,
+ struct itimerspec64 *old_setting);
+ int (*timer_del) (struct k_itimer *timr);
#define TIMER_RETRY 1
- void (*timer_get) (struct k_itimer * timr,
- struct itimerspec * cur_setting);
+ void (*timer_get) (struct k_itimer *timr,
+ struct itimerspec64 *cur_setting);
};
extern struct k_clock clock_posix_cpu;
+++ /dev/null
-/*
- * Platform data for the TI bq24190 battery charger driver.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _BQ24190_CHARGER_H_
-#define _BQ24190_CHARGER_H_
-
-struct bq24190_platform_data {
- unsigned int gpio_int; /* GPIO pin that's connected to INT# */
-};
-
-#endif
DEV_DMA_COHERENT,
};
+struct fwnode_handle *dev_fwnode(struct device *dev);
+
bool device_property_present(struct device *dev, const char *propname);
int device_property_read_u8_array(struct device *dev, const char *propname,
u8 *val, size_t nval);
int fwnode_property_match_string(struct fwnode_handle *fwnode,
const char *propname, const char *string);
+struct fwnode_handle *fwnode_get_parent(struct fwnode_handle *fwnode);
+struct fwnode_handle *fwnode_get_next_parent(struct fwnode_handle *fwnode);
+struct fwnode_handle *fwnode_get_next_child_node(struct fwnode_handle *fwnode,
+ struct fwnode_handle *child);
+
+#define fwnode_for_each_child_node(fwnode, child) \
+ for (child = fwnode_get_next_child_node(fwnode, NULL); child; \
+ child = fwnode_get_next_child_node(fwnode, child))
+
struct fwnode_handle *device_get_next_child_node(struct device *dev,
struct fwnode_handle *child);
for (child = device_get_next_child_node(dev, NULL); child; \
child = device_get_next_child_node(dev, child))
+struct fwnode_handle *fwnode_get_named_child_node(struct fwnode_handle *fwnode,
+ const char *childname);
struct fwnode_handle *device_get_named_child_node(struct device *dev,
const char *childname);
+void fwnode_handle_get(struct fwnode_handle *fwnode);
void fwnode_handle_put(struct fwnode_handle *fwnode);
unsigned int device_get_child_node_count(struct device *dev);
void *device_get_mac_address(struct device *dev, char *addr, int alen);
+struct fwnode_handle *fwnode_graph_get_next_endpoint(
+ struct fwnode_handle *fwnode, struct fwnode_handle *prev);
+struct fwnode_handle *fwnode_graph_get_remote_port_parent(
+ struct fwnode_handle *fwnode);
+struct fwnode_handle *fwnode_graph_get_remote_port(
+ struct fwnode_handle *fwnode);
+struct fwnode_handle *fwnode_graph_get_remote_endpoint(
+ struct fwnode_handle *fwnode);
+
+int fwnode_graph_parse_endpoint(struct fwnode_handle *fwnode,
+ struct fwnode_endpoint *endpoint);
+
#endif /* _LINUX_PROPERTY_H_ */
#ifndef __RAS_H__
#define __RAS_H__
+#include <asm/errno.h>
+
#ifdef CONFIG_DEBUG_FS
int ras_userspace_consumers(void);
void ras_debugfs_init(void);
int ras_add_daemon_trace(void);
#else
static inline int ras_userspace_consumers(void) { return 0; }
-static inline void ras_debugfs_init(void) { return; }
+static inline void ras_debugfs_init(void) { }
static inline int ras_add_daemon_trace(void) { return 0; }
#endif
+#ifdef CONFIG_RAS_CEC
+void __init cec_init(void);
+int __init parse_cec_param(char *str);
+int cec_add_elem(u64 pfn);
+#else
+static inline void __init cec_init(void) { }
+static inline int cec_add_elem(u64 pfn) { return -ENODEV; }
#endif
+
+#endif /* __RAS_H__ */
#include <linux/spinlock.h>
#include <linux/kernel.h>
+/**
+ * refcount_t - variant of atomic_t specialized for reference counts
+ * @refs: atomic_t counter field
+ *
+ * The counter saturates at UINT_MAX and will not move once
+ * there. This avoids wrapping the counter and causing 'spurious'
+ * use-after-free bugs.
+ */
typedef struct refcount_struct {
atomic_t refs;
} refcount_t;
#define REFCOUNT_INIT(n) { .refs = ATOMIC_INIT(n), }
+/**
+ * refcount_set - set a refcount's value
+ * @r: the refcount
+ * @n: value to which the refcount will be set
+ */
static inline void refcount_set(refcount_t *r, unsigned int n)
{
atomic_set(&r->refs, n);
}
+/**
+ * refcount_read - get a refcount's value
+ * @r: the refcount
+ *
+ * Return: the refcount's value
+ */
static inline unsigned int refcount_read(const refcount_t *r)
{
return atomic_read(&r->refs);
struct reset_control *__of_reset_control_get(struct device_node *node,
const char *id, int index, bool shared,
bool optional);
+struct reset_control *__reset_control_get(struct device *dev, const char *id,
+ int index, bool shared,
+ bool optional);
void reset_control_put(struct reset_control *rstc);
struct reset_control *__devm_reset_control_get(struct device *dev,
const char *id, int index, bool shared,
return optional ? NULL : ERR_PTR(-ENOTSUPP);
}
+static inline struct reset_control *__reset_control_get(
+ struct device *dev, const char *id,
+ int index, bool shared, bool optional)
+{
+ return optional ? NULL : ERR_PTR(-ENOTSUPP);
+}
+
static inline struct reset_control *__devm_reset_control_get(
struct device *dev, const char *id,
int index, bool shared, bool optional)
#ifndef CONFIG_RESET_CONTROLLER
WARN_ON(1);
#endif
- return __of_reset_control_get(dev ? dev->of_node : NULL, id, 0, false,
- false);
+ return __reset_control_get(dev, id, 0, false, false);
}
/**
static inline struct reset_control *reset_control_get_shared(
struct device *dev, const char *id)
{
- return __of_reset_control_get(dev ? dev->of_node : NULL, id, 0, true,
- false);
+ return __reset_control_get(dev, id, 0, true, false);
}
static inline struct reset_control *reset_control_get_optional_exclusive(
struct device *dev, const char *id)
{
- return __of_reset_control_get(dev ? dev->of_node : NULL, id, 0, false,
- true);
+ return __reset_control_get(dev, id, 0, false, true);
}
static inline struct reset_control *reset_control_get_optional_shared(
struct device *dev, const char *id)
{
- return __of_reset_control_get(dev ? dev->of_node : NULL, id, 0, true,
- true);
+ return __reset_control_get(dev, id, 0, true, true);
}
/**
int sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint, bool round_robin);
/**
+ * sbitmap_get_shallow() - Try to allocate a free bit from a &struct sbitmap,
+ * limiting the depth used from each word.
+ * @sb: Bitmap to allocate from.
+ * @alloc_hint: Hint for where to start searching for a free bit.
+ * @shallow_depth: The maximum number of bits to allocate from a single word.
+ *
+ * This rather specific operation allows for having multiple users with
+ * different allocation limits. E.g., there can be a high-priority class that
+ * uses sbitmap_get() and a low-priority class that uses sbitmap_get_shallow()
+ * with a @shallow_depth of (1 << (@sb->shift - 1)). Then, the low-priority
+ * class can only allocate half of the total bits in the bitmap, preventing it
+ * from starving out the high-priority class.
+ *
+ * Return: Non-negative allocated bit number if successful, -1 otherwise.
+ */
+int sbitmap_get_shallow(struct sbitmap *sb, unsigned int alloc_hint,
+ unsigned long shallow_depth);
+
+/**
* sbitmap_any_bit_set() - Check for a set bit in a &struct sbitmap.
* @sb: Bitmap to check.
*
int __sbitmap_queue_get(struct sbitmap_queue *sbq);
/**
+ * __sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct
+ * sbitmap_queue, limiting the depth used from each word, with preemption
+ * already disabled.
+ * @sbq: Bitmap queue to allocate from.
+ * @shallow_depth: The maximum number of bits to allocate from a single word.
+ * See sbitmap_get_shallow().
+ *
+ * Return: Non-negative allocated bit number if successful, -1 otherwise.
+ */
+int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
+ unsigned int shallow_depth);
+
+/**
* sbitmap_queue_get() - Try to allocate a free bit from a &struct
* sbitmap_queue.
* @sbq: Bitmap queue to allocate from.
}
/**
+ * sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct
+ * sbitmap_queue, limiting the depth used from each word.
+ * @sbq: Bitmap queue to allocate from.
+ * @cpu: Output parameter; will contain the CPU we ran on (e.g., to be passed to
+ * sbitmap_queue_clear()).
+ * @shallow_depth: The maximum number of bits to allocate from a single word.
+ * See sbitmap_get_shallow().
+ *
+ * Return: Non-negative allocated bit number if successful, -1 otherwise.
+ */
+static inline int sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
+ unsigned int *cpu,
+ unsigned int shallow_depth)
+{
+ int nr;
+
+ *cpu = get_cpu();
+ nr = __sbitmap_queue_get_shallow(sbq, shallow_depth);
+ put_cpu();
+ return nr;
+}
+
+/**
* sbitmap_queue_clear() - Free an allocated bit and wake up waiters on a
* &struct sbitmap_queue.
* @sbq: Bitmap to free from.
#ifdef CONFIG_COMPAT_BRK
unsigned brk_randomized:1;
#endif
+#ifdef CONFIG_CGROUPS
+ /* disallow userland-initiated cgroup migration */
+ unsigned no_cgroup_migration:1;
+#endif
unsigned long atomic_flags; /* Flags requiring atomic access. */
/* PI waiters blocked on a rt_mutex held by this task: */
struct rb_root pi_waiters;
struct rb_node *pi_waiters_leftmost;
+ /* Updated under owner's pi_lock and rq lock */
+ struct task_struct *pi_top_task;
/* Deadlock detection and priority inheritance handling: */
struct rt_mutex_waiter *pi_blocked_on;
#endif
TASK_PFA_SET(LMK_WAITING, lmk_waiting)
static inline void
-tsk_restore_flags(struct task_struct *task, unsigned long orig_flags, unsigned long flags)
+current_restore_flags(unsigned long orig_flags, unsigned long flags)
{
- task->flags &= ~flags;
- task->flags |= orig_flags & flags;
+ current->flags &= ~flags;
+ current->flags |= orig_flags & flags;
}
extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
}
#ifdef CONFIG_RT_MUTEXES
-extern int rt_mutex_getprio(struct task_struct *p);
-extern void rt_mutex_setprio(struct task_struct *p, int prio);
-extern int rt_mutex_get_effective_prio(struct task_struct *task, int newprio);
-extern struct task_struct *rt_mutex_get_top_task(struct task_struct *task);
+/*
+ * Must hold either p->pi_lock or task_rq(p)->lock.
+ */
+static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *p)
+{
+ return p->pi_top_task;
+}
+extern void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task);
extern void rt_mutex_adjust_pi(struct task_struct *p);
static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
{
return tsk->pi_blocked_on != NULL;
}
#else
-static inline int rt_mutex_getprio(struct task_struct *p)
-{
- return p->normal_prio;
-}
-
-static inline int rt_mutex_get_effective_prio(struct task_struct *task,
- int newprio)
-{
- return newprio;
-}
-
static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
{
return NULL;
extern void __init setup_nr_cpu_ids(void);
extern void __init smp_init(void);
+extern int __boot_cpu_id;
+
+static inline int get_boot_cpu_id(void)
+{
+ return __boot_cpu_id;
+}
+
#else /* !SMP */
static inline void smp_send_stop(void) { }
static inline void smp_init(void) { }
#endif
+static inline int get_boot_cpu_id(void)
+{
+ return 0;
+}
+
#endif /* !SMP */
/*
unsigned int nlink;
uint32_t blksize; /* Preferred I/O size */
u64 attributes;
+ u64 attributes_mask;
#define KSTAT_ATTR_FS_IOC_FLAGS \
(STATX_ATTR_COMPRESSED | \
STATX_ATTR_IMMUTABLE | \
};
-extern struct blk_integrity_profile t10_pi_type1_crc;
-extern struct blk_integrity_profile t10_pi_type1_ip;
-extern struct blk_integrity_profile t10_pi_type3_crc;
-extern struct blk_integrity_profile t10_pi_type3_ip;
+extern const struct blk_integrity_profile t10_pi_type1_crc;
+extern const struct blk_integrity_profile t10_pi_type1_ip;
+extern const struct blk_integrity_profile t10_pi_type3_crc;
+extern const struct blk_integrity_profile t10_pi_type3_ip;
#endif
{ }
#endif /* CONFIG_HARDENED_USERCOPY */
+#ifndef arch_setup_new_exec
+static inline void arch_setup_new_exec(void) { }
+#endif
+
#endif /* __KERNEL__ */
#endif /* _LINUX_THREAD_INFO_H */
extern void tick_nohz_idle_exit(void);
extern void tick_nohz_irq_exit(void);
extern ktime_t tick_nohz_get_sleep_length(void);
+extern unsigned long tick_nohz_get_idle_calls(void);
extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time);
#else /* !CONFIG_NO_HZ_COMMON */
extern int do_settimeofday64(const struct timespec64 *ts);
extern int do_sys_settimeofday64(const struct timespec64 *tv,
const struct timezone *tz);
-static inline int do_sys_settimeofday(const struct timespec *tv,
- const struct timezone *tz)
-{
- struct timespec64 ts64;
-
- if (!tv)
- return do_sys_settimeofday64(NULL, tz);
-
- if (!timespec_valid(tv))
- return -EINVAL;
-
- ts64 = timespec_to_timespec64(*tv);
- return do_sys_settimeofday64(&ts64, tz);
-}
-
/*
* Kernel time accessors
*/
*ts = ktime_to_timespec(ktime_get_clocktai());
}
+static inline void timekeeping_clocktai64(struct timespec64 *ts)
+{
+ *ts = ktime_to_timespec64(ktime_get_clocktai());
+}
+
/*
* RTC specific
*/
#define __LINUX_UACCESS_H__
#include <linux/sched.h>
+#include <linux/thread_info.h>
+#include <linux/kasan-checks.h>
+
+#define VERIFY_READ 0
+#define VERIFY_WRITE 1
+
+#define uaccess_kernel() segment_eq(get_fs(), KERNEL_DS)
+
#include <asm/uaccess.h>
+/*
+ * Architectures should provide two primitives (raw_copy_{to,from}_user())
+ * and get rid of their private instances of copy_{to,from}_user() and
+ * __copy_{to,from}_user{,_inatomic}().
+ *
+ * raw_copy_{to,from}_user(to, from, size) should copy up to size bytes and
+ * return the amount left to copy. They should assume that access_ok() has
+ * already been checked (and succeeded); they should *not* zero-pad anything.
+ * No KASAN or object size checks either - those belong here.
+ *
+ * Both of these functions should attempt to copy size bytes starting at from
+ * into the area starting at to. They must not fetch or store anything
+ * outside of those areas. Return value must be between 0 (everything
+ * copied successfully) and size (nothing copied).
+ *
+ * If raw_copy_{to,from}_user(to, from, size) returns N, size - N bytes starting
+ * at to must become equal to the bytes fetched from the corresponding area
+ * starting at from. All data past to + size - N must be left unmodified.
+ *
+ * If copying succeeds, the return value must be 0. If some data cannot be
+ * fetched, it is permitted to copy less than had been fetched; the only
+ * hard requirement is that not storing anything at all (i.e. returning size)
+ * should happen only when nothing could be copied. In other words, you don't
+ * have to squeeze as much as possible - it is allowed, but not necessary.
+ *
+ * For raw_copy_from_user() to always points to kernel memory and no faults
+ * on store should happen. Interpretation of from is affected by set_fs().
+ * For raw_copy_to_user() it's the other way round.
+ *
+ * Both can be inlined - it's up to architectures whether it wants to bother
+ * with that. They should not be used directly; they are used to implement
+ * the 6 functions (copy_{to,from}_user(), __copy_{to,from}_user_inatomic())
+ * that are used instead. Out of those, __... ones are inlined. Plain
+ * copy_{to,from}_user() might or might not be inlined. If you want them
+ * inlined, have asm/uaccess.h define INLINE_COPY_{TO,FROM}_USER.
+ *
+ * NOTE: only copy_from_user() zero-pads the destination in case of short copy.
+ * Neither __copy_from_user() nor __copy_from_user_inatomic() zero anything
+ * at all; their callers absolutely must check the return value.
+ *
+ * Biarch ones should also provide raw_copy_in_user() - similar to the above,
+ * but both source and destination are __user pointers (affected by set_fs()
+ * as usual) and both source and destination can trigger faults.
+ */
+
+static __always_inline unsigned long
+__copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
+{
+ kasan_check_write(to, n);
+ check_object_size(to, n, false);
+ return raw_copy_from_user(to, from, n);
+}
+
+static __always_inline unsigned long
+__copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+ might_fault();
+ kasan_check_write(to, n);
+ check_object_size(to, n, false);
+ return raw_copy_from_user(to, from, n);
+}
+
+/**
+ * __copy_to_user_inatomic: - Copy a block of data into user space, with less checking.
+ * @to: Destination address, in user space.
+ * @from: Source address, in kernel space.
+ * @n: Number of bytes to copy.
+ *
+ * Context: User context only.
+ *
+ * Copy data from kernel space to user space. Caller must check
+ * the specified block with access_ok() before calling this function.
+ * The caller should also make sure he pins the user space address
+ * so that we don't result in page fault and sleep.
+ */
+static __always_inline unsigned long
+__copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
+{
+ kasan_check_read(from, n);
+ check_object_size(from, n, true);
+ return raw_copy_to_user(to, from, n);
+}
+
+static __always_inline unsigned long
+__copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+ might_fault();
+ kasan_check_read(from, n);
+ check_object_size(from, n, true);
+ return raw_copy_to_user(to, from, n);
+}
+
+#ifdef INLINE_COPY_FROM_USER
+static inline unsigned long
+_copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+ unsigned long res = n;
+ if (likely(access_ok(VERIFY_READ, from, n)))
+ res = raw_copy_from_user(to, from, n);
+ if (unlikely(res))
+ memset(to + (n - res), 0, res);
+ return res;
+}
+#else
+extern unsigned long
+_copy_from_user(void *, const void __user *, unsigned long);
+#endif
+
+#ifdef INLINE_COPY_TO_USER
+static inline unsigned long
+_copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+ if (access_ok(VERIFY_WRITE, to, n))
+ n = raw_copy_to_user(to, from, n);
+ return n;
+}
+#else
+extern unsigned long
+_copy_to_user(void __user *, const void *, unsigned long);
+#endif
+
+extern void __compiletime_error("usercopy buffer size is too small")
+__bad_copy_user(void);
+
+static inline void copy_user_overflow(int size, unsigned long count)
+{
+ WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
+}
+
+static __always_inline unsigned long __must_check
+copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+ int sz = __compiletime_object_size(to);
+
+ might_fault();
+ kasan_check_write(to, n);
+
+ if (likely(sz < 0 || sz >= n)) {
+ check_object_size(to, n, false);
+ n = _copy_from_user(to, from, n);
+ } else if (!__builtin_constant_p(n))
+ copy_user_overflow(sz, n);
+ else
+ __bad_copy_user();
+
+ return n;
+}
+
+static __always_inline unsigned long __must_check
+copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+ int sz = __compiletime_object_size(from);
+
+ kasan_check_read(from, n);
+ might_fault();
+
+ if (likely(sz < 0 || sz >= n)) {
+ check_object_size(from, n, true);
+ n = _copy_to_user(to, from, n);
+ } else if (!__builtin_constant_p(n))
+ copy_user_overflow(sz, n);
+ else
+ __bad_copy_user();
+
+ return n;
+}
+#ifdef CONFIG_COMPAT
+static __always_inline unsigned long __must_check
+__copy_in_user(void __user *to, const void *from, unsigned long n)
+{
+ might_fault();
+ return raw_copy_in_user(to, from, n);
+}
+static __always_inline unsigned long __must_check
+copy_in_user(void __user *to, const void *from, unsigned long n)
+{
+ might_fault();
+ if (access_ok(VERIFY_WRITE, to, n) && access_ok(VERIFY_READ, from, n))
+ n = raw_copy_in_user(to, from, n);
+ return n;
+}
+#endif
+
static __always_inline void pagefault_disabled_inc(void)
{
current->pagefault_disabled++;
return __copy_from_user_inatomic(to, from, n);
}
-static inline unsigned long __copy_from_user_nocache(void *to,
- const void __user *from, unsigned long n)
-{
- return __copy_from_user(to, from, n);
-}
-
#endif /* ARCH_HAS_NOCACHE_UACCESS */
/*
};
union {
unsigned long nr_segs;
- int idx;
+ struct {
+ int idx;
+ int start_idx;
+ };
};
};
size_t iov_iter_copy_from_user_atomic(struct page *page,
struct iov_iter *i, unsigned long offset, size_t bytes);
void iov_iter_advance(struct iov_iter *i, size_t bytes);
+void iov_iter_revert(struct iov_iter *i, size_t bytes);
int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes);
size_t iov_iter_single_seg_count(const struct iov_iter *i);
size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
unsigned int feature_table_size;
const unsigned int *feature_table_legacy;
unsigned int feature_table_size_legacy;
+ int (*validate)(struct virtio_device *dev);
int (*probe)(struct virtio_device *dev);
void (*scan)(struct virtio_device *dev);
void (*remove)(struct virtio_device *dev);
{
return fn(arg);
}
+static inline long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg)
+{
+ return fn(arg);
+}
#else
long work_on_cpu(int cpu, long (*fn)(void *), void *arg);
+long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg);
#endif /* CONFIG_SMP */
#ifdef CONFIG_FREEZER
static inline void inode_detach_wb(struct inode *inode)
{
if (inode->i_wb) {
+ WARN_ON_ONCE(!(inode->i_state & I_CLEAR));
wb_put(inode->i_wb);
inode->i_wb = NULL;
}
return frag;
}
-static inline void sctp_assoc_pending_pmtu(struct sock *sk, struct sctp_association *asoc)
+static inline void sctp_assoc_pending_pmtu(struct sctp_association *asoc)
{
-
- sctp_assoc_sync_pmtu(sk, asoc);
+ sctp_assoc_sync_pmtu(asoc);
asoc->pmtu_pending = 0;
}
*/
static inline struct dst_entry *sctp_transport_dst_check(struct sctp_transport *t)
{
- if (t->dst && (!dst_check(t->dst, t->dst_cookie) ||
- t->pathmtu != max_t(size_t, SCTP_TRUNC4(dst_mtu(t->dst)),
- SCTP_DEFAULT_MINSEGMENT)))
+ if (t->dst && !dst_check(t->dst, t->dst_cookie))
sctp_transport_dst_release(t);
return t->dst;
}
+static inline bool sctp_transport_pmtu_check(struct sctp_transport *t)
+{
+ __u32 pmtu = max_t(size_t, SCTP_TRUNC4(dst_mtu(t->dst)),
+ SCTP_DEFAULT_MINSEGMENT);
+
+ if (t->pathmtu == pmtu)
+ return true;
+
+ t->pathmtu = pmtu;
+
+ return false;
+}
+
#endif /* __net_sctp_h__ */
__u64 hb_nonce;
} sctp_sender_hb_info_t;
-struct sctp_stream *sctp_stream_new(__u16 incnt, __u16 outcnt, gfp_t gfp);
+int sctp_stream_new(struct sctp_association *asoc, gfp_t gfp);
+int sctp_stream_init(struct sctp_association *asoc, gfp_t gfp);
void sctp_stream_free(struct sctp_stream *stream);
void sctp_stream_clear(struct sctp_stream *stream);
/* Did the messenge fail to send? */
int send_error;
u8 send_failed:1,
- force_delay:1,
can_delay; /* should this message be Nagle delayed */
};
void sctp_transport_burst_limited(struct sctp_transport *);
void sctp_transport_burst_reset(struct sctp_transport *);
unsigned long sctp_transport_timeout(struct sctp_transport *);
-void sctp_transport_reset(struct sctp_transport *);
-void sctp_transport_update_pmtu(struct sock *, struct sctp_transport *, u32);
+void sctp_transport_reset(struct sctp_transport *t);
+void sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu);
void sctp_transport_immediate_rtx(struct sctp_transport *);
void sctp_transport_dst_release(struct sctp_transport *t);
void sctp_transport_dst_confirm(struct sctp_transport *t);
__u8 need_ecne:1, /* Need to send an ECNE Chunk? */
temp:1, /* Is it a temporary association? */
+ force_delay:1,
prsctp_enable:1,
reconf_enable:1;
__u32 sctp_association_get_next_tsn(struct sctp_association *);
-void sctp_assoc_sync_pmtu(struct sock *, struct sctp_association *);
+void sctp_assoc_sync_pmtu(struct sctp_association *asoc);
void sctp_assoc_rwnd_increase(struct sctp_association *, unsigned int);
void sctp_assoc_rwnd_decrease(struct sctp_association *, unsigned int);
void sctp_assoc_set_primary(struct sctp_association *,
*/
static inline bool ib_safe_file_access(struct file *filp)
{
- return filp->f_cred == current_cred() && segment_eq(get_fs(), USER_DS);
+ return filp->f_cred == current_cred() && !uaccess_kernel();
}
#endif /* _RDMA_IB_H */
unsigned char __cmd[BLK_MAX_CDB];
unsigned char *cmd;
unsigned short cmd_len;
+ int result;
unsigned int sense_len;
unsigned int resid_len; /* residual count */
+ int retries;
void *sense;
};
TRANSPORT_ISTATE_PROCESSING = 11,
TRANSPORT_COMPLETE_QF_WP = 18,
TRANSPORT_COMPLETE_QF_OK = 19,
+ TRANSPORT_COMPLETE_QF_ERR = 20,
};
/* Used for struct se_cmd->se_cmd_flags */
u16 tg_pt_gp_id;
int tg_pt_gp_valid_id;
int tg_pt_gp_alua_supported_states;
- int tg_pt_gp_alua_pending_state;
- int tg_pt_gp_alua_previous_state;
int tg_pt_gp_alua_access_status;
int tg_pt_gp_alua_access_type;
int tg_pt_gp_nonop_delay_msecs;
int tg_pt_gp_pref;
int tg_pt_gp_write_metadata;
u32 tg_pt_gp_members;
- atomic_t tg_pt_gp_alua_access_state;
+ int tg_pt_gp_alua_access_state;
atomic_t tg_pt_gp_ref_cnt;
spinlock_t tg_pt_gp_lock;
- struct mutex tg_pt_gp_md_mutex;
+ struct mutex tg_pt_gp_transition_mutex;
struct se_device *tg_pt_gp_dev;
struct config_group tg_pt_gp_group;
struct list_head tg_pt_gp_list;
struct list_head tg_pt_gp_lun_list;
struct se_lun *tg_pt_gp_alua_lun;
struct se_node_acl *tg_pt_gp_alua_nacl;
- struct work_struct tg_pt_gp_transition_work;
- struct completion *tg_pt_gp_transition_complete;
};
struct t10_vpd {
u64 unpacked_lun;
#define SE_LUN_LINK_MAGIC 0xffff7771
u32 lun_link_magic;
+ bool lun_shutdown;
bool lun_access_ro;
u32 lun_index;
TP_ARGS(bh)
);
-DECLARE_EVENT_CLASS(block_rq_with_error,
+/**
+ * block_rq_requeue - place block IO request back on a queue
+ * @q: queue holding operation
+ * @rq: block IO operation request
+ *
+ * The block operation request @rq is being placed back into queue
+ * @q. For some reason the request was not completed and needs to be
+ * put back in the queue.
+ */
+TRACE_EVENT(block_rq_requeue,
TP_PROTO(struct request_queue *q, struct request *rq),
__field( dev_t, dev )
__field( sector_t, sector )
__field( unsigned int, nr_sector )
- __field( int, errors )
__array( char, rwbs, RWBS_LEN )
__dynamic_array( char, cmd, 1 )
),
__entry->dev = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
__entry->sector = blk_rq_trace_sector(rq);
__entry->nr_sector = blk_rq_trace_nr_sectors(rq);
- __entry->errors = rq->errors;
blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq));
__get_str(cmd)[0] = '\0';
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->rwbs, __get_str(cmd),
(unsigned long long)__entry->sector,
- __entry->nr_sector, __entry->errors)
-);
-
-/**
- * block_rq_abort - abort block operation request
- * @q: queue containing the block operation request
- * @rq: block IO operation request
- *
- * Called immediately after pending block IO operation request @rq in
- * queue @q is aborted. The fields in the operation request @rq
- * can be examined to determine which device and sectors the pending
- * operation would access.
- */
-DEFINE_EVENT(block_rq_with_error, block_rq_abort,
-
- TP_PROTO(struct request_queue *q, struct request *rq),
-
- TP_ARGS(q, rq)
-);
-
-/**
- * block_rq_requeue - place block IO request back on a queue
- * @q: queue holding operation
- * @rq: block IO operation request
- *
- * The block operation request @rq is being placed back into queue
- * @q. For some reason the request was not completed and needs to be
- * put back in the queue.
- */
-DEFINE_EVENT(block_rq_with_error, block_rq_requeue,
-
- TP_PROTO(struct request_queue *q, struct request *rq),
-
- TP_ARGS(q, rq)
+ __entry->nr_sector, 0)
);
/**
* block_rq_complete - block IO operation completed by device driver
- * @q: queue containing the block operation request
* @rq: block operations request
+ * @error: status code
* @nr_bytes: number of completed bytes
*
* The block_rq_complete tracepoint event indicates that some portion
*/
TRACE_EVENT(block_rq_complete,
- TP_PROTO(struct request_queue *q, struct request *rq,
- unsigned int nr_bytes),
+ TP_PROTO(struct request *rq, int error, unsigned int nr_bytes),
- TP_ARGS(q, rq, nr_bytes),
+ TP_ARGS(rq, error, nr_bytes),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( sector_t, sector )
__field( unsigned int, nr_sector )
- __field( int, errors )
+ __field( int, error )
__array( char, rwbs, RWBS_LEN )
__dynamic_array( char, cmd, 1 )
),
__entry->dev = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
__entry->sector = blk_rq_pos(rq);
__entry->nr_sector = nr_bytes >> 9;
- __entry->errors = rq->errors;
+ __entry->error = error;
blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, nr_bytes);
__get_str(cmd)[0] = '\0';
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->rwbs, __get_str(cmd),
(unsigned long long)__entry->sector,
- __entry->nr_sector, __entry->errors)
+ __entry->nr_sector, __entry->error)
);
DECLARE_EVENT_CLASS(block_rq,
TP_fast_assign(
memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
__entry->pid = p->pid;
- __entry->prio = p->prio;
+ __entry->prio = p->prio; /* XXX SCHED_DEADLINE */
__entry->success = 1; /* rudiment, kill when possible */
__entry->target_cpu = task_cpu(p);
),
memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
__entry->next_pid = next->pid;
__entry->next_prio = next->prio;
+ /* XXX SCHED_DEADLINE */
),
TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s%s ==> next_comm=%s next_pid=%d next_prio=%d",
TP_fast_assign(
memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
__entry->pid = p->pid;
- __entry->prio = p->prio;
+ __entry->prio = p->prio; /* XXX SCHED_DEADLINE */
__entry->orig_cpu = task_cpu(p);
__entry->dest_cpu = dest_cpu;
),
TP_fast_assign(
memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
__entry->pid = p->pid;
- __entry->prio = p->prio;
+ __entry->prio = p->prio; /* XXX SCHED_DEADLINE */
),
TP_printk("comm=%s pid=%d prio=%d",
TP_fast_assign(
memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
__entry->pid = pid_nr(pid);
- __entry->prio = current->prio;
+ __entry->prio = current->prio; /* XXX SCHED_DEADLINE */
),
TP_printk("comm=%s pid=%d prio=%d",
*/
TRACE_EVENT(sched_pi_setprio,
- TP_PROTO(struct task_struct *tsk, int newprio),
+ TP_PROTO(struct task_struct *tsk, struct task_struct *pi_task),
- TP_ARGS(tsk, newprio),
+ TP_ARGS(tsk, pi_task),
TP_STRUCT__entry(
__array( char, comm, TASK_COMM_LEN )
memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
__entry->pid = tsk->pid;
__entry->oldprio = tsk->prio;
- __entry->newprio = newprio;
+ __entry->newprio = pi_task ? pi_task->prio : tsk->prio;
+ /* XXX SCHED_DEADLINE bits missing */
),
TP_printk("comm=%s pid=%d oldprio=%d newprio=%d",
header-y += unix_diag.h
header-y += usbdevice_fs.h
header-y += usbip.h
+header-y += userio.h
header-y += utime.h
header-y += utsname.h
header-y += uuid.h
#define EM_TILEGX 191 /* Tilera TILE-Gx */
#define EM_BPF 247 /* Linux BPF - in-kernel virtual machine */
#define EM_FRV 0x5441 /* Fujitsu FR-V */
-#define EM_AVR32 0x18ad /* Atmel AVR32 */
/*
* This is an interim value that we will use until the committee comes
#define RTF_PREF(pref) ((pref) << 27)
#define RTF_PREF_MASK 0x18000000
-#define RTF_PCPU 0x40000000
+#define RTF_PCPU 0x40000000 /* read-only: can not be set by user */
#define RTF_LOCAL 0x80000000
};
};
+enum {
+ NVM_TARGET_FACTORY = 1 << 0, /* Init target in factory mode */
+};
+
struct nvm_ioctl_create {
char dev[DISK_NAME_LEN]; /* open-channel SSD device */
char tgttype[NVM_TTYPE_NAME_MAX]; /* target type name */
--- /dev/null
+/*
+ * Copyright (C) 2017 Facebook. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+#ifndef _UAPILINUX_NBD_NETLINK_H
+#define _UAPILINUX_NBD_NETLINK_H
+
+#define NBD_GENL_FAMILY_NAME "nbd"
+#define NBD_GENL_VERSION 0x1
+#define NBD_GENL_MCAST_GROUP_NAME "nbd_mc_group"
+
+/* Configuration policy attributes, used for CONNECT */
+enum {
+ NBD_ATTR_UNSPEC,
+ NBD_ATTR_INDEX,
+ NBD_ATTR_SIZE_BYTES,
+ NBD_ATTR_BLOCK_SIZE_BYTES,
+ NBD_ATTR_TIMEOUT,
+ NBD_ATTR_SERVER_FLAGS,
+ NBD_ATTR_CLIENT_FLAGS,
+ NBD_ATTR_SOCKETS,
+ NBD_ATTR_DEAD_CONN_TIMEOUT,
+ NBD_ATTR_DEVICE_LIST,
+ __NBD_ATTR_MAX,
+};
+#define NBD_ATTR_MAX (__NBD_ATTR_MAX - 1)
+
+/*
+ * This is the format for multiple devices with NBD_ATTR_DEVICE_LIST
+ *
+ * [NBD_ATTR_DEVICE_LIST]
+ * [NBD_DEVICE_ITEM]
+ * [NBD_DEVICE_INDEX]
+ * [NBD_DEVICE_CONNECTED]
+ */
+enum {
+ NBD_DEVICE_ITEM_UNSPEC,
+ NBD_DEVICE_ITEM,
+ __NBD_DEVICE_ITEM_MAX,
+};
+#define NBD_DEVICE_ITEM_MAX (__NBD_DEVICE_ITEM_MAX - 1)
+
+enum {
+ NBD_DEVICE_UNSPEC,
+ NBD_DEVICE_INDEX,
+ NBD_DEVICE_CONNECTED,
+ __NBD_DEVICE_MAX,
+};
+#define NBD_DEVICE_ATTR_MAX (__NBD_DEVICE_MAX - 1)
+
+/*
+ * This is the format for multiple sockets with NBD_ATTR_SOCKETS
+ *
+ * [NBD_ATTR_SOCKETS]
+ * [NBD_SOCK_ITEM]
+ * [NBD_SOCK_FD]
+ * [NBD_SOCK_ITEM]
+ * [NBD_SOCK_FD]
+ */
+enum {
+ NBD_SOCK_ITEM_UNSPEC,
+ NBD_SOCK_ITEM,
+ __NBD_SOCK_ITEM_MAX,
+};
+#define NBD_SOCK_ITEM_MAX (__NBD_SOCK_ITEM_MAX - 1)
+
+enum {
+ NBD_SOCK_UNSPEC,
+ NBD_SOCK_FD,
+ __NBD_SOCK_MAX,
+};
+#define NBD_SOCK_MAX (__NBD_SOCK_MAX - 1)
+
+enum {
+ NBD_CMD_UNSPEC,
+ NBD_CMD_CONNECT,
+ NBD_CMD_DISCONNECT,
+ NBD_CMD_RECONFIGURE,
+ NBD_CMD_LINK_DEAD,
+ NBD_CMD_STATUS,
+ __NBD_CMD_MAX,
+};
+#define NBD_CMD_MAX (__NBD_CMD_MAX - 1)
+
+#endif /* _UAPILINUX_NBD_NETLINK_H */
NBD_CMD_TRIM = 4
};
-/* values for flags field */
+/* values for flags field, these are server interaction specific. */
#define NBD_FLAG_HAS_FLAGS (1 << 0) /* nbd-server supports flags */
#define NBD_FLAG_READ_ONLY (1 << 1) /* device is read-only */
#define NBD_FLAG_SEND_FLUSH (1 << 2) /* can flush writeback cache */
#define NBD_FLAG_SEND_TRIM (1 << 5) /* send trim/discard */
#define NBD_FLAG_CAN_MULTI_CONN (1 << 8) /* Server supports multiple connections per export. */
+/* These are client behavior specific flags. */
+#define NBD_CFLAG_DESTROY_ON_DISCONNECT (1 << 0) /* delete the nbd device on
+ disconnect. */
+
/* userspace doesn't need the nbd_device structure */
/* These are sent over the network in the request/reply magic fields */
use_clockid : 1, /* use @clockid for time fields */
context_switch : 1, /* context switch data */
write_backward : 1, /* Write ring buffer from end to beginning */
- __reserved_1 : 36;
+ namespaces : 1, /* include namespaces data */
+ __reserved_1 : 35;
union {
__u32 wakeup_events; /* wakeup every n events */
__u16 size;
};
+struct perf_ns_link_info {
+ __u64 dev;
+ __u64 ino;
+};
+
+enum {
+ NET_NS_INDEX = 0,
+ UTS_NS_INDEX = 1,
+ IPC_NS_INDEX = 2,
+ PID_NS_INDEX = 3,
+ USER_NS_INDEX = 4,
+ MNT_NS_INDEX = 5,
+ CGROUP_NS_INDEX = 6,
+
+ NR_NAMESPACES, /* number of available namespaces */
+};
+
enum perf_event_type {
/*
*/
PERF_RECORD_SWITCH_CPU_WIDE = 15,
+ /*
+ * struct {
+ * struct perf_event_header header;
+ * u32 pid;
+ * u32 tid;
+ * u64 nr_namespaces;
+ * { u64 dev, inode; } [nr_namespaces];
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_NAMESPACES = 16,
+
PERF_RECORD_MAX, /* non-ABI */
};
*/
#define PERF_AUX_FLAG_TRUNCATED 0x01 /* record was truncated to fit */
#define PERF_AUX_FLAG_OVERWRITE 0x02 /* snapshot from overwrite mode */
+#define PERF_AUX_FLAG_PARTIAL 0x04 /* record contains gaps */
#define PERF_FLAG_FD_NO_GROUP (1UL << 0)
#define PERF_FLAG_FD_OUTPUT (1UL << 1)
* tv_sec holds the number of seconds before (negative) or after (positive)
* 00:00:00 1st January 1970 UTC.
*
- * tv_nsec holds a number of nanoseconds before (0..-999,999,999 if tv_sec is
- * negative) or after (0..999,999,999 if tv_sec is positive) the tv_sec time.
- *
- * Note that if both tv_sec and tv_nsec are non-zero, then the two values must
- * either be both positive or both negative.
+ * tv_nsec holds a number of nanoseconds (0..999,999,999) after the tv_sec time.
*
* __reserved is held in case we need a yet finer resolution.
*/
struct statx_timestamp {
__s64 tv_sec;
- __s32 tv_nsec;
+ __u32 tv_nsec;
__s32 __reserved;
};
__u64 stx_ino; /* Inode number */
__u64 stx_size; /* File size */
__u64 stx_blocks; /* Number of 512-byte blocks allocated */
- __u64 __spare1[1];
+ __u64 stx_attributes_mask; /* Mask to show what's supported in stx_attributes */
/* 0x40 */
struct statx_timestamp stx_atime; /* Last access time */
struct statx_timestamp stx_btime; /* File creation time */
#define STATX_BASIC_STATS 0x000007ffU /* The stuff in the normal stat struct */
#define STATX_BTIME 0x00000800U /* Want/got stx_btime */
#define STATX_ALL 0x00000fffU /* All currently supported flags */
+#define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */
/*
- * Attributes to be found in stx_attributes
+ * Attributes to be found in stx_attributes and masked in stx_attributes_mask.
*
* These give information about the features or the state of a file that might
* be of use to ordinary userspace programs such as GUIs or ls rather than
* configuration space */
#define VIRTIO_PCI_CONFIG_OFF(msix_enabled) ((msix_enabled) ? 24 : 20)
/* Deprecated: please use VIRTIO_PCI_CONFIG_OFF instead */
-#define VIRTIO_PCI_CONFIG(dev) VIRTIO_PCI_CONFIG_OFF((dev)->pci_dev->msix_enabled)
+#define VIRTIO_PCI_CONFIG(dev) VIRTIO_PCI_CONFIG_OFF((dev)->msix_enabled)
/* Virtio ABI version, this must match exactly */
#define VIRTIO_PCI_ABI_VERSION 0
unsigned long n_pfns;
};
-#define XEN_EXTRA_MEM_MAX_REGIONS 128 /* == E820MAX */
+#define XEN_EXTRA_MEM_MAX_REGIONS 128 /* == E820_MAX_ENTRIES_ZEROPAGE */
extern __initdata
struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS];
/* queue msgs to send via kauditd_task */
static struct sk_buff_head audit_queue;
-static void kauditd_hold_skb(struct sk_buff *skb);
/* queue msgs due to temporary unicast send problems */
static struct sk_buff_head audit_retry_queue;
/* queue msgs waiting for new auditd connection */
}
/**
- * auditd_reset - Disconnect the auditd connection
- *
- * Description:
- * Break the auditd/kauditd connection and move all the queued records into the
- * hold queue in case auditd reconnects.
- */
-static void auditd_reset(void)
-{
- struct sk_buff *skb;
-
- /* if it isn't already broken, break the connection */
- rcu_read_lock();
- if (auditd_conn.pid)
- auditd_set(0, 0, NULL);
- rcu_read_unlock();
-
- /* flush all of the main and retry queues to the hold queue */
- while ((skb = skb_dequeue(&audit_retry_queue)))
- kauditd_hold_skb(skb);
- while ((skb = skb_dequeue(&audit_queue)))
- kauditd_hold_skb(skb);
-}
-
-/**
* kauditd_print_skb - Print the audit record to the ring buffer
* @skb: audit record
*
{
/* put the record back in the queue at the same place */
skb_queue_head(&audit_hold_queue, skb);
-
- /* fail the auditd connection */
- auditd_reset();
}
/**
/* we have no other options - drop the message */
audit_log_lost("kauditd hold queue overflow");
kfree_skb(skb);
-
- /* fail the auditd connection */
- auditd_reset();
}
/**
}
/**
+ * auditd_reset - Disconnect the auditd connection
+ *
+ * Description:
+ * Break the auditd/kauditd connection and move all the queued records into the
+ * hold queue in case auditd reconnects.
+ */
+static void auditd_reset(void)
+{
+ struct sk_buff *skb;
+
+ /* if it isn't already broken, break the connection */
+ rcu_read_lock();
+ if (auditd_conn.pid)
+ auditd_set(0, 0, NULL);
+ rcu_read_unlock();
+
+ /* flush all of the main and retry queues to the hold queue */
+ while ((skb = skb_dequeue(&audit_retry_queue)))
+ kauditd_hold_skb(skb);
+ while ((skb = skb_dequeue(&audit_queue)))
+ kauditd_hold_skb(skb);
+}
+
+/**
* auditd_send_unicast_skb - Send a record via unicast to auditd
* @skb: audit record
*
NULL, kauditd_rehold_skb);
if (rc < 0) {
sk = NULL;
+ auditd_reset();
goto main_queue;
}
NULL, kauditd_hold_skb);
if (rc < 0) {
sk = NULL;
+ auditd_reset();
goto main_queue;
}
* unicast, dump failed record sends to the retry queue; if
* sk == NULL due to previous failures we will just do the
* multicast send and move the record to the retry queue */
- kauditd_send_queue(sk, portid, &audit_queue, 1,
- kauditd_send_multicast_skb,
- kauditd_retry_skb);
+ rc = kauditd_send_queue(sk, portid, &audit_queue, 1,
+ kauditd_send_multicast_skb,
+ kauditd_retry_skb);
+ if (sk == NULL || rc < 0)
+ auditd_reset();
+ sk = NULL;
/* drop our netns reference, no auditd sends past this line */
if (net) {
put_net(net);
net = NULL;
}
- sk = NULL;
/* we have processed all the queues so wake everyone */
wake_up(&audit_backlog_wait);
extern int audit_filter(int msgtype, unsigned int listtype);
#ifdef CONFIG_AUDITSYSCALL
-extern int __audit_signal_info(int sig, struct task_struct *t);
-static inline int audit_signal_info(int sig, struct task_struct *t)
-{
- if (auditd_test_task(t) || (audit_signals && !audit_dummy_context()))
- return __audit_signal_info(sig, t);
- return 0;
-}
+extern int audit_signal_info(int sig, struct task_struct *t);
extern void audit_filter_inodes(struct task_struct *, struct audit_context *);
extern struct list_head *audit_killed_trees(void);
#else
* If the audit subsystem is being terminated, record the task (pid)
* and uid that is doing that.
*/
-int __audit_signal_info(int sig, struct task_struct *t)
+int audit_signal_info(int sig, struct task_struct *t)
{
struct audit_aux_data_pids *axp;
struct task_struct *tsk = current;
struct audit_context *ctx = tsk->audit_context;
kuid_t uid = current_uid(), t_uid = task_uid(t);
- if (auditd_test_task(t)) {
- if (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1 || sig == SIGUSR2) {
- audit_sig_pid = task_tgid_nr(tsk);
- if (uid_valid(tsk->loginuid))
- audit_sig_uid = tsk->loginuid;
- else
- audit_sig_uid = uid;
- security_task_getsecid(tsk, &audit_sig_sid);
- }
- if (!audit_signals || audit_dummy_context())
- return 0;
+ if (auditd_test_task(t) &&
+ (sig == SIGTERM || sig == SIGHUP ||
+ sig == SIGUSR1 || sig == SIGUSR2)) {
+ audit_sig_pid = task_tgid_nr(tsk);
+ if (uid_valid(tsk->loginuid))
+ audit_sig_uid = tsk->loginuid;
+ else
+ audit_sig_uid = uid;
+ security_task_getsecid(tsk, &audit_sig_sid);
}
+ if (!audit_signals || audit_dummy_context())
+ return 0;
+
/* optimize the common case by putting first signal recipient directly
* in audit_context */
if (!ctx->target_pid) {
LD_ABS_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + imm32)) */
off = IMM;
load_word:
- /* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are
- * only appearing in the programs where ctx ==
- * skb. All programs keep 'ctx' in regs[BPF_REG_CTX]
- * == BPF_R6, bpf_convert_filter() saves it in BPF_R6,
- * internal BPF verifier will check that BPF_R6 ==
- * ctx.
+ /* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are only
+ * appearing in the programs where ctx == skb
+ * (see may_access_skb() in the verifier). All programs
+ * keep 'ctx' in regs[BPF_REG_CTX] == BPF_R6,
+ * bpf_convert_filter() saves it in BPF_R6, internal BPF
+ * verifier will check that BPF_R6 == ctx.
*
* BPF_ABS and BPF_IND are wrappers of function calls,
* so they scratch BPF_R1-BPF_R5 registers, preserve
if (insn->imm == BPF_FUNC_xdp_adjust_head)
prog->xdp_adjust_head = 1;
if (insn->imm == BPF_FUNC_tail_call) {
+ /* If we tail call into other programs, we
+ * cannot make any assumptions since they
+ * can be replaced dynamically during runtime
+ * in the program array.
+ */
+ prog->cb_access = 1;
+ prog->xdp_adjust_head = 1;
+
/* mark bpf_tail_call as different opcode
* to avoid conditional branch in
* interpeter for every normal call
}
}
-static int check_ptr_alignment(struct bpf_verifier_env *env,
- struct bpf_reg_state *reg, int off, int size)
+static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg,
+ int off, int size)
{
- if (reg->type != PTR_TO_PACKET && reg->type != PTR_TO_MAP_VALUE_ADJ) {
- if (off % size != 0) {
- verbose("misaligned access off %d size %d\n",
- off, size);
- return -EACCES;
- } else {
- return 0;
- }
- }
-
- if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
- /* misaligned access to packet is ok on x86,arm,arm64 */
- return 0;
-
if (reg->id && size != 1) {
- verbose("Unknown packet alignment. Only byte-sized access allowed\n");
+ verbose("Unknown alignment. Only byte-sized access allowed in packet access.\n");
return -EACCES;
}
/* skb->data is NET_IP_ALIGN-ed */
- if (reg->type == PTR_TO_PACKET &&
- (NET_IP_ALIGN + reg->off + off) % size != 0) {
+ if ((NET_IP_ALIGN + reg->off + off) % size != 0) {
verbose("misaligned packet access off %d+%d+%d size %d\n",
NET_IP_ALIGN, reg->off, off, size);
return -EACCES;
}
+
return 0;
}
+static int check_val_ptr_alignment(const struct bpf_reg_state *reg,
+ int size)
+{
+ if (size != 1) {
+ verbose("Unknown alignment. Only byte-sized access allowed in value access.\n");
+ return -EACCES;
+ }
+
+ return 0;
+}
+
+static int check_ptr_alignment(const struct bpf_reg_state *reg,
+ int off, int size)
+{
+ switch (reg->type) {
+ case PTR_TO_PACKET:
+ return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ? 0 :
+ check_pkt_ptr_alignment(reg, off, size);
+ case PTR_TO_MAP_VALUE_ADJ:
+ return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ? 0 :
+ check_val_ptr_alignment(reg, size);
+ default:
+ if (off % size != 0) {
+ verbose("misaligned access off %d size %d\n",
+ off, size);
+ return -EACCES;
+ }
+
+ return 0;
+ }
+}
+
/* check whether memory at (regno + off) is accessible for t = (read | write)
* if t==write, value_regno is a register which value is stored into memory
* if t==read, value_regno is a register which will receive the value from memory
if (size < 0)
return size;
- err = check_ptr_alignment(env, reg, off, size);
+ err = check_ptr_alignment(reg, off, size);
if (err)
return err;
* register as unknown.
*/
if (env->allow_ptr_leaks &&
+ BPF_CLASS(insn->code) == BPF_ALU64 && opcode == BPF_ADD &&
(dst_reg->type == PTR_TO_MAP_VALUE ||
dst_reg->type == PTR_TO_MAP_VALUE_ADJ))
dst_reg->type = PTR_TO_MAP_VALUE_ADJ;
for (i = 0; i < MAX_BPF_REG; i++)
if (regs[i].type == PTR_TO_PACKET && regs[i].id == dst_reg->id)
- regs[i].range = dst_reg->off;
+ /* keep the maximum range already checked */
+ regs[i].range = max(regs[i].range, dst_reg->off);
for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
if (state->stack_slot_type[i] != STACK_SPILL)
continue;
reg = &state->spilled_regs[i / BPF_REG_SIZE];
if (reg->type == PTR_TO_PACKET && reg->id == dst_reg->id)
- reg->range = dst_reg->off;
+ reg->range = max(reg->range, dst_reg->off);
}
}
#include <linux/kernfs.h>
#include <linux/workqueue.h>
#include <linux/list.h>
+#include <linux/refcount.h>
/*
* A cgroup can be associated with multiple css_sets as different tasks may
* can see it. Similar to atomic_dec_and_lock(), but for an
* rwlock
*/
- if (atomic_add_unless(&cset->refcount, -1, 1))
+ if (refcount_dec_not_one(&cset->refcount))
return;
spin_lock_irqsave(&css_set_lock, flags);
*/
static inline void get_css_set(struct css_set *cset)
{
- atomic_inc(&cset->refcount);
+ refcount_inc(&cset->refcount);
}
bool cgroup_ssid_enabled(int ssid);
void cgroup_free_root(struct cgroup_root *root);
void init_cgroup_root(struct cgroup_root *root, struct cgroup_sb_opts *opts);
-int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask);
+int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask, int ref_flags);
int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask);
struct dentry *cgroup_do_mount(struct file_system_type *fs_type, int flags,
struct cgroup_root *root, unsigned long magic,
spin_lock_irq(&css_set_lock);
list_for_each_entry(link, &cgrp->cset_links, cset_link)
- count += atomic_read(&link->cset->refcount);
+ count += refcount_read(&link->cset->refcount);
spin_unlock_irq(&css_set_lock);
return count;
}
struct cgroup_subsys *ss;
struct dentry *dentry;
int i, ret;
+ bool new_root = false;
cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp);
ret = -ENOMEM;
goto out_unlock;
}
+ new_root = true;
init_cgroup_root(root, &opts);
- ret = cgroup_setup_root(root, opts.subsys_mask);
+ ret = cgroup_setup_root(root, opts.subsys_mask, PERCPU_REF_INIT_DEAD);
if (ret)
cgroup_free_root(root);
CGROUP_SUPER_MAGIC, ns);
/*
+ * There's a race window after we release cgroup_mutex and before
+ * allocating a superblock. Make sure a concurrent process won't
+ * be able to re-use the root during this window by delaying the
+ * initialization of root refcnt.
+ */
+ if (new_root) {
+ mutex_lock(&cgroup_mutex);
+ percpu_ref_reinit(&root->cgrp.self.refcnt);
+ mutex_unlock(&cgroup_mutex);
+ }
+
+ /*
* If @pinned_sb, we're reusing an existing root and holding an
* extra ref on its sb. Mount is complete. Put the extra ref.
*/
u64 count;
rcu_read_lock();
- count = atomic_read(&task_css_set(current)->refcount);
+ count = refcount_read(&task_css_set(current)->refcount);
rcu_read_unlock();
return count;
}
/* cgroup namespace for init task */
struct cgroup_namespace init_cgroup_ns = {
- .count = { .counter = 2, },
+ .count = REFCOUNT_INIT(2),
.user_ns = &init_user_ns,
.ns.ops = &cgroupns_operations,
.ns.inum = PROC_CGROUP_INIT_INO,
return css;
}
-static void cgroup_get(struct cgroup *cgrp)
+static void __maybe_unused cgroup_get(struct cgroup *cgrp)
+{
+ css_get(&cgrp->self);
+}
+
+static void cgroup_get_live(struct cgroup *cgrp)
{
WARN_ON_ONCE(cgroup_is_dead(cgrp));
css_get(&cgrp->self);
* haven't been created.
*/
struct css_set init_css_set = {
- .refcount = ATOMIC_INIT(1),
+ .refcount = REFCOUNT_INIT(1),
.tasks = LIST_HEAD_INIT(init_css_set.tasks),
.mg_tasks = LIST_HEAD_INIT(init_css_set.mg_tasks),
.task_iters = LIST_HEAD_INIT(init_css_set.task_iters),
lockdep_assert_held(&css_set_lock);
- if (!atomic_dec_and_test(&cset->refcount))
+ if (!refcount_dec_and_test(&cset->refcount))
return;
/* This css_set is dead. unlink it and release cgroup and css refs */
list_add_tail(&link->cgrp_link, &cset->cgrp_links);
if (cgroup_parent(cgrp))
- cgroup_get(cgrp);
+ cgroup_get_live(cgrp);
}
/**
return NULL;
}
- atomic_set(&cset->refcount, 1);
+ refcount_set(&cset->refcount, 1);
INIT_LIST_HEAD(&cset->tasks);
INIT_LIST_HEAD(&cset->mg_tasks);
INIT_LIST_HEAD(&cset->task_iters);
set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags);
}
-int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
+int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask, int ref_flags)
{
LIST_HEAD(tmp_links);
struct cgroup *root_cgrp = &root->cgrp;
root_cgrp->id = ret;
root_cgrp->ancestor_ids[0] = ret;
- ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release, 0,
- GFP_KERNEL);
+ ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release,
+ ref_flags, GFP_KERNEL);
if (ret)
goto out;
return ERR_PTR(-EINVAL);
}
cgrp_dfl_visible = true;
- cgroup_get(&cgrp_dfl_root.cgrp);
+ cgroup_get_live(&cgrp_dfl_root.cgrp);
dentry = cgroup_do_mount(&cgroup2_fs_type, flags, &cgrp_dfl_root,
CGROUP2_SUPER_MAGIC, ns);
tsk = tsk->group_leader;
/*
- * Workqueue threads may acquire PF_NO_SETAFFINITY and become
- * trapped in a cpuset, or RT worker may be born in a cgroup
- * with no rt_runtime allocated. Just say no.
+ * kthreads may acquire PF_NO_SETAFFINITY during initialization.
+ * If userland migrates such a kthread to a non-root cgroup, it can
+ * become trapped in a cpuset, or RT kthread may be born in a
+ * cgroup with no rt_runtime allocated. Just say no.
*/
- if (tsk == kthreadd_task || (tsk->flags & PF_NO_SETAFFINITY)) {
+ if (tsk->no_cgroup_migration || (tsk->flags & PF_NO_SETAFFINITY)) {
ret = -EINVAL;
goto out_unlock_rcu;
}
if (!css || !percpu_ref_is_dying(&css->refcnt))
continue;
- cgroup_get(dsct);
+ cgroup_get_live(dsct);
prepare_to_wait(&dsct->offline_waitq, &wait,
TASK_UNINTERRUPTIBLE);
{
lockdep_assert_held(&cgroup_mutex);
- cgroup_get(cgrp);
+ cgroup_get_live(cgrp);
memset(css, 0, sizeof(*css));
css->cgroup = cgrp;
/* allocation complete, commit to creation */
list_add_tail_rcu(&cgrp->self.sibling, &cgroup_parent(cgrp)->self.children);
atomic_inc(&root->nr_cgrps);
- cgroup_get(parent);
+ cgroup_get_live(parent);
/*
* @cgrp is now fully operational. If something fails after this
hash_add(css_set_table, &init_css_set.hlist,
css_set_hash(init_css_set.subsys));
- BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0));
+ BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0, 0));
mutex_unlock(&cgroup_mutex);
if (kn) {
if (kernfs_type(kn) == KERNFS_DIR) {
cgrp = kn->priv;
- cgroup_get(cgrp);
+ cgroup_get_live(cgrp);
} else {
cgrp = ERR_PTR(-ENOTDIR);
}
/* Socket clone path */
if (skcd->val) {
+ /*
+ * We might be cloning a socket which is left in an empty
+ * cgroup and the cgroup might have already been rmdir'd.
+ * Don't use cgroup_get_live().
+ */
cgroup_get(sock_cgroup_ptr(skcd));
return;
}
{
int err = 0;
- if (!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL))
- BUG();
- if (!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL))
- BUG();
+ BUG_ON(!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL));
+ BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL));
cpumask_setall(top_cpuset.cpus_allowed);
nodes_setall(top_cpuset.mems_allowed);
if (err < 0)
return err;
- if (!alloc_cpumask_var(&cpus_attach, GFP_KERNEL))
- BUG();
+ BUG_ON(!alloc_cpumask_var(&cpus_attach, GFP_KERNEL));
return 0;
}
rebuild_sched_domains();
}
-void cpuset_update_active_cpus(bool cpu_online)
+void cpuset_update_active_cpus(void)
{
/*
* We're inside cpu hotplug critical region which usually nests
kfree(new_ns);
return ERR_PTR(ret);
}
- atomic_set(&new_ns->count, 1);
+ refcount_set(&new_ns->count, 1);
new_ns->ns.ops = &cgroupns_operations;
return new_ns;
}
COMPAT_SYSCALL_DEFINE2(settimeofday, struct compat_timeval __user *, tv,
struct timezone __user *, tz)
{
+ struct timespec64 new_ts;
struct timeval user_tv;
- struct timespec new_ts;
struct timezone new_tz;
if (tv) {
return -EFAULT;
}
- return do_sys_settimeofday(tv ? &new_ts : NULL, tz ? &new_tz : NULL);
+ return do_sys_settimeofday64(tv ? &new_ts : NULL, tz ? &new_tz : NULL);
}
static int __compat_get_timeval(struct timeval *tv, const struct compat_timeval __user *ctv)
struct compat_timespec __user *, rmtp)
{
struct timespec tu, rmt;
+ struct timespec64 tu64;
mm_segment_t oldfs;
long ret;
if (compat_get_timespec(&tu, rqtp))
return -EFAULT;
- if (!timespec_valid(&tu))
+ tu64 = timespec_to_timespec64(tu);
+ if (!timespec64_valid(&tu64))
return -EINVAL;
oldfs = get_fs();
set_fs(KERNEL_DS);
- ret = hrtimer_nanosleep(&tu,
+ ret = hrtimer_nanosleep(&tu64,
rmtp ? (struct timespec __user *)&rmt : NULL,
HRTIMER_MODE_REL, CLOCK_MONOTONIC);
set_fs(oldfs);
#endif /* CONFIG_PM_SLEEP_SMP */
+int __boot_cpu_id;
+
#endif /* CONFIG_SMP */
/* Boot processor state steps */
set_cpu_active(cpu, true);
set_cpu_present(cpu, true);
set_cpu_possible(cpu, true);
+
+#ifdef CONFIG_SMP
+ __boot_cpu_id = cpu;
+#endif
}
/*
#include <linux/parser.h>
#include <linux/sched/clock.h>
#include <linux/sched/mm.h>
+#include <linux/proc_ns.h>
+#include <linux/mount.h>
#include "internal.h"
static atomic_t nr_mmap_events __read_mostly;
static atomic_t nr_comm_events __read_mostly;
+static atomic_t nr_namespaces_events __read_mostly;
static atomic_t nr_task_events __read_mostly;
static atomic_t nr_freq_events __read_mostly;
static atomic_t nr_switch_events __read_mostly;
atomic_dec(&nr_mmap_events);
if (event->attr.comm)
atomic_dec(&nr_comm_events);
+ if (event->attr.namespaces)
+ atomic_dec(&nr_namespaces_events);
if (event->attr.task)
atomic_dec(&nr_task_events);
if (event->attr.freq)
void perf_event_fork(struct task_struct *task)
{
perf_event_task(task, NULL, 1);
+ perf_event_namespaces(task);
}
/*
}
/*
+ * namespaces tracking
+ */
+
+struct perf_namespaces_event {
+ struct task_struct *task;
+
+ struct {
+ struct perf_event_header header;
+
+ u32 pid;
+ u32 tid;
+ u64 nr_namespaces;
+ struct perf_ns_link_info link_info[NR_NAMESPACES];
+ } event_id;
+};
+
+static int perf_event_namespaces_match(struct perf_event *event)
+{
+ return event->attr.namespaces;
+}
+
+static void perf_event_namespaces_output(struct perf_event *event,
+ void *data)
+{
+ struct perf_namespaces_event *namespaces_event = data;
+ struct perf_output_handle handle;
+ struct perf_sample_data sample;
+ int ret;
+
+ if (!perf_event_namespaces_match(event))
+ return;
+
+ perf_event_header__init_id(&namespaces_event->event_id.header,
+ &sample, event);
+ ret = perf_output_begin(&handle, event,
+ namespaces_event->event_id.header.size);
+ if (ret)
+ return;
+
+ namespaces_event->event_id.pid = perf_event_pid(event,
+ namespaces_event->task);
+ namespaces_event->event_id.tid = perf_event_tid(event,
+ namespaces_event->task);
+
+ perf_output_put(&handle, namespaces_event->event_id);
+
+ perf_event__output_id_sample(event, &handle, &sample);
+
+ perf_output_end(&handle);
+}
+
+static void perf_fill_ns_link_info(struct perf_ns_link_info *ns_link_info,
+ struct task_struct *task,
+ const struct proc_ns_operations *ns_ops)
+{
+ struct path ns_path;
+ struct inode *ns_inode;
+ void *error;
+
+ error = ns_get_path(&ns_path, task, ns_ops);
+ if (!error) {
+ ns_inode = ns_path.dentry->d_inode;
+ ns_link_info->dev = new_encode_dev(ns_inode->i_sb->s_dev);
+ ns_link_info->ino = ns_inode->i_ino;
+ }
+}
+
+void perf_event_namespaces(struct task_struct *task)
+{
+ struct perf_namespaces_event namespaces_event;
+ struct perf_ns_link_info *ns_link_info;
+
+ if (!atomic_read(&nr_namespaces_events))
+ return;
+
+ namespaces_event = (struct perf_namespaces_event){
+ .task = task,
+ .event_id = {
+ .header = {
+ .type = PERF_RECORD_NAMESPACES,
+ .misc = 0,
+ .size = sizeof(namespaces_event.event_id),
+ },
+ /* .pid */
+ /* .tid */
+ .nr_namespaces = NR_NAMESPACES,
+ /* .link_info[NR_NAMESPACES] */
+ },
+ };
+
+ ns_link_info = namespaces_event.event_id.link_info;
+
+ perf_fill_ns_link_info(&ns_link_info[MNT_NS_INDEX],
+ task, &mntns_operations);
+
+#ifdef CONFIG_USER_NS
+ perf_fill_ns_link_info(&ns_link_info[USER_NS_INDEX],
+ task, &userns_operations);
+#endif
+#ifdef CONFIG_NET_NS
+ perf_fill_ns_link_info(&ns_link_info[NET_NS_INDEX],
+ task, &netns_operations);
+#endif
+#ifdef CONFIG_UTS_NS
+ perf_fill_ns_link_info(&ns_link_info[UTS_NS_INDEX],
+ task, &utsns_operations);
+#endif
+#ifdef CONFIG_IPC_NS
+ perf_fill_ns_link_info(&ns_link_info[IPC_NS_INDEX],
+ task, &ipcns_operations);
+#endif
+#ifdef CONFIG_PID_NS
+ perf_fill_ns_link_info(&ns_link_info[PID_NS_INDEX],
+ task, &pidns_operations);
+#endif
+#ifdef CONFIG_CGROUPS
+ perf_fill_ns_link_info(&ns_link_info[CGROUP_NS_INDEX],
+ task, &cgroupns_operations);
+#endif
+
+ perf_iterate_sb(perf_event_namespaces_output,
+ &namespaces_event,
+ NULL);
+}
+
+/*
* mmap tracking
*/
atomic_inc(&nr_mmap_events);
if (event->attr.comm)
atomic_inc(&nr_comm_events);
+ if (event->attr.namespaces)
+ atomic_inc(&nr_namespaces_events);
if (event->attr.task)
atomic_inc(&nr_task_events);
if (event->attr.freq)
return -EACCES;
}
+ if (attr.namespaces) {
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
+ }
+
if (attr.freq) {
if (attr.sample_freq > sysctl_perf_event_sample_rate)
return -EINVAL;
rb->paused = 1;
}
+void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags)
+{
+ /*
+ * OVERWRITE is determined by perf_aux_output_end() and can't
+ * be passed in directly.
+ */
+ if (WARN_ON_ONCE(flags & PERF_AUX_FLAG_OVERWRITE))
+ return;
+
+ handle->aux_flags |= flags;
+}
+EXPORT_SYMBOL_GPL(perf_aux_output_flag);
+
/*
* This is called before hardware starts writing to the AUX area to
* obtain an output handle and make sure there's room in the buffer.
handle->event = event;
handle->head = aux_head;
handle->size = 0;
+ handle->aux_flags = 0;
/*
* In overwrite mode, AUX data stores do not depend on aux_tail,
* of the AUX buffer management code is that after pmu::stop(), the AUX
* transaction must be stopped and therefore drop the AUX reference count.
*/
-void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size,
- bool truncated)
+void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
{
+ bool wakeup = !!(handle->aux_flags & PERF_AUX_FLAG_TRUNCATED);
struct ring_buffer *rb = handle->rb;
- bool wakeup = truncated;
unsigned long aux_head;
- u64 flags = 0;
-
- if (truncated)
- flags |= PERF_AUX_FLAG_TRUNCATED;
/* in overwrite mode, driver provides aux_head via handle */
if (rb->aux_overwrite) {
- flags |= PERF_AUX_FLAG_OVERWRITE;
+ handle->aux_flags |= PERF_AUX_FLAG_OVERWRITE;
aux_head = handle->head;
local_set(&rb->aux_head, aux_head);
} else {
+ handle->aux_flags &= ~PERF_AUX_FLAG_OVERWRITE;
+
aux_head = local_read(&rb->aux_head);
local_add(size, &rb->aux_head);
}
- if (size || flags) {
+ if (size || handle->aux_flags) {
/*
* Only send RECORD_AUX if we have something useful to communicate
*/
- perf_event_aux_event(handle->event, aux_head, size, flags);
+ perf_event_aux_event(handle->event, aux_head, size,
+ handle->aux_flags);
}
aux_head = rb->user_page->aux_head = local_read(&rb->aux_head);
}
if (wakeup) {
- if (truncated)
+ if (handle->aux_flags & PERF_AUX_FLAG_TRUNCATED)
handle->event->pending_disable = 1;
perf_output_wakeup(handle);
}
#ifdef CONFIG_RT_MUTEXES
p->pi_waiters = RB_ROOT;
p->pi_waiters_leftmost = NULL;
+ p->pi_top_task = NULL;
p->pi_blocked_on = NULL;
#endif
}
}
}
+ perf_event_namespaces(current);
+
bad_unshare_cleanup_cred:
if (new_cred)
put_cred(new_cred);
return 0;
}
-static struct futex_pi_state * alloc_pi_state(void)
+static struct futex_pi_state *alloc_pi_state(void)
{
struct futex_pi_state *pi_state = current->pi_state_cache;
return pi_state;
}
+static void get_pi_state(struct futex_pi_state *pi_state)
+{
+ WARN_ON_ONCE(!atomic_inc_not_zero(&pi_state->refcount));
+}
+
/*
* Drops a reference to the pi_state object and frees or caches it
* when the last reference is gone.
* Look up the task based on what TID userspace gave us.
* We dont trust it.
*/
-static struct task_struct * futex_find_get_task(pid_t pid)
+static struct task_struct *futex_find_get_task(pid_t pid)
{
struct task_struct *p;
pi_state->owner = NULL;
raw_spin_unlock_irq(&curr->pi_lock);
- rt_mutex_unlock(&pi_state->pi_mutex);
-
+ get_pi_state(pi_state);
spin_unlock(&hb->lock);
+ rt_mutex_futex_unlock(&pi_state->pi_mutex);
+ put_pi_state(pi_state);
+
raw_spin_lock_irq(&curr->pi_lock);
}
raw_spin_unlock_irq(&curr->pi_lock);
*
* [10] There is no transient state which leaves owner and user space
* TID out of sync.
+ *
+ *
+ * Serialization and lifetime rules:
+ *
+ * hb->lock:
+ *
+ * hb -> futex_q, relation
+ * futex_q -> pi_state, relation
+ *
+ * (cannot be raw because hb can contain arbitrary amount
+ * of futex_q's)
+ *
+ * pi_mutex->wait_lock:
+ *
+ * {uval, pi_state}
+ *
+ * (and pi_mutex 'obviously')
+ *
+ * p->pi_lock:
+ *
+ * p->pi_state_list -> pi_state->list, relation
+ *
+ * pi_state->refcount:
+ *
+ * pi_state lifetime
+ *
+ *
+ * Lock order:
+ *
+ * hb->lock
+ * pi_mutex->wait_lock
+ * p->pi_lock
+ *
*/
/*
* the pi_state against the user space value. If correct, attach to
* it.
*/
-static int attach_to_pi_state(u32 uval, struct futex_pi_state *pi_state,
+static int attach_to_pi_state(u32 __user *uaddr, u32 uval,
+ struct futex_pi_state *pi_state,
struct futex_pi_state **ps)
{
pid_t pid = uval & FUTEX_TID_MASK;
+ u32 uval2;
+ int ret;
/*
* Userspace might have messed up non-PI and PI futexes [3]
if (unlikely(!pi_state))
return -EINVAL;
+ /*
+ * We get here with hb->lock held, and having found a
+ * futex_top_waiter(). This means that futex_lock_pi() of said futex_q
+ * has dropped the hb->lock in between queue_me() and unqueue_me_pi(),
+ * which in turn means that futex_lock_pi() still has a reference on
+ * our pi_state.
+ *
+ * The waiter holding a reference on @pi_state also protects against
+ * the unlocked put_pi_state() in futex_unlock_pi(), futex_lock_pi()
+ * and futex_wait_requeue_pi() as it cannot go to 0 and consequently
+ * free pi_state before we can take a reference ourselves.
+ */
WARN_ON(!atomic_read(&pi_state->refcount));
/*
+ * Now that we have a pi_state, we can acquire wait_lock
+ * and do the state validation.
+ */
+ raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+
+ /*
+ * Since {uval, pi_state} is serialized by wait_lock, and our current
+ * uval was read without holding it, it can have changed. Verify it
+ * still is what we expect it to be, otherwise retry the entire
+ * operation.
+ */
+ if (get_futex_value_locked(&uval2, uaddr))
+ goto out_efault;
+
+ if (uval != uval2)
+ goto out_eagain;
+
+ /*
* Handle the owner died case:
*/
if (uval & FUTEX_OWNER_DIED) {
* is not 0. Inconsistent state. [5]
*/
if (pid)
- return -EINVAL;
+ goto out_einval;
/*
* Take a ref on the state and return success. [4]
*/
- goto out_state;
+ goto out_attach;
}
/*
* Take a ref on the state and return success. [6]
*/
if (!pid)
- goto out_state;
+ goto out_attach;
} else {
/*
* If the owner died bit is not set, then the pi_state
* must have an owner. [7]
*/
if (!pi_state->owner)
- return -EINVAL;
+ goto out_einval;
}
/*
* user space TID. [9/10]
*/
if (pid != task_pid_vnr(pi_state->owner))
- return -EINVAL;
-out_state:
- atomic_inc(&pi_state->refcount);
+ goto out_einval;
+
+out_attach:
+ get_pi_state(pi_state);
+ raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
*ps = pi_state;
return 0;
+
+out_einval:
+ ret = -EINVAL;
+ goto out_error;
+
+out_eagain:
+ ret = -EAGAIN;
+ goto out_error;
+
+out_efault:
+ ret = -EFAULT;
+ goto out_error;
+
+out_error:
+ raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
+ return ret;
}
/*
/*
* No existing pi state. First waiter. [2]
+ *
+ * This creates pi_state, we have hb->lock held, this means nothing can
+ * observe this state, wait_lock is irrelevant.
*/
pi_state = alloc_pi_state();
return 0;
}
-static int lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
+static int lookup_pi_state(u32 __user *uaddr, u32 uval,
+ struct futex_hash_bucket *hb,
union futex_key *key, struct futex_pi_state **ps)
{
- struct futex_q *match = futex_top_waiter(hb, key);
+ struct futex_q *top_waiter = futex_top_waiter(hb, key);
/*
* If there is a waiter on that futex, validate it and
* attach to the pi_state when the validation succeeds.
*/
- if (match)
- return attach_to_pi_state(uval, match->pi_state, ps);
+ if (top_waiter)
+ return attach_to_pi_state(uaddr, uval, top_waiter->pi_state, ps);
/*
* We are the first waiter - try to look up the owner based on
if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
return -EFAULT;
- /*If user space value changed, let the caller retry */
+ /* If user space value changed, let the caller retry */
return curval != uval ? -EAGAIN : 0;
}
struct task_struct *task, int set_waiters)
{
u32 uval, newval, vpid = task_pid_vnr(task);
- struct futex_q *match;
+ struct futex_q *top_waiter;
int ret;
/*
* Lookup existing state first. If it exists, try to attach to
* its pi_state.
*/
- match = futex_top_waiter(hb, key);
- if (match)
- return attach_to_pi_state(uval, match->pi_state, ps);
+ top_waiter = futex_top_waiter(hb, key);
+ if (top_waiter)
+ return attach_to_pi_state(uaddr, uval, top_waiter->pi_state, ps);
/*
* No waiter and user TID is 0. We are here because the
wake_q_add(wake_q, p);
__unqueue_futex(q);
/*
- * The waiting task can free the futex_q as soon as
- * q->lock_ptr = NULL is written, without taking any locks. A
- * memory barrier is required here to prevent the following
- * store to lock_ptr from getting ahead of the plist_del.
+ * The waiting task can free the futex_q as soon as q->lock_ptr = NULL
+ * is written, without taking any locks. This is possible in the event
+ * of a spurious wakeup, for example. A memory barrier is required here
+ * to prevent the following store to lock_ptr from getting ahead of the
+ * plist_del in __unqueue_futex().
*/
- smp_wmb();
- q->lock_ptr = NULL;
+ smp_store_release(&q->lock_ptr, NULL);
}
-static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
- struct futex_hash_bucket *hb)
+/*
+ * Caller must hold a reference on @pi_state.
+ */
+static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_state)
{
- struct task_struct *new_owner;
- struct futex_pi_state *pi_state = this->pi_state;
u32 uninitialized_var(curval), newval;
+ struct task_struct *new_owner;
+ bool postunlock = false;
DEFINE_WAKE_Q(wake_q);
- bool deboost;
int ret = 0;
- if (!pi_state)
- return -EINVAL;
-
- /*
- * If current does not own the pi_state then the futex is
- * inconsistent and user space fiddled with the futex value.
- */
- if (pi_state->owner != current)
- return -EINVAL;
-
- raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
new_owner = rt_mutex_next_owner(&pi_state->pi_mutex);
+ if (WARN_ON_ONCE(!new_owner)) {
+ /*
+ * As per the comment in futex_unlock_pi() this should not happen.
+ *
+ * When this happens, give up our locks and try again, giving
+ * the futex_lock_pi() instance time to complete, either by
+ * waiting on the rtmutex or removing itself from the futex
+ * queue.
+ */
+ ret = -EAGAIN;
+ goto out_unlock;
+ }
/*
- * It is possible that the next waiter (the one that brought
- * this owner to the kernel) timed out and is no longer
- * waiting on the lock.
- */
- if (!new_owner)
- new_owner = this->task;
-
- /*
- * We pass it to the next owner. The WAITERS bit is always
- * kept enabled while there is PI state around. We cleanup the
- * owner died bit, because we are the owner.
+ * We pass it to the next owner. The WAITERS bit is always kept
+ * enabled while there is PI state around. We cleanup the owner
+ * died bit, because we are the owner.
*/
newval = FUTEX_WAITERS | task_pid_vnr(new_owner);
if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) {
ret = -EFAULT;
+
} else if (curval != uval) {
/*
* If a unconditional UNLOCK_PI operation (user space did not
else
ret = -EINVAL;
}
- if (ret) {
- raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
- return ret;
- }
+
+ if (ret)
+ goto out_unlock;
+
+ /*
+ * This is a point of no return; once we modify the uval there is no
+ * going back and subsequent operations must not fail.
+ */
raw_spin_lock(&pi_state->owner->pi_lock);
WARN_ON(list_empty(&pi_state->list));
pi_state->owner = new_owner;
raw_spin_unlock(&new_owner->pi_lock);
- raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
+ postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q);
- deboost = rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q);
+out_unlock:
+ raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
- /*
- * First unlock HB so the waiter does not spin on it once he got woken
- * up. Second wake up the waiter before the priority is adjusted. If we
- * deboost first (and lose our higher priority), then the task might get
- * scheduled away before the wake up can take place.
- */
- spin_unlock(&hb->lock);
- wake_up_q(&wake_q);
- if (deboost)
- rt_mutex_adjust_prio(current);
+ if (postunlock)
+ rt_mutex_postunlock(&wake_q);
- return 0;
+ return ret;
}
/*
* If that call succeeds then we have pi_state and an
* initial refcount on it.
*/
- ret = lookup_pi_state(ret, hb2, &key2, &pi_state);
+ ret = lookup_pi_state(uaddr2, ret, hb2, &key2, &pi_state);
}
switch (ret) {
* refcount on the pi_state and store the pointer in
* the futex_q object of the waiter.
*/
- atomic_inc(&pi_state->refcount);
+ get_pi_state(pi_state);
this->pi_state = pi_state;
ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex,
this->rt_waiter,
hb_waiters_dec(hb);
}
-/**
- * queue_me() - Enqueue the futex_q on the futex_hash_bucket
- * @q: The futex_q to enqueue
- * @hb: The destination hash bucket
- *
- * The hb->lock must be held by the caller, and is released here. A call to
- * queue_me() is typically paired with exactly one call to unqueue_me(). The
- * exceptions involve the PI related operations, which may use unqueue_me_pi()
- * or nothing if the unqueue is done as part of the wake process and the unqueue
- * state is implicit in the state of woken task (see futex_wait_requeue_pi() for
- * an example).
- */
-static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
- __releases(&hb->lock)
+static inline void __queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
{
int prio;
plist_node_init(&q->list, prio);
plist_add(&q->list, &hb->chain);
q->task = current;
+}
+
+/**
+ * queue_me() - Enqueue the futex_q on the futex_hash_bucket
+ * @q: The futex_q to enqueue
+ * @hb: The destination hash bucket
+ *
+ * The hb->lock must be held by the caller, and is released here. A call to
+ * queue_me() is typically paired with exactly one call to unqueue_me(). The
+ * exceptions involve the PI related operations, which may use unqueue_me_pi()
+ * or nothing if the unqueue is done as part of the wake process and the unqueue
+ * state is implicit in the state of woken task (see futex_wait_requeue_pi() for
+ * an example).
+ */
+static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
+ __releases(&hb->lock)
+{
+ __queue_me(q, hb);
spin_unlock(&hb->lock);
}
{
u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS;
struct futex_pi_state *pi_state = q->pi_state;
- struct task_struct *oldowner = pi_state->owner;
u32 uval, uninitialized_var(curval), newval;
+ struct task_struct *oldowner;
int ret;
+ raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+
+ oldowner = pi_state->owner;
/* Owner died? */
if (!pi_state->owner)
newtid |= FUTEX_OWNER_DIED;
/*
* We are here either because we stole the rtmutex from the
* previous highest priority waiter or we are the highest priority
- * waiter but failed to get the rtmutex the first time.
+ * waiter but have failed to get the rtmutex the first time.
+ *
* We have to replace the newowner TID in the user space variable.
* This must be atomic as we have to preserve the owner died bit here.
*
* because we can fault here. Imagine swapped out pages or a fork
* that marked all the anonymous memory readonly for cow.
*
- * Modifying pi_state _before_ the user space value would
- * leave the pi_state in an inconsistent state when we fault
- * here, because we need to drop the hash bucket lock to
- * handle the fault. This might be observed in the PID check
- * in lookup_pi_state.
+ * Modifying pi_state _before_ the user space value would leave the
+ * pi_state in an inconsistent state when we fault here, because we
+ * need to drop the locks to handle the fault. This might be observed
+ * in the PID check in lookup_pi_state.
*/
retry:
if (get_futex_value_locked(&uval, uaddr))
goto handle_fault;
- while (1) {
+ for (;;) {
newval = (uval & FUTEX_OWNER_DIED) | newtid;
if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
* itself.
*/
if (pi_state->owner != NULL) {
- raw_spin_lock_irq(&pi_state->owner->pi_lock);
+ raw_spin_lock(&pi_state->owner->pi_lock);
WARN_ON(list_empty(&pi_state->list));
list_del_init(&pi_state->list);
- raw_spin_unlock_irq(&pi_state->owner->pi_lock);
+ raw_spin_unlock(&pi_state->owner->pi_lock);
}
pi_state->owner = newowner;
- raw_spin_lock_irq(&newowner->pi_lock);
+ raw_spin_lock(&newowner->pi_lock);
WARN_ON(!list_empty(&pi_state->list));
list_add(&pi_state->list, &newowner->pi_state_list);
- raw_spin_unlock_irq(&newowner->pi_lock);
+ raw_spin_unlock(&newowner->pi_lock);
+ raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
+
return 0;
/*
- * To handle the page fault we need to drop the hash bucket
- * lock here. That gives the other task (either the highest priority
- * waiter itself or the task which stole the rtmutex) the
- * chance to try the fixup of the pi_state. So once we are
- * back from handling the fault we need to check the pi_state
- * after reacquiring the hash bucket lock and before trying to
- * do another fixup. When the fixup has been done already we
- * simply return.
+ * To handle the page fault we need to drop the locks here. That gives
+ * the other task (either the highest priority waiter itself or the
+ * task which stole the rtmutex) the chance to try the fixup of the
+ * pi_state. So once we are back from handling the fault we need to
+ * check the pi_state after reacquiring the locks and before trying to
+ * do another fixup. When the fixup has been done already we simply
+ * return.
+ *
+ * Note: we hold both hb->lock and pi_mutex->wait_lock. We can safely
+ * drop hb->lock since the caller owns the hb -> futex_q relation.
+ * Dropping the pi_mutex->wait_lock requires the state revalidate.
*/
handle_fault:
+ raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
spin_unlock(q->lock_ptr);
ret = fault_in_user_writeable(uaddr);
spin_lock(q->lock_ptr);
+ raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
/*
* Check if someone else fixed it for us:
*/
- if (pi_state->owner != oldowner)
- return 0;
+ if (pi_state->owner != oldowner) {
+ ret = 0;
+ goto out_unlock;
+ }
if (ret)
- return ret;
+ goto out_unlock;
goto retry;
+
+out_unlock:
+ raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
+ return ret;
}
static long futex_wait_restart(struct restart_block *restart);
*/
static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
{
- struct task_struct *owner;
int ret = 0;
if (locked) {
/*
* Got the lock. We might not be the anticipated owner if we
* did a lock-steal - fix up the PI-state in that case:
+ *
+ * We can safely read pi_state->owner without holding wait_lock
+ * because we now own the rt_mutex, only the owner will attempt
+ * to change it.
*/
if (q->pi_state->owner != current)
ret = fixup_pi_state_owner(uaddr, q, current);
}
/*
- * Catch the rare case, where the lock was released when we were on the
- * way back before we locked the hash bucket.
- */
- if (q->pi_state->owner == current) {
- /*
- * Try to get the rt_mutex now. This might fail as some other
- * task acquired the rt_mutex after we removed ourself from the
- * rt_mutex waiters list.
- */
- if (rt_mutex_trylock(&q->pi_state->pi_mutex)) {
- locked = 1;
- goto out;
- }
-
- /*
- * pi_state is incorrect, some other task did a lock steal and
- * we returned due to timeout or signal without taking the
- * rt_mutex. Too late.
- */
- raw_spin_lock_irq(&q->pi_state->pi_mutex.wait_lock);
- owner = rt_mutex_owner(&q->pi_state->pi_mutex);
- if (!owner)
- owner = rt_mutex_next_owner(&q->pi_state->pi_mutex);
- raw_spin_unlock_irq(&q->pi_state->pi_mutex.wait_lock);
- ret = fixup_pi_state_owner(uaddr, q, owner);
- goto out;
- }
-
- /*
* Paranoia check. If we did not take the lock, then we should not be
* the owner of the rt_mutex.
*/
- if (rt_mutex_owner(&q->pi_state->pi_mutex) == current)
+ if (rt_mutex_owner(&q->pi_state->pi_mutex) == current) {
printk(KERN_ERR "fixup_owner: ret = %d pi-mutex: %p "
"pi-state %p\n", ret,
q->pi_state->pi_mutex.owner,
q->pi_state->owner);
+ }
out:
return ret ? ret : locked;
ktime_t *time, int trylock)
{
struct hrtimer_sleeper timeout, *to = NULL;
+ struct futex_pi_state *pi_state = NULL;
+ struct rt_mutex_waiter rt_waiter;
struct futex_hash_bucket *hb;
struct futex_q q = futex_q_init;
int res, ret;
}
}
+ WARN_ON(!q.pi_state);
+
/*
* Only actually queue now that the atomic ops are done:
*/
- queue_me(&q, hb);
+ __queue_me(&q, hb);
- WARN_ON(!q.pi_state);
- /*
- * Block on the PI mutex:
- */
- if (!trylock) {
- ret = rt_mutex_timed_futex_lock(&q.pi_state->pi_mutex, to);
- } else {
- ret = rt_mutex_trylock(&q.pi_state->pi_mutex);
+ if (trylock) {
+ ret = rt_mutex_futex_trylock(&q.pi_state->pi_mutex);
/* Fixup the trylock return value: */
ret = ret ? 0 : -EWOULDBLOCK;
+ goto no_block;
}
+ rt_mutex_init_waiter(&rt_waiter);
+
+ /*
+ * On PREEMPT_RT_FULL, when hb->lock becomes an rt_mutex, we must not
+ * hold it while doing rt_mutex_start_proxy(), because then it will
+ * include hb->lock in the blocking chain, even through we'll not in
+ * fact hold it while blocking. This will lead it to report -EDEADLK
+ * and BUG when futex_unlock_pi() interleaves with this.
+ *
+ * Therefore acquire wait_lock while holding hb->lock, but drop the
+ * latter before calling rt_mutex_start_proxy_lock(). This still fully
+ * serializes against futex_unlock_pi() as that does the exact same
+ * lock handoff sequence.
+ */
+ raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock);
+ spin_unlock(q.lock_ptr);
+ ret = __rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current);
+ raw_spin_unlock_irq(&q.pi_state->pi_mutex.wait_lock);
+
+ if (ret) {
+ if (ret == 1)
+ ret = 0;
+
+ spin_lock(q.lock_ptr);
+ goto no_block;
+ }
+
+
+ if (unlikely(to))
+ hrtimer_start_expires(&to->timer, HRTIMER_MODE_ABS);
+
+ ret = rt_mutex_wait_proxy_lock(&q.pi_state->pi_mutex, to, &rt_waiter);
+
spin_lock(q.lock_ptr);
/*
+ * If we failed to acquire the lock (signal/timeout), we must
+ * first acquire the hb->lock before removing the lock from the
+ * rt_mutex waitqueue, such that we can keep the hb and rt_mutex
+ * wait lists consistent.
+ *
+ * In particular; it is important that futex_unlock_pi() can not
+ * observe this inconsistency.
+ */
+ if (ret && !rt_mutex_cleanup_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter))
+ ret = 0;
+
+no_block:
+ /*
* Fixup the pi_state owner and possibly acquire the lock if we
* haven't already.
*/
* If fixup_owner() faulted and was unable to handle the fault, unlock
* it and return the fault to userspace.
*/
- if (ret && (rt_mutex_owner(&q.pi_state->pi_mutex) == current))
- rt_mutex_unlock(&q.pi_state->pi_mutex);
+ if (ret && (rt_mutex_owner(&q.pi_state->pi_mutex) == current)) {
+ pi_state = q.pi_state;
+ get_pi_state(pi_state);
+ }
/* Unqueue and drop the lock */
unqueue_me_pi(&q);
+ if (pi_state) {
+ rt_mutex_futex_unlock(&pi_state->pi_mutex);
+ put_pi_state(pi_state);
+ }
+
goto out_put_key;
out_unlock_put_key:
out_put_key:
put_futex_key(&q.key);
out:
- if (to)
+ if (to) {
+ hrtimer_cancel(&to->timer);
destroy_hrtimer_on_stack(&to->timer);
+ }
return ret != -EINTR ? ret : -ERESTARTNOINTR;
uaddr_faulted:
u32 uninitialized_var(curval), uval, vpid = task_pid_vnr(current);
union futex_key key = FUTEX_KEY_INIT;
struct futex_hash_bucket *hb;
- struct futex_q *match;
+ struct futex_q *top_waiter;
int ret;
retry:
* all and we at least want to know if user space fiddled
* with the futex value instead of blindly unlocking.
*/
- match = futex_top_waiter(hb, &key);
- if (match) {
- ret = wake_futex_pi(uaddr, uval, match, hb);
+ top_waiter = futex_top_waiter(hb, &key);
+ if (top_waiter) {
+ struct futex_pi_state *pi_state = top_waiter->pi_state;
+
+ ret = -EINVAL;
+ if (!pi_state)
+ goto out_unlock;
+
/*
- * In case of success wake_futex_pi dropped the hash
- * bucket lock.
+ * If current does not own the pi_state then the futex is
+ * inconsistent and user space fiddled with the futex value.
+ */
+ if (pi_state->owner != current)
+ goto out_unlock;
+
+ get_pi_state(pi_state);
+ /*
+ * By taking wait_lock while still holding hb->lock, we ensure
+ * there is no point where we hold neither; and therefore
+ * wake_futex_pi() must observe a state consistent with what we
+ * observed.
+ */
+ raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+ spin_unlock(&hb->lock);
+
+ ret = wake_futex_pi(uaddr, uval, pi_state);
+
+ put_pi_state(pi_state);
+
+ /*
+ * Success, we're done! No tricky corner cases.
*/
if (!ret)
goto out_putkey;
* setting the FUTEX_WAITERS bit. Try again.
*/
if (ret == -EAGAIN) {
- spin_unlock(&hb->lock);
put_futex_key(&key);
goto retry;
}
* wake_futex_pi has detected invalid state. Tell user
* space.
*/
- goto out_unlock;
+ goto out_putkey;
}
/*
* preserve the WAITERS bit not the OWNER_DIED one. We are the
* owner.
*/
- if (cmpxchg_futex_value_locked(&curval, uaddr, uval, 0))
+ if (cmpxchg_futex_value_locked(&curval, uaddr, uval, 0)) {
+ spin_unlock(&hb->lock);
goto pi_faulted;
+ }
/*
* If uval has changed, let user space handle it.
return ret;
pi_faulted:
- spin_unlock(&hb->lock);
put_futex_key(&key);
ret = fault_in_user_writeable(uaddr);
u32 __user *uaddr2)
{
struct hrtimer_sleeper timeout, *to = NULL;
+ struct futex_pi_state *pi_state = NULL;
struct rt_mutex_waiter rt_waiter;
struct futex_hash_bucket *hb;
union futex_key key2 = FUTEX_KEY_INIT;
* The waiter is allocated on our stack, manipulated by the requeue
* code while we sleep on uaddr.
*/
- debug_rt_mutex_init_waiter(&rt_waiter);
- RB_CLEAR_NODE(&rt_waiter.pi_tree_entry);
- RB_CLEAR_NODE(&rt_waiter.tree_entry);
- rt_waiter.task = NULL;
+ rt_mutex_init_waiter(&rt_waiter);
ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE);
if (unlikely(ret != 0))
if (q.pi_state && (q.pi_state->owner != current)) {
spin_lock(q.lock_ptr);
ret = fixup_pi_state_owner(uaddr2, &q, current);
- if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current)
- rt_mutex_unlock(&q.pi_state->pi_mutex);
+ if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) {
+ pi_state = q.pi_state;
+ get_pi_state(pi_state);
+ }
/*
* Drop the reference to the pi state which
* the requeue_pi() code acquired for us.
*/
WARN_ON(!q.pi_state);
pi_mutex = &q.pi_state->pi_mutex;
- ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter);
- debug_rt_mutex_free_waiter(&rt_waiter);
+ ret = rt_mutex_wait_proxy_lock(pi_mutex, to, &rt_waiter);
spin_lock(q.lock_ptr);
+ if (ret && !rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter))
+ ret = 0;
+
+ debug_rt_mutex_free_waiter(&rt_waiter);
/*
* Fixup the pi_state owner and possibly acquire the lock if we
* haven't already.
* the fault, unlock the rt_mutex and return the fault to
* userspace.
*/
- if (ret && rt_mutex_owner(pi_mutex) == current)
- rt_mutex_unlock(pi_mutex);
+ if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) {
+ pi_state = q.pi_state;
+ get_pi_state(pi_state);
+ }
/* Unqueue and drop the lock. */
unqueue_me_pi(&q);
}
+ if (pi_state) {
+ rt_mutex_futex_unlock(&pi_state->pi_mutex);
+ put_pi_state(pi_state);
+ }
+
if (ret == -EINTR) {
/*
* We've already been requeued, but cannot restart by calling
struct cpumask *
irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
{
- int n, nodes, vecs_per_node, cpus_per_vec, extra_vecs, curvec;
+ int n, nodes, cpus_per_vec, extra_vecs, curvec;
int affv = nvecs - affd->pre_vectors - affd->post_vectors;
int last_affv = affv + affd->pre_vectors;
nodemask_t nodemsk = NODE_MASK_NONE;
goto done;
}
- /* Spread the vectors per node */
- vecs_per_node = affv / nodes;
- /* Account for rounding errors */
- extra_vecs = affv - (nodes * vecs_per_node);
-
for_each_node_mask(n, nodemsk) {
- int ncpus, v, vecs_to_assign = vecs_per_node;
+ int ncpus, v, vecs_to_assign, vecs_per_node;
+
+ /* Spread the vectors per node */
+ vecs_per_node = (affv - (curvec - affd->pre_vectors)) / nodes;
/* Get the cpus on this node which are in the mask */
cpumask_and(nmsk, cpu_online_mask, cpumask_of_node(n));
/* Calculate the number of cpus per vector */
ncpus = cpumask_weight(nmsk);
+ vecs_to_assign = min(vecs_per_node, ncpus);
+
+ /* Account for rounding errors */
+ extra_vecs = ncpus - vecs_to_assign * (ncpus / vecs_to_assign);
for (v = 0; curvec < last_affv && v < vecs_to_assign;
curvec++, v++) {
/* Account for extra vectors to compensate rounding errors */
if (extra_vecs) {
cpus_per_vec++;
- if (!--extra_vecs)
- vecs_per_node++;
+ --extra_vecs;
}
irq_spread_init_one(masks + curvec, nmsk, cpus_per_vec);
}
if (curvec >= last_affv)
break;
+ --nodes;
}
done:
irqd_set(&desc->irq_data, IRQD_IRQ_INPROGRESS);
raw_spin_unlock_irq(&desc->lock);
- action_ret = action->thread_fn(action->irq, action->dev_id);
+ action_ret = IRQ_NONE;
+ for_each_action_of_desc(desc, action)
+ action_ret |= action->thread_fn(action->irq, action->dev_id);
+
if (!noirqdebug)
note_interrupt(desc, action_ret);
* This code is triggered unconditionally. Check the affinity
* mask pointer. For CPU_MASK_OFFSTACK=n this is optimized out.
*/
- if (desc->irq_common_data.affinity)
+ if (cpumask_available(desc->irq_common_data.affinity))
cpumask_copy(mask, desc->irq_common_data.affinity);
else
valid = false;
* set the trigger type must match. Also all must
* agree on ONESHOT.
*/
+ unsigned int oldtype = irqd_get_trigger_type(&desc->irq_data);
+
if (!((old->flags & new->flags) & IRQF_SHARED) ||
- ((old->flags ^ new->flags) & IRQF_TRIGGER_MASK) ||
+ (oldtype != (new->flags & IRQF_TRIGGER_MASK)) ||
((old->flags ^ new->flags) & IRQF_ONESHOT))
goto mismatch;
* This returns encoded errors if it fails to look up symbol or invalid
* combination of parameters.
*/
-static kprobe_opcode_t *kprobe_addr(struct kprobe *p)
+static kprobe_opcode_t *_kprobe_addr(kprobe_opcode_t *addr,
+ const char *symbol_name, unsigned int offset)
{
- kprobe_opcode_t *addr = p->addr;
-
- if ((p->symbol_name && p->addr) ||
- (!p->symbol_name && !p->addr))
+ if ((symbol_name && addr) || (!symbol_name && !addr))
goto invalid;
- if (p->symbol_name) {
- kprobe_lookup_name(p->symbol_name, addr);
+ if (symbol_name) {
+ kprobe_lookup_name(symbol_name, addr);
if (!addr)
return ERR_PTR(-ENOENT);
}
- addr = (kprobe_opcode_t *)(((char *)addr) + p->offset);
+ addr = (kprobe_opcode_t *)(((char *)addr) + offset);
if (addr)
return addr;
return ERR_PTR(-EINVAL);
}
+static kprobe_opcode_t *kprobe_addr(struct kprobe *p)
+{
+ return _kprobe_addr(p->addr, p->symbol_name, p->offset);
+}
+
/* Check passed kprobe is valid and return kprobe in kprobe_table. */
static struct kprobe *__get_valid_kprobe(struct kprobe *p)
{
}
EXPORT_SYMBOL_GPL(unregister_kprobes);
-int __weak __kprobes kprobe_exceptions_notify(struct notifier_block *self,
- unsigned long val, void *data)
+int __weak kprobe_exceptions_notify(struct notifier_block *self,
+ unsigned long val, void *data)
{
return NOTIFY_DONE;
}
+NOKPROBE_SYMBOL(kprobe_exceptions_notify);
static struct notifier_block kprobe_exceptions_nb = {
.notifier_call = kprobe_exceptions_notify,
}
NOKPROBE_SYMBOL(pre_handler_kretprobe);
+bool __weak arch_function_offset_within_entry(unsigned long offset)
+{
+ return !offset;
+}
+
+bool function_offset_within_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset)
+{
+ kprobe_opcode_t *kp_addr = _kprobe_addr(addr, sym, offset);
+
+ if (IS_ERR(kp_addr))
+ return false;
+
+ if (!kallsyms_lookup_size_offset((unsigned long)kp_addr, NULL, &offset) ||
+ !arch_function_offset_within_entry(offset))
+ return false;
+
+ return true;
+}
+
int register_kretprobe(struct kretprobe *rp)
{
int ret = 0;
int i;
void *addr;
+ if (!function_offset_within_entry(rp->kp.addr, rp->kp.symbol_name, rp->kp.offset))
+ return -EINVAL;
+
if (kretprobe_blacklist_size) {
addr = kprobe_addr(&rp->kp);
if (IS_ERR(addr))
#include <linux/freezer.h>
#include <linux/ptrace.h>
#include <linux/uaccess.h>
+#include <linux/cgroup.h>
#include <trace/events/sched.h>
static DEFINE_SPINLOCK(kthread_create_lock);
ret = -EINTR;
if (!test_bit(KTHREAD_SHOULD_STOP, &self->flags)) {
+ cgroup_kthread_ready();
__kthread_parkme(self);
ret = threadfn(data);
}
set_mems_allowed(node_states[N_MEMORY]);
current->flags |= PF_NOFREEZE;
+ cgroup_init_kthreadd();
for (;;) {
set_current_state(TASK_INTERRUPTIBLE);
struct lockdep_subclass_key *key;
struct hlist_head *hash_head;
struct lock_class *class;
+ bool is_static = false;
if (unlikely(subclass >= MAX_LOCKDEP_SUBCLASSES)) {
debug_locks_off();
/*
* Static locks do not have their class-keys yet - for them the key
- * is the lock object itself:
+ * is the lock object itself. If the lock is in the per cpu area,
+ * the canonical address of the lock (per cpu offset removed) is
+ * used.
*/
- if (unlikely(!lock->key))
- lock->key = (void *)lock;
+ if (unlikely(!lock->key)) {
+ unsigned long can_addr, addr = (unsigned long)lock;
+
+ if (__is_kernel_percpu_address(addr, &can_addr))
+ lock->key = (void *)can_addr;
+ else if (__is_module_percpu_address(addr, &can_addr))
+ lock->key = (void *)can_addr;
+ else if (static_obj(lock))
+ lock->key = (void *)lock;
+ else
+ return ERR_PTR(-EINVAL);
+ is_static = true;
+ }
/*
* NOTE: the class-key must be unique. For dynamic locks, a static
}
}
- return NULL;
+ return is_static || static_obj(lock->key) ? NULL : ERR_PTR(-EINVAL);
}
/*
DEBUG_LOCKS_WARN_ON(!irqs_disabled());
class = look_up_lock_class(lock, subclass);
- if (likely(class))
+ if (likely(!IS_ERR_OR_NULL(class)))
goto out_set_class_cache;
/*
* Debug-check: all keys must be persistent!
- */
- if (!static_obj(lock->key)) {
+ */
+ if (IS_ERR(class)) {
debug_locks_off();
printk("INFO: trying to register non-static key.\n");
printk("the code is fine but needs lockdep annotation.\n");
printk("turning off the locking correctness validator.\n");
dump_stack();
-
return NULL;
}
* Clearly if the lock hasn't been acquired _ever_, we're not
* holding it either, so report failure.
*/
- if (!class)
+ if (IS_ERR_OR_NULL(class))
return 0;
/*
return 0;
}
+/* @depth must not be zero */
+static struct held_lock *find_held_lock(struct task_struct *curr,
+ struct lockdep_map *lock,
+ unsigned int depth, int *idx)
+{
+ struct held_lock *ret, *hlock, *prev_hlock;
+ int i;
+
+ i = depth - 1;
+ hlock = curr->held_locks + i;
+ ret = hlock;
+ if (match_held_lock(hlock, lock))
+ goto out;
+
+ ret = NULL;
+ for (i--, prev_hlock = hlock--;
+ i >= 0;
+ i--, prev_hlock = hlock--) {
+ /*
+ * We must not cross into another context:
+ */
+ if (prev_hlock->irq_context != hlock->irq_context) {
+ ret = NULL;
+ break;
+ }
+ if (match_held_lock(hlock, lock)) {
+ ret = hlock;
+ break;
+ }
+ }
+
+out:
+ *idx = i;
+ return ret;
+}
+
+static int reacquire_held_locks(struct task_struct *curr, unsigned int depth,
+ int idx)
+{
+ struct held_lock *hlock;
+
+ for (hlock = curr->held_locks + idx; idx < depth; idx++, hlock++) {
+ if (!__lock_acquire(hlock->instance,
+ hlock_class(hlock)->subclass,
+ hlock->trylock,
+ hlock->read, hlock->check,
+ hlock->hardirqs_off,
+ hlock->nest_lock, hlock->acquire_ip,
+ hlock->references, hlock->pin_count))
+ return 1;
+ }
+ return 0;
+}
+
static int
__lock_set_class(struct lockdep_map *lock, const char *name,
struct lock_class_key *key, unsigned int subclass,
unsigned long ip)
{
struct task_struct *curr = current;
- struct held_lock *hlock, *prev_hlock;
+ struct held_lock *hlock;
struct lock_class *class;
unsigned int depth;
int i;
if (DEBUG_LOCKS_WARN_ON(!depth))
return 0;
- prev_hlock = NULL;
- for (i = depth-1; i >= 0; i--) {
- hlock = curr->held_locks + i;
- /*
- * We must not cross into another context:
- */
- if (prev_hlock && prev_hlock->irq_context != hlock->irq_context)
- break;
- if (match_held_lock(hlock, lock))
- goto found_it;
- prev_hlock = hlock;
- }
- return print_unlock_imbalance_bug(curr, lock, ip);
+ hlock = find_held_lock(curr, lock, depth, &i);
+ if (!hlock)
+ return print_unlock_imbalance_bug(curr, lock, ip);
-found_it:
lockdep_init_map(lock, name, key, 0);
class = register_lock_class(lock, subclass, 0);
hlock->class_idx = class - lock_classes + 1;
curr->lockdep_depth = i;
curr->curr_chain_key = hlock->prev_chain_key;
- for (; i < depth; i++) {
- hlock = curr->held_locks + i;
- if (!__lock_acquire(hlock->instance,
- hlock_class(hlock)->subclass, hlock->trylock,
- hlock->read, hlock->check, hlock->hardirqs_off,
- hlock->nest_lock, hlock->acquire_ip,
- hlock->references, hlock->pin_count))
- return 0;
- }
+ if (reacquire_held_locks(curr, depth, i))
+ return 0;
+
+ /*
+ * I took it apart and put it back together again, except now I have
+ * these 'spare' parts.. where shall I put them.
+ */
+ if (DEBUG_LOCKS_WARN_ON(curr->lockdep_depth != depth))
+ return 0;
+ return 1;
+}
+
+static int __lock_downgrade(struct lockdep_map *lock, unsigned long ip)
+{
+ struct task_struct *curr = current;
+ struct held_lock *hlock;
+ unsigned int depth;
+ int i;
+
+ depth = curr->lockdep_depth;
+ /*
+ * This function is about (re)setting the class of a held lock,
+ * yet we're not actually holding any locks. Naughty user!
+ */
+ if (DEBUG_LOCKS_WARN_ON(!depth))
+ return 0;
+
+ hlock = find_held_lock(curr, lock, depth, &i);
+ if (!hlock)
+ return print_unlock_imbalance_bug(curr, lock, ip);
+
+ curr->lockdep_depth = i;
+ curr->curr_chain_key = hlock->prev_chain_key;
+
+ WARN(hlock->read, "downgrading a read lock");
+ hlock->read = 1;
+ hlock->acquire_ip = ip;
+
+ if (reacquire_held_locks(curr, depth, i))
+ return 0;
/*
* I took it apart and put it back together again, except now I have
__lock_release(struct lockdep_map *lock, int nested, unsigned long ip)
{
struct task_struct *curr = current;
- struct held_lock *hlock, *prev_hlock;
+ struct held_lock *hlock;
unsigned int depth;
int i;
* Check whether the lock exists in the current stack
* of held locks:
*/
- prev_hlock = NULL;
- for (i = depth-1; i >= 0; i--) {
- hlock = curr->held_locks + i;
- /*
- * We must not cross into another context:
- */
- if (prev_hlock && prev_hlock->irq_context != hlock->irq_context)
- break;
- if (match_held_lock(hlock, lock))
- goto found_it;
- prev_hlock = hlock;
- }
- return print_unlock_imbalance_bug(curr, lock, ip);
+ hlock = find_held_lock(curr, lock, depth, &i);
+ if (!hlock)
+ return print_unlock_imbalance_bug(curr, lock, ip);
-found_it:
if (hlock->instance == lock)
lock_release_holdtime(hlock);
curr->lockdep_depth = i;
curr->curr_chain_key = hlock->prev_chain_key;
- for (i++; i < depth; i++) {
- hlock = curr->held_locks + i;
- if (!__lock_acquire(hlock->instance,
- hlock_class(hlock)->subclass, hlock->trylock,
- hlock->read, hlock->check, hlock->hardirqs_off,
- hlock->nest_lock, hlock->acquire_ip,
- hlock->references, hlock->pin_count))
- return 0;
- }
+ if (reacquire_held_locks(curr, depth, i + 1))
+ return 0;
/*
* We had N bottles of beer on the wall, we drank one, but now
}
EXPORT_SYMBOL_GPL(lock_set_class);
+void lock_downgrade(struct lockdep_map *lock, unsigned long ip)
+{
+ unsigned long flags;
+
+ if (unlikely(current->lockdep_recursion))
+ return;
+
+ raw_local_irq_save(flags);
+ current->lockdep_recursion = 1;
+ check_flags(flags);
+ if (__lock_downgrade(lock, ip))
+ check_chain_key(current);
+ current->lockdep_recursion = 0;
+ raw_local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(lock_downgrade);
+
/*
* We are not always called with irqs disabled - do that here,
* and also avoid lockdep recursion:
__lock_contended(struct lockdep_map *lock, unsigned long ip)
{
struct task_struct *curr = current;
- struct held_lock *hlock, *prev_hlock;
+ struct held_lock *hlock;
struct lock_class_stats *stats;
unsigned int depth;
int i, contention_point, contending_point;
if (DEBUG_LOCKS_WARN_ON(!depth))
return;
- prev_hlock = NULL;
- for (i = depth-1; i >= 0; i--) {
- hlock = curr->held_locks + i;
- /*
- * We must not cross into another context:
- */
- if (prev_hlock && prev_hlock->irq_context != hlock->irq_context)
- break;
- if (match_held_lock(hlock, lock))
- goto found_it;
- prev_hlock = hlock;
+ hlock = find_held_lock(curr, lock, depth, &i);
+ if (!hlock) {
+ print_lock_contention_bug(curr, lock, ip);
+ return;
}
- print_lock_contention_bug(curr, lock, ip);
- return;
-found_it:
if (hlock->instance != lock)
return;
__lock_acquired(struct lockdep_map *lock, unsigned long ip)
{
struct task_struct *curr = current;
- struct held_lock *hlock, *prev_hlock;
+ struct held_lock *hlock;
struct lock_class_stats *stats;
unsigned int depth;
u64 now, waittime = 0;
if (DEBUG_LOCKS_WARN_ON(!depth))
return;
- prev_hlock = NULL;
- for (i = depth-1; i >= 0; i--) {
- hlock = curr->held_locks + i;
- /*
- * We must not cross into another context:
- */
- if (prev_hlock && prev_hlock->irq_context != hlock->irq_context)
- break;
- if (match_held_lock(hlock, lock))
- goto found_it;
- prev_hlock = hlock;
+ hlock = find_held_lock(curr, lock, depth, &i);
+ if (!hlock) {
+ print_lock_contention_bug(curr, lock, _RET_IP_);
+ return;
}
- print_lock_contention_bug(curr, lock, _RET_IP_);
- return;
-found_it:
if (hlock->instance != lock)
return;
* If the class exists we look it up and zap it:
*/
class = look_up_lock_class(lock, j);
- if (class)
+ if (!IS_ERR_OR_NULL(class))
zap_class(class);
}
/*
(LOCKF_USED_IN_HARDIRQ_READ | LOCKF_USED_IN_SOFTIRQ_READ)
/*
- * CONFIG_PROVE_LOCKING_SMALL is defined for sparc. Sparc requires .text,
+ * CONFIG_LOCKDEP_SMALL is defined for sparc. Sparc requires .text,
* .data and .bss to fit in required 32MB limit for the kernel. With
- * PROVE_LOCKING we could go over this limit and cause system boot-up problems.
+ * CONFIG_LOCKDEP we could go over this limit and cause system boot-up problems.
* So, reduce the static allocations for lockdeps related structures so that
* everything fits in current required size limit.
*/
-#ifdef CONFIG_PROVE_LOCKING_SMALL
+#ifdef CONFIG_LOCKDEP_SMALL
/*
* MAX_LOCKDEP_ENTRIES is the maximum number of lock dependencies
* we track.
lock->name = name;
}
-void
-rt_mutex_deadlock_account_lock(struct rt_mutex *lock, struct task_struct *task)
-{
-}
-
-void rt_mutex_deadlock_account_unlock(struct task_struct *task)
-{
-}
-
* This file contains macros used solely by rtmutex.c. Debug version.
*/
-extern void
-rt_mutex_deadlock_account_lock(struct rt_mutex *lock, struct task_struct *task);
-extern void rt_mutex_deadlock_account_unlock(struct task_struct *task);
extern void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter);
extern void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter);
extern void debug_rt_mutex_init(struct rt_mutex *lock, const char *name);
}
#endif
+/*
+ * Only use with rt_mutex_waiter_{less,equal}()
+ */
+#define task_to_waiter(p) \
+ &(struct rt_mutex_waiter){ .prio = (p)->prio, .deadline = (p)->dl.deadline }
+
static inline int
rt_mutex_waiter_less(struct rt_mutex_waiter *left,
struct rt_mutex_waiter *right)
* then right waiter has a dl_prio() too.
*/
if (dl_prio(left->prio))
- return dl_time_before(left->task->dl.deadline,
- right->task->dl.deadline);
+ return dl_time_before(left->deadline, right->deadline);
return 0;
}
+static inline int
+rt_mutex_waiter_equal(struct rt_mutex_waiter *left,
+ struct rt_mutex_waiter *right)
+{
+ if (left->prio != right->prio)
+ return 0;
+
+ /*
+ * If both waiters have dl_prio(), we check the deadlines of the
+ * associated tasks.
+ * If left waiter has a dl_prio(), and we didn't return 0 above,
+ * then right waiter has a dl_prio() too.
+ */
+ if (dl_prio(left->prio))
+ return left->deadline == right->deadline;
+
+ return 1;
+}
+
static void
rt_mutex_enqueue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
{
RB_CLEAR_NODE(&waiter->pi_tree_entry);
}
-/*
- * Calculate task priority from the waiter tree priority
- *
- * Return task->normal_prio when the waiter tree is empty or when
- * the waiter is not allowed to do priority boosting
- */
-int rt_mutex_getprio(struct task_struct *task)
-{
- if (likely(!task_has_pi_waiters(task)))
- return task->normal_prio;
-
- return min(task_top_pi_waiter(task)->prio,
- task->normal_prio);
-}
-
-struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
+static void rt_mutex_adjust_prio(struct task_struct *p)
{
- if (likely(!task_has_pi_waiters(task)))
- return NULL;
-
- return task_top_pi_waiter(task)->task;
-}
+ struct task_struct *pi_task = NULL;
-/*
- * Called by sched_setscheduler() to get the priority which will be
- * effective after the change.
- */
-int rt_mutex_get_effective_prio(struct task_struct *task, int newprio)
-{
- if (!task_has_pi_waiters(task))
- return newprio;
+ lockdep_assert_held(&p->pi_lock);
- if (task_top_pi_waiter(task)->task->prio <= newprio)
- return task_top_pi_waiter(task)->task->prio;
- return newprio;
-}
+ if (task_has_pi_waiters(p))
+ pi_task = task_top_pi_waiter(p)->task;
-/*
- * Adjust the priority of a task, after its pi_waiters got modified.
- *
- * This can be both boosting and unboosting. task->pi_lock must be held.
- */
-static void __rt_mutex_adjust_prio(struct task_struct *task)
-{
- int prio = rt_mutex_getprio(task);
-
- if (task->prio != prio || dl_prio(prio))
- rt_mutex_setprio(task, prio);
-}
-
-/*
- * Adjust task priority (undo boosting). Called from the exit path of
- * rt_mutex_slowunlock() and rt_mutex_slowlock().
- *
- * (Note: We do this outside of the protection of lock->wait_lock to
- * allow the lock to be taken while or before we readjust the priority
- * of task. We do not use the spin_xx_mutex() variants here as we are
- * outside of the debug path.)
- */
-void rt_mutex_adjust_prio(struct task_struct *task)
-{
- unsigned long flags;
-
- raw_spin_lock_irqsave(&task->pi_lock, flags);
- __rt_mutex_adjust_prio(task);
- raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+ rt_mutex_setprio(p, pi_task);
}
/*
* enabled we continue, but stop the requeueing in the chain
* walk.
*/
- if (waiter->prio == task->prio) {
+ if (rt_mutex_waiter_equal(waiter, task_to_waiter(task))) {
if (!detect_deadlock)
goto out_unlock_pi;
else
/* [7] Requeue the waiter in the lock waiter tree. */
rt_mutex_dequeue(lock, waiter);
+
+ /*
+ * Update the waiter prio fields now that we're dequeued.
+ *
+ * These values can have changed through either:
+ *
+ * sys_sched_set_scheduler() / sys_sched_setattr()
+ *
+ * or
+ *
+ * DL CBS enforcement advancing the effective deadline.
+ *
+ * Even though pi_waiters also uses these fields, and that tree is only
+ * updated in [11], we can do this here, since we hold [L], which
+ * serializes all pi_waiters access and rb_erase() does not care about
+ * the values of the node being removed.
+ */
waiter->prio = task->prio;
+ waiter->deadline = task->dl.deadline;
+
rt_mutex_enqueue(lock, waiter);
/* [8] Release the task */
*/
rt_mutex_dequeue_pi(task, prerequeue_top_waiter);
rt_mutex_enqueue_pi(task, waiter);
- __rt_mutex_adjust_prio(task);
+ rt_mutex_adjust_prio(task);
} else if (prerequeue_top_waiter == waiter) {
/*
rt_mutex_dequeue_pi(task, waiter);
waiter = rt_mutex_top_waiter(lock);
rt_mutex_enqueue_pi(task, waiter);
- __rt_mutex_adjust_prio(task);
+ rt_mutex_adjust_prio(task);
} else {
/*
* Nothing changed. No need to do any priority
static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
struct rt_mutex_waiter *waiter)
{
+ lockdep_assert_held(&lock->wait_lock);
+
/*
* Before testing whether we can acquire @lock, we set the
* RT_MUTEX_HAS_WAITERS bit in @lock->owner. This forces all
* the top waiter priority (kernel view),
* @task lost.
*/
- if (task->prio >= rt_mutex_top_waiter(lock)->prio)
+ if (!rt_mutex_waiter_less(task_to_waiter(task),
+ rt_mutex_top_waiter(lock)))
return 0;
/*
*/
rt_mutex_set_owner(lock, task);
- rt_mutex_deadlock_account_lock(lock, task);
-
return 1;
}
struct rt_mutex *next_lock;
int chain_walk = 0, res;
+ lockdep_assert_held(&lock->wait_lock);
+
/*
* Early deadlock detection. We really don't want the task to
* enqueue on itself just to untangle the mess later. It's not
return -EDEADLK;
raw_spin_lock(&task->pi_lock);
- __rt_mutex_adjust_prio(task);
+ rt_mutex_adjust_prio(task);
waiter->task = task;
waiter->lock = lock;
waiter->prio = task->prio;
+ waiter->deadline = task->dl.deadline;
/* Get the top priority waiter on the lock */
if (rt_mutex_has_waiters(lock))
rt_mutex_dequeue_pi(owner, top_waiter);
rt_mutex_enqueue_pi(owner, waiter);
- __rt_mutex_adjust_prio(owner);
+ rt_mutex_adjust_prio(owner);
if (owner->pi_blocked_on)
chain_walk = 1;
} else if (rt_mutex_cond_detect_deadlock(waiter, chwalk)) {
waiter = rt_mutex_top_waiter(lock);
/*
- * Remove it from current->pi_waiters. We do not adjust a
- * possible priority boost right now. We execute wakeup in the
- * boosted mode and go back to normal after releasing
- * lock->wait_lock.
+ * Remove it from current->pi_waiters and deboost.
+ *
+ * We must in fact deboost here in order to ensure we call
+ * rt_mutex_setprio() to update p->pi_top_task before the
+ * task unblocks.
*/
rt_mutex_dequeue_pi(current, waiter);
+ rt_mutex_adjust_prio(current);
/*
* As we are waking up the top waiter, and the waiter stays
*/
lock->owner = (void *) RT_MUTEX_HAS_WAITERS;
- raw_spin_unlock(¤t->pi_lock);
-
+ /*
+ * We deboosted before waking the top waiter task such that we don't
+ * run two tasks with the 'same' priority (and ensure the
+ * p->pi_top_task pointer points to a blocked task). This however can
+ * lead to priority inversion if we would get preempted after the
+ * deboost but before waking our donor task, hence the preempt_disable()
+ * before unlock.
+ *
+ * Pairs with preempt_enable() in rt_mutex_postunlock();
+ */
+ preempt_disable();
wake_q_add(wake_q, waiter->task);
+ raw_spin_unlock(¤t->pi_lock);
}
/*
struct task_struct *owner = rt_mutex_owner(lock);
struct rt_mutex *next_lock;
+ lockdep_assert_held(&lock->wait_lock);
+
raw_spin_lock(¤t->pi_lock);
rt_mutex_dequeue(lock, waiter);
current->pi_blocked_on = NULL;
if (rt_mutex_has_waiters(lock))
rt_mutex_enqueue_pi(owner, rt_mutex_top_waiter(lock));
- __rt_mutex_adjust_prio(owner);
+ rt_mutex_adjust_prio(owner);
/* Store the lock on which owner is blocked or NULL */
next_lock = task_blocked_on_lock(owner);
raw_spin_lock_irqsave(&task->pi_lock, flags);
waiter = task->pi_blocked_on;
- if (!waiter || (waiter->prio == task->prio &&
- !dl_prio(task->prio))) {
+ if (!waiter || rt_mutex_waiter_equal(waiter, task_to_waiter(task))) {
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
return;
}
next_lock, NULL, task);
}
+void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter)
+{
+ debug_rt_mutex_init_waiter(waiter);
+ RB_CLEAR_NODE(&waiter->pi_tree_entry);
+ RB_CLEAR_NODE(&waiter->tree_entry);
+ waiter->task = NULL;
+}
+
/**
* __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop
* @lock: the rt_mutex to take
unsigned long flags;
int ret = 0;
- debug_rt_mutex_init_waiter(&waiter);
- RB_CLEAR_NODE(&waiter.pi_tree_entry);
- RB_CLEAR_NODE(&waiter.tree_entry);
+ rt_mutex_init_waiter(&waiter);
/*
* Technically we could use raw_spin_[un]lock_irq() here, but this can
/*
* Slow path to release a rt-mutex.
- * Return whether the current task needs to undo a potential priority boosting.
+ *
+ * Return whether the current task needs to call rt_mutex_postunlock().
*/
static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
struct wake_q_head *wake_q)
debug_rt_mutex_unlock(lock);
- rt_mutex_deadlock_account_unlock(current);
-
/*
* We must be careful here if the fast path is enabled. If we
* have no waiters queued we cannot set owner to NULL here
* Queue the next waiter for wakeup once we release the wait_lock.
*/
mark_wakeup_next_waiter(wake_q, lock);
-
raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
- /* check PI boosting */
- return true;
+ return true; /* call rt_mutex_postunlock() */
}
/*
struct hrtimer_sleeper *timeout,
enum rtmutex_chainwalk chwalk))
{
- if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) {
- rt_mutex_deadlock_account_lock(lock, current);
+ if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
return 0;
- } else
- return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK);
+
+ return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK);
}
static inline int
enum rtmutex_chainwalk chwalk))
{
if (chwalk == RT_MUTEX_MIN_CHAINWALK &&
- likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) {
- rt_mutex_deadlock_account_lock(lock, current);
+ likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
return 0;
- } else
- return slowfn(lock, state, timeout, chwalk);
+
+ return slowfn(lock, state, timeout, chwalk);
}
static inline int
rt_mutex_fasttrylock(struct rt_mutex *lock,
int (*slowfn)(struct rt_mutex *lock))
{
- if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) {
- rt_mutex_deadlock_account_lock(lock, current);
+ if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
return 1;
- }
+
return slowfn(lock);
}
+/*
+ * Performs the wakeup of the the top-waiter and re-enables preemption.
+ */
+void rt_mutex_postunlock(struct wake_q_head *wake_q)
+{
+ wake_up_q(wake_q);
+
+ /* Pairs with preempt_disable() in rt_mutex_slowunlock() */
+ preempt_enable();
+}
+
static inline void
rt_mutex_fastunlock(struct rt_mutex *lock,
bool (*slowfn)(struct rt_mutex *lock,
{
DEFINE_WAKE_Q(wake_q);
- if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) {
- rt_mutex_deadlock_account_unlock(current);
-
- } else {
- bool deboost = slowfn(lock, &wake_q);
-
- wake_up_q(&wake_q);
+ if (likely(rt_mutex_cmpxchg_release(lock, current, NULL)))
+ return;
- /* Undo pi boosting if necessary: */
- if (deboost)
- rt_mutex_adjust_prio(current);
- }
+ if (slowfn(lock, &wake_q))
+ rt_mutex_postunlock(&wake_q);
}
/**
EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible);
/*
- * Futex variant with full deadlock detection.
+ * Futex variant, must not use fastpath.
*/
-int rt_mutex_timed_futex_lock(struct rt_mutex *lock,
- struct hrtimer_sleeper *timeout)
+int __sched rt_mutex_futex_trylock(struct rt_mutex *lock)
{
- might_sleep();
-
- return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout,
- RT_MUTEX_FULL_CHAINWALK,
- rt_mutex_slowlock);
+ return rt_mutex_slowtrylock(lock);
}
/**
EXPORT_SYMBOL_GPL(rt_mutex_unlock);
/**
- * rt_mutex_futex_unlock - Futex variant of rt_mutex_unlock
- * @lock: the rt_mutex to be unlocked
- *
- * Returns: true/false indicating whether priority adjustment is
- * required or not.
+ * Futex variant, that since futex variants do not use the fast-path, can be
+ * simple and will not need to retry.
*/
-bool __sched rt_mutex_futex_unlock(struct rt_mutex *lock,
- struct wake_q_head *wqh)
+bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock,
+ struct wake_q_head *wake_q)
{
- if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) {
- rt_mutex_deadlock_account_unlock(current);
- return false;
+ lockdep_assert_held(&lock->wait_lock);
+
+ debug_rt_mutex_unlock(lock);
+
+ if (!rt_mutex_has_waiters(lock)) {
+ lock->owner = NULL;
+ return false; /* done */
}
- return rt_mutex_slowunlock(lock, wqh);
+
+ /*
+ * We've already deboosted, mark_wakeup_next_waiter() will
+ * retain preempt_disabled when we drop the wait_lock, to
+ * avoid inversion prior to the wakeup. preempt_disable()
+ * therein pairs with rt_mutex_postunlock().
+ */
+ mark_wakeup_next_waiter(wake_q, lock);
+
+ return true; /* call postunlock() */
+}
+
+void __sched rt_mutex_futex_unlock(struct rt_mutex *lock)
+{
+ DEFINE_WAKE_Q(wake_q);
+ bool postunlock;
+
+ raw_spin_lock_irq(&lock->wait_lock);
+ postunlock = __rt_mutex_futex_unlock(lock, &wake_q);
+ raw_spin_unlock_irq(&lock->wait_lock);
+
+ if (postunlock)
+ rt_mutex_postunlock(&wake_q);
}
/**
__rt_mutex_init(lock, NULL);
debug_rt_mutex_proxy_lock(lock, proxy_owner);
rt_mutex_set_owner(lock, proxy_owner);
- rt_mutex_deadlock_account_lock(lock, proxy_owner);
}
/**
{
debug_rt_mutex_proxy_unlock(lock);
rt_mutex_set_owner(lock, NULL);
- rt_mutex_deadlock_account_unlock(proxy_owner);
}
-/**
- * rt_mutex_start_proxy_lock() - Start lock acquisition for another task
- * @lock: the rt_mutex to take
- * @waiter: the pre-initialized rt_mutex_waiter
- * @task: the task to prepare
- *
- * Returns:
- * 0 - task blocked on lock
- * 1 - acquired the lock for task, caller should wake it up
- * <0 - error
- *
- * Special API call for FUTEX_REQUEUE_PI support.
- */
-int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
+int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
struct rt_mutex_waiter *waiter,
struct task_struct *task)
{
int ret;
- raw_spin_lock_irq(&lock->wait_lock);
-
- if (try_to_take_rt_mutex(lock, task, NULL)) {
- raw_spin_unlock_irq(&lock->wait_lock);
+ if (try_to_take_rt_mutex(lock, task, NULL))
return 1;
- }
/* We enforce deadlock detection for futexes */
ret = task_blocks_on_rt_mutex(lock, waiter, task,
if (unlikely(ret))
remove_waiter(lock, waiter);
- raw_spin_unlock_irq(&lock->wait_lock);
-
debug_rt_mutex_print_deadlock(waiter);
return ret;
}
/**
+ * rt_mutex_start_proxy_lock() - Start lock acquisition for another task
+ * @lock: the rt_mutex to take
+ * @waiter: the pre-initialized rt_mutex_waiter
+ * @task: the task to prepare
+ *
+ * Returns:
+ * 0 - task blocked on lock
+ * 1 - acquired the lock for task, caller should wake it up
+ * <0 - error
+ *
+ * Special API call for FUTEX_REQUEUE_PI support.
+ */
+int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
+ struct rt_mutex_waiter *waiter,
+ struct task_struct *task)
+{
+ int ret;
+
+ raw_spin_lock_irq(&lock->wait_lock);
+ ret = __rt_mutex_start_proxy_lock(lock, waiter, task);
+ raw_spin_unlock_irq(&lock->wait_lock);
+
+ return ret;
+}
+
+/**
* rt_mutex_next_owner - return the next owner of the lock
*
* @lock: the rt lock query
}
/**
- * rt_mutex_finish_proxy_lock() - Complete lock acquisition
+ * rt_mutex_wait_proxy_lock() - Wait for lock acquisition
* @lock: the rt_mutex we were woken on
* @to: the timeout, null if none. hrtimer should already have
* been started.
* @waiter: the pre-initialized rt_mutex_waiter
*
- * Complete the lock acquisition started our behalf by another thread.
+ * Wait for the the lock acquisition started on our behalf by
+ * rt_mutex_start_proxy_lock(). Upon failure, the caller must call
+ * rt_mutex_cleanup_proxy_lock().
*
* Returns:
* 0 - success
* <0 - error, one of -EINTR, -ETIMEDOUT
*
- * Special API call for PI-futex requeue support
+ * Special API call for PI-futex support
*/
-int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
+int rt_mutex_wait_proxy_lock(struct rt_mutex *lock,
struct hrtimer_sleeper *to,
struct rt_mutex_waiter *waiter)
{
/* sleep on the mutex */
ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter);
- if (unlikely(ret))
+ raw_spin_unlock_irq(&lock->wait_lock);
+
+ return ret;
+}
+
+/**
+ * rt_mutex_cleanup_proxy_lock() - Cleanup failed lock acquisition
+ * @lock: the rt_mutex we were woken on
+ * @waiter: the pre-initialized rt_mutex_waiter
+ *
+ * Attempt to clean up after a failed rt_mutex_wait_proxy_lock().
+ *
+ * Unless we acquired the lock; we're still enqueued on the wait-list and can
+ * in fact still be granted ownership until we're removed. Therefore we can
+ * find we are in fact the owner and must disregard the
+ * rt_mutex_wait_proxy_lock() failure.
+ *
+ * Returns:
+ * true - did the cleanup, we done.
+ * false - we acquired the lock after rt_mutex_wait_proxy_lock() returned,
+ * caller should disregards its return value.
+ *
+ * Special API call for PI-futex support
+ */
+bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
+ struct rt_mutex_waiter *waiter)
+{
+ bool cleanup = false;
+
+ raw_spin_lock_irq(&lock->wait_lock);
+ /*
+ * Unless we're the owner; we're still enqueued on the wait_list.
+ * So check if we became owner, if not, take us off the wait_list.
+ */
+ if (rt_mutex_owner(lock) != current) {
remove_waiter(lock, waiter);
+ fixup_rt_mutex_waiters(lock);
+ cleanup = true;
+ }
/*
* try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
raw_spin_unlock_irq(&lock->wait_lock);
- return ret;
+ return cleanup;
}
*/
#define rt_mutex_deadlock_check(l) (0)
-#define rt_mutex_deadlock_account_lock(m, t) do { } while (0)
-#define rt_mutex_deadlock_account_unlock(l) do { } while (0)
#define debug_rt_mutex_init_waiter(w) do { } while (0)
#define debug_rt_mutex_free_waiter(w) do { } while (0)
#define debug_rt_mutex_lock(l) do { } while (0)
struct rt_mutex *deadlock_lock;
#endif
int prio;
+ u64 deadline;
};
/*
struct task_struct *proxy_owner);
extern void rt_mutex_proxy_unlock(struct rt_mutex *lock,
struct task_struct *proxy_owner);
+extern void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter);
+extern int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
+ struct rt_mutex_waiter *waiter,
+ struct task_struct *task);
extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
struct rt_mutex_waiter *waiter,
struct task_struct *task);
-extern int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
- struct hrtimer_sleeper *to,
- struct rt_mutex_waiter *waiter);
-extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to);
-extern bool rt_mutex_futex_unlock(struct rt_mutex *lock,
- struct wake_q_head *wqh);
-extern void rt_mutex_adjust_prio(struct task_struct *task);
+extern int rt_mutex_wait_proxy_lock(struct rt_mutex *lock,
+ struct hrtimer_sleeper *to,
+ struct rt_mutex_waiter *waiter);
+extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
+ struct rt_mutex_waiter *waiter);
+
+extern int rt_mutex_futex_trylock(struct rt_mutex *l);
+
+extern void rt_mutex_futex_unlock(struct rt_mutex *lock);
+extern bool __rt_mutex_futex_unlock(struct rt_mutex *lock,
+ struct wake_q_head *wqh);
+
+extern void rt_mutex_postunlock(struct wake_q_head *wake_q);
#ifdef CONFIG_DEBUG_RT_MUTEXES
# include "rtmutex-debug.h"
*/
void downgrade_write(struct rw_semaphore *sem)
{
- /*
- * lockdep: a downgraded write will live on as a write
- * dependency.
- */
+ lock_downgrade(&sem->dep_map, _RET_IP_);
+
rwsem_set_reader_owned(sem);
__downgrade_write(sem);
}
struct stress {
struct work_struct work;
struct ww_mutex *locks;
+ unsigned long timeout;
int nlocks;
- int nloops;
};
static int *get_random_order(int count)
if (!order)
return;
- ww_acquire_init(&ctx, &ww_class);
-
do {
int contended = -1;
int n, err;
+ ww_acquire_init(&ctx, &ww_class);
retry:
err = 0;
for (n = 0; n < nlocks; n++) {
__func__, err);
break;
}
- } while (--stress->nloops);
- ww_acquire_fini(&ctx);
+ ww_acquire_fini(&ctx);
+ } while (!time_after(jiffies, stress->timeout));
kfree(order);
kfree(stress);
kfree(order);
order = NULL;
- ww_acquire_init(&ctx, &ww_class);
-
do {
+ ww_acquire_init(&ctx, &ww_class);
+
list_for_each_entry(ll, &locks, link) {
err = ww_mutex_lock(ll->lock, &ctx);
if (!err)
dummy_load(stress);
list_for_each_entry(ll, &locks, link)
ww_mutex_unlock(ll->lock);
- } while (--stress->nloops);
- ww_acquire_fini(&ctx);
+ ww_acquire_fini(&ctx);
+ } while (!time_after(jiffies, stress->timeout));
out:
list_for_each_entry_safe(ll, ln, &locks, link)
__func__, err);
break;
}
- } while (--stress->nloops);
+ } while (!time_after(jiffies, stress->timeout));
kfree(stress);
}
#define STRESS_ONE BIT(2)
#define STRESS_ALL (STRESS_INORDER | STRESS_REORDER | STRESS_ONE)
-static int stress(int nlocks, int nthreads, int nloops, unsigned int flags)
+static int stress(int nlocks, int nthreads, unsigned int flags)
{
struct ww_mutex *locks;
int n;
INIT_WORK(&stress->work, fn);
stress->locks = locks;
stress->nlocks = nlocks;
- stress->nloops = nloops;
+ stress->timeout = jiffies + 2*HZ;
queue_work(wq, &stress->work);
nthreads--;
if (ret)
return ret;
- ret = stress(16, 2*ncpus, 1<<10, STRESS_INORDER);
+ ret = stress(16, 2*ncpus, STRESS_INORDER);
if (ret)
return ret;
- ret = stress(16, 2*ncpus, 1<<10, STRESS_REORDER);
+ ret = stress(16, 2*ncpus, STRESS_REORDER);
if (ret)
return ret;
- ret = stress(4095, hweight32(STRESS_ALL)*ncpus, 1<<12, STRESS_ALL);
+ ret = stress(4095, hweight32(STRESS_ALL)*ncpus, STRESS_ALL);
if (ret)
return ret;
memcpy(per_cpu_ptr(mod->percpu, cpu), from, size);
}
-/**
- * is_module_percpu_address - test whether address is from module static percpu
- * @addr: address to test
- *
- * Test whether @addr belongs to module static percpu area.
- *
- * RETURNS:
- * %true if @addr is from module static percpu area
- */
-bool is_module_percpu_address(unsigned long addr)
+bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr)
{
struct module *mod;
unsigned int cpu;
continue;
for_each_possible_cpu(cpu) {
void *start = per_cpu_ptr(mod->percpu, cpu);
-
- if ((void *)addr >= start &&
- (void *)addr < start + mod->percpu_size) {
+ void *va = (void *)addr;
+
+ if (va >= start && va < start + mod->percpu_size) {
+ if (can_addr) {
+ *can_addr = (unsigned long) (va - start);
+ *can_addr += (unsigned long)
+ per_cpu_ptr(mod->percpu,
+ get_boot_cpu_id());
+ }
preempt_enable();
return true;
}
return false;
}
+/**
+ * is_module_percpu_address - test whether address is from module static percpu
+ * @addr: address to test
+ *
+ * Test whether @addr belongs to module static percpu area.
+ *
+ * RETURNS:
+ * %true if @addr is from module static percpu area
+ */
+bool is_module_percpu_address(unsigned long addr)
+{
+ return __is_module_percpu_address(addr, NULL);
+}
+
#else /* ... !CONFIG_SMP */
static inline void __percpu *mod_percpu(struct module *mod)
return false;
}
+bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr)
+{
+ return false;
+}
+
#endif /* CONFIG_SMP */
#define MODINFO_ATTR(field) \
#include <linux/file.h>
#include <linux/syscalls.h>
#include <linux/cgroup.h>
+#include <linux/perf_event.h>
static struct kmem_cache *nsproxy_cachep;
goto out;
}
switch_task_namespaces(tsk, new_nsproxy);
+
+ perf_event_namespaces(tsk);
out:
fput(file);
return err;
return -ENOENT;
}
-/* You can use " around spaces, but can't escape ". */
-/* Hyphens and underscores equivalent in parameter names. */
-static char *next_arg(char *args, char **param, char **val)
-{
- unsigned int i, equals = 0;
- int in_quote = 0, quoted = 0;
- char *next;
-
- if (*args == '"') {
- args++;
- in_quote = 1;
- quoted = 1;
- }
-
- for (i = 0; args[i]; i++) {
- if (isspace(args[i]) && !in_quote)
- break;
- if (equals == 0) {
- if (args[i] == '=')
- equals = i;
- }
- if (args[i] == '"')
- in_quote = !in_quote;
- }
-
- *param = args;
- if (!equals)
- *val = NULL;
- else {
- args[equals] = '\0';
- *val = args + equals + 1;
-
- /* Don't include quotes in value. */
- if (**val == '"') {
- (*val)++;
- if (args[i-1] == '"')
- args[i-1] = '\0';
- }
- }
- if (quoted && args[i-1] == '"')
- args[i-1] = '\0';
-
- if (args[i]) {
- args[i] = '\0';
- next = args + i + 1;
- } else
- next = args + i;
-
- /* Chew up trailing spaces. */
- return skip_spaces(next);
-}
-
/* Args looks like "foo=bar,bar2 baz=fuz wiz". */
char *parse_args(const char *doing,
char *args,
WARN_ON(!task->ptrace || task->parent != current);
+ /*
+ * PTRACE_LISTEN can allow ptrace_trap_notify to wake us up remotely.
+ * Recheck state under the lock to close this race.
+ */
spin_lock_irq(&task->sighand->siglock);
- if (__fatal_signal_pending(task))
- wake_up_state(task, __TASK_TRACED);
- else
- task->state = TASK_TRACED;
+ if (task->state == __TASK_TRACED) {
+ if (__fatal_signal_pending(task))
+ wake_up_state(task, __TASK_TRACED);
+ else
+ task->state = TASK_TRACED;
+ }
spin_unlock_irq(&task->sighand->siglock);
}
cpumask_var_t cpu_isolated_map;
/*
- * this_rq_lock - lock this runqueue and disable interrupts.
- */
-static struct rq *this_rq_lock(void)
- __acquires(rq->lock)
-{
- struct rq *rq;
-
- local_irq_disable();
- rq = this_rq();
- raw_spin_lock(&rq->lock);
-
- return rq;
-}
-
-/*
* __task_rq_lock - lock the rq @p resides on.
*/
struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
return;
#ifdef CONFIG_SCHED_DEBUG
+ if (sched_feat(WARN_DOUBLE_CLOCK))
+ SCHED_WARN_ON(rq->clock_update_flags & RQCF_UPDATED);
rq->clock_update_flags |= RQCF_UPDATED;
#endif
+
delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
if (delta < 0)
return;
static enum hrtimer_restart hrtick(struct hrtimer *timer)
{
struct rq *rq = container_of(timer, struct rq, hrtick_timer);
+ struct rq_flags rf;
WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
- raw_spin_lock(&rq->lock);
+ rq_lock(rq, &rf);
update_rq_clock(rq);
rq->curr->sched_class->task_tick(rq, rq->curr, 1);
- raw_spin_unlock(&rq->lock);
+ rq_unlock(rq, &rf);
return HRTIMER_NORESTART;
}
static void __hrtick_start(void *arg)
{
struct rq *rq = arg;
+ struct rq_flags rf;
- raw_spin_lock(&rq->lock);
+ rq_lock(rq, &rf);
__hrtick_restart(rq);
rq->hrtick_csd_pending = 0;
- raw_spin_unlock(&rq->lock);
+ rq_unlock(rq, &rf);
}
/*
static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
{
- update_rq_clock(rq);
+ if (!(flags & ENQUEUE_NOCLOCK))
+ update_rq_clock(rq);
+
if (!(flags & ENQUEUE_RESTORE))
sched_info_queued(rq, p);
+
p->sched_class->enqueue_task(rq, p, flags);
}
static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
{
- update_rq_clock(rq);
+ if (!(flags & DEQUEUE_NOCLOCK))
+ update_rq_clock(rq);
+
if (!(flags & DEQUEUE_SAVE))
sched_info_dequeued(rq, p);
+
p->sched_class->dequeue_task(rq, p, flags);
}
*
* Returns (locked) new rq. Old rq's lock is released.
*/
-static struct rq *move_queued_task(struct rq *rq, struct task_struct *p, int new_cpu)
+static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
+ struct task_struct *p, int new_cpu)
{
lockdep_assert_held(&rq->lock);
p->on_rq = TASK_ON_RQ_MIGRATING;
- dequeue_task(rq, p, 0);
+ dequeue_task(rq, p, DEQUEUE_NOCLOCK);
set_task_cpu(p, new_cpu);
- raw_spin_unlock(&rq->lock);
+ rq_unlock(rq, rf);
rq = cpu_rq(new_cpu);
- raw_spin_lock(&rq->lock);
+ rq_lock(rq, rf);
BUG_ON(task_cpu(p) != new_cpu);
enqueue_task(rq, p, 0);
p->on_rq = TASK_ON_RQ_QUEUED;
* So we race with normal scheduler movements, but that's OK, as long
* as the task is no longer on this CPU.
*/
-static struct rq *__migrate_task(struct rq *rq, struct task_struct *p, int dest_cpu)
+static struct rq *__migrate_task(struct rq *rq, struct rq_flags *rf,
+ struct task_struct *p, int dest_cpu)
{
if (unlikely(!cpu_active(dest_cpu)))
return rq;
if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
return rq;
- rq = move_queued_task(rq, p, dest_cpu);
+ update_rq_clock(rq);
+ rq = move_queued_task(rq, rf, p, dest_cpu);
return rq;
}
struct migration_arg *arg = data;
struct task_struct *p = arg->task;
struct rq *rq = this_rq();
+ struct rq_flags rf;
/*
* The original target CPU might have gone down and we might
sched_ttwu_pending();
raw_spin_lock(&p->pi_lock);
- raw_spin_lock(&rq->lock);
+ rq_lock(rq, &rf);
/*
* If task_rq(p) != rq, it cannot be migrated here, because we're
* holding rq->lock, if p->on_rq == 0 it cannot get enqueued because
*/
if (task_rq(p) == rq) {
if (task_on_rq_queued(p))
- rq = __migrate_task(rq, p, arg->dest_cpu);
+ rq = __migrate_task(rq, &rf, p, arg->dest_cpu);
else
p->wake_cpu = arg->dest_cpu;
}
- raw_spin_unlock(&rq->lock);
+ rq_unlock(rq, &rf);
raw_spin_unlock(&p->pi_lock);
local_irq_enable();
* holding rq->lock.
*/
lockdep_assert_held(&rq->lock);
- dequeue_task(rq, p, DEQUEUE_SAVE);
+ dequeue_task(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK);
}
if (running)
put_prev_task(rq, p);
p->sched_class->set_cpus_allowed(p, new_mask);
if (queued)
- enqueue_task(rq, p, ENQUEUE_RESTORE);
+ enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
if (running)
set_curr_task(rq, p);
}
* OK, since we're going to drop the lock immediately
* afterwards anyway.
*/
- rq_unpin_lock(rq, &rf);
- rq = move_queued_task(rq, p, dest_cpu);
- rq_repin_lock(rq, &rf);
+ rq = move_queued_task(rq, &rf, p, dest_cpu);
}
out:
task_rq_unlock(rq, p, &rf);
{
if (task_on_rq_queued(p)) {
struct rq *src_rq, *dst_rq;
+ struct rq_flags srf, drf;
src_rq = task_rq(p);
dst_rq = cpu_rq(cpu);
+ rq_pin_lock(src_rq, &srf);
+ rq_pin_lock(dst_rq, &drf);
+
p->on_rq = TASK_ON_RQ_MIGRATING;
deactivate_task(src_rq, p, 0);
set_task_cpu(p, cpu);
activate_task(dst_rq, p, 0);
p->on_rq = TASK_ON_RQ_QUEUED;
check_preempt_curr(dst_rq, p, 0);
+
+ rq_unpin_lock(dst_rq, &drf);
+ rq_unpin_lock(src_rq, &srf);
+
} else {
/*
* Task isn't running anymore; make it appear like we migrated
ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
struct rq_flags *rf)
{
- int en_flags = ENQUEUE_WAKEUP;
+ int en_flags = ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK;
lockdep_assert_held(&rq->lock);
struct rq *rq = this_rq();
struct llist_node *llist = llist_del_all(&rq->wake_list);
struct task_struct *p;
- unsigned long flags;
struct rq_flags rf;
if (!llist)
return;
- raw_spin_lock_irqsave(&rq->lock, flags);
- rq_pin_lock(rq, &rf);
+ rq_lock_irqsave(rq, &rf);
+ update_rq_clock(rq);
while (llist) {
int wake_flags = 0;
ttwu_do_activate(rq, p, wake_flags, &rf);
}
- rq_unpin_lock(rq, &rf);
- raw_spin_unlock_irqrestore(&rq->lock, flags);
+ rq_unlock_irqrestore(rq, &rf);
}
void scheduler_ipi(void)
void wake_up_if_idle(int cpu)
{
struct rq *rq = cpu_rq(cpu);
- unsigned long flags;
+ struct rq_flags rf;
rcu_read_lock();
if (set_nr_if_polling(rq->idle)) {
trace_sched_wake_idle_without_ipi(cpu);
} else {
- raw_spin_lock_irqsave(&rq->lock, flags);
+ rq_lock_irqsave(rq, &rf);
if (is_idle_task(rq->curr))
smp_send_reschedule(cpu);
/* Else CPU is not idle, do nothing here: */
- raw_spin_unlock_irqrestore(&rq->lock, flags);
+ rq_unlock_irqrestore(rq, &rf);
}
out:
}
#endif
- raw_spin_lock(&rq->lock);
- rq_pin_lock(rq, &rf);
+ rq_lock(rq, &rf);
+ update_rq_clock(rq);
ttwu_do_activate(rq, p, wake_flags, &rf);
- rq_unpin_lock(rq, &rf);
- raw_spin_unlock(&rq->lock);
+ rq_unlock(rq, &rf);
}
/*
* disabled avoiding further scheduler activity on it and we've
* not yet picked a replacement task.
*/
- rq_unpin_lock(rq, rf);
- raw_spin_unlock(&rq->lock);
+ rq_unlock(rq, rf);
raw_spin_lock(&p->pi_lock);
- raw_spin_lock(&rq->lock);
- rq_repin_lock(rq, rf);
+ rq_relock(rq, rf);
}
if (!(p->state & TASK_NORMAL))
delayacct_blkio_end();
atomic_dec(&rq->nr_iowait);
}
- ttwu_activate(rq, p, ENQUEUE_WAKEUP);
+ ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK);
}
ttwu_do_wakeup(rq, p, 0, rf);
update_rq_clock(rq);
post_init_entity_util_avg(&p->se);
- activate_task(rq, p, 0);
+ activate_task(rq, p, ENQUEUE_NOCLOCK);
p->on_rq = TASK_ON_RQ_QUEUED;
trace_sched_wakeup_new(p);
check_preempt_curr(rq, p, WF_FORK);
int cpu = smp_processor_id();
struct rq *rq = cpu_rq(cpu);
struct task_struct *curr = rq->curr;
+ struct rq_flags rf;
sched_clock_tick();
- raw_spin_lock(&rq->lock);
+ rq_lock(rq, &rf);
+
update_rq_clock(rq);
curr->sched_class->task_tick(rq, curr, 0);
cpu_load_update_active(rq);
calc_global_load_tick(rq);
- raw_spin_unlock(&rq->lock);
+
+ rq_unlock(rq, &rf);
perf_event_task_tick();
* done by the caller to avoid the race with signal_wake_up().
*/
smp_mb__before_spinlock();
- raw_spin_lock(&rq->lock);
- rq_pin_lock(rq, &rf);
+ rq_lock(rq, &rf);
/* Promote REQ to ACT */
rq->clock_update_flags <<= 1;
+ update_rq_clock(rq);
switch_count = &prev->nivcsw;
if (!preempt && prev->state) {
if (unlikely(signal_pending_state(prev->state, prev))) {
prev->state = TASK_RUNNING;
} else {
- deactivate_task(rq, prev, DEQUEUE_SLEEP);
+ deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);
prev->on_rq = 0;
if (prev->in_iowait) {
switch_count = &prev->nvcsw;
}
- if (task_on_rq_queued(prev))
- update_rq_clock(rq);
-
next = pick_next_task(rq, prev, &rf);
clear_tsk_need_resched(prev);
clear_preempt_need_resched();
rq = context_switch(rq, prev, next, &rf);
} else {
rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
- rq_unpin_lock(rq, &rf);
- raw_spin_unlock_irq(&rq->lock);
+ rq_unlock_irq(rq, &rf);
}
balance_callback(rq);
#ifdef CONFIG_RT_MUTEXES
+static inline int __rt_effective_prio(struct task_struct *pi_task, int prio)
+{
+ if (pi_task)
+ prio = min(prio, pi_task->prio);
+
+ return prio;
+}
+
+static inline int rt_effective_prio(struct task_struct *p, int prio)
+{
+ struct task_struct *pi_task = rt_mutex_get_top_task(p);
+
+ return __rt_effective_prio(pi_task, prio);
+}
+
/*
* rt_mutex_setprio - set the current priority of a task
- * @p: task
- * @prio: prio value (kernel-internal form)
+ * @p: task to boost
+ * @pi_task: donor task
*
* This function changes the 'effective' priority of a task. It does
* not touch ->normal_prio like __setscheduler().
* Used by the rt_mutex code to implement priority inheritance
* logic. Call site only calls if the priority of the task changed.
*/
-void rt_mutex_setprio(struct task_struct *p, int prio)
+void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
{
- int oldprio, queued, running, queue_flag = DEQUEUE_SAVE | DEQUEUE_MOVE;
+ int prio, oldprio, queued, running, queue_flag =
+ DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
const struct sched_class *prev_class;
struct rq_flags rf;
struct rq *rq;
- BUG_ON(prio > MAX_PRIO);
+ /* XXX used to be waiter->prio, not waiter->task->prio */
+ prio = __rt_effective_prio(pi_task, p->normal_prio);
+
+ /*
+ * If nothing changed; bail early.
+ */
+ if (p->pi_top_task == pi_task && prio == p->prio && !dl_prio(prio))
+ return;
rq = __task_rq_lock(p, &rf);
update_rq_clock(rq);
+ /*
+ * Set under pi_lock && rq->lock, such that the value can be used under
+ * either lock.
+ *
+ * Note that there is loads of tricky to make this pointer cache work
+ * right. rt_mutex_slowunlock()+rt_mutex_postunlock() work together to
+ * ensure a task is de-boosted (pi_task is set to NULL) before the
+ * task is allowed to run again (and can exit). This ensures the pointer
+ * points to a blocked task -- which guaratees the task is present.
+ */
+ p->pi_top_task = pi_task;
+
+ /*
+ * For FIFO/RR we only need to set prio, if that matches we're done.
+ */
+ if (prio == p->prio && !dl_prio(prio))
+ goto out_unlock;
/*
* Idle task boosting is a nono in general. There is one
goto out_unlock;
}
- trace_sched_pi_setprio(p, prio);
+ trace_sched_pi_setprio(p, pi_task);
oldprio = p->prio;
if (oldprio == prio)
* running task
*/
if (dl_prio(prio)) {
- struct task_struct *pi_task = rt_mutex_get_top_task(p);
if (!dl_prio(p->normal_prio) ||
(pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) {
p->dl.dl_boosted = 1;
balance_callback(rq);
preempt_enable();
}
+#else
+static inline int rt_effective_prio(struct task_struct *p, int prio)
+{
+ return prio;
+}
#endif
void set_user_nice(struct task_struct *p, long nice)
queued = task_on_rq_queued(p);
running = task_current(rq, p);
if (queued)
- dequeue_task(rq, p, DEQUEUE_SAVE);
+ dequeue_task(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK);
if (running)
put_prev_task(rq, p);
delta = p->prio - old_prio;
if (queued) {
- enqueue_task(rq, p, ENQUEUE_RESTORE);
+ enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
/*
* If the task increased its priority or is running and
* lowered its priority, then reschedule its CPU:
* Keep a potential priority boosting if called from
* sched_setscheduler().
*/
+ p->prio = normal_prio(p);
if (keep_boost)
- p->prio = rt_mutex_get_effective_prio(p, normal_prio(p));
- else
- p->prio = normal_prio(p);
+ p->prio = rt_effective_prio(p, p->prio);
if (dl_prio(p->prio))
p->sched_class = &dl_sched_class;
const struct sched_class *prev_class;
struct rq_flags rf;
int reset_on_fork;
- int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE;
+ int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
struct rq *rq;
/* May grab non-irq protected spin_locks: */
* the runqueue. This will be done when the task deboost
* itself.
*/
- new_effective_prio = rt_mutex_get_effective_prio(p, newprio);
+ new_effective_prio = rt_effective_prio(p, newprio);
if (new_effective_prio == oldprio)
queue_flags &= ~DEQUEUE_MOVE;
}
*/
SYSCALL_DEFINE0(sched_yield)
{
- struct rq *rq = this_rq_lock();
+ struct rq_flags rf;
+ struct rq *rq;
+
+ local_irq_disable();
+ rq = this_rq();
+ rq_lock(rq, &rf);
schedstat_inc(rq->yld_count);
current->sched_class->yield_task(rq);
* Since we are going to call schedule() anyway, there's
* no need to preempt or enable interrupts:
*/
- __release(rq->lock);
- spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
- do_raw_spin_unlock(&rq->lock);
+ preempt_disable();
+ rq_unlock(rq, &rf);
sched_preempt_enable_no_resched();
schedule();
p->numa_preferred_nid = nid;
if (queued)
- enqueue_task(rq, p, ENQUEUE_RESTORE);
+ enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
if (running)
set_curr_task(rq, p);
task_rq_unlock(rq, p, &rf);
* there's no concurrency possible, we hold the required locks anyway
* because of lock validation efforts.
*/
-static void migrate_tasks(struct rq *dead_rq)
+static void migrate_tasks(struct rq *dead_rq, struct rq_flags *rf)
{
struct rq *rq = dead_rq;
struct task_struct *next, *stop = rq->stop;
- struct rq_flags rf;
+ struct rq_flags orf = *rf;
int dest_cpu;
/*
* class method both need to have an up-to-date
* value of rq->clock[_task]
*/
- rq_pin_lock(rq, &rf);
update_rq_clock(rq);
- rq_unpin_lock(rq, &rf);
for (;;) {
/*
/*
* pick_next_task() assumes pinned rq->lock:
*/
- rq_repin_lock(rq, &rf);
- next = pick_next_task(rq, &fake_task, &rf);
+ next = pick_next_task(rq, &fake_task, rf);
BUG_ON(!next);
next->sched_class->put_prev_task(rq, next);
* because !cpu_active at this point, which means load-balance
* will not interfere. Also, stop-machine.
*/
- rq_unpin_lock(rq, &rf);
- raw_spin_unlock(&rq->lock);
+ rq_unlock(rq, rf);
raw_spin_lock(&next->pi_lock);
- raw_spin_lock(&rq->lock);
+ rq_relock(rq, rf);
/*
* Since we're inside stop-machine, _nothing_ should have
/* Find suitable destination for @next, with force if needed. */
dest_cpu = select_fallback_rq(dead_rq->cpu, next);
-
- rq = __migrate_task(rq, next, dest_cpu);
+ rq = __migrate_task(rq, rf, next, dest_cpu);
if (rq != dead_rq) {
- raw_spin_unlock(&rq->lock);
+ rq_unlock(rq, rf);
rq = dead_rq;
- raw_spin_lock(&rq->lock);
+ *rf = orf;
+ rq_relock(rq, rf);
}
raw_spin_unlock(&next->pi_lock);
}
* cpuset configurations.
*/
}
- cpuset_update_active_cpus(true);
+ cpuset_update_active_cpus();
}
static int cpuset_cpu_inactive(unsigned int cpu)
if (overflow)
return -EBUSY;
- cpuset_update_active_cpus(false);
+ cpuset_update_active_cpus();
} else {
num_cpus_frozen++;
partition_sched_domains(1, NULL, NULL);
int sched_cpu_activate(unsigned int cpu)
{
struct rq *rq = cpu_rq(cpu);
- unsigned long flags;
+ struct rq_flags rf;
set_cpu_active(cpu, true);
* 2) At runtime, if cpuset_cpu_active() fails to rebuild the
* domains.
*/
- raw_spin_lock_irqsave(&rq->lock, flags);
+ rq_lock_irqsave(rq, &rf);
if (rq->rd) {
BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
set_rq_online(rq);
}
- raw_spin_unlock_irqrestore(&rq->lock, flags);
+ rq_unlock_irqrestore(rq, &rf);
update_max_interval();
int sched_cpu_dying(unsigned int cpu)
{
struct rq *rq = cpu_rq(cpu);
- unsigned long flags;
+ struct rq_flags rf;
/* Handle pending wakeups and then migrate everything off */
sched_ttwu_pending();
- raw_spin_lock_irqsave(&rq->lock, flags);
+
+ rq_lock_irqsave(rq, &rf);
if (rq->rd) {
BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
set_rq_offline(rq);
}
- migrate_tasks(rq);
+ migrate_tasks(rq, &rf);
BUG_ON(rq->nr_running != 1);
- raw_spin_unlock_irqrestore(&rq->lock, flags);
+ rq_unlock_irqrestore(rq, &rf);
+
calc_load_migrate(rq);
update_max_interval();
nohz_balance_exit_idle(cpu);
*/
void sched_move_task(struct task_struct *tsk)
{
- int queued, running;
+ int queued, running, queue_flags =
+ DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
struct rq_flags rf;
struct rq *rq;
queued = task_on_rq_queued(tsk);
if (queued)
- dequeue_task(rq, tsk, DEQUEUE_SAVE | DEQUEUE_MOVE);
+ dequeue_task(rq, tsk, queue_flags);
if (running)
put_prev_task(rq, tsk);
sched_change_group(tsk, TASK_MOVE_GROUP);
if (queued)
- enqueue_task(rq, tsk, ENQUEUE_RESTORE | ENQUEUE_MOVE);
+ enqueue_task(rq, tsk, queue_flags);
if (running)
set_curr_task(rq, tsk);
for_each_online_cpu(i) {
struct cfs_rq *cfs_rq = tg->cfs_rq[i];
struct rq *rq = cfs_rq->rq;
+ struct rq_flags rf;
- raw_spin_lock_irq(&rq->lock);
+ rq_lock_irq(rq, &rf);
cfs_rq->runtime_enabled = runtime_enabled;
cfs_rq->runtime_remaining = 0;
if (cfs_rq->throttled)
unthrottle_cfs_rq(cfs_rq);
- raw_spin_unlock_irq(&rq->lock);
+ rq_unlock_irq(rq, &rf);
}
if (runtime_was_enabled && !runtime_enabled)
cfs_bandwidth_usage_dec();
unsigned long util;
unsigned long max;
unsigned int flags;
+
+ /* The field below is for single-CPU policies only. */
+#ifdef CONFIG_NO_HZ_COMMON
+ unsigned long saved_idle_calls;
+#endif
};
static DEFINE_PER_CPU(struct sugov_cpu, sugov_cpu);
{
struct cpufreq_policy *policy = sg_policy->policy;
+ if (sg_policy->next_freq == next_freq)
+ return;
+
+ if (sg_policy->next_freq > next_freq)
+ next_freq = (sg_policy->next_freq + next_freq) >> 1;
+
+ sg_policy->next_freq = next_freq;
sg_policy->last_freq_update_time = time;
if (policy->fast_switch_enabled) {
- if (sg_policy->next_freq == next_freq) {
- trace_cpu_frequency(policy->cur, smp_processor_id());
- return;
- }
- sg_policy->next_freq = next_freq;
next_freq = cpufreq_driver_fast_switch(policy, next_freq);
if (next_freq == CPUFREQ_ENTRY_INVALID)
return;
policy->cur = next_freq;
trace_cpu_frequency(next_freq, smp_processor_id());
- } else if (sg_policy->next_freq != next_freq) {
- sg_policy->next_freq = next_freq;
+ } else {
sg_policy->work_in_progress = true;
irq_work_queue(&sg_policy->irq_work);
}
sg_cpu->iowait_boost >>= 1;
}
+#ifdef CONFIG_NO_HZ_COMMON
+static bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu)
+{
+ unsigned long idle_calls = tick_nohz_get_idle_calls();
+ bool ret = idle_calls == sg_cpu->saved_idle_calls;
+
+ sg_cpu->saved_idle_calls = idle_calls;
+ return ret;
+}
+#else
+static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
+#endif /* CONFIG_NO_HZ_COMMON */
+
static void sugov_update_single(struct update_util_data *hook, u64 time,
unsigned int flags)
{
struct cpufreq_policy *policy = sg_policy->policy;
unsigned long util, max;
unsigned int next_f;
+ bool busy;
sugov_set_iowait_boost(sg_cpu, time, flags);
sg_cpu->last_update = time;
if (!sugov_should_update_freq(sg_policy, time))
return;
+ busy = sugov_cpu_is_busy(sg_cpu);
+
if (flags & SCHED_CPUFREQ_RT_DL) {
next_f = policy->cpuinfo.max_freq;
} else {
sugov_get_util(&util, &max);
sugov_iowait_boost(sg_cpu, &util, &max);
next_f = get_next_freq(sg_policy, util, max);
+ /*
+ * Do not reduce the frequency if the CPU has not been idle
+ * recently, as the reduction is likely to be premature then.
+ */
+ if (busy && next_f < sg_policy->next_freq)
+ next_f = sg_policy->next_freq;
}
sugov_update_commit(sg_policy, time, next_f);
}
-static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu,
- unsigned long util, unsigned long max,
- unsigned int flags)
+static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu)
{
struct sugov_policy *sg_policy = sg_cpu->sg_policy;
struct cpufreq_policy *policy = sg_policy->policy;
- unsigned int max_f = policy->cpuinfo.max_freq;
u64 last_freq_update_time = sg_policy->last_freq_update_time;
+ unsigned long util = 0, max = 1;
unsigned int j;
- if (flags & SCHED_CPUFREQ_RT_DL)
- return max_f;
-
- sugov_iowait_boost(sg_cpu, &util, &max);
-
for_each_cpu(j, policy->cpus) {
- struct sugov_cpu *j_sg_cpu;
+ struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j);
unsigned long j_util, j_max;
s64 delta_ns;
- if (j == smp_processor_id())
- continue;
-
- j_sg_cpu = &per_cpu(sugov_cpu, j);
/*
* If the CPU utilization was last updated before the previous
* frequency update and the time elapsed between the last update
continue;
}
if (j_sg_cpu->flags & SCHED_CPUFREQ_RT_DL)
- return max_f;
+ return policy->cpuinfo.max_freq;
j_util = j_sg_cpu->util;
j_max = j_sg_cpu->max;
sg_cpu->last_update = time;
if (sugov_should_update_freq(sg_policy, time)) {
- next_f = sugov_next_freq_shared(sg_cpu, util, max, flags);
+ if (flags & SCHED_CPUFREQ_RT_DL)
+ next_f = sg_policy->policy->cpuinfo.max_freq;
+ else
+ next_f = sugov_next_freq_shared(sg_cpu);
+
sugov_update_commit(sg_policy, time, next_f);
}
{
struct sugov_policy *sg_policy;
struct sugov_tunables *tunables;
- unsigned int lat;
int ret = 0;
/* State should be equivalent to EXIT */
goto stop_kthread;
}
- tunables->rate_limit_us = LATENCY_MULTIPLIER;
- lat = policy->cpuinfo.transition_latency / NSEC_PER_USEC;
- if (lat)
- tunables->rate_limit_us *= lat;
+ if (policy->transition_delay_us) {
+ tunables->rate_limit_us = policy->transition_delay_us;
+ } else {
+ unsigned int lat;
+
+ tunables->rate_limit_us = LATENCY_MULTIPLIER;
+ lat = policy->cpuinfo.transition_latency / NSEC_PER_USEC;
+ if (lat)
+ tunables->rate_limit_us *= lat;
+ }
policy->governor_data = sg_policy;
sg_policy->tunables = tunables;
sched_clock_irqtime = 0;
}
+static void irqtime_account_delta(struct irqtime *irqtime, u64 delta,
+ enum cpu_usage_stat idx)
+{
+ u64 *cpustat = kcpustat_this_cpu->cpustat;
+
+ u64_stats_update_begin(&irqtime->sync);
+ cpustat[idx] += delta;
+ irqtime->total += delta;
+ irqtime->tick_delta += delta;
+ u64_stats_update_end(&irqtime->sync);
+}
+
/*
* Called before incrementing preempt_count on {soft,}irq_enter
* and before decrementing preempt_count on {soft,}irq_exit.
void irqtime_account_irq(struct task_struct *curr)
{
struct irqtime *irqtime = this_cpu_ptr(&cpu_irqtime);
- u64 *cpustat = kcpustat_this_cpu->cpustat;
s64 delta;
int cpu;
delta = sched_clock_cpu(cpu) - irqtime->irq_start_time;
irqtime->irq_start_time += delta;
- u64_stats_update_begin(&irqtime->sync);
/*
* We do not account for softirq time from ksoftirqd here.
* We want to continue accounting softirq time to ksoftirqd thread
* in that case, so as not to confuse scheduler with a special task
* that do not consume any time, but still wants to run.
*/
- if (hardirq_count()) {
- cpustat[CPUTIME_IRQ] += delta;
- irqtime->tick_delta += delta;
- } else if (in_serving_softirq() && curr != this_cpu_ksoftirqd()) {
- cpustat[CPUTIME_SOFTIRQ] += delta;
- irqtime->tick_delta += delta;
- }
-
- u64_stats_update_end(&irqtime->sync);
+ if (hardirq_count())
+ irqtime_account_delta(irqtime, delta, CPUTIME_IRQ);
+ else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
+ irqtime_account_delta(irqtime, delta, CPUTIME_SOFTIRQ);
}
EXPORT_SYMBOL_GPL(irqtime_account_irq);
}
#ifdef CONFIG_SMP
+
+#include "sched-pelt.h"
+
static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu);
static unsigned long task_h_load(struct task_struct *p);
-/*
- * We choose a half-life close to 1 scheduling period.
- * Note: The tables runnable_avg_yN_inv and runnable_avg_yN_sum are
- * dependent on this value.
- */
-#define LOAD_AVG_PERIOD 32
-#define LOAD_AVG_MAX 47742 /* maximum possible load avg */
-#define LOAD_AVG_MAX_N 345 /* number of full periods to produce LOAD_AVG_MAX */
-
/* Give new sched_entity start runnable values to heavy its load in infant time */
void init_entity_runnable_average(struct sched_entity *se)
{
#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_SMP
-/* Precomputed fixed inverse multiplies for multiplication by y^n */
-static const u32 runnable_avg_yN_inv[] = {
- 0xffffffff, 0xfa83b2da, 0xf5257d14, 0xefe4b99a, 0xeac0c6e6, 0xe5b906e6,
- 0xe0ccdeeb, 0xdbfbb796, 0xd744fcc9, 0xd2a81d91, 0xce248c14, 0xc9b9bd85,
- 0xc5672a10, 0xc12c4cc9, 0xbd08a39e, 0xb8fbaf46, 0xb504f333, 0xb123f581,
- 0xad583ee9, 0xa9a15ab4, 0xa5fed6a9, 0xa2704302, 0x9ef5325f, 0x9b8d39b9,
- 0x9837f050, 0x94f4efa8, 0x91c3d373, 0x8ea4398a, 0x8b95c1e3, 0x88980e80,
- 0x85aac367, 0x82cd8698,
-};
-
-/*
- * Precomputed \Sum y^k { 1<=k<=n }. These are floor(true_value) to prevent
- * over-estimates when re-combining.
- */
-static const u32 runnable_avg_yN_sum[] = {
- 0, 1002, 1982, 2941, 3880, 4798, 5697, 6576, 7437, 8279, 9103,
- 9909,10698,11470,12226,12966,13690,14398,15091,15769,16433,17082,
- 17718,18340,18949,19545,20128,20698,21256,21802,22336,22859,23371,
-};
-
-/*
- * Precomputed \Sum y^k { 1<=k<=n, where n%32=0). Values are rolled down to
- * lower integers. See Documentation/scheduler/sched-avg.txt how these
- * were generated:
- */
-static const u32 __accumulated_sum_N32[] = {
- 0, 23371, 35056, 40899, 43820, 45281,
- 46011, 46376, 46559, 46650, 46696, 46719,
-};
-
/*
* Approximate:
* val * y^n, where y^32 ~= 0.5 (~1 scheduling period)
*/
-static __always_inline u64 decay_load(u64 val, u64 n)
+static u64 decay_load(u64 val, u64 n)
{
unsigned int local_n;
- if (!n)
- return val;
- else if (unlikely(n > LOAD_AVG_PERIOD * 63))
+ if (unlikely(n > LOAD_AVG_PERIOD * 63))
return 0;
/* after bounds checking we can collapse to 32-bit */
return val;
}
+static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3)
+{
+ u32 c1, c2, c3 = d3; /* y^0 == 1 */
+
+ /*
+ * c1 = d1 y^p
+ */
+ c1 = decay_load((u64)d1, periods);
+
+ /*
+ * p-1
+ * c2 = 1024 \Sum y^n
+ * n=1
+ *
+ * inf inf
+ * = 1024 ( \Sum y^n - \Sum y^n - y^0 )
+ * n=0 n=p
+ */
+ c2 = LOAD_AVG_MAX - decay_load(LOAD_AVG_MAX, periods) - 1024;
+
+ return c1 + c2 + c3;
+}
+
+#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
+
/*
- * For updates fully spanning n periods, the contribution to runnable
- * average will be: \Sum 1024*y^n
+ * Accumulate the three separate parts of the sum; d1 the remainder
+ * of the last (incomplete) period, d2 the span of full periods and d3
+ * the remainder of the (incomplete) current period.
+ *
+ * d1 d2 d3
+ * ^ ^ ^
+ * | | |
+ * |<->|<----------------->|<--->|
+ * ... |---x---|------| ... |------|-----x (now)
+ *
+ * p-1
+ * u' = (u + d1) y^p + 1024 \Sum y^n + d3 y^0
+ * n=1
*
- * We can compute this reasonably efficiently by combining:
- * y^PERIOD = 1/2 with precomputed \Sum 1024*y^n {for n <PERIOD}
+ * = u y^p + (Step 1)
+ *
+ * p-1
+ * d1 y^p + 1024 \Sum y^n + d3 y^0 (Step 2)
+ * n=1
*/
-static u32 __compute_runnable_contrib(u64 n)
+static __always_inline u32
+accumulate_sum(u64 delta, int cpu, struct sched_avg *sa,
+ unsigned long weight, int running, struct cfs_rq *cfs_rq)
{
- u32 contrib = 0;
+ unsigned long scale_freq, scale_cpu;
+ u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */
+ u64 periods;
- if (likely(n <= LOAD_AVG_PERIOD))
- return runnable_avg_yN_sum[n];
- else if (unlikely(n >= LOAD_AVG_MAX_N))
- return LOAD_AVG_MAX;
+ scale_freq = arch_scale_freq_capacity(NULL, cpu);
+ scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
- /* Since n < LOAD_AVG_MAX_N, n/LOAD_AVG_PERIOD < 11 */
- contrib = __accumulated_sum_N32[n/LOAD_AVG_PERIOD];
- n %= LOAD_AVG_PERIOD;
- contrib = decay_load(contrib, n);
- return contrib + runnable_avg_yN_sum[n];
-}
+ delta += sa->period_contrib;
+ periods = delta / 1024; /* A period is 1024us (~1ms) */
-#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
+ /*
+ * Step 1: decay old *_sum if we crossed period boundaries.
+ */
+ if (periods) {
+ sa->load_sum = decay_load(sa->load_sum, periods);
+ if (cfs_rq) {
+ cfs_rq->runnable_load_sum =
+ decay_load(cfs_rq->runnable_load_sum, periods);
+ }
+ sa->util_sum = decay_load((u64)(sa->util_sum), periods);
+
+ /*
+ * Step 2
+ */
+ delta %= 1024;
+ contrib = __accumulate_pelt_segments(periods,
+ 1024 - sa->period_contrib, delta);
+ }
+ sa->period_contrib = delta;
+
+ contrib = cap_scale(contrib, scale_freq);
+ if (weight) {
+ sa->load_sum += weight * contrib;
+ if (cfs_rq)
+ cfs_rq->runnable_load_sum += weight * contrib;
+ }
+ if (running)
+ sa->util_sum += contrib * scale_cpu;
+
+ return periods;
+}
/*
* We can represent the historical contribution to runnable average as the
* = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}]
*/
static __always_inline int
-__update_load_avg(u64 now, int cpu, struct sched_avg *sa,
+___update_load_avg(u64 now, int cpu, struct sched_avg *sa,
unsigned long weight, int running, struct cfs_rq *cfs_rq)
{
- u64 delta, scaled_delta, periods;
- u32 contrib;
- unsigned int delta_w, scaled_delta_w, decayed = 0;
- unsigned long scale_freq, scale_cpu;
+ u64 delta;
delta = now - sa->last_update_time;
/*
delta >>= 10;
if (!delta)
return 0;
- sa->last_update_time = now;
-
- scale_freq = arch_scale_freq_capacity(NULL, cpu);
- scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
-
- /* delta_w is the amount already accumulated against our next period */
- delta_w = sa->period_contrib;
- if (delta + delta_w >= 1024) {
- decayed = 1;
- /* how much left for next period will start over, we don't know yet */
- sa->period_contrib = 0;
+ sa->last_update_time += delta << 10;
- /*
- * Now that we know we're crossing a period boundary, figure
- * out how much from delta we need to complete the current
- * period and accrue it.
- */
- delta_w = 1024 - delta_w;
- scaled_delta_w = cap_scale(delta_w, scale_freq);
- if (weight) {
- sa->load_sum += weight * scaled_delta_w;
- if (cfs_rq) {
- cfs_rq->runnable_load_sum +=
- weight * scaled_delta_w;
- }
- }
- if (running)
- sa->util_sum += scaled_delta_w * scale_cpu;
-
- delta -= delta_w;
-
- /* Figure out how many additional periods this update spans */
- periods = delta / 1024;
- delta %= 1024;
+ /*
+ * Now we know we crossed measurement unit boundaries. The *_avg
+ * accrues by two steps:
+ *
+ * Step 1: accumulate *_sum since last_update_time. If we haven't
+ * crossed period boundaries, finish.
+ */
+ if (!accumulate_sum(delta, cpu, sa, weight, running, cfs_rq))
+ return 0;
- sa->load_sum = decay_load(sa->load_sum, periods + 1);
- if (cfs_rq) {
- cfs_rq->runnable_load_sum =
- decay_load(cfs_rq->runnable_load_sum, periods + 1);
- }
- sa->util_sum = decay_load((u64)(sa->util_sum), periods + 1);
-
- /* Efficiently calculate \sum (1..n_period) 1024*y^i */
- contrib = __compute_runnable_contrib(periods);
- contrib = cap_scale(contrib, scale_freq);
- if (weight) {
- sa->load_sum += weight * contrib;
- if (cfs_rq)
- cfs_rq->runnable_load_sum += weight * contrib;
- }
- if (running)
- sa->util_sum += contrib * scale_cpu;
+ /*
+ * Step 2: update *_avg.
+ */
+ sa->load_avg = div_u64(sa->load_sum, LOAD_AVG_MAX);
+ if (cfs_rq) {
+ cfs_rq->runnable_load_avg =
+ div_u64(cfs_rq->runnable_load_sum, LOAD_AVG_MAX);
}
+ sa->util_avg = sa->util_sum / LOAD_AVG_MAX;
- /* Remainder of delta accrued against u_0` */
- scaled_delta = cap_scale(delta, scale_freq);
- if (weight) {
- sa->load_sum += weight * scaled_delta;
- if (cfs_rq)
- cfs_rq->runnable_load_sum += weight * scaled_delta;
- }
- if (running)
- sa->util_sum += scaled_delta * scale_cpu;
+ return 1;
+}
- sa->period_contrib += delta;
+static int
+__update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se)
+{
+ return ___update_load_avg(now, cpu, &se->avg, 0, 0, NULL);
+}
- if (decayed) {
- sa->load_avg = div_u64(sa->load_sum, LOAD_AVG_MAX);
- if (cfs_rq) {
- cfs_rq->runnable_load_avg =
- div_u64(cfs_rq->runnable_load_sum, LOAD_AVG_MAX);
- }
- sa->util_avg = sa->util_sum / LOAD_AVG_MAX;
- }
+static int
+__update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ return ___update_load_avg(now, cpu, &se->avg,
+ se->on_rq * scale_load_down(se->load.weight),
+ cfs_rq->curr == se, NULL);
+}
- return decayed;
+static int
+__update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq)
+{
+ return ___update_load_avg(now, cpu, &cfs_rq->avg,
+ scale_load_down(cfs_rq->load.weight),
+ cfs_rq->curr != NULL, cfs_rq);
}
/*
void set_task_rq_fair(struct sched_entity *se,
struct cfs_rq *prev, struct cfs_rq *next)
{
+ u64 p_last_update_time;
+ u64 n_last_update_time;
+
if (!sched_feat(ATTACH_AGE_LOAD))
return;
* time. This will result in the wakee task is less decayed, but giving
* the wakee more load sounds not bad.
*/
- if (se->avg.last_update_time && prev) {
- u64 p_last_update_time;
- u64 n_last_update_time;
+ if (!(se->avg.last_update_time && prev))
+ return;
#ifndef CONFIG_64BIT
+ {
u64 p_last_update_time_copy;
u64 n_last_update_time_copy;
} while (p_last_update_time != p_last_update_time_copy ||
n_last_update_time != n_last_update_time_copy);
+ }
#else
- p_last_update_time = prev->avg.last_update_time;
- n_last_update_time = next->avg.last_update_time;
+ p_last_update_time = prev->avg.last_update_time;
+ n_last_update_time = next->avg.last_update_time;
#endif
- __update_load_avg(p_last_update_time, cpu_of(rq_of(prev)),
- &se->avg, 0, 0, NULL);
- se->avg.last_update_time = n_last_update_time;
- }
+ __update_load_avg_blocked_se(p_last_update_time, cpu_of(rq_of(prev)), se);
+ se->avg.last_update_time = n_last_update_time;
}
/* Take into account change of utilization of a child task group */
return 1;
}
+/*
+ * Check if we need to update the load and the utilization of a blocked
+ * group_entity:
+ */
+static inline bool skip_blocked_update(struct sched_entity *se)
+{
+ struct cfs_rq *gcfs_rq = group_cfs_rq(se);
+
+ /*
+ * If sched_entity still have not zero load or utilization, we have to
+ * decay it:
+ */
+ if (se->avg.load_avg || se->avg.util_avg)
+ return false;
+
+ /*
+ * If there is a pending propagation, we have to update the load and
+ * the utilization of the sched_entity:
+ */
+ if (gcfs_rq->propagate_avg)
+ return false;
+
+ /*
+ * Otherwise, the load and the utilization of the sched_entity is
+ * already zero and there is no pending propagation, so it will be a
+ * waste of time to try to decay it:
+ */
+ return true;
+}
+
#else /* CONFIG_FAIR_GROUP_SCHED */
static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
set_tg_cfs_propagate(cfs_rq);
}
- decayed = __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa,
- scale_load_down(cfs_rq->load.weight), cfs_rq->curr != NULL, cfs_rq);
+ decayed = __update_load_avg_cfs_rq(now, cpu_of(rq_of(cfs_rq)), cfs_rq);
#ifndef CONFIG_64BIT
smp_wmb();
* Track task load average for carrying it to new CPU after migrated, and
* track group sched_entity load average for task_h_load calc in migration
*/
- if (se->avg.last_update_time && !(flags & SKIP_AGE_LOAD)) {
- __update_load_avg(now, cpu, &se->avg,
- se->on_rq * scale_load_down(se->load.weight),
- cfs_rq->curr == se, NULL);
- }
+ if (se->avg.last_update_time && !(flags & SKIP_AGE_LOAD))
+ __update_load_avg_se(now, cpu, cfs_rq, se);
decayed = update_cfs_rq_load_avg(now, cfs_rq, true);
decayed |= propagate_entity_load_avg(se);
u64 last_update_time;
last_update_time = cfs_rq_last_update_time(cfs_rq);
- __update_load_avg(last_update_time, cpu_of(rq_of(cfs_rq)), &se->avg, 0, 0, NULL);
+ __update_load_avg_blocked_se(last_update_time, cpu_of(rq_of(cfs_rq)), se);
}
/*
list_for_each_entry_rcu(cfs_rq, &cfs_b->throttled_cfs_rq,
throttled_list) {
struct rq *rq = rq_of(cfs_rq);
+ struct rq_flags rf;
- raw_spin_lock(&rq->lock);
+ rq_lock(rq, &rf);
if (!cfs_rq_throttled(cfs_rq))
goto next;
unthrottle_cfs_rq(cfs_rq);
next:
- raw_spin_unlock(&rq->lock);
+ rq_unlock(rq, &rf);
if (!remaining)
break;
unsigned long curr_jiffies = READ_ONCE(jiffies);
struct rq *this_rq = this_rq();
unsigned long load;
+ struct rq_flags rf;
if (curr_jiffies == this_rq->last_load_update_tick)
return;
load = weighted_cpuload(cpu_of(this_rq));
- raw_spin_lock(&this_rq->lock);
+ rq_lock(this_rq, &rf);
update_rq_clock(this_rq);
cpu_load_update_nohz(this_rq, curr_jiffies, load);
- raw_spin_unlock(&this_rq->lock);
+ rq_unlock(this_rq, &rf);
}
#else /* !CONFIG_NO_HZ_COMMON */
static inline void cpu_load_update_nohz(struct rq *this_rq,
lockdep_assert_held(&env->src_rq->lock);
p->on_rq = TASK_ON_RQ_MIGRATING;
- deactivate_task(env->src_rq, p, 0);
+ deactivate_task(env->src_rq, p, DEQUEUE_NOCLOCK);
set_task_cpu(p, env->dst_cpu);
}
lockdep_assert_held(&rq->lock);
BUG_ON(task_rq(p) != rq);
- activate_task(rq, p, 0);
+ activate_task(rq, p, ENQUEUE_NOCLOCK);
p->on_rq = TASK_ON_RQ_QUEUED;
check_preempt_curr(rq, p, 0);
}
*/
static void attach_one_task(struct rq *rq, struct task_struct *p)
{
- raw_spin_lock(&rq->lock);
+ struct rq_flags rf;
+
+ rq_lock(rq, &rf);
+ update_rq_clock(rq);
attach_task(rq, p);
- raw_spin_unlock(&rq->lock);
+ rq_unlock(rq, &rf);
}
/*
{
struct list_head *tasks = &env->tasks;
struct task_struct *p;
+ struct rq_flags rf;
- raw_spin_lock(&env->dst_rq->lock);
+ rq_lock(env->dst_rq, &rf);
+ update_rq_clock(env->dst_rq);
while (!list_empty(tasks)) {
p = list_first_entry(tasks, struct task_struct, se.group_node);
attach_task(env->dst_rq, p);
}
- raw_spin_unlock(&env->dst_rq->lock);
+ rq_unlock(env->dst_rq, &rf);
}
#ifdef CONFIG_FAIR_GROUP_SCHED
{
struct rq *rq = cpu_rq(cpu);
struct cfs_rq *cfs_rq;
- unsigned long flags;
+ struct rq_flags rf;
- raw_spin_lock_irqsave(&rq->lock, flags);
+ rq_lock_irqsave(rq, &rf);
update_rq_clock(rq);
/*
* list_add_leaf_cfs_rq() for details.
*/
for_each_leaf_cfs_rq(rq, cfs_rq) {
+ struct sched_entity *se;
+
/* throttled entities do not contribute to load */
if (throttled_hierarchy(cfs_rq))
continue;
if (update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq, true))
update_tg_load_avg(cfs_rq, 0);
- /* Propagate pending load changes to the parent */
- if (cfs_rq->tg->se[cpu])
- update_load_avg(cfs_rq->tg->se[cpu], 0);
+ /* Propagate pending load changes to the parent, if any: */
+ se = cfs_rq->tg->se[cpu];
+ if (se && !skip_blocked_update(se))
+ update_load_avg(se, 0);
}
- raw_spin_unlock_irqrestore(&rq->lock, flags);
+ rq_unlock_irqrestore(rq, &rf);
}
/*
{
struct rq *rq = cpu_rq(cpu);
struct cfs_rq *cfs_rq = &rq->cfs;
- unsigned long flags;
+ struct rq_flags rf;
- raw_spin_lock_irqsave(&rq->lock, flags);
+ rq_lock_irqsave(rq, &rf);
update_rq_clock(rq);
update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq, true);
- raw_spin_unlock_irqrestore(&rq->lock, flags);
+ rq_unlock_irqrestore(rq, &rf);
}
static unsigned long task_h_load(struct task_struct *p)
{
struct sched_domain *child = env->sd->child;
struct sched_group *sg = env->sd->groups;
+ struct sg_lb_stats *local = &sds->local_stat;
struct sg_lb_stats tmp_sgs;
int load_idx, prefer_sibling = 0;
bool overload = false;
local_group = cpumask_test_cpu(env->dst_cpu, sched_group_cpus(sg));
if (local_group) {
sds->local = sg;
- sgs = &sds->local_stat;
+ sgs = local;
if (env->idle != CPU_NEWLY_IDLE ||
time_after_eq(jiffies, sg->sgc->next_update))
* the tasks on the system).
*/
if (prefer_sibling && sds->local &&
- group_has_capacity(env, &sds->local_stat) &&
- (sgs->sum_nr_running > 1)) {
+ group_has_capacity(env, local) &&
+ (sgs->sum_nr_running > local->sum_nr_running + 1)) {
sgs->group_no_capacity = 1;
sgs->group_type = group_classify(sg, sgs);
}
struct sched_domain *sd_parent = sd->parent;
struct sched_group *group;
struct rq *busiest;
- unsigned long flags;
+ struct rq_flags rf;
struct cpumask *cpus = this_cpu_cpumask_var_ptr(load_balance_mask);
struct lb_env env = {
env.loop_max = min(sysctl_sched_nr_migrate, busiest->nr_running);
more_balance:
- raw_spin_lock_irqsave(&busiest->lock, flags);
+ rq_lock_irqsave(busiest, &rf);
update_rq_clock(busiest);
/*
* See task_rq_lock() family for the details.
*/
- raw_spin_unlock(&busiest->lock);
+ rq_unlock(busiest, &rf);
if (cur_ld_moved) {
attach_tasks(&env);
ld_moved += cur_ld_moved;
}
- local_irq_restore(flags);
+ local_irq_restore(rf.flags);
if (env.flags & LBF_NEED_BREAK) {
env.flags &= ~LBF_NEED_BREAK;
sd->nr_balance_failed++;
if (need_active_balance(&env)) {
+ unsigned long flags;
+
raw_spin_lock_irqsave(&busiest->lock, flags);
/* don't kick the active_load_balance_cpu_stop,
struct rq *target_rq = cpu_rq(target_cpu);
struct sched_domain *sd;
struct task_struct *p = NULL;
+ struct rq_flags rf;
- raw_spin_lock_irq(&busiest_rq->lock);
+ rq_lock_irq(busiest_rq, &rf);
/* make sure the requested cpu hasn't gone down in the meantime */
if (unlikely(busiest_cpu != smp_processor_id() ||
rcu_read_unlock();
out_unlock:
busiest_rq->active_balance = 0;
- raw_spin_unlock(&busiest_rq->lock);
+ rq_unlock(busiest_rq, &rf);
if (p)
attach_one_task(target_rq, p);
* do the balance.
*/
if (time_after_eq(jiffies, rq->next_balance)) {
- raw_spin_lock_irq(&rq->lock);
+ struct rq_flags rf;
+
+ rq_lock_irq(rq, &rf);
update_rq_clock(rq);
cpu_load_update_idle(rq);
- raw_spin_unlock_irq(&rq->lock);
+ rq_unlock_irq(rq, &rf);
+
rebalance_domains(rq, CPU_IDLE);
}
struct cfs_rq *cfs_rq;
struct sched_entity *se = &p->se, *curr;
struct rq *rq = this_rq();
+ struct rq_flags rf;
- raw_spin_lock(&rq->lock);
+ rq_lock(rq, &rf);
update_rq_clock(rq);
cfs_rq = task_cfs_rq(current);
}
se->vruntime -= cfs_rq->min_vruntime;
- raw_spin_unlock(&rq->lock);
+ rq_unlock(rq, &rf);
}
/*
int sched_group_set_shares(struct task_group *tg, unsigned long shares)
{
int i;
- unsigned long flags;
/*
* We can't change the weight of the root cgroup.
tg->shares = shares;
for_each_possible_cpu(i) {
struct rq *rq = cpu_rq(i);
- struct sched_entity *se;
+ struct sched_entity *se = tg->se[i];
+ struct rq_flags rf;
- se = tg->se[i];
/* Propagate contribution to hierarchy */
- raw_spin_lock_irqsave(&rq->lock, flags);
-
- /* Possible calls to update_curr() need rq clock */
+ rq_lock_irqsave(rq, &rf);
update_rq_clock(rq);
for_each_sched_entity(se) {
update_load_avg(se, UPDATE_TG);
update_cfs_shares(se);
}
- raw_spin_unlock_irqrestore(&rq->lock, flags);
+ rq_unlock_irqrestore(rq, &rf);
}
done:
*/
SCHED_FEAT(SIS_AVG_CPU, false)
+/*
+ * Issue a WARN when we do multiple update_rq_clock() calls
+ * in a single rq->lock section. Default disabled because the
+ * annotations are not complete.
+ */
+SCHED_FEAT(WARN_DOUBLE_CLOCK, false)
+
#ifdef HAVE_RT_PUSH_IPI
/*
* In order to avoid a thundering herd attack of CPUs that are
#define RT_PUSH_IPI_EXECUTING 1
#define RT_PUSH_IPI_RESTART 2
+/*
+ * When a high priority task schedules out from a CPU and a lower priority
+ * task is scheduled in, a check is made to see if there's any RT tasks
+ * on other CPUs that are waiting to run because a higher priority RT task
+ * is currently running on its CPU. In this case, the CPU with multiple RT
+ * tasks queued on it (overloaded) needs to be notified that a CPU has opened
+ * up that may be able to run one of its non-running queued RT tasks.
+ *
+ * On large CPU boxes, there's the case that several CPUs could schedule
+ * a lower priority task at the same time, in which case it will look for
+ * any overloaded CPUs that it could pull a task from. To do this, the runqueue
+ * lock must be taken from that overloaded CPU. Having 10s of CPUs all fighting
+ * for a single overloaded CPU's runqueue lock can produce a large latency.
+ * (This has actually been observed on large boxes running cyclictest).
+ * Instead of taking the runqueue lock of the overloaded CPU, each of the
+ * CPUs that scheduled a lower priority task simply sends an IPI to the
+ * overloaded CPU. An IPI is much cheaper than taking an runqueue lock with
+ * lots of contention. The overloaded CPU will look to push its non-running
+ * RT task off, and if it does, it can then ignore the other IPIs coming
+ * in, and just pass those IPIs off to any other overloaded CPU.
+ *
+ * When a CPU schedules a lower priority task, it only sends an IPI to
+ * the "next" CPU that has overloaded RT tasks. This prevents IPI storms,
+ * as having 10 CPUs scheduling lower priority tasks and 10 CPUs with
+ * RT overloaded tasks, would cause 100 IPIs to go out at once.
+ *
+ * The overloaded RT CPU, when receiving an IPI, will try to push off its
+ * overloaded RT tasks and then send an IPI to the next CPU that has
+ * overloaded RT tasks. This stops when all CPUs with overloaded RT tasks
+ * have completed. Just because a CPU may have pushed off its own overloaded
+ * RT task does not mean it should stop sending the IPI around to other
+ * overloaded CPUs. There may be another RT task waiting to run on one of
+ * those CPUs that are of higher priority than the one that was just
+ * pushed.
+ *
+ * An optimization that could possibly be made is to make a CPU array similar
+ * to the cpupri array mask of all running RT tasks, but for the overloaded
+ * case, then the IPI could be sent to only the CPU with the highest priority
+ * RT task waiting, and that CPU could send off further IPIs to the CPU with
+ * the next highest waiting task. Since the overloaded case is much less likely
+ * to happen, the complexity of this implementation may not be worth it.
+ * Instead, just send an IPI around to all overloaded CPUs.
+ *
+ * The rq->rt.push_flags holds the status of the IPI that is going around.
+ * A run queue can only send out a single IPI at a time. The possible flags
+ * for rq->rt.push_flags are:
+ *
+ * (None or zero): No IPI is going around for the current rq
+ * RT_PUSH_IPI_EXECUTING: An IPI for the rq is being passed around
+ * RT_PUSH_IPI_RESTART: The priority of the running task for the rq
+ * has changed, and the IPI should restart
+ * circulating the overloaded CPUs again.
+ *
+ * rq->rt.push_cpu contains the CPU that is being sent the IPI. It is updated
+ * before sending to the next CPU.
+ *
+ * Instead of having all CPUs that schedule a lower priority task send
+ * an IPI to the same "first" CPU in the RT overload mask, they send it
+ * to the next overloaded CPU after their own CPU. This helps distribute
+ * the work when there's more than one overloaded CPU and multiple CPUs
+ * scheduling in lower priority tasks.
+ *
+ * When a rq schedules a lower priority task than what was currently
+ * running, the next CPU with overloaded RT tasks is examined first.
+ * That is, if CPU 1 and 5 are overloaded, and CPU 3 schedules a lower
+ * priority task, it will send an IPI first to CPU 5, then CPU 5 will
+ * send to CPU 1 if it is still overloaded. CPU 1 will clear the
+ * rq->rt.push_flags if RT_PUSH_IPI_RESTART is not set.
+ *
+ * The first CPU to notice IPI_RESTART is set, will clear that flag and then
+ * send an IPI to the next overloaded CPU after the rq->cpu and not the next
+ * CPU after push_cpu. That is, if CPU 1, 4 and 5 are overloaded when CPU 3
+ * schedules a lower priority task, and the IPI_RESTART gets set while the
+ * handling is being done on CPU 5, it will clear the flag and send it back to
+ * CPU 4 instead of CPU 1.
+ *
+ * Note, the above logic can be disabled by turning off the sched_feature
+ * RT_PUSH_IPI. Then the rq lock of the overloaded CPU will simply be
+ * taken by the CPU requesting a pull and the waiting RT task will be pulled
+ * by that CPU. This may be fine for machines with few CPUs.
+ */
static void tell_cpu_to_push(struct rq *rq)
{
int cpu;
--- /dev/null
+/* Generated by Documentation/scheduler/sched-pelt; do not modify. */
+
+static const u32 runnable_avg_yN_inv[] = {
+ 0xffffffff, 0xfa83b2da, 0xf5257d14, 0xefe4b99a, 0xeac0c6e6, 0xe5b906e6,
+ 0xe0ccdeeb, 0xdbfbb796, 0xd744fcc9, 0xd2a81d91, 0xce248c14, 0xc9b9bd85,
+ 0xc5672a10, 0xc12c4cc9, 0xbd08a39e, 0xb8fbaf46, 0xb504f333, 0xb123f581,
+ 0xad583ee9, 0xa9a15ab4, 0xa5fed6a9, 0xa2704302, 0x9ef5325f, 0x9b8d39b9,
+ 0x9837f050, 0x94f4efa8, 0x91c3d373, 0x8ea4398a, 0x8b95c1e3, 0x88980e80,
+ 0x85aac367, 0x82cd8698,
+};
+
+#define LOAD_AVG_PERIOD 32
+#define LOAD_AVG_MAX 47742
#define DEQUEUE_SLEEP 0x01
#define DEQUEUE_SAVE 0x02 /* matches ENQUEUE_RESTORE */
#define DEQUEUE_MOVE 0x04 /* matches ENQUEUE_MOVE */
+#define DEQUEUE_NOCLOCK 0x08 /* matches ENQUEUE_NOCLOCK */
#define ENQUEUE_WAKEUP 0x01
#define ENQUEUE_RESTORE 0x02
#define ENQUEUE_MOVE 0x04
+#define ENQUEUE_NOCLOCK 0x08
-#define ENQUEUE_HEAD 0x08
-#define ENQUEUE_REPLENISH 0x10
+#define ENQUEUE_HEAD 0x10
+#define ENQUEUE_REPLENISH 0x20
#ifdef CONFIG_SMP
-#define ENQUEUE_MIGRATED 0x20
+#define ENQUEUE_MIGRATED 0x40
#else
#define ENQUEUE_MIGRATED 0x00
#endif
struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
__acquires(rq->lock);
+
struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
__acquires(p->pi_lock)
__acquires(rq->lock);
raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
}
+static inline void
+rq_lock_irqsave(struct rq *rq, struct rq_flags *rf)
+ __acquires(rq->lock)
+{
+ raw_spin_lock_irqsave(&rq->lock, rf->flags);
+ rq_pin_lock(rq, rf);
+}
+
+static inline void
+rq_lock_irq(struct rq *rq, struct rq_flags *rf)
+ __acquires(rq->lock)
+{
+ raw_spin_lock_irq(&rq->lock);
+ rq_pin_lock(rq, rf);
+}
+
+static inline void
+rq_lock(struct rq *rq, struct rq_flags *rf)
+ __acquires(rq->lock)
+{
+ raw_spin_lock(&rq->lock);
+ rq_pin_lock(rq, rf);
+}
+
+static inline void
+rq_relock(struct rq *rq, struct rq_flags *rf)
+ __acquires(rq->lock)
+{
+ raw_spin_lock(&rq->lock);
+ rq_repin_lock(rq, rf);
+}
+
+static inline void
+rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf)
+ __releases(rq->lock)
+{
+ rq_unpin_lock(rq, rf);
+ raw_spin_unlock_irqrestore(&rq->lock, rf->flags);
+}
+
+static inline void
+rq_unlock_irq(struct rq *rq, struct rq_flags *rf)
+ __releases(rq->lock)
+{
+ rq_unpin_lock(rq, rf);
+ raw_spin_unlock_irq(&rq->lock);
+}
+
+static inline void
+rq_unlock(struct rq *rq, struct rq_flags *rf)
+ __releases(rq->lock)
+{
+ rq_unpin_lock(rq, rf);
+ raw_spin_unlock(&rq->lock);
+}
+
#ifdef CONFIG_SMP
#ifdef CONFIG_PREEMPT
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
struct irqtime {
+ u64 total;
u64 tick_delta;
u64 irq_start_time;
struct u64_stats_sync sync;
DECLARE_PER_CPU(struct irqtime, cpu_irqtime);
+/*
+ * Returns the irqtime minus the softirq time computed by ksoftirqd.
+ * Otherwise ksoftirqd's sum_exec_runtime is substracted its own runtime
+ * and never move forward.
+ */
static inline u64 irq_time_read(int cpu)
{
struct irqtime *irqtime = &per_cpu(cpu_irqtime, cpu);
- u64 *cpustat = kcpustat_cpu(cpu).cpustat;
unsigned int seq;
u64 total;
do {
seq = __u64_stats_fetch_begin(&irqtime->sync);
- total = cpustat[CPUTIME_SOFTIRQ] + cpustat[CPUTIME_IRQ];
+ total = irqtime->total;
} while (__u64_stats_fetch_retry(&irqtime->sync, seq));
return total;
account_irq_exit_time(current);
__local_bh_enable(SOFTIRQ_OFFSET);
WARN_ON_ONCE(in_interrupt());
- tsk_restore_flags(current, old_flags, PF_MEMALLOC);
+ current_restore_flags(old_flags, PF_MEMALLOC);
}
asmlinkage __visible void do_softirq(void)
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = timer_migration_handler,
+ .extra1 = &zero,
+ .extra2 = &one,
},
#endif
#ifdef CONFIG_BPF_SYSCALL
if (write) {
if (*negp)
return -EINVAL;
+ if (*lvalp > UINT_MAX)
+ return -EINVAL;
*valp = *lvalp;
} else {
unsigned int val = *valp;
+ *negp = false;
*lvalp = (unsigned long)val;
}
return 0;
*
* Returns the granularity of underlying alarm base clock
*/
-static int alarm_clock_getres(const clockid_t which_clock, struct timespec *tp)
+static int alarm_clock_getres(const clockid_t which_clock, struct timespec64 *tp)
{
if (!alarmtimer_get_rtcdev())
return -EINVAL;
*
* Provides the underlying alarm base time.
*/
-static int alarm_clock_get(clockid_t which_clock, struct timespec *tp)
+static int alarm_clock_get(clockid_t which_clock, struct timespec64 *tp)
{
struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)];
if (!alarmtimer_get_rtcdev())
return -EINVAL;
- *tp = ktime_to_timespec(base->gettime());
+ *tp = ktime_to_timespec64(base->gettime());
return 0;
}
* Copies out the current itimerspec data
*/
static void alarm_timer_get(struct k_itimer *timr,
- struct itimerspec *cur_setting)
+ struct itimerspec64 *cur_setting)
{
ktime_t relative_expiry_time =
alarm_expires_remaining(&(timr->it.alarm.alarmtimer));
if (ktime_to_ns(relative_expiry_time) > 0) {
- cur_setting->it_value = ktime_to_timespec(relative_expiry_time);
+ cur_setting->it_value = ktime_to_timespec64(relative_expiry_time);
} else {
cur_setting->it_value.tv_sec = 0;
cur_setting->it_value.tv_nsec = 0;
}
- cur_setting->it_interval = ktime_to_timespec(timr->it.alarm.interval);
+ cur_setting->it_interval = ktime_to_timespec64(timr->it.alarm.interval);
}
/**
* Sets the timer to new_setting, and starts the timer.
*/
static int alarm_timer_set(struct k_itimer *timr, int flags,
- struct itimerspec *new_setting,
- struct itimerspec *old_setting)
+ struct itimerspec64 *new_setting,
+ struct itimerspec64 *old_setting)
{
ktime_t exp;
return TIMER_RETRY;
/* start the timer */
- timr->it.alarm.interval = timespec_to_ktime(new_setting->it_interval);
- exp = timespec_to_ktime(new_setting->it_value);
+ timr->it.alarm.interval = timespec64_to_ktime(new_setting->it_interval);
+ exp = timespec64_to_ktime(new_setting->it_value);
/* Convert (if necessary) to absolute time */
if (flags != TIMER_ABSTIME) {
ktime_t now;
* Handles clock_nanosleep calls against _ALARM clockids
*/
static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
- struct timespec *tsreq, struct timespec __user *rmtp)
+ struct timespec64 *tsreq,
+ struct timespec __user *rmtp)
{
enum alarmtimer_type type = clock2alarm(which_clock);
+ struct restart_block *restart;
struct alarm alarm;
ktime_t exp;
int ret = 0;
- struct restart_block *restart;
if (!alarmtimer_get_rtcdev())
return -ENOTSUPP;
alarm_init(&alarm, type, alarmtimer_nsleep_wakeup);
- exp = timespec_to_ktime(*tsreq);
+ exp = timespec64_to_ktime(*tsreq);
/* Convert (if necessary) to absolute time */
if (flags != TIMER_ABSTIME) {
ktime_t now = alarm_bases[type].gettime();
}
EXPORT_SYMBOL_GPL(clockevents_register_device);
-void clockevents_config(struct clock_event_device *dev, u32 freq)
+static void clockevents_config(struct clock_event_device *dev, u32 freq)
{
u64 sec;
ktime_to_ns(delta));
}
-/*
- * local version of hrtimer_peek_ahead_timers() called with interrupts
- * disabled.
- */
+/* called with interrupts disabled */
static inline void __hrtimer_peek_ahead_timers(void)
{
struct tick_device *td;
return ret;
}
-long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
+long hrtimer_nanosleep(struct timespec64 *rqtp, struct timespec __user *rmtp,
const enum hrtimer_mode mode, const clockid_t clockid)
{
struct restart_block *restart;
slack = 0;
hrtimer_init_on_stack(&t.timer, clockid, mode);
- hrtimer_set_expires_range_ns(&t.timer, timespec_to_ktime(*rqtp), slack);
+ hrtimer_set_expires_range_ns(&t.timer, timespec64_to_ktime(*rqtp), slack);
if (do_nanosleep(&t, mode))
goto out;
SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
struct timespec __user *, rmtp)
{
+ struct timespec64 tu64;
struct timespec tu;
if (copy_from_user(&tu, rqtp, sizeof(tu)))
return -EFAULT;
- if (!timespec_valid(&tu))
+ tu64 = timespec_to_timespec64(tu);
+ if (!timespec64_valid(&tu64))
return -EINVAL;
- return hrtimer_nanosleep(&tu, rmtp, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
+ return hrtimer_nanosleep(&tu64, rmtp, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
}
/*
return err;
}
-static int pc_clock_gettime(clockid_t id, struct timespec *ts)
+static int pc_clock_gettime(clockid_t id, struct timespec64 *ts)
{
struct posix_clock_desc cd;
int err;
return err;
}
-static int pc_clock_getres(clockid_t id, struct timespec *ts)
+static int pc_clock_getres(clockid_t id, struct timespec64 *ts)
{
struct posix_clock_desc cd;
int err;
return err;
}
-static int pc_clock_settime(clockid_t id, const struct timespec *ts)
+static int pc_clock_settime(clockid_t id, const struct timespec64 *ts)
{
struct posix_clock_desc cd;
int err;
return err;
}
-static void pc_timer_gettime(struct k_itimer *kit, struct itimerspec *ts)
+static void pc_timer_gettime(struct k_itimer *kit, struct itimerspec64 *ts)
{
clockid_t id = kit->it_clock;
struct posix_clock_desc cd;
}
static int pc_timer_settime(struct k_itimer *kit, int flags,
- struct itimerspec *ts, struct itimerspec *old)
+ struct itimerspec64 *ts, struct itimerspec64 *old)
{
clockid_t id = kit->it_clock;
struct posix_clock_desc cd;
}
static int
-posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp)
+posix_cpu_clock_getres(const clockid_t which_clock, struct timespec64 *tp)
{
int error = check_clock(which_clock);
if (!error) {
}
static int
-posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *tp)
+posix_cpu_clock_set(const clockid_t which_clock, const struct timespec64 *tp)
{
/*
* You can never reset a CPU clock, but we check for other errors
static int posix_cpu_clock_get_task(struct task_struct *tsk,
const clockid_t which_clock,
- struct timespec *tp)
+ struct timespec64 *tp)
{
int err = -EINVAL;
u64 rtn;
}
if (!err)
- *tp = ns_to_timespec(rtn);
+ *tp = ns_to_timespec64(rtn);
return err;
}
-static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
+static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec64 *tp)
{
const pid_t pid = CPUCLOCK_PID(which_clock);
int err = -EINVAL;
* and try again. (This happens when the timer is in the middle of firing.)
*/
static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
- struct itimerspec *new, struct itimerspec *old)
+ struct itimerspec64 *new, struct itimerspec64 *old)
{
unsigned long flags;
struct sighand_struct *sighand;
WARN_ON_ONCE(p == NULL);
- new_expires = timespec_to_ns(&new->it_value);
+ new_expires = timespec64_to_ns(&new->it_value);
/*
* Protect against sighand release/switch in exit/exec and p->cpu_timers
bump_cpu_timer(timer, val);
if (val < timer->it.cpu.expires) {
old_expires = timer->it.cpu.expires - val;
- old->it_value = ns_to_timespec(old_expires);
+ old->it_value = ns_to_timespec64(old_expires);
} else {
old->it_value.tv_nsec = 1;
old->it_value.tv_sec = 0;
* Install the new reload setting, and
* set up the signal and overrun bookkeeping.
*/
- timer->it.cpu.incr = timespec_to_ns(&new->it_interval);
+ timer->it.cpu.incr = timespec64_to_ns(&new->it_interval);
/*
* This acts as a modification timestamp for the timer,
ret = 0;
out:
if (old)
- old->it_interval = ns_to_timespec(old_incr);
+ old->it_interval = ns_to_timespec64(old_incr);
return ret;
}
-static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
+static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp)
{
u64 now;
struct task_struct *p = timer->it.cpu.task;
/*
* Easy part: convert the reload time.
*/
- itp->it_interval = ns_to_timespec(timer->it.cpu.incr);
+ itp->it_interval = ns_to_timespec64(timer->it.cpu.incr);
if (timer->it.cpu.expires == 0) { /* Timer not armed at all. */
itp->it_value.tv_sec = itp->it_value.tv_nsec = 0;
* Call the timer disarmed, nothing else to do.
*/
timer->it.cpu.expires = 0;
- itp->it_value = ns_to_timespec(timer->it.cpu.expires);
+ itp->it_value = ns_to_timespec64(timer->it.cpu.expires);
return;
} else {
cpu_timer_sample_group(timer->it_clock, p, &now);
}
if (now < timer->it.cpu.expires) {
- itp->it_value = ns_to_timespec(timer->it.cpu.expires - now);
+ itp->it_value = ns_to_timespec64(timer->it.cpu.expires - now);
} else {
/*
* The timer should have expired already, but the firing
* At the hard limit, we just die.
* No need to calculate anything else now.
*/
+ pr_info("CPU Watchdog Timeout (hard): %s[%d]\n",
+ tsk->comm, task_pid_nr(tsk));
__group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk);
return;
}
soft += USEC_PER_SEC;
sig->rlim[RLIMIT_RTTIME].rlim_cur = soft;
}
- printk(KERN_INFO
- "RT Watchdog Timeout: %s[%d]\n",
+ pr_info("RT Watchdog Timeout (soft): %s[%d]\n",
tsk->comm, task_pid_nr(tsk));
__group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
}
* At the hard limit, we just die.
* No need to calculate anything else now.
*/
+ pr_info("RT Watchdog Timeout (hard): %s[%d]\n",
+ tsk->comm, task_pid_nr(tsk));
__group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk);
return;
}
/*
* At the soft limit, send a SIGXCPU every second.
*/
+ pr_info("CPU Watchdog Timeout (soft): %s[%d]\n",
+ tsk->comm, task_pid_nr(tsk));
__group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
if (soft < hard) {
soft++;
}
static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
- struct timespec *rqtp, struct itimerspec *it)
+ struct timespec64 *rqtp, struct itimerspec64 *it)
{
struct k_itimer timer;
int error;
error = posix_cpu_timer_create(&timer);
timer.it_process = current;
if (!error) {
- static struct itimerspec zero_it;
+ static struct itimerspec64 zero_it;
memset(it, 0, sizeof *it);
it->it_value = *rqtp;
/*
* We were interrupted by a signal.
*/
- *rqtp = ns_to_timespec(timer.it.cpu.expires);
+ *rqtp = ns_to_timespec64(timer.it.cpu.expires);
error = posix_cpu_timer_set(&timer, 0, &zero_it, it);
if (!error) {
/*
static long posix_cpu_nsleep_restart(struct restart_block *restart_block);
static int posix_cpu_nsleep(const clockid_t which_clock, int flags,
- struct timespec *rqtp, struct timespec __user *rmtp)
+ struct timespec64 *rqtp, struct timespec __user *rmtp)
{
struct restart_block *restart_block = ¤t->restart_block;
- struct itimerspec it;
+ struct itimerspec64 it;
+ struct timespec ts;
int error;
/*
/*
* Report back to the user the time still remaining.
*/
- if (rmtp && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
+ ts = timespec64_to_timespec(it.it_value);
+ if (rmtp && copy_to_user(rmtp, &ts, sizeof(*rmtp)))
return -EFAULT;
restart_block->fn = posix_cpu_nsleep_restart;
restart_block->nanosleep.clockid = which_clock;
restart_block->nanosleep.rmtp = rmtp;
- restart_block->nanosleep.expires = timespec_to_ns(rqtp);
+ restart_block->nanosleep.expires = timespec64_to_ns(rqtp);
}
return error;
}
static long posix_cpu_nsleep_restart(struct restart_block *restart_block)
{
clockid_t which_clock = restart_block->nanosleep.clockid;
- struct timespec t;
- struct itimerspec it;
+ struct itimerspec64 it;
+ struct timespec64 t;
+ struct timespec tmp;
int error;
- t = ns_to_timespec(restart_block->nanosleep.expires);
+ t = ns_to_timespec64(restart_block->nanosleep.expires);
error = do_cpu_nanosleep(which_clock, TIMER_ABSTIME, &t, &it);
/*
* Report back to the user the time still remaining.
*/
- if (rmtp && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
+ tmp = timespec64_to_timespec(it.it_value);
+ if (rmtp && copy_to_user(rmtp, &tmp, sizeof(*rmtp)))
return -EFAULT;
- restart_block->nanosleep.expires = timespec_to_ns(&t);
+ restart_block->nanosleep.expires = timespec64_to_ns(&t);
}
return error;
#define THREAD_CLOCK MAKE_THREAD_CPUCLOCK(0, CPUCLOCK_SCHED)
static int process_cpu_clock_getres(const clockid_t which_clock,
- struct timespec *tp)
+ struct timespec64 *tp)
{
return posix_cpu_clock_getres(PROCESS_CLOCK, tp);
}
static int process_cpu_clock_get(const clockid_t which_clock,
- struct timespec *tp)
+ struct timespec64 *tp)
{
return posix_cpu_clock_get(PROCESS_CLOCK, tp);
}
return posix_cpu_timer_create(timer);
}
static int process_cpu_nsleep(const clockid_t which_clock, int flags,
- struct timespec *rqtp,
+ struct timespec64 *rqtp,
struct timespec __user *rmtp)
{
return posix_cpu_nsleep(PROCESS_CLOCK, flags, rqtp, rmtp);
return -EINVAL;
}
static int thread_cpu_clock_getres(const clockid_t which_clock,
- struct timespec *tp)
+ struct timespec64 *tp)
{
return posix_cpu_clock_getres(THREAD_CLOCK, tp);
}
static int thread_cpu_clock_get(const clockid_t which_clock,
- struct timespec *tp)
+ struct timespec64 *tp)
{
return posix_cpu_clock_get(THREAD_CLOCK, tp);
}
SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
const struct timespec __user *, tp)
{
+ struct timespec64 new_tp64;
struct timespec new_tp;
if (which_clock != CLOCK_REALTIME)
return -EINVAL;
if (copy_from_user(&new_tp, tp, sizeof (*tp)))
return -EFAULT;
- return do_sys_settimeofday(&new_tp, NULL);
+
+ new_tp64 = timespec_to_timespec64(new_tp);
+ return do_sys_settimeofday64(&new_tp64, NULL);
}
SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
struct timespec __user *,tp)
{
+ struct timespec64 kernel_tp64;
struct timespec kernel_tp;
switch (which_clock) {
- case CLOCK_REALTIME: ktime_get_real_ts(&kernel_tp); break;
- case CLOCK_MONOTONIC: ktime_get_ts(&kernel_tp); break;
- case CLOCK_BOOTTIME: get_monotonic_boottime(&kernel_tp); break;
+ case CLOCK_REALTIME: ktime_get_real_ts64(&kernel_tp64); break;
+ case CLOCK_MONOTONIC: ktime_get_ts64(&kernel_tp64); break;
+ case CLOCK_BOOTTIME: get_monotonic_boottime64(&kernel_tp64); break;
default: return -EINVAL;
}
+
+ kernel_tp = timespec64_to_timespec(kernel_tp64);
if (copy_to_user(tp, &kernel_tp, sizeof (kernel_tp)))
return -EFAULT;
return 0;
const struct timespec __user *, rqtp,
struct timespec __user *, rmtp)
{
+ struct timespec64 t64;
struct timespec t;
switch (which_clock) {
case CLOCK_BOOTTIME:
if (copy_from_user(&t, rqtp, sizeof (struct timespec)))
return -EFAULT;
- if (!timespec_valid(&t))
+ t64 = timespec_to_timespec64(t);
+ if (!timespec64_valid(&t64))
return -EINVAL;
- return hrtimer_nanosleep(&t, rmtp, flags & TIMER_ABSTIME ?
+ return hrtimer_nanosleep(&t64, rmtp, flags & TIMER_ABSTIME ?
HRTIMER_MODE_ABS : HRTIMER_MODE_REL,
which_clock);
default:
/*
* These ones are defined below.
*/
-static int common_nsleep(const clockid_t, int flags, struct timespec *t,
+static int common_nsleep(const clockid_t, int flags, struct timespec64 *t,
struct timespec __user *rmtp);
static int common_timer_create(struct k_itimer *new_timer);
-static void common_timer_get(struct k_itimer *, struct itimerspec *);
+static void common_timer_get(struct k_itimer *, struct itimerspec64 *);
static int common_timer_set(struct k_itimer *, int,
- struct itimerspec *, struct itimerspec *);
+ struct itimerspec64 *, struct itimerspec64 *);
static int common_timer_del(struct k_itimer *timer);
static enum hrtimer_restart posix_timer_fn(struct hrtimer *data);
}
/* Get clock_realtime */
-static int posix_clock_realtime_get(clockid_t which_clock, struct timespec *tp)
+static int posix_clock_realtime_get(clockid_t which_clock, struct timespec64 *tp)
{
- ktime_get_real_ts(tp);
+ ktime_get_real_ts64(tp);
return 0;
}
/* Set clock_realtime */
static int posix_clock_realtime_set(const clockid_t which_clock,
- const struct timespec *tp)
+ const struct timespec64 *tp)
{
- return do_sys_settimeofday(tp, NULL);
+ return do_sys_settimeofday64(tp, NULL);
}
static int posix_clock_realtime_adj(const clockid_t which_clock,
/*
* Get monotonic time for posix timers
*/
-static int posix_ktime_get_ts(clockid_t which_clock, struct timespec *tp)
+static int posix_ktime_get_ts(clockid_t which_clock, struct timespec64 *tp)
{
- ktime_get_ts(tp);
+ ktime_get_ts64(tp);
return 0;
}
/*
* Get monotonic-raw time for posix timers
*/
-static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec *tp)
+static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec64 *tp)
{
- getrawmonotonic(tp);
+ getrawmonotonic64(tp);
return 0;
}
-static int posix_get_realtime_coarse(clockid_t which_clock, struct timespec *tp)
+static int posix_get_realtime_coarse(clockid_t which_clock, struct timespec64 *tp)
{
- *tp = current_kernel_time();
+ *tp = current_kernel_time64();
return 0;
}
static int posix_get_monotonic_coarse(clockid_t which_clock,
- struct timespec *tp)
+ struct timespec64 *tp)
{
- *tp = get_monotonic_coarse();
+ *tp = get_monotonic_coarse64();
return 0;
}
-static int posix_get_coarse_res(const clockid_t which_clock, struct timespec *tp)
+static int posix_get_coarse_res(const clockid_t which_clock, struct timespec64 *tp)
{
- *tp = ktime_to_timespec(KTIME_LOW_RES);
+ *tp = ktime_to_timespec64(KTIME_LOW_RES);
return 0;
}
-static int posix_get_boottime(const clockid_t which_clock, struct timespec *tp)
+static int posix_get_boottime(const clockid_t which_clock, struct timespec64 *tp)
{
- get_monotonic_boottime(tp);
+ get_monotonic_boottime64(tp);
return 0;
}
-static int posix_get_tai(clockid_t which_clock, struct timespec *tp)
+static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp)
{
- timekeeping_clocktai(tp);
+ timekeeping_clocktai64(tp);
return 0;
}
-static int posix_get_hrtimer_res(clockid_t which_clock, struct timespec *tp)
+static int posix_get_hrtimer_res(clockid_t which_clock, struct timespec64 *tp)
{
tp->tv_sec = 0;
tp->tv_nsec = hrtimer_resolution;
* report.
*/
static void
-common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting)
+common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting)
{
ktime_t now, remaining, iv;
struct hrtimer *timer = &timr->it.real.timer;
- memset(cur_setting, 0, sizeof(struct itimerspec));
+ memset(cur_setting, 0, sizeof(*cur_setting));
iv = timr->it.real.interval;
/* interval timer ? */
if (iv)
- cur_setting->it_interval = ktime_to_timespec(iv);
+ cur_setting->it_interval = ktime_to_timespec64(iv);
else if (!hrtimer_active(timer) &&
(timr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE)
return;
if ((timr->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE)
cur_setting->it_value.tv_nsec = 1;
} else
- cur_setting->it_value = ktime_to_timespec(remaining);
+ cur_setting->it_value = ktime_to_timespec64(remaining);
}
/* Get the time remaining on a POSIX.1b interval timer. */
SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
struct itimerspec __user *, setting)
{
+ struct itimerspec64 cur_setting64;
struct itimerspec cur_setting;
struct k_itimer *timr;
struct k_clock *kc;
if (WARN_ON_ONCE(!kc || !kc->timer_get))
ret = -EINVAL;
else
- kc->timer_get(timr, &cur_setting);
+ kc->timer_get(timr, &cur_setting64);
unlock_timer(timr, flags);
+ cur_setting = itimerspec64_to_itimerspec(&cur_setting64);
if (!ret && copy_to_user(setting, &cur_setting, sizeof (cur_setting)))
return -EFAULT;
/* timr->it_lock is taken. */
static int
common_timer_set(struct k_itimer *timr, int flags,
- struct itimerspec *new_setting, struct itimerspec *old_setting)
+ struct itimerspec64 *new_setting, struct itimerspec64 *old_setting)
{
struct hrtimer *timer = &timr->it.real.timer;
enum hrtimer_mode mode;
hrtimer_init(&timr->it.real.timer, timr->it_clock, mode);
timr->it.real.timer.function = posix_timer_fn;
- hrtimer_set_expires(timer, timespec_to_ktime(new_setting->it_value));
+ hrtimer_set_expires(timer, timespec64_to_ktime(new_setting->it_value));
/* Convert interval */
- timr->it.real.interval = timespec_to_ktime(new_setting->it_interval);
+ timr->it.real.interval = timespec64_to_ktime(new_setting->it_interval);
/* SIGEV_NONE timers are not queued ! See common_timer_get */
if (((timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) {
const struct itimerspec __user *, new_setting,
struct itimerspec __user *, old_setting)
{
- struct k_itimer *timr;
+ struct itimerspec64 new_spec64, old_spec64;
+ struct itimerspec64 *rtn = old_setting ? &old_spec64 : NULL;
struct itimerspec new_spec, old_spec;
- int error = 0;
+ struct k_itimer *timr;
unsigned long flag;
- struct itimerspec *rtn = old_setting ? &old_spec : NULL;
struct k_clock *kc;
+ int error = 0;
if (!new_setting)
return -EINVAL;
if (copy_from_user(&new_spec, new_setting, sizeof (new_spec)))
return -EFAULT;
+ new_spec64 = itimerspec_to_itimerspec64(&new_spec);
- if (!timespec_valid(&new_spec.it_interval) ||
- !timespec_valid(&new_spec.it_value))
+ if (!timespec64_valid(&new_spec64.it_interval) ||
+ !timespec64_valid(&new_spec64.it_value))
return -EINVAL;
retry:
timr = lock_timer(timer_id, &flag);
if (WARN_ON_ONCE(!kc || !kc->timer_set))
error = -EINVAL;
else
- error = kc->timer_set(timr, flags, &new_spec, rtn);
+ error = kc->timer_set(timr, flags, &new_spec64, rtn);
unlock_timer(timr, flag);
if (error == TIMER_RETRY) {
goto retry;
}
+ old_spec = itimerspec64_to_itimerspec(&old_spec64);
if (old_setting && !error &&
copy_to_user(old_setting, &old_spec, sizeof (old_spec)))
error = -EFAULT;
const struct timespec __user *, tp)
{
struct k_clock *kc = clockid_to_kclock(which_clock);
+ struct timespec64 new_tp64;
struct timespec new_tp;
if (!kc || !kc->clock_set)
if (copy_from_user(&new_tp, tp, sizeof (*tp)))
return -EFAULT;
+ new_tp64 = timespec_to_timespec64(new_tp);
- return kc->clock_set(which_clock, &new_tp);
+ return kc->clock_set(which_clock, &new_tp64);
}
SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
struct timespec __user *,tp)
{
struct k_clock *kc = clockid_to_kclock(which_clock);
+ struct timespec64 kernel_tp64;
struct timespec kernel_tp;
int error;
if (!kc)
return -EINVAL;
- error = kc->clock_get(which_clock, &kernel_tp);
+ error = kc->clock_get(which_clock, &kernel_tp64);
+ kernel_tp = timespec64_to_timespec(kernel_tp64);
if (!error && copy_to_user(tp, &kernel_tp, sizeof (kernel_tp)))
error = -EFAULT;
struct timespec __user *, tp)
{
struct k_clock *kc = clockid_to_kclock(which_clock);
+ struct timespec64 rtn_tp64;
struct timespec rtn_tp;
int error;
if (!kc)
return -EINVAL;
- error = kc->clock_getres(which_clock, &rtn_tp);
+ error = kc->clock_getres(which_clock, &rtn_tp64);
+ rtn_tp = timespec64_to_timespec(rtn_tp64);
if (!error && tp && copy_to_user(tp, &rtn_tp, sizeof (rtn_tp)))
error = -EFAULT;
* nanosleep for monotonic and realtime clocks
*/
static int common_nsleep(const clockid_t which_clock, int flags,
- struct timespec *tsave, struct timespec __user *rmtp)
+ struct timespec64 *tsave, struct timespec __user *rmtp)
{
return hrtimer_nanosleep(tsave, rmtp, flags & TIMER_ABSTIME ?
HRTIMER_MODE_ABS : HRTIMER_MODE_REL,
struct timespec __user *, rmtp)
{
struct k_clock *kc = clockid_to_kclock(which_clock);
+ struct timespec64 t64;
struct timespec t;
if (!kc)
if (copy_from_user(&t, rqtp, sizeof (struct timespec)))
return -EFAULT;
- if (!timespec_valid(&t))
+ t64 = timespec_to_timespec64(t);
+ if (!timespec64_valid(&t64))
return -EINVAL;
- return kc->nsleep(which_clock, flags, &t, rmtp);
+ return kc->nsleep(which_clock, flags, &t64, rmtp);
}
/*
update_clock_read_data(&rd);
+ if (sched_clock_timer.function != NULL) {
+ /* update timeout for clock wrap */
+ hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL);
+ }
+
r = rate;
if (r >= 4000000) {
r /= 1000000;
return ts->sleep_length;
}
+/**
+ * tick_nohz_get_idle_calls - return the current idle calls counter value
+ *
+ * Called from the schedutil frequency scaling governor in scheduler context.
+ */
+unsigned long tick_nohz_get_idle_calls(void)
+{
+ struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
+
+ return ts->idle_calls;
+}
+
static void tick_nohz_account_idle_ticks(struct tick_sched *ts)
{
#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
SYSCALL_DEFINE2(settimeofday, struct timeval __user *, tv,
struct timezone __user *, tz)
{
+ struct timespec64 new_ts;
struct timeval user_tv;
- struct timespec new_ts;
struct timezone new_tz;
if (tv) {
return -EFAULT;
}
- return do_sys_settimeofday(tv ? &new_ts : NULL, tz ? &new_tz : NULL);
+ return do_sys_settimeofday64(tv ? &new_ts : NULL, tz ? &new_tz : NULL);
}
SYSCALL_DEFINE1(adjtimex, struct timex __user *, txc_p)
return 0;
/* Interpolate shortest distance from beginning or end of history */
- interp_forward = partial_history_cycles > total_history_cycles/2 ?
- true : false;
+ interp_forward = partial_history_cycles > total_history_cycles / 2;
partial_history_cycles = interp_forward ?
total_history_cycles - partial_history_cycles :
partial_history_cycles;
int ret;
mutex_lock(&mutex);
- ret = proc_dointvec(table, write, buffer, lenp, ppos);
+ ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (!ret && write)
timers_update_migration(false);
mutex_unlock(&mutex);
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/kallsyms.h>
+#include <linux/nmi.h>
#include <linux/uaccess.h>
next_one:
i = 0;
+
+ touch_nmi_watchdog();
+
raw_spin_lock_irqsave(&base->cpu_base->lock, flags);
curr = timerqueue_getnext(&base->active);
{
struct clock_event_device *dev = td->evtdev;
+ touch_nmi_watchdog();
+
SEQ_printf(m, "Tick Device: mode: %d\n", td->mode);
if (cpu < 0)
SEQ_printf(m, "Broadcast device\n");
select UPROBES
select PROBE_EVENTS
select TRACING
- default n
+ default y
help
This allows the user to add tracing events on top of userspace
dynamic events (similar to tracepoints) on the fly via the trace
/**
* blk_add_trace_rq - Add a trace for a request oriented action
- * @q: queue the io is for
* @rq: the source request
+ * @error: return status to log
* @nr_bytes: number of completed bytes
* @what: the action
*
* Records an action against a request. Will log the bio offset + size.
*
**/
-static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
+static void blk_add_trace_rq(struct request *rq, int error,
unsigned int nr_bytes, u32 what)
{
- struct blk_trace *bt = q->blk_trace;
+ struct blk_trace *bt = rq->q->blk_trace;
if (likely(!bt))
return;
what |= BLK_TC_ACT(BLK_TC_FS);
__blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, req_op(rq),
- rq->cmd_flags, what, rq->errors, 0, NULL);
-}
-
-static void blk_add_trace_rq_abort(void *ignore,
- struct request_queue *q, struct request *rq)
-{
- blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ABORT);
+ rq->cmd_flags, what, error, 0, NULL);
}
static void blk_add_trace_rq_insert(void *ignore,
struct request_queue *q, struct request *rq)
{
- blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_INSERT);
+ blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_INSERT);
}
static void blk_add_trace_rq_issue(void *ignore,
struct request_queue *q, struct request *rq)
{
- blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_ISSUE);
+ blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_ISSUE);
}
static void blk_add_trace_rq_requeue(void *ignore,
struct request_queue *q,
struct request *rq)
{
- blk_add_trace_rq(q, rq, blk_rq_bytes(rq), BLK_TA_REQUEUE);
+ blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_REQUEUE);
}
-static void blk_add_trace_rq_complete(void *ignore,
- struct request_queue *q,
- struct request *rq,
- unsigned int nr_bytes)
+static void blk_add_trace_rq_complete(void *ignore, struct request *rq,
+ int error, unsigned int nr_bytes)
{
- blk_add_trace_rq(q, rq, nr_bytes, BLK_TA_COMPLETE);
+ blk_add_trace_rq(rq, error, nr_bytes, BLK_TA_COMPLETE);
}
/**
r.sector_from = cpu_to_be64(from);
__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
- rq_data_dir(rq), 0, BLK_TA_REMAP, !!rq->errors,
+ rq_data_dir(rq), 0, BLK_TA_REMAP, 0,
sizeof(r), &r);
}
return;
__blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, 0,
- BLK_TA_DRV_DATA, rq->errors, len, data);
+ BLK_TA_DRV_DATA, 0, len, data);
}
EXPORT_SYMBOL_GPL(blk_add_driver_data);
{
int ret;
- ret = register_trace_block_rq_abort(blk_add_trace_rq_abort, NULL);
- WARN_ON(ret);
ret = register_trace_block_rq_insert(blk_add_trace_rq_insert, NULL);
WARN_ON(ret);
ret = register_trace_block_rq_issue(blk_add_trace_rq_issue, NULL);
unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL);
unregister_trace_block_rq_issue(blk_add_trace_rq_issue, NULL);
unregister_trace_block_rq_insert(blk_add_trace_rq_insert, NULL);
- unregister_trace_block_rq_abort(blk_add_trace_rq_abort, NULL);
tracepoint_synchronize_unregister();
}
if (unlikely(in_interrupt() ||
current->flags & (PF_KTHREAD | PF_EXITING)))
return -EPERM;
- if (unlikely(segment_eq(get_fs(), KERNEL_DS)))
+ if (unlikely(uaccess_kernel()))
return -EPERM;
if (!access_ok(VERIFY_WRITE, unsafe_ptr, size))
return -EPERM;
ftrace_probe_registered = 1;
}
-static void __disable_ftrace_function_probe(void)
+static bool __disable_ftrace_function_probe(void)
{
int i;
if (!ftrace_probe_registered)
- return;
+ return false;
for (i = 0; i < FTRACE_FUNC_HASHSIZE; i++) {
struct hlist_head *hhd = &ftrace_func_hash[i];
if (hhd->first)
- return;
+ return false;
}
/* no more funcs left */
ftrace_shutdown(&trace_probe_ops, 0);
ftrace_probe_registered = 0;
+ return true;
}
__unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
void *data, int flags)
{
+ struct ftrace_ops_hash old_hash_ops;
struct ftrace_func_entry *rec_entry;
struct ftrace_func_probe *entry;
struct ftrace_func_probe *p;
struct hlist_node *tmp;
char str[KSYM_SYMBOL_LEN];
int i, ret;
+ bool disabled;
if (glob && (strcmp(glob, "*") == 0 || !strlen(glob)))
func_g.search = NULL;
mutex_lock(&trace_probe_ops.func_hash->regex_lock);
+ old_hash_ops.filter_hash = old_hash;
+ /* Probes only have filters */
+ old_hash_ops.notrace_hash = NULL;
+
hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash);
if (!hash)
/* Hmm, should report this somehow */
}
}
mutex_lock(&ftrace_lock);
- __disable_ftrace_function_probe();
+ disabled = __disable_ftrace_function_probe();
/*
* Remove after the disable is called. Otherwise, if the last
* probe is removed, a null hash means *all enabled*.
*/
ret = ftrace_hash_move(&trace_probe_ops, 1, orig_hash, hash);
+
+ /* still need to update the function call sites */
+ if (ftrace_enabled && !disabled)
+ ftrace_run_modify_code(&trace_probe_ops, FTRACE_UPDATE_CALLS,
+ &old_hash_ops);
synchronize_sched();
if (!ret)
free_ftrace_hash_rcu(old_hash);
trace_free_pid_list(pid_list);
}
+void ftrace_clear_pids(struct trace_array *tr)
+{
+ mutex_lock(&ftrace_lock);
+
+ clear_ftrace_pids(tr);
+
+ mutex_unlock(&ftrace_lock);
+}
+
static void ftrace_pid_reset(struct trace_array *tr)
{
mutex_lock(&ftrace_lock);
int ring_buffer_iter_empty(struct ring_buffer_iter *iter)
{
struct ring_buffer_per_cpu *cpu_buffer;
+ struct buffer_page *reader;
+ struct buffer_page *head_page;
+ struct buffer_page *commit_page;
+ unsigned commit;
cpu_buffer = iter->cpu_buffer;
- return iter->head_page == cpu_buffer->commit_page &&
- iter->head == rb_commit_index(cpu_buffer);
+ /* Remember, trace recording is off when iterator is in use */
+ reader = cpu_buffer->reader_page;
+ head_page = cpu_buffer->head_page;
+ commit_page = cpu_buffer->commit_page;
+ commit = rb_page_commit(commit_page);
+
+ return ((iter->head_page == commit_page && iter->head == commit) ||
+ (iter->head_page == reader && commit_page == head_page &&
+ head_page->read == commit &&
+ iter->head == rb_page_commit(cpu_buffer->reader_page)));
}
EXPORT_SYMBOL_GPL(ring_buffer_iter_empty);
rb_data[cpu].cnt = cpu;
rb_threads[cpu] = kthread_create(rb_test, &rb_data[cpu],
"rbtester/%d", cpu);
- if (WARN_ON(!rb_threads[cpu])) {
+ if (WARN_ON(IS_ERR(rb_threads[cpu]))) {
pr_cont("FAILED\n");
- ret = -1;
+ ret = PTR_ERR(rb_threads[cpu]);
goto out_free;
}
/* Now create the rb hammer! */
rb_hammer = kthread_run(rb_hammer_test, NULL, "rbhammer");
- if (WARN_ON(!rb_hammer)) {
+ if (WARN_ON(IS_ERR(rb_hammer))) {
pr_cont("FAILED\n");
- ret = -1;
+ ret = PTR_ERR(rb_hammer);
goto out_free;
}
"\t -:[<group>/]<event>\n"
#ifdef CONFIG_KPROBE_EVENTS
"\t place: [<module>:]<symbol>[+<offset>]|<memaddr>\n"
+ "place (kretprobe): [<module>:]<symbol>[+<offset>]|<memaddr>\n"
#endif
#ifdef CONFIG_UPROBE_EVENTS
"\t place: <path>:<offset>\n"
return ret;
out_reg:
- ret = register_ftrace_function_probe(glob, ops, count);
+ ret = alloc_snapshot(&global_trace);
+ if (ret < 0)
+ goto out;
- if (ret >= 0)
- alloc_snapshot(&global_trace);
+ ret = register_ftrace_function_probe(glob, ops, count);
+ out:
return ret < 0 ? ret : 0;
}
tracing_set_nop(tr);
event_trace_del_tracer(tr);
+ ftrace_clear_pids(tr);
ftrace_destroy_function_files(tr);
tracefs_remove_recursive(tr->dir);
free_trace_buffers(tr);
void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer);
void ftrace_init_tracefs_toplevel(struct trace_array *tr,
struct dentry *d_tracer);
+void ftrace_clear_pids(struct trace_array *tr);
#else
static inline int ftrace_trace_task(struct trace_array *tr)
{
static inline void ftrace_reset_array_ops(struct trace_array *tr) { }
static inline void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d) { }
static inline void ftrace_init_tracefs_toplevel(struct trace_array *tr, struct dentry *d) { }
+static inline void ftrace_clear_pids(struct trace_array *tr) { }
/* ftace_func_t type is not defined, use macro instead of static inline */
#define ftrace_init_array_ops(tr, func) do { } while (0)
#endif /* CONFIG_FUNCTION_TRACER */
return -EINVAL;
}
if (isdigit(argv[1][0])) {
- if (is_return) {
- pr_info("Return probe point must be a symbol.\n");
- return -EINVAL;
- }
/* an address specified */
ret = kstrtoul(&argv[1][0], 0, (unsigned long *)&addr);
if (ret) {
pr_info("Failed to parse symbol.\n");
return ret;
}
- if (offset && is_return) {
- pr_info("Return probe must be used without offset.\n");
+ if (offset && is_return &&
+ !function_offset_within_entry(NULL, symbol, offset)) {
+ pr_info("Given offset is not valid for return probe.\n");
return -EINVAL;
}
}
INIT_LIST_HEAD(&pool->idle_list);
hash_init(pool->busy_hash);
- init_timer_deferrable(&pool->idle_timer);
- pool->idle_timer.function = idle_worker_timeout;
- pool->idle_timer.data = (unsigned long)pool;
+ setup_deferrable_timer(&pool->idle_timer, idle_worker_timeout,
+ (unsigned long)pool);
setup_timer(&pool->mayday_timer, pool_mayday_timeout,
(unsigned long)pool);
return wfc.ret;
}
EXPORT_SYMBOL_GPL(work_on_cpu);
+
+/**
+ * work_on_cpu_safe - run a function in thread context on a particular cpu
+ * @cpu: the cpu to run on
+ * @fn: the function to run
+ * @arg: the function argument
+ *
+ * Disables CPU hotplug and calls work_on_cpu(). The caller must not hold
+ * any locks which would prevent @fn from completing.
+ *
+ * Return: The value @fn returns.
+ */
+long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg)
+{
+ long ret = -ENODEV;
+
+ get_online_cpus();
+ if (cpu_online(cpu))
+ ret = work_on_cpu(cpu, fn, arg);
+ put_online_cpus();
+ return ret;
+}
+EXPORT_SYMBOL_GPL(work_on_cpu_safe);
#endif /* CONFIG_SMP */
#ifdef CONFIG_FREEZER
bool "Compile the kernel with frame pointers"
depends on DEBUG_KERNEL && \
(CRIS || M68K || FRV || UML || \
- AVR32 || SUPERH || BLACKFIN || MN10300 || METAG) || \
+ SUPERH || BLACKFIN || MN10300 || METAG) || \
ARCH_WANT_FRAME_POINTERS
default y if (DEBUG_INFO && UML) || ARCH_WANT_FRAME_POINTERS
help
For more details, see Documentation/locking/lockdep-design.txt.
-config PROVE_LOCKING_SMALL
- bool
-
config LOCKDEP
bool
depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
select KALLSYMS
select KALLSYMS_ALL
+config LOCKDEP_SMALL
+ bool
+
config LOCK_STAT
bool "Lock usage statistics"
depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
gcd.o lcm.o list_sort.o uuid.o flex_array.o iov_iter.o clz_ctz.o \
bsearch.o find_bit.o llist.o memweight.o kfifo.o \
percpu-refcount.o percpu_ida.o rhashtable.o reciprocal_div.o \
- once.o refcount.o
+ once.o refcount.o usercopy.o
obj-y += string_helpers.o
obj-$(CONFIG_TEST_STRING_HELPERS) += test-string_helpers.o
obj-y += hexdump.o
#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/string.h>
+#include <linux/ctype.h>
/*
* If a hyphen was found in get_option, this will handle the
return false;
}
+
+/*
+ * Parse a string to get a param value pair.
+ * You can use " around spaces, but can't escape ".
+ * Hyphens and underscores equivalent in parameter names.
+ */
+char *next_arg(char *args, char **param, char **val)
+{
+ unsigned int i, equals = 0;
+ int in_quote = 0, quoted = 0;
+ char *next;
+
+ if (*args == '"') {
+ args++;
+ in_quote = 1;
+ quoted = 1;
+ }
+
+ for (i = 0; args[i]; i++) {
+ if (isspace(args[i]) && !in_quote)
+ break;
+ if (equals == 0) {
+ if (args[i] == '=')
+ equals = i;
+ }
+ if (args[i] == '"')
+ in_quote = !in_quote;
+ }
+
+ *param = args;
+ if (!equals)
+ *val = NULL;
+ else {
+ args[equals] = '\0';
+ *val = args + equals + 1;
+
+ /* Don't include quotes in value. */
+ if (**val == '"') {
+ (*val)++;
+ if (args[i-1] == '"')
+ args[i-1] = '\0';
+ }
+ }
+ if (quoted && args[i-1] == '"')
+ args[i-1] = '\0';
+
+ if (args[i]) {
+ args[i] = '\0';
+ next = args + i + 1;
+ } else
+ next = args + i;
+
+ /* Chew up trailing spaces. */
+ return skip_spaces(next);
+ //return next;
+}
size_t count)
{
/* It will get better. Eventually... */
- if (segment_eq(get_fs(), KERNEL_DS)) {
+ if (uaccess_kernel()) {
direction |= ITER_KVEC;
i->type = direction;
i->kvec = (struct kvec *)iov;
return 0;
}
iterate_and_advance(i, bytes, v,
- __copy_from_user_nocache((to += v.iov_len) - v.iov_len,
+ __copy_from_user_inatomic_nocache((to += v.iov_len) - v.iov_len,
v.iov_base, v.iov_len),
memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page,
v.bv_offset, v.bv_len),
if (unlikely(i->count < bytes))
return false;
iterate_all_kinds(i, bytes, v, ({
- if (__copy_from_user_nocache((to += v.iov_len) - v.iov_len,
+ if (__copy_from_user_inatomic_nocache((to += v.iov_len) - v.iov_len,
v.iov_base, v.iov_len))
return false;
0;}),
}
EXPORT_SYMBOL(iov_iter_advance);
+void iov_iter_revert(struct iov_iter *i, size_t unroll)
+{
+ if (!unroll)
+ return;
+ i->count += unroll;
+ if (unlikely(i->type & ITER_PIPE)) {
+ struct pipe_inode_info *pipe = i->pipe;
+ int idx = i->idx;
+ size_t off = i->iov_offset;
+ while (1) {
+ size_t n = off - pipe->bufs[idx].offset;
+ if (unroll < n) {
+ off -= unroll;
+ break;
+ }
+ unroll -= n;
+ if (!unroll && idx == i->start_idx) {
+ off = 0;
+ break;
+ }
+ if (!idx--)
+ idx = pipe->buffers - 1;
+ off = pipe->bufs[idx].offset + pipe->bufs[idx].len;
+ }
+ i->iov_offset = off;
+ i->idx = idx;
+ pipe_truncate(i);
+ return;
+ }
+ if (unroll <= i->iov_offset) {
+ i->iov_offset -= unroll;
+ return;
+ }
+ unroll -= i->iov_offset;
+ if (i->type & ITER_BVEC) {
+ const struct bio_vec *bvec = i->bvec;
+ while (1) {
+ size_t n = (--bvec)->bv_len;
+ i->nr_segs++;
+ if (unroll <= n) {
+ i->bvec = bvec;
+ i->iov_offset = n - unroll;
+ return;
+ }
+ unroll -= n;
+ }
+ } else { /* same logics for iovec and kvec */
+ const struct iovec *iov = i->iov;
+ while (1) {
+ size_t n = (--iov)->iov_len;
+ i->nr_segs++;
+ if (unroll <= n) {
+ i->iov = iov;
+ i->iov_offset = n - unroll;
+ return;
+ }
+ unroll -= n;
+ }
+ }
+}
+EXPORT_SYMBOL(iov_iter_revert);
+
/*
* Return the count of just the current iov_iter segment.
*/
i->idx = (pipe->curbuf + pipe->nrbufs) & (pipe->buffers - 1);
i->iov_offset = 0;
i->count = count;
+ i->start_idx = i->idx;
}
EXPORT_SYMBOL(iov_iter_pipe);
}
EXPORT_SYMBOL(kobject_get);
-static struct kobject * __must_check kobject_get_unless_zero(struct kobject *kobj)
+struct kobject * __must_check kobject_get_unless_zero(struct kobject *kobj)
{
+ if (!kobj)
+ return NULL;
if (!kref_get_unless_zero(&kobj->kref))
kobj = NULL;
return kobj;
}
+EXPORT_SYMBOL(kobject_get_unless_zero);
/*
* kobject_cleanup - free kobject resources.
#include <linux/refcount.h>
#include <linux/bug.h>
+/**
+ * refcount_add_not_zero - add a value to a refcount unless it is 0
+ * @i: the value to add to the refcount
+ * @r: the refcount
+ *
+ * Will saturate at UINT_MAX and WARN.
+ *
+ * Provides no memory ordering, it is assumed the caller has guaranteed the
+ * object memory to be stable (RCU, etc.). It does provide a control dependency
+ * and thereby orders future stores. See the comment on top.
+ *
+ * Use of this function is not recommended for the normal reference counting
+ * use case in which references are taken and released one at a time. In these
+ * cases, refcount_inc(), or one of its variants, should instead be used to
+ * increment a reference count.
+ *
+ * Return: false if the passed refcount is 0, true otherwise
+ */
bool refcount_add_not_zero(unsigned int i, refcount_t *r)
{
- unsigned int old, new, val = atomic_read(&r->refs);
+ unsigned int new, val = atomic_read(&r->refs);
- for (;;) {
+ do {
if (!val)
return false;
new = val + i;
if (new < val)
new = UINT_MAX;
- old = atomic_cmpxchg_relaxed(&r->refs, val, new);
- if (old == val)
- break;
- val = old;
- }
+ } while (!atomic_try_cmpxchg_relaxed(&r->refs, &val, new));
WARN_ONCE(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
}
EXPORT_SYMBOL_GPL(refcount_add_not_zero);
+/**
+ * refcount_add - add a value to a refcount
+ * @i: the value to add to the refcount
+ * @r: the refcount
+ *
+ * Similar to atomic_add(), but will saturate at UINT_MAX and WARN.
+ *
+ * Provides no memory ordering, it is assumed the caller has guaranteed the
+ * object memory to be stable (RCU, etc.). It does provide a control dependency
+ * and thereby orders future stores. See the comment on top.
+ *
+ * Use of this function is not recommended for the normal reference counting
+ * use case in which references are taken and released one at a time. In these
+ * cases, refcount_inc(), or one of its variants, should instead be used to
+ * increment a reference count.
+ */
void refcount_add(unsigned int i, refcount_t *r)
{
WARN_ONCE(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n");
}
EXPORT_SYMBOL_GPL(refcount_add);
-/*
- * Similar to atomic_inc_not_zero(), will saturate at UINT_MAX and WARN.
+/**
+ * refcount_inc_not_zero - increment a refcount unless it is 0
+ * @r: the refcount to increment
+ *
+ * Similar to atomic_inc_not_zero(), but will saturate at UINT_MAX and WARN.
*
* Provides no memory ordering, it is assumed the caller has guaranteed the
* object memory to be stable (RCU, etc.). It does provide a control dependency
* and thereby orders future stores. See the comment on top.
+ *
+ * Return: true if the increment was successful, false otherwise
*/
bool refcount_inc_not_zero(refcount_t *r)
{
- unsigned int old, new, val = atomic_read(&r->refs);
+ unsigned int new, val = atomic_read(&r->refs);
- for (;;) {
+ do {
new = val + 1;
if (!val)
if (unlikely(!new))
return true;
- old = atomic_cmpxchg_relaxed(&r->refs, val, new);
- if (old == val)
- break;
-
- val = old;
- }
+ } while (!atomic_try_cmpxchg_relaxed(&r->refs, &val, new));
WARN_ONCE(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
}
EXPORT_SYMBOL_GPL(refcount_inc_not_zero);
-/*
- * Similar to atomic_inc(), will saturate at UINT_MAX and WARN.
+/**
+ * refcount_inc - increment a refcount
+ * @r: the refcount to increment
+ *
+ * Similar to atomic_inc(), but will saturate at UINT_MAX and WARN.
*
* Provides no memory ordering, it is assumed the caller already has a
- * reference on the object, will WARN when this is not so.
+ * reference on the object.
+ *
+ * Will WARN if the refcount is 0, as this represents a possible use-after-free
+ * condition.
*/
void refcount_inc(refcount_t *r)
{
}
EXPORT_SYMBOL_GPL(refcount_inc);
+/**
+ * refcount_sub_and_test - subtract from a refcount and test if it is 0
+ * @i: amount to subtract from the refcount
+ * @r: the refcount
+ *
+ * Similar to atomic_dec_and_test(), but it will WARN, return false and
+ * ultimately leak on underflow and will fail to decrement when saturated
+ * at UINT_MAX.
+ *
+ * Provides release memory ordering, such that prior loads and stores are done
+ * before, and provides a control dependency such that free() must come after.
+ * See the comment on top.
+ *
+ * Use of this function is not recommended for the normal reference counting
+ * use case in which references are taken and released one at a time. In these
+ * cases, refcount_dec(), or one of its variants, should instead be used to
+ * decrement a reference count.
+ *
+ * Return: true if the resulting refcount is 0, false otherwise
+ */
bool refcount_sub_and_test(unsigned int i, refcount_t *r)
{
- unsigned int old, new, val = atomic_read(&r->refs);
+ unsigned int new, val = atomic_read(&r->refs);
- for (;;) {
+ do {
if (unlikely(val == UINT_MAX))
return false;
return false;
}
- old = atomic_cmpxchg_release(&r->refs, val, new);
- if (old == val)
- break;
-
- val = old;
- }
+ } while (!atomic_try_cmpxchg_release(&r->refs, &val, new));
return !new;
}
EXPORT_SYMBOL_GPL(refcount_sub_and_test);
-/*
+/**
+ * refcount_dec_and_test - decrement a refcount and test if it is 0
+ * @r: the refcount
+ *
* Similar to atomic_dec_and_test(), it will WARN on underflow and fail to
* decrement when saturated at UINT_MAX.
*
* Provides release memory ordering, such that prior loads and stores are done
* before, and provides a control dependency such that free() must come after.
* See the comment on top.
+ *
+ * Return: true if the resulting refcount is 0, false otherwise
*/
bool refcount_dec_and_test(refcount_t *r)
{
}
EXPORT_SYMBOL_GPL(refcount_dec_and_test);
-/*
+/**
+ * refcount_dec - decrement a refcount
+ * @r: the refcount
+ *
* Similar to atomic_dec(), it will WARN on underflow and fail to decrement
* when saturated at UINT_MAX.
*
* Provides release memory ordering, such that prior loads and stores are done
* before.
*/
-
void refcount_dec(refcount_t *r)
{
WARN_ONCE(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n");
}
EXPORT_SYMBOL_GPL(refcount_dec);
-/*
+/**
+ * refcount_dec_if_one - decrement a refcount if it is 1
+ * @r: the refcount
+ *
* No atomic_t counterpart, it attempts a 1 -> 0 transition and returns the
* success thereof.
*
* It can be used like a try-delete operator; this explicit case is provided
* and not cmpxchg in generic, because that would allow implementing unsafe
* operations.
+ *
+ * Return: true if the resulting refcount is 0, false otherwise
*/
bool refcount_dec_if_one(refcount_t *r)
{
- return atomic_cmpxchg_release(&r->refs, 1, 0) == 1;
+ int val = 1;
+
+ return atomic_try_cmpxchg_release(&r->refs, &val, 0);
}
EXPORT_SYMBOL_GPL(refcount_dec_if_one);
-/*
+/**
+ * refcount_dec_not_one - decrement a refcount if it is not 1
+ * @r: the refcount
+ *
* No atomic_t counterpart, it decrements unless the value is 1, in which case
* it will return false.
*
* Was often done like: atomic_add_unless(&var, -1, 1)
+ *
+ * Return: true if the decrement operation was successful, false otherwise
*/
bool refcount_dec_not_one(refcount_t *r)
{
- unsigned int old, new, val = atomic_read(&r->refs);
+ unsigned int new, val = atomic_read(&r->refs);
- for (;;) {
+ do {
if (unlikely(val == UINT_MAX))
return true;
return true;
}
- old = atomic_cmpxchg_release(&r->refs, val, new);
- if (old == val)
- break;
-
- val = old;
- }
+ } while (!atomic_try_cmpxchg_release(&r->refs, &val, new));
return true;
}
EXPORT_SYMBOL_GPL(refcount_dec_not_one);
-/*
+/**
+ * refcount_dec_and_mutex_lock - return holding mutex if able to decrement
+ * refcount to 0
+ * @r: the refcount
+ * @lock: the mutex to be locked
+ *
* Similar to atomic_dec_and_mutex_lock(), it will WARN on underflow and fail
* to decrement when saturated at UINT_MAX.
*
* Provides release memory ordering, such that prior loads and stores are done
* before, and provides a control dependency such that free() must come after.
* See the comment on top.
+ *
+ * Return: true and hold mutex if able to decrement refcount to 0, false
+ * otherwise
*/
bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock)
{
}
EXPORT_SYMBOL_GPL(refcount_dec_and_mutex_lock);
-/*
+/**
+ * refcount_dec_and_lock - return holding spinlock if able to decrement
+ * refcount to 0
+ * @r: the refcount
+ * @lock: the spinlock to be locked
+ *
* Similar to atomic_dec_and_lock(), it will WARN on underflow and fail to
* decrement when saturated at UINT_MAX.
*
* Provides release memory ordering, such that prior loads and stores are done
* before, and provides a control dependency such that free() must come after.
* See the comment on top.
+ *
+ * Return: true and hold spinlock if able to decrement refcount to 0, false
+ * otherwise
*/
bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock)
{
}
EXPORT_SYMBOL_GPL(sbitmap_resize);
-static int __sbitmap_get_word(struct sbitmap_word *word, unsigned int hint,
- bool wrap)
+static int __sbitmap_get_word(unsigned long *word, unsigned long depth,
+ unsigned int hint, bool wrap)
{
unsigned int orig_hint = hint;
int nr;
while (1) {
- nr = find_next_zero_bit(&word->word, word->depth, hint);
- if (unlikely(nr >= word->depth)) {
+ nr = find_next_zero_bit(word, depth, hint);
+ if (unlikely(nr >= depth)) {
/*
* We started with an offset, and we didn't reset the
* offset to 0 in a failure case, so start from 0 to
return -1;
}
- if (!test_and_set_bit(nr, &word->word))
+ if (!test_and_set_bit(nr, word))
break;
hint = nr + 1;
- if (hint >= word->depth - 1)
+ if (hint >= depth - 1)
hint = 0;
}
index = SB_NR_TO_INDEX(sb, alloc_hint);
for (i = 0; i < sb->map_nr; i++) {
- nr = __sbitmap_get_word(&sb->map[index],
+ nr = __sbitmap_get_word(&sb->map[index].word,
+ sb->map[index].depth,
SB_NR_TO_BIT(sb, alloc_hint),
!round_robin);
if (nr != -1) {
}
EXPORT_SYMBOL_GPL(sbitmap_get);
+int sbitmap_get_shallow(struct sbitmap *sb, unsigned int alloc_hint,
+ unsigned long shallow_depth)
+{
+ unsigned int i, index;
+ int nr = -1;
+
+ index = SB_NR_TO_INDEX(sb, alloc_hint);
+
+ for (i = 0; i < sb->map_nr; i++) {
+ nr = __sbitmap_get_word(&sb->map[index].word,
+ min(sb->map[index].depth, shallow_depth),
+ SB_NR_TO_BIT(sb, alloc_hint), true);
+ if (nr != -1) {
+ nr += index << sb->shift;
+ break;
+ }
+
+ /* Jump to next index. */
+ index++;
+ alloc_hint = index << sb->shift;
+
+ if (index >= sb->map_nr) {
+ index = 0;
+ alloc_hint = 0;
+ }
+ }
+
+ return nr;
+}
+EXPORT_SYMBOL_GPL(sbitmap_get_shallow);
+
bool sbitmap_any_bit_set(const struct sbitmap *sb)
{
unsigned int i;
}
EXPORT_SYMBOL_GPL(__sbitmap_queue_get);
+int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,
+ unsigned int shallow_depth)
+{
+ unsigned int hint, depth;
+ int nr;
+
+ hint = this_cpu_read(*sbq->alloc_hint);
+ depth = READ_ONCE(sbq->sb.depth);
+ if (unlikely(hint >= depth)) {
+ hint = depth ? prandom_u32() % depth : 0;
+ this_cpu_write(*sbq->alloc_hint, hint);
+ }
+ nr = sbitmap_get_shallow(&sbq->sb, hint, shallow_depth);
+
+ if (nr == -1) {
+ /* If the map is full, a hint won't do us much good. */
+ this_cpu_write(*sbq->alloc_hint, 0);
+ } else if (nr == hint || unlikely(sbq->round_robin)) {
+ /* Only update the hint if we used it. */
+ hint = nr + 1;
+ if (hint >= depth - 1)
+ hint = 0;
+ this_cpu_write(*sbq->alloc_hint, hint);
+ }
+
+ return nr;
+}
+EXPORT_SYMBOL_GPL(__sbitmap_queue_get_shallow);
+
static struct sbq_wait_state *sbq_wake_ptr(struct sbitmap_queue *sbq)
{
int i, wake_index;
* their capability at compile-time, we just have to opt-out certain archs.
*/
#if BITS_PER_LONG == 64 || (!(defined(CONFIG_ARM) && !defined(MMU)) && \
- !defined(CONFIG_AVR32) && \
!defined(CONFIG_BLACKFIN) && \
!defined(CONFIG_M32R) && \
!defined(CONFIG_M68K) && \
--- /dev/null
+#include <linux/uaccess.h>
+
+/* out-of-line parts */
+
+#ifndef INLINE_COPY_FROM_USER
+unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+ unsigned long res = n;
+ if (likely(access_ok(VERIFY_READ, from, n)))
+ res = raw_copy_from_user(to, from, n);
+ if (unlikely(res))
+ memset(to + (n - res), 0, res);
+ return res;
+}
+EXPORT_SYMBOL(_copy_from_user);
+#endif
+
+#ifndef INLINE_COPY_TO_USER
+unsigned long _copy_to_user(void *to, const void __user *from, unsigned long n)
+{
+ if (likely(access_ok(VERIFY_WRITE, to, n)))
+ n = raw_copy_to_user(to, from, n);
+ return n;
+}
+EXPORT_SYMBOL(_copy_to_user);
+#endif
config NR_QUICK
int
depends on QUICKLIST
- default "2" if AVR32
default "1"
config VIRT_TO_BUS
#include <linux/device.h>
#include <trace/events/writeback.h>
-static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
-
struct backing_dev_info noop_backing_dev_info = {
.name = "noop",
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
}
postcore_initcall(bdi_class_init);
+static int bdi_init(struct backing_dev_info *bdi);
+
static int __init default_bdi_init(void)
{
int err;
memset(wb, 0, sizeof(*wb));
+ if (wb != &bdi->wb)
+ bdi_get(bdi);
wb->bdi = bdi;
wb->last_old_flush = jiffies;
INIT_LIST_HEAD(&wb->b_dirty);
wb->dirty_sleep = jiffies;
wb->congested = wb_congested_get_create(bdi, blkcg_id, gfp);
- if (!wb->congested)
- return -ENOMEM;
+ if (!wb->congested) {
+ err = -ENOMEM;
+ goto out_put_bdi;
+ }
err = fprop_local_init_percpu(&wb->completions, gfp);
if (err)
fprop_local_destroy_percpu(&wb->completions);
out_put_cong:
wb_congested_put(wb->congested);
+out_put_bdi:
+ if (wb != &bdi->wb)
+ bdi_put(bdi);
return err;
}
+static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb);
+
/*
* Remove bdi from the global list and shutdown any threads we have running
*/
spin_lock_bh(&wb->work_lock);
if (!test_and_clear_bit(WB_registered, &wb->state)) {
spin_unlock_bh(&wb->work_lock);
+ /*
+ * Wait for wb shutdown to finish if someone else is just
+ * running wb_shutdown(). Otherwise we could proceed to wb /
+ * bdi destruction before wb_shutdown() is finished.
+ */
+ wait_on_bit(&wb->state, WB_shutting_down, TASK_UNINTERRUPTIBLE);
return;
}
+ set_bit(WB_shutting_down, &wb->state);
spin_unlock_bh(&wb->work_lock);
+ cgwb_remove_from_bdi_list(wb);
/*
* Drain work list and shutdown the delayed_work. !WB_registered
* tells wb_workfn() that @wb is dying and its work_list needs to
mod_delayed_work(bdi_wq, &wb->dwork, 0);
flush_delayed_work(&wb->dwork);
WARN_ON(!list_empty(&wb->work_list));
+ /*
+ * Make sure bit gets cleared after shutdown is finished. Matches with
+ * the barrier provided by test_and_clear_bit() above.
+ */
+ smp_wmb();
+ clear_bit(WB_shutting_down, &wb->state);
}
static void wb_exit(struct bdi_writeback *wb)
fprop_local_destroy_percpu(&wb->completions);
wb_congested_put(wb->congested);
+ if (wb != &wb->bdi->wb)
+ bdi_put(wb->bdi);
}
#ifdef CONFIG_CGROUP_WRITEBACK
/*
* cgwb_lock protects bdi->cgwb_tree, bdi->cgwb_congested_tree,
* blkcg->cgwb_list, and memcg->cgwb_list. bdi->cgwb_tree is also RCU
- * protected. cgwb_release_wait is used to wait for the completion of cgwb
- * releases from bdi destruction path.
+ * protected.
*/
static DEFINE_SPINLOCK(cgwb_lock);
-static DECLARE_WAIT_QUEUE_HEAD(cgwb_release_wait);
/**
* wb_congested_get_create - get or create a wb_congested
return NULL;
atomic_set(&new_congested->refcnt, 0);
- new_congested->bdi = bdi;
+ new_congested->__bdi = bdi;
new_congested->blkcg_id = blkcg_id;
goto retry;
}
/* bdi might already have been destroyed leaving @congested unlinked */
- if (congested->bdi) {
+ if (congested->__bdi) {
rb_erase(&congested->rb_node,
- &congested->bdi->cgwb_congested_tree);
- congested->bdi = NULL;
+ &congested->__bdi->cgwb_congested_tree);
+ congested->__bdi = NULL;
}
spin_unlock_irqrestore(&cgwb_lock, flags);
{
struct bdi_writeback *wb = container_of(work, struct bdi_writeback,
release_work);
- struct backing_dev_info *bdi = wb->bdi;
-
- spin_lock_irq(&cgwb_lock);
- list_del_rcu(&wb->bdi_node);
- spin_unlock_irq(&cgwb_lock);
wb_shutdown(wb);
percpu_ref_exit(&wb->refcnt);
wb_exit(wb);
kfree_rcu(wb, rcu);
-
- if (atomic_dec_and_test(&bdi->usage_cnt))
- wake_up_all(&cgwb_release_wait);
}
static void cgwb_release(struct percpu_ref *refcnt)
percpu_ref_kill(&wb->refcnt);
}
+static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb)
+{
+ spin_lock_irq(&cgwb_lock);
+ list_del_rcu(&wb->bdi_node);
+ spin_unlock_irq(&cgwb_lock);
+}
+
static int cgwb_create(struct backing_dev_info *bdi,
struct cgroup_subsys_state *memcg_css, gfp_t gfp)
{
/* we might have raced another instance of this function */
ret = radix_tree_insert(&bdi->cgwb_tree, memcg_css->id, wb);
if (!ret) {
- atomic_inc(&bdi->usage_cnt);
list_add_tail_rcu(&wb->bdi_node, &bdi->wb_list);
list_add(&wb->memcg_node, memcg_cgwb_list);
list_add(&wb->blkcg_node, blkcg_cgwb_list);
INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC);
bdi->cgwb_congested_tree = RB_ROOT;
- atomic_set(&bdi->usage_cnt, 1);
ret = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL);
if (!ret) {
return ret;
}
-static void cgwb_bdi_destroy(struct backing_dev_info *bdi)
+static void cgwb_bdi_unregister(struct backing_dev_info *bdi)
{
struct radix_tree_iter iter;
void **slot;
+ struct bdi_writeback *wb;
WARN_ON(test_bit(WB_registered, &bdi->wb.state));
spin_lock_irq(&cgwb_lock);
radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0)
cgwb_kill(*slot);
- spin_unlock_irq(&cgwb_lock);
- /*
- * All cgwb's must be shutdown and released before returning. Drain
- * the usage counter to wait for all cgwb's ever created on @bdi.
- */
- atomic_dec(&bdi->usage_cnt);
- wait_event(cgwb_release_wait, !atomic_read(&bdi->usage_cnt));
- /*
- * Grab back our reference so that we hold it when @bdi gets
- * re-registered.
- */
- atomic_inc(&bdi->usage_cnt);
+ while (!list_empty(&bdi->wb_list)) {
+ wb = list_first_entry(&bdi->wb_list, struct bdi_writeback,
+ bdi_node);
+ spin_unlock_irq(&cgwb_lock);
+ wb_shutdown(wb);
+ spin_lock_irq(&cgwb_lock);
+ }
+ spin_unlock_irq(&cgwb_lock);
}
/**
rb_entry(rbn, struct bdi_writeback_congested, rb_node);
rb_erase(rbn, &bdi->cgwb_congested_tree);
- congested->bdi = NULL; /* mark @congested unlinked */
+ congested->__bdi = NULL; /* mark @congested unlinked */
}
spin_unlock_irq(&cgwb_lock);
}
+static void cgwb_bdi_register(struct backing_dev_info *bdi)
+{
+ spin_lock_irq(&cgwb_lock);
+ list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list);
+ spin_unlock_irq(&cgwb_lock);
+}
+
#else /* CONFIG_CGROUP_WRITEBACK */
static int cgwb_bdi_init(struct backing_dev_info *bdi)
return 0;
}
-static void cgwb_bdi_destroy(struct backing_dev_info *bdi) { }
+static void cgwb_bdi_unregister(struct backing_dev_info *bdi) { }
static void cgwb_bdi_exit(struct backing_dev_info *bdi)
{
wb_congested_put(bdi->wb_congested);
}
+static void cgwb_bdi_register(struct backing_dev_info *bdi)
+{
+ list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list);
+}
+
+static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb)
+{
+ list_del_rcu(&wb->bdi_node);
+}
+
#endif /* CONFIG_CGROUP_WRITEBACK */
-int bdi_init(struct backing_dev_info *bdi)
+static int bdi_init(struct backing_dev_info *bdi)
{
int ret;
ret = cgwb_bdi_init(bdi);
- list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list);
-
return ret;
}
-EXPORT_SYMBOL(bdi_init);
struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id)
{
}
return bdi;
}
+EXPORT_SYMBOL(bdi_alloc_node);
-int bdi_register(struct backing_dev_info *bdi, struct device *parent,
- const char *fmt, ...)
+int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args)
{
- va_list args;
struct device *dev;
if (bdi->dev) /* The driver needs to use separate queues per device */
return 0;
- va_start(args, fmt);
- dev = device_create_vargs(bdi_class, parent, MKDEV(0, 0), bdi, fmt, args);
- va_end(args);
+ dev = device_create_vargs(bdi_class, NULL, MKDEV(0, 0), bdi, fmt, args);
if (IS_ERR(dev))
return PTR_ERR(dev);
+ cgwb_bdi_register(bdi);
bdi->dev = dev;
bdi_debug_register(bdi, dev_name(dev));
trace_writeback_bdi_register(bdi);
return 0;
}
-EXPORT_SYMBOL(bdi_register);
+EXPORT_SYMBOL(bdi_register_va);
-int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev)
+int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...)
{
- return bdi_register(bdi, NULL, "%u:%u", MAJOR(dev), MINOR(dev));
+ va_list args;
+ int ret;
+
+ va_start(args, fmt);
+ ret = bdi_register_va(bdi, fmt, args);
+ va_end(args);
+ return ret;
}
-EXPORT_SYMBOL(bdi_register_dev);
+EXPORT_SYMBOL(bdi_register);
int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner)
{
int rc;
- rc = bdi_register(bdi, NULL, "%u:%u", MAJOR(owner->devt),
- MINOR(owner->devt));
+ rc = bdi_register(bdi, "%u:%u", MAJOR(owner->devt), MINOR(owner->devt));
if (rc)
return rc;
/* Leaking owner reference... */
/* make sure nobody finds us on the bdi_list anymore */
bdi_remove_from_list(bdi);
wb_shutdown(&bdi->wb);
- cgwb_bdi_destroy(bdi);
+ cgwb_bdi_unregister(bdi);
if (bdi->dev) {
bdi_debug_unregister(bdi);
}
}
-static void bdi_exit(struct backing_dev_info *bdi)
-{
- WARN_ON_ONCE(bdi->dev);
- wb_exit(&bdi->wb);
- cgwb_bdi_exit(bdi);
-}
-
static void release_bdi(struct kref *ref)
{
struct backing_dev_info *bdi =
container_of(ref, struct backing_dev_info, refcnt);
- bdi_exit(bdi);
+ if (test_bit(WB_registered, &bdi->wb.state))
+ bdi_unregister(bdi);
+ WARN_ON_ONCE(bdi->dev);
+ wb_exit(&bdi->wb);
+ cgwb_bdi_exit(bdi);
kfree(bdi);
}
{
kref_put(&bdi->refcnt, release_bdi);
}
-
-void bdi_destroy(struct backing_dev_info *bdi)
-{
- bdi_unregister(bdi);
- bdi_exit(bdi);
-}
-EXPORT_SYMBOL(bdi_destroy);
-
-/*
- * For use from filesystems to quickly init and register a bdi associated
- * with dirty writeback
- */
-int bdi_setup_and_register(struct backing_dev_info *bdi, char *name)
-{
- int err;
-
- bdi->name = name;
- bdi->capabilities = 0;
- err = bdi_init(bdi);
- if (err)
- return err;
-
- err = bdi_register(bdi, NULL, "%.28s-%ld", name,
- atomic_long_inc_return(&bdi_seq));
- if (err) {
- bdi_destroy(bdi);
- return err;
- }
-
- return 0;
-}
-EXPORT_SYMBOL(bdi_setup_and_register);
+EXPORT_SYMBOL(bdi_put);
static wait_queue_head_t congestion_wqh[2] = {
__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]),
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
- } else if (!memcmp("defer", buf,
- min(sizeof("defer")-1, count))) {
- clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
- clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
- clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
- set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
} else if (!memcmp("defer+madvise", buf,
min(sizeof("defer+madvise")-1, count))) {
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
+ } else if (!memcmp("defer", buf,
+ min(sizeof("defer")-1, count))) {
+ clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
+ clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
+ clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
+ set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
} else if (!memcmp("madvise", buf,
min(sizeof("madvise")-1, count))) {
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
deactivate_page(page);
if (pmd_young(orig_pmd) || pmd_dirty(orig_pmd)) {
- orig_pmd = pmdp_huge_get_and_clear_full(tlb->mm, addr, pmd,
- tlb->fullmm);
+ pmdp_invalidate(vma, addr, pmd);
orig_pmd = pmd_mkold(orig_pmd);
orig_pmd = pmd_mkclean(orig_pmd);
{
struct mm_struct *mm = vma->vm_mm;
spinlock_t *ptl;
- int ret = 0;
+ pmd_t entry;
+ bool preserve_write;
+ int ret;
ptl = __pmd_trans_huge_lock(pmd, vma);
- if (ptl) {
- pmd_t entry;
- bool preserve_write = prot_numa && pmd_write(*pmd);
- ret = 1;
+ if (!ptl)
+ return 0;
- /*
- * Avoid trapping faults against the zero page. The read-only
- * data is likely to be read-cached on the local CPU and
- * local/remote hits to the zero page are not interesting.
- */
- if (prot_numa && is_huge_zero_pmd(*pmd)) {
- spin_unlock(ptl);
- return ret;
- }
+ preserve_write = prot_numa && pmd_write(*pmd);
+ ret = 1;
- if (!prot_numa || !pmd_protnone(*pmd)) {
- entry = pmdp_huge_get_and_clear_notify(mm, addr, pmd);
- entry = pmd_modify(entry, newprot);
- if (preserve_write)
- entry = pmd_mk_savedwrite(entry);
- ret = HPAGE_PMD_NR;
- set_pmd_at(mm, addr, pmd, entry);
- BUG_ON(vma_is_anonymous(vma) && !preserve_write &&
- pmd_write(entry));
- }
- spin_unlock(ptl);
- }
+ /*
+ * Avoid trapping faults against the zero page. The read-only
+ * data is likely to be read-cached on the local CPU and
+ * local/remote hits to the zero page are not interesting.
+ */
+ if (prot_numa && is_huge_zero_pmd(*pmd))
+ goto unlock;
+
+ if (prot_numa && pmd_protnone(*pmd))
+ goto unlock;
+
+ /*
+ * In case prot_numa, we are under down_read(mmap_sem). It's critical
+ * to not clear pmd intermittently to avoid race with MADV_DONTNEED
+ * which is also under down_read(mmap_sem):
+ *
+ * CPU0: CPU1:
+ * change_huge_pmd(prot_numa=1)
+ * pmdp_huge_get_and_clear_notify()
+ * madvise_dontneed()
+ * zap_pmd_range()
+ * pmd_trans_huge(*pmd) == 0 (without ptl)
+ * // skip the pmd
+ * set_pmd_at();
+ * // pmd is re-established
+ *
+ * The race makes MADV_DONTNEED miss the huge pmd and don't clear it
+ * which may break userspace.
+ *
+ * pmdp_invalidate() is required to make sure we don't miss
+ * dirty/young flags set by hardware.
+ */
+ entry = *pmd;
+ pmdp_invalidate(vma, addr, pmd);
+ /*
+ * Recover dirty/young flags. It relies on pmdp_invalidate to not
+ * corrupt them.
+ */
+ if (pmd_dirty(*pmd))
+ entry = pmd_mkdirty(entry);
+ if (pmd_young(*pmd))
+ entry = pmd_mkyoung(entry);
+
+ entry = pmd_modify(entry, newprot);
+ if (preserve_write)
+ entry = pmd_mk_savedwrite(entry);
+ ret = HPAGE_PMD_NR;
+ set_pmd_at(mm, addr, pmd, entry);
+ BUG_ON(vma_is_anonymous(vma) && !preserve_write && pmd_write(entry));
+unlock:
+ spin_unlock(ptl);
return ret;
}
enum ttu_flags;
struct tlbflush_unmap_batch;
+
+/*
+ * only for MM internal work items which do not depend on
+ * any allocations or locks which might depend on allocations
+ */
+extern struct workqueue_struct *mm_percpu_wq;
+
#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
void try_to_unmap_flush(void);
void try_to_unmap_flush_dirty(void);
* get paged out, therefore we'll never actually fault, and the
* below annotations will generate false positives.
*/
- if (segment_eq(get_fs(), KERNEL_DS))
+ if (uaccess_kernel())
return;
if (pagefault_disabled())
return;
COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask,
compat_ulong_t, maxnode)
{
- long err = 0;
unsigned long __user *nm = NULL;
unsigned long nr_bits, alloc_size;
DECLARE_BITMAP(bm, MAX_NUMNODES);
alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;
if (nmask) {
- err = compat_get_bitmap(bm, nmask, nr_bits);
+ if (compat_get_bitmap(bm, nmask, nr_bits))
+ return -EFAULT;
nm = compat_alloc_user_space(alloc_size);
- err |= copy_to_user(nm, bm, alloc_size);
+ if (copy_to_user(nm, bm, alloc_size))
+ return -EFAULT;
}
- if (err)
- return -EFAULT;
-
return sys_set_mempolicy(mode, nm, nr_bits+1);
}
compat_ulong_t, mode, compat_ulong_t __user *, nmask,
compat_ulong_t, maxnode, compat_ulong_t, flags)
{
- long err = 0;
unsigned long __user *nm = NULL;
unsigned long nr_bits, alloc_size;
nodemask_t bm;
alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;
if (nmask) {
- err = compat_get_bitmap(nodes_addr(bm), nmask, nr_bits);
+ if (compat_get_bitmap(nodes_addr(bm), nmask, nr_bits))
+ return -EFAULT;
nm = compat_alloc_user_space(alloc_size);
- err |= copy_to_user(nm, nodes_addr(bm), alloc_size);
+ if (copy_to_user(nm, nodes_addr(bm), alloc_size))
+ return -EFAULT;
}
- if (err)
- return -EFAULT;
-
return sys_mbind(start, len, mode, nm, nr_bits+1, flags);
}
unlock_page(page);
put_page(page);
} else {
- putback_lru_page(page);
dec_node_page_state(page, NR_ISOLATED_ANON +
page_is_file_cache(page));
+ putback_lru_page(page);
}
}
}
{
int migratetype = 0;
int batch_free = 0;
- unsigned long nr_scanned, flags;
+ unsigned long nr_scanned;
bool isolated_pageblocks;
- spin_lock_irqsave(&zone->lock, flags);
+ spin_lock(&zone->lock);
isolated_pageblocks = has_isolate_pageblock(zone);
nr_scanned = node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED);
if (nr_scanned)
trace_mm_page_pcpu_drain(page, 0, mt);
} while (--count && --batch_free && !list_empty(list));
}
- spin_unlock_irqrestore(&zone->lock, flags);
+ spin_unlock(&zone->lock);
}
static void free_one_page(struct zone *zone,
unsigned int order,
int migratetype)
{
- unsigned long nr_scanned, flags;
- spin_lock_irqsave(&zone->lock, flags);
- __count_vm_events(PGFREE, 1 << order);
+ unsigned long nr_scanned;
+ spin_lock(&zone->lock);
nr_scanned = node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED);
if (nr_scanned)
__mod_node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED, -nr_scanned);
migratetype = get_pfnblock_migratetype(page, pfn);
}
__free_one_page(page, pfn, zone, order, migratetype);
- spin_unlock_irqrestore(&zone->lock, flags);
+ spin_unlock(&zone->lock);
}
static void __meminit __init_single_page(struct page *page, unsigned long pfn,
static void __free_pages_ok(struct page *page, unsigned int order)
{
+ unsigned long flags;
int migratetype;
unsigned long pfn = page_to_pfn(page);
return;
migratetype = get_pfnblock_migratetype(page, pfn);
+ local_irq_save(flags);
+ __count_vm_events(PGFREE, 1 << order);
free_one_page(page_zone(page), page, pfn, order, migratetype);
+ local_irq_restore(flags);
}
static void __init __free_pages_boot_core(struct page *page, unsigned int order)
int migratetype, bool cold)
{
int i, alloced = 0;
- unsigned long flags;
- spin_lock_irqsave(&zone->lock, flags);
+ spin_lock(&zone->lock);
for (i = 0; i < count; ++i) {
struct page *page = __rmqueue(zone, order, migratetype);
if (unlikely(page == NULL))
* pages added to the pcp list.
*/
__mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order));
- spin_unlock_irqrestore(&zone->lock, flags);
+ spin_unlock(&zone->lock);
return alloced;
}
*/
static cpumask_t cpus_with_pcps;
+ /*
+ * Make sure nobody triggers this path before mm_percpu_wq is fully
+ * initialized.
+ */
+ if (WARN_ON_ONCE(!mm_percpu_wq))
+ return;
+
/* Workqueues cannot recurse */
if (current->flags & PF_WQ_WORKER)
return;
for_each_cpu(cpu, &cpus_with_pcps) {
struct work_struct *work = per_cpu_ptr(&pcpu_drain, cpu);
INIT_WORK(work, drain_local_pages_wq);
- schedule_work_on(cpu, work);
+ queue_work_on(cpu, mm_percpu_wq, work);
}
for_each_cpu(cpu, &cpus_with_pcps)
flush_work(per_cpu_ptr(&pcpu_drain, cpu));
{
struct zone *zone = page_zone(page);
struct per_cpu_pages *pcp;
+ unsigned long flags;
unsigned long pfn = page_to_pfn(page);
int migratetype;
- if (in_interrupt()) {
- __free_pages_ok(page, 0);
- return;
- }
-
if (!free_pcp_prepare(page))
return;
migratetype = get_pfnblock_migratetype(page, pfn);
set_pcppage_migratetype(page, migratetype);
- preempt_disable();
+ local_irq_save(flags);
+ __count_vm_event(PGFREE);
/*
* We only track unmovable, reclaimable and movable on pcp lists.
migratetype = MIGRATE_MOVABLE;
}
- __count_vm_event(PGFREE);
pcp = &this_cpu_ptr(zone->pageset)->pcp;
if (!cold)
list_add(&page->lru, &pcp->lists[migratetype]);
}
out:
- preempt_enable();
+ local_irq_restore(flags);
}
/*
{
struct page *page;
- VM_BUG_ON(in_interrupt());
-
do {
if (list_empty(list)) {
pcp->count += rmqueue_bulk(zone, 0,
struct list_head *list;
bool cold = ((gfp_flags & __GFP_COLD) != 0);
struct page *page;
+ unsigned long flags;
- preempt_disable();
+ local_irq_save(flags);
pcp = &this_cpu_ptr(zone->pageset)->pcp;
list = &pcp->lists[migratetype];
page = __rmqueue_pcplist(zone, migratetype, cold, pcp, list);
__count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
zone_statistics(preferred_zone, zone);
}
- preempt_enable();
+ local_irq_restore(flags);
return page;
}
unsigned long flags;
struct page *page;
- if (likely(order == 0) && !in_interrupt()) {
+ if (likely(order == 0)) {
page = rmqueue_pcplist(preferred_zone, zone, order,
gfp_flags, migratetype);
goto out;
K(node_page_state(pgdat, NR_FILE_MAPPED)),
K(node_page_state(pgdat, NR_FILE_DIRTY)),
K(node_page_state(pgdat, NR_WRITEBACK)),
+ K(node_page_state(pgdat, NR_SHMEM)),
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
K(node_page_state(pgdat, NR_SHMEM_THPS) * HPAGE_PMD_NR),
K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED)
* HPAGE_PMD_NR),
K(node_page_state(pgdat, NR_ANON_THPS) * HPAGE_PMD_NR),
#endif
- K(node_page_state(pgdat, NR_SHMEM)),
K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
K(node_page_state(pgdat, NR_UNSTABLE_NFS)),
node_page_state(pgdat, NR_PAGES_SCANNED),
if (pvmw->pmd && !pvmw->pte)
return not_found(pvmw);
- /* Only for THP, seek to next pte entry makes sense */
- if (pvmw->pte) {
- if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page))
- return not_found(pvmw);
+ if (pvmw->pte)
goto next_pte;
- }
if (unlikely(PageHuge(pvmw->page))) {
/* when pud is not present, pte will be NULL */
while (1) {
if (check_pte(pvmw))
return true;
-next_pte: do {
+next_pte:
+ /* Seek to next pte only makes sense for THP */
+ if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page))
+ return not_found(pvmw);
+ do {
pvmw->address += PAGE_SIZE;
- if (pvmw->address >=
+ if (pvmw->address >= pvmw->vma->vm_end ||
+ pvmw->address >=
__vma_address(pvmw->page, pvmw->vma) +
hpage_nr_pages(pvmw->page) * PAGE_SIZE)
return not_found(pvmw);
}
EXPORT_SYMBOL_GPL(free_percpu);
-/**
- * is_kernel_percpu_address - test whether address is from static percpu area
- * @addr: address to test
- *
- * Test whether @addr belongs to in-kernel static percpu area. Module
- * static percpu areas are not considered. For those, use
- * is_module_percpu_address().
- *
- * RETURNS:
- * %true if @addr is from in-kernel static percpu area, %false otherwise.
- */
-bool is_kernel_percpu_address(unsigned long addr)
+bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr)
{
#ifdef CONFIG_SMP
const size_t static_size = __per_cpu_end - __per_cpu_start;
for_each_possible_cpu(cpu) {
void *start = per_cpu_ptr(base, cpu);
+ void *va = (void *)addr;
- if ((void *)addr >= start && (void *)addr < start + static_size)
+ if (va >= start && va < start + static_size) {
+ if (can_addr) {
+ *can_addr = (unsigned long) (va - start);
+ *can_addr += (unsigned long)
+ per_cpu_ptr(base, get_boot_cpu_id());
+ }
return true;
- }
+ }
+ }
#endif
/* on UP, can't distinguish from other static vars, always false */
return false;
}
/**
+ * is_kernel_percpu_address - test whether address is from static percpu area
+ * @addr: address to test
+ *
+ * Test whether @addr belongs to in-kernel static percpu area. Module
+ * static percpu areas are not considered. For those, use
+ * is_module_percpu_address().
+ *
+ * RETURNS:
+ * %true if @addr is from in-kernel static percpu area, %false otherwise.
+ */
+bool is_kernel_percpu_address(unsigned long addr)
+{
+ return __is_kernel_percpu_address(addr, NULL);
+}
+
+/**
* per_cpu_ptr_to_phys - convert translated percpu address to physical address
* @addr: the address to be converted to physical address
*
static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work);
-/*
- * lru_add_drain_wq is used to do lru_add_drain_all() from a WQ_MEM_RECLAIM
- * workqueue, aiding in getting memory freed.
- */
-static struct workqueue_struct *lru_add_drain_wq;
-
-static int __init lru_init(void)
-{
- lru_add_drain_wq = alloc_workqueue("lru-add-drain", WQ_MEM_RECLAIM, 0);
-
- if (WARN(!lru_add_drain_wq,
- "Failed to create workqueue lru_add_drain_wq"))
- return -ENOMEM;
-
- return 0;
-}
-early_initcall(lru_init);
-
void lru_add_drain_all(void)
{
static DEFINE_MUTEX(lock);
static struct cpumask has_work;
int cpu;
+ /*
+ * Make sure nobody triggers this path before mm_percpu_wq is fully
+ * initialized.
+ */
+ if (WARN_ON(!mm_percpu_wq))
+ return;
+
mutex_lock(&lock);
get_online_cpus();
cpumask_clear(&has_work);
pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) ||
need_activate_page_drain(cpu)) {
INIT_WORK(work, lru_add_drain_per_cpu);
- queue_work_on(cpu, lru_add_drain_wq, work);
+ queue_work_on(cpu, mm_percpu_wq, work);
cpumask_set_cpu(cpu, &has_work);
}
}
struct page *page = map[i];
if (page)
__free_page(page);
+ if (!(i % SWAP_CLUSTER_MAX))
+ cond_resched();
}
vfree(map);
}
#endif /* CONFIG_PROC_FS */
#ifdef CONFIG_SMP
-static struct workqueue_struct *vmstat_wq;
static DEFINE_PER_CPU(struct delayed_work, vmstat_work);
int sysctl_stat_interval __read_mostly = HZ;
* to occur in the future. Keep on running the
* update worker thread.
*/
- queue_delayed_work_on(smp_processor_id(), vmstat_wq,
+ queue_delayed_work_on(smp_processor_id(), mm_percpu_wq,
this_cpu_ptr(&vmstat_work),
round_jiffies_relative(sysctl_stat_interval));
}
struct delayed_work *dw = &per_cpu(vmstat_work, cpu);
if (!delayed_work_pending(dw) && need_update(cpu))
- queue_delayed_work_on(cpu, vmstat_wq, dw, 0);
+ queue_delayed_work_on(cpu, mm_percpu_wq, dw, 0);
}
put_online_cpus();
INIT_DEFERRABLE_WORK(per_cpu_ptr(&vmstat_work, cpu),
vmstat_update);
- vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
schedule_delayed_work(&shepherd,
round_jiffies_relative(sysctl_stat_interval));
}
#endif
+struct workqueue_struct *mm_percpu_wq;
+
void __init init_mm_internals(void)
{
-#ifdef CONFIG_SMP
- int ret;
+ int ret __maybe_unused;
+ mm_percpu_wq = alloc_workqueue("mm_percpu_wq", WQ_MEM_RECLAIM, 0);
+
+#ifdef CONFIG_SMP
ret = cpuhp_setup_state_nocalls(CPUHP_MM_VMSTAT_DEAD, "mm/vmstat:dead",
NULL, vmstat_cpu_dead);
if (ret < 0)
spin_lock(&zhdr->page_lock);
}
+/* Try to lock a z3fold page */
+static inline int z3fold_page_trylock(struct z3fold_header *zhdr)
+{
+ return spin_trylock(&zhdr->page_lock);
+}
+
/* Unlock a z3fold page */
static inline void z3fold_page_unlock(struct z3fold_header *zhdr)
{
spin_lock(&pool->lock);
zhdr = list_first_entry_or_null(&pool->unbuddied[i],
struct z3fold_header, buddy);
- if (!zhdr) {
+ if (!zhdr || !z3fold_page_trylock(zhdr)) {
spin_unlock(&pool->lock);
continue;
}
spin_unlock(&pool->lock);
page = virt_to_page(zhdr);
- z3fold_page_lock(zhdr);
if (zhdr->first_chunks == 0) {
if (zhdr->middle_chunks != 0 &&
chunks >= zhdr->start_middle)
struct zspage {
struct {
unsigned int fullness:FULLNESS_BITS;
- unsigned int class:CLASS_BITS;
+ unsigned int class:CLASS_BITS + 1;
unsigned int isolated:ISOLATED_BITS;
unsigned int magic:MAGIC_VAL_BITS;
};
trace_9p_protocol_dump(clnt, req->rc);
goto free_and_error;
}
+ if (rsize < count) {
+ pr_err("bogus RREADDIR count (%d > %d)\n", count, rsize);
+ count = rsize;
+ }
p9_debug(P9_DEBUG_9P, "<<< RREADDIR count %d\n", count);
return err;
}
+static void br_dev_uninit(struct net_device *dev)
+{
+ struct net_bridge *br = netdev_priv(dev);
+
+ br_multicast_dev_del(br);
+ br_multicast_uninit_stats(br);
+ br_vlan_flush(br);
+ free_percpu(br->stats);
+}
+
static int br_dev_open(struct net_device *dev)
{
struct net_bridge *br = netdev_priv(dev);
.ndo_open = br_dev_open,
.ndo_stop = br_dev_stop,
.ndo_init = br_dev_init,
+ .ndo_uninit = br_dev_uninit,
.ndo_start_xmit = br_dev_xmit,
.ndo_get_stats64 = br_get_stats64,
.ndo_set_mac_address = br_set_mac_address,
.ndo_features_check = passthru_features_check,
};
-static void br_dev_free(struct net_device *dev)
-{
- struct net_bridge *br = netdev_priv(dev);
-
- free_percpu(br->stats);
- free_netdev(dev);
-}
-
static struct device_type br_type = {
.name = "bridge",
};
ether_setup(dev);
dev->netdev_ops = &br_netdev_ops;
- dev->destructor = br_dev_free;
+ dev->destructor = free_netdev;
dev->ethtool_ops = &br_ethtool_ops;
SET_NETDEV_DEVTYPE(dev, &br_type);
dev->priv_flags = IFF_EBRIDGE | IFF_NO_QUEUE;
br_fdb_delete_by_port(br, NULL, 0, 1);
- br_vlan_flush(br);
- br_multicast_dev_del(br);
cancel_delayed_work_sync(&br->gc_work);
br_sysfs_delbr(br->dev);
out:
spin_unlock_bh(&br->multicast_lock);
-
- free_percpu(br->mcast_stats);
}
int br_multicast_set_router(struct net_bridge *br, unsigned long val)
return 0;
}
+void br_multicast_uninit_stats(struct net_bridge *br)
+{
+ free_percpu(br->mcast_stats);
+}
+
static void mcast_stats_add_dir(u64 *dst, u64 *src)
{
dst[BR_MCAST_DIR_RX] += src[BR_MCAST_DIR_RX];
spin_unlock_bh(&br->lock);
}
- err = br_changelink(dev, tb, data);
+ err = register_netdevice(dev);
if (err)
return err;
- return register_netdevice(dev);
+ err = br_changelink(dev, tb, data);
+ if (err)
+ unregister_netdevice(dev);
+ return err;
}
static size_t br_get_size(const struct net_device *brdev)
void br_multicast_count(struct net_bridge *br, const struct net_bridge_port *p,
const struct sk_buff *skb, u8 type, u8 dir);
int br_multicast_init_stats(struct net_bridge *br);
+void br_multicast_uninit_stats(struct net_bridge *br);
void br_multicast_get_stats(const struct net_bridge *br,
const struct net_bridge_port *p,
struct br_mcast_stats *dest);
return 0;
}
+static inline void br_multicast_uninit_stats(struct net_bridge *br)
+{
+}
+
static inline int br_multicast_igmp_type(const struct sk_buff *skb)
{
return 0;
struct iov_iter *to, int len)
{
int start = skb_headlen(skb);
- int i, copy = start - offset;
+ int i, copy = start - offset, start_off = offset, n;
struct sk_buff *frag_iter;
trace_skb_copy_datagram_iovec(skb, len);
if (copy > 0) {
if (copy > len)
copy = len;
- if (copy_to_iter(skb->data + offset, copy, to) != copy)
+ n = copy_to_iter(skb->data + offset, copy, to);
+ offset += n;
+ if (n != copy)
goto short_copy;
if ((len -= copy) == 0)
return 0;
- offset += copy;
}
/* Copy paged appendix. Hmm... why does this look so complicated? */
if ((copy = end - offset) > 0) {
if (copy > len)
copy = len;
- if (copy_page_to_iter(skb_frag_page(frag),
+ n = copy_page_to_iter(skb_frag_page(frag),
frag->page_offset + offset -
- start, copy, to) != copy)
+ start, copy, to);
+ offset += n;
+ if (n != copy)
goto short_copy;
if (!(len -= copy))
return 0;
- offset += copy;
}
start = end;
}
*/
fault:
+ iov_iter_revert(to, offset - start_off);
return -EFAULT;
short_copy:
__wsum *csump)
{
int start = skb_headlen(skb);
- int i, copy = start - offset;
+ int i, copy = start - offset, start_off = offset;
struct sk_buff *frag_iter;
int pos = 0;
int n;
if (copy > len)
copy = len;
n = csum_and_copy_to_iter(skb->data + offset, copy, csump, to);
+ offset += n;
if (n != copy)
goto fault;
if ((len -= copy) == 0)
return 0;
- offset += copy;
pos = copy;
}
offset - start, copy,
&csum2, to);
kunmap(page);
+ offset += n;
if (n != copy)
goto fault;
*csump = csum_block_add(*csump, csum2, pos);
if (!(len -= copy))
return 0;
- offset += copy;
pos += copy;
}
start = end;
return 0;
fault:
+ iov_iter_revert(to, offset - start_off);
return -EFAULT;
}
}
return 0;
csum_error:
+ iov_iter_revert(&msg->msg_iter, chunk);
return -EINVAL;
fault:
return -EFAULT;
{
unsigned long flags;
+ if (unlikely(!skb))
+ return;
+
if (likely(atomic_read(&skb->users) == 1)) {
smp_rmb();
atomic_set(&skb->users, 0);
*/
current->flags |= PF_MEMALLOC;
ret = __netif_receive_skb_core(skb, true);
- tsk_restore_flags(current, pflags, PF_MEMALLOC);
+ current_restore_flags(pflags, PF_MEMALLOC);
} else
ret = __netif_receive_skb_core(skb, false);
return err;
}
-EXPORT_SYMBOL(dev_change_xdp_fd);
/**
* dev_new_index - allocate an ifindex
unsigned char ar_tip[4];
} *arp_eth, _arp_eth;
const struct arphdr *arp;
- struct arphdr *_arp;
+ struct arphdr _arp;
arp = __skb_header_pointer(skb, nhoff, sizeof(_arp), data,
hlen, &_arp);
if (skb)
skb = skb_clone(skb, GFP_ATOMIC);
write_unlock(&neigh->lock);
- neigh->ops->solicit(neigh, skb);
+ if (neigh->ops->solicit)
+ neigh->ops->solicit(neigh, skb);
atomic_inc(&neigh->probes);
kfree_skb(skb);
}
while ((skb = skb_dequeue(&npinfo->txq))) {
struct net_device *dev = skb->dev;
struct netdev_queue *txq;
+ unsigned int q_index;
if (!netif_device_present(dev) || !netif_running(dev)) {
kfree_skb(skb);
continue;
}
- txq = skb_get_tx_queue(dev, skb);
-
local_irq_save(flags);
+ /* check if skb->queue_mapping is still valid */
+ q_index = skb_get_queue_mapping(skb);
+ if (unlikely(q_index >= dev->real_num_tx_queues)) {
+ q_index = q_index % dev->real_num_tx_queues;
+ skb_set_queue_mapping(skb, q_index);
+ }
+ txq = netdev_get_tx_queue(dev, q_index);
HARD_TX_LOCK(dev, txq, smp_processor_id());
if (netif_xmit_frozen_or_stopped(txq) ||
netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) {
#include <net/tcp.h>
static siphash_key_t net_secret __read_mostly;
+static siphash_key_t ts_secret __read_mostly;
static __always_inline void net_secret_init(void)
{
+ net_get_random_once(&ts_secret, sizeof(ts_secret));
net_get_random_once(&net_secret, sizeof(net_secret));
}
#endif
#endif
#if IS_ENABLED(CONFIG_IPV6)
+static u32 secure_tcpv6_ts_off(const __be32 *saddr, const __be32 *daddr)
+{
+ const struct {
+ struct in6_addr saddr;
+ struct in6_addr daddr;
+ } __aligned(SIPHASH_ALIGNMENT) combined = {
+ .saddr = *(struct in6_addr *)saddr,
+ .daddr = *(struct in6_addr *)daddr,
+ };
+
+ if (sysctl_tcp_timestamps != 1)
+ return 0;
+
+ return siphash(&combined, offsetofend(typeof(combined), daddr),
+ &ts_secret);
+}
+
u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
__be16 sport, __be16 dport, u32 *tsoff)
{
net_secret_init();
hash = siphash(&combined, offsetofend(typeof(combined), dport),
&net_secret);
- *tsoff = sysctl_tcp_timestamps == 1 ? (hash >> 32) : 0;
+ *tsoff = secure_tcpv6_ts_off(saddr, daddr);
return seq_scale(hash);
}
EXPORT_SYMBOL(secure_tcpv6_sequence_number);
#endif
#ifdef CONFIG_INET
+static u32 secure_tcp_ts_off(__be32 saddr, __be32 daddr)
+{
+ if (sysctl_tcp_timestamps != 1)
+ return 0;
+
+ return siphash_2u32((__force u32)saddr, (__force u32)daddr,
+ &ts_secret);
+}
/* secure_tcp_sequence_number(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d),
* but fortunately, `sport' cannot be 0 in any circumstances. If this changes,
hash = siphash_3u32((__force u32)saddr, (__force u32)daddr,
(__force u32)sport << 16 | (__force u32)dport,
&net_secret);
- *tsoff = sysctl_tcp_timestamps == 1 ? (hash >> 32) : 0;
+ *tsoff = secure_tcp_ts_off(saddr, daddr);
return seq_scale(hash);
}
skb_set_tail_pointer(skb, len);
}
+ if (!skb->sk || skb->destructor == sock_edemux)
+ skb_condense(skb);
return 0;
}
EXPORT_SYMBOL(___pskb_trim);
if (sg && csum && (mss != GSO_BY_FRAGS)) {
if (!(features & NETIF_F_GSO_PARTIAL)) {
struct sk_buff *iter;
+ unsigned int frag_len;
if (!list_skb ||
!net_gso_ok(features, skb_shinfo(head_skb)->gso_type))
goto normal;
- /* Split the buffer at the frag_list pointer.
- * This is based on the assumption that all
- * buffers in the chain excluding the last
- * containing the same amount of data.
+ /* If we get here then all the required
+ * GSO features except frag_list are supported.
+ * Try to split the SKB to multiple GSO SKBs
+ * with no frag_list.
+ * Currently we can do that only when the buffers don't
+ * have a linear part and all the buffers except
+ * the last are of the same length.
*/
+ frag_len = list_skb->len;
skb_walk_frags(head_skb, iter) {
+ if (frag_len != iter->len && iter->next)
+ goto normal;
if (skb_headlen(iter))
goto normal;
len -= iter->len;
}
+
+ if (len != frag_len)
+ goto normal;
}
/* GSO partial only requires that we trim off any excess that
serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING;
serr->ee.ee_info = tstype;
serr->opt_stats = opt_stats;
+ serr->header.h4.iif = skb->dev ? skb->dev->ifindex : 0;
if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) {
serr->ee.ee_data = skb_shinfo(skb)->tskey;
if (sk->sk_protocol == IPPROTO_TCP &&
current->flags |= PF_MEMALLOC;
ret = sk->sk_backlog_rcv(sk, skb);
- tsk_restore_flags(current, pflags, PF_MEMALLOC);
+ current_restore_flags(pflags, PF_MEMALLOC);
return ret;
}
.data = &sysctl_net_busy_poll,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = proc_dointvec
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
},
{
.procname = "busy_read",
.data = &sysctl_net_busy_read,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = proc_dointvec
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
},
#endif
#ifdef CONFIG_NET_SCHED
#include <linux/percpu.h>
#include <linux/init.h>
#include <linux/ratelimit.h>
+#include <linux/socket.h>
#include <net/sock.h>
#include <net/net_ratelimit.h>
+#include <net/ipv6.h>
#include <asm/byteorder.h>
#include <linux/uaccess.h>
}
EXPORT_SYMBOL(in6_pton);
+static int inet4_pton(const char *src, u16 port_num,
+ struct sockaddr_storage *addr)
+{
+ struct sockaddr_in *addr4 = (struct sockaddr_in *)addr;
+ int srclen = strlen(src);
+
+ if (srclen > INET_ADDRSTRLEN)
+ return -EINVAL;
+
+ if (in4_pton(src, srclen, (u8 *)&addr4->sin_addr.s_addr,
+ '\n', NULL) == 0)
+ return -EINVAL;
+
+ addr4->sin_family = AF_INET;
+ addr4->sin_port = htons(port_num);
+
+ return 0;
+}
+
+static int inet6_pton(struct net *net, const char *src, u16 port_num,
+ struct sockaddr_storage *addr)
+{
+ struct sockaddr_in6 *addr6 = (struct sockaddr_in6 *)addr;
+ const char *scope_delim;
+ int srclen = strlen(src);
+
+ if (srclen > INET6_ADDRSTRLEN)
+ return -EINVAL;
+
+ if (in6_pton(src, srclen, (u8 *)&addr6->sin6_addr.s6_addr,
+ '%', &scope_delim) == 0)
+ return -EINVAL;
+
+ if (ipv6_addr_type(&addr6->sin6_addr) & IPV6_ADDR_LINKLOCAL &&
+ src + srclen != scope_delim && *scope_delim == '%') {
+ struct net_device *dev;
+ char scope_id[16];
+ size_t scope_len = min_t(size_t, sizeof(scope_id) - 1,
+ src + srclen - scope_delim - 1);
+
+ memcpy(scope_id, scope_delim + 1, scope_len);
+ scope_id[scope_len] = '\0';
+
+ dev = dev_get_by_name(net, scope_id);
+ if (dev) {
+ addr6->sin6_scope_id = dev->ifindex;
+ dev_put(dev);
+ } else if (kstrtouint(scope_id, 0, &addr6->sin6_scope_id)) {
+ return -EINVAL;
+ }
+ }
+
+ addr6->sin6_family = AF_INET6;
+ addr6->sin6_port = htons(port_num);
+
+ return 0;
+}
+
+/**
+ * inet_pton_with_scope - convert an IPv4/IPv6 and port to socket address
+ * @net: net namespace (used for scope handling)
+ * @af: address family, AF_INET, AF_INET6 or AF_UNSPEC for either
+ * @src: the start of the address string
+ * @port: the start of the port string (or NULL for none)
+ * @addr: output socket address
+ *
+ * Return zero on success, return errno when any error occurs.
+ */
+int inet_pton_with_scope(struct net *net, __kernel_sa_family_t af,
+ const char *src, const char *port, struct sockaddr_storage *addr)
+{
+ u16 port_num;
+ int ret = -EINVAL;
+
+ if (port) {
+ if (kstrtou16(port, 0, &port_num))
+ return -EINVAL;
+ } else {
+ port_num = 0;
+ }
+
+ switch (af) {
+ case AF_INET:
+ ret = inet4_pton(src, port_num, addr);
+ break;
+ case AF_INET6:
+ ret = inet6_pton(net, src, port_num, addr);
+ break;
+ case AF_UNSPEC:
+ ret = inet4_pton(src, port_num, addr);
+ if (ret)
+ ret = inet6_pton(net, src, port_num, addr);
+ break;
+ default:
+ pr_err("unexpected address family %d\n", af);
+ };
+
+ return ret;
+}
+EXPORT_SYMBOL(inet_pton_with_scope);
+
void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb,
__be32 from, __be32 to, bool pseudohdr)
{
if (*(u8 *)iph != 0x45)
goto out_unlock;
+ if (ip_is_fragment(iph))
+ goto out_unlock;
+
if (unlikely(ip_fast_csum((u8 *)iph, 5)))
goto out_unlock;
return false;
/* Support IP_PKTINFO on tstamp packets if requested, to correlate
- * timestamp with egress dev. Not possible for packets without dev
+ * timestamp with egress dev. Not possible for packets without iif
* or without payload (SOF_TIMESTAMPING_OPT_TSONLY).
*/
- if ((!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG)) ||
- (!skb->dev))
+ info = PKTINFO_SKB_CB(skb);
+ if (!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG) ||
+ !info->ipi_ifindex)
return false;
- info = PKTINFO_SKB_CB(skb);
info->ipi_spec_dst.s_addr = ip_hdr(skb)->saddr;
- info->ipi_ifindex = skb->dev->ifindex;
return true;
}
case MCAST_LEAVE_GROUP:
case MCAST_LEAVE_SOURCE_GROUP:
case MCAST_UNBLOCK_SOURCE:
+ case IP_ROUTER_ALERT:
return true;
}
return false;
while ((d = next)) {
next = d->next;
dev = d->dev;
- if ((!ic_dev || dev != ic_dev->dev) && !netdev_uses_dsa(dev)) {
+ if (d != ic_dev && !netdev_uses_dsa(dev)) {
pr_debug("IP-Config: Downing %s\n", dev->name);
dev_change_flags(dev, d->flags);
}
struct net *net = sock_net(sk);
struct mr_table *mrt;
- rtnl_lock();
+ ASSERT_RTNL();
ipmr_for_each_table(mrt, net) {
if (sk == rtnl_dereference(mrt->mroute_sk)) {
IPV4_DEVCONF_ALL(net, MC_FORWARDING)--;
mroute_clean_tables(mrt, false);
}
}
- rtnl_unlock();
}
/* Socket options and virtual interface manipulation. The whole
if (sk != rcu_access_pointer(mrt->mroute_sk)) {
ret = -EACCES;
} else {
- /* We need to unlock here because mrtsock_destruct takes
- * care of rtnl itself and we can't change that due to
- * the IP_ROUTER_ALERT setsockopt which runs without it.
- */
- rtnl_unlock();
ret = ip_ra_control(sk, 0, NULL);
- goto out;
+ goto out_unlock;
}
break;
case MRT_ADD_VIF:
}
out_unlock:
rtnl_unlock();
-out:
return ret;
}
clusterip_config_put(cipinfo->config);
- nf_ct_netns_get(par->net, par->family);
+ nf_ct_netns_put(par->net, par->family);
}
#ifdef CONFIG_COMPAT
.timeout = 180,
};
-static struct nf_conntrack_helper snmp_helper __read_mostly = {
- .me = THIS_MODULE,
- .help = help,
- .expect_policy = &snmp_exp_policy,
- .name = "snmp",
- .tuple.src.l3num = AF_INET,
- .tuple.src.u.udp.port = cpu_to_be16(SNMP_PORT),
- .tuple.dst.protonum = IPPROTO_UDP,
-};
-
static struct nf_conntrack_helper snmp_trap_helper __read_mostly = {
.me = THIS_MODULE,
.help = help,
static int __init nf_nat_snmp_basic_init(void)
{
- int ret = 0;
-
BUG_ON(nf_nat_snmp_hook != NULL);
RCU_INIT_POINTER(nf_nat_snmp_hook, help);
- ret = nf_conntrack_helper_register(&snmp_trap_helper);
- if (ret < 0) {
- nf_conntrack_helper_unregister(&snmp_helper);
- return ret;
- }
- return ret;
+ return nf_conntrack_helper_register(&snmp_trap_helper);
}
static void __exit nf_nat_snmp_basic_fini(void)
{
RCU_INIT_POINTER(nf_nat_snmp_hook, NULL);
+ synchronize_rcu();
nf_conntrack_helper_unregister(&snmp_trap_helper);
}
void ping_unhash(struct sock *sk)
{
struct inet_sock *isk = inet_sk(sk);
+
pr_debug("ping_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num);
+ write_lock_bh(&ping_table.lock);
if (sk_hashed(sk)) {
- write_lock_bh(&ping_table.lock);
hlist_nulls_del(&sk->sk_nulls_node);
sk_nulls_node_init(&sk->sk_nulls_node);
sock_put(sk);
isk->inet_num = 0;
isk->inet_sport = 0;
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
- write_unlock_bh(&ping_table.lock);
}
+ write_unlock_bh(&ping_table.lock);
}
EXPORT_SYMBOL_GPL(ping_unhash);
/*
* Raw sockets may have direct kernel references. Kill them.
*/
+ rtnl_lock();
ip_ra_control(sk, 0, NULL);
+ rtnl_unlock();
sk_common_release(sk);
}
}
/* L3 master device is the loopback for that domain */
- dev_out = l3mdev_master_dev_rcu(dev_out) ? : net->loopback_dev;
+ dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(res)) ? :
+ net->loopback_dev;
fl4->flowi4_oif = dev_out->ifindex;
flags |= RTCF_LOCAL;
goto make_route;
skb_reset_network_header(skb);
/* Bugfix: need to give ip_route_input enough of an IP header to not gag. */
- ip_hdr(skb)->protocol = IPPROTO_ICMP;
+ ip_hdr(skb)->protocol = IPPROTO_UDP;
skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr));
src = tb[RTA_SRC] ? nla_get_in_addr(tb[RTA_SRC]) : 0;
tcp_init_send_head(sk);
memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
__sk_dst_reset(sk);
+ tcp_saved_syn_free(tp);
/* Clean up fastopen related fields */
tcp_free_fastopen_req(tp);
}
out:
rcu_read_unlock();
+ memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
- /* Clear out private data before diag gets it and
- * the ca has not been initialized.
- */
- if (ca->get_info)
- memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
if (ca->flags & TCP_CONG_NEEDS_ECN)
INET_ECN_xmit(sk);
else
tcp_cleanup_congestion_control(sk);
icsk->icsk_ca_ops = ca;
icsk->icsk_ca_setsockopt = 1;
+ memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
- if (sk->sk_state != TCP_CLOSE) {
- memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
+ if (sk->sk_state != TCP_CLOSE)
tcp_init_congestion_control(sk);
- }
}
/* Manage refcounts on socket close. */
#define REXMIT_LOST 1 /* retransmit packets marked lost */
#define REXMIT_NEW 2 /* FRTO-style transmit of unsent/new packets */
-static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb)
+static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb,
+ unsigned int len)
{
static bool __once __read_mostly;
rcu_read_lock();
dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif);
- pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n",
- dev ? dev->name : "Unknown driver");
+ if (!dev || len >= dev->mtu)
+ pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n",
+ dev ? dev->name : "Unknown driver");
rcu_read_unlock();
}
}
if (len >= icsk->icsk_ack.rcv_mss) {
icsk->icsk_ack.rcv_mss = min_t(unsigned int, len,
tcp_sk(sk)->advmss);
- if (unlikely(icsk->icsk_ack.rcv_mss != len))
- tcp_gro_dev_warn(sk, skb);
+ /* Account for possibly-removed options */
+ if (unlikely(len > icsk->icsk_ack.rcv_mss +
+ MAX_TCP_OPTION_SPACE))
+ tcp_gro_dev_warn(sk, skb, len);
} else {
/* Otherwise, we make more careful check taking into account,
* that SACKs block is variable.
const int ts)
{
struct tcp_sock *tp = tcp_sk(sk);
- if (metric > tp->reordering) {
- int mib_idx;
+ int mib_idx;
+ if (metric > tp->reordering) {
tp->reordering = min(sysctl_tcp_max_reordering, metric);
- /* This exciting event is worth to be remembered. 8) */
- if (ts)
- mib_idx = LINUX_MIB_TCPTSREORDER;
- else if (tcp_is_reno(tp))
- mib_idx = LINUX_MIB_TCPRENOREORDER;
- else if (tcp_is_fack(tp))
- mib_idx = LINUX_MIB_TCPFACKREORDER;
- else
- mib_idx = LINUX_MIB_TCPSACKREORDER;
-
- NET_INC_STATS(sock_net(sk), mib_idx);
#if FASTRETRANS_DEBUG > 1
pr_debug("Disorder%d %d %u f%u s%u rr%d\n",
tp->rx_opt.sack_ok, inet_csk(sk)->icsk_ca_state,
}
tp->rack.reord = 1;
+
+ /* This exciting event is worth to be remembered. 8) */
+ if (ts)
+ mib_idx = LINUX_MIB_TCPTSREORDER;
+ else if (tcp_is_reno(tp))
+ mib_idx = LINUX_MIB_TCPRENOREORDER;
+ else if (tcp_is_fack(tp))
+ mib_idx = LINUX_MIB_TCPFACKREORDER;
+ else
+ mib_idx = LINUX_MIB_TCPSACKREORDER;
+
+ NET_INC_STATS(sock_net(sk), mib_idx);
}
/* This must be called before lost_out is incremented */
struct tcp_sock *tp = tcp_sk(sk);
struct net *net = sock_net(sk);
struct sk_buff *skb;
+ bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery;
bool is_reneg; /* is receiver reneging on SACKs? */
bool mark_lost;
tp->high_seq = tp->snd_nxt;
tcp_ecn_queue_cwr(tp);
- /* F-RTO RFC5682 sec 3.1 step 1 mandates to disable F-RTO
- * if a previous recovery is underway, otherwise it may incorrectly
- * call a timeout spurious if some previously retransmitted packets
- * are s/acked (sec 3.2). We do not apply that retriction since
- * retransmitted skbs are permanently tagged with TCPCB_EVER_RETRANS
- * so FLAG_ORIG_SACK_ACKED is always correct. But we do disable F-RTO
- * on PTMU discovery to avoid sending new data.
+ /* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous
+ * loss recovery is underway except recurring timeout(s) on
+ * the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing
+ *
+ * In theory F-RTO can be used repeatedly during loss recovery.
+ * In practice this interacts badly with broken middle-boxes that
+ * falsely raise the receive window, which results in repeated
+ * timeouts and stop-and-go behavior.
*/
- tp->frto = sysctl_tcp_frto && !inet_csk(sk)->icsk_mtup.probe_size;
+ tp->frto = sysctl_tcp_frto &&
+ (new_recovery || icsk->icsk_retransmits) &&
+ !inet_csk(sk)->icsk_mtup.probe_size;
}
/* If ACK arrived pointing to a remembered SACK, it means that our
* eventually). The difference is that pulled data not copied, but
* immediately discarded.
*/
-static void __pskb_trim_head(struct sk_buff *skb, int len)
+static int __pskb_trim_head(struct sk_buff *skb, int len)
{
struct skb_shared_info *shinfo;
int i, k, eat;
__skb_pull(skb, eat);
len -= eat;
if (!len)
- return;
+ return 0;
}
eat = len;
k = 0;
skb_reset_tail_pointer(skb);
skb->data_len -= len;
skb->len = skb->data_len;
+ return len;
}
/* Remove acked data from a packet in the transmit queue. */
int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
{
+ u32 delta_truesize;
+
if (skb_unclone(skb, GFP_ATOMIC))
return -ENOMEM;
- __pskb_trim_head(skb, len);
+ delta_truesize = __pskb_trim_head(skb, len);
TCP_SKB_CB(skb)->seq += len;
skb->ip_summed = CHECKSUM_PARTIAL;
- skb->truesize -= len;
- sk->sk_wmem_queued -= len;
- sk_mem_uncharge(sk, len);
- sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
+ if (delta_truesize) {
+ skb->truesize -= delta_truesize;
+ sk->sk_wmem_queued -= delta_truesize;
+ sk_mem_uncharge(sk, delta_truesize);
+ sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
+ }
/* Any change of skb->len requires recalculation of tso factor. */
if (tcp_skb_pcount(skb) > 1)
{
struct sk_buff *skb;
+ TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS);
+
/* NOTE: No TCP options attached and we never retransmit this. */
skb = alloc_skb(MAX_TCP_HEADER, priority);
if (!skb) {
/* Send it off. */
if (tcp_transmit_skb(sk, skb, 0, priority))
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED);
-
- TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS);
}
/* Send a crossed SYN-ACK during socket establishment.
/* Account for retransmits that are lost again */
TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
tp->retrans_out -= tcp_skb_pcount(skb);
- NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT);
+ NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT,
+ tcp_skb_pcount(skb));
}
}
u16 mac_len = skb->mac_len;
int udp_offset, outer_hlen;
__wsum partial;
+ bool need_ipsec;
if (unlikely(!pskb_may_pull(skb, tnl_hlen)))
goto out;
ufo = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP);
+ need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb));
/* Try to offload checksum if possible */
offload_csum = !!(need_csum &&
+ !need_ipsec &&
(skb->dev->features &
(is_ipv6 ? (NETIF_F_HW_CSUM | NETIF_F_IPV6_CSUM) :
(NETIF_F_HW_CSUM | NETIF_F_IP_CSUM))));
static int fixup_permanent_addr(struct inet6_dev *idev,
struct inet6_ifaddr *ifp)
{
- if (!ifp->rt) {
- struct rt6_info *rt;
+ /* rt6i_ref == 0 means the host route was removed from the
+ * FIB, for example, if 'lo' device is taken down. In that
+ * case regenerate the host route.
+ */
+ if (!ifp->rt || !atomic_read(&ifp->rt->rt6i_ref)) {
+ struct rt6_info *rt, *prev;
rt = addrconf_dst_alloc(idev, &ifp->addr, false);
if (unlikely(IS_ERR(rt)))
return PTR_ERR(rt);
+ /* ifp->rt can be accessed outside of rtnl */
+ spin_lock(&ifp->lock);
+ prev = ifp->rt;
ifp->rt = rt;
+ spin_unlock(&ifp->lock);
+
+ ip6_rt_put(prev);
}
if (!(ifp->flags & IFA_F_NOPREFIXROUTE)) {
INIT_LIST_HEAD(&del_list);
list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) {
struct rt6_info *rt = NULL;
+ bool keep;
addrconf_del_dad_work(ifa);
+ keep = keep_addr && (ifa->flags & IFA_F_PERMANENT) &&
+ !addr_is_local(&ifa->addr);
+ if (!keep)
+ list_move(&ifa->if_list, &del_list);
+
write_unlock_bh(&idev->lock);
spin_lock_bh(&ifa->lock);
- if (keep_addr && (ifa->flags & IFA_F_PERMANENT) &&
- !addr_is_local(&ifa->addr)) {
+ if (keep) {
/* set state to skip the notifier below */
state = INET6_IFADDR_STATE_DEAD;
ifa->state = 0;
} else {
state = ifa->state;
ifa->state = INET6_IFADDR_STATE_DEAD;
-
- list_move(&ifa->if_list, &del_list);
}
spin_unlock_bh(&ifa->lock);
if (err)
goto igmp_fail;
- ipv6_stub = &ipv6_stub_impl;
-
err = ipv6_netfilter_init();
if (err)
goto netfilter_fail;
if (err)
goto sysctl_fail;
#endif
+
+ /* ensure that ipv6 stubs are visible only after ipv6 is ready */
+ wmb();
+ ipv6_stub = &ipv6_stub_impl;
out:
return err;
* At one point, excluding local errors was a quick test to identify icmp/icmp6
* errors. This is no longer true, but the test remained, so the v6 stack,
* unlike v4, also honors cmsg requests on all wifi and timestamp errors.
- *
- * Timestamp code paths do not initialize the fields expected by cmsg:
- * the PKTINFO fields in skb->cb[]. Fill those in here.
*/
static bool ip6_datagram_support_cmsg(struct sk_buff *skb,
struct sock_exterr_skb *serr)
if (serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL)
return false;
- if (!skb->dev)
+ if (!IP6CB(skb)->iif)
return false;
- if (skb->protocol == htons(ETH_P_IPV6))
- IP6CB(skb)->iif = skb->dev->ifindex;
- else
- PKTINFO_SKB_CB(skb)->ipi_ifindex = skb->dev->ifindex;
-
return true;
}
icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
((&hdr->segments_left) -
skb_network_header(skb)));
- kfree_skb(skb);
return -1;
}
{
switch (opt->type) {
case IPV6_SRCRT_TYPE_0:
+ case IPV6_SRCRT_STRICT:
+ case IPV6_SRCRT_TYPE_2:
ipv6_push_rthdr0(skb, proto, opt, addr_p, saddr);
break;
case IPV6_SRCRT_TYPE_4:
switch (opt->srcrt->type) {
case IPV6_SRCRT_TYPE_0:
+ case IPV6_SRCRT_STRICT:
+ case IPV6_SRCRT_TYPE_2:
fl6->daddr = *((struct rt0_hdr *)opt->srcrt)->addr;
break;
case IPV6_SRCRT_TYPE_4:
max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs));
/*
* RFC4291 2.5.3
+ * The loopback address must not be used as the source address in IPv6
+ * packets that are sent outside of a single node. [..]
* A packet received on an interface with a destination address
* of loopback must be dropped.
*/
- if (!(dev->flags & IFF_LOOPBACK) &&
- ipv6_addr_loopback(&hdr->daddr))
+ if ((ipv6_addr_loopback(&hdr->saddr) ||
+ ipv6_addr_loopback(&hdr->daddr)) &&
+ !(dev->flags & IFF_LOOPBACK))
goto err;
/* RFC4291 Errata ID: 3480
struct ip6_tnl *t = netdev_priv(dev);
struct net *net = t->net;
struct net_device_stats *stats = &t->dev->stats;
- struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+ struct ipv6hdr *ipv6h;
struct ipv6_tel_txoption opt;
struct dst_entry *dst = NULL, *ndst = NULL;
struct net_device *tdev;
/* NBMA tunnel */
if (ipv6_addr_any(&t->parms.raddr)) {
- struct in6_addr *addr6;
- struct neighbour *neigh;
- int addr_type;
+ if (skb->protocol == htons(ETH_P_IPV6)) {
+ struct in6_addr *addr6;
+ struct neighbour *neigh;
+ int addr_type;
- if (!skb_dst(skb))
- goto tx_err_link_failure;
+ if (!skb_dst(skb))
+ goto tx_err_link_failure;
- neigh = dst_neigh_lookup(skb_dst(skb),
- &ipv6_hdr(skb)->daddr);
- if (!neigh)
- goto tx_err_link_failure;
+ neigh = dst_neigh_lookup(skb_dst(skb),
+ &ipv6_hdr(skb)->daddr);
+ if (!neigh)
+ goto tx_err_link_failure;
- addr6 = (struct in6_addr *)&neigh->primary_key;
- addr_type = ipv6_addr_type(addr6);
+ addr6 = (struct in6_addr *)&neigh->primary_key;
+ addr_type = ipv6_addr_type(addr6);
- if (addr_type == IPV6_ADDR_ANY)
- addr6 = &ipv6_hdr(skb)->daddr;
+ if (addr_type == IPV6_ADDR_ANY)
+ addr6 = &ipv6_hdr(skb)->daddr;
- memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));
- neigh_release(neigh);
+ memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));
+ neigh_release(neigh);
+ }
} else if (!(t->parms.flags &
(IP6_TNL_F_USE_ORIG_TCLASS | IP6_TNL_F_USE_ORIG_FWMARK))) {
/* enable the cache only only if the routing decision does
* Delete a VIF entry
*/
-static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head)
+static int mif6_delete(struct mr6_table *mrt, int vifi, int notify,
+ struct list_head *head)
{
struct mif_device *v;
struct net_device *dev;
dev->ifindex, &in6_dev->cnf);
}
- if (v->flags & MIFF_REGISTER)
+ if ((v->flags & MIFF_REGISTER) && !notify)
unregister_netdevice_queue(dev, head);
dev_put(dev);
struct mr6_table *mrt;
struct mif_device *v;
int ct;
- LIST_HEAD(list);
if (event != NETDEV_UNREGISTER)
return NOTIFY_DONE;
v = &mrt->vif6_table[0];
for (ct = 0; ct < mrt->maxvif; ct++, v++) {
if (v->dev == dev)
- mif6_delete(mrt, ct, &list);
+ mif6_delete(mrt, ct, 1, NULL);
}
}
- unregister_netdevice_many(&list);
return NOTIFY_DONE;
}
for (i = 0; i < mrt->maxvif; i++) {
if (!all && (mrt->vif6_table[i].flags & VIFF_STATIC))
continue;
- mif6_delete(mrt, i, &list);
+ mif6_delete(mrt, i, 0, &list);
}
unregister_netdevice_many(&list);
if (copy_from_user(&mifi, optval, sizeof(mifi_t)))
return -EFAULT;
rtnl_lock();
- ret = mif6_delete(mrt, mifi, NULL);
+ ret = mif6_delete(mrt, mifi, 0, NULL);
rtnl_unlock();
return ret;
idev = in6_dev_get(dev);
if (!idev)
break;
- if (idev->cnf.ndisc_notify)
+ if (idev->cnf.ndisc_notify ||
+ net->ipv6.devconf_all->ndisc_notify)
ndisc_send_unsol_na(dev);
in6_dev_put(idev);
break;
spin_lock_bh(&sk->sk_receive_queue.lock);
skb = skb_peek(&sk->sk_receive_queue);
if (skb)
- amount = skb_tail_pointer(skb) -
- skb_transport_header(skb);
+ amount = skb->len;
spin_unlock_bh(&sk->sk_receive_queue.lock);
return put_user(amount, (int __user *)arg);
}
int addr_type;
int err = -EINVAL;
+ /* RTF_PCPU is an internal flag; can not be set by userspace */
+ if (cfg->fc_flags & RTF_PCPU)
+ goto out;
+
if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128)
goto out;
#ifndef CONFIG_IPV6_SUBTREES
struct sr6_tlv *tlv;
unsigned int tlv_len;
+ if (trailing < sizeof(*tlv))
+ return false;
+
tlv = (struct sr6_tlv *)((unsigned char *)srh + tlv_offset);
tlv_len = sizeof(*tlv) + tlv->len;
struct kcm_attach info;
if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
- err = -EFAULT;
+ return -EFAULT;
err = kcm_attach_ioctl(sock, &info);
struct kcm_unattach info;
if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
- err = -EFAULT;
+ return -EFAULT;
err = kcm_unattach_ioctl(sock, &info);
struct socket *newsock = NULL;
if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
- err = -EFAULT;
+ return -EFAULT;
err = kcm_clone(sock, &info, &newsock);
} u;
struct sk_buff *skb;
} dump;
+ struct mutex dump_lock;
};
+static int parse_sockaddr_pair(struct sockaddr *sa, int ext_len,
+ xfrm_address_t *saddr, xfrm_address_t *daddr,
+ u16 *family);
+
static inline struct pfkey_sock *pfkey_sk(struct sock *sk)
{
return (struct pfkey_sock *)sk;
{
struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id);
struct sock *sk;
+ struct pfkey_sock *pfk;
int err;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
if (sk == NULL)
goto out;
+ pfk = pfkey_sk(sk);
+ mutex_init(&pfk->dump_lock);
+
sock->ops = &pfkey_ops;
sock_init_data(sock, sk);
struct sadb_msg *hdr;
int rc;
+ mutex_lock(&pfk->dump_lock);
+ if (!pfk->dump.dump) {
+ rc = 0;
+ goto out;
+ }
+
rc = pfk->dump.dump(pfk);
- if (rc == -ENOBUFS)
- return 0;
+ if (rc == -ENOBUFS) {
+ rc = 0;
+ goto out;
+ }
if (pfk->dump.skb) {
- if (!pfkey_can_dump(&pfk->sk))
- return 0;
+ if (!pfkey_can_dump(&pfk->sk)) {
+ rc = 0;
+ goto out;
+ }
hdr = (struct sadb_msg *) pfk->dump.skb->data;
hdr->sadb_msg_seq = 0;
}
pfkey_terminate_dump(pfk);
+
+out:
+ mutex_unlock(&pfk->dump_lock);
return rc;
}
struct xfrm_address_filter *filter = NULL;
struct pfkey_sock *pfk = pfkey_sk(sk);
- if (pfk->dump.dump != NULL)
+ mutex_lock(&pfk->dump_lock);
+ if (pfk->dump.dump != NULL) {
+ mutex_unlock(&pfk->dump_lock);
return -EBUSY;
+ }
proto = pfkey_satype2proto(hdr->sadb_msg_satype);
- if (proto == 0)
+ if (proto == 0) {
+ mutex_unlock(&pfk->dump_lock);
return -EINVAL;
+ }
if (ext_hdrs[SADB_X_EXT_FILTER - 1]) {
struct sadb_x_filter *xfilter = ext_hdrs[SADB_X_EXT_FILTER - 1];
filter = kmalloc(sizeof(*filter), GFP_KERNEL);
- if (filter == NULL)
+ if (filter == NULL) {
+ mutex_unlock(&pfk->dump_lock);
return -ENOMEM;
+ }
memcpy(&filter->saddr, &xfilter->sadb_x_filter_saddr,
sizeof(xfrm_address_t));
pfk->dump.dump = pfkey_dump_sa;
pfk->dump.done = pfkey_dump_sa_done;
xfrm_state_walk_init(&pfk->dump.u.state, proto, filter);
+ mutex_unlock(&pfk->dump_lock);
return pfkey_do_dump(pfk);
}
/* addresses present only in tunnel mode */
if (t->mode == XFRM_MODE_TUNNEL) {
- u8 *sa = (u8 *) (rq + 1);
- int family, socklen;
+ int err;
- family = pfkey_sockaddr_extract((struct sockaddr *)sa,
- &t->saddr);
- if (!family)
- return -EINVAL;
-
- socklen = pfkey_sockaddr_len(family);
- if (pfkey_sockaddr_extract((struct sockaddr *)(sa + socklen),
- &t->id.daddr) != family)
- return -EINVAL;
- t->encap_family = family;
+ err = parse_sockaddr_pair(
+ (struct sockaddr *)(rq + 1),
+ rq->sadb_x_ipsecrequest_len - sizeof(*rq),
+ &t->saddr, &t->id.daddr, &t->encap_family);
+ if (err)
+ return err;
} else
t->encap_family = xp->family;
if (pol->sadb_x_policy_len * 8 < sizeof(struct sadb_x_policy))
return -EINVAL;
- while (len >= sizeof(struct sadb_x_ipsecrequest)) {
+ while (len >= sizeof(*rq)) {
+ if (len < rq->sadb_x_ipsecrequest_len ||
+ rq->sadb_x_ipsecrequest_len < sizeof(*rq))
+ return -EINVAL;
+
if ((err = parse_ipsecrequest(xp, rq)) < 0)
return err;
len -= rq->sadb_x_ipsecrequest_len;
return err;
}
-#ifdef CONFIG_NET_KEY_MIGRATE
static int pfkey_sockaddr_pair_size(sa_family_t family)
{
return PFKEY_ALIGN8(pfkey_sockaddr_len(family) * 2);
{
int af, socklen;
- if (ext_len < pfkey_sockaddr_pair_size(sa->sa_family))
+ if (ext_len < 2 || ext_len < pfkey_sockaddr_pair_size(sa->sa_family))
return -EINVAL;
af = pfkey_sockaddr_extract(sa, saddr);
return 0;
}
+#ifdef CONFIG_NET_KEY_MIGRATE
static int ipsecrequests_to_migrate(struct sadb_x_ipsecrequest *rq1, int len,
struct xfrm_migrate *m)
{
struct sadb_x_ipsecrequest *rq2;
int mode;
- if (len <= sizeof(struct sadb_x_ipsecrequest) ||
- len < rq1->sadb_x_ipsecrequest_len)
+ if (len < sizeof(*rq1) ||
+ len < rq1->sadb_x_ipsecrequest_len ||
+ rq1->sadb_x_ipsecrequest_len < sizeof(*rq1))
return -EINVAL;
/* old endoints */
err = parse_sockaddr_pair((struct sockaddr *)(rq1 + 1),
- rq1->sadb_x_ipsecrequest_len,
+ rq1->sadb_x_ipsecrequest_len - sizeof(*rq1),
&m->old_saddr, &m->old_daddr,
&m->old_family);
if (err)
rq2 = (struct sadb_x_ipsecrequest *)((u8 *)rq1 + rq1->sadb_x_ipsecrequest_len);
len -= rq1->sadb_x_ipsecrequest_len;
- if (len <= sizeof(struct sadb_x_ipsecrequest) ||
- len < rq2->sadb_x_ipsecrequest_len)
+ if (len <= sizeof(*rq2) ||
+ len < rq2->sadb_x_ipsecrequest_len ||
+ rq2->sadb_x_ipsecrequest_len < sizeof(*rq2))
return -EINVAL;
/* new endpoints */
err = parse_sockaddr_pair((struct sockaddr *)(rq2 + 1),
- rq2->sadb_x_ipsecrequest_len,
+ rq2->sadb_x_ipsecrequest_len - sizeof(*rq2),
&m->new_saddr, &m->new_daddr,
&m->new_family);
if (err)
{
struct pfkey_sock *pfk = pfkey_sk(sk);
- if (pfk->dump.dump != NULL)
+ mutex_lock(&pfk->dump_lock);
+ if (pfk->dump.dump != NULL) {
+ mutex_unlock(&pfk->dump_lock);
return -EBUSY;
+ }
pfk->dump.msg_version = hdr->sadb_msg_version;
pfk->dump.msg_portid = hdr->sadb_msg_pid;
pfk->dump.dump = pfkey_dump_sp;
pfk->dump.done = pfkey_dump_sp_done;
xfrm_policy_walk_init(&pfk->dump.u.policy, XFRM_POLICY_TYPE_MAIN);
+ mutex_unlock(&pfk->dump_lock);
return pfkey_do_dump(pfk);
}
}
EXPORT_SYMBOL_GPL(l2tp_session_find);
-struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth)
+/* Like l2tp_session_find() but takes a reference on the returned session.
+ * Optionally calls session->ref() too if do_ref is true.
+ */
+struct l2tp_session *l2tp_session_get(struct net *net,
+ struct l2tp_tunnel *tunnel,
+ u32 session_id, bool do_ref)
+{
+ struct hlist_head *session_list;
+ struct l2tp_session *session;
+
+ if (!tunnel) {
+ struct l2tp_net *pn = l2tp_pernet(net);
+
+ session_list = l2tp_session_id_hash_2(pn, session_id);
+
+ rcu_read_lock_bh();
+ hlist_for_each_entry_rcu(session, session_list, global_hlist) {
+ if (session->session_id == session_id) {
+ l2tp_session_inc_refcount(session);
+ if (do_ref && session->ref)
+ session->ref(session);
+ rcu_read_unlock_bh();
+
+ return session;
+ }
+ }
+ rcu_read_unlock_bh();
+
+ return NULL;
+ }
+
+ session_list = l2tp_session_id_hash(tunnel, session_id);
+ read_lock_bh(&tunnel->hlist_lock);
+ hlist_for_each_entry(session, session_list, hlist) {
+ if (session->session_id == session_id) {
+ l2tp_session_inc_refcount(session);
+ if (do_ref && session->ref)
+ session->ref(session);
+ read_unlock_bh(&tunnel->hlist_lock);
+
+ return session;
+ }
+ }
+ read_unlock_bh(&tunnel->hlist_lock);
+
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(l2tp_session_get);
+
+struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth,
+ bool do_ref)
{
int hash;
struct l2tp_session *session;
for (hash = 0; hash < L2TP_HASH_SIZE; hash++) {
hlist_for_each_entry(session, &tunnel->session_hlist[hash], hlist) {
if (++count > nth) {
+ l2tp_session_inc_refcount(session);
+ if (do_ref && session->ref)
+ session->ref(session);
read_unlock_bh(&tunnel->hlist_lock);
return session;
}
return NULL;
}
-EXPORT_SYMBOL_GPL(l2tp_session_find_nth);
+EXPORT_SYMBOL_GPL(l2tp_session_get_nth);
/* Lookup a session by interface name.
* This is very inefficient but is only used by management interfaces.
*/
-struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname)
+struct l2tp_session *l2tp_session_get_by_ifname(struct net *net, char *ifname,
+ bool do_ref)
{
struct l2tp_net *pn = l2tp_pernet(net);
int hash;
for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) {
hlist_for_each_entry_rcu(session, &pn->l2tp_session_hlist[hash], global_hlist) {
if (!strcmp(session->ifname, ifname)) {
+ l2tp_session_inc_refcount(session);
+ if (do_ref && session->ref)
+ session->ref(session);
rcu_read_unlock_bh();
+
return session;
}
}
return NULL;
}
-EXPORT_SYMBOL_GPL(l2tp_session_find_by_ifname);
+EXPORT_SYMBOL_GPL(l2tp_session_get_by_ifname);
+
+static int l2tp_session_add_to_tunnel(struct l2tp_tunnel *tunnel,
+ struct l2tp_session *session)
+{
+ struct l2tp_session *session_walk;
+ struct hlist_head *g_head;
+ struct hlist_head *head;
+ struct l2tp_net *pn;
+
+ head = l2tp_session_id_hash(tunnel, session->session_id);
+
+ write_lock_bh(&tunnel->hlist_lock);
+ hlist_for_each_entry(session_walk, head, hlist)
+ if (session_walk->session_id == session->session_id)
+ goto exist;
+
+ if (tunnel->version == L2TP_HDR_VER_3) {
+ pn = l2tp_pernet(tunnel->l2tp_net);
+ g_head = l2tp_session_id_hash_2(l2tp_pernet(tunnel->l2tp_net),
+ session->session_id);
+
+ spin_lock_bh(&pn->l2tp_session_hlist_lock);
+ hlist_for_each_entry(session_walk, g_head, global_hlist)
+ if (session_walk->session_id == session->session_id)
+ goto exist_glob;
+
+ hlist_add_head_rcu(&session->global_hlist, g_head);
+ spin_unlock_bh(&pn->l2tp_session_hlist_lock);
+ }
+
+ hlist_add_head(&session->hlist, head);
+ write_unlock_bh(&tunnel->hlist_lock);
+
+ return 0;
+
+exist_glob:
+ spin_unlock_bh(&pn->l2tp_session_hlist_lock);
+exist:
+ write_unlock_bh(&tunnel->hlist_lock);
+
+ return -EEXIST;
+}
/* Lookup a tunnel by id
*/
* a data (not control) frame before coming here. Fields up to the
* session-id have already been parsed and ptr points to the data
* after the session-id.
+ *
+ * session->ref() must have been called prior to l2tp_recv_common().
+ * session->deref() will be called automatically after skb is processed.
*/
void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
unsigned char *ptr, unsigned char *optr, u16 hdrflags,
int offset;
u32 ns, nr;
- /* The ref count is increased since we now hold a pointer to
- * the session. Take care to decrement the refcnt when exiting
- * this function from now on...
- */
- l2tp_session_inc_refcount(session);
- if (session->ref)
- (*session->ref)(session);
-
/* Parse and check optional cookie */
if (session->peer_cookie_len > 0) {
if (memcmp(ptr, &session->peer_cookie[0], session->peer_cookie_len)) {
/* Try to dequeue as many skbs from reorder_q as we can. */
l2tp_recv_dequeue(session);
- l2tp_session_dec_refcount(session);
-
return;
discard:
if (session->deref)
(*session->deref)(session);
-
- l2tp_session_dec_refcount(session);
}
EXPORT_SYMBOL(l2tp_recv_common);
}
/* Find the session context */
- session = l2tp_session_find(tunnel->l2tp_net, tunnel, session_id);
+ session = l2tp_session_get(tunnel->l2tp_net, tunnel, session_id, true);
if (!session || !session->recv_skb) {
+ if (session) {
+ if (session->deref)
+ session->deref(session);
+ l2tp_session_dec_refcount(session);
+ }
+
/* Not found? Pass to userspace to deal with */
l2tp_info(tunnel, L2TP_MSG_DATA,
"%s: no session found (%u/%u). Passing up.\n",
}
l2tp_recv_common(session, skb, ptr, optr, hdrflags, length, payload_hook);
+ l2tp_session_dec_refcount(session);
return 0;
struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg)
{
struct l2tp_session *session;
+ int err;
session = kzalloc(sizeof(struct l2tp_session) + priv_size, GFP_KERNEL);
if (session != NULL) {
l2tp_session_set_header_len(session, tunnel->version);
+ err = l2tp_session_add_to_tunnel(tunnel, session);
+ if (err) {
+ kfree(session);
+
+ return ERR_PTR(err);
+ }
+
/* Bump the reference count. The session context is deleted
* only when this drops to zero.
*/
/* Ensure tunnel socket isn't deleted */
sock_hold(tunnel->sock);
- /* Add session to the tunnel's hash list */
- write_lock_bh(&tunnel->hlist_lock);
- hlist_add_head(&session->hlist,
- l2tp_session_id_hash(tunnel, session_id));
- write_unlock_bh(&tunnel->hlist_lock);
-
- /* And to the global session list if L2TPv3 */
- if (tunnel->version != L2TP_HDR_VER_2) {
- struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net);
-
- spin_lock_bh(&pn->l2tp_session_hlist_lock);
- hlist_add_head_rcu(&session->global_hlist,
- l2tp_session_id_hash_2(pn, session_id));
- spin_unlock_bh(&pn->l2tp_session_hlist_lock);
- }
-
/* Ignore management session in session count value */
if (session->session_id != 0)
atomic_inc(&l2tp_session_count);
+
+ return session;
}
- return session;
+ return ERR_PTR(-ENOMEM);
}
EXPORT_SYMBOL_GPL(l2tp_session_create);
return tunnel;
}
+struct l2tp_session *l2tp_session_get(struct net *net,
+ struct l2tp_tunnel *tunnel,
+ u32 session_id, bool do_ref);
struct l2tp_session *l2tp_session_find(struct net *net,
struct l2tp_tunnel *tunnel,
u32 session_id);
-struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth);
-struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname);
+struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth,
+ bool do_ref);
+struct l2tp_session *l2tp_session_get_by_ifname(struct net *net, char *ifname,
+ bool do_ref);
struct l2tp_tunnel *l2tp_tunnel_find(struct net *net, u32 tunnel_id);
struct l2tp_tunnel *l2tp_tunnel_find_nth(struct net *net, int nth);
static void l2tp_dfs_next_session(struct l2tp_dfs_seq_data *pd)
{
- pd->session = l2tp_session_find_nth(pd->tunnel, pd->session_idx);
+ pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx, true);
pd->session_idx++;
if (pd->session == NULL) {
}
/* Show the tunnel or session context */
- if (pd->session == NULL)
+ if (!pd->session) {
l2tp_dfs_seq_tunnel_show(m, pd->tunnel);
- else
+ } else {
l2tp_dfs_seq_session_show(m, pd->session);
+ if (pd->session->deref)
+ pd->session->deref(pd->session);
+ l2tp_session_dec_refcount(pd->session);
+ }
out:
return 0;
goto out;
}
- session = l2tp_session_find(net, tunnel, session_id);
- if (session) {
- rc = -EEXIST;
- goto out;
- }
-
if (cfg->ifname) {
dev = dev_get_by_name(net, cfg->ifname);
if (dev) {
session = l2tp_session_create(sizeof(*spriv), tunnel, session_id,
peer_session_id, cfg);
- if (!session) {
- rc = -ENOMEM;
+ if (IS_ERR(session)) {
+ rc = PTR_ERR(session);
goto out;
}
}
/* Ok, this is a data packet. Lookup the session. */
- session = l2tp_session_find(net, NULL, session_id);
- if (session == NULL)
+ session = l2tp_session_get(net, NULL, session_id, true);
+ if (!session)
goto discard;
tunnel = session->tunnel;
- if (tunnel == NULL)
- goto discard;
+ if (!tunnel)
+ goto discard_sess;
/* Trace packet contents, if enabled */
if (tunnel->debug & L2TP_MSG_DATA) {
length = min(32u, skb->len);
if (!pskb_may_pull(skb, length))
- goto discard;
+ goto discard_sess;
/* Point to L2TP header */
optr = ptr = skb->data;
}
l2tp_recv_common(session, skb, ptr, optr, 0, skb->len, tunnel->recv_payload_hook);
+ l2tp_session_dec_refcount(session);
return 0;
tunnel_id = ntohl(*(__be32 *) &skb->data[4]);
tunnel = l2tp_tunnel_find(net, tunnel_id);
- if (tunnel != NULL)
+ if (tunnel) {
sk = tunnel->sock;
- else {
+ sock_hold(sk);
+ } else {
struct iphdr *iph = (struct iphdr *) skb_network_header(skb);
read_lock_bh(&l2tp_ip_lock);
return sk_receive_skb(sk, skb, 1);
+discard_sess:
+ if (session->deref)
+ session->deref(session);
+ l2tp_session_dec_refcount(session);
+ goto discard;
+
discard_put:
sock_put(sk);
}
/* Ok, this is a data packet. Lookup the session. */
- session = l2tp_session_find(net, NULL, session_id);
- if (session == NULL)
+ session = l2tp_session_get(net, NULL, session_id, true);
+ if (!session)
goto discard;
tunnel = session->tunnel;
- if (tunnel == NULL)
- goto discard;
+ if (!tunnel)
+ goto discard_sess;
/* Trace packet contents, if enabled */
if (tunnel->debug & L2TP_MSG_DATA) {
length = min(32u, skb->len);
if (!pskb_may_pull(skb, length))
- goto discard;
+ goto discard_sess;
/* Point to L2TP header */
optr = ptr = skb->data;
l2tp_recv_common(session, skb, ptr, optr, 0, skb->len,
tunnel->recv_payload_hook);
+ l2tp_session_dec_refcount(session);
+
return 0;
pass_up:
tunnel_id = ntohl(*(__be32 *) &skb->data[4]);
tunnel = l2tp_tunnel_find(net, tunnel_id);
- if (tunnel != NULL)
+ if (tunnel) {
sk = tunnel->sock;
- else {
+ sock_hold(sk);
+ } else {
struct ipv6hdr *iph = ipv6_hdr(skb);
read_lock_bh(&l2tp_ip6_lock);
return sk_receive_skb(sk, skb, 1);
+discard_sess:
+ if (session->deref)
+ session->deref(session);
+ l2tp_session_dec_refcount(session);
+ goto discard;
+
discard_put:
sock_put(sk);
/* Accessed under genl lock */
static const struct l2tp_nl_cmd_ops *l2tp_nl_cmd_ops[__L2TP_PWTYPE_MAX];
-static struct l2tp_session *l2tp_nl_session_find(struct genl_info *info)
+static struct l2tp_session *l2tp_nl_session_get(struct genl_info *info,
+ bool do_ref)
{
u32 tunnel_id;
u32 session_id;
if (info->attrs[L2TP_ATTR_IFNAME]) {
ifname = nla_data(info->attrs[L2TP_ATTR_IFNAME]);
- session = l2tp_session_find_by_ifname(net, ifname);
+ session = l2tp_session_get_by_ifname(net, ifname, do_ref);
} else if ((info->attrs[L2TP_ATTR_SESSION_ID]) &&
(info->attrs[L2TP_ATTR_CONN_ID])) {
tunnel_id = nla_get_u32(info->attrs[L2TP_ATTR_CONN_ID]);
session_id = nla_get_u32(info->attrs[L2TP_ATTR_SESSION_ID]);
tunnel = l2tp_tunnel_find(net, tunnel_id);
if (tunnel)
- session = l2tp_session_find(net, tunnel, session_id);
+ session = l2tp_session_get(net, tunnel, session_id,
+ do_ref);
}
return session;
session_id, peer_session_id, &cfg);
if (ret >= 0) {
- session = l2tp_session_find(net, tunnel, session_id);
- if (session)
+ session = l2tp_session_get(net, tunnel, session_id, false);
+ if (session) {
ret = l2tp_session_notify(&l2tp_nl_family, info, session,
L2TP_CMD_SESSION_CREATE);
+ l2tp_session_dec_refcount(session);
+ }
}
out:
struct l2tp_session *session;
u16 pw_type;
- session = l2tp_nl_session_find(info);
+ session = l2tp_nl_session_get(info, true);
if (session == NULL) {
ret = -ENODEV;
goto out;
if (l2tp_nl_cmd_ops[pw_type] && l2tp_nl_cmd_ops[pw_type]->session_delete)
ret = (*l2tp_nl_cmd_ops[pw_type]->session_delete)(session);
+ if (session->deref)
+ session->deref(session);
+ l2tp_session_dec_refcount(session);
+
out:
return ret;
}
int ret = 0;
struct l2tp_session *session;
- session = l2tp_nl_session_find(info);
+ session = l2tp_nl_session_get(info, false);
if (session == NULL) {
ret = -ENODEV;
goto out;
ret = l2tp_session_notify(&l2tp_nl_family, info,
session, L2TP_CMD_SESSION_MODIFY);
+ l2tp_session_dec_refcount(session);
+
out:
return ret;
}
struct sk_buff *msg;
int ret;
- session = l2tp_nl_session_find(info);
+ session = l2tp_nl_session_get(info, false);
if (session == NULL) {
ret = -ENODEV;
- goto out;
+ goto err;
}
msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
if (!msg) {
ret = -ENOMEM;
- goto out;
+ goto err_ref;
}
ret = l2tp_nl_session_send(msg, info->snd_portid, info->snd_seq,
0, session, L2TP_CMD_SESSION_GET);
if (ret < 0)
- goto err_out;
+ goto err_ref_msg;
- return genlmsg_unicast(genl_info_net(info), msg, info->snd_portid);
+ ret = genlmsg_unicast(genl_info_net(info), msg, info->snd_portid);
-err_out:
- nlmsg_free(msg);
+ l2tp_session_dec_refcount(session);
-out:
+ return ret;
+
+err_ref_msg:
+ nlmsg_free(msg);
+err_ref:
+ l2tp_session_dec_refcount(session);
+err:
return ret;
}
goto out;
}
- session = l2tp_session_find_nth(tunnel, si);
+ session = l2tp_session_get_nth(tunnel, si, false);
if (session == NULL) {
ti++;
tunnel = NULL;
if (l2tp_nl_session_send(skb, NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI,
- session, L2TP_CMD_SESSION_GET) < 0)
+ session, L2TP_CMD_SESSION_GET) < 0) {
+ l2tp_session_dec_refcount(session);
break;
+ }
+ l2tp_session_dec_refcount(session);
si++;
}
static void pppol2tp_session_destruct(struct sock *sk)
{
struct l2tp_session *session = sk->sk_user_data;
+
+ skb_queue_purge(&sk->sk_receive_queue);
+ skb_queue_purge(&sk->sk_write_queue);
+
if (session) {
sk->sk_user_data = NULL;
BUG_ON(session->magic != L2TP_SESSION_MAGIC);
l2tp_session_queue_purge(session);
sock_put(sk);
}
- skb_queue_purge(&sk->sk_receive_queue);
- skb_queue_purge(&sk->sk_write_queue);
-
release_sock(sk);
/* This will delete the session context via
int error = 0;
u32 tunnel_id, peer_tunnel_id;
u32 session_id, peer_session_id;
+ bool drop_refcnt = false;
int ver = 2;
int fd;
if (tunnel->peer_tunnel_id == 0)
tunnel->peer_tunnel_id = peer_tunnel_id;
- /* Create session if it doesn't already exist. We handle the
- * case where a session was previously created by the netlink
- * interface by checking that the session doesn't already have
- * a socket and its tunnel socket are what we expect. If any
- * of those checks fail, return EEXIST to the caller.
- */
- session = l2tp_session_find(sock_net(sk), tunnel, session_id);
- if (session == NULL) {
- /* Default MTU must allow space for UDP/L2TP/PPP
- * headers.
+ session = l2tp_session_get(sock_net(sk), tunnel, session_id, false);
+ if (session) {
+ drop_refcnt = true;
+ ps = l2tp_session_priv(session);
+
+ /* Using a pre-existing session is fine as long as it hasn't
+ * been connected yet.
*/
- cfg.mtu = cfg.mru = 1500 - PPPOL2TP_HEADER_OVERHEAD;
+ if (ps->sock) {
+ error = -EEXIST;
+ goto end;
+ }
- /* Allocate and initialize a new session context. */
- session = l2tp_session_create(sizeof(struct pppol2tp_session),
- tunnel, session_id,
- peer_session_id, &cfg);
- if (session == NULL) {
- error = -ENOMEM;
+ /* consistency checks */
+ if (ps->tunnel_sock != tunnel->sock) {
+ error = -EEXIST;
goto end;
}
} else {
- ps = l2tp_session_priv(session);
- error = -EEXIST;
- if (ps->sock != NULL)
- goto end;
+ /* Default MTU must allow space for UDP/L2TP/PPP headers */
+ cfg.mtu = 1500 - PPPOL2TP_HEADER_OVERHEAD;
+ cfg.mru = cfg.mtu;
- /* consistency checks */
- if (ps->tunnel_sock != tunnel->sock)
+ session = l2tp_session_create(sizeof(struct pppol2tp_session),
+ tunnel, session_id,
+ peer_session_id, &cfg);
+ if (IS_ERR(session)) {
+ error = PTR_ERR(session);
goto end;
+ }
}
/* Associate session with its PPPoL2TP socket */
session->name);
end:
+ if (drop_refcnt)
+ l2tp_session_dec_refcount(session);
release_sock(sk);
return error;
if (tunnel->sock == NULL)
goto out;
- /* Check that this session doesn't already exist */
- error = -EEXIST;
- session = l2tp_session_find(net, tunnel, session_id);
- if (session != NULL)
- goto out;
-
/* Default MTU values. */
if (cfg->mtu == 0)
cfg->mtu = 1500 - PPPOL2TP_HEADER_OVERHEAD;
cfg->mru = cfg->mtu;
/* Allocate and initialize a new session context. */
- error = -ENOMEM;
session = l2tp_session_create(sizeof(struct pppol2tp_session),
tunnel, session_id,
peer_session_id, cfg);
- if (session == NULL)
+ if (IS_ERR(session)) {
+ error = PTR_ERR(session);
goto out;
+ }
ps = l2tp_session_priv(session);
ps->tunnel_sock = tunnel->sock;
if (stats.session_id != 0) {
/* resend to session ioctl handler */
struct l2tp_session *session =
- l2tp_session_find(sock_net(sk), tunnel, stats.session_id);
- if (session != NULL)
- err = pppol2tp_session_ioctl(session, cmd, arg);
- else
+ l2tp_session_get(sock_net(sk), tunnel,
+ stats.session_id, true);
+
+ if (session) {
+ err = pppol2tp_session_ioctl(session, cmd,
+ arg);
+ if (session->deref)
+ session->deref(session);
+ l2tp_session_dec_refcount(session);
+ } else {
err = -EBADR;
+ }
break;
}
#ifdef CONFIG_XFRM
} else
err = pppol2tp_session_setsockopt(sk, session, optname, val);
- err = 0;
-
end_put_sess:
sock_put(sk);
end:
err = pppol2tp_tunnel_getsockopt(sk, tunnel, optname, &val);
sock_put(ps->tunnel_sock);
- } else
+ if (err)
+ goto end_put_sess;
+ } else {
err = pppol2tp_session_getsockopt(sk, session, optname, &val);
+ if (err)
+ goto end_put_sess;
+ }
err = -EFAULT;
if (put_user(len, optlen))
static void pppol2tp_next_session(struct net *net, struct pppol2tp_seq_data *pd)
{
- pd->session = l2tp_session_find_nth(pd->tunnel, pd->session_idx);
+ pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx, true);
pd->session_idx++;
if (pd->session == NULL) {
/* Show the tunnel or session context.
*/
- if (pd->session == NULL)
+ if (!pd->session) {
pppol2tp_seq_tunnel_show(m, pd->tunnel);
- else
+ } else {
pppol2tp_seq_session_show(m, pd->session);
+ if (pd->session->deref)
+ pd->session->deref(pd->session);
+ l2tp_session_dec_refcount(pd->session);
+ }
out:
return 0;
MODULE_LICENSE("GPL");
MODULE_VERSION(PPPOL2TP_DRV_VERSION);
MODULE_ALIAS_NET_PF_PROTO(PF_PPPOX, PX_PROTO_OL2TP);
-MODULE_ALIAS_L2TP_PWTYPE(11);
+MODULE_ALIAS_L2TP_PWTYPE(7);
ieee80211_recalc_ps(local);
if (sdata->vif.type == NL80211_IFTYPE_MONITOR ||
- sdata->vif.type == NL80211_IFTYPE_AP_VLAN) {
+ sdata->vif.type == NL80211_IFTYPE_AP_VLAN ||
+ local->ops->wake_tx_queue) {
/* XXX: for AP_VLAN, actually track AP queues */
netif_tx_start_all_queues(dev);
} else if (dev) {
return len;
}
+static void ieee80211_handle_mu_mimo_mon(struct ieee80211_sub_if_data *sdata,
+ struct sk_buff *skb,
+ int rtap_vendor_space)
+{
+ struct {
+ struct ieee80211_hdr_3addr hdr;
+ u8 category;
+ u8 action_code;
+ } __packed action;
+
+ if (!sdata)
+ return;
+
+ BUILD_BUG_ON(sizeof(action) != IEEE80211_MIN_ACTION_SIZE + 1);
+
+ if (skb->len < rtap_vendor_space + sizeof(action) +
+ VHT_MUMIMO_GROUPS_DATA_LEN)
+ return;
+
+ if (!is_valid_ether_addr(sdata->u.mntr.mu_follow_addr))
+ return;
+
+ skb_copy_bits(skb, rtap_vendor_space, &action, sizeof(action));
+
+ if (!ieee80211_is_action(action.hdr.frame_control))
+ return;
+
+ if (action.category != WLAN_CATEGORY_VHT)
+ return;
+
+ if (action.action_code != WLAN_VHT_ACTION_GROUPID_MGMT)
+ return;
+
+ if (!ether_addr_equal(action.hdr.addr1, sdata->u.mntr.mu_follow_addr))
+ return;
+
+ skb = skb_copy(skb, GFP_ATOMIC);
+ if (!skb)
+ return;
+
+ skb->pkt_type = IEEE80211_SDATA_QUEUE_TYPE_FRAME;
+ skb_queue_tail(&sdata->skb_queue, skb);
+ ieee80211_queue_work(&sdata->local->hw, &sdata->work);
+}
+
/*
* ieee80211_add_rx_radiotap_header - add radiotap header
*
struct net_device *prev_dev = NULL;
int present_fcs_len = 0;
unsigned int rtap_vendor_space = 0;
- struct ieee80211_mgmt *mgmt;
struct ieee80211_sub_if_data *monitor_sdata =
rcu_dereference(local->monitor_sdata);
return remove_monitor_info(local, origskb, rtap_vendor_space);
}
+ ieee80211_handle_mu_mimo_mon(monitor_sdata, origskb, rtap_vendor_space);
+
/* room for the radiotap header based on driver features */
rt_hdrlen = ieee80211_rx_radiotap_hdrlen(local, status, origskb);
needed_headroom = rt_hdrlen - rtap_vendor_space;
ieee80211_rx_stats(sdata->dev, skb->len);
}
- mgmt = (void *)skb->data;
- if (monitor_sdata &&
- skb->len >= IEEE80211_MIN_ACTION_SIZE + 1 + VHT_MUMIMO_GROUPS_DATA_LEN &&
- ieee80211_is_action(mgmt->frame_control) &&
- mgmt->u.action.category == WLAN_CATEGORY_VHT &&
- mgmt->u.action.u.vht_group_notif.action_code == WLAN_VHT_ACTION_GROUPID_MGMT &&
- is_valid_ether_addr(monitor_sdata->u.mntr.mu_follow_addr) &&
- ether_addr_equal(mgmt->da, monitor_sdata->u.mntr.mu_follow_addr)) {
- struct sk_buff *mu_skb = skb_copy(skb, GFP_ATOMIC);
-
- if (mu_skb) {
- mu_skb->pkt_type = IEEE80211_SDATA_QUEUE_TYPE_FRAME;
- skb_queue_tail(&monitor_sdata->skb_queue, mu_skb);
- ieee80211_queue_work(&local->hw, &monitor_sdata->work);
- }
- }
-
if (prev_dev) {
skb->dev = prev_dev;
netif_receive_skb(skb);
!ether_addr_equal(bssid, hdr->addr1))
return false;
}
+
+ /*
+ * 802.11-2016 Table 9-26 says that for data frames, A1 must be
+ * the BSSID - we've checked that already but may have accepted
+ * the wildcard (ff:ff:ff:ff:ff:ff).
+ *
+ * It also says:
+ * The BSSID of the Data frame is determined as follows:
+ * a) If the STA is contained within an AP or is associated
+ * with an AP, the BSSID is the address currently in use
+ * by the STA contained in the AP.
+ *
+ * So we should not accept data frames with an address that's
+ * multicast.
+ *
+ * Accepting it also opens a security problem because stations
+ * could encrypt it with the GTK and inject traffic that way.
+ */
+ if (ieee80211_is_data(hdr->frame_control) && multicast)
+ return false;
+
return true;
case NL80211_IFTYPE_WDS:
if (bssid || !ieee80211_is_data(hdr->frame_control))
BUG_ON(notify != new);
RCU_INIT_POINTER(net->ct.nf_conntrack_event_cb, NULL);
mutex_unlock(&nf_ct_ecache_mutex);
+ /* synchronize_rcu() is called from ctnetlink_exit. */
}
EXPORT_SYMBOL_GPL(nf_conntrack_unregister_notifier);
BUG_ON(notify != new);
RCU_INIT_POINTER(net->ct.nf_expect_event_cb, NULL);
mutex_unlock(&nf_ct_ecache_mutex);
+ /* synchronize_rcu() is called from ctnetlink_exit. */
}
EXPORT_SYMBOL_GPL(nf_ct_expect_unregister_notifier);
hlist_del_rcu(&exp->hnode);
net->ct.expect_count--;
- hlist_del(&exp->lnode);
+ hlist_del_rcu(&exp->lnode);
master_help->expecting[exp->class]--;
nf_ct_expect_event_report(IPEXP_DESTROY, exp, portid, report);
/* two references : one for hash insert, one for the timer */
atomic_add(2, &exp->use);
- hlist_add_head(&exp->lnode, &master_help->expectations);
+ hlist_add_head_rcu(&exp->lnode, &master_help->expectations);
master_help->expecting[exp->class]++;
hlist_add_head_rcu(&exp->hnode, &nf_ct_expect_hash[h]);
rcu_read_lock();
t = rcu_dereference(nf_ct_ext_types[id]);
- BUG_ON(t == NULL);
+ if (!t) {
+ rcu_read_unlock();
+ return NULL;
+ }
+
off = ALIGN(sizeof(struct nf_ct_ext), t->align);
len = off + t->len + var_alloc_len;
alloc_size = t->alloc_size + var_alloc_len;
rcu_read_lock();
t = rcu_dereference(nf_ct_ext_types[id]);
- BUG_ON(t == NULL);
+ if (!t) {
+ rcu_read_unlock();
+ return NULL;
+ }
newoff = ALIGN(old->len, t->align);
newlen = newoff + t->len + var_alloc_len;
RCU_INIT_POINTER(nf_ct_ext_types[type->id], NULL);
update_alloc_size(type);
mutex_unlock(&nf_ct_ext_type_mutex);
- rcu_barrier(); /* Wait for completion of call_rcu()'s */
+ synchronize_rcu();
}
EXPORT_SYMBOL_GPL(nf_ct_extend_unregister);
{
struct nf_conntrack_helper *h;
+ rcu_read_lock();
+
h = __nf_conntrack_helper_find(name, l3num, protonum);
#ifdef CONFIG_MODULES
if (h == NULL) {
- if (request_module("nfct-helper-%s", name) == 0)
+ rcu_read_unlock();
+ if (request_module("nfct-helper-%s", name) == 0) {
+ rcu_read_lock();
h = __nf_conntrack_helper_find(name, l3num, protonum);
+ } else {
+ return h;
+ }
}
#endif
if (h != NULL && !try_module_get(h->me))
h = NULL;
+ rcu_read_unlock();
+
return h;
}
EXPORT_SYMBOL_GPL(nf_conntrack_helper_try_module_get);
}
EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_unregister);
+/* Caller should hold the rcu lock */
struct nf_ct_helper_expectfn *
nf_ct_helper_expectfn_find_by_name(const char *name)
{
struct nf_ct_helper_expectfn *cur;
bool found = false;
- rcu_read_lock();
list_for_each_entry_rcu(cur, &nf_ct_helper_expectfn_list, head) {
if (!strcmp(cur->name, name)) {
found = true;
break;
}
}
- rcu_read_unlock();
return found ? cur : NULL;
}
EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_find_by_name);
+/* Caller should hold the rcu lock */
struct nf_ct_helper_expectfn *
nf_ct_helper_expectfn_find_by_symbol(const void *symbol)
{
struct nf_ct_helper_expectfn *cur;
bool found = false;
- rcu_read_lock();
list_for_each_entry_rcu(cur, &nf_ct_helper_expectfn_list, head) {
if (cur->expectfn == symbol) {
found = true;
break;
}
}
- rcu_read_unlock();
return found ? cur : NULL;
}
EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_find_by_symbol);
* treat the second attempt as a no-op instead of returning
* an error.
*/
- if (help && help->helper &&
- !strcmp(help->helper->name, helpname))
- return 0;
- else
- return -EBUSY;
+ err = -EBUSY;
+ if (help) {
+ rcu_read_lock();
+ helper = rcu_dereference(help->helper);
+ if (helper && !strcmp(helper->name, helpname))
+ err = 0;
+ rcu_read_unlock();
+ }
+
+ return err;
}
if (!strcmp(helpname, "")) {
err = 0;
if (test_bit(IPS_EXPECTED_BIT, &ct->status))
- events = IPCT_RELATED;
+ events = 1 << IPCT_RELATED;
else
- events = IPCT_NEW;
+ events = 1 << IPCT_NEW;
if (cda[CTA_LABELS] &&
ctnetlink_attach_labels(ct, cda) == 0)
last = (struct nf_conntrack_expect *)cb->args[1];
for (; cb->args[0] < nf_ct_expect_hsize; cb->args[0]++) {
restart:
- hlist_for_each_entry(exp, &nf_ct_expect_hash[cb->args[0]],
- hnode) {
+ hlist_for_each_entry_rcu(exp, &nf_ct_expect_hash[cb->args[0]],
+ hnode) {
if (l3proto && exp->tuple.src.l3num != l3proto)
continue;
rcu_read_lock();
last = (struct nf_conntrack_expect *)cb->args[1];
restart:
- hlist_for_each_entry(exp, &help->expectations, lnode) {
+ hlist_for_each_entry_rcu(exp, &help->expectations, lnode) {
if (l3proto && exp->tuple.src.l3num != l3proto)
continue;
if (cb->args[1]) {
return -ENOENT;
ct = nf_ct_tuplehash_to_ctrack(h);
+ /* No expectation linked to this connection tracking. */
+ if (!nfct_help(ct)) {
+ nf_ct_put(ct);
+ return 0;
+ }
+
c.data = ct;
err = netlink_dump_start(ctnl, skb, nlh, &c);
return -ENOENT;
ct = nf_ct_tuplehash_to_ctrack(h);
+ rcu_read_lock();
if (cda[CTA_EXPECT_HELP_NAME]) {
const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]);
helper = __nf_conntrack_helper_find(helpname, u3,
nf_ct_protonum(ct));
if (helper == NULL) {
+ rcu_read_unlock();
#ifdef CONFIG_MODULES
if (request_module("nfct-helper-%s", helpname) < 0) {
err = -EOPNOTSUPP;
goto err_ct;
}
+ rcu_read_lock();
helper = __nf_conntrack_helper_find(helpname, u3,
nf_ct_protonum(ct));
if (helper) {
err = -EAGAIN;
- goto err_ct;
+ goto err_rcu;
}
+ rcu_read_unlock();
#endif
err = -EOPNOTSUPP;
goto err_ct;
exp = ctnetlink_alloc_expect(cda, ct, helper, &tuple, &mask);
if (IS_ERR(exp)) {
err = PTR_ERR(exp);
- goto err_ct;
+ goto err_rcu;
}
err = nf_ct_expect_related_report(exp, portid, report);
nf_ct_expect_put(exp);
+err_rcu:
+ rcu_read_unlock();
err_ct:
nf_ct_put(ct);
return err;
#ifdef CONFIG_NETFILTER_NETLINK_GLUE_CT
RCU_INIT_POINTER(nfnl_ct_hook, NULL);
#endif
+ synchronize_rcu();
}
module_init(ctnetlink_init);
#ifdef CONFIG_XFRM
RCU_INIT_POINTER(nf_nat_decode_session_hook, NULL);
#endif
+ synchronize_rcu();
+
for (i = 0; i < NFPROTO_NUMPROTO; i++)
kfree(nf_nat_l4protos[i]);
rcu_read_lock();
idev = __in6_dev_get(skb->dev);
if (idev != NULL) {
+ read_lock_bh(&idev->lock);
list_for_each_entry(ifa, &idev->addr_list, if_list) {
newdst = ifa->addr;
addr = true;
break;
}
+ read_unlock_bh(&idev->lock);
}
rcu_read_unlock();
MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
MODULE_DESCRIPTION("nfnl_cthelper: User-space connection tracking helpers");
+struct nfnl_cthelper {
+ struct list_head list;
+ struct nf_conntrack_helper helper;
+};
+
+static LIST_HEAD(nfnl_cthelper_list);
+
static int
nfnl_userspace_cthelper(struct sk_buff *skb, unsigned int protoff,
struct nf_conn *ct, enum ip_conntrack_info ctinfo)
int i, ret;
struct nf_conntrack_expect_policy *expect_policy;
struct nlattr *tb[NFCTH_POLICY_SET_MAX+1];
+ unsigned int class_max;
ret = nla_parse_nested(tb, NFCTH_POLICY_SET_MAX, attr,
nfnl_cthelper_expect_policy_set);
if (!tb[NFCTH_POLICY_SET_NUM])
return -EINVAL;
- helper->expect_class_max =
- ntohl(nla_get_be32(tb[NFCTH_POLICY_SET_NUM]));
-
- if (helper->expect_class_max != 0 &&
- helper->expect_class_max > NF_CT_MAX_EXPECT_CLASSES)
+ class_max = ntohl(nla_get_be32(tb[NFCTH_POLICY_SET_NUM]));
+ if (class_max == 0)
+ return -EINVAL;
+ if (class_max > NF_CT_MAX_EXPECT_CLASSES)
return -EOVERFLOW;
expect_policy = kzalloc(sizeof(struct nf_conntrack_expect_policy) *
- helper->expect_class_max, GFP_KERNEL);
+ class_max, GFP_KERNEL);
if (expect_policy == NULL)
return -ENOMEM;
- for (i=0; i<helper->expect_class_max; i++) {
+ for (i = 0; i < class_max; i++) {
if (!tb[NFCTH_POLICY_SET+i])
goto err;
if (ret < 0)
goto err;
}
+
+ helper->expect_class_max = class_max - 1;
helper->expect_policy = expect_policy;
return 0;
err:
struct nf_conntrack_tuple *tuple)
{
struct nf_conntrack_helper *helper;
+ struct nfnl_cthelper *nfcth;
int ret;
if (!tb[NFCTH_TUPLE] || !tb[NFCTH_POLICY] || !tb[NFCTH_PRIV_DATA_LEN])
return -EINVAL;
- helper = kzalloc(sizeof(struct nf_conntrack_helper), GFP_KERNEL);
- if (helper == NULL)
+ nfcth = kzalloc(sizeof(*nfcth), GFP_KERNEL);
+ if (nfcth == NULL)
return -ENOMEM;
+ helper = &nfcth->helper;
ret = nfnl_cthelper_parse_expect_policy(helper, tb[NFCTH_POLICY]);
if (ret < 0)
- goto err;
+ goto err1;
strncpy(helper->name, nla_data(tb[NFCTH_NAME]), NF_CT_HELPER_NAME_LEN);
helper->data_len = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN]));
ret = nf_conntrack_helper_register(helper);
if (ret < 0)
- goto err;
+ goto err2;
+ list_add_tail(&nfcth->list, &nfnl_cthelper_list);
return 0;
-err:
- kfree(helper);
+err2:
+ kfree(helper->expect_policy);
+err1:
+ kfree(nfcth);
return ret;
}
static int
+nfnl_cthelper_update_policy_one(const struct nf_conntrack_expect_policy *policy,
+ struct nf_conntrack_expect_policy *new_policy,
+ const struct nlattr *attr)
+{
+ struct nlattr *tb[NFCTH_POLICY_MAX + 1];
+ int err;
+
+ err = nla_parse_nested(tb, NFCTH_POLICY_MAX, attr,
+ nfnl_cthelper_expect_pol);
+ if (err < 0)
+ return err;
+
+ if (!tb[NFCTH_POLICY_NAME] ||
+ !tb[NFCTH_POLICY_EXPECT_MAX] ||
+ !tb[NFCTH_POLICY_EXPECT_TIMEOUT])
+ return -EINVAL;
+
+ if (nla_strcmp(tb[NFCTH_POLICY_NAME], policy->name))
+ return -EBUSY;
+
+ new_policy->max_expected =
+ ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_MAX]));
+ new_policy->timeout =
+ ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_TIMEOUT]));
+
+ return 0;
+}
+
+static int nfnl_cthelper_update_policy_all(struct nlattr *tb[],
+ struct nf_conntrack_helper *helper)
+{
+ struct nf_conntrack_expect_policy new_policy[helper->expect_class_max + 1];
+ struct nf_conntrack_expect_policy *policy;
+ int i, err;
+
+ /* Check first that all policy attributes are well-formed, so we don't
+ * leave things in inconsistent state on errors.
+ */
+ for (i = 0; i < helper->expect_class_max + 1; i++) {
+
+ if (!tb[NFCTH_POLICY_SET + i])
+ return -EINVAL;
+
+ err = nfnl_cthelper_update_policy_one(&helper->expect_policy[i],
+ &new_policy[i],
+ tb[NFCTH_POLICY_SET + i]);
+ if (err < 0)
+ return err;
+ }
+ /* Now we can safely update them. */
+ for (i = 0; i < helper->expect_class_max + 1; i++) {
+ policy = (struct nf_conntrack_expect_policy *)
+ &helper->expect_policy[i];
+ policy->max_expected = new_policy->max_expected;
+ policy->timeout = new_policy->timeout;
+ }
+
+ return 0;
+}
+
+static int nfnl_cthelper_update_policy(struct nf_conntrack_helper *helper,
+ const struct nlattr *attr)
+{
+ struct nlattr *tb[NFCTH_POLICY_SET_MAX + 1];
+ unsigned int class_max;
+ int err;
+
+ err = nla_parse_nested(tb, NFCTH_POLICY_SET_MAX, attr,
+ nfnl_cthelper_expect_policy_set);
+ if (err < 0)
+ return err;
+
+ if (!tb[NFCTH_POLICY_SET_NUM])
+ return -EINVAL;
+
+ class_max = ntohl(nla_get_be32(tb[NFCTH_POLICY_SET_NUM]));
+ if (helper->expect_class_max + 1 != class_max)
+ return -EBUSY;
+
+ return nfnl_cthelper_update_policy_all(tb, helper);
+}
+
+static int
nfnl_cthelper_update(const struct nlattr * const tb[],
struct nf_conntrack_helper *helper)
{
return -EBUSY;
if (tb[NFCTH_POLICY]) {
- ret = nfnl_cthelper_parse_expect_policy(helper,
- tb[NFCTH_POLICY]);
+ ret = nfnl_cthelper_update_policy(helper, tb[NFCTH_POLICY]);
if (ret < 0)
return ret;
}
const char *helper_name;
struct nf_conntrack_helper *cur, *helper = NULL;
struct nf_conntrack_tuple tuple;
- int ret = 0, i;
+ struct nfnl_cthelper *nlcth;
+ int ret = 0;
if (!tb[NFCTH_NAME] || !tb[NFCTH_TUPLE])
return -EINVAL;
if (ret < 0)
return ret;
- rcu_read_lock();
- for (i = 0; i < nf_ct_helper_hsize && !helper; i++) {
- hlist_for_each_entry_rcu(cur, &nf_ct_helper_hash[i], hnode) {
+ list_for_each_entry(nlcth, &nfnl_cthelper_list, list) {
+ cur = &nlcth->helper;
- /* skip non-userspace conntrack helpers. */
- if (!(cur->flags & NF_CT_HELPER_F_USERSPACE))
- continue;
+ if (strncmp(cur->name, helper_name, NF_CT_HELPER_NAME_LEN))
+ continue;
- if (strncmp(cur->name, helper_name,
- NF_CT_HELPER_NAME_LEN) != 0)
- continue;
+ if ((tuple.src.l3num != cur->tuple.src.l3num ||
+ tuple.dst.protonum != cur->tuple.dst.protonum))
+ continue;
- if ((tuple.src.l3num != cur->tuple.src.l3num ||
- tuple.dst.protonum != cur->tuple.dst.protonum))
- continue;
+ if (nlh->nlmsg_flags & NLM_F_EXCL)
+ return -EEXIST;
- if (nlh->nlmsg_flags & NLM_F_EXCL) {
- ret = -EEXIST;
- goto err;
- }
- helper = cur;
- break;
- }
+ helper = cur;
+ break;
}
- rcu_read_unlock();
if (helper == NULL)
ret = nfnl_cthelper_create(tb, &tuple);
ret = nfnl_cthelper_update(tb, helper);
return ret;
-err:
- rcu_read_unlock();
- return ret;
}
static int
goto nla_put_failure;
if (nla_put_be32(skb, NFCTH_POLICY_SET_NUM,
- htonl(helper->expect_class_max)))
+ htonl(helper->expect_class_max + 1)))
goto nla_put_failure;
- for (i=0; i<helper->expect_class_max; i++) {
+ for (i = 0; i < helper->expect_class_max + 1; i++) {
nest_parms2 = nla_nest_start(skb,
(NFCTH_POLICY_SET+i) | NLA_F_NESTED);
if (nest_parms2 == NULL)
struct sk_buff *skb, const struct nlmsghdr *nlh,
const struct nlattr * const tb[])
{
- int ret = -ENOENT, i;
+ int ret = -ENOENT;
struct nf_conntrack_helper *cur;
struct sk_buff *skb2;
char *helper_name = NULL;
struct nf_conntrack_tuple tuple;
+ struct nfnl_cthelper *nlcth;
bool tuple_set = false;
if (nlh->nlmsg_flags & NLM_F_DUMP) {
tuple_set = true;
}
- for (i = 0; i < nf_ct_helper_hsize; i++) {
- hlist_for_each_entry_rcu(cur, &nf_ct_helper_hash[i], hnode) {
+ list_for_each_entry(nlcth, &nfnl_cthelper_list, list) {
+ cur = &nlcth->helper;
+ if (helper_name &&
+ strncmp(cur->name, helper_name, NF_CT_HELPER_NAME_LEN))
+ continue;
- /* skip non-userspace conntrack helpers. */
- if (!(cur->flags & NF_CT_HELPER_F_USERSPACE))
- continue;
+ if (tuple_set &&
+ (tuple.src.l3num != cur->tuple.src.l3num ||
+ tuple.dst.protonum != cur->tuple.dst.protonum))
+ continue;
- if (helper_name && strncmp(cur->name, helper_name,
- NF_CT_HELPER_NAME_LEN) != 0) {
- continue;
- }
- if (tuple_set &&
- (tuple.src.l3num != cur->tuple.src.l3num ||
- tuple.dst.protonum != cur->tuple.dst.protonum))
- continue;
-
- skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (skb2 == NULL) {
- ret = -ENOMEM;
- break;
- }
+ skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (skb2 == NULL) {
+ ret = -ENOMEM;
+ break;
+ }
- ret = nfnl_cthelper_fill_info(skb2, NETLINK_CB(skb).portid,
- nlh->nlmsg_seq,
- NFNL_MSG_TYPE(nlh->nlmsg_type),
- NFNL_MSG_CTHELPER_NEW, cur);
- if (ret <= 0) {
- kfree_skb(skb2);
- break;
- }
+ ret = nfnl_cthelper_fill_info(skb2, NETLINK_CB(skb).portid,
+ nlh->nlmsg_seq,
+ NFNL_MSG_TYPE(nlh->nlmsg_type),
+ NFNL_MSG_CTHELPER_NEW, cur);
+ if (ret <= 0) {
+ kfree_skb(skb2);
+ break;
+ }
- ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).portid,
- MSG_DONTWAIT);
- if (ret > 0)
- ret = 0;
+ ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).portid,
+ MSG_DONTWAIT);
+ if (ret > 0)
+ ret = 0;
- /* this avoids a loop in nfnetlink. */
- return ret == -EAGAIN ? -ENOBUFS : ret;
- }
+ /* this avoids a loop in nfnetlink. */
+ return ret == -EAGAIN ? -ENOBUFS : ret;
}
return ret;
}
{
char *helper_name = NULL;
struct nf_conntrack_helper *cur;
- struct hlist_node *tmp;
struct nf_conntrack_tuple tuple;
bool tuple_set = false, found = false;
- int i, j = 0, ret;
+ struct nfnl_cthelper *nlcth, *n;
+ int j = 0, ret;
if (tb[NFCTH_NAME])
helper_name = nla_data(tb[NFCTH_NAME]);
tuple_set = true;
}
- for (i = 0; i < nf_ct_helper_hsize; i++) {
- hlist_for_each_entry_safe(cur, tmp, &nf_ct_helper_hash[i],
- hnode) {
- /* skip non-userspace conntrack helpers. */
- if (!(cur->flags & NF_CT_HELPER_F_USERSPACE))
- continue;
+ list_for_each_entry_safe(nlcth, n, &nfnl_cthelper_list, list) {
+ cur = &nlcth->helper;
+ j++;
- j++;
+ if (helper_name &&
+ strncmp(cur->name, helper_name, NF_CT_HELPER_NAME_LEN))
+ continue;
- if (helper_name && strncmp(cur->name, helper_name,
- NF_CT_HELPER_NAME_LEN) != 0) {
- continue;
- }
- if (tuple_set &&
- (tuple.src.l3num != cur->tuple.src.l3num ||
- tuple.dst.protonum != cur->tuple.dst.protonum))
- continue;
+ if (tuple_set &&
+ (tuple.src.l3num != cur->tuple.src.l3num ||
+ tuple.dst.protonum != cur->tuple.dst.protonum))
+ continue;
- found = true;
- nf_conntrack_helper_unregister(cur);
- }
+ found = true;
+ nf_conntrack_helper_unregister(cur);
+ kfree(cur->expect_policy);
+
+ list_del(&nlcth->list);
+ kfree(nlcth);
}
+
/* Make sure we return success if we flush and there is no helpers */
return (found || j == 0) ? 0 : -ENOENT;
}
static void __exit nfnl_cthelper_exit(void)
{
struct nf_conntrack_helper *cur;
- struct hlist_node *tmp;
- int i;
+ struct nfnl_cthelper *nlcth, *n;
nfnetlink_subsys_unregister(&nfnl_cthelper_subsys);
- for (i=0; i<nf_ct_helper_hsize; i++) {
- hlist_for_each_entry_safe(cur, tmp, &nf_ct_helper_hash[i],
- hnode) {
- /* skip non-userspace conntrack helpers. */
- if (!(cur->flags & NF_CT_HELPER_F_USERSPACE))
- continue;
+ list_for_each_entry_safe(nlcth, n, &nfnl_cthelper_list, list) {
+ cur = &nlcth->helper;
- nf_conntrack_helper_unregister(cur);
- }
+ nf_conntrack_helper_unregister(cur);
+ kfree(cur->expect_policy);
+ kfree(nlcth);
}
}
#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
RCU_INIT_POINTER(nf_ct_timeout_find_get_hook, NULL);
RCU_INIT_POINTER(nf_ct_timeout_put_hook, NULL);
+ synchronize_rcu();
#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */
- rcu_barrier();
}
module_init(cttimeout_init);
skb = alloc_skb(size, GFP_ATOMIC);
if (!skb) {
skb_tx_error(entskb);
- return NULL;
+ goto nlmsg_failure;
}
nlh = nlmsg_put(skb, 0, 0,
if (!nlh) {
skb_tx_error(entskb);
kfree_skb(skb);
- return NULL;
+ goto nlmsg_failure;
}
nfmsg = nlmsg_data(nlh);
nfmsg->nfgen_family = entry->state.pf;
}
nlh->nlmsg_len = skb->len;
+ if (seclen)
+ security_release_secctx(secdata, seclen);
return skb;
nla_put_failure:
skb_tx_error(entskb);
kfree_skb(skb);
net_err_ratelimited("nf_queue: error creating packet message\n");
+nlmsg_failure:
+ if (seclen)
+ security_release_secctx(secdata, seclen);
return NULL;
}
enum nft_registers sreg:8;
enum nft_registers dreg:8;
u8 len;
+ bool autogen_seed:1;
u32 modulus;
u32 seed;
u32 offset;
if (priv->offset + priv->modulus - 1 < priv->offset)
return -EOVERFLOW;
- if (tb[NFTA_HASH_SEED])
+ if (tb[NFTA_HASH_SEED]) {
priv->seed = ntohl(nla_get_be32(tb[NFTA_HASH_SEED]));
- else
+ } else {
+ priv->autogen_seed = true;
get_random_bytes(&priv->seed, sizeof(priv->seed));
+ }
return nft_validate_register_load(priv->sreg, len) &&
nft_validate_register_store(ctx, priv->dreg, NULL,
goto nla_put_failure;
if (nla_put_be32(skb, NFTA_HASH_MODULUS, htonl(priv->modulus)))
goto nla_put_failure;
- if (nla_put_be32(skb, NFTA_HASH_SEED, htonl(priv->seed)))
+ if (!priv->autogen_seed &&
+ nla_put_be32(skb, NFTA_HASH_SEED, htonl(priv->seed)))
goto nla_put_failure;
if (priv->offset != 0)
if (nla_put_be32(skb, NFTA_HASH_OFFSET, htonl(priv->offset)))
tcph = (struct tcphdr *)(skb_network_header(skb) + tcphoff);
tcp_hdrlen = tcph->doff * 4;
- if (len < tcp_hdrlen)
+ if (len < tcp_hdrlen || tcp_hdrlen < sizeof(struct tcphdr))
return -1;
if (info->mss == XT_TCPMSS_CLAMP_PMTU) {
if (len > tcp_hdrlen)
return 0;
+ /* tcph->doff has 4 bits, do not wrap it to 0 */
+ if (tcp_hdrlen >= 15 * 4)
+ return 0;
+
/*
* MSS Option not found ?! add it..
*/
rcu_read_lock();
indev = __in6_dev_get(skb->dev);
- if (indev)
+ if (indev) {
+ read_lock_bh(&indev->lock);
list_for_each_entry(ifa, &indev->addr_list, if_list) {
if (ifa->flags & (IFA_F_TENTATIVE | IFA_F_DEPRECATED))
continue;
laddr = &ifa->addr;
break;
}
+ read_unlock_bh(&indev->lock);
+ }
rcu_read_unlock();
return laddr ? laddr : daddr;
*/
if (nf_ct_is_confirmed(ct))
nf_ct_delete(ct, 0, 0);
- else
- nf_conntrack_put(&ct->ct_general);
+
+ nf_conntrack_put(&ct->ct_general);
nf_ct_set(skb, NULL, 0);
return false;
}
/* Link layer. */
clear_vlan(key);
- if (key->mac_proto == MAC_PROTO_NONE) {
+ if (ovs_key_mac_proto(key) == MAC_PROTO_NONE) {
if (unlikely(eth_type_vlan(skb->protocol)))
return -EINVAL;
int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key)
{
- return key_extract(skb, key);
+ int res;
+
+ res = key_extract(skb, key);
+ if (!res)
+ key->mac_proto &= ~SW_FLOW_KEY_INVALID;
+
+ return res;
}
static int key_extract_mac_proto(struct sk_buff *skb)
return -EBUSY;
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
+ if (val > INT_MAX)
+ return -EINVAL;
po->tp_reserve = val;
return 0;
}
case PACKET_HDRLEN:
if (len > sizeof(int))
len = sizeof(int);
+ if (len < sizeof(int))
+ return -EINVAL;
if (copy_from_user(&val, optval, len))
return -EFAULT;
switch (val) {
if (unlikely(!PAGE_ALIGNED(req->tp_block_size)))
goto out;
if (po->tp_version >= TPACKET_V3 &&
- (int)(req->tp_block_size -
- BLK_PLUS_PRIV(req_u->req3.tp_sizeof_priv)) <= 0)
+ req->tp_block_size <=
+ BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv))
goto out;
if (unlikely(req->tp_frame_size < po->tp_hdrlen +
po->tp_reserve))
rb->frames_per_block = req->tp_block_size / req->tp_frame_size;
if (unlikely(rb->frames_per_block == 0))
goto out;
+ if (unlikely(req->tp_block_size > UINT_MAX / req->tp_block_nr))
+ goto out;
if (unlikely((rb->frames_per_block * req->tp_block_nr) !=
req->tp_frame_nr))
goto out;
}
if (plen != len) {
- skb_pad(skb, plen - len);
+ rc = skb_pad(skb, plen - len);
+ if (rc)
+ goto out_node;
skb_put(skb, plen - len);
}
/* doing it this way avoids calling tcp_sk() */
void rds_tcp_nonagle(struct socket *sock)
{
- mm_segment_t oldfs = get_fs();
int val = 1;
- set_fs(KERNEL_DS);
- sock->ops->setsockopt(sock, SOL_TCP, TCP_NODELAY, (char __user *)&val,
+ kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, (void *)&val,
sizeof(val));
- set_fs(oldfs);
}
u32 rds_tcp_snd_nxt(struct rds_tcp_connection *tc)
static void rds_tcp_cork(struct socket *sock, int val)
{
- mm_segment_t oldfs;
-
- oldfs = get_fs();
- set_fs(KERNEL_DS);
- sock->ops->setsockopt(sock, SOL_TCP, TCP_CORK, (char __user *)&val,
- sizeof(val));
- set_fs(oldfs);
+ kernel_setsockopt(sock, SOL_TCP, TCP_CORK, (void *)&val, sizeof(val));
}
void rds_tcp_xmit_path_prepare(struct rds_conn_path *cp)
return err;
}
-static int nla_memdup_cookie(struct tc_action *a, struct nlattr **tb)
+static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb)
{
- a->act_cookie = kzalloc(sizeof(*a->act_cookie), GFP_KERNEL);
- if (!a->act_cookie)
- return -ENOMEM;
+ struct tc_cookie *c = kzalloc(sizeof(*c), GFP_KERNEL);
+ if (!c)
+ return NULL;
- a->act_cookie->data = nla_memdup(tb[TCA_ACT_COOKIE], GFP_KERNEL);
- if (!a->act_cookie->data) {
- kfree(a->act_cookie);
- return -ENOMEM;
+ c->data = nla_memdup(tb[TCA_ACT_COOKIE], GFP_KERNEL);
+ if (!c->data) {
+ kfree(c);
+ return NULL;
}
- a->act_cookie->len = nla_len(tb[TCA_ACT_COOKIE]);
+ c->len = nla_len(tb[TCA_ACT_COOKIE]);
- return 0;
+ return c;
}
struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla,
{
struct tc_action *a;
struct tc_action_ops *a_o;
+ struct tc_cookie *cookie = NULL;
char act_name[IFNAMSIZ];
struct nlattr *tb[TCA_ACT_MAX + 1];
struct nlattr *kind;
goto err_out;
if (nla_strlcpy(act_name, kind, IFNAMSIZ) >= IFNAMSIZ)
goto err_out;
+ if (tb[TCA_ACT_COOKIE]) {
+ int cklen = nla_len(tb[TCA_ACT_COOKIE]);
+
+ if (cklen > TC_COOKIE_MAX_SIZE)
+ goto err_out;
+
+ cookie = nla_memdup_cookie(tb);
+ if (!cookie) {
+ err = -ENOMEM;
+ goto err_out;
+ }
+ }
} else {
err = -EINVAL;
if (strlcpy(act_name, name, IFNAMSIZ) >= IFNAMSIZ)
if (err < 0)
goto err_mod;
- if (tb[TCA_ACT_COOKIE]) {
- int cklen = nla_len(tb[TCA_ACT_COOKIE]);
-
- if (cklen > TC_COOKIE_MAX_SIZE) {
- err = -EINVAL;
- tcf_hash_release(a, bind);
- goto err_mod;
- }
-
- if (nla_memdup_cookie(a, tb) < 0) {
- err = -ENOMEM;
- tcf_hash_release(a, bind);
- goto err_mod;
+ if (name == NULL && tb[TCA_ACT_COOKIE]) {
+ if (a->act_cookie) {
+ kfree(a->act_cookie->data);
+ kfree(a->act_cookie);
}
+ a->act_cookie = cookie;
}
/* module count goes up only when brand new policy is created
err_mod:
module_put(a_o->owner);
err_out:
+ if (cookie) {
+ kfree(cookie->data);
+ kfree(cookie);
+ }
return ERR_PTR(err);
}
}
}
#ifdef CONFIG_NET_SCHED
- if (dev->qdisc)
+ if (dev->qdisc != &noop_qdisc)
qdisc_hash_add(dev->qdisc);
#endif
}
if (!sctp_ulpq_init(&asoc->ulpq, asoc))
goto fail_init;
+ if (sctp_stream_new(asoc, gfp))
+ goto fail_init;
+
/* Assume that peer would support both address types unless we are
* told otherwise.
*/
/* AUTH related initializations */
INIT_LIST_HEAD(&asoc->endpoint_shared_keys);
if (sctp_auth_asoc_copy_shkeys(ep, asoc, gfp))
- goto fail_init;
+ goto stream_free;
asoc->active_key_id = ep->active_key_id;
asoc->prsctp_enable = ep->prsctp_enable;
return asoc;
+stream_free:
+ sctp_stream_free(asoc->stream);
fail_init:
sock_put(asoc->base.sk);
sctp_endpoint_put(asoc->ep);
/* Update the association's pmtu and frag_point by going through all the
* transports. This routine is called when a transport's PMTU has changed.
*/
-void sctp_assoc_sync_pmtu(struct sock *sk, struct sctp_association *asoc)
+void sctp_assoc_sync_pmtu(struct sctp_association *asoc)
{
struct sctp_transport *t;
__u32 pmtu = 0;
list_for_each_entry(t, &asoc->peer.transport_addr_list,
transports) {
if (t->pmtu_pending && t->dst) {
- sctp_transport_update_pmtu(sk, t,
- SCTP_TRUNC4(dst_mtu(t->dst)));
+ sctp_transport_update_pmtu(
+ t, SCTP_TRUNC4(dst_mtu(t->dst)));
t->pmtu_pending = 0;
}
if (!pmtu || (t->pathmtu < pmtu))
if (t->param_flags & SPP_PMTUD_ENABLE) {
/* Update transports view of the MTU */
- sctp_transport_update_pmtu(sk, t, pmtu);
+ sctp_transport_update_pmtu(t, pmtu);
/* Update association pmtu. */
- sctp_assoc_sync_pmtu(sk, asoc);
+ sctp_assoc_sync_pmtu(asoc);
}
/* Retransmit with the new pmtu setting.
{
struct sctp_transport *tp = packet->transport;
struct sctp_association *asoc = tp->asoc;
+ struct sock *sk;
pr_debug("%s: packet:%p vtag:0x%x\n", __func__, packet, vtag);
-
packet->vtag = vtag;
- if (asoc && tp->dst) {
- struct sock *sk = asoc->base.sk;
-
- rcu_read_lock();
- if (__sk_dst_get(sk) != tp->dst) {
- dst_hold(tp->dst);
- sk_setup_caps(sk, tp->dst);
- }
-
- if (sk_can_gso(sk)) {
- struct net_device *dev = tp->dst->dev;
+ /* do the following jobs only once for a flush schedule */
+ if (!sctp_packet_empty(packet))
+ return;
- packet->max_size = dev->gso_max_size;
- } else {
- packet->max_size = asoc->pathmtu;
- }
- rcu_read_unlock();
+ /* set packet max_size with pathmtu */
+ packet->max_size = tp->pathmtu;
+ if (!asoc)
+ return;
- } else {
- packet->max_size = tp->pathmtu;
+ /* update dst or transport pathmtu if in need */
+ sk = asoc->base.sk;
+ if (!sctp_transport_dst_check(tp)) {
+ sctp_transport_route(tp, NULL, sctp_sk(sk));
+ if (asoc->param_flags & SPP_PMTUD_ENABLE)
+ sctp_assoc_sync_pmtu(asoc);
+ } else if (!sctp_transport_pmtu_check(tp)) {
+ if (asoc->param_flags & SPP_PMTUD_ENABLE)
+ sctp_assoc_sync_pmtu(asoc);
}
- if (ecn_capable && sctp_packet_empty(packet)) {
- struct sctp_chunk *chunk;
+ /* If there a is a prepend chunk stick it on the list before
+ * any other chunks get appended.
+ */
+ if (ecn_capable) {
+ struct sctp_chunk *chunk = sctp_get_ecne_prepend(asoc);
- /* If there a is a prepend chunk stick it on the list before
- * any other chunks get appended.
- */
- chunk = sctp_get_ecne_prepend(asoc);
if (chunk)
sctp_packet_append_chunk(packet, chunk);
}
+
+ if (!tp->dst)
+ return;
+
+ /* set packet max_size with gso_max_size if gso is enabled*/
+ rcu_read_lock();
+ if (__sk_dst_get(sk) != tp->dst) {
+ dst_hold(tp->dst);
+ sk_setup_caps(sk, tp->dst);
+ }
+ packet->max_size = sk_can_gso(sk) ? tp->dst->dev->gso_max_size
+ : asoc->pathmtu;
+ rcu_read_unlock();
}
/* Initialize the packet structure. */
sh->vtag = htonl(packet->vtag);
sh->checksum = 0;
- /* update dst if in need */
- if (!sctp_transport_dst_check(tp)) {
- sctp_transport_route(tp, NULL, sctp_sk(sk));
- if (asoc && asoc->param_flags & SPP_PMTUD_ENABLE)
- sctp_assoc_sync_pmtu(sk, asoc);
- }
+ /* drop packet if no dst */
dst = dst_clone(tp->dst);
if (!dst) {
IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
*/
if ((sctp_sk(asoc->base.sk)->nodelay || inflight == 0) &&
- !chunk->msg->force_delay)
+ !asoc->force_delay)
/* Nothing unacked */
return SCTP_XMIT_OK;
/* RFC 2960 6.5 Every DATA chunk MUST carry a valid
* stream identifier.
*/
- if (chunk->sinfo.sinfo_stream >=
- asoc->c.sinit_num_ostreams) {
+ if (chunk->sinfo.sinfo_stream >= asoc->stream->outcnt) {
/* Mark as failed send. */
sctp_chunk_fail(chunk, SCTP_ERROR_INV_STRM);
sctp_seq_dump_remote_addrs(seq, assoc);
seq_printf(seq, "\t%8lu %5d %5d %4d %4d %4d %8d "
"%8d %8d %8d %8d",
- assoc->hbinterval, assoc->c.sinit_max_instreams,
- assoc->c.sinit_num_ostreams, assoc->max_retrans,
+ assoc->hbinterval, assoc->stream->incnt,
+ assoc->stream->outcnt, assoc->max_retrans,
assoc->init_retries, assoc->shutdown_retries,
assoc->rtx_data_chunks,
atomic_read(&sk->sk_wmem_alloc),
* association.
*/
if (!asoc->temp) {
- int error;
-
- asoc->stream = sctp_stream_new(asoc->c.sinit_max_instreams,
- asoc->c.sinit_num_ostreams, gfp);
- if (!asoc->stream)
+ if (sctp_stream_init(asoc, gfp))
goto clean_up;
- error = sctp_assoc_set_id(asoc, gfp);
- if (error)
+ if (sctp_assoc_set_id(asoc, gfp))
goto clean_up;
}
/* Silently discard the chunk if stream-id is not valid */
sctp_walk_fwdtsn(skip, chunk) {
- if (ntohs(skip->stream) >= asoc->c.sinit_max_instreams)
+ if (ntohs(skip->stream) >= asoc->stream->incnt)
goto discard_noforce;
}
/* Silently discard the chunk if stream-id is not valid */
sctp_walk_fwdtsn(skip, chunk) {
- if (ntohs(skip->stream) >= asoc->c.sinit_max_instreams)
+ if (ntohs(skip->stream) >= asoc->stream->incnt)
goto gen_shutdown;
}
* and discard the DATA chunk.
*/
sid = ntohs(data_hdr->stream);
- if (sid >= asoc->c.sinit_max_instreams) {
+ if (sid >= asoc->stream->incnt) {
/* Mark tsn as received even though we drop it */
sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_TSN, SCTP_U32(tsn));
}
if (asoc->pmtu_pending)
- sctp_assoc_pending_pmtu(sk, asoc);
+ sctp_assoc_pending_pmtu(asoc);
/* If fragmentation is disabled and the message length exceeds the
* association fragmentation point, return EMSGSIZE. The I-D
}
/* Check for invalid stream. */
- if (sinfo->sinfo_stream >= asoc->c.sinit_num_ostreams) {
+ if (sinfo->sinfo_stream >= asoc->stream->outcnt) {
err = -EINVAL;
goto out_free;
}
err = PTR_ERR(datamsg);
goto out_free;
}
- datamsg->force_delay = !!(msg->msg_flags & MSG_MORE);
+ asoc->force_delay = !!(msg->msg_flags & MSG_MORE);
/* Now send the (possibly) fragmented message. */
list_for_each_entry(chunk, &datamsg->chunks, frag_list) {
if ((params->spp_flags & SPP_PMTUD_DISABLE) && params->spp_pathmtu) {
if (trans) {
trans->pathmtu = params->spp_pathmtu;
- sctp_assoc_sync_pmtu(sctp_opt2sk(sp), asoc);
+ sctp_assoc_sync_pmtu(asoc);
} else if (asoc) {
asoc->pathmtu = params->spp_pathmtu;
} else {
(trans->param_flags & ~SPP_PMTUD) | pmtud_change;
if (update) {
sctp_transport_pmtu(trans, sctp_opt2sk(sp));
- sctp_assoc_sync_pmtu(sctp_opt2sk(sp), asoc);
+ sctp_assoc_sync_pmtu(asoc);
}
} else if (asoc) {
asoc->param_flags =
info->sctpi_rwnd = asoc->a_rwnd;
info->sctpi_unackdata = asoc->unack_data;
info->sctpi_penddata = sctp_tsnmap_pending(&asoc->peer.tsn_map);
- info->sctpi_instrms = asoc->c.sinit_max_instreams;
- info->sctpi_outstrms = asoc->c.sinit_num_ostreams;
+ info->sctpi_instrms = asoc->stream->incnt;
+ info->sctpi_outstrms = asoc->stream->outcnt;
list_for_each(pos, &asoc->base.inqueue.in_chunk_list)
info->sctpi_inqueue++;
list_for_each(pos, &asoc->outqueue.out_chunk_list)
status.sstat_unackdata = asoc->unack_data;
status.sstat_penddata = sctp_tsnmap_pending(&asoc->peer.tsn_map);
- status.sstat_instrms = asoc->c.sinit_max_instreams;
- status.sstat_outstrms = asoc->c.sinit_num_ostreams;
+ status.sstat_instrms = asoc->stream->incnt;
+ status.sstat_outstrms = asoc->stream->outcnt;
status.sstat_fragmentation_point = asoc->frag_point;
status.sstat_primary.spinfo_assoc_id = sctp_assoc2id(transport->asoc);
memcpy(&status.sstat_primary.spinfo_address, &transport->ipaddr,
if (sock->state != SS_UNCONNECTED)
goto out;
+ if (!sctp_sstate(sk, LISTENING) && !sctp_sstate(sk, CLOSED))
+ goto out;
+
/* If backlog is zero, disable listening. */
if (!backlog) {
if (sctp_sstate(sk, CLOSED))
#include <net/sctp/sctp.h>
#include <net/sctp/sm.h>
-struct sctp_stream *sctp_stream_new(__u16 incnt, __u16 outcnt, gfp_t gfp)
+int sctp_stream_new(struct sctp_association *asoc, gfp_t gfp)
{
struct sctp_stream *stream;
int i;
stream = kzalloc(sizeof(*stream), gfp);
if (!stream)
- return NULL;
+ return -ENOMEM;
- stream->outcnt = outcnt;
+ stream->outcnt = asoc->c.sinit_num_ostreams;
stream->out = kcalloc(stream->outcnt, sizeof(*stream->out), gfp);
if (!stream->out) {
kfree(stream);
- return NULL;
+ return -ENOMEM;
}
for (i = 0; i < stream->outcnt; i++)
stream->out[i].state = SCTP_STREAM_OPEN;
- stream->incnt = incnt;
+ asoc->stream = stream;
+
+ return 0;
+}
+
+int sctp_stream_init(struct sctp_association *asoc, gfp_t gfp)
+{
+ struct sctp_stream *stream = asoc->stream;
+ int i;
+
+ /* Initial stream->out size may be very big, so free it and alloc
+ * a new one with new outcnt to save memory.
+ */
+ kfree(stream->out);
+ stream->outcnt = asoc->c.sinit_num_ostreams;
+ stream->out = kcalloc(stream->outcnt, sizeof(*stream->out), gfp);
+ if (!stream->out)
+ goto nomem;
+
+ for (i = 0; i < stream->outcnt; i++)
+ stream->out[i].state = SCTP_STREAM_OPEN;
+
+ stream->incnt = asoc->c.sinit_max_instreams;
stream->in = kcalloc(stream->incnt, sizeof(*stream->in), gfp);
if (!stream->in) {
kfree(stream->out);
- kfree(stream);
- return NULL;
+ goto nomem;
}
- return stream;
+ return 0;
+
+nomem:
+ asoc->stream = NULL;
+ kfree(stream);
+
+ return -ENOMEM;
}
void sctp_stream_free(struct sctp_stream *stream)
transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT;
}
-void sctp_transport_update_pmtu(struct sock *sk, struct sctp_transport *t, u32 pmtu)
+void sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu)
{
- struct dst_entry *dst;
+ struct dst_entry *dst = sctp_transport_dst_check(t);
if (unlikely(pmtu < SCTP_DEFAULT_MINSEGMENT)) {
pr_warn("%s: Reported pmtu %d too low, using default minimum of %d\n",
- __func__, pmtu,
- SCTP_DEFAULT_MINSEGMENT);
+ __func__, pmtu, SCTP_DEFAULT_MINSEGMENT);
/* Use default minimum segment size and disable
* pmtu discovery on this transport.
*/
t->pathmtu = pmtu;
}
- dst = sctp_transport_dst_check(t);
- if (!dst)
- t->af_specific->get_dst(t, &t->saddr, &t->fl, sk);
-
if (dst) {
- dst->ops->update_pmtu(dst, sk, NULL, pmtu);
-
+ dst->ops->update_pmtu(dst, t->asoc->base.sk, NULL, pmtu);
dst = sctp_transport_dst_check(t);
- if (!dst)
- t->af_specific->get_dst(t, &t->saddr, &t->fl, sk);
}
+
+ if (!dst)
+ t->af_specific->get_dst(t, &t->saddr, &t->fl, t->asoc->base.sk);
}
/* Caches the dst entry and source address for a transport's destination
if (!tsk_peer_msg(tsk, hdr))
goto exit;
+ if (unlikely(msg_errcode(hdr))) {
+ tipc_set_sk_state(sk, TIPC_DISCONNECTING);
+ tipc_node_remove_conn(sock_net(sk), tsk_peer_node(tsk),
+ tsk_peer_port(tsk));
+ sk->sk_state_change(sk);
+ goto exit;
+ }
+
tsk->probe_unacked = false;
if (mtyp == CONN_PROBE) {
}
} while (sent < dlen && !rc);
- return rc ? rc : sent;
+ return sent ? sent : rc;
}
/**
struct sock *sk = sock->sk;
DEFINE_WAIT(wait);
long timeo = *timeop;
- int err;
+ int err = sock_error(sk);
+
+ if (err)
+ return err;
for (;;) {
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
err = sock_intr_errno(timeo);
if (signal_pending(current))
break;
+
+ err = sock_error(sk);
+ if (err)
+ break;
}
finish_wait(sk_sleep(sk), &wait);
*timeop = timeo;
if (unlikely(flags & MSG_PEEK))
goto exit;
- tsk->rcv_unacked += tsk_inc(tsk, hlen + sz);
+ tsk->rcv_unacked += tsk_inc(tsk, hlen + msg_data_sz(msg));
if (unlikely(tsk->rcv_unacked >= (tsk->rcv_win / 4)))
tipc_sk_send_ack(tsk);
tsk_advance_rx_queue(sk);
struct sock *sk = &tsk->sk;
struct net *net = sock_net(sk);
struct tipc_msg *hdr = buf_msg(skb);
+ u32 pport = msg_origport(hdr);
+ u32 pnode = msg_orignode(hdr);
if (unlikely(msg_mcast(hdr)))
return false;
switch (sk->sk_state) {
case TIPC_CONNECTING:
/* Accept only ACK or NACK message */
- if (unlikely(!msg_connected(hdr)))
- return false;
+ if (unlikely(!msg_connected(hdr))) {
+ if (pport != tsk_peer_port(tsk) ||
+ pnode != tsk_peer_node(tsk))
+ return false;
+
+ tipc_set_sk_state(sk, TIPC_DISCONNECTING);
+ sk->sk_err = ECONNREFUSED;
+ sk->sk_state_change(sk);
+ return true;
+ }
if (unlikely(msg_errcode(hdr))) {
tipc_set_sk_state(sk, TIPC_DISCONNECTING);
sk->sk_err = ECONNREFUSED;
+ sk->sk_state_change(sk);
return true;
}
if (unlikely(!msg_isdata(hdr))) {
tipc_set_sk_state(sk, TIPC_DISCONNECTING);
sk->sk_err = EINVAL;
+ sk->sk_state_change(sk);
return true;
}
return true;
/* If empty 'ACK-' message, wake up sleeping connect() */
- if (waitqueue_active(sk_sleep(sk)))
- wake_up_interruptible(sk_sleep(sk));
+ sk->sk_data_ready(sk);
/* 'ACK-' message is neither accepted nor rejected: */
msg_set_dest_droppable(hdr, 1);
/* Age scan results with time spent in suspend */
cfg80211_bss_age(rdev, get_seconds() - rdev->suspend_at);
- if (rdev->ops->resume) {
- rtnl_lock();
- if (rdev->wiphy.registered)
- ret = rdev_resume(rdev);
- rtnl_unlock();
- }
+ rtnl_lock();
+ if (rdev->wiphy.registered && rdev->ops->resume)
+ ret = rdev_resume(rdev);
+ rtnl_unlock();
return ret;
}
if (xo)
xfrm_gro = xo->flags & XFRM_GRO;
- err = x->inner_mode->afinfo->transport_finish(skb, async);
+ err = x->inner_mode->afinfo->transport_finish(skb, xfrm_gro || async);
if (xfrm_gro) {
skb_dst_drop(skb);
gro_cells_receive(&gro_cells, skb);
err = -ESRCH;
out:
spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+
+ if (cnt)
+ xfrm_garbage_collect(net);
+
return err;
}
EXPORT_SYMBOL(xfrm_policy_flush);
if (stx->stx_mask & STATX_BTIME)
print_time(" Birth: ", &stx->stx_btime);
- if (stx->stx_attributes) {
- unsigned char bits;
+ if (stx->stx_attributes_mask) {
+ unsigned char bits, mbits;
int loop, byte;
static char attr_representation[64 + 1] =
printf("Attributes: %016llx (", stx->stx_attributes);
for (byte = 64 - 8; byte >= 0; byte -= 8) {
bits = stx->stx_attributes >> byte;
+ mbits = stx->stx_attributes_mask >> byte;
for (loop = 7; loop >= 0; loop--) {
int bit = byte + loop;
- if (bits & 0x80)
+ if (!(mbits & 0x80))
+ putchar('.'); /* Not supported */
+ else if (bits & 0x80)
putchar(attr_representation[63 - bit]);
else
- putchar('-');
+ putchar('-'); /* Not set */
bits <<= 1;
+ mbits <<= 1;
}
if (byte)
putchar(' ');
# $(call addtree,-I$(obj)) locates .h files in srctree, from generated .c files
# and locates generated .h files
# FIXME: Replace both with specific CFLAGS* statements in the makefiles
-__c_flags = $(if $(obj),-I$(srctree)/$(src) -I$(obj)) \
+__c_flags = $(if $(obj),$(call addtree,-I$(src)) -I$(obj)) \
$(call flags,_c_flags)
__a_flags = $(call flags,_a_flags)
__cpp_flags = $(call flags,_cpp_flags)
# sh64 port by Paul Mundt
# Random bits by Matt Mackall <mpm@selenic.com>
# M68k port by Geert Uytterhoeven and Andreas Schwab
-# AVR32 port by Haavard Skinnemoen (Atmel)
# AArch64, PARISC ports by Kyle McMartin
# sparc port by Martin Habets <errandir_news@mph.eclipse.co.uk>
#
} elsif ($arch eq 'arm') {
#c0008ffc: e24dd064 sub sp, sp, #100 ; 0x64
$re = qr/.*sub.*sp, sp, #(([0-9]{2}|[3-9])[0-9]{2})/o;
- } elsif ($arch eq 'avr32') {
- #8000008a: 20 1d sub sp,4
- #80000ca8: fa cd 05 b0 sub sp,sp,1456
- $re = qr/^.*sub.*sp.*,([0-9]{1,8})/o;
} elsif ($arch =~ /^x86(_64)?$/ || $arch =~ /^i[3456]86$/) {
#c0105234: 81 ec ac 05 00 00 sub $0x5ac,%esp
# or
#define __IGNORE_sysfs
#define __IGNORE_uselib
#define __IGNORE__sysctl
+#define __IGNORE_arch_prctl
/* ... including the "new" 32-bit uid syscalls */
#define __IGNORE_lchown32
current = menu;
display_tree_part();
gtk_widget_set_sensitive(back_btn, TRUE);
- } else if ((col == COL_OPTION)) {
+ } else if (col == COL_OPTION) {
toggle_sym_value(menu);
gtk_tree_view_expand_row(view, path, TRUE);
}
validating memory ranges against heap object sizes in
support of CONFIG_HARDENED_USERCOPY.
-config HAVE_ARCH_HARDENED_USERCOPY
- bool
- help
- The architecture supports CONFIG_HARDENED_USERCOPY by
- calling check_object_size() just before performing the
- userspace copies in the low level implementation of
- copy_to_user() and copy_from_user().
-
config HARDENED_USERCOPY
bool "Harden memory copies between kernel and userspace"
- depends on HAVE_ARCH_HARDENED_USERCOPY
depends on HAVE_HARDENED_USERCOPY_ALLOCATOR
select BUG
help
* immediately unlinked.
*/
struct key_type key_type_dead = {
- .name = "dead",
+ .name = ".dead",
};
/*
* Create and join an anonymous session keyring or join a named session
* keyring, creating it if necessary. A named session keyring must have Search
* permission for it to be joined. Session keyrings without this permit will
- * be skipped over.
+ * be skipped over. It is not permitted for userspace to create or join
+ * keyrings whose name begin with a dot.
*
* If successful, the ID of the joined session keyring will be returned.
*/
ret = PTR_ERR(name);
goto error;
}
+
+ ret = -EPERM;
+ if (name[0] == '.')
+ goto error_name;
}
/* join the session */
ret = join_session_keyring(name);
+error_name:
kfree(name);
-
error:
return ret;
}
* Read or set the default keyring in which request_key() will cache keys and
* return the old setting.
*
- * If a process keyring is specified then this will be created if it doesn't
- * yet exist. The old setting will be returned if successful.
+ * If a thread or process keyring is specified then it will be created if it
+ * doesn't yet exist. The old setting will be returned if successful.
*/
long keyctl_set_reqkey_keyring(int reqkey_defl)
{
case KEY_REQKEY_DEFL_PROCESS_KEYRING:
ret = install_process_keyring_to_cred(new);
- if (ret < 0) {
- if (ret != -EEXIST)
- goto error;
- ret = 0;
- }
+ if (ret < 0)
+ goto error;
goto set;
case KEY_REQKEY_DEFL_DEFAULT:
}
/*
- * Install a fresh thread keyring directly to new credentials. This keyring is
- * allowed to overrun the quota.
+ * Install a thread keyring to the given credentials struct if it didn't have
+ * one already. This is allowed to overrun the quota.
+ *
+ * Return: 0 if a thread keyring is now present; -errno on failure.
*/
int install_thread_keyring_to_cred(struct cred *new)
{
struct key *keyring;
+ if (new->thread_keyring)
+ return 0;
+
keyring = keyring_alloc("_tid", new->uid, new->gid, new,
KEY_POS_ALL | KEY_USR_VIEW,
KEY_ALLOC_QUOTA_OVERRUN,
}
/*
- * Install a fresh thread keyring, discarding the old one.
+ * Install a thread keyring to the current task if it didn't have one already.
+ *
+ * Return: 0 if a thread keyring is now present; -errno on failure.
*/
static int install_thread_keyring(void)
{
if (!new)
return -ENOMEM;
- BUG_ON(new->thread_keyring);
-
ret = install_thread_keyring_to_cred(new);
if (ret < 0) {
abort_creds(new);
}
/*
- * Install a process keyring directly to a credentials struct.
+ * Install a process keyring to the given credentials struct if it didn't have
+ * one already. This is allowed to overrun the quota.
*
- * Returns -EEXIST if there was already a process keyring, 0 if one installed,
- * and other value on any other error
+ * Return: 0 if a process keyring is now present; -errno on failure.
*/
int install_process_keyring_to_cred(struct cred *new)
{
struct key *keyring;
if (new->process_keyring)
- return -EEXIST;
+ return 0;
keyring = keyring_alloc("_pid", new->uid, new->gid, new,
KEY_POS_ALL | KEY_USR_VIEW,
}
/*
- * Make sure a process keyring is installed for the current process. The
- * existing process keyring is not replaced.
+ * Install a process keyring to the current task if it didn't have one already.
*
- * Returns 0 if there is a process keyring by the end of this function, some
- * error otherwise.
+ * Return: 0 if a process keyring is now present; -errno on failure.
*/
static int install_process_keyring(void)
{
ret = install_process_keyring_to_cred(new);
if (ret < 0) {
abort_creds(new);
- return ret != -EEXIST ? ret : 0;
+ return ret;
}
return commit_creds(new);
}
/*
- * Install a session keyring directly to a credentials struct.
+ * Install the given keyring as the session keyring of the given credentials
+ * struct, replacing the existing one if any. If the given keyring is NULL,
+ * then install a new anonymous session keyring.
+ *
+ * Return: 0 on success; -errno on failure.
*/
int install_session_keyring_to_cred(struct cred *cred, struct key *keyring)
{
}
/*
- * Install a session keyring, discarding the old one. If a keyring is not
- * supplied, an empty one is invented.
+ * Install the given keyring as the session keyring of the current task,
+ * replacing the existing one if any. If the given keyring is NULL, then
+ * install a new anonymous session keyring.
+ *
+ * Return: 0 on success; -errno on failure.
*/
static int install_session_keyring(struct key *keyring)
{
static bool tomoyo_kernel_service(void)
{
/* Nothing to do if I am a kernel service. */
- return segment_eq(get_fs(), KERNEL_DS);
+ return uaccess_kernel();
}
/**
/* wait until all locks are released */
void snd_use_lock_sync_helper(snd_use_lock_t *lockp, const char *file, int line)
{
- int max_count = 5 * HZ;
+ int warn_count = 5 * HZ;
if (atomic_read(lockp) < 0) {
pr_warn("ALSA: seq_lock: lock trouble [counter = %d] in %s:%d\n", atomic_read(lockp), file, line);
return;
}
while (atomic_read(lockp) > 0) {
- if (max_count == 0) {
- pr_warn("ALSA: seq_lock: timeout [%d left] in %s:%d\n", atomic_read(lockp), file, line);
- break;
- }
+ if (warn_count-- == 0)
+ pr_warn("ALSA: seq_lock: waiting [%d left] in %s:%d\n", atomic_read(lockp), file, line);
schedule_timeout_uninterruptible(1);
- max_count--;
}
}
struct snd_rawmidi_substream *substream;
snd_fw_async_midi_port_fill fill;
- unsigned int consume_bytes;
+ int consume_bytes;
};
int snd_fw_async_midi_port_init(struct snd_fw_async_midi_port *port,
if (err < 0)
goto error;
- err = detect_quirks(oxfw);
+ err = snd_oxfw_stream_discover(oxfw);
if (err < 0)
goto error;
- err = snd_oxfw_stream_discover(oxfw);
+ err = detect_quirks(oxfw);
if (err < 0)
goto error;
* to be included from codec driver
*/
-#if IS_ENABLED(CONFIG_LEDS_DELL_NETBOOKS)
+#if IS_ENABLED(CONFIG_DELL_LAPTOP)
#include <linux/dell-led.h>
static int dell_led_value;
-static int (*dell_led_set_func)(int, int);
+static int (*dell_micmute_led_set_func)(int);
static void (*dell_old_cap_hook)(struct hda_codec *,
struct snd_kcontrol *,
struct snd_ctl_elem_value *);
if (dell_old_cap_hook)
dell_old_cap_hook(codec, kcontrol, ucontrol);
- if (!ucontrol || !dell_led_set_func)
+ if (!ucontrol || !dell_micmute_led_set_func)
return;
if (strcmp("Capture Switch", ucontrol->id.name) == 0 && ucontrol->id.index == 0) {
/* TODO: How do I verify if it's a mono or stereo here? */
if (val == dell_led_value)
return;
dell_led_value = val;
- if (dell_led_set_func)
- dell_led_set_func(DELL_LED_MICMUTE, dell_led_value);
+ if (dell_micmute_led_set_func)
+ dell_micmute_led_set_func(dell_led_value);
}
}
bool removefunc = false;
if (action == HDA_FIXUP_ACT_PROBE) {
- if (!dell_led_set_func)
- dell_led_set_func = symbol_request(dell_app_wmi_led_set);
- if (!dell_led_set_func) {
- codec_warn(codec, "Failed to find dell wmi symbol dell_app_wmi_led_set\n");
+ if (!dell_micmute_led_set_func)
+ dell_micmute_led_set_func = symbol_request(dell_micmute_led_set);
+ if (!dell_micmute_led_set_func) {
+ codec_warn(codec, "Failed to find dell wmi symbol dell_micmute_led_set\n");
return;
}
removefunc = true;
- if (dell_led_set_func(DELL_LED_MICMUTE, false) >= 0) {
+ if (dell_micmute_led_set_func(false) >= 0) {
dell_led_value = 0;
if (spec->gen.num_adc_nids > 1 && !spec->gen.dyn_adc_switch)
codec_dbg(codec, "Skipping micmute LED control due to several ADCs");
}
- if (dell_led_set_func && (action == HDA_FIXUP_ACT_FREE || removefunc)) {
- symbol_put(dell_app_wmi_led_set);
- dell_led_set_func = NULL;
+ if (dell_micmute_led_set_func && (action == HDA_FIXUP_ACT_FREE || removefunc)) {
+ symbol_put(dell_micmute_led_set);
+ dell_micmute_led_set_func = NULL;
dell_old_cap_hook = NULL;
}
}
-#else /* CONFIG_LEDS_DELL_NETBOOKS */
+#else /* CONFIG_DELL_LAPTOP */
static void alc_fixup_dell_wmi(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
{
}
-#endif /* CONFIG_LEDS_DELL_NETBOOKS */
+#endif /* CONFIG_DELL_LAPTOP */
.codec_dai_name = "snd-soc-dummy-dai",
.codec_name = "snd-soc-dummy",
.platform_name = "sst-mfld-platform",
- .ignore_suspend = 1,
+ .nonatomic = true,
.dynamic = 1,
.dpcm_playback = 1,
.dpcm_capture = 1,
.codec_dai_name = "snd-soc-dummy-dai",
.codec_name = "snd-soc-dummy",
.platform_name = "sst-mfld-platform",
- .ignore_suspend = 1,
.nonatomic = true,
.dynamic = 1,
.dpcm_playback = 1,
| SND_SOC_DAIFMT_CBS_CFS,
.be_hw_params_fixup = byt_rt5640_codec_fixup,
.ignore_suspend = 1,
+ .nonatomic = true,
.dpcm_playback = 1,
.dpcm_capture = 1,
.init = byt_rt5640_init,
.codec_dai_name = "snd-soc-dummy-dai",
.codec_name = "snd-soc-dummy",
.platform_name = "sst-mfld-platform",
- .ignore_suspend = 1,
.nonatomic = true,
.dynamic = 1,
.dpcm_playback = 1,
.codec_dai_name = "snd-soc-dummy-dai",
.codec_name = "snd-soc-dummy",
.platform_name = "sst-mfld-platform",
- .ignore_suspend = 1,
.nonatomic = true,
.dynamic = 1,
.dpcm_playback = 1,
}
}
+ se->texts = (const char * const *)se->dobj.control.dtexts;
return 0;
err:
int ver; /* IP version, used by register access macros */
struct regmap_field *clk_sel;
struct regmap_field *valid_sel;
+ spinlock_t irq_lock; /* use to prevent race condition with IRQ */
/* capabilities */
const struct snd_pcm_hardware *hw;
unsigned int status;
unsigned int tmp;
- if (player->state == UNIPERIF_STATE_STOPPED) {
- /* Unexpected IRQ: do nothing */
- return IRQ_NONE;
- }
+ spin_lock(&player->irq_lock);
+ if (!player->substream)
+ goto irq_spin_unlock;
+
+ snd_pcm_stream_lock(player->substream);
+ if (player->state == UNIPERIF_STATE_STOPPED)
+ goto stream_unlock;
/* Get interrupt status & clear them immediately */
status = GET_UNIPERIF_ITS(player);
SET_UNIPERIF_ITM_BCLR_FIFO_ERROR(player);
/* Stop the player */
- snd_pcm_stream_lock(player->substream);
snd_pcm_stop(player->substream, SNDRV_PCM_STATE_XRUN);
- snd_pcm_stream_unlock(player->substream);
}
ret = IRQ_HANDLED;
SET_UNIPERIF_ITM_BCLR_DMA_ERROR(player);
/* Stop the player */
- snd_pcm_stream_lock(player->substream);
snd_pcm_stop(player->substream, SNDRV_PCM_STATE_XRUN);
- snd_pcm_stream_unlock(player->substream);
ret = IRQ_HANDLED;
}
if (!player->underflow_enabled) {
dev_err(player->dev,
"unexpected Underflow recovering\n");
- return -EPERM;
+ ret = -EPERM;
+ goto stream_unlock;
}
/* Read the underflow recovery duration */
tmp = GET_UNIPERIF_STATUS_1_UNDERFLOW_DURATION(player);
dev_err(player->dev, "Underflow recovery failed\n");
/* Stop the player */
- snd_pcm_stream_lock(player->substream);
snd_pcm_stop(player->substream, SNDRV_PCM_STATE_XRUN);
- snd_pcm_stream_unlock(player->substream);
ret = IRQ_HANDLED;
}
+stream_unlock:
+ snd_pcm_stream_unlock(player->substream);
+irq_spin_unlock:
+ spin_unlock(&player->irq_lock);
+
return ret;
}
struct sti_uniperiph_data *priv = snd_soc_dai_get_drvdata(dai);
struct uniperif *player = priv->dai_data.uni;
struct snd_aes_iec958 *iec958 = &player->stream_settings.iec958;
+ unsigned long flags;
mutex_lock(&player->ctrl_lock);
iec958->status[0] = ucontrol->value.iec958.status[0];
iec958->status[3] = ucontrol->value.iec958.status[3];
mutex_unlock(&player->ctrl_lock);
+ spin_lock_irqsave(&player->irq_lock, flags);
if (player->substream && player->substream->runtime)
uni_player_set_channel_status(player,
player->substream->runtime);
else
uni_player_set_channel_status(player, NULL);
+ spin_unlock_irqrestore(&player->irq_lock, flags);
return 0;
}
{
struct sti_uniperiph_data *priv = snd_soc_dai_get_drvdata(dai);
struct uniperif *player = priv->dai_data.uni;
+ unsigned long flags;
int ret;
+ spin_lock_irqsave(&player->irq_lock, flags);
player->substream = substream;
+ spin_unlock_irqrestore(&player->irq_lock, flags);
player->clk_adj = 0;
{
struct sti_uniperiph_data *priv = snd_soc_dai_get_drvdata(dai);
struct uniperif *player = priv->dai_data.uni;
+ unsigned long flags;
+ spin_lock_irqsave(&player->irq_lock, flags);
if (player->state != UNIPERIF_STATE_STOPPED)
/* Stop the player */
uni_player_stop(player);
player->substream = NULL;
+ spin_unlock_irqrestore(&player->irq_lock, flags);
}
static int uni_player_parse_dt_audio_glue(struct platform_device *pdev,
}
mutex_init(&player->ctrl_lock);
+ spin_lock_init(&player->irq_lock);
/* Ensure that disabled by default */
SET_UNIPERIF_CONFIG_BACK_STALL_REQ_DISABLE(player);
struct uniperif *reader = dev_id;
unsigned int status;
+ spin_lock(&reader->irq_lock);
+ if (!reader->substream)
+ goto irq_spin_unlock;
+
+ snd_pcm_stream_lock(reader->substream);
if (reader->state == UNIPERIF_STATE_STOPPED) {
/* Unexpected IRQ: do nothing */
dev_warn(reader->dev, "unexpected IRQ\n");
- return IRQ_HANDLED;
+ goto stream_unlock;
}
/* Get interrupt status & clear them immediately */
if (unlikely(status & UNIPERIF_ITS_FIFO_ERROR_MASK(reader))) {
dev_err(reader->dev, "FIFO error detected\n");
- snd_pcm_stream_lock(reader->substream);
snd_pcm_stop(reader->substream, SNDRV_PCM_STATE_XRUN);
- snd_pcm_stream_unlock(reader->substream);
- return IRQ_HANDLED;
+ ret = IRQ_HANDLED;
}
+stream_unlock:
+ snd_pcm_stream_unlock(reader->substream);
+irq_spin_unlock:
+ spin_unlock(&reader->irq_lock);
+
return ret;
}
{
struct sti_uniperiph_data *priv = snd_soc_dai_get_drvdata(dai);
struct uniperif *reader = priv->dai_data.uni;
+ unsigned long flags;
int ret;
+ spin_lock_irqsave(&reader->irq_lock, flags);
reader->substream = substream;
+ spin_unlock_irqrestore(&reader->irq_lock, flags);
if (!UNIPERIF_TYPE_IS_TDM(reader))
return 0;
{
struct sti_uniperiph_data *priv = snd_soc_dai_get_drvdata(dai);
struct uniperif *reader = priv->dai_data.uni;
+ unsigned long flags;
+ spin_lock_irqsave(&reader->irq_lock, flags);
if (reader->state != UNIPERIF_STATE_STOPPED) {
/* Stop the reader */
uni_reader_stop(reader);
}
reader->substream = NULL;
+ spin_unlock_irqrestore(&reader->irq_lock, flags);
}
static const struct snd_soc_dai_ops uni_reader_dai_ops = {
return -EBUSY;
}
+ spin_lock_init(&reader->irq_lock);
+
return 0;
}
EXPORT_SYMBOL_GPL(uni_reader_init);
#define KVM_DEV_ARM_VGIC_GRP_CPU_REGS 2
#define KVM_DEV_ARM_VGIC_CPUID_SHIFT 32
#define KVM_DEV_ARM_VGIC_CPUID_MASK (0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT)
+#define KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT 32
+#define KVM_DEV_ARM_VGIC_V3_MPIDR_MASK \
+ (0xffffffffULL << KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT)
#define KVM_DEV_ARM_VGIC_OFFSET_SHIFT 0
#define KVM_DEV_ARM_VGIC_OFFSET_MASK (0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
+#define KVM_DEV_ARM_VGIC_SYSREG_INSTR_MASK (0xffff)
#define KVM_DEV_ARM_VGIC_GRP_NR_IRQS 3
#define KVM_DEV_ARM_VGIC_GRP_CTRL 4
+#define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5
+#define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6
+#define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO 7
+#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT 10
+#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \
+ (0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT)
+#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK 0x3ff
+#define VGIC_LEVEL_INFO_LINE_LEVEL 0
+
#define KVM_DEV_ARM_VGIC_CTRL_INIT 0
/* KVM_IRQ_LINE irq field index values */
#define KVM_DEV_ARM_VGIC_GRP_CPU_REGS 2
#define KVM_DEV_ARM_VGIC_CPUID_SHIFT 32
#define KVM_DEV_ARM_VGIC_CPUID_MASK (0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT)
+#define KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT 32
+#define KVM_DEV_ARM_VGIC_V3_MPIDR_MASK \
+ (0xffffffffULL << KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT)
#define KVM_DEV_ARM_VGIC_OFFSET_SHIFT 0
#define KVM_DEV_ARM_VGIC_OFFSET_MASK (0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
+#define KVM_DEV_ARM_VGIC_SYSREG_INSTR_MASK (0xffff)
#define KVM_DEV_ARM_VGIC_GRP_NR_IRQS 3
#define KVM_DEV_ARM_VGIC_GRP_CTRL 4
+#define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5
+#define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6
+#define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO 7
+#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT 10
+#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \
+ (0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT)
+#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK 0x3ff
+#define VGIC_LEVEL_INFO_LINE_LEVEL 0
+
#define KVM_DEV_ARM_VGIC_CTRL_INIT 0
/* Device Control API on vcpu fd */
__u16 n_invalid;
};
+/* For KVM_PPC_CONFIGURE_V3_MMU */
+struct kvm_ppc_mmuv3_cfg {
+ __u64 flags;
+ __u64 process_table; /* second doubleword of partition table entry */
+};
+
+/* Flag values for KVM_PPC_CONFIGURE_V3_MMU */
+#define KVM_PPC_MMUV3_RADIX 1 /* 1 = radix mode, 0 = HPT */
+#define KVM_PPC_MMUV3_GTSE 2 /* global translation shootdown enb. */
+
+/* For KVM_PPC_GET_RMMU_INFO */
+struct kvm_ppc_rmmu_info {
+ struct kvm_ppc_radix_geom {
+ __u8 page_shift;
+ __u8 level_bits[4];
+ __u8 pad[3];
+ } geometries[8];
+ __u32 ap_encodings[8];
+};
+
/* Per-vcpu XICS interrupt controller state */
#define KVM_REG_PPC_ICP_STATE (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c)
#define KVM_XICS_LEVEL_SENSITIVE (1ULL << 40)
#define KVM_XICS_MASKED (1ULL << 41)
#define KVM_XICS_PENDING (1ULL << 42)
+#define KVM_XICS_PRESENTED (1ULL << 43)
+#define KVM_XICS_QUEUED (1ULL << 44)
#endif /* __LINUX_KVM_POWERPC_H */
#define LOCK_PREFIX "\n\tlock; "
+#include <asm/cmpxchg.h>
+
/*
* Atomic operations that C can't guarantee us. Useful for
* resource counting etc..
GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e");
}
+static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new)
+{
+ return cmpxchg(&v->counter, old, new);
+}
+
#endif /* _TOOLS_LINUX_ASM_X86_ATOMIC_H */
--- /dev/null
+#ifndef TOOLS_ASM_X86_CMPXCHG_H
+#define TOOLS_ASM_X86_CMPXCHG_H
+
+#include <linux/compiler.h>
+
+/*
+ * Non-existant functions to indicate usage errors at link time
+ * (or compile-time if the compiler implements __compiletime_error().
+ */
+extern void __cmpxchg_wrong_size(void)
+ __compiletime_error("Bad argument size for cmpxchg");
+
+/*
+ * Constants for operation sizes. On 32-bit, the 64-bit size it set to
+ * -1 because sizeof will never return -1, thereby making those switch
+ * case statements guaranteeed dead code which the compiler will
+ * eliminate, and allowing the "missing symbol in the default case" to
+ * indicate a usage error.
+ */
+#define __X86_CASE_B 1
+#define __X86_CASE_W 2
+#define __X86_CASE_L 4
+#ifdef __x86_64__
+#define __X86_CASE_Q 8
+#else
+#define __X86_CASE_Q -1 /* sizeof will never return -1 */
+#endif
+
+/*
+ * Atomic compare and exchange. Compare OLD with MEM, if identical,
+ * store NEW in MEM. Return the initial value in MEM. Success is
+ * indicated by comparing RETURN with OLD.
+ */
+#define __raw_cmpxchg(ptr, old, new, size, lock) \
+({ \
+ __typeof__(*(ptr)) __ret; \
+ __typeof__(*(ptr)) __old = (old); \
+ __typeof__(*(ptr)) __new = (new); \
+ switch (size) { \
+ case __X86_CASE_B: \
+ { \
+ volatile u8 *__ptr = (volatile u8 *)(ptr); \
+ asm volatile(lock "cmpxchgb %2,%1" \
+ : "=a" (__ret), "+m" (*__ptr) \
+ : "q" (__new), "0" (__old) \
+ : "memory"); \
+ break; \
+ } \
+ case __X86_CASE_W: \
+ { \
+ volatile u16 *__ptr = (volatile u16 *)(ptr); \
+ asm volatile(lock "cmpxchgw %2,%1" \
+ : "=a" (__ret), "+m" (*__ptr) \
+ : "r" (__new), "0" (__old) \
+ : "memory"); \
+ break; \
+ } \
+ case __X86_CASE_L: \
+ { \
+ volatile u32 *__ptr = (volatile u32 *)(ptr); \
+ asm volatile(lock "cmpxchgl %2,%1" \
+ : "=a" (__ret), "+m" (*__ptr) \
+ : "r" (__new), "0" (__old) \
+ : "memory"); \
+ break; \
+ } \
+ case __X86_CASE_Q: \
+ { \
+ volatile u64 *__ptr = (volatile u64 *)(ptr); \
+ asm volatile(lock "cmpxchgq %2,%1" \
+ : "=a" (__ret), "+m" (*__ptr) \
+ : "r" (__new), "0" (__old) \
+ : "memory"); \
+ break; \
+ } \
+ default: \
+ __cmpxchg_wrong_size(); \
+ } \
+ __ret; \
+})
+
+#define __cmpxchg(ptr, old, new, size) \
+ __raw_cmpxchg((ptr), (old), (new), (size), LOCK_PREFIX)
+
+#define cmpxchg(ptr, old, new) \
+ __cmpxchg(ptr, old, new, sizeof(*(ptr)))
+
+
+#endif /* TOOLS_ASM_X86_CMPXCHG_H */
#define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* cpu topology enum extensions */
#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */
#define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* TSC does not stop in C states */
-/* free, was #define X86_FEATURE_CLFLUSH_MONITOR ( 3*32+25) * "" clflush reqd with monitor */
+#define X86_FEATURE_CPUID ( 3*32+25) /* CPU has CPUID instruction itself */
#define X86_FEATURE_EXTD_APICID ( 3*32+26) /* has extended APICID (8 bits) */
#define X86_FEATURE_AMD_DCM ( 3*32+27) /* multi-node processor */
#define X86_FEATURE_APERFMPERF ( 3*32+28) /* APERFMPERF */
*
* Reuse free bits when adding new feature flags!
*/
-
+#define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* Ring 3 MONITOR/MWAIT */
+#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* Intel CPUID faulting */
#define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */
#define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */
#define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */
#define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */
#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */
-#define X86_FEATURE_RDPID (16*32+ 22) /* RDPID instruction */
+#define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */
+#define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */
/* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
#define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */
#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */
#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */
#define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */
-
#endif /* _ASM_X86_CPUFEATURES_H */
_ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail)
_ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail)
_ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail)
- _ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
+ _ASM_EXTABLE_FAULT(.L_cache_w2, .L_memcpy_mcsafe_fail)
_ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
_ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail)
_ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail)
lzma \
get_cpuid \
bpf \
+ sched_getcpu \
sdt
# FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list
test-get_cpuid.bin \
test-sdt.bin \
test-cxx.bin \
- test-jvmti.bin
+ test-jvmti.bin \
+ test-sched_getcpu.bin
FILES := $(addprefix $(OUTPUT),$(FILES))
-CC := $(CROSS_COMPILE)gcc -MD
-CXX := $(CROSS_COMPILE)g++ -MD
-PKG_CONFIG := $(CROSS_COMPILE)pkg-config
+CC ?= $(CROSS_COMPILE)gcc
+CXX ?= $(CROSS_COMPILE)g++
+PKG_CONFIG ?= $(CROSS_COMPILE)pkg-config
LLVM_CONFIG ?= llvm-config
all: $(FILES)
-__BUILD = $(CC) $(CFLAGS) -Wall -Werror -o $@ $(patsubst %.bin,%.c,$(@F)) $(LDFLAGS)
+__BUILD = $(CC) $(CFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.c,$(@F)) $(LDFLAGS)
BUILD = $(__BUILD) > $(@:.bin=.make.output) 2>&1
-__BUILDXX = $(CXX) $(CXXFLAGS) -Wall -Werror -o $@ $(patsubst %.bin,%.cpp,$(@F)) $(LDFLAGS)
+__BUILDXX = $(CXX) $(CXXFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.cpp,$(@F)) $(LDFLAGS)
BUILDXX = $(__BUILDXX) > $(@:.bin=.make.output) 2>&1
###############################
$(OUTPUT)test-glibc.bin:
$(BUILD)
+$(OUTPUT)test-sched_getcpu.bin:
+ $(BUILD)
+
DWARFLIBS := -ldw
ifeq ($(findstring -static,${LDFLAGS}),-static)
DWARFLIBS += -lelf -lebl -lz -llzma -lbz2
$(BUILD) $(FLAGS_PERL_EMBED)
$(OUTPUT)test-libpython.bin:
- $(BUILD)
+ $(BUILD) $(FLAGS_PYTHON_EMBED)
$(OUTPUT)test-libpython-version.bin:
$(BUILD)
# include "test-pthread-attr-setaffinity-np.c"
#undef main
+#define main main_test_sched_getcpu
+# include "test-sched_getcpu.c"
+#undef main
+
# if 0
/*
* Disable libbabeltrace check for test-all, because the requested
main_test_get_cpuid();
main_test_bpf();
main_test_libcrypto();
+ main_test_sched_getcpu();
main_test_sdt();
return 0;
--- /dev/null
+#define _GNU_SOURCE
+#include <sched.h>
+
+int main(void)
+{
+ return sched_getcpu();
+}
return __sync_sub_and_fetch(&v->counter, 1) == 0;
}
+#define cmpxchg(ptr, oldval, newval) \
+ __sync_val_compare_and_swap(ptr, oldval, newval)
+
+static inline int atomic_cmpxchg(atomic_t *v, int oldval, int newval)
+{
+ return cmpxchg(&(v)->counter, oldval, newval);
+}
+
#endif /* __TOOLS_ASM_GENERIC_ATOMIC_H */
#include <asm/atomic.h>
+/* atomic_cmpxchg_relaxed */
+#ifndef atomic_cmpxchg_relaxed
+#define atomic_cmpxchg_relaxed atomic_cmpxchg
+#define atomic_cmpxchg_release atomic_cmpxchg
+#endif /* atomic_cmpxchg_relaxed */
+
#endif /* __TOOLS_LINUX_ATOMIC_H */
--- /dev/null
+#ifndef _TOOLS_PERF_LINUX_BUG_H
+#define _TOOLS_PERF_LINUX_BUG_H
+
+/* Force a compilation error if condition is true, but also produce a
+ result (of value 0 and type size_t), so the expression can be used
+ e.g. in a structure initializer (or where-ever else comma expressions
+ aren't permitted). */
+#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); }))
+
+#endif /* _TOOLS_PERF_LINUX_BUG_H */
#if GCC_VERSION >= 70000 && !defined(__CHECKER__)
# define __fallthrough __attribute__ ((fallthrough))
#endif
+
+#if GCC_VERSION >= 40300
+# define __compiletime_error(message) __attribute__((error(message)))
+#endif /* GCC_VERSION >= 40300 */
+
+/* &a[0] degrades to a pointer: a different type from an array */
+#define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
#include <linux/compiler-gcc.h>
#endif
+#ifndef __compiletime_error
+# define __compiletime_error(message)
+#endif
+
/* Optimization barrier */
/* The "volatile" is due to gcc bugs */
#define barrier() __asm__ __volatile__("": : :"memory")
# define __always_inline inline __attribute__((always_inline))
#endif
+/* Are two types/vars the same type (ignoring qualifiers)? */
+#ifndef __same_type
+# define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b))
+#endif
+
#ifdef __ANDROID__
/*
* FIXME: Big hammer to get rid of tons of:
.off = OFF, \
.imm = 0 })
+/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */
+
+#define BPF_STX_XADD(SIZE, DST, SRC, OFF) \
+ ((struct bpf_insn) { \
+ .code = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = OFF, \
+ .imm = 0 })
+
/* Memory store, *(uint *) (dst_reg + off16) = imm32 */
#define BPF_ST_MEM(SIZE, DST, OFF, IMM) \
#include <linux/hash.h>
#include <linux/log2.h>
-#ifndef ARRAY_SIZE
-#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
-#endif
-
#define DEFINE_HASHTABLE(name, bits) \
struct hlist_head name[1 << (bits)] = \
{ [0 ... ((1 << (bits)) - 1)] = HLIST_HEAD_INIT }
#include <stdarg.h>
#include <stddef.h>
#include <assert.h>
+#include <linux/compiler.h>
+
+#ifndef UINT_MAX
+#define UINT_MAX (~0U)
+#endif
#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
int vscnprintf(char *buf, size_t size, const char *fmt, va_list args);
int scnprintf(char * buf, size_t size, const char * fmt, ...);
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr))
+
/*
* This looks more complex than it should be. But we need to
* get the type for the ~ right in round_down (it needs to be
#ifndef _TOOLS_LINUX_LOG2_H
#define _TOOLS_LINUX_LOG2_H
+#include <linux/bitops.h>
+#include <linux/types.h>
+
/*
* non-constant log of base 2 calculators
* - the arch may override these in asm/bitops.h if they can be implemented
--- /dev/null
+#ifndef _TOOLS_LINUX_REFCOUNT_H
+#define _TOOLS_LINUX_REFCOUNT_H
+
+/*
+ * Variant of atomic_t specialized for reference counts.
+ *
+ * The interface matches the atomic_t interface (to aid in porting) but only
+ * provides the few functions one should use for reference counting.
+ *
+ * It differs in that the counter saturates at UINT_MAX and will not move once
+ * there. This avoids wrapping the counter and causing 'spurious'
+ * use-after-free issues.
+ *
+ * Memory ordering rules are slightly relaxed wrt regular atomic_t functions
+ * and provide only what is strictly required for refcounts.
+ *
+ * The increments are fully relaxed; these will not provide ordering. The
+ * rationale is that whatever is used to obtain the object we're increasing the
+ * reference count on will provide the ordering. For locked data structures,
+ * its the lock acquire, for RCU/lockless data structures its the dependent
+ * load.
+ *
+ * Do note that inc_not_zero() provides a control dependency which will order
+ * future stores against the inc, this ensures we'll never modify the object
+ * if we did not in fact acquire a reference.
+ *
+ * The decrements will provide release order, such that all the prior loads and
+ * stores will be issued before, it also provides a control dependency, which
+ * will order us against the subsequent free().
+ *
+ * The control dependency is against the load of the cmpxchg (ll/sc) that
+ * succeeded. This means the stores aren't fully ordered, but this is fine
+ * because the 1->0 transition indicates no concurrency.
+ *
+ * Note that the allocator is responsible for ordering things between free()
+ * and alloc().
+ *
+ */
+
+#include <linux/atomic.h>
+#include <linux/kernel.h>
+
+#ifdef NDEBUG
+#define REFCOUNT_WARN(cond, str) (void)(cond)
+#define __refcount_check
+#else
+#define REFCOUNT_WARN(cond, str) BUG_ON(cond)
+#define __refcount_check __must_check
+#endif
+
+typedef struct refcount_struct {
+ atomic_t refs;
+} refcount_t;
+
+#define REFCOUNT_INIT(n) { .refs = ATOMIC_INIT(n), }
+
+static inline void refcount_set(refcount_t *r, unsigned int n)
+{
+ atomic_set(&r->refs, n);
+}
+
+static inline unsigned int refcount_read(const refcount_t *r)
+{
+ return atomic_read(&r->refs);
+}
+
+/*
+ * Similar to atomic_inc_not_zero(), will saturate at UINT_MAX and WARN.
+ *
+ * Provides no memory ordering, it is assumed the caller has guaranteed the
+ * object memory to be stable (RCU, etc.). It does provide a control dependency
+ * and thereby orders future stores. See the comment on top.
+ */
+static inline __refcount_check
+bool refcount_inc_not_zero(refcount_t *r)
+{
+ unsigned int old, new, val = atomic_read(&r->refs);
+
+ for (;;) {
+ new = val + 1;
+
+ if (!val)
+ return false;
+
+ if (unlikely(!new))
+ return true;
+
+ old = atomic_cmpxchg_relaxed(&r->refs, val, new);
+ if (old == val)
+ break;
+
+ val = old;
+ }
+
+ REFCOUNT_WARN(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
+
+ return true;
+}
+
+/*
+ * Similar to atomic_inc(), will saturate at UINT_MAX and WARN.
+ *
+ * Provides no memory ordering, it is assumed the caller already has a
+ * reference on the object, will WARN when this is not so.
+ */
+static inline void refcount_inc(refcount_t *r)
+{
+ REFCOUNT_WARN(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n");
+}
+
+/*
+ * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to
+ * decrement when saturated at UINT_MAX.
+ *
+ * Provides release memory ordering, such that prior loads and stores are done
+ * before, and provides a control dependency such that free() must come after.
+ * See the comment on top.
+ */
+static inline __refcount_check
+bool refcount_sub_and_test(unsigned int i, refcount_t *r)
+{
+ unsigned int old, new, val = atomic_read(&r->refs);
+
+ for (;;) {
+ if (unlikely(val == UINT_MAX))
+ return false;
+
+ new = val - i;
+ if (new > val) {
+ REFCOUNT_WARN(new > val, "refcount_t: underflow; use-after-free.\n");
+ return false;
+ }
+
+ old = atomic_cmpxchg_release(&r->refs, val, new);
+ if (old == val)
+ break;
+
+ val = old;
+ }
+
+ return !new;
+}
+
+static inline __refcount_check
+bool refcount_dec_and_test(refcount_t *r)
+{
+ return refcount_sub_and_test(1, r);
+}
+
+
+#endif /* _ATOMIC_LINUX_REFCOUNT_H */
#define __SANE_USERSPACE_TYPES__ /* For PPC64, to get LL64 types */
#include <asm/types.h>
+#include <asm/posix_types.h>
struct page;
struct kmem_cache;
--- /dev/null
+#ifndef _UAPI_LINUX_FCNTL_H
+#define _UAPI_LINUX_FCNTL_H
+
+#include <asm/fcntl.h>
+
+#define F_SETLEASE (F_LINUX_SPECIFIC_BASE + 0)
+#define F_GETLEASE (F_LINUX_SPECIFIC_BASE + 1)
+
+/*
+ * Cancel a blocking posix lock; internal use only until we expose an
+ * asynchronous lock api to userspace:
+ */
+#define F_CANCELLK (F_LINUX_SPECIFIC_BASE + 5)
+
+/* Create a file descriptor with FD_CLOEXEC set. */
+#define F_DUPFD_CLOEXEC (F_LINUX_SPECIFIC_BASE + 6)
+
+/*
+ * Request nofications on a directory.
+ * See below for events that may be notified.
+ */
+#define F_NOTIFY (F_LINUX_SPECIFIC_BASE+2)
+
+/*
+ * Set and get of pipe page size array
+ */
+#define F_SETPIPE_SZ (F_LINUX_SPECIFIC_BASE + 7)
+#define F_GETPIPE_SZ (F_LINUX_SPECIFIC_BASE + 8)
+
+/*
+ * Set/Get seals
+ */
+#define F_ADD_SEALS (F_LINUX_SPECIFIC_BASE + 9)
+#define F_GET_SEALS (F_LINUX_SPECIFIC_BASE + 10)
+
+/*
+ * Types of seals
+ */
+#define F_SEAL_SEAL 0x0001 /* prevent further seals from being set */
+#define F_SEAL_SHRINK 0x0002 /* prevent file from shrinking */
+#define F_SEAL_GROW 0x0004 /* prevent file from growing */
+#define F_SEAL_WRITE 0x0008 /* prevent writes */
+/* (1U << 31) is reserved for signed error codes */
+
+/*
+ * Types of directory notifications that may be requested.
+ */
+#define DN_ACCESS 0x00000001 /* File accessed */
+#define DN_MODIFY 0x00000002 /* File modified */
+#define DN_CREATE 0x00000004 /* File created */
+#define DN_DELETE 0x00000008 /* File removed */
+#define DN_RENAME 0x00000010 /* File renamed */
+#define DN_ATTRIB 0x00000020 /* File changed attibutes */
+#define DN_MULTISHOT 0x80000000 /* Don't remove notifier */
+
+#define AT_FDCWD -100 /* Special value used to indicate
+ openat should use the current
+ working directory. */
+#define AT_SYMLINK_NOFOLLOW 0x100 /* Do not follow symbolic links. */
+#define AT_REMOVEDIR 0x200 /* Remove directory instead of
+ unlinking file. */
+#define AT_SYMLINK_FOLLOW 0x400 /* Follow symbolic links. */
+#define AT_NO_AUTOMOUNT 0x800 /* Suppress terminal automount traversal */
+#define AT_EMPTY_PATH 0x1000 /* Allow empty relative pathname */
+
+#define AT_STATX_SYNC_TYPE 0x6000 /* Type of synchronisation required from statx() */
+#define AT_STATX_SYNC_AS_STAT 0x0000 /* - Do whatever stat() does */
+#define AT_STATX_FORCE_SYNC 0x2000 /* - Force the attributes to be sync'd with the server */
+#define AT_STATX_DONT_SYNC 0x4000 /* - Don't sync attributes with the server */
+
+
+#endif /* _UAPI_LINUX_FCNTL_H */
use_clockid : 1, /* use @clockid for time fields */
context_switch : 1, /* context switch data */
write_backward : 1, /* Write ring buffer from end to beginning */
- __reserved_1 : 36;
+ namespaces : 1, /* include namespaces data */
+ __reserved_1 : 35;
union {
__u32 wakeup_events; /* wakeup every n events */
__u16 size;
};
+struct perf_ns_link_info {
+ __u64 dev;
+ __u64 ino;
+};
+
+enum {
+ NET_NS_INDEX = 0,
+ UTS_NS_INDEX = 1,
+ IPC_NS_INDEX = 2,
+ PID_NS_INDEX = 3,
+ USER_NS_INDEX = 4,
+ MNT_NS_INDEX = 5,
+ CGROUP_NS_INDEX = 6,
+
+ NR_NAMESPACES, /* number of available namespaces */
+};
+
enum perf_event_type {
/*
*/
PERF_RECORD_SWITCH_CPU_WIDE = 15,
+ /*
+ * struct {
+ * struct perf_event_header header;
+ * u32 pid;
+ * u32 tid;
+ * u64 nr_namespaces;
+ * { u64 dev, inode; } [nr_namespaces];
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_NAMESPACES = 16,
+
PERF_RECORD_MAX, /* non-ABI */
};
*/
#define PERF_AUX_FLAG_TRUNCATED 0x01 /* record was truncated to fit */
#define PERF_AUX_FLAG_OVERWRITE 0x02 /* snapshot from overwrite mode */
+#define PERF_AUX_FLAG_PARTIAL 0x04 /* record contains gaps */
#define PERF_FLAG_FD_NO_GROUP (1UL << 0)
#define PERF_FLAG_FD_OUTPUT (1UL << 1)
--- /dev/null
+#ifndef _UAPI_LINUX_STAT_H
+#define _UAPI_LINUX_STAT_H
+
+#include <linux/types.h>
+
+#if defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2)
+
+#define S_IFMT 00170000
+#define S_IFSOCK 0140000
+#define S_IFLNK 0120000
+#define S_IFREG 0100000
+#define S_IFBLK 0060000
+#define S_IFDIR 0040000
+#define S_IFCHR 0020000
+#define S_IFIFO 0010000
+#define S_ISUID 0004000
+#define S_ISGID 0002000
+#define S_ISVTX 0001000
+
+#define S_ISLNK(m) (((m) & S_IFMT) == S_IFLNK)
+#define S_ISREG(m) (((m) & S_IFMT) == S_IFREG)
+#define S_ISDIR(m) (((m) & S_IFMT) == S_IFDIR)
+#define S_ISCHR(m) (((m) & S_IFMT) == S_IFCHR)
+#define S_ISBLK(m) (((m) & S_IFMT) == S_IFBLK)
+#define S_ISFIFO(m) (((m) & S_IFMT) == S_IFIFO)
+#define S_ISSOCK(m) (((m) & S_IFMT) == S_IFSOCK)
+
+#define S_IRWXU 00700
+#define S_IRUSR 00400
+#define S_IWUSR 00200
+#define S_IXUSR 00100
+
+#define S_IRWXG 00070
+#define S_IRGRP 00040
+#define S_IWGRP 00020
+#define S_IXGRP 00010
+
+#define S_IRWXO 00007
+#define S_IROTH 00004
+#define S_IWOTH 00002
+#define S_IXOTH 00001
+
+#endif
+
+/*
+ * Timestamp structure for the timestamps in struct statx.
+ *
+ * tv_sec holds the number of seconds before (negative) or after (positive)
+ * 00:00:00 1st January 1970 UTC.
+ *
+ * tv_nsec holds a number of nanoseconds before (0..-999,999,999 if tv_sec is
+ * negative) or after (0..999,999,999 if tv_sec is positive) the tv_sec time.
+ *
+ * Note that if both tv_sec and tv_nsec are non-zero, then the two values must
+ * either be both positive or both negative.
+ *
+ * __reserved is held in case we need a yet finer resolution.
+ */
+struct statx_timestamp {
+ __s64 tv_sec;
+ __s32 tv_nsec;
+ __s32 __reserved;
+};
+
+/*
+ * Structures for the extended file attribute retrieval system call
+ * (statx()).
+ *
+ * The caller passes a mask of what they're specifically interested in as a
+ * parameter to statx(). What statx() actually got will be indicated in
+ * st_mask upon return.
+ *
+ * For each bit in the mask argument:
+ *
+ * - if the datum is not supported:
+ *
+ * - the bit will be cleared, and
+ *
+ * - the datum will be set to an appropriate fabricated value if one is
+ * available (eg. CIFS can take a default uid and gid), otherwise
+ *
+ * - the field will be cleared;
+ *
+ * - otherwise, if explicitly requested:
+ *
+ * - the datum will be synchronised to the server if AT_STATX_FORCE_SYNC is
+ * set or if the datum is considered out of date, and
+ *
+ * - the field will be filled in and the bit will be set;
+ *
+ * - otherwise, if not requested, but available in approximate form without any
+ * effort, it will be filled in anyway, and the bit will be set upon return
+ * (it might not be up to date, however, and no attempt will be made to
+ * synchronise the internal state first);
+ *
+ * - otherwise the field and the bit will be cleared before returning.
+ *
+ * Items in STATX_BASIC_STATS may be marked unavailable on return, but they
+ * will have values installed for compatibility purposes so that stat() and
+ * co. can be emulated in userspace.
+ */
+struct statx {
+ /* 0x00 */
+ __u32 stx_mask; /* What results were written [uncond] */
+ __u32 stx_blksize; /* Preferred general I/O size [uncond] */
+ __u64 stx_attributes; /* Flags conveying information about the file [uncond] */
+ /* 0x10 */
+ __u32 stx_nlink; /* Number of hard links */
+ __u32 stx_uid; /* User ID of owner */
+ __u32 stx_gid; /* Group ID of owner */
+ __u16 stx_mode; /* File mode */
+ __u16 __spare0[1];
+ /* 0x20 */
+ __u64 stx_ino; /* Inode number */
+ __u64 stx_size; /* File size */
+ __u64 stx_blocks; /* Number of 512-byte blocks allocated */
+ __u64 stx_attributes_mask; /* Mask to show what's supported in stx_attributes */
+ /* 0x40 */
+ struct statx_timestamp stx_atime; /* Last access time */
+ struct statx_timestamp stx_btime; /* File creation time */
+ struct statx_timestamp stx_ctime; /* Last attribute change time */
+ struct statx_timestamp stx_mtime; /* Last data modification time */
+ /* 0x80 */
+ __u32 stx_rdev_major; /* Device ID of special file [if bdev/cdev] */
+ __u32 stx_rdev_minor;
+ __u32 stx_dev_major; /* ID of device containing file [uncond] */
+ __u32 stx_dev_minor;
+ /* 0x90 */
+ __u64 __spare2[14]; /* Spare space for future expansion */
+ /* 0x100 */
+};
+
+/*
+ * Flags to be stx_mask
+ *
+ * Query request/result mask for statx() and struct statx::stx_mask.
+ *
+ * These bits should be set in the mask argument of statx() to request
+ * particular items when calling statx().
+ */
+#define STATX_TYPE 0x00000001U /* Want/got stx_mode & S_IFMT */
+#define STATX_MODE 0x00000002U /* Want/got stx_mode & ~S_IFMT */
+#define STATX_NLINK 0x00000004U /* Want/got stx_nlink */
+#define STATX_UID 0x00000008U /* Want/got stx_uid */
+#define STATX_GID 0x00000010U /* Want/got stx_gid */
+#define STATX_ATIME 0x00000020U /* Want/got stx_atime */
+#define STATX_MTIME 0x00000040U /* Want/got stx_mtime */
+#define STATX_CTIME 0x00000080U /* Want/got stx_ctime */
+#define STATX_INO 0x00000100U /* Want/got stx_ino */
+#define STATX_SIZE 0x00000200U /* Want/got stx_size */
+#define STATX_BLOCKS 0x00000400U /* Want/got stx_blocks */
+#define STATX_BASIC_STATS 0x000007ffU /* The stuff in the normal stat struct */
+#define STATX_BTIME 0x00000800U /* Want/got stx_btime */
+#define STATX_ALL 0x00000fffU /* All currently supported flags */
+#define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */
+
+/*
+ * Attributes to be found in stx_attributes and masked in stx_attributes_mask.
+ *
+ * These give information about the features or the state of a file that might
+ * be of use to ordinary userspace programs such as GUIs or ls rather than
+ * specialised tools.
+ *
+ * Note that the flags marked [I] correspond to generic FS_IOC_FLAGS
+ * semantically. Where possible, the numerical value is picked to correspond
+ * also.
+ */
+#define STATX_ATTR_COMPRESSED 0x00000004 /* [I] File is compressed by the fs */
+#define STATX_ATTR_IMMUTABLE 0x00000010 /* [I] File is marked immutable */
+#define STATX_ATTR_APPEND 0x00000020 /* [I] File is append-only */
+#define STATX_ATTR_NODUMP 0x00000040 /* [I] File is not to be dumped */
+#define STATX_ATTR_ENCRYPTED 0x00000800 /* [I] File requires key to decrypt in fs */
+
+#define STATX_ATTR_AUTOMOUNT 0x00001000 /* Dir: Automount trigger */
+
+
+#endif /* _UAPI_LINUX_STAT_H */
* simple, single region.
*/
boot->e820_entries = 1;
- boot->e820_map[0] = ((struct e820entry) { 0, mem, E820_RAM });
+ boot->e820_table[0] = ((struct e820_entry) { 0, mem, E820_TYPE_RAM });
/*
* The boot header contains a command line pointer: we put the command
* line after the boot header.
return filename__read_str(path, buf, sizep);
}
+int sysfs__read_bool(const char *entry, bool *value)
+{
+ char *buf;
+ size_t size;
+ int ret;
+
+ ret = sysfs__read_str(entry, &buf, &size);
+ if (ret < 0)
+ return ret;
+
+ switch (buf[0]) {
+ case '1':
+ case 'y':
+ case 'Y':
+ *value = true;
+ break;
+ case '0':
+ case 'n':
+ case 'N':
+ *value = false;
+ break;
+ default:
+ ret = -1;
+ }
+
+ free(buf);
+
+ return ret;
+}
int sysctl__read_int(const char *sysctl, int *value)
{
char path[PATH_MAX];
int sysfs__read_int(const char *entry, int *value);
int sysfs__read_ull(const char *entry, unsigned long long *value);
int sysfs__read_str(const char *entry, char **buf, size_t *sizep);
+int sysfs__read_bool(const char *entry, bool *value);
#endif /* __API_FS__ */
#define __SUBCMD_HELP_H
#include <sys/types.h>
+#include <stdio.h>
struct cmdnames {
size_t alloc;
+#include <ctype.h>
#include "symbol/kallsyms.h"
#include <stdio.h>
#include <stdlib.h>
#include "warn.h"
#include <linux/hashtable.h>
-
-#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#include <linux/kernel.h>
#define STATE_FP_SAVED 0x1
#define STATE_FP_SETUP 0x2
#include <stdlib.h>
#include <subcmd/exec-cmd.h>
#include <subcmd/pager.h>
+#include <linux/kernel.h>
#include "builtin.h"
-#define ARRAY_SIZE(x) (sizeof(x)/sizeof(x[0]))
-
struct cmd_struct {
const char *name;
int (*fn)(int, const char **);
.config-detected
util/intel-pt-decoder/inat-tables.c
arch/*/include/generated/
+pmu-events/pmu-events.c
+pmu-events/jevents
libperf-y += arch/
libperf-y += ui/
libperf-y += scripts/
+libperf-y += trace/beauty/
gtk-y += ui/gtk/
--verbose=::
Verbosity level.
+-p::
+--pid=::
+ Trace on existing process id (comma separated list).
+
+-a::
+--all-cpus::
+ Force system-wide collection. Scripts run without a <command>
+ normally use -a by default, while scripts run with a <command>
+ normally don't - this option allows the latter to be run in
+ system-wide mode.
+
+-C::
+--cpu=::
+ Only trace for the list of CPUs provided. Multiple CPUs can
+ be provided as a comma separated list with no space like: 0,1.
+ Ranges of CPUs are specified with -: 0-2.
+ Default is to trace on all online CPUs.
+
SEE ALSO
--------
SYNOPSIS
--------
[verse]
-'perf list' [--no-desc] [--long-desc] [hw|sw|cache|tracepoint|pmu|event_glob]
+'perf list' [--no-desc] [--long-desc] [hw|sw|cache|tracepoint|pmu|sdt|event_glob]
DESCRIPTION
-----------
--long-desc::
Print longer event descriptions.
+--details::
+Print how named events are resolved internally into perf events, and also
+any extra expressions computed by perf stat.
+
[[EVENT_MODIFIERS]]
EVENT MODIFIERS
. 'pmu' to print the kernel supplied PMU events.
+. 'sdt' to list all Statically Defined Tracepoint events.
+
. If none of the above is matched, it will apply the supplied glob to all
events, printing the ones that match.
displayed with the weight and local_weight sort keys. This currently works for TSX
abort events and some memory events in precise mode on modern Intel CPUs.
+--namespaces::
+Record events of type PERF_RECORD_NAMESPACES.
+
--transaction::
Record transaction flags for transaction related events.
--sort=::
Sort histogram entries by given key(s) - multiple keys can be specified
in CSV format. Following sort keys are available:
- pid, comm, dso, symbol, parent, cpu, socket, srcline, weight, local_weight.
+ pid, comm, dso, symbol, parent, cpu, socket, srcline, weight,
+ local_weight, cgroup_id.
Each key has following meaning:
- pid: command and tid of the task
- dso: name of library or module executed at the time of sample
- symbol: name of function executed at the time of sample
+ - symbol_size: size of function executed at the time of sample
- parent: name of function matched to the parent regex filter. Unmatched
entries are displayed as "[other]".
- cpu: cpu number the task ran at the time of sample
- weight: Event specific weight, e.g. memory latency or transaction
abort cost. This is the global weight.
- local_weight: Local weight version of the weight above.
+ - cgroup_id: ID derived from cgroup namespace device and inode numbers.
- transaction: Transaction abort flags.
- overhead: Overhead percentage of sample
- overhead_sys: Overhead percentage of sample running in system mode
By default, every sort keys not specified in -F will be appended
automatically.
+ If the keys starts with a prefix '+', then it will append the specified
+ field(s) to the default field order. For example: perf report -F +period,sample.
+
-p::
--parent=<regex>::
A regex filter to identify parent. The parent is a caller of this
sort_key can be:
- function: compare on functions (default)
- address: compare on individual code addresses
+ - srcline: compare on source filename and line number
branch can be:
- branch: include last branch information in callgraph when available.
--hierarchy::
Enable hierarchical output.
+--inline::
+ If a callgraph address belongs to an inlined function, the inline stack
+ will be printed. Each entry is function name or file/line.
+
include::callchain-overhead-calculation.txt[]
SEE ALSO
--migrations::
Show migration events.
+-n::
+--next::
+ Show next task.
+
-I::
--idle-hist::
Show idle-related events only.
--fields::
Comma separated list of fields to print. Options are:
comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
- srcline, period, iregs, brstack, brstacksym, flags, bpf-output,
+ srcline, period, iregs, brstack, brstacksym, flags, bpf-output, brstackinsn,
callindent, insn, insnlen. Field list can be prepended with the type, trace, sw or hw,
to indicate to which event type the field list applies.
e.g., -F sw:comm,tid,time,ip,sym and -F trace:time,cpu,trace
i.e., -F "" is not allowed.
The brstack output includes branch related information with raw addresses using the
- /v/v/v/v/ syntax in the following order:
+ /v/v/v/v/cycles syntax in the following order:
FROM: branch source instruction
TO : branch target instruction
M/P/-: M=branch target mispredicted or branch direction was mispredicted, P=target predicted or direction predicted, -=not supported
X/- : X=branch inside a transactional region, -=not in transaction region or not supported
A/- : A=TSX abort entry, -=not aborted region or not supported
+ cycles
The brstacksym is identical to brstack, except that the FROM and TO addresses are printed in a symbolic form if possible.
+ When brstackinsn is specified the full assembler sequences of branch sequences for each sample
+ is printed. This is the full execution path leading to the sample. This is only supported when the
+ sample was recorded with perf record -b or -j any.
+
-k::
--vmlinux=<file>::
vmlinux pathname
--show-mmap-events
Display mmap related events (e.g. MMAP, MMAP2).
+--show-namespace-events
+ Display namespace events i.e. events of type PERF_RECORD_NAMESPACES.
+
--show-switch-events
Display context switch events i.e. events of type PERF_RECORD_SWITCH or
PERF_RECORD_SWITCH_CPU_WIDE.
stop time is not given (i.e, time string is 'x.y,') then analysis goes
to end of file.
+--max-blocks::
+ Set the maximum number of program blocks to print with brstackasm for
+ each sample.
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-script-perl[1],
-A::
--no-aggr::
-Do not aggregate counts across all monitored CPUs in system-wide mode (-a).
-This option is only valid in system-wide mode.
+Do not aggregate counts across all monitored CPUs.
-n::
--null::
CPUs the workload runs on. If needed the CPUs can be forced using
taskset.
+--no-merge::
+Do not merge results from same PMUs.
+
EXAMPLES
--------
major or all pagefaults. Default value is maj.
--syscalls::
- Trace system calls. This options is enabled by default.
+ Trace system calls. This options is enabled by default, disable with
+ --no-syscalls.
--call-graph [mode,type,min[,limit],order[,key][,branch]]::
Setup and enable call-graph (stack chain/backtrace) recording.
When perf is writing to a pipe it uses a special version of the file
format that does not rely on seeking to adjust data offsets. This
-format is not described here. The pipe version can be converted to
-normal perf.data with perf inject.
+format is described in "Pipe-mode data" section. The pipe data version can be
+augmented with additional events using perf inject.
The file starts with a perf_header:
ids points to a array of uint64_t defining the ids for event attr attr.
+Pipe-mode data
+
+Pipe-mode avoid seeks in the file by removing the perf_file_section and flags
+from the struct perf_header. The trimmed header is:
+
+struct perf_pipe_file_header {
+ u64 magic;
+ u64 size;
+};
+
+The information about attrs, data, and event_types is instead in the
+synthesized events PERF_RECORD_ATTR, PERF_RECORD_HEADER_TRACING_DATA and
+PERF_RECORD_HEADER_EVENT_TYPE that are generated by perf record in pipe-mode.
+
+
References:
include/uapi/linux/perf_event.h
tools/arch/sparc/include/asm/barrier_64.h
tools/arch/tile/include/asm/barrier.h
tools/arch/x86/include/asm/barrier.h
+tools/arch/x86/include/asm/cmpxchg.h
tools/arch/x86/include/asm/cpufeatures.h
tools/arch/x86/include/asm/disabled-features.h
tools/arch/x86/include/asm/required-features.h
tools/include/linux/compiler.h
tools/include/linux/compiler-gcc.h
tools/include/linux/coresight-pmu.h
+tools/include/linux/bug.h
tools/include/linux/filter.h
tools/include/linux/hash.h
tools/include/linux/kernel.h
tools/include/uapi/asm-generic/mman.h
tools/include/uapi/linux/bpf.h
tools/include/uapi/linux/bpf_common.h
+tools/include/uapi/linux/fcntl.h
tools/include/uapi/linux/hw_breakpoint.h
tools/include/uapi/linux/mman.h
tools/include/uapi/linux/perf_event.h
+tools/include/uapi/linux/stat.h
tools/include/linux/poison.h
tools/include/linux/rbtree.h
tools/include/linux/rbtree_augmented.h
+tools/include/linux/refcount.h
tools/include/linux/string.h
tools/include/linux/stringify.h
tools/include/linux/types.h
override PYTHON_CONFIG := \
$(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON2_CONFIG))
-PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
+grep-libs = $(filter -l%,$(1))
+strip-libs = $(filter-out -l%,$(1))
-PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
-PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
+PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
-ifeq ($(CC), clang)
- PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
+ifdef PYTHON_CONFIG
+ PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
+ PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
+ PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
+ PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
+ ifeq ($(CC), clang)
+ PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
+ endif
+ FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
endif
FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS)
NO_LIBUNWIND := 1
NO_LIBDW_DWARF_UNWIND := 1
NO_LIBBPF := 1
+ NO_JVMTI := 1
else
ifeq ($(feature-libelf), 0)
ifeq ($(feature-glibc), 1)
LIBC_SUPPORT := 1
endif
ifeq ($(LIBC_SUPPORT),1)
- msg := $(warning No libelf found, disables 'probe' tool and BPF support in 'perf record', please install libelf-dev, libelf-devel or elfutils-libelf-devel);
+ msg := $(warning No libelf found. Disables 'probe' tool, jvmti and BPF support in 'perf record'. Please install libelf-dev, libelf-devel or elfutils-libelf-devel);
NO_LIBELF := 1
NO_DWARF := 1
NO_LIBUNWIND := 1
NO_LIBDW_DWARF_UNWIND := 1
NO_LIBBPF := 1
+ NO_JVMTI := 1
else
ifneq ($(filter s% -static%,$(LDFLAGS),),)
msg := $(error No static glibc found, please install glibc-static);
NO_LIBDW_DWARF_UNWIND := 1
endif
+ifeq ($(feature-sched_getcpu), 1)
+ CFLAGS += -DHAVE_SCHED_GETCPU_SUPPORT
+endif
+
ifndef NO_LIBELF
CFLAGS += -DHAVE_LIBELF_SUPPORT
EXTLIBS += -lelf
endif
endif
-grep-libs = $(filter -l%,$(1))
-strip-libs = $(filter-out -l%,$(1))
ifdef NO_LIBPERL
CFLAGS += -DNO_LIBPERL
$(call disable-python,No 'python-config' tool was found: disables Python support - please install python-devel/python-dev)
else
- PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
-
- PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
- PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
- PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
- PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
- ifeq ($(CC), clang)
- PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
- endif
- FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
-
ifneq ($(feature-libpython), 1)
$(call disable-python,No 'Python.h' (for Python 2.x support) was found: disables Python support - please install python-devel/python-dev)
else
-
ifneq ($(feature-libpython-version), 1)
$(warning Python 3 is not yet supported; please set)
$(warning PYTHON and/or PYTHON_CONFIG appropriately.)
#include "../../util/cs-etm.h"
#include <stdlib.h>
+#include <sys/stat.h>
#define ENABLE_SINK_MAX 128
#define CS_BUS_DEVICE_PATH "/bus/coresight/devices/"
*/
#include <stddef.h>
+#include <linux/stringify.h>
#include <dwarf-regs.h>
struct pt_regs_dwarfnum {
unsigned int dwarfnum;
};
-#define STR(s) #s
#define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num}
#define GPR_DWARFNUM_NAME(num) \
- {.name = STR(%r##num), .dwarfnum = num}
+ {.name = __stringify(%r##num), .dwarfnum = num}
#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
/*
#include <elfutils/libdwfl.h>
#include "../../util/unwind-libdw.h"
#include "../../util/perf_regs.h"
+#include "../../util/event.h"
bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
{
* published by the Free Software Foundation.
*/
+#include <errno.h>
#include <stddef.h>
+#include <string.h>
#include <dwarf-regs.h>
#include <linux/ptrace.h> /* for struct user_pt_regs */
+#include <linux/stringify.h>
#include "util.h"
struct pt_regs_dwarfnum {
#define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num}
#define GPR_DWARFNUM_NAME(num) \
- {.name = STR(%x##num), .dwarfnum = num}
+ {.name = __stringify(%x##num), .dwarfnum = num}
#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
#define DWARFNUM2OFFSET(index) \
(index * sizeof((struct user_pt_regs *)0)->regs[0])
+#include <errno.h>
#ifndef REMOTE_UNWIND_LIBUNWIND
-#include <errno.h>
#include <libunwind.h>
#include "perf_regs.h"
#include "../../util/unwind.h"
#include "../util/util.h"
#include "../util/debug.h"
+#include "sane_ctype.h"
+
const char *const arm_triplets[] = {
"arm-eabi-",
"arm-linux-androideabi-",
#include <dwarf-regs.h>
#include <linux/ptrace.h>
#include <linux/kernel.h>
+#include <linux/stringify.h>
#include "util.h"
struct pt_regs_dwarfnum {
};
#define REG_DWARFNUM_NAME(r, num) \
- {.name = STR(%)STR(r), .dwarfnum = num, \
+ {.name = __stringify(%)__stringify(r), .dwarfnum = num, \
.ptregs_offset = offsetof(struct pt_regs, r)}
#define GPR_DWARFNUM_NAME(num) \
- {.name = STR(%gpr##num), .dwarfnum = num, \
+ {.name = __stringify(%gpr##num), .dwarfnum = num, \
.ptregs_offset = offsetof(struct pt_regs, gpr[num])}
#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0, .ptregs_offset = 0}
+#include <errno.h>
#include "util/kvm-stat.h"
#include "util/parse-events.h"
#include "util/debug.h"
+#include <errno.h>
+#include <string.h>
+#include <regex.h>
+
#include "../../perf.h"
+#include "../../util/util.h"
#include "../../util/perf_regs.h"
+#include "../../util/debug.h"
const struct sample_reg sample_reg_masks[] = {
SMPL_REG(r0, PERF_REG_POWERPC_R0),
SMPL_REG(dsisr, PERF_REG_POWERPC_DSISR),
SMPL_REG_END
};
+
+/* REG or %rREG */
+#define SDT_OP_REGEX1 "^(%r)?([1-2]?[0-9]|3[0-1])$"
+
+/* -NUM(REG) or NUM(REG) or -NUM(%rREG) or NUM(%rREG) */
+#define SDT_OP_REGEX2 "^(\\-)?([0-9]+)\\((%r)?([1-2]?[0-9]|3[0-1])\\)$"
+
+static regex_t sdt_op_regex1, sdt_op_regex2;
+
+static int sdt_init_op_regex(void)
+{
+ static int initialized;
+ int ret = 0;
+
+ if (initialized)
+ return 0;
+
+ ret = regcomp(&sdt_op_regex1, SDT_OP_REGEX1, REG_EXTENDED);
+ if (ret)
+ goto error;
+
+ ret = regcomp(&sdt_op_regex2, SDT_OP_REGEX2, REG_EXTENDED);
+ if (ret)
+ goto free_regex1;
+
+ initialized = 1;
+ return 0;
+
+free_regex1:
+ regfree(&sdt_op_regex1);
+error:
+ pr_debug4("Regex compilation error.\n");
+ return ret;
+}
+
+/*
+ * Parse OP and convert it into uprobe format, which is, +/-NUM(%gprREG).
+ * Possible variants of OP are:
+ * Format Example
+ * -------------------------
+ * NUM(REG) 48(18)
+ * -NUM(REG) -48(18)
+ * NUM(%rREG) 48(%r18)
+ * -NUM(%rREG) -48(%r18)
+ * REG 18
+ * %rREG %r18
+ * iNUM i0
+ * i-NUM i-1
+ *
+ * SDT marker arguments on Powerpc uses %rREG form with -mregnames flag
+ * and REG form with -mno-regnames. Here REG is general purpose register,
+ * which is in 0 to 31 range.
+ */
+int arch_sdt_arg_parse_op(char *old_op, char **new_op)
+{
+ int ret, new_len;
+ regmatch_t rm[5];
+ char prefix;
+
+ /* Constant argument. Uprobe does not support it */
+ if (old_op[0] == 'i') {
+ pr_debug4("Skipping unsupported SDT argument: %s\n", old_op);
+ return SDT_ARG_SKIP;
+ }
+
+ ret = sdt_init_op_regex();
+ if (ret < 0)
+ return ret;
+
+ if (!regexec(&sdt_op_regex1, old_op, 3, rm, 0)) {
+ /* REG or %rREG --> %gprREG */
+
+ new_len = 5; /* % g p r NULL */
+ new_len += (int)(rm[2].rm_eo - rm[2].rm_so);
+
+ *new_op = zalloc(new_len);
+ if (!*new_op)
+ return -ENOMEM;
+
+ scnprintf(*new_op, new_len, "%%gpr%.*s",
+ (int)(rm[2].rm_eo - rm[2].rm_so), old_op + rm[2].rm_so);
+ } else if (!regexec(&sdt_op_regex2, old_op, 5, rm, 0)) {
+ /*
+ * -NUM(REG) or NUM(REG) or -NUM(%rREG) or NUM(%rREG) -->
+ * +/-NUM(%gprREG)
+ */
+ prefix = (rm[1].rm_so == -1) ? '+' : '-';
+
+ new_len = 8; /* +/- ( % g p r ) NULL */
+ new_len += (int)(rm[2].rm_eo - rm[2].rm_so);
+ new_len += (int)(rm[4].rm_eo - rm[4].rm_so);
+
+ *new_op = zalloc(new_len);
+ if (!*new_op)
+ return -ENOMEM;
+
+ scnprintf(*new_op, new_len, "%c%.*s(%%gpr%.*s)", prefix,
+ (int)(rm[2].rm_eo - rm[2].rm_so), old_op + rm[2].rm_so,
+ (int)(rm[4].rm_eo - rm[4].rm_so), old_op + rm[4].rm_so);
+ } else {
+ pr_debug4("Skipping unsupported SDT argument: %s\n", old_op);
+ return SDT_ARG_SKIP;
+ }
+
+ return SDT_ARG_VALID;
+}
#include "symbol.h"
#include "map.h"
#include "probe-event.h"
+#include "probe-file.h"
#ifdef HAVE_LIBELF_SUPPORT
bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
* However, if the user specifies an offset, we fall back to using the
* GEP since all userspace applications (objdump/readelf) show function
* disassembly with offsets from the GEP.
- *
- * In addition, we shouldn't specify an offset for kretprobes.
*/
- if (pev->point.offset || (!pev->uprobes && pev->point.retprobe) ||
- !map || !sym)
+ if (pev->point.offset || !map || !sym)
return;
+ /* For kretprobes, add an offset only if the kernel supports it */
+ if (!pev->uprobes && pev->point.retprobe) {
+#ifdef HAVE_LIBELF_SUPPORT
+ if (!kretprobe_offset_is_supported())
+#endif
+ return;
+ }
+
lep_offset = PPC64_LOCAL_ENTRY_OFFSET(sym->arch_sym);
if (map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS)
--- /dev/null
+static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *name)
+{
+ struct ins_ops *ops = NULL;
+
+ /* catch all kind of jumps */
+ if (strchr(name, 'j') ||
+ !strncmp(name, "bct", 3) ||
+ !strncmp(name, "br", 2))
+ ops = &jump_ops;
+ /* override call/returns */
+ if (!strcmp(name, "bras") ||
+ !strcmp(name, "brasl") ||
+ !strcmp(name, "basr"))
+ ops = &call_ops;
+ if (!strcmp(name, "br"))
+ ops = &ret_ops;
+
+ arch__associate_ins_ops(arch, name, ops);
+ return ops;
+}
+
+static int s390__annotate_init(struct arch *arch)
+{
+ if (!arch->initialized) {
+ arch->initialized = true;
+ arch->associate_instruction_ops = s390__associate_ins_ops;
+ }
+
+ return 0;
+}
* as published by the Free Software Foundation.
*/
+#include <errno.h>
#include "../../util/kvm-stat.h"
#include <asm/sie.h>
329 common pkey_mprotect sys_pkey_mprotect
330 common pkey_alloc sys_pkey_alloc
331 common pkey_free sys_pkey_free
+332 common statx sys_statx
#
# x32-specific system call numbers start at 512 to avoid cache impact
#include "evsel.h"
#include "arch-tests.h"
+#include <signal.h>
#include <sys/mman.h>
+#include <sys/wait.h>
+#include <errno.h>
#include <string.h>
static pid_t spawn(void)
+#include <errno.h>
+#include <inttypes.h>
#include <stdio.h>
#include <unistd.h>
#include <linux/types.h>
*
*/
+#include <errno.h>
#include <stdbool.h>
#include "../../util/header.h"
*
*/
+#include <errno.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/bitops.h>
*
*/
+#include <errno.h>
#include <stdbool.h>
#include <linux/kernel.h>
#include <linux/types.h>
+#include <errno.h>
#include "../../util/kvm-stat.h"
#include <asm/svm.h>
#include <asm/vmx.h>
+#include <errno.h>
+#include <string.h>
+#include <regex.h>
+
#include "../../perf.h"
+#include "../../util/util.h"
#include "../../util/perf_regs.h"
+#include "../../util/debug.h"
const struct sample_reg sample_reg_masks[] = {
SMPL_REG(AX, PERF_REG_X86_AX),
#endif
SMPL_REG_END
};
+
+struct sdt_name_reg {
+ const char *sdt_name;
+ const char *uprobe_name;
+};
+#define SDT_NAME_REG(n, m) {.sdt_name = "%" #n, .uprobe_name = "%" #m}
+#define SDT_NAME_REG_END {.sdt_name = NULL, .uprobe_name = NULL}
+
+static const struct sdt_name_reg sdt_reg_tbl[] = {
+ SDT_NAME_REG(eax, ax),
+ SDT_NAME_REG(rax, ax),
+ SDT_NAME_REG(al, ax),
+ SDT_NAME_REG(ah, ax),
+ SDT_NAME_REG(ebx, bx),
+ SDT_NAME_REG(rbx, bx),
+ SDT_NAME_REG(bl, bx),
+ SDT_NAME_REG(bh, bx),
+ SDT_NAME_REG(ecx, cx),
+ SDT_NAME_REG(rcx, cx),
+ SDT_NAME_REG(cl, cx),
+ SDT_NAME_REG(ch, cx),
+ SDT_NAME_REG(edx, dx),
+ SDT_NAME_REG(rdx, dx),
+ SDT_NAME_REG(dl, dx),
+ SDT_NAME_REG(dh, dx),
+ SDT_NAME_REG(esi, si),
+ SDT_NAME_REG(rsi, si),
+ SDT_NAME_REG(sil, si),
+ SDT_NAME_REG(edi, di),
+ SDT_NAME_REG(rdi, di),
+ SDT_NAME_REG(dil, di),
+ SDT_NAME_REG(ebp, bp),
+ SDT_NAME_REG(rbp, bp),
+ SDT_NAME_REG(bpl, bp),
+ SDT_NAME_REG(rsp, sp),
+ SDT_NAME_REG(esp, sp),
+ SDT_NAME_REG(spl, sp),
+
+ /* rNN registers */
+ SDT_NAME_REG(r8b, r8),
+ SDT_NAME_REG(r8w, r8),
+ SDT_NAME_REG(r8d, r8),
+ SDT_NAME_REG(r9b, r9),
+ SDT_NAME_REG(r9w, r9),
+ SDT_NAME_REG(r9d, r9),
+ SDT_NAME_REG(r10b, r10),
+ SDT_NAME_REG(r10w, r10),
+ SDT_NAME_REG(r10d, r10),
+ SDT_NAME_REG(r11b, r11),
+ SDT_NAME_REG(r11w, r11),
+ SDT_NAME_REG(r11d, r11),
+ SDT_NAME_REG(r12b, r12),
+ SDT_NAME_REG(r12w, r12),
+ SDT_NAME_REG(r12d, r12),
+ SDT_NAME_REG(r13b, r13),
+ SDT_NAME_REG(r13w, r13),
+ SDT_NAME_REG(r13d, r13),
+ SDT_NAME_REG(r14b, r14),
+ SDT_NAME_REG(r14w, r14),
+ SDT_NAME_REG(r14d, r14),
+ SDT_NAME_REG(r15b, r15),
+ SDT_NAME_REG(r15w, r15),
+ SDT_NAME_REG(r15d, r15),
+ SDT_NAME_REG_END,
+};
+
+/*
+ * Perf only supports OP which is in +/-NUM(REG) form.
+ * Here plus-minus sign, NUM and parenthesis are optional,
+ * only REG is mandatory.
+ *
+ * SDT events also supports indirect addressing mode with a
+ * symbol as offset, scaled mode and constants in OP. But
+ * perf does not support them yet. Below are few examples.
+ *
+ * OP with scaled mode:
+ * (%rax,%rsi,8)
+ * 10(%ras,%rsi,8)
+ *
+ * OP with indirect addressing mode:
+ * check_action(%rip)
+ * mp_+52(%rip)
+ * 44+mp_(%rip)
+ *
+ * OP with constant values:
+ * $0
+ * $123
+ * $-1
+ */
+#define SDT_OP_REGEX "^([+\\-]?)([0-9]*)(\\(?)(%[a-z][a-z0-9]+)(\\)?)$"
+
+static regex_t sdt_op_regex;
+
+static int sdt_init_op_regex(void)
+{
+ static int initialized;
+ int ret = 0;
+
+ if (initialized)
+ return 0;
+
+ ret = regcomp(&sdt_op_regex, SDT_OP_REGEX, REG_EXTENDED);
+ if (ret < 0) {
+ pr_debug4("Regex compilation error.\n");
+ return ret;
+ }
+
+ initialized = 1;
+ return 0;
+}
+
+/*
+ * Max x86 register name length is 5(ex: %r15d). So, 6th char
+ * should always contain NULL. This helps to find register name
+ * length using strlen, insted of maintaing one more variable.
+ */
+#define SDT_REG_NAME_SIZE 6
+
+/*
+ * The uprobe parser does not support all gas register names;
+ * so, we have to replace them (ex. for x86_64: %rax -> %ax).
+ * Note: If register does not require renaming, just copy
+ * paste as it is, but don't leave it empty.
+ */
+static void sdt_rename_register(char *sdt_reg, int sdt_len, char *uprobe_reg)
+{
+ int i = 0;
+
+ for (i = 0; sdt_reg_tbl[i].sdt_name != NULL; i++) {
+ if (!strncmp(sdt_reg_tbl[i].sdt_name, sdt_reg, sdt_len)) {
+ strcpy(uprobe_reg, sdt_reg_tbl[i].uprobe_name);
+ return;
+ }
+ }
+
+ strncpy(uprobe_reg, sdt_reg, sdt_len);
+}
+
+int arch_sdt_arg_parse_op(char *old_op, char **new_op)
+{
+ char new_reg[SDT_REG_NAME_SIZE] = {0};
+ int new_len = 0, ret;
+ /*
+ * rm[0]: +/-NUM(REG)
+ * rm[1]: +/-
+ * rm[2]: NUM
+ * rm[3]: (
+ * rm[4]: REG
+ * rm[5]: )
+ */
+ regmatch_t rm[6];
+ /*
+ * Max prefix length is 2 as it may contains sign(+/-)
+ * and displacement 0 (Both sign and displacement 0 are
+ * optional so it may be empty). Use one more character
+ * to hold last NULL so that strlen can be used to find
+ * prefix length, instead of maintaing one more variable.
+ */
+ char prefix[3] = {0};
+
+ ret = sdt_init_op_regex();
+ if (ret < 0)
+ return ret;
+
+ /*
+ * If unsupported OR does not match with regex OR
+ * register name too long, skip it.
+ */
+ if (strchr(old_op, ',') || strchr(old_op, '$') ||
+ regexec(&sdt_op_regex, old_op, 6, rm, 0) ||
+ rm[4].rm_eo - rm[4].rm_so > SDT_REG_NAME_SIZE) {
+ pr_debug4("Skipping unsupported SDT argument: %s\n", old_op);
+ return SDT_ARG_SKIP;
+ }
+
+ /*
+ * Prepare prefix.
+ * If SDT OP has parenthesis but does not provide
+ * displacement, add 0 for displacement.
+ * SDT Uprobe Prefix
+ * -----------------------------
+ * +24(%rdi) +24(%di) +
+ * 24(%rdi) +24(%di) +
+ * %rdi %di
+ * (%rdi) +0(%di) +0
+ * -80(%rbx) -80(%bx) -
+ */
+ if (rm[3].rm_so != rm[3].rm_eo) {
+ if (rm[1].rm_so != rm[1].rm_eo)
+ prefix[0] = *(old_op + rm[1].rm_so);
+ else if (rm[2].rm_so != rm[2].rm_eo)
+ prefix[0] = '+';
+ else
+ strncpy(prefix, "+0", 2);
+ }
+
+ /* Rename register */
+ sdt_rename_register(old_op + rm[4].rm_so, rm[4].rm_eo - rm[4].rm_so,
+ new_reg);
+
+ /* Prepare final OP which should be valid for uprobe_events */
+ new_len = strlen(prefix) +
+ (rm[2].rm_eo - rm[2].rm_so) +
+ (rm[3].rm_eo - rm[3].rm_so) +
+ strlen(new_reg) +
+ (rm[5].rm_eo - rm[5].rm_so) +
+ 1; /* NULL */
+
+ *new_op = zalloc(new_len);
+ if (!*new_op)
+ return -ENOMEM;
+
+ scnprintf(*new_op, new_len, "%.*s%.*s%.*s%.*s%.*s",
+ strlen(prefix), prefix,
+ (int)(rm[2].rm_eo - rm[2].rm_so), old_op + rm[2].rm_so,
+ (int)(rm[3].rm_eo - rm[3].rm_so), old_op + rm[3].rm_so,
+ strlen(new_reg), new_reg,
+ (int)(rm[5].rm_eo - rm[5].rm_so), old_op + rm[5].rm_so);
+
+ return SDT_ARG_VALID;
+}
#include <elfutils/libdwfl.h>
#include "../../util/unwind-libdw.h"
#include "../../util/perf_regs.h"
+#include "../../util/event.h"
bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
{
# endif
#endif
-int bench_numa(int argc, const char **argv, const char *prefix);
-int bench_sched_messaging(int argc, const char **argv, const char *prefix);
-int bench_sched_pipe(int argc, const char **argv, const char *prefix);
-int bench_mem_memcpy(int argc, const char **argv, const char *prefix);
-int bench_mem_memset(int argc, const char **argv, const char *prefix);
-int bench_futex_hash(int argc, const char **argv, const char *prefix);
-int bench_futex_wake(int argc, const char **argv, const char *prefix);
-int bench_futex_wake_parallel(int argc, const char **argv, const char *prefix);
-int bench_futex_requeue(int argc, const char **argv, const char *prefix);
+int bench_numa(int argc, const char **argv);
+int bench_sched_messaging(int argc, const char **argv);
+int bench_sched_pipe(int argc, const char **argv);
+int bench_mem_memcpy(int argc, const char **argv);
+int bench_mem_memset(int argc, const char **argv);
+int bench_futex_hash(int argc, const char **argv);
+int bench_futex_wake(int argc, const char **argv);
+int bench_futex_wake_parallel(int argc, const char **argv);
+int bench_futex_requeue(int argc, const char **argv);
/* pi futexes */
-int bench_futex_lock_pi(int argc, const char **argv, const char *prefix);
+int bench_futex_lock_pi(int argc, const char **argv);
#define BENCH_FORMAT_DEFAULT_STR "default"
#define BENCH_FORMAT_DEFAULT 0
*/
/* For the CLR_() macros */
+#include <string.h>
#include <pthread.h>
#include <errno.h>
(int) runtime.tv_sec);
}
-int bench_futex_hash(int argc, const char **argv,
- const char *prefix __maybe_unused)
+int bench_futex_hash(int argc, const char **argv)
{
int ret = 0;
cpu_set_t cpu;
*/
/* For the CLR_() macros */
+#include <string.h>
#include <pthread.h>
#include <signal.h>
}
}
-int bench_futex_lock_pi(int argc, const char **argv,
- const char *prefix __maybe_unused)
+int bench_futex_lock_pi(int argc, const char **argv)
{
int ret = 0;
unsigned int i;
*/
/* For the CLR_() macros */
+#include <string.h>
#include <pthread.h>
#include <signal.h>
done = true;
}
-int bench_futex_requeue(int argc, const char **argv,
- const char *prefix __maybe_unused)
+int bench_futex_requeue(int argc, const char **argv)
{
int ret = 0;
unsigned int i, j;
*/
/* For the CLR_() macros */
+#include <string.h>
#include <pthread.h>
#include <signal.h>
done = true;
}
-int bench_futex_wake_parallel(int argc, const char **argv,
- const char *prefix __maybe_unused)
+int bench_futex_wake_parallel(int argc, const char **argv)
{
int ret = 0;
unsigned int i, j;
*/
/* For the CLR_() macros */
+#include <string.h>
#include <pthread.h>
#include <signal.h>
done = true;
}
-int bench_futex_wake(int argc, const char **argv,
- const char *prefix __maybe_unused)
+int bench_futex_wake(int argc, const char **argv)
{
int ret = 0;
unsigned int i, j;
#ifndef HAVE_PTHREAD_ATTR_SETAFFINITY_NP
#include <pthread.h>
-static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr,
- size_t cpusetsize,
- cpu_set_t *cpuset)
+#include <linux/compiler.h>
+static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr __maybe_unused,
+ size_t cpusetsize __maybe_unused,
+ cpu_set_t *cpuset __maybe_unused)
{
- attr = attr;
- cpusetsize = cpusetsize;
- cpuset = cpuset;
return 0;
}
#endif
#include <subcmd/parse-options.h>
#include "../util/header.h"
#include "../util/cloexec.h"
+#include "../util/string2.h"
#include "bench.h"
#include "mem-memcpy-arch.h"
#include "mem-memset-arch.h"
NULL
};
-int bench_mem_memcpy(int argc, const char **argv, const char *prefix __maybe_unused)
+int bench_mem_memcpy(int argc, const char **argv)
{
struct bench_mem_info info = {
.functions = memcpy_functions,
{ .name = NULL, }
};
-int bench_mem_memset(int argc, const char **argv, const char *prefix __maybe_unused)
+int bench_mem_memset(int argc, const char **argv)
{
struct bench_mem_info info = {
.functions = memset_functions,
* numa: Simulate NUMA-sensitive workload and measure their NUMA performance
*/
+#include <inttypes.h>
/* For the CLR_() macros */
#include <pthread.h>
#include <sys/wait.h>
#include <sys/prctl.h>
#include <sys/types.h>
+#include <linux/kernel.h>
#include <linux/time64.h>
#include <numa.h>
OPT_INCR ('d', "show_details" , &p0.show_details, "Show details"),
OPT_INCR ('a', "all" , &p0.run_all, "Run all tests in the suite"),
OPT_INTEGER('H', "thp" , &p0.thp, "MADV_NOHUGEPAGE < 0 < MADV_HUGEPAGE"),
- OPT_BOOLEAN('c', "show_convergence", &p0.show_convergence, "show convergence details"),
+ OPT_BOOLEAN('c', "show_convergence", &p0.show_convergence, "show convergence details, "
+ "convergence is reached when each process (all its threads) is running on a single NUMA node."),
OPT_BOOLEAN('m', "measure_convergence", &p0.measure_convergence, "measure convergence latency"),
OPT_BOOLEAN('q', "quiet" , &p0.show_quiet, "quiet mode"),
OPT_BOOLEAN('S', "serialize-startup", &p0.serialize_startup,"serialize thread startup"),
return 0;
}
-int bench_numa(int argc, const char **argv, const char *prefix __maybe_unused)
+int bench_numa(int argc, const char **argv)
{
init_params(&p0, "main,", argc, argv);
argc = parse_options(argc, argv, options, bench_numa_usage, 0);
NULL
};
-int bench_sched_messaging(int argc, const char **argv,
- const char *prefix __maybe_unused)
+int bench_sched_messaging(int argc, const char **argv)
{
unsigned int i, total_children;
struct timeval start, stop, diff;
return NULL;
}
-int bench_sched_pipe(int argc, const char **argv, const char *prefix __maybe_unused)
+int bench_sched_pipe(int argc, const char **argv)
{
struct thread_data threads[2], *td;
int pipe_1[2], pipe_2[2];
#include "util/block-range.h"
#include <dlfcn.h>
+#include <errno.h>
#include <linux/bitmap.h>
struct perf_annotate {
NULL
};
-int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_annotate(int argc, const char **argv)
{
struct perf_annotate annotate = {
.tool = {
.comm = perf_event__process_comm,
.exit = perf_event__process_exit,
.fork = perf_event__process_fork,
+ .namespaces = perf_event__process_namespaces,
+ .attr = perf_event__process_attr,
+ .build_id = perf_event__process_build_id,
.ordered_events = true,
.ordering_requires_timestamps = true,
},
#include <string.h>
#include <sys/prctl.h>
-typedef int (*bench_fn_t)(int argc, const char **argv, const char *prefix);
+typedef int (*bench_fn_t)(int argc, const char **argv);
struct bench {
const char *name;
* to something meaningful:
*/
static int run_bench(const char *coll_name, const char *bench_name, bench_fn_t fn,
- int argc, const char **argv, const char *prefix)
+ int argc, const char **argv)
{
int size;
char *name;
prctl(PR_SET_NAME, name);
argv[0] = name;
- ret = fn(argc, argv, prefix);
+ ret = fn(argc, argv);
free(name);
fflush(stdout);
argv[1] = bench->name;
- run_bench(coll->name, bench->name, bench->fn, 1, argv, NULL);
+ run_bench(coll->name, bench->name, bench->fn, 1, argv);
printf("\n");
}
}
run_collection(coll);
}
-int cmd_bench(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_bench(int argc, const char **argv)
{
struct collection *coll;
int ret = 0;
if (bench_format == BENCH_FORMAT_DEFAULT)
printf("# Running '%s/%s' benchmark:\n", coll->name, bench->name);
fflush(stdout);
- ret = run_bench(coll->name, bench->name, bench->fn, argc-1, argv+1, prefix);
+ ret = run_bench(coll->name, bench->name, bench->fn, argc-1, argv+1);
goto end;
}
#include <sys/time.h>
#include <time.h>
#include <dirent.h>
+#include <errno.h>
#include <unistd.h>
#include "builtin.h"
#include "perf.h"
#include "util/build-id.h"
#include "util/session.h"
#include "util/symbol.h"
+#include "util/time-utils.h"
static int build_id_cache__kcore_buildid(const char *proc_dir, char *sbuildid)
{
return err;
}
-int cmd_buildid_cache(int argc, const char **argv,
- const char *prefix __maybe_unused)
+int cmd_buildid_cache(int argc, const char **argv)
{
struct strlist *list;
struct str_node *pos;
#include "util/session.h"
#include "util/symbol.h"
#include "util/data.h"
+#include <errno.h>
static int sysfs__fprintf_build_id(FILE *fp)
{
return 0;
}
-int cmd_buildid_list(int argc, const char **argv,
- const char *prefix __maybe_unused)
+int cmd_buildid_list(int argc, const char **argv)
{
bool show_kernel = false;
bool with_hits = false;
* Dick Fowles <fowles@inreach.com>
* Joe Mario <jmario@redhat.com>
*/
+#include <errno.h>
+#include <inttypes.h>
#include <linux/compiler.h>
#include <linux/kernel.h>
#include <linux/stringify.h>
#include <asm/bug.h>
+#include <sys/param.h>
#include "util.h"
#include "debug.h"
#include "builtin.h"
#include <asm/bug.h>
#include "ui/browsers/hists.h"
#include "evlist.h"
+#include "thread.h"
struct c2c_hists {
struct hists hists;
static void perf_c2c_display(struct perf_session *session)
{
- if (c2c.use_stdio)
+ if (use_browser == 0)
perf_c2c__hists_fprintf(stdout, session);
else
perf_c2c__hists_browse(&c2c.hists.hists);
OPT_BOOLEAN(0, "stdio", &c2c.use_stdio, "Use the stdio interface"),
#endif
OPT_BOOLEAN(0, "stats", &c2c.stats_only,
- "Use the stdio interface"),
+ "Display only statistic tables (implies --stdio)"),
OPT_BOOLEAN(0, "full-symbols", &c2c.symbol_full,
"Display full length of symbols"),
OPT_BOOLEAN(0, "no-source", &no_source,
pr_debug("\n");
}
- ret = cmd_record(i, rec_argv, NULL);
+ ret = cmd_record(i, rec_argv);
free(rec_argv);
return ret;
}
-int cmd_c2c(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_c2c(int argc, const char **argv)
{
argc = parse_options(argc, argv, c2c_options, c2c_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
return 0;
}
-int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_config(int argc, const char **argv)
{
int i, ret = 0;
struct perf_config_set *set;
#include "data-convert.h"
#include "data-convert-bt.h"
-typedef int (*data_cmd_fn_t)(int argc, const char **argv, const char *prefix);
+typedef int (*data_cmd_fn_t)(int argc, const char **argv);
struct data_cmd {
const char *name;
NULL
};
-static int cmd_data_convert(int argc, const char **argv,
- const char *prefix __maybe_unused)
+static int cmd_data_convert(int argc, const char **argv)
{
const char *to_ctf = NULL;
struct perf_data_convert_opts opts = {
{ .name = NULL, },
};
-int cmd_data(int argc, const char **argv, const char *prefix)
+int cmd_data(int argc, const char **argv)
{
struct data_cmd *cmd;
const char *cmdstr;
if (strcmp(cmd->name, cmdstr))
continue;
- return cmd->fn(argc, argv, prefix);
+ return cmd->fn(argc, argv);
}
pr_err("Unknown command: %s\n", cmdstr);
#include "util/data.h"
#include "util/config.h"
+#include <errno.h>
+#include <inttypes.h>
#include <stdlib.h>
#include <math.h>
.exit = perf_event__process_exit,
.fork = perf_event__process_fork,
.lost = perf_event__process_lost,
+ .namespaces = perf_event__process_namespaces,
.ordered_events = true,
.ordering_requires_timestamps = true,
};
return 0;
}
-int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_diff(int argc, const char **argv)
{
int ret = hists__init();
return 0;
}
-int cmd_evlist(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_evlist(int argc, const char **argv)
{
struct perf_attr_details details = { .verbose = false, };
const struct option options[] = {
#include "builtin.h"
#include "perf.h"
+#include <errno.h>
#include <unistd.h>
#include <signal.h>
+#include <fcntl.h>
+#include <poll.h>
#include "debug.h"
#include <subcmd/parse-options.h>
+#include <api/fs/tracing_path.h>
#include "evlist.h"
#include "target.h"
+#include "cpumap.h"
#include "thread_map.h"
#include "util/config.h"
done = true;
}
-static int write_tracing_file(const char *name, const char *val)
+static int __write_tracing_file(const char *name, const char *val, bool append)
{
char *file;
int fd, ret = -1;
ssize_t size = strlen(val);
+ int flags = O_WRONLY;
file = get_tracing_file(name);
if (!file) {
return -1;
}
- fd = open(file, O_WRONLY);
+ if (append)
+ flags |= O_APPEND;
+ else
+ flags |= O_TRUNC;
+
+ fd = open(file, flags);
if (fd < 0) {
pr_debug("cannot open tracing file: %s\n", name);
goto out;
return ret;
}
+static int write_tracing_file(const char *name, const char *val)
+{
+ return __write_tracing_file(name, val, false);
+}
+
+static int append_tracing_file(const char *name, const char *val)
+{
+ return __write_tracing_file(name, val, true);
+}
+
+static int reset_tracing_cpu(void);
+
static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused)
{
if (write_tracing_file("tracing_on", "0") < 0)
if (write_tracing_file("set_ftrace_pid", " ") < 0)
return -1;
+ if (reset_tracing_cpu() < 0)
+ return -1;
+
+ return 0;
+}
+
+static int set_tracing_pid(struct perf_ftrace *ftrace)
+{
+ int i;
+ char buf[16];
+
+ if (target__has_cpu(&ftrace->target))
+ return 0;
+
+ for (i = 0; i < thread_map__nr(ftrace->evlist->threads); i++) {
+ scnprintf(buf, sizeof(buf), "%d",
+ ftrace->evlist->threads->map[i]);
+ if (append_tracing_file("set_ftrace_pid", buf) < 0)
+ return -1;
+ }
return 0;
}
+static int set_tracing_cpumask(struct cpu_map *cpumap)
+{
+ char *cpumask;
+ size_t mask_size;
+ int ret;
+ int last_cpu;
+
+ last_cpu = cpu_map__cpu(cpumap, cpumap->nr - 1);
+ mask_size = (last_cpu + 3) / 4 + 1;
+ mask_size += last_cpu / 32; /* ',' is needed for every 32th cpus */
+
+ cpumask = malloc(mask_size);
+ if (cpumask == NULL) {
+ pr_debug("failed to allocate cpu mask\n");
+ return -1;
+ }
+
+ cpu_map__snprint_mask(cpumap, cpumask, mask_size);
+
+ ret = write_tracing_file("tracing_cpumask", cpumask);
+
+ free(cpumask);
+ return ret;
+}
+
+static int set_tracing_cpu(struct perf_ftrace *ftrace)
+{
+ struct cpu_map *cpumap = ftrace->evlist->cpus;
+
+ if (!target__has_cpu(&ftrace->target))
+ return 0;
+
+ return set_tracing_cpumask(cpumap);
+}
+
+static int reset_tracing_cpu(void)
+{
+ struct cpu_map *cpumap = cpu_map__new(NULL);
+ int ret;
+
+ ret = set_tracing_cpumask(cpumap);
+ cpu_map__put(cpumap);
+ return ret;
+}
+
static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
{
char *trace_file;
int trace_fd;
- char *trace_pid;
char buf[4096];
struct pollfd pollfd = {
.events = POLLIN,
return -1;
}
- if (argc < 1)
- return -1;
-
signal(SIGINT, sig_handler);
signal(SIGUSR1, sig_handler);
signal(SIGCHLD, sig_handler);
+ signal(SIGPIPE, sig_handler);
- reset_tracing_files(ftrace);
+ if (reset_tracing_files(ftrace) < 0)
+ goto out;
/* reset ftrace buffer */
if (write_tracing_file("trace", "0") < 0)
goto out;
- if (perf_evlist__prepare_workload(ftrace->evlist, &ftrace->target,
- argv, false, ftrace__workload_exec_failed_signal) < 0)
+ if (argc && perf_evlist__prepare_workload(ftrace->evlist,
+ &ftrace->target, argv, false,
+ ftrace__workload_exec_failed_signal) < 0) {
goto out;
+ }
- if (write_tracing_file("current_tracer", ftrace->tracer) < 0) {
- pr_err("failed to set current_tracer to %s\n", ftrace->tracer);
- goto out;
+ if (set_tracing_pid(ftrace) < 0) {
+ pr_err("failed to set ftrace pid\n");
+ goto out_reset;
}
- if (asprintf(&trace_pid, "%d", thread_map__pid(ftrace->evlist->threads, 0)) < 0) {
- pr_err("failed to allocate pid string\n");
- goto out;
+ if (set_tracing_cpu(ftrace) < 0) {
+ pr_err("failed to set tracing cpumask\n");
+ goto out_reset;
}
- if (write_tracing_file("set_ftrace_pid", trace_pid) < 0) {
- pr_err("failed to set pid: %s\n", trace_pid);
- goto out_free_pid;
+ if (write_tracing_file("current_tracer", ftrace->tracer) < 0) {
+ pr_err("failed to set current_tracer to %s\n", ftrace->tracer);
+ goto out_reset;
}
trace_file = get_tracing_file("trace_pipe");
if (!trace_file) {
pr_err("failed to open trace_pipe\n");
- goto out_free_pid;
+ goto out_reset;
}
trace_fd = open(trace_file, O_RDONLY);
if (trace_fd < 0) {
pr_err("failed to open trace_pipe\n");
- goto out_free_pid;
+ goto out_reset;
}
fcntl(trace_fd, F_SETFL, O_NONBLOCK);
goto out_close_fd;
}
+ setup_pager();
+
perf_evlist__start_workload(ftrace->evlist);
while (!done) {
out_close_fd:
close(trace_fd);
-out_free_pid:
- free(trace_pid);
-out:
+out_reset:
reset_tracing_files(ftrace);
-
+out:
return done ? 0 : -1;
}
return -1;
}
-int cmd_ftrace(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_ftrace(int argc, const char **argv)
{
int ret;
struct perf_ftrace ftrace = {
.target = { .uid = UINT_MAX, },
};
const char * const ftrace_usage[] = {
- "perf ftrace [<options>] <command>",
+ "perf ftrace [<options>] [<command>]",
"perf ftrace [<options>] -- <command> [<options>]",
NULL
};
const struct option ftrace_options[] = {
OPT_STRING('t', "tracer", &ftrace.tracer, "tracer",
"tracer to use: function_graph(default) or function"),
+ OPT_STRING('p', "pid", &ftrace.target.pid, "pid",
+ "trace on existing process id"),
OPT_INCR('v', "verbose", &verbose,
"be more verbose"),
+ OPT_BOOLEAN('a', "all-cpus", &ftrace.target.system_wide,
+ "system-wide collection from all CPUs"),
+ OPT_STRING('C', "cpu", &ftrace.target.cpu_list, "cpu",
+ "list of cpus to monitor"),
OPT_END()
};
argc = parse_options(argc, argv, ftrace_options, ftrace_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
- if (!argc)
+ if (!argc && target__none(&ftrace.target))
usage_with_options(ftrace_usage, ftrace_options);
+ ret = target__validate(&ftrace.target);
+ if (ret) {
+ char errbuf[512];
+
+ target__strerror(&ftrace.target, ret, errbuf, 512);
+ pr_err("%s\n", errbuf);
+ return -EINVAL;
+ }
+
ftrace.evlist = perf_evlist__new();
if (ftrace.evlist == NULL)
return -ENOMEM;
#include <subcmd/run-command.h>
#include <subcmd/help.h>
#include "util/debug.h"
+#include <linux/kernel.h>
+#include <errno.h>
+#include <stdio.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
static struct man_viewer_list {
struct man_viewer_list *next;
- char name[FLEX_ARRAY];
+ char name[0];
} *man_viewer_list;
static struct man_viewer_info_list {
struct man_viewer_info_list *next;
const char *info;
- char name[FLEX_ARRAY];
+ char name[0];
} *man_viewer_info_list;
enum help_format {
}
}
-static int is_perf_command(const char *s)
-{
- return is_in_cmdlist(&main_cmds, s) ||
- is_in_cmdlist(&other_cmds, s);
-}
-
static const char *cmd_to_page(const char *perf_cmd)
{
char *s;
return 0;
}
-int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_help(int argc, const char **argv)
{
bool show_all = false;
enum help_format help_format = HELP_FORMAT_MAN;
"perf help [--all] [--man|--web|--info] [command]",
NULL
};
- const char *alias;
int rc;
load_command_list("perf-", &main_cmds, &other_cmds);
return 0;
}
- alias = alias_lookup(argv[0]);
- if (alias && !is_perf_command(argv[0])) {
- printf("`perf %s' is aliased to `%s'\n", argv[0], alias);
- return 0;
- }
-
switch (help_format) {
case HELP_FORMAT_MAN:
rc = show_man_page(argv[0]);
#include "util/data.h"
#include "util/auxtrace.h"
#include "util/jit.h"
+#include "util/thread.h"
#include <subcmd/parse-options.h>
#include <linux/list.h>
+#include <errno.h>
+#include <signal.h>
struct perf_inject {
struct perf_tool tool;
return err;
}
+static int perf_event__repipe_namespaces(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine)
+{
+ int err = perf_event__process_namespaces(tool, event, sample, machine);
+
+ perf_event__repipe(tool, event, sample, machine);
+
+ return err;
+}
+
static int perf_event__repipe_exit(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
session->itrace_synth_opts = &inject->itrace_synth_opts;
inject->itrace_synth_opts.inject = true;
inject->tool.comm = perf_event__repipe_comm;
+ inject->tool.namespaces = perf_event__repipe_namespaces;
inject->tool.exit = perf_event__repipe_exit;
inject->tool.id_index = perf_event__repipe_id_index;
inject->tool.auxtrace_info = perf_event__process_auxtrace_info;
lseek(fd, output_data_offset, SEEK_SET);
ret = perf_session__process_events(session);
+ if (ret)
+ return ret;
if (!file_out->is_pipe) {
if (inject->build_ids)
return ret;
}
-int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_inject(int argc, const char **argv)
{
struct perf_inject inject = {
.tool = {
*
* Released under the GPL v2. (and only v2, not any later version)
*/
+#include <inttypes.h>
#include "builtin.h"
#include <linux/compiler.h>
#include <subcmd/parse-options.h>
return 0;
}
-int cmd_kallsyms(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_kallsyms(int argc, const char **argv)
{
const struct option options[] = {
OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"),
#include "util/debug.h"
+#include <linux/kernel.h>
#include <linux/rbtree.h>
#include <linux/string.h>
+#include <errno.h>
+#include <inttypes.h>
#include <locale.h>
#include <regex.h>
+#include "sane_ctype.h"
+
static int kmem_slab;
static int kmem_page;
.comm = perf_event__process_comm,
.mmap = perf_event__process_mmap,
.mmap2 = perf_event__process_mmap2,
+ .namespaces = perf_event__process_namespaces,
.ordered_events = true,
};
for (j = 1; j < (unsigned int)argc; j++, i++)
rec_argv[i] = argv[j];
- return cmd_record(i, rec_argv, NULL);
+ return cmd_record(i, rec_argv);
}
static int kmem_config(const char *var, const char *value, void *cb __maybe_unused)
return 0;
}
-int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_kmem(int argc, const char **argv)
{
const char * const default_slab_sort = "frag,hit,bytes";
const char * const default_page_sort = "bytes,hit";
#include "util/evsel.h"
#include "util/evlist.h"
+#include "util/term.h"
#include "util/util.h"
#include "util/cache.h"
#include "util/symbol.h"
#ifdef HAVE_TIMERFD_SUPPORT
#include <sys/timerfd.h>
#endif
+#include <sys/time.h>
+#include <linux/kernel.h>
#include <linux/time64.h>
+#include <errno.h>
+#include <inttypes.h>
+#include <poll.h>
#include <termios.h>
#include <semaphore.h>
+#include <signal.h>
#include <pthread.h>
#include <math.h>
+static const char *get_filename_for_perf_kvm(void)
+{
+ const char *filename;
+
+ if (perf_host && !perf_guest)
+ filename = strdup("perf.data.host");
+ else if (!perf_host && perf_guest)
+ filename = strdup("perf.data.guest");
+ else
+ filename = strdup("perf.data.kvm");
+
+ return filename;
+}
+
#ifdef HAVE_KVM_STAT_SUPPORT
#include "util/kvm-stat.h"
struct perf_tool eops = {
.sample = process_sample_event,
.comm = perf_event__process_comm,
+ .namespaces = perf_event__process_namespaces,
.ordered_events = true,
};
struct perf_data_file file = {
set_option_flag(record_options, 0, "transaction", PARSE_OPT_DISABLED);
record_usage = kvm_stat_record_usage;
- return cmd_record(i, rec_argv, NULL);
+ return cmd_record(i, rec_argv);
}
static int
kvm->tool.exit = perf_event__process_exit;
kvm->tool.fork = perf_event__process_fork;
kvm->tool.lost = process_lost_event;
+ kvm->tool.namespaces = perf_event__process_namespaces;
kvm->tool.ordered_events = true;
perf_tool__fill_defaults(&kvm->tool);
#endif
perf_stat:
- return cmd_stat(argc, argv, NULL);
+ return cmd_stat(argc, argv);
}
#endif /* HAVE_KVM_STAT_SUPPORT */
BUG_ON(i != rec_argc);
- return cmd_record(i, rec_argv, NULL);
+ return cmd_record(i, rec_argv);
}
static int __cmd_report(const char *file_name, int argc, const char **argv)
BUG_ON(i != rec_argc);
- return cmd_report(i, rec_argv, NULL);
+ return cmd_report(i, rec_argv);
}
static int
BUG_ON(i != rec_argc);
- return cmd_buildid_list(i, rec_argv, NULL);
+ return cmd_buildid_list(i, rec_argv);
}
-int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_kvm(int argc, const char **argv)
{
const char *file_name = NULL;
const struct option kvm_options[] = {
else if (!strncmp(argv[0], "rep", 3))
return __cmd_report(file_name, argc, argv);
else if (!strncmp(argv[0], "diff", 4))
- return cmd_diff(argc, argv, NULL);
+ return cmd_diff(argc, argv);
else if (!strncmp(argv[0], "top", 3))
- return cmd_top(argc, argv, NULL);
+ return cmd_top(argc, argv);
else if (!strncmp(argv[0], "buildid-list", 12))
return __cmd_buildid_list(file_name, argc, argv);
#ifdef HAVE_KVM_STAT_SUPPORT
#include <subcmd/parse-options.h>
static bool desc_flag = true;
+static bool details_flag;
-int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_list(int argc, const char **argv)
{
int i;
bool raw_dump = false;
"Print extra event descriptions. --no-desc to not print."),
OPT_BOOLEAN('v', "long-desc", &long_desc_flag,
"Print longer event descriptions."),
+ OPT_BOOLEAN(0, "details", &details_flag,
+ "Print information on the perf event names and expressions used internally by events."),
OPT_INCR(0, "debug", &verbose,
"Enable debugging output"),
OPT_END()
printf("\nList of pre-defined events (to be used in -e):\n\n");
if (argc == 0) {
- print_events(NULL, raw_dump, !desc_flag, long_desc_flag);
+ print_events(NULL, raw_dump, !desc_flag, long_desc_flag,
+ details_flag);
return 0;
}
print_hwcache_events(NULL, raw_dump);
else if (strcmp(argv[i], "pmu") == 0)
print_pmu_events(NULL, raw_dump, !desc_flag,
- long_desc_flag);
+ long_desc_flag, details_flag);
else if (strcmp(argv[i], "sdt") == 0)
print_sdt_events(NULL, NULL, raw_dump);
else if ((sep = strchr(argv[i], ':')) != NULL) {
if (sep == NULL) {
print_events(argv[i], raw_dump, !desc_flag,
- long_desc_flag);
+ long_desc_flag,
+ details_flag);
continue;
}
sep_idx = sep - argv[i];
event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump);
print_hwcache_events(s, raw_dump);
print_pmu_events(s, raw_dump, !desc_flag,
- long_desc_flag);
+ long_desc_flag,
+ details_flag);
print_tracepoint_events(NULL, s, raw_dump);
print_sdt_events(NULL, s, raw_dump);
free(s);
+#include <errno.h>
+#include <inttypes.h>
#include "builtin.h"
#include "perf.h"
#include <linux/list.h>
#include <linux/hash.h>
+#include <linux/kernel.h>
static struct perf_session *session;
struct perf_tool eops = {
.sample = process_sample_event,
.comm = perf_event__process_comm,
+ .namespaces = perf_event__process_namespaces,
.ordered_events = true,
};
struct perf_data_file file = {
BUG_ON(i != rec_argc);
- ret = cmd_record(i, rec_argv, NULL);
+ ret = cmd_record(i, rec_argv);
free(rec_argv);
return ret;
}
-int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_lock(int argc, const char **argv)
{
- const struct option info_options[] = {
- OPT_BOOLEAN('t', "threads", &info_threads,
- "dump thread list in perf.data"),
- OPT_BOOLEAN('m', "map", &info_map,
- "map of lock instances (address:name table)"),
- OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
- OPT_END()
- };
const struct option lock_options[] = {
OPT_STRING('i', "input", &input_name, "file", "input file name"),
OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"),
OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"),
+ OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
OPT_END()
};
+
+ const struct option info_options[] = {
+ OPT_BOOLEAN('t', "threads", &info_threads,
+ "dump thread list in perf.data"),
+ OPT_BOOLEAN('m', "map", &info_map,
+ "map of lock instances (address:name table)"),
+ OPT_PARENT(lock_options)
+ };
+
const struct option report_options[] = {
OPT_STRING('k', "key", &sort_key, "acquired",
"key for sorting (acquired / contended / avg_wait / wait_total / wait_max / wait_min)"),
- OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
/* TODO: type */
- OPT_END()
+ OPT_PARENT(lock_options)
};
+
const char * const info_usage[] = {
"perf lock info [<options>]",
NULL
rc = __cmd_report(false);
} else if (!strcmp(argv[0], "script")) {
/* Aliased to 'perf script' */
- return cmd_script(argc, argv, prefix);
+ return cmd_script(argc, argv);
} else if (!strcmp(argv[0], "info")) {
if (argc) {
argc = parse_options(argc, argv,
+#include <inttypes.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
#include "builtin.h"
#include "perf.h"
#include "util/data.h"
#include "util/mem-events.h"
#include "util/debug.h"
+#include "util/symbol.h"
#define MEM_OPERATION_LOAD 0x1
#define MEM_OPERATION_STORE 0x2
pr_debug("\n");
}
- ret = cmd_record(i, rec_argv, NULL);
+ ret = cmd_record(i, rec_argv);
free(rec_argv);
return ret;
}
for (j = 1; j < argc; j++, i++)
rep_argv[i] = argv[j];
- ret = cmd_report(i, rep_argv, NULL);
+ ret = cmd_report(i, rep_argv);
free(rep_argv);
return ret;
}
return ret;
}
-int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_mem(int argc, const char **argv)
{
struct stat st;
struct perf_mem mem = {
.lost = perf_event__process_lost,
.fork = perf_event__process_fork,
.build_id = perf_event__process_build_id,
+ .namespaces = perf_event__process_namespaces,
.ordered_events = true,
},
.input_name = "perf.data",
}
if (ret == -ENOENT && ret2 == -ENOENT)
- pr_debug("\"%s\" does not hit any event.\n", str);
- /* Note that this is silently ignored */
- ret = 0;
+ pr_warning("\"%s\" does not hit any event.\n", str);
+ else
+ ret = 0;
error:
if (kfd >= 0)
static int
-__cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
+__cmd_probe(int argc, const char **argv)
{
const char * const probe_usage[] = {
"perf probe [<options>] 'PROBEDEF' ['PROBEDEF' ...]",
return 0;
}
-int cmd_probe(int argc, const char **argv, const char *prefix)
+int cmd_probe(int argc, const char **argv)
{
int ret;
ret = init_params();
if (!ret) {
- ret = __cmd_probe(argc, argv, prefix);
+ ret = __cmd_probe(argc, argv);
cleanup_params();
}
#include "util/bpf-loader.h"
#include "util/trigger.h"
#include "util/perf-hooks.h"
+#include "util/time-utils.h"
+#include "util/units.h"
#include "asm/bug.h"
+#include <errno.h>
+#include <inttypes.h>
+#include <poll.h>
#include <unistd.h>
#include <sched.h>
+#include <signal.h>
#include <sys/mman.h>
+#include <sys/wait.h>
#include <asm/bug.h>
#include <linux/time64.h>
signal(SIGTERM, sig_handler);
signal(SIGSEGV, sigsegv_handler);
+ if (rec->opts.record_namespaces)
+ tool->namespace_events = true;
+
if (rec->opts.auxtrace_snapshot_mode || rec->switch_output.enabled) {
signal(SIGUSR2, snapshot_sig_handler);
if (rec->opts.auxtrace_snapshot_mode)
*/
if (forks) {
union perf_event *event;
+ pid_t tgid;
event = malloc(sizeof(event->comm) + machine->id_hdr_size);
if (event == NULL) {
* cannot see a correct process name for those events.
* Synthesize COMM event to prevent it.
*/
- perf_event__synthesize_comm(tool, event,
- rec->evlist->workload.pid,
- process_synthesized_event,
- machine);
+ tgid = perf_event__synthesize_comm(tool, event,
+ rec->evlist->workload.pid,
+ process_synthesized_event,
+ machine);
+ free(event);
+
+ if (tgid == -1)
+ goto out_child;
+
+ event = malloc(sizeof(event->namespaces) +
+ (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+ machine->id_hdr_size);
+ if (event == NULL) {
+ err = -ENOMEM;
+ goto out_child;
+ }
+
+ /*
+ * Synthesize NAMESPACES event for the command specified.
+ */
+ perf_event__synthesize_namespaces(tool, event,
+ rec->evlist->workload.pid,
+ tgid, process_synthesized_event,
+ machine);
free(event);
perf_evlist__start_workload(rec->evlist);
.fork = perf_event__process_fork,
.exit = perf_event__process_exit,
.comm = perf_event__process_comm,
+ .namespaces = perf_event__process_namespaces,
.mmap = perf_event__process_mmap,
.mmap2 = perf_event__process_mmap2,
.ordered_events = true,
"opts", "AUX area tracing Snapshot Mode", ""),
OPT_UINTEGER(0, "proc-map-timeout", &record.opts.proc_map_timeout,
"per thread proc mmap processing timeout in ms"),
+ OPT_BOOLEAN(0, "namespaces", &record.opts.record_namespaces,
+ "Record namespaces events"),
OPT_BOOLEAN(0, "switch-events", &record.opts.record_switch_events,
"Record context switch events"),
OPT_BOOLEAN_FLAG(0, "all-kernel", &record.opts.all_kernel,
struct option *record_options = __record_options;
-int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_record(int argc, const char **argv)
{
int err;
struct record *rec = &record;
#include <linux/rbtree.h>
#include "util/symbol.h"
#include "util/callchain.h"
-#include "util/strlist.h"
#include "util/values.h"
#include "perf.h"
#include "arch/common.h"
#include "util/time-utils.h"
#include "util/auxtrace.h"
+#include "util/units.h"
#include <dlfcn.h>
+#include <errno.h>
+#include <inttypes.h>
+#include <regex.h>
+#include <signal.h>
#include <linux/bitmap.h>
#include <linux/stringify.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
struct report {
struct perf_tool tool;
fprintf(stdout, "\n\n");
}
- if (sort_order == NULL &&
- parent_pattern == default_parent_pattern)
+ if (!quiet)
fprintf(stdout, "#\n# (%s)\n#\n", help);
if (rep->show_threads) {
CALLCHAIN_REPORT_HELP
"\n\t\t\t\tDefault: " CALLCHAIN_DEFAULT_OPT;
-int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_report(int argc, const char **argv)
{
struct perf_session *session;
struct itrace_synth_opts itrace_synth_opts = { .set = 0, };
.mmap = perf_event__process_mmap,
.mmap2 = perf_event__process_mmap2,
.comm = perf_event__process_comm,
+ .namespaces = perf_event__process_namespaces,
.exit = perf_event__process_exit,
.fork = perf_event__process_fork,
.lost = perf_event__process_lost,
stdio__config_color, "always"),
OPT_STRING(0, "time", &report.time_str, "str",
"Time span of interest (start,stop)"),
+ OPT_BOOLEAN(0, "inline", &symbol_conf.inline_name,
+ "Show inline function"),
OPT_END()
};
struct perf_data_file file = {
#include "util/debug.h"
+#include <linux/kernel.h>
#include <linux/log2.h>
#include <sys/prctl.h>
#include <sys/resource.h>
+#include <inttypes.h>
+#include <errno.h>
#include <semaphore.h>
#include <pthread.h>
#include <math.h>
#include <api/fs/fs.h>
#include <linux/time64.h>
+#include "sane_ctype.h"
+
#define PR_SET_NAME 15 /* Set process name */
#define MAX_CPUS 4096
#define COMM_LEN 20
unsigned int max_stack;
bool show_cpu_visual;
bool show_wakeups;
+ bool show_next;
bool show_migrations;
bool show_state;
u64 skipped_samples;
}
static void timehist_print_sample(struct perf_sched *sched,
+ struct perf_evsel *evsel,
struct perf_sample *sample,
struct addr_location *al,
struct thread *thread,
u64 t, int state)
{
struct thread_runtime *tr = thread__priv(thread);
+ const char *next_comm = perf_evsel__strval(evsel, sample, "next_comm");
+ const u32 next_pid = perf_evsel__intval(evsel, sample, "next_pid");
u32 max_cpus = sched->max_cpu + 1;
char tstr[64];
+ char nstr[30];
u64 wait_time;
timestamp__scnprintf_usec(t, tstr, sizeof(tstr));
if (sched->show_state)
printf(" %5c ", task_state_char(thread, state));
- if (sched->show_wakeups)
+ if (sched->show_next) {
+ snprintf(nstr, sizeof(nstr), "next: %s[%d]", next_comm, next_pid);
+ printf(" %-*s", comm_width, nstr);
+ }
+
+ if (sched->show_wakeups && !sched->show_next)
printf(" %-*s", comm_width, "");
if (thread->tid == 0)
}
if (!sched->summary_only)
- timehist_print_sample(sched, sample, &al, thread, t, state);
+ timehist_print_sample(sched, evsel, sample, &al, thread, t, state);
out:
if (sched->hist_time.start == 0 && t >= ptime->start)
BUG_ON(i != rec_argc);
- return cmd_record(i, rec_argv, NULL);
+ return cmd_record(i, rec_argv);
}
-int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_sched(int argc, const char **argv)
{
const char default_sort_order[] = "avg, max, switch, runtime";
struct perf_sched sched = {
.tool = {
.sample = perf_sched__process_tracepoint_sample,
.comm = perf_event__process_comm,
+ .namespaces = perf_event__process_namespaces,
.lost = perf_event__process_lost,
.fork = perf_sched__process_fork_event,
.ordered_events = true,
OPT_BOOLEAN('S', "with-summary", &sched.summary,
"Show all syscalls and summary with statistics"),
OPT_BOOLEAN('w', "wakeups", &sched.show_wakeups, "Show wakeup events"),
+ OPT_BOOLEAN('n', "next", &sched.show_next, "Show next task"),
OPT_BOOLEAN('M', "migrations", &sched.show_migrations, "Show migration events"),
OPT_BOOLEAN('V', "cpu-visual", &sched.show_cpu_visual, "Add CPU visual"),
OPT_BOOLEAN('I', "idle-hist", &sched.idle_hist, "Show idle events only"),
* Aliased to 'perf script' for now:
*/
if (!strcmp(argv[0], "script"))
- return cmd_script(argc, argv, prefix);
+ return cmd_script(argc, argv);
if (!strncmp(argv[0], "rec", 3)) {
return __cmd_record(argc, argv);
if (argc)
usage_with_options(timehist_usage, timehist_options);
}
- if (sched.show_wakeups && sched.summary_only) {
- pr_err(" Error: -s and -w are mutually exclusive.\n");
+ if ((sched.show_wakeups || sched.show_next) &&
+ sched.summary_only) {
+ pr_err(" Error: -s and -[n|w] are mutually exclusive.\n");
parse_options_usage(timehist_usage, timehist_options, "s", true);
- parse_options_usage(NULL, timehist_options, "w", true);
+ if (sched.show_wakeups)
+ parse_options_usage(NULL, timehist_options, "w", true);
+ if (sched.show_next)
+ parse_options_usage(NULL, timehist_options, "n", true);
return -EINVAL;
}
#include "util/cpumap.h"
#include "util/thread_map.h"
#include "util/stat.h"
+#include "util/string2.h"
#include "util/thread-stack.h"
#include "util/time-utils.h"
+#include "print_binary.h"
#include <linux/bitmap.h>
+#include <linux/kernel.h>
#include <linux/stringify.h>
#include <linux/time64.h>
#include "asm/bug.h"
#include "util/mem-events.h"
+#include "util/dump-insn.h"
+#include <dirent.h>
+#include <errno.h>
+#include <inttypes.h>
+#include <signal.h>
+#include <sys/param.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+
+#include "sane_ctype.h"
static char const *script_name;
static char const *generate_script_lang;
static const char *cpu_list;
static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
static struct perf_stat_config stat_config;
+static int max_blocks;
unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH;
PERF_OUTPUT_CALLINDENT = 1U << 20,
PERF_OUTPUT_INSN = 1U << 21,
PERF_OUTPUT_INSNLEN = 1U << 22,
+ PERF_OUTPUT_BRSTACKINSN = 1U << 23,
};
struct output_option {
{.str = "callindent", .field = PERF_OUTPUT_CALLINDENT},
{.str = "insn", .field = PERF_OUTPUT_INSN},
{.str = "insnlen", .field = PERF_OUTPUT_INSNLEN},
+ {.str = "brstackinsn", .field = PERF_OUTPUT_BRSTACKINSN},
};
/* default set to maintain compatibility with current format */
"selected. Hence, no address to lookup the source line number.\n");
return -EINVAL;
}
-
+ if (PRINT_FIELD(BRSTACKINSN) &&
+ !(perf_evlist__combined_branch_type(session->evlist) &
+ PERF_SAMPLE_BRANCH_ANY)) {
+ pr_err("Display of branch stack assembler requested, but non all-branch filter set\n"
+ "Hint: run 'perf record -b ...'\n");
+ return -EINVAL;
+ }
if ((PRINT_FIELD(PID) || PRINT_FIELD(TID)) &&
perf_evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID",
PERF_OUTPUT_TID|PERF_OUTPUT_PID))
}
}
+#define MAXBB 16384UL
+
+static int grab_bb(u8 *buffer, u64 start, u64 end,
+ struct machine *machine, struct thread *thread,
+ bool *is64bit, u8 *cpumode, bool last)
+{
+ long offset, len;
+ struct addr_location al;
+ bool kernel;
+
+ if (!start || !end)
+ return 0;
+
+ kernel = machine__kernel_ip(machine, start);
+ if (kernel)
+ *cpumode = PERF_RECORD_MISC_KERNEL;
+ else
+ *cpumode = PERF_RECORD_MISC_USER;
+
+ /*
+ * Block overlaps between kernel and user.
+ * This can happen due to ring filtering
+ * On Intel CPUs the entry into the kernel is filtered,
+ * but the exit is not. Let the caller patch it up.
+ */
+ if (kernel != machine__kernel_ip(machine, end)) {
+ printf("\tblock %" PRIx64 "-%" PRIx64 " transfers between kernel and user\n",
+ start, end);
+ return -ENXIO;
+ }
+
+ memset(&al, 0, sizeof(al));
+ if (end - start > MAXBB - MAXINSN) {
+ if (last)
+ printf("\tbrstack does not reach to final jump (%" PRIx64 "-%" PRIx64 ")\n", start, end);
+ else
+ printf("\tblock %" PRIx64 "-%" PRIx64 " (%" PRIu64 ") too long to dump\n", start, end, end - start);
+ return 0;
+ }
+
+ thread__find_addr_map(thread, *cpumode, MAP__FUNCTION, start, &al);
+ if (!al.map || !al.map->dso) {
+ printf("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end);
+ return 0;
+ }
+ if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR) {
+ printf("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end);
+ return 0;
+ }
+
+ /* Load maps to ensure dso->is_64_bit has been updated */
+ map__load(al.map);
+
+ offset = al.map->map_ip(al.map, start);
+ len = dso__data_read_offset(al.map->dso, machine, offset, (u8 *)buffer,
+ end - start + MAXINSN);
+
+ *is64bit = al.map->dso->is_64_bit;
+ if (len <= 0)
+ printf("\tcannot fetch code for block at %" PRIx64 "-%" PRIx64 "\n",
+ start, end);
+ return len;
+}
+
+static void print_jump(uint64_t ip, struct branch_entry *en,
+ struct perf_insn *x, u8 *inbuf, int len,
+ int insn)
+{
+ printf("\t%016" PRIx64 "\t%-30s\t#%s%s%s%s",
+ ip,
+ dump_insn(x, ip, inbuf, len, NULL),
+ en->flags.predicted ? " PRED" : "",
+ en->flags.mispred ? " MISPRED" : "",
+ en->flags.in_tx ? " INTX" : "",
+ en->flags.abort ? " ABORT" : "");
+ if (en->flags.cycles) {
+ printf(" %d cycles", en->flags.cycles);
+ if (insn)
+ printf(" %.2f IPC", (float)insn / en->flags.cycles);
+ }
+ putchar('\n');
+}
+
+static void print_ip_sym(struct thread *thread, u8 cpumode, int cpu,
+ uint64_t addr, struct symbol **lastsym,
+ struct perf_event_attr *attr)
+{
+ struct addr_location al;
+ int off;
+
+ memset(&al, 0, sizeof(al));
+
+ thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al);
+ if (!al.map)
+ thread__find_addr_map(thread, cpumode, MAP__VARIABLE,
+ addr, &al);
+ if ((*lastsym) && al.addr >= (*lastsym)->start && al.addr < (*lastsym)->end)
+ return;
+
+ al.cpu = cpu;
+ al.sym = NULL;
+ if (al.map)
+ al.sym = map__find_symbol(al.map, al.addr);
+
+ if (!al.sym)
+ return;
+
+ if (al.addr < al.sym->end)
+ off = al.addr - al.sym->start;
+ else
+ off = al.addr - al.map->start - al.sym->start;
+ printf("\t%s", al.sym->name);
+ if (off)
+ printf("%+d", off);
+ putchar(':');
+ if (PRINT_FIELD(SRCLINE))
+ map__fprintf_srcline(al.map, al.addr, "\t", stdout);
+ putchar('\n');
+ *lastsym = al.sym;
+}
+
+static void print_sample_brstackinsn(struct perf_sample *sample,
+ struct thread *thread,
+ struct perf_event_attr *attr,
+ struct machine *machine)
+{
+ struct branch_stack *br = sample->branch_stack;
+ u64 start, end;
+ int i, insn, len, nr, ilen;
+ struct perf_insn x;
+ u8 buffer[MAXBB];
+ unsigned off;
+ struct symbol *lastsym = NULL;
+
+ if (!(br && br->nr))
+ return;
+ nr = br->nr;
+ if (max_blocks && nr > max_blocks + 1)
+ nr = max_blocks + 1;
+
+ x.thread = thread;
+ x.cpu = sample->cpu;
+
+ putchar('\n');
+
+ /* Handle first from jump, of which we don't know the entry. */
+ len = grab_bb(buffer, br->entries[nr-1].from,
+ br->entries[nr-1].from,
+ machine, thread, &x.is64bit, &x.cpumode, false);
+ if (len > 0) {
+ print_ip_sym(thread, x.cpumode, x.cpu,
+ br->entries[nr - 1].from, &lastsym, attr);
+ print_jump(br->entries[nr - 1].from, &br->entries[nr - 1],
+ &x, buffer, len, 0);
+ }
+
+ /* Print all blocks */
+ for (i = nr - 2; i >= 0; i--) {
+ if (br->entries[i].from || br->entries[i].to)
+ pr_debug("%d: %" PRIx64 "-%" PRIx64 "\n", i,
+ br->entries[i].from,
+ br->entries[i].to);
+ start = br->entries[i + 1].to;
+ end = br->entries[i].from;
+
+ len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false);
+ /* Patch up missing kernel transfers due to ring filters */
+ if (len == -ENXIO && i > 0) {
+ end = br->entries[--i].from;
+ pr_debug("\tpatching up to %" PRIx64 "-%" PRIx64 "\n", start, end);
+ len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, false);
+ }
+ if (len <= 0)
+ continue;
+
+ insn = 0;
+ for (off = 0;; off += ilen) {
+ uint64_t ip = start + off;
+
+ print_ip_sym(thread, x.cpumode, x.cpu, ip, &lastsym, attr);
+ if (ip == end) {
+ print_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn);
+ break;
+ } else {
+ printf("\t%016" PRIx64 "\t%s\n", ip,
+ dump_insn(&x, ip, buffer + off, len - off, &ilen));
+ if (ilen == 0)
+ break;
+ insn++;
+ }
+ }
+ }
+
+ /*
+ * Hit the branch? In this case we are already done, and the target
+ * has not been executed yet.
+ */
+ if (br->entries[0].from == sample->ip)
+ return;
+ if (br->entries[0].flags.abort)
+ return;
+
+ /*
+ * Print final block upto sample
+ */
+ start = br->entries[0].to;
+ end = sample->ip;
+ len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, true);
+ print_ip_sym(thread, x.cpumode, x.cpu, start, &lastsym, attr);
+ if (len <= 0) {
+ /* Print at least last IP if basic block did not work */
+ len = grab_bb(buffer, sample->ip, sample->ip,
+ machine, thread, &x.is64bit, &x.cpumode, false);
+ if (len <= 0)
+ return;
+
+ printf("\t%016" PRIx64 "\t%s\n", sample->ip,
+ dump_insn(&x, sample->ip, buffer, len, NULL));
+ return;
+ }
+ for (off = 0; off <= end - start; off += ilen) {
+ printf("\t%016" PRIx64 "\t%s\n", start + off,
+ dump_insn(&x, start + off, buffer + off, len - off, &ilen));
+ if (ilen == 0)
+ break;
+ }
+}
static void print_sample_addr(struct perf_sample *sample,
struct thread *thread,
}
static void print_insn(struct perf_sample *sample,
- struct perf_event_attr *attr)
+ struct perf_event_attr *attr,
+ struct thread *thread,
+ struct machine *machine)
{
if (PRINT_FIELD(INSNLEN))
printf(" ilen: %d", sample->insn_len);
for (i = 0; i < sample->insn_len; i++)
printf(" %02x", (unsigned char)sample->insn[i]);
}
+ if (PRINT_FIELD(BRSTACKINSN))
+ print_sample_brstackinsn(sample, thread, attr, machine);
}
static void print_sample_bts(struct perf_sample *sample,
struct perf_evsel *evsel,
struct thread *thread,
- struct addr_location *al)
+ struct addr_location *al,
+ struct machine *machine)
{
struct perf_event_attr *attr = &evsel->attr;
bool print_srcline_last = false;
if (print_srcline_last)
map__fprintf_srcline(al->map, al->addr, "\n ", stdout);
- print_insn(sample, attr);
+ print_insn(sample, attr, thread, machine);
printf("\n");
}
bool show_task_events;
bool show_mmap_events;
bool show_switch_events;
+ bool show_namespace_events;
bool allocated;
struct cpu_map *cpus;
struct thread_map *threads;
static void process_event(struct perf_script *script,
struct perf_sample *sample, struct perf_evsel *evsel,
- struct addr_location *al)
+ struct addr_location *al,
+ struct machine *machine)
{
struct thread *thread = al->thread;
struct perf_event_attr *attr = &evsel->attr;
print_sample_flags(sample->flags);
if (is_bts_event(attr)) {
- print_sample_bts(sample, evsel, thread, al);
+ print_sample_bts(sample, evsel, thread, al, machine);
return;
}
if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
print_sample_bpf_output(sample);
- print_insn(sample, attr);
+ print_insn(sample, attr, thread, machine);
printf("\n");
}
if (scripting_ops)
scripting_ops->process_event(event, sample, evsel, &al);
else
- process_event(scr, sample, evsel, &al);
+ process_event(scr, sample, evsel, &al, machine);
out_put:
addr_location__put(&al);
return ret;
}
+static int process_namespaces_event(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine)
+{
+ struct thread *thread;
+ struct perf_script *script = container_of(tool, struct perf_script, tool);
+ struct perf_session *session = script->session;
+ struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id);
+ int ret = -1;
+
+ thread = machine__findnew_thread(machine, event->namespaces.pid,
+ event->namespaces.tid);
+ if (thread == NULL) {
+ pr_debug("problem processing NAMESPACES event, skipping it.\n");
+ return -1;
+ }
+
+ if (perf_event__process_namespaces(tool, event, sample, machine) < 0)
+ goto out;
+
+ if (!evsel->attr.sample_id_all) {
+ sample->cpu = 0;
+ sample->time = 0;
+ sample->tid = event->namespaces.tid;
+ sample->pid = event->namespaces.pid;
+ }
+ print_sample_start(sample, thread, evsel);
+ perf_event__fprintf(event, stdout);
+ ret = 0;
+out:
+ thread__put(thread);
+ return ret;
+}
+
static int process_fork_event(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
}
if (script->show_switch_events)
script->tool.context_switch = process_switch_event;
+ if (script->show_namespace_events)
+ script->tool.namespaces = process_namespaces_event;
ret = perf_session__process_events(script->session);
static int parse_output_fields(const struct option *opt __maybe_unused,
const char *arg, int unset __maybe_unused)
{
- char *tok;
+ char *tok, *strtok_saveptr = NULL;
int i, imax = ARRAY_SIZE(all_output_options);
int j;
int rc = 0;
}
}
- for (tok = strtok(tok, ","); tok; tok = strtok(NULL, ",")) {
+ for (tok = strtok_r(tok, ",", &strtok_saveptr); tok; tok = strtok_r(NULL, ",", &strtok_saveptr)) {
for (i = 0; i < imax; ++i) {
if (strcmp(tok, all_output_options[i].str) == 0)
break;
return set_maps(script);
}
-int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_script(int argc, const char **argv)
{
bool show_full_info = false;
bool header = false;
.mmap = perf_event__process_mmap,
.mmap2 = perf_event__process_mmap2,
.comm = perf_event__process_comm,
+ .namespaces = perf_event__process_namespaces,
.exit = perf_event__process_exit,
.fork = perf_event__process_fork,
.attr = process_attr,
"Valid types: hw,sw,trace,raw. "
"Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
"addr,symoff,period,iregs,brstack,brstacksym,flags,"
- "bpf-output,callindent,insn,insnlen", parse_output_fields),
+ "bpf-output,callindent,insn,insnlen,brstackinsn",
+ parse_output_fields),
OPT_BOOLEAN('a', "all-cpus", &system_wide,
"system-wide collection from all CPUs"),
OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
"Show the mmap events"),
OPT_BOOLEAN('\0', "show-switch-events", &script.show_switch_events,
"Show context switch events (if recorded)"),
+ OPT_BOOLEAN('\0', "show-namespace-events", &script.show_namespace_events,
+ "Show namespace events (if recorded)"),
OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
+ OPT_INTEGER(0, "max-blocks", &max_blocks,
+ "Maximum number of code blocks to dump with brstackinsn"),
OPT_BOOLEAN(0, "ns", &nanosecs,
"Use 9 decimal places when displaying time"),
OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) {
rec_script_path = get_script_path(argv[1], RECORD_SUFFIX);
if (!rec_script_path)
- return cmd_record(argc, argv, NULL);
+ return cmd_record(argc, argv);
}
if (argc > 1 && !strncmp(argv[0], "rep", strlen("rep"))) {
#include "util/session.h"
#include "util/tool.h"
#include "util/group.h"
+#include "util/string2.h"
#include "asm/bug.h"
#include <linux/time64.h>
#include <api/fs/fs.h>
+#include <errno.h>
+#include <signal.h>
#include <stdlib.h>
#include <sys/prctl.h>
+#include <inttypes.h>
#include <locale.h>
#include <math.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "sane_ctype.h"
#define DEFAULT_SEPARATOR " "
#define CNTR_NOT_SUPPORTED "<not supported>"
static bool forever = false;
static bool metric_only = false;
static bool force_metric_only = false;
+static bool no_merge = false;
static struct timespec ref_time;
static struct cpu_map *aggr_map;
static aggr_get_id_t aggr_get_id;
static bool append_file;
static const char *output_name;
static int output_fd;
+static int print_free_counters_hint;
struct perf_stat {
bool record;
struct perf_counts_values *count;
count = perf_counts(counter->counts, cpu, thread);
- if (perf_evsel__read(counter, cpu, thread, count))
+ if (perf_evsel__read(counter, cpu, thread, count)) {
+ counter->counts->scaled = -1;
+ perf_counts(counter->counts, cpu, thread)->ena = 0;
+ perf_counts(counter->counts, cpu, thread)->run = 0;
return -1;
+ }
if (STAT_RECORD) {
if (perf_evsel__write_stat_event(counter, cpu, thread, count)) {
static void read_counters(void)
{
struct perf_evsel *counter;
+ int ret;
evlist__for_each_entry(evsel_list, counter) {
- if (read_counter(counter))
+ ret = read_counter(counter);
+ if (ret)
pr_debug("failed to read counter %s\n", counter->name);
- if (perf_stat_process_counter(&stat_config, counter))
+ if (ret == 0 && perf_stat_process_counter(&stat_config, counter))
pr_warning("failed to process counter %s\n", counter->name);
}
}
return;
}
snprintf(buf, sizeof(buf), fmt, val);
- vals = buf;
- while (isspace(*vals))
- vals++;
- ends = vals;
+ ends = vals = ltrim(buf);
while (isdigit(*ends) || *ends == '.')
ends++;
*ends = 0;
return;
unit = fixunit(tbuf, os->evsel, unit);
snprintf(buf, sizeof buf, fmt, val);
- vals = buf;
- while (isspace(*vals))
- vals++;
- ends = vals;
+ ends = vals = ltrim(buf);
while (isdigit(*ends) || *ends == '.')
ends++;
*ends = 0;
counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
csv_sep);
+ if (counter->supported)
+ print_free_counters_hint = 1;
+
fprintf(stat_config.output, "%-*s%s",
csv_output ? 0 : unit_width,
counter->unit, csv_sep);
out.print_metric = pm;
out.new_line = nl;
out.ctx = &os;
+ out.force_header = false;
if (csv_output && !metric_only) {
print_noise(counter, noise);
}
}
+static void collect_all_aliases(struct perf_evsel *counter,
+ void (*cb)(struct perf_evsel *counter, void *data,
+ bool first),
+ void *data)
+{
+ struct perf_evsel *alias;
+
+ alias = list_prepare_entry(counter, &(evsel_list->entries), node);
+ list_for_each_entry_continue (alias, &evsel_list->entries, node) {
+ if (strcmp(perf_evsel__name(alias), perf_evsel__name(counter)) ||
+ alias->scale != counter->scale ||
+ alias->cgrp != counter->cgrp ||
+ strcmp(alias->unit, counter->unit) ||
+ nsec_counter(alias) != nsec_counter(counter))
+ break;
+ alias->merged_stat = true;
+ cb(alias, data, false);
+ }
+}
+
+static bool collect_data(struct perf_evsel *counter,
+ void (*cb)(struct perf_evsel *counter, void *data,
+ bool first),
+ void *data)
+{
+ if (counter->merged_stat)
+ return false;
+ cb(counter, data, true);
+ if (!no_merge)
+ collect_all_aliases(counter, cb, data);
+ return true;
+}
+
+struct aggr_data {
+ u64 ena, run, val;
+ int id;
+ int nr;
+ int cpu;
+};
+
+static void aggr_cb(struct perf_evsel *counter, void *data, bool first)
+{
+ struct aggr_data *ad = data;
+ int cpu, s2;
+
+ for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+ struct perf_counts_values *counts;
+
+ s2 = aggr_get_id(perf_evsel__cpus(counter), cpu);
+ if (s2 != ad->id)
+ continue;
+ if (first)
+ ad->nr++;
+ counts = perf_counts(counter->counts, cpu, 0);
+ /*
+ * When any result is bad, make them all to give
+ * consistent output in interval mode.
+ */
+ if (counts->ena == 0 || counts->run == 0 ||
+ counter->counts->scaled == -1) {
+ ad->ena = 0;
+ ad->run = 0;
+ break;
+ }
+ ad->val += counts->val;
+ ad->ena += counts->ena;
+ ad->run += counts->run;
+ }
+}
+
static void print_aggr(char *prefix)
{
FILE *output = stat_config.output;
struct perf_evsel *counter;
- int cpu, s, s2, id, nr;
+ int s, id, nr;
double uval;
u64 ena, run, val;
bool first;
* Without each counter has its own line.
*/
for (s = 0; s < aggr_map->nr; s++) {
+ struct aggr_data ad;
if (prefix && metric_only)
fprintf(output, "%s", prefix);
- id = aggr_map->map[s];
+ ad.id = id = aggr_map->map[s];
first = true;
evlist__for_each_entry(evsel_list, counter) {
- val = ena = run = 0;
- nr = 0;
- for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
- s2 = aggr_get_id(perf_evsel__cpus(counter), cpu);
- if (s2 != id)
- continue;
- val += perf_counts(counter->counts, cpu, 0)->val;
- ena += perf_counts(counter->counts, cpu, 0)->ena;
- run += perf_counts(counter->counts, cpu, 0)->run;
- nr++;
- }
+ ad.val = ad.ena = ad.run = 0;
+ ad.nr = 0;
+ if (!collect_data(counter, aggr_cb, &ad))
+ continue;
+ nr = ad.nr;
+ ena = ad.ena;
+ run = ad.run;
+ val = ad.val;
if (first && metric_only) {
first = false;
aggr_printout(counter, id, nr);
}
}
+struct caggr_data {
+ double avg, avg_enabled, avg_running;
+};
+
+static void counter_aggr_cb(struct perf_evsel *counter, void *data,
+ bool first __maybe_unused)
+{
+ struct caggr_data *cd = data;
+ struct perf_stat_evsel *ps = counter->priv;
+
+ cd->avg += avg_stats(&ps->res_stats[0]);
+ cd->avg_enabled += avg_stats(&ps->res_stats[1]);
+ cd->avg_running += avg_stats(&ps->res_stats[2]);
+}
+
/*
* Print out the results of a single counter:
* aggregated counts in system-wide mode
static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
{
FILE *output = stat_config.output;
- struct perf_stat_evsel *ps = counter->priv;
- double avg = avg_stats(&ps->res_stats[0]);
double uval;
- double avg_enabled, avg_running;
+ struct caggr_data cd = { .avg = 0.0 };
- avg_enabled = avg_stats(&ps->res_stats[1]);
- avg_running = avg_stats(&ps->res_stats[2]);
+ if (!collect_data(counter, counter_aggr_cb, &cd))
+ return;
if (prefix && !metric_only)
fprintf(output, "%s", prefix);
- uval = avg * counter->scale;
- printout(-1, 0, counter, uval, prefix, avg_running, avg_enabled, avg);
+ uval = cd.avg * counter->scale;
+ printout(-1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled, cd.avg);
if (!metric_only)
fprintf(output, "\n");
}
+static void counter_cb(struct perf_evsel *counter, void *data,
+ bool first __maybe_unused)
+{
+ struct aggr_data *ad = data;
+
+ ad->val += perf_counts(counter->counts, ad->cpu, 0)->val;
+ ad->ena += perf_counts(counter->counts, ad->cpu, 0)->ena;
+ ad->run += perf_counts(counter->counts, ad->cpu, 0)->run;
+}
+
/*
* Print out the results of a single counter:
* does not use aggregated count in system-wide
int cpu;
for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
- val = perf_counts(counter->counts, cpu, 0)->val;
- ena = perf_counts(counter->counts, cpu, 0)->ena;
- run = perf_counts(counter->counts, cpu, 0)->run;
+ struct aggr_data ad = { .cpu = cpu };
+
+ if (!collect_data(counter, counter_cb, &ad))
+ return;
+ val = ad.val;
+ ena = ad.ena;
+ run = ad.run;
if (prefix)
fprintf(output, "%s", prefix);
out.ctx = &os;
out.print_metric = print_metric_header;
out.new_line = new_line_metric;
+ out.force_header = true;
os.evsel = counter;
perf_stat__print_shadow_stats(counter, 0,
0,
avg_stats(&walltime_nsecs_stats));
}
fprintf(output, "\n\n");
+
+ if (print_free_counters_hint)
+ fprintf(output,
+"Some events weren't counted. Try disabling the NMI watchdog:\n"
+" echo 0 > /proc/sys/kernel/nmi_watchdog\n"
+" perf stat ...\n"
+" echo 1 > /proc/sys/kernel/nmi_watchdog\n");
}
static void print_counters(struct timespec *ts, int argc, const char **argv)
"list of cpus to monitor in system-wide"),
OPT_SET_UINT('A', "no-aggr", &stat_config.aggr_mode,
"disable CPU count aggregation", AGGR_NONE),
+ OPT_BOOLEAN(0, "no-merge", &no_merge, "Do not merge identical named events"),
OPT_STRING('x', "field-separator", &csv_sep, "separator",
"print counts with custom separator"),
OPT_CALLBACK('G', "cgroup", &evsel_list, "name",
return 0;
}
-int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
+static void setup_system_wide(int forks)
+{
+ /*
+ * Make system wide (-a) the default target if
+ * no target was specified and one of following
+ * conditions is met:
+ *
+ * - there's no workload specified
+ * - there is workload specified but all requested
+ * events are system wide events
+ */
+ if (!target__none(&target))
+ return;
+
+ if (!forks)
+ target.system_wide = true;
+ else {
+ struct perf_evsel *counter;
+
+ evlist__for_each_entry(evsel_list, counter) {
+ if (!counter->system_wide)
+ return;
+ }
+
+ if (evsel_list->nr_entries)
+ target.system_wide = true;
+ }
+}
+
+int cmd_stat(int argc, const char **argv)
{
const char * const stat_usage[] = {
"perf stat [<options>] [<command>]",
argc = parse_options_subcommand(argc, argv, stat_options, stat_subcommands,
(const char **) stat_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
+ perf_stat__collect_metric_expr(evsel_list);
perf_stat__init_shadow_stats();
if (csv_sep) {
} else if (big_num_opt == 0) /* User passed --no-big-num */
big_num = false;
- /* Make system wide (-a) the default target. */
- if (!argc && target__none(&target))
- target.system_wide = true;
+ setup_system_wide(argc);
if (run_count < 0) {
pr_err("Run count must be a positive number\n");
* of the License.
*/
+#include <errno.h>
+#include <inttypes.h>
#include <traceevent/event-parse.h>
#include "builtin.h"
#include "util/cache.h"
#include "util/evlist.h"
#include "util/evsel.h"
+#include <linux/kernel.h>
#include <linux/rbtree.h>
#include <linux/time64.h>
#include "util/symbol.h"
+#include "util/thread.h"
#include "util/callchain.h"
-#include "util/strlist.h"
#include "perf.h"
#include "util/header.h"
for (i = 0; i < (unsigned int)argc; i++)
*p++ = argv[i];
- return cmd_record(rec_argc, rec_argv, NULL);
+ return cmd_record(rec_argc, rec_argv);
}
for (j = 0; j < (unsigned int)argc; j++)
*p++ = argv[j];
- return cmd_record(rec_argc, rec_argv, NULL);
+ return cmd_record(rec_argc, rec_argv);
}
static int
return 0;
}
-int cmd_timechart(int argc, const char **argv,
- const char *prefix __maybe_unused)
+int cmd_timechart(int argc, const char **argv)
{
struct timechart tchart = {
.tool = {
.merge_dist = 1000,
};
const char *output_name = "output.svg";
+ const struct option timechart_common_options[] = {
+ OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"),
+ OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only, "output processes data only"),
+ OPT_END()
+ };
const struct option timechart_options[] = {
OPT_STRING('i', "input", &input_name, "file", "input file name"),
OPT_STRING('o', "output", &output_name, "file", "output file name"),
OPT_CALLBACK(0, "highlight", NULL, "duration or task name",
"highlight tasks. Pass duration in ns or process name.",
parse_highlight),
- OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"),
- OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only,
- "output processes data only"),
OPT_CALLBACK('p', "process", NULL, "process",
"process selector. Pass a pid or process name.",
parse_process),
"merge events that are merge-dist us apart",
parse_time),
OPT_BOOLEAN('f', "force", &tchart.force, "don't complain, do it"),
- OPT_END()
+ OPT_PARENT(timechart_common_options),
};
const char * const timechart_subcommands[] = { "record", NULL };
const char *timechart_usage[] = {
"perf timechart [<options>] {record}",
NULL
};
-
const struct option timechart_record_options[] = {
- OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"),
- OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only,
- "output processes data only"),
OPT_BOOLEAN('I', "io-only", &tchart.io_only,
"record only IO data"),
OPT_BOOLEAN('g', "callchain", &tchart.with_backtrace, "record callchain"),
- OPT_END()
+ OPT_PARENT(timechart_common_options),
};
const char * const timechart_record_usage[] = {
"perf timechart record [<options>]",
#include "util/cpumap.h"
#include "util/xyarray.h"
#include "util/sort.h"
+#include "util/term.h"
#include "util/intlist.h"
#include "util/parse-branch-options.h"
#include "arch/common.h"
#include <errno.h>
#include <time.h>
#include <sched.h>
+#include <signal.h>
#include <sys/syscall.h>
#include <sys/ioctl.h>
#include <linux/time64.h>
#include <linux/types.h>
+#include "sane_ctype.h"
+
static volatile int done;
#define HEADER_LINE_NR 5
const char top_callchain_help[] = CALLCHAIN_RECORD_HELP CALLCHAIN_REPORT_HELP
"\n\t\t\t\tDefault: fp,graph,0.5,caller,function";
-int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_top(int argc, const char **argv)
{
char errbuf[BUFSIZ];
struct perf_top top = {
#include "util/evlist.h"
#include <subcmd/exec-cmd.h>
#include "util/machine.h"
+#include "util/path.h"
#include "util/session.h"
#include "util/thread.h"
#include <subcmd/parse-options.h>
#include "util/intlist.h"
#include "util/thread_map.h"
#include "util/stat.h"
+#include "trace/beauty/beauty.h"
#include "trace-event.h"
#include "util/parse-events.h"
#include "util/bpf-loader.h"
#include "callchain.h"
+#include "print_binary.h"
+#include "string2.h"
#include "syscalltbl.h"
#include "rb_resort.h"
+#include <errno.h>
+#include <inttypes.h>
#include <libaudit.h> /* FIXME: Still needed for audit_errno_to_name */
+#include <poll.h>
+#include <signal.h>
#include <stdlib.h>
#include <string.h>
#include <linux/err.h>
#include <linux/filter.h>
#include <linux/audit.h>
+#include <linux/kernel.h>
#include <linux/random.h>
#include <linux/stringify.h>
#include <linux/time64.h>
+#include "sane_ctype.h"
+
#ifndef O_CLOEXEC
# define O_CLOEXEC 02000000
#endif
({ struct syscall_tp *fields = evsel->priv; \
fields->name.pointer(&fields->name, sample); })
-struct syscall_arg {
- unsigned long val;
- struct thread *thread;
- struct trace *trace;
- void *parm;
- u8 idx;
- u8 mask;
-};
-
struct strarray {
int offset;
int nr_entries;
.arg_parm = { [0] = &strarray__socket_families, /* family */ }, },
{ .name = "stat", .errmsg = true, .alias = "newstat", },
{ .name = "statfs", .errmsg = true, },
+ { .name = "statx", .errmsg = true,
+ .arg_scnprintf = { [0] = SCA_FDAT, /* flags */
+ [2] = SCA_STATX_FLAGS, /* flags */
+ [3] = SCA_STATX_MASK, /* mask */ }, },
{ .name = "swapoff", .errmsg = true,
.arg_scnprintf = { [0] = SCA_FILENAME, /* specialfile */ }, },
{ .name = "swapon", .errmsg = true,
void **arg_parm;
};
-static size_t fprintf_duration(unsigned long t, FILE *fp)
+/*
+ * We need to have this 'calculated' boolean because in some cases we really
+ * don't know what is the duration of a syscall, for instance, when we start
+ * a session and some threads are waiting for a syscall to finish, say 'poll',
+ * in which case all we can do is to print "( ? ) for duration and for the
+ * start timestamp.
+ */
+static size_t fprintf_duration(unsigned long t, bool calculated, FILE *fp)
{
double duration = (double)t / NSEC_PER_MSEC;
size_t printed = fprintf(fp, "(");
- if (duration >= 1.0)
+ if (!calculated)
+ printed += fprintf(fp, " ? ");
+ else if (duration >= 1.0)
printed += color_fprintf(fp, PERF_COLOR_RED, "%6.3f ms", duration);
else if (duration >= 0.01)
printed += color_fprintf(fp, PERF_COLOR_YELLOW, "%6.3f ms", duration);
return t < (trace->duration_filter * NSEC_PER_MSEC);
}
-static size_t trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp)
+static size_t __trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp)
{
double ts = (double)(tstamp - trace->base_time) / NSEC_PER_MSEC;
return fprintf(fp, "%10.3f ", ts);
}
+/*
+ * We're handling tstamp=0 as an undefined tstamp, i.e. like when we are
+ * using ttrace->entry_time for a thread that receives a sys_exit without
+ * first having received a sys_enter ("poll" issued before tracing session
+ * starts, lost sys_enter exit due to ring buffer overflow).
+ */
+static size_t trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp)
+{
+ if (tstamp > 0)
+ return __trace__fprintf_tstamp(trace, tstamp, fp);
+
+ return fprintf(fp, " ? ");
+}
+
static bool done = false;
static bool interrupted = false;
}
static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread,
- u64 duration, u64 tstamp, FILE *fp)
+ u64 duration, bool duration_calculated, u64 tstamp, FILE *fp)
{
size_t printed = trace__fprintf_tstamp(trace, tstamp, fp);
- printed += fprintf_duration(duration, fp);
+ printed += fprintf_duration(duration, duration_calculated, fp);
if (trace->multiple_threads) {
if (trace->show_comm)
duration = sample->time - ttrace->entry_time;
- printed = trace__fprintf_entry_head(trace, trace->current, duration, ttrace->entry_time, trace->output);
+ printed = trace__fprintf_entry_head(trace, trace->current, duration, true, ttrace->entry_time, trace->output);
printed += fprintf(trace->output, "%-70s) ...\n", ttrace->entry_str);
ttrace->entry_pending = false;
if (sc->is_exit) {
if (!(trace->duration_filter || trace->summary_only || trace->min_stack)) {
- trace__fprintf_entry_head(trace, thread, 1, ttrace->entry_time, trace->output);
+ trace__fprintf_entry_head(trace, thread, 0, false, ttrace->entry_time, trace->output);
fprintf(trace->output, "%-70s)\n", ttrace->entry_str);
}
} else {
{
long ret;
u64 duration = 0;
+ bool duration_calculated = false;
struct thread *thread;
int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1, callchain_ret = 0;
struct syscall *sc = trace__syscall_info(trace, evsel, id);
duration = sample->time - ttrace->entry_time;
if (trace__filter_duration(trace, duration))
goto out;
+ duration_calculated = true;
} else if (trace->duration_filter)
goto out;
if (trace->summary_only)
goto out;
- trace__fprintf_entry_head(trace, thread, duration, ttrace->entry_time, trace->output);
+ trace__fprintf_entry_head(trace, thread, duration, duration_calculated, ttrace->entry_time, trace->output);
if (ttrace->entry_pending) {
fprintf(trace->output, "%-70s", ttrace->entry_str);
ttrace = thread__priv(thread);
if (!ttrace)
- goto out;
+ goto out_put;
filename_len = strlen(filename);
+ if (filename_len == 0)
+ goto out_put;
if (ttrace->filename.namelen < filename_len) {
char *f = realloc(ttrace->filename.name, filename_len + 1);
if (f == NULL)
- goto out;
+ goto out_put;
ttrace->filename.namelen = filename_len;
ttrace->filename.name = f;
ttrace->filename.pending_open = true;
if (!ttrace->filename.ptr)
- goto out;
+ goto out_put;
entry_str_len = strlen(ttrace->entry_str);
remaining_space = trace__entry_str_size - entry_str_len - 1; /* \0 */
if (remaining_space <= 0)
- goto out;
+ goto out_put;
if (filename_len > (size_t)remaining_space) {
filename += filename_len - remaining_space;
ttrace->filename.ptr = 0;
ttrace->filename.entry_str_pos = 0;
+out_put:
+ thread__put(thread);
out:
return 0;
}
ttrace->runtime_ms += runtime_ms;
trace->runtime_ms += runtime_ms;
+out_put:
thread__put(thread);
return 0;
(pid_t)perf_evsel__intval(evsel, sample, "pid"),
runtime,
perf_evsel__intval(evsel, sample, "vruntime"));
- thread__put(thread);
- return 0;
+ goto out_put;
}
static void bpf_output__printer(enum binary_printer_ops op,
thread__find_addr_location(thread, sample->cpumode, MAP__FUNCTION,
sample->ip, &al);
- trace__fprintf_entry_head(trace, thread, 0, sample->time, trace->output);
+ trace__fprintf_entry_head(trace, thread, 0, true, sample->time, trace->output);
fprintf(trace->output, "%sfault [",
evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ ?
thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
if (thread && thread__is_filtered(thread))
- return 0;
+ goto out;
trace__set_base_time(trace, evsel, sample);
++trace->nr_events;
handler(trace, evsel, event, sample);
}
-
+out:
+ thread__put(thread);
return err;
}
for (i = 0; i < (unsigned int)argc; i++)
rec_argv[j++] = argv[i];
- return cmd_record(j, rec_argv, NULL);
+ return cmd_record(j, rec_argv);
}
static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp);
trace->tool.exit = perf_event__process_exit;
trace->tool.fork = perf_event__process_fork;
trace->tool.attr = perf_event__process_attr;
- trace->tool.tracing_data = perf_event__process_tracing_data;
+ trace->tool.tracing_data = perf_event__process_tracing_data;
trace->tool.build_id = perf_event__process_build_id;
+ trace->tool.namespaces = perf_event__process_namespaces;
trace->tool.ordered_events = true;
trace->tool.ordering_requires_timestamps = true;
return err;
}
-int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_trace(int argc, const char **argv)
{
const char *trace_usage[] = {
"perf trace [<options>] [<command>]",
-#include "util/util.h"
#include "builtin.h"
#include "perf.h"
+#include <linux/compiler.h>
+#include <stdio.h>
-int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused,
- const char *prefix __maybe_unused)
+int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused)
{
printf("perf version %s\n", perf_version_string);
return 0;
#define BUILTIN_H
#include "util/util.h"
-#include "util/strbuf.h"
extern const char perf_usage_string[];
extern const char perf_more_info_string[];
void list_common_cmds_help(void);
const char *help_unknown_cmd(const char *cmd);
-void prune_packed_objects(int);
-int read_line_with_nul(char *buf, int size, FILE *file);
-int check_pager_config(const char *cmd);
-int cmd_annotate(int argc, const char **argv, const char *prefix);
-int cmd_bench(int argc, const char **argv, const char *prefix);
-int cmd_buildid_cache(int argc, const char **argv, const char *prefix);
-int cmd_buildid_list(int argc, const char **argv, const char *prefix);
-int cmd_config(int argc, const char **argv, const char *prefix);
-int cmd_c2c(int argc, const char **argv, const char *prefix);
-int cmd_diff(int argc, const char **argv, const char *prefix);
-int cmd_evlist(int argc, const char **argv, const char *prefix);
-int cmd_help(int argc, const char **argv, const char *prefix);
-int cmd_sched(int argc, const char **argv, const char *prefix);
-int cmd_kallsyms(int argc, const char **argv, const char *prefix);
-int cmd_list(int argc, const char **argv, const char *prefix);
-int cmd_record(int argc, const char **argv, const char *prefix);
-int cmd_report(int argc, const char **argv, const char *prefix);
-int cmd_stat(int argc, const char **argv, const char *prefix);
-int cmd_timechart(int argc, const char **argv, const char *prefix);
-int cmd_top(int argc, const char **argv, const char *prefix);
-int cmd_script(int argc, const char **argv, const char *prefix);
-int cmd_version(int argc, const char **argv, const char *prefix);
-int cmd_probe(int argc, const char **argv, const char *prefix);
-int cmd_kmem(int argc, const char **argv, const char *prefix);
-int cmd_lock(int argc, const char **argv, const char *prefix);
-int cmd_kvm(int argc, const char **argv, const char *prefix);
-int cmd_test(int argc, const char **argv, const char *prefix);
-int cmd_trace(int argc, const char **argv, const char *prefix);
-int cmd_inject(int argc, const char **argv, const char *prefix);
-int cmd_mem(int argc, const char **argv, const char *prefix);
-int cmd_data(int argc, const char **argv, const char *prefix);
-int cmd_ftrace(int argc, const char **argv, const char *prefix);
+int cmd_annotate(int argc, const char **argv);
+int cmd_bench(int argc, const char **argv);
+int cmd_buildid_cache(int argc, const char **argv);
+int cmd_buildid_list(int argc, const char **argv);
+int cmd_config(int argc, const char **argv);
+int cmd_c2c(int argc, const char **argv);
+int cmd_diff(int argc, const char **argv);
+int cmd_evlist(int argc, const char **argv);
+int cmd_help(int argc, const char **argv);
+int cmd_sched(int argc, const char **argv);
+int cmd_kallsyms(int argc, const char **argv);
+int cmd_list(int argc, const char **argv);
+int cmd_record(int argc, const char **argv);
+int cmd_report(int argc, const char **argv);
+int cmd_stat(int argc, const char **argv);
+int cmd_timechart(int argc, const char **argv);
+int cmd_top(int argc, const char **argv);
+int cmd_script(int argc, const char **argv);
+int cmd_version(int argc, const char **argv);
+int cmd_probe(int argc, const char **argv);
+int cmd_kmem(int argc, const char **argv);
+int cmd_lock(int argc, const char **argv);
+int cmd_kvm(int argc, const char **argv);
+int cmd_test(int argc, const char **argv);
+int cmd_trace(int argc, const char **argv);
+int cmd_inject(int argc, const char **argv);
+int cmd_mem(int argc, const char **argv);
+int cmd_data(int argc, const char **argv);
+int cmd_ftrace(int argc, const char **argv);
int find_scripts(char **scripts_array, char **scripts_path_array);
#endif
#!/bin/sh
HEADERS='
+include/uapi/linux/fcntl.h
include/uapi/linux/perf_event.h
+include/uapi/linux/stat.h
include/linux/hash.h
include/uapi/linux/hw_breakpoint.h
arch/x86/include/asm/disabled-features.h
perf-buildid-list mainporcelain common
perf-data mainporcelain common
perf-diff mainporcelain common
+perf-c2c mainporcelain common
perf-config mainporcelain common
perf-evlist mainporcelain common
perf-ftrace mainporcelain common
#include "util/debug.h"
#include <api/fs/fs.h>
#include <api/fs/tracing_path.h>
+#include <errno.h>
#include <pthread.h>
+#include <signal.h>
#include <stdlib.h>
#include <time.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <linux/kernel.h>
const char perf_usage_string[] =
"perf [--version] [--help] [OPTIONS] COMMAND [ARGS]";
struct cmd_struct {
const char *cmd;
- int (*fn)(int, const char **, const char *);
+ int (*fn)(int, const char **);
int option;
};
}
/* returns 0 for "no pager", 1 for "use pager", and -1 for "not specified" */
-int check_pager_config(const char *cmd)
+static int check_pager_config(const char *cmd)
{
int err;
struct pager_config c;
return handled;
}
-static int handle_alias(int *argcp, const char ***argv)
-{
- int envchanged = 0, ret = 0, saved_errno = errno;
- int count, option_count;
- const char **new_argv;
- const char *alias_command;
- char *alias_string;
-
- alias_command = (*argv)[0];
- alias_string = alias_lookup(alias_command);
- if (alias_string) {
- if (alias_string[0] == '!') {
- if (*argcp > 1) {
- struct strbuf buf;
-
- if (strbuf_init(&buf, PATH_MAX) < 0 ||
- strbuf_addstr(&buf, alias_string) < 0 ||
- sq_quote_argv(&buf, (*argv) + 1,
- PATH_MAX) < 0)
- die("Failed to allocate memory.");
- free(alias_string);
- alias_string = buf.buf;
- }
- ret = system(alias_string + 1);
- if (ret >= 0 && WIFEXITED(ret) &&
- WEXITSTATUS(ret) != 127)
- exit(WEXITSTATUS(ret));
- die("Failed to run '%s' when expanding alias '%s'",
- alias_string + 1, alias_command);
- }
- count = split_cmdline(alias_string, &new_argv);
- if (count < 0)
- die("Bad alias.%s string", alias_command);
- option_count = handle_options(&new_argv, &count, &envchanged);
- if (envchanged)
- die("alias '%s' changes environment variables\n"
- "You can use '!perf' in the alias to do this.",
- alias_command);
- memmove(new_argv - option_count, new_argv,
- count * sizeof(char *));
- new_argv -= option_count;
-
- if (count < 1)
- die("empty alias for %s", alias_command);
-
- if (!strcmp(alias_command, new_argv[0]))
- die("recursive alias: %s", alias_command);
-
- new_argv = realloc(new_argv, sizeof(char *) *
- (count + *argcp + 1));
- /* insert after command name */
- memcpy(new_argv + count, *argv + 1, sizeof(char *) * *argcp);
- new_argv[count + *argcp] = NULL;
-
- *argv = new_argv;
- *argcp += count - 1;
-
- ret = 1;
- }
-
- errno = saved_errno;
-
- return ret;
-}
-
#define RUN_SETUP (1<<0)
#define USE_PAGER (1<<1)
{
int status;
struct stat st;
- const char *prefix;
char sbuf[STRERR_BUFSIZE];
- prefix = NULL;
- if (p->option & RUN_SETUP)
- prefix = NULL; /* setup_perf_directory(); */
-
if (use_browser == -1)
use_browser = check_browser_config(p->cmd);
commit_pager_choice();
perf_env__set_cmdline(&perf_env, argc, argv);
- status = p->fn(argc, argv, prefix);
+ status = p->fn(argc, argv);
perf_config__exit();
exit_browser(status);
perf_env__exit(&perf_env);
{
const char *cmd = argv[0];
unsigned int i;
- static const char ext[] = STRIP_EXTENSION;
-
- if (sizeof(ext) > 1) {
- i = strlen(argv[0]) - strlen(ext);
- if (i > 0 && !strcmp(argv[0] + i, ext)) {
- char *argv0 = strdup(argv[0]);
- argv[0] = cmd = argv0;
- argv0[i] = '\0';
- }
- }
/* Turn "perf cmd --help" into "perf help cmd" */
if (argc > 1 && !strcmp(argv[1], "--help")) {
if (status != -ERR_RUN_COMMAND_EXEC) {
if (IS_RUN_COMMAND_ERR(status)) {
do_die:
- die("unable to run '%s'", argv[0]);
+ pr_err("FATAL: unable to run '%s'", argv[0]);
+ status = -128;
}
exit(-status);
}
static int run_argv(int *argcp, const char ***argv)
{
- int done_alias = 0;
+ /* See if it's an internal command */
+ handle_internal_command(*argcp, *argv);
- while (1) {
- /* See if it's an internal command */
- handle_internal_command(*argcp, *argv);
-
- /* .. then try the external ones */
- execv_dashed_external(*argv);
-
- /* It could be an alias -- this works around the insanity
- * of overriding "perf log" with "perf show" by having
- * alias.log = show
- */
- if (done_alias || !handle_alias(argcp, argv))
- break;
- done_alias = 1;
- }
-
- return done_alias;
+ /* .. then try the external ones */
+ execv_dashed_external(*argv);
+ return 0;
}
static void pthread__block_sigwinch(void)
#ifdef HAVE_LIBAUDIT_SUPPORT
setup_path();
argv[0] = "trace";
- return cmd_trace(argc, argv, NULL);
+ return cmd_trace(argc, argv);
#else
fprintf(stderr,
"trace command not available: missing audit-libs devel package at build time.\n");
while (1) {
static int done_help;
- int was_alias = run_argv(&argc, &argv);
+
+ run_argv(&argc, &argv);
if (errno != ENOENT)
break;
- if (was_alias) {
- fprintf(stderr, "Expansion of alias '%s' failed; "
- "'%s' is not a perf-command\n",
- cmd, argv[0]);
- goto out;
- }
if (!done_help) {
cmd = argv[0] = help_unknown_cmd(cmd);
done_help = 1;
bool running_time;
bool full_auxtrace;
bool auxtrace_snapshot_mode;
+ bool record_namespaces;
bool record_switch_events;
bool all_kernel;
bool all_user;
--- /dev/null
+[
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x41",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_XCORE",
+ "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.",
+ "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x81",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EVICTION",
+ "BriefDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.",
+ "PublicDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x44",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_XCORE",
+ "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.",
+ "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x48",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_XCORE",
+ "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.",
+ "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x11",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_M",
+ "BriefDescription": "L3 Lookup read request that access cache and found line in M-state",
+ "PublicDescription": "L3 Lookup read request that access cache and found line in M-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x21",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_M",
+ "BriefDescription": "L3 Lookup write request that access cache and found line in M-state",
+ "PublicDescription": "L3 Lookup write request that access cache and found line in M-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x81",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_M",
+ "BriefDescription": "L3 Lookup any request that access cache and found line in M-state",
+ "PublicDescription": "L3 Lookup any request that access cache and found line in M-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x18",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_I",
+ "BriefDescription": "L3 Lookup read request that access cache and found line in I-state",
+ "PublicDescription": "L3 Lookup read request that access cache and found line in I-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x88",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_I",
+ "BriefDescription": "L3 Lookup any request that access cache and found line in I-state",
+ "PublicDescription": "L3 Lookup any request that access cache and found line in I-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x1f",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_MESI",
+ "BriefDescription": "L3 Lookup read request that access cache and found line in any MESI-state",
+ "PublicDescription": "L3 Lookup read request that access cache and found line in any MESI-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x2f",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_MESI",
+ "BriefDescription": "L3 Lookup write request that access cache and found line in MESI-state",
+ "PublicDescription": "L3 Lookup write request that access cache and found line in MESI-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x8f",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_MESI",
+ "BriefDescription": "L3 Lookup any request that access cache and found line in MESI-state",
+ "PublicDescription": "L3 Lookup any request that access cache and found line in MESI-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x86",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_ES",
+ "BriefDescription": "L3 Lookup any request that access cache and found line in E or S-state",
+ "PublicDescription": "L3 Lookup any request that access cache and found line in E or S-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x16",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_ES",
+ "BriefDescription": "L3 Lookup read request that access cache and found line in E or S-state",
+ "PublicDescription": "L3 Lookup read request that access cache and found line in E or S-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x26",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_ES",
+ "BriefDescription": "L3 Lookup write request that access cache and found line in E or S-state",
+ "PublicDescription": "L3 Lookup write request that access cache and found line in E or S-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "iMPH-U",
+ "EventCode": "0x80",
+ "UMask": "0x01",
+ "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL",
+ "BriefDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from it's allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.",
+ "PublicDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from it's allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.",
+ "Counter": "0,",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "iMPH-U",
+ "EventCode": "0x80",
+ "UMask": "0x02",
+ "EventName": "UNC_ARB_TRK_OCCUPANCY.DRD_DIRECT",
+ "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries that are in DirectData mode. Such entry is defined as valid when it is allocated till data sent to Core (first chunk, IDI0). Applicable for IA Cores' requests in normal case.",
+ "PublicDescription": "Each cycle count number of 'valid' coherent Data Read entries that are in DirectData mode. Such entry is defined as valid when it is allocated till data sent to Core (first chunk, IDI0). Applicable for IA Cores' requests in normal case.",
+ "Counter": "0,",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "iMPH-U",
+ "EventCode": "0x81",
+ "UMask": "0x01",
+ "EventName": "UNC_ARB_TRK_REQUESTS.ALL",
+ "BriefDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
+ "PublicDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "iMPH-U",
+ "EventCode": "0x81",
+ "UMask": "0x02",
+ "EventName": "UNC_ARB_TRK_REQUESTS.DRD_DIRECT",
+ "BriefDescription": "Number of Core coherent Data Read entries allocated in DirectData mode",
+ "PublicDescription": "Number of Core coherent Data Read entries allocated in DirectData mode.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "iMPH-U",
+ "EventCode": "0x81",
+ "UMask": "0x20",
+ "EventName": "UNC_ARB_TRK_REQUESTS.WRITES",
+ "BriefDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.",
+ "PublicDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "iMPH-U",
+ "EventCode": "0x84",
+ "UMask": "0x01",
+ "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL",
+ "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.",
+ "PublicDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "iMPH-U",
+ "EventCode": "0x80",
+ "UMask": "0x01",
+ "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST",
+ "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.;",
+ "PublicDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+ "Counter": "0,",
+ "CounterMask": "1",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "NCU",
+ "EventCode": "0x0",
+ "UMask": "0x01",
+ "EventName": "UNC_CLOCK.SOCKET",
+ "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles",
+ "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.",
+ "Counter": "FIXED",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ }
+]
\ No newline at end of file
[
{
- "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+ "BriefDescription": "Uncore cache clock ticks",
"Counter": "0,1,2,3",
"EventName": "UNC_C_CLOCKTICKS",
"PerPkg": "1",
"Unit": "CBO"
},
{
- "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+ "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)",
"Counter": "0,1,2,3",
"EventCode": "0x34",
"EventName": "UNC_C_LLC_LOOKUP.ANY",
"Unit": "CBO"
},
{
- "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+ "BriefDescription": "M line evictions from LLC (writebacks to memory)",
"Counter": "0,1,2,3",
"EventCode": "0x37",
"EventName": "UNC_C_LLC_VICTIMS.M_STATE",
"Unit": "CBO"
},
{
- "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
+ "BriefDescription": "read requests to home agent",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.READS",
"Unit": "HA"
},
{
- "BriefDescription": "read requests to local home agent. Derived from unc_h_requests.reads_local",
+ "BriefDescription": "read requests to local home agent",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.READS_LOCAL",
"Unit": "HA"
},
{
- "BriefDescription": "read requests to remote home agent. Derived from unc_h_requests.reads_remote",
+ "BriefDescription": "read requests to remote home agent",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.READS_REMOTE",
"Unit": "HA"
},
{
- "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
+ "BriefDescription": "write requests to home agent",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.WRITES",
"Unit": "HA"
},
{
- "BriefDescription": "write requests to local home agent. Derived from unc_h_requests.writes_local",
+ "BriefDescription": "write requests to local home agent",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.WRITES_LOCAL",
"Unit": "HA"
},
{
- "BriefDescription": "write requests to remote home agent. Derived from unc_h_requests.writes_remote",
+ "BriefDescription": "write requests to remote home agent",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.WRITES_REMOTE",
"Unit": "HA"
},
{
- "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously). Derived from unc_h_snoop_resp.rspcnflct",
+ "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously)",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT",
"Unit": "HA"
},
{
- "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
+ "BriefDescription": "M line forwarded from remote cache along with writeback to memory",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
"Unit": "HA"
},
{
- "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
+ "BriefDescription": "M line forwarded from remote cache with no writeback to memory",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
"Unit": "HA"
},
{
- "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
+ "BriefDescription": "Shared line response from remote cache",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPS",
"Unit": "HA"
},
{
- "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
+ "BriefDescription": "Shared line forwarded from remote cache",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
"BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
"Counter": "0,1,2,3",
"EventCode": "0x4",
- "EventName": "UNC_M_CAS_COUNT.RD",
+ "EventName": "LLC_MISSES.MEM_READ",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
"Counter": "0,1,2,3",
"EventCode": "0x4",
- "EventName": "UNC_M_CAS_COUNT.WR",
+ "EventName": "LLC_MISSES.MEM_WRITE",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0xC",
"Unit": "iMC"
},
{
- "BriefDescription": "Memory controller clock ticks. Derived from unc_m_clockticks",
+ "BriefDescription": "Memory controller clock ticks",
"Counter": "0,1,2,3",
- "EventName": "UNC_M_CLOCKTICKS",
+ "EventName": "UNC_M_DCLOCKTICKS",
"PerPkg": "1",
"Unit": "iMC"
},
{
- "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+ "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode",
"Counter": "0,1,2,3",
"EventCode": "0x85",
"EventName": "UNC_M_POWER_CHANNEL_PPD",
- "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+ "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_DCLOCKTICKS) * 100.",
+ "MetricName": "power_channel_ppd %",
"PerPkg": "1",
"Unit": "iMC"
},
{
- "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+ "BriefDescription": "Cycles all ranks are in critical thermal throttle",
"Counter": "0,1,2,3",
"EventCode": "0x86",
"EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
- "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+ "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_DCLOCKTICKS) * 100.",
+ "MetricName": "power_critical_throttle_cycles %",
"PerPkg": "1",
"Unit": "iMC"
},
{
- "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+ "BriefDescription": "Cycles Memory is in self refresh power mode",
"Counter": "0,1,2,3",
"EventCode": "0x43",
"EventName": "UNC_M_POWER_SELF_REFRESH",
- "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+ "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_DCLOCKTICKS) * 100.",
+ "MetricName": "power_self_refresh %",
"PerPkg": "1",
"Unit": "iMC"
},
{
- "BriefDescription": "Pre-charges due to page misses. Derived from unc_m_pre_count.page_miss",
+ "BriefDescription": "Pre-charges due to page misses",
"Counter": "0,1,2,3",
"EventCode": "0x2",
"EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
"Unit": "iMC"
},
{
- "BriefDescription": "Pre-charge for reads. Derived from unc_m_pre_count.rd",
+ "BriefDescription": "Pre-charge for reads",
"Counter": "0,1,2,3",
"EventCode": "0x2",
"EventName": "UNC_M_PRE_COUNT.RD",
"Unit": "iMC"
},
{
- "BriefDescription": "Pre-charge for writes. Derived from unc_m_pre_count.wr",
+ "BriefDescription": "Pre-charge for writes",
"Counter": "0,1,2,3",
"EventCode": "0x2",
"EventName": "UNC_M_PRE_COUNT.WR",
[
{
- "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+ "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events",
"Counter": "0,1,2,3",
"EventName": "UNC_P_CLOCKTICKS",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "C0 and C1. Derived from unc_p_power_state_occupancy.cores_c0",
+ "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
"Filter": "occ_sel=1",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "power_state_occupancy.cores_c0 %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "C3. Derived from unc_p_power_state_occupancy.cores_c3",
+ "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
"Filter": "occ_sel=2",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "power_state_occupancy.cores_c3 %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "C6 and C7. Derived from unc_p_power_state_occupancy.cores_c6",
+ "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events ",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
"Filter": "occ_sel=3",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "power_state_occupancy.cores_c6 %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "External Prochot. Derived from unc_p_prochot_external_cycles",
+ "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip",
"Counter": "0,1,2,3",
"EventCode": "0xA",
"EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
"MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "prochot_external_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Thermal Strongest Upper Limit Cycles. Derived from unc_p_freq_max_limit_thermal_cycles",
+ "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency",
"Counter": "0,1,2,3",
"EventCode": "0x4",
"EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_max_limit_thermal_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "OS Strongest Upper Limit Cycles. Derived from unc_p_freq_max_os_cycles",
+ "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency",
"Counter": "0,1,2,3",
"EventCode": "0x6",
"EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_max_os_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Power Strongest Upper Limit Cycles. Derived from unc_p_freq_max_power_cycles",
+ "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency",
"Counter": "0,1,2,3",
"EventCode": "0x5",
"EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_max_power_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
+ "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency",
"Counter": "0,1,2,3",
"EventCode": "0x74",
"EventName": "UNC_P_FREQ_TRANS_CYCLES",
"MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_trans_cycles %",
"PerPkg": "1",
"Unit": "PCU"
}
[
{
- "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+ "BriefDescription": "Uncore cache clock ticks",
"Counter": "0,1,2,3",
"EventName": "UNC_C_CLOCKTICKS",
"PerPkg": "1",
"Unit": "CBO"
},
{
- "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+ "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)",
"Counter": "0,1,2,3",
"EventCode": "0x34",
"EventName": "UNC_C_LLC_LOOKUP.ANY",
"Unit": "CBO"
},
{
- "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+ "BriefDescription": "M line evictions from LLC (writebacks to memory)",
"Counter": "0,1,2,3",
"EventCode": "0x37",
"EventName": "UNC_C_LLC_VICTIMS.M_STATE",
"Unit": "CBO"
},
{
- "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
+ "BriefDescription": "read requests to home agent",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.READS",
"Unit": "HA"
},
{
- "BriefDescription": "read requests to local home agent. Derived from unc_h_requests.reads_local",
+ "BriefDescription": "read requests to local home agent",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.READS_LOCAL",
"Unit": "HA"
},
{
- "BriefDescription": "read requests to remote home agent. Derived from unc_h_requests.reads_remote",
+ "BriefDescription": "read requests to remote home agent",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.READS_REMOTE",
"Unit": "HA"
},
{
- "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
+ "BriefDescription": "write requests to home agent",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.WRITES",
"Unit": "HA"
},
{
- "BriefDescription": "write requests to local home agent. Derived from unc_h_requests.writes_local",
+ "BriefDescription": "write requests to local home agent",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.WRITES_LOCAL",
"Unit": "HA"
},
{
- "BriefDescription": "write requests to remote home agent. Derived from unc_h_requests.writes_remote",
+ "BriefDescription": "write requests to remote home agent",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.WRITES_REMOTE",
"Unit": "HA"
},
{
- "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously). Derived from unc_h_snoop_resp.rspcnflct",
+ "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously)",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT",
"Unit": "HA"
},
{
- "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
+ "BriefDescription": "M line forwarded from remote cache along with writeback to memory",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
"Unit": "HA"
},
{
- "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
+ "BriefDescription": "M line forwarded from remote cache with no writeback to memory",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
"Unit": "HA"
},
{
- "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
+ "BriefDescription": "Shared line response from remote cache",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPS",
"Unit": "HA"
},
{
- "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
+ "BriefDescription": "Shared line forwarded from remote cache",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
[
{
- "BriefDescription": "QPI clock ticks. Derived from unc_q_clockticks",
+ "BriefDescription": "QPI clock ticks",
"Counter": "0,1,2,3",
"EventCode": "0x14",
"EventName": "UNC_Q_CLOCKTICKS",
{
"BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
"Counter": "0,1,2,3",
- "EventName": "UNC_Q_TxL_FLITS_G0.DATA",
+ "EventName": "QPI_DATA_BANDWIDTH_TX",
"PerPkg": "1",
"ScaleUnit": "8Bytes",
"UMask": "0x2",
{
"BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
"Counter": "0,1,2,3",
- "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
+ "EventName": "QPI_CTL_BANDWIDTH_TX",
"PerPkg": "1",
"ScaleUnit": "8Bytes",
"UMask": "0x4",
"BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
"Counter": "0,1,2,3",
"EventCode": "0x4",
- "EventName": "UNC_M_CAS_COUNT.RD",
+ "EventName": "LLC_MISSES.MEM_READ",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
"Counter": "0,1,2,3",
"EventCode": "0x4",
- "EventName": "UNC_M_CAS_COUNT.WR",
+ "EventName": "LLC_MISSES.MEM_WRITE",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0xC",
"Unit": "iMC"
},
{
- "BriefDescription": "Memory controller clock ticks. Derived from unc_m_clockticks",
+ "BriefDescription": "Memory controller clock ticks",
"Counter": "0,1,2,3",
"EventName": "UNC_M_CLOCKTICKS",
"PerPkg": "1",
"Unit": "iMC"
},
{
- "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+ "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode",
"Counter": "0,1,2,3",
"EventCode": "0x85",
"EventName": "UNC_M_POWER_CHANNEL_PPD",
"MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+ "MetricName": "power_channel_ppd %",
"PerPkg": "1",
"Unit": "iMC"
},
{
- "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+ "BriefDescription": "Cycles all ranks are in critical thermal throttle",
"Counter": "0,1,2,3",
"EventCode": "0x86",
"EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
"MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+ "MetricName": "power_critical_throttle_cycles %",
"PerPkg": "1",
"Unit": "iMC"
},
{
- "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+ "BriefDescription": "Cycles Memory is in self refresh power mode",
"Counter": "0,1,2,3",
"EventCode": "0x43",
"EventName": "UNC_M_POWER_SELF_REFRESH",
"MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+ "MetricName": "power_self_refresh %",
"PerPkg": "1",
"Unit": "iMC"
},
{
- "BriefDescription": "Pre-charges due to page misses. Derived from unc_m_pre_count.page_miss",
+ "BriefDescription": "Pre-charges due to page misses",
"Counter": "0,1,2,3",
"EventCode": "0x2",
"EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
"Unit": "iMC"
},
{
- "BriefDescription": "Pre-charge for reads. Derived from unc_m_pre_count.rd",
+ "BriefDescription": "Pre-charge for reads",
"Counter": "0,1,2,3",
"EventCode": "0x2",
"EventName": "UNC_M_PRE_COUNT.RD",
"Unit": "iMC"
},
{
- "BriefDescription": "Pre-charge for writes. Derived from unc_m_pre_count.wr",
+ "BriefDescription": "Pre-charge for writes",
"Counter": "0,1,2,3",
"EventCode": "0x2",
"EventName": "UNC_M_PRE_COUNT.WR",
[
{
- "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+ "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events",
"Counter": "0,1,2,3",
"EventName": "UNC_P_CLOCKTICKS",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "C0 and C1. Derived from unc_p_power_state_occupancy.cores_c0",
+ "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
"Filter": "occ_sel=1",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "power_state_occupancy.cores_c0 %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "C3. Derived from unc_p_power_state_occupancy.cores_c3",
+ "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
"Filter": "occ_sel=2",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "power_state_occupancy.cores_c3 %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "C6 and C7. Derived from unc_p_power_state_occupancy.cores_c6",
+ "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events ",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
"Filter": "occ_sel=3",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "power_state_occupancy.cores_c6 %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "External Prochot. Derived from unc_p_prochot_external_cycles",
+ "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip",
"Counter": "0,1,2,3",
"EventCode": "0xA",
"EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
"MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "prochot_external_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Thermal Strongest Upper Limit Cycles. Derived from unc_p_freq_max_limit_thermal_cycles",
+ "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency",
"Counter": "0,1,2,3",
"EventCode": "0x4",
"EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_max_limit_thermal_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "OS Strongest Upper Limit Cycles. Derived from unc_p_freq_max_os_cycles",
+ "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency",
"Counter": "0,1,2,3",
"EventCode": "0x6",
"EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_max_os_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Power Strongest Upper Limit Cycles. Derived from unc_p_freq_max_power_cycles",
+ "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency",
"Counter": "0,1,2,3",
"EventCode": "0x5",
"EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_max_power_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
+ "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency",
"Counter": "0,1,2,3",
"EventCode": "0x74",
"EventName": "UNC_P_FREQ_TRANS_CYCLES",
"MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_trans_cycles %",
"PerPkg": "1",
"Unit": "PCU"
}
--- /dev/null
+[
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x21",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EXTERNAL",
+ "BriefDescription": "An external snoop misses in some processor core.",
+ "PublicDescription": "An external snoop misses in some processor core.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x41",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_XCORE",
+ "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.",
+ "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x81",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EVICTION",
+ "BriefDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.",
+ "PublicDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x24",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_EXTERNAL",
+ "BriefDescription": "An external snoop hits a non-modified line in some processor core.",
+ "PublicDescription": "An external snoop hits a non-modified line in some processor core.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x44",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_XCORE",
+ "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.",
+ "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x84",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_EVICTION",
+ "BriefDescription": "A cross-core snoop resulted from L3 Eviction which hits a non-modified line in some processor core.",
+ "PublicDescription": "A cross-core snoop resulted from L3 Eviction which hits a non-modified line in some processor core.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x28",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_EXTERNAL",
+ "BriefDescription": "An external snoop hits a modified line in some processor core.",
+ "PublicDescription": "An external snoop hits a modified line in some processor core.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x48",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_XCORE",
+ "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.",
+ "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x88",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_EVICTION",
+ "BriefDescription": "A cross-core snoop resulted from L3 Eviction which hits a modified line in some processor core.",
+ "PublicDescription": "A cross-core snoop resulted from L3 Eviction which hits a modified line in some processor core.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x11",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_M",
+ "BriefDescription": "L3 Lookup read request that access cache and found line in M-state.",
+ "PublicDescription": "L3 Lookup read request that access cache and found line in M-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x21",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_M",
+ "BriefDescription": "L3 Lookup write request that access cache and found line in M-state.",
+ "PublicDescription": "L3 Lookup write request that access cache and found line in M-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x41",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_M",
+ "BriefDescription": "L3 Lookup external snoop request that access cache and found line in M-state.",
+ "PublicDescription": "L3 Lookup external snoop request that access cache and found line in M-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x81",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_M",
+ "BriefDescription": "L3 Lookup any request that access cache and found line in M-state.",
+ "PublicDescription": "L3 Lookup any request that access cache and found line in M-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x18",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_I",
+ "BriefDescription": "L3 Lookup read request that access cache and found line in I-state.",
+ "PublicDescription": "L3 Lookup read request that access cache and found line in I-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x28",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_I",
+ "BriefDescription": "L3 Lookup write request that access cache and found line in I-state.",
+ "PublicDescription": "L3 Lookup write request that access cache and found line in I-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x48",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_I",
+ "BriefDescription": "L3 Lookup external snoop request that access cache and found line in I-state.",
+ "PublicDescription": "L3 Lookup external snoop request that access cache and found line in I-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x88",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_I",
+ "BriefDescription": "L3 Lookup any request that access cache and found line in I-state.",
+ "PublicDescription": "L3 Lookup any request that access cache and found line in I-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x1f",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_MESI",
+ "BriefDescription": "L3 Lookup read request that access cache and found line in any MESI-state.",
+ "PublicDescription": "L3 Lookup read request that access cache and found line in any MESI-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x2f",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_MESI",
+ "BriefDescription": "L3 Lookup write request that access cache and found line in MESI-state.",
+ "PublicDescription": "L3 Lookup write request that access cache and found line in MESI-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x4f",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_MESI",
+ "BriefDescription": "L3 Lookup external snoop request that access cache and found line in MESI-state.",
+ "PublicDescription": "L3 Lookup external snoop request that access cache and found line in MESI-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x8f",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_MESI",
+ "BriefDescription": "L3 Lookup any request that access cache and found line in MESI-state.",
+ "PublicDescription": "L3 Lookup any request that access cache and found line in MESI-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x86",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_ES",
+ "BriefDescription": "L3 Lookup any request that access cache and found line in E or S-state.",
+ "PublicDescription": "L3 Lookup any request that access cache and found line in E or S-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x46",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_ES",
+ "BriefDescription": "L3 Lookup external snoop request that access cache and found line in E or S-state.",
+ "PublicDescription": "L3 Lookup external snoop request that access cache and found line in E or S-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x16",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_ES",
+ "BriefDescription": "L3 Lookup read request that access cache and found line in E or S-state.",
+ "PublicDescription": "L3 Lookup read request that access cache and found line in E or S-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x26",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_ES",
+ "BriefDescription": "L3 Lookup write request that access cache and found line in E or S-state.",
+ "PublicDescription": "L3 Lookup write request that access cache and found line in E or S-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "iMPH-U",
+ "EventCode": "0x80",
+ "UMask": "0x01",
+ "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL",
+ "BriefDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from it's allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.",
+ "PublicDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from it's allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.",
+ "Counter": "0",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "iMPH-U",
+ "EventCode": "0x81",
+ "UMask": "0x01",
+ "EventName": "UNC_ARB_TRK_REQUESTS.ALL",
+ "BriefDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
+ "PublicDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "iMPH-U",
+ "EventCode": "0x81",
+ "UMask": "0x20",
+ "EventName": "UNC_ARB_TRK_REQUESTS.WRITES",
+ "BriefDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.",
+ "PublicDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "iMPH-U",
+ "EventCode": "0x83",
+ "UMask": "0x01",
+ "EventName": "UNC_ARB_COH_TRK_OCCUPANCY.All",
+ "BriefDescription": "Each cycle count number of valid entries in Coherency Tracker queue from allocation till deallocation. Aperture requests (snoops) appear as NC decoded internally and become coherent (snoop L3, access memory)",
+ "PublicDescription": "Each cycle count number of valid entries in Coherency Tracker queue from allocation till deallocation. Aperture requests (snoops) appear as NC decoded internally and become coherent (snoop L3, access memory).",
+ "Counter": "0",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "iMPH-U",
+ "EventCode": "0x84",
+ "UMask": "0x01",
+ "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL",
+ "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.",
+ "PublicDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "NCU",
+ "EventCode": "0x0",
+ "UMask": "0x01",
+ "EventName": "UNC_CLOCK.SOCKET",
+ "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.",
+ "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.",
+ "Counter": "FIXED",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ }
+]
\ No newline at end of file
[
{
- "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+ "BriefDescription": "Uncore cache clock ticks",
"Counter": "0,1,2,3",
"EventName": "UNC_C_CLOCKTICKS",
"PerPkg": "1",
"Unit": "CBO"
},
{
- "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+ "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)",
"Counter": "0,1,2,3",
"EventCode": "0x34",
"EventName": "UNC_C_LLC_LOOKUP.ANY",
"Unit": "CBO"
},
{
- "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+ "BriefDescription": "M line evictions from LLC (writebacks to memory)",
"Counter": "0,1,2,3",
"EventCode": "0x37",
"EventName": "UNC_C_LLC_VICTIMS.M_STATE",
"Unit": "CBO"
},
{
- "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
+ "BriefDescription": "read requests to home agent",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.READS",
"Unit": "HA"
},
{
- "BriefDescription": "read requests to local home agent. Derived from unc_h_requests.reads_local",
+ "BriefDescription": "read requests to local home agent",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.READS_LOCAL",
"Unit": "HA"
},
{
- "BriefDescription": "read requests to remote home agent. Derived from unc_h_requests.reads_remote",
+ "BriefDescription": "read requests to remote home agent",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.READS_REMOTE",
"Unit": "HA"
},
{
- "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
+ "BriefDescription": "write requests to home agent",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.WRITES",
"Unit": "HA"
},
{
- "BriefDescription": "write requests to local home agent. Derived from unc_h_requests.writes_local",
+ "BriefDescription": "write requests to local home agent",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.WRITES_LOCAL",
"Unit": "HA"
},
{
- "BriefDescription": "write requests to remote home agent. Derived from unc_h_requests.writes_remote",
+ "BriefDescription": "write requests to remote home agent",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.WRITES_REMOTE",
"Unit": "HA"
},
{
- "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously). Derived from unc_h_snoop_resp.rspcnflct",
+ "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously)",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT",
"Unit": "HA"
},
{
- "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
+ "BriefDescription": "M line forwarded from remote cache along with writeback to memory",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
"Unit": "HA"
},
{
- "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
+ "BriefDescription": "M line forwarded from remote cache with no writeback to memory",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
"Unit": "HA"
},
{
- "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
+ "BriefDescription": "Shared line response from remote cache",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPS",
"Unit": "HA"
},
{
- "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
+ "BriefDescription": "Shared line forwarded from remote cache",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
[
{
- "BriefDescription": "QPI clock ticks. Derived from unc_q_clockticks",
+ "BriefDescription": "QPI clock ticks",
"Counter": "0,1,2,3",
"EventCode": "0x14",
"EventName": "UNC_Q_CLOCKTICKS",
{
"BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
"Counter": "0,1,2,3",
- "EventName": "UNC_Q_TxL_FLITS_G0.DATA",
+ "EventName": "QPI_DATA_BANDWIDTH_TX",
"PerPkg": "1",
"ScaleUnit": "8Bytes",
"UMask": "0x2",
{
"BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
"Counter": "0,1,2,3",
- "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
+ "EventName": "QPI_CTL_BANDWIDTH_TX",
"PerPkg": "1",
"ScaleUnit": "8Bytes",
"UMask": "0x4",
"BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
"Counter": "0,1,2,3",
"EventCode": "0x4",
- "EventName": "UNC_M_CAS_COUNT.RD",
+ "EventName": "LLC_MISSES.MEM_READ",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
"Counter": "0,1,2,3",
"EventCode": "0x4",
- "EventName": "UNC_M_CAS_COUNT.WR",
+ "EventName": "LLC_MISSES.MEM_WRITE",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0xC",
"Unit": "iMC"
},
{
- "BriefDescription": "Memory controller clock ticks. Derived from unc_m_clockticks",
+ "BriefDescription": "Memory controller clock ticks",
"Counter": "0,1,2,3",
"EventName": "UNC_M_CLOCKTICKS",
"PerPkg": "1",
"Unit": "iMC"
},
{
- "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+ "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode",
"Counter": "0,1,2,3",
"EventCode": "0x85",
"EventName": "UNC_M_POWER_CHANNEL_PPD",
"MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+ "MetricName": "power_channel_ppd %",
"PerPkg": "1",
"Unit": "iMC"
},
{
- "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+ "BriefDescription": "Cycles all ranks are in critical thermal throttle",
"Counter": "0,1,2,3",
"EventCode": "0x86",
"EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
"MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+ "MetricName": "power_critical_throttle_cycles %",
"PerPkg": "1",
"Unit": "iMC"
},
{
- "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+ "BriefDescription": "Cycles Memory is in self refresh power mode",
"Counter": "0,1,2,3",
"EventCode": "0x43",
"EventName": "UNC_M_POWER_SELF_REFRESH",
"MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+ "MetricName": "power_self_refresh %",
"PerPkg": "1",
"Unit": "iMC"
},
{
- "BriefDescription": "Pre-charges due to page misses. Derived from unc_m_pre_count.page_miss",
+ "BriefDescription": "Pre-charges due to page misses",
"Counter": "0,1,2,3",
"EventCode": "0x2",
"EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
"Unit": "iMC"
},
{
- "BriefDescription": "Pre-charge for reads. Derived from unc_m_pre_count.rd",
+ "BriefDescription": "Pre-charge for reads",
"Counter": "0,1,2,3",
"EventCode": "0x2",
"EventName": "UNC_M_PRE_COUNT.RD",
"Unit": "iMC"
},
{
- "BriefDescription": "Pre-charge for writes. Derived from unc_m_pre_count.wr",
+ "BriefDescription": "Pre-charge for writes",
"Counter": "0,1,2,3",
"EventCode": "0x2",
"EventName": "UNC_M_PRE_COUNT.WR",
[
{
- "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+ "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events",
"Counter": "0,1,2,3",
"EventName": "UNC_P_CLOCKTICKS",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "C0 and C1. Derived from unc_p_power_state_occupancy.cores_c0",
+ "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
"Filter": "occ_sel=1",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "power_state_occupancy.cores_c0 %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "C3. Derived from unc_p_power_state_occupancy.cores_c3",
+ "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
"Filter": "occ_sel=2",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "power_state_occupancy.cores_c3 %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "C6 and C7. Derived from unc_p_power_state_occupancy.cores_c6",
+ "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events ",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
"Filter": "occ_sel=3",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "power_state_occupancy.cores_c6 %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "External Prochot. Derived from unc_p_prochot_external_cycles",
+ "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip",
"Counter": "0,1,2,3",
"EventCode": "0xA",
"EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
"MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "prochot_external_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Thermal Strongest Upper Limit Cycles. Derived from unc_p_freq_max_limit_thermal_cycles",
+ "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency",
"Counter": "0,1,2,3",
"EventCode": "0x4",
"EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_max_limit_thermal_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "OS Strongest Upper Limit Cycles. Derived from unc_p_freq_max_os_cycles",
+ "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency",
"Counter": "0,1,2,3",
"EventCode": "0x6",
"EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_max_os_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Power Strongest Upper Limit Cycles. Derived from unc_p_freq_max_power_cycles",
+ "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency",
"Counter": "0,1,2,3",
"EventCode": "0x5",
"EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_max_power_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
+ "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency",
"Counter": "0,1,2,3",
"EventCode": "0x74",
"EventName": "UNC_P_FREQ_TRANS_CYCLES",
"MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_trans_cycles %",
"PerPkg": "1",
"Unit": "PCU"
}
--- /dev/null
+[
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x01",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.MISS",
+ "BriefDescription": "A snoop misses in some processor core.",
+ "PublicDescription": "A snoop misses in some processor core.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x02",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.INVAL",
+ "BriefDescription": "A snoop invalidates a non-modified line in some processor core.",
+ "PublicDescription": "A snoop invalidates a non-modified line in some processor core.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x04",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.HIT",
+ "BriefDescription": "A snoop hits a non-modified line in some processor core.",
+ "PublicDescription": "A snoop hits a non-modified line in some processor core.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x08",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.HITM",
+ "BriefDescription": "A snoop hits a modified line in some processor core.",
+ "PublicDescription": "A snoop hits a modified line in some processor core.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x10",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.INVAL_M",
+ "BriefDescription": "A snoop invalidates a modified line in some processor core.",
+ "PublicDescription": "A snoop invalidates a modified line in some processor core.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x20",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.EXTERNAL_FILTER",
+ "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to external snoop request.",
+ "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to external snoop request.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x40",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.XCORE_FILTER",
+ "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to processor core memory request.",
+ "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to processor core memory request.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x80",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.EVICTION_FILTER",
+ "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to LLC eviction.",
+ "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to LLC eviction.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x01",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.M",
+ "BriefDescription": "LLC lookup request that access cache and found line in M-state.",
+ "PublicDescription": "LLC lookup request that access cache and found line in M-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x02",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.E",
+ "BriefDescription": "LLC lookup request that access cache and found line in E-state.",
+ "PublicDescription": "LLC lookup request that access cache and found line in E-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x04",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.S",
+ "BriefDescription": "LLC lookup request that access cache and found line in S-state.",
+ "PublicDescription": "LLC lookup request that access cache and found line in S-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x08",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.I",
+ "BriefDescription": "LLC lookup request that access cache and found line in I-state.",
+ "PublicDescription": "LLC lookup request that access cache and found line in I-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x10",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_FILTER",
+ "BriefDescription": "Filter on processor core initiated cacheable read requests.",
+ "PublicDescription": "Filter on processor core initiated cacheable read requests.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x20",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_FILTER",
+ "BriefDescription": "Filter on processor core initiated cacheable write requests.",
+ "PublicDescription": "Filter on processor core initiated cacheable write requests.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x40",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_FILTER",
+ "BriefDescription": "Filter on external snoop requests.",
+ "PublicDescription": "Filter on external snoop requests.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x80",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_REQUEST_FILTER",
+ "BriefDescription": "Filter on any IRQ or IPQ initiated requests including uncacheable, non-coherent requests.",
+ "PublicDescription": "Filter on any IRQ or IPQ initiated requests including uncacheable, non-coherent requests.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "ARB",
+ "EventCode": "0x80",
+ "UMask": "0x01",
+ "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL",
+ "BriefDescription": "Counts cycles weighted by the number of requests waiting for data returning from the memory controller. Accounts for coherent and non-coherent requests initiated by IA cores, processor graphic units, or LLC.",
+ "PublicDescription": "Counts cycles weighted by the number of requests waiting for data returning from the memory controller. Accounts for coherent and non-coherent requests initiated by IA cores, processor graphic units, or LLC.",
+ "Counter": "0",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "ARB",
+ "EventCode": "0x81",
+ "UMask": "0x01",
+ "EventName": "UNC_ARB_TRK_REQUESTS.ALL",
+ "BriefDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC.",
+ "PublicDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "ARB",
+ "EventCode": "0x81",
+ "UMask": "0x20",
+ "EventName": "UNC_ARB_TRK_REQUESTS.WRITES",
+ "BriefDescription": "Counts the number of allocated write entries, include full, partial, and LLC evictions.",
+ "PublicDescription": "Counts the number of allocated write entries, include full, partial, and LLC evictions.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "ARB",
+ "EventCode": "0x81",
+ "UMask": "0x80",
+ "EventName": "UNC_ARB_TRK_REQUESTS.EVICTIONS",
+ "BriefDescription": "Counts the number of LLC evictions allocated.",
+ "PublicDescription": "Counts the number of LLC evictions allocated.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "ARB",
+ "EventCode": "0x83",
+ "UMask": "0x01",
+ "EventName": "UNC_ARB_COH_TRK_OCCUPANCY.ALL",
+ "BriefDescription": "Cycles weighted by number of requests pending in Coherency Tracker.",
+ "PublicDescription": "Cycles weighted by number of requests pending in Coherency Tracker.",
+ "Counter": "0",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "ARB",
+ "EventCode": "0x84",
+ "UMask": "0x01",
+ "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL",
+ "BriefDescription": "Number of requests allocated in Coherency Tracker.",
+ "PublicDescription": "Number of requests allocated in Coherency Tracker.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "ARB",
+ "EventCode": "0x80",
+ "UMask": "0x01",
+ "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST",
+ "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+ "PublicDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+ "Counter": "0,1",
+ "CounterMask": "1",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "ARB",
+ "EventCode": "0x80",
+ "UMask": "0x01",
+ "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_OVER_HALF_FULL",
+ "BriefDescription": "Cycles with at least half of the requests outstanding are waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+ "PublicDescription": "Cycles with at least half of the requests outstanding are waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+ "Counter": "0,1",
+ "CounterMask": "10",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "ARB",
+ "EventCode": "0x0",
+ "UMask": "0x01",
+ "EventName": "UNC_CLOCK.SOCKET",
+ "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.",
+ "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.",
+ "Counter": "Fixed",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x06",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.ES",
+ "BriefDescription": "LLC lookup request that access cache and found line in E-state or S-state.",
+ "PublicDescription": "LLC lookup request that access cache and found line in E-state or S-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ }
+]
\ No newline at end of file
[
{
- "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+ "BriefDescription": "Uncore cache clock ticks",
"Counter": "0,1,2,3",
"EventName": "UNC_C_CLOCKTICKS",
"PerPkg": "1",
"Unit": "CBO"
},
{
- "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+ "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)",
"Counter": "0,1",
"EventCode": "0x34",
"EventName": "UNC_C_LLC_LOOKUP.ANY",
"Unit": "CBO"
},
{
- "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+ "BriefDescription": "M line evictions from LLC (writebacks to memory)",
"Counter": "0,1",
"EventCode": "0x37",
"EventName": "UNC_C_LLC_VICTIMS.M_STATE",
"Unit": "CBO"
},
{
- "BriefDescription": "Occupancy for all LLC misses that are addressed to local memory. Derived from unc_c_tor_occupancy.miss_local",
+ "BriefDescription": "Occupancy for all LLC misses that are addressed to local memory",
"EventCode": "0x36",
"EventName": "UNC_C_TOR_OCCUPANCY.MISS_LOCAL",
"PerPkg": "1",
"Unit": "CBO"
},
{
- "BriefDescription": "Occupancy for all LLC misses that are addressed to remote memory. Derived from unc_c_tor_occupancy.miss_remote",
+ "BriefDescription": "Occupancy for all LLC misses that are addressed to remote memory",
"EventCode": "0x36",
"EventName": "UNC_C_TOR_OCCUPANCY.MISS_REMOTE",
"PerPkg": "1",
"Unit": "CBO"
},
{
- "BriefDescription": "Read requests to home agent. Derived from unc_h_requests.reads",
+ "BriefDescription": "Read requests to home agent",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.READS",
"Unit": "HA"
},
{
- "BriefDescription": "Write requests to home agent. Derived from unc_h_requests.writes",
+ "BriefDescription": "Write requests to home agent",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.WRITES",
"Unit": "HA"
},
{
- "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
+ "BriefDescription": "M line forwarded from remote cache along with writeback to memory",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
"Unit": "HA"
},
{
- "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
+ "BriefDescription": "M line forwarded from remote cache with no writeback to memory",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
"Unit": "HA"
},
{
- "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
+ "BriefDescription": "Shared line response from remote cache",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPS",
"Unit": "HA"
},
{
- "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
+ "BriefDescription": "Shared line forwarded from remote cache",
"Counter": "0,1,2,3",
"EventCode": "0x21",
"EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
[
{
- "BriefDescription": "QPI clock ticks. Use to get percentages for QPI cycles events. Derived from unc_q_clockticks",
+ "BriefDescription": "QPI clock ticks. Use to get percentages for QPI cycles events",
"Counter": "0,1,2,3",
"EventCode": "0x14",
"EventName": "UNC_Q_CLOCKTICKS",
"Unit": "QPI LL"
},
{
- "BriefDescription": "Cycles where receiving QPI link is in half-width mode. Derived from unc_q_rxl0p_power_cycles",
+ "BriefDescription": "Cycles where receiving QPI link is in half-width mode",
"Counter": "0,1,2,3",
"EventCode": "0x10",
"EventName": "UNC_Q_RxL0P_POWER_CYCLES",
"MetricExpr": "(UNC_Q_RxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+ "MetricName": "rxl0p_power_cycles %",
"PerPkg": "1",
"Unit": "QPI LL"
},
{
- "BriefDescription": "Cycles where transmitting QPI link is in half-width mode. Derived from unc_q_txl0p_power_cycles",
+ "BriefDescription": "Cycles where transmitting QPI link is in half-width mode",
"Counter": "0,1,2,3",
"EventCode": "0xd",
"EventName": "UNC_Q_TxL0P_POWER_CYCLES",
"MetricExpr": "(UNC_Q_TxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+ "MetricName": "txl0p_power_cycles %",
"PerPkg": "1",
"Unit": "QPI LL"
},
{
- "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
+ "BriefDescription": "Number of data flits transmitted ",
"Counter": "0,1,2,3",
"EventName": "UNC_Q_TxL_FLITS_G0.DATA",
"PerPkg": "1",
"Unit": "QPI LL"
},
{
- "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
+ "BriefDescription": "Number of non data (control) flits transmitted ",
"Counter": "0,1,2,3",
"EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
"PerPkg": "1",
[
{
- "BriefDescription": "Memory page activates for reads and writes. Derived from unc_m_act_count.rd",
+ "BriefDescription": "Memory page activates for reads and writes",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_M_ACT_COUNT.RD",
"BriefDescription": "Read requests to memory controller. Derived from unc_m_cas_count.rd",
"Counter": "0,1,2,3",
"EventCode": "0x4",
- "EventName": "UNC_M_CAS_COUNT.RD",
+ "EventName": "LLC_MISSES.MEM_READ",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0x3",
"BriefDescription": "Write requests to memory controller. Derived from unc_m_cas_count.wr",
"Counter": "0,1,2,3",
"EventCode": "0x4",
- "EventName": "UNC_M_CAS_COUNT.WR",
+ "EventName": "LLC_MISSES.MEM_WRITE",
"PerPkg": "1",
"ScaleUnit": "64Bytes",
"UMask": "0xC",
"Unit": "iMC"
},
{
- "BriefDescription": "Memory controller clock ticks. Use to generate percentages for memory controller CYCLES events. Derived from unc_m_clockticks",
+ "BriefDescription": "Memory controller clock ticks. Use to generate percentages for memory controller CYCLES events",
"Counter": "0,1,2,3",
"EventName": "UNC_M_CLOCKTICKS",
"PerPkg": "1",
"Unit": "iMC"
},
{
- "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+ "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode",
"Counter": "0,1,2,3",
"EventCode": "0x85",
"EventName": "UNC_M_POWER_CHANNEL_PPD",
"MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+ "MetricName": "power_channel_ppd %",
"PerPkg": "1",
"Unit": "iMC"
},
{
- "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+ "BriefDescription": "Cycles all ranks are in critical thermal throttle",
"Counter": "0,1,2,3",
"EventCode": "0x86",
"EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
"MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+ "MetricName": "power_critical_throttle_cycles %",
"PerPkg": "1",
"Unit": "iMC"
},
{
- "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+ "BriefDescription": "Cycles Memory is in self refresh power mode",
"Counter": "0,1,2,3",
"EventCode": "0x43",
"EventName": "UNC_M_POWER_SELF_REFRESH",
"MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+ "MetricName": "power_self_refresh %",
"PerPkg": "1",
"Unit": "iMC"
},
{
- "BriefDescription": "Memory page conflicts. Derived from unc_m_pre_count.page_miss",
+ "BriefDescription": "Memory page conflicts",
"Counter": "0,1,2,3",
"EventCode": "0x2",
"EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
[
{
- "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+ "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events",
"Counter": "0,1,2,3",
"EventName": "UNC_P_CLOCKTICKS",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles",
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency",
"Counter": "0,1,2,3",
"EventCode": "0xb",
"EventName": "UNC_P_FREQ_BAND0_CYCLES",
"MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_band0_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles",
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency",
"Counter": "0,1,2,3",
"EventCode": "0xc",
"EventName": "UNC_P_FREQ_BAND1_CYCLES",
"MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_band1_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles",
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency",
"Counter": "0,1,2,3",
"EventCode": "0xd",
"EventName": "UNC_P_FREQ_BAND2_CYCLES",
"MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_band2_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles",
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency",
"Counter": "0,1,2,3",
"EventCode": "0xe",
"EventName": "UNC_P_FREQ_BAND3_CYCLES",
"MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_band3_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
"EventName": "UNC_P_FREQ_BAND0_TRANSITIONS",
"Filter": "edge=1",
"MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_band0_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
"EventName": "UNC_P_FREQ_BAND1_TRANSITIONS",
"Filter": "edge=1",
"MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_band1_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
"EventName": "UNC_P_FREQ_BAND2_TRANSITIONS",
"Filter": "edge=1",
"MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_band2_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
"EventName": "UNC_P_FREQ_BAND3_TRANSITIONS",
"Filter": "edge=1",
"MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_band3_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c0",
+ "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
"Filter": "occ_sel=1",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "power_state_occupancy.cores_c0 %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c3",
+ "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
"Filter": "occ_sel=2",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "power_state_occupancy.cores_c3 %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c6",
+ "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events ",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
"Filter": "occ_sel=3",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "power_state_occupancy.cores_c6 %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip. Derived from unc_p_prochot_external_cycles",
+ "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip",
"Counter": "0,1,2,3",
"EventCode": "0xa",
"EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
"MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "prochot_external_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Counts the number of cycles when thermal conditions are the upper limit on frequency. This is related to the THERMAL_THROTTLE CYCLES_ABOVE_TEMP event, which always counts cycles when we are above the thermal temperature. This event (STRONGEST_UPPER_LIMIT) is sampled at the output of the algorithm that determines the actual frequency, while THERMAL_THROTTLE looks at the input. Derived from unc_p_freq_max_limit_thermal_cycles",
+ "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency",
"Counter": "0,1,2,3",
"EventCode": "0x4",
"EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_max_limit_thermal_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency. Derived from unc_p_freq_max_os_cycles",
+ "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency",
"Counter": "0,1,2,3",
"EventCode": "0x6",
"EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_max_os_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency. Derived from unc_p_freq_max_power_cycles",
+ "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency",
"Counter": "0,1,2,3",
"EventCode": "0x5",
"EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_max_power_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency. Derived from unc_p_freq_max_current_cycles",
+ "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency",
"Counter": "0,1,2,3",
"EventCode": "0x7",
"EventName": "UNC_P_FREQ_MAX_CURRENT_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_CURRENT_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_max_current_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Counts the number of cycles when the system is changing frequency. This can not be filtered by thread ID. One can also use it with the occupancy counter that monitors number of threads in C0 to estimate the performance impact that frequency transitions had on the system. Derived from unc_p_freq_trans_cycles",
+ "BriefDescription": "Cycles spent changing Frequency",
"Counter": "0,1,2,3",
"EventCode": "0x60",
"EventName": "UNC_P_FREQ_TRANS_CYCLES",
"MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_trans_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
"EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES",
"Filter": "filter_band0=1200",
"MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_ge_1200mhz_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
"EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES",
"Filter": "filter_band1=2000",
"MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_ge_2000mhz_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
"EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES",
"Filter": "filter_band2=3000",
"MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_ge_3000mhz_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
"EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES",
"Filter": "filter_band3=4000",
"MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_ge_4000mhz_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
"EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS",
"Filter": "edge=1,filter_band0=1200",
"MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_ge_1200mhz_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
"EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS",
"Filter": "edge=1,filter_band1=2000",
"MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_ge_2000mhz_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
"EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS",
"Filter": "edge=1,filter_band2=4000",
"MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_ge_3000mhz_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
"EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS",
"Filter": "edge=1,filter_band3=4000",
"MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_ge_4000mhz_cycles %",
"PerPkg": "1",
"Unit": "PCU"
}
[
{
- "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+ "BriefDescription": "Uncore cache clock ticks",
"Counter": "0,1,2,3",
"EventName": "UNC_C_CLOCKTICKS",
"PerPkg": "1",
"Unit": "CBO"
},
{
- "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+ "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch)",
"Counter": "0,1",
"EventCode": "0x34",
"EventName": "UNC_C_LLC_LOOKUP.ANY",
"Unit": "CBO"
},
{
- "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+ "BriefDescription": "M line evictions from LLC (writebacks to memory)",
"Counter": "0,1",
"EventCode": "0x37",
"EventName": "UNC_C_LLC_VICTIMS.M_STATE",
"Unit": "CBO"
},
{
- "BriefDescription": "Occupancy counter for all LLC misses; we divide this by UNC_C_CLOCKTICKS to get average Q depth. Derived from unc_c_tor_occupancy.miss_all",
+ "BriefDescription": "Occupancy counter for all LLC misses; we divide this by UNC_C_CLOCKTICKS to get average Q depth",
"EventCode": "0x36",
"EventName": "UNC_C_TOR_OCCUPANCY.MISS_ALL",
"Filter": "filter_opc=0x182",
"MetricExpr": "(UNC_C_TOR_OCCUPANCY.MISS_ALL / UNC_C_CLOCKTICKS) * 100.",
+ "MetricName": "tor_occupancy.miss_all %",
"PerPkg": "1",
"UMask": "0xa",
"Unit": "CBO"
"Unit": "CBO"
},
{
- "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
+ "BriefDescription": "read requests to home agent",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.READS",
"Unit": "HA"
},
{
- "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
+ "BriefDescription": "write requests to home agent",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_H_REQUESTS.WRITES",
[
{
- "BriefDescription": "QPI clock ticks. Used to get percentages of QPI cycles events. Derived from unc_q_clockticks",
+ "BriefDescription": "QPI clock ticks. Used to get percentages of QPI cycles events",
"Counter": "0,1,2,3",
"EventCode": "0x14",
"EventName": "UNC_Q_CLOCKTICKS",
"Unit": "QPI LL"
},
{
- "BriefDescription": "Cycles where receiving QPI link is in half-width mode. Derived from unc_q_rxl0p_power_cycles",
+ "BriefDescription": "Cycles where receiving QPI link is in half-width mode",
"Counter": "0,1,2,3",
"EventCode": "0x10",
"EventName": "UNC_Q_RxL0P_POWER_CYCLES",
"MetricExpr": "(UNC_Q_RxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+ "MetricName": "rxl0p_power_cycles %",
"PerPkg": "1",
"Unit": "QPI LL"
},
{
- "BriefDescription": "Cycles where transmitting QPI link is in half-width mode. Derived from unc_q_txl0p_power_cycles",
+ "BriefDescription": "Cycles where transmitting QPI link is in half-width mode",
"Counter": "0,1,2,3",
"EventCode": "0xd",
"EventName": "UNC_Q_TxL0P_POWER_CYCLES",
"MetricExpr": "(UNC_Q_TxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+ "MetricName": "txl0p_power_cycles %",
"PerPkg": "1",
"Unit": "QPI LL"
},
{
- "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
+ "BriefDescription": "Number of data flits transmitted ",
"Counter": "0,1,2,3",
"EventName": "UNC_Q_TxL_FLITS_G0.DATA",
"PerPkg": "1",
"Unit": "QPI LL"
},
{
- "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
+ "BriefDescription": "Number of non data (control) flits transmitted ",
"Counter": "0,1,2,3",
"EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
"PerPkg": "1",
[
{
- "BriefDescription": "Memory page activates. Derived from unc_m_act_count",
+ "BriefDescription": "Memory page activates",
"Counter": "0,1,2,3",
"EventCode": "0x1",
"EventName": "UNC_M_ACT_COUNT",
"BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
"Counter": "0,1,2,3",
"EventCode": "0x4",
- "EventName": "UNC_M_CAS_COUNT.RD",
+ "EventName": "LLC_MISSES.MEM_READ",
"PerPkg": "1",
"UMask": "0x3",
"Unit": "iMC"
"BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
"Counter": "0,1,2,3",
"EventCode": "0x4",
- "EventName": "UNC_M_CAS_COUNT.WR",
+ "EventName": "LLC_MISSES.MEM_WRITE",
"PerPkg": "1",
"UMask": "0xc",
"Unit": "iMC"
},
{
- "BriefDescription": "Memory controller clock ticks. Used to get percentages of memory controller cycles events. Derived from unc_m_clockticks",
+ "BriefDescription": "Memory controller clock ticks. Used to get percentages of memory controller cycles events",
"Counter": "0,1,2,3",
"EventName": "UNC_M_CLOCKTICKS",
"PerPkg": "1",
"Unit": "iMC"
},
{
- "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+ "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode",
"Counter": "0,1,2,3",
"EventCode": "0x85",
"EventName": "UNC_M_POWER_CHANNEL_PPD",
"MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+ "MetricName": "power_channel_ppd %",
"PerPkg": "1",
"Unit": "iMC"
},
{
- "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+ "BriefDescription": "Cycles all ranks are in critical thermal throttle",
"Counter": "0,1,2,3",
"EventCode": "0x86",
"EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
"MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+ "MetricName": "power_critical_throttle_cycles %",
"PerPkg": "1",
"Unit": "iMC"
},
{
- "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+ "BriefDescription": "Cycles Memory is in self refresh power mode",
"Counter": "0,1,2,3",
"EventCode": "0x43",
"EventName": "UNC_M_POWER_SELF_REFRESH",
"MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+ "MetricName": "power_self_refresh %",
"PerPkg": "1",
"Unit": "iMC"
},
{
- "BriefDescription": "Memory page conflicts. Derived from unc_m_pre_count.page_miss",
+ "BriefDescription": "Memory page conflicts",
"Counter": "0,1,2,3",
"EventCode": "0x2",
"EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
"Unit": "iMC"
},
{
- "BriefDescription": "Occupancy counter for memory read queue. Derived from unc_m_rpq_occupancy",
+ "BriefDescription": "Occupancy counter for memory read queue",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_M_RPQ_OCCUPANCY",
[
{
- "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+ "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events",
"Counter": "0,1,2,3",
"EventName": "UNC_P_CLOCKTICKS",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles",
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band0=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency",
"Counter": "0,1,2,3",
"EventCode": "0xb",
"EventName": "UNC_P_FREQ_BAND0_CYCLES",
"MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_band0_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles",
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band1=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency",
"Counter": "0,1,2,3",
"EventCode": "0xc",
"EventName": "UNC_P_FREQ_BAND1_CYCLES",
"MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_band1_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles",
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band2=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency",
"Counter": "0,1,2,3",
"EventCode": "0xd",
"EventName": "UNC_P_FREQ_BAND2_CYCLES",
"MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_band2_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles",
+ "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter. (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency",
"Counter": "0,1,2,3",
"EventCode": "0xe",
"EventName": "UNC_P_FREQ_BAND3_CYCLES",
"MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_band3_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
"EventName": "UNC_P_FREQ_BAND0_TRANSITIONS",
"Filter": "edge=1",
"MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_band0_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
"EventName": "UNC_P_FREQ_BAND1_TRANSITIONS",
"Filter": "edge=1",
"MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_band1_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
"EventName": "UNC_P_FREQ_BAND2_TRANSITIONS",
"Filter": "edge=1",
"MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_band2_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
"EventName": "UNC_P_FREQ_BAND3_TRANSITIONS",
"Filter": "edge=1",
"MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_band3_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c0",
+ "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
"Filter": "occ_sel=1",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "power_state_occupancy.cores_c0 %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c3",
+ "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
"Filter": "occ_sel=2",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "power_state_occupancy.cores_c3 %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events . Derived from unc_p_power_state_occupancy.cores_c6",
+ "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6. It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events ",
"Counter": "0,1,2,3",
"EventCode": "0x80",
"EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
"Filter": "occ_sel=3",
"MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "power_state_occupancy.cores_c6 %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip. Derived from unc_p_prochot_external_cycles",
+ "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip",
"Counter": "0,1,2,3",
"EventCode": "0xa",
"EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
"MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "prochot_external_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency. Derived from unc_p_freq_max_limit_thermal_cycles",
+ "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency",
"Counter": "0,1,2,3",
"EventCode": "0x4",
"EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_max_limit_thermal_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency. Derived from unc_p_freq_max_os_cycles",
+ "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency",
"Counter": "0,1,2,3",
"EventCode": "0x6",
"EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_max_os_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency. Derived from unc_p_freq_max_power_cycles",
+ "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency",
"Counter": "0,1,2,3",
"EventCode": "0x5",
"EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_max_power_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency. Derived from unc_p_freq_max_current_cycles",
+ "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency",
"Counter": "0,1,2,3",
"EventCode": "0x7",
"EventName": "UNC_P_FREQ_MAX_CURRENT_CYCLES",
"MetricExpr": "(UNC_P_FREQ_MAX_CURRENT_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_max_current_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
{
- "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
+ "BriefDescription": "Cycles spent changing Frequency",
"Counter": "0,1,2,3",
"EventName": "UNC_P_FREQ_TRANS_CYCLES",
"MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_trans_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
"EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES",
"Filter": "filter_band0=1200",
"MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_ge_1200mhz_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
"EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES",
"Filter": "filter_band1=2000",
"MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_ge_2000mhz_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
"EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES",
"Filter": "filter_band2=3000",
"MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_ge_3000mhz_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
"EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES",
"Filter": "filter_band3=4000",
"MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_ge_4000mhz_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
"EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS",
"Filter": "edge=1,filter_band0=1200",
"MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_ge_1200mhz_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
"EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS",
"Filter": "edge=1,filter_band1=2000",
"MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_ge_2000mhz_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
"EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS",
"Filter": "edge=1,filter_band2=4000",
"MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_ge_3000mhz_cycles %",
"PerPkg": "1",
"Unit": "PCU"
},
"EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS",
"Filter": "edge=1,filter_band3=4000",
"MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+ "MetricName": "freq_ge_4000mhz_cycles %",
"PerPkg": "1",
"Unit": "PCU"
}
GenuineIntel-6-3E,v19,ivytown,core
GenuineIntel-6-2D,v20,jaketown,core
GenuineIntel-6-57,v9,knightslanding,core
+GenuineIntel-6-85,v9,knightslanding,core
GenuineIntel-6-1E,v2,nehalemep,core
GenuineIntel-6-1F,v2,nehalemep,core
GenuineIntel-6-1A,v2,nehalemep,core
--- /dev/null
+[
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x01",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.MISS",
+ "BriefDescription": "A snoop misses in some processor core.",
+ "PublicDescription": "A snoop misses in some processor core.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x02",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.INVAL",
+ "BriefDescription": "A snoop invalidates a non-modified line in some processor core.",
+ "PublicDescription": "A snoop invalidates a non-modified line in some processor core.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x04",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.HIT",
+ "BriefDescription": "A snoop hits a non-modified line in some processor core.",
+ "PublicDescription": "A snoop hits a non-modified line in some processor core.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x08",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.HITM",
+ "BriefDescription": "A snoop hits a modified line in some processor core.",
+ "PublicDescription": "A snoop hits a modified line in some processor core.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x10",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.INVAL_M",
+ "BriefDescription": "A snoop invalidates a modified line in some processor core.",
+ "PublicDescription": "A snoop invalidates a modified line in some processor core.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x20",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.EXTERNAL_FILTER",
+ "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to external snoop request.",
+ "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to external snoop request.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x40",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.XCORE_FILTER",
+ "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to processor core memory request.",
+ "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to processor core memory request.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x80",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.EVICTION_FILTER",
+ "BriefDescription": "Filter on cross-core snoops initiated by this Cbox due to LLC eviction.",
+ "PublicDescription": "Filter on cross-core snoops initiated by this Cbox due to LLC eviction.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x01",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.M",
+ "BriefDescription": "LLC lookup request that access cache and found line in M-state.",
+ "PublicDescription": "LLC lookup request that access cache and found line in M-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x02",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.E",
+ "BriefDescription": "LLC lookup request that access cache and found line in E-state.",
+ "PublicDescription": "LLC lookup request that access cache and found line in E-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x04",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.S",
+ "BriefDescription": "LLC lookup request that access cache and found line in S-state.",
+ "PublicDescription": "LLC lookup request that access cache and found line in S-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x08",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.I",
+ "BriefDescription": "LLC lookup request that access cache and found line in I-state.",
+ "PublicDescription": "LLC lookup request that access cache and found line in I-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x10",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_FILTER",
+ "BriefDescription": "Filter on processor core initiated cacheable read requests.",
+ "PublicDescription": "Filter on processor core initiated cacheable read requests.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x20",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_FILTER",
+ "BriefDescription": "Filter on processor core initiated cacheable write requests.",
+ "PublicDescription": "Filter on processor core initiated cacheable write requests.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x40",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.EXTSNP_FILTER",
+ "BriefDescription": "Filter on external snoop requests.",
+ "PublicDescription": "Filter on external snoop requests.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x80",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_REQUEST_FILTER",
+ "BriefDescription": "Filter on any IRQ or IPQ initiated requests including uncacheable, non-coherent requests.",
+ "PublicDescription": "Filter on any IRQ or IPQ initiated requests including uncacheable, non-coherent requests.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "ARB",
+ "EventCode": "0x80",
+ "UMask": "0x01",
+ "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL",
+ "BriefDescription": "Counts cycles weighted by the number of requests waiting for data returning from the memory controller. Accounts for coherent and non-coherent requests initiated by IA cores, processor graphic units, or LLC.",
+ "PublicDescription": "Counts cycles weighted by the number of requests waiting for data returning from the memory controller. Accounts for coherent and non-coherent requests initiated by IA cores, processor graphic units, or LLC.",
+ "Counter": "0",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "ARB",
+ "EventCode": "0x81",
+ "UMask": "0x01",
+ "EventName": "UNC_ARB_TRK_REQUESTS.ALL",
+ "BriefDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC.",
+ "PublicDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "ARB",
+ "EventCode": "0x81",
+ "UMask": "0x20",
+ "EventName": "UNC_ARB_TRK_REQUESTS.WRITES",
+ "BriefDescription": "Counts the number of allocated write entries, include full, partial, and LLC evictions.",
+ "PublicDescription": "Counts the number of allocated write entries, include full, partial, and LLC evictions.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "ARB",
+ "EventCode": "0x81",
+ "UMask": "0x80",
+ "EventName": "UNC_ARB_TRK_REQUESTS.EVICTIONS",
+ "BriefDescription": "Counts the number of LLC evictions allocated.",
+ "PublicDescription": "Counts the number of LLC evictions allocated.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "ARB",
+ "EventCode": "0x83",
+ "UMask": "0x01",
+ "EventName": "UNC_ARB_COH_TRK_OCCUPANCY.ALL",
+ "BriefDescription": "Cycles weighted by number of requests pending in Coherency Tracker.",
+ "PublicDescription": "Cycles weighted by number of requests pending in Coherency Tracker.",
+ "Counter": "0",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "ARB",
+ "EventCode": "0x84",
+ "UMask": "0x01",
+ "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL",
+ "BriefDescription": "Number of requests allocated in Coherency Tracker.",
+ "PublicDescription": "Number of requests allocated in Coherency Tracker.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "ARB",
+ "EventCode": "0x80",
+ "UMask": "0x01",
+ "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST",
+ "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+ "PublicDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+ "Counter": "0,1",
+ "CounterMask": "1",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "ARB",
+ "EventCode": "0x80",
+ "UMask": "0x01",
+ "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_OVER_HALF_FULL",
+ "BriefDescription": "Cycles with at least half of the requests outstanding are waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+ "PublicDescription": "Cycles with at least half of the requests outstanding are waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+ "Counter": "0,1",
+ "CounterMask": "10",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "ARB",
+ "EventCode": "0x0",
+ "UMask": "0x01",
+ "EventName": "UNC_CLOCK.SOCKET",
+ "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.",
+ "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.",
+ "Counter": "Fixed",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x06",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.ES",
+ "BriefDescription": "LLC lookup request that access cache and found line in E-state or S-state.",
+ "PublicDescription": "LLC lookup request that access cache and found line in E-state or S-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ }
+]
\ No newline at end of file
--- /dev/null
+[
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x41",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_XCORE",
+ "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.",
+ "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which misses in some processor core.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x81",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.MISS_EVICTION",
+ "BriefDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.",
+ "PublicDescription": "A cross-core snoop resulted from L3 Eviction which misses in some processor core.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x44",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.HIT_XCORE",
+ "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.",
+ "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a non-modified line in some processor core.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x22",
+ "UMask": "0x48",
+ "EventName": "UNC_CBO_XSNP_RESPONSE.HITM_XCORE",
+ "BriefDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.",
+ "PublicDescription": "A cross-core snoop initiated by this Cbox due to processor core memory request which hits a modified line in some processor core.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x21",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_M",
+ "BriefDescription": "L3 Lookup write request that access cache and found line in M-state",
+ "PublicDescription": "L3 Lookup write request that access cache and found line in M-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x81",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_M",
+ "BriefDescription": "L3 Lookup any request that access cache and found line in M-state",
+ "PublicDescription": "L3 Lookup any request that access cache and found line in M-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x18",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_I",
+ "BriefDescription": "L3 Lookup read request that access cache and found line in I-state",
+ "PublicDescription": "L3 Lookup read request that access cache and found line in I-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x88",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_I",
+ "BriefDescription": "L3 Lookup any request that access cache and found line in I-state",
+ "PublicDescription": "L3 Lookup any request that access cache and found line in I-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x1f",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_MESI",
+ "BriefDescription": "L3 Lookup read request that access cache and found line in any MESI-state",
+ "PublicDescription": "L3 Lookup read request that access cache and found line in any MESI-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x2f",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_MESI",
+ "BriefDescription": "L3 Lookup write request that access cache and found line in MESI-state",
+ "PublicDescription": "L3 Lookup write request that access cache and found line in MESI-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x8f",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_MESI",
+ "BriefDescription": "L3 Lookup any request that access cache and found line in MESI-state",
+ "PublicDescription": "L3 Lookup any request that access cache and found line in MESI-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x86",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.ANY_ES",
+ "BriefDescription": "L3 Lookup any request that access cache and found line in E or S-state",
+ "PublicDescription": "L3 Lookup any request that access cache and found line in E or S-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x16",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.READ_ES",
+ "BriefDescription": "L3 Lookup read request that access cache and found line in E or S-state",
+ "PublicDescription": "L3 Lookup read request that access cache and found line in E or S-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "CBO",
+ "EventCode": "0x34",
+ "UMask": "0x26",
+ "EventName": "UNC_CBO_CACHE_LOOKUP.WRITE_ES",
+ "BriefDescription": "L3 Lookup write request that access cache and found line in E or S-state",
+ "PublicDescription": "L3 Lookup write request that access cache and found line in E or S-state.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "iMPH-U",
+ "EventCode": "0x80",
+ "UMask": "0x01",
+ "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL",
+ "BriefDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from its allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.",
+ "PublicDescription": "Each cycle count number of all Core outgoing valid entries. Such entry is defined as valid from its allocation till first of IDI0 or DRS0 messages is sent out. Accounts for Coherent and non-coherent traffic.",
+ "Counter": "0",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "iMPH-U",
+ "EventCode": "0x81",
+ "UMask": "0x01",
+ "EventName": "UNC_ARB_TRK_REQUESTS.ALL",
+ "BriefDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
+ "PublicDescription": "Total number of Core outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "iMPH-U",
+ "EventCode": "0x81",
+ "UMask": "0x02",
+ "EventName": "UNC_ARB_TRK_REQUESTS.DRD_DIRECT",
+ "BriefDescription": "Number of Core coherent Data Read entries allocated in DirectData mode",
+ "PublicDescription": "Number of Core coherent Data Read entries allocated in DirectData mode.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "iMPH-U",
+ "EventCode": "0x81",
+ "UMask": "0x20",
+ "EventName": "UNC_ARB_TRK_REQUESTS.WRITES",
+ "BriefDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.",
+ "PublicDescription": "Number of Writes allocated - any write transactions: full/partials writes and evictions.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "iMPH-U",
+ "EventCode": "0x84",
+ "UMask": "0x01",
+ "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL",
+ "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.",
+ "PublicDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, Core aperture, etc.",
+ "Counter": "0,1",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "iMPH-U",
+ "EventCode": "0x80",
+ "UMask": "0x01",
+ "EventName": "UNC_ARB_TRK_OCCUPANCY.CYCLES_WITH_ANY_REQUEST",
+ "BriefDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.;",
+ "PublicDescription": "Cycles with at least one request outstanding is waiting for data return from memory controller. Account for coherent and non-coherent requests initiated by IA Cores, Processor Graphics Unit, or LLC.",
+ "Counter": "0",
+ "CounterMask": "1",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ },
+ {
+ "Unit": "NCU",
+ "EventCode": "0x0",
+ "UMask": "0x01",
+ "EventName": "UNC_CLOCK.SOCKET",
+ "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles",
+ "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.",
+ "Counter": "FIXED",
+ "CounterMask": "0",
+ "Invert": "0",
+ "EdgeDetect": "0"
+ }
+]
\ No newline at end of file
{ "CBO", "uncore_cbox" },
{ "QPI LL", "uncore_qpi" },
{ "SBO", "uncore_sbox" },
+ { "iMPH-U", "uncore_arb" },
{}
};
static int print_events_table_entry(void *data, char *name, char *event,
char *desc, char *long_desc,
- char *pmu, char *unit, char *perpkg)
+ char *pmu, char *unit, char *perpkg,
+ char *metric_expr,
+ char *metric_name)
{
struct perf_entry_data *pd = data;
FILE *outfp = pd->outfp;
fprintf(outfp, "\t.unit = \"%s\",\n", unit);
if (perpkg)
fprintf(outfp, "\t.perpkg = \"%s\",\n", perpkg);
+ if (metric_expr)
+ fprintf(outfp, "\t.metric_expr = \"%s\",\n", metric_expr);
+ if (metric_name)
+ fprintf(outfp, "\t.metric_name = \"%s\",\n", metric_name);
fprintf(outfp, "},\n");
return 0;
int json_events(const char *fn,
int (*func)(void *data, char *name, char *event, char *desc,
char *long_desc,
- char *pmu, char *unit, char *perpkg),
+ char *pmu, char *unit, char *perpkg,
+ char *metric_expr,
+ char *metric_name),
void *data)
{
int err = -EIO;
char *filter = NULL;
char *perpkg = NULL;
char *unit = NULL;
+ char *metric_expr = NULL;
+ char *metric_name = NULL;
unsigned long long eventcode = 0;
struct msrmap *msr = NULL;
jsmntok_t *msrval = NULL;
for (j = 0; j < obj->size; j += 2) {
jsmntok_t *field, *val;
int nz;
+ char *s;
field = tok + j;
EXPECT(field->type == JSMN_STRING, tok + j,
NULL);
} else if (json_streq(map, field, "Unit")) {
const char *ppmu;
- char *s;
ppmu = field_to_perf(unit_to_pmu, map, val);
if (ppmu) {
}
addfield(map, &desc, ". ", "Unit: ", NULL);
addfield(map, &desc, "", pmu, NULL);
+ addfield(map, &desc, "", " ", NULL);
} else if (json_streq(map, field, "Filter")) {
addfield(map, &filter, "", "", val);
} else if (json_streq(map, field, "ScaleUnit")) {
addfield(map, &unit, "", "", val);
} else if (json_streq(map, field, "PerPkg")) {
addfield(map, &perpkg, "", "", val);
+ } else if (json_streq(map, field, "MetricName")) {
+ addfield(map, &metric_name, "", "", val);
+ } else if (json_streq(map, field, "MetricExpr")) {
+ addfield(map, &metric_expr, "", "", val);
+ for (s = metric_expr; *s; s++)
+ *s = tolower(*s);
}
/* ignore unknown fields */
}
fixname(name);
err = func(data, name, real_event(name, event), desc, long_desc,
- pmu, unit, perpkg);
+ pmu, unit, perpkg, metric_expr, metric_name);
free(event);
free(desc);
free(name);
free(filter);
free(perpkg);
free(unit);
+ free(metric_expr);
+ free(metric_name);
if (err)
break;
tok += j;
int (*func)(void *data, char *name, char *event, char *desc,
char *long_desc,
char *pmu,
- char *unit, char *perpkg),
+ char *unit, char *perpkg, char *metric_expr,
+ char *metric_name),
void *data);
char *get_cpu_str(void);
const char *pmu;
const char *unit;
const char *perpkg;
+ const char *metric_expr;
+ const char *metric_name;
};
/*
perf-y += stat.o
perf-y += event_update.o
perf-y += event-times.o
+perf-y += expr.o
perf-y += backward-ring-buffer.o
perf-y += sdt.o
perf-y += is_printable_array.o
* permissions. All the event text files are stored there.
*/
+#include <errno.h>
+#include <inttypes.h>
#include <stdlib.h>
#include <stdio.h>
#include <linux/types.h>
#include <linux/kernel.h>
+#include <sys/param.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
#include "../perf.h"
#include "util.h"
#include <subcmd/exec-cmd.h>
#include <sys/prctl.h>
#include "tests.h"
#include "debug.h"
+#include <errno.h>
#define NR_ITERS 111
+#include <errno.h>
#include <stdio.h>
#include <sys/epoll.h>
+#include <sys/types.h>
+#include <sys/stat.h>
#include <util/util.h>
#include <util/bpf-loader.h>
#include <util/evlist.h>
#include <linux/bpf.h>
#include <linux/filter.h>
+#include <linux/kernel.h>
#include <api/fs/fs.h>
#include <bpf/bpf.h>
#include "tests.h"
*
* Builtin regression testing command: ever growing number of sanity tests
*/
+#include <errno.h>
#include <unistd.h>
#include <string.h>
+#include <sys/wait.h>
#include "builtin.h"
#include "hist.h"
#include "intlist.h"
#include "color.h"
#include <subcmd/parse-options.h>
#include "symbol.h"
+#include <linux/kernel.h>
static bool dont_fork;
.func = test__parse_events,
},
{
+ .desc = "Simple expression parser",
+ .func = test__expr,
+ },
+ {
.desc = "PERF_RECORD_* events & perf_sample fields",
.func = test__PERF_RECORD,
},
return 0;
}
-int cmd_test(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_test(int argc, const char **argv)
{
const char *test_usage[] = {
"perf test [<options>] [{list <test-name-fragment>|[<test-name-fragments>|<test-numbers>]}]",
#include "debug.h"
#include "util.h"
#include "c++/clang-c.h"
+#include <linux/kernel.h>
static struct {
int (*func)(void);
+#include <errno.h>
+#include <linux/kernel.h>
#include <linux/types.h>
+#include <inttypes.h>
#include <stdlib.h>
#include <unistd.h>
#include <stdio.h>
-#include <ctype.h>
#include <string.h>
+#include <sys/param.h>
#include "parse-events.h"
#include "evlist.h"
#include "tests.h"
+#include "sane_ctype.h"
+
#define BUFSZ 1024
#define READLEN 128
TEST_ASSERT_VAL("wrong nr", map->nr == 2);
TEST_ASSERT_VAL("wrong cpu", map->map[0] == 1);
TEST_ASSERT_VAL("wrong cpu", map->map[1] == 256);
- TEST_ASSERT_VAL("wrong refcnt", atomic_read(&map->refcnt) == 1);
+ TEST_ASSERT_VAL("wrong refcnt", refcount_read(&map->refcnt) == 1);
cpu_map__put(map);
return 0;
}
+#include <dirent.h>
#include <stdlib.h>
+#include <linux/kernel.h>
#include <linux/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <linux/compiler.h>
#include <linux/types.h>
+#include <inttypes.h>
#include <unistd.h>
#include "tests.h"
#include "debug.h"
#include <linux/compiler.h>
+#include <errno.h>
+#include <inttypes.h>
#include <string.h>
+#include <sys/wait.h>
#include "tests.h"
#include "evlist.h"
#include "evsel.h"
#include "parse-events.h"
#include "tests.h"
#include "debug.h"
+#include <errno.h>
+#include <linux/kernel.h>
static int perf_evsel__roundtrip_cache_name_test(void)
{
--- /dev/null
+#include "util/debug.h"
+#include "util/expr.h"
+#include "tests.h"
+#include <stdlib.h>
+
+static int test(struct parse_ctx *ctx, const char *e, double val2)
+{
+ double val;
+
+ if (expr__parse(&val, ctx, &e))
+ TEST_ASSERT_VAL("parse test failed", 0);
+ TEST_ASSERT_VAL("unexpected value", val == val2);
+ return 0;
+}
+
+int test__expr(int subtest __maybe_unused)
+{
+ const char *p;
+ const char **other;
+ double val;
+ int ret;
+ struct parse_ctx ctx;
+ int num_other;
+
+ expr__ctx_init(&ctx);
+ expr__add_id(&ctx, "FOO", 1);
+ expr__add_id(&ctx, "BAR", 2);
+
+ ret = test(&ctx, "1+1", 2);
+ ret |= test(&ctx, "FOO+BAR", 3);
+ ret |= test(&ctx, "(BAR/2)%2", 1);
+ ret |= test(&ctx, "1 - -4", 5);
+ ret |= test(&ctx, "(FOO-1)*2 + (BAR/2)%2 - -4", 5);
+
+ if (ret)
+ return ret;
+
+ p = "FOO/0";
+ ret = expr__parse(&val, &ctx, &p);
+ TEST_ASSERT_VAL("division by zero", ret == 1);
+
+ p = "BAR/";
+ ret = expr__parse(&val, &ctx, &p);
+ TEST_ASSERT_VAL("missing operand", ret == 1);
+
+ TEST_ASSERT_VAL("find other",
+ expr__find_other("FOO + BAR + BAZ + BOZO", "FOO", &other, &num_other) == 0);
+ TEST_ASSERT_VAL("find other", num_other == 3);
+ TEST_ASSERT_VAL("find other", !strcmp(other[0], "BAR"));
+ TEST_ASSERT_VAL("find other", !strcmp(other[1], "BAZ"));
+ TEST_ASSERT_VAL("find other", !strcmp(other[2], "BOZO"));
+ TEST_ASSERT_VAL("find other", other[3] == NULL);
+ free((void *)other);
+
+ return 0;
+}
+#include <inttypes.h>
#include "perf.h"
#include "util/debug.h"
#include "util/symbol.h"
#include "util/machine.h"
#include "util/thread.h"
#include "tests/hists_common.h"
+#include <linux/kernel.h>
static struct {
u32 pid;
#include "util/parse-events.h"
#include "tests/tests.h"
#include "tests/hists_common.h"
+#include <linux/kernel.h>
struct sample {
u32 pid;
#include "util/parse-events.h"
#include "tests/tests.h"
#include "tests/hists_common.h"
+#include <linux/kernel.h>
struct sample {
u32 pid;
#include "thread.h"
#include "parse-events.h"
#include "hists_common.h"
+#include <errno.h>
+#include <linux/kernel.h>
struct sample {
u32 pid;
#include "util/parse-events.h"
#include "tests/tests.h"
#include "tests/hists_common.h"
+#include <linux/kernel.h>
struct sample {
u32 cpu;
#include <linux/compiler.h>
+#include <linux/kernel.h>
#include "tests.h"
#include "debug.h"
-#include "util.h"
+#include "print_binary.h"
int test__is_printable_array(int subtest __maybe_unused)
{
+#include <errno.h>
+#include <inttypes.h>
/* For the CLR_() macros */
#include <pthread.h>
#include "cpumap.h"
#include "tests.h"
#include <linux/err.h>
+#include <linux/kernel.h>
/*
* This test will generate random numbers of calls to some getpid syscalls,
+#include <inttypes.h>
#include <unistd.h>
#include <sys/syscall.h>
#include <sys/types.h>
#include "thread_map.h"
#include "symbol.h"
#include "thread.h"
+#include "util.h"
#define THREADS 4
+#include <errno.h>
+#include <inttypes.h>
/* For the CPU_* macros */
#include <pthread.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
#include <api/fs/fs.h>
#include <linux/err.h>
+#include <api/fs/tracing_path.h>
#include "evsel.h"
#include "tests.h"
#include "thread_map.h"
#include "thread_map.h"
#include "tests.h"
#include "debug.h"
+#include <errno.h>
#ifndef O_DIRECTORY
#define O_DIRECTORY 00200000
+#include <errno.h>
+#include <inttypes.h>
#include <api/fs/tracing_path.h>
#include <linux/err.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
#include "thread_map.h"
#include "evsel.h"
#include "debug.h"
-
#include "parse-events.h"
#include "evsel.h"
#include "evlist.h"
#include "tests.h"
#include "debug.h"
#include "util.h"
+#include <dirent.h>
+#include <errno.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <linux/kernel.h>
#include <linux/hw_breakpoint.h>
#include <api/fs/fs.h>
+#include <api/fs/tracing_path.h>
#define PERF_TP_SAMPLE_TYPE (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | \
PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD)
+#include <linux/kernel.h>
#include <linux/types.h>
#include <stddef.h>
+#include <errno.h>
+#include <inttypes.h>
/* For the CLR_() macros */
#include <pthread.h>
#include "pmu.h"
#include "util.h"
#include "tests.h"
+#include <errno.h>
+#include <linux/kernel.h>
/* Simulated format definitions. */
static struct test_format {
#include <stdbool.h>
+#include <inttypes.h>
+#include <linux/kernel.h>
#include <linux/types.h>
#include "util.h"
+#include <errno.h>
#include <stdio.h>
#include <sys/epoll.h>
#include <util/util.h>
{
char *buf = calloc(PATH_MAX, sizeof(char));
- if (buf && readlink("/proc/self/exe", buf, PATH_MAX) < 0) {
+ if (buf && readlink("/proc/self/exe", buf, PATH_MAX - 1) < 0) {
pr_debug("Failed to get correct path of perf\n");
free(buf);
return NULL;
+#include <errno.h>
+#include <inttypes.h>
#include <unistd.h>
#include <stdlib.h>
#include <signal.h>
#include <sys/time.h>
#include <sys/prctl.h>
+#include <errno.h>
#include <time.h>
#include <stdlib.h>
#include "cpumap.h"
#include "tests.h"
+#include <errno.h>
#include <signal.h>
static int exited;
int test__keep_tracking(int subtest);
int test__parse_no_sample_id_all(int subtest);
int test__dwarf_unwind(int subtest);
+int test__expr(int subtest);
int test__hists_filter(int subtest);
int test__mmap_thread_lookup(int subtest);
int test__thread_mg_share(int subtest);
thread_map__comm(map, 0) &&
!strcmp(thread_map__comm(map, 0), NAME));
TEST_ASSERT_VAL("wrong refcnt",
- atomic_read(&map->refcnt) == 1);
+ refcount_read(&map->refcnt) == 1);
thread_map__put(map);
/* test dummy pid */
thread_map__comm(map, 0) &&
!strcmp(thread_map__comm(map, 0), "dummy"));
TEST_ASSERT_VAL("wrong refcnt",
- atomic_read(&map->refcnt) == 1);
+ refcount_read(&map->refcnt) == 1);
thread_map__put(map);
return 0;
}
thread_map__comm(threads, 0) &&
!strcmp(thread_map__comm(threads, 0), NAME));
TEST_ASSERT_VAL("wrong refcnt",
- atomic_read(&threads->refcnt) == 1);
+ refcount_read(&threads->refcnt) == 1);
thread_map__put(threads);
return 0;
}
leader && t1 && t2 && t3 && other);
mg = leader->mg;
- TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 4);
+ TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 4);
/* test the map groups pointer is shared */
TEST_ASSERT_VAL("map groups don't match", mg == t1->mg);
machine__remove_thread(machine, other_leader);
other_mg = other->mg;
- TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&other_mg->refcnt), 2);
+ TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&other_mg->refcnt), 2);
TEST_ASSERT_VAL("map groups don't match", other_mg == other_leader->mg);
/* release thread group */
thread__put(leader);
- TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 3);
+ TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 3);
thread__put(t1);
- TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 2);
+ TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 2);
thread__put(t2);
- TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 1);
+ TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&mg->refcnt), 1);
thread__put(t3);
/* release other group */
thread__put(other_leader);
- TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&other_mg->refcnt), 1);
+ TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(&other_mg->refcnt), 1);
thread__put(other);
+#include <inttypes.h>
#include <linux/compiler.h>
#include <linux/types.h>
#include "tests.h"
-#include "util.h"
+#include "units.h"
#include "debug.h"
int test__unit_number__scnprint(int subtest __maybe_unused)
#include <linux/compiler.h>
#include <linux/rbtree.h>
+#include <inttypes.h>
#include <string.h>
#include "map.h"
#include "symbol.h"
--- /dev/null
+libperf-y += statx.o
--- /dev/null
+#ifndef _PERF_TRACE_BEAUTY_H
+#define _PERF_TRACE_BEAUTY_H
+
+#include <linux/types.h>
+
+struct trace;
+struct thread;
+
+struct syscall_arg {
+ unsigned long val;
+ struct thread *thread;
+ struct trace *trace;
+ void *parm;
+ u8 idx;
+ u8 mask;
+};
+
+size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_STATX_FLAGS syscall_arg__scnprintf_statx_flags
+
+size_t syscall_arg__scnprintf_statx_mask(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_STATX_MASK syscall_arg__scnprintf_statx_mask
+
+#endif /* _PERF_TRACE_BEAUTY_H */
+#include <signal.h>
static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscall_arg *arg)
{
--- /dev/null
+/*
+ * trace/beauty/statx.c
+ *
+ * Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include "trace/beauty/beauty.h"
+#include <linux/kernel.h>
+#include <sys/types.h>
+#include <uapi/linux/fcntl.h>
+#include <uapi/linux/stat.h>
+
+size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg)
+{
+ int printed = 0, flags = arg->val;
+
+ if (flags == 0)
+ return scnprintf(bf, size, "SYNC_AS_STAT");
+#define P_FLAG(n) \
+ if (flags & AT_##n) { \
+ printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+ flags &= ~AT_##n; \
+ }
+
+ P_FLAG(SYMLINK_NOFOLLOW);
+ P_FLAG(REMOVEDIR);
+ P_FLAG(SYMLINK_FOLLOW);
+ P_FLAG(NO_AUTOMOUNT);
+ P_FLAG(EMPTY_PATH);
+ P_FLAG(STATX_FORCE_SYNC);
+ P_FLAG(STATX_DONT_SYNC);
+
+#undef P_FLAG
+
+ if (flags)
+ printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+ return printed;
+}
+
+size_t syscall_arg__scnprintf_statx_mask(char *bf, size_t size, struct syscall_arg *arg)
+{
+ int printed = 0, flags = arg->val;
+
+#define P_FLAG(n) \
+ if (flags & STATX_##n) { \
+ printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+ flags &= ~STATX_##n; \
+ }
+
+ P_FLAG(TYPE);
+ P_FLAG(MODE);
+ P_FLAG(NLINK);
+ P_FLAG(UID);
+ P_FLAG(GID);
+ P_FLAG(ATIME);
+ P_FLAG(MTIME);
+ P_FLAG(CTIME);
+ P_FLAG(INO);
+ P_FLAG(SIZE);
+ P_FLAG(BLOCKS);
+ P_FLAG(BTIME);
+
+#undef P_FLAG
+
+ if (flags)
+ printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+ return printed;
+}
#include "../util.h"
+#include "../string2.h"
#include "../config.h"
#include "../../perf.h"
#include "libslang.h"
#include "helpline.h"
#include "keysyms.h"
#include "../color.h"
+#include "sane_ctype.h"
static int ui_browser__percent_color(struct ui_browser *browser,
double percent, bool current)
break;
*bg = '\0';
- while (isspace(*++bg));
+ bg = ltrim(++bg);
ui_browser__colorsets[i].bg = bg;
ui_browser__colorsets[i].fg = fg;
return 0;
#include "../../util/symbol.h"
#include "../../util/evsel.h"
#include "../../util/config.h"
+#include <inttypes.h>
#include <pthread.h>
+#include <linux/kernel.h>
+#include <sys/ttydefaults.h>
struct disasm_line_samples {
double percent;
#include "util/header.h"
#include "util/session.h"
+#include <sys/ttydefaults.h>
+
static void ui_browser__argv_write(struct ui_browser *browser,
void *entry, int row)
{
+#include <dirent.h>
+#include <errno.h>
+#include <inttypes.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <linux/rbtree.h>
+#include <sys/ttydefaults.h>
#include "../../util/evsel.h"
#include "../../util/evlist.h"
#include "../../util/sort.h"
#include "../../util/util.h"
#include "../../util/top.h"
+#include "../../util/thread.h"
#include "../../arch/common.h"
#include "../browsers/hists.h"
#include "../ui.h"
#include "map.h"
#include "annotate.h"
+#include "srcline.h"
+#include "string2.h"
+#include "units.h"
+
+#include "sane_ctype.h"
extern void hist_browser__init_hpp(void);
cl->unfolded = unfold ? cl->has_children : false;
}
+static struct inline_node *inline_node__create(struct map *map, u64 ip)
+{
+ struct dso *dso;
+ struct inline_node *node;
+
+ if (map == NULL)
+ return NULL;
+
+ dso = map->dso;
+ if (dso == NULL)
+ return NULL;
+
+ if (dso->kernel != DSO_TYPE_USER)
+ return NULL;
+
+ node = dso__parse_addr_inlines(dso,
+ map__rip_2objdump(map, ip));
+
+ return node;
+}
+
+static int inline__count_rows(struct inline_node *node)
+{
+ struct inline_list *ilist;
+ int i = 0;
+
+ if (node == NULL)
+ return 0;
+
+ list_for_each_entry(ilist, &node->val, list) {
+ if ((ilist->filename != NULL) || (ilist->funcname != NULL))
+ i++;
+ }
+
+ return i;
+}
+
+static int callchain_list__inline_rows(struct callchain_list *chain)
+{
+ struct inline_node *node;
+ int rows;
+
+ node = inline_node__create(chain->ms.map, chain->ip);
+ if (node == NULL)
+ return 0;
+
+ rows = inline__count_rows(node);
+ inline_node__delete(node);
+ return rows;
+}
+
static int callchain_node__count_rows_rb_tree(struct callchain_node *node)
{
- int n = 0;
+ int n = 0, inline_rows;
struct rb_node *nd;
for (nd = rb_first(&node->rb_root); nd; nd = rb_next(nd)) {
list_for_each_entry(chain, &child->val, list) {
++n;
+
+ if (symbol_conf.inline_name) {
+ inline_rows =
+ callchain_list__inline_rows(chain);
+ n += inline_rows;
+ }
+
/* We need this because we may not have children */
folded_sign = callchain_list__folded(chain);
if (folded_sign == '+')
{
struct callchain_list *chain;
bool unfolded = false;
- int n = 0;
+ int n = 0, inline_rows;
if (callchain_param.mode == CHAIN_FLAT)
return callchain_node__count_flat_rows(node);
list_for_each_entry(chain, &node->val, list) {
++n;
+ if (symbol_conf.inline_name) {
+ inline_rows = callchain_list__inline_rows(chain);
+ n += inline_rows;
+ }
+
unfolded = chain->unfolded;
}
he->init_have_children = true;
}
+static void hist_entry_init_inline_node(struct hist_entry *he)
+{
+ if (he->inline_node)
+ return;
+
+ he->inline_node = inline_node__create(he->ms.map, he->ip);
+
+ if (he->inline_node == NULL)
+ return;
+
+ he->has_children = true;
+}
+
static bool hist_browser__toggle_fold(struct hist_browser *browser)
{
struct hist_entry *he = browser->he_selection;
if (he->unfolded) {
if (he->leaf)
- he->nr_rows = callchain__count_rows(&he->sorted_chain);
+ if (he->inline_node)
+ he->nr_rows = inline__count_rows(
+ he->inline_node);
+ else
+ he->nr_rows = callchain__count_rows(
+ &he->sorted_chain);
else
he->nr_rows = hierarchy_count_rows(browser, he, false);
#define LEVEL_OFFSET_STEP 3
+static int hist_browser__show_inline(struct hist_browser *browser,
+ struct inline_node *node,
+ unsigned short row,
+ int offset)
+{
+ struct inline_list *ilist;
+ char buf[1024];
+ int color, width, first_row;
+
+ first_row = row;
+ width = browser->b.width - (LEVEL_OFFSET_STEP + 2);
+ list_for_each_entry(ilist, &node->val, list) {
+ if ((ilist->filename != NULL) || (ilist->funcname != NULL)) {
+ color = HE_COLORSET_NORMAL;
+ if (ui_browser__is_current_entry(&browser->b, row))
+ color = HE_COLORSET_SELECTED;
+
+ if (callchain_param.key == CCKEY_ADDRESS ||
+ callchain_param.key == CCKEY_SRCLINE) {
+ if (ilist->filename != NULL)
+ scnprintf(buf, sizeof(buf),
+ "%s:%d (inline)",
+ ilist->filename,
+ ilist->line_nr);
+ else
+ scnprintf(buf, sizeof(buf), "??");
+ } else if (ilist->funcname != NULL)
+ scnprintf(buf, sizeof(buf), "%s (inline)",
+ ilist->funcname);
+ else if (ilist->filename != NULL)
+ scnprintf(buf, sizeof(buf),
+ "%s:%d (inline)",
+ ilist->filename,
+ ilist->line_nr);
+ else
+ scnprintf(buf, sizeof(buf), "??");
+
+ ui_browser__set_color(&browser->b, color);
+ hist_browser__gotorc(browser, row, 0);
+ ui_browser__write_nstring(&browser->b, " ",
+ LEVEL_OFFSET_STEP + offset);
+ ui_browser__write_nstring(&browser->b, buf, width);
+ row++;
+ }
+ }
+
+ return row - first_row;
+}
+
+static size_t show_inline_list(struct hist_browser *browser, struct map *map,
+ u64 ip, int row, int offset)
+{
+ struct inline_node *node;
+ int ret;
+
+ node = inline_node__create(map, ip);
+ if (node == NULL)
+ return 0;
+
+ ret = hist_browser__show_inline(browser, node, row, offset);
+
+ inline_node__delete(node);
+ return ret;
+}
+
static int hist_browser__show_callchain_list(struct hist_browser *browser,
struct callchain_node *node,
struct callchain_list *chain,
char bf[1024], *alloc_str;
char buf[64], *alloc_str2;
const char *str;
+ int inline_rows = 0, ret = 1;
if (arg->row_offset != 0) {
arg->row_offset--;
}
print(browser, chain, str, offset, row, arg);
-
free(alloc_str);
free(alloc_str2);
- return 1;
+
+ if (symbol_conf.inline_name) {
+ inline_rows = show_inline_list(browser, chain->ms.map,
+ chain->ip, row + 1, offset);
+ }
+
+ return ret + inline_rows;
}
static bool check_percent_display(struct rb_node *node, u64 parent_total)
folded_sign = hist_entry__folded(entry);
}
+ if (symbol_conf.inline_name &&
+ (!entry->has_children)) {
+ hist_entry_init_inline_node(entry);
+ folded_sign = hist_entry__folded(entry);
+ }
+
if (row_offset == 0) {
struct hpp_arg arg = {
.b = &browser->b,
}
if (first) {
- if (symbol_conf.use_callchain) {
+ if (symbol_conf.use_callchain ||
+ symbol_conf.inline_name) {
ui_browser__printf(&browser->b, "%c ", folded_sign);
width -= 2;
}
.is_current_entry = current_entry,
};
- printed += hist_browser__show_callchain(browser, entry, 1, row,
- hist_browser__show_callchain_entry, &arg,
+ if (entry->inline_node)
+ printed += hist_browser__show_inline(browser,
+ entry->inline_node, row, 0);
+ else
+ printed += hist_browser__show_callchain(browser,
+ entry, 1, row,
+ hist_browser__show_callchain_entry,
+ &arg,
hist_browser__check_output_full);
}
return ret;
memset(options, 0, sizeof(options));
- memset(options, 0, sizeof(abs_path));
+ memset(abs_path, 0, sizeof(abs_path));
while ((dent = readdir(pwd_dir))) {
char path[PATH_MAX];
#include "../keysyms.h"
#include "map.h"
+#include "sane_ctype.h"
+
struct map_browser {
struct ui_browser b;
struct map *map;
#include "util/annotate.h"
#include "util/evsel.h"
#include "ui/helpline.h"
-
+#include <inttypes.h>
+#include <signal.h>
enum {
ANN_COL__PERCENT,
#include "../sort.h"
#include "../hist.h"
#include "../helpline.h"
+#include "../string2.h"
#include "gtk.h"
+#include <signal.h>
#define MAX_COLUMNS 32
+#include <inttypes.h>
#include <math.h>
#include <linux/compiler.h>
#include "../util/cache.h"
#include "../util/debug.h"
#include "../util/hist.h"
+#include "../util/util.h"
pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER;
void *perf_gtk_handle;
#include "../../util/hist.h"
#include "../../util/sort.h"
#include "../../util/evsel.h"
-
+#include "../../util/srcline.h"
+#include "../../util/string2.h"
+#include "../../util/thread.h"
+#include "../../util/sane_ctype.h"
static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin)
{
return ret;
}
+static size_t inline__fprintf(struct map *map, u64 ip, int left_margin,
+ int depth, int depth_mask, FILE *fp)
+{
+ struct dso *dso;
+ struct inline_node *node;
+ struct inline_list *ilist;
+ int ret = 0, i;
+
+ if (map == NULL)
+ return 0;
+
+ dso = map->dso;
+ if (dso == NULL)
+ return 0;
+
+ if (dso->kernel != DSO_TYPE_USER)
+ return 0;
+
+ node = dso__parse_addr_inlines(dso,
+ map__rip_2objdump(map, ip));
+ if (node == NULL)
+ return 0;
+
+ list_for_each_entry(ilist, &node->val, list) {
+ if ((ilist->filename != NULL) || (ilist->funcname != NULL)) {
+ ret += callchain__fprintf_left_margin(fp, left_margin);
+
+ for (i = 0; i < depth; i++) {
+ if (depth_mask & (1 << i))
+ ret += fprintf(fp, "|");
+ else
+ ret += fprintf(fp, " ");
+ ret += fprintf(fp, " ");
+ }
+
+ if (callchain_param.key == CCKEY_ADDRESS ||
+ callchain_param.key == CCKEY_SRCLINE) {
+ if (ilist->filename != NULL)
+ ret += fprintf(fp, "%s:%d (inline)",
+ ilist->filename,
+ ilist->line_nr);
+ else
+ ret += fprintf(fp, "??");
+ } else if (ilist->funcname != NULL)
+ ret += fprintf(fp, "%s (inline)",
+ ilist->funcname);
+ else if (ilist->filename != NULL)
+ ret += fprintf(fp, "%s:%d (inline)",
+ ilist->filename,
+ ilist->line_nr);
+ else
+ ret += fprintf(fp, "??");
+
+ ret += fprintf(fp, "\n");
+ }
+ }
+
+ inline_node__delete(node);
+ return ret;
+}
+
static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask,
int left_margin)
{
fputs(str, fp);
fputc('\n', fp);
free(alloc_str);
+
+ if (symbol_conf.inline_name)
+ ret += inline__fprintf(chain->ms.map, chain->ip,
+ left_margin, depth, depth_mask, fp);
return ret;
}
if (!i++ && field_order == NULL &&
sort_order && !prefixcmp(sort_order, "sym"))
continue;
+
if (!printed) {
ret += callchain__fprintf_left_margin(fp, left_margin);
ret += fprintf(fp, "|\n");
if (++entries_printed == callchain_param.print_limit)
break;
+
+ if (symbol_conf.inline_name)
+ ret += inline__fprintf(chain->ms.map,
+ chain->ip,
+ left_margin,
+ 0, 0,
+ fp);
}
root = &cnode->rb_root;
}
bool use_callchain)
{
int ret;
+ int callchain_ret = 0;
+ int inline_ret = 0;
struct perf_hpp hpp = {
.buf = bf,
.size = size,
ret = fprintf(fp, "%s\n", bf);
if (use_callchain)
- ret += hist_entry_callchain__fprintf(he, total_period, 0, fp);
+ callchain_ret = hist_entry_callchain__fprintf(he, total_period,
+ 0, fp);
+
+ if (callchain_ret == 0 && symbol_conf.inline_name) {
+ inline_ret = inline__fprintf(he->ms.map, he->ip, 0, 0, 0, fp);
+ ret += inline_ret;
+ if (inline_ret > 0)
+ ret += fprintf(fp, "\n");
+ } else
+ ret += callchain_ret;
return ret;
}
#include <errno.h>
#include <signal.h>
#include <stdbool.h>
+#include <linux/kernel.h>
#ifdef HAVE_BACKTRACE_SUPPORT
#include <execinfo.h>
#endif
-libperf-y += alias.o
libperf-y += annotate.o
libperf-y += block-range.o
libperf-y += build-id.o
libperf-y += parse-events.o
libperf-y += perf_regs.o
libperf-y += path.o
+libperf-y += print_binary.o
libperf-y += rbtree.o
libperf-y += libstring.o
libperf-y += bitmap.o
libperf-y += session.o
libperf-$(CONFIG_AUDIT) += syscalltbl.o
libperf-y += ordered-events.o
+libperf-y += namespaces.o
libperf-y += comm.o
libperf-y += thread.o
libperf-y += thread_map.o
libperf-$(CONFIG_AUXTRACE) += intel-pt.o
libperf-$(CONFIG_AUXTRACE) += intel-bts.o
libperf-y += parse-branch-options.o
+libperf-y += dump-insn.o
libperf-y += parse-regs-options.o
libperf-y += term.o
libperf-y += help-unknown-cmd.o
libperf-y += mem-events.o
libperf-y += vsprintf.o
libperf-y += drv_configs.o
+libperf-y += units.o
libperf-y += time-utils.o
+libperf-y += expr-bison.o
libperf-$(CONFIG_LIBBPF) += bpf-loader.o
libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
$(call rule_mkdir)
$(Q)$(call echo-cmd,bison)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $@ -p parse_events_
+$(OUTPUT)util/expr-bison.c: util/expr.y
+ $(call rule_mkdir)
+ $(Q)$(call echo-cmd,bison)$(BISON) -v util/expr.y -d $(PARSER_DEBUG_BISON) -o $@ -p expr__
+
$(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c
$(call rule_mkdir)
$(Q)$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/pmu-flex.h util/pmu.l
CFLAGS_pmu-flex.o += -w
CFLAGS_parse-events-bison.o += -DYYENABLE_NLS=0 -w
CFLAGS_pmu-bison.o += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w
+CFLAGS_expr-bison.o += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w
$(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c
$(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c
+++ /dev/null
-#include "cache.h"
-#include "util.h"
-#include "config.h"
-
-static const char *alias_key;
-static char *alias_val;
-
-static int alias_lookup_cb(const char *k, const char *v,
- void *cb __maybe_unused)
-{
- if (!prefixcmp(k, "alias.") && !strcmp(k+6, alias_key)) {
- if (!v)
- return config_error_nonbool(k);
- alias_val = strdup(v);
- return 0;
- }
- return 0;
-}
-
-char *alias_lookup(const char *alias)
-{
- alias_key = alias;
- alias_val = NULL;
- perf_config(alias_lookup_cb, NULL);
- return alias_val;
-}
-
-int split_cmdline(char *cmdline, const char ***argv)
-{
- int src, dst, count = 0, size = 16;
- char quoted = 0;
-
- *argv = malloc(sizeof(char*) * size);
-
- /* split alias_string */
- (*argv)[count++] = cmdline;
- for (src = dst = 0; cmdline[src];) {
- char c = cmdline[src];
- if (!quoted && isspace(c)) {
- cmdline[dst++] = 0;
- while (cmdline[++src]
- && isspace(cmdline[src]))
- ; /* skip */
- if (count >= size) {
- size += 16;
- *argv = realloc(*argv, sizeof(char*) * size);
- }
- (*argv)[count++] = cmdline + dst;
- } else if (!quoted && (c == '\'' || c == '"')) {
- quoted = c;
- src++;
- } else if (c == quoted) {
- quoted = 0;
- src++;
- } else {
- if (c == '\\' && quoted != '\'') {
- src++;
- c = cmdline[src];
- if (!c) {
- zfree(argv);
- return error("cmdline ends with \\");
- }
- }
- cmdline[dst++] = c;
- src++;
- }
- }
-
- cmdline[dst] = 0;
-
- if (quoted) {
- zfree(argv);
- return error("unclosed quote");
- }
-
- return count;
-}
-
* Released under the GPL v2. (and only v2, not any later version)
*/
+#include <errno.h>
+#include <inttypes.h>
#include "util.h"
#include "ui/ui.h"
#include "sort.h"
#include "annotate.h"
#include "evsel.h"
#include "block-range.h"
+#include "string2.h"
#include "arch/common.h"
#include <regex.h>
#include <pthread.h>
#include <linux/bitops.h>
+#include <linux/kernel.h>
#include <sys/utsname.h>
+#include "sane_ctype.h"
+
const char *disassembler_style;
const char *objdump_path;
static regex_t file_lineno;
#include "arch/arm64/annotate/instructions.c"
#include "arch/x86/annotate/instructions.c"
#include "arch/powerpc/annotate/instructions.c"
+#include "arch/s390/annotate/instructions.c"
static struct arch architectures[] = {
{
.name = "powerpc",
.init = powerpc__annotate_init,
},
+ {
+ .name = "s390",
+ .init = s390__annotate_init,
+ .objdump = {
+ .comment_char = '#',
+ },
+ },
};
static void ins__delete(struct ins_operands *ops)
if (comment == NULL)
return 0;
- while (comment[0] != '\0' && isspace(comment[0]))
- ++comment;
-
+ comment = ltrim(comment);
comment__symbol(ops->source.raw, comment, &ops->source.addr, &ops->source.name);
comment__symbol(ops->target.raw, comment, &ops->target.addr, &ops->target.name);
if (comment == NULL)
return 0;
- while (comment[0] != '\0' && isspace(comment[0]))
- ++comment;
-
+ comment = ltrim(comment);
comment__symbol(ops->target.raw, comment, &ops->target.addr, &ops->target.name);
return 0;
static int disasm_line__parse(char *line, const char **namep, char **rawp)
{
- char *name = line, tmp;
-
- while (isspace(name[0]))
- ++name;
+ char tmp, *name = ltrim(line);
if (name[0] == '\0')
return -1;
goto out_free_name;
(*rawp)[0] = tmp;
-
- if ((*rawp)[0] != '\0') {
- (*rawp)++;
- while (isspace((*rawp)[0]))
- ++(*rawp);
- }
+ *rawp = ltrim(*rawp);
return 0;
{
struct annotation *notes = symbol__annotation(sym);
struct disasm_line *dl;
- char *line = NULL, *parsed_line, *tmp, *tmp2, *c;
+ char *line = NULL, *parsed_line, *tmp, *tmp2;
size_t line_len;
s64 line_ip, offset = -1;
regmatch_t match[2];
if (!line)
return -1;
- while (line_len != 0 && isspace(line[line_len - 1]))
- line[--line_len] = '\0';
-
- c = strchr(line, '\n');
- if (c)
- *c = 0;
-
line_ip = -1;
- parsed_line = line;
+ parsed_line = rtrim(line);
/* /filename:linenr ? Save line number and ignore. */
- if (regexec(&file_lineno, line, 2, match, 0) == 0) {
- *line_nr = atoi(line + match[1].rm_so);
+ if (regexec(&file_lineno, parsed_line, 2, match, 0) == 0) {
+ *line_nr = atoi(parsed_line + match[1].rm_so);
return 0;
}
- /*
- * Strip leading spaces:
- */
- tmp = line;
- while (*tmp) {
- if (*tmp != ' ')
- break;
- tmp++;
- }
-
+ tmp = ltrim(parsed_line);
if (*tmp) {
/*
* Parse hexa addresses followed by ':'
{
char linkname[PATH_MAX];
char *build_id_filename;
+ char *build_id_path = NULL;
if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
!dso__is_kcore(dso))
goto fallback;
}
+ build_id_path = strdup(filename);
+ if (!build_id_path)
+ return -1;
+
+ dirname(build_id_path);
+
if (dso__is_kcore(dso) ||
- readlink(filename, linkname, sizeof(linkname)) < 0 ||
+ readlink(build_id_path, linkname, sizeof(linkname)) < 0 ||
strstr(linkname, DSO__NAME_KALLSYMS) ||
access(filename, R_OK)) {
fallback:
__symbol__join_symfs(filename, filename_size, dso->long_name);
}
+ free(build_id_path);
return 0;
}
snprintf(command, sizeof(command),
"%s %s%s --start-address=0x%016" PRIx64
" --stop-address=0x%016" PRIx64
- " -l -d %s %s -C %s 2>/dev/null|grep -v %s|expand",
+ " -l -d %s %s -C %s 2>/dev/null|grep -v %s:|expand",
objdump_path ? objdump_path : "objdump",
disassembler_style ? "-M " : "",
disassembler_style ? disassembler_style : "",
nline = 0;
while (!feof(file)) {
+ /*
+ * The source code line number (lineno) needs to be kept in
+ * accross calls to symbol__parse_objdump_line(), so that it
+ * can associate it with the instructions till the next one.
+ * See disasm_line__new() and struct disasm_line::line_nr.
+ */
if (symbol__parse_objdump_line(sym, map, arch, file, privsize,
&lineno) < 0)
break;
start = map__rip_2objdump(map, sym->start);
for (i = 0; i < len; i++) {
- u64 offset;
+ u64 offset, nr_samples;
double percent_max = 0.0;
src_line->nr_pcnt = nr_pcnt;
for (k = 0; k < nr_pcnt; k++) {
+ double percent = 0.0;
+
h = annotation__histogram(notes, evidx + k);
- src_line->samples[k].percent = 100.0 * h->addr[i] / h->sum;
+ nr_samples = h->addr[i];
+ if (h->sum)
+ percent = 100.0 * nr_samples / h->sum;
- if (src_line->samples[k].percent > percent_max)
- percent_max = src_line->samples[k].percent;
+ if (percent > percent_max)
+ percent_max = percent;
+ src_line->samples[k].percent = percent;
+ src_line->samples[k].nr = nr_samples;
}
if (percent_max <= 0.5)
goto next;
offset = start + i;
- src_line->path = get_srcline(map->dso, offset, NULL, false);
+ src_line->path = get_srcline(map->dso, offset, NULL,
+ false, true);
insert_source_line(&tmp_root, src_line);
next:
struct source_line_samples {
double percent;
double percent_sum;
- double nr;
+ u64 nr;
};
struct source_line {
*
*/
+#include <inttypes.h>
#include <sys/types.h>
#include <sys/mman.h>
#include <stdbool.h>
-#include <ctype.h>
#include <string.h>
#include <limits.h>
#include <errno.h>
#include "cpumap.h"
#include "thread_map.h"
#include "asm/bug.h"
-#include "symbol/kallsyms.h"
#include "auxtrace.h"
#include <linux/hash.h>
#include "intel-pt.h"
#include "intel-bts.h"
+#include "sane_ctype.h"
+#include "symbol/kallsyms.h"
+
int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
struct auxtrace_mmap_params *mp,
void *userpg, int fd)
filt->addr = start;
if (filt->range && !filt->size && !filt->sym_to) {
filt->size = size;
- no_size = !!size;
+ no_size = !size;
}
}
if (err)
return err;
filt->size = start + size - filt->addr;
- no_size = !!size;
+ no_size = !size;
}
/* The very last symbol in kallsyms does not imply a particular size */
#define __PERF_AUXTRACE_H
#include <sys/types.h>
+#include <errno.h>
#include <stdbool.h>
#include <stddef.h>
#include <linux/list.h>
#include <bpf/libbpf.h>
#include <bpf/bpf.h>
#include <linux/err.h>
+#include <linux/kernel.h>
#include <linux/string.h>
+#include <errno.h>
#include "perf.h"
#include "debug.h"
#include "bpf-loader.h"
#include "probe-event.h"
#include "probe-finder.h" // for MAX_PROBES
#include "parse-events.h"
+#include "strfilter.h"
#include "llvm-utils.h"
#include "c++/clang-c.h"
char *buf, size_t size);
#else
+#include <errno.h>
+
static inline struct bpf_object *
bpf__prepare_load(const char *filename __maybe_unused,
bool source __maybe_unused)
#include "bpf-loader.h"
#include "bpf-prologue.h"
#include "probe-finder.h"
+#include <errno.h>
#include <dwarf-regs.h>
#include <linux/filter.h>
struct bpf_insn *new_prog, size_t *new_cnt,
size_t cnt_space);
#else
+#include <errno.h>
+
static inline int
bpf__gen_prologue(struct probe_trace_arg *args __maybe_unused,
int nargs __maybe_unused,
* Copyright (C) 2009, 2010 Arnaldo Carvalho de Melo <acme@redhat.com>
*/
#include "util.h"
+#include <dirent.h>
+#include <errno.h>
#include <stdio.h>
+#include <sys/stat.h>
+#include <sys/types.h>
#include "build-id.h"
#include "event.h"
#include "symbol.h"
+#include "thread.h"
#include <linux/kernel.h>
#include "debug.h"
#include "session.h"
#include "tool.h"
#include "header.h"
#include "vdso.h"
+#include "path.h"
#include "probe-file.h"
+#include "strlist.h"
+#include "sane_ctype.h"
static bool no_buildid_cache;
char buf[PATH_MAX];
char *ret = NULL, *p;
size_t offs = 5; /* == strlen("../..") */
+ ssize_t len;
linkname = build_id_cache__linkname(sbuild_id, NULL, 0);
if (!linkname)
return NULL;
- if (readlink(linkname, buf, PATH_MAX) < 0)
+ len = readlink(linkname, buf, sizeof(buf) - 1);
+ if (len <= 0)
goto out;
+ buf[len] = '\0';
+
/* The link should be "../..<origpath>/<sbuild_id>" */
p = strrchr(buf, '/'); /* Cut off the "/<sbuild_id>" */
if (p && (p > buf + offs)) {
}
static bool lsdir_bid_head_filter(const char *name __maybe_unused,
- struct dirent *d __maybe_unused)
+ struct dirent *d)
{
return (strlen(d->d_name) == 2) &&
isxdigit(d->d_name[0]) && isxdigit(d->d_name[1]);
}
static bool lsdir_bid_tail_filter(const char *name __maybe_unused,
- struct dirent *d __maybe_unused)
+ struct dirent *d)
{
int i = 0;
while (isxdigit(d->d_name[i]) && i < SBUILD_ID_SIZE - 3)
err = 0;
/* Update SDT cache : error is just warned */
- if (build_id_cache__add_sdt_cache(sbuild_id, realname) < 0)
+ if (realname && build_id_cache__add_sdt_cache(sbuild_id, realname) < 0)
pr_debug4("Failed to update/scan SDT cache for %s\n", realname);
out_free:
#define SBUILD_ID_SIZE (BUILD_ID_SIZE * 2 + 1)
#include "tool.h"
-#include "strlist.h"
#include <linux/types.h>
extern struct perf_tool build_id__mark_dso_hit_ops;
char *build_id_cache__linkname(const char *sbuild_id, char *bf, size_t size);
char *build_id_cache__cachedir(const char *sbuild_id, const char *name,
bool is_kallsyms, bool is_vdso);
+
+struct strlist;
+
struct strlist *build_id_cache__list_all(bool validonly);
char *build_id_cache__complement(const char *incomplete_sbuild_id);
int build_id_cache__list_build_ids(const char *pathname,
size_t *p_obj_buf_sz);
#else
+#include <errno.h>
static inline void perf_clang__init(void) { }
static inline void perf_clang__cleanup(void) { }
#define PERF_TRACEFS_ENVIRONMENT "PERF_TRACEFS_DIR"
#define PERF_PAGER_ENVIRONMENT "PERF_PAGER"
-char *alias_lookup(const char *alias);
int split_cmdline(char *cmdline, const char ***argv);
#define alloc_nr(x) (((x)+16)*3/2)
*
*/
+#include <inttypes.h>
#include <stdlib.h>
#include <stdio.h>
#include <stdbool.h>
#include "machine.h"
#include "callchain.h"
+#define CALLCHAIN_PARAM_DEFAULT \
+ .mode = CHAIN_GRAPH_ABS, \
+ .min_percent = 0.5, \
+ .order = ORDER_CALLEE, \
+ .key = CCKEY_FUNCTION, \
+ .value = CCVAL_PERCENT, \
+
+struct callchain_param callchain_param = {
+ CALLCHAIN_PARAM_DEFAULT
+};
+
+struct callchain_param callchain_param_default = {
+ CALLCHAIN_PARAM_DEFAULT
+};
+
__thread struct callchain_cursor callchain_cursor;
int parse_callchain_record_opt(const char *arg, struct callchain_param *param)
callchain_param.key = CCKEY_ADDRESS;
return 0;
}
+ if (!strncmp(value, "srcline", strlen(value))) {
+ callchain_param.key = CCKEY_SRCLINE;
+ return 0;
+ }
if (!strncmp(value, "branch", strlen(value))) {
callchain_param.branch_callstack = 1;
return 0;
return -1;
}
+static int get_stack_size(const char *str, unsigned long *_size)
+{
+ char *endptr;
+ unsigned long size;
+ unsigned long max_size = round_down(USHRT_MAX, sizeof(u64));
+
+ size = strtoul(str, &endptr, 0);
+
+ do {
+ if (*endptr)
+ break;
+
+ size = round_up(size, sizeof(u64));
+ if (!size || size > max_size)
+ break;
+
+ *_size = size;
+ return 0;
+
+ } while (0);
+
+ pr_err("callchain: Incorrect stack dump size (max %ld): %s\n",
+ max_size, str);
+ return -1;
+}
+
static int
__parse_callchain_report_opt(const char *arg, bool allow_record_opt)
{
char *tok;
- char *endptr;
+ char *endptr, *saveptr = NULL;
bool minpcnt_set = false;
bool record_opt_set = false;
bool try_stack_size = false;
if (!arg)
return 0;
- while ((tok = strtok((char *)arg, ",")) != NULL) {
+ while ((tok = strtok_r((char *)arg, ",", &saveptr)) != NULL) {
if (!strncmp(tok, "none", strlen(tok))) {
callchain_param.mode = CHAIN_NONE;
callchain_param.enabled = false;
return __parse_callchain_report_opt(arg, true);
}
+int parse_callchain_record(const char *arg, struct callchain_param *param)
+{
+ char *tok, *name, *saveptr = NULL;
+ char *buf;
+ int ret = -1;
+
+ /* We need buffer that we know we can write to. */
+ buf = malloc(strlen(arg) + 1);
+ if (!buf)
+ return -ENOMEM;
+
+ strcpy(buf, arg);
+
+ tok = strtok_r((char *)buf, ",", &saveptr);
+ name = tok ? : (char *)buf;
+
+ do {
+ /* Framepointer style */
+ if (!strncmp(name, "fp", sizeof("fp"))) {
+ if (!strtok_r(NULL, ",", &saveptr)) {
+ param->record_mode = CALLCHAIN_FP;
+ ret = 0;
+ } else
+ pr_err("callchain: No more arguments "
+ "needed for --call-graph fp\n");
+ break;
+
+ /* Dwarf style */
+ } else if (!strncmp(name, "dwarf", sizeof("dwarf"))) {
+ const unsigned long default_stack_dump_size = 8192;
+
+ ret = 0;
+ param->record_mode = CALLCHAIN_DWARF;
+ param->dump_size = default_stack_dump_size;
+
+ tok = strtok_r(NULL, ",", &saveptr);
+ if (tok) {
+ unsigned long size = 0;
+
+ ret = get_stack_size(tok, &size);
+ param->dump_size = size;
+ }
+ } else if (!strncmp(name, "lbr", sizeof("lbr"))) {
+ if (!strtok_r(NULL, ",", &saveptr)) {
+ param->record_mode = CALLCHAIN_LBR;
+ ret = 0;
+ } else
+ pr_err("callchain: No more arguments "
+ "needed for --call-graph lbr\n");
+ break;
+ } else {
+ pr_err("callchain: Unknown --call-graph option "
+ "value: %s\n", arg);
+ break;
+ }
+
+ } while (0);
+
+ free(buf);
+ return ret;
+}
+
int perf_callchain_config(const char *var, const char *value)
{
char *endptr;
MATCH_GT,
};
+static enum match_result match_chain_srcline(struct callchain_cursor_node *node,
+ struct callchain_list *cnode)
+{
+ char *left = get_srcline(cnode->ms.map->dso,
+ map__rip_2objdump(cnode->ms.map, cnode->ip),
+ cnode->ms.sym, true, false);
+ char *right = get_srcline(node->map->dso,
+ map__rip_2objdump(node->map, node->ip),
+ node->sym, true, false);
+ enum match_result ret = MATCH_EQ;
+ int cmp;
+
+ if (left && right)
+ cmp = strcmp(left, right);
+ else if (!left && right)
+ cmp = 1;
+ else if (left && !right)
+ cmp = -1;
+ else if (cnode->ip == node->ip)
+ cmp = 0;
+ else
+ cmp = (cnode->ip < node->ip) ? -1 : 1;
+
+ if (cmp != 0)
+ ret = cmp < 0 ? MATCH_LT : MATCH_GT;
+
+ free_srcline(left);
+ free_srcline(right);
+ return ret;
+}
+
static enum match_result match_chain(struct callchain_cursor_node *node,
struct callchain_list *cnode)
{
struct symbol *sym = node->sym;
u64 left, right;
- if (cnode->ms.sym && sym &&
- callchain_param.key == CCKEY_FUNCTION) {
+ if (callchain_param.key == CCKEY_SRCLINE) {
+ enum match_result match = match_chain_srcline(node, cnode);
+
+ if (match != MATCH_ERROR)
+ return match;
+ }
+
+ if (cnode->ms.sym && sym && callchain_param.key == CCKEY_FUNCTION) {
left = cnode->ms.sym->start;
right = sym->start;
} else {
char *callchain_list__sym_name(struct callchain_list *cl,
char *bf, size_t bfsize, bool show_dso)
{
+ bool show_addr = callchain_param.key == CCKEY_ADDRESS;
+ bool show_srcline = show_addr || callchain_param.key == CCKEY_SRCLINE;
int printed;
if (cl->ms.sym) {
- if (callchain_param.key == CCKEY_ADDRESS &&
- cl->ms.map && !cl->srcline)
+ if (show_srcline && cl->ms.map && !cl->srcline)
cl->srcline = get_srcline(cl->ms.map->dso,
map__rip_2objdump(cl->ms.map,
cl->ip),
- cl->ms.sym, false);
+ cl->ms.sym, false, show_addr);
if (cl->srcline)
printed = scnprintf(bf, bfsize, "%s %s",
cl->ms.sym->name, cl->srcline);
cycles_count);
}
-static int callchain_counts_printf(FILE *fp, char *bf, int bfsize,
- u64 branch_count, u64 predicted_count,
- u64 abort_count, u64 cycles_count,
- u64 iter_count, u64 samples_count)
+static int counts_str_build(char *bf, int bfsize,
+ u64 branch_count, u64 predicted_count,
+ u64 abort_count, u64 cycles_count,
+ u64 iter_count, u64 samples_count)
{
double predicted_percent = 0.0;
const char *null_str = "";
char iter_str[32];
- char *str;
- u64 cycles = 0;
-
- if (branch_count == 0) {
- if (fp)
- return fprintf(fp, " (calltrace)");
+ char cycle_str[32];
+ char *istr, *cstr;
+ u64 cycles;
+ if (branch_count == 0)
return scnprintf(bf, bfsize, " (calltrace)");
- }
+
+ cycles = cycles_count / branch_count;
if (iter_count && samples_count) {
- scnprintf(iter_str, sizeof(iter_str),
- ", iterations:%" PRId64 "",
- iter_count / samples_count);
- str = iter_str;
+ if (cycles > 0)
+ scnprintf(iter_str, sizeof(iter_str),
+ " iterations:%" PRId64 "",
+ iter_count / samples_count);
+ else
+ scnprintf(iter_str, sizeof(iter_str),
+ "iterations:%" PRId64 "",
+ iter_count / samples_count);
+ istr = iter_str;
+ } else
+ istr = (char *)null_str;
+
+ if (cycles > 0) {
+ scnprintf(cycle_str, sizeof(cycle_str),
+ "cycles:%" PRId64 "", cycles);
+ cstr = cycle_str;
} else
- str = (char *)null_str;
+ cstr = (char *)null_str;
predicted_percent = predicted_count * 100.0 / branch_count;
- cycles = cycles_count / branch_count;
- if ((predicted_percent >= 100.0) && (abort_count == 0)) {
- if (fp)
- return fprintf(fp, " (cycles:%" PRId64 "%s)",
- cycles, str);
+ if ((predicted_count == branch_count) && (abort_count == 0)) {
+ if ((cycles > 0) || (istr != (char *)null_str))
+ return scnprintf(bf, bfsize, " (%s%s)", cstr, istr);
+ else
+ return scnprintf(bf, bfsize, "%s", (char *)null_str);
+ }
- return scnprintf(bf, bfsize, " (cycles:%" PRId64 "%s)",
- cycles, str);
+ if ((predicted_count < branch_count) && (abort_count == 0)) {
+ if ((cycles > 0) || (istr != (char *)null_str))
+ return scnprintf(bf, bfsize,
+ " (predicted:%.1f%% %s%s)",
+ predicted_percent, cstr, istr);
+ else {
+ return scnprintf(bf, bfsize,
+ " (predicted:%.1f%%)",
+ predicted_percent);
+ }
}
- if ((predicted_percent < 100.0) && (abort_count == 0)) {
- if (fp)
- return fprintf(fp,
- " (predicted:%.1f%%, cycles:%" PRId64 "%s)",
- predicted_percent, cycles, str);
+ if ((predicted_count == branch_count) && (abort_count > 0)) {
+ if ((cycles > 0) || (istr != (char *)null_str))
+ return scnprintf(bf, bfsize,
+ " (abort:%" PRId64 " %s%s)",
+ abort_count, cstr, istr);
+ else
+ return scnprintf(bf, bfsize,
+ " (abort:%" PRId64 ")",
+ abort_count);
+ }
+ if ((cycles > 0) || (istr != (char *)null_str))
return scnprintf(bf, bfsize,
- " (predicted:%.1f%%, cycles:%" PRId64 "%s)",
- predicted_percent, cycles, str);
- }
+ " (predicted:%.1f%% abort:%" PRId64 " %s%s)",
+ predicted_percent, abort_count, cstr, istr);
+
+ return scnprintf(bf, bfsize,
+ " (predicted:%.1f%% abort:%" PRId64 ")",
+ predicted_percent, abort_count);
+}
+
+static int callchain_counts_printf(FILE *fp, char *bf, int bfsize,
+ u64 branch_count, u64 predicted_count,
+ u64 abort_count, u64 cycles_count,
+ u64 iter_count, u64 samples_count)
+{
+ char str[128];
+
+ counts_str_build(str, sizeof(str), branch_count,
+ predicted_count, abort_count, cycles_count,
+ iter_count, samples_count);
if (fp)
- return fprintf(fp,
- " (predicted:%.1f%%, abort:%" PRId64 ", cycles:%" PRId64 "%s)",
- predicted_percent, abort_count, cycles, str);
+ return fprintf(fp, "%s", str);
- return scnprintf(bf, bfsize,
- " (predicted:%.1f%%, abort:%" PRId64 ", cycles:%" PRId64 "%s)",
- predicted_percent, abort_count, cycles, str);
+ return scnprintf(bf, bfsize, "%s", str);
}
int callchain_list_counts__printf_value(struct callchain_node *node,
enum chain_key {
CCKEY_FUNCTION,
- CCKEY_ADDRESS
+ CCKEY_ADDRESS,
+ CCKEY_SRCLINE
};
enum chain_value {
#include "evsel.h"
#include "cgroup.h"
#include "evlist.h"
+#include <linux/stringify.h>
int nr_cgroups;
path_v1[0] = '\0';
path_v2[0] = '\0';
- while (fscanf(fp, "%*s %"STR(PATH_MAX)"s %"STR(PATH_MAX)"s %"
- STR(PATH_MAX)"s %*d %*d\n",
+ while (fscanf(fp, "%*s %"__stringify(PATH_MAX)"s %"__stringify(PATH_MAX)"s %"
+ __stringify(PATH_MAX)"s %*d %*d\n",
mountpoint, type, tokens) == 3) {
if (!path_v1[0] && !strcmp(type, "cgroup")) {
goto found;
n++;
}
- if (atomic_read(&cgrp->refcnt) == 0)
+ if (refcount_read(&cgrp->refcnt) == 0)
free(cgrp);
return -1;
found:
- atomic_inc(&cgrp->refcnt);
+ refcount_inc(&cgrp->refcnt);
counter->cgrp = cgrp;
return 0;
}
void close_cgroup(struct cgroup_sel *cgrp)
{
- if (cgrp && atomic_dec_and_test(&cgrp->refcnt)) {
+ if (cgrp && refcount_dec_and_test(&cgrp->refcnt)) {
close(cgrp->fd);
zfree(&cgrp->name);
free(cgrp);
#ifndef __CGROUP_H__
#define __CGROUP_H__
-#include <linux/atomic.h>
+#include <linux/refcount.h>
struct option;
struct cgroup_sel {
char *name;
int fd;
- atomic_t refcnt;
+ refcount_t refcnt;
};
+#include <errno.h>
#include <sched.h>
#include "util.h"
#include "../perf.h"
unsigned long perf_event_open_cloexec_flag(void);
-#ifdef __GLIBC_PREREQ
-#if !__GLIBC_PREREQ(2, 6) && !defined(__UCLIBC__)
-int sched_getcpu(void) __THROW;
-#endif
-#endif
-
#endif /* __PERF_CLOEXEC_H */
#ifndef __PERF_COLOR_H
#define __PERF_COLOR_H
+#include <stdio.h>
+
/* "\033[1;38;5;2xx;48;5;2xxm\0" is 23 bytes */
#define COLOR_MAXLEN 24
#include "comm.h"
#include "util.h"
+#include <errno.h>
#include <stdlib.h>
#include <stdio.h>
-#include <linux/atomic.h>
+#include <string.h>
+#include <linux/refcount.h>
struct comm_str {
char *str;
struct rb_node rb_node;
- atomic_t refcnt;
+ refcount_t refcnt;
};
/* Should perhaps be moved to struct machine */
static struct comm_str *comm_str__get(struct comm_str *cs)
{
if (cs)
- atomic_inc(&cs->refcnt);
+ refcount_inc(&cs->refcnt);
return cs;
}
static void comm_str__put(struct comm_str *cs)
{
- if (cs && atomic_dec_and_test(&cs->refcnt)) {
+ if (cs && refcount_dec_and_test(&cs->refcnt)) {
rb_erase(&cs->rb_node, &comm_str_root);
zfree(&cs->str);
free(cs);
return NULL;
}
- atomic_set(&cs->refcnt, 0);
+ refcount_set(&cs->refcnt, 1);
return cs;
}
cmp = strcmp(str, iter->str);
if (!cmp)
- return iter;
+ return comm_str__get(iter);
if (cmp < 0)
p = &(*p)->rb_left;
return NULL;
}
- comm_str__get(comm->comm_str);
-
return comm;
}
if (!new)
return -ENOMEM;
- comm_str__get(new);
comm_str__put(old);
comm->comm_str = new;
comm->start = timestamp;
--- /dev/null
+#ifndef PERF_COMPRESS_H
+#define PERF_COMPRESS_H
+
+#ifdef HAVE_ZLIB_SUPPORT
+int gzip_decompress_to_file(const char *input, int output_fd);
+#endif
+
+#ifdef HAVE_LZMA_SUPPORT
+int lzma_decompress_to_file(const char *input, int output_fd);
+#endif
+
+#endif /* PERF_COMPRESS_H */
* Copyright (C) Johannes Schindelin, 2005
*
*/
+#include <errno.h>
+#include <sys/param.h>
#include "util.h"
#include "cache.h"
#include <subcmd/exec-cmd.h>
#include "util/hist.h" /* perf_hist_config */
#include "util/llvm-utils.h" /* perf_llvm_config */
#include "config.h"
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+
+#include "sane_ctype.h"
#define MAXNAME (256)
{
int ret = -1;
const char *home = NULL;
+ char *user_config;
+ struct stat st;
/* Setting $PERF_CONFIG makes perf read _only_ the given config file. */
if (config_exclusive_filename)
}
home = getenv("HOME");
- if (perf_config_global() && home) {
- char *user_config = strdup(mkpath("%s/.perfconfig", home));
- struct stat st;
- if (user_config == NULL) {
- warning("Not enough memory to process %s/.perfconfig, "
- "ignoring it.", home);
- goto out;
- }
+ /*
+ * Skip reading user config if:
+ * - there is no place to read it from (HOME)
+ * - we are asked not to (PERF_CONFIG_NOGLOBAL=1)
+ */
+ if (!home || !*home || !perf_config_global())
+ return 0;
- if (stat(user_config, &st) < 0) {
- if (errno == ENOENT)
- ret = 0;
- goto out_free;
- }
+ user_config = strdup(mkpath("%s/.perfconfig", home));
+ if (user_config == NULL) {
+ warning("Not enough memory to process %s/.perfconfig, "
+ "ignoring it.", home);
+ goto out;
+ }
- ret = 0;
+ if (stat(user_config, &st) < 0) {
+ if (errno == ENOENT)
+ ret = 0;
+ goto out_free;
+ }
- if (st.st_uid && (st.st_uid != geteuid())) {
- warning("File %s not owned by current user or root, "
- "ignoring it.", user_config);
- goto out_free;
- }
+ ret = 0;
- if (st.st_size)
- ret = perf_config_from_file(collect_config, user_config, set);
-out_free:
- free(user_config);
+ if (st.st_uid && (st.st_uid != geteuid())) {
+ warning("File %s not owned by current user or root, "
+ "ignoring it.", user_config);
+ goto out_free;
}
+
+ if (st.st_size)
+ ret = perf_config_from_file(collect_config, user_config, set);
+
+out_free:
+ free(user_config);
out:
return ret;
}
+#include <errno.h>
#include <stdlib.h>
#include "evsel.h"
#include "counts.h"
+#include "util.h"
struct perf_counts *perf_counts__new(int ncpus, int nthreads)
{
#include "../perf.h"
#include "cpumap.h"
#include <assert.h>
+#include <dirent.h>
#include <stdio.h>
#include <stdlib.h>
#include <linux/bitmap.h>
#include "asm/bug.h"
+#include "sane_ctype.h"
+
static int max_cpu_num;
static int max_present_cpu_num;
static int max_node_num;
cpus->map[i] = i;
cpus->nr = nr_cpus;
- atomic_set(&cpus->refcnt, 1);
+ refcount_set(&cpus->refcnt, 1);
}
return cpus;
if (cpus != NULL) {
cpus->nr = nr_cpus;
memcpy(cpus->map, tmp_cpus, payload_size);
- atomic_set(&cpus->refcnt, 1);
+ refcount_set(&cpus->refcnt, 1);
}
return cpus;
if (cpus != NULL) {
cpus->nr = 1;
cpus->map[0] = -1;
- atomic_set(&cpus->refcnt, 1);
+ refcount_set(&cpus->refcnt, 1);
}
return cpus;
for (i = 0; i < nr; i++)
cpus->map[i] = -1;
- atomic_set(&cpus->refcnt, 1);
+ refcount_set(&cpus->refcnt, 1);
}
return cpus;
static void cpu_map__delete(struct cpu_map *map)
{
if (map) {
- WARN_ONCE(atomic_read(&map->refcnt) != 0,
+ WARN_ONCE(refcount_read(&map->refcnt) != 0,
"cpu_map refcnt unbalanced\n");
free(map);
}
struct cpu_map *cpu_map__get(struct cpu_map *map)
{
if (map)
- atomic_inc(&map->refcnt);
+ refcount_inc(&map->refcnt);
return map;
}
void cpu_map__put(struct cpu_map *map)
{
- if (map && atomic_dec_and_test(&map->refcnt))
+ if (map && refcount_dec_and_test(&map->refcnt))
cpu_map__delete(map);
}
/* ensure we process id in increasing order */
qsort(c->map, c->nr, sizeof(int), cmp_ids);
- atomic_set(&c->refcnt, 1);
+ refcount_set(&c->refcnt, 1);
*res = c;
return 0;
}
pr_debug("cpumask list: %s\n", buf);
return ret;
}
+
+static char hex_char(unsigned char val)
+{
+ if (val < 10)
+ return val + '0';
+ if (val < 16)
+ return val - 10 + 'a';
+ return '?';
+}
+
+size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size)
+{
+ int i, cpu;
+ char *ptr = buf;
+ unsigned char *bitmap;
+ int last_cpu = cpu_map__cpu(map, map->nr - 1);
+
+ bitmap = zalloc((last_cpu + 7) / 8);
+ if (bitmap == NULL) {
+ buf[0] = '\0';
+ return 0;
+ }
+
+ for (i = 0; i < map->nr; i++) {
+ cpu = cpu_map__cpu(map, i);
+ bitmap[cpu / 8] |= 1 << (cpu % 8);
+ }
+
+ for (cpu = last_cpu / 4 * 4; cpu >= 0; cpu -= 4) {
+ unsigned char bits = bitmap[cpu / 8];
+
+ if (cpu % 8)
+ bits >>= 4;
+ else
+ bits &= 0xf;
+
+ *ptr++ = hex_char(bits);
+ if ((cpu % 32) == 0 && cpu > 0)
+ *ptr++ = ',';
+ }
+ *ptr = '\0';
+ free(bitmap);
+
+ buf[size - 1] = '\0';
+ return ptr - buf;
+}
#include <stdio.h>
#include <stdbool.h>
-#include <linux/atomic.h>
+#include <linux/refcount.h>
#include "perf.h"
#include "util/debug.h"
struct cpu_map {
- atomic_t refcnt;
+ refcount_t refcnt;
int nr;
int map[];
};
struct cpu_map *cpu_map__new_data(struct cpu_map_data *data);
struct cpu_map *cpu_map__read(FILE *file);
size_t cpu_map__snprint(struct cpu_map *map, char *buf, size_t size);
+size_t cpu_map__snprint_mask(struct cpu_map *map, char *buf, size_t size);
size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp);
int cpu_map__get_socket_id(int cpu);
int cpu_map__get_socket(struct cpu_map *map, int idx, void *data);
*
* No surprises, and works with signed and unsigned chars.
*/
-#include "util.h"
+#include "sane_ctype.h"
enum {
S = GIT_SPACE,
* Released under the GPL v2. (and only v2, not any later version)
*/
+#include <errno.h>
+#include <inttypes.h>
#include <linux/compiler.h>
+#include <linux/kernel.h>
#include <babeltrace/ctf-writer/writer.h>
#include <babeltrace/ctf-writer/clock.h>
#include <babeltrace/ctf-writer/stream.h>
#include "evsel.h"
#include "machine.h"
#include "config.h"
+#include "sane_ctype.h"
#define pr_N(n, fmt, ...) \
eprintf(n, debug_data_convert, fmt, ##__VA_ARGS__)
.lost = perf_event__process_lost,
.tracing_data = perf_event__process_tracing_data,
.build_id = perf_event__process_build_id,
+ .namespaces = perf_event__process_namespaces,
.ordered_events = true,
.ordering_requires_timestamps = true,
},
#include <linux/kernel.h>
#include <sys/types.h>
#include <sys/stat.h>
+#include <errno.h>
#include <unistd.h>
#include <string.h>
#include "../perf.h"
+#include <inttypes.h>
#include <string.h>
#include <stdarg.h>
#include <stdio.h>
+#include <sys/wait.h>
#include <api/debug.h>
#include <linux/time64.h>
-
+#ifdef HAVE_BACKTRACE_SUPPORT
+#include <execinfo.h>
+#endif
#include "cache.h"
#include "color.h"
#include "event.h"
#include "debug.h"
+#include "print_binary.h"
#include "util.h"
#include "target.h"
+#include "sane_ctype.h"
+
int verbose;
bool dump_trace = false, quiet = false;
int debug_ordered_events;
{
libapi_set_print(pr_warning_wrapper, pr_warning_wrapper, pr_debug_wrapper);
}
+
+/* Obtain a backtrace and print it to stdout. */
+#ifdef HAVE_BACKTRACE_SUPPORT
+void dump_stack(void)
+{
+ void *array[16];
+ size_t size = backtrace(array, ARRAY_SIZE(array));
+ char **strings = backtrace_symbols(array, size);
+ size_t i;
+
+ printf("Obtained %zd stack frames.\n", size);
+
+ for (i = 0; i < size; i++)
+ printf("%s\n", strings[i]);
+
+ free(strings);
+}
+#else
+void dump_stack(void) {}
+#endif
+
+void sighandler_dump_stack(int sig)
+{
+ psignal(sig, "perf");
+ dump_stack();
+ signal(sig, SIG_DFL);
+ raise(sig);
+}
void perf_debug_setup(void);
int perf_quiet_option(void);
+void dump_stack(void);
+void sighandler_dump_stack(int sig);
+
#endif /* __PERF_DEBUG_H */
#include "demangle-java.h"
+#include "sane_ctype.h"
+
enum {
MODE_PREFIX = 0,
MODE_CLASS = 1,
#include "evlist.h"
#include "evsel.h"
#include "pmu.h"
+#include <errno.h>
static int
perf_evsel__apply_drv_configs(struct perf_evsel *evsel,
#include <asm/bug.h>
+#include <linux/kernel.h>
#include <sys/time.h>
#include <sys/resource.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <errno.h>
+#include "compress.h"
+#include "path.h"
#include "symbol.h"
#include "dso.h"
#include "machine.h"
#include "auxtrace.h"
#include "util.h"
#include "debug.h"
+#include "string2.h"
#include "vdso.h"
static const char * const debuglink_paths[] = {
INIT_LIST_HEAD(&dso->node);
INIT_LIST_HEAD(&dso->data.open_entry);
pthread_mutex_init(&dso->lock, NULL);
- atomic_set(&dso->refcnt, 1);
+ refcount_set(&dso->refcnt, 1);
}
return dso;
struct dso *dso__get(struct dso *dso)
{
if (dso)
- atomic_inc(&dso->refcnt);
+ refcount_inc(&dso->refcnt);
return dso;
}
void dso__put(struct dso *dso)
{
- if (dso && atomic_dec_and_test(&dso->refcnt))
+ if (dso && refcount_dec_and_test(&dso->refcnt))
dso__delete(dso);
}
#ifndef __PERF_DSO
#define __PERF_DSO
-#include <linux/atomic.h>
+#include <linux/refcount.h>
#include <linux/types.h>
#include <linux/rbtree.h>
#include <sys/types.h>
void *priv;
u64 db_id;
};
- atomic_t refcnt;
+ refcount_t refcnt;
char name[0];
};
--- /dev/null
+#include <linux/compiler.h>
+#include "dump-insn.h"
+
+/* Fallback code */
+
+__weak
+const char *dump_insn(struct perf_insn *x __maybe_unused,
+ u64 ip __maybe_unused, u8 *inbuf __maybe_unused,
+ int inlen __maybe_unused, int *lenp)
+{
+ if (lenp)
+ *lenp = 0;
+ return "?";
+}
--- /dev/null
+#ifndef __PERF_DUMP_INSN_H
+#define __PERF_DUMP_INSN_H 1
+
+#define MAXINSN 15
+
+#include <linux/types.h>
+
+struct thread;
+
+struct perf_insn {
+ /* Initialized by callers: */
+ struct thread *thread;
+ u8 cpumode;
+ bool is64bit;
+ int cpu;
+ /* Temporary */
+ char out[256];
+};
+
+const char *dump_insn(struct perf_insn *x, u64 ip,
+ u8 *inbuf, int inlen, int *lenp);
+#endif
*
*/
+#include <errno.h>
+#include <inttypes.h>
#include <stdbool.h>
#include "util.h"
#include "debug.h"
#include "dwarf-aux.h"
+#include "string2.h"
/**
* cu_find_realpath - Find the realpath of the target file
#include <debug.h>
#include <dwarf-regs.h>
#include <elf.h>
+#include <linux/kernel.h>
#ifndef EM_AARCH64
#define EM_AARCH64 183 /* ARM 64 bit */
#include "cpumap.h"
#include "env.h"
#include "util.h"
+#include <errno.h>
struct perf_env perf_env;
+#include <dirent.h>
+#include <errno.h>
+#include <inttypes.h>
+#include <linux/kernel.h>
#include <linux/types.h>
-#include <linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
#include <api/fs/fs.h>
#include "event.h"
#include "debug.h"
#include "hist.h"
#include "machine.h"
#include "sort.h"
-#include "string.h"
+#include "string2.h"
#include "strlist.h"
#include "thread.h"
#include "thread_map.h"
+#include "sane_ctype.h"
#include "symbol/kallsyms.h"
#include "asm/bug.h"
#include "stat.h"
[PERF_RECORD_LOST_SAMPLES] = "LOST_SAMPLES",
[PERF_RECORD_SWITCH] = "SWITCH",
[PERF_RECORD_SWITCH_CPU_WIDE] = "SWITCH_CPU_WIDE",
+ [PERF_RECORD_NAMESPACES] = "NAMESPACES",
[PERF_RECORD_HEADER_ATTR] = "ATTR",
[PERF_RECORD_HEADER_EVENT_TYPE] = "EVENT_TYPE",
[PERF_RECORD_HEADER_TRACING_DATA] = "TRACING_DATA",
[PERF_RECORD_TIME_CONV] = "TIME_CONV",
};
+static const char *perf_ns__names[] = {
+ [NET_NS_INDEX] = "net",
+ [UTS_NS_INDEX] = "uts",
+ [IPC_NS_INDEX] = "ipc",
+ [PID_NS_INDEX] = "pid",
+ [USER_NS_INDEX] = "user",
+ [MNT_NS_INDEX] = "mnt",
+ [CGROUP_NS_INDEX] = "cgroup",
+};
+
const char *perf_event__name(unsigned int id)
{
if (id >= ARRAY_SIZE(perf_event__names))
return perf_event__names[id];
}
+static const char *perf_ns__name(unsigned int id)
+{
+ if (id >= ARRAY_SIZE(perf_ns__names))
+ return "UNKNOWN";
+ return perf_ns__names[id];
+}
+
static int perf_tool__process_synth_event(struct perf_tool *tool,
union perf_event *event,
struct machine *machine,
int fd;
size_t size = 0;
ssize_t n;
- char *nl, *name, *tgids, *ppids;
+ char *name, *tgids, *ppids;
*tgid = -1;
*ppid = -1;
ppids = strstr(bf, "PPid:");
if (name) {
- name += 5; /* strlen("Name:") */
+ char *nl;
- while (*name && isspace(*name))
- ++name;
+ name += 5; /* strlen("Name:") */
+ name = ltrim(name);
nl = strchr(name, '\n');
if (nl)
return tgid;
}
+static void perf_event__get_ns_link_info(pid_t pid, const char *ns,
+ struct perf_ns_link_info *ns_link_info)
+{
+ struct stat64 st;
+ char proc_ns[128];
+
+ sprintf(proc_ns, "/proc/%u/ns/%s", pid, ns);
+ if (stat64(proc_ns, &st) == 0) {
+ ns_link_info->dev = st.st_dev;
+ ns_link_info->ino = st.st_ino;
+ }
+}
+
+int perf_event__synthesize_namespaces(struct perf_tool *tool,
+ union perf_event *event,
+ pid_t pid, pid_t tgid,
+ perf_event__handler_t process,
+ struct machine *machine)
+{
+ u32 idx;
+ struct perf_ns_link_info *ns_link_info;
+
+ if (!tool || !tool->namespace_events)
+ return 0;
+
+ memset(&event->namespaces, 0, (sizeof(event->namespaces) +
+ (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+ machine->id_hdr_size));
+
+ event->namespaces.pid = tgid;
+ event->namespaces.tid = pid;
+
+ event->namespaces.nr_namespaces = NR_NAMESPACES;
+
+ ns_link_info = event->namespaces.link_info;
+
+ for (idx = 0; idx < event->namespaces.nr_namespaces; idx++)
+ perf_event__get_ns_link_info(pid, perf_ns__name(idx),
+ &ns_link_info[idx]);
+
+ event->namespaces.header.type = PERF_RECORD_NAMESPACES;
+
+ event->namespaces.header.size = (sizeof(event->namespaces) +
+ (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+ machine->id_hdr_size);
+
+ if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
+ return -1;
+
+ return 0;
+}
+
static int perf_event__synthesize_fork(struct perf_tool *tool,
union perf_event *event,
pid_t pid, pid_t tgid, pid_t ppid,
if (machine__is_default_guest(machine))
return 0;
- snprintf(filename, sizeof(filename), "%s/proc/%d/maps",
- machine->root_dir, pid);
+ snprintf(filename, sizeof(filename), "%s/proc/%d/task/%d/maps",
+ machine->root_dir, pid, pid);
fp = fopen(filename, "r");
if (fp == NULL) {
static int __event__synthesize_thread(union perf_event *comm_event,
union perf_event *mmap_event,
union perf_event *fork_event,
+ union perf_event *namespaces_event,
pid_t pid, int full,
- perf_event__handler_t process,
+ perf_event__handler_t process,
struct perf_tool *tool,
struct machine *machine,
bool mmap_data,
if (tgid == -1)
return -1;
+ if (perf_event__synthesize_namespaces(tool, namespaces_event, pid,
+ tgid, process, machine) < 0)
+ return -1;
+
+
return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
process, machine, mmap_data,
proc_map_timeout);
if (perf_event__synthesize_fork(tool, fork_event, _pid, tgid,
ppid, process, machine) < 0)
break;
+
+ if (perf_event__synthesize_namespaces(tool, namespaces_event, _pid,
+ tgid, process, machine) < 0)
+ break;
+
/*
* Send the prepared comm event
*/
unsigned int proc_map_timeout)
{
union perf_event *comm_event, *mmap_event, *fork_event;
+ union perf_event *namespaces_event;
int err = -1, thread, j;
comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
if (fork_event == NULL)
goto out_free_mmap;
+ namespaces_event = malloc(sizeof(namespaces_event->namespaces) +
+ (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+ machine->id_hdr_size);
+ if (namespaces_event == NULL)
+ goto out_free_fork;
+
err = 0;
for (thread = 0; thread < threads->nr; ++thread) {
if (__event__synthesize_thread(comm_event, mmap_event,
- fork_event,
+ fork_event, namespaces_event,
thread_map__pid(threads, thread), 0,
process, tool, machine,
mmap_data, proc_map_timeout)) {
/* if not, generate events for it */
if (need_leader &&
__event__synthesize_thread(comm_event, mmap_event,
- fork_event,
+ fork_event, namespaces_event,
comm_event->comm.pid, 0,
process, tool, machine,
mmap_data, proc_map_timeout)) {
}
}
}
+ free(namespaces_event);
+out_free_fork:
free(fork_event);
out_free_mmap:
free(mmap_event);
char proc_path[PATH_MAX];
struct dirent *dirent;
union perf_event *comm_event, *mmap_event, *fork_event;
+ union perf_event *namespaces_event;
int err = -1;
if (machine__is_default_guest(machine))
if (fork_event == NULL)
goto out_free_mmap;
+ namespaces_event = malloc(sizeof(namespaces_event->namespaces) +
+ (NR_NAMESPACES * sizeof(struct perf_ns_link_info)) +
+ machine->id_hdr_size);
+ if (namespaces_event == NULL)
+ goto out_free_fork;
+
snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
proc = opendir(proc_path);
if (proc == NULL)
- goto out_free_fork;
+ goto out_free_namespaces;
while ((dirent = readdir(proc)) != NULL) {
char *end;
* We may race with exiting thread, so don't stop just because
* one thread couldn't be synthesized.
*/
- __event__synthesize_thread(comm_event, mmap_event, fork_event, pid,
- 1, process, tool, machine, mmap_data,
+ __event__synthesize_thread(comm_event, mmap_event, fork_event,
+ namespaces_event, pid, 1, process,
+ tool, machine, mmap_data,
proc_map_timeout);
}
err = 0;
closedir(proc);
+out_free_namespaces:
+ free(namespaces_event);
out_free_fork:
free(fork_event);
out_free_mmap:
return fprintf(fp, "%s: %s:%d/%d\n", s, event->comm.comm, event->comm.pid, event->comm.tid);
}
+size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp)
+{
+ size_t ret = 0;
+ struct perf_ns_link_info *ns_link_info;
+ u32 nr_namespaces, idx;
+
+ ns_link_info = event->namespaces.link_info;
+ nr_namespaces = event->namespaces.nr_namespaces;
+
+ ret += fprintf(fp, " %d/%d - nr_namespaces: %u\n\t\t[",
+ event->namespaces.pid,
+ event->namespaces.tid,
+ nr_namespaces);
+
+ for (idx = 0; idx < nr_namespaces; idx++) {
+ if (idx && (idx % 4 == 0))
+ ret += fprintf(fp, "\n\t\t ");
+
+ ret += fprintf(fp, "%u/%s: %" PRIu64 "/%#" PRIx64 "%s", idx,
+ perf_ns__name(idx), (u64)ns_link_info[idx].dev,
+ (u64)ns_link_info[idx].ino,
+ ((idx + 1) != nr_namespaces) ? ", " : "]\n");
+ }
+
+ return ret;
+}
+
int perf_event__process_comm(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_sample *sample,
return machine__process_comm_event(machine, event, sample);
}
+int perf_event__process_namespaces(struct perf_tool *tool __maybe_unused,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine)
+{
+ return machine__process_namespaces_event(machine, event, sample);
+}
+
int perf_event__process_lost(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_sample *sample,
size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp)
{
- return fprintf(fp, " offset: %#"PRIx64" size: %#"PRIx64" flags: %#"PRIx64" [%s%s]\n",
+ return fprintf(fp, " offset: %#"PRIx64" size: %#"PRIx64" flags: %#"PRIx64" [%s%s%s]\n",
event->aux.aux_offset, event->aux.aux_size,
event->aux.flags,
event->aux.flags & PERF_AUX_FLAG_TRUNCATED ? "T" : "",
- event->aux.flags & PERF_AUX_FLAG_OVERWRITE ? "O" : "");
+ event->aux.flags & PERF_AUX_FLAG_OVERWRITE ? "O" : "",
+ event->aux.flags & PERF_AUX_FLAG_PARTIAL ? "P" : "");
}
size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp)
case PERF_RECORD_MMAP:
ret += perf_event__fprintf_mmap(event, fp);
break;
+ case PERF_RECORD_NAMESPACES:
+ ret += perf_event__fprintf_namespaces(event, fp);
+ break;
case PERF_RECORD_MMAP2:
ret += perf_event__fprintf_mmap2(event, fp);
break;
#include <limits.h>
#include <stdio.h>
+#include <linux/kernel.h>
#include "../perf.h"
-#include "map.h"
#include "build-id.h"
#include "perf_regs.h"
char comm[16];
};
+struct namespaces_event {
+ struct perf_event_header header;
+ u32 pid, tid;
+ u64 nr_namespaces;
+ struct perf_ns_link_info link_info[];
+};
+
struct fork_event {
struct perf_event_header header;
u32 pid, ppid;
u64 total_lost;
u64 total_lost_samples;
u64 total_aux_lost;
+ u64 total_aux_partial;
u64 total_invalid_chains;
u32 nr_events[PERF_RECORD_HEADER_MAX];
u32 nr_non_filtered_samples;
struct mmap_event mmap;
struct mmap2_event mmap2;
struct comm_event comm;
+ struct namespaces_event namespaces;
struct fork_event fork;
struct lost_event lost;
struct lost_samples_event lost_samples;
union perf_event *event,
struct perf_sample *sample,
struct machine *machine);
+int perf_event__process_namespaces(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine);
int perf_event__process_mmap(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
perf_event__handler_t process,
struct machine *machine);
+int perf_event__synthesize_namespaces(struct perf_tool *tool,
+ union perf_event *event,
+ pid_t pid, pid_t tgid,
+ perf_event__handler_t process,
+ struct machine *machine);
+
int perf_event__synthesize_mmap_events(struct perf_tool *tool,
union perf_event *event,
pid_t pid, pid_t tgid,
size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp);
size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp);
size_t perf_event__fprintf(union perf_event *event, FILE *fp);
u64 kallsyms__get_function_start(const char *kallsyms_filename,
*/
#include "util.h"
#include <api/fs/fs.h>
+#include <errno.h>
+#include <inttypes.h>
#include <poll.h>
#include "cpumap.h"
#include "thread_map.h"
#include "evlist.h"
#include "evsel.h"
#include "debug.h"
+#include "units.h"
#include "asm/bug.h"
+#include <signal.h>
#include <unistd.h>
#include "parse-events.h"
#include <subcmd/parse-options.h>
+#include <sys/ioctl.h>
#include <sys/mman.h>
#include <linux/bitops.h>
/*
* Check if event was unmapped due to a POLLHUP/POLLERR.
*/
- if (!atomic_read(&md->refcnt))
+ if (!refcount_read(&md->refcnt))
return NULL;
head = perf_mmap__read_head(md);
/*
* Check if event was unmapped due to a POLLHUP/POLLERR.
*/
- if (!atomic_read(&md->refcnt))
+ if (!refcount_read(&md->refcnt))
return NULL;
head = perf_mmap__read_head(md);
{
u64 head;
- if (!atomic_read(&md->refcnt))
+ if (!refcount_read(&md->refcnt))
return;
head = perf_mmap__read_head(md);
static void perf_mmap__get(struct perf_mmap *map)
{
- atomic_inc(&map->refcnt);
+ refcount_inc(&map->refcnt);
}
static void perf_mmap__put(struct perf_mmap *md)
{
- BUG_ON(md->base && atomic_read(&md->refcnt) == 0);
+ BUG_ON(md->base && refcount_read(&md->refcnt) == 0);
- if (atomic_dec_and_test(&md->refcnt))
+ if (refcount_dec_and_test(&md->refcnt))
perf_mmap__munmap(md);
}
perf_mmap__write_tail(md, old);
}
- if (atomic_read(&md->refcnt) == 1 && perf_mmap__empty(md))
+ if (refcount_read(&md->refcnt) == 1 && perf_mmap__empty(md))
perf_mmap__put(md);
}
munmap(map->base, perf_mmap__mmap_len(map));
map->base = NULL;
map->fd = -1;
- atomic_set(&map->refcnt, 0);
+ refcount_set(&map->refcnt, 0);
}
auxtrace_mmap__munmap(&map->auxtrace_mmap);
}
if (!map)
return NULL;
- for (i = 0; i < evlist->nr_mmaps; i++)
+ for (i = 0; i < evlist->nr_mmaps; i++) {
map[i].fd = -1;
+ /*
+ * When the perf_mmap() call is made we grab one refcount, plus
+ * one extra to let perf_evlist__mmap_consume() get the last
+ * events after all real references (perf_mmap__get()) are
+ * dropped.
+ *
+ * Each PERF_EVENT_IOC_SET_OUTPUT points to this mmap and
+ * thus does perf_mmap__get() on it.
+ */
+ refcount_set(&map[i].refcnt, 0);
+ }
return map;
}
* evlist layer can't just drop it when filtering events in
* perf_evlist__filter_pollfd().
*/
- atomic_set(&map->refcnt, 2);
+ refcount_set(&map->refcnt, 2);
map->prev = 0;
map->mask = mp->mask;
map->base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot,
#ifndef __PERF_EVLIST_H
#define __PERF_EVLIST_H 1
-#include <linux/atomic.h>
+#include <linux/kernel.h>
+#include <linux/refcount.h>
#include <linux/list.h>
#include <api/fd/array.h>
#include <stdio.h>
#include "evsel.h"
#include "util.h"
#include "auxtrace.h"
+#include <signal.h>
#include <unistd.h>
struct pollfd;
void *base;
int mask;
int fd;
- atomic_t refcnt;
+ refcount_t refcnt;
u64 prev;
struct auxtrace_mmap auxtrace_mmap;
char event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8)));
*/
#include <byteswap.h>
+#include <errno.h>
+#include <inttypes.h>
#include <linux/bitops.h>
#include <api/fs/tracing_path.h>
#include <traceevent/event-parse.h>
#include <linux/hw_breakpoint.h>
#include <linux/perf_event.h>
#include <linux/err.h>
+#include <sys/ioctl.h>
#include <sys/resource.h>
#include "asm/bug.h"
#include "callchain.h"
#include "stat.h"
#include "util/parse-branch-options.h"
+#include "sane_ctype.h"
+
static struct {
bool sample_id_all;
bool exclude_guest;
evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
perf_evsel__calc_id_pos(evsel);
evsel->cmdline_group_boundary = false;
+ evsel->metric_expr = NULL;
+ evsel->metric_name = NULL;
+ evsel->metric_events = NULL;
+ evsel->collect_stat = false;
}
struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
attr->mmap2 = track && !perf_missing_features.mmap2;
attr->comm = track;
+ if (opts->record_namespaces)
+ attr->namespaces = track;
+
if (opts->record_switch_events)
attr->context_switch = track;
if (FD(evsel, cpu, thread) < 0)
return -EINVAL;
- if (readn(FD(evsel, cpu, thread), count, sizeof(*count)) < 0)
+ if (readn(FD(evsel, cpu, thread), count, sizeof(*count)) <= 0)
return -errno;
return 0;
if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1, thread + 1) < 0)
return -ENOMEM;
- if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0)
+ if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) <= 0)
return -errno;
perf_evsel__compute_deltas(evsel, cpu, thread, &count);
int err, char *msg, size_t size)
{
char sbuf[STRERR_BUFSIZE];
+ int printed = 0;
switch (err) {
case EPERM:
case EACCES:
- return scnprintf(msg, size,
+ if (err == EPERM)
+ printed = scnprintf(msg, size,
+ "No permission to enable %s event.\n\n",
+ perf_evsel__name(evsel));
+
+ return scnprintf(msg + printed, size - printed,
"You may not have permission to collect %sstats.\n\n"
"Consider tweaking /proc/sys/kernel/perf_event_paranoid,\n"
"which controls use of the performance events system by\n"
bool cmdline_group_boundary;
struct list_head config_terms;
int bpf_fd;
+ bool merged_stat;
+ const char * metric_expr;
+ const char * metric_name;
+ struct perf_evsel **metric_events;
+ bool collect_stat;
};
union u64_swap {
+#include <inttypes.h>
#include <stdio.h>
#include <stdbool.h>
#include <traceevent/event-parse.h>
#include "evsel.h"
#include "callchain.h"
#include "map.h"
+#include "strlist.h"
#include "symbol.h"
static int comma_fprintf(FILE *fp, bool *first, const char *fmt, ...)
--- /dev/null
+#ifndef PARSE_CTX_H
+#define PARSE_CTX_H 1
+
+#define EXPR_MAX_OTHER 8
+#define MAX_PARSE_ID EXPR_MAX_OTHER
+
+struct parse_id {
+ const char *name;
+ double val;
+};
+
+struct parse_ctx {
+ int num_ids;
+ struct parse_id ids[MAX_PARSE_ID];
+};
+
+void expr__ctx_init(struct parse_ctx *ctx);
+void expr__add_id(struct parse_ctx *ctx, const char *id, double val);
+#ifndef IN_EXPR_Y
+int expr__parse(double *final_val, struct parse_ctx *ctx, const char **pp);
+#endif
+int expr__find_other(const char *p, const char *one, const char ***other,
+ int *num_other);
+
+#endif
--- /dev/null
+/* Simple expression parser */
+%{
+#include "util.h"
+#include "util/debug.h"
+#define IN_EXPR_Y 1
+#include "expr.h"
+#include <string.h>
+
+#define MAXIDLEN 256
+%}
+
+%pure-parser
+%parse-param { double *final_val }
+%parse-param { struct parse_ctx *ctx }
+%parse-param { const char **pp }
+%lex-param { const char **pp }
+
+%union {
+ double num;
+ char id[MAXIDLEN+1];
+}
+
+%token <num> NUMBER
+%token <id> ID
+%left '|'
+%left '^'
+%left '&'
+%left '-' '+'
+%left '*' '/' '%'
+%left NEG NOT
+%type <num> expr
+
+%{
+static int expr__lex(YYSTYPE *res, const char **pp);
+
+static void expr__error(double *final_val __maybe_unused,
+ struct parse_ctx *ctx __maybe_unused,
+ const char **pp __maybe_unused,
+ const char *s)
+{
+ pr_debug("%s\n", s);
+}
+
+static int lookup_id(struct parse_ctx *ctx, char *id, double *val)
+{
+ int i;
+
+ for (i = 0; i < ctx->num_ids; i++) {
+ if (!strcasecmp(ctx->ids[i].name, id)) {
+ *val = ctx->ids[i].val;
+ return 0;
+ }
+ }
+ return -1;
+}
+
+%}
+%%
+
+all_expr: expr { *final_val = $1; }
+ ;
+
+expr: NUMBER
+ | ID { if (lookup_id(ctx, $1, &$$) < 0) {
+ pr_debug("%s not found", $1);
+ YYABORT;
+ }
+ }
+ | expr '+' expr { $$ = $1 + $3; }
+ | expr '-' expr { $$ = $1 - $3; }
+ | expr '*' expr { $$ = $1 * $3; }
+ | expr '/' expr { if ($3 == 0) YYABORT; $$ = $1 / $3; }
+ | expr '%' expr { if ((long)$3 == 0) YYABORT; $$ = (long)$1 % (long)$3; }
+ | '-' expr %prec NEG { $$ = -$2; }
+ | '(' expr ')' { $$ = $2; }
+ ;
+
+%%
+
+static int expr__symbol(YYSTYPE *res, const char *p, const char **pp)
+{
+ char *dst = res->id;
+ const char *s = p;
+
+ while (isalnum(*p) || *p == '_' || *p == '.') {
+ if (p - s >= MAXIDLEN)
+ return -1;
+ *dst++ = *p++;
+ }
+ *dst = 0;
+ *pp = p;
+ return ID;
+}
+
+static int expr__lex(YYSTYPE *res, const char **pp)
+{
+ int tok;
+ const char *s;
+ const char *p = *pp;
+
+ while (isspace(*p))
+ p++;
+ s = p;
+ switch (*p++) {
+ case 'a' ... 'z':
+ case 'A' ... 'Z':
+ return expr__symbol(res, p - 1, pp);
+ case '0' ... '9': case '.':
+ res->num = strtod(s, (char **)&p);
+ tok = NUMBER;
+ break;
+ default:
+ tok = *s;
+ break;
+ }
+ *pp = p;
+ return tok;
+}
+
+/* Caller must make sure id is allocated */
+void expr__add_id(struct parse_ctx *ctx, const char *name, double val)
+{
+ int idx;
+ assert(ctx->num_ids < MAX_PARSE_ID);
+ idx = ctx->num_ids++;
+ ctx->ids[idx].name = name;
+ ctx->ids[idx].val = val;
+}
+
+void expr__ctx_init(struct parse_ctx *ctx)
+{
+ ctx->num_ids = 0;
+}
+
+int expr__find_other(const char *p, const char *one, const char ***other,
+ int *num_otherp)
+{
+ const char *orig = p;
+ int err = -1;
+ int num_other;
+
+ *other = malloc((EXPR_MAX_OTHER + 1) * sizeof(char *));
+ if (!*other)
+ return -1;
+
+ num_other = 0;
+ for (;;) {
+ YYSTYPE val;
+ int tok = expr__lex(&val, &p);
+ if (tok == 0) {
+ err = 0;
+ break;
+ }
+ if (tok == ID && strcasecmp(one, val.id)) {
+ if (num_other >= EXPR_MAX_OTHER - 1) {
+ pr_debug("Too many extra events in %s\n", orig);
+ break;
+ }
+ (*other)[num_other] = strdup(val.id);
+ if (!(*other)[num_other])
+ return -1;
+ num_other++;
+ }
+ }
+ (*other)[num_other] = NULL;
+ *num_otherp = num_other;
+ if (err) {
+ *num_otherp = 0;
+ free(*other);
+ *other = NULL;
+ }
+ return err;
+}
+#include <errno.h>
+#include <inttypes.h>
#include "util.h"
+#include "string2.h"
+#include <sys/param.h>
#include <sys/types.h>
#include <byteswap.h>
#include <unistd.h>
#include <linux/list.h>
#include <linux/kernel.h>
#include <linux/bitops.h>
+#include <sys/stat.h>
+#include <sys/types.h>
#include <sys/utsname.h>
+#include <unistd.h>
#include "evlist.h"
#include "evsel.h"
#include <api/fs/fs.h>
#include "asm/bug.h"
+#include "sane_ctype.h"
+
/*
* magic2 = "PERFILE2"
* must be a numerical value to let the endianness
struct perf_evlist *evlist __maybe_unused)
{
char buf[MAXPATHLEN];
- char proc[32];
u32 n;
int i, ret;
- /*
- * actual atual path to perf binary
- */
- sprintf(proc, "/proc/%d/exe", getpid());
- ret = readlink(proc, buf, sizeof(buf));
+ /* actual path to perf binary */
+ ret = readlink("/proc/self/exe", buf, sizeof(buf) - 1);
if (ret <= 0)
return -1;
perf_header__process_sections(header, fd, &hd,
perf_file_section__fprintf_info);
+ if (session->file->is_pipe)
+ return 0;
+
fprintf(fp, "# missing features: ");
for_each_clear_bit(bit, header->adds_features, HEADER_LAST_FEATURE) {
if (bit)
#include "cache.h"
#include "config.h"
+#include <poll.h>
#include <stdio.h>
#include <subcmd/help.h>
#include "../builtin.h"
#include "levenshtein.h"
static int autocorrect;
-static struct cmdnames aliases;
static int perf_unknown_cmd_config(const char *var, const char *value,
void *cb __maybe_unused)
{
if (!strcmp(var, "help.autocorrect"))
autocorrect = perf_config_int(var,value);
- /* Also use aliases for command lookup */
- if (!prefixcmp(var, "alias."))
- add_cmdname(&aliases, var + 6, strlen(var + 6));
return 0;
}
memset(&main_cmds, 0, sizeof(main_cmds));
memset(&other_cmds, 0, sizeof(main_cmds));
- memset(&aliases, 0, sizeof(aliases));
perf_config(perf_unknown_cmd_config, NULL);
load_command_list("perf-", &main_cmds, &other_cmds);
- if (add_cmd_list(&main_cmds, &aliases) < 0 ||
- add_cmd_list(&main_cmds, &other_cmds) < 0) {
+ if (add_cmd_list(&main_cmds, &other_cmds) < 0) {
fprintf(stderr, "ERROR: Failed to allocate command list for unknown command.\n");
goto end;
}
#include "hist.h"
#include "map.h"
#include "session.h"
+#include "namespaces.h"
#include "sort.h"
#include "evlist.h"
#include "evsel.h"
#include "annotate.h"
+#include "srcline.h"
+#include "thread.h"
#include "ui/progress.h"
+#include <errno.h>
#include <math.h>
+#include <sys/param.h>
static bool hists__filter_entry_by_dso(struct hists *hists,
struct hist_entry *he);
hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO);
}
+ hists__new_col_len(hists, HISTC_CGROUP_ID, 20);
hists__new_col_len(hists, HISTC_CPU, 3);
hists__new_col_len(hists, HISTC_SOCKET, 6);
hists__new_col_len(hists, HISTC_MEM_LOCKED, 6);
bool sample_self,
struct hist_entry_ops *ops)
{
+ struct namespaces *ns = thread__namespaces(al->thread);
struct hist_entry entry = {
.thread = al->thread,
.comm = thread__comm(al->thread),
+ .cgroup_id = {
+ .dev = ns ? ns->link_info[CGROUP_NS_INDEX].dev : 0,
+ .ino = ns ? ns->link_info[CGROUP_NS_INDEX].ino : 0,
+ },
.ms = {
.map = al->map,
.sym = al->sym,
zfree(&he->mem_info);
}
+ if (he->inline_node) {
+ inline_node__delete(he->inline_node);
+ he->inline_node = NULL;
+ }
+
zfree(&he->stat_acc);
free_srcline(he->srcline);
if (he->srcfile && he->srcfile[0])
else if (!strcmp(arg, "absolute"))
symbol_conf.filter_relative = false;
else {
- pr_debug("Invalud percentage: %s\n", arg);
+ pr_debug("Invalid percentage: %s\n", arg);
return -1;
}
HISTC_DSO,
HISTC_THREAD,
HISTC_COMM,
+ HISTC_CGROUP_ID,
HISTC_PARENT,
HISTC_CPU,
HISTC_SOCKET,
HISTC_SRCLINE_FROM,
HISTC_SRCLINE_TO,
HISTC_TRACE,
+ HISTC_SYM_SIZE,
HISTC_NR_COLS, /* Last entry */
};
*/
#include <endian.h>
+#include <errno.h>
#include <byteswap.h>
+#include <inttypes.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/bitops.h>
#include "insn.c"
#include "intel-pt-insn-decoder.h"
+#include "dump-insn.h"
#if INTEL_PT_INSN_BUF_SZ < MAX_INSN_SIZE || INTEL_PT_INSN_BUF_SZ > MAX_INSN
#error Instruction buffer size too small
enum intel_pt_insn_branch branch = INTEL_PT_BR_NO_BRANCH;
int ext;
+ intel_pt_insn->rel = 0;
+
if (insn_is_avx(insn)) {
intel_pt_insn->op = INTEL_PT_OP_OTHER;
intel_pt_insn->branch = INTEL_PT_BR_NO_BRANCH;
return 0;
}
+const char *dump_insn(struct perf_insn *x, uint64_t ip __maybe_unused,
+ u8 *inbuf, int inlen, int *lenp)
+{
+ struct insn insn;
+ int n, i;
+ int left;
+
+ insn_init(&insn, inbuf, inlen, x->is64bit);
+ insn_get_length(&insn);
+ if (!insn_complete(&insn) || insn.length > inlen)
+ return "<bad>";
+ if (lenp)
+ *lenp = insn.length;
+ left = sizeof(x->out);
+ n = snprintf(x->out, left, "insn: ");
+ left -= n;
+ for (i = 0; i < insn.length; i++) {
+ n += snprintf(x->out + n, left, "%02x ", inbuf[i]);
+ left -= n;
+ }
+ return x->out;
+}
+
const char *branch_name[] = {
[INTEL_PT_OP_OTHER] = "Other",
[INTEL_PT_OP_CALL] = "Call",
*
*/
+#include <inttypes.h>
#include <stdio.h>
#include <stdbool.h>
#include <errno.h>
#include <sys/sysmacros.h>
#include <sys/types.h>
+#include <errno.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <byteswap.h>
#include <sys/stat.h>
#include <sys/mman.h>
+#include <linux/stringify.h>
#include "util.h"
#include "event.h"
#include "debug.h"
#include "evlist.h"
#include "symbol.h"
-#include "strlist.h"
#include <elf.h>
#include "tsc.h"
#include "genelf.h"
#include "../builtin.h"
+#include "sane_ctype.h"
+
struct jit_buf_desc {
struct perf_data_file *output;
struct perf_session *session;
jd->use_arch_timestamp);
if (header.version > JITHEADER_VERSION) {
- pr_err("wrong jitdump version %u, expected " STR(JITHEADER_VERSION),
+ pr_err("wrong jitdump version %u, expected " __stringify(JITHEADER_VERSION),
header.version);
goto error;
}
#include "llvm-utils.h"
#include "config.h"
#include "util.h"
+#include <sys/wait.h>
#define CLANG_BPF_CMD_DEFAULT_TEMPLATE \
"$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
+#include <errno.h>
#include <lzma.h>
#include <stdio.h>
#include <linux/compiler.h>
+#include "compress.h"
#include "util.h"
#include "debug.h"
+#include <dirent.h>
+#include <errno.h>
+#include <inttypes.h>
+#include <regex.h>
#include "callchain.h"
#include "debug.h"
#include "event.h"
#include "thread.h"
#include "vdso.h"
#include <stdbool.h>
-#include <symbol/kallsyms.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
#include "unwind.h"
#include "linux/hash.h"
+#include "asm/bug.h"
+
+#include "sane_ctype.h"
+#include <symbol/kallsyms.h>
static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock);
return err;
}
+int machine__process_namespaces_event(struct machine *machine __maybe_unused,
+ union perf_event *event,
+ struct perf_sample *sample __maybe_unused)
+{
+ struct thread *thread = machine__findnew_thread(machine,
+ event->namespaces.pid,
+ event->namespaces.tid);
+ int err = 0;
+
+ WARN_ONCE(event->namespaces.nr_namespaces > NR_NAMESPACES,
+ "\nWARNING: kernel seems to support more namespaces than perf"
+ " tool.\nTry updating the perf tool..\n\n");
+
+ WARN_ONCE(event->namespaces.nr_namespaces < NR_NAMESPACES,
+ "\nWARNING: perf tool seems to support more namespaces than"
+ " the kernel.\nTry updating the kernel..\n\n");
+
+ if (dump_trace)
+ perf_event__fprintf_namespaces(event, stdout);
+
+ if (thread == NULL ||
+ thread__set_namespaces(thread, sample->time, &event->namespaces)) {
+ dump_printf("problem processing PERF_RECORD_NAMESPACES, skipping event.\n");
+ err = -1;
+ }
+
+ thread__put(thread);
+
+ return err;
+}
+
int machine__process_lost_event(struct machine *machine __maybe_unused,
union perf_event *event, struct perf_sample *sample __maybe_unused)
{
if (machine->last_match == th)
machine->last_match = NULL;
- BUG_ON(atomic_read(&th->refcnt) == 0);
+ BUG_ON(refcount_read(&th->refcnt) == 0);
if (lock)
pthread_rwlock_wrlock(&machine->threads_lock);
rb_erase_init(&th->rb_node, &machine->threads);
ret = machine__process_comm_event(machine, event, sample); break;
case PERF_RECORD_MMAP:
ret = machine__process_mmap_event(machine, event, sample); break;
+ case PERF_RECORD_NAMESPACES:
+ ret = machine__process_namespaces_event(machine, event, sample); break;
case PERF_RECORD_MMAP2:
ret = machine__process_mmap2_event(machine, event, sample); break;
case PERF_RECORD_FORK:
union perf_event *event);
int machine__process_switch_event(struct machine *machine,
union perf_event *event);
+int machine__process_namespaces_event(struct machine *machine,
+ union perf_event *event,
+ struct perf_sample *sample);
int machine__process_mmap_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample);
int machine__process_mmap2_event(struct machine *machine, union perf_event *event,
#include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
#include "map.h"
#include "thread.h"
-#include "strlist.h"
#include "vdso.h"
#include "build-id.h"
#include "util.h"
#include "debug.h"
#include "machine.h"
#include <linux/string.h>
+#include "srcline.h"
#include "unwind.h"
static void __maps__insert(struct maps *maps, struct map *map);
RB_CLEAR_NODE(&map->rb_node);
map->groups = NULL;
map->erange_warned = false;
- atomic_set(&map->refcnt, 1);
+ refcount_set(&map->refcnt, 1);
}
struct map *map__new(struct machine *machine, u64 start, u64 len,
void map__put(struct map *map)
{
- if (map && atomic_dec_and_test(&map->refcnt))
+ if (map && refcount_dec_and_test(&map->refcnt))
map__delete(map);
}
struct map *map = memdup(from, sizeof(*map));
if (map != NULL) {
- atomic_set(&map->refcnt, 1);
+ refcount_set(&map->refcnt, 1);
RB_CLEAR_NODE(&map->rb_node);
dso__get(map->dso);
map->groups = NULL;
if (map && map->dso) {
srcline = get_srcline(map->dso,
- map__rip_2objdump(map, addr), NULL, true);
+ map__rip_2objdump(map, addr), NULL,
+ true, true);
if (srcline != SRCLINE_UNKNOWN)
ret = fprintf(fp, "%s%s", prefix, srcline);
free_srcline(srcline);
maps__init(&mg->maps[i]);
}
mg->machine = machine;
- atomic_set(&mg->refcnt, 1);
+ refcount_set(&mg->refcnt, 1);
}
static void __maps__purge(struct maps *maps)
void map_groups__put(struct map_groups *mg)
{
- if (mg && atomic_dec_and_test(&mg->refcnt))
+ if (mg && refcount_dec_and_test(&mg->refcnt))
map_groups__delete(mg);
}
#ifndef __PERF_MAP_H
#define __PERF_MAP_H
-#include <linux/atomic.h>
+#include <linux/refcount.h>
#include <linux/compiler.h>
#include <linux/list.h>
#include <linux/rbtree.h>
struct dso *dso;
struct map_groups *groups;
- atomic_t refcnt;
+ refcount_t refcnt;
};
struct kmap {
struct map_groups {
struct maps maps[MAP__NR_TYPES];
struct machine *machine;
- atomic_t refcnt;
+ refcount_t refcnt;
};
struct map_groups *map_groups__new(struct machine *machine);
static inline struct map_groups *map_groups__get(struct map_groups *mg)
{
if (mg)
- atomic_inc(&mg->refcnt);
+ refcount_inc(&mg->refcnt);
return mg;
}
static inline struct map *map__get(struct map *map)
{
if (map)
- atomic_inc(&map->refcnt);
+ refcount_inc(&map->refcnt);
return map;
}
#include <sys/stat.h>
#include <unistd.h>
#include <api/fs/fs.h>
+#include <linux/kernel.h>
#include "mem-events.h"
#include "debug.h"
#include "symbol.h"
static const char * const snoop_access[] = {
"N/A",
"None",
- "Miss",
"Hit",
+ "Miss",
"HitM",
};
--- /dev/null
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * Copyright (C) 2017 Hari Bathini, IBM Corporation
+ */
+
+#include "namespaces.h"
+#include "util.h"
+#include "event.h"
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+
+struct namespaces *namespaces__new(struct namespaces_event *event)
+{
+ struct namespaces *namespaces;
+ u64 link_info_size = ((event ? event->nr_namespaces : NR_NAMESPACES) *
+ sizeof(struct perf_ns_link_info));
+
+ namespaces = zalloc(sizeof(struct namespaces) + link_info_size);
+ if (!namespaces)
+ return NULL;
+
+ namespaces->end_time = -1;
+
+ if (event)
+ memcpy(namespaces->link_info, event->link_info, link_info_size);
+
+ return namespaces;
+}
+
+void namespaces__free(struct namespaces *namespaces)
+{
+ free(namespaces);
+}
--- /dev/null
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * Copyright (C) 2017 Hari Bathini, IBM Corporation
+ */
+
+#ifndef __PERF_NAMESPACES_H
+#define __PERF_NAMESPACES_H
+
+#include "../perf.h"
+#include <linux/list.h>
+
+struct namespaces_event;
+
+struct namespaces {
+ struct list_head list;
+ u64 end_time;
+ struct perf_ns_link_info link_info[];
+};
+
+struct namespaces *namespaces__new(struct namespaces_event *event);
+void namespaces__free(struct namespaces *namespaces);
+
+#endif /* __PERF_NAMESPACES_H */
+#include <errno.h>
+#include <inttypes.h>
#include <linux/list.h>
#include <linux/compiler.h>
#include <linux/string.h>
static void free_dup_event(struct ordered_events *oe, union perf_event *event)
{
- if (oe->copy_on_queue) {
+ if (event && oe->copy_on_queue) {
oe->cur_alloc_size -= event->header.size;
free(event);
}
list_move(&event->list, &oe->cache);
oe->nr_events--;
free_dup_event(oe, event->event);
+ event->event = NULL;
}
int ordered_events__queue(struct ordered_events *oe, union perf_event *event,
#include <linux/hw_breakpoint.h>
#include <linux/err.h>
-#include "util.h"
+#include <dirent.h>
+#include <errno.h>
+#include <sys/ioctl.h>
+#include <sys/param.h>
+#include "term.h"
#include "../perf.h"
#include "evlist.h"
#include "evsel.h"
#include <subcmd/parse-options.h>
#include "parse-events.h"
#include <subcmd/exec-cmd.h>
-#include "string.h"
+#include "string2.h"
+#include "strlist.h"
#include "symbol.h"
#include "cache.h"
#include "header.h"
return NULL;
(*idx)++;
- evsel->cpus = cpu_map__get(cpus);
- evsel->own_cpus = cpu_map__get(cpus);
+ evsel->cpus = cpu_map__get(cpus);
+ evsel->own_cpus = cpu_map__get(cpus);
+ evsel->system_wide = !!cpus;
if (name)
evsel->name = strdup(name);
evsel->scale = info.scale;
evsel->per_pkg = info.per_pkg;
evsel->snapshot = info.snapshot;
+ evsel->metric_expr = info.metric_expr;
+ evsel->metric_name = info.metric_name;
}
return evsel ? 0 : -ENOMEM;
}
+int parse_events_multi_pmu_add(struct parse_events_evlist *data,
+ char *str, struct list_head **listp)
+{
+ struct list_head *head;
+ struct parse_events_term *term;
+ struct list_head *list;
+ struct perf_pmu *pmu = NULL;
+ int ok = 0;
+
+ *listp = NULL;
+ /* Add it for all PMUs that support the alias */
+ list = malloc(sizeof(struct list_head));
+ if (!list)
+ return -1;
+ INIT_LIST_HEAD(list);
+ while ((pmu = perf_pmu__scan(pmu)) != NULL) {
+ struct perf_pmu_alias *alias;
+
+ list_for_each_entry(alias, &pmu->aliases, list) {
+ if (!strcasecmp(alias->name, str)) {
+ head = malloc(sizeof(struct list_head));
+ if (!head)
+ return -1;
+ INIT_LIST_HEAD(head);
+ if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+ str, 1, false, &str, NULL) < 0)
+ return -1;
+ list_add_tail(&term->list, head);
+
+ if (!parse_events_add_pmu(data, list,
+ pmu->name, head)) {
+ pr_debug("%s -> %s/%s/\n", str,
+ pmu->name, alias->str);
+ ok++;
+ }
+
+ parse_events_terms__delete(head);
+ }
+ }
+ }
+ if (!ok)
+ return -1;
+ *listp = list;
+ return 0;
+}
+
int parse_events__modifier_group(struct list_head *list,
char *event_mod)
{
* Print the help text for the event symbols:
*/
void print_events(const char *event_glob, bool name_only, bool quiet_flag,
- bool long_desc)
+ bool long_desc, bool details_flag)
{
print_symbol_events(event_glob, PERF_TYPE_HARDWARE,
event_symbols_hw, PERF_COUNT_HW_MAX, name_only);
print_hwcache_events(event_glob, name_only);
- print_pmu_events(event_glob, name_only, quiet_flag, long_desc);
+ print_pmu_events(event_glob, name_only, quiet_flag, long_desc,
+ details_flag);
if (event_glob != NULL)
return;
return new_term(new, &temp, term->val.str, term->val.num);
}
+int parse_events_copy_term_list(struct list_head *old,
+ struct list_head **new)
+{
+ struct parse_events_term *term, *n;
+ int ret;
+
+ if (!old) {
+ *new = NULL;
+ return 0;
+ }
+
+ *new = malloc(sizeof(struct list_head));
+ if (!*new)
+ return -ENOMEM;
+ INIT_LIST_HEAD(*new);
+
+ list_for_each_entry (term, old, list) {
+ ret = parse_events_term__clone(&n, term);
+ if (ret)
+ return ret;
+ list_add_tail(&n->list, *new);
+ }
+ return 0;
+}
+
void parse_events_terms__purge(struct list_head *terms)
{
struct parse_events_term *term, *h;
#include <stdbool.h>
#include <linux/types.h>
#include <linux/perf_event.h>
+#include <string.h>
struct list_head;
struct perf_evsel;
int parse_events_add_pmu(struct parse_events_evlist *data,
struct list_head *list, char *name,
struct list_head *head_config);
+
+int parse_events_multi_pmu_add(struct parse_events_evlist *data,
+ char *str,
+ struct list_head **listp);
+
+int parse_events_copy_term_list(struct list_head *old,
+ struct list_head **new);
+
enum perf_pmu_event_symbol_type
perf_pmu__parse_check(const char *name);
void parse_events__set_leader(char *name, struct list_head *list);
int idx, const char *str);
void print_events(const char *event_glob, bool name_only, bool quiet,
- bool long_desc);
+ bool long_desc, bool details_flag);
struct event_symbol {
const char *symbol;
int valid_event_mount(const char *eventfs);
char *parse_events_formats_error_string(char *additional_terms);
+#ifdef HAVE_LIBELF_SUPPORT
+/*
+ * If the probe point starts with '%',
+ * or starts with "sdt_" and has a ':' but no '=',
+ * then it should be a SDT/cached probe point.
+ */
+static inline bool is_sdt_event(char *str)
+{
+ return (str[0] == '%' ||
+ (!strncmp(str, "sdt_", 4) &&
+ !!strchr(str, ':') && !strchr(str, '=')));
+}
+#else
+static inline bool is_sdt_event(char *str __maybe_unused)
+{
+ return false;
+}
+#endif /* HAVE_LIBELF_SUPPORT */
+
#endif /* __PERF_PARSE_EVENTS_H */
PE_NAME opt_event_config
{
struct parse_events_evlist *data = _data;
- struct list_head *list;
+ struct list_head *list, *orig_terms, *terms;
+
+ if (parse_events_copy_term_list($2, &orig_terms))
+ YYABORT;
ALLOC_LIST(list);
- ABORT_ON(parse_events_add_pmu(data, list, $1, $2));
+ if (parse_events_add_pmu(data, list, $1, $2)) {
+ struct perf_pmu *pmu = NULL;
+ int ok = 0;
+
+ while ((pmu = perf_pmu__scan(pmu)) != NULL) {
+ char *name = pmu->name;
+
+ if (!strncmp(name, "uncore_", 7) &&
+ strncmp($1, "uncore_", 7))
+ name += 7;
+ if (!strncmp($1, name, strlen($1))) {
+ if (parse_events_copy_term_list(orig_terms, &terms))
+ YYABORT;
+ if (!parse_events_add_pmu(data, list, pmu->name, terms))
+ ok++;
+ parse_events_terms__delete(terms);
+ }
+ }
+ if (!ok)
+ YYABORT;
+ }
parse_events_terms__delete($2);
+ parse_events_terms__delete(orig_terms);
$$ = list;
}
|
PE_KERNEL_PMU_EVENT sep_dc
{
- struct parse_events_evlist *data = _data;
- struct list_head *head;
- struct parse_events_term *term;
struct list_head *list;
- struct perf_pmu *pmu = NULL;
- int ok = 0;
-
- /* Add it for all PMUs that support the alias */
- ALLOC_LIST(list);
- while ((pmu = perf_pmu__scan(pmu)) != NULL) {
- struct perf_pmu_alias *alias;
-
- list_for_each_entry(alias, &pmu->aliases, list) {
- if (!strcasecmp(alias->name, $1)) {
- ALLOC_LIST(head);
- ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
- $1, 1, false, &@1, NULL));
- list_add_tail(&term->list, head);
-
- if (!parse_events_add_pmu(data, list,
- pmu->name, head)) {
- pr_debug("%s -> %s/%s/\n", $1,
- pmu->name, alias->str);
- ok++;
- }
- parse_events_terms__delete(head);
- }
- }
- }
- if (!ok)
+ if (parse_events_multi_pmu_add(_data, $1, &list) < 0)
YYABORT;
$$ = list;
}
|
PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc
{
- struct parse_events_evlist *data = _data;
- struct list_head *head;
- struct parse_events_term *term;
struct list_head *list;
char pmu_name[128];
- snprintf(&pmu_name, 128, "%s-%s", $1, $3);
- ALLOC_LIST(head);
- ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
- &pmu_name, 1, false, &@1, NULL));
- list_add_tail(&term->list, head);
-
- ALLOC_LIST(list);
- ABORT_ON(parse_events_add_pmu(data, list, "cpu", head));
- parse_events_terms__delete(head);
+ snprintf(&pmu_name, 128, "%s-%s", $1, $3);
+ if (parse_events_multi_pmu_add(_data, pmu_name, &list) < 0)
+ YYABORT;
$$ = list;
}
* which is what it's designed for.
*/
#include "cache.h"
-#include "util.h"
+#include "path.h"
+#include <linux/kernel.h>
#include <limits.h>
+#include <stdio.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
static char bad_path[] = "/bad-path/";
/*
return bad_path;
return cleanup_path(pathname);
}
+
+int path__join(char *bf, size_t size, const char *path1, const char *path2)
+{
+ return scnprintf(bf, size, "%s%s%s", path1, path1[0] ? "/" : "", path2);
+}
+
+int path__join3(char *bf, size_t size, const char *path1, const char *path2, const char *path3)
+{
+ return scnprintf(bf, size, "%s%s%s%s%s", path1, path1[0] ? "/" : "",
+ path2, path2[0] ? "/" : "", path3);
+}
+
+bool is_regular_file(const char *file)
+{
+ struct stat st;
+
+ if (stat(file, &st))
+ return false;
+
+ return S_ISREG(st.st_mode);
+}
--- /dev/null
+#ifndef _PERF_PATH_H
+#define _PERF_PATH_H
+
+int path__join(char *bf, size_t size, const char *path1, const char *path2);
+int path__join3(char *bf, size_t size, const char *path1, const char *path2, const char *path3);
+
+bool is_regular_file(const char *file);
+
+#endif /* _PERF_PATH_H */
#include <stdlib.h>
#include <setjmp.h>
#include <linux/err.h>
+#include <linux/kernel.h>
#include "util/util.h"
#include "util/debug.h"
#include "util/perf-hooks.h"
SMPL_REG_END
};
+int __weak arch_sdt_arg_parse_op(char *old_op __maybe_unused,
+ char **new_op __maybe_unused)
+{
+ return SDT_ARG_SKIP;
+}
+
#ifdef HAVE_PERF_REGS_SUPPORT
int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
{
extern const struct sample_reg sample_reg_masks[];
+enum {
+ SDT_ARG_VALID = 0,
+ SDT_ARG_SKIP,
+};
+
+int arch_sdt_arg_parse_op(char *old_op, char **new_op);
+
#ifdef HAVE_PERF_REGS_SUPPORT
#include <perf_regs.h>
#include <linux/list.h>
#include <linux/compiler.h>
#include <sys/types.h>
+#include <errno.h>
+#include <sys/stat.h>
#include <unistd.h>
#include <stdio.h>
#include <stdbool.h>
#include "header.h"
#include "pmu-events/pmu-events.h"
#include "cache.h"
+#include "string2.h"
struct perf_pmu_format {
char *name;
static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
char *desc, char *val,
char *long_desc, char *topic,
- char *unit, char *perpkg)
+ char *unit, char *perpkg,
+ char *metric_expr,
+ char *metric_name)
{
struct perf_pmu_alias *alias;
int ret;
perf_pmu__parse_snapshot(alias, dir, name);
}
+ alias->metric_expr = metric_expr ? strdup(metric_expr) : NULL;
+ alias->metric_name = metric_name ? strdup(metric_name): NULL;
alias->desc = desc ? strdup(desc) : NULL;
alias->long_desc = long_desc ? strdup(long_desc) :
desc ? strdup(desc) : NULL;
buf[ret] = 0;
return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL, NULL,
- NULL);
+ NULL, NULL, NULL);
}
static inline bool pmu_alias_info_file(char *name)
__perf_pmu__new_alias(head, NULL, (char *)pe->name,
(char *)pe->desc, (char *)pe->event,
(char *)pe->long_desc, (char *)pe->topic,
- (char *)pe->unit, (char *)pe->perpkg);
+ (char *)pe->unit, (char *)pe->perpkg,
+ (char *)pe->metric_expr,
+ (char *)pe->metric_name);
}
out:
info->unit = NULL;
info->scale = 0.0;
info->snapshot = false;
+ info->metric_expr = NULL;
+ info->metric_name = NULL;
list_for_each_entry_safe(term, h, head_terms, list) {
alias = pmu_find_alias(pmu, term);
if (alias->per_pkg)
info->per_pkg = true;
+ info->metric_expr = alias->metric_expr;
+ info->metric_name = alias->metric_name;
list_del(&term->list);
free(term);
char *topic;
char *str;
char *pmu;
+ char *metric_expr;
+ char *metric_name;
};
static int cmp_sevent(const void *a, const void *b)
break;
s += wlen;
column += n;
- while (isspace(*s))
- s++;
+ s = ltrim(s);
}
}
void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag,
- bool long_desc)
+ bool long_desc, bool details_flag)
{
struct perf_pmu *pmu;
struct perf_pmu_alias *alias;
aliases[j].topic = alias->topic;
aliases[j].str = alias->str;
aliases[j].pmu = pmu->name;
+ aliases[j].metric_expr = alias->metric_expr;
+ aliases[j].metric_name = alias->metric_name;
j++;
}
if (pmu->selectable &&
printf("%*s", 8, "[");
wordwrap(aliases[j].desc, 8, columns, 0);
printf("]\n");
- if (verbose > 0)
- printf("%*s%s/%s/\n", 8, "", aliases[j].pmu, aliases[j].str);
+ if (details_flag) {
+ printf("%*s%s/%s/ ", 8, "", aliases[j].pmu, aliases[j].str);
+ if (aliases[j].metric_name)
+ printf(" MetricName: %s", aliases[j].metric_name);
+ if (aliases[j].metric_expr)
+ printf(" MetricExpr: %s", aliases[j].metric_expr);
+ putchar('\n');
+ }
} else
printf(" %-50s [Kernel PMU event]\n", aliases[j].name);
printed++;
struct perf_pmu_info {
const char *unit;
+ const char *metric_expr;
+ const char *metric_name;
double scale;
bool per_pkg;
bool snapshot;
double scale;
bool per_pkg;
bool snapshot;
+ char *metric_expr;
+ char *metric_name;
};
struct perf_pmu *perf_pmu__find(const char *name);
struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu);
void print_pmu_events(const char *event_glob, bool name_only, bool quiet,
- bool long_desc);
+ bool long_desc, bool details_flag);
bool pmu_have_event(const char *pname, const char *name);
int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt,
--- /dev/null
+#include "print_binary.h"
+#include <linux/log2.h>
+#include "sane_ctype.h"
+
+void print_binary(unsigned char *data, size_t len,
+ size_t bytes_per_line, print_binary_t printer,
+ void *extra)
+{
+ size_t i, j, mask;
+
+ if (!printer)
+ return;
+
+ bytes_per_line = roundup_pow_of_two(bytes_per_line);
+ mask = bytes_per_line - 1;
+
+ printer(BINARY_PRINT_DATA_BEGIN, 0, extra);
+ for (i = 0; i < len; i++) {
+ if ((i & mask) == 0) {
+ printer(BINARY_PRINT_LINE_BEGIN, -1, extra);
+ printer(BINARY_PRINT_ADDR, i, extra);
+ }
+
+ printer(BINARY_PRINT_NUM_DATA, data[i], extra);
+
+ if (((i & mask) == mask) || i == len - 1) {
+ for (j = 0; j < mask-(i & mask); j++)
+ printer(BINARY_PRINT_NUM_PAD, -1, extra);
+
+ printer(BINARY_PRINT_SEP, i, extra);
+ for (j = i & ~mask; j <= i; j++)
+ printer(BINARY_PRINT_CHAR_DATA, data[j], extra);
+ for (j = 0; j < mask-(i & mask); j++)
+ printer(BINARY_PRINT_CHAR_PAD, i, extra);
+ printer(BINARY_PRINT_LINE_END, -1, extra);
+ }
+ }
+ printer(BINARY_PRINT_DATA_END, -1, extra);
+}
+
+int is_printable_array(char *p, unsigned int len)
+{
+ unsigned int i;
+
+ if (!p || !len || p[len - 1] != 0)
+ return 0;
+
+ len--;
+
+ for (i = 0; i < len; i++) {
+ if (!isprint(p[i]) && !isspace(p[i]))
+ return 0;
+ }
+ return 1;
+}
--- /dev/null
+#ifndef PERF_PRINT_BINARY_H
+#define PERF_PRINT_BINARY_H
+
+#include <stddef.h>
+
+enum binary_printer_ops {
+ BINARY_PRINT_DATA_BEGIN,
+ BINARY_PRINT_LINE_BEGIN,
+ BINARY_PRINT_ADDR,
+ BINARY_PRINT_NUM_DATA,
+ BINARY_PRINT_NUM_PAD,
+ BINARY_PRINT_SEP,
+ BINARY_PRINT_CHAR_DATA,
+ BINARY_PRINT_CHAR_PAD,
+ BINARY_PRINT_LINE_END,
+ BINARY_PRINT_DATA_END,
+};
+
+typedef void (*print_binary_t)(enum binary_printer_ops op,
+ unsigned int val, void *extra);
+
+void print_binary(unsigned char *data, size_t len,
+ size_t bytes_per_line, print_binary_t printer,
+ void *extra);
+
+int is_printable_array(char *p, unsigned int len);
+
+#endif /* PERF_PRINT_BINARY_H */
*
*/
+#include <inttypes.h>
#include <sys/utsname.h>
#include <sys/types.h>
#include <sys/stat.h>
#include "util.h"
#include "event.h"
#include "strlist.h"
+#include "strfilter.h"
#include "debug.h"
#include "cache.h"
#include "color.h"
#include "probe-finder.h"
#include "probe-file.h"
#include "session.h"
+#include "string2.h"
+
+#include "sane_ctype.h"
-#define MAX_CMDLEN 256
#define PERFPROBE_GROUP "probe"
bool probe_event_dry_run; /* Dry run flag */
}
for (i = 0; i < ntevs; i++) {
- if (!tevs[i].point.address || tevs[i].point.retprobe)
+ if (!tevs[i].point.address)
+ continue;
+ if (tevs[i].point.retprobe && !kretprobe_offset_is_supported())
continue;
/* If we found a wrong one, mark it by NULL symbol */
if (kprobe_warn_out_range(tevs[i].point.symbol,
if (!arg)
return -EINVAL;
- /*
- * If the probe point starts with '%',
- * or starts with "sdt_" and has a ':' but no '=',
- * then it should be a SDT/cached probe point.
- */
- if (arg[0] == '%' ||
- (!strncmp(arg, "sdt_", 4) &&
- !!strchr(arg, ':') && !strchr(arg, '='))) {
+ if (is_sdt_event(arg)) {
pev->sdt = true;
if (arg[0] == '%')
arg++;
return -EINVAL;
}
- if (pp->retprobe && !pp->function) {
- semantic_error("Return probe requires an entry function.\n");
- return -EINVAL;
- }
-
if ((pp->offset || pp->line || pp->lazy_line) && pp->retprobe) {
semantic_error("Offset/Line/Lazy pattern can't be used with "
"return probe.\n");
}
/* Note that the symbols in the kmodule are not relocated */
- if (!pev->uprobes && !pp->retprobe && !pev->target) {
+ if (!pev->uprobes && !pev->target &&
+ (!pp->retprobe || kretprobe_offset_is_supported())) {
reloc_sym = kernel_get_ref_reloc_sym();
if (!reloc_sym) {
pr_warning("Relocated base symbol is not found!\n");
struct probe_trace_event *new_tevs;
int ret = 0;
- if (ntevs == 0) {
+ if (*ntevs == 0) {
*tevs = *tevs2;
*ntevs = ntevs2;
*tevs2 = NULL;
#include <stdbool.h>
#include "intlist.h"
-#include "strlist.h"
-#include "strfilter.h"
/* Probe related configurations */
struct probe_conf {
struct intlist *line_list; /* Visible lines */
};
+struct strlist;
+
/* List of variables */
struct variable_list {
struct probe_trace_point point; /* Actual probepoint */
int apply_perf_probe_events(struct perf_probe_event *pevs, int npevs);
int show_probe_trace_events(struct perf_probe_event *pevs, int npevs);
void cleanup_perf_probe_events(struct perf_probe_event *pevs, int npevs);
+
+struct strfilter;
+
int del_perf_probe_events(struct strfilter *filter);
int show_perf_probe_event(const char *group, const char *event,
* GNU General Public License for more details.
*
*/
+#include <errno.h>
+#include <sys/stat.h>
+#include <sys/types.h>
#include <sys/uio.h>
+#include <unistd.h>
#include "util.h"
#include "event.h"
#include "strlist.h"
+#include "strfilter.h"
#include "debug.h"
#include "cache.h"
#include "color.h"
#include "probe-event.h"
#include "probe-file.h"
#include "session.h"
+#include "perf_regs.h"
+#include "string2.h"
-#define MAX_CMDLEN 256
+/* 4096 - 2 ('\n' + '\0') */
+#define MAX_CMDLEN 4094
static void print_open_warning(int err, bool uprobe)
{
}
}
-static int open_probe_events(const char *trace_file, bool readwrite)
+int open_trace_file(const char *trace_file, bool readwrite)
{
char buf[PATH_MAX];
int ret;
static int open_kprobe_events(bool readwrite)
{
- return open_probe_events("kprobe_events", readwrite);
+ return open_trace_file("kprobe_events", readwrite);
}
static int open_uprobe_events(bool readwrite)
{
- return open_probe_events("uprobe_events", readwrite);
+ return open_trace_file("uprobe_events", readwrite);
}
int probe_file__open(int flag)
: (unsigned long long)note->addr.a64[0];
}
+static const char * const type_to_suffix[] = {
+ ":s64", "", "", "", ":s32", "", ":s16", ":s8",
+ "", ":u8", ":u16", "", ":u32", "", "", "", ":u64"
+};
+
+/*
+ * Isolate the string number and convert it into a decimal value;
+ * this will be an index to get suffix of the uprobe name (defining
+ * the type)
+ */
+static int sdt_arg_parse_size(char *n_ptr, const char **suffix)
+{
+ long type_idx;
+
+ type_idx = strtol(n_ptr, NULL, 10);
+ if (type_idx < -8 || type_idx > 8) {
+ pr_debug4("Failed to get a valid sdt type\n");
+ return -1;
+ }
+
+ *suffix = type_to_suffix[type_idx + 8];
+ return 0;
+}
+
+static int synthesize_sdt_probe_arg(struct strbuf *buf, int i, const char *arg)
+{
+ char *op, *desc = strdup(arg), *new_op = NULL;
+ const char *suffix = "";
+ int ret = -1;
+
+ if (desc == NULL) {
+ pr_debug4("Allocation error\n");
+ return ret;
+ }
+
+ /*
+ * Argument is in N@OP format. N is size of the argument and OP is
+ * the actual assembly operand. N can be omitted; in that case
+ * argument is just OP(without @).
+ */
+ op = strchr(desc, '@');
+ if (op) {
+ op[0] = '\0';
+ op++;
+
+ if (sdt_arg_parse_size(desc, &suffix))
+ goto error;
+ } else {
+ op = desc;
+ }
+
+ ret = arch_sdt_arg_parse_op(op, &new_op);
+
+ if (ret < 0)
+ goto error;
+
+ if (ret == SDT_ARG_VALID) {
+ ret = strbuf_addf(buf, " arg%d=%s%s", i + 1, new_op, suffix);
+ if (ret < 0)
+ goto error;
+ }
+
+ ret = 0;
+error:
+ free(desc);
+ free(new_op);
+ return ret;
+}
+
+static char *synthesize_sdt_probe_command(struct sdt_note *note,
+ const char *pathname,
+ const char *sdtgrp)
+{
+ struct strbuf buf;
+ char *ret = NULL, **args;
+ int i, args_count;
+
+ if (strbuf_init(&buf, 32) < 0)
+ return NULL;
+
+ if (strbuf_addf(&buf, "p:%s/%s %s:0x%llx",
+ sdtgrp, note->name, pathname,
+ sdt_note__get_addr(note)) < 0)
+ goto error;
+
+ if (!note->args)
+ goto out;
+
+ if (note->args) {
+ args = argv_split(note->args, &args_count);
+
+ for (i = 0; i < args_count; ++i) {
+ if (synthesize_sdt_probe_arg(&buf, i, args[i]) < 0)
+ goto error;
+ }
+ }
+
+out:
+ ret = strbuf_detach(&buf, NULL);
+error:
+ strbuf_release(&buf);
+ return ret;
+}
+
int probe_cache__scan_sdt(struct probe_cache *pcache, const char *pathname)
{
struct probe_cache_entry *entry = NULL;
entry->pev.group = strdup(sdtgrp);
list_add_tail(&entry->node, &pcache->entries);
}
- ret = asprintf(&buf, "p:%s/%s %s:0x%llx",
- sdtgrp, note->name, pathname,
- sdt_note__get_addr(note));
- if (ret < 0)
+ buf = synthesize_sdt_probe_command(note, pathname, sdtgrp);
+ if (!buf) {
+ ret = -ENOMEM;
break;
+ }
+
strlist__add(entry->tevlist, buf);
free(buf);
entry = NULL;
return 0;
}
+enum ftrace_readme {
+ FTRACE_README_PROBE_TYPE_X = 0,
+ FTRACE_README_KRETPROBE_OFFSET,
+ FTRACE_README_END,
+};
+
static struct {
const char *pattern;
- bool avail;
- bool checked;
-} probe_type_table[] = {
-#define DEFINE_TYPE(idx, pat, def_avail) \
- [idx] = {.pattern = pat, .avail = (def_avail)}
- DEFINE_TYPE(PROBE_TYPE_U, "* u8/16/32/64,*", true),
- DEFINE_TYPE(PROBE_TYPE_S, "* s8/16/32/64,*", true),
- DEFINE_TYPE(PROBE_TYPE_X, "* x8/16/32/64,*", false),
- DEFINE_TYPE(PROBE_TYPE_STRING, "* string,*", true),
- DEFINE_TYPE(PROBE_TYPE_BITFIELD,
- "* b<bit-width>@<bit-offset>/<container-size>", true),
+ bool avail;
+} ftrace_readme_table[] = {
+#define DEFINE_TYPE(idx, pat) \
+ [idx] = {.pattern = pat, .avail = false}
+ DEFINE_TYPE(FTRACE_README_PROBE_TYPE_X, "*type: * x8/16/32/64,*"),
+ DEFINE_TYPE(FTRACE_README_KRETPROBE_OFFSET, "*place (kretprobe): *"),
};
-bool probe_type_is_available(enum probe_type type)
+static bool scan_ftrace_readme(enum ftrace_readme type)
{
+ int fd;
FILE *fp;
char *buf = NULL;
size_t len = 0;
- bool target_line = false;
- bool ret = probe_type_table[type].avail;
+ bool ret = false;
+ static bool scanned = false;
- if (type >= PROBE_TYPE_END)
- return false;
- /* We don't have to check the type which supported by default */
- if (ret || probe_type_table[type].checked)
- return ret;
+ if (scanned)
+ goto result;
- if (asprintf(&buf, "%s/README", tracing_path) < 0)
+ fd = open_trace_file("README", false);
+ if (fd < 0)
return ret;
- fp = fopen(buf, "r");
- if (!fp)
- goto end;
-
- zfree(&buf);
- while (getline(&buf, &len, fp) > 0 && !ret) {
- if (!target_line) {
- target_line = !!strstr(buf, " type: ");
- if (!target_line)
- continue;
- } else if (strstr(buf, "\t ") != buf)
- break;
- ret = strglobmatch(buf, probe_type_table[type].pattern);
+ fp = fdopen(fd, "r");
+ if (!fp) {
+ close(fd);
+ return ret;
}
- /* Cache the result */
- probe_type_table[type].checked = true;
- probe_type_table[type].avail = ret;
+
+ while (getline(&buf, &len, fp) > 0)
+ for (enum ftrace_readme i = 0; i < FTRACE_README_END; i++)
+ if (!ftrace_readme_table[i].avail)
+ ftrace_readme_table[i].avail =
+ strglobmatch(buf, ftrace_readme_table[i].pattern);
+ scanned = true;
fclose(fp);
-end:
free(buf);
- return ret;
+result:
+ if (type >= FTRACE_README_END)
+ return false;
+
+ return ftrace_readme_table[type].avail;
+}
+
+bool probe_type_is_available(enum probe_type type)
+{
+ if (type >= PROBE_TYPE_END)
+ return false;
+ else if (type == PROBE_TYPE_X)
+ return scan_ftrace_readme(FTRACE_README_PROBE_TYPE_X);
+
+ return true;
+}
+
+bool kretprobe_offset_is_supported(void)
+{
+ return scan_ftrace_readme(FTRACE_README_KRETPROBE_OFFSET);
}
#ifndef __PROBE_FILE_H
#define __PROBE_FILE_H
-#include "strlist.h"
-#include "strfilter.h"
#include "probe-event.h"
+struct strlist;
+struct strfilter;
+
/* Cache of probe definitions */
struct probe_cache_entry {
struct list_head node;
/* probe-file.c depends on libelf */
#ifdef HAVE_LIBELF_SUPPORT
+int open_trace_file(const char *trace_file, bool readwrite);
int probe_file__open(int flag);
int probe_file__open_both(int *kfd, int *ufd, int flag);
struct strlist *probe_file__get_namelist(int fd);
struct strlist *probe_file__get_rawlist(int fd);
int probe_file__add_event(int fd, struct probe_trace_event *tev);
+
int probe_file__del_events(int fd, struct strfilter *filter);
int probe_file__get_events(int fd, struct strfilter *filter,
struct strlist *plist);
const char *group, const char *event);
int probe_cache__show_all_caches(struct strfilter *filter);
bool probe_type_is_available(enum probe_type type);
+bool kretprobe_offset_is_supported(void);
#else /* ! HAVE_LIBELF_SUPPORT */
static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused)
{
*
*/
+#include <inttypes.h>
#include <sys/utsname.h>
#include <sys/types.h>
#include <sys/stat.h>
#include "debug.h"
#include "intlist.h"
#include "util.h"
+#include "strlist.h"
#include "symbol.h"
#include "probe-finder.h"
#include "probe-file.h"
+#include "string2.h"
/* Kprobe tracer basic type is up to u64 */
#define MAX_BASIC_TYPE_BITS 64
#define _PROBE_FINDER_H
#include <stdbool.h>
-#include "util.h"
#include "intlist.h"
#include "probe-event.h"
+#include "sane_ctype.h"
#define MAX_PROBE_BUFFER 1024
#define MAX_PROBES 128
util/parse-branch-options.c
util/rblist.c
util/counts.c
+util/print_binary.c
util/strlist.c
util/trace-event.c
../lib/rbtree.c
util/string.c
util/symbol_fprintf.c
+util/units.c
#include <poll.h>
#include <linux/err.h>
#include "evlist.h"
+#include "callchain.h"
#include "evsel.h"
#include "event.h"
#include "cpumap.h"
+#include "print_binary.h"
#include "thread_map.h"
/*
+ * Provide these two so that we don't have to link against callchain.c and
+ * start dragging hist.c, etc.
+ */
+struct callchain_param callchain_param;
+
+int parse_callchain_record(const char *arg __maybe_unused,
+ struct callchain_param *param __maybe_unused)
+{
+ return 0;
+}
+
+/*
* Support debug printing even though util/debug.c is not linked. That means
* implementing 'verbose' and 'eprintf'.
*/
+#include <errno.h>
#include <stdlib.h>
#include "strbuf.h"
#include "quote.h"
#include "evsel.h"
#include "cpumap.h"
#include "parse-events.h"
+#include <errno.h>
#include <api/fs/fs.h>
#include "util.h"
#include "cloexec.h"
--- /dev/null
+#ifndef _PERF_SANE_CTYPE_H
+#define _PERF_SANE_CTYPE_H
+
+extern const char *graph_line;
+extern const char *graph_dotted_line;
+extern const char *spaces;
+extern const char *dots;
+
+/* Sane ctype - no locale, and works with signed chars */
+#undef isascii
+#undef isspace
+#undef isdigit
+#undef isxdigit
+#undef isalpha
+#undef isprint
+#undef isalnum
+#undef islower
+#undef isupper
+#undef tolower
+#undef toupper
+
+extern unsigned char sane_ctype[256];
+#define GIT_SPACE 0x01
+#define GIT_DIGIT 0x02
+#define GIT_ALPHA 0x04
+#define GIT_GLOB_SPECIAL 0x08
+#define GIT_REGEX_SPECIAL 0x10
+#define GIT_PRINT_EXTRA 0x20
+#define GIT_PRINT 0x3E
+#define sane_istest(x,mask) ((sane_ctype[(unsigned char)(x)] & (mask)) != 0)
+#define isascii(x) (((x) & ~0x7f) == 0)
+#define isspace(x) sane_istest(x,GIT_SPACE)
+#define isdigit(x) sane_istest(x,GIT_DIGIT)
+#define isxdigit(x) \
+ (sane_istest(toupper(x), GIT_ALPHA | GIT_DIGIT) && toupper(x) < 'G')
+#define isalpha(x) sane_istest(x,GIT_ALPHA)
+#define isalnum(x) sane_istest(x,GIT_ALPHA | GIT_DIGIT)
+#define isprint(x) sane_istest(x,GIT_PRINT)
+#define islower(x) (sane_istest(x,GIT_ALPHA) && (x & 0x20))
+#define isupper(x) (sane_istest(x,GIT_ALPHA) && !(x & 0x20))
+#define tolower(x) sane_case((unsigned char)(x), 0x20)
+#define toupper(x) sane_case((unsigned char)(x), 0)
+
+static inline int sane_case(int x, int high)
+{
+ if (sane_istest(x, GIT_ALPHA))
+ x = (x & ~0x20) | high;
+ return x;
+}
+
+#endif /* _PERF_SANE_CTYPE_H */
*
*/
+#include <inttypes.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <Python.h>
+#include <inttypes.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "../call-path.h"
#include "thread_map.h"
#include "cpumap.h"
+#include "print_binary.h"
#include "stat.h"
PyMODINIT_FUNC initperf_trace_context(void);
+#include <errno.h>
+#include <inttypes.h>
#include <linux/kernel.h>
#include <traceevent/event-parse.h>
+#include <api/fs/fs.h>
#include <byteswap.h>
#include <unistd.h>
#include "perf_regs.h"
#include "asm/bug.h"
#include "auxtrace.h"
+#include "thread.h"
#include "thread-stack.h"
#include "stat.h"
if (perf_session__open(session) < 0)
goto out_close;
- perf_session__set_id_hdr_size(session);
- perf_session__set_comm_exec(session);
+ /*
+ * set session attributes that are present in perf.data
+ * but not in pipe-mode.
+ */
+ if (!file->is_pipe) {
+ perf_session__set_id_hdr_size(session);
+ perf_session__set_comm_exec(session);
+ }
}
} else {
session->machines.host.env = &perf_env;
pr_warning("Cannot read kernel map\n");
}
- if (tool && tool->ordering_requires_timestamps &&
+ /*
+ * In pipe-mode, evlist is empty until PERF_RECORD_HEADER_ATTR is
+ * processed, so perf_evlist__sample_id_all is not meaningful here.
+ */
+ if ((!file || !file->is_pipe) && tool && tool->ordering_requires_timestamps &&
tool->ordered_events && !perf_evlist__sample_id_all(session->evlist)) {
dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n");
tool->ordered_events = false;
return tool->mmap2(tool, event, sample, machine);
case PERF_RECORD_COMM:
return tool->comm(tool, event, sample, machine);
+ case PERF_RECORD_NAMESPACES:
+ return tool->namespaces(tool, event, sample, machine);
case PERF_RECORD_FORK:
return tool->fork(tool, event, sample, machine);
case PERF_RECORD_EXIT:
case PERF_RECORD_UNTHROTTLE:
return tool->unthrottle(tool, event, sample, machine);
case PERF_RECORD_AUX:
- if (tool->aux == perf_event__process_aux &&
- (event->aux.flags & PERF_AUX_FLAG_TRUNCATED))
- evlist->stats.total_aux_lost += 1;
+ if (tool->aux == perf_event__process_aux) {
+ if (event->aux.flags & PERF_AUX_FLAG_TRUNCATED)
+ evlist->stats.total_aux_lost += 1;
+ if (event->aux.flags & PERF_AUX_FLAG_PARTIAL)
+ evlist->stats.total_aux_partial += 1;
+ }
return tool->aux(tool, event, sample, machine);
case PERF_RECORD_ITRACE_START:
return tool->itrace_start(tool, event, sample, machine);
err = -1;
}
+ if (thread == NULL || thread__set_namespaces(thread, 0, NULL)) {
+ pr_err("problem inserting idle task.\n");
+ err = -1;
+ }
+
/* machine__findnew_thread() got the thread, so put it */
thread__put(thread);
return err;
stats->nr_events[PERF_RECORD_AUX]);
}
+ if (session->tool->aux == perf_event__process_aux &&
+ stats->total_aux_partial != 0) {
+ bool vmm_exclusive = false;
+
+ (void)sysfs__read_bool("module/kvm_intel/parameters/vmm_exclusive",
+ &vmm_exclusive);
+
+ ui__warning("AUX data had gaps in it %" PRIu64 " times out of %u!\n\n"
+ "Are you running a KVM guest in the background?%s\n\n",
+ stats->total_aux_partial,
+ stats->nr_events[PERF_RECORD_AUX],
+ vmm_exclusive ?
+ "\nReloading kvm_intel module with vmm_exclusive=0\n"
+ "will reduce the gaps to only guest's timeslices." :
+ "");
+ }
+
if (stats->nr_unknown_events != 0) {
ui__warning("Found %u unknown events!\n\n"
"Is this an older tool processing a perf.data "
buf = malloc(cur_size);
if (!buf)
return -errno;
+ ordered_events__set_copy_on_queue(oe, true);
more:
event = buf;
err = readn(fd, event, sizeof(struct perf_event_header));
#include "event.h"
#include "header.h"
#include "machine.h"
-#include "symbol.h"
-#include "thread.h"
#include "data.h"
#include "ordered-events.h"
+#include <linux/kernel.h>
#include <linux/rbtree.h>
#include <linux/perf_event.h>
struct ip_callchain;
+struct symbol;
struct thread;
struct auxtrace;
+#include <errno.h>
+#include <inttypes.h>
+#include <regex.h>
#include <sys/mman.h>
#include "sort.h"
#include "hist.h"
#include "comm.h"
#include "symbol.h"
+#include "thread.h"
#include "evsel.h"
#include "evlist.h"
+#include "strlist.h"
#include <traceevent/event-parse.h>
#include "mem-events.h"
+#include <linux/kernel.h>
regex_t parent_regex;
const char default_parent_pattern[] = "^sys_|^do_page_fault";
return SRCLINE_UNKNOWN;
return get_srcline(map->dso, map__rip_2objdump(map, he->ip),
- he->ms.sym, true);
+ he->ms.sym, true, true);
}
static int64_t
left->branch_info->srcline_from = get_srcline(map->dso,
map__rip_2objdump(map,
left->branch_info->from.al_addr),
- left->branch_info->from.sym, true);
+ left->branch_info->from.sym,
+ true, true);
}
if (!right->branch_info->srcline_from) {
struct map *map = right->branch_info->from.map;
right->branch_info->srcline_from = get_srcline(map->dso,
map__rip_2objdump(map,
right->branch_info->from.al_addr),
- right->branch_info->from.sym, true);
+ right->branch_info->from.sym,
+ true, true);
}
return strcmp(right->branch_info->srcline_from, left->branch_info->srcline_from);
}
left->branch_info->srcline_to = get_srcline(map->dso,
map__rip_2objdump(map,
left->branch_info->to.al_addr),
- left->branch_info->from.sym, true);
+ left->branch_info->from.sym,
+ true, true);
}
if (!right->branch_info->srcline_to) {
struct map *map = right->branch_info->to.map;
right->branch_info->srcline_to = get_srcline(map->dso,
map__rip_2objdump(map,
right->branch_info->to.al_addr),
- right->branch_info->to.sym, true);
+ right->branch_info->to.sym,
+ true, true);
}
return strcmp(right->branch_info->srcline_to, left->branch_info->srcline_to);
}
return no_srcfile;
sf = __get_srcline(map->dso, map__rip_2objdump(map, e->ip),
- e->ms.sym, false, true);
+ e->ms.sym, false, true, true);
if (!strcmp(sf, SRCLINE_UNKNOWN))
return no_srcfile;
p = strchr(sf, ':');
.se_width_idx = HISTC_CPU,
};
+/* --sort cgroup_id */
+
+static int64_t _sort__cgroup_dev_cmp(u64 left_dev, u64 right_dev)
+{
+ return (int64_t)(right_dev - left_dev);
+}
+
+static int64_t _sort__cgroup_inode_cmp(u64 left_ino, u64 right_ino)
+{
+ return (int64_t)(right_ino - left_ino);
+}
+
+static int64_t
+sort__cgroup_id_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+ int64_t ret;
+
+ ret = _sort__cgroup_dev_cmp(right->cgroup_id.dev, left->cgroup_id.dev);
+ if (ret != 0)
+ return ret;
+
+ return _sort__cgroup_inode_cmp(right->cgroup_id.ino,
+ left->cgroup_id.ino);
+}
+
+static int hist_entry__cgroup_id_snprintf(struct hist_entry *he,
+ char *bf, size_t size,
+ unsigned int width __maybe_unused)
+{
+ return repsep_snprintf(bf, size, "%lu/0x%lx", he->cgroup_id.dev,
+ he->cgroup_id.ino);
+}
+
+struct sort_entry sort_cgroup_id = {
+ .se_header = "cgroup id (dev/inode)",
+ .se_cmp = sort__cgroup_id_cmp,
+ .se_snprintf = hist_entry__cgroup_id_snprintf,
+ .se_width_idx = HISTC_CGROUP_ID,
+};
+
/* --sort socket */
static int64_t
static int64_t
sort__cycles_cmp(struct hist_entry *left, struct hist_entry *right)
{
+ if (!left->branch_info || !right->branch_info)
+ return cmp_null(left->branch_info, right->branch_info);
+
return left->branch_info->flags.cycles -
right->branch_info->flags.cycles;
}
static int hist_entry__cycles_snprintf(struct hist_entry *he, char *bf,
size_t size, unsigned int width)
{
+ if (!he->branch_info)
+ return scnprintf(bf, size, "%-.*s", width, "N/A");
if (he->branch_info->flags.cycles == 0)
return repsep_snprintf(bf, size, "%-*s", width, "-");
return repsep_snprintf(bf, size, "%-*hd", width,
.se_width_idx = HISTC_TRANSACTION,
};
+/* --sort symbol_size */
+
+static int64_t _sort__sym_size_cmp(struct symbol *sym_l, struct symbol *sym_r)
+{
+ int64_t size_l = sym_l != NULL ? symbol__size(sym_l) : 0;
+ int64_t size_r = sym_r != NULL ? symbol__size(sym_r) : 0;
+
+ return size_l < size_r ? -1 :
+ size_l == size_r ? 0 : 1;
+}
+
+static int64_t
+sort__sym_size_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+ return _sort__sym_size_cmp(right->ms.sym, left->ms.sym);
+}
+
+static int _hist_entry__sym_size_snprintf(struct symbol *sym, char *bf,
+ size_t bf_size, unsigned int width)
+{
+ if (sym)
+ return repsep_snprintf(bf, bf_size, "%*d", width, symbol__size(sym));
+
+ return repsep_snprintf(bf, bf_size, "%*s", width, "unknown");
+}
+
+static int hist_entry__sym_size_snprintf(struct hist_entry *he, char *bf,
+ size_t size, unsigned int width)
+{
+ return _hist_entry__sym_size_snprintf(he->ms.sym, bf, size, width);
+}
+
+struct sort_entry sort_sym_size = {
+ .se_header = "Symbol size",
+ .se_cmp = sort__sym_size_cmp,
+ .se_snprintf = hist_entry__sym_size_snprintf,
+ .se_width_idx = HISTC_SYM_SIZE,
+};
+
+
struct sort_dimension {
const char *name;
struct sort_entry *entry;
DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight),
DIM(SORT_TRANSACTION, "transaction", sort_transaction),
DIM(SORT_TRACE, "trace", sort_trace),
+ DIM(SORT_SYM_SIZE, "symbol_size", sort_sym_size),
+ DIM(SORT_CGROUP_ID, "cgroup_id", sort_cgroup_id),
};
#undef DIM
#define __PERF_SORT_H
#include "../builtin.h"
-#include "util.h"
+#include <regex.h>
#include "color.h"
#include <linux/list.h>
#include "symbol.h"
#include "string.h"
#include "callchain.h"
-#include "strlist.h"
#include "values.h"
#include "../perf.h"
#include <subcmd/parse-options.h>
#include "parse-events.h"
#include "hist.h"
-#include "thread.h"
+#include "srcline.h"
+
+struct thread;
extern regex_t parent_regex;
extern const char *sort_order;
u32 nr_events;
};
+struct namespace_id {
+ u64 dev;
+ u64 ino;
+};
+
struct hist_entry_diff {
bool computed;
union {
struct map_symbol ms;
struct thread *thread;
struct comm *comm;
+ struct namespace_id cgroup_id;
u64 ip;
u64 transaction;
s32 socket;
};
char *srcline;
char *srcfile;
+ struct inline_node *inline_node;
struct symbol *parent;
struct branch_info *branch_info;
struct hists *hists;
SORT_GLOBAL_WEIGHT,
SORT_TRANSACTION,
SORT_TRACE,
+ SORT_SYM_SIZE,
+ SORT_CGROUP_ID,
/* branch stack specific sort keys */
__SORT_BRANCH_STACK,
+#include <inttypes.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "util/dso.h"
#include "util/util.h"
#include "util/debug.h"
+#include "util/callchain.h"
+#include "srcline.h"
#include "symbol.h"
bool srcline_full_filename;
+static const char *dso__name(struct dso *dso)
+{
+ const char *dso_name;
+
+ if (dso->symsrc_filename)
+ dso_name = dso->symsrc_filename;
+ else
+ dso_name = dso->long_name;
+
+ if (dso_name[0] == '[')
+ return NULL;
+
+ if (!strncmp(dso_name, "/tmp/perf-", 10))
+ return NULL;
+
+ return dso_name;
+}
+
+static int inline_list__append(char *filename, char *funcname, int line_nr,
+ struct inline_node *node, struct dso *dso)
+{
+ struct inline_list *ilist;
+ char *demangled;
+
+ ilist = zalloc(sizeof(*ilist));
+ if (ilist == NULL)
+ return -1;
+
+ ilist->filename = filename;
+ ilist->line_nr = line_nr;
+
+ if (dso != NULL) {
+ demangled = dso__demangle_sym(dso, 0, funcname);
+ if (demangled == NULL) {
+ ilist->funcname = funcname;
+ } else {
+ ilist->funcname = demangled;
+ free(funcname);
+ }
+ }
+
+ list_add_tail(&ilist->list, &node->val);
+
+ return 0;
+}
+
#ifdef HAVE_LIBBFD_SUPPORT
/*
#define MAX_INLINE_NEST 1024
+static void inline_list__reverse(struct inline_node *node)
+{
+ struct inline_list *ilist, *n;
+
+ list_for_each_entry_safe_reverse(ilist, n, &node->val, list)
+ list_move_tail(&ilist->list, &node->val);
+}
+
static int addr2line(const char *dso_name, u64 addr,
char **file, unsigned int *line, struct dso *dso,
- bool unwind_inlines)
+ bool unwind_inlines, struct inline_node *node)
{
int ret = 0;
struct a2l_data *a2l = dso->a2l;
while (bfd_find_inliner_info(a2l->abfd, &a2l->filename,
&a2l->funcname, &a2l->line) &&
- cnt++ < MAX_INLINE_NEST)
- ;
+ cnt++ < MAX_INLINE_NEST) {
+
+ if (node != NULL) {
+ if (inline_list__append(strdup(a2l->filename),
+ strdup(a2l->funcname),
+ a2l->line, node,
+ dso) != 0)
+ return 0;
+ }
+ }
+
+ if ((node != NULL) &&
+ (callchain_param.order != ORDER_CALLEE)) {
+ inline_list__reverse(node);
+ }
}
if (a2l->found && a2l->filename) {
dso->a2l = NULL;
}
+static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
+ struct dso *dso)
+{
+ char *file = NULL;
+ unsigned int line = 0;
+ struct inline_node *node;
+
+ node = zalloc(sizeof(*node));
+ if (node == NULL) {
+ perror("not enough memory for the inline node");
+ return NULL;
+ }
+
+ INIT_LIST_HEAD(&node->val);
+ node->addr = addr;
+
+ if (!addr2line(dso_name, addr, &file, &line, dso, TRUE, node))
+ goto out_free_inline_node;
+
+ if (list_empty(&node->val))
+ goto out_free_inline_node;
+
+ return node;
+
+out_free_inline_node:
+ inline_node__delete(node);
+ return NULL;
+}
+
#else /* HAVE_LIBBFD_SUPPORT */
+static int filename_split(char *filename, unsigned int *line_nr)
+{
+ char *sep;
+
+ sep = strchr(filename, '\n');
+ if (sep)
+ *sep = '\0';
+
+ if (!strcmp(filename, "??:0"))
+ return 0;
+
+ sep = strchr(filename, ':');
+ if (sep) {
+ *sep++ = '\0';
+ *line_nr = strtoul(sep, NULL, 0);
+ return 1;
+ }
+
+ return 0;
+}
+
static int addr2line(const char *dso_name, u64 addr,
char **file, unsigned int *line_nr,
struct dso *dso __maybe_unused,
- bool unwind_inlines __maybe_unused)
+ bool unwind_inlines __maybe_unused,
+ struct inline_node *node __maybe_unused)
{
FILE *fp;
char cmd[PATH_MAX];
char *filename = NULL;
size_t len;
- char *sep;
int ret = 0;
scnprintf(cmd, sizeof(cmd), "addr2line -e %s %016"PRIx64,
goto out;
}
- sep = strchr(filename, '\n');
- if (sep)
- *sep = '\0';
-
- if (!strcmp(filename, "??:0")) {
- pr_debug("no debugging info in %s\n", dso_name);
+ ret = filename_split(filename, line_nr);
+ if (ret != 1) {
free(filename);
goto out;
}
- sep = strchr(filename, ':');
- if (sep) {
- *sep++ = '\0';
- *file = filename;
- *line_nr = strtoul(sep, NULL, 0);
- ret = 1;
- }
+ *file = filename;
+
out:
pclose(fp);
return ret;
{
}
+static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
+ struct dso *dso __maybe_unused)
+{
+ FILE *fp;
+ char cmd[PATH_MAX];
+ struct inline_node *node;
+ char *filename = NULL;
+ size_t len;
+ unsigned int line_nr = 0;
+
+ scnprintf(cmd, sizeof(cmd), "addr2line -e %s -i %016"PRIx64,
+ dso_name, addr);
+
+ fp = popen(cmd, "r");
+ if (fp == NULL) {
+ pr_err("popen failed for %s\n", dso_name);
+ return NULL;
+ }
+
+ node = zalloc(sizeof(*node));
+ if (node == NULL) {
+ perror("not enough memory for the inline node");
+ goto out;
+ }
+
+ INIT_LIST_HEAD(&node->val);
+ node->addr = addr;
+
+ while (getline(&filename, &len, fp) != -1) {
+ if (filename_split(filename, &line_nr) != 1) {
+ free(filename);
+ goto out;
+ }
+
+ if (inline_list__append(filename, NULL, line_nr, node,
+ NULL) != 0)
+ goto out;
+
+ filename = NULL;
+ }
+
+out:
+ pclose(fp);
+
+ if (list_empty(&node->val)) {
+ inline_node__delete(node);
+ return NULL;
+ }
+
+ return node;
+}
+
#endif /* HAVE_LIBBFD_SUPPORT */
/*
#define A2L_FAIL_LIMIT 123
char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
- bool show_sym, bool unwind_inlines)
+ bool show_sym, bool show_addr, bool unwind_inlines)
{
char *file = NULL;
unsigned line = 0;
if (!dso->has_srcline)
goto out;
- if (dso->symsrc_filename)
- dso_name = dso->symsrc_filename;
- else
- dso_name = dso->long_name;
-
- if (dso_name[0] == '[')
- goto out;
-
- if (!strncmp(dso_name, "/tmp/perf-", 10))
+ dso_name = dso__name(dso);
+ if (dso_name == NULL)
goto out;
- if (!addr2line(dso_name, addr, &file, &line, dso, unwind_inlines))
+ if (!addr2line(dso_name, addr, &file, &line, dso, unwind_inlines, NULL))
goto out;
if (asprintf(&srcline, "%s:%u",
dso->has_srcline = 0;
dso__free_a2l(dso);
}
+
+ if (!show_addr)
+ return (show_sym && sym) ?
+ strndup(sym->name, sym->namelen) : NULL;
+
if (sym) {
if (asprintf(&srcline, "%s+%" PRIu64, show_sym ? sym->name : "",
addr - sym->start) < 0)
}
char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
- bool show_sym)
+ bool show_sym, bool show_addr)
+{
+ return __get_srcline(dso, addr, sym, show_sym, show_addr, false);
+}
+
+struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr)
{
- return __get_srcline(dso, addr, sym, show_sym, false);
+ const char *dso_name;
+
+ dso_name = dso__name(dso);
+ if (dso_name == NULL)
+ return NULL;
+
+ return addr2inlines(dso_name, addr, dso);
+}
+
+void inline_node__delete(struct inline_node *node)
+{
+ struct inline_list *ilist, *tmp;
+
+ list_for_each_entry_safe(ilist, tmp, &node->val, list) {
+ list_del_init(&ilist->list);
+ zfree(&ilist->filename);
+ zfree(&ilist->funcname);
+ free(ilist);
+ }
+
+ free(node);
}
--- /dev/null
+#ifndef PERF_SRCLINE_H
+#define PERF_SRCLINE_H
+
+#include <linux/list.h>
+#include <linux/types.h>
+
+struct dso;
+struct symbol;
+
+extern bool srcline_full_filename;
+char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
+ bool show_sym, bool show_addr);
+char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
+ bool show_sym, bool show_addr, bool unwind_inlines);
+void free_srcline(char *srcline);
+
+#define SRCLINE_UNKNOWN ((char *) "??:0")
+
+struct inline_list {
+ char *filename;
+ char *funcname;
+ unsigned int line_nr;
+ struct list_head list;
+};
+
+struct inline_node {
+ u64 addr;
+ struct list_head val;
+};
+
+struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr);
+void inline_node__delete(struct inline_node *node);
+
+#endif /* PERF_SRCLINE_H */
#include "stat.h"
#include "color.h"
#include "pmu.h"
+#include "rblist.h"
+#include "evlist.h"
+#include "expr.h"
enum {
CTX_BIT_USER = 1 << 0,
static struct stats runtime_topdown_slots_retired[NUM_CTX][MAX_NR_CPUS];
static struct stats runtime_topdown_fetch_bubbles[NUM_CTX][MAX_NR_CPUS];
static struct stats runtime_topdown_recovery_bubbles[NUM_CTX][MAX_NR_CPUS];
+static struct rblist runtime_saved_values;
static bool have_frontend_stalled;
struct stats walltime_nsecs_stats;
+struct saved_value {
+ struct rb_node rb_node;
+ struct perf_evsel *evsel;
+ int cpu;
+ int ctx;
+ struct stats stats;
+};
+
+static int saved_value_cmp(struct rb_node *rb_node, const void *entry)
+{
+ struct saved_value *a = container_of(rb_node,
+ struct saved_value,
+ rb_node);
+ const struct saved_value *b = entry;
+
+ if (a->ctx != b->ctx)
+ return a->ctx - b->ctx;
+ if (a->cpu != b->cpu)
+ return a->cpu - b->cpu;
+ return a->evsel - b->evsel;
+}
+
+static struct rb_node *saved_value_new(struct rblist *rblist __maybe_unused,
+ const void *entry)
+{
+ struct saved_value *nd = malloc(sizeof(struct saved_value));
+
+ if (!nd)
+ return NULL;
+ memcpy(nd, entry, sizeof(struct saved_value));
+ return &nd->rb_node;
+}
+
+static struct saved_value *saved_value_lookup(struct perf_evsel *evsel,
+ int cpu, int ctx,
+ bool create)
+{
+ struct rb_node *nd;
+ struct saved_value dm = {
+ .cpu = cpu,
+ .ctx = ctx,
+ .evsel = evsel,
+ };
+ nd = rblist__find(&runtime_saved_values, &dm);
+ if (nd)
+ return container_of(nd, struct saved_value, rb_node);
+ if (create) {
+ rblist__add_node(&runtime_saved_values, &dm);
+ nd = rblist__find(&runtime_saved_values, &dm);
+ if (nd)
+ return container_of(nd, struct saved_value, rb_node);
+ }
+ return NULL;
+}
+
void perf_stat__init_shadow_stats(void)
{
have_frontend_stalled = pmu_have_event("cpu", "stalled-cycles-frontend");
+ rblist__init(&runtime_saved_values);
+ runtime_saved_values.node_cmp = saved_value_cmp;
+ runtime_saved_values.node_new = saved_value_new;
+ /* No delete for now */
}
static int evsel_context(struct perf_evsel *evsel)
void perf_stat__reset_shadow_stats(void)
{
+ struct rb_node *pos, *next;
+
memset(runtime_nsecs_stats, 0, sizeof(runtime_nsecs_stats));
memset(runtime_cycles_stats, 0, sizeof(runtime_cycles_stats));
memset(runtime_stalled_cycles_front_stats, 0, sizeof(runtime_stalled_cycles_front_stats));
memset(runtime_topdown_slots_issued, 0, sizeof(runtime_topdown_slots_issued));
memset(runtime_topdown_fetch_bubbles, 0, sizeof(runtime_topdown_fetch_bubbles));
memset(runtime_topdown_recovery_bubbles, 0, sizeof(runtime_topdown_recovery_bubbles));
+
+ next = rb_first(&runtime_saved_values.entries);
+ while (next) {
+ pos = next;
+ next = rb_next(pos);
+ memset(&container_of(pos, struct saved_value, rb_node)->stats,
+ 0,
+ sizeof(struct stats));
+ }
}
/*
update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count[0]);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
update_stats(&runtime_itlb_cache_stats[ctx][cpu], count[0]);
+
+ if (counter->collect_stat) {
+ struct saved_value *v = saved_value_lookup(counter, cpu, ctx,
+ true);
+ update_stats(&v->stats, count[0]);
+ }
}
/* used for get_ratio_color() */
return color;
}
+static struct perf_evsel *perf_stat__find_event(struct perf_evlist *evsel_list,
+ const char *name)
+{
+ struct perf_evsel *c2;
+
+ evlist__for_each_entry (evsel_list, c2) {
+ if (!strcasecmp(c2->name, name))
+ return c2;
+ }
+ return NULL;
+}
+
+/* Mark MetricExpr target events and link events using them to them. */
+void perf_stat__collect_metric_expr(struct perf_evlist *evsel_list)
+{
+ struct perf_evsel *counter, *leader, **metric_events, *oc;
+ bool found;
+ const char **metric_names;
+ int i;
+ int num_metric_names;
+
+ evlist__for_each_entry(evsel_list, counter) {
+ bool invalid = false;
+
+ leader = counter->leader;
+ if (!counter->metric_expr)
+ continue;
+ metric_events = counter->metric_events;
+ if (!metric_events) {
+ if (expr__find_other(counter->metric_expr, counter->name,
+ &metric_names, &num_metric_names) < 0)
+ continue;
+
+ metric_events = calloc(sizeof(struct perf_evsel *),
+ num_metric_names + 1);
+ if (!metric_events)
+ return;
+ counter->metric_events = metric_events;
+ }
+
+ for (i = 0; i < num_metric_names; i++) {
+ found = false;
+ if (leader) {
+ /* Search in group */
+ for_each_group_member (oc, leader) {
+ if (!strcasecmp(oc->name, metric_names[i])) {
+ found = true;
+ break;
+ }
+ }
+ }
+ if (!found) {
+ /* Search ignoring groups */
+ oc = perf_stat__find_event(evsel_list, metric_names[i]);
+ }
+ if (!oc) {
+ /* Deduping one is good enough to handle duplicated PMUs. */
+ static char *printed;
+
+ /*
+ * Adding events automatically would be difficult, because
+ * it would risk creating groups that are not schedulable.
+ * perf stat doesn't understand all the scheduling constraints
+ * of events. So we ask the user instead to add the missing
+ * events.
+ */
+ if (!printed || strcasecmp(printed, metric_names[i])) {
+ fprintf(stderr,
+ "Add %s event to groups to get metric expression for %s\n",
+ metric_names[i],
+ counter->name);
+ printed = strdup(metric_names[i]);
+ }
+ invalid = true;
+ continue;
+ }
+ metric_events[i] = oc;
+ oc->collect_stat = true;
+ }
+ metric_events[i] = NULL;
+ free(metric_names);
+ if (invalid) {
+ free(metric_events);
+ counter->metric_events = NULL;
+ counter->metric_expr = NULL;
+ }
+ }
+}
+
static void print_stalled_cycles_frontend(int cpu,
struct perf_evsel *evsel, double avg,
struct perf_stat_output_ctx *out)
be_bound * 100.);
else
print_metric(ctxp, NULL, NULL, name, 0);
+ } else if (evsel->metric_expr) {
+ struct parse_ctx pctx;
+ int i;
+
+ expr__ctx_init(&pctx);
+ expr__add_id(&pctx, evsel->name, avg);
+ for (i = 0; evsel->metric_events[i]; i++) {
+ struct saved_value *v;
+
+ v = saved_value_lookup(evsel->metric_events[i], cpu, ctx, false);
+ if (!v)
+ break;
+ expr__add_id(&pctx, evsel->metric_events[i]->name,
+ avg_stats(&v->stats));
+ }
+ if (!evsel->metric_events[i]) {
+ const char *p = evsel->metric_expr;
+
+ if (expr__parse(&ratio, &pctx, &p) == 0)
+ print_metric(ctxp, NULL, "%8.1f",
+ evsel->metric_name ?
+ evsel->metric_name :
+ out->force_header ? evsel->name : "",
+ ratio);
+ else
+ print_metric(ctxp, NULL, NULL, "", 0);
+ } else
+ print_metric(ctxp, NULL, NULL, "", 0);
} else if (runtime_nsecs_stats[cpu].n != 0) {
char unit = 'M';
char unit_buf[10];
+#include <errno.h>
+#include <inttypes.h>
#include <math.h>
#include "stat.h"
#include "evlist.h"
void *ctx;
print_metric_t print_metric;
new_line_t new_line;
+ bool force_header;
};
void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
double avg, int cpu,
struct perf_stat_output_ctx *out);
+void perf_stat__collect_metric_expr(struct perf_evlist *);
int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
void perf_evlist__free_stats(struct perf_evlist *evlist);
#include "debug.h"
#include "util.h"
#include <linux/kernel.h>
+#include <errno.h>
int prefixcmp(const char *str, const char *prefix)
{
#include "util.h"
-#include "string.h"
+#include "string2.h"
#include "strfilter.h"
+#include <errno.h>
+#include "sane_ctype.h"
+
/* Operators */
static const char *OP_and = "&"; /* Logical AND */
static const char *OP_or = "|"; /* Logical OR */
-#include "util.h"
-#include "linux/string.h"
+#include "string2.h"
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <stdlib.h>
+
+#include "sane_ctype.h"
#define K 1024LL
/*
void argv_free(char **argv)
{
char **p;
- for (p = argv; *p; p++)
- zfree(p);
+ for (p = argv; *p; p++) {
+ free(*p);
+ *p = NULL;
+ }
free(argv);
}
char **argv_split(const char *str, int *argcp)
{
int argc = count_argc(str);
- char **argv = zalloc(sizeof(*argv) * (argc+1));
+ char **argv = calloc(argc + 1, sizeof(*argv));
char **argvp;
if (argv == NULL)
*/
char *ltrim(char *s)
{
- int len = strlen(s);
-
- while (len && isspace(*s)) {
- len--;
+ while (isspace(*s))
s++;
- }
return s;
}
goto out_err_overflow;
if (i > 0)
- printed += snprintf(e + printed, size - printed, " %s ", or_and);
+ printed += scnprintf(e + printed, size - printed, " %s ", or_and);
printed += scnprintf(e + printed, size - printed,
"%s %s %d", var, eq_neq, ints[i]);
}
--- /dev/null
+#ifndef PERF_STRING_H
+#define PERF_STRING_H
+
+#include <linux/types.h>
+#include <stddef.h>
+#include <string.h>
+
+s64 perf_atoll(const char *str);
+char **argv_split(const char *str, int *argcp);
+void argv_free(char **argv);
+bool strglobmatch(const char *str, const char *pat);
+bool strglobmatch_nocase(const char *str, const char *pat);
+bool strlazymatch(const char *str, const char *pat);
+static inline bool strisglob(const char *str)
+{
+ return strpbrk(str, "*?[") != NULL;
+}
+int strtailcmp(const char *s1, const char *s2);
+char *strxfrchar(char *s, char from, char to);
+
+char *ltrim(char *s);
+char *rtrim(char *s);
+
+static inline char *trim(char *s)
+{
+ return ltrim(rtrim(s));
+}
+
+char *asprintf_expr_inout_ints(const char *var, bool in, size_t nints, int *ints);
+
+static inline char *asprintf_expr_in_ints(const char *var, size_t nints, int *ints)
+{
+ return asprintf_expr_inout_ints(var, true, nints, ints);
+}
+
+static inline char *asprintf_expr_not_in_ints(const char *var, size_t nints, int *ints)
+{
+ return asprintf_expr_inout_ints(var, false, nints, ints);
+}
+
+
+#endif /* PERF_STRING_H */
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
+#include <unistd.h>
static
struct rb_node *strlist__node_new(struct rblist *rblist, const void *entry)
#include "demangle-rust.h"
#include "machine.h"
#include "vdso.h"
-#include <symbol/kallsyms.h>
#include "debug.h"
+#include "sane_ctype.h"
+#include <symbol/kallsyms.h>
#ifndef EM_AARCH64
#define EM_AARCH64 183 /* ARM 64 bit */
return 0;
}
+char *dso__demangle_sym(struct dso *dso, int kmodule, char *elf_name)
+{
+ return demangle_sym(dso, kmodule, elf_name);
+}
+
/*
* Align offset to 4 bytes as needed for note name and descriptor data.
*/
static int populate_sdt_note(Elf **elf, const char *data, size_t len,
struct list_head *sdt_notes)
{
- const char *provider, *name;
+ const char *provider, *name, *args;
struct sdt_note *tmp = NULL;
GElf_Ehdr ehdr;
GElf_Addr base_off = 0;
goto out_free_prov;
}
+ args = memchr(name, '\0', data + len - name);
+
+ /*
+ * There is no argument if:
+ * - We reached the end of the note;
+ * - There is not enough room to hold a potential string;
+ * - The argument string is empty or just contains ':'.
+ */
+ if (args == NULL || data + len - args < 2 ||
+ args[1] == ':' || args[1] == '\0')
+ tmp->args = NULL;
+ else {
+ tmp->args = strdup(++args);
+ if (!tmp->args) {
+ ret = -ENOMEM;
+ goto out_free_name;
+ }
+ }
+
if (gelf_getclass(*elf) == ELFCLASS32) {
memcpy(&tmp->addr, &buf, 3 * sizeof(Elf32_Addr));
tmp->bit32 = true;
if (!gelf_getehdr(*elf, &ehdr)) {
pr_debug("%s : cannot get elf header.\n", __func__);
ret = -EBADF;
- goto out_free_name;
+ goto out_free_args;
}
/* Adjust the prelink effect :
list_add_tail(&tmp->note_list, sdt_notes);
return 0;
+out_free_args:
+ free(tmp->args);
out_free_name:
free(tmp->name);
out_free_prov:
#include "symbol.h"
#include "util.h"
+#include <errno.h>
#include <stdio.h>
#include <fcntl.h>
#include <string.h>
void symbol__elf_init(void)
{
}
+
+char *dso__demangle_sym(struct dso *dso __maybe_unused,
+ int kmodule __maybe_unused,
+ char *elf_name __maybe_unused)
+{
+ return NULL;
+}
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
+#include <linux/kernel.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/param.h>
#include "strlist.h"
#include "intlist.h"
#include "header.h"
+#include "path.h"
+#include "sane_ctype.h"
#include <elf.h>
#include <limits.h>
#include <libgen.h>
#include "build-id.h"
#include "event.h"
-#include "util.h"
+#include "path.h"
#ifdef HAVE_LIBELF_SUPPORT
#include <libelf.h>
show_ref_callgraph,
hide_unresolved,
raw_trace,
- report_hierarchy;
+ report_hierarchy,
+ inline_name;
const char *vmlinux_name,
*kallsyms_name,
*source_prefix,
int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss,
struct map *map);
+char *dso__demangle_sym(struct dso *dso, int kmodule, char *elf_name);
+
void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel);
void symbols__insert(struct rb_root *symbols, struct symbol *sym);
void symbols__fixup_duplicate(struct rb_root *symbols);
struct sdt_note {
char *name; /* name of the note*/
char *provider; /* provider name */
+ char *args;
bool bit32; /* whether the location is 32 bits? */
union { /* location, base and semaphore addrs */
Elf64_Addr a64[3];
-#include "util.h"
+#include "term.h"
+#include <stdlib.h>
+#include <termios.h>
+#include <unistd.h>
+#include <sys/ioctl.h>
void get_term_dimensions(struct winsize *ws)
{
#include <linux/rbtree.h>
#include <linux/list.h>
+#include <errno.h>
#include "thread.h"
#include "event.h"
#include "machine.h"
#include "../perf.h"
+#include <errno.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
+#include <linux/kernel.h>
#include "session.h"
#include "thread.h"
#include "thread-stack.h"
#include "util.h"
#include "debug.h"
+#include "namespaces.h"
#include "comm.h"
#include "unwind.h"
thread->tid = tid;
thread->ppid = -1;
thread->cpu = -1;
+ INIT_LIST_HEAD(&thread->namespaces_list);
INIT_LIST_HEAD(&thread->comm_list);
comm_str = malloc(32);
goto err_thread;
list_add(&comm->list, &thread->comm_list);
- atomic_set(&thread->refcnt, 1);
+ refcount_set(&thread->refcnt, 1);
RB_CLEAR_NODE(&thread->rb_node);
}
void thread__delete(struct thread *thread)
{
- struct comm *comm, *tmp;
+ struct namespaces *namespaces, *tmp_namespaces;
+ struct comm *comm, *tmp_comm;
BUG_ON(!RB_EMPTY_NODE(&thread->rb_node));
map_groups__put(thread->mg);
thread->mg = NULL;
}
- list_for_each_entry_safe(comm, tmp, &thread->comm_list, list) {
+ list_for_each_entry_safe(namespaces, tmp_namespaces,
+ &thread->namespaces_list, list) {
+ list_del(&namespaces->list);
+ namespaces__free(namespaces);
+ }
+ list_for_each_entry_safe(comm, tmp_comm, &thread->comm_list, list) {
list_del(&comm->list);
comm__free(comm);
}
struct thread *thread__get(struct thread *thread)
{
if (thread)
- atomic_inc(&thread->refcnt);
+ refcount_inc(&thread->refcnt);
return thread;
}
void thread__put(struct thread *thread)
{
- if (thread && atomic_dec_and_test(&thread->refcnt)) {
+ if (thread && refcount_dec_and_test(&thread->refcnt)) {
/*
* Remove it from the dead_threads list, as last reference
* is gone.
}
}
+struct namespaces *thread__namespaces(const struct thread *thread)
+{
+ if (list_empty(&thread->namespaces_list))
+ return NULL;
+
+ return list_first_entry(&thread->namespaces_list, struct namespaces, list);
+}
+
+int thread__set_namespaces(struct thread *thread, u64 timestamp,
+ struct namespaces_event *event)
+{
+ struct namespaces *new, *curr = thread__namespaces(thread);
+
+ new = namespaces__new(event);
+ if (!new)
+ return -ENOMEM;
+
+ list_add(&new->list, &thread->namespaces_list);
+
+ if (timestamp && curr) {
+ /*
+ * setns syscall must have changed few or all the namespaces
+ * of this thread. Update end time for the namespaces
+ * previously used.
+ */
+ curr = list_next_entry(new, list);
+ curr->end_time = timestamp;
+ }
+
+ return 0;
+}
+
struct comm *thread__comm(const struct thread *thread)
{
if (list_empty(&thread->comm_list))
#ifndef __PERF_THREAD_H
#define __PERF_THREAD_H
-#include <linux/atomic.h>
+#include <linux/refcount.h>
#include <linux/rbtree.h>
#include <linux/list.h>
#include <unistd.h>
pid_t tid;
pid_t ppid;
int cpu;
- atomic_t refcnt;
+ refcount_t refcnt;
char shortname[3];
bool comm_set;
int comm_len;
bool dead; /* if set thread has exited */
+ struct list_head namespaces_list;
struct list_head comm_list;
u64 db_id;
};
struct machine;
+struct namespaces;
struct comm;
struct thread *thread__new(pid_t pid, pid_t tid);
thread->dead = true;
}
+struct namespaces *thread__namespaces(const struct thread *thread);
+int thread__set_namespaces(struct thread *thread, u64 timestamp,
+ struct namespaces_event *event);
+
int __thread__set_comm(struct thread *thread, const char *comm, u64 timestamp,
bool exec);
static inline int thread__set_comm(struct thread *thread, const char *comm,
#include <dirent.h>
+#include <errno.h>
#include <limits.h>
#include <stdbool.h>
#include <stdlib.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <unistd.h>
+#include "string2.h"
#include "strlist.h"
#include <string.h>
#include <api/fs/fs.h>
for (i = 0; i < items; i++)
thread_map__set_pid(threads, i, atoi(namelist[i]->d_name));
threads->nr = items;
- atomic_set(&threads->refcnt, 1);
+ refcount_set(&threads->refcnt, 1);
}
for (i=0; i<items; i++)
if (threads != NULL) {
thread_map__set_pid(threads, 0, tid);
threads->nr = 1;
- atomic_set(&threads->refcnt, 1);
+ refcount_set(&threads->refcnt, 1);
}
return threads;
goto out_free_threads;
threads->nr = 0;
- atomic_set(&threads->refcnt, 1);
+ refcount_set(&threads->refcnt, 1);
while ((dirent = readdir(proc)) != NULL) {
char *end;
out:
strlist__delete(slist);
if (threads)
- atomic_set(&threads->refcnt, 1);
+ refcount_set(&threads->refcnt, 1);
return threads;
out_free_namelist:
if (threads != NULL) {
thread_map__set_pid(threads, 0, -1);
threads->nr = 1;
- atomic_set(&threads->refcnt, 1);
+ refcount_set(&threads->refcnt, 1);
}
return threads;
}
}
out:
if (threads)
- atomic_set(&threads->refcnt, 1);
+ refcount_set(&threads->refcnt, 1);
return threads;
out_free_threads:
if (threads) {
int i;
- WARN_ONCE(atomic_read(&threads->refcnt) != 0,
+ WARN_ONCE(refcount_read(&threads->refcnt) != 0,
"thread map refcnt unbalanced\n");
for (i = 0; i < threads->nr; i++)
free(thread_map__comm(threads, i));
struct thread_map *thread_map__get(struct thread_map *map)
{
if (map)
- atomic_inc(&map->refcnt);
+ refcount_inc(&map->refcnt);
return map;
}
void thread_map__put(struct thread_map *map)
{
- if (map && atomic_dec_and_test(&map->refcnt))
+ if (map && refcount_dec_and_test(&map->refcnt))
thread_map__delete(map);
}
threads->map[i].comm = strndup(event->entries[i].comm, 16);
}
- atomic_set(&threads->refcnt, 1);
+ refcount_set(&threads->refcnt, 1);
}
struct thread_map *thread_map__new_event(struct thread_map_event *event)
#include <sys/types.h>
#include <stdio.h>
-#include <linux/atomic.h>
+#include <linux/refcount.h>
struct thread_map_data {
pid_t pid;
};
struct thread_map {
- atomic_t refcnt;
+ refcount_t refcnt;
int nr;
struct thread_map_data map[];
};
return false;
}
+
+int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz)
+{
+ u64 sec = timestamp / NSEC_PER_SEC;
+ u64 usec = (timestamp % NSEC_PER_SEC) / NSEC_PER_USEC;
+
+ return scnprintf(buf, sz, "%"PRIu64".%06"PRIu64, sec, usec);
+}
+
+int fetch_current_timestamp(char *buf, size_t sz)
+{
+ struct timeval tv;
+ struct tm tm;
+ char dt[32];
+
+ if (gettimeofday(&tv, NULL) || !localtime_r(&tv.tv_sec, &tm))
+ return -1;
+
+ if (!strftime(dt, sizeof(dt), "%Y%m%d%H%M%S", &tm))
+ return -1;
+
+ scnprintf(buf, sz, "%s%02u", dt, (unsigned)tv.tv_usec / 10000);
+
+ return 0;
+}
#ifndef _TIME_UTILS_H_
#define _TIME_UTILS_H_
+#include <stddef.h>
+#include <linux/types.h>
+
struct perf_time_interval {
u64 start, end;
};
bool perf_time__skip_sample(struct perf_time_interval *ptime, u64 timestamp);
+int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz);
+
+int fetch_current_timestamp(char *buf, size_t sz);
+
#endif
event_op mmap,
mmap2,
comm,
+ namespaces,
fork,
exit,
lost,
event_op3 auxtrace;
bool ordered_events;
bool ordering_requires_timestamps;
+ bool namespace_events;
};
#endif /* __PERF_TOOL_H */
#include <linux/types.h>
#include <stddef.h>
#include <stdbool.h>
-#include <termios.h>
+#include <sys/ioctl.h>
struct perf_evlist;
struct perf_evsel;
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
-#include <ctype.h>
#include <errno.h>
#include "../perf.h"
#include "util.h"
#include "trace-event.h"
+#include "sane_ctype.h"
+
static int get_common_field(struct scripting_context *context,
int *offset, int *size, const char *type)
{
if (!size)
return 0;
- buf = malloc(size);
+ buf = malloc(size + 1);
if (buf == NULL)
return -1;
return -1;
}
+ buf[size] = '\0';
+
parse_ftrace_printk(pevent, buf, size);
free(buf);
--- /dev/null
+#include "units.h"
+#include <inttypes.h>
+#include <linux/kernel.h>
+#include <linux/time64.h>
+
+unsigned long convert_unit(unsigned long value, char *unit)
+{
+ *unit = ' ';
+
+ if (value > 1000) {
+ value /= 1000;
+ *unit = 'K';
+ }
+
+ if (value > 1000) {
+ value /= 1000;
+ *unit = 'M';
+ }
+
+ if (value > 1000) {
+ value /= 1000;
+ *unit = 'G';
+ }
+
+ return value;
+}
+
+int unit_number__scnprintf(char *buf, size_t size, u64 n)
+{
+ char unit[4] = "BKMG";
+ int i = 0;
+
+ while (((n / 1024) > 1) && (i < 3)) {
+ n /= 1024;
+ i++;
+ }
+
+ return scnprintf(buf, size, "%" PRIu64 "%c", n, unit[i]);
+}
--- /dev/null
+#ifndef PERF_UNIT_H
+#define PERF_UNIT_H
+
+#include <stddef.h>
+#include <linux/types.h>
+
+unsigned long convert_unit(unsigned long value, char *unit);
+int unit_number__scnprintf(char *buf, size_t size, u64 n);
+
+#endif /* PERF_UNIT_H */
#include "event.h"
#include "perf_regs.h"
#include "callchain.h"
+#include "util.h"
static char *debuginfo_path;
#define __PERF_UNWIND_LIBDW_H
#include <elfutils/libdwfl.h>
-#include "event.h"
-#include "thread.h"
#include "unwind.h"
+struct machine;
+struct perf_sample;
+struct thread;
+
bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg);
struct unwind_info {
*/
#include <elf.h>
+#include <errno.h>
#include <gelf.h>
#include <fcntl.h>
+#include <inttypes.h>
#include <string.h>
#include <unistd.h>
#include <sys/mman.h>
#ifndef __UNWIND_H
#define __UNWIND_H
+#include <linux/compiler.h>
#include <linux/types.h>
-#include "event.h"
-#include "symbol.h"
-#include "thread.h"
+
+struct map;
+struct perf_sample;
+struct symbol;
+struct thread;
struct unwind_entry {
struct map *map;
#include "debug.h"
#include <api/fs/fs.h>
#include <sys/mman.h>
+#include <sys/stat.h>
#include <sys/utsname.h>
-#ifdef HAVE_BACKTRACE_SUPPORT
-#include <execinfo.h>
-#endif
+#include <dirent.h>
+#include <inttypes.h>
+#include <signal.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <linux/log2.h>
#include <linux/time64.h>
#include <unistd.h>
-#include "callchain.h"
#include "strlist.h"
-#define CALLCHAIN_PARAM_DEFAULT \
- .mode = CHAIN_GRAPH_ABS, \
- .min_percent = 0.5, \
- .order = ORDER_CALLEE, \
- .key = CCKEY_FUNCTION, \
- .value = CCVAL_PERCENT, \
-
-struct callchain_param callchain_param = {
- CALLCHAIN_PARAM_DEFAULT
-};
-
-struct callchain_param callchain_param_default = {
- CALLCHAIN_PARAM_DEFAULT
-};
-
/*
* XXX We need to find a better place for these things...
*/
return copyfile_mode(from, to, 0755);
}
-unsigned long convert_unit(unsigned long value, char *unit)
-{
- *unit = ' ';
-
- if (value > 1000) {
- value /= 1000;
- *unit = 'K';
- }
-
- if (value > 1000) {
- value /= 1000;
- *unit = 'M';
- }
-
- if (value > 1000) {
- value /= 1000;
- *unit = 'G';
- }
-
- return value;
-}
-
static ssize_t ion(bool is_read, int fd, void *buf, size_t n)
{
void *buf_start = buf;
return p - ptr;
}
-/* Obtain a backtrace and print it to stdout. */
-#ifdef HAVE_BACKTRACE_SUPPORT
-void dump_stack(void)
-{
- void *array[16];
- size_t size = backtrace(array, ARRAY_SIZE(array));
- char **strings = backtrace_symbols(array, size);
- size_t i;
-
- printf("Obtained %zd stack frames.\n", size);
-
- for (i = 0; i < size; i++)
- printf("%s\n", strings[i]);
-
- free(strings);
-}
-#else
-void dump_stack(void) {}
-#endif
-
-void sighandler_dump_stack(int sig)
-{
- psignal(sig, "perf");
- dump_stack();
- signal(sig, SIG_DFL);
- raise(sig);
-}
-
-int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz)
-{
- u64 sec = timestamp / NSEC_PER_SEC;
- u64 usec = (timestamp % NSEC_PER_SEC) / NSEC_PER_USEC;
-
- return scnprintf(buf, sz, "%"PRIu64".%06"PRIu64, sec, usec);
-}
-
unsigned long parse_tag_value(const char *str, struct parse_tag *tags)
{
struct parse_tag *i = tags;
return (unsigned long) -1;
}
-int get_stack_size(const char *str, unsigned long *_size)
-{
- char *endptr;
- unsigned long size;
- unsigned long max_size = round_down(USHRT_MAX, sizeof(u64));
-
- size = strtoul(str, &endptr, 0);
-
- do {
- if (*endptr)
- break;
-
- size = round_up(size, sizeof(u64));
- if (!size || size > max_size)
- break;
-
- *_size = size;
- return 0;
-
- } while (0);
-
- pr_err("callchain: Incorrect stack dump size (max %ld): %s\n",
- max_size, str);
- return -1;
-}
-
-int parse_callchain_record(const char *arg, struct callchain_param *param)
-{
- char *tok, *name, *saveptr = NULL;
- char *buf;
- int ret = -1;
-
- /* We need buffer that we know we can write to. */
- buf = malloc(strlen(arg) + 1);
- if (!buf)
- return -ENOMEM;
-
- strcpy(buf, arg);
-
- tok = strtok_r((char *)buf, ",", &saveptr);
- name = tok ? : (char *)buf;
-
- do {
- /* Framepointer style */
- if (!strncmp(name, "fp", sizeof("fp"))) {
- if (!strtok_r(NULL, ",", &saveptr)) {
- param->record_mode = CALLCHAIN_FP;
- ret = 0;
- } else
- pr_err("callchain: No more arguments "
- "needed for --call-graph fp\n");
- break;
-
- /* Dwarf style */
- } else if (!strncmp(name, "dwarf", sizeof("dwarf"))) {
- const unsigned long default_stack_dump_size = 8192;
-
- ret = 0;
- param->record_mode = CALLCHAIN_DWARF;
- param->dump_size = default_stack_dump_size;
-
- tok = strtok_r(NULL, ",", &saveptr);
- if (tok) {
- unsigned long size = 0;
-
- ret = get_stack_size(tok, &size);
- param->dump_size = size;
- }
- } else if (!strncmp(name, "lbr", sizeof("lbr"))) {
- if (!strtok_r(NULL, ",", &saveptr)) {
- param->record_mode = CALLCHAIN_LBR;
- ret = 0;
- } else
- pr_err("callchain: No more arguments "
- "needed for --call-graph lbr\n");
- break;
- } else {
- pr_err("callchain: Unknown --call-graph option "
- "value: %s\n", arg);
- break;
- }
-
- } while (0);
-
- free(buf);
- return ret;
-}
-
-const char *get_filename_for_perf_kvm(void)
-{
- const char *filename;
-
- if (perf_host && !perf_guest)
- filename = strdup("perf.data.host");
- else if (!perf_host && perf_guest)
- filename = strdup("perf.data.guest");
- else
- filename = strdup("perf.data.kvm");
-
- return filename;
-}
-
int perf_event_paranoid(void)
{
int value;
tips = strlist__new("tips.txt", &conf);
if (tips == NULL)
- return errno == ENOENT ? NULL : "Tip: get more memory! ;-p";
+ return errno == ENOENT ? NULL :
+ "Tip: check path of tips.txt or get more memory! ;-p";
if (strlist__nr_entries(tips) == 0)
goto out;
return tip;
}
-
-bool is_regular_file(const char *file)
-{
- struct stat st;
-
- if (stat(file, &st))
- return false;
-
- return S_ISREG(st.st_mode);
-}
-
-int fetch_current_timestamp(char *buf, size_t sz)
-{
- struct timeval tv;
- struct tm tm;
- char dt[32];
-
- if (gettimeofday(&tv, NULL) || !localtime_r(&tv.tv_sec, &tm))
- return -1;
-
- if (!strftime(dt, sizeof(dt), "%Y%m%d%H%M%S", &tm))
- return -1;
-
- scnprintf(buf, sz, "%s%02u", dt, (unsigned)tv.tv_usec / 10000);
-
- return 0;
-}
-
-void print_binary(unsigned char *data, size_t len,
- size_t bytes_per_line, print_binary_t printer,
- void *extra)
-{
- size_t i, j, mask;
-
- if (!printer)
- return;
-
- bytes_per_line = roundup_pow_of_two(bytes_per_line);
- mask = bytes_per_line - 1;
-
- printer(BINARY_PRINT_DATA_BEGIN, 0, extra);
- for (i = 0; i < len; i++) {
- if ((i & mask) == 0) {
- printer(BINARY_PRINT_LINE_BEGIN, -1, extra);
- printer(BINARY_PRINT_ADDR, i, extra);
- }
-
- printer(BINARY_PRINT_NUM_DATA, data[i], extra);
-
- if (((i & mask) == mask) || i == len - 1) {
- for (j = 0; j < mask-(i & mask); j++)
- printer(BINARY_PRINT_NUM_PAD, -1, extra);
-
- printer(BINARY_PRINT_SEP, i, extra);
- for (j = i & ~mask; j <= i; j++)
- printer(BINARY_PRINT_CHAR_DATA, data[j], extra);
- for (j = 0; j < mask-(i & mask); j++)
- printer(BINARY_PRINT_CHAR_PAD, i, extra);
- printer(BINARY_PRINT_LINE_END, -1, extra);
- }
- }
- printer(BINARY_PRINT_DATA_END, -1, extra);
-}
-
-int is_printable_array(char *p, unsigned int len)
-{
- unsigned int i;
-
- if (!p || !len || p[len - 1] != 0)
- return 0;
-
- len--;
-
- for (i = 0; i < len; i++) {
- if (!isprint(p[i]) && !isspace(p[i]))
- return 0;
- }
- return 1;
-}
-
-int unit_number__scnprintf(char *buf, size_t size, u64 n)
-{
- char unit[4] = "BKMG";
- int i = 0;
-
- while (((n / 1024) > 1) && (i < 3)) {
- n /= 1024;
- i++;
- }
-
- return scnprintf(buf, size, "%" PRIu64 "%c", n, unit[i]);
-}
#ifndef GIT_COMPAT_UTIL_H
#define GIT_COMPAT_UTIL_H
-#ifndef FLEX_ARRAY
-/*
- * See if our compiler is known to support flexible array members.
- */
-#if defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L)
-# define FLEX_ARRAY /* empty */
-#elif defined(__GNUC__)
-# if (__GNUC__ >= 3)
-# define FLEX_ARRAY /* empty */
-# else
-# define FLEX_ARRAY 0 /* older GNU extension */
-# endif
-#endif
-
-/*
- * Otherwise, default to safer but a bit wasteful traditional style
- */
-#ifndef FLEX_ARRAY
-# define FLEX_ARRAY 1
-#endif
-#endif
-
-#define ARRAY_SIZE(x) (sizeof(x)/sizeof(x[0]))
-
-#ifdef __GNUC__
-#define TYPEOF(x) (__typeof__(x))
-#else
-#define TYPEOF(x)
-#endif
-
-#define MSB(x, bits) ((x) & TYPEOF(x)(~0ULL << (sizeof(x) * 8 - (bits))))
-#define HAS_MULTI_BITS(i) ((i) & ((i) - 1)) /* checks if an integer has more than 1 bit set */
-
-/* Approximation of the length of the decimal representation of this type. */
-#define decimal_length(x) ((int)(sizeof(x) * 2.56 + 0.5) + 1)
-
#define _ALL_SOURCE 1
#define _BSD_SOURCE 1
/* glibc 2.20 deprecates _BSD_SOURCE in favour of _DEFAULT_SOURCE */
#define _DEFAULT_SOURCE 1
#define HAS_BOOL
-#include <unistd.h>
-#include <stdio.h>
-#include <sys/stat.h>
-#include <sys/statfs.h>
#include <fcntl.h>
#include <stdbool.h>
#include <stddef.h>
#include <stdlib.h>
#include <stdarg.h>
-#include <string.h>
-#include <term.h>
-#include <errno.h>
-#include <limits.h>
-#include <sys/param.h>
-#include <sys/types.h>
-#include <dirent.h>
-#include <sys/time.h>
-#include <time.h>
-#include <signal.h>
-#include <fnmatch.h>
-#include <assert.h>
-#include <regex.h>
-#include <utime.h>
-#include <sys/wait.h>
-#include <poll.h>
-#include <sys/socket.h>
-#include <sys/ioctl.h>
-#include <inttypes.h>
-#include <linux/kernel.h>
#include <linux/types.h>
-#include <sys/ttydefaults.h>
-#include <api/fs/tracing_path.h>
-#include <termios.h>
-#include <linux/bitops.h>
-#include <termios.h>
-#include "strlist.h"
-extern const char *graph_line;
-extern const char *graph_dotted_line;
-extern const char *spaces;
-extern const char *dots;
extern char buildid_dir[];
-/* On most systems <limits.h> would have given us this, but
- * not on some systems (e.g. GNU/Hurd).
- */
-#ifndef PATH_MAX
-#define PATH_MAX 4096
-#endif
-
-#ifndef PRIuMAX
-#define PRIuMAX "llu"
-#endif
-
-#ifndef PRIu32
-#define PRIu32 "u"
-#endif
-
-#ifndef PRIx32
-#define PRIx32 "x"
-#endif
-
-#ifndef PATH_SEP
-#define PATH_SEP ':'
-#endif
-
-#ifndef STRIP_EXTENSION
-#define STRIP_EXTENSION ""
-#endif
-
-#ifndef has_dos_drive_prefix
-#define has_dos_drive_prefix(path) 0
-#endif
-
-#ifndef is_dir_sep
-#define is_dir_sep(c) ((c) == '/')
-#endif
-
#ifdef __GNUC__
#define NORETURN __attribute__((__noreturn__))
#else
int prefixcmp(const char *str, const char *prefix);
void set_buildid_dir(const char *dir);
-#ifdef __GLIBC_PREREQ
-#if __GLIBC_PREREQ(2, 1)
-#define HAVE_STRCHRNUL
-#endif
-#endif
-
-#ifndef HAVE_STRCHRNUL
-#define strchrnul gitstrchrnul
-static inline char *gitstrchrnul(const char *s, int c)
-{
- while (*s && *s != c)
- s++;
- return (char *)s;
-}
-#endif
-
static inline void *zalloc(size_t size)
{
return calloc(1, size);
#define zfree(ptr) ({ free(*ptr); *ptr = NULL; })
-/* Sane ctype - no locale, and works with signed chars */
-#undef isascii
-#undef isspace
-#undef isdigit
-#undef isxdigit
-#undef isalpha
-#undef isprint
-#undef isalnum
-#undef islower
-#undef isupper
-#undef tolower
-#undef toupper
-
-extern unsigned char sane_ctype[256];
-#define GIT_SPACE 0x01
-#define GIT_DIGIT 0x02
-#define GIT_ALPHA 0x04
-#define GIT_GLOB_SPECIAL 0x08
-#define GIT_REGEX_SPECIAL 0x10
-#define GIT_PRINT_EXTRA 0x20
-#define GIT_PRINT 0x3E
-#define sane_istest(x,mask) ((sane_ctype[(unsigned char)(x)] & (mask)) != 0)
-#define isascii(x) (((x) & ~0x7f) == 0)
-#define isspace(x) sane_istest(x,GIT_SPACE)
-#define isdigit(x) sane_istest(x,GIT_DIGIT)
-#define isxdigit(x) \
- (sane_istest(toupper(x), GIT_ALPHA | GIT_DIGIT) && toupper(x) < 'G')
-#define isalpha(x) sane_istest(x,GIT_ALPHA)
-#define isalnum(x) sane_istest(x,GIT_ALPHA | GIT_DIGIT)
-#define isprint(x) sane_istest(x,GIT_PRINT)
-#define islower(x) (sane_istest(x,GIT_ALPHA) && (x & 0x20))
-#define isupper(x) (sane_istest(x,GIT_ALPHA) && !(x & 0x20))
-#define tolower(x) sane_case((unsigned char)(x), 0x20)
-#define toupper(x) sane_case((unsigned char)(x), 0)
-
-static inline int sane_case(int x, int high)
-{
- if (sane_istest(x, GIT_ALPHA))
- x = (x & ~0x20) | high;
- return x;
-}
+struct dirent;
+struct strlist;
int mkdir_p(char *path, mode_t mode);
int rm_rf(const char *path);
int copyfile_mode(const char *from, const char *to, mode_t mode);
int copyfile_offset(int fromfd, loff_t from_ofs, int tofd, loff_t to_ofs, u64 size);
-s64 perf_atoll(const char *str);
-char **argv_split(const char *str, int *argcp);
-void argv_free(char **argv);
-bool strglobmatch(const char *str, const char *pat);
-bool strglobmatch_nocase(const char *str, const char *pat);
-bool strlazymatch(const char *str, const char *pat);
-static inline bool strisglob(const char *str)
-{
- return strpbrk(str, "*?[") != NULL;
-}
-int strtailcmp(const char *s1, const char *s2);
-char *strxfrchar(char *s, char from, char to);
-unsigned long convert_unit(unsigned long value, char *unit);
ssize_t readn(int fd, void *buf, size_t n);
ssize_t writen(int fd, void *buf, size_t n);
void event_attr_init(struct perf_event_attr *attr);
-#define _STR(x) #x
-#define STR(x) _STR(x)
-
size_t hex_width(u64 v);
int hex2u64(const char *ptr, u64 *val);
-char *ltrim(char *s);
-char *rtrim(char *s);
-
-static inline char *trim(char *s)
-{
- return ltrim(rtrim(s));
-}
-
-void dump_stack(void);
-void sighandler_dump_stack(int sig);
-
extern unsigned int page_size;
extern int cacheline_size;
extern int sysctl_perf_event_max_stack;
unsigned long parse_tag_value(const char *str, struct parse_tag *tags);
-#define SRCLINE_UNKNOWN ((char *) "??:0")
-
-static inline int path__join(char *bf, size_t size,
- const char *path1, const char *path2)
-{
- return scnprintf(bf, size, "%s%s%s", path1, path1[0] ? "/" : "", path2);
-}
-
-static inline int path__join3(char *bf, size_t size,
- const char *path1, const char *path2,
- const char *path3)
-{
- return scnprintf(bf, size, "%s%s%s%s%s",
- path1, path1[0] ? "/" : "",
- path2, path2[0] ? "/" : "", path3);
-}
-
-struct dso;
-struct symbol;
-
-extern bool srcline_full_filename;
-char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
- bool show_sym);
-char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
- bool show_sym, bool unwind_inlines);
-void free_srcline(char *srcline);
-
int perf_event_paranoid(void);
void mem_bswap_64(void *src, int byte_size);
void mem_bswap_32(void *src, int byte_size);
-const char *get_filename_for_perf_kvm(void);
bool find_process(const char *name);
-#ifdef HAVE_ZLIB_SUPPORT
-int gzip_decompress_to_file(const char *input, int output_fd);
-#endif
-
-#ifdef HAVE_LZMA_SUPPORT
-int lzma_decompress_to_file(const char *input, int output_fd);
-#endif
-
-char *asprintf_expr_inout_ints(const char *var, bool in, size_t nints, int *ints);
-
-static inline char *asprintf_expr_in_ints(const char *var, size_t nints, int *ints)
-{
- return asprintf_expr_inout_ints(var, true, nints, ints);
-}
-
-static inline char *asprintf_expr_not_in_ints(const char *var, size_t nints, int *ints)
-{
- return asprintf_expr_inout_ints(var, false, nints, ints);
-}
-
-int get_stack_size(const char *str, unsigned long *_size);
-
int fetch_kernel_version(unsigned int *puint,
char *str, size_t str_sz);
#define KVER_VERSION(x) (((x) >> 16) & 0xff)
#define KVER_PARAM(x) KVER_VERSION(x), KVER_PATCHLEVEL(x), KVER_SUBLEVEL(x)
const char *perf_tip(const char *dirpath);
-bool is_regular_file(const char *file);
-int fetch_current_timestamp(char *buf, size_t sz);
-
-enum binary_printer_ops {
- BINARY_PRINT_DATA_BEGIN,
- BINARY_PRINT_LINE_BEGIN,
- BINARY_PRINT_ADDR,
- BINARY_PRINT_NUM_DATA,
- BINARY_PRINT_NUM_PAD,
- BINARY_PRINT_SEP,
- BINARY_PRINT_CHAR_DATA,
- BINARY_PRINT_CHAR_PAD,
- BINARY_PRINT_LINE_END,
- BINARY_PRINT_DATA_END,
-};
-typedef void (*print_binary_t)(enum binary_printer_ops,
- unsigned int val,
- void *extra);
-
-void print_binary(unsigned char *data, size_t len,
- size_t bytes_per_line, print_binary_t printer,
- void *extra);
-
-#if !defined(__GLIBC__) && !defined(__ANDROID__)
-extern int sched_getcpu(void);
+#ifndef HAVE_SCHED_GETCPU_SUPPORT
+int sched_getcpu(void);
#endif
-int is_printable_array(char *p, unsigned int len);
-
-int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz);
-
-int unit_number__scnprintf(char *buf, size_t size, u64 n);
#endif /* GIT_COMPAT_UTIL_H */
+#include <inttypes.h>
+#include <stdio.h>
#include <stdlib.h>
+#include <errno.h>
#include "util.h"
#include "values.h"
return i;
}
-static void perf_read_values__enlarge_counters(struct perf_read_values *values)
+static int perf_read_values__enlarge_counters(struct perf_read_values *values)
{
- int i;
+ char **countername;
+ int i, counters_max = values->counters_max * 2;
+ u64 *counterrawid = realloc(values->counterrawid, counters_max * sizeof(*values->counterrawid));
+
+ if (!counterrawid) {
+ pr_debug("failed to enlarge read_values rawid array");
+ goto out_enomem;
+ }
- values->counters_max *= 2;
- values->counterrawid = realloc(values->counterrawid,
- values->counters_max * sizeof(*values->counterrawid));
- values->countername = realloc(values->countername,
- values->counters_max * sizeof(*values->countername));
- if (!values->counterrawid || !values->countername)
- die("failed to enlarge read_values counters arrays");
+ countername = realloc(values->countername, counters_max * sizeof(*values->countername));
+ if (!countername) {
+ pr_debug("failed to enlarge read_values rawid array");
+ goto out_free_rawid;
+ }
for (i = 0; i < values->threads; i++) {
- values->value[i] = realloc(values->value[i],
- values->counters_max * sizeof(**values->value));
- if (!values->value[i])
- die("failed to enlarge read_values counters arrays");
+ u64 *value = realloc(values->value[i], counters_max * sizeof(**values->value));
+
+ if (value) {
+ pr_debug("failed to enlarge read_values ->values array");
+ goto out_free_name;
+ }
+
+ values->value[i] = value;
}
+
+ values->counters_max = counters_max;
+ values->counterrawid = counterrawid;
+ values->countername = countername;
+
+ return 0;
+out_free_name:
+ free(countername);
+out_free_rawid:
+ free(counterrawid);
+out_enomem:
+ return -ENOMEM;
}
static int perf_read_values__findnew_counter(struct perf_read_values *values,
if (values->counterrawid[i] == rawid)
return i;
- if (values->counters == values->counters_max)
- perf_read_values__enlarge_counters(values);
+ if (values->counters == values->counters_max) {
+ i = perf_read_values__enlarge_counters(values);
+ if (i)
+ return i;
+ }
i = values->counters++;
values->counterrawid[i] = rawid;
int *counterwidth;
counterwidth = malloc(values->counters * sizeof(*counterwidth));
- if (!counterwidth)
- die("failed to allocate counterwidth array");
+ if (!counterwidth) {
+ fprintf(fp, "INTERNAL ERROR: Failed to allocate counterwidth array\n");
+ return;
+ }
tidwidth = 3;
pidwidth = 3;
for (j = 0; j < values->counters; j++)
-
+#include <errno.h>
#include <unistd.h>
#include <stdio.h>
#include <string.h>
#include "xyarray.h"
#include "util.h"
+#include <stdlib.h>
+#include <string.h>
struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size)
{
#include <sys/mman.h>
#include <zlib.h>
+#include "util/compress.h"
#include "util/util.h"
#include "util/debug.h"
*/
case 0x2C: /* Westmere EP - Gulftown */
cpu_info->caps |= CPUPOWER_CAP_HAS_TURBO_RATIO;
+ break;
case 0x2A: /* SNB */
case 0x2D: /* SNB Xeon */
case 0x3A: /* IVB */
--- /dev/null
+PREFIX ?= /usr
+DESTDIR ?=
+
+all:
+ @echo "Nothing to build"
+
+install :
+ install -d $(DESTDIR)$(PREFIX)/lib/pm-graph
+ install analyze_suspend.py $(DESTDIR)$(PREFIX)/lib/pm-graph
+ install analyze_boot.py $(DESTDIR)$(PREFIX)/lib/pm-graph
+
+ ln -s $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_boot.py $(DESTDIR)$(PREFIX)/bin/bootgraph
+ ln -s $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_suspend.py $(DESTDIR)$(PREFIX)/bin/sleepgraph
+
+ install -d $(DESTDIR)$(PREFIX)/share/man/man8
+ install bootgraph.8 $(DESTDIR)$(PREFIX)/share/man/man8
+ install sleepgraph.8 $(DESTDIR)$(PREFIX)/share/man/man8
+
+uninstall :
+ rm $(DESTDIR)$(PREFIX)/share/man/man8/bootgraph.8
+ rm $(DESTDIR)$(PREFIX)/share/man/man8/sleepgraph.8
+
+ rm $(DESTDIR)$(PREFIX)/bin/bootgraph
+ rm $(DESTDIR)$(PREFIX)/bin/sleepgraph
+
+ rm $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_boot.py
+ rm $(DESTDIR)$(PREFIX)/lib/pm-graph/analyze_suspend.py
+ rmdir $(DESTDIR)$(PREFIX)/lib/pm-graph
--- /dev/null
+#!/usr/bin/python
+#
+# Tool for analyzing boot timing
+# Copyright (c) 2013, Intel Corporation.
+#
+# This program is free software; you can redistribute it and/or modify it
+# under the terms and conditions of the GNU General Public License,
+# version 2, as published by the Free Software Foundation.
+#
+# This program is distributed in the hope it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+# more details.
+#
+# Authors:
+# Todd Brandt <todd.e.brandt@linux.intel.com>
+#
+# Description:
+# This tool is designed to assist kernel and OS developers in optimizing
+# their linux stack's boot time. It creates an html representation of
+# the kernel boot timeline up to the start of the init process.
+#
+
+# ----------------- LIBRARIES --------------------
+
+import sys
+import time
+import os
+import string
+import re
+import platform
+import shutil
+from datetime import datetime, timedelta
+from subprocess import call, Popen, PIPE
+import analyze_suspend as aslib
+
+# ----------------- CLASSES --------------------
+
+# Class: SystemValues
+# Description:
+# A global, single-instance container used to
+# store system values and test parameters
+class SystemValues(aslib.SystemValues):
+ title = 'BootGraph'
+ version = 2.0
+ hostname = 'localhost'
+ testtime = ''
+ kernel = ''
+ dmesgfile = ''
+ ftracefile = ''
+ htmlfile = 'bootgraph.html'
+ outfile = ''
+ phoronix = False
+ addlogs = False
+ useftrace = False
+ usedevsrc = True
+ suspendmode = 'boot'
+ max_graph_depth = 2
+ graph_filter = 'do_one_initcall'
+ reboot = False
+ manual = False
+ iscronjob = False
+ timeformat = '%.6f'
+ def __init__(self):
+ if('LOG_FILE' in os.environ and 'TEST_RESULTS_IDENTIFIER' in os.environ):
+ self.phoronix = True
+ self.addlogs = True
+ self.outfile = os.environ['LOG_FILE']
+ self.htmlfile = os.environ['LOG_FILE']
+ self.hostname = platform.node()
+ self.testtime = datetime.now().strftime('%Y-%m-%d_%H:%M:%S')
+ if os.path.exists('/proc/version'):
+ fp = open('/proc/version', 'r')
+ val = fp.read().strip()
+ fp.close()
+ self.kernel = self.kernelVersion(val)
+ else:
+ self.kernel = 'unknown'
+ def kernelVersion(self, msg):
+ return msg.split()[2]
+ def kernelParams(self):
+ cmdline = 'initcall_debug log_buf_len=32M'
+ if self.useftrace:
+ cmdline += ' trace_buf_size=128M trace_clock=global '\
+ 'trace_options=nooverwrite,funcgraph-abstime,funcgraph-cpu,'\
+ 'funcgraph-duration,funcgraph-proc,funcgraph-tail,'\
+ 'nofuncgraph-overhead,context-info,graph-time '\
+ 'ftrace=function_graph '\
+ 'ftrace_graph_max_depth=%d '\
+ 'ftrace_graph_filter=%s' % \
+ (self.max_graph_depth, self.graph_filter)
+ return cmdline
+ def setGraphFilter(self, val):
+ fp = open(self.tpath+'available_filter_functions')
+ master = fp.read().split('\n')
+ fp.close()
+ for i in val.split(','):
+ func = i.strip()
+ if func not in master:
+ doError('function "%s" not available for ftrace' % func)
+ self.graph_filter = val
+ def cronjobCmdString(self):
+ cmdline = '%s -cronjob' % os.path.abspath(sys.argv[0])
+ args = iter(sys.argv[1:])
+ for arg in args:
+ if arg in ['-h', '-v', '-cronjob', '-reboot']:
+ continue
+ elif arg in ['-o', '-dmesg', '-ftrace', '-filter']:
+ args.next()
+ continue
+ cmdline += ' '+arg
+ if self.graph_filter != 'do_one_initcall':
+ cmdline += ' -filter "%s"' % self.graph_filter
+ cmdline += ' -o "%s"' % os.path.abspath(self.htmlfile)
+ return cmdline
+ def manualRebootRequired(self):
+ cmdline = self.kernelParams()
+ print 'To generate a new timeline manually, follow these steps:\n'
+ print '1. Add the CMDLINE string to your kernel command line.'
+ print '2. Reboot the system.'
+ print '3. After reboot, re-run this tool with the same arguments but no command (w/o -reboot or -manual).\n'
+ print 'CMDLINE="%s"' % cmdline
+ sys.exit()
+
+sysvals = SystemValues()
+
+# Class: Data
+# Description:
+# The primary container for test data.
+class Data(aslib.Data):
+ dmesg = {} # root data structure
+ start = 0.0 # test start
+ end = 0.0 # test end
+ dmesgtext = [] # dmesg text file in memory
+ testnumber = 0
+ idstr = ''
+ html_device_id = 0
+ valid = False
+ initstart = 0.0
+ boottime = ''
+ phases = ['boot']
+ do_one_initcall = False
+ def __init__(self, num):
+ self.testnumber = num
+ self.idstr = 'a'
+ self.dmesgtext = []
+ self.dmesg = {
+ 'boot': {'list': dict(), 'start': -1.0, 'end': -1.0, 'row': 0, 'color': '#dddddd'}
+ }
+ def deviceTopology(self):
+ return ''
+ def newAction(self, phase, name, start, end, ret, ulen):
+ # new device callback for a specific phase
+ self.html_device_id += 1
+ devid = '%s%d' % (self.idstr, self.html_device_id)
+ list = self.dmesg[phase]['list']
+ length = -1.0
+ if(start >= 0 and end >= 0):
+ length = end - start
+ i = 2
+ origname = name
+ while(name in list):
+ name = '%s[%d]' % (origname, i)
+ i += 1
+ list[name] = {'name': name, 'start': start, 'end': end,
+ 'pid': 0, 'length': length, 'row': 0, 'id': devid,
+ 'ret': ret, 'ulen': ulen }
+ return name
+ def deviceMatch(self, cg):
+ if cg.end - cg.start == 0:
+ return True
+ list = self.dmesg['boot']['list']
+ for devname in list:
+ dev = list[devname]
+ if cg.name == 'do_one_initcall':
+ if(cg.start <= dev['start'] and cg.end >= dev['end'] and dev['length'] > 0):
+ dev['ftrace'] = cg
+ self.do_one_initcall = True
+ return True
+ else:
+ if(cg.start > dev['start'] and cg.end < dev['end']):
+ if 'ftraces' not in dev:
+ dev['ftraces'] = []
+ dev['ftraces'].append(cg)
+ return True
+ return False
+
+# ----------------- FUNCTIONS --------------------
+
+# Function: loadKernelLog
+# Description:
+# Load a raw kernel log from dmesg
+def loadKernelLog():
+ data = Data(0)
+ data.dmesg['boot']['start'] = data.start = ktime = 0.0
+ sysvals.stamp = {
+ 'time': datetime.now().strftime('%B %d %Y, %I:%M:%S %p'),
+ 'host': sysvals.hostname,
+ 'mode': 'boot', 'kernel': ''}
+
+ devtemp = dict()
+ if(sysvals.dmesgfile):
+ lf = open(sysvals.dmesgfile, 'r')
+ else:
+ lf = Popen('dmesg', stdout=PIPE).stdout
+ for line in lf:
+ line = line.replace('\r\n', '')
+ idx = line.find('[')
+ if idx > 1:
+ line = line[idx:]
+ m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) (?P<msg>.*)', line)
+ if(not m):
+ continue
+ ktime = float(m.group('ktime'))
+ if(ktime > 120):
+ break
+ msg = m.group('msg')
+ data.end = data.initstart = ktime
+ data.dmesgtext.append(line)
+ if(ktime == 0.0 and re.match('^Linux version .*', msg)):
+ if(not sysvals.stamp['kernel']):
+ sysvals.stamp['kernel'] = sysvals.kernelVersion(msg)
+ continue
+ m = re.match('.* setting system clock to (?P<t>.*) UTC.*', msg)
+ if(m):
+ bt = datetime.strptime(m.group('t'), '%Y-%m-%d %H:%M:%S')
+ bt = bt - timedelta(seconds=int(ktime))
+ data.boottime = bt.strftime('%Y-%m-%d_%H:%M:%S')
+ sysvals.stamp['time'] = bt.strftime('%B %d %Y, %I:%M:%S %p')
+ continue
+ m = re.match('^calling *(?P<f>.*)\+.*', msg)
+ if(m):
+ devtemp[m.group('f')] = ktime
+ continue
+ m = re.match('^initcall *(?P<f>.*)\+.* returned (?P<r>.*) after (?P<t>.*) usecs', msg)
+ if(m):
+ data.valid = True
+ f, r, t = m.group('f', 'r', 't')
+ if(f in devtemp):
+ data.newAction('boot', f, devtemp[f], ktime, int(r), int(t))
+ data.end = ktime
+ del devtemp[f]
+ continue
+ if(re.match('^Freeing unused kernel memory.*', msg)):
+ break
+
+ data.dmesg['boot']['end'] = data.end
+ lf.close()
+ return data
+
+# Function: loadTraceLog
+# Description:
+# Check if trace is available and copy to a temp file
+def loadTraceLog(data):
+ # load the data to a temp file if none given
+ if not sysvals.ftracefile:
+ lib = aslib.sysvals
+ aslib.rootCheck(True)
+ if not lib.verifyFtrace():
+ doError('ftrace not available')
+ if lib.fgetVal('current_tracer').strip() != 'function_graph':
+ doError('ftrace not configured for a boot callgraph')
+ sysvals.ftracefile = '/tmp/boot_ftrace.%s.txt' % os.getpid()
+ call('cat '+lib.tpath+'trace > '+sysvals.ftracefile, shell=True)
+ if not sysvals.ftracefile:
+ doError('No trace data available')
+
+ # parse the trace log
+ ftemp = dict()
+ tp = aslib.TestProps()
+ tp.setTracerType('function_graph')
+ tf = open(sysvals.ftracefile, 'r')
+ for line in tf:
+ if line[0] == '#':
+ continue
+ m = re.match(tp.ftrace_line_fmt, line.strip())
+ if(not m):
+ continue
+ m_time, m_proc, m_pid, m_msg, m_dur = \
+ m.group('time', 'proc', 'pid', 'msg', 'dur')
+ if float(m_time) > data.end:
+ break
+ if(m_time and m_pid and m_msg):
+ t = aslib.FTraceLine(m_time, m_msg, m_dur)
+ pid = int(m_pid)
+ else:
+ continue
+ if t.fevent or t.fkprobe:
+ continue
+ key = (m_proc, pid)
+ if(key not in ftemp):
+ ftemp[key] = []
+ ftemp[key].append(aslib.FTraceCallGraph(pid))
+ cg = ftemp[key][-1]
+ if(cg.addLine(t)):
+ ftemp[key].append(aslib.FTraceCallGraph(pid))
+ tf.close()
+
+ # add the callgraph data to the device hierarchy
+ for key in ftemp:
+ proc, pid = key
+ for cg in ftemp[key]:
+ if len(cg.list) < 1 or cg.invalid:
+ continue
+ if(not cg.postProcess()):
+ print('Sanity check failed for %s-%d' % (proc, pid))
+ continue
+ # match cg data to devices
+ if not data.deviceMatch(cg):
+ print ' BAD: %s %s-%d [%f - %f]' % (cg.name, proc, pid, cg.start, cg.end)
+
+# Function: colorForName
+# Description:
+# Generate a repeatable color from a list for a given name
+def colorForName(name):
+ list = [
+ ('c1', '#ec9999'),
+ ('c2', '#ffc1a6'),
+ ('c3', '#fff0a6'),
+ ('c4', '#adf199'),
+ ('c5', '#9fadea'),
+ ('c6', '#a699c1'),
+ ('c7', '#ad99b4'),
+ ('c8', '#eaffea'),
+ ('c9', '#dcecfb'),
+ ('c10', '#ffffea')
+ ]
+ i = 0
+ total = 0
+ count = len(list)
+ while i < len(name):
+ total += ord(name[i])
+ i += 1
+ return list[total % count]
+
+def cgOverview(cg, minlen):
+ stats = dict()
+ large = []
+ for l in cg.list:
+ if l.fcall and l.depth == 1:
+ if l.length >= minlen:
+ large.append(l)
+ if l.name not in stats:
+ stats[l.name] = [0, 0.0]
+ stats[l.name][0] += (l.length * 1000.0)
+ stats[l.name][1] += 1
+ return (large, stats)
+
+# Function: createBootGraph
+# Description:
+# Create the output html file from the resident test data
+# Arguments:
+# testruns: array of Data objects from parseKernelLog or parseTraceLog
+# Output:
+# True if the html file was created, false if it failed
+def createBootGraph(data, embedded):
+ # html function templates
+ html_srccall = '<div id={6} title="{5}" class="srccall" style="left:{1}%;top:{2}px;height:{3}px;width:{4}%;line-height:{3}px;">{0}</div>\n'
+ html_timetotal = '<table class="time1">\n<tr>'\
+ '<td class="blue">Time from Kernel Boot to start of User Mode: <b>{0} ms</b></td>'\
+ '</tr>\n</table>\n'
+
+ # device timeline
+ devtl = aslib.Timeline(100, 20)
+
+ # write the test title and general info header
+ devtl.createHeader(sysvals, 'noftrace')
+
+ # Generate the header for this timeline
+ t0 = data.start
+ tMax = data.end
+ tTotal = tMax - t0
+ if(tTotal == 0):
+ print('ERROR: No timeline data')
+ return False
+ boot_time = '%.0f'%(tTotal*1000)
+ devtl.html += html_timetotal.format(boot_time)
+
+ # determine the maximum number of rows we need to draw
+ phase = 'boot'
+ list = data.dmesg[phase]['list']
+ devlist = []
+ for devname in list:
+ d = aslib.DevItem(0, phase, list[devname])
+ devlist.append(d)
+ devtl.getPhaseRows(devlist)
+ devtl.calcTotalRows()
+
+ # draw the timeline background
+ devtl.createZoomBox()
+ boot = data.dmesg[phase]
+ length = boot['end']-boot['start']
+ left = '%.3f' % (((boot['start']-t0)*100.0)/tTotal)
+ width = '%.3f' % ((length*100.0)/tTotal)
+ devtl.html += devtl.html_tblock.format(phase, left, width, devtl.scaleH)
+ devtl.html += devtl.html_phase.format('0', '100', \
+ '%.3f'%devtl.scaleH, '%.3f'%devtl.bodyH, \
+ 'white', '')
+
+ # draw the device timeline
+ num = 0
+ devstats = dict()
+ for devname in sorted(list):
+ cls, color = colorForName(devname)
+ dev = list[devname]
+ info = '@|%.3f|%.3f|%.3f|%d' % (dev['start']*1000.0, dev['end']*1000.0,
+ dev['ulen']/1000.0, dev['ret'])
+ devstats[dev['id']] = {'info':info}
+ dev['color'] = color
+ height = devtl.phaseRowHeight(0, phase, dev['row'])
+ top = '%.6f' % ((dev['row']*height) + devtl.scaleH)
+ left = '%.6f' % (((dev['start']-t0)*100)/tTotal)
+ width = '%.6f' % (((dev['end']-dev['start'])*100)/tTotal)
+ length = ' (%0.3f ms) ' % ((dev['end']-dev['start'])*1000)
+ devtl.html += devtl.html_device.format(dev['id'],
+ devname+length+'kernel_mode', left, top, '%.3f'%height,
+ width, devname, ' '+cls, '')
+ rowtop = devtl.phaseRowTop(0, phase, dev['row'])
+ height = '%.6f' % (devtl.rowH / 2)
+ top = '%.6f' % (rowtop + devtl.scaleH + (devtl.rowH / 2))
+ if data.do_one_initcall:
+ if('ftrace' not in dev):
+ continue
+ cg = dev['ftrace']
+ large, stats = cgOverview(cg, 0.001)
+ devstats[dev['id']]['fstat'] = stats
+ for l in large:
+ left = '%f' % (((l.time-t0)*100)/tTotal)
+ width = '%f' % (l.length*100/tTotal)
+ title = '%s (%0.3fms)' % (l.name, l.length * 1000.0)
+ devtl.html += html_srccall.format(l.name, left,
+ top, height, width, title, 'x%d'%num)
+ num += 1
+ continue
+ if('ftraces' not in dev):
+ continue
+ for cg in dev['ftraces']:
+ left = '%f' % (((cg.start-t0)*100)/tTotal)
+ width = '%f' % ((cg.end-cg.start)*100/tTotal)
+ cglen = (cg.end - cg.start) * 1000.0
+ title = '%s (%0.3fms)' % (cg.name, cglen)
+ cg.id = 'x%d' % num
+ devtl.html += html_srccall.format(cg.name, left,
+ top, height, width, title, dev['id']+cg.id)
+ num += 1
+
+ # draw the time scale, try to make the number of labels readable
+ devtl.createTimeScale(t0, tMax, tTotal, phase)
+ devtl.html += '</div>\n'
+
+ # timeline is finished
+ devtl.html += '</div>\n</div>\n'
+
+ if(sysvals.outfile == sysvals.htmlfile):
+ hf = open(sysvals.htmlfile, 'a')
+ else:
+ hf = open(sysvals.htmlfile, 'w')
+
+ # add the css if this is not an embedded run
+ extra = '\
+ .c1 {background:rgba(209,0,0,0.4);}\n\
+ .c2 {background:rgba(255,102,34,0.4);}\n\
+ .c3 {background:rgba(255,218,33,0.4);}\n\
+ .c4 {background:rgba(51,221,0,0.4);}\n\
+ .c5 {background:rgba(17,51,204,0.4);}\n\
+ .c6 {background:rgba(34,0,102,0.4);}\n\
+ .c7 {background:rgba(51,0,68,0.4);}\n\
+ .c8 {background:rgba(204,255,204,0.4);}\n\
+ .c9 {background:rgba(169,208,245,0.4);}\n\
+ .c10 {background:rgba(255,255,204,0.4);}\n\
+ .vt {transform:rotate(-60deg);transform-origin:0 0;}\n\
+ table.fstat {table-layout:fixed;padding:150px 15px 0 0;font-size:10px;column-width:30px;}\n\
+ .fstat th {width:55px;}\n\
+ .fstat td {text-align:left;width:35px;}\n\
+ .srccall {position:absolute;font-size:10px;z-index:7;overflow:hidden;color:black;text-align:center;white-space:nowrap;border-radius:5px;border:1px solid black;background:linear-gradient(to bottom right,#CCC,#969696);}\n\
+ .srccall:hover {color:white;font-weight:bold;border:1px solid white;}\n'
+ if(not embedded):
+ aslib.addCSS(hf, sysvals, 1, False, extra)
+
+ # write the device timeline
+ hf.write(devtl.html)
+
+ # add boot specific html
+ statinfo = 'var devstats = {\n'
+ for n in sorted(devstats):
+ statinfo += '\t"%s": [\n\t\t"%s",\n' % (n, devstats[n]['info'])
+ if 'fstat' in devstats[n]:
+ funcs = devstats[n]['fstat']
+ for f in sorted(funcs, key=funcs.get, reverse=True):
+ if funcs[f][0] < 0.01 and len(funcs) > 10:
+ break
+ statinfo += '\t\t"%f|%s|%d",\n' % (funcs[f][0], f, funcs[f][1])
+ statinfo += '\t],\n'
+ statinfo += '};\n'
+ html = \
+ '<div id="devicedetailtitle"></div>\n'\
+ '<div id="devicedetail" style="display:none;">\n'\
+ '<div id="devicedetail0">\n'\
+ '<div id="kernel_mode" class="phaselet" style="left:0%;width:100%;background:#DDDDDD"></div>\n'\
+ '</div>\n</div>\n'\
+ '<script type="text/javascript">\n'+statinfo+\
+ '</script>\n'
+ hf.write(html)
+
+ # add the callgraph html
+ if(sysvals.usecallgraph):
+ aslib.addCallgraphs(sysvals, hf, data)
+
+ # add the dmesg log as a hidden div
+ if sysvals.addlogs:
+ hf.write('<div id="dmesglog" style="display:none;">\n')
+ for line in data.dmesgtext:
+ line = line.replace('<', '<').replace('>', '>')
+ hf.write(line)
+ hf.write('</div>\n')
+
+ if(not embedded):
+ # write the footer and close
+ aslib.addScriptCode(hf, [data])
+ hf.write('</body>\n</html>\n')
+ else:
+ # embedded out will be loaded in a page, skip the js
+ hf.write('<div id=bounds style=display:none>%f,%f</div>' % \
+ (data.start*1000, data.initstart*1000))
+ hf.close()
+ return True
+
+# Function: updateCron
+# Description:
+# (restore=False) Set the tool to run automatically on reboot
+# (restore=True) Restore the original crontab
+def updateCron(restore=False):
+ if not restore:
+ sysvals.rootUser(True)
+ crondir = '/var/spool/cron/crontabs/'
+ cronfile = crondir+'root'
+ backfile = crondir+'root-analyze_boot-backup'
+ if not os.path.exists(crondir):
+ doError('%s not found' % crondir)
+ out = Popen(['which', 'crontab'], stdout=PIPE).stdout.read()
+ if not out:
+ doError('crontab not found')
+ # on restore: move the backup cron back into place
+ if restore:
+ if os.path.exists(backfile):
+ shutil.move(backfile, cronfile)
+ return
+ # backup current cron and install new one with reboot
+ if os.path.exists(cronfile):
+ shutil.move(cronfile, backfile)
+ else:
+ fp = open(backfile, 'w')
+ fp.close()
+ res = -1
+ try:
+ fp = open(backfile, 'r')
+ op = open(cronfile, 'w')
+ for line in fp:
+ if '@reboot' not in line:
+ op.write(line)
+ continue
+ fp.close()
+ op.write('@reboot python %s\n' % sysvals.cronjobCmdString())
+ op.close()
+ res = call('crontab %s' % cronfile, shell=True)
+ except Exception, e:
+ print 'Exception: %s' % str(e)
+ shutil.move(backfile, cronfile)
+ res = -1
+ if res != 0:
+ doError('crontab failed')
+
+# Function: updateGrub
+# Description:
+# update grub.cfg for all kernels with our parameters
+def updateGrub(restore=False):
+ # call update-grub on restore
+ if restore:
+ try:
+ call(['update-grub'], stderr=PIPE, stdout=PIPE,
+ env={'PATH': '.:/sbin:/usr/sbin:/usr/bin:/sbin:/bin'})
+ except Exception, e:
+ print 'Exception: %s\n' % str(e)
+ return
+ # verify we can do this
+ sysvals.rootUser(True)
+ grubfile = '/etc/default/grub'
+ if not os.path.exists(grubfile):
+ print 'ERROR: Unable to set the kernel parameters via grub.\n'
+ sysvals.manualRebootRequired()
+ out = Popen(['which', 'update-grub'], stdout=PIPE).stdout.read()
+ if not out:
+ print 'ERROR: Unable to set the kernel parameters via grub.\n'
+ sysvals.manualRebootRequired()
+
+ # extract the option and create a grub config without it
+ tgtopt = 'GRUB_CMDLINE_LINUX_DEFAULT'
+ cmdline = ''
+ tempfile = '/etc/default/grub.analyze_boot'
+ shutil.move(grubfile, tempfile)
+ res = -1
+ try:
+ fp = open(tempfile, 'r')
+ op = open(grubfile, 'w')
+ cont = False
+ for line in fp:
+ line = line.strip()
+ if len(line) == 0 or line[0] == '#':
+ continue
+ opt = line.split('=')[0].strip()
+ if opt == tgtopt:
+ cmdline = line.split('=', 1)[1].strip('\\')
+ if line[-1] == '\\':
+ cont = True
+ elif cont:
+ cmdline += line.strip('\\')
+ if line[-1] != '\\':
+ cont = False
+ else:
+ op.write('%s\n' % line)
+ fp.close()
+ # if the target option value is in quotes, strip them
+ sp = '"'
+ val = cmdline.strip()
+ if val[0] == '\'' or val[0] == '"':
+ sp = val[0]
+ val = val.strip(sp)
+ cmdline = val
+ # append our cmd line options
+ if len(cmdline) > 0:
+ cmdline += ' '
+ cmdline += sysvals.kernelParams()
+ # write out the updated target option
+ op.write('\n%s=%s%s%s\n' % (tgtopt, sp, cmdline, sp))
+ op.close()
+ res = call('update-grub')
+ os.remove(grubfile)
+ except Exception, e:
+ print 'Exception: %s' % str(e)
+ res = -1
+ # cleanup
+ shutil.move(tempfile, grubfile)
+ if res != 0:
+ doError('update-grub failed')
+
+# Function: doError
+# Description:
+# generic error function for catastrphic failures
+# Arguments:
+# msg: the error message to print
+# help: True if printHelp should be called after, False otherwise
+def doError(msg, help=False):
+ if help == True:
+ printHelp()
+ print 'ERROR: %s\n' % msg
+ sys.exit()
+
+# Function: printHelp
+# Description:
+# print out the help text
+def printHelp():
+ print('')
+ print('%s v%.1f' % (sysvals.title, sysvals.version))
+ print('Usage: bootgraph <options> <command>')
+ print('')
+ print('Description:')
+ print(' This tool reads in a dmesg log of linux kernel boot and')
+ print(' creates an html representation of the boot timeline up to')
+ print(' the start of the init process.')
+ print('')
+ print(' If no specific command is given the tool reads the current dmesg')
+ print(' and/or ftrace log and outputs bootgraph.html')
+ print('')
+ print('Options:')
+ print(' -h Print this help text')
+ print(' -v Print the current tool version')
+ print(' -addlogs Add the dmesg log to the html output')
+ print(' -o file Html timeline name (default: bootgraph.html)')
+ print(' [advanced]')
+ print(' -f Use ftrace to add function detail (default: disabled)')
+ print(' -callgraph Add callgraph detail, can be very large (default: disabled)')
+ print(' -maxdepth N limit the callgraph data to N call levels (default: 2)')
+ print(' -mincg ms Discard all callgraphs shorter than ms milliseconds (e.g. 0.001 for us)')
+ print(' -timeprec N Number of significant digits in timestamps (0:S, 3:ms, [6:us])')
+ print(' -expandcg pre-expand the callgraph data in the html output (default: disabled)')
+ print(' -filter list Limit ftrace to comma-delimited list of functions (default: do_one_initcall)')
+ print(' [commands]')
+ print(' -reboot Reboot the machine automatically and generate a new timeline')
+ print(' -manual Show the requirements to generate a new timeline manually')
+ print(' -dmesg file Load a stored dmesg file (used with -ftrace)')
+ print(' -ftrace file Load a stored ftrace file (used with -dmesg)')
+ print(' -flistall Print all functions capable of being captured in ftrace')
+ print('')
+ return True
+
+# ----------------- MAIN --------------------
+# exec start (skipped if script is loaded as library)
+if __name__ == '__main__':
+ # loop through the command line arguments
+ cmd = ''
+ simplecmds = ['-updategrub', '-flistall']
+ args = iter(sys.argv[1:])
+ for arg in args:
+ if(arg == '-h'):
+ printHelp()
+ sys.exit()
+ elif(arg == '-v'):
+ print("Version %.1f" % sysvals.version)
+ sys.exit()
+ elif(arg in simplecmds):
+ cmd = arg[1:]
+ elif(arg == '-f'):
+ sysvals.useftrace = True
+ elif(arg == '-callgraph'):
+ sysvals.useftrace = True
+ sysvals.usecallgraph = True
+ elif(arg == '-mincg'):
+ sysvals.mincglen = aslib.getArgFloat('-mincg', args, 0.0, 10000.0)
+ elif(arg == '-timeprec'):
+ sysvals.setPrecision(aslib.getArgInt('-timeprec', args, 0, 6))
+ elif(arg == '-maxdepth'):
+ sysvals.max_graph_depth = aslib.getArgInt('-maxdepth', args, 0, 1000)
+ elif(arg == '-filter'):
+ try:
+ val = args.next()
+ except:
+ doError('No filter functions supplied', True)
+ aslib.rootCheck(True)
+ sysvals.setGraphFilter(val)
+ elif(arg == '-ftrace'):
+ try:
+ val = args.next()
+ except:
+ doError('No ftrace file supplied', True)
+ if(os.path.exists(val) == False):
+ doError('%s does not exist' % val)
+ sysvals.ftracefile = val
+ elif(arg == '-addlogs'):
+ sysvals.addlogs = True
+ elif(arg == '-expandcg'):
+ sysvals.cgexp = True
+ elif(arg == '-dmesg'):
+ try:
+ val = args.next()
+ except:
+ doError('No dmesg file supplied', True)
+ if(os.path.exists(val) == False):
+ doError('%s does not exist' % val)
+ if(sysvals.htmlfile == val or sysvals.outfile == val):
+ doError('Output filename collision')
+ sysvals.dmesgfile = val
+ elif(arg == '-o'):
+ try:
+ val = args.next()
+ except:
+ doError('No HTML filename supplied', True)
+ if(sysvals.dmesgfile == val or sysvals.ftracefile == val):
+ doError('Output filename collision')
+ sysvals.htmlfile = val
+ elif(arg == '-reboot'):
+ if sysvals.iscronjob:
+ doError('-reboot and -cronjob are incompatible')
+ sysvals.reboot = True
+ elif(arg == '-manual'):
+ sysvals.reboot = True
+ sysvals.manual = True
+ # remaining options are only for cron job use
+ elif(arg == '-cronjob'):
+ sysvals.iscronjob = True
+ if sysvals.reboot:
+ doError('-reboot and -cronjob are incompatible')
+ else:
+ doError('Invalid argument: '+arg, True)
+
+ if cmd != '':
+ if cmd == 'updategrub':
+ updateGrub()
+ elif cmd == 'flistall':
+ sysvals.getFtraceFilterFunctions(False)
+ sys.exit()
+
+ # update grub, setup a cronjob, and reboot
+ if sysvals.reboot:
+ if not sysvals.manual:
+ updateGrub()
+ updateCron()
+ call('reboot')
+ else:
+ sysvals.manualRebootRequired()
+ sys.exit()
+
+ # disable the cronjob
+ if sysvals.iscronjob:
+ updateCron(True)
+ updateGrub(True)
+
+ data = loadKernelLog()
+ if sysvals.useftrace:
+ loadTraceLog(data)
+ if sysvals.iscronjob:
+ try:
+ sysvals.fsetVal('0', 'tracing_on')
+ except:
+ pass
+
+ if(sysvals.outfile and sysvals.phoronix):
+ fp = open(sysvals.outfile, 'w')
+ fp.write('pass %s initstart %.3f end %.3f boot %s\n' %
+ (data.valid, data.initstart*1000, data.end*1000, data.boottime))
+ fp.close()
+ if(not data.valid):
+ if sysvals.dmesgfile:
+ doError('No initcall data found in %s' % sysvals.dmesgfile)
+ else:
+ doError('No initcall data found, is initcall_debug enabled?')
+
+ print(' Host: %s' % sysvals.hostname)
+ print(' Test time: %s' % sysvals.testtime)
+ print(' Boot time: %s' % data.boottime)
+ print('Kernel Version: %s' % sysvals.kernel)
+ print(' Kernel start: %.3f' % (data.start * 1000))
+ print(' init start: %.3f' % (data.initstart * 1000))
+
+ createBootGraph(data, sysvals.phoronix)
# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
# more details.
#
-# You should have received a copy of the GNU General Public License along with
-# this program; if not, write to the Free Software Foundation, Inc.,
-# 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-#
# Authors:
# Todd Brandt <todd.e.brandt@linux.intel.com>
#
# Home Page
# https://01.org/suspendresume
# Source repo
-# https://github.com/01org/suspendresume
+# https://github.com/01org/pm-graph
#
# Description:
# This tool is designed to assist kernel and OS developers in optimizing
# A global, single-instance container used to
# store system values and test parameters
class SystemValues:
+ title = 'SleepGraph'
+ version = '4.6'
ansi = False
- version = '4.5'
verbose = False
addlogs = False
mindevlen = 0.0
mincglen = 0.0
cgphase = ''
cgtest = -1
+ max_graph_depth = 0
callloopmaxgap = 0.0001
callloopmaxlen = 0.005
srgap = 0
ftracefile = ''
htmlfile = ''
embedded = False
- rtcwake = False
- rtcwaketime = 10
+ rtcwake = True
+ rtcwaketime = 15
rtcpath = ''
devicefilter = []
stamp = 0
self.rtcpath = rtc
if (hasattr(sys.stdout, 'isatty') and sys.stdout.isatty()):
self.ansi = True
+ def rootUser(self, fatal=False):
+ if 'USER' in os.environ and os.environ['USER'] == 'root':
+ return True
+ if fatal:
+ doError('This command must be run as root')
+ return False
def setPrecision(self, num):
if num < 0 or num > 6:
return
self.fsetVal('global', 'trace_clock')
# set trace buffer to a huge value
self.fsetVal('nop', 'current_tracer')
- self.fsetVal('100000', 'buffer_size_kb')
+ self.fsetVal('131073', 'buffer_size_kb')
# go no further if this is just a status check
if testing:
return
self.fsetVal('nofuncgraph-overhead', 'trace_options')
self.fsetVal('context-info', 'trace_options')
self.fsetVal('graph-time', 'trace_options')
- self.fsetVal('0', 'max_graph_depth')
+ self.fsetVal('%d' % self.max_graph_depth, 'max_graph_depth')
cf = ['dpm_run_callback']
if(self.usetraceeventsonly):
cf += ['dpm_prepare', 'dpm_complete']
return '\x1B[%d;40m%s\x1B[m' % (color, str)
sysvals = SystemValues()
+suspendmodename = {
+ 'freeze': 'Freeze (S0)',
+ 'standby': 'Standby (S1)',
+ 'mem': 'Suspend (S3)',
+ 'disk': 'Hibernate (S4)'
+}
# Class: DevProps
# Description:
tmp = dict()
for devname in list:
dev = list[devname]
+ if dev['length'] == 0:
+ continue
tmp[dev['start']] = devname
for t in sorted(tmp):
slist.append(tmp[t])
# Each instance is tied to a single device in a single phase, and is
# comprised of an ordered list of FTraceLine objects
class FTraceCallGraph:
+ id = ''
start = -1.0
end = -1.0
list = []
invalid = False
depth = 0
pid = 0
+ name = ''
def __init__(self, pid):
self.start = -1.0
self.end = -1.0
return True
return False
def postProcess(self, debug=False):
+ if len(self.list) > 0:
+ self.name = self.list[0].name
stack = dict()
cnt = 0
+ last = 0
for l in self.list:
+ # ftrace bug: reported duration is not reliable
+ # check each leaf and clip it at max possible length
+ if(last and last.freturn and last.fcall):
+ if last.length > l.time - last.time:
+ last.length = l.time - last.time
if(l.fcall and not l.freturn):
stack[l.depth] = l
cnt += 1
print 'Post Process Error: Depth missing'
l.debugPrint()
return False
- # transfer total time from return line to call line
- stack[l.depth].length = l.length
+ # calculate call length from call/return lines
+ stack[l.depth].length = l.time - stack[l.depth].time
stack.pop(l.depth)
l.length = 0
cnt -= 1
+ last = l
if(cnt == 0):
# trace caught the whole call tree
return True
'dpm_prepare': 'suspend_prepare',
'dpm_complete': 'resume_complete'
}
- if(self.list[0].name in borderphase):
- p = borderphase[self.list[0].name]
+ if(self.name in borderphase):
+ p = borderphase[self.name]
list = data.dmesg[p]['list']
for devname in list:
dev = list[devname]
break
return found
def newActionFromFunction(self, data):
- name = self.list[0].name
+ name = self.name
if name in ['dpm_run_callback', 'dpm_prepare', 'dpm_complete']:
return
fs = self.start
phase, myname = out
data.dmesg[phase]['list'][myname]['ftrace'] = self
def debugPrint(self):
- print('[%f - %f] %s (%d)') % (self.start, self.end, self.list[0].name, self.pid)
+ print('[%f - %f] %s (%d)') % (self.start, self.end, self.name, self.pid)
for l in self.list:
if(l.freturn and l.fcall):
print('%f (%02d): %s(); (%.3f us)' % (l.time, \
# A container for a device timeline which calculates
# all the html properties to display it correctly
class Timeline:
- html = {}
+ html = ''
height = 0 # total timeline height
scaleH = 20 # timescale (top) row height
rowH = 30 # device row height
rows = 0 # total timeline rows
rowlines = dict()
rowheight = dict()
+ html_tblock = '<div id="block{0}" class="tblock" style="left:{1}%;width:{2}%;"><div class="tback" style="height:{3}px"></div>\n'
+ html_device = '<div id="{0}" title="{1}" class="thread{7}" style="left:{2}%;top:{3}px;height:{4}px;width:{5}%;{8}">{6}</div>\n'
+ html_phase = '<div class="phase" style="left:{0}%;width:{1}%;top:{2}px;height:{3}px;background:{4}">{5}</div>\n'
+ html_phaselet = '<div id="{0}" class="phaselet" style="left:{1}%;width:{2}%;background:{3}"></div>\n'
def __init__(self, rowheight, scaleheight):
self.rowH = rowheight
self.scaleH = scaleheight
- self.html = {
- 'header': '',
- 'timeline': '',
- 'legend': '',
- }
+ self.html = ''
+ def createHeader(self, sv, suppress=''):
+ if(not sv.stamp['time']):
+ return
+ self.html += '<div class="version"><a href="https://01.org/suspendresume">%s v%s</a></div>' \
+ % (sv.title, sv.version)
+ if sv.logmsg and 'log' not in suppress:
+ self.html += '<button id="showtest" class="logbtn">log</button>'
+ if sv.addlogs and 'dmesg' not in suppress:
+ self.html += '<button id="showdmesg" class="logbtn">dmesg</button>'
+ if sv.addlogs and sv.ftracefile and 'ftrace' not in suppress:
+ self.html += '<button id="showftrace" class="logbtn">ftrace</button>'
+ headline_stamp = '<div class="stamp">{0} {1} {2} {3}</div>\n'
+ self.html += headline_stamp.format(sv.stamp['host'], sv.stamp['kernel'],
+ sv.stamp['mode'], sv.stamp['time'])
# Function: getDeviceRows
# Description:
# determine how may rows the device funcs will take
break
top += self.rowheight[test][phase][i]
return top
- # Function: calcTotalRows
- # Description:
- # Calculate the heights and offsets for the header and rows
def calcTotalRows(self):
+ # Calculate the heights and offsets for the header and rows
maxrows = 0
standardphases = []
for t in self.rowlines:
for t, p in standardphases:
for i in sorted(self.rowheight[t][p]):
self.rowheight[t][p][i] = self.bodyH/len(self.rowlines[t][p])
+ def createZoomBox(self, mode='command', testcount=1):
+ # Create bounding box, add buttons
+ html_zoombox = '<center><button id="zoomin">ZOOM IN +</button><button id="zoomout">ZOOM OUT -</button><button id="zoomdef">ZOOM 1:1</button></center>\n'
+ html_timeline = '<div id="dmesgzoombox" class="zoombox">\n<div id="{0}" class="timeline" style="height:{1}px">\n'
+ html_devlist1 = '<button id="devlist1" class="devlist" style="float:left;">Device Detail{0}</button>'
+ html_devlist2 = '<button id="devlist2" class="devlist" style="float:right;">Device Detail2</button>\n'
+ if mode != 'command':
+ if testcount > 1:
+ self.html += html_devlist2
+ self.html += html_devlist1.format('1')
+ else:
+ self.html += html_devlist1.format('')
+ self.html += html_zoombox
+ self.html += html_timeline.format('dmesg', self.height)
# Function: createTimeScale
# Description:
# Create the timescale for a timeline block
# The html code needed to display the time scale
def createTimeScale(self, m0, mMax, tTotal, mode):
timescale = '<div class="t" style="right:{0}%">{1}</div>\n'
- rline = '<div class="t" style="left:0;border-left:1px solid black;border-right:0;">Resume</div>\n'
+ rline = '<div class="t" style="left:0;border-left:1px solid black;border-right:0;">{0}</div>\n'
output = '<div class="timescale">\n'
# set scale for timeline
mTotal = mMax - m0
divEdge = (mTotal - tS*(divTotal-1))*100/mTotal
for i in range(divTotal):
htmlline = ''
- if(mode == 'resume'):
- pos = '%0.3f' % (100 - ((float(i)*tS*100)/mTotal))
- val = '%0.fms' % (float(i)*tS*1000)
- htmlline = timescale.format(pos, val)
- if(i == 0):
- htmlline = rline
- else:
+ if(mode == 'suspend'):
pos = '%0.3f' % (100 - ((float(i)*tS*100)/mTotal) - divEdge)
val = '%0.fms' % (float(i-divTotal+1)*tS*1000)
if(i == divTotal - 1):
- val = 'Suspend'
+ val = mode
+ htmlline = timescale.format(pos, val)
+ else:
+ pos = '%0.3f' % (100 - ((float(i)*tS*100)/mTotal))
+ val = '%0.fms' % (float(i)*tS*1000)
htmlline = timescale.format(pos, val)
+ if(i == 0):
+ htmlline = rline.format(mode)
output += htmlline
- output += '</div>\n'
- return output
+ self.html += output+'</div>\n'
# Class: TestProps
# Description:
val['kern'] = kern
if ujiff > 0 or kjiff > 0:
running[pid] = ujiff + kjiff
- result = process.wait()
+ process.wait()
out = ''
for pid in running:
jiffies = running[pid]
if not sysvals.stamp:
sysvals.stamp = data.stamp
-# Function: diffStamp
-# Description:
-# compare the host, kernel, and mode fields in 3 stamps
-# Arguments:
-# stamp1: string array with mode, kernel, and host
-# stamp2: string array with mode, kernel, and host
-# Return:
-# True if stamps differ, False if they're the same
-def diffStamp(stamp1, stamp2):
- if 'host' in stamp1 and 'host' in stamp2:
- if stamp1['host'] != stamp2['host']:
- return True
- if 'kernel' in stamp1 and 'kernel' in stamp2:
- if stamp1['kernel'] != stamp2['kernel']:
- return True
- if 'mode' in stamp1 and 'mode' in stamp2:
- if stamp1['mode'] != stamp2['mode']:
- return True
- return False
-
# Function: doesTraceLogHaveTraceEvents
# Description:
# Quickly determine if the ftrace log has some or all of the trace events
# create blocks for orphan cg data
for sortkey in sorted(sortlist):
cg = sortlist[sortkey]
- name = cg.list[0].name
+ name = cg.name
if sysvals.isCallgraphFunc(name):
vprint('Callgraph found for task %d: %.3fms, %s' % (cg.pid, (cg.end - cg.start)*1000, name))
cg.newActionFromFunction(data)
data.fixupInitcallsThatDidntReturn()
return True
+def callgraphHTML(sv, hf, num, cg, title, color, devid):
+ html_func_top = '<article id="{0}" class="atop" style="background:{1}">\n<input type="checkbox" class="pf" id="f{2}" checked/><label for="f{2}">{3} {4}</label>\n'
+ html_func_start = '<article>\n<input type="checkbox" class="pf" id="f{0}" checked/><label for="f{0}">{1} {2}</label>\n'
+ html_func_end = '</article>\n'
+ html_func_leaf = '<article>{0} {1}</article>\n'
+
+ cgid = devid
+ if cg.id:
+ cgid += cg.id
+ cglen = (cg.end - cg.start) * 1000
+ if cglen < sv.mincglen:
+ return num
+
+ fmt = '<r>(%.3f ms @ '+sv.timeformat+' to '+sv.timeformat+')</r>'
+ flen = fmt % (cglen, cg.start, cg.end)
+ hf.write(html_func_top.format(cgid, color, num, title, flen))
+ num += 1
+ for line in cg.list:
+ if(line.length < 0.000000001):
+ flen = ''
+ else:
+ fmt = '<n>(%.3f ms @ '+sv.timeformat+')</n>'
+ flen = fmt % (line.length*1000, line.time)
+ if(line.freturn and line.fcall):
+ hf.write(html_func_leaf.format(line.name, flen))
+ elif(line.freturn):
+ hf.write(html_func_end)
+ else:
+ hf.write(html_func_start.format(num, line.name, flen))
+ num += 1
+ hf.write(html_func_end)
+ return num
+
+def addCallgraphs(sv, hf, data):
+ hf.write('<section id="callgraphs" class="callgraph">\n')
+ # write out the ftrace data converted to html
+ num = 0
+ for p in data.phases:
+ if sv.cgphase and p != sv.cgphase:
+ continue
+ list = data.dmesg[p]['list']
+ for devname in data.sortedDevices(p):
+ dev = list[devname]
+ color = 'white'
+ if 'color' in data.dmesg[p]:
+ color = data.dmesg[p]['color']
+ if 'color' in dev:
+ color = dev['color']
+ name = devname
+ if(devname in sv.devprops):
+ name = sv.devprops[devname].altName(devname)
+ if sv.suspendmode in suspendmodename:
+ name += ' '+p
+ if('ftrace' in dev):
+ cg = dev['ftrace']
+ num = callgraphHTML(sv, hf, num, cg,
+ name, color, dev['id'])
+ if('ftraces' in dev):
+ for cg in dev['ftraces']:
+ num = callgraphHTML(sv, hf, num, cg,
+ name+' → '+cg.name, color, dev['id'])
+
+ hf.write('\n\n </section>\n')
+
# Function: createHTMLSummarySimple
# Description:
# Create summary html file for a series of tests
# Arguments:
# testruns: array of Data objects from parseTraceLog
-def createHTMLSummarySimple(testruns, htmlfile):
- # print out the basic summary of all the tests
- hf = open(htmlfile, 'w')
-
+def createHTMLSummarySimple(testruns, htmlfile, folder):
# write the html header first (html head, css code, up to body start)
html = '<!DOCTYPE html>\n<html>\n<head>\n\
<meta http-equiv="content-type" content="text/html; charset=UTF-8">\n\
- <title>AnalyzeSuspend Summary</title>\n\
+ <title>SleepGraph Summary</title>\n\
<style type=\'text/css\'>\n\
- body {overflow-y: scroll;}\n\
- .stamp {width: 100%;text-align:center;background-color:#495E09;line-height:30px;color:white;font: 25px Arial;}\n\
+ .stamp {width: 100%;text-align:center;background:#888;line-height:30px;color:white;font: 25px Arial;}\n\
table {width:100%;border-collapse: collapse;}\n\
- .summary {font: 22px Arial;border:1px solid;}\n\
- th {border: 1px solid black;background-color:#A7C942;color:white;}\n\
- td {text-align: center;}\n\
- tr.alt td {background-color:#EAF2D3;}\n\
- tr.avg td {background-color:#BDE34C;}\n\
- a:link {color: #90B521;}\n\
- a:visited {color: #495E09;}\n\
- a:hover {color: #B1DF28;}\n\
- a:active {color: #FFFFFF;}\n\
+ .summary {border:1px solid;}\n\
+ th {border: 1px solid black;background:#222;color:white;}\n\
+ td {font: 16px "Times New Roman";text-align: center;}\n\
+ tr.alt td {background:#ddd;}\n\
+ tr.avg td {background:#aaa;}\n\
</style>\n</head>\n<body>\n'
# group test header
- count = len(testruns)
- headline_stamp = '<div class="stamp">{0} {1} {2} {3} ({4} tests)</div>\n'
- html += headline_stamp.format(sysvals.stamp['host'],
- sysvals.stamp['kernel'], sysvals.stamp['mode'],
- sysvals.stamp['time'], count)
-
- # check to see if all the tests have the same value
- stampcolumns = False
- for data in testruns:
- if diffStamp(sysvals.stamp, data.stamp):
- stampcolumns = True
- break
-
+ html += '<div class="stamp">%s (%d tests)</div>\n' % (folder, len(testruns))
th = '\t<th>{0}</th>\n'
td = '\t<td>{0}</td>\n'
- tdlink = '\t<td><a href="{0}">Click Here</a></td>\n'
+ tdlink = '\t<td><a href="{0}">html</a></td>\n'
# table header
- html += '<table class="summary">\n<tr>\n'
- html += th.format("Test #")
- if stampcolumns:
- html += th.format("Hostname")
- html += th.format("Kernel Version")
- html += th.format("Suspend Mode")
- html += th.format("Test Time")
- html += th.format("Suspend Time")
- html += th.format("Resume Time")
- html += th.format("Detail")
- html += '</tr>\n'
+ html += '<table class="summary">\n<tr>\n' + th.format('#') +\
+ th.format('Mode') + th.format('Host') + th.format('Kernel') +\
+ th.format('Test Time') + th.format('Suspend') + th.format('Resume') +\
+ th.format('Detail') + '</tr>\n'
# test data, 1 row per test
- sTimeAvg = 0.0
- rTimeAvg = 0.0
- num = 1
- for data in testruns:
- # data.end is the end of post_resume
- resumeEnd = data.dmesg['resume_complete']['end']
+ avg = '<tr class="avg"><td></td><td></td><td></td><td></td>'+\
+ '<td>Average of {0} {1} tests</td><td>{2}</td><td>{3}</td><td></td></tr>\n'
+ sTimeAvg = rTimeAvg = 0.0
+ mode = ''
+ num = 0
+ for data in sorted(testruns, key=lambda v:(v['mode'], v['host'], v['kernel'])):
+ if mode != data['mode']:
+ # test average line
+ if(num > 0):
+ sTimeAvg /= (num - 1)
+ rTimeAvg /= (num - 1)
+ html += avg.format('%d' % (num - 1), mode,
+ '%3.3f ms' % sTimeAvg, '%3.3f ms' % rTimeAvg)
+ sTimeAvg = rTimeAvg = 0.0
+ mode = data['mode']
+ num = 1
+ # alternate row color
if num % 2 == 1:
html += '<tr class="alt">\n'
else:
html += '<tr>\n'
-
- # test num
- html += td.format("test %d" % num)
+ html += td.format("%d" % num)
num += 1
- if stampcolumns:
- # host name
- val = "unknown"
- if('host' in data.stamp):
- val = data.stamp['host']
- html += td.format(val)
- # host kernel
+ # basic info
+ for item in ['mode', 'host', 'kernel', 'time']:
val = "unknown"
- if('kernel' in data.stamp):
- val = data.stamp['kernel']
+ if(item in data):
+ val = data[item]
html += td.format(val)
- # suspend mode
- val = "unknown"
- if('mode' in data.stamp):
- val = data.stamp['mode']
- html += td.format(val)
- # test time
- val = "unknown"
- if('time' in data.stamp):
- val = data.stamp['time']
- html += td.format(val)
# suspend time
- sTime = (data.tSuspended - data.start)*1000
+ sTime = float(data['suspend'])
sTimeAvg += sTime
- html += td.format("%3.3f ms" % sTime)
+ html += td.format('%.3f ms' % sTime)
# resume time
- rTime = (resumeEnd - data.tResumed)*1000
+ rTime = float(data['resume'])
rTimeAvg += rTime
- html += td.format("%3.3f ms" % rTime)
+ html += td.format('%.3f ms' % rTime)
# link to the output html
- html += tdlink.format(data.outfile)
-
- html += '</tr>\n'
-
- # last line: test average
- if(count > 0):
- sTimeAvg /= count
- rTimeAvg /= count
- html += '<tr class="avg">\n'
- html += td.format('Average') # name
- if stampcolumns:
- html += td.format('') # host
- html += td.format('') # kernel
- html += td.format('') # mode
- html += td.format('') # time
- html += td.format("%3.3f ms" % sTimeAvg) # suspend time
- html += td.format("%3.3f ms" % rTimeAvg) # resume time
- html += td.format('') # output link
- html += '</tr>\n'
+ html += tdlink.format(data['url']) + '</tr>\n'
+ # last test average line
+ if(num > 0):
+ sTimeAvg /= (num - 1)
+ rTimeAvg /= (num - 1)
+ html += avg.format('%d' % (num - 1), mode,
+ '%3.3f ms' % sTimeAvg, '%3.3f ms' % rTimeAvg)
# flush the data to file
- hf.write(html+'</table>\n')
- hf.write('</body>\n</html>\n')
+ hf = open(htmlfile, 'w')
+ hf.write(html+'</table>\n</body>\n</html>\n')
hf.close()
-def htmlTitle():
- modename = {
- 'freeze': 'Freeze (S0)',
- 'standby': 'Standby (S1)',
- 'mem': 'Suspend (S3)',
- 'disk': 'Hibernate (S4)'
- }
- kernel = sysvals.stamp['kernel']
- host = sysvals.hostname[0].upper()+sysvals.hostname[1:]
- mode = sysvals.suspendmode
- if sysvals.suspendmode in modename:
- mode = modename[sysvals.suspendmode]
- return host+' '+mode+' '+kernel
-
def ordinal(value):
suffix = 'th'
if value < 10 or value > 19:
kerror = True
data.normalizeTime(testruns[-1].tSuspended)
- x2changes = ['', 'absolute']
- if len(testruns) > 1:
- x2changes = ['1', 'relative']
# html function templates
- headline_version = '<div class="version"><a href="https://01.org/suspendresume">AnalyzeSuspend v%s</a></div>' % sysvals.version
- headline_stamp = '<div class="stamp">{0} {1} {2} {3}</div>\n'
- html_devlist1 = '<button id="devlist1" class="devlist" style="float:left;">Device Detail%s</button>' % x2changes[0]
- html_zoombox = '<center><button id="zoomin">ZOOM IN +</button><button id="zoomout">ZOOM OUT -</button><button id="zoomdef">ZOOM 1:1</button></center>\n'
- html_devlist2 = '<button id="devlist2" class="devlist" style="float:right;">Device Detail2</button>\n'
- html_timeline = '<div id="dmesgzoombox" class="zoombox">\n<div id="{0}" class="timeline" style="height:{1}px">\n'
- html_tblock = '<div id="block{0}" class="tblock" style="left:{1}%;width:{2}%;"><div class="tback" style="height:{3}px"></div>\n'
- html_device = '<div id="{0}" title="{1}" class="thread{7}" style="left:{2}%;top:{3}px;height:{4}px;width:{5}%;{8}">{6}</div>\n'
html_error = '<div id="{1}" title="kernel error/warning" class="err" style="right:{0}%">ERROR→</div>\n'
html_traceevent = '<div title="{0}" class="traceevent{6}" style="left:{1}%;top:{2}px;height:{3}px;width:{4}%;line-height:{3}px;{7}">{5}</div>\n'
html_cpuexec = '<div class="jiffie" style="left:{0}%;top:{1}px;height:{2}px;width:{3}%;background:{4};"></div>\n'
- html_phase = '<div class="phase" style="left:{0}%;width:{1}%;top:{2}px;height:{3}px;background-color:{4}">{5}</div>\n'
- html_phaselet = '<div id="{0}" class="phaselet" style="left:{1}%;width:{2}%;background:{3}"></div>\n'
- html_legend = '<div id="p{3}" class="square" style="left:{0}%;background-color:{1}"> {2}</div>\n'
+ html_legend = '<div id="p{3}" class="square" style="left:{0}%;background:{1}"> {2}</div>\n'
html_timetotal = '<table class="time1">\n<tr>'\
'<td class="green" title="{3}">{2} Suspend Time: <b>{0} ms</b></td>'\
'<td class="yellow" title="{4}">{2} Resume Time: <b>{1} ms</b></td>'\
'</tr>\n</table>\n'
# html format variables
- hoverZ = 'z-index:8;'
- if sysvals.usedevsrc:
- hoverZ = ''
scaleH = 20
- scaleTH = 20
if kerror:
scaleH = 40
- scaleTH = 60
# device timeline
vprint('Creating Device Timeline...')
devtl = Timeline(30, scaleH)
+ # write the test title and general info header
+ devtl.createHeader(sysvals)
+
# Generate the header for this timeline
for data in testruns:
tTotal = data.end - data.start
if(len(testruns) > 1):
testdesc = ordinal(data.testnumber+1)+' '+testdesc
thtml = html_timetotal3.format(run_time, testdesc)
- devtl.html['header'] += thtml
+ devtl.html += thtml
elif data.fwValid:
suspend_time = '%.0f'%(sktime + (data.fwSuspend/1000000.0))
resume_time = '%.0f'%(rktime + (data.fwResume/1000000.0))
else:
thtml = html_timetotal2.format(suspend_time, low_time, \
resume_time, testdesc1, stitle, rtitle)
- devtl.html['header'] += thtml
+ devtl.html += thtml
sftime = '%.3f'%(data.fwSuspend / 1000000.0)
rftime = '%.3f'%(data.fwResume / 1000000.0)
- devtl.html['header'] += html_timegroups.format('%.3f'%sktime, \
+ devtl.html += html_timegroups.format('%.3f'%sktime, \
sftime, rftime, '%.3f'%rktime, testdesc2, sysvals.suspendmode)
else:
suspend_time = '%.3f' % sktime
else:
thtml = html_timetotal2.format(suspend_time, low_time, \
resume_time, testdesc, stitle, rtitle)
- devtl.html['header'] += thtml
+ devtl.html += thtml
# time scale for potentially multiple datasets
t0 = testruns[0].start
devtl.getPhaseRows(threadlist, devtl.rows)
devtl.calcTotalRows()
- # create bounding box, add buttons
- if sysvals.suspendmode != 'command':
- devtl.html['timeline'] += html_devlist1
- if len(testruns) > 1:
- devtl.html['timeline'] += html_devlist2
- devtl.html['timeline'] += html_zoombox
- devtl.html['timeline'] += html_timeline.format('dmesg', devtl.height)
-
# draw the full timeline
+ devtl.createZoomBox(sysvals.suspendmode, len(testruns))
phases = {'suspend':[],'resume':[]}
for phase in data.dmesg:
if 'resume' in phase:
# draw suspend and resume blocks separately
bname = '%s%d' % (dir[0], data.testnumber)
if dir == 'suspend':
- m0 = testruns[data.testnumber].start
- mMax = testruns[data.testnumber].tSuspended
- mTotal = mMax - m0
+ m0 = data.start
+ mMax = data.tSuspended
left = '%f' % (((m0-t0)*100.0)/tTotal)
else:
- m0 = testruns[data.testnumber].tSuspended
- mMax = testruns[data.testnumber].end
+ m0 = data.tSuspended
+ mMax = data.end
# in an x2 run, remove any gap between blocks
if len(testruns) > 1 and data.testnumber == 0:
mMax = testruns[1].start
- mTotal = mMax - m0
left = '%f' % ((((m0-t0)*100.0)+sysvals.srgap/2)/tTotal)
+ mTotal = mMax - m0
# if a timeline block is 0 length, skip altogether
if mTotal == 0:
continue
width = '%f' % (((mTotal*100.0)-sysvals.srgap/2)/tTotal)
- devtl.html['timeline'] += html_tblock.format(bname, left, width, devtl.scaleH)
+ devtl.html += devtl.html_tblock.format(bname, left, width, devtl.scaleH)
for b in sorted(phases[dir]):
# draw the phase color background
phase = data.dmesg[b]
length = phase['end']-phase['start']
left = '%f' % (((phase['start']-m0)*100.0)/mTotal)
width = '%f' % ((length*100.0)/mTotal)
- devtl.html['timeline'] += html_phase.format(left, width, \
+ devtl.html += devtl.html_phase.format(left, width, \
'%.3f'%devtl.scaleH, '%.3f'%devtl.bodyH, \
data.dmesg[b]['color'], '')
for e in data.errorinfo[dir]:
# draw red lines for any kernel errors found
t, err = e
right = '%f' % (((mMax-t)*100.0)/mTotal)
- devtl.html['timeline'] += html_error.format(right, err)
+ devtl.html += html_error.format(right, err)
for b in sorted(phases[dir]):
# draw the devices for this phase
phaselist = data.dmesg[b]['list']
if 'htmlclass' in dev:
xtraclass = dev['htmlclass']
if 'color' in dev:
- xtrastyle = 'background-color:%s;' % dev['color']
+ xtrastyle = 'background:%s;' % dev['color']
if(d in sysvals.devprops):
name = sysvals.devprops[d].altName(d)
xtraclass = sysvals.devprops[d].xtraClass()
title += 'post_resume_process'
else:
title += b
- devtl.html['timeline'] += html_device.format(dev['id'], \
+ devtl.html += devtl.html_device.format(dev['id'], \
title, left, top, '%.3f'%rowheight, width, \
d+drv, xtraclass, xtrastyle)
if('cpuexec' in dev):
left = '%f' % (((start-m0)*100)/mTotal)
width = '%f' % ((end-start)*100/mTotal)
color = 'rgba(255, 0, 0, %f)' % j
- devtl.html['timeline'] += \
+ devtl.html += \
html_cpuexec.format(left, top, height, width, color)
if('src' not in dev):
continue
xtrastyle = ''
if e.color:
xtrastyle = 'background:%s;' % e.color
- devtl.html['timeline'] += \
+ devtl.html += \
html_traceevent.format(e.title(), \
left, top, height, width, e.text(), '', xtrastyle)
# draw the time scale, try to make the number of labels readable
- devtl.html['timeline'] += devtl.createTimeScale(m0, mMax, tTotal, dir)
- devtl.html['timeline'] += '</div>\n'
+ devtl.createTimeScale(m0, mMax, tTotal, dir)
+ devtl.html += '</div>\n'
# timeline is finished
- devtl.html['timeline'] += '</div>\n</div>\n'
+ devtl.html += '</div>\n</div>\n'
# draw a legend which describes the phases by color
if sysvals.suspendmode != 'command':
data = testruns[-1]
- devtl.html
['legend'] = '<div class="legend">\n'
+ devtl.html
+= '<div class="legend">\n'
pdelta = 100.0/len(data.phases)
pmargin = pdelta / 4.0
for phase in data.phases:
id += tmp[1][0]
order = '%.2f' % ((data.dmesg[phase]['order'] * pdelta) + pmargin)
name = string.replace(phase, '_', ' ')
- devtl.html['legend'] += html_legend.format(order, \
+ devtl.html += html_legend.format(order, \
data.dmesg[phase]['color'], name, id)
- devtl.html['legend'] += '</div>\n'
+ devtl.html += '</div>\n'
hf = open(sysvals.htmlfile, 'w')
- if not sysvals.cgexp:
- cgchk = 'checked'
- cgnchk = 'not(:checked)'
- else:
- cgchk = 'not(:checked)'
- cgnchk = 'checked'
-
- # write the html header first (html head, css code, up to body start)
- html_header = '<!DOCTYPE html>\n<html>\n<head>\n\
- <meta http-equiv="content-type" content="text/html; charset=UTF-8">\n\
- <title>'+htmlTitle()+'</title>\n\
- <style type=\'text/css\'>\n\
- body {overflow-y:scroll;}\n\
- .stamp {width:100%;text-align:center;background-color:gray;line-height:30px;color:white;font:25px Arial;}\n\
- .callgraph {margin-top:30px;box-shadow:5px 5px 20px black;}\n\
- .callgraph article * {padding-left:28px;}\n\
- h1 {color:black;font:bold 30px Times;}\n\
- t0 {color:black;font:bold 30px Times;}\n\
- t1 {color:black;font:30px Times;}\n\
- t2 {color:black;font:25px Times;}\n\
- t3 {color:black;font:20px Times;white-space:nowrap;}\n\
- t4 {color:black;font:bold 30px Times;line-height:60px;white-space:nowrap;}\n\
- cS {font:bold 13px Times;}\n\
- table {width:100%;}\n\
- .gray {background-color:rgba(80,80,80,0.1);}\n\
- .green {background-color:rgba(204,255,204,0.4);}\n\
- .purple {background-color:rgba(128,0,128,0.2);}\n\
- .yellow {background-color:rgba(255,255,204,0.4);}\n\
- .time1 {font:22px Arial;border:1px solid;}\n\
- .time2 {font:15px Arial;border-bottom:1px solid;border-left:1px solid;border-right:1px solid;}\n\
- td {text-align:center;}\n\
- r {color:#500000;font:15px Tahoma;}\n\
- n {color:#505050;font:15px Tahoma;}\n\
- .tdhl {color:red;}\n\
- .hide {display:none;}\n\
- .pf {display:none;}\n\
- .pf:'+cgchk+' + label {background:url(\'data:image/svg+xml;utf,<?xml version="1.0" standalone="no"?><svg xmlns="http://www.w3.org/2000/svg" height="18" width="18" version="1.1"><circle cx="9" cy="9" r="8" stroke="black" stroke-width="1" fill="white"/><rect x="4" y="8" width="10" height="2" style="fill:black;stroke-width:0"/><rect x="8" y="4" width="2" height="10" style="fill:black;stroke-width:0"/></svg>\') no-repeat left center;}\n\
- .pf:'+cgnchk+' ~ label {background:url(\'data:image/svg+xml;utf,<?xml version="1.0" standalone="no"?><svg xmlns="http://www.w3.org/2000/svg" height="18" width="18" version="1.1"><circle cx="9" cy="9" r="8" stroke="black" stroke-width="1" fill="white"/><rect x="4" y="8" width="10" height="2" style="fill:black;stroke-width:0"/></svg>\') no-repeat left center;}\n\
- .pf:'+cgchk+' ~ *:not(:nth-child(2)) {display:none;}\n\
- .zoombox {position:relative;width:100%;overflow-x:scroll;-webkit-user-select:none;-moz-user-select:none;user-select:none;}\n\
- .timeline {position:relative;font-size:14px;cursor:pointer;width:100%; overflow:hidden;background:linear-gradient(#cccccc, white);}\n\
- .thread {position:absolute;height:0%;overflow:hidden;z-index:7;line-height:30px;font-size:14px;border:1px solid;text-align:center;white-space:nowrap;}\n\
- .thread.ps {border-radius:3px;background:linear-gradient(to top, #ccc, #eee);}\n\
- .thread:hover {background-color:white;border:1px solid red;'+hoverZ+'}\n\
- .thread.sec,.thread.sec:hover {background-color:black;border:0;color:white;line-height:15px;font-size:10px;}\n\
- .hover {background-color:white;border:1px solid red;'+hoverZ+'}\n\
- .hover.sync {background-color:white;}\n\
- .hover.bg,.hover.kth,.hover.sync,.hover.ps {background-color:white;}\n\
- .jiffie {position:absolute;pointer-events: none;z-index:8;}\n\
- .traceevent {position:absolute;font-size:10px;z-index:7;overflow:hidden;color:black;text-align:center;white-space:nowrap;border-radius:5px;border:1px solid black;background:linear-gradient(to bottom right,#CCC,#969696);}\n\
- .traceevent:hover {color:white;font-weight:bold;border:1px solid white;}\n\
- .phase {position:absolute;overflow:hidden;border:0px;text-align:center;}\n\
- .phaselet {position:absolute;overflow:hidden;border:0px;text-align:center;height:100px;font-size:24px;}\n\
- .t {position:absolute;line-height:'+('%d'%scaleTH)+'px;pointer-events:none;top:0;height:100%;border-right:1px solid black;z-index:6;}\n\
- .err {position:absolute;top:0%;height:100%;border-right:3px solid red;color:red;font:bold 14px Times;line-height:18px;}\n\
- .legend {position:relative; width:100%; height:40px; text-align:center;margin-bottom:20px}\n\
- .legend .square {position:absolute;cursor:pointer;top:10px; width:0px;height:20px;border:1px solid;padding-left:20px;}\n\
- button {height:40px;width:200px;margin-bottom:20px;margin-top:20px;font-size:24px;}\n\
- .logbtn {position:relative;float:right;height:25px;width:50px;margin-top:3px;margin-bottom:0;font-size:10px;text-align:center;}\n\
- .devlist {position:'+x2changes[1]+';width:190px;}\n\
- a:link {color:white;text-decoration:none;}\n\
- a:visited {color:white;}\n\
- a:hover {color:white;}\n\
- a:active {color:white;}\n\
- .version {position:relative;float:left;color:white;font-size:10px;line-height:30px;margin-left:10px;}\n\
- #devicedetail {height:100px;box-shadow:5px 5px 20px black;}\n\
- .tblock {position:absolute;height:100%;background-color:#ddd;}\n\
- .tback {position:absolute;width:100%;background:linear-gradient(#ccc, #ddd);}\n\
- .bg {z-index:1;}\n\
- </style>\n</head>\n<body>\n'
-
# no header or css if its embedded
if(sysvals.embedded):
hf.write('pass True tSus %.3f tRes %.3f tLow %.3f fwvalid %s tSus %.3f tRes %.3f\n' %
(data.tSuspended-data.start, data.end-data.tSuspended, data.tLow, data.fwValid, \
data.fwSuspend/1000000, data.fwResume/1000000))
else:
- hf.write(html_header)
-
- # write the test title and general info header
- if(sysvals.stamp['time'] != ""):
- hf.write(headline_version)
- if sysvals.logmsg:
- hf.write('<button id="showtest" class="logbtn">log</button>')
- if sysvals.addlogs and sysvals.dmesgfile:
- hf.write('<button id="showdmesg" class="logbtn">dmesg</button>')
- if sysvals.addlogs and sysvals.ftracefile:
- hf.write('<button id="showftrace" class="logbtn">ftrace</button>')
- hf.write(headline_stamp.format(sysvals.stamp['host'],
- sysvals.stamp['kernel'], sysvals.stamp['mode'], \
- sysvals.stamp['time']))
+ addCSS(hf, sysvals, len(testruns), kerror)
# write the device timeline
- hf.write(devtl.html['header'])
- hf.write(devtl.html['timeline'])
- hf.write(devtl.html['legend'])
+ hf.write(devtl.html)
hf.write('<div id="devicedetailtitle"></div>\n')
hf.write('<div id="devicedetail" style="display:none;">\n')
# draw the colored boxes for the device detail section
for data in testruns:
hf.write('<div id="devicedetail%d">\n' % data.testnumber)
pscolor = 'linear-gradient(to top left, #ccc, #eee)'
- hf.write(html_phaselet.format('pre_suspend_process', \
+ hf.write(devtl.html_phaselet.format('pre_suspend_process', \
'0', '0', pscolor))
for b in data.phases:
phase = data.dmesg[b]
length = phase['end']-phase['start']
left = '%.3f' % (((phase['start']-t0)*100.0)/tTotal)
width = '%.3f' % ((length*100.0)/tTotal)
- hf.write(html_phaselet.format(b, left, width, \
+ hf.write(devtl.html_phaselet.format(b, left, width, \
data.dmesg[b]['color']))
- hf.write(html_phaselet.format('post_resume_process', \
+ hf.write(devtl.html_phaselet.format('post_resume_process', \
'0', '0', pscolor))
if sysvals.suspendmode == 'command':
- hf.write(html_phaselet.format('cmdexec', '0', '0', pscolor))
+ hf.write(devtl.html_phaselet.format('cmdexec', '0', '0', pscolor))
hf.write('</div>\n')
hf.write('</div>\n')
else:
data = testruns[-1]
if(sysvals.usecallgraph and not sysvals.embedded):
- hf.write('<section id="callgraphs" class="callgraph">\n')
- # write out the ftrace data converted to html
- html_func_top = '<article id="{0}" class="atop" style="background-color:{1}">\n<input type="checkbox" class="pf" id="f{2}" checked/><label for="f{2}">{3} {4}</label>\n'
- html_func_start = '<article>\n<input type="checkbox" class="pf" id="f{0}" checked/><label for="f{0}">{1} {2}</label>\n'
- html_func_end = '</article>\n'
- html_func_leaf = '<article>{0} {1}</article>\n'
- num = 0
- for p in data.phases:
- if sysvals.cgphase and p != sysvals.cgphase:
- continue
- list = data.dmesg[p]['list']
- for devname in data.sortedDevices(p):
- if('ftrace' not in list[devname]):
- continue
- devid = list[devname]['id']
- cg = list[devname]['ftrace']
- clen = (cg.end - cg.start) * 1000
- if clen < sysvals.mincglen:
- continue
- fmt = '<r>(%.3f ms @ '+sysvals.timeformat+' to '+sysvals.timeformat+')</r>'
- flen = fmt % (clen, cg.start, cg.end)
- name = devname
- if(devname in sysvals.devprops):
- name = sysvals.devprops[devname].altName(devname)
- if sysvals.suspendmode == 'command':
- ftitle = name
- else:
- ftitle = name+' '+p
- hf.write(html_func_top.format(devid, data.dmesg[p]['color'], \
- num, ftitle, flen))
- num += 1
- for line in cg.list:
- if(line.length < 0.000000001):
- flen = ''
- else:
- fmt = '<n>(%.3f ms @ '+sysvals.timeformat+')</n>'
- flen = fmt % (line.length*1000, line.time)
- if(line.freturn and line.fcall):
- hf.write(html_func_leaf.format(line.name, flen))
- elif(line.freturn):
- hf.write(html_func_end)
- else:
- hf.write(html_func_start.format(num, line.name, flen))
- num += 1
- hf.write(html_func_end)
- hf.write('\n\n </section>\n')
+ addCallgraphs(sysvals, hf, data)
# add the test log as a hidden div
if sysvals.logmsg:
hf.close()
return True
+def addCSS(hf, sv, testcount=1, kerror=False, extra=''):
+ kernel = sv.stamp['kernel']
+ host = sv.hostname[0].upper()+sv.hostname[1:]
+ mode = sv.suspendmode
+ if sv.suspendmode in suspendmodename:
+ mode = suspendmodename[sv.suspendmode]
+ title = host+' '+mode+' '+kernel
+
+ # various format changes by flags
+ cgchk = 'checked'
+ cgnchk = 'not(:checked)'
+ if sv.cgexp:
+ cgchk = 'not(:checked)'
+ cgnchk = 'checked'
+
+ hoverZ = 'z-index:8;'
+ if sv.usedevsrc:
+ hoverZ = ''
+
+ devlistpos = 'absolute'
+ if testcount > 1:
+ devlistpos = 'relative'
+
+ scaleTH = 20
+ if kerror:
+ scaleTH = 60
+
+ # write the html header first (html head, css code, up to body start)
+ html_header = '<!DOCTYPE html>\n<html>\n<head>\n\
+ <meta http-equiv="content-type" content="text/html; charset=UTF-8">\n\
+ <title>'+title+'</title>\n\
+ <style type=\'text/css\'>\n\
+ body {overflow-y:scroll;}\n\
+ .stamp {width:100%;text-align:center;background:gray;line-height:30px;color:white;font:25px Arial;}\n\
+ .callgraph {margin-top:30px;box-shadow:5px 5px 20px black;}\n\
+ .callgraph article * {padding-left:28px;}\n\
+ h1 {color:black;font:bold 30px Times;}\n\
+ t0 {color:black;font:bold 30px Times;}\n\
+ t1 {color:black;font:30px Times;}\n\
+ t2 {color:black;font:25px Times;}\n\
+ t3 {color:black;font:20px Times;white-space:nowrap;}\n\
+ t4 {color:black;font:bold 30px Times;line-height:60px;white-space:nowrap;}\n\
+ cS {font:bold 13px Times;}\n\
+ table {width:100%;}\n\
+ .gray {background:rgba(80,80,80,0.1);}\n\
+ .green {background:rgba(204,255,204,0.4);}\n\
+ .purple {background:rgba(128,0,128,0.2);}\n\
+ .yellow {background:rgba(255,255,204,0.4);}\n\
+ .blue {background:rgba(169,208,245,0.4);}\n\
+ .time1 {font:22px Arial;border:1px solid;}\n\
+ .time2 {font:15px Arial;border-bottom:1px solid;border-left:1px solid;border-right:1px solid;}\n\
+ td {text-align:center;}\n\
+ r {color:#500000;font:15px Tahoma;}\n\
+ n {color:#505050;font:15px Tahoma;}\n\
+ .tdhl {color:red;}\n\
+ .hide {display:none;}\n\
+ .pf {display:none;}\n\
+ .pf:'+cgchk+' + label {background:url(\'data:image/svg+xml;utf,<?xml version="1.0" standalone="no"?><svg xmlns="http://www.w3.org/2000/svg" height="18" width="18" version="1.1"><circle cx="9" cy="9" r="8" stroke="black" stroke-width="1" fill="white"/><rect x="4" y="8" width="10" height="2" style="fill:black;stroke-width:0"/><rect x="8" y="4" width="2" height="10" style="fill:black;stroke-width:0"/></svg>\') no-repeat left center;}\n\
+ .pf:'+cgnchk+' ~ label {background:url(\'data:image/svg+xml;utf,<?xml version="1.0" standalone="no"?><svg xmlns="http://www.w3.org/2000/svg" height="18" width="18" version="1.1"><circle cx="9" cy="9" r="8" stroke="black" stroke-width="1" fill="white"/><rect x="4" y="8" width="10" height="2" style="fill:black;stroke-width:0"/></svg>\') no-repeat left center;}\n\
+ .pf:'+cgchk+' ~ *:not(:nth-child(2)) {display:none;}\n\
+ .zoombox {position:relative;width:100%;overflow-x:scroll;-webkit-user-select:none;-moz-user-select:none;user-select:none;}\n\
+ .timeline {position:relative;font-size:14px;cursor:pointer;width:100%; overflow:hidden;background:linear-gradient(#cccccc, white);}\n\
+ .thread {position:absolute;height:0%;overflow:hidden;z-index:7;line-height:30px;font-size:14px;border:1px solid;text-align:center;white-space:nowrap;}\n\
+ .thread.ps {border-radius:3px;background:linear-gradient(to top, #ccc, #eee);}\n\
+ .thread:hover {background:white;border:1px solid red;'+hoverZ+'}\n\
+ .thread.sec,.thread.sec:hover {background:black;border:0;color:white;line-height:15px;font-size:10px;}\n\
+ .hover {background:white;border:1px solid red;'+hoverZ+'}\n\
+ .hover.sync {background:white;}\n\
+ .hover.bg,.hover.kth,.hover.sync,.hover.ps {background:white;}\n\
+ .jiffie {position:absolute;pointer-events: none;z-index:8;}\n\
+ .traceevent {position:absolute;font-size:10px;z-index:7;overflow:hidden;color:black;text-align:center;white-space:nowrap;border-radius:5px;border:1px solid black;background:linear-gradient(to bottom right,#CCC,#969696);}\n\
+ .traceevent:hover {color:white;font-weight:bold;border:1px solid white;}\n\
+ .phase {position:absolute;overflow:hidden;border:0px;text-align:center;}\n\
+ .phaselet {float:left;overflow:hidden;border:0px;text-align:center;min-height:100px;font-size:24px;}\n\
+ .t {position:absolute;line-height:'+('%d'%scaleTH)+'px;pointer-events:none;top:0;height:100%;border-right:1px solid black;z-index:6;}\n\
+ .err {position:absolute;top:0%;height:100%;border-right:3px solid red;color:red;font:bold 14px Times;line-height:18px;}\n\
+ .legend {position:relative; width:100%; height:40px; text-align:center;margin-bottom:20px}\n\
+ .legend .square {position:absolute;cursor:pointer;top:10px; width:0px;height:20px;border:1px solid;padding-left:20px;}\n\
+ button {height:40px;width:200px;margin-bottom:20px;margin-top:20px;font-size:24px;}\n\
+ .logbtn {position:relative;float:right;height:25px;width:50px;margin-top:3px;margin-bottom:0;font-size:10px;text-align:center;}\n\
+ .devlist {position:'+devlistpos+';width:190px;}\n\
+ a:link {color:white;text-decoration:none;}\n\
+ a:visited {color:white;}\n\
+ a:hover {color:white;}\n\
+ a:active {color:white;}\n\
+ .version {position:relative;float:left;color:white;font-size:10px;line-height:30px;margin-left:10px;}\n\
+ #devicedetail {min-height:100px;box-shadow:5px 5px 20px black;}\n\
+ .tblock {position:absolute;height:100%;background:#ddd;}\n\
+ .tback {position:absolute;width:100%;background:linear-gradient(#ccc, #ddd);}\n\
+ .bg {z-index:1;}\n\
+'+extra+'\
+ </style>\n</head>\n<body>\n'
+ hf.write(html_header)
+
# Function: addScriptCode
# Description:
# Adds the javascript code to the output html
' var resolution = -1;\n'\
' var dragval = [0, 0];\n'\
' function redrawTimescale(t0, tMax, tS) {\n'\
- ' var rline = \'<div class="t" style="left:0;border-left:1px solid black;border-right:0;"><cS>←R</cS></div>\';\n'\
+ ' var rline = \'<div class="t" style="left:0;border-left:1px solid black;border-right:0;">\';\n'\
' var tTotal = tMax - t0;\n'\
' var list = document.getElementsByClassName("tblock");\n'\
' for (var i = 0; i < list.length; i++) {\n'\
' var pos = 0.0, val = 0.0;\n'\
' for (var j = 0; j < divTotal; j++) {\n'\
' var htmlline = "";\n'\
- ' if(list[i].id[5] == "r") {\n'\
- ' pos = 100 - (((j)*tS*100)/mTotal);\n'\
- ' val = (j)*tS;\n'\
- ' htmlline = \'<div class="t" style="right:\'+pos+\'%">\'+val+\'ms</div>\';\n'\
- ' if(j == 0)\n'\
- ' htmlline = rline;\n'\
- ' } else {\n'\
+ ' var mode = list[i].id[5];\n'\
+ ' if(mode == "s") {\n'\
' pos = 100 - (((j)*tS*100)/mTotal) - divEdge;\n'\
' val = (j-divTotal+1)*tS;\n'\
' if(j == divTotal - 1)\n'\
' htmlline = \'<div class="t" style="right:\'+pos+\'%"><cS>S→</cS></div>\';\n'\
' else\n'\
' htmlline = \'<div class="t" style="right:\'+pos+\'%">\'+val+\'ms</div>\';\n'\
+ ' } else {\n'\
+ ' pos = 100 - (((j)*tS*100)/mTotal);\n'\
+ ' val = (j)*tS;\n'\
+ ' htmlline = \'<div class="t" style="right:\'+pos+\'%">\'+val+\'ms</div>\';\n'\
+ ' if(j == 0)\n'\
+ ' if(mode == "r")\n'\
+ ' htmlline = rline+"<cS>←R</cS></div>";\n'\
+ ' else\n'\
+ ' htmlline = rline+"<cS>0ms</div>";\n'\
' }\n'\
' html += htmlline;\n'\
' }\n'\
' }\n'\
' }\n'\
' }\n'\
+ ' if(typeof devstats !== \'undefined\')\n'\
+ ' callDetail(this.id, this.title);\n'\
' var cglist = document.getElementById("callgraphs");\n'\
' if(!cglist) return;\n'\
' var cg = cglist.getElementsByClassName("atop");\n'\
' if(cg.length < 10) return;\n'\
' for (var i = 0; i < cg.length; i++) {\n'\
- ' if(idlist.indexOf(cg[i].id) >= 0) {\n'\
+ ' cgid = cg[i].id.split("x")[0]\n'\
+ ' if(idlist.indexOf(cgid) >= 0) {\n'\
+ ' cg[i].style.display = "block";\n'\
+ ' } else {\n'\
+ ' cg[i].style.display = "none";\n'\
+ ' }\n'\
+ ' }\n'\
+ ' }\n'\
+ ' function callDetail(devid, devtitle) {\n'\
+ ' if(!(devid in devstats) || devstats[devid].length < 1)\n'\
+ ' return;\n'\
+ ' var list = devstats[devid];\n'\
+ ' var tmp = devtitle.split(" ");\n'\
+ ' var name = tmp[0], phase = tmp[tmp.length-1];\n'\
+ ' var dd = document.getElementById(phase);\n'\
+ ' var total = parseFloat(tmp[1].slice(1));\n'\
+ ' var mlist = [];\n'\
+ ' var maxlen = 0;\n'\
+ ' var info = []\n'\
+ ' for(var i in list) {\n'\
+ ' if(list[i][0] == "@") {\n'\
+ ' info = list[i].split("|");\n'\
+ ' continue;\n'\
+ ' }\n'\
+ ' var tmp = list[i].split("|");\n'\
+ ' var t = parseFloat(tmp[0]), f = tmp[1], c = parseInt(tmp[2]);\n'\
+ ' var p = (t*100.0/total).toFixed(2);\n'\
+ ' mlist[mlist.length] = [f, c, t.toFixed(2), p+"%"];\n'\
+ ' if(f.length > maxlen)\n'\
+ ' maxlen = f.length;\n'\
+ ' }\n'\
+ ' var pad = 5;\n'\
+ ' if(mlist.length == 0) pad = 30;\n'\
+ ' var html = \'<div style="padding-top:\'+pad+\'px"><t3> <b>\'+name+\':</b>\';\n'\
+ ' if(info.length > 2)\n'\
+ ' html += " start=<b>"+info[1]+"</b>, end=<b>"+info[2]+"</b>";\n'\
+ ' if(info.length > 3)\n'\
+ ' html += ", length<i>(w/o overhead)</i>=<b>"+info[3]+" ms</b>";\n'\
+ ' if(info.length > 4)\n'\
+ ' html += ", return=<b>"+info[4]+"</b>";\n'\
+ ' html += "</t3></div>";\n'\
+ ' if(mlist.length > 0) {\n'\
+ ' html += \'<table class=fstat style="padding-top:\'+(maxlen*5)+\'px;"><tr><th>Function</th>\';\n'\
+ ' for(var i in mlist)\n'\
+ ' html += "<td class=vt>"+mlist[i][0]+"</td>";\n'\
+ ' html += "</tr><tr><th>Calls</th>";\n'\
+ ' for(var i in mlist)\n'\
+ ' html += "<td>"+mlist[i][1]+"</td>";\n'\
+ ' html += "</tr><tr><th>Time(ms)</th>";\n'\
+ ' for(var i in mlist)\n'\
+ ' html += "<td>"+mlist[i][2]+"</td>";\n'\
+ ' html += "</tr><tr><th>Percent</th>";\n'\
+ ' for(var i in mlist)\n'\
+ ' html += "<td>"+mlist[i][3]+"</td>";\n'\
+ ' html += "</tr></table>";\n'\
+ ' }\n'\
+ ' dd.innerHTML = html;\n'\
+ ' var height = (maxlen*5)+100;\n'\
+ ' dd.style.height = height+"px";\n'\
+ ' document.getElementById("devicedetail").style.height = height+"px";\n'\
+ ' }\n'\
+ ' function callSelect() {\n'\
+ ' var cglist = document.getElementById("callgraphs");\n'\
+ ' if(!cglist) return;\n'\
+ ' var cg = cglist.getElementsByClassName("atop");\n'\
+ ' for (var i = 0; i < cg.length; i++) {\n'\
+ ' if(this.id == cg[i].id) {\n'\
' cg[i].style.display = "block";\n'\
' } else {\n'\
' cg[i].style.display = "none";\n'\
' dev[i].onmouseover = deviceHover;\n'\
' dev[i].onmouseout = deviceUnhover;\n'\
' }\n'\
+ ' var dev = dmesg.getElementsByClassName("srccall");\n'\
+ ' for (var i = 0; i < dev.length; i++)\n'\
+ ' dev[i].onclick = callSelect;\n'\
' zoomTimeline();\n'\
' });\n'\
'</script>\n'
if(os.access(sysvals.powerfile, os.W_OK)):
return True
if fatal:
- doError('This command must be run as root')
+ doError('This command requires sysfs mount and root access')
return False
# Function: getArgInt
cmd = 'chown -R {0}:{0} {1} > /dev/null 2>&1'
call(cmd.format(os.environ['SUDO_USER'], sysvals.testdir), shell=True)
+def find_in_html(html, strs, div=False):
+ for str in strs:
+ l = len(str)
+ i = html.find(str)
+ if i >= 0:
+ break
+ if i < 0:
+ return ''
+ if not div:
+ return re.search(r'[-+]?\d*\.\d+|\d+', html[i+l:i+l+50]).group()
+ n = html[i+l:].find('</div>')
+ if n < 0:
+ return ''
+ return html[i+l:i+l+n]
+
# Function: runSummary
# Description:
# create a summary of tests in a sub-directory
-def runSummary(subdir, output):
- # get a list of ftrace output files
- files = []
+def runSummary(subdir, local=True):
+ inpath = os.path.abspath(subdir)
+ outpath = inpath
+ if local:
+ outpath = os.path.abspath('.')
+ print('Generating a summary of folder "%s"' % inpath)
+ testruns = []
for dirname, dirnames, filenames in os.walk(subdir):
for filename in filenames:
- if(re.match('.*_ftrace.txt', filename)):
- files.append("%s/%s" % (dirname, filename))
-
- # process the files in order and get an array of data objects
- testruns = []
- for file in sorted(files):
- if output:
- print("Test found in %s" % os.path.dirname(file))
- sysvals.ftracefile = file
- sysvals.dmesgfile = file.replace('_ftrace.txt', '_dmesg.txt')
- doesTraceLogHaveTraceEvents()
- sysvals.usecallgraph = False
- if not sysvals.usetraceeventsonly:
- if(not os.path.exists(sysvals.dmesgfile)):
- print("Skipping %s: not a valid test input" % file)
+ if(not re.match('.*.html', filename)):
continue
- else:
- if output:
- f = os.path.basename(sysvals.ftracefile)
- d = os.path.basename(sysvals.dmesgfile)
- print("\tInput files: %s and %s" % (f, d))
- testdata = loadKernelLog()
- data = testdata[0]
- parseKernelLog(data)
- testdata = [data]
- appendIncompleteTraceLog(testdata)
- else:
- if output:
- print("\tInput file: %s" % os.path.basename(sysvals.ftracefile))
- testdata = parseTraceLog()
- data = testdata[0]
- data.normalizeTime(data.tSuspended)
- link = file.replace(subdir+'/', '').replace('_ftrace.txt', '.html')
- data.outfile = link
- testruns.append(data)
-
- createHTMLSummarySimple(testruns, subdir+'/summary.html')
+ file = os.path.join(dirname, filename)
+ html = open(file, 'r').read(10000)
+ suspend = find_in_html(html,
+ ['Kernel Suspend: ', 'Kernel Suspend Time: '])
+ resume = find_in_html(html,
+ ['Kernel Resume: ', 'Kernel Resume Time: '])
+ line = find_in_html(html, ['<div class="stamp">'], True)
+ stmp = line.split()
+ if not suspend or not resume or len(stmp) < 4:
+ continue
+ data = {
+ 'host': stmp[0],
+ 'kernel': stmp[1],
+ 'mode': stmp[2],
+ 'time': string.join(stmp[3:], ' '),
+ 'suspend': suspend,
+ 'resume': resume,
+ 'url': os.path.relpath(file, outpath),
+ }
+ if len(stmp) == 7:
+ data['kernel'] = 'unknown'
+ data['mode'] = stmp[1]
+ data['time'] = string.join(stmp[2:], ' ')
+ testruns.append(data)
+ outfile = os.path.join(outpath, 'summary.html')
+ print('Summary file: %s' % outfile)
+ createHTMLSummarySimple(testruns, outfile, inpath)
# Function: checkArgBool
# Description:
sysvals.predelay = getArgInt('-predelay', value, 0, 60000, False)
elif(opt.lower() == 'postdelay'):
sysvals.postdelay = getArgInt('-postdelay', value, 0, 60000, False)
+ elif(opt.lower() == 'maxdepth'):
+ sysvals.max_graph_depth = getArgInt('-maxdepth', value, 0, 1000, False)
elif(opt.lower() == 'rtcwake'):
- sysvals.rtcwake = True
- sysvals.rtcwaketime = getArgInt('-rtcwake', value, 0, 3600, False)
+ if value.lower() == 'off':
+ sysvals.rtcwake = False
+ else:
+ sysvals.rtcwake = True
+ sysvals.rtcwaketime = getArgInt('-rtcwake', value, 0, 3600, False)
elif(opt.lower() == 'timeprec'):
sysvals.setPrecision(getArgInt('-timeprec', value, 0, 6, False))
elif(opt.lower() == 'mindev'):
modes = getModes()
print('')
- print('AnalyzeSuspend v%s' % sysvals.version)
- print('Usage: sudo analyze_suspend.py <options>')
+ print('%s v%s' % (sysvals.title, sysvals.version))
+ print('Usage: sudo sleepgraph <options> <commands>')
print('')
print('Description:')
print(' This tool is designed to assist kernel and OS developers in optimizing')
print(' a detailed view of which devices/subsystems are taking the most')
print(' time in suspend/resume.')
print('')
+ print(' If no specific command is given, the default behavior is to initiate')
+ print(' a suspend/resume and capture the dmesg/ftrace output as an html timeline.')
+ print('')
print(' Generates output files in subdirectory: suspend-mmddyy-HHMMSS')
print(' HTML output: <hostname>_<mode>.html')
print(' raw dmesg output: <hostname>_<mode>_dmesg.txt')
print(' raw ftrace output: <hostname>_<mode>_ftrace.txt')
print('')
print('Options:')
- print(' [general]')
print(' -h Print this help text')
print(' -v Print the current tool version')
print(' -config fn Pull arguments and config options from file fn')
print(' -verbose Print extra information during execution and analysis')
- print(' -status Test to see if the system is enabled to run this tool')
- print(' -modes List available suspend modes')
print(' -m mode Mode to initiate for suspend %s (default: %s)') % (modes, sysvals.suspendmode)
print(' -o subdir Override the output subdirectory')
- print(' -rtcwake t Use rtcwake to autoresume after <t> seconds (default: disabled)')
+ print(' -rtcwake t Wakeup t seconds after suspend, set t to "off" to disable (default: 15)')
print(' -addlogs Add the dmesg and ftrace logs to the html output')
print(' -srgap Add a visible gap in the timeline between sus/res (default: disabled)')
print(' [advanced]')
print(' be created in a new subdirectory with a summary page.')
print(' [debug]')
print(' -f Use ftrace to create device callgraphs (default: disabled)')
+ print(' -maxdepth N limit the callgraph data to N call levels (default: 0=all)')
print(' -expandcg pre-expand the callgraph data in the html output (default: disabled)')
- print(' -flist Print the list of functions currently being captured in ftrace')
- print(' -flistall Print all functions capable of being captured in ftrace')
print(' -fadd file Add functions to be graphed in the timeline from a list in a text file')
print(' -filter "d1,d2,..." Filter out all but this comma-delimited list of device names')
print(' -mincg ms Discard all callgraphs shorter than ms milliseconds (e.g. 0.001 for us)')
print(' -cgphase P Only show callgraph data for phase P (e.g. suspend_late)')
print(' -cgtest N Only show callgraph data for test N (e.g. 0 or 1 in an x2 run)')
print(' -timeprec N Number of significant digits in timestamps (0:S, [3:ms], 6:us)')
- print(' [utilities]')
+ print(' [commands]')
+ print(' -ftrace ftracefile Create HTML output using ftrace input (used with -dmesg)')
+ print(' -dmesg dmesgfile Create HTML output using dmesg (used with -ftrace)')
+ print(' -summary directory Create a summary of all test in this dir')
+ print(' -modes List available suspend modes')
+ print(' -status Test to see if the system is enabled to run this tool')
print(' -fpdt Print out the contents of the ACPI Firmware Performance Data Table')
print(' -usbtopo Print out the current USB topology with power info')
print(' -usbauto Enable autosuspend for all connected USB devices')
- print(' [re-analyze data from previous runs]')
- print(' -ftrace ftracefile Create HTML output using ftrace input')
- print(' -dmesg dmesgfile Create HTML output using dmesg (not needed for kernel >= 3.15)')
- print(' -summary directory Create a summary of all test in this dir')
+ print(' -flist Print the list of functions currently being captured in ftrace')
+ print(' -flistall Print all functions capable of being captured in ftrace')
print('')
return True
sysvals.useprocmon = True
elif(arg == '-dev'):
sysvals.usedevsrc = True
+ elif(arg == '-maxdepth'):
+ sysvals.max_graph_depth = getArgInt('-maxdepth', args, 0, 1000)
elif(arg == '-rtcwake'):
- sysvals.rtcwake = True
- sysvals.rtcwaketime = getArgInt('-rtcwake', args, 0, 3600)
+ try:
+ val = args.next()
+ except:
+ doError('No rtcwake time supplied', True)
+ if val.lower() == 'off':
+ sysvals.rtcwake = False
+ else:
+ sysvals.rtcwake = True
+ sysvals.rtcwaketime = getArgInt('-rtcwake', val, 0, 3600, False)
elif(arg == '-timeprec'):
sysvals.setPrecision(getArgInt('-timeprec', args, 0, 6))
elif(arg == '-mindev'):
elif(cmd == 'usbauto'):
setUSBDevicesAuto()
elif(cmd == 'summary'):
- print("Generating a summary of folder \"%s\"" % cmdarg)
runSummary(cmdarg, True)
sys.exit()
--- /dev/null
+.TH BOOTGRAPH 8
+.SH NAME
+bootgraph \- Kernel boot timing analysis
+.SH SYNOPSIS
+.ft B
+.B bootgraph
+.RB [ OPTIONS ]
+.RB [ COMMAND ]
+.SH DESCRIPTION
+\fBbootgraph \fP reads the dmesg log from kernel boot and
+creates an html representation of the initcall timeline up to the start
+of the init process.
+.PP
+If no specific command is given, the tool reads the current dmesg log and
+outputs bootgraph.html.
+.PP
+The tool can also augment the timeline with ftrace data on custom target
+functions as well as full trace callgraphs.
+.SH OPTIONS
+.TP
+\fB-h\fR
+Print this help text
+.TP
+\fB-v\fR
+Print the current tool version
+.TP
+\fB-addlogs\fR
+Add the dmesg log to the html output. It will be viewable by
+clicking a button in the timeline.
+.TP
+\fB-o \fIfile\fR
+Override the HTML output filename (default: bootgraph.html)
+.SS "Ftrace Debug"
+.TP
+\fB-f\fR
+Use ftrace to add function detail (default: disabled)
+.TP
+\fB-callgraph\fR
+Use ftrace to create initcall callgraphs (default: disabled). If -filter
+is not used there will be one callgraph per initcall. This can produce
+very large outputs, i.e. 10MB - 100MB.
+.TP
+\fB-maxdepth \fIlevel\fR
+limit the callgraph trace depth to \fIlevel\fR (default: 2). This is
+the best way to limit the output size when using -callgraph.
+.TP
+\fB-mincg \fIt\fR
+Discard all callgraphs shorter than \fIt\fR milliseconds (default: 0=all).
+This reduces the html file size as there can be many tiny callgraphs
+which are barely visible in the timeline.
+The value is a float: e.g. 0.001 represents 1 us.
+.TP
+\fB-timeprec \fIn\fR
+Number of significant digits in timestamps (0:S, 3:ms, [6:us])
+.TP
+\fB-expandcg\fR
+pre-expand the callgraph data in the html output (default: disabled)
+.TP
+\fB-filter \fI"func1,func2,..."\fR
+Instead of tracing each initcall, trace a custom list of functions (default: do_one_initcall)
+
+.SH COMMANDS
+.TP
+\fB-reboot\fR
+Reboot the machine and generate a new timeline automatically. Works in 4 steps.
+ 1. updates grub with the required kernel parameters
+ 2. installs a cron job which re-runs the tool after reboot
+ 3. reboots the system
+ 4. after startup, extracts the data and generates the timeline
+.TP
+\fB-manual\fR
+Show the requirements to generate a new timeline manually. Requires 3 steps.
+ 1. append the string to the kernel command line via your native boot manager.
+ 2. reboot the system
+ 3. after startup, re-run the tool with the same arguments and no command
+.TP
+\fB-dmesg \fIfile\fR
+Create HTML output from an existing dmesg file.
+.TP
+\fB-ftrace \fIfile\fR
+Create HTML output from an existing ftrace file (used with -dmesg).
+.TP
+\fB-flistall\fR
+Print all ftrace functions capable of being captured. These are all the
+possible values you can add to trace via the -filter argument.
+
+.SH EXAMPLES
+Create a timeline using the current dmesg log.
+.IP
+\f(CW$ bootgraph\fR
+.PP
+Create a timeline using the current dmesg and ftrace log.
+.IP
+\f(CW$ bootgraph -callgraph\fR
+.PP
+Create a timeline using the current dmesg, add the log to the html and change the name.
+.IP
+\f(CW$ bootgraph -addlogs -o myboot.html\fR
+.PP
+Capture a new boot timeline by automatically rebooting the machine.
+.IP
+\f(CW$ sudo bootgraph -reboot -addlogs -o latestboot.html\fR
+.PP
+Capture a new boot timeline with function trace data.
+.IP
+\f(CW$ sudo bootgraph -reboot -f\fR
+.PP
+Capture a new boot timeline with trace & callgraph data. Skip callgraphs smaller than 5ms.
+.IP
+\f(CW$ sudo bootgraph -reboot -callgraph -mincg 5\fR
+.PP
+Capture a new boot timeline with callgraph data over custom functions.
+.IP
+\f(CW$ sudo bootgraph -reboot -callgraph -filter "acpi_ps_parse_aml,msleep"\fR
+.PP
+Capture a brand new boot timeline with manual reboot.
+.IP
+\f(CW$ sudo bootgraph -callgraph -manual\fR
+.IP
+\f(CW$ vi /etc/default/grub # add the CMDLINE string to your kernel params\fR
+.IP
+\f(CW$ sudo reboot # reboot the machine\fR
+.IP
+\f(CW$ sudo bootgraph -callgraph # re-run the tool after restart\fR
+.PP
+
+.SH "SEE ALSO"
+dmesg(1), update-grub(8), crontab(1), reboot(8)
+.PP
+.SH AUTHOR
+.nf
+Written by Todd Brandt <todd.e.brandt@linux.intel.com>
--- /dev/null
+.TH SLEEPGRAPH 8
+.SH NAME
+sleepgraph \- Suspend/Resume timing analysis
+.SH SYNOPSIS
+.ft B
+.B sleepgraph
+.RB [ OPTIONS ]
+.RB [ COMMAND ]
+.SH DESCRIPTION
+\fBsleepgraph \fP is designed to assist kernel and OS developers
+in optimizing their linux stack's suspend/resume time. Using a kernel
+image built with a few extra options enabled, the tool will execute a
+suspend and capture dmesg and ftrace data until resume is complete.
+This data is transformed into a device timeline and an optional
+callgraph to give a detailed view of which devices/subsystems are
+taking the most time in suspend/resume.
+.PP
+If no specific command is given, the default behavior is to initiate
+a suspend/resume.
+.PP
+Generates output files in subdirectory: suspend-yymmdd-HHMMSS
+ html timeline : <hostname>_<mode>.html
+ raw dmesg file : <hostname>_<mode>_dmesg.txt
+ raw ftrace file : <hostname>_<mode>_ftrace.txt
+.SH OPTIONS
+.TP
+\fB-h\fR
+Print the help text.
+.TP
+\fB-v\fR
+Print the current tool version.
+.TP
+\fB-verbose\fR
+Print extra information during execution and analysis.
+.TP
+\fB-config \fIfile\fR
+Pull arguments and config options from a file.
+.TP
+\fB-m \fImode\fR
+Mode to initiate for suspend e.g. standby, freeze, mem (default: mem).
+.TP
+\fB-o \fIsubdir\fR
+Override the output subdirectory. Use {date}, {time}, {hostname} for current values.
+.sp
+e.g. suspend-{hostname}-{date}-{time}
+.TP
+\fB-rtcwake \fIt\fR | off
+Use rtcwake to autoresume after \fIt\fR seconds (default: 15). Set t to "off" to
+disable rtcwake and require a user keypress to resume.
+.TP
+\fB-addlogs\fR
+Add the dmesg and ftrace logs to the html output. They will be viewable by
+clicking buttons in the timeline.
+
+.SS "Advanced"
+.TP
+\fB-cmd \fIstr\fR
+Run the timeline over a custom suspend command, e.g. pm-suspend. By default
+the tool forces suspend via /sys/power/state so this allows testing over
+an OS's official suspend method. The output file will change to
+hostname_command.html and will autodetect which suspend mode was triggered.
+.TP
+\fB-filter \fI"d1,d2,..."\fR
+Filter out all but these device callbacks. These strings can be device names
+or module names. e.g. 0000:00:02.0, ata5, i915, usb, etc.
+.TP
+\fB-mindev \fIt\fR
+Discard all device callbacks shorter than \fIt\fR milliseconds (default: 0.0).
+This reduces the html file size as there can be many tiny callbacks which are barely
+visible. The value is a float: e.g. 0.001 represents 1 us.
+.TP
+\fB-proc\fR
+Add usermode process info into the timeline (default: disabled).
+.TP
+\fB-dev\fR
+Add kernel source calls and threads to the timeline (default: disabled).
+.TP
+\fB-x2\fR
+Run two suspend/resumes back to back (default: disabled).
+.TP
+\fB-x2delay \fIt\fR
+Include \fIt\fR ms delay between multiple test runs (default: 0 ms).
+.TP
+\fB-predelay \fIt\fR
+Include \fIt\fR ms delay before 1st suspend (default: 0 ms).
+.TP
+\fB-postdelay \fIt\fR
+Include \fIt\fR ms delay after last resume (default: 0 ms).
+.TP
+\fB-multi \fIn d\fR
+Execute \fIn\fR consecutive tests at \fId\fR seconds intervals. The outputs will
+be created in a new subdirectory with a summary page: suspend-xN-{date}-{time}.
+
+.SS "Ftrace Debug"
+.TP
+\fB-f\fR
+Use ftrace to create device callgraphs (default: disabled). This can produce
+very large outputs, i.e. 10MB - 100MB.
+.TP
+\fB-maxdepth \fIlevel\fR
+limit the callgraph trace depth to \fIlevel\fR (default: 0=all). This is
+the best way to limit the output size when using callgraphs via -f.
+.TP
+\fB-expandcg\fR
+pre-expand the callgraph data in the html output (default: disabled)
+.TP
+\fB-fadd \fIfile\fR
+Add functions to be graphed in the timeline from a list in a text file
+.TP
+\fB-mincg \fIt\fR
+Discard all callgraphs shorter than \fIt\fR milliseconds (default: 0.0).
+This reduces the html file size as there can be many tiny callgraphs
+which are barely visible in the timeline.
+The value is a float: e.g. 0.001 represents 1 us.
+.TP
+\fB-cgphase \fIp\fR
+Only show callgraph data for phase \fIp\fR (e.g. suspend_late).
+.TP
+\fB-cgtest \fIn\fR
+In an x2 run, only show callgraph data for test \fIn\fR (e.g. 0 or 1).
+.TP
+\fB-timeprec \fIn\fR
+Number of significant digits in timestamps (0:S, [3:ms], 6:us).
+
+.SH COMMANDS
+.TP
+\fB-ftrace \fIfile\fR
+Create HTML output from an existing ftrace file.
+.TP
+\fB-dmesg \fIfile\fR
+Create HTML output from an existing dmesg file.
+.TP
+\fB-summary \fIindir\fR
+Create a summary page of all tests in \fIindir\fR. Creates summary.html
+in the current folder. The output page is a table of tests with
+suspend and resume values sorted by suspend mode, host, and kernel.
+Includes test averages by mode and links to the test html files.
+.TP
+\fB-modes\fR
+List available suspend modes.
+.TP
+\fB-status\fR
+Test to see if the system is able to run this tool. Use this along
+with any options you intend to use to see if they will work.
+.TP
+\fB-fpdt\fR
+Print out the contents of the ACPI Firmware Performance Data Table.
+.TP
+\fB-usbtopo\fR
+Print out the current USB topology with power info.
+.TP
+\fB-usbauto\fR
+Enable autosuspend for all connected USB devices.
+.TP
+\fB-flist\fR
+Print the list of ftrace functions currently being captured. Functions
+that are not available as symbols in the current kernel are shown in red.
+By default, the tool traces a list of important suspend/resume functions
+in order to better fill out the timeline. If the user has added their own
+with -fadd they will also be checked.
+.TP
+\fB-flistall\fR
+Print all ftrace functions capable of being captured. These are all the
+possible values you can add to trace via the -fadd argument.
+
+.SH EXAMPLES
+.SS "Simple Commands"
+Check which suspend modes are currently supported.
+.IP
+\f(CW$ sleepgraph -modes\fR
+.PP
+Read the Firmware Performance Data Table (FPDT)
+.IP
+\f(CW$ sudo sleepgraph -fpdt\fR
+.PP
+Print out the current USB power topology
+.IP
+\f(CW$ sleepgraph -usbtopo
+.PP
+Verify that you can run a command with a set of arguments
+.IP
+\f(CW$ sudo sleepgraph -f -rtcwake 30 -status
+.PP
+Generate a summary of all timelines in a particular folder.
+.IP
+\f(CW$ sleepgraph -summary ~/workspace/myresults/\fR
+.PP
+Re-generate the html output from a previous run's dmesg and ftrace log.
+.IP
+\f(CW$ sleepgraph -dmesg myhost_mem_dmesg.txt -ftrace myhost_mem_ftrace.txt\fR
+.PP
+
+.SS "Capturing Simple Timelines"
+Execute a mem suspend with a 15 second wakeup. Include the logs in the html.
+.IP
+\f(CW$ sudo sleepgraph -rtcwake 15 -addlogs\fR
+.PP
+Execute a standby with a 15 second wakeup. Change the output folder name.
+.IP
+\f(CW$ sudo sleepgraph -m standby -rtcwake 15 -o "standby-{hostname}-{date}-{time}"\fR
+.PP
+Execute a freeze with no wakeup (require keypress). Change output folder name.
+.IP
+\f(CW$ sudo sleepgraph -m freeze -rtcwake off -o "freeze-{hostname}-{date}-{time}"\fR
+.PP
+
+.SS "Capturing Advanced Timelines"
+Execute a suspend & include dev mode source calls, limit callbacks to 5ms or larger.
+.IP
+\f(CW$ sudo sleepgraph -m mem -rtcwake 15 -dev -mindev 5\fR
+.PP
+Run two suspends back to back, include a 500ms delay before, after, and in between runs.
+.IP
+\f(CW$ sudo sleepgraph -m mem -rtcwake 15 -x2 -predelay 500 -x2delay 500 -postdelay 500\fR
+.PP
+Do a batch run of 10 freezes with 30 seconds delay between runs.
+.IP
+\f(CW$ sudo sleepgraph -m freeze -rtcwake 15 -multi 10 30\fR
+.PP
+Execute a suspend using a custom command.
+.IP
+\f(CW$ sudo sleepgraph -cmd "echo mem > /sys/power/state" -rtcwake 15\fR
+.PP
+
+
+.SS "Capturing Timelines with Callgraph Data"
+Add device callgraphs. Limit the trace depth and only show callgraphs 10ms or larger.
+.IP
+\f(CW$ sudo sleepgraph -m mem -rtcwake 15 -f -maxdepth 5 -mincg 10\fR
+.PP
+Capture a full callgraph across all suspend, then filter the html by a single phase.
+.IP
+\f(CW$ sudo sleepgraph -m mem -rtcwake 15 -f\fR
+.IP
+\f(CW$ sleepgraph -dmesg host_mem_dmesg.txt -ftrace host_mem_ftrace.txt -f -cgphase resume
+.PP
+
+.SH "SEE ALSO"
+dmesg(1)
+.PP
+.SH AUTHOR
+.nf
+Written by Todd Brandt <todd.e.brandt@linux.intel.com>
os.system('grep -m 1 common_cpu cpu.csv > cpu{:0>3}.csv'.format(index))
os.system('grep CPU_{:0>3} cpu.csv >> cpu{:0>3}.csv'.format(index, index))
+def fix_ownership(path):
+ """Change the owner of the file to SUDO_UID, if required"""
+
+ uid = os.environ.get('SUDO_UID')
+ gid = os.environ.get('SUDO_GID')
+ if uid is not None:
+ os.chown(path, int(uid), int(gid))
+
def cleanup_data_files():
""" clean up existing data files """
if not os.path.exists('results'):
os.mkdir('results')
+ # The regular user needs to own the directory, not root.
+ fix_ownership('results')
os.chdir('results')
if os.path.exists(testname):
print('The test name directory already exists. Please provide a unique test name. Test re-run not supported, yet.')
sys.exit()
os.mkdir(testname)
+# The regular user needs to own the directory, not root.
+fix_ownership(testname)
os.chdir(testname)
# Temporary (or perhaps not)
plot_boost_cpu()
plot_ghz_cpu()
+# It is preferrable, but not necessary, that the regular user owns the files, not root.
+for root, dirs, files in os.walk('.'):
+ for f in files:
+ fix_ownership(f)
+
os.chdir('../../')
\fBCPU%c1, CPU%c3, CPU%c6, CPU%c7\fP show the percentage residency in hardware core idle states. These numbers are from hardware residency counters.
\fBCoreTmp\fP Degrees Celsius reported by the per-core Digital Thermal Sensor.
\fBPkgTtmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor.
+\fBGFX%rc6\fP The percentage of time the GPU is in the "render C6" state, rc6, during the measurement interval. From /sys/class/drm/card0/power/rc6_residency_ms.
+\fBGFXMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz.
\fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states. These numbers are from hardware residency counters.
\fBPkgWatt\fP Watts consumed by the whole package.
\fBCorWatt\fP Watts consumed by the core part of the package.
* it is possible for mperf's non-halted cycles + idle states
* to exceed TSC's all cycles: show c1 = 0% in that case.
*/
- if ((old->mperf + core_delta->c3 + core_delta->c6 + core_delta->c7) > old->tsc)
+ if ((old->mperf + core_delta->c3 + core_delta->c6 + core_delta->c7) > (old->tsc * tsc_tweak))
old->c1 = 0;
else {
/* normal case, derive c1 */
if (fp == NULL)
fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", "r");
- else
+ else {
rewind(fp);
+ fflush(fp);
+ }
retval = fscanf(fp, "%d", &gfx_cur_mhz);
if (retval != 1)
return 0;
fprintf(outf, "cpu%d: MSR_HWP_CAPABILITIES: 0x%08llx "
- "(high 0x%x guar 0x%x eff 0x%x low 0x%x)\n",
+ "(high %d guar %d eff %d low %d)\n",
cpu, msr,
(unsigned int)HWP_HIGHEST_PERF(msr),
(unsigned int)HWP_GUARANTEED_PERF(msr),
return 0;
fprintf(outf, "cpu%d: MSR_HWP_REQUEST: 0x%08llx "
- "(min 0x%x max 0x%x des 0x%x epp 0x%x window 0x%x pkg 0x%x)\n",
+ "(min %d max %d des %d epp 0x%x window 0x%x pkg 0x%x)\n",
cpu, msr,
(unsigned int)(((msr) >> 0) & 0xff),
(unsigned int)(((msr) >> 8) & 0xff),
return 0;
fprintf(outf, "cpu%d: MSR_HWP_REQUEST_PKG: 0x%08llx "
- "(min 0x%x max 0x%x des 0x%x epp 0x%x window 0x%x)\n",
+ "(min %d max %d des %d epp 0x%x window 0x%x)\n",
cpu, msr,
(unsigned int)(((msr) >> 0) & 0xff),
(unsigned int)(((msr) >> 8) & 0xff),
case INTEL_FAM6_SKYLAKE_DESKTOP: /* SKL */
case INTEL_FAM6_KABYLAKE_MOBILE: /* KBL */
case INTEL_FAM6_KABYLAKE_DESKTOP: /* KBL */
- do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
+ do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_GFX | RAPL_PKG_POWER_INFO;
BIC_PRESENT(BIC_PKG__);
BIC_PRESENT(BIC_RAM__);
if (rapl_joules) {
BIC_PRESENT(BIC_Pkg_J);
BIC_PRESENT(BIC_Cor_J);
BIC_PRESENT(BIC_RAM_J);
+ BIC_PRESENT(BIC_GFX_J);
} else {
BIC_PRESENT(BIC_PkgWatt);
BIC_PRESENT(BIC_CorWatt);
BIC_PRESENT(BIC_RAMWatt);
+ BIC_PRESENT(BIC_GFXWatt);
}
break;
case INTEL_FAM6_HASWELL_X: /* HSX */
int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p)
{
unsigned long long msr;
- unsigned int dts;
+ unsigned int dts, dts2;
int cpu;
if (!(do_dts || do_ptm))
fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_STATUS: 0x%08llx (%d C)\n",
cpu, msr, tcc_activation_temp - dts);
-#ifdef THERM_DEBUG
if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, &msr))
return 0;
dts2 = (msr >> 8) & 0x7F;
fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n",
cpu, msr, tcc_activation_temp - dts, tcc_activation_temp - dts2);
-#endif
}
- if (do_dts) {
+ if (do_dts && debug) {
unsigned int resolution;
if (get_msr(cpu, MSR_IA32_THERM_STATUS, &msr))
fprintf(outf, "cpu%d: MSR_IA32_THERM_STATUS: 0x%08llx (%d C +/- %d)\n",
cpu, msr, tcc_activation_temp - dts, resolution);
-#ifdef THERM_DEBUG
if (get_msr(cpu, MSR_IA32_THERM_INTERRUPT, &msr))
return 0;
dts2 = (msr >> 8) & 0x7F;
fprintf(outf, "cpu%d: MSR_IA32_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n",
cpu, msr, tcc_activation_temp - dts, tcc_activation_temp - dts2);
-#endif
}
return 0;
}
void print_version() {
- fprintf(outf, "turbostat version 17.02.24"
+ fprintf(outf, "turbostat version 17.04.12"
" - Len Brown <lenb@kernel.org>\n");
}
EXTRA_WARNINGS += -Wstrict-aliasing=3
endif
+# Hack to avoid type-punned warnings on old systems such as RHEL5:
+# We should be changing CFLAGS and checking gcc version, but this
+# will do for now and keep the above -Wstrict-aliasing=3 in place
+# in newer systems.
+# Needed for the __raw_cmpxchg in tools/arch/x86/include/asm/cmpxchg.h
+ifneq ($(filter 3.%,$(MAKE_VERSION)),) # make-3
+EXTRA_WARNINGS += -fno-strict-aliasing
+endif
+
ifneq ($(findstring $(MAKEFLAGS), w),w)
PRINT_DIR = --no-print-directory
else
LIBDIR := ../../../lib
BPFDIR := $(LIBDIR)/bpf
+APIDIR := ../../../include/uapi
+GENDIR := ../../../../include/generated
+GENHDR := $(GENDIR)/autoconf.h
-CFLAGS += -Wall -O2 -I../../../include/uapi -I$(LIBDIR)
+ifneq ($(wildcard $(GENHDR)),)
+ GENFLAGS := -DHAVE_GENHDR
+endif
+
+CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS)
LDLIBS += -lcap
TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map
{
unsigned int nr_cpus = bpf_num_possible_cpus();
int key, next_key, fd, i;
- long values[nr_cpus];
+ long long values[nr_cpus];
fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key),
sizeof(values[0]), 2, 0);
* allocator more than anything else
*/
unsigned int nr_keys = 2000;
- long values[nr_cpus];
+ long long values[nr_cpus];
int key, fd, i;
fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key),
#include <bpf/bpf.h>
+#ifdef HAVE_GENHDR
+# include "autoconf.h"
+#else
+# if defined(__i386) || defined(__x86_64) || defined(__s390x__) || defined(__aarch64__)
+# define CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS 1
+# endif
+#endif
+
#include "../../../include/linux/filter.h"
#ifndef ARRAY_SIZE
#define MAX_INSNS 512
#define MAX_FIXUPS 8
+#define F_NEEDS_EFFICIENT_UNALIGNED_ACCESS (1 << 0)
+
struct bpf_test {
const char *descr;
struct bpf_insn insns[MAX_INSNS];
REJECT
} result, result_unpriv;
enum bpf_prog_type prog_type;
+ uint8_t flags;
};
/* Note we want this to be 64 bit aligned so that the end of our array is
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
},
{
+ "direct packet access: test15 (spill with xadd)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct __sk_buff, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ offsetof(struct __sk_buff, data_end)),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+ BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 8),
+ BPF_MOV64_IMM(BPF_REG_5, 4096),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+ BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+ BPF_STX_XADD(BPF_DW, BPF_REG_4, BPF_REG_5, 0),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_4, 0),
+ BPF_STX_MEM(BPF_W, BPF_REG_2, BPF_REG_5, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R2 invalid mem access 'inv'",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ },
+ {
"helper access to packet: test1, valid packet_ptr range",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
.errstr_unpriv = "R0 pointer arithmetic prohibited",
.result_unpriv = REJECT,
.result = ACCEPT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"valid map access into an array with a variable",
.errstr_unpriv = "R0 pointer arithmetic prohibited",
.result_unpriv = REJECT,
.result = ACCEPT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"valid map access into an array with a signed variable",
.errstr_unpriv = "R0 pointer arithmetic prohibited",
.result_unpriv = REJECT,
.result = ACCEPT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"invalid map access into an array with a constant",
.errstr = "R0 min value is outside of the array range",
.result_unpriv = REJECT,
.result = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"invalid map access into an array with a variable",
.errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
.result_unpriv = REJECT,
.result = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"invalid map access into an array with no floor check",
.errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
.result_unpriv = REJECT,
.result = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"invalid map access into an array with a invalid max check",
.errstr = "invalid access to map value, value_size=48 off=44 size=8",
.result_unpriv = REJECT,
.result = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"invalid map access into an array with a invalid max check",
.errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
.result_unpriv = REJECT,
.result = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"multiple registers share map_lookup_elem result",
.result = REJECT,
.errstr_unpriv = "R0 pointer arithmetic prohibited",
.result_unpriv = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"constant register |= constant should keep constant type",
.prog_type = BPF_PROG_TYPE_LWT_XMIT,
},
{
+ "overlapping checks for direct packet access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct __sk_buff, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ offsetof(struct __sk_buff, data_end)),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+ BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 4),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
+ BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+ BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_2, 6),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_LWT_XMIT,
+ },
+ {
"invalid access of tc_classid for LWT_IN",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
.result_unpriv = REJECT,
},
{
- "map element value (adjusted) is preserved across register spilling",
+ "map element value or null is marked on register spilling",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -152),
+ BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_1, 0),
+ BPF_ST_MEM(BPF_DW, BPF_REG_3, 0, 42),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 3 },
+ .errstr_unpriv = "R0 leaks addr",
+ .result = ACCEPT,
+ .result_unpriv = REJECT,
+ },
+ {
+ "map element value store of cleared call register",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 3 },
+ .errstr_unpriv = "R1 !read_ok",
+ .errstr = "R1 !read_ok",
+ .result = REJECT,
+ .result_unpriv = REJECT,
+ },
+ {
+ "map element value with unaligned store",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 17),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 3),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 42),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 2, 43),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, -2, 44),
+ BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
+ BPF_ST_MEM(BPF_DW, BPF_REG_8, 0, 32),
+ BPF_ST_MEM(BPF_DW, BPF_REG_8, 2, 33),
+ BPF_ST_MEM(BPF_DW, BPF_REG_8, -2, 34),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_8, 5),
+ BPF_ST_MEM(BPF_DW, BPF_REG_8, 0, 22),
+ BPF_ST_MEM(BPF_DW, BPF_REG_8, 4, 23),
+ BPF_ST_MEM(BPF_DW, BPF_REG_8, -7, 24),
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_8),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 3),
+ BPF_ST_MEM(BPF_DW, BPF_REG_7, 0, 22),
+ BPF_ST_MEM(BPF_DW, BPF_REG_7, 4, 23),
+ BPF_ST_MEM(BPF_DW, BPF_REG_7, -4, 24),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 3 },
+ .errstr_unpriv = "R0 pointer arithmetic prohibited",
+ .result = ACCEPT,
+ .result_unpriv = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+ },
+ {
+ "map element value with unaligned load",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
+ BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JGE, BPF_REG_1, MAX_ENTRIES, 9),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 3),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 2),
+ BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_8, 0),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_8, 2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 5),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 4),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 3 },
+ .errstr_unpriv = "R0 pointer arithmetic prohibited",
+ .result = ACCEPT,
+ .result_unpriv = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+ },
+ {
+ "map element value illegal alu op, 1",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 3 },
+ .errstr_unpriv = "R0 pointer arithmetic prohibited",
+ .errstr = "invalid mem access 'inv'",
+ .result = REJECT,
+ .result_unpriv = REJECT,
+ },
+ {
+ "map element value illegal alu op, 2",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_ALU32_IMM(BPF_ADD, BPF_REG_0, 0),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 3 },
+ .errstr_unpriv = "R0 pointer arithmetic prohibited",
+ .errstr = "invalid mem access 'inv'",
+ .result = REJECT,
+ .result_unpriv = REJECT,
+ },
+ {
+ "map element value illegal alu op, 3",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_ALU64_IMM(BPF_DIV, BPF_REG_0, 42),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 3 },
+ .errstr_unpriv = "R0 pointer arithmetic prohibited",
+ .errstr = "invalid mem access 'inv'",
+ .result = REJECT,
+ .result_unpriv = REJECT,
+ },
+ {
+ "map element value illegal alu op, 4",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_ENDIAN(BPF_FROM_BE, BPF_REG_0, 64),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 3 },
+ .errstr_unpriv = "R0 pointer arithmetic prohibited",
+ .errstr = "invalid mem access 'inv'",
+ .result = REJECT,
+ .result_unpriv = REJECT,
+ },
+ {
+ "map element value illegal alu op, 5",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+ BPF_MOV64_IMM(BPF_REG_3, 4096),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
+ BPF_STX_XADD(BPF_DW, BPF_REG_2, BPF_REG_3, 0),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 0),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 3 },
+ .errstr_unpriv = "R0 invalid mem access 'inv'",
+ .errstr = "R0 invalid mem access 'inv'",
+ .result = REJECT,
+ .result_unpriv = REJECT,
+ },
+ {
+ "map element value is preserved across register spilling",
.insns = {
BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
.errstr_unpriv = "R0 pointer arithmetic prohibited",
.result = ACCEPT,
.result_unpriv = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"helper access to variable memory: stack, bitwise AND + JMP, correct bounds",
.errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
.result = REJECT,
.result_unpriv = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"invalid range check",
.errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
.result = REJECT,
.result_unpriv = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
}
};
static void do_test_single(struct bpf_test *test, bool unpriv,
int *passes, int *errors)
{
+ int fd_prog, expected_ret, reject_from_alignment;
struct bpf_insn *prog = test->insns;
int prog_len = probe_filter_length(prog);
int prog_type = test->prog_type;
int fd_f1 = -1, fd_f2 = -1, fd_f3 = -1;
- int fd_prog, expected_ret;
const char *expected_err;
do_test_fixup(test, prog, &fd_f1, &fd_f2, &fd_f3);
test->result_unpriv : test->result;
expected_err = unpriv && test->errstr_unpriv ?
test->errstr_unpriv : test->errstr;
+
+ reject_from_alignment = fd_prog < 0 &&
+ (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS) &&
+ strstr(bpf_vlog, "Unknown alignment.");
+#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+ if (reject_from_alignment) {
+ printf("FAIL\nFailed due to alignment despite having efficient unaligned access: '%s'!\n",
+ strerror(errno));
+ goto fail_log;
+ }
+#endif
if (expected_ret == ACCEPT) {
- if (fd_prog < 0) {
+ if (fd_prog < 0 && !reject_from_alignment) {
printf("FAIL\nFailed to load prog '%s'!\n",
strerror(errno));
goto fail_log;
printf("FAIL\nUnexpected success to load!\n");
goto fail_log;
}
- if (!strstr(bpf_vlog, expected_err)) {
+ if (!strstr(bpf_vlog, expected_err) && !reject_from_alignment) {
printf("FAIL\nUnexpected error message!\n");
goto fail_log;
}
}
(*passes)++;
- printf("OK\n");
+ printf("OK%s\n", reject_from_alignment ?
+ " (NOTE: reject due to unknown alignment)" : "");
close_fds:
close(fd_prog);
close(fd_f1);
--- /dev/null
+#!/bin/sh
+# description: ftrace - function pid filters
+
+# Make sure that function pid matching filter works.
+# Also test it on an instance directory
+
+if ! grep -q function available_tracers; then
+ echo "no function tracer configured"
+ exit_unsupported
+fi
+
+if [ ! -f set_ftrace_pid ]; then
+ echo "set_ftrace_pid not found? Is function tracer not set?"
+ exit_unsupported
+fi
+
+if [ ! -f set_ftrace_filter ]; then
+ echo "set_ftrace_filter not found? Is function tracer not set?"
+ exit_unsupported
+fi
+
+do_function_fork=1
+
+if [ ! -f options/function-fork ]; then
+ do_function_fork=0
+ echo "no option for function-fork found. Option will not be tested."
+fi
+
+read PID _ < /proc/self/stat
+
+if [ $do_function_fork -eq 1 ]; then
+ # default value of function-fork option
+ orig_value=`grep function-fork trace_options`
+fi
+
+do_reset() {
+ reset_tracer
+ clear_trace
+ enable_tracing
+ echo > set_ftrace_filter
+ echo > set_ftrace_pid
+
+ if [ $do_function_fork -eq 0 ]; then
+ return
+ fi
+
+ echo $orig_value > trace_options
+}
+
+fail() { # msg
+ do_reset
+ echo $1
+ exit $FAIL
+}
+
+yield() {
+ ping localhost -c 1 || sleep .001 || usleep 1 || sleep 1
+}
+
+do_test() {
+ disable_tracing
+
+ echo do_execve* > set_ftrace_filter
+ echo *do_fork >> set_ftrace_filter
+
+ echo $PID > set_ftrace_pid
+ echo function > current_tracer
+
+ if [ $do_function_fork -eq 1 ]; then
+ # don't allow children to be traced
+ echo nofunction-fork > trace_options
+ fi
+
+ enable_tracing
+ yield
+
+ count_pid=`cat trace | grep -v ^# | grep $PID | wc -l`
+ count_other=`cat trace | grep -v ^# | grep -v $PID | wc -l`
+
+ # count_other should be 0
+ if [ $count_pid -eq 0 -o $count_other -ne 0 ]; then
+ fail "PID filtering not working?"
+ fi
+
+ disable_tracing
+ clear_trace
+
+ if [ $do_function_fork -eq 0 ]; then
+ return
+ fi
+
+ # allow children to be traced
+ echo function-fork > trace_options
+
+ enable_tracing
+ yield
+
+ count_pid=`cat trace | grep -v ^# | grep $PID | wc -l`
+ count_other=`cat trace | grep -v ^# | grep -v $PID | wc -l`
+
+ # count_other should NOT be 0
+ if [ $count_pid -eq 0 -o $count_other -eq 0 ]; then
+ fail "PID filtering not following fork?"
+ fi
+}
+
+do_test
+
+mkdir instances/foo
+cd instances/foo
+do_test
+cd ../../
+rmdir instances/foo
+
+do_reset
+
+exit 0
{
int fd, val;
- fd = socket(PF_PACKET, SOCK_DGRAM, htons(ETH_P_IP));
+ fd = socket(PF_PACKET, SOCK_RAW, htons(ETH_P_IP));
if (fd < 0) {
perror("socket packet");
exit(1);
return fd;
}
+static void sock_fanout_set_cbpf(int fd)
+{
+ struct sock_filter bpf_filter[] = {
+ BPF_STMT(BPF_LD+BPF_B+BPF_ABS, 80), /* ldb [80] */
+ BPF_STMT(BPF_RET+BPF_A, 0), /* ret A */
+ };
+ struct sock_fprog bpf_prog;
+
+ bpf_prog.filter = bpf_filter;
+ bpf_prog.len = sizeof(bpf_filter) / sizeof(struct sock_filter);
+
+ if (setsockopt(fd, SOL_PACKET, PACKET_FANOUT_DATA, &bpf_prog,
+ sizeof(bpf_prog))) {
+ perror("fanout data cbpf");
+ exit(1);
+ }
+}
+
static void sock_fanout_set_ebpf(int fd)
{
const int len_off = __builtin_offsetof(struct __sk_buff, len);
exit(1);
}
if (type == PACKET_FANOUT_CBPF)
- sock_setfilter(fds[0], SOL_PACKET, PACKET_FANOUT_DATA);
+ sock_fanout_set_cbpf(fds[0]);
else if (type == PACKET_FANOUT_EBPF)
sock_fanout_set_ebpf(fds[0]);
# define __maybe_unused __attribute__ ((__unused__))
#endif
-static __maybe_unused void sock_setfilter(int fd, int lvl, int optnum)
+static __maybe_unused void pair_udp_setfilter(int fd)
{
/* the filter below checks for all of the following conditions that
* are based on the contents of create_payload()
};
struct sock_fprog bpf_prog;
- if (lvl == SOL_PACKET && optnum == PACKET_FANOUT_DATA)
- bpf_filter[5].code = 0x16; /* RET A */
-
bpf_prog.filter = bpf_filter;
bpf_prog.len = sizeof(bpf_filter) / sizeof(struct sock_filter);
- if (setsockopt(fd, lvl, optnum, &bpf_prog,
+
+ if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &bpf_prog,
sizeof(bpf_prog))) {
perror("setsockopt SO_ATTACH_FILTER");
exit(1);
}
}
-static __maybe_unused void pair_udp_setfilter(int fd)
-{
- sock_setfilter(fd, SOL_SOCKET, SO_ATTACH_FILTER);
-}
-
static __maybe_unused void pair_udp_open(int fds[], uint16_t port)
{
struct sockaddr_in saddr, daddr;
all: $(SUB_DIRS)
$(SUB_DIRS):
- BUILD_TARGET=$$OUTPUT/$@; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $@ all
+ BUILD_TARGET=$(OUTPUT)/$@; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $@ all
include ../lib.mk
override define RUN_TESTS
@for TARGET in $(SUB_DIRS); do \
- BUILD_TARGET=$$OUTPUT/$$TARGET; \
+ BUILD_TARGET=$(OUTPUT)/$$TARGET; \
$(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests;\
done;
endef
override define INSTALL_RULE
@for TARGET in $(SUB_DIRS); do \
- BUILD_TARGET=$$OUTPUT/$$TARGET; \
+ BUILD_TARGET=$(OUTPUT)/$$TARGET; \
$(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install;\
done;
endef
override define EMIT_TESTS
@for TARGET in $(SUB_DIRS); do \
- BUILD_TARGET=$$OUTPUT/$$TARGET; \
+ BUILD_TARGET=$(OUTPUT)/$$TARGET; \
$(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests;\
done;
endef
clean:
@for TARGET in $(SUB_DIRS); do \
- BUILD_TARGET=$$OUTPUT/$$TARGET; \
+ BUILD_TARGET=$(OUTPUT)/$$TARGET; \
$(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean; \
done;
rm -f tags
}
/**
+ * kvm_vgic_init_cpu_hardware - initialize the GIC VE hardware
+ *
+ * For a specific CPU, initialize the GIC VE hardware.
+ */
+void kvm_vgic_init_cpu_hardware(void)
+{
+ BUG_ON(preemptible());
+
+ /*
+ * We want to make sure the list registers start out clear so that we
+ * only have the program the used registers.
+ */
+ if (kvm_vgic_global_state.type == VGIC_V2)
+ vgic_v2_init_lrs();
+ else
+ kvm_call_hyp(__vgic_v3_init_lrs);
+}
+
+/**
* kvm_vgic_hyp_init: populates the kvm_vgic_global_state variable
* according to the host GIC model. Accordingly calls either
* vgic_v2/v3_probe which registers the KVM_DEVICE that can be
val = vmcr.ctlr;
break;
case GIC_CPU_PRIMASK:
- val = vmcr.pmr;
+ /*
+ * Our KVM_DEV_TYPE_ARM_VGIC_V2 device ABI exports the
+ * the PMR field as GICH_VMCR.VMPriMask rather than
+ * GICC_PMR.Priority, so we expose the upper five bits of
+ * priority mask to userspace using the lower bits in the
+ * unsigned long.
+ */
+ val = (vmcr.pmr & GICV_PMR_PRIORITY_MASK) >>
+ GICV_PMR_PRIORITY_SHIFT;
break;
case GIC_CPU_BINPOINT:
val = vmcr.bpr;
vmcr.ctlr = val;
break;
case GIC_CPU_PRIMASK:
- vmcr.pmr = val;
+ /*
+ * Our KVM_DEV_TYPE_ARM_VGIC_V2 device ABI exports the
+ * the PMR field as GICH_VMCR.VMPriMask rather than
+ * GICC_PMR.Priority, so we expose the upper five bits of
+ * priority mask to userspace using the lower bits in the
+ * unsigned long.
+ */
+ vmcr.pmr = (val << GICV_PMR_PRIORITY_SHIFT) &
+ GICV_PMR_PRIORITY_MASK;
break;
case GIC_CPU_BINPOINT:
vmcr.bpr = val;
return (unsigned long *)val;
}
+static inline void vgic_v2_write_lr(int lr, u32 val)
+{
+ void __iomem *base = kvm_vgic_global_state.vctrl_base;
+
+ writel_relaxed(val, base + GICH_LR0 + (lr * 4));
+}
+
+void vgic_v2_init_lrs(void)
+{
+ int i;
+
+ for (i = 0; i < kvm_vgic_global_state.nr_lr; i++)
+ vgic_v2_write_lr(i, 0);
+}
+
void vgic_v2_process_maintenance(struct kvm_vcpu *vcpu)
{
struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2;
GICH_VMCR_ALIAS_BINPOINT_MASK;
vmcr |= (vmcrp->bpr << GICH_VMCR_BINPOINT_SHIFT) &
GICH_VMCR_BINPOINT_MASK;
- vmcr |= (vmcrp->pmr << GICH_VMCR_PRIMASK_SHIFT) &
- GICH_VMCR_PRIMASK_MASK;
+ vmcr |= ((vmcrp->pmr >> GICV_PMR_PRIORITY_SHIFT) <<
+ GICH_VMCR_PRIMASK_SHIFT) & GICH_VMCR_PRIMASK_MASK;
vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr = vmcr;
}
GICH_VMCR_ALIAS_BINPOINT_SHIFT;
vmcrp->bpr = (vmcr & GICH_VMCR_BINPOINT_MASK) >>
GICH_VMCR_BINPOINT_SHIFT;
- vmcrp->pmr = (vmcr & GICH_VMCR_PRIMASK_MASK) >>
- GICH_VMCR_PRIMASK_SHIFT;
+ vmcrp->pmr = ((vmcr & GICH_VMCR_PRIMASK_MASK) >>
+ GICH_VMCR_PRIMASK_SHIFT) << GICV_PMR_PRIORITY_SHIFT;
}
void vgic_v2_enable(struct kvm_vcpu *vcpu)
return irq->pending_latch || irq->line_level;
}
+/*
+ * This struct provides an intermediate representation of the fields contained
+ * in the GICH_VMCR and ICH_VMCR registers, such that code exporting the GIC
+ * state to userspace can generate either GICv2 or GICv3 CPU interface
+ * registers regardless of the hardware backed GIC used.
+ */
struct vgic_vmcr {
u32 ctlr;
u32 abpr;
u32 bpr;
- u32 pmr;
+ u32 pmr; /* Priority mask field in the GICC_PMR and
+ * ICC_PMR_EL1 priority field format */
/* Below member variable are valid only for GICv3 */
u32 grpen0;
u32 grpen1;
int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address,
enum vgic_type);
+void vgic_v2_init_lrs(void);
+
static inline void vgic_get_irq_kref(struct vgic_irq *irq)
{
if (irq->intid < VGIC_MIN_LPI)
projects / platform / kernel / linux-exynos.git / commitdiff