What: /sys/kernel/uids/<uid>/cpu_shares
-Date: December 2007
+Date: December 2007, finally removed in kernel v2.6.34-rc1
Contact: Dhaval Giani <dhaval@linux.vnet.ibm.com>
Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Description:
SPHINXBUILD = sphinx-build
SPHINXOPTS =
SPHINXDIRS = .
-_SPHINXDIRS = $(patsubst $(srctree)/Documentation/%/index.rst,%,$(wildcard $(srctree)/Documentation/*/index.rst))
+_SPHINXDIRS = $(sort $(patsubst $(srctree)/Documentation/%/index.rst,%,$(wildcard $(srctree)/Documentation/*/index.rst)))
SPHINX_CONF = conf.py
PAPER =
BUILDDIR = $(obj)/output
as the PCI "bus address" might have been remapped to a "host physical"
address by the arch/chip-set specific kernel support.
-See Documentation/io-mapping.txt for how to access device registers
+See Documentation/driver-api/io-mapping.rst for how to access device registers
or device memory.
The device driver needs to call pci_request_region() to verify
+.. _psi:
+
================================
PSI - Pressure Stall Information
================================
-Kernel Support for miscellaneous (your favourite) Binary Formats v1.1
-=====================================================================
+Kernel Support for miscellaneous Binary Formats (binfmt_misc)
+=============================================================
This Kernel feature allows you to invoke almost (for restrictions see below)
every program by simply typing its name in the shell.
================ =============================================================
orig_data_size uncompressed size of data stored in this disk.
- This excludes same-element-filled pages (same_pages) since
- no memory is allocated for them.
Unit: bytes
compr_data_size compressed size of data stored in this disk
mem_used_total the amount of memory allocated for this disk. This
has to be terminated by semi-colon (``;``) or newline (``\n``).
For array value, array entries are separated by comma (``,``). ::
-KEY[.WORD[...]] = VALUE[, VALUE2[...]][;]
+ KEY[.WORD[...]] = VALUE[, VALUE2[...]][;]
Unlike the kernel command line syntax, spaces are OK around the comma and ``=``.
+.. _cgroup-v1:
+
========================
Control Groups version 1
========================
conventions of cgroup v2. It describes all userland-visible aspects
of cgroup including core and specific controller behaviors. All
future changes must be reflected in this document. Documentation for
-v1 is available under Documentation/admin-guide/cgroup-v1/.
+v1 is available under :ref:`Documentation/admin-guide/cgroup-v1/index.rst <cgroup-v1>`.
.. CONTENTS
A read-only nested-key file which exists on non-root cgroups.
Shows pressure stall information for CPU. See
- Documentation/accounting/psi.rst for details.
+ :ref:`Documentation/accounting/psi.rst <psi>` for details.
cpu.uclamp.min
A read-write single value file which exists on non-root cgroups.
proportionally to the overage, reducing reclaim pressure for
smaller overages.
- Effective min boundary is limited by memory.min values of
+ Effective min boundary is limited by memory.min values of
all ancestor cgroups. If there is memory.min overcommitment
(child cgroup or cgroups are requiring more protected memory
than parent will allow), then each child cgroup will get
Number of major page faults incurred
workingset_refault
-
Number of refaults of previously evicted pages
workingset_activate
-
Number of refaulted pages that were immediately activated
workingset_nodereclaim
-
Number of times a shadow node has been reclaimed
pgrefill
-
Amount of scanned pages (in an active LRU list)
pgscan
-
Amount of scanned pages (in an inactive LRU list)
pgsteal
-
Amount of reclaimed pages
pgactivate
-
Amount of pages moved to the active LRU list
pgdeactivate
-
Amount of pages moved to the inactive LRU list
pglazyfree
-
Amount of pages postponed to be freed under memory pressure
pglazyfreed
-
Amount of reclaimed lazyfree pages
thp_fault_alloc
-
Number of transparent hugepages which were allocated to satisfy
a page fault, including COW faults. This counter is not present
when CONFIG_TRANSPARENT_HUGEPAGE is not set.
thp_collapse_alloc
-
Number of transparent hugepages which were allocated to allow
collapsing an existing range of pages. This counter is not
present when CONFIG_TRANSPARENT_HUGEPAGE is not set.
A read-only nested-key file which exists on non-root cgroups.
Shows pressure stall information for memory. See
- Documentation/accounting/psi.rst for details.
+ :ref:`Documentation/accounting/psi.rst <psi>` for details.
Usage Guidelines
dios Number of discard IOs
====== =====================
- An example read output follows:
+ An example read output follows::
8:16 rbytes=1459200 wbytes=314773504 rios=192 wios=353 dbytes=0 dios=0
8:0 rbytes=90430464 wbytes=299008000 rios=8950 wios=1252 dbytes=50331648 dios=3021
A read-only nested-key file which exists on non-root cgroups.
Shows pressure stall information for IO. See
- Documentation/accounting/psi.rst for details.
+ :ref:`Documentation/accounting/psi.rst <psi>` for details.
Writeback
from the requested CPUs.
The CPU numbers are comma-separated numbers or ranges.
- For example:
+ For example::
# cat cpuset.cpus
0-4,6,8-10
from the requested memory nodes.
The memory node numbers are comma-separated numbers or ranges.
- For example:
+ For example::
# cat cpuset.mems
0-1,3
either correctly working because all components follow the standards -
or the computer is unusable, because the screen remains dark after
booting or it displays the wrong area. Cases when this happens are:
+
- The graphics board does not recognize the monitor.
- The graphics board is unable to detect any EDID data.
- The graphics board incorrectly forwards EDID data to the driver.
- The monitor sends no or bogus EDID data.
- A KVM sends its own EDID data instead of querying the connected monitor.
+
Adding the kernel parameter "nomodeset" helps in most cases, but causes
restrictions later on.
and a Makefile environment are given here.
To create binary EDID and C source code files from the existing data
-material, simply type "make".
+material, simply type "make" in tools/edid/.
If you want to create your own EDID file, copy the file 1024x768.S,
replace the settings with your own data and add a new target to the
The mitigation can be controlled at boot time via a kernel command line option.
See :ref:`taa_mitigation_control_command_line`.
-.. _virt_mechanism:
-
Virtualization mitigation
^^^^^^^^^^^^^^^^^^^^^^^^^
cputopology
dell_rbu
device-mapper/index
+ edid
efi-stub
ext4
nfs/index
Since 5.0 this field counts jiffies when at least one request was
started or completed. If request runs more than 2 jiffies then some
- I/O time will not be accounted unless there are other requests.
+ I/O time might be not accounted in case of concurrent requests.
Field 11 -- weighted # of milliseconds spent doing I/Os (unsigned int)
This field is incremented at each I/O start, I/O completion, I/O
summed to) and the result given to the user. There is no convenient
user interface for accessing the per-CPU counters themselves.
+Since 4.19 request times are measured with nanoseconds precision and
+truncated to milliseconds before showing in this interface.
+
Disks vs Partitions
-------------------
A valid base address must be provided, and the serial
port must already be setup and configured.
+ ec_imx21,<addr>
+ ec_imx6q,<addr>
+ Start an early, polled-mode, output-only console on the
+ Freescale i.MX UART at the specified address. The UART
+ must already be setup and configured.
+
ar3700_uart,<addr>
Start an early, polled-mode console on the
Armada 3700 serial port at the specified
provided by tboot because it makes the system
vulnerable to DMA attacks.
nobounce [Default off]
- Disable bounce buffer for unstrusted devices such as
+ Disable bounce buffer for untrusted devices such as
the Thunderbolt devices. This will treat the untrusted
devices as the trusted ones, hence might expose security
risks of DMA attacks.
No delay
ip= [IP_PNP]
- See Documentation/filesystems/nfs/nfsroot.txt.
+ See Documentation/admin-guide/nfs/nfsroot.rst.
ipcmni_extend [KNL] Extend the maximum number of unique System V
IPC identifiers from 32,768 to 16,777,216.
<name>,<region-number>[,<base>,<size>,<buswidth>,<altbuswidth>]
mtdparts= [MTD]
- See drivers/mtd/cmdlinepart.c.
+ See drivers/mtd/parsers/cmdlinepart.c
multitce=off [PPC] This parameter disables the use of the pSeries
firmware feature for updating multiple TCE entries
Default value is 0.
nfsaddrs= [NFS] Deprecated. Use ip= instead.
- See Documentation/filesystems/nfs/nfsroot.txt.
+ See Documentation/admin-guide/nfs/nfsroot.rst.
nfsroot= [NFS] nfs root filesystem for disk-less boxes.
- See Documentation/filesystems/nfs/nfsroot.txt.
+ See Documentation/admin-guide/nfs/nfsroot.rst.
nfsrootdebug [NFS] enable nfsroot debugging messages.
- See Documentation/filesystems/nfs/nfsroot.txt.
+ See Documentation/admin-guide/nfs/nfsroot.rst.
nfs.callback_nr_threads=
[NFSv4] set the total number of threads that the
Format: <integer>
A nonzero value instructs the soft-lockup detector
- to panic the machine when a soft-lockup occurs. This
- is also controlled by CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC
- which is the respective build-time switch to that
- functionality.
+ to panic the machine when a soft-lockup occurs. It is
+ also controlled by the kernel.softlockup_panic sysctl
+ and CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC, which is the
+ respective build-time switch to that functionality.
softlockup_all_cpu_backtrace=
[KNL] Should the soft-lockup detector generate
Such a workqueue can be confined to a given subset of the
CPUs using the ``/sys/devices/virtual/workqueue/*/cpumask`` sysfs
files. The set of WQ_SYSFS workqueues can be displayed using
- "ls sys/devices/virtual/workqueue". That said, the workqueues
+ "ls /sys/devices/virtual/workqueue". That said, the workqueues
maintainer would like to caution people against indiscriminately
sprinkling WQ_SYSFS across all the workqueues. The reason for
caution is that it is easy to add WQ_SYSFS, but because sysfs is
AXI_ID and AXI_MASKING are mapped on DPCR1 register in performance counter.
When non-masked bits are matching corresponding AXI_ID bits then counter is
- incremented. Perf counter is incremented if
+ incremented. Perf counter is incremented if::
+
AxID && AXI_MASKING == AXI_ID && AXI_MASKING
This filter doesn't support filter different AXI ID for axid-read and axid-write
Documentation for /proc/sys/kernel/
===================================
-kernel version 2.2.10
+.. See scripts/check-sysctl-docs to keep this up to date
+
Copyright (c) 1998, 1999, Rik van Riel <riel@nl.linux.org>
Copyright (c) 2009, Shen Feng<shen@cn.fujitsu.com>
-For general info and legal blurb, please look in index.rst.
+For general info and legal blurb, please look in :doc:`index`.
------------------------------------------------------------------------------
This file contains documentation for the sysctl files in
-/proc/sys/kernel/ and is valid for Linux kernel version 2.2.
+``/proc/sys/kernel/`` and is valid for Linux kernel version 2.2.
The files in this directory can be used to tune and monitor
miscellaneous and general things in the operation of the Linux
-kernel. Since some of the files _can_ be used to screw up your
+kernel. Since some of the files *can* be used to screw up your
system, it is advisable to read both documentation and source
before actually making adjustments.
Currently, these files might (depending on your configuration)
-show up in /proc/sys/kernel:
-
-- acct
-- acpi_video_flags
-- auto_msgmni
-- bootloader_type [ X86 only ]
-- bootloader_version [ X86 only ]
-- cap_last_cap
-- core_pattern
-- core_pipe_limit
-- core_uses_pid
-- ctrl-alt-del
-- dmesg_restrict
-- domainname
-- hostname
-- hotplug
-- hardlockup_all_cpu_backtrace
-- hardlockup_panic
-- hung_task_panic
-- hung_task_check_count
-- hung_task_timeout_secs
-- hung_task_check_interval_secs
-- hung_task_warnings
-- hyperv_record_panic_msg
-- kexec_load_disabled
-- kptr_restrict
-- l2cr [ PPC only ]
-- modprobe ==> Documentation/debugging-modules.txt
-- modules_disabled
-- msg_next_id [ sysv ipc ]
-- msgmax
-- msgmnb
-- msgmni
-- nmi_watchdog
-- osrelease
-- ostype
-- overflowgid
-- overflowuid
-- panic
-- panic_on_oops
-- panic_on_stackoverflow
-- panic_on_unrecovered_nmi
-- panic_on_warn
-- panic_print
-- panic_on_rcu_stall
-- perf_cpu_time_max_percent
-- perf_event_paranoid
-- perf_event_max_stack
-- perf_event_mlock_kb
-- perf_event_max_contexts_per_stack
-- pid_max
-- powersave-nap [ PPC only ]
-- printk
-- printk_delay
-- printk_ratelimit
-- printk_ratelimit_burst
-- pty ==> Documentation/filesystems/devpts.txt
-- randomize_va_space
-- real-root-dev ==> Documentation/admin-guide/initrd.rst
-- reboot-cmd [ SPARC only ]
-- rtsig-max
-- rtsig-nr
-- sched_energy_aware
-- seccomp/ ==> Documentation/userspace-api/seccomp_filter.rst
-- sem
-- sem_next_id [ sysv ipc ]
-- sg-big-buff [ generic SCSI device (sg) ]
-- shm_next_id [ sysv ipc ]
-- shm_rmid_forced
-- shmall
-- shmmax [ sysv ipc ]
-- shmmni
-- softlockup_all_cpu_backtrace
-- soft_watchdog
-- stack_erasing
-- stop-a [ SPARC only ]
-- sysrq ==> Documentation/admin-guide/sysrq.rst
-- sysctl_writes_strict
-- tainted ==> Documentation/admin-guide/tainted-kernels.rst
-- threads-max
-- unknown_nmi_panic
-- watchdog
-- watchdog_thresh
-- version
-
-
-acct:
-=====
+show up in ``/proc/sys/kernel``:
+
+.. contents:: :local:
+
+
+acct
+====
+
+::
-highwater lowwater frequency
+ highwater lowwater frequency
If BSD-style process accounting is enabled these values control
its behaviour. If free space on filesystem where the log lives
-goes below <lowwater>% accounting suspends. If free space gets
-above <highwater>% accounting resumes. <Frequency> determines
+goes below ``lowwater``% accounting suspends. If free space gets
+above ``highwater``% accounting resumes. ``frequency`` determines
how often do we check the amount of free space (value is in
seconds). Default:
-4 2 30
-That is, suspend accounting if there left <= 2% free; resume it
-if we got >=4%; consider information about amount of free space
-valid for 30 seconds.
+::
-acpi_video_flags:
-=================
+ 4 2 30
+
+That is, suspend accounting if free space drops below 2%; resume it
+if it increases to at least 4%; consider information about amount of
+free space valid for 30 seconds.
-flags
-See Doc*/kernel/power/video.txt, it allows mode of video boot to be
-set during run time.
+acpi_video_flags
+================
+See :doc:`/power/video`. This allows the video resume mode to be set,
+in a similar fashion to the ``acpi_sleep`` kernel parameter, by
+combining the following values:
+
+= =======
+1 s3_bios
+2 s3_mode
+4 s3_beep
+= =======
-auto_msgmni:
-============
+
+auto_msgmni
+===========
This variable has no effect and may be removed in future kernel
releases. Reading it always returns 0.
-Up to Linux 3.17, it enabled/disabled automatic recomputing of msgmni
-upon memory add/remove or upon ipc namespace creation/removal.
+Up to Linux 3.17, it enabled/disabled automatic recomputing of
+`msgmni`_
+upon memory add/remove or upon IPC namespace creation/removal.
Echoing "1" into this file enabled msgmni automatic recomputing.
-Echoing "0" turned it off. auto_msgmni default value was 1.
-
+Echoing "0" turned it off. The default value was 1.
-bootloader_type:
-================
-x86 bootloader identification
+bootloader_type (x86 only)
+==========================
This gives the bootloader type number as indicated by the bootloader,
shifted left by 4, and OR'd with the low four bits of the bootloader
version. The reason for this encoding is that this used to match the
-type_of_loader field in the kernel header; the encoding is kept for
+``type_of_loader`` field in the kernel header; the encoding is kept for
backwards compatibility. That is, if the full bootloader type number
is 0x15 and the full version number is 0x234, this file will contain
the value 340 = 0x154.
-See the type_of_loader and ext_loader_type fields in
-Documentation/x86/boot.rst for additional information.
-
+See the ``type_of_loader`` and ``ext_loader_type`` fields in
+:doc:`/x86/boot` for additional information.
-bootloader_version:
-===================
-x86 bootloader version
+bootloader_version (x86 only)
+=============================
The complete bootloader version number. In the example above, this
file will contain the value 564 = 0x234.
-See the type_of_loader and ext_loader_ver fields in
-Documentation/x86/boot.rst for additional information.
+See the ``type_of_loader`` and ``ext_loader_ver`` fields in
+:doc:`/x86/boot` for additional information.
-cap_last_cap:
-=============
+cap_last_cap
+============
Highest valid capability of the running kernel. Exports
-CAP_LAST_CAP from the kernel.
+``CAP_LAST_CAP`` from the kernel.
-core_pattern:
-=============
+core_pattern
+============
-core_pattern is used to specify a core dumpfile pattern name.
+``core_pattern`` is used to specify a core dumpfile pattern name.
* max length 127 characters; default value is "core"
-* core_pattern is used as a pattern template for the output filename;
- certain string patterns (beginning with '%') are substituted with
- their actual values.
-* backward compatibility with core_uses_pid:
+* ``core_pattern`` is used as a pattern template for the output
+ filename; certain string patterns (beginning with '%') are
+ substituted with their actual values.
+* backward compatibility with ``core_uses_pid``:
- If core_pattern does not include "%p" (default does not)
- and core_uses_pid is set, then .PID will be appended to
+ If ``core_pattern`` does not include "%p" (default does not)
+ and ``core_uses_pid`` is set, then .PID will be appended to
the filename.
-* corename format specifiers::
-
- %<NUL> '%' is dropped
- %% output one '%'
- %p pid
- %P global pid (init PID namespace)
- %i tid
- %I global tid (init PID namespace)
- %u uid (in initial user namespace)
- %g gid (in initial user namespace)
- %d dump mode, matches PR_SET_DUMPABLE and
- /proc/sys/fs/suid_dumpable
- %s signal number
- %t UNIX time of dump
- %h hostname
- %e executable filename (may be shortened)
- %E executable path
- %<OTHER> both are dropped
+* corename format specifiers
+
+ ======== ==========================================
+ %<NUL> '%' is dropped
+ %% output one '%'
+ %p pid
+ %P global pid (init PID namespace)
+ %i tid
+ %I global tid (init PID namespace)
+ %u uid (in initial user namespace)
+ %g gid (in initial user namespace)
+ %d dump mode, matches ``PR_SET_DUMPABLE`` and
+ ``/proc/sys/fs/suid_dumpable``
+ %s signal number
+ %t UNIX time of dump
+ %h hostname
+ %e executable filename (may be shortened)
+ %E executable path
+ %c maximum size of core file by resource limit RLIMIT_CORE
+ %<OTHER> both are dropped
+ ======== ==========================================
* If the first character of the pattern is a '|', the kernel will treat
the rest of the pattern as a command to run. The core dump will be
written to the standard input of that program instead of to a file.
-core_pipe_limit:
-================
+core_pipe_limit
+===============
-This sysctl is only applicable when core_pattern is configured to pipe
-core files to a user space helper (when the first character of
-core_pattern is a '|', see above). When collecting cores via a pipe
-to an application, it is occasionally useful for the collecting
-application to gather data about the crashing process from its
-/proc/pid directory. In order to do this safely, the kernel must wait
-for the collecting process to exit, so as not to remove the crashing
-processes proc files prematurely. This in turn creates the
-possibility that a misbehaving userspace collecting process can block
-the reaping of a crashed process simply by never exiting. This sysctl
-defends against that. It defines how many concurrent crashing
-processes may be piped to user space applications in parallel. If
-this value is exceeded, then those crashing processes above that value
-are noted via the kernel log and their cores are skipped. 0 is a
-special value, indicating that unlimited processes may be captured in
-parallel, but that no waiting will take place (i.e. the collecting
-process is not guaranteed access to /proc/<crashing pid>/). This
-value defaults to 0.
-
-
-core_uses_pid:
-==============
+This sysctl is only applicable when `core_pattern`_ is configured to
+pipe core files to a user space helper (when the first character of
+``core_pattern`` is a '|', see above).
+When collecting cores via a pipe to an application, it is occasionally
+useful for the collecting application to gather data about the
+crashing process from its ``/proc/pid`` directory.
+In order to do this safely, the kernel must wait for the collecting
+process to exit, so as not to remove the crashing processes proc files
+prematurely.
+This in turn creates the possibility that a misbehaving userspace
+collecting process can block the reaping of a crashed process simply
+by never exiting.
+This sysctl defends against that.
+It defines how many concurrent crashing processes may be piped to user
+space applications in parallel.
+If this value is exceeded, then those crashing processes above that
+value are noted via the kernel log and their cores are skipped.
+0 is a special value, indicating that unlimited processes may be
+captured in parallel, but that no waiting will take place (i.e. the
+collecting process is not guaranteed access to ``/proc/<crashing
+pid>/``).
+This value defaults to 0.
+
+
+core_uses_pid
+=============
The default coredump filename is "core". By setting
-core_uses_pid to 1, the coredump filename becomes core.PID.
-If core_pattern does not include "%p" (default does not)
-and core_uses_pid is set, then .PID will be appended to
+``core_uses_pid`` to 1, the coredump filename becomes core.PID.
+If `core_pattern`_ does not include "%p" (default does not)
+and ``core_uses_pid`` is set, then .PID will be appended to
the filename.
-ctrl-alt-del:
-=============
+ctrl-alt-del
+============
When the value in this file is 0, ctrl-alt-del is trapped and
-sent to the init(1) program to handle a graceful restart.
+sent to the ``init(1)`` program to handle a graceful restart.
When, however, the value is > 0, Linux's reaction to a Vulcan
Nerve Pinch (tm) will be an immediate reboot, without even
syncing its dirty buffers.
to decide what to do with it.
-dmesg_restrict:
-===============
+dmesg_restrict
+==============
This toggle indicates whether unprivileged users are prevented
-from using dmesg(8) to view messages from the kernel's log buffer.
-When dmesg_restrict is set to (0) there are no restrictions. When
-dmesg_restrict is set set to (1), users must have CAP_SYSLOG to use
-dmesg(8).
+from using ``dmesg(8)`` to view messages from the kernel's log
+buffer.
+When ``dmesg_restrict`` is set to 0 there are no restrictions.
+When ``dmesg_restrict`` is set set to 1, users must have
+``CAP_SYSLOG`` to use ``dmesg(8)``.
-The kernel config option CONFIG_SECURITY_DMESG_RESTRICT sets the
-default value of dmesg_restrict.
+The kernel config option ``CONFIG_SECURITY_DMESG_RESTRICT`` sets the
+default value of ``dmesg_restrict``.
-domainname & hostname:
-======================
+domainname & hostname
+=====================
These files can be used to set the NIS/YP domainname and the
hostname of your box in exactly the same way as the commands
domainname "frop.org", not to be confused with the NIS (Network
Information Service) or YP (Yellow Pages) domainname. These two
domain names are in general different. For a detailed discussion
-see the hostname(1) man page.
+see the ``hostname(1)`` man page.
-hardlockup_all_cpu_backtrace:
-=============================
+hardlockup_all_cpu_backtrace
+============================
This value controls the hard lockup detector behavior when a hard
lockup condition is detected as to whether or not to gather further
debug information. If enabled, arch-specific all-CPU stack dumping
will be initiated.
-0: do nothing. This is the default behavior.
-
-1: on detection capture more debug information.
+= ============================================
+0 Do nothing. This is the default behavior.
+1 On detection capture more debug information.
+= ============================================
-hardlockup_panic:
-=================
+hardlockup_panic
+================
This parameter can be used to control whether the kernel panics
when a hard lockup is detected.
- 0 - don't panic on hard lockup
- 1 - panic on hard lockup
+= ===========================
+0 Don't panic on hard lockup.
+1 Panic on hard lockup.
+= ===========================
-See Documentation/admin-guide/lockup-watchdogs.rst for more information. This can
-also be set using the nmi_watchdog kernel parameter.
+See :doc:`/admin-guide/lockup-watchdogs` for more information.
+This can also be set using the nmi_watchdog kernel parameter.
-hotplug:
-========
+hotplug
+=======
Path for the hotplug policy agent.
-Default value is "/sbin/hotplug".
+Default value is "``/sbin/hotplug``".
-hung_task_panic:
-================
+hung_task_panic
+===============
Controls the kernel's behavior when a hung task is detected.
-This file shows up if CONFIG_DETECT_HUNG_TASK is enabled.
-
-0: continue operation. This is the default behavior.
+This file shows up if ``CONFIG_DETECT_HUNG_TASK`` is enabled.
-1: panic immediately.
+= =================================================
+0 Continue operation. This is the default behavior.
+1 Panic immediately.
+= =================================================
-hung_task_check_count:
-======================
+hung_task_check_count
+=====================
The upper bound on the number of tasks that are checked.
-This file shows up if CONFIG_DETECT_HUNG_TASK is enabled.
+This file shows up if ``CONFIG_DETECT_HUNG_TASK`` is enabled.
-hung_task_timeout_secs:
-=======================
+hung_task_timeout_secs
+======================
When a task in D state did not get scheduled
for more than this value report a warning.
-This file shows up if CONFIG_DETECT_HUNG_TASK is enabled.
+This file shows up if ``CONFIG_DETECT_HUNG_TASK`` is enabled.
-0: means infinite timeout - no checking done.
+0 means infinite timeout, no checking is done.
-Possible values to set are in range {0..LONG_MAX/HZ}.
+Possible values to set are in range {0:``LONG_MAX``/``HZ``}.
-hung_task_check_interval_secs:
-==============================
+hung_task_check_interval_secs
+=============================
Hung task check interval. If hung task checking is enabled
-(see hung_task_timeout_secs), the check is done every
-hung_task_check_interval_secs seconds.
-This file shows up if CONFIG_DETECT_HUNG_TASK is enabled.
+(see `hung_task_timeout_secs`_), the check is done every
+``hung_task_check_interval_secs`` seconds.
+This file shows up if ``CONFIG_DETECT_HUNG_TASK`` is enabled.
-0 (default): means use hung_task_timeout_secs as checking interval.
-Possible values to set are in range {0..LONG_MAX/HZ}.
+0 (default) means use ``hung_task_timeout_secs`` as checking
+interval.
+Possible values to set are in range {0:``LONG_MAX``/``HZ``}.
-hung_task_warnings:
-===================
+
+hung_task_warnings
+==================
The maximum number of warnings to report. During a check interval
if a hung task is detected, this value is decreased by 1.
When this value reaches 0, no more warnings will be reported.
-This file shows up if CONFIG_DETECT_HUNG_TASK is enabled.
+This file shows up if ``CONFIG_DETECT_HUNG_TASK`` is enabled.
-1: report an infinite number of warnings.
-hyperv_record_panic_msg:
-========================
+hyperv_record_panic_msg
+=======================
Controls whether the panic kmsg data should be reported to Hyper-V.
-0: do not report panic kmsg data.
+= =========================================================
+0 Do not report panic kmsg data.
+1 Report the panic kmsg data. This is the default behavior.
+= =========================================================
-1: report the panic kmsg data. This is the default behavior.
+kexec_load_disabled
+===================
-kexec_load_disabled:
-====================
-
-A toggle indicating if the kexec_load syscall has been disabled. This
-value defaults to 0 (false: kexec_load enabled), but can be set to 1
-(true: kexec_load disabled). Once true, kexec can no longer be used, and
-the toggle cannot be set back to false. This allows a kexec image to be
-loaded before disabling the syscall, allowing a system to set up (and
-later use) an image without it being altered. Generally used together
-with the "modules_disabled" sysctl.
+A toggle indicating if the ``kexec_load`` syscall has been disabled.
+This value defaults to 0 (false: ``kexec_load`` enabled), but can be
+set to 1 (true: ``kexec_load`` disabled).
+Once true, kexec can no longer be used, and the toggle cannot be set
+back to false.
+This allows a kexec image to be loaded before disabling the syscall,
+allowing a system to set up (and later use) an image without it being
+altered.
+Generally used together with the `modules_disabled`_ sysctl.
-kptr_restrict:
-==============
+kptr_restrict
+=============
This toggle indicates whether restrictions are placed on
-exposing kernel addresses via /proc and other interfaces.
+exposing kernel addresses via ``/proc`` and other interfaces.
+
+When ``kptr_restrict`` is set to 0 (the default) the address is hashed
+before printing.
+(This is the equivalent to %p.)
+
+When ``kptr_restrict`` is set to 1, kernel pointers printed using the
+%pK format specifier will be replaced with 0s unless the user has
+``CAP_SYSLOG`` and effective user and group ids are equal to the real
+ids.
+This is because %pK checks are done at read() time rather than open()
+time, so if permissions are elevated between the open() and the read()
+(e.g via a setuid binary) then %pK will not leak kernel pointers to
+unprivileged users.
+Note, this is a temporary solution only.
+The correct long-term solution is to do the permission checks at
+open() time.
+Consider removing world read permissions from files that use %pK, and
+using `dmesg_restrict`_ to protect against uses of %pK in ``dmesg(8)``
+if leaking kernel pointer values to unprivileged users is a concern.
+
+When ``kptr_restrict`` is set to 2, kernel pointers printed using
+%pK will be replaced with 0s regardless of privileges.
+
+
+modprobe
+========
-When kptr_restrict is set to 0 (the default) the address is hashed before
-printing. (This is the equivalent to %p.)
+This gives the full path of the modprobe command which the kernel will
+use to load modules. This can be used to debug module loading
+requests::
-When kptr_restrict is set to (1), kernel pointers printed using the %pK
-format specifier will be replaced with 0's unless the user has CAP_SYSLOG
-and effective user and group ids are equal to the real ids. This is
-because %pK checks are done at read() time rather than open() time, so
-if permissions are elevated between the open() and the read() (e.g via
-a setuid binary) then %pK will not leak kernel pointers to unprivileged
-users. Note, this is a temporary solution only. The correct long-term
-solution is to do the permission checks at open() time. Consider removing
-world read permissions from files that use %pK, and using dmesg_restrict
-to protect against uses of %pK in dmesg(8) if leaking kernel pointer
-values to unprivileged users is a concern.
+ echo '#! /bin/sh' > /tmp/modprobe
+ echo 'echo "$@" >> /tmp/modprobe.log' >> /tmp/modprobe
+ echo 'exec /sbin/modprobe "$@"' >> /tmp/modprobe
+ chmod a+x /tmp/modprobe
+ echo /tmp/modprobe > /proc/sys/kernel/modprobe
-When kptr_restrict is set to (2), kernel pointers printed using
-%pK will be replaced with 0's regardless of privileges.
+This only applies when the *kernel* is requesting that the module be
+loaded; it won't have any effect if the module is being loaded
+explicitly using ``modprobe`` from userspace.
-l2cr: (PPC only)
+modules_disabled
================
-This flag controls the L2 cache of G3 processor boards. If
-0, the cache is disabled. Enabled if nonzero.
-
-
-modules_disabled:
-=================
-
A toggle value indicating if modules are allowed to be loaded
in an otherwise modular kernel. This toggle defaults to off
(0), but can be set true (1). Once true, modules can be
neither loaded nor unloaded, and the toggle cannot be set back
-to false. Generally used with the "kexec_load_disabled" toggle.
+to false. Generally used with the `kexec_load_disabled`_ toggle.
+
+
+.. _msgmni:
+
+msgmax, msgmnb, and msgmni
+==========================
+
+``msgmax`` is the maximum size of an IPC message, in bytes. 8192 by
+default (``MSGMAX``).
+``msgmnb`` is the maximum size of an IPC queue, in bytes. 16384 by
+default (``MSGMNB``).
-msg_next_id, sem_next_id, and shm_next_id:
-==========================================
+``msgmni`` is the maximum number of IPC queues. 32000 by default
+(``MSGMNI``).
+
+
+msg_next_id, sem_next_id, and shm_next_id (System V IPC)
+========================================================
These three toggles allows to specify desired id for next allocated IPC
object: message, semaphore or shared memory respectively.
By default they are equal to -1, which means generic allocation logic.
-Possible values to set are in range {0..INT_MAX}.
+Possible values to set are in range {0:``INT_MAX``}.
Notes:
1) kernel doesn't guarantee, that new object will have desired id. So,
fails, it is undefined if the value remains unmodified or is reset to -1.
-nmi_watchdog:
-=============
+nmi_watchdog
+============
This parameter can be used to control the NMI watchdog
(i.e. the hard lockup detector) on x86 systems.
-0 - disable the hard lockup detector
-
-1 - enable the hard lockup detector
+= =================================
+0 Disable the hard lockup detector.
+1 Enable the hard lockup detector.
+= =================================
The hard lockup detector monitors each CPU for its ability to respond to
timer interrupts. The mechanism utilizes CPU performance counter registers
nmi_watchdog=1
-to the guest kernel command line (see Documentation/admin-guide/kernel-parameters.rst).
+to the guest kernel command line (see :doc:`/admin-guide/kernel-parameters`).
-numa_balancing:
-===============
+numa_balancing
+==============
Enables/disables automatic page fault based NUMA memory
balancing. Memory is moved automatically to nodes
guarantee. If the target workload is already bound to NUMA nodes then this
feature should be disabled. Otherwise, if the system overhead from the
feature is too high then the rate the kernel samples for NUMA hinting
-faults may be controlled by the numa_balancing_scan_period_min_ms,
+faults may be controlled by the `numa_balancing_scan_period_min_ms,
numa_balancing_scan_delay_ms, numa_balancing_scan_period_max_ms,
-numa_balancing_scan_size_mb, and numa_balancing_settle_count sysctls.
+numa_balancing_scan_size_mb`_, and numa_balancing_settle_count sysctls.
+
numa_balancing_scan_period_min_ms, numa_balancing_scan_delay_ms, numa_balancing_scan_period_max_ms, numa_balancing_scan_size_mb
===============================================================================================================================
memory accesses. These sysctls control the thresholds for scan delays and
the number of pages scanned.
-numa_balancing_scan_period_min_ms is the minimum time in milliseconds to
+``numa_balancing_scan_period_min_ms`` is the minimum time in milliseconds to
scan a tasks virtual memory. It effectively controls the maximum scanning
rate for each task.
-numa_balancing_scan_delay_ms is the starting "scan delay" used for a task
+``numa_balancing_scan_delay_ms`` is the starting "scan delay" used for a task
when it initially forks.
-numa_balancing_scan_period_max_ms is the maximum time in milliseconds to
+``numa_balancing_scan_period_max_ms`` is the maximum time in milliseconds to
scan a tasks virtual memory. It effectively controls the minimum scanning
rate for each task.
-numa_balancing_scan_size_mb is how many megabytes worth of pages are
+``numa_balancing_scan_size_mb`` is how many megabytes worth of pages are
scanned for a given scan.
-osrelease, ostype & version:
-============================
+osrelease, ostype & version
+===========================
::
# cat version
#5 Wed Feb 25 21:49:24 MET 1998
-The files osrelease and ostype should be clear enough. Version
+The files ``osrelease`` and ``ostype`` should be clear enough.
+``version``
needs a little more clarification however. The '#5' means that
this is the fifth kernel built from this source base and the
date behind it indicates the time the kernel was built.
The only way to tune these values is to rebuild the kernel :-)
-overflowgid & overflowuid:
-==========================
+overflowgid & overflowuid
+=========================
if your architecture did not always support 32-bit UIDs (i.e. arm,
i386, m68k, sh, and sparc32), a fixed UID and GID will be returned to
The default is 65534.
+panic
+=====
+
+The value in this file determines the behaviour of the kernel on a
panic:
-======
-The value in this file represents the number of seconds the kernel
-waits before rebooting on a panic. When you use the software watchdog,
-the recommended setting is 60.
+* if zero, the kernel will loop forever;
+* if negative, the kernel will reboot immediately;
+* if positive, the kernel will reboot after the corresponding number
+ of seconds.
+When you use the software watchdog, the recommended setting is 60.
-panic_on_io_nmi:
-================
+
+panic_on_io_nmi
+===============
Controls the kernel's behavior when a CPU receives an NMI caused by
an IO error.
-0: try to continue operation (default)
-
-1: panic immediately. The IO error triggered an NMI. This indicates a
- serious system condition which could result in IO data corruption.
- Rather than continuing, panicking might be a better choice. Some
- servers issue this sort of NMI when the dump button is pushed,
- and you can use this option to take a crash dump.
+= ==================================================================
+0 Try to continue operation (default).
+1 Panic immediately. The IO error triggered an NMI. This indicates a
+ serious system condition which could result in IO data corruption.
+ Rather than continuing, panicking might be a better choice. Some
+ servers issue this sort of NMI when the dump button is pushed,
+ and you can use this option to take a crash dump.
+= ==================================================================
-panic_on_oops:
-==============
+panic_on_oops
+=============
Controls the kernel's behaviour when an oops or BUG is encountered.
-0: try to continue operation
-
-1: panic immediately. If the `panic` sysctl is also non-zero then the
- machine will be rebooted.
+= ===================================================================
+0 Try to continue operation.
+1 Panic immediately. If the `panic` sysctl is also non-zero then the
+ machine will be rebooted.
+= ===================================================================
-panic_on_stackoverflow:
-=======================
+panic_on_stackoverflow
+======================
Controls the kernel's behavior when detecting the overflows of
kernel, IRQ and exception stacks except a user stack.
-This file shows up if CONFIG_DEBUG_STACKOVERFLOW is enabled.
-
-0: try to continue operation.
+This file shows up if ``CONFIG_DEBUG_STACKOVERFLOW`` is enabled.
-1: panic immediately.
+= ==========================
+0 Try to continue operation.
+1 Panic immediately.
+= ==========================
-panic_on_unrecovered_nmi:
-=========================
+panic_on_unrecovered_nmi
+========================
The default Linux behaviour on an NMI of either memory or unknown is
to continue operation. For many environments such as scientific
computing it is preferable that the box is taken out and the error
dealt with than an uncorrected parity/ECC error get propagated.
-A small number of systems do generate NMI's for bizarre random reasons
+A small number of systems do generate NMIs for bizarre random reasons
such as power management so the default is off. That sysctl works like
the existing panic controls already in that directory.
-panic_on_warn:
-==============
+panic_on_warn
+=============
Calls panic() in the WARN() path when set to 1. This is useful to avoid
a kernel rebuild when attempting to kdump at the location of a WARN().
-0: only WARN(), default behaviour.
-
-1: call panic() after printing out WARN() location.
+= ================================================
+0 Only WARN(), default behaviour.
+1 Call panic() after printing out WARN() location.
+= ================================================
-panic_print:
-============
+panic_print
+===========
Bitmask for printing system info when panic happens. User can chose
combination of the following bits:
-===== ========================================
+===== ============================================
bit 0 print all tasks info
bit 1 print system memory info
bit 2 print timer info
-bit 3 print locks info if CONFIG_LOCKDEP is on
+bit 3 print locks info if ``CONFIG_LOCKDEP`` is on
bit 4 print ftrace buffer
-===== ========================================
+===== ============================================
So for example to print tasks and memory info on panic, user can::
echo 3 > /proc/sys/kernel/panic_print
-panic_on_rcu_stall:
-===================
+panic_on_rcu_stall
+==================
When set to 1, calls panic() after RCU stall detection messages. This
is useful to define the root cause of RCU stalls using a vmcore.
-0: do not panic() when RCU stall takes place, default behavior.
+= ============================================================
+0 Do not panic() when RCU stall takes place, default behavior.
+1 panic() after printing RCU stall messages.
+= ============================================================
-1: panic() after printing RCU stall messages.
-
-perf_cpu_time_max_percent:
-==========================
+perf_cpu_time_max_percent
+=========================
Hints to the kernel how much CPU time it should be allowed to
use to handle perf sampling events. If the perf subsystem
stacked up next to each other so much that nothing else is
allowed to execute.
-0:
- disable the mechanism. Do not monitor or correct perf's
- sampling rate no matter how CPU time it takes.
+===== ========================================================
+0 Disable the mechanism. Do not monitor or correct perf's
+ sampling rate no matter how CPU time it takes.
-1-100:
- attempt to throttle perf's sample rate to this
- percentage of CPU. Note: the kernel calculates an
- "expected" length of each sample event. 100 here means
- 100% of that expected length. Even if this is set to
- 100, you may still see sample throttling if this
- length is exceeded. Set to 0 if you truly do not care
- how much CPU is consumed.
+1-100 Attempt to throttle perf's sample rate to this
+ percentage of CPU. Note: the kernel calculates an
+ "expected" length of each sample event. 100 here means
+ 100% of that expected length. Even if this is set to
+ 100, you may still see sample throttling if this
+ length is exceeded. Set to 0 if you truly do not care
+ how much CPU is consumed.
+===== ========================================================
-perf_event_paranoid:
-====================
+perf_event_paranoid
+===================
Controls use of the performance events system by unprivileged
users (without CAP_SYS_ADMIN). The default value is 2.
=== ==================================================================
- -1 Allow use of (almost) all events by all users
+ -1 Allow use of (almost) all events by all users.
- Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK
+ Ignore mlock limit after perf_event_mlock_kb without
+ ``CAP_IPC_LOCK``.
->=0 Disallow ftrace function tracepoint by users without CAP_SYS_ADMIN
+>=0 Disallow ftrace function tracepoint by users without
+ ``CAP_SYS_ADMIN``.
- Disallow raw tracepoint access by users without CAP_SYS_ADMIN
+ Disallow raw tracepoint access by users without ``CAP_SYS_ADMIN``.
->=1 Disallow CPU event access by users without CAP_SYS_ADMIN
+>=1 Disallow CPU event access by users without ``CAP_SYS_ADMIN``.
->=2 Disallow kernel profiling by users without CAP_SYS_ADMIN
+>=2 Disallow kernel profiling by users without ``CAP_SYS_ADMIN``.
=== ==================================================================
-perf_event_max_stack:
-=====================
+perf_event_max_stack
+====================
-Controls maximum number of stack frames to copy for (attr.sample_type &
-PERF_SAMPLE_CALLCHAIN) configured events, for instance, when using
-'perf record -g' or 'perf trace --call-graph fp'.
+Controls maximum number of stack frames to copy for (``attr.sample_type &
+PERF_SAMPLE_CALLCHAIN``) configured events, for instance, when using
+'``perf record -g``' or '``perf trace --call-graph fp``'.
This can only be done when no events are in use that have callchains
-enabled, otherwise writing to this file will return -EBUSY.
+enabled, otherwise writing to this file will return ``-EBUSY``.
The default value is 127.
-perf_event_mlock_kb:
-====================
+perf_event_mlock_kb
+===================
Control size of per-cpu ring buffer not counted agains mlock limit.
The default value is 512 + 1 page
-perf_event_max_contexts_per_stack:
-==================================
+perf_event_max_contexts_per_stack
+=================================
Controls maximum number of stack frame context entries for
-(attr.sample_type & PERF_SAMPLE_CALLCHAIN) configured events, for
-instance, when using 'perf record -g' or 'perf trace --call-graph fp'.
+(``attr.sample_type & PERF_SAMPLE_CALLCHAIN``) configured events, for
+instance, when using '``perf record -g``' or '``perf trace --call-graph fp``'.
This can only be done when no events are in use that have callchains
-enabled, otherwise writing to this file will return -EBUSY.
+enabled, otherwise writing to this file will return ``-EBUSY``.
The default value is 8.
-pid_max:
-========
+pid_max
+=======
PID allocation wrap value. When the kernel's next PID value
reaches this value, it wraps back to a minimum PID value.
-PIDs of value pid_max or larger are not allocated.
+PIDs of value ``pid_max`` or larger are not allocated.
-ns_last_pid:
-============
+ns_last_pid
+===========
The last pid allocated in the current (the one task using this sysctl
lives in) pid namespace. When selecting a pid for a next task on fork
kernel tries to allocate a number starting from this one.
-powersave-nap: (PPC only)
-=========================
+powersave-nap (PPC only)
+========================
If set, Linux-PPC will use the 'nap' mode of powersaving,
otherwise the 'doze' mode will be used.
+
==============================================================
-printk:
-=======
+printk
+======
-The four values in printk denote: console_loglevel,
-default_message_loglevel, minimum_console_loglevel and
-default_console_loglevel respectively.
+The four values in printk denote: ``console_loglevel``,
+``default_message_loglevel``, ``minimum_console_loglevel`` and
+``default_console_loglevel`` respectively.
These values influence printk() behavior when printing or
-logging error messages. See 'man 2 syslog' for more info on
+logging error messages. See '``man 2 syslog``' for more info on
the different loglevels.
-- console_loglevel:
- messages with a higher priority than
- this will be printed to the console
-- default_message_loglevel:
- messages without an explicit priority
- will be printed with this priority
-- minimum_console_loglevel:
- minimum (highest) value to which
- console_loglevel can be set
-- default_console_loglevel:
- default value for console_loglevel
+======================== =====================================
+console_loglevel messages with a higher priority than
+ this will be printed to the console
+default_message_loglevel messages without an explicit priority
+ will be printed with this priority
+minimum_console_loglevel minimum (highest) value to which
+ console_loglevel can be set
+default_console_loglevel default value for console_loglevel
+======================== =====================================
-printk_delay:
-=============
+printk_delay
+============
-Delay each printk message in printk_delay milliseconds
+Delay each printk message in ``printk_delay`` milliseconds
Value from 0 - 10000 is allowed.
-printk_ratelimit:
-=================
+printk_ratelimit
+================
-Some warning messages are rate limited. printk_ratelimit specifies
+Some warning messages are rate limited. ``printk_ratelimit`` specifies
the minimum length of time between these messages (in seconds).
The default value is 5 seconds.
A value of 0 will disable rate limiting.
-printk_ratelimit_burst:
-=======================
+printk_ratelimit_burst
+======================
-While long term we enforce one message per printk_ratelimit
+While long term we enforce one message per `printk_ratelimit`_
seconds, we do allow a burst of messages to pass through.
-printk_ratelimit_burst specifies the number of messages we can
+``printk_ratelimit_burst`` specifies the number of messages we can
send before ratelimiting kicks in.
The default value is 10 messages.
-printk_devkmsg:
-===============
-
-Control the logging to /dev/kmsg from userspace:
-
-ratelimit:
- default, ratelimited
+printk_devkmsg
+==============
-on: unlimited logging to /dev/kmsg from userspace
+Control the logging to ``/dev/kmsg`` from userspace:
-off: logging to /dev/kmsg disabled
+========= =============================================
+ratelimit default, ratelimited
+on unlimited logging to /dev/kmsg from userspace
+off logging to /dev/kmsg disabled
+========= =============================================
-The kernel command line parameter printk.devkmsg= overrides this and is
+The kernel command line parameter ``printk.devkmsg=`` overrides this and is
a one-time setting until next reboot: once set, it cannot be changed by
this sysctl interface anymore.
+==============================================================
-randomize_va_space:
-===================
+
+pty
+===
+
+See Documentation/filesystems/devpts.txt.
+
+
+randomize_va_space
+==================
This option can be used to select the type of process address
space randomization that is used in the system, for architectures
This, among other things, implies that shared libraries will be
loaded to random addresses. Also for PIE-linked binaries, the
location of code start is randomized. This is the default if the
- CONFIG_COMPAT_BRK option is enabled.
+ ``CONFIG_COMPAT_BRK`` option is enabled.
2 Additionally enable heap randomization. This is the default if
- CONFIG_COMPAT_BRK is disabled.
+ ``CONFIG_COMPAT_BRK`` is disabled.
There are a few legacy applications out there (such as some ancient
versions of libc.so.5 from 1996) that assume that brk area starts
systems it is safe to choose full randomization.
Systems with ancient and/or broken binaries should be configured
- with CONFIG_COMPAT_BRK enabled, which excludes the heap from process
+ with ``CONFIG_COMPAT_BRK`` enabled, which excludes the heap from process
address space randomization.
== ===========================================================================
-reboot-cmd: (Sparc only)
-========================
-
-??? This seems to be a way to give an argument to the Sparc
-ROM/Flash boot loader. Maybe to tell it what to do after
-rebooting. ???
+real-root-dev
+=============
+See :doc:`/admin-guide/initrd`.
-rtsig-max & rtsig-nr:
-=====================
-The file rtsig-max can be used to tune the maximum number
-of POSIX realtime (queued) signals that can be outstanding
-in the system.
+reboot-cmd (SPARC only)
+=======================
-rtsig-nr shows the number of RT signals currently queued.
+??? This seems to be a way to give an argument to the Sparc
+ROM/Flash boot loader. Maybe to tell it what to do after
+rebooting. ???
-sched_energy_aware:
-===================
+sched_energy_aware
+==================
Enables/disables Energy Aware Scheduling (EAS). EAS starts
automatically on platforms where it can run (that is,
this value to 0.
-sched_schedstats:
-=================
+sched_schedstats
+================
Enables/disables scheduler statistics. Enabling this feature
incurs a small amount of overhead in the scheduler but is
useful for debugging and performance tuning.
-sg-big-buff:
-============
+seccomp
+=======
+
+See :doc:`/userspace-api/seccomp_filter`.
+
+
+sg-big-buff
+===========
This file shows the size of the generic SCSI (sg) buffer.
You can't tune it just yet, but you could change it on
-compile time by editing include/scsi/sg.h and changing
-the value of SG_BIG_BUFF.
+compile time by editing ``include/scsi/sg.h`` and changing
+the value of ``SG_BIG_BUFF``.
There shouldn't be any reason to change this value. If
you can come up with one, you probably know what you
are doing anyway :)
-shmall:
-=======
+shmall
+======
This parameter sets the total amount of shared memory pages that
-can be used system wide. Hence, SHMALL should always be at least
-ceil(shmmax/PAGE_SIZE).
+can be used system wide. Hence, ``shmall`` should always be at least
+``ceil(shmmax/PAGE_SIZE)``.
-If you are not sure what the default PAGE_SIZE is on your Linux
-system, you can run the following command:
+If you are not sure what the default ``PAGE_SIZE`` is on your Linux
+system, you can run the following command::
# getconf PAGE_SIZE
-shmmax:
-=======
+shmmax
+======
This value can be used to query and set the run time limit
on the maximum shared memory segment size that can be created.
Shared memory segments up to 1Gb are now supported in the
-kernel. This value defaults to SHMMAX.
+kernel. This value defaults to ``SHMMAX``.
-shm_rmid_forced:
-================
+shmmni
+======
+
+This value determines the maximum number of shared memory segments.
+4096 by default (``SHMMNI``).
+
+
+shm_rmid_forced
+===============
Linux lets you set resource limits, including how much memory one
-process can consume, via setrlimit(2). Unfortunately, shared memory
+process can consume, via ``setrlimit(2)``. Unfortunately, shared memory
segments are allowed to exist without association with any process, and
thus might not be counted against any resource limits. If enabled,
shared memory segments are automatically destroyed when their attach
count becomes zero after a detach or a process termination. It will
also destroy segments that were created, but never attached to, on exit
-from the process. The only use left for IPC_RMID is to immediately
+from the process. The only use left for ``IPC_RMID`` is to immediately
destroy an unattached segment. Of course, this breaks the way things are
defined, so some applications might stop working. Note that this
feature will do you no good unless you also configure your resource
-limits (in particular, RLIMIT_AS and RLIMIT_NPROC). Most systems don't
+limits (in particular, ``RLIMIT_AS`` and ``RLIMIT_NPROC``). Most systems don't
need this.
Note that if you change this from 0 to 1, already created segments
without users and with a dead originative process will be destroyed.
-sysctl_writes_strict:
-=====================
+sysctl_writes_strict
+====================
Control how file position affects the behavior of updating sysctl values
-via the /proc/sys interface:
+via the ``/proc/sys`` interface:
== ======================================================================
-1 Legacy per-write sysctl value handling, with no printk warnings.
== ======================================================================
-softlockup_all_cpu_backtrace:
-=============================
+softlockup_all_cpu_backtrace
+============================
This value controls the soft lockup detector thread's behavior
when a soft lockup condition is detected as to whether or not
This feature is only applicable for architectures which support
NMI.
-0: do nothing. This is the default behavior.
+= ============================================
+0 Do nothing. This is the default behavior.
+1 On detection capture more debug information.
+= ============================================
-1: on detection capture more debug information.
+softlockup_panic
+=================
-soft_watchdog:
-==============
+This parameter can be used to control whether the kernel panics
+when a soft lockup is detected.
-This parameter can be used to control the soft lockup detector.
+= ============================================
+0 Don't panic on soft lockup.
+1 Panic on soft lockup.
+= ============================================
- 0 - disable the soft lockup detector
+This can also be set using the softlockup_panic kernel parameter.
- 1 - enable the soft lockup detector
+
+soft_watchdog
+=============
+
+This parameter can be used to control the soft lockup detector.
+
+= =================================
+0 Disable the soft lockup detector.
+1 Enable the soft lockup detector.
+= =================================
The soft lockup detector monitors CPUs for threads that are hogging the CPUs
without rescheduling voluntarily, and thus prevent the 'watchdog/N' threads
from running. The mechanism depends on the CPUs ability to respond to timer
interrupts which are needed for the 'watchdog/N' threads to be woken up by
-the watchdog timer function, otherwise the NMI watchdog - if enabled - can
+the watchdog timer function, otherwise the NMI watchdog — if enabled — can
detect a hard lockup condition.
-stack_erasing:
-==============
+stack_erasing
+=============
This parameter can be used to control kernel stack erasing at the end
-of syscalls for kernels built with CONFIG_GCC_PLUGIN_STACKLEAK.
+of syscalls for kernels built with ``CONFIG_GCC_PLUGIN_STACKLEAK``.
That erasing reduces the information which kernel stack leak bugs
can reveal and blocks some uninitialized stack variable attacks.
The tradeoff is the performance impact: on a single CPU system kernel
compilation sees a 1% slowdown, other systems and workloads may vary.
- 0: kernel stack erasing is disabled, STACKLEAK_METRICS are not updated.
+= ====================================================================
+0 Kernel stack erasing is disabled, STACKLEAK_METRICS are not updated.
+1 Kernel stack erasing is enabled (default), it is performed before
+ returning to the userspace at the end of syscalls.
+= ====================================================================
+
+
+stop-a (SPARC only)
+===================
+
+Controls Stop-A:
+
+= ====================================
+0 Stop-A has no effect.
+1 Stop-A breaks to the PROM (default).
+= ====================================
+
+Stop-A is always enabled on a panic, so that the user can return to
+the boot PROM.
- 1: kernel stack erasing is enabled (default), it is performed before
- returning to the userspace at the end of syscalls.
+
+sysrq
+=====
+
+See :doc:`/admin-guide/sysrq`.
tainted
131072 `(T)` The kernel was built with the struct randomization plugin
====== ===== ==============================================================
-See Documentation/admin-guide/tainted-kernels.rst for more information.
+See :doc:`/admin-guide/tainted-kernels` for more information.
-threads-max:
-============
+threads-max
+===========
This value controls the maximum number of threads that can be created
-using fork().
+using ``fork()``.
During initialization the kernel sets this value such that even if the
maximum number of threads is created, the thread structures occupy only
a part (1/8th) of the available RAM pages.
-The minimum value that can be written to threads-max is 1.
+The minimum value that can be written to ``threads-max`` is 1.
-The maximum value that can be written to threads-max is given by the
-constant FUTEX_TID_MASK (0x3fffffff).
+The maximum value that can be written to ``threads-max`` is given by the
+constant ``FUTEX_TID_MASK`` (0x3fffffff).
-If a value outside of this range is written to threads-max an error
-EINVAL occurs.
+If a value outside of this range is written to ``threads-max`` an
+``EINVAL`` error occurs.
-unknown_nmi_panic:
-==================
+unknown_nmi_panic
+=================
The value in this file affects behavior of handling NMI. When the
value is non-zero, unknown NMI is trapped and then panic occurs. At
example. If a system hangs up, try pressing the NMI switch.
-watchdog:
-=========
+watchdog
+========
This parameter can be used to disable or enable the soft lockup detector
-_and_ the NMI watchdog (i.e. the hard lockup detector) at the same time.
-
- 0 - disable both lockup detectors
+*and* the NMI watchdog (i.e. the hard lockup detector) at the same time.
- 1 - enable both lockup detectors
+= ==============================
+0 Disable both lockup detectors.
+1 Enable both lockup detectors.
+= ==============================
The soft lockup detector and the NMI watchdog can also be disabled or
-enabled individually, using the soft_watchdog and nmi_watchdog parameters.
-If the watchdog parameter is read, for example by executing::
+enabled individually, using the ``soft_watchdog`` and ``nmi_watchdog``
+parameters.
+If the ``watchdog`` parameter is read, for example by executing::
cat /proc/sys/kernel/watchdog
-the output of this command (0 or 1) shows the logical OR of soft_watchdog
-and nmi_watchdog.
+the output of this command (0 or 1) shows the logical OR of
+``soft_watchdog`` and ``nmi_watchdog``.
-watchdog_cpumask:
-=================
+watchdog_cpumask
+================
This value can be used to control on which cpus the watchdog may run.
-The default cpumask is all possible cores, but if NO_HZ_FULL is
+The default cpumask is all possible cores, but if ``NO_HZ_FULL`` is
enabled in the kernel config, and cores are specified with the
-nohz_full= boot argument, those cores are excluded by default.
+``nohz_full=`` boot argument, those cores are excluded by default.
Offline cores can be included in this mask, and if the core is later
brought online, the watchdog will be started based on the mask value.
-Typically this value would only be touched in the nohz_full case
+Typically this value would only be touched in the ``nohz_full`` case
to re-enable cores that by default were not running the watchdog,
if a kernel lockup was suspected on those cores.
echo 0,2-4 > /proc/sys/kernel/watchdog_cpumask
-watchdog_thresh:
-================
+watchdog_thresh
+===============
This value can be used to control the frequency of hrtimer and NMI
events and the soft and hard lockup thresholds. The default threshold
is 10 seconds.
-The softlockup threshold is (2 * watchdog_thresh). Setting this
+The softlockup threshold is (``2 * watchdog_thresh``). Setting this
tunable to zero will disable lockup detection altogether.
Written by Linus Walleij <linus.walleij@stericsson.com>
-Some ARM SoC:s have a so-called TCM (Tightly-Coupled Memory).
+Some ARM SoCs have a so-called TCM (Tightly-Coupled Memory).
This is usually just a few (4-64) KiB of RAM inside the ARM
processor.
-Due to being embedded inside the CPU The TCM has a
+Due to being embedded inside the CPU, the TCM has a
Harvard-architecture, so there is an ITCM (instruction TCM)
and a DTCM (data TCM). The DTCM can not contain any
instructions, but the ITCM can actually contain data.
The size of DTCM or ITCM is minimum 4KiB so the typical
minimum configuration is 4KiB ITCM and 4KiB DTCM.
-ARM CPU:s have special registers to read out status, physical
+ARM CPUs have special registers to read out status, physical
location and size of TCM memories. arch/arm/include/asm/cputype.h
defines a CPUID_TCM register that you can read out from the
system control coprocessor. Documentation from ARM can be found
Generic Block Device Capability
===============================
-This file documents the sysfs file block/<disk>/capability
+This file documents the sysfs file ``block/<disk>/capability``.
-capability is a hex word indicating which capabilities a specific disk
-supports. For more information on bits not listed here, see
-include/linux/genhd.h
+``capability`` is a bitfield, printed in hexadecimal, indicating which
+capabilities a specific block device supports:
-GENHD_FL_MEDIA_CHANGE_NOTIFY
-----------------------------
-
-Value: 4
-
-When this bit is set, the disk supports Asynchronous Notification
-of media change events. These events will be broadcast to user
-space via kernel uevent.
+.. kernel-doc:: include/linux/genhd.h
# ones.
extensions = ['kerneldoc', 'rstFlatTable', 'kernel_include', 'cdomain',
'kfigure', 'sphinx.ext.ifconfig', 'automarkup',
- 'maintainers_include']
+ 'maintainers_include', 'sphinx.ext.autosectionlabel' ]
+
+# Ensure that autosectionlabel will produce unique names
+autosectionlabel_prefix_document = True
+autosectionlabel_maxdepth = 2
# The name of the math extension changed on Sphinx 1.4
if (major == 1 and minor > 3) or (major > 1):
Core utilities
==============
+This section has general and "core core" documentation. The first is a
+massive grab-bag of kerneldoc info left over from the docbook days; it
+should really be broken up someday when somebody finds the energy to do
+it.
+
.. toctree::
:maxdepth: 1
kernel-api
+ workqueue
+ printk-formats
+ symbol-namespaces
+
+Data structures and low-level utilities
+=======================================
+
+Library functionality that is used throughout the kernel.
+
+.. toctree::
+ :maxdepth: 1
+
+ kobject
assoc_array
+ xarray
+ idr
+ circular-buffers
+ generic-radix-tree
+ packing
+ timekeeping
+ errseq
+
+Concurrency primitives
+======================
+
+How Linux keeps everything from happening at the same time. See
+:doc:`/locking/index` for more related documentation.
+
+.. toctree::
+ :maxdepth: 1
+
atomic_ops
- cachetlb
refcount-vs-atomic
- cpu_hotplug
- idr
local_ops
- workqueue
+ padata
+ ../RCU/index
+
+Low-level hardware management
+=============================
+
+Cache management, managing CPU hotplug, etc.
+
+.. toctree::
+ :maxdepth: 1
+
+ cachetlb
+ cpu_hotplug
+ memory-hotplug
genericirq
- xarray
- librs
- genalloc
- errseq
- packing
- printk-formats
- circular-buffers
- generic-radix-tree
+ protection-keys
+
+Memory management
+=================
+
+How to allocate and use memory in the kernel. Note that there is a lot
+more memory-management documentation in :doc:`/vm/index`.
+
+.. toctree::
+ :maxdepth: 1
+
memory-allocation
mm-api
+ genalloc
pin_user_pages
- gfp_mask-from-fs-io
- timekeeping
boot-time-mm
- memory-hotplug
- protection-keys
- ../RCU/index
- gcc-plugins
- symbol-namespaces
- padata
- ioctl
-
+ gfp_mask-from-fs-io
Interfaces for kernel debugging
===============================
debug-objects
tracepoint
+Everything else
+===============
+
+Documents that don't fit elsewhere or which have yet to be categorized.
+
+.. toctree::
+ :maxdepth: 1
+
+ librs
+
.. only:: subproject and html
Indices
usually embedded within some other structure which contains the stuff
the code is really interested in.
- No structure should EVER have more than one kobject embedded within it.
+ No structure should **EVER** have more than one kobject embedded within it.
If it does, the reference counting for the object is sure to be messed
up and incorrect, and your code will be buggy. So do not do this.
embedded in other structures. If you are used to thinking of things in
object-oriented terms, kobjects can be seen as a top-level, abstract class
from which other classes are derived. A kobject implements a set of
-capabilities which are not particularly useful by themselves, but which are
+capabilities which are not particularly useful by themselves, but are
nice to have in other objects. The C language does not allow for the
direct expression of inheritance, so other techniques - such as structure
embedding - must be used.
their own, but are invariably found embedded in the larger objects of
interest.)
-So, for example, the UIO code in drivers/uio/uio.c has a structure that
+So, for example, the UIO code in ``drivers/uio/uio.c`` has a structure that
defines the memory region associated with a uio device::
struct uio_map {
- struct kobject kobj;
- struct uio_mem *mem;
+ struct kobject kobj;
+ struct uio_mem *mem;
};
If you have a struct uio_map structure, finding its embedded kobject is
often have the opposite problem, however: given a struct kobject pointer,
what is the pointer to the containing structure? You must avoid tricks
(such as assuming that the kobject is at the beginning of the structure)
-and, instead, use the container_of() macro, found in <linux/kernel.h>::
+and, instead, use the container_of() macro, found in ``<linux/kernel.h>``::
container_of(pointer, type, member)
where:
- * "pointer" is the pointer to the embedded kobject,
- * "type" is the type of the containing structure, and
- * "member" is the name of the structure field to which "pointer" points.
+ * ``pointer`` is the pointer to the embedded kobject,
+ * ``type`` is the type of the containing structure, and
+ * ``member`` is the name of the structure field to which ``pointer`` points.
The return value from container_of() is a pointer to the corresponding
-container type. So, for example, a pointer "kp" to a struct kobject
-embedded *within* a struct uio_map could be converted to a pointer to the
-*containing* uio_map structure with::
+container type. So, for example, a pointer ``kp`` to a struct kobject
+embedded **within** a struct uio_map could be converted to a pointer to the
+**containing** uio_map structure with::
struct uio_map *u_map = container_of(kp, struct uio_map, kobj);
-For convenience, programmers often define a simple macro for "back-casting"
+For convenience, programmers often define a simple macro for **back-casting**
kobject pointers to the containing type. Exactly this happens in the
-earlier drivers/uio/uio.c, as you can see here::
+earlier ``drivers/uio/uio.c``, as you can see here::
struct uio_map {
- struct kobject kobj;
- struct uio_mem *mem;
+ struct kobject kobj;
+ struct uio_mem *mem;
};
#define to_map(map) container_of(map, struct uio_map, kobj)
register the kobject with sysfs, the function kobject_add() must be called::
int kobject_add(struct kobject *kobj, struct kobject *parent,
- const char *fmt, ...);
+ const char *fmt, ...);
This sets up the parent of the kobject and the name for the kobject
properly. If the kobject is to be associated with a specific kset,
int kobject_uevent(struct kobject *kobj, enum kobject_action action);
-Use the KOBJ_ADD action for when the kobject is first added to the kernel.
+Use the **KOBJ_ADD** action for when the kobject is first added to the kernel.
This should be done only after any attributes or children of the kobject
have been initialized properly, as userspace will instantly start to look
for them when this call happens.
When the kobject is removed from the kernel (details on how to do that are
-below), the uevent for KOBJ_REMOVE will be automatically created by the
+below), the uevent for **KOBJ_REMOVE** will be automatically created by the
kobject core, so the caller does not have to worry about doing that by
hand.
with the kobject_create_and_add(), can be of type kobj_attribute, so no
special custom attribute is needed to be created.
-See the example module, samples/kobject/kobject-example.c for an
+See the example module, ``samples/kobject/kobject-example.c`` for an
implementation of a simple kobject and attributes.
void my_object_release(struct kobject *kobj)
{
- struct my_object *mine = container_of(kobj, struct my_object, kobj);
+ struct my_object *mine = container_of(kobj, struct my_object, kobj);
- /* Perform any additional cleanup on this object, then... */
- kfree(mine);
+ /* Perform any additional cleanup on this object, then... */
+ kfree(mine);
}
One important point cannot be overstated: every kobject must have a
kobj_type::
struct kobj_type {
- void (*release)(struct kobject *kobj);
- const struct sysfs_ops *sysfs_ops;
- struct attribute **default_attrs;
- const struct kobj_ns_type_operations *(*child_ns_type)(struct kobject *kobj);
- const void *(*namespace)(struct kobject *kobj);
+ void (*release)(struct kobject *kobj);
+ const struct sysfs_ops *sysfs_ops;
+ struct attribute **default_attrs;
+ const struct kobj_ns_type_operations *(*child_ns_type)(struct kobject *kobj);
+ const void *(*namespace)(struct kobject *kobj);
};
This structure is used to describe a particular type of kobject (or, more
kset use::
struct kset *kset_create_and_add(const char *name,
- struct kset_uevent_ops *u,
- struct kobject *parent);
+ struct kset_uevent_ops *u,
+ struct kobject *parent);
When you are finished with the kset, call::
after kset_unregister() returns.
An example of using a kset can be seen in the
-samples/kobject/kset-example.c file in the kernel tree.
+``samples/kobject/kset-example.c`` file in the kernel tree.
If a kset wishes to control the uevent operations of the kobjects
associated with it, it can use the struct kset_uevent_ops to handle it::
struct kset_uevent_ops {
- int (*filter)(struct kset *kset, struct kobject *kobj);
- const char *(*name)(struct kset *kset, struct kobject *kobj);
- int (*uevent)(struct kset *kset, struct kobject *kobj,
- struct kobj_uevent_env *env);
+ int (*filter)(struct kset *kset, struct kobject *kobj);
+ const char *(*name)(struct kset *kset, struct kobject *kobj);
+ int (*uevent)(struct kset *kset, struct kobject *kobj,
+ struct kobj_uevent_env *env);
};
After a kobject has been registered with the kobject core successfully, it
must be cleaned up when the code is finished with it. To do that, call
kobject_put(). By doing this, the kobject core will automatically clean up
-all of the memory allocated by this kobject. If a KOBJ_ADD uevent has been
-sent for the object, a corresponding KOBJ_REMOVE uevent will be sent, and
+all of the memory allocated by this kobject. If a ``KOBJ_ADD`` uevent has been
+sent for the object, a corresponding ``KOBJ_REMOVE`` uevent will be sent, and
any other sysfs housekeeping will be handled for the caller properly.
If you need to do a two-stage delete of the kobject (say you are not
=========================
For a more complete example of using ksets and kobjects properly, see the
-example programs samples/kobject/{kobject-example.c,kset-example.c},
-which will be built as loadable modules if you select CONFIG_SAMPLE_KOBJECT.
+example programs ``samples/kobject/{kobject-example.c,kset-example.c}``,
+which will be built as loadable modules if you select ``CONFIG_SAMPLE_KOBJECT``.
+++ /dev/null
-Debugging Modules after 2.6.3
------------------------------
-
-In almost all distributions, the kernel asks for modules which don't
-exist, such as "net-pf-10" or whatever. Changing "modprobe -q" to
-"succeed" in this case is hacky and breaks some setups, and also we
-want to know if it failed for the fallback code for old aliases in
-fs/char_dev.c, for example.
-
-In the past a debugging message which would fill people's logs was
-emitted. This debugging message has been removed. The correct way
-of debugging module problems is something like this:
-
-echo '#! /bin/sh' > /tmp/modprobe
-echo 'echo "$@" >> /tmp/modprobe.log' >> /tmp/modprobe
-echo 'exec /sbin/modprobe "$@"' >> /tmp/modprobe
-chmod a+x /tmp/modprobe
-echo /tmp/modprobe > /proc/sys/kernel/modprobe
-
-Note that the above applies only when the *kernel* is requesting
-that the module be loaded -- it won't have any effect if that module
-is being loaded explicitly using "modprobe" from userspace.
may not correctly copy files from sysfs.
Solution
- Use ``cat``' to read ``.gcda`` files and ``cp -d`` to copy links.
+ Use ``cat`` to read ``.gcda`` files and ``cp -d`` to copy links.
Alternatively use the mechanism shown in Appendix B.
reported via /sys/kernel/debug/kmemleak. A similar method is used by the
Valgrind tool (``memcheck --leak-check``) to detect the memory leaks in
user-space applications.
-Kmemleak is supported on x86, arm, powerpc, sparc, sh, microblaze, ppc, mips, s390 and tile.
+Kmemleak is supported on x86, arm, arm64, powerpc, sparc, sh, microblaze, mips,
+s390, nds32, arc and xtensa.
Usage
-----
.. kernel-doc:: net/mac80211/sta_info.c
:doc: STA information lifetime rules
-Aggregation
-===========
+Aggregation Functions
+=====================
.. kernel-doc:: net/mac80211/sta_info.h
:functions: sta_ampdu_mlme
.. kernel-doc:: net/mac80211/sta_info.h
:functions: tid_ampdu_rx
-Synchronisation
-===============
+Synchronisation Functions
+=========================
TBD
DMAEngine documentation provides documents for various aspects of DMAEngine
framework.
-DMAEngine documentation
------------------------
+DMAEngine development documentation
+-----------------------------------
This book helps with DMAengine internal APIs and guide for DMAEngine device
driver writers.
While the typical use case for sync_state() is to have the kernel cleanly take
over management of devices from the bootloader, the usage of sync_state() is
not restricted to that. Use it whenever it makes sense to take an action after
-all the consumers of a device have probed.
+all the consumers of a device have probed::
int (*remove) (struct device *dev);
driver-model/index
basics
infrastructure
+ ioctl
early-userspace/index
pm/index
clk
connector
console
dcdbas
- edid
eisa
ipmb
isa
isapnp
+ io-mapping
+ io_ordering
generic-counter
lightnvm-pblk
memory-devices/index
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | ok |
- | riscv: | TODO |
+ | riscv: | ok |
| s390: | ok |
| sh: | ok |
| sparc: | ok |
- v9fs: Plan 9 Resource Sharing for Linux
- =======================================
+.. SPDX-License-Identifier: GPL-2.0
-ABOUT
+=======================================
+v9fs: Plan 9 Resource Sharing for Linux
+=======================================
+
+About
=====
v9fs is a Unix implementation of the Plan 9 9p remote filesystem protocol.
The best detailed explanation of the Linux implementation and applications of
the 9p client is available in the form of a USENIX paper:
+
http://www.usenix.org/events/usenix05/tech/freenix/hensbergen.html
Other applications are described in the following papers:
+
* XCPU & Clustering
- http://xcpu.org/papers/xcpu-talk.pdf
+ http://xcpu.org/papers/xcpu-talk.pdf
* KVMFS: control file system for KVM
- http://xcpu.org/papers/kvmfs.pdf
+ http://xcpu.org/papers/kvmfs.pdf
* CellFS: A New Programming Model for the Cell BE
- http://xcpu.org/papers/cellfs-talk.pdf
+ http://xcpu.org/papers/cellfs-talk.pdf
* PROSE I/O: Using 9p to enable Application Partitions
- http://plan9.escet.urjc.es/iwp9/cready/PROSE_iwp9_2006.pdf
+ http://plan9.escet.urjc.es/iwp9/cready/PROSE_iwp9_2006.pdf
* VirtFS: A Virtualization Aware File System pass-through
- http://goo.gl/3WPDg
+ http://goo.gl/3WPDg
-USAGE
+Usage
=====
-For remote file server:
+For remote file server::
mount -t 9p 10.10.1.2 /mnt/9
-For Plan 9 From User Space applications (http://swtch.com/plan9)
+For Plan 9 From User Space applications (http://swtch.com/plan9)::
mount -t 9p `namespace`/acme /mnt/9 -o trans=unix,uname=$USER
-For server running on QEMU host with virtio transport:
+For server running on QEMU host with virtio transport::
mount -t 9p -o trans=virtio <mount_tag> /mnt/9
associated "mount_tag" property. Available mount tags can be
seen by reading /sys/bus/virtio/drivers/9pnet_virtio/virtio<n>/mount_tag files.
-OPTIONS
+Options
=======
+ ============= ===============================================================
trans=name select an alternative transport. Valid options are
currently:
- unix - specifying a named pipe mount point
- tcp - specifying a normal TCP/IP connection
- fd - used passed file descriptors for connection
- (see rfdno and wfdno)
- virtio - connect to the next virtio channel available
- (from QEMU with trans_virtio module)
- rdma - connect to a specified RDMA channel
+
+ ======== ============================================
+ unix specifying a named pipe mount point
+ tcp specifying a normal TCP/IP connection
+ fd used passed file descriptors for connection
+ (see rfdno and wfdno)
+ virtio connect to the next virtio channel available
+ (from QEMU with trans_virtio module)
+ rdma connect to a specified RDMA channel
+ ======== ============================================
uname=name user name to attempt mount as on the remote server. The
server may override or ignore this value. Certain user
offering several exported file systems.
cache=mode specifies a caching policy. By default, no caches are used.
- none = default no cache policy, metadata and data
+
+ none
+ default no cache policy, metadata and data
alike are synchronous.
- loose = no attempts are made at consistency,
+ loose
+ no attempts are made at consistency,
intended for exclusive, read-only mounts
- fscache = use FS-Cache for a persistent, read-only
+ fscache
+ use FS-Cache for a persistent, read-only
cache backend.
- mmap = minimal cache that is only used for read-write
+ mmap
+ minimal cache that is only used for read-write
mmap. Northing else is cached, like cache=none
debug=n specifies debug level. The debug level is a bitmask.
- 0x01 = display verbose error messages
- 0x02 = developer debug (DEBUG_CURRENT)
- 0x04 = display 9p trace
- 0x08 = display VFS trace
- 0x10 = display Marshalling debug
- 0x20 = display RPC debug
- 0x40 = display transport debug
- 0x80 = display allocation debug
- 0x100 = display protocol message debug
- 0x200 = display Fid debug
- 0x400 = display packet debug
- 0x800 = display fscache tracing debug
+
+ ===== ================================
+ 0x01 display verbose error messages
+ 0x02 developer debug (DEBUG_CURRENT)
+ 0x04 display 9p trace
+ 0x08 display VFS trace
+ 0x10 display Marshalling debug
+ 0x20 display RPC debug
+ 0x40 display transport debug
+ 0x80 display allocation debug
+ 0x100 display protocol message debug
+ 0x200 display Fid debug
+ 0x400 display packet debug
+ 0x800 display fscache tracing debug
+ ===== ================================
rfdno=n the file descriptor for reading with trans=fd
noextend force legacy mode (no 9p2000.u or 9p2000.L semantics)
version=name Select 9P protocol version. Valid options are:
- 9p2000 - Legacy mode (same as noextend)
- 9p2000.u - Use 9P2000.u protocol
- 9p2000.L - Use 9P2000.L protocol
+
+ ======== ==============================
+ 9p2000 Legacy mode (same as noextend)
+ 9p2000.u Use 9P2000.u protocol
+ 9p2000.L Use 9P2000.L protocol
+ ======== ==============================
dfltuid attempt to mount as a particular uid
hosts. This functionality will be expanded in later versions.
access there are four access modes.
- user = if a user tries to access a file on v9fs
+ user
+ if a user tries to access a file on v9fs
filesystem for the first time, v9fs sends an
attach command (Tattach) for that user.
This is the default mode.
- <uid> = allows only user with uid=<uid> to access
+ <uid>
+ allows only user with uid=<uid> to access
the files on the mounted filesystem
- any = v9fs does single attach and performs all
+ any
+ v9fs does single attach and performs all
operations as one user
- client = ACL based access check on the 9p client
+ clien
+ ACL based access check on the 9p client
side for access validation
cachetag cache tag to use the specified persistent cache.
cache tags for existing cache sessions can be listed at
/sys/fs/9p/caches. (applies only to cache=fscache)
+ ============= ===============================================================
-RESOURCES
+Resources
=========
Protocol specifications are maintained on github:
For information on Plan 9 from User Space (Plan 9 applications and libraries
ported to Linux/BSD/OSX/etc) check out http://swtch.com/plan9
-
+.. SPDX-License-Identifier: GPL-2.0
+
+===============================
+Acorn Disc Filing System - ADFS
+===============================
+
Filesystems supported by ADFS
-----------------------------
Mount options for ADFS
----------------------
+ ============ ======================================================
uid=nnn All files in the partition will be owned by
user id nnn. Default 0 (root).
gid=nnn All files in the partition will be in group
ftsuffix=n When ftsuffix=0, no file type suffix will be applied.
When ftsuffix=1, a hexadecimal suffix corresponding to
the RISC OS file type will be added. Default 0.
+ ============ ======================================================
Mapping of ADFS permissions to Linux permissions
------------------------------------------------
ADFS permissions consist of the following:
- Owner read
- Owner write
- Other read
- Other write
+ - Owner read
+ - Owner write
+ - Other read
+ - Other write
(In older versions, an 'execute' permission did exist, but this
- does not hold the same meaning as the Linux 'execute' permission
- and is now obsolete).
+ does not hold the same meaning as the Linux 'execute' permission
+ and is now obsolete).
- The mapping is performed as follows:
+ The mapping is performed as follows::
Owner read -> -r--r--r--
Owner write -> --w--w---w
Possible other mode permissions -> ----rwxrwx
Hence, with the default masks, if a file is owner read/write, and
- not a UnixExec filetype, then the permissions will be:
+ not a UnixExec filetype, then the permissions will be::
-rw-------
However, if the masks were ownmask=0770,othmask=0007, then this would
- be modified to:
+ be modified to::
+
-rw-rw----
There is no restriction on what you can do with these masks. You may
wish that either read bits give read access to the file for all, but
- keep the default write protection (ownmask=0755,othmask=0577):
+ keep the default write protection (ownmask=0755,othmask=0577)::
-rw-r--r--
+.. SPDX-License-Identifier: GPL-2.0
+
+=============================
Overview of Amiga Filesystems
=============================
Not all varieties of the Amiga filesystems are supported for reading and
writing. The Amiga currently knows six different filesystems:
+============== ===============================================================
DOS\0 The old or original filesystem, not really suited for
hard disks and normally not used on them, either.
Supported read/write.
sense on hard disks. Supported read only.
DOS\5 The Fast File System with directory cache. Supported read only.
+============== ===============================================================
All of the above filesystems allow block sizes from 512 to 32K bytes.
Supported block sizes are: 512, 1024, 2048 and 4096 bytes. Larger blocks
Mount options for the AFFS
==========================
-protect If this option is set, the protection bits cannot be altered.
+protect
+ If this option is set, the protection bits cannot be altered.
-setuid[=uid] This sets the owner of all files and directories in the file
+setuid[=uid]
+ This sets the owner of all files and directories in the file
system to uid or the uid of the current user, respectively.
-setgid[=gid] Same as above, but for gid.
+setgid[=gid]
+ Same as above, but for gid.
-mode=mode Sets the mode flags to the given (octal) value, regardless
+mode=mode
+ Sets the mode flags to the given (octal) value, regardless
of the original permissions. Directories will get an x
permission if the corresponding r bit is set.
This is useful since most of the plain AmigaOS files
The file system will return an error when filename exceeds
standard maximum filename length (30 characters).
-reserved=num Sets the number of reserved blocks at the start of the
+reserved=num
+ Sets the number of reserved blocks at the start of the
partition to num. You should never need this option.
Default is 2.
-root=block Sets the block number of the root block. This should never
+root=block
+ Sets the block number of the root block. This should never
be necessary.
-bs=blksize Sets the blocksize to blksize. Valid block sizes are 512,
+bs=blksize
+ Sets the blocksize to blksize. Valid block sizes are 512,
1024, 2048 and 4096. Like the root option, this should
never be necessary, as the affs can figure it out itself.
-quiet The file system will not return an error for disallowed
+quiet
+ The file system will not return an error for disallowed
mode changes.
-verbose The volume name, file system type and block size will
+verbose
+ The volume name, file system type and block size will
be written to the syslog when the filesystem is mounted.
-mufs The filesystem is really a muFS, also it doesn't
+mufs
+ The filesystem is really a muFS, also it doesn't
identify itself as one. This option is necessary if
the filesystem wasn't formatted as muFS, but is used
as one.
-prefix=path Path will be prefixed to every absolute path name of
+prefix=path
+ Path will be prefixed to every absolute path name of
symbolic links on an AFFS partition. Default = "/".
(See below.)
-volume=name When symbolic links with an absolute path are created
+volume=name
+ When symbolic links with an absolute path are created
on an AFFS partition, name will be prepended as the
volume name. Default = "" (empty string).
(See below.)
- All other flags (suid, sgid, ...) are ignored and will
not be retained.
-
+
Newly created files and directories will get the user and group ID
of the current user and a mode according to the umask.
Examples
========
-Command line:
+Command line::
+
mount Archive/Amiga/Workbench3.1.adf /mnt -t affs -o loop,verbose
mount /dev/sda3 /Amiga -t affs
-/etc/fstab entry:
+/etc/fstab entry::
+
/dev/sdb5 /amiga/Workbench affs noauto,user,exec,verbose 0 0
IMPORTANT NOTE
If the damage is already done, the following should fix the RDB
(where <disk> is the device name).
-DO AT YOUR OWN RISK:
+
+DO AT YOUR OWN RISK::
dd if=/dev/<disk> of=rdb.tmp count=1
cp rdb.tmp rdb.fixed
'nofilenametruncate' mount option can change that behavior.
Case is ignored by the affs in filename matching, but Linux shells
-do care about the case. Example (with /wb being an affs mounted fs):
+do care about the case. Example (with /wb being an affs mounted fs)::
+
rm /wb/WRONGCASE
-will remove /mnt/wrongcase, but
+
+will remove /mnt/wrongcase, but::
+
rm /wb/WR*
+
will not since the names are matched by the shell.
The block allocation is designed for hard disk partitions. If more
If you are interested in an Amiga Emulator for Linux, look at
-http://web.archive.org/web/*/http://www.freiburg.linux.de/~uae/
+http://web.archive.org/web/%2E/http://www.freiburg.linux.de/~uae/
- ====================
- kAFS: AFS FILESYSTEM
- ====================
+.. SPDX-License-Identifier: GPL-2.0
-Contents:
+====================
+kAFS: AFS FILESYSTEM
+====================
+
+.. Contents:
- Overview.
- Usage.
- The @sys substitution.
-========
-OVERVIEW
+Overview
========
This filesystem provides a fairly simple secure AFS filesystem driver. It is
(*) pioctl() system call.
-===========
-COMPILATION
+Compilation
===========
The filesystem should be enabled by turning on the kernel configuration
-options:
+options::
CONFIG_AF_RXRPC - The RxRPC protocol transport
CONFIG_RXKAD - The RxRPC Kerberos security handler
CONFIG_AFS - The AFS filesystem
-Additionally, the following can be turned on to aid debugging:
+Additionally, the following can be turned on to aid debugging::
CONFIG_AF_RXRPC_DEBUG - Permit AF_RXRPC debugging to be enabled
CONFIG_AFS_DEBUG - Permit AFS debugging to be enabled
They permit the debugging messages to be turned on dynamically by manipulating
-the masks in the following files:
+the masks in the following files::
/sys/module/af_rxrpc/parameters/debug
/sys/module/kafs/parameters/debug
-=====
-USAGE
+Usage
=====
When inserting the driver modules the root cell must be specified along with a
-list of volume location server IP addresses:
+list of volume location server IP addresses::
modprobe rxrpc
modprobe kafs rootcell=cambridge.redhat.com:172.16.18.73:172.16.18.91
is the actual filesystem driver for the AFS filesystem.
Once the module has been loaded, more modules can be added by the following
-procedure:
+procedure::
echo add grand.central.org 18.9.48.14:128.2.203.61:130.237.48.87 >/proc/fs/afs/cells
Where the parameters to the "add" command are the name of a cell and a list of
volume location servers within that cell, with the latter separated by colons.
-Filesystems can be mounted anywhere by commands similar to the following:
+Filesystems can be mounted anywhere by commands similar to the following::
mount -t afs "%cambridge.redhat.com:root.afs." /afs
mount -t afs "#cambridge.redhat.com:root.cell." /afs/cambridge
Additional cells can be added through /proc (see later section).
-===========
-MOUNTPOINTS
+Mountpoints
===========
AFS has a concept of mountpoints. In AFS terms, these are specially formatted
unmounted, otherwise error EBUSY will be returned.
This can be used by the administrator to attempt to unmount the whole AFS tree
-mounted on /afs in one go by doing:
+mounted on /afs in one go by doing::
umount /afs
-============
-DYNAMIC ROOT
+Dynamic Root
============
A mount option is available to create a serverless mount that is only usable
-for dynamic lookup. Creating such a mount can be done by, for example:
+for dynamic lookup. Creating such a mount can be done by, for example::
mount -t afs none /afs -o dyn
This creates a mount that just has an empty directory at the root. Attempting
to look up a name in this directory will cause a mountpoint to be created that
-looks up a cell of the same name, for example:
+looks up a cell of the same name, for example::
ls /afs/grand.central.org/
-===============
-PROC FILESYSTEM
+Proc Filesystem
===============
The AFS modules creates a "/proc/fs/afs/" directory and populates it:
(*) A "cells" file that lists cells currently known to the afs module and
- their usage counts:
+ their usage counts::
[root@andromeda ~]# cat /proc/fs/afs/cells
USE NAME
3 cambridge.redhat.com
(*) A directory per cell that contains files that list volume location
- servers, volumes, and active servers known within that cell.
+ servers, volumes, and active servers known within that cell::
[root@andromeda ~]# cat /proc/fs/afs/cambridge.redhat.com/servers
USE ADDR STATE
1 Val 20000000 20000001 20000002 root.afs
-=================
-THE CELL DATABASE
+The Cell Database
=================
The filesystem maintains an internal database of all the cells it knows and the
"rootcell=" argument or, if compiled in, using a "kafs.rootcell=" argument on
the kernel command line.
-Further cells can be added by commands similar to the following:
+Further cells can be added by commands similar to the following::
echo add CELLNAME VLADDR[:VLADDR][:VLADDR]... >/proc/fs/afs/cells
echo add grand.central.org 18.9.48.14:128.2.203.61:130.237.48.87 >/proc/fs/afs/cells
No other cell database operations are available at this time.
-========
-SECURITY
+Security
========
Secure operations are initiated by acquiring a key using the klog program. A
http://people.redhat.com/~dhowells/rxrpc/klog.c
-This should be compiled by:
+This should be compiled by::
make klog LDLIBS="-lcrypto -lcrypt -lkrb4 -lkeyutils"
-And then run as:
+And then run as::
./klog
Assuming it's successful, this adds a key of type RxRPC, named for the service
and cell, eg: "afs@<cellname>". This can be viewed with the keyctl program or
-by cat'ing /proc/keys:
+by cat'ing /proc/keys::
[root@andromeda ~]# keyctl show
Session Keyring
open the file.
-=====================
-THE @SYS SUBSTITUTION
+The @sys Substitution
=====================
The list of up to 16 @sys substitutions for the current network namespace can
-be configured by writing a list to /proc/fs/afs/sysname:
+be configured by writing a list to /proc/fs/afs/sysname::
[root@andromeda ~]# echo foo amd64_linux_26 >/proc/fs/afs/sysname
-or cleared entirely by writing an empty list:
+or cleared entirely by writing an empty list::
[root@andromeda ~]# echo >/proc/fs/afs/sysname
-The current list for current network namespace can be retrieved by:
+The current list for current network namespace can be retrieved by::
[root@andromeda ~]# cat /proc/fs/afs/sysname
foo
+.. SPDX-License-Identifier: GPL-2.0
+====================================================================
Miscellaneous Device control operations for the autofs kernel module
====================================================================
module source you will see a third type called an offset, which is just
a direct mount in disguise) and indirect.
-Here is a master map with direct and indirect map entries:
+Here is a master map with direct and indirect map entries::
-/- /etc/auto.direct
-/test /etc/auto.indirect
+ /- /etc/auto.direct
+ /test /etc/auto.indirect
-and the corresponding map files:
+and the corresponding map files::
-/etc/auto.direct:
+ /etc/auto.direct:
-/automount/dparse/g6 budgie:/autofs/export1
-/automount/dparse/g1 shark:/autofs/export1
-and so on.
+ /automount/dparse/g6 budgie:/autofs/export1
+ /automount/dparse/g1 shark:/autofs/export1
+ and so on.
-/etc/auto.indirect:
+/etc/auto.indirect::
-g1 shark:/autofs/export1
-g6 budgie:/autofs/export1
-and so on.
+ g1 shark:/autofs/export1
+ g6 budgie:/autofs/export1
+ and so on.
For the above indirect map an autofs file system is mounted on /test and
mounts are triggered for each sub-directory key by the inode lookup
But, each entry in direct and indirect maps can have offsets (making
them multi-mount map entries).
-For example, an indirect mount map entry could also be:
+For example, an indirect mount map entry could also be::
-g1 \
- / shark:/autofs/export5/testing/test \
- /s1 shark:/autofs/export/testing/test/s1 \
- /s2 shark:/autofs/export5/testing/test/s2 \
- /s1/ss1 shark:/autofs/export1 \
- /s2/ss2 shark:/autofs/export2
+ g1 \
+ / shark:/autofs/export5/testing/test \
+ /s1 shark:/autofs/export/testing/test/s1 \
+ /s2 shark:/autofs/export5/testing/test/s2 \
+ /s1/ss1 shark:/autofs/export1 \
+ /s2/ss2 shark:/autofs/export2
-and a similarly a direct mount map entry could also be:
+and a similarly a direct mount map entry could also be::
-/automount/dparse/g1 \
- / shark:/autofs/export5/testing/test \
- /s1 shark:/autofs/export/testing/test/s1 \
- /s2 shark:/autofs/export5/testing/test/s2 \
- /s1/ss1 shark:/autofs/export2 \
- /s2/ss2 shark:/autofs/export2
+ /automount/dparse/g1 \
+ / shark:/autofs/export5/testing/test \
+ /s1 shark:/autofs/export/testing/test/s1 \
+ /s2 shark:/autofs/export5/testing/test/s2 \
+ /s1/ss1 shark:/autofs/export2 \
+ /s2/ss2 shark:/autofs/export2
One of the issues with version 4 of autofs was that, when mounting an
entry with a large number of offsets, possibly with nesting, we needed
The control interface is opening a device node, typically /dev/autofs.
All the ioctls use a common structure to pass the needed parameter
-information and return operation results:
-
-struct autofs_dev_ioctl {
- __u32 ver_major;
- __u32 ver_minor;
- __u32 size; /* total size of data passed in
- * including this struct */
- __s32 ioctlfd; /* automount command fd */
-
- /* Command parameters */
- union {
- struct args_protover protover;
- struct args_protosubver protosubver;
- struct args_openmount openmount;
- struct args_ready ready;
- struct args_fail fail;
- struct args_setpipefd setpipefd;
- struct args_timeout timeout;
- struct args_requester requester;
- struct args_expire expire;
- struct args_askumount askumount;
- struct args_ismountpoint ismountpoint;
- };
-
- char path[0];
-};
+information and return operation results::
+
+ struct autofs_dev_ioctl {
+ __u32 ver_major;
+ __u32 ver_minor;
+ __u32 size; /* total size of data passed in
+ * including this struct */
+ __s32 ioctlfd; /* automount command fd */
+
+ /* Command parameters */
+ union {
+ struct args_protover protover;
+ struct args_protosubver protosubver;
+ struct args_openmount openmount;
+ struct args_ready ready;
+ struct args_fail fail;
+ struct args_setpipefd setpipefd;
+ struct args_timeout timeout;
+ struct args_requester requester;
+ struct args_expire expire;
+ struct args_askumount askumount;
+ struct args_ismountpoint ismountpoint;
+ };
+
+ char path[0];
+ };
The ioctlfd field is a mount point file descriptor of an autofs mount
point. It is returned by the open call and is used by all calls except
structure sent from user space.
This structure can be initialized before setting specific fields by using
-the void function call init_autofs_dev_ioctl(struct autofs_dev_ioctl *).
+the void function call init_autofs_dev_ioctl(``struct autofs_dev_ioctl *``).
All of the ioctls perform a copy of this structure from user space to
kernel space and return -EINVAL if the size parameter is smaller than
+.. SPDX-License-Identifier: GPL-2.0
+
+=========================
BeOS filesystem for Linux
+=========================
Document last updated: Dec 6, 2001
-WARNING
+Warning
=======
Make sure you understand that this is alpha software. This means that the
-implementation is neither complete nor well-tested.
+implementation is neither complete nor well-tested.
I DISCLAIM ALL RESPONSIBILITY FOR ANY POSSIBLE BAD EFFECTS OF THIS CODE!
-LICENSE
-=====
-This software is covered by the GNU General Public License.
+License
+=======
+This software is covered by the GNU General Public License.
See the file COPYING for the complete text of the license.
Or the GNU website: <http://www.gnu.org/licenses/licenses.html>
-AUTHOR
-=====
+Author
+======
The largest part of the code written by Will Dyson <will_dyson@pobox.com>
He has been working on the code since Aug 13, 2001. See the changelog for
details.
Original Author: Makoto Kato <m_kato@ga2.so-net.ne.jp>
+
His original code can still be found at:
<http://hp.vector.co.jp/authors/VA008030/bfs/>
+
Does anyone know of a more current email address for Makoto? He doesn't
respond to the address given above...
This filesystem doesn't have a maintainer.
-WHAT IS THIS DRIVER?
-==================
-This module implements the native filesystem of BeOS http://www.beincorporated.com/
+What is this Driver?
+====================
+This module implements the native filesystem of BeOS http://www.beincorporated.com/
for the linux 2.4.1 and later kernels. Currently it is a read-only
implementation.
Which is it, BFS or BEFS?
-================
-Be, Inc said, "BeOS Filesystem is officially called BFS, not BeFS".
+=========================
+Be, Inc said, "BeOS Filesystem is officially called BFS, not BeFS".
But Unixware Boot Filesystem is called bfs, too. And they are already in
the kernel. Because of this naming conflict, on Linux the BeOS
filesystem is called befs.
-HOW TO INSTALL
+How to Install
==============
step 1. Install the BeFS patch into the source code tree of linux.
patch -p1 < /path/to/patch-befs-xxx
if the patching step fails (i.e. there are rejected hunks), you can try to
-figure it out yourself (it shouldn't be hard), or mail the maintainer
+figure it out yourself (it shouldn't be hard), or mail the maintainer
(Will Dyson <will_dyson@pobox.com>) for help.
step 2. Configuration & make kernel
The linux kernel has many compile-time options. Most of them are beyond the
scope of this document. I suggest the Kernel-HOWTO document as a good general
-reference on this topic. http://www.linuxdocs.org/HOWTOs/Kernel-HOWTO-4.html
+reference on this topic. http://www.linuxdocs.org/HOWTOs/Kernel-HOWTO-4.html
-However, to use the BeFS module, you must enable it at configure time.
+However, to use the BeFS module, you must enable it at configure time::
cd /foo/bar/linux
make menuconfig (or xconfig)
See the kernel howto <http://www.linux.com/howto/Kernel-HOWTO.html> for
instructions on this critical step.
-USING BFS
+Using BFS
=========
To use the BeOS filesystem, use filesystem type 'befs'.
-ex)
+ex::
+
mount -t befs /dev/fd0 /beos
-MOUNT OPTIONS
+Mount Options
=============
+
+============= ===========================================================
uid=nnn All files in the partition will be owned by user id nnn.
gid=nnn All files in the partition will be in group nnn.
iocharset=xxx Use xxx as the name of the NLS translation table.
debug The driver will output debugging information to the syslog.
+============= ===========================================================
-HOW TO GET LASTEST VERSION
+How to Get Lastest Version
==========================
The latest version is currently available at:
<http://befs-driver.sourceforge.net/>
-ANY KNOWN BUGS?
-===========
+Any Known Bugs?
+===============
As of Jan 20, 2002:
-
+
None
-SPECIAL THANKS
+Special Thanks
==============
Dominic Giampalo ... Writing "Practical file system design with Be filesystem"
+
Hiroyuki Yamada ... Testing LinuxPPC.
-BFS FILESYSTEM FOR LINUX
+.. SPDX-License-Identifier: GPL-2.0
+
+========================
+BFS Filesystem for Linux
========================
The BFS filesystem is used by SCO UnixWare OS for the /stand slice, which
know the partition number and the kernel must support UnixWare disk slices
(CONFIG_UNIXWARE_DISKLABEL config option). However BFS support does not
depend on having UnixWare disklabel support because one can also mount
-BFS filesystem via loopback:
+BFS filesystem via loopback::
-# losetup /dev/loop0 stand.img
-# mount -t bfs /dev/loop0 /mnt/stand
+ # losetup /dev/loop0 stand.img
+ # mount -t bfs /dev/loop0 /mnt/stand
-where stand.img is a file containing the image of BFS filesystem.
+where stand.img is a file containing the image of BFS filesystem.
When you have finished using it and umounted you need to also deallocate
-/dev/loop0 device by:
+/dev/loop0 device by::
-# losetup -d /dev/loop0
+ # losetup -d /dev/loop0
-You can simplify mounting by just typing:
+You can simplify mounting by just typing::
-# mount -t bfs -o loop stand.img /mnt/stand
+ # mount -t bfs -o loop stand.img /mnt/stand
-this will allocate the first available loopback device (and load loop.o
+this will allocate the first available loopback device (and load loop.o
kernel module if necessary) automatically. If the loopback driver is not
loaded automatically, make sure that you have compiled the module and
that modprobe is functioning. Beware that umount will not deallocate
losetup(8). Read losetup(8) manpage for more info.
To create the BFS image under UnixWare you need to find out first which
-slice contains it. The command prtvtoc(1M) is your friend:
+slice contains it. The command prtvtoc(1M) is your friend::
-# prtvtoc /dev/rdsk/c0b0t0d0s0
+ # prtvtoc /dev/rdsk/c0b0t0d0s0
(assuming your root disk is on target=0, lun=0, bus=0, controller=0). Then you
look for the slice with tag "STAND", which is usually slice 10. With this
-information you can use dd(1) to create the BFS image:
+information you can use dd(1) to create the BFS image::
-# umount /stand
-# dd if=/dev/rdsk/c0b0t0d0sa of=stand.img bs=512
+ # umount /stand
+ # dd if=/dev/rdsk/c0b0t0d0sa of=stand.img bs=512
Just in case, you can verify that you have done the right thing by checking
-the magic number:
+the magic number::
-# od -Ad -tx4 stand.img | more
+ # od -Ad -tx4 stand.img | more
The first 4 bytes should be 0x1badface.
+.. SPDX-License-Identifier: GPL-2.0
+
+=====
BTRFS
=====
+.. SPDX-License-Identifier: GPL-2.0
+
+============================
Ceph Distributed File System
============================
* Easy deployment: most FS components are userspace daemons
Also,
+
* Flexible snapshots (on any directory)
* Recursive accounting (nested files, directories, bytes)
Finally, Ceph also allows quotas to be set on any directory in the system.
The quota can restrict the number of bytes or the number of files stored
beneath that point in the directory hierarchy. Quotas can be set using
-extended attributes 'ceph.quota.max_files' and 'ceph.quota.max_bytes', eg:
+extended attributes 'ceph.quota.max_files' and 'ceph.quota.max_bytes', eg::
setfattr -n ceph.quota.max_bytes -v 100000000 /some/dir
getfattr -n ceph.quota.max_bytes /some/dir
Mount Syntax
============
-The basic mount syntax is:
+The basic mount syntax is::
# mount -t ceph monip[:port][,monip2[:port]...]:/[subdir] mnt
full list when it connects. (However, if the monitor you specify
happens to be down, the mount won't succeed.) The port can be left
off if the monitor is using the default. So if the monitor is at
-1.2.3.4,
+1.2.3.4::
# mount -t ceph 1.2.3.4:/ /mnt/ceph
available modes are "no" and "clean". The default is "no".
* no: never attempt to reconnect when client detects that it has been
- blacklisted. Operations will generally fail after being blacklisted.
+ blacklisted. Operations will generally fail after being blacklisted.
* clean: client reconnects to the ceph cluster automatically when it
- detects that it has been blacklisted. During reconnect, client drops
- dirty data/metadata, invalidates page caches and writable file handles.
- After reconnect, file locks become stale because the MDS loses track
- of them. If an inode contains any stale file locks, read/write on the
- inode is not allowed until applications release all stale file locks.
+ detects that it has been blacklisted. During reconnect, client drops
+ dirty data/metadata, invalidates page caches and writable file handles.
+ After reconnect, file locks become stale because the MDS loses track
+ of them. If an inode contains any stale file locks, read/write on the
+ inode is not allowed until applications release all stale file locks.
More Information
================
https://ceph.com/
The Linux kernel client source tree is available at
- https://github.com/ceph/ceph-client.git
- git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
+ - https://github.com/ceph/ceph-client.git
+ - git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
and the source for the full system is at
https://github.com/ceph/ceph.git
In order to mount, the network stack will also need to be set up by
using 'ip=' config option. For more details, see
-Documentation/filesystems/nfs/nfsroot.txt.
+Documentation/admin-guide/nfs/nfsroot.rst.
A CIFS root mount currently requires the use of SMB1+UNIX Extensions
which is only supported by the Samba server. SMB1 is the older
+.. SPDX-License-Identifier: GPL-2.0
- Cramfs - cram a filesystem onto a small ROM
+===========================================
+Cramfs - cram a filesystem onto a small ROM
+===========================================
-cramfs is designed to be simple and small, and to compress things well.
+cramfs is designed to be simple and small, and to compress things well.
It uses the zlib routines to compress a file one page at a time, and
allows random page access. The meta-data is not compressed, but is
expressed in a very terse representation to make it use much less
-diskspace than traditional filesystems.
+diskspace than traditional filesystems.
You can't write to a cramfs filesystem (making it compressible and
compact also makes it _very_ hard to update on-the-fly), so you have to
Hard links are supported, but hard linked files
will still have a link count of 1 in the cramfs image.
-Cramfs directories have no `.' or `..' entries. Directories (like
+Cramfs directories have no ``.`` or ``..`` entries. Directories (like
every other file on cramfs) always have a link count of 1. (There's
-no need to use -noleaf in `find', btw.)
+no need to use -noleaf in ``find``, btw.)
No timestamps are stored in a cramfs, so these default to the epoch
(1970 GMT). Recently-accessed files may have updated timestamps, but
(Flash device in physical memory map). MTD partitions based on such devices
are fine too. Then that device should be specified with the "mtd:" prefix
as the mount device argument. For example, to mount the MTD device named
-"fs_partition" on the /mnt directory:
+"fs_partition" on the /mnt directory::
-$ mount -t cramfs mtd:fs_partition /mnt
+ $ mount -t cramfs mtd:fs_partition /mnt
To boot a kernel with this as root filesystem, suffice to specify
something like "root=mtd:fs_partition" on the kernel command line.
For /usr/share/magic
--------------------
+===== ======================= =======================
0 ulelong 0x28cd3d45 Linux cramfs offset 0
>4 ulelong x size %d
>8 ulelong x flags 0x%x
>552 ulelong x fsid.blocks %d
>556 ulelong x fsid.files %d
>560 string >\0 name "%.16s"
+===== ======================= =======================
Hacker Notes
-Copyright 2009 Jonathan Corbet <corbet@lwn.net>
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
+=======
+DebugFS
+=======
+
+Copyright |copy| 2009 Jonathan Corbet <corbet@lwn.net>
Debugfs exists as a simple way for kernel developers to make information
available to user space. Unlike /proc, which is only meant for information
debugfs has no rules at all. Developers can put any information they want
there. The debugfs filesystem is also intended to not serve as a stable
ABI to user space; in theory, there are no stability constraints placed on
-files exported there. The real world is not always so simple, though [1];
+files exported there. The real world is not always so simple, though [1]_;
even debugfs interfaces are best designed with the idea that they will need
to be maintained forever.
-Debugfs is typically mounted with a command like:
+Debugfs is typically mounted with a command like::
mount -t debugfs none /sys/kernel/debug
Code using debugfs should include <linux/debugfs.h>. Then, the first order
of business will be to create at least one directory to hold a set of
-debugfs files:
+debugfs files::
struct dentry *debugfs_create_dir(const char *name, struct dentry *parent);
indication that the kernel has been built without debugfs support and none
of the functions described below will work.
-The most general way to create a file within a debugfs directory is with:
+The most general way to create a file within a debugfs directory is with::
struct dentry *debugfs_create_file(const char *name, umode_t mode,
struct dentry *parent, void *data,
missing.
Create a file with an initial size, the following function can be used
-instead:
+instead::
struct dentry *debugfs_create_file_size(const char *name, umode_t mode,
struct dentry *parent, void *data,
In a number of cases, the creation of a set of file operations is not
actually necessary; the debugfs code provides a number of helper functions
for simple situations. Files containing a single integer value can be
-created with any of:
+created with any of::
void debugfs_create_u8(const char *name, umode_t mode,
struct dentry *parent, u8 *value);
These files support both reading and writing the given value; if a specific
file should not be written to, simply set the mode bits accordingly. The
values in these files are in decimal; if hexadecimal is more appropriate,
-the following functions can be used instead:
+the following functions can be used instead::
void debugfs_create_x8(const char *name, umode_t mode,
struct dentry *parent, u8 *value);
These functions are useful as long as the developer knows the size of the
value to be exported. Some types can have different widths on different
architectures, though, complicating the situation somewhat. There are
-functions meant to help out in such special cases:
+functions meant to help out in such special cases::
void debugfs_create_size_t(const char *name, umode_t mode,
struct dentry *parent, size_t *value);
a variable of type size_t.
Similarly, there are helpers for variables of type unsigned long, in decimal
-and hexadecimal:
+and hexadecimal::
struct dentry *debugfs_create_ulong(const char *name, umode_t mode,
struct dentry *parent,
void debugfs_create_xul(const char *name, umode_t mode,
struct dentry *parent, unsigned long *value);
-Boolean values can be placed in debugfs with:
+Boolean values can be placed in debugfs with::
struct dentry *debugfs_create_bool(const char *name, umode_t mode,
struct dentry *parent, bool *value);
N, followed by a newline. If written to, it will accept either upper- or
lower-case values, or 1 or 0. Any other input will be silently ignored.
-Also, atomic_t values can be placed in debugfs with:
+Also, atomic_t values can be placed in debugfs with::
void debugfs_create_atomic_t(const char *name, umode_t mode,
struct dentry *parent, atomic_t *value)
will set atomic_t values.
Another option is exporting a block of arbitrary binary data, with
-this structure and function:
+this structure and function::
struct debugfs_blob_wrapper {
void *data;
often during development, even if little such code reaches mainline.
Debugfs offers two functions: one to make a registers-only file, and
another to insert a register block in the middle of another sequential
-file.
+file::
struct debugfs_reg32 {
char *name;
using __stringify, and a number of register names (macros) are actually
byte offsets over a base for the register block.
-If you want to dump an u32 array in debugfs, you can create file with:
+If you want to dump an u32 array in debugfs, you can create file with::
void debugfs_create_u32_array(const char *name, umode_t mode,
struct dentry *parent,
the number of elements in the array. Note: Once array is created its
size can not be changed.
-There is a helper function to create device related seq_file:
+There is a helper function to create device related seq_file::
struct dentry *debugfs_create_devm_seqfile(struct device *dev,
const char *name,
the "read_fn" is a function pointer which to be called to print the
seq_file content.
-There are a couple of other directory-oriented helper functions:
+There are a couple of other directory-oriented helper functions::
- struct dentry *debugfs_rename(struct dentry *old_dir,
+ struct dentry *debugfs_rename(struct dentry *old_dir,
struct dentry *old_dentry,
- struct dentry *new_dir,
+ struct dentry *new_dir,
const char *new_name);
- struct dentry *debugfs_create_symlink(const char *name,
+ struct dentry *debugfs_create_symlink(const char *name,
struct dentry *parent,
const char *target);
will be a lot of stale pointers and no end of highly antisocial behavior.
So all debugfs users - at least those which can be built as modules - must
be prepared to remove all files and directories they create there. A file
-can be removed with:
+can be removed with::
void debugfs_remove(struct dentry *dentry);
Once upon a time, debugfs users were required to remember the dentry
pointer for every debugfs file they created so that all files could be
cleaned up. We live in more civilized times now, though, and debugfs users
-can call:
+can call::
void debugfs_remove_recursive(struct dentry *dentry);
top-level directory, the entire hierarchy below that directory will be
removed.
-Notes:
- [1] http://lwn.net/Articles/309298/
+.. [1] http://lwn.net/Articles/309298/
-dlmfs
-==================
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
+=====
+DLMFS
+=====
+
A minimal DLM userspace interface implemented via a virtual file
system.
dlmfs is built with OCFS2 as it requires most of its infrastructure.
-Project web page: http://ocfs2.wiki.kernel.org
-Tools web page: https://github.com/markfasheh/ocfs2-tools
-OCFS2 mailing lists: http://oss.oracle.com/projects/ocfs2/mailman/
+:Project web page: http://ocfs2.wiki.kernel.org
+:Tools web page: https://github.com/markfasheh/ocfs2-tools
+:OCFS2 mailing lists: http://oss.oracle.com/projects/ocfs2/mailman/
All code copyright 2005 Oracle except when otherwise noted.
-CREDITS
+Credits
=======
-Some code taken from ramfs which is Copyright (C) 2000 Linus Torvalds
+Some code taken from ramfs which is Copyright |copy| 2000 Linus Torvalds
and Transmeta Corp.
Mark Fasheh <mark.fasheh@oracle.com>
open(2) with O_CREAT to ensure the resource inode is created - dlmfs does
not automatically create inodes for existing lock resources.
+============ ===========================
Open Flag Lock Request Type
---------- -----------------
+============ ===========================
O_RDONLY Shared Read
O_RDWR Exclusive
+============ ===========================
+
+============ ===========================
Open Flag Resulting Locking Behavior
---------- --------------------------
+============ ===========================
O_NONBLOCK Trylock operation
+============ ===========================
You must provide exactly one of O_RDONLY or O_RDWR.
+.. SPDX-License-Identifier: GPL-2.0
+
+======================================================
eCryptfs: A stacked cryptographic filesystem for Linux
+======================================================
eCryptfs is free software. Please see the file COPYING for details.
For documentation, please see the files in the doc/ subdirectory. For
building and installation instructions please see the INSTALL file.
-Maintainer: Phillip Hellewell
-Lead developer: Michael A. Halcrow <mhalcrow@us.ibm.com>
-Developers: Michael C. Thompson
- Kent Yoder
-Web Site: http://ecryptfs.sf.net
+:Maintainer: Phillip Hellewell
+:Lead developer: Michael A. Halcrow <mhalcrow@us.ibm.com>
+:Developers: Michael C. Thompson
+ Kent Yoder
+:Web Site: http://ecryptfs.sf.net
This software is currently undergoing development. Make sure to
maintain a backup copy of any data you write into eCryptfs.
http://sourceforge.net/projects/ecryptfs/
Userspace requirements include:
- - David Howells' userspace keyring headers and libraries (version
- 1.0 or higher), obtainable from
- http://people.redhat.com/~dhowells/keyutils/
- - Libgcrypt
+
+- David Howells' userspace keyring headers and libraries (version
+ 1.0 or higher), obtainable from
+ http://people.redhat.com/~dhowells/keyutils/
+- Libgcrypt
-NOTES
+.. note::
-In the beta/experimental releases of eCryptfs, when you upgrade
-eCryptfs, you should copy the files to an unencrypted location and
-then copy the files back into the new eCryptfs mount to migrate the
-files.
+ In the beta/experimental releases of eCryptfs, when you upgrade
+ eCryptfs, you should copy the files to an unencrypted location and
+ then copy the files back into the new eCryptfs mount to migrate the
+ files.
-MOUNT-WIDE PASSPHRASE
+Mount-wide Passphrase
+=====================
Create a new directory into which eCryptfs will write its encrypted
files (i.e., /root/crypt). Then, create the mount point directory
-(i.e., /mnt/crypt). Now it's time to mount eCryptfs:
+(i.e., /mnt/crypt). Now it's time to mount eCryptfs::
-mount -t ecryptfs /root/crypt /mnt/crypt
+ mount -t ecryptfs /root/crypt /mnt/crypt
You should be prompted for a passphrase and a salt (the salt may be
blank).
-Try writing a new file:
+Try writing a new file::
-echo "Hello, World" > /mnt/crypt/hello.txt
+ echo "Hello, World" > /mnt/crypt/hello.txt
The operation will complete. Notice that there is a new file in
/root/crypt that is at least 12288 bytes in size (depending on your
Then umount /mnt/crypt and mount again per the instructions given
above.
-cat /mnt/crypt/hello.txt
+::
+
+ cat /mnt/crypt/hello.txt
-NOTES
+Notes
+=====
eCryptfs version 0.1 should only be mounted on (1) empty directories
or (2) directories containing files only created by eCryptfs. If you
+.. SPDX-License-Identifier: GPL-2.0
+=======================================
efivarfs - a (U)EFI variable filesystem
+=======================================
The efivarfs filesystem was created to address the shortcomings of
using entries in sysfs to maintain EFI variables. The old sysfs EFI
Variables can be created, deleted and modified with the efivarfs
filesystem.
-efivarfs is typically mounted like this,
+efivarfs is typically mounted like this::
mount -t efivarfs none /sys/firmware/efi/efivars
+.. SPDX-License-Identifier: GPL-2.0
+
+======================================
+Enhanced Read-Only File System - EROFS
+======================================
+
Overview
========
scalability, but be kept simple and high performance.
It is designed as a better filesystem solution for the following scenarios:
+
- read-only storage media or
- part of a fully trusted read-only solution, which means it needs to be
for those embedded devices with limited memory (ex, smartphone);
Here is the main features of EROFS:
+
- Little endian on-disk design;
- Currently 4KB block size (nobh) and therefore maximum 16TB address space;
- Metadata & data could be mixed by design;
- 2 inode versions for different requirements:
+
+ ===================== ============ =====================================
compact (v1) extended (v2)
- Inode metadata size: 32 bytes 64 bytes
- Max file size: 4 GB 16 EB (also limited by max. vol size)
- Max uids/gids: 65536 4294967296
- File change time: no yes (64 + 32-bit timestamp)
- Max hardlinks: 65536 4294967296
- Metadata reserved: 4 bytes 14 bytes
+ ===================== ============ =====================================
+ Inode metadata size 32 bytes 64 bytes
+ Max file size 4 GB 16 EB (also limited by max. vol size)
+ Max uids/gids 65536 4294967296
+ File change time no yes (64 + 32-bit timestamp)
+ Max hardlinks 65536 4294967296
+ Metadata reserved 4 bytes 14 bytes
+ ===================== ============ =====================================
- Support extended attributes (xattrs) as an option;
The following git tree provides the file system user-space tools under
development (ex, formatting tool mkfs.erofs):
->> git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs-utils.git
+
+- git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs-utils.git
Bugs and patches are welcome, please kindly help us and send to the following
linux-erofs mailing list:
->> linux-erofs mailing list <linux-erofs@lists.ozlabs.org>
+
+- linux-erofs mailing list <linux-erofs@lists.ozlabs.org>
Mount options
=============
+=================== =========================================================
(no)user_xattr Setup Extended User Attributes. Note: xattr is enabled
by default if CONFIG_EROFS_FS_XATTR is selected.
(no)acl Setup POSIX Access Control List. Note: acl is enabled
by default if CONFIG_EROFS_FS_POSIX_ACL is selected.
cache_strategy=%s Select a strategy for cached decompression from now on:
- disabled: In-place I/O decompression only;
- readahead: Cache the last incomplete compressed physical
+
+ ========== =============================================
+ disabled In-place I/O decompression only;
+ readahead Cache the last incomplete compressed physical
cluster for further reading. It still does
in-place I/O decompression for the rest
compressed physical clusters;
- readaround: Cache the both ends of incomplete compressed
+ readaround Cache the both ends of incomplete compressed
physical clusters for further reading.
It still does in-place I/O decompression
for the rest compressed physical clusters.
+ ========== =============================================
+=================== =========================================================
On-disk details
===============
Summary
-------
Different from other read-only file systems, an EROFS volume is designed
-to be as simple as possible:
+to be as simple as possible::
|-> aligned with the block size
____________________________________________________________
All data areas should be aligned with the block size, but metadata areas
may not. All metadatas can be now observed in two different spaces (views):
+
1. Inode metadata space
+
Each valid inode should be aligned with an inode slot, which is a fixed
value (32 bytes) and designed to be kept in line with compact inode size.
Each inode can be directly found with the following formula:
inode offset = meta_blkaddr * block_size + 32 * nid
- |-> aligned with 8B
- |-> followed closely
- + meta_blkaddr blocks |-> another slot
- _____________________________________________________________________
- | ... | inode | xattrs | extents | data inline | ... | inode ...
- |________|_______|(optional)|(optional)|__(optional)_|_____|__________
- |-> aligned with the inode slot size
- . .
- . .
- . .
- . .
- . .
- . .
- .____________________________________________________|-> aligned with 4B
- | xattr_ibody_header | shared xattrs | inline xattrs |
- |____________________|_______________|_______________|
- |-> 12 bytes <-|->x * 4 bytes<-| .
- . . .
- . . .
- . . .
- ._______________________________.______________________.
- | id | id | id | id | ... | id | ent | ... | ent| ... |
- |____|____|____|____|______|____|_____|_____|____|_____|
- |-> aligned with 4B
- |-> aligned with 4B
+ ::
+
+ |-> aligned with 8B
+ |-> followed closely
+ + meta_blkaddr blocks |-> another slot
+ _____________________________________________________________________
+ | ... | inode | xattrs | extents | data inline | ... | inode ...
+ |________|_______|(optional)|(optional)|__(optional)_|_____|__________
+ |-> aligned with the inode slot size
+ . .
+ . .
+ . .
+ . .
+ . .
+ . .
+ .____________________________________________________|-> aligned with 4B
+ | xattr_ibody_header | shared xattrs | inline xattrs |
+ |____________________|_______________|_______________|
+ |-> 12 bytes <-|->x * 4 bytes<-| .
+ . . .
+ . . .
+ . . .
+ ._______________________________.______________________.
+ | id | id | id | id | ... | id | ent | ... | ent| ... |
+ |____|____|____|____|______|____|_____|_____|____|_____|
+ |-> aligned with 4B
+ |-> aligned with 4B
Inode could be 32 or 64 bytes, which can be distinguished from a common
- field which all inode versions have -- i_format:
+ field which all inode versions have -- i_format::
__________________ __________________
| i_format | | i_format |
proper alignment, and they could be optional for different data mappings.
_currently_ total 4 valid data mappings are supported:
+ == ====================================================================
0 flat file data without data inline (no extent);
1 fixed-sized output data compression (with non-compacted indexes);
2 flat file data with tail packing data inline (no extent);
3 fixed-sized output data compression (with compacted indexes, v5.3+).
+ == ====================================================================
The size of the optional xattrs is indicated by i_xattr_count in inode
header. Large xattrs or xattrs shared by many different files can be
stored in shared xattrs metadata rather than inlined right after inode.
2. Shared xattrs metadata space
+
Shared xattrs space is similar to the above inode space, started with
a specific block indicated by xattr_blkaddr, organized one by one with
proper align.
Each share xattr can also be directly found by the following formula:
xattr offset = xattr_blkaddr * block_size + 4 * xattr_id
- |-> aligned by 4 bytes
- + xattr_blkaddr blocks |-> aligned with 4 bytes
- _________________________________________________________________________
- | ... | xattr_entry | xattr data | ... | xattr_entry | xattr data ...
- |________|_____________|_____________|_____|______________|_______________
+ ::
+
+ |-> aligned by 4 bytes
+ + xattr_blkaddr blocks |-> aligned with 4 bytes
+ _________________________________________________________________________
+ | ... | xattr_entry | xattr data | ... | xattr_entry | xattr data ...
+ |________|_____________|_____________|_____|______________|_______________
Directories
-----------
alphabetical order in order to support improved prefix binary search
algorithm (could refer to the related source code).
- ___________________________
- / |
- / ______________|________________
- / / | nameoff1 | nameoffN-1
- ____________.______________._______________v________________v__________
-| dirent | dirent | ... | dirent | filename | filename | ... | filename |
-|___.0___|____1___|_____|___N-1__|____0_____|____1_____|_____|___N-1____|
- \ ^
- \ | * could have
- \ | trailing '\0'
- \________________________| nameoff0
+::
+
+ ___________________________
+ / |
+ / ______________|________________
+ / / | nameoff1 | nameoffN-1
+ ____________.______________._______________v________________v__________
+ | dirent | dirent | ... | dirent | filename | filename | ... | filename |
+ |___.0___|____1___|_____|___N-1__|____0_____|____1_____|_____|___N-1____|
+ \ ^
+ \ | * could have
+ \ | trailing '\0'
+ \________________________| nameoff0
- Directory block
+ Directory block
Note that apart from the offset of the first filename, nameoff0 also indicates
the total number of directory entries in this block since it is no need to
Compression
-----------
Currently, EROFS supports 4KB fixed-sized output transparent file compression,
-as illustrated below:
-
- |---- Variant-Length Extent ----|-------- VLE --------|----- VLE -----
- clusterofs clusterofs clusterofs
- | | | logical data
-_________v_______________________________v_____________________v_______________
-... | . | | . | | . | ...
-____|____.________|_____________|________.____|_____________|__.__________|____
- |-> cluster <-|-> cluster <-|-> cluster <-|-> cluster <-|-> cluster <-|
- size size size size size
- . . . .
- . . . .
- . . . .
- _______._____________._____________._____________._____________________
- ... | | | | ... physical data
- _______|_____________|_____________|_____________|_____________________
- |-> cluster <-|-> cluster <-|-> cluster <-|
- size size size
+as illustrated below::
+
+ |---- Variant-Length Extent ----|-------- VLE --------|----- VLE -----
+ clusterofs clusterofs clusterofs
+ | | | logical data
+ _________v_______________________________v_____________________v_______________
+ ... | . | | . | | . | ...
+ ____|____.________|_____________|________.____|_____________|__.__________|____
+ |-> cluster <-|-> cluster <-|-> cluster <-|-> cluster <-|-> cluster <-|
+ size size size size size
+ . . . .
+ . . . .
+ . . . .
+ _______._____________._____________._____________._____________________
+ ... | | | | ... physical data
+ _______|_____________|_____________|_____________|_____________________
+ |-> cluster <-|-> cluster <-|-> cluster <-|
+ size size size
Currently each on-disk physical cluster can contain 4KB (un)compressed data
at most. For each logical cluster, there is a corresponding on-disk index to
describe its cluster type, physical cluster address, etc.
See "struct z_erofs_vle_decompressed_index" in erofs_fs.h for more details.
-
+.. SPDX-License-Identifier: GPL-2.0
+
The Second Extended Filesystem
==============================
Most defaults are determined by the filesystem superblock, and can be
set using tune2fs(8). Kernel-determined defaults are indicated by (*).
-bsddf (*) Makes `df' act like BSD.
-minixdf Makes `df' act like Minix.
+==================== === ================================================
+bsddf (*) Makes ``df`` act like BSD.
+minixdf Makes ``df`` act like Minix.
check=none, nocheck (*) Don't do extra checking of bitmaps on mount
(check=normal and check=strict options removed)
grpquota Enable group disk quota support
(requires CONFIG_QUOTA).
+==================== === ================================================
noquota option ls silently ignored by ext2.
If you're exceptionally paranoid, there are 3 ways of making metadata
writes synchronous on ext2:
-per-file if you have the program source: use the O_SYNC flag to open()
-per-file if you don't have the source: use "chattr +S" on the file
-per-filesystem: add the "sync" option to mount (or in /etc/fstab)
+- per-file if you have the program source: use the O_SYNC flag to open()
+- per-file if you don't have the source: use "chattr +S" on the file
+- per-filesystem: add the "sync" option to mount (or in /etc/fstab)
the first and last are not ext2 specific but do force the metadata to
be written synchronously. See also Journaling below.
format and using a compatibility flag to signal the format change (at
the expense of some compatibility).
-Filesystem block size: 1kB 2kB 4kB 8kB
-
-File size limit: 16GB 256GB 2048GB 2048GB
-Filesystem size limit: 2047GB 8192GB 16384GB 32768GB
+===================== ======= ======= ======= ========
+Filesystem block size 1kB 2kB 4kB 8kB
+===================== ======= ======= ======= ========
+File size limit 16GB 256GB 2048GB 2048GB
+Filesystem size limit 2047GB 8192GB 16384GB 32768GB
+===================== ======= ======= ======= ========
There is a 2.4 kernel limit of 2048GB for a single block device, so no
filesystem larger than that can be created at this time. There is also
References
==========
+======================= ===============================================
The kernel source file:/usr/src/linux/fs/ext2/
e2fsprogs (e2fsck) http://e2fsprogs.sourceforge.net/
Design & Implementation http://e2fsprogs.sourceforge.net/ext2intro.html
Journaling (ext3) ftp://ftp.uk.linux.org/pub/linux/sct/fs/jfs/
Filesystem Resizing http://ext2resize.sourceforge.net/
-Compression (*) http://e2compr.sourceforge.net/
+Compression [1]_ http://e2compr.sourceforge.net/
+======================= ===============================================
Implementations for:
+
+======================= ===========================================================
Windows 95/98/NT/2000 http://www.chrysocome.net/explore2fs
-Windows 95 (*) http://www.yipton.net/content.html#FSDEXT2
-DOS client (*) ftp://metalab.unc.edu/pub/Linux/system/filesystems/ext2/
-OS/2 (+) ftp://metalab.unc.edu/pub/Linux/system/filesystems/ext2/
+Windows 95 [1]_ http://www.yipton.net/content.html#FSDEXT2
+DOS client [1]_ ftp://metalab.unc.edu/pub/Linux/system/filesystems/ext2/
+OS/2 [2]_ ftp://metalab.unc.edu/pub/Linux/system/filesystems/ext2/
RISC OS client http://www.esw-heim.tu-clausthal.de/~marco/smorbrod/IscaFS/
+======================= ===========================================================
-(*) no longer actively developed/supported (as of Apr 2001)
-(+) no longer actively developed/supported (as of Mar 2009)
+.. [1] no longer actively developed/supported (as of Apr 2001)
+.. [2] no longer actively developed/supported (as of Mar 2009)
+.. SPDX-License-Identifier: GPL-2.0
+===============
Ext3 Filesystem
===============
-================================================================================
+.. SPDX-License-Identifier: GPL-2.0
+
+==========================================
WHAT IS Flash-Friendly File System (F2FS)?
-================================================================================
+==========================================
NAND flash memory-based storage devices, such as SSD, eMMC, and SD cards, have
been equipped on a variety systems ranging from mobile to server systems. Since
The following git tree provides the file system formatting tool (mkfs.f2fs),
a consistency checking tool (fsck.f2fs), and a debugging tool (dump.f2fs).
->> git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs-tools.git
+
+- git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs-tools.git
For reporting bugs and sending patches, please use the following mailing list:
->> linux-f2fs-devel@lists.sourceforge.net
-================================================================================
-BACKGROUND AND DESIGN ISSUES
-================================================================================
+- linux-f2fs-devel@lists.sourceforge.net
+
+Background and Design issues
+============================
Log-structured File System (LFS)
--------------------------------
as a cleaning process.
The process consists of three operations as follows.
+
1. A victim segment is selected through referencing segment usage table.
2. It loads parent index structures of all the data in the victim identified by
segment summary blocks.
is to hide the latencies to users. And also definitely, it should reduce the
amount of valid data to be moved, and move them quickly as well.
-================================================================================
-KEY FEATURES
-================================================================================
+Key Features
+============
Flash Awareness
---------------
- Support multi-head logs for static/dynamic hot and cold data separation
- Introduce adaptive logging for efficient block allocation
-================================================================================
-MOUNT OPTIONS
-================================================================================
+Mount Options
+=============
+
+====================== ============================================================
background_gc=%s Turn on/off cleaning operations, namely garbage
collection, triggered in background when I/O subsystem is
idle. If background_gc=on, it will turn on the garbage
fault_type=%d Support configuring fault injection type, should be
enabled with fault_injection option, fault type value
is shown below, it supports single or combined type.
+
+ =================== ===========
Type_Name Type_Value
+ =================== ===========
FAULT_KMALLOC 0x000000001
FAULT_KVMALLOC 0x000000002
FAULT_PAGE_ALLOC 0x000000004
FAULT_CHECKPOINT 0x000001000
FAULT_DISCARD 0x000002000
FAULT_WRITE_IO 0x000004000
+ =================== ===========
mode=%s Control block allocation mode which supports "adaptive"
and "lfs". In "lfs" mode, there should be no random
writes towards main area.
non-atomic files likewise "nobarrier" mount option.
test_dummy_encryption Enable dummy encryption, which provides a fake fscrypt
context. The fake fscrypt context is used by xfstests.
-checkpoint=%s[:%u[%]] Set to "disable" to turn off checkpointing. Set to "enable"
+checkpoint=%s[:%u[%]] Set to "disable" to turn off checkpointing. Set to "enable"
to reenable checkpointing. Is enabled by default. While
disabled, any unmounting or unexpected shutdowns will cause
the filesystem contents to appear as they did when the
on compression extension list and enable compression on
these file by default rather than to enable it via ioctl.
For other files, we can still enable compression via ioctl.
+====================== ============================================================
-================================================================================
-DEBUGFS ENTRIES
-================================================================================
+Debugfs Entries
+===============
/sys/kernel/debug/f2fs/ contains information about all the partitions mounted as
f2fs. Each file shows the whole f2fs information.
/sys/kernel/debug/f2fs/status includes:
+
- major file system information managed by f2fs currently
- average SIT information about whole segments
- current memory footprint consumed by f2fs.
-================================================================================
-SYSFS ENTRIES
-================================================================================
+Sysfs Entries
+=============
Information about mounted f2fs file systems can be found in
/sys/fs/f2fs. Each mounted filesystem will have a directory in
Files in /sys/fs/f2fs/<devname>
(see also Documentation/ABI/testing/sysfs-fs-f2fs)
-================================================================================
-USAGE
-================================================================================
+Usage
+=====
1. Download userland tools and compile them.
2. Skip, if f2fs was compiled statically inside kernel.
- Otherwise, insert the f2fs.ko module.
- # insmod f2fs.ko
+ Otherwise, insert the f2fs.ko module::
+
+ # insmod f2fs.ko
-3. Create a directory trying to mount
- # mkdir /mnt/f2fs
+3. Create a directory trying to mount::
-4. Format the block device, and then mount as f2fs
- # mkfs.f2fs -l label /dev/block_device
- # mount -t f2fs /dev/block_device /mnt/f2fs
+ # mkdir /mnt/f2fs
+
+4. Format the block device, and then mount as f2fs::
+
+ # mkfs.f2fs -l label /dev/block_device
+ # mount -t f2fs /dev/block_device /mnt/f2fs
mkfs.f2fs
---------
which builds a basic on-disk layout.
The options consist of:
--l [label] : Give a volume label, up to 512 unicode name.
--a [0 or 1] : Split start location of each area for heap-based allocation.
- 1 is set by default, which performs this.
--o [int] : Set overprovision ratio in percent over volume size.
- 5 is set by default.
--s [int] : Set the number of segments per section.
- 1 is set by default.
--z [int] : Set the number of sections per zone.
- 1 is set by default.
--e [str] : Set basic extension list. e.g. "mp3,gif,mov"
--t [0 or 1] : Disable discard command or not.
- 1 is set by default, which conducts discard.
+
+=============== ===========================================================
+``-l [label]`` Give a volume label, up to 512 unicode name.
+``-a [0 or 1]`` Split start location of each area for heap-based allocation.
+
+ 1 is set by default, which performs this.
+``-o [int]`` Set overprovision ratio in percent over volume size.
+
+ 5 is set by default.
+``-s [int]`` Set the number of segments per section.
+
+ 1 is set by default.
+``-z [int]`` Set the number of sections per zone.
+
+ 1 is set by default.
+``-e [str]`` Set basic extension list. e.g. "mp3,gif,mov"
+``-t [0 or 1]`` Disable discard command or not.
+
+ 1 is set by default, which conducts discard.
+=============== ===========================================================
fsck.f2fs
---------
are cross-referenced correctly or not.
Note that, initial version of the tool does not fix any inconsistency.
-The options consist of:
+The options consist of::
+
-d debug level [default:0]
dump.f2fs
able to dump all the SSA and SIT entries into predefined files, ./dump_ssa and
./dump_sit respectively.
-The options consist of:
+The options consist of::
+
-d debug level [default:0]
-i inode no (hex)
-s [SIT dump segno from #1~#2 (decimal), for all 0~-1]
-a [SSA dump segno from #1~#2 (decimal), for all 0~-1]
-Examples:
-# dump.f2fs -i [ino] /dev/sdx
-# dump.f2fs -s 0~-1 /dev/sdx (SIT dump)
-# dump.f2fs -a 0~-1 /dev/sdx (SSA dump)
+Examples::
+
+ # dump.f2fs -i [ino] /dev/sdx
+ # dump.f2fs -s 0~-1 /dev/sdx (SIT dump)
+ # dump.f2fs -a 0~-1 /dev/sdx (SSA dump)
-================================================================================
-DESIGN
-================================================================================
+Design
+======
On-disk Layout
--------------
segment size identically, but users can easily modify the sizes by mkfs.
F2FS splits the entire volume into six areas, and all the areas except superblock
-consists of multiple segments as described below.
+consists of multiple segments as described below::
align with the zone size <-|
|-> align with the segment size
|__zone__|
- Superblock (SB)
- : It is located at the beginning of the partition, and there exist two copies
+ It is located at the beginning of the partition, and there exist two copies
to avoid file system crash. It contains basic partition information and some
default parameters of f2fs.
- Checkpoint (CP)
- : It contains file system information, bitmaps for valid NAT/SIT sets, orphan
+ It contains file system information, bitmaps for valid NAT/SIT sets, orphan
inode lists, and summary entries of current active segments.
- Segment Information Table (SIT)
- : It contains segment information such as valid block count and bitmap for the
+ It contains segment information such as valid block count and bitmap for the
validity of all the blocks.
- Node Address Table (NAT)
- : It is composed of a block address table for all the node blocks stored in
+ It is composed of a block address table for all the node blocks stored in
Main area.
- Segment Summary Area (SSA)
- : It contains summary entries which contains the owner information of all the
+ It contains summary entries which contains the owner information of all the
data and node blocks stored in Main area.
- Main Area
- : It contains file and directory data including their indices.
+ It contains file and directory data including their indices.
In order to avoid misalignment between file system and flash-based storage, F2FS
aligns the start block address of CP with the segment size. Also, it aligns the
mechanism. In addition to CP, NAT and SIT also adopt the shadow copy mechanism.
For file system consistency, each CP points to which NAT and SIT copies are
-valid, as shown as below.
+valid, as shown as below::
+--------+----------+---------+
| CP | SIT | NAT |
indices, two direct node pointers, two indirect node pointers, and one double
indirect node pointer as described below. One direct node block contains 1018
data blocks, and one indirect node block contains also 1018 node blocks. Thus,
-one inode block (i.e., a file) covers:
+one inode block (i.e., a file) covers::
4KB * (923 + 2 * 1018 + 2 * 1018 * 1018 + 1018 * 1018 * 1018) := 3.94TB.
used to represent whether each dentry is valid or not. A dentry block occupies
4KB with the following composition.
+::
+
Dentry Block(4 K) = bitmap (27 bytes) + reserved (3 bytes) +
dentries(11 * 214 bytes) + file name (8 * 214 bytes)
a hash table with dedicated number of hash buckets as shown below. Note that
"A(2B)" means a bucket includes 2 data blocks.
-----------------------
-A : bucket
-B : block
-N : MAX_DIR_HASH_DEPTH
-----------------------
+::
+
+ ----------------------
+ A : bucket
+ B : block
+ N : MAX_DIR_HASH_DEPTH
+ ----------------------
-level #0 | A(2B)
- |
-level #1 | A(2B) - A(2B)
- |
-level #2 | A(2B) - A(2B) - A(2B) - A(2B)
- . | . . . .
-level #N/2 | A(2B) - A(2B) - A(2B) - A(2B) - A(2B) - ... - A(2B)
- . | . . . .
-level #N | A(4B) - A(4B) - A(4B) - A(4B) - A(4B) - ... - A(4B)
+ level #0 | A(2B)
+ |
+ level #1 | A(2B) - A(2B)
+ |
+ level #2 | A(2B) - A(2B) - A(2B) - A(2B)
+ . | . . . .
+ level #N/2 | A(2B) - A(2B) - A(2B) - A(2B) - A(2B) - ... - A(2B)
+ . | . . . .
+ level #N | A(4B) - A(4B) - A(4B) - A(4B) - A(4B) - ... - A(4B)
-The number of blocks and buckets are determined by,
+The number of blocks and buckets are determined by::
,- 2, if n < MAX_DIR_HASH_DEPTH / 2,
# of blocks in level #n = |
scans the next hash table in level #1. In this way, F2FS scans hash tables in
each levels incrementally from 1 to N. In each levels F2FS needs to scan only
one bucket determined by the following equation, which shows O(log(# of files))
-complexity.
+complexity::
bucket number to scan in level #n = (hash value) % (# of buckets in level #n)
file name. F2FS searches the empty slots in the hash tables of whole levels from
1 to N in the same way as the lookup operation.
-The following figure shows an example of two cases holding children.
+The following figure shows an example of two cases holding children::
+
--------------> Dir <--------------
| |
child child
2) whint_mode=user-based. F2FS tries to pass down hints given by
users.
+===================== ======================== ===================
User F2FS Block
----- ---- -----
+===================== ======================== ===================
META WRITE_LIFE_NOT_SET
HOT_NODE "
WARM_NODE "
COLD_NODE "
-*ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME
-*extension list " "
+ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME
+extension list " "
-- buffered io
WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME
WRITE_LIFE_NONE " WRITE_LIFE_NONE
WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM
WRITE_LIFE_LONG " WRITE_LIFE_LONG
+===================== ======================== ===================
3) whint_mode=fs-based. F2FS passes down hints with its policy.
+===================== ======================== ===================
User F2FS Block
----- ---- -----
+===================== ======================== ===================
META WRITE_LIFE_MEDIUM;
HOT_NODE WRITE_LIFE_NOT_SET
WARM_NODE "
WRITE_LIFE_NONE " WRITE_LIFE_NONE
WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM
WRITE_LIFE_LONG " WRITE_LIFE_LONG
+===================== ======================== ===================
Fallocate(2) Policy
-------------------
However, once F2FS receives ioctl(fd, F2FS_IOC_SET_PIN_FILE) in prior to
fallocate(fd, DEFAULT_MODE), it allocates on-disk blocks addressess having
zero or random data, which is useful to the below scenario where:
+
1. create(fd)
2. ioctl(fd, F2FS_IOC_SET_PIN_FILE)
3. fallocate(fd, 0, 0, size)
--------------------------
- New term named cluster is defined as basic unit of compression, file can
-be divided into multiple clusters logically. One cluster includes 4 << n
-(n >= 0) logical pages, compression size is also cluster size, each of
-cluster can be compressed or not.
+ be divided into multiple clusters logically. One cluster includes 4 << n
+ (n >= 0) logical pages, compression size is also cluster size, each of
+ cluster can be compressed or not.
- In cluster metadata layout, one special block address is used to indicate
-cluster is compressed one or normal one, for compressed cluster, following
-metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs
-stores data including compress header and compressed data.
+ cluster is compressed one or normal one, for compressed cluster, following
+ metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs
+ stores data including compress header and compressed data.
- In order to eliminate write amplification during overwrite, F2FS only
-support compression on write-once file, data can be compressed only when
-all logical blocks in file are valid and cluster compress ratio is lower
-than specified threshold.
+ support compression on write-once file, data can be compressed only when
+ all logical blocks in file are valid and cluster compress ratio is lower
+ than specified threshold.
- To enable compression on regular inode, there are three ways:
-* chattr +c file
-* chattr +c dir; touch dir/file
-* mount w/ -o compress_extension=ext; touch file.ext
-
-Compress metadata layout:
- [Dnode Structure]
- +-----------------------------------------------+
- | cluster 1 | cluster 2 | ......... | cluster N |
- +-----------------------------------------------+
- . . . .
- . . . .
- . Compressed Cluster . . Normal Cluster .
-+----------+---------+---------+---------+ +---------+---------+---------+---------+
-|compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 |
-+----------+---------+---------+---------+ +---------+---------+---------+---------+
- . .
- . .
- . .
- +-------------+-------------+----------+----------------------------+
- | data length | data chksum | reserved | compressed data |
- +-------------+-------------+----------+----------------------------+
+
+ * chattr +c file
+ * chattr +c dir; touch dir/file
+ * mount w/ -o compress_extension=ext; touch file.ext
+
+Compress metadata layout::
+
+ [Dnode Structure]
+ +-----------------------------------------------+
+ | cluster 1 | cluster 2 | ......... | cluster N |
+ +-----------------------------------------------+
+ . . . .
+ . . . .
+ . Compressed Cluster . . Normal Cluster .
+ +----------+---------+---------+---------+ +---------+---------+---------+---------+
+ |compr flag| block 1 | block 2 | block 3 | | block 1 | block 2 | block 3 | block 4 |
+ +----------+---------+---------+---------+ +---------+---------+---------+---------+
+ . .
+ . .
+ . .
+ +-------------+-------------+----------+----------------------------+
+ | data length | data chksum | reserved | compressed data |
+ +-------------+-------------+----------+----------------------------+
.. SPDX-License-Identifier: GPL-2.0
-==============
+
+====
FUSE
-==============
+====
Definitions
===========
- uevents and GFS2
- ==================
+.. SPDX-License-Identifier: GPL-2.0
+
+================
+uevents and GFS2
+================
During the lifetime of a GFS2 mount, a number of uevents are generated.
This document explains what the events are and what they are used
for (by gfs_controld in gfs2-utils).
A list of GFS2 uevents
------------------------
+======================
1. ADD
+------
The ADD event occurs at mount time. It will always be the first
uevent generated by the newly created filesystem. If the mount
of the filesystem respectively.
2. ONLINE
+---------
The ONLINE uevent is generated after a successful mount or remount. It
has the same environment variables as the ADD uevent. The ONLINE
be generated by older kernels.
3. CHANGE
+---------
The CHANGE uevent is used in two places. One is when reporting the
successful mount of the filesystem by the first node (FIRSTMOUNT=Done).
uevent for a successful mount or remount.
4. OFFLINE
+----------
The OFFLINE uevent is only generated due to filesystem errors and is used
as part of the "withdraw" mechanism. Currently this doesn't give any
be fixed.
5. REMOVE
+---------
The REMOVE uevent is generated at the end of an unsuccessful mount
or at the end of a umount of the filesystem. All REMOVE uevents will
Information common to all GFS2 uevents (uevent environment variables)
-----------------------------------------------------------------------
+=====================================================================
1. LOCKTABLE=
+--------------
The LOCKTABLE is a string, as supplied on the mount command
line (locktable=) or via fstab. It is used as a filesystem label
able to join the cluster.
2. LOCKPROTO=
+-------------
The LOCKPROTO is a string, and its value depends on what is set
on the mount command line, or via fstab. It will be either
may be supported.
3. JOURNALID=
+-------------
If a journal is in use by the filesystem (journals are not
assigned for spectator mounts) then this will give the
numeric journal id in all GFS2 uevents.
4. UUID=
+--------
With recent versions of gfs2-utils, mkfs.gfs2 writes a UUID
into the filesystem superblock. If it exists, this will
+.. SPDX-License-Identifier: GPL-2.0
+
+==================
Global File System
-------------------
+==================
https://fedorahosted.org/cluster/wiki/HomePage
GFS uses interchangeable inter-node locking mechanisms, the currently
supported mechanisms are:
- lock_nolock -- allows gfs to be used as a local file system
+ lock_nolock
+ - allows gfs to be used as a local file system
- lock_dlm -- uses a distributed lock manager (dlm) for inter-node locking
- The dlm is found at linux/fs/dlm/
+ lock_dlm
+ - uses a distributed lock manager (dlm) for inter-node locking.
+ The dlm is found at linux/fs/dlm/
Lock_dlm depends on user space cluster management systems found
at the URL above.
To use gfs as a local file system, no external clustering systems are
-needed, simply:
+needed, simply::
$ mkfs -t gfs2 -p lock_nolock -j 1 /dev/block_device
$ mount -t gfs2 /dev/block_device /dir
is pretty close.
The following man pages can be found at the URL above:
+
+ ============ =============================================
fsck.gfs2 to repair a filesystem
gfs2_grow to expand a filesystem online
gfs2_jadd to add journals to a filesystem online
tunegfs2 to manipulate, examine and tune a filesystem
- gfs2_convert to convert a gfs filesystem to gfs2 in-place
+ gfs2_convert to convert a gfs filesystem to gfs2 in-place
mkfs.gfs2 to make a filesystem
+ ============ =============================================
-Note: This filesystem doesn't have a maintainer.
+.. SPDX-License-Identifier: GPL-2.0
+==================================
Macintosh HFS Filesystem for Linux
==================================
-HFS stands for ``Hierarchical File System'' and is the filesystem used
+
+.. Note:: This filesystem doesn't have a maintainer.
+
+
+HFS stands for ``Hierarchical File System`` and is the filesystem used
by the Mac Plus and all later Macintosh models. Earlier Macintosh
-models used MFS (``Macintosh File System''), which is not supported,
+models used MFS (``Macintosh File System``), which is not supported,
MacOS 8.1 and newer support a filesystem called HFS+ that's similar to
HFS but is extended in various areas. Use the hfsplus filesystem driver
to access such filesystems from Linux.
HFS is not a UNIX filesystem, thus it does not have the usual features you'd
expect:
- o You can't modify the set-uid, set-gid, sticky or executable bits or the uid
+ * You can't modify the set-uid, set-gid, sticky or executable bits or the uid
and gid of files.
- o You can't create hard- or symlinks, device files, sockets or FIFOs.
+ * You can't create hard- or symlinks, device files, sockets or FIFOs.
HFS does on the other have the concepts of multiple forks per file. These
non-standard forks are represented as hidden additional files in the normal
filesystems namespace which is kind of a cludge and makes the semantics for
the a little strange:
- o You can't create, delete or rename resource forks of files or the
+ * You can't create, delete or rename resource forks of files or the
Finder's metadata.
- o They are however created (with default values), deleted and renamed
+ * They are however created (with default values), deleted and renamed
along with the corresponding data fork or directory.
- o Copying files to a different filesystem will loose those attributes
+ * Copying files to a different filesystem will loose those attributes
that are essential for MacOS to work.
Creating HFS filesystems
-===================================
+========================
The hfsutils package from Robert Leslie contains a program called
hformat that can be used to create HFS filesystem. See
+.. SPDX-License-Identifier: GPL-2.0
+======================================
Macintosh HFSPlus Filesystem for Linux
======================================
+.. SPDX-License-Identifier: GPL-2.0
+
+====================
Read/Write HPFS 2.09
+====================
+
1998-2004, Mikulas Patocka
-email: mikulas@artax.karlin.mff.cuni.cz
-homepage: http://artax.karlin.mff.cuni.cz/~mikulas/vyplody/hpfs/index-e.cgi
+:email: mikulas@artax.karlin.mff.cuni.cz
+:homepage: http://artax.karlin.mff.cuni.cz/~mikulas/vyplody/hpfs/index-e.cgi
-CREDITS:
+Credits
+=======
Chris Smith, 1993, original read-only HPFS, some code and hpfs structures file
is taken from it
+
Jacques Gelinas, MSDos mmap, Inspired by fs/nfs/mmap.c (Jon Tombs 15 Aug 1993)
+
Werner Almesberger, 1992, 1993, MSDos option parser & CR/LF conversion
Mount options
File names
+==========
As in OS/2, filenames are case insensitive. However, shell thinks that names
are case sensitive, so for example when you create a file FOO, you can use
Extended attributes
+===================
On HPFS partitions, OS/2 can associate to each file a special information called
extended attributes. Extended attributes are pairs of (key,value) where key is
Symlinks
+========
You can do symlinks on HPFS partition, symlinks are achieved by setting extended
attribute named "SYMLINK" with symlink value. Like on ext2, you can chown and
Codepages
+=========
HPFS can contain several uppercasing tables for several codepages and each
file has a pointer to codepage its name is in. However OS/2 was created in
Known bugs
+==========
HPFS386 on OS/2 server is not supported. HPFS386 installed on normal OS/2 client
should work. If you have OS/2 server, use only read-only mode. I don't know how
to delete other files that are leaf (probability that the file is non-leaf is
about 1/50) or to truncate file first to make some space.
You encounter this problem only if you have many directories so that
-preallocated directory band is full i.e.
+preallocated directory band is full i.e.::
+
number_of_directories / size_of_filesystem_in_mb > 4.
You can't delete open directories.
What does "unbalanced tree" message mean?
+=========================================
Old versions of this driver created sometimes unbalanced dnode trees. OS/2
chkdsk doesn't scream if the tree is unbalanced (and sometimes creates
Bugs in OS/2
+============
When you have two (or more) lost directories pointing each to other, chkdsk
locks up when repairing filesystem.
marks them as short (and writes "minor fs error corrected"). This bug is not in
HPFS386.
-Codepage bugs described above.
+Codepage bugs described above
+=============================
If you don't install fixpacks, there are many, many more...
History
+=======
+
+====== =========================================================================
+0.90 First public release
+0.91 Fixed bug that caused shooting to memory when write_inode was called on
+ open inode (rarely happened)
+0.92 Fixed a little memory leak in freeing directory inodes
+0.93 Fixed bug that locked up the machine when there were too many filenames
+ with first 15 characters same
+ Fixed write_file to zero file when writing behind file end
+0.94 Fixed a little memory leak when trying to delete busy file or directory
+0.95 Fixed a bug that i_hpfs_parent_dir was not updated when moving files
+1.90 First version for 2.1.1xx kernels
+1.91 Fixed a bug that chk_sectors failed when sectors were at the end of disk
+ Fixed a race-condition when write_inode is called while deleting file
+ Fixed a bug that could possibly happen (with very low probability) when
+ using 0xff in filenames.
+
+ Rewritten locking to avoid race-conditions
+
+ Mount option 'eas' now works
+
+ Fsync no longer returns error
+
+ Files beginning with '.' are marked hidden
+
+ Remount support added
+
+ Alloc is not so slow when filesystem becomes full
+
+ Atimes are no more updated because it slows down operation
+
+ Code cleanup (removed all commented debug prints)
+1.92 Corrected a bug when sync was called just before closing file
+1.93 Modified, so that it works with kernels >= 2.1.131, I don't know if it
+ works with previous versions
+
+ Fixed a possible problem with disks > 64G (but I don't have one, so I can't
+ test it)
+
+ Fixed a file overflow at 2G
+
+ Added new option 'timeshift'
+
+ Changed behaviour on HPFS386: It is now possible to operate on HPFS386 in
+ read-only mode
+
+ Fixed a bug that slowed down alloc and prevented allocating 100% space
+ (this bug was not destructive)
+1.94 Added workaround for one bug in Linux
+
+ Fixed one buffer leak
+
+ Fixed some incompatibilities with large extended attributes (but it's still
+ not 100% ok, I have no info on it and OS/2 doesn't want to create them)
+
+ Rewritten allocation
-0.90 First public release
-0.91 Fixed bug that caused shooting to memory when write_inode was called on
- open inode (rarely happened)
-0.92 Fixed a little memory leak in freeing directory inodes
-0.93 Fixed bug that locked up the machine when there were too many filenames
- with first 15 characters same
- Fixed write_file to zero file when writing behind file end
-0.94 Fixed a little memory leak when trying to delete busy file or directory
-0.95 Fixed a bug that i_hpfs_parent_dir was not updated when moving files
-1.90 First version for 2.1.1xx kernels
-1.91 Fixed a bug that chk_sectors failed when sectors were at the end of disk
- Fixed a race-condition when write_inode is called while deleting file
- Fixed a bug that could possibly happen (with very low probability) when
- using 0xff in filenames
- Rewritten locking to avoid race-conditions
- Mount option 'eas' now works
- Fsync no longer returns error
- Files beginning with '.' are marked hidden
- Remount support added
- Alloc is not so slow when filesystem becomes full
- Atimes are no more updated because it slows down operation
- Code cleanup (removed all commented debug prints)
-1.92 Corrected a bug when sync was called just before closing file
-1.93 Modified, so that it works with kernels >= 2.1.131, I don't know if it
- works with previous versions
- Fixed a possible problem with disks > 64G (but I don't have one, so I can't
- test it)
- Fixed a file overflow at 2G
- Added new option 'timeshift'
- Changed behaviour on HPFS386: It is now possible to operate on HPFS386 in
- read-only mode
- Fixed a bug that slowed down alloc and prevented allocating 100% space
- (this bug was not destructive)
-1.94 Added workaround for one bug in Linux
- Fixed one buffer leak
- Fixed some incompatibilities with large extended attributes (but it's still
- not 100% ok, I have no info on it and OS/2 doesn't want to create them)
- Rewritten allocation
- Fixed a bug with i_blocks (du sometimes didn't display correct values)
- Directories have no longer archive attribute set (some programs don't like
- it)
- Fixed a bug that it set badly one flag in large anode tree (it was not
- destructive)
-1.95 Fixed one buffer leak, that could happen on corrupted filesystem
- Fixed one bug in allocation in 1.94
-1.96 Added workaround for one bug in OS/2 (HPFS locked up, HPFS386 reported
- error sometimes when opening directories in PMSHELL)
- Fixed a possible bitmap race
- Fixed possible problem on large disks
- You can now delete open files
- Fixed a nondestructive race in rename
-1.97 Support for HPFS v3 (on large partitions)
- Fixed a bug that it didn't allow creation of files > 128M (it should be 2G)
+ Fixed a bug with i_blocks (du sometimes didn't display correct values)
+
+ Directories have no longer archive attribute set (some programs don't like
+ it)
+
+ Fixed a bug that it set badly one flag in large anode tree (it was not
+ destructive)
+1.95 Fixed one buffer leak, that could happen on corrupted filesystem
+
+ Fixed one bug in allocation in 1.94
+1.96 Added workaround for one bug in OS/2 (HPFS locked up, HPFS386 reported
+ error sometimes when opening directories in PMSHELL)
+
+ Fixed a possible bitmap race
+
+ Fixed possible problem on large disks
+
+ You can now delete open files
+
+ Fixed a nondestructive race in rename
+1.97 Support for HPFS v3 (on large partitions)
+
+ ZFixed a bug that it didn't allow creation of files > 128M
+ (it should be 2G)
1.97.1 Changed names of global symbols
+
Fixed a bug when chmoding or chowning root directory
-1.98 Fixed a deadlock when using old_readdir
- Better directory handling; workaround for "unbalanced tree" bug in OS/2
-1.99 Corrected a possible problem when there's not enough space while deleting
- file
- Now it tries to truncate the file if there's not enough space when deleting
- Removed a lot of redundant code
-2.00 Fixed a bug in rename (it was there since 1.96)
- Better anti-fragmentation strategy
-2.01 Fixed problem with directory listing over NFS
- Directory lseek now checks for proper parameters
- Fixed race-condition in buffer code - it is in all filesystems in Linux;
- when reading device (cat /dev/hda) while creating files on it, files
- could be damaged
-2.02 Workaround for bug in breada in Linux. breada could cause accesses beyond
- end of partition
-2.03 Char, block devices and pipes are correctly created
- Fixed non-crashing race in unlink (Alexander Viro)
- Now it works with Japanese version of OS/2
-2.04 Fixed error when ftruncate used to extend file
-2.05 Fixed crash when got mount parameters without =
- Fixed crash when allocation of anode failed due to full disk
- Fixed some crashes when block io or inode allocation failed
-2.06 Fixed some crash on corrupted disk structures
- Better allocation strategy
- Reschedule points added so that it doesn't lock CPU long time
- It should work in read-only mode on Warp Server
-2.07 More fixes for Warp Server. Now it really works
-2.08 Creating new files is not so slow on large disks
- An attempt to sync deleted file does not generate filesystem error
-2.09 Fixed error on extremely fragmented files
-
-
- vim: set textwidth=80:
+1.98 Fixed a deadlock when using old_readdir
+ Better directory handling; workaround for "unbalanced tree" bug in OS/2
+1.99 Corrected a possible problem when there's not enough space while deleting
+ file
+
+ Now it tries to truncate the file if there's not enough space when
+ deleting
+
+ Removed a lot of redundant code
+2.00 Fixed a bug in rename (it was there since 1.96)
+ Better anti-fragmentation strategy
+2.01 Fixed problem with directory listing over NFS
+
+ Directory lseek now checks for proper parameters
+
+ Fixed race-condition in buffer code - it is in all filesystems in Linux;
+ when reading device (cat /dev/hda) while creating files on it, files
+ could be damaged
+2.02 Workaround for bug in breada in Linux. breada could cause accesses beyond
+ end of partition
+2.03 Char, block devices and pipes are correctly created
+
+ Fixed non-crashing race in unlink (Alexander Viro)
+
+ Now it works with Japanese version of OS/2
+2.04 Fixed error when ftruncate used to extend file
+2.05 Fixed crash when got mount parameters without =
+
+ Fixed crash when allocation of anode failed due to full disk
+
+ Fixed some crashes when block io or inode allocation failed
+2.06 Fixed some crash on corrupted disk structures
+
+ Better allocation strategy
+
+ Reschedule points added so that it doesn't lock CPU long time
+
+ It should work in read-only mode on Warp Server
+2.07 More fixes for Warp Server. Now it really works
+2.08 Creating new files is not so slow on large disks
+
+ An attempt to sync deleted file does not generate filesystem error
+2.09 Fixed error on extremely fragmented files
+====== =========================================================================
+.. _filesystems_index:
+
===============================
Filesystems in the Linux kernel
===============================
.. toctree::
:maxdepth: 2
+ 9p
+ adfs
+ affs
+ afs
autofs
+ autofs-mount-control
+ befs
+ bfs
+ btrfs
+ ceph
+ cramfs
+ debugfs
+ dlmfs
+ ecryptfs
+ efivarfs
+ erofs
+ ext2
+ ext3
+ f2fs
+ gfs2
+ gfs2-uevents
+ hfs
+ hfsplus
+ hpfs
fuse
+ inotify
+ isofs
+ nilfs2
+ nfs/index
+ ntfs
+ ocfs2
+ ocfs2-online-filecheck
+ omfs
+ orangefs
overlayfs
+ proc
+ qnx6
+ ramfs-rootfs-initramfs
+ relay
+ romfs
+ squashfs
+ sysfs
+ sysv-fs
+ tmpfs
+ ubifs
+ ubifs-authentication.rst
+ udf
virtiofs
vfat
+ zonefs
- inotify
- a powerful yet simple file change notification system
+.. SPDX-License-Identifier: GPL-2.0
+
+===============================================================
+Inotify - A Powerful yet Simple File Change Notification System
+===============================================================
Document started 15 Mar 2005 by Robert Love <rml@novell.com>
+
Document updated 4 Jan 2015 by Zhang Zhen <zhenzhang.zhang@huawei.com>
- --Deleted obsoleted interface, just refer to manpages for user interface.
+
+ - Deleted obsoleted interface, just refer to manpages for user interface.
(i) Rationale
-Q: What is the design decision behind not tying the watch to the open fd of
+Q:
+ What is the design decision behind not tying the watch to the open fd of
the watched object?
-A: Watches are associated with an open inotify device, not an open file.
+A:
+ Watches are associated with an open inotify device, not an open file.
This solves the primary problem with dnotify: keeping the file open pins
the file and thus, worse, pins the mount. Dnotify is therefore infeasible
for use on a desktop system with removable media as the media cannot be
unmounted. Watching a file should not require that it be open.
-Q: What is the design decision behind using an-fd-per-instance as opposed to
+Q:
+ What is the design decision behind using an-fd-per-instance as opposed to
an fd-per-watch?
-A: An fd-per-watch quickly consumes more file descriptors than are allowed,
+A:
+ An fd-per-watch quickly consumes more file descriptors than are allowed,
more fd's than are feasible to manage, and more fd's than are optimally
select()-able. Yes, root can bump the per-process fd limit and yes, users
can use epoll, but requiring both is a silly and extraneous requirement.
spaces is thus sensible. The current design is what user-space developers
want: Users initialize inotify, once, and add n watches, requiring but one
fd and no twiddling with fd limits. Initializing an inotify instance two
- thousand times is silly. If we can implement user-space's preferences
- cleanly--and we can, the idr layer makes stuff like this trivial--then we
+ thousand times is silly. If we can implement user-space's preferences
+ cleanly--and we can, the idr layer makes stuff like this trivial--then we
should.
There are other good arguments. With a single fd, there is a single
need not be a one-fd-per-process mapping; it is one-fd-per-queue and a
process can easily want more than one queue.
-Q: Why the system call approach?
+Q:
+ Why the system call approach?
-A: The poor user-space interface is the second biggest problem with dnotify.
+A:
+ The poor user-space interface is the second biggest problem with dnotify.
Signals are a terrible, terrible interface for file notification. Or for
anything, for that matter. The ideal solution, from all perspectives, is a
file descriptor-based one that allows basic file I/O and poll/select.
--- /dev/null
+.. SPDX-License-Identifier: GPL-2.0
+
+==================
+ISO9660 Filesystem
+==================
+
+Mount options that are the same as for msdos and vfat partitions.
+
+ ========= ========================================================
+ gid=nnn All files in the partition will be in group nnn.
+ uid=nnn All files in the partition will be owned by user id nnn.
+ umask=nnn The permission mask (see umask(1)) for the partition.
+ ========= ========================================================
+
+Mount options that are the same as vfat partitions. These are only useful
+when using discs encoded using Microsoft's Joliet extensions.
+
+ ============== =============================================================
+ iocharset=name Character set to use for converting from Unicode to
+ ASCII. Joliet filenames are stored in Unicode format, but
+ Unix for the most part doesn't know how to deal with Unicode.
+ There is also an option of doing UTF-8 translations with the
+ utf8 option.
+ utf8 Encode Unicode names in UTF-8 format. Default is no.
+ ============== =============================================================
+
+Mount options unique to the isofs filesystem.
+
+ ================= ============================================================
+ block=512 Set the block size for the disk to 512 bytes
+ block=1024 Set the block size for the disk to 1024 bytes
+ block=2048 Set the block size for the disk to 2048 bytes
+ check=relaxed Matches filenames with different cases
+ check=strict Matches only filenames with the exact same case
+ cruft Try to handle badly formatted CDs.
+ map=off Do not map non-Rock Ridge filenames to lower case
+ map=normal Map non-Rock Ridge filenames to lower case
+ map=acorn As map=normal but also apply Acorn extensions if present
+ mode=xxx Sets the permissions on files to xxx unless Rock Ridge
+ extensions set the permissions otherwise
+ dmode=xxx Sets the permissions on directories to xxx unless Rock Ridge
+ extensions set the permissions otherwise
+ overriderockperm Set permissions on files and directories according to
+ 'mode' and 'dmode' even though Rock Ridge extensions are
+ present.
+ nojoliet Ignore Joliet extensions if they are present.
+ norock Ignore Rock Ridge extensions if they are present.
+ hide Completely strip hidden files from the file system.
+ showassoc Show files marked with the 'associated' bit
+ unhide Deprecated; showing hidden files is now default;
+ If given, it is a synonym for 'showassoc' which will
+ recreate previous unhide behavior
+ session=x Select number of session on multisession CD
+ sbsector=xxx Session begins from sector xxx
+ ================= ============================================================
+
+Recommended documents about ISO 9660 standard are located at:
+
+- http://www.y-adagio.com/
+- ftp://ftp.ecma.ch/ecma-st/Ecma-119.pdf
+
+Quoting from the PDF "This 2nd Edition of Standard ECMA-119 is technically
+identical with ISO 9660.", so it is a valid and gratis substitute of the
+official ISO specification.
+++ /dev/null
-Mount options that are the same as for msdos and vfat partitions.
-
- gid=nnn All files in the partition will be in group nnn.
- uid=nnn All files in the partition will be owned by user id nnn.
- umask=nnn The permission mask (see umask(1)) for the partition.
-
-Mount options that are the same as vfat partitions. These are only useful
-when using discs encoded using Microsoft's Joliet extensions.
- iocharset=name Character set to use for converting from Unicode to
- ASCII. Joliet filenames are stored in Unicode format, but
- Unix for the most part doesn't know how to deal with Unicode.
- There is also an option of doing UTF-8 translations with the
- utf8 option.
- utf8 Encode Unicode names in UTF-8 format. Default is no.
-
-Mount options unique to the isofs filesystem.
- block=512 Set the block size for the disk to 512 bytes
- block=1024 Set the block size for the disk to 1024 bytes
- block=2048 Set the block size for the disk to 2048 bytes
- check=relaxed Matches filenames with different cases
- check=strict Matches only filenames with the exact same case
- cruft Try to handle badly formatted CDs.
- map=off Do not map non-Rock Ridge filenames to lower case
- map=normal Map non-Rock Ridge filenames to lower case
- map=acorn As map=normal but also apply Acorn extensions if present
- mode=xxx Sets the permissions on files to xxx unless Rock Ridge
- extensions set the permissions otherwise
- dmode=xxx Sets the permissions on directories to xxx unless Rock Ridge
- extensions set the permissions otherwise
- overriderockperm Set permissions on files and directories according to
- 'mode' and 'dmode' even though Rock Ridge extensions are
- present.
- nojoliet Ignore Joliet extensions if they are present.
- norock Ignore Rock Ridge extensions if they are present.
- hide Completely strip hidden files from the file system.
- showassoc Show files marked with the 'associated' bit
- unhide Deprecated; showing hidden files is now default;
- If given, it is a synonym for 'showassoc' which will
- recreate previous unhide behavior
- session=x Select number of session on multisession CD
- sbsector=xxx Session begins from sector xxx
-
-Recommended documents about ISO 9660 standard are located at:
-http://www.y-adagio.com/
-ftp://ftp.ecma.ch/ecma-st/Ecma-119.pdf
-Quoting from the PDF "This 2nd Edition of Standard ECMA-119 is technically
-identical with ISO 9660.", so it is a valid and gratis substitute of the
-official ISO specification.
--- /dev/null
+===============================
+NFS
+===============================
+
+
+.. toctree::
+ :maxdepth: 1
+
+ pnfs
+ rpc-cache
+ rpc-server-gss
+ nfs41-server
+ knfsd-stats
-
+============================
Kernel NFS Server Statistics
============================
+:Authors: Greg Banks <gnb@sgi.com> - 26 Mar 2009
+
This document describes the format and semantics of the statistics
which the kernel NFS server makes available to userspace. These
statistics are available in several text form pseudo files, each of
separated by whitespace.
/proc/fs/nfsd/pool_stats
-------------------------
+========================
This file is available in kernels from 2.6.30 onwards, if the
/proc/fs/nfsd filesystem is mounted (it almost always should be).
(sockets-enqueued counts this case), or the packet can be temporarily
deferred because the transport is currently being used by an nfsd
thread. This last case is not very interesting and is not explicitly
-counted, but can be inferred from the other counters thus:
+counted, but can be inferred from the other counters thus::
-packets-deferred = packets-arrived - ( sockets-enqueued + threads-woken )
+ packets-deferred = packets-arrived - ( sockets-enqueued + threads-woken )
More
-----
-Descriptions of the other statistics file should go here.
-
+====
-Greg Banks <gnb@sgi.com>
-26 Mar 2009
+Descriptions of the other statistics file should go here.
--- /dev/null
+=============================
+NFSv4.1 Server Implementation
+=============================
+
+Server support for minorversion 1 can be controlled using the
+/proc/fs/nfsd/versions control file. The string output returned
+by reading this file will contain either "+4.1" or "-4.1"
+correspondingly.
+
+Currently, server support for minorversion 1 is enabled by default.
+It can be disabled at run time by writing the string "-4.1" to
+the /proc/fs/nfsd/versions control file. Note that to write this
+control file, the nfsd service must be taken down. You can use rpc.nfsd
+for this; see rpc.nfsd(8).
+
+(Warning: older servers will interpret "+4.1" and "-4.1" as "+4" and
+"-4", respectively. Therefore, code meant to work on both new and old
+kernels must turn 4.1 on or off *before* turning support for version 4
+on or off; rpc.nfsd does this correctly.)
+
+The NFSv4 minorversion 1 (NFSv4.1) implementation in nfsd is based
+on RFC 5661.
+
+From the many new features in NFSv4.1 the current implementation
+focuses on the mandatory-to-implement NFSv4.1 Sessions, providing
+"exactly once" semantics and better control and throttling of the
+resources allocated for each client.
+
+The table below, taken from the NFSv4.1 document, lists
+the operations that are mandatory to implement (REQ), optional
+(OPT), and NFSv4.0 operations that are required not to implement (MNI)
+in minor version 1. The first column indicates the operations that
+are not supported yet by the linux server implementation.
+
+The OPTIONAL features identified and their abbreviations are as follows:
+
+- **pNFS** Parallel NFS
+- **FDELG** File Delegations
+- **DDELG** Directory Delegations
+
+The following abbreviations indicate the linux server implementation status.
+
+- **I** Implemented NFSv4.1 operations.
+- **NS** Not Supported.
+- **NS\*** Unimplemented optional feature.
+
+Operations
+==========
+
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| Implementation status | Operation | REQ,REC, OPT or NMI | Feature (REQ, REC or OPT) | Definition |
++=======================+======================+=====================+===========================+================+
+| | ACCESS | REQ | | Section 18.1 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| I | BACKCHANNEL_CTL | REQ | | Section 18.33 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| I | BIND_CONN_TO_SESSION | REQ | | Section 18.34 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | CLOSE | REQ | | Section 18.2 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | COMMIT | REQ | | Section 18.3 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | CREATE | REQ | | Section 18.4 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| I | CREATE_SESSION | REQ | | Section 18.36 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| NS* | DELEGPURGE | OPT | FDELG (REQ) | Section 18.5 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | DELEGRETURN | OPT | FDELG, | Section 18.6 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | | | DDELG, pNFS | |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | | | (REQ) | |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| I | DESTROY_CLIENTID | REQ | | Section 18.50 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| I | DESTROY_SESSION | REQ | | Section 18.37 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| I | EXCHANGE_ID | REQ | | Section 18.35 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| I | FREE_STATEID | REQ | | Section 18.38 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | GETATTR | REQ | | Section 18.7 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| I | GETDEVICEINFO | OPT | pNFS (REQ) | Section 18.40 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| NS* | GETDEVICELIST | OPT | pNFS (OPT) | Section 18.41 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | GETFH | REQ | | Section 18.8 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| NS* | GET_DIR_DELEGATION | OPT | DDELG (REQ) | Section 18.39 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| I | LAYOUTCOMMIT | OPT | pNFS (REQ) | Section 18.42 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| I | LAYOUTGET | OPT | pNFS (REQ) | Section 18.43 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| I | LAYOUTRETURN | OPT | pNFS (REQ) | Section 18.44 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | LINK | OPT | | Section 18.9 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | LOCK | REQ | | Section 18.10 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | LOCKT | REQ | | Section 18.11 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | LOCKU | REQ | | Section 18.12 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | LOOKUP | REQ | | Section 18.13 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | LOOKUPP | REQ | | Section 18.14 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | NVERIFY | REQ | | Section 18.15 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | OPEN | REQ | | Section 18.16 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| NS* | OPENATTR | OPT | | Section 18.17 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | OPEN_CONFIRM | MNI | | N/A |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | OPEN_DOWNGRADE | REQ | | Section 18.18 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | PUTFH | REQ | | Section 18.19 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | PUTPUBFH | REQ | | Section 18.20 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | PUTROOTFH | REQ | | Section 18.21 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | READ | REQ | | Section 18.22 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | READDIR | REQ | | Section 18.23 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | READLINK | OPT | | Section 18.24 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | RECLAIM_COMPLETE | REQ | | Section 18.51 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | RELEASE_LOCKOWNER | MNI | | N/A |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | REMOVE | REQ | | Section 18.25 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | RENAME | REQ | | Section 18.26 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | RENEW | MNI | | N/A |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | RESTOREFH | REQ | | Section 18.27 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | SAVEFH | REQ | | Section 18.28 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | SECINFO | REQ | | Section 18.29 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| I | SECINFO_NO_NAME | REC | pNFS files | Section 18.45, |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | | | layout (REQ) | Section 13.12 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| I | SEQUENCE | REQ | | Section 18.46 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | SETATTR | REQ | | Section 18.30 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | SETCLIENTID | MNI | | N/A |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | SETCLIENTID_CONFIRM | MNI | | N/A |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| NS | SET_SSV | REQ | | Section 18.47 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| I | TEST_STATEID | REQ | | Section 18.48 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | VERIFY | REQ | | Section 18.31 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| NS* | WANT_DELEGATION | OPT | FDELG (OPT) | Section 18.49 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+| | WRITE | REQ | | Section 18.32 |
++-----------------------+----------------------+---------------------+---------------------------+----------------+
+
+
+Callback Operations
+===================
++-----------------------+-------------------------+---------------------+---------------------------+---------------+
+| Implementation status | Operation | REQ,REC, OPT or NMI | Feature (REQ, REC or OPT) | Definition |
++=======================+=========================+=====================+===========================+===============+
+| | CB_GETATTR | OPT | FDELG (REQ) | Section 20.1 |
++-----------------------+-------------------------+---------------------+---------------------------+---------------+
+| I | CB_LAYOUTRECALL | OPT | pNFS (REQ) | Section 20.3 |
++-----------------------+-------------------------+---------------------+---------------------------+---------------+
+| NS* | CB_NOTIFY | OPT | DDELG (REQ) | Section 20.4 |
++-----------------------+-------------------------+---------------------+---------------------------+---------------+
+| NS* | CB_NOTIFY_DEVICEID | OPT | pNFS (OPT) | Section 20.12 |
++-----------------------+-------------------------+---------------------+---------------------------+---------------+
+| NS* | CB_NOTIFY_LOCK | OPT | | Section 20.11 |
++-----------------------+-------------------------+---------------------+---------------------------+---------------+
+| NS* | CB_PUSH_DELEG | OPT | FDELG (OPT) | Section 20.5 |
++-----------------------+-------------------------+---------------------+---------------------------+---------------+
+| | CB_RECALL | OPT | FDELG, | Section 20.2 |
++-----------------------+-------------------------+---------------------+---------------------------+---------------+
+| | | | DDELG, pNFS | |
++-----------------------+-------------------------+---------------------+---------------------------+---------------+
+| | | | (REQ) | |
++-----------------------+-------------------------+---------------------+---------------------------+---------------+
+| NS* | CB_RECALL_ANY | OPT | FDELG, | Section 20.6 |
++-----------------------+-------------------------+---------------------+---------------------------+---------------+
+| | | | DDELG, pNFS | |
++-----------------------+-------------------------+---------------------+---------------------------+---------------+
+| | | | (REQ) | |
++-----------------------+-------------------------+---------------------+---------------------------+---------------+
+| NS | CB_RECALL_SLOT | REQ | | Section 20.8 |
++-----------------------+-------------------------+---------------------+---------------------------+---------------+
+| NS* | CB_RECALLABLE_OBJ_AVAIL | OPT | DDELG, pNFS | Section 20.7 |
++-----------------------+-------------------------+---------------------+---------------------------+---------------+
+| | | | (REQ) | |
++-----------------------+-------------------------+---------------------+---------------------------+---------------+
+| I | CB_SEQUENCE | OPT | FDELG, | Section 20.9 |
++-----------------------+-------------------------+---------------------+---------------------------+---------------+
+| | | | DDELG, pNFS | |
++-----------------------+-------------------------+---------------------+---------------------------+---------------+
+| | | | (REQ) | |
++-----------------------+-------------------------+---------------------+---------------------------+---------------+
+| NS* | CB_WANTS_CANCELLED | OPT | FDELG, | Section 20.10 |
++-----------------------+-------------------------+---------------------+---------------------------+---------------+
+| | | | DDELG, pNFS | |
++-----------------------+-------------------------+---------------------+---------------------------+---------------+
+| | | | (REQ) | |
++-----------------------+-------------------------+---------------------+---------------------------+---------------+
+
+
+Implementation notes:
+=====================
+
+SSV:
+ The spec claims this is mandatory, but we don't actually know of any
+ implementations, so we're ignoring it for now. The server returns
+ NFS4ERR_ENCR_ALG_UNSUPP on EXCHANGE_ID, which should be future-proof.
+
+GSS on the backchannel:
+ Again, theoretically required but not widely implemented (in
+ particular, the current Linux client doesn't request it). We return
+ NFS4ERR_ENCR_ALG_UNSUPP on CREATE_SESSION.
+
+DELEGPURGE:
+ mandatory only for servers that support CLAIM_DELEGATE_PREV and/or
+ CLAIM_DELEG_PREV_FH (which allows clients to keep delegations that
+ persist across client reboots). Thus we need not implement this for
+ now.
+
+EXCHANGE_ID:
+ implementation ids are ignored
+
+CREATE_SESSION:
+ backchannel attributes are ignored
+
+SEQUENCE:
+ no support for dynamic slot table renegotiation (optional)
+
+Nonstandard compound limitations:
+ No support for a sessions fore channel RPC compound that requires both a
+ ca_maxrequestsize request and a ca_maxresponsesize reply, so we may
+ fail to live up to the promise we made in CREATE_SESSION fore channel
+ negotiation.
+
+See also http://wiki.linux-nfs.org/wiki/index.php/Server_4.0_and_4.1_issues.
+++ /dev/null
-NFSv4.1 Server Implementation
-
-Server support for minorversion 1 can be controlled using the
-/proc/fs/nfsd/versions control file. The string output returned
-by reading this file will contain either "+4.1" or "-4.1"
-correspondingly.
-
-Currently, server support for minorversion 1 is enabled by default.
-It can be disabled at run time by writing the string "-4.1" to
-the /proc/fs/nfsd/versions control file. Note that to write this
-control file, the nfsd service must be taken down. You can use rpc.nfsd
-for this; see rpc.nfsd(8).
-
-(Warning: older servers will interpret "+4.1" and "-4.1" as "+4" and
-"-4", respectively. Therefore, code meant to work on both new and old
-kernels must turn 4.1 on or off *before* turning support for version 4
-on or off; rpc.nfsd does this correctly.)
-
-The NFSv4 minorversion 1 (NFSv4.1) implementation in nfsd is based
-on RFC 5661.
-
-From the many new features in NFSv4.1 the current implementation
-focuses on the mandatory-to-implement NFSv4.1 Sessions, providing
-"exactly once" semantics and better control and throttling of the
-resources allocated for each client.
-
-The table below, taken from the NFSv4.1 document, lists
-the operations that are mandatory to implement (REQ), optional
-(OPT), and NFSv4.0 operations that are required not to implement (MNI)
-in minor version 1. The first column indicates the operations that
-are not supported yet by the linux server implementation.
-
-The OPTIONAL features identified and their abbreviations are as follows:
- pNFS Parallel NFS
- FDELG File Delegations
- DDELG Directory Delegations
-
-The following abbreviations indicate the linux server implementation status.
- I Implemented NFSv4.1 operations.
- NS Not Supported.
- NS* Unimplemented optional feature.
-
-Operations
-
- +----------------------+------------+--------------+----------------+
- | Operation | REQ, REC, | Feature | Definition |
- | | OPT, or | (REQ, REC, | |
- | | MNI | or OPT) | |
- +----------------------+------------+--------------+----------------+
- | ACCESS | REQ | | Section 18.1 |
-I | BACKCHANNEL_CTL | REQ | | Section 18.33 |
-I | BIND_CONN_TO_SESSION | REQ | | Section 18.34 |
- | CLOSE | REQ | | Section 18.2 |
- | COMMIT | REQ | | Section 18.3 |
- | CREATE | REQ | | Section 18.4 |
-I | CREATE_SESSION | REQ | | Section 18.36 |
-NS*| DELEGPURGE | OPT | FDELG (REQ) | Section 18.5 |
- | DELEGRETURN | OPT | FDELG, | Section 18.6 |
- | | | DDELG, pNFS | |
- | | | (REQ) | |
-I | DESTROY_CLIENTID | REQ | | Section 18.50 |
-I | DESTROY_SESSION | REQ | | Section 18.37 |
-I | EXCHANGE_ID | REQ | | Section 18.35 |
-I | FREE_STATEID | REQ | | Section 18.38 |
- | GETATTR | REQ | | Section 18.7 |
-I | GETDEVICEINFO | OPT | pNFS (REQ) | Section 18.40 |
-NS*| GETDEVICELIST | OPT | pNFS (OPT) | Section 18.41 |
- | GETFH | REQ | | Section 18.8 |
-NS*| GET_DIR_DELEGATION | OPT | DDELG (REQ) | Section 18.39 |
-I | LAYOUTCOMMIT | OPT | pNFS (REQ) | Section 18.42 |
-I | LAYOUTGET | OPT | pNFS (REQ) | Section 18.43 |
-I | LAYOUTRETURN | OPT | pNFS (REQ) | Section 18.44 |
- | LINK | OPT | | Section 18.9 |
- | LOCK | REQ | | Section 18.10 |
- | LOCKT | REQ | | Section 18.11 |
- | LOCKU | REQ | | Section 18.12 |
- | LOOKUP | REQ | | Section 18.13 |
- | LOOKUPP | REQ | | Section 18.14 |
- | NVERIFY | REQ | | Section 18.15 |
- | OPEN | REQ | | Section 18.16 |
-NS*| OPENATTR | OPT | | Section 18.17 |
- | OPEN_CONFIRM | MNI | | N/A |
- | OPEN_DOWNGRADE | REQ | | Section 18.18 |
- | PUTFH | REQ | | Section 18.19 |
- | PUTPUBFH | REQ | | Section 18.20 |
- | PUTROOTFH | REQ | | Section 18.21 |
- | READ | REQ | | Section 18.22 |
- | READDIR | REQ | | Section 18.23 |
- | READLINK | OPT | | Section 18.24 |
- | RECLAIM_COMPLETE | REQ | | Section 18.51 |
- | RELEASE_LOCKOWNER | MNI | | N/A |
- | REMOVE | REQ | | Section 18.25 |
- | RENAME | REQ | | Section 18.26 |
- | RENEW | MNI | | N/A |
- | RESTOREFH | REQ | | Section 18.27 |
- | SAVEFH | REQ | | Section 18.28 |
- | SECINFO | REQ | | Section 18.29 |
-I | SECINFO_NO_NAME | REC | pNFS files | Section 18.45, |
- | | | layout (REQ) | Section 13.12 |
-I | SEQUENCE | REQ | | Section 18.46 |
- | SETATTR | REQ | | Section 18.30 |
- | SETCLIENTID | MNI | | N/A |
- | SETCLIENTID_CONFIRM | MNI | | N/A |
-NS | SET_SSV | REQ | | Section 18.47 |
-I | TEST_STATEID | REQ | | Section 18.48 |
- | VERIFY | REQ | | Section 18.31 |
-NS*| WANT_DELEGATION | OPT | FDELG (OPT) | Section 18.49 |
- | WRITE | REQ | | Section 18.32 |
-
-Callback Operations
-
- +-------------------------+-----------+-------------+---------------+
- | Operation | REQ, REC, | Feature | Definition |
- | | OPT, or | (REQ, REC, | |
- | | MNI | or OPT) | |
- +-------------------------+-----------+-------------+---------------+
- | CB_GETATTR | OPT | FDELG (REQ) | Section 20.1 |
-I | CB_LAYOUTRECALL | OPT | pNFS (REQ) | Section 20.3 |
-NS*| CB_NOTIFY | OPT | DDELG (REQ) | Section 20.4 |
-NS*| CB_NOTIFY_DEVICEID | OPT | pNFS (OPT) | Section 20.12 |
-NS*| CB_NOTIFY_LOCK | OPT | | Section 20.11 |
-NS*| CB_PUSH_DELEG | OPT | FDELG (OPT) | Section 20.5 |
- | CB_RECALL | OPT | FDELG, | Section 20.2 |
- | | | DDELG, pNFS | |
- | | | (REQ) | |
-NS*| CB_RECALL_ANY | OPT | FDELG, | Section 20.6 |
- | | | DDELG, pNFS | |
- | | | (REQ) | |
-NS | CB_RECALL_SLOT | REQ | | Section 20.8 |
-NS*| CB_RECALLABLE_OBJ_AVAIL | OPT | DDELG, pNFS | Section 20.7 |
- | | | (REQ) | |
-I | CB_SEQUENCE | OPT | FDELG, | Section 20.9 |
- | | | DDELG, pNFS | |
- | | | (REQ) | |
-NS*| CB_WANTS_CANCELLED | OPT | FDELG, | Section 20.10 |
- | | | DDELG, pNFS | |
- | | | (REQ) | |
- +-------------------------+-----------+-------------+---------------+
-
-Implementation notes:
-
-SSV:
-* The spec claims this is mandatory, but we don't actually know of any
- implementations, so we're ignoring it for now. The server returns
- NFS4ERR_ENCR_ALG_UNSUPP on EXCHANGE_ID, which should be future-proof.
-
-GSS on the backchannel:
-* Again, theoretically required but not widely implemented (in
- particular, the current Linux client doesn't request it). We return
- NFS4ERR_ENCR_ALG_UNSUPP on CREATE_SESSION.
-
-DELEGPURGE:
-* mandatory only for servers that support CLAIM_DELEGATE_PREV and/or
- CLAIM_DELEG_PREV_FH (which allows clients to keep delegations that
- persist across client reboots). Thus we need not implement this for
- now.
-
-EXCHANGE_ID:
-* implementation ids are ignored
-
-CREATE_SESSION:
-* backchannel attributes are ignored
-
-SEQUENCE:
-* no support for dynamic slot table renegotiation (optional)
-
-Nonstandard compound limitations:
-* No support for a sessions fore channel RPC compound that requires both a
- ca_maxrequestsize request and a ca_maxresponsesize reply, so we may
- fail to live up to the promise we made in CREATE_SESSION fore channel
- negotiation.
-
-See also http://wiki.linux-nfs.org/wiki/index.php/Server_4.0_and_4.1_issues.
-Reference counting in pnfs:
+==========================
+Reference counting in pnfs
==========================
The are several inter-related caches. We have layouts which can
reference multiple devices, each of which can reference multiple data servers.
Each data server can be referenced by multiple devices. Each device
-can be referenced by multiple layouts. To keep all of this straight,
+can be referenced by multiple layouts. To keep all of this straight,
we need to reference count.
struct pnfs_layout_hdr
-----------------------
+======================
+
The on-the-wire command LAYOUTGET corresponds to struct
pnfs_layout_segment, usually referred to by the variable name lseg.
Each nfs_inode may hold a pointer to a cache of these layout
keeps it in the list.
deviceid_cache
---------------
+==============
+
lsegs reference device ids, which are resolved per nfs_client and
layout driver type. The device ids are held in a RCU cache (struct
nfs4_deviceid_cache). The cache itself is referenced across each
deviceid's per filesystem, and multiple filesystems per nfs_client.
The hash code is copied from the nfsd code base. A discussion of
-hashing and variations of this algorithm can be found at:
-http://groups.google.com/group/comp.lang.c/browse_thread/thread/9522965e2b8d3809
+hashing and variations of this algorithm can be found `here.
+<http://groups.google.com/group/comp.lang.c/browse_thread/thread/9522965e2b8d3809>`_
data server cache
------------------
+=================
+
file driver devices refer to data servers, which are kept in a module
level cache. Its reference is held over the lifetime of the deviceid
pointing to it.
lseg
-----
+====
+
lseg maintains an extra reference corresponding to the NFS_LSEG_VALID
bit which holds it in the pnfs_layout_hdr's list. When the final lseg
is removed from the pnfs_layout_hdr's list, the NFS_LAYOUT_DESTROYED
bit is set, preventing any new lsegs from being added.
layout drivers
---------------
+==============
PNFS utilizes what is called layout drivers. The STD defines 4 basic
layout types: "files", "objects", "blocks", and "flexfiles". For each
Flexfiles-layout-driver code is in: fs/nfs/flexfilelayout/.. directory
blocks-layout setup
--------------------
+===================
TODO: Document the setup needs of the blocks layout driver
- This document gives a brief introduction to the caching
+=========
+RPC Cache
+=========
+
+This document gives a brief introduction to the caching
mechanisms in the sunrpc layer that is used, in particular,
for NFS authentication.
-CACHES
+Caches
======
+
The caching replaces the old exports table and allows for
a wide variety of values to be caches.
of common code for managing these caches.
Examples of caches that are likely to be needed are:
+
- mapping from IP address to client name
- mapping from client name and filesystem to export options
- mapping from UID to list of GIDs, to work around NFS's limitation
- mapping from network identify to public key for crypto authentication.
The common code handles such things as:
+
- general cache lookup with correct locking
- supporting 'NEGATIVE' as well as positive entries
- allowing an EXPIRED time on cache items, and removing
Creating a Cache
----------------
-1/ A cache needs a datum to store. This is in the form of a
- structure definition that must contain a
- struct cache_head
+- A cache needs a datum to store. This is in the form of a
+ structure definition that must contain a struct cache_head
as an element, usually the first.
It will also contain a key and some content.
Each cache element is reference counted and contains
expiry and update times for use in cache management.
-2/ A cache needs a "cache_detail" structure that
+- A cache needs a "cache_detail" structure that
describes the cache. This stores the hash table, some
parameters for cache management, and some operations detailing how
to work with particular cache items.
- The operations requires are:
- struct cache_head *alloc(void)
- This simply allocates appropriate memory and returns
- a pointer to the cache_detail embedded within the
- structure
- void cache_put(struct kref *)
- This is called when the last reference to an item is
- dropped. The pointer passed is to the 'ref' field
- in the cache_head. cache_put should release any
- references create by 'cache_init' and, if CACHE_VALID
- is set, any references created by cache_update.
- It should then release the memory allocated by
- 'alloc'.
- int match(struct cache_head *orig, struct cache_head *new)
- test if the keys in the two structures match. Return
- 1 if they do, 0 if they don't.
- void init(struct cache_head *orig, struct cache_head *new)
- Set the 'key' fields in 'new' from 'orig'. This may
- include taking references to shared objects.
- void update(struct cache_head *orig, struct cache_head *new)
- Set the 'content' fileds in 'new' from 'orig'.
- int cache_show(struct seq_file *m, struct cache_detail *cd,
- struct cache_head *h)
- Optional. Used to provide a /proc file that lists the
- contents of a cache. This should show one item,
- usually on just one line.
- int cache_request(struct cache_detail *cd, struct cache_head *h,
- char **bpp, int *blen)
- Format a request to be send to user-space for an item
- to be instantiated. *bpp is a buffer of size *blen.
- bpp should be moved forward over the encoded message,
- and *blen should be reduced to show how much free
- space remains. Return 0 on success or <0 if not
- enough room or other problem.
- int cache_parse(struct cache_detail *cd, char *buf, int len)
- A message from user space has arrived to fill out a
- cache entry. It is in 'buf' of length 'len'.
- cache_parse should parse this, find the item in the
- cache with sunrpc_cache_lookup_rcu, and update the item
- with sunrpc_cache_update.
-
-
-3/ A cache needs to be registered using cache_register(). This
+
+ The operations are:
+
+ struct cache_head \*alloc(void)
+ This simply allocates appropriate memory and returns
+ a pointer to the cache_detail embedded within the
+ structure
+
+ void cache_put(struct kref \*)
+ This is called when the last reference to an item is
+ dropped. The pointer passed is to the 'ref' field
+ in the cache_head. cache_put should release any
+ references create by 'cache_init' and, if CACHE_VALID
+ is set, any references created by cache_update.
+ It should then release the memory allocated by
+ 'alloc'.
+
+ int match(struct cache_head \*orig, struct cache_head \*new)
+ test if the keys in the two structures match. Return
+ 1 if they do, 0 if they don't.
+
+ void init(struct cache_head \*orig, struct cache_head \*new)
+ Set the 'key' fields in 'new' from 'orig'. This may
+ include taking references to shared objects.
+
+ void update(struct cache_head \*orig, struct cache_head \*new)
+ Set the 'content' fileds in 'new' from 'orig'.
+
+ int cache_show(struct seq_file \*m, struct cache_detail \*cd, struct cache_head \*h)
+ Optional. Used to provide a /proc file that lists the
+ contents of a cache. This should show one item,
+ usually on just one line.
+
+ int cache_request(struct cache_detail \*cd, struct cache_head \*h, char \*\*bpp, int \*blen)
+ Format a request to be send to user-space for an item
+ to be instantiated. \*bpp is a buffer of size \*blen.
+ bpp should be moved forward over the encoded message,
+ and \*blen should be reduced to show how much free
+ space remains. Return 0 on success or <0 if not
+ enough room or other problem.
+
+ int cache_parse(struct cache_detail \*cd, char \*buf, int len)
+ A message from user space has arrived to fill out a
+ cache entry. It is in 'buf' of length 'len'.
+ cache_parse should parse this, find the item in the
+ cache with sunrpc_cache_lookup_rcu, and update the item
+ with sunrpc_cache_update.
+
+
+- A cache needs to be registered using cache_register(). This
includes it on a list of caches that will be regularly
cleaned to discard old data.
call is needed but not possible, -EAGAIN if an upcall is pending,
or 0 if the data is valid;
-cache_check can be passed a "struct cache_req *". This structure is
+cache_check can be passed a "struct cache_req\*". This structure is
typically embedded in the actual request and can be used to create a
deferred copy of the request (struct cache_deferred_req). This is
done when the found cache item is not uptodate, but the is reason to
passed as a whole to the cache for parsing and interpretation.
Each cache can treat the write requests differently, but it is
expected that a message written will contain:
+
- a key
- an expiry time
- a content.
+
with the intention that an item in the cache with the give key
should be create or updated to have the given content, and the
expiry time should be set on that item.
select or poll for read will block waiting for another request to be
added.
-Thus a user-space helper is likely to:
+Thus a user-space helper is likely to::
+
open the channel.
select for readable
read a request
takes a cache item and encodes a request into the buffer
provided.
-Note: If a cache has no active readers on the channel, and has had not
-active readers for more than 60 seconds, further requests will not be
-added to the channel but instead all lookups that do not find a valid
-entry will fail. This is partly for backward compatibility: The
-previous nfs exports table was deemed to be authoritative and a
-failed lookup meant a definite 'no'.
+.. note::
+ If a cache has no active readers on the channel, and has had not
+ active readers for more than 60 seconds, further requests will not be
+ added to the channel but instead all lookups that do not find a valid
+ entry will fail. This is partly for backward compatibility: The
+ previous nfs exports table was deemed to be authoritative and a
+ failed lookup meant a definite 'no'.
request/response format
-----------------------
Fields within the record should be separated by spaces, normally one.
If spaces, newlines, or nul characters are needed in a field they
much be quoted. two mechanisms are available:
-1/ If a field begins '\x' then it must contain an even number of
+
+- If a field begins '\x' then it must contain an even number of
hex digits, and pairs of these digits provide the bytes in the
field.
-2/ otherwise a \ in the field must be followed by 3 octal digits
+- otherwise a \ in the field must be followed by 3 octal digits
which give the code for a byte. Other characters are treated
as them selves. At the very least, space, newline, nul, and
'\' must be quoted in this way.
-
+=========================================
rpcsec_gss support for kernel RPC servers
=========================================
purposes of authentication.)
RPCGSS is specified in a few IETF documents:
+
- RFC2203 v1: http://tools.ietf.org/rfc/rfc2203.txt
- RFC5403 v2: http://tools.ietf.org/rfc/rfc5403.txt
+
and there is a 3rd version being proposed:
+
- http://tools.ietf.org/id/draft-williams-rpcsecgssv3.txt
(At draft n. 02 at the time of writing)
Background
-----------
+==========
The RPCGSS Authentication method describes a way to perform GSSAPI
Authentication for NFS. Although GSSAPI is itself completely mechanism
GSSAPI is a complex library, and implementing it completely in kernel is
unwarranted. However GSSAPI operations are fundementally separable in 2
parts:
+
- initial context establishment
- integrity/privacy protection (signing and encrypting of individual
packets)
need upcalls to request userspace to perform context establishment.
NFS Server Legacy Upcall Mechanism
-----------------------------------
+==================================
The classic upcall mechanism uses a custom text based upcall mechanism
to talk to a custom daemon called rpc.svcgssd that is provide by the
back to the kernel (4KiB).
NFS Server New RPC Upcall Mechanism
------------------------------------
+===================================
The newer upcall mechanism uses RPC over a unix socket to a daemon
called gss-proxy, implemented by a userspace program called Gssproxy.
-The gss_proxy RPC protocol is currently documented here:
-
- https://fedorahosted.org/gss-proxy/wiki/ProtocolDocumentation
+The gss_proxy RPC protocol is currently documented `here
+<https://fedorahosted.org/gss-proxy/wiki/ProtocolDocumentation>`_.
This upcall mechanism uses the kernel rpc client and connects to the gssproxy
userspace program over a regular unix socket. The gssproxy protocol does not
suffer from the size limitations of the legacy protocol.
Negotiating Upcall Mechanisms
------------------------------
+=============================
To provide backward compatibility, the kernel defaults to using the
legacy mechanism. To switch to the new mechanism, gss-proxy must bind
+.. SPDX-License-Identifier: GPL-2.0
+
+======
NILFS2
-------
+======
NILFS2 is a log-structured file system (LFS) supporting continuous
snapshotting. In addition to versioning capability of the entire file
cleaner or garbage collector) are required. Details on the tools are
described in the man pages included in the package.
-Project web page: https://nilfs.sourceforge.io/
-Download page: https://nilfs.sourceforge.io/en/download.html
-List info: http://vger.kernel.org/vger-lists.html#linux-nilfs
+:Project web page: https://nilfs.sourceforge.io/
+:Download page: https://nilfs.sourceforge.io/en/download.html
+:List info: http://vger.kernel.org/vger-lists.html#linux-nilfs
Caveats
=======
NILFS2 supports the following mount options:
(*) == default
+======================= =======================================================
barrier(*) This enables/disables the use of write barriers. This
nobarrier requires an IO stack which can support barriers, and
if nilfs gets an error on a barrier write, it will
nodiscard(*) The discard/TRIM commands are sent to the underlying
block device when blocks are freed. This is useful
for SSD devices and sparse/thinly-provisioned LUNs.
+======================= =======================================================
Ioctls
======
through the system call interfaces. The list of all NILFS2 specific ioctls are
shown in the table below.
-Table of NILFS2 specific ioctls
-..............................................................................
+Table of NILFS2 specific ioctls:
+
+ ============================== ===============================================
Ioctl Description
+ ============================== ===============================================
NILFS_IOCTL_CHANGE_CPMODE Change mode of given checkpoint between
checkpoint and snapshot state. This ioctl is
used in chcp and mkcp utilities.
NILFS_IOCTL_SET_ALLOC_RANGE Define lower limit of segments in bytes and
upper limit of segments in bytes. This ioctl
is used by nilfs_resize utility.
+ ============================== ===============================================
NILFS2 usage
============
-To use nilfs2 as a local file system, simply:
+To use nilfs2 as a local file system, simply::
# mkfs -t nilfs2 /dev/block_device
# mount -t nilfs2 /dev/block_device /dir
Checkpoints and snapshots are managed by the following commands.
Their manpages are included in the nilfs-utils package above.
+ ==== ===========================================================
lscp list checkpoints or snapshots.
mkcp make a checkpoint or a snapshot.
chcp change an existing checkpoint to a snapshot or vice versa.
rmcp invalidate specified checkpoint(s).
+ ==== ===========================================================
-To mount a snapshot,
+To mount a snapshot::
# mount -t nilfs2 -r -o cp=<cno> /dev/block_device /snap_dir
where <cno> is the checkpoint number of the snapshot.
-To unmount the NILFS2 mount point or snapshot, simply:
+To unmount the NILFS2 mount point or snapshot, simply::
# umount /dir
A nilfs2 volume is equally divided into a number of segments except
for the super block (SB) and segment #0. A segment is the container
of logs. Each log is composed of summary information blocks, payload
-blocks, and an optional super root block (SR):
+blocks, and an optional super root block (SR)::
______________________________________________________
| |SB| | Segment | Segment | Segment | ... | Segment | |
|_blocks__|_________________|__|
The payload blocks are organized per file, and each file consists of
-data blocks and B-tree node blocks:
+data blocks and B-tree node blocks::
|<--- File-A --->|<--- File-B --->|
_______________________________________________________________
The organization of the blocks is recorded in the summary information
blocks, which contains a header structure (nilfs_segment_summary), per
-file structures (nilfs_finfo), and per block structures (nilfs_binfo):
+file structures (nilfs_finfo), and per block structures (nilfs_binfo)::
_________________________________________________________________________
| Summary | finfo | binfo | ... | binfo | finfo | binfo | ... | binfo |...
The logs include regular files, directory files, symbolic link files
and several meta data files. The mata data files are the files used
to maintain file system meta data. The current version of NILFS2 uses
-the following meta data files:
+the following meta data files::
1) Inode file (ifile) -- Stores on-disk inodes
2) Checkpoint file (cpfile) -- Stores checkpoints
(DAT) block numbers. This file serves to
make on-disk blocks relocatable.
-The following figure shows a typical organization of the logs:
+The following figure shows a typical organization of the logs::
_________________________________________________________________________
| Summary | regular file | file | ... | ifile | cpfile | sufile | DAT |SR|
of regular files, directories, symlinks and other special files, are
included in the ifile. The inode of ifile itself is included in the
corresponding checkpoint entry in the cpfile. Thus, the hierarchy
-among NILFS2 files can be depicted as follows:
+among NILFS2 files can be depicted as follows::
Super block (SB)
|
+.. SPDX-License-Identifier: GPL-2.0
+
+================================
The Linux NTFS filesystem driver
================================
-Table of contents
-=================
+.. Table of contents
-- Overview
-- Web site
-- Features
-- Supported mount options
-- Known bugs and (mis-)features
-- Using NTFS volume and stripe sets
- - The Device-Mapper driver
- - The Software RAID / MD driver
- - Limitations when using the MD driver
+ - Overview
+ - Web site
+ - Features
+ - Supported mount options
+ - Known bugs and (mis-)features
+ - Using NTFS volume and stripe sets
+ - The Device-Mapper driver
+ - The Software RAID / MD driver
+ - Limitations when using the MD driver
Overview
partition by creating a large file while in Windows and then loopback
mounting the file while in Linux and creating a Linux filesystem on it that
is used to install Linux on it.
-- A comparison of the two drivers using:
+- A comparison of the two drivers using::
+
time find . -type f -exec md5sum "{}" \;
+
run three times in sequence with each driver (after a reboot) on a 1.4GiB
NTFS partition, showed the new driver to be 20% faster in total time elapsed
(from 9:43 minutes on average down to 7:53). The time spent in user space
mount command (man 8 mount, also see man 5 fstab), the NTFS driver supports the
following mount options:
+======================= =======================================================
iocharset=name Deprecated option. Still supported but please use
nls=name in the future. See description for nls=name.
errors=opt What to do when critical filesystem errors are found.
Following values can be used for "opt":
- continue: DEFAULT, try to clean-up as much as
+
+ ======== =========================================
+ continue DEFAULT, try to clean-up as much as
possible, e.g. marking a corrupt inode as
bad so it is no longer accessed, and then
continue.
- recover: At present only supported is recovery of
+ recover At present only supported is recovery of
the boot sector from the backup copy.
If read-only mount, the recovery is done
in memory only and not written to disk.
- Note that the options are additive, i.e. specifying:
+ ======== =========================================
+
+ Note that the options are additive, i.e. specifying::
+
errors=continue,errors=recover
+
means the driver will attempt to recover and if that
fails it will clean-up as much as possible and
continue.
In general use the default. If you have a lot of small
files then use a higher value. The values have the
following meaning:
+
+ ===== =================================
Value MFT zone size (% of volume size)
+ ===== =================================
1 12.5%
2 25%
3 37.5%
4 50%
+ ===== =================================
+
Note this option is irrelevant for read-only mounts.
+======================= =======================================================
Known bugs and (mis-)features
components and their sizes in sectors, i.e. multiples of 512-byte blocks.
For NT4 fault tolerant volumes you can obtain the sizes using fdisk. So for
-example if one of your partitions is /dev/hda2 you would do:
+example if one of your partitions is /dev/hda2 you would do::
-$ fdisk -ul /dev/hda
+ $ fdisk -ul /dev/hda
-Disk /dev/hda: 81.9 GB, 81964302336 bytes
-255 heads, 63 sectors/track, 9964 cylinders, total 160086528 sectors
-Units = sectors of 1 * 512 = 512 bytes
+ Disk /dev/hda: 81.9 GB, 81964302336 bytes
+ 255 heads, 63 sectors/track, 9964 cylinders, total 160086528 sectors
+ Units = sectors of 1 * 512 = 512 bytes
- Device Boot Start End Blocks Id System
- /dev/hda1 * 63 4209029 2104483+ 83 Linux
- /dev/hda2 4209030 37768814 16779892+ 86 NTFS
- /dev/hda3 37768815 46170809 4200997+ 83 Linux
+ Device Boot Start End Blocks Id System
+ /dev/hda1 * 63 4209029 2104483+ 83 Linux
+ /dev/hda2 4209030 37768814 16779892+ 86 NTFS
+ /dev/hda3 37768815 46170809 4200997+ 83 Linux
And you would know that /dev/hda2 has a size of 37768814 - 4209030 + 1 =
33559785 sectors.
For Win2k and later dynamic disks, you can for example use the ldminfo utility
which is part of the Linux LDM tools (the latest version at the time of
writing is linux-ldm-0.0.8.tar.bz2). You can download it from:
+
http://www.linux-ntfs.org/
+
Simply extract the downloaded archive (tar xvjf linux-ldm-0.0.8.tar.bz2), go
into it (cd linux-ldm-0.0.8) and change to the test directory (cd test). You
will find the precompiled (i386) ldminfo utility there. NOTE: You will not be
able to compile this yourself easily so use the binary version!
-Then you would use ldminfo in dump mode to obtain the necessary information:
+Then you would use ldminfo in dump mode to obtain the necessary information::
-$ ./ldminfo --dump /dev/hda
+ $ ./ldminfo --dump /dev/hda
This would dump the LDM database found on /dev/hda which describes all of your
dynamic disks and all the volumes on them. At the bottom you will see the
Assuming you know all your devices and their sizes things are easy.
For a linear raid the table would look like this (note all values are in
-512-byte sectors):
+512-byte sectors)::
---- cut here ---
-# Offset into Size of this Raid type Device Start sector
-# volume device of device
-0 1028161 linear /dev/hda1 0
-1028161 3903762 linear /dev/hdb2 0
-4931923 2103211 linear /dev/hdc1 0
---- cut here ---
+ # Offset into Size of this Raid type Device Start sector
+ # volume device of device
+ 0 1028161 linear /dev/hda1 0
+ 1028161 3903762 linear /dev/hdb2 0
+ 4931923 2103211 linear /dev/hdc1 0
For a striped volume, i.e. raid level 0, you will need to know the chunk size
you used when creating the volume. Windows uses 64kiB as the default, so it
will probably be this unless you changes the defaults when creating the array.
For a raid level 0 the table would look like this (note all values are in
-512-byte sectors):
+512-byte sectors)::
---- cut here ---
-# Offset Size Raid Number Chunk 1st Start 2nd Start
-# into of the type of size Device in Device in
-# volume volume stripes device device
-0 2056320 striped 2 128 /dev/hda1 0 /dev/hdb1 0
---- cut here ---
+ # Offset Size Raid Number Chunk 1st Start 2nd Start
+ # into of the type of size Device in Device in
+ # volume volume stripes device device
+ 0 2056320 striped 2 128 /dev/hda1 0 /dev/hdb1 0
If there are more than two devices, just add each of them to the end of the
line.
Finally, for a mirrored volume, i.e. raid level 1, the table would look like
-this (note all values are in 512-byte sectors):
+this (note all values are in 512-byte sectors)::
---- cut here ---
-# Ofs Size Raid Log Number Region Should Number Source Start Target Start
-# in of the type type of log size sync? of Device in Device in
-# vol volume params mirrors Device Device
-0 2056320 mirror core 2 16 nosync 2 /dev/hda1 0 /dev/hdb1 0
---- cut here ---
+ # Ofs Size Raid Log Number Region Should Number Source Start Target Start
+ # in of the type type of log size sync? of Device in Device in
+ # vol volume params mirrors Device Device
+ 0 2056320 mirror core 2 16 nosync 2 /dev/hda1 0 /dev/hdb1 0
If you are mirroring to multiple devices you can specify further targets at the
end of the line.
them.
Once you have your table, save it in a file somewhere (e.g. /etc/ntfsvolume1),
-and hand it over to dmsetup to work with, like so:
+and hand it over to dmsetup to work with, like so::
-$ dmsetup create myvolume1 /etc/ntfsvolume1
+ $ dmsetup create myvolume1 /etc/ntfsvolume1
You can obviously replace "myvolume1" with whatever name you like.
If it all worked, you will now have the device /dev/device-mapper/myvolume1
which you can then just use as an argument to the mount command as usual to
-mount the ntfs volume. For example:
+mount the ntfs volume. For example::
-$ mount -t ntfs -o ro /dev/device-mapper/myvolume1 /mnt/myvol1
+ $ mount -t ntfs -o ro /dev/device-mapper/myvolume1 /mnt/myvol1
(You need to create the directory /mnt/myvol1 first and of course you can use
anything you like instead of /mnt/myvol1 as long as it is an existing
"chunk-size 64k" option for each raid-disk, too.
For example, if you have a stripe set consisting of two partitions /dev/hda5
-and /dev/hdb1 your /etc/raidtab would look like this:
-
-raiddev /dev/md0
- raid-level 0
- nr-raid-disks 2
- nr-spare-disks 0
- persistent-superblock 0
- chunk-size 64k
- device /dev/hda5
- raid-disk 0
- device /dev/hdb1
- raid-disk 1
+and /dev/hdb1 your /etc/raidtab would look like this::
+
+ raiddev /dev/md0
+ raid-level 0
+ nr-raid-disks 2
+ nr-spare-disks 0
+ persistent-superblock 0
+ chunk-size 64k
+ device /dev/hda5
+ raid-disk 0
+ device /dev/hdb1
+ raid-disk 1
For linear raid, just change the raid-level above to "raid-level linear", for
mirrors, change it to "raid-level 1", and for stripe sets with parity, change
raid0run /dev/md0 to start a particular md device, in this case /dev/md0.
Then just use the mount command as usual to mount the ntfs volume using for
-example: mount -t ntfs -o ro /dev/md0 /mnt/myntfsvolume
+example::
+
+ mount -t ntfs -o ro /dev/md0 /mnt/myntfsvolume
It is advisable to do the mount read-only to see if the md volume has been
setup correctly to avoid the possibility of causing damage to the data on the
- OCFS2 online file check
- -----------------------
+.. SPDX-License-Identifier: GPL-2.0
+
+=====================================
+OCFS2 file system - online file check
+=====================================
This document will describe OCFS2 online file check feature.
by the inode number which caused the error. This inode number would be the
input to check/fix the file.
-There is a sysfs directory for each OCFS2 file system mounting:
+There is a sysfs directory for each OCFS2 file system mounting::
/sys/fs/ocfs2/<devname>/filecheck
fixed. Currently, three operations are supported, which includes checking
inode, fixing inode and setting the size of result record history.
-1. If you want to know what error exactly happened to <inode> before fixing, do
+1. If you want to know what error exactly happened to <inode> before fixing, do::
+
+ # echo "<inode>" > /sys/fs/ocfs2/<devname>/filecheck/check
+ # cat /sys/fs/ocfs2/<devname>/filecheck/check
+
+The output is like this::
- # echo "<inode>" > /sys/fs/ocfs2/<devname>/filecheck/check
- # cat /sys/fs/ocfs2/<devname>/filecheck/check
+ INO DONE ERROR
+ 39502 1 GENERATION
-The output is like this:
- INO DONE ERROR
-39502 1 GENERATION
+ <INO> lists the inode numbers.
+ <DONE> indicates whether the operation has been finished.
+ <ERROR> says what kind of errors was found. For the detailed error numbers,
+ please refer to the file linux/fs/ocfs2/filecheck.h.
-<INO> lists the inode numbers.
-<DONE> indicates whether the operation has been finished.
-<ERROR> says what kind of errors was found. For the detailed error numbers,
-please refer to the file linux/fs/ocfs2/filecheck.h.
+2. If you determine to fix this inode, do::
-2. If you determine to fix this inode, do
+ # echo "<inode>" > /sys/fs/ocfs2/<devname>/filecheck/fix
+ # cat /sys/fs/ocfs2/<devname>/filecheck/fix
- # echo "<inode>" > /sys/fs/ocfs2/<devname>/filecheck/fix
- # cat /sys/fs/ocfs2/<devname>/filecheck/fix
+The output is like this:::
-The output is like this:
- INO DONE ERROR
-39502 1 SUCCESS
+ INO DONE ERROR
+ 39502 1 SUCCESS
This time, the <ERROR> column indicates whether this fix is successful or not.
3. The record cache is used to store the history of check/fix results. It's
default size is 10, and can be adjust between the range of 10 ~ 100. You can
-adjust the size like this:
+adjust the size like this::
# echo "<size>" > /sys/fs/ocfs2/<devname>/filecheck/set
+.. SPDX-License-Identifier: GPL-2.0
+
+================
OCFS2 filesystem
-==================
+================
+
OCFS2 is a general purpose extent based shared disk cluster file
system with many similarities to ext3. It supports 64 bit inode
numbers, and has automatically extending metadata groups which may
All code copyright 2005 Oracle except when otherwise noted.
-CREDITS:
+Credits
+=======
+
Lots of code taken from ext3 and other projects.
Authors in alphabetical order:
-Joel Becker <joel.becker@oracle.com>
-Zach Brown <zach.brown@oracle.com>
-Mark Fasheh <mfasheh@suse.com>
-Kurt Hackel <kurt.hackel@oracle.com>
-Tao Ma <tao.ma@oracle.com>
-Sunil Mushran <sunil.mushran@oracle.com>
-Manish Singh <manish.singh@oracle.com>
-Tiger Yang <tiger.yang@oracle.com>
+
+- Joel Becker <joel.becker@oracle.com>
+- Zach Brown <zach.brown@oracle.com>
+- Mark Fasheh <mfasheh@suse.com>
+- Kurt Hackel <kurt.hackel@oracle.com>
+- Tao Ma <tao.ma@oracle.com>
+- Sunil Mushran <sunil.mushran@oracle.com>
+- Manish Singh <manish.singh@oracle.com>
+- Tiger Yang <tiger.yang@oracle.com>
Caveats
=======
Features which OCFS2 does not support yet:
+
- Directory change notification (F_NOTIFY)
- Distributed Caching (F_SETLEASE/F_GETLEASE/break_lease)
=============
OCFS2 supports the following mount options:
+
(*) == default
+======================= ========================================================
barrier=1 This enables/disables barriers. barrier=0 disables it,
barrier=1 enables it.
errors=remount-ro(*) Remount the filesystem read-only on an error.
for descriptor blocks. If enabled older kernels cannot
mount the device. This will enable 'journal_checksum'
internally.
+======================= ========================================================
--- /dev/null
+.. SPDX-License-Identifier: GPL-2.0
+
+================================
+Optimized MPEG Filesystem (OMFS)
+================================
+
+Overview
+========
+
+OMFS is a filesystem created by SonicBlue for use in the ReplayTV DVR
+and Rio Karma MP3 player. The filesystem is extent-based, utilizing
+block sizes from 2k to 8k, with hash-based directories. This
+filesystem driver may be used to read and write disks from these
+devices.
+
+Note, it is not recommended that this FS be used in place of a general
+filesystem for your own streaming media device. Native Linux filesystems
+will likely perform better.
+
+More information is available at:
+
+ http://linux-karma.sf.net/
+
+Various utilities, including mkomfs and omfsck, are included with
+omfsprogs, available at:
+
+ http://bobcopeland.com/karma/
+
+Instructions are included in its README.
+
+Options
+=======
+
+OMFS supports the following mount-time options:
+
+ ============ ========================================
+ uid=n make all files owned by specified user
+ gid=n make all files owned by specified group
+ umask=xxx set permission umask to xxx
+ fmask=xxx set umask to xxx for files
+ dmask=xxx set umask to xxx for directories
+ ============ ========================================
+
+Disk format
+===========
+
+OMFS discriminates between "sysblocks" and normal data blocks. The sysblock
+group consists of super block information, file metadata, directory structures,
+and extents. Each sysblock has a header containing CRCs of the entire
+sysblock, and may be mirrored in successive blocks on the disk. A sysblock may
+have a smaller size than a data block, but since they are both addressed by the
+same 64-bit block number, any remaining space in the smaller sysblock is
+unused.
+
+Sysblock header information::
+
+ struct omfs_header {
+ __be64 h_self; /* FS block where this is located */
+ __be32 h_body_size; /* size of useful data after header */
+ __be16 h_crc; /* crc-ccitt of body_size bytes */
+ char h_fill1[2];
+ u8 h_version; /* version, always 1 */
+ char h_type; /* OMFS_INODE_X */
+ u8 h_magic; /* OMFS_IMAGIC */
+ u8 h_check_xor; /* XOR of header bytes before this */
+ __be32 h_fill2;
+ };
+
+Files and directories are both represented by omfs_inode::
+
+ struct omfs_inode {
+ struct omfs_header i_head; /* header */
+ __be64 i_parent; /* parent containing this inode */
+ __be64 i_sibling; /* next inode in hash bucket */
+ __be64 i_ctime; /* ctime, in milliseconds */
+ char i_fill1[35];
+ char i_type; /* OMFS_[DIR,FILE] */
+ __be32 i_fill2;
+ char i_fill3[64];
+ char i_name[OMFS_NAMELEN]; /* filename */
+ __be64 i_size; /* size of file, in bytes */
+ };
+
+Directories in OMFS are implemented as a large hash table. Filenames are
+hashed then prepended into the bucket list beginning at OMFS_DIR_START.
+Lookup requires hashing the filename, then seeking across i_sibling pointers
+until a match is found on i_name. Empty buckets are represented by block
+pointers with all-1s (~0).
+
+A file is an omfs_inode structure followed by an extent table beginning at
+OMFS_EXTENT_START::
+
+ struct omfs_extent_entry {
+ __be64 e_cluster; /* start location of a set of blocks */
+ __be64 e_blocks; /* number of blocks after e_cluster */
+ };
+
+ struct omfs_extent {
+ __be64 e_next; /* next extent table location */
+ __be32 e_extent_count; /* total # extents in this table */
+ __be32 e_fill;
+ struct omfs_extent_entry e_entry; /* start of extent entries */
+ };
+
+Each extent holds the block offset followed by number of blocks allocated to
+the extent. The final extent in each table is a terminator with e_cluster
+being ~0 and e_blocks being ones'-complement of the total number of blocks
+in the table.
+
+If this table overflows, a continuation inode is written and pointed to by
+e_next. These have a header but lack the rest of the inode structure.
+
+++ /dev/null
-Optimized MPEG Filesystem (OMFS)
-
-Overview
-========
-
-OMFS is a filesystem created by SonicBlue for use in the ReplayTV DVR
-and Rio Karma MP3 player. The filesystem is extent-based, utilizing
-block sizes from 2k to 8k, with hash-based directories. This
-filesystem driver may be used to read and write disks from these
-devices.
-
-Note, it is not recommended that this FS be used in place of a general
-filesystem for your own streaming media device. Native Linux filesystems
-will likely perform better.
-
-More information is available at:
-
- http://linux-karma.sf.net/
-
-Various utilities, including mkomfs and omfsck, are included with
-omfsprogs, available at:
-
- http://bobcopeland.com/karma/
-
-Instructions are included in its README.
-
-Options
-=======
-
-OMFS supports the following mount-time options:
-
- uid=n - make all files owned by specified user
- gid=n - make all files owned by specified group
- umask=xxx - set permission umask to xxx
- fmask=xxx - set umask to xxx for files
- dmask=xxx - set umask to xxx for directories
-
-Disk format
-===========
-
-OMFS discriminates between "sysblocks" and normal data blocks. The sysblock
-group consists of super block information, file metadata, directory structures,
-and extents. Each sysblock has a header containing CRCs of the entire
-sysblock, and may be mirrored in successive blocks on the disk. A sysblock may
-have a smaller size than a data block, but since they are both addressed by the
-same 64-bit block number, any remaining space in the smaller sysblock is
-unused.
-
-Sysblock header information:
-
-struct omfs_header {
- __be64 h_self; /* FS block where this is located */
- __be32 h_body_size; /* size of useful data after header */
- __be16 h_crc; /* crc-ccitt of body_size bytes */
- char h_fill1[2];
- u8 h_version; /* version, always 1 */
- char h_type; /* OMFS_INODE_X */
- u8 h_magic; /* OMFS_IMAGIC */
- u8 h_check_xor; /* XOR of header bytes before this */
- __be32 h_fill2;
-};
-
-Files and directories are both represented by omfs_inode:
-
-struct omfs_inode {
- struct omfs_header i_head; /* header */
- __be64 i_parent; /* parent containing this inode */
- __be64 i_sibling; /* next inode in hash bucket */
- __be64 i_ctime; /* ctime, in milliseconds */
- char i_fill1[35];
- char i_type; /* OMFS_[DIR,FILE] */
- __be32 i_fill2;
- char i_fill3[64];
- char i_name[OMFS_NAMELEN]; /* filename */
- __be64 i_size; /* size of file, in bytes */
-};
-
-Directories in OMFS are implemented as a large hash table. Filenames are
-hashed then prepended into the bucket list beginning at OMFS_DIR_START.
-Lookup requires hashing the filename, then seeking across i_sibling pointers
-until a match is found on i_name. Empty buckets are represented by block
-pointers with all-1s (~0).
-
-A file is an omfs_inode structure followed by an extent table beginning at
-OMFS_EXTENT_START:
-
-struct omfs_extent_entry {
- __be64 e_cluster; /* start location of a set of blocks */
- __be64 e_blocks; /* number of blocks after e_cluster */
-};
-
-struct omfs_extent {
- __be64 e_next; /* next extent table location */
- __be32 e_extent_count; /* total # extents in this table */
- __be32 e_fill;
- struct omfs_extent_entry e_entry; /* start of extent entries */
-};
-
-Each extent holds the block offset followed by number of blocks allocated to
-the extent. The final extent in each table is a terminator with e_cluster
-being ~0 and e_blocks being ones'-complement of the total number of blocks
-in the table.
-
-If this table overflows, a continuation inode is written and pointed to by
-e_next. These have a header but lack the rest of the inode structure.
-
+.. SPDX-License-Identifier: GPL-2.0
+
+========
ORANGEFS
========
* Stateless
-MAILING LIST ARCHIVES
+Mailing List Archives
=====================
http://lists.orangefs.org/pipermail/devel_lists.orangefs.org/
-MAILING LIST SUBMISSIONS
+Mailing List Submissions
========================
devel@lists.orangefs.org
-DOCUMENTATION
+Documentation
=============
http://www.orangefs.org/documentation/
-USERSPACE FILESYSTEM SOURCE
+Userspace Filesystem Source
===========================
http://www.orangefs.org/download
upstream version of the kernel client.
-RUNNING ORANGEFS ON A SINGLE SERVER
+Running ORANGEFS On a Single Server
===================================
OrangeFS is usually run in large installations with multiple servers and
clients, but a complete filesystem can be run on a single machine for
development and testing.
-On Fedora, install orangefs and orangefs-server.
+On Fedora, install orangefs and orangefs-server::
-dnf -y install orangefs orangefs-server
+ dnf -y install orangefs orangefs-server
There is an example server configuration file in
/etc/orangefs/orangefs.conf. Change localhost to your hostname if
controls clients which use libpvfs2. This does not control the
pvfs2-client-core.
-Create the filesystem.
+Create the filesystem::
-pvfs2-server -f /etc/orangefs/orangefs.conf
+ pvfs2-server -f /etc/orangefs/orangefs.conf
-Start the server.
+Start the server::
-systemctl start orangefs-server
+ systemctl start orangefs-server
-Test the server.
+Test the server::
-pvfs2-ping -m /pvfsmnt
+ pvfs2-ping -m /pvfsmnt
Start the client. The module must be compiled in or loaded before this
-point.
+point::
-systemctl start orangefs-client
+ systemctl start orangefs-client
-Mount the filesystem.
+Mount the filesystem::
-mount -t pvfs2 tcp://localhost:3334/orangefs /pvfsmnt
+ mount -t pvfs2 tcp://localhost:3334/orangefs /pvfsmnt
-BUILDING ORANGEFS ON A SINGLE SERVER
+Building ORANGEFS on a Single Server
====================================
Where OrangeFS cannot be installed from distribution packages, it may be
in /usr/local. As of version 2.9.6, OrangeFS uses Berkeley DB by
default, we will probably be changing the default to LMDB soon.
-./configure --prefix=/opt/ofs --with-db-backend=lmdb
+::
-make
+ ./configure --prefix=/opt/ofs --with-db-backend=lmdb
-make install
+ make
-Create an orangefs config file.
+ make install
-/opt/ofs/bin/pvfs2-genconfig /etc/pvfs2.conf
+Create an orangefs config file::
-Create an /etc/pvfs2tab file.
+ /opt/ofs/bin/pvfs2-genconfig /etc/pvfs2.conf
-echo tcp://localhost:3334/orangefs /pvfsmnt pvfs2 defaults,noauto 0 0 > \
- /etc/pvfs2tab
+Create an /etc/pvfs2tab file::
-Create the mount point you specified in the tab file if needed.
+ echo tcp://localhost:3334/orangefs /pvfsmnt pvfs2 defaults,noauto 0 0 > \
+ /etc/pvfs2tab
-mkdir /pvfsmnt
+Create the mount point you specified in the tab file if needed::
-Bootstrap the server.
+ mkdir /pvfsmnt
-/opt/ofs/sbin/pvfs2-server -f /etc/pvfs2.conf
+Bootstrap the server::
-Start the server.
+ /opt/ofs/sbin/pvfs2-server -f /etc/pvfs2.conf
-/opt/osf/sbin/pvfs2-server /etc/pvfs2.conf
+Start the server::
+
+ /opt/osf/sbin/pvfs2-server /etc/pvfs2.conf
Now the server should be running. Pvfs2-ls is a simple
-test to verify that the server is running.
+test to verify that the server is running::
-/opt/ofs/bin/pvfs2-ls /pvfsmnt
+ /opt/ofs/bin/pvfs2-ls /pvfsmnt
If stuff seems to be working, load the kernel module and
-turn on the client core.
+turn on the client core::
-/opt/ofs/sbin/pvfs2-client -p /opt/osf/sbin/pvfs2-client-core
+ /opt/ofs/sbin/pvfs2-client -p /opt/osf/sbin/pvfs2-client-core
-Mount your filesystem.
+Mount your filesystem::
-mount -t pvfs2 tcp://localhost:3334/orangefs /pvfsmnt
+ mount -t pvfs2 tcp://localhost:3334/orangefs /pvfsmnt
-RUNNING XFSTESTS
+Running xfstests
================
It is useful to use a scratch filesystem with xfstests. This can be
This change should be made before creating the filesystem.
-pvfs2-server -f /etc/orangefs/orangefs.conf
+::
+
+ pvfs2-server -f /etc/orangefs/orangefs.conf
-To run xfstests, create /etc/xfsqa.config.
+To run xfstests, create /etc/xfsqa.config::
-TEST_DIR=/orangefs
-TEST_DEV=tcp://localhost:3334/orangefs
-SCRATCH_MNT=/scratch
-SCRATCH_DEV=tcp://localhost:3334/scratch
+ TEST_DIR=/orangefs
+ TEST_DEV=tcp://localhost:3334/orangefs
+ SCRATCH_MNT=/scratch
+ SCRATCH_DEV=tcp://localhost:3334/scratch
-Then xfstests can be run
+Then xfstests can be run::
-./check -pvfs2
+ ./check -pvfs2
-OPTIONS
+Options
=======
The following mount options are accepted:
Distributed locking is being worked on for the future.
-DEBUGGING
+Debugging
=========
If you want the debug (GOSSIP) statements in a particular
-source file (inode.c for example) go to syslog:
+source file (inode.c for example) go to syslog::
echo inode > /sys/kernel/debug/orangefs/kernel-debug
-No debugging (the default):
+No debugging (the default)::
echo none > /sys/kernel/debug/orangefs/kernel-debug
-Debugging from several source files:
+Debugging from several source files::
echo inode,dir > /sys/kernel/debug/orangefs/kernel-debug
-All debugging:
+All debugging::
echo all > /sys/kernel/debug/orangefs/kernel-debug
-Get a list of all debugging keywords:
+Get a list of all debugging keywords::
cat /sys/kernel/debug/orangefs/debug-help
-PROTOCOL BETWEEN KERNEL MODULE AND USERSPACE
+Protocol between Kernel Module and Userspace
============================================
Orangefs is a user space filesystem and an associated kernel module.
can read from and write to. Userspace can also manipulate the
kernel module through the pseudo device with ioctl.
-THE BUFMAP:
+The Bufmap
+----------
At startup userspace allocates two page-size-aligned (posix_memalign)
mlocked memory buffers, one is used for IO and one is used for readdir
to initialize the kernel module's "bufmap" (struct orangefs_bufmap), which
then contains:
- * refcnt - a reference counter
+ * refcnt
+ - a reference counter
* desc_size - PVFS2_BUFMAP_DEFAULT_DESC_SIZE (4194304) - the IO buffer's
partition size, which represents the filesystem's block size and
is used for s_blocksize in super blocks.
* desc_shift - log2(desc_size), used for s_blocksize_bits in super blocks.
* total_size - the total size of the IO buffer.
* page_count - the number of 4096 byte pages in the IO buffer.
- * page_array - a pointer to page_count * (sizeof(struct page*)) bytes
+ * page_array - a pointer to ``page_count * (sizeof(struct page*))`` bytes
of kcalloced memory. This memory is used as an array of pointers
to each of the pages in the IO buffer through a call to get_user_pages.
- * desc_array - a pointer to desc_count * (sizeof(struct orangefs_bufmap_desc))
+ * desc_array - a pointer to ``desc_count * (sizeof(struct orangefs_bufmap_desc))``
bytes of kcalloced memory. This memory is further intialized:
user_desc is the kernel's copy of the IO buffer's ORANGEFS_dev_map_desc
structure. user_desc->ptr points to the IO buffer.
- pages_per_desc = bufmap->desc_size / PAGE_SIZE
- offset = 0
+ ::
+
+ pages_per_desc = bufmap->desc_size / PAGE_SIZE
+ offset = 0
bufmap->desc_array[0].page_array = &bufmap->page_array[offset]
bufmap->desc_array[0].array_count = pages_per_desc = 1024
* readdir_index_lock - a spinlock to protect readdir_index_array during
update.
-OPERATIONS:
+Operations
+----------
The kernel module builds an "op" (struct orangefs_kernel_op_s) when it
needs to communicate with userspace. Part of the op contains the "upcall"
Ops are stateful:
- * unknown - op was just initialized
- * waiting - op is on request_list (upward bound)
- * inprogr - op is in progress (waiting for downcall)
- * serviced - op has matching downcall; ok
- * purged - op has to start a timer since client-core
+ * unknown
+ - op was just initialized
+ * waiting
+ - op is on request_list (upward bound)
+ * inprogr
+ - op is in progress (waiting for downcall)
+ * serviced
+ - op has matching downcall; ok
+ * purged
+ - op has to start a timer since client-core
exited uncleanly before servicing op
- * given up - submitter has given up waiting for it
+ * given up
+ - submitter has given up waiting for it
When some arbitrary userspace program needs to perform a
filesystem operation on Orangefs (readdir, I/O, create, whatever)
response type.
The several members outside of the union are:
- - int32_t type - type of operation.
- - int32_t status - return code for the operation.
- - int64_t trailer_size - 0 unless readdir operation.
- - char *trailer_buf - initialized to NULL, used during readdir operations.
+
+ ``int32_t type``
+ - type of operation.
+ ``int32_t status``
+ - return code for the operation.
+ ``int64_t trailer_size``
+ - 0 unless readdir operation.
+ ``char *trailer_buf``
+ - initialized to NULL, used during readdir operations.
The appropriate member inside the union is filled out for any
particular response.
made by the kernel side.
A buffer_list containing:
+
- a pointer to the prepared response to the request from the
kernel (struct pvfs2_downcall_t).
- and also, in the case of a readdir request, a pointer to a
buffer containing descriptors for the objects in the target
directory.
+
... is sent to the function (PINT_dev_write_list) which performs
the writev.
PINT_dev_write_list has a local iovec array: struct iovec io_array[10];
The first four elements of io_array are initialized like this for all
-responses:
+responses::
io_array[0].iov_base = address of local variable "proto_ver" (int32_t)
io_array[0].iov_len = sizeof(int32_t)
of global variable vfs_request (vfs_request_t)
io_array[3].iov_len = sizeof(pvfs2_downcall_t)
-Readdir responses initialize the fifth element io_array like this:
+Readdir responses initialize the fifth element io_array like this::
io_array[4].iov_base = contents of member trailer_buf (char *)
from out_downcall member of global variable
hence the motivation to use the dentry when possible.
The timeout values d_time and getattr_time are jiffy based, and the
-code is designed to avoid the jiffy-wrap problem:
+code is designed to avoid the jiffy-wrap problem::
-"In general, if the clock may have wrapped around more than once, there
-is no way to tell how much time has elapsed. However, if the times t1
-and t2 are known to be fairly close, we can reliably compute the
-difference in a way that takes into account the possibility that the
-clock may have wrapped between times."
+ "In general, if the clock may have wrapped around more than once, there
+ is no way to tell how much time has elapsed. However, if the times t1
+ and t2 are known to be fairly close, we can reliably compute the
+ difference in a way that takes into account the possibility that the
+ clock may have wrapped between times."
- from course notes by instructor Andy Wang
+from course notes by instructor Andy Wang
-------------------------------------------------------------------------------
- T H E /proc F I L E S Y S T E M
-------------------------------------------------------------------------------
-/proc/sys Terrehon Bowden <terrehon@pacbell.net> October 7 1999
- Bodo Bauer <bb@ricochet.net>
+.. SPDX-License-Identifier: GPL-2.0
+
+====================
+The /proc Filesystem
+====================
+
+===================== ======================================= ================
+/proc/sys Terrehon Bowden <terrehon@pacbell.net>, October 7 1999
+ Bodo Bauer <bb@ricochet.net>
+2.4.x update Jorge Nerin <comandante@zaralinux.com> November 14 2000
+move /proc/sys Shen Feng <shen@cn.fujitsu.com> April 1 2009
+fixes/update part 1.1 Stefani Seibold <stefani@seibold.net> June 9 2009
+===================== ======================================= ================
+
-2.4.x update Jorge Nerin <comandante@zaralinux.com> November 14 2000
-move /proc/sys Shen Feng <shen@cn.fujitsu.com> April 1 2009
-------------------------------------------------------------------------------
-Version 1.3 Kernel version 2.2.12
- Kernel version 2.4.0-test11-pre4
-------------------------------------------------------------------------------
-fixes/update part 1.1 Stefani Seibold <stefani@seibold.net> June 9 2009
-Table of Contents
------------------
+.. Table of Contents
0 Preface
0.1 Introduction/Credits
4 Configuring procfs
4.1 Mount options
-------------------------------------------------------------------------------
Preface
-------------------------------------------------------------------------------
+=======
0.1 Introduction/Credits
------------------------
complaining about how you screwed up your system because of incorrect
documentation, we won't feel responsible...
-------------------------------------------------------------------------------
-CHAPTER 1: COLLECTING SYSTEM INFORMATION
-------------------------------------------------------------------------------
+Chapter 1: Collecting System Information
+========================================
-------------------------------------------------------------------------------
In This Chapter
-------------------------------------------------------------------------------
+---------------
* Investigating the properties of the pseudo file system /proc and its
ability to provide information on the running Linux system
* Examining /proc's structure
* Uncovering various information about the kernel and the processes running
on the system
-------------------------------------------------------------------------------
+------------------------------------------------------------------------------
The proc file system acts as an interface to internal data structures in the
kernel. It can be used to obtain information about the system and to change
also assigned the process ID <pid>. Instead, operations on these FDs
usually fail with ESRCH.
-Table 1-1: Process specific entries in /proc
-..............................................................................
+.. table:: Table 1-1: Process specific entries in /proc
+
+ ============= ===============================================================
File Content
+ ============= ===============================================================
clear_refs Clears page referenced bits shown in smaps output
cmdline Command line arguments
cpu Current and last cpu in which it was executed (2.4)(smp)
can be derived from smaps, but is faster and more convenient
numa_maps An extension based on maps, showing the memory locality and
binding policy as well as mem usage (in pages) of each mapping.
-..............................................................................
+ ============= ===============================================================
For example, to get the status information of a process, all you have to do is
-read the file /proc/PID/status:
+read the file /proc/PID/status::
>cat /proc/self/status
Name: cat
explained in Table 1-4.
(for SMP CONFIG users)
+
For making accounting scalable, RSS related information are handled in an
asynchronous manner and the value may not be very precise. To see a precise
snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table.
It's slow but very precise.
-Table 1-2: Contents of the status files (as of 4.19)
-..............................................................................
+.. table:: Table 1-2: Contents of the status files (as of 4.19)
+
+ ========================== ===================================================
Field Content
+ ========================== ===================================================
Name filename of the executable
Umask file mode creation mask
State state (R is running, S is sleeping, D is sleeping
VmPin pinned memory size
VmHWM peak resident set size ("high water mark")
VmRSS size of memory portions. It contains the three
- following parts (VmRSS = RssAnon + RssFile + RssShmem)
+ following parts
+ (VmRSS = RssAnon + RssFile + RssShmem)
RssAnon size of resident anonymous memory
RssFile size of resident file mappings
RssShmem size of resident shmem memory (includes SysV shm,
Mems_allowed_list Same as previous, but in "list format"
voluntary_ctxt_switches number of voluntary context switches
nonvoluntary_ctxt_switches number of non voluntary context switches
-..............................................................................
+ ========================== ===================================================
-Table 1-3: Contents of the statm files (as of 2.6.8-rc3)
-..............................................................................
+
+.. table:: Table 1-3: Contents of the statm files (as of 2.6.8-rc3)
+
+ ======== =============================== ==============================
Field Content
+ ======== =============================== ==============================
size total program size (pages) (same as VmSize in status)
resident size of memory portions (pages) (same as VmRSS in status)
shared number of pages that are shared (i.e. backed by a file, same
as RssFile+RssShmem in status)
trs number of pages that are 'code' (not including libs; broken,
- includes data segment)
+ includes data segment)
lrs number of pages of library (always 0 on 2.6)
drs number of pages of data/stack (including libs; broken,
- includes library text)
+ includes library text)
dt number of dirty pages (always 0 on 2.6)
-..............................................................................
+ ======== =============================== ==============================
+
+.. table:: Table 1-4: Contents of the stat files (as of 2.6.30-rc7)
-Table 1-4: Contents of the stat files (as of 2.6.30-rc7)
-..............................................................................
- Field Content
+ ============= ===============================================================
+ Field Content
+ ============= ===============================================================
pid process id
tcomm filename of the executable
state state (R is running, S is sleeping, D is sleeping in an
blocked bitmap of blocked signals
sigign bitmap of ignored signals
sigcatch bitmap of caught signals
- 0 (place holder, used to be the wchan address, use /proc/PID/wchan instead)
+ 0 (place holder, used to be the wchan address,
+ use /proc/PID/wchan instead)
0 (place holder)
0 (place holder)
exit_signal signal to send to parent thread on exit
arg_end address below which program command line is placed
env_start address above which program environment is placed
env_end address below which program environment is placed
- exit_code the thread's exit_code in the form reported by the waitpid system call
-..............................................................................
+ exit_code the thread's exit_code in the form reported by the waitpid
+ system call
+ ============= ===============================================================
The /proc/PID/maps file contains the currently mapped memory regions and
their access permissions.
-The format is:
-
-address perms offset dev inode pathname
-
-08048000-08049000 r-xp 00000000 03:00 8312 /opt/test
-08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test
-0804a000-0806b000 rw-p 00000000 00:00 0 [heap]
-a7cb1000-a7cb2000 ---p 00000000 00:00 0
-a7cb2000-a7eb2000 rw-p 00000000 00:00 0
-a7eb2000-a7eb3000 ---p 00000000 00:00 0
-a7eb3000-a7ed5000 rw-p 00000000 00:00 0
-a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6
-a8008000-a800a000 r--p 00133000 03:00 4222 /lib/libc.so.6
-a800a000-a800b000 rw-p 00135000 03:00 4222 /lib/libc.so.6
-a800b000-a800e000 rw-p 00000000 00:00 0
-a800e000-a8022000 r-xp 00000000 03:00 14462 /lib/libpthread.so.0
-a8022000-a8023000 r--p 00013000 03:00 14462 /lib/libpthread.so.0
-a8023000-a8024000 rw-p 00014000 03:00 14462 /lib/libpthread.so.0
-a8024000-a8027000 rw-p 00000000 00:00 0
-a8027000-a8043000 r-xp 00000000 03:00 8317 /lib/ld-linux.so.2
-a8043000-a8044000 r--p 0001b000 03:00 8317 /lib/ld-linux.so.2
-a8044000-a8045000 rw-p 0001c000 03:00 8317 /lib/ld-linux.so.2
-aff35000-aff4a000 rw-p 00000000 00:00 0 [stack]
-ffffe000-fffff000 r-xp 00000000 00:00 0 [vdso]
+The format is::
+
+ address perms offset dev inode pathname
+
+ 08048000-08049000 r-xp 00000000 03:00 8312 /opt/test
+ 08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test
+ 0804a000-0806b000 rw-p 00000000 00:00 0 [heap]
+ a7cb1000-a7cb2000 ---p 00000000 00:00 0
+ a7cb2000-a7eb2000 rw-p 00000000 00:00 0
+ a7eb2000-a7eb3000 ---p 00000000 00:00 0
+ a7eb3000-a7ed5000 rw-p 00000000 00:00 0
+ a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6
+ a8008000-a800a000 r--p 00133000 03:00 4222 /lib/libc.so.6
+ a800a000-a800b000 rw-p 00135000 03:00 4222 /lib/libc.so.6
+ a800b000-a800e000 rw-p 00000000 00:00 0
+ a800e000-a8022000 r-xp 00000000 03:00 14462 /lib/libpthread.so.0
+ a8022000-a8023000 r--p 00013000 03:00 14462 /lib/libpthread.so.0
+ a8023000-a8024000 rw-p 00014000 03:00 14462 /lib/libpthread.so.0
+ a8024000-a8027000 rw-p 00000000 00:00 0
+ a8027000-a8043000 r-xp 00000000 03:00 8317 /lib/ld-linux.so.2
+ a8043000-a8044000 r--p 0001b000 03:00 8317 /lib/ld-linux.so.2
+ a8044000-a8045000 rw-p 0001c000 03:00 8317 /lib/ld-linux.so.2
+ aff35000-aff4a000 rw-p 00000000 00:00 0 [stack]
+ ffffe000-fffff000 r-xp 00000000 00:00 0 [vdso]
where "address" is the address space in the process that it occupies, "perms"
-is a set of permissions:
+is a set of permissions::
r = read
w = write
The "pathname" shows the name associated file for this mapping. If the mapping
is not associated with a file:
- [heap] = the heap of the program
- [stack] = the stack of the main process
- [vdso] = the "virtual dynamic shared object",
+ ======= ====================================
+ [heap] the heap of the program
+ [stack] the stack of the main process
+ [vdso] the "virtual dynamic shared object",
the kernel system call handler
+ ======= ====================================
or if empty, the mapping is anonymous.
The /proc/PID/smaps is an extension based on maps, showing the memory
consumption for each of the process's mappings. For each mapping (aka Virtual
-Memory Area, or VMA) there is a series of lines such as the following:
-
-08048000-080bc000 r-xp 00000000 03:02 13130 /bin/bash
-
-Size: 1084 kB
-KernelPageSize: 4 kB
-MMUPageSize: 4 kB
-Rss: 892 kB
-Pss: 374 kB
-Shared_Clean: 892 kB
-Shared_Dirty: 0 kB
-Private_Clean: 0 kB
-Private_Dirty: 0 kB
-Referenced: 892 kB
-Anonymous: 0 kB
-LazyFree: 0 kB
-AnonHugePages: 0 kB
-ShmemPmdMapped: 0 kB
-Shared_Hugetlb: 0 kB
-Private_Hugetlb: 0 kB
-Swap: 0 kB
-SwapPss: 0 kB
-KernelPageSize: 4 kB
-MMUPageSize: 4 kB
-Locked: 0 kB
-THPeligible: 0
-VmFlags: rd ex mr mw me dw
+Memory Area, or VMA) there is a series of lines such as the following::
+
+ 08048000-080bc000 r-xp 00000000 03:02 13130 /bin/bash
+
+ Size: 1084 kB
+ KernelPageSize: 4 kB
+ MMUPageSize: 4 kB
+ Rss: 892 kB
+ Pss: 374 kB
+ Shared_Clean: 892 kB
+ Shared_Dirty: 0 kB
+ Private_Clean: 0 kB
+ Private_Dirty: 0 kB
+ Referenced: 892 kB
+ Anonymous: 0 kB
+ LazyFree: 0 kB
+ AnonHugePages: 0 kB
+ ShmemPmdMapped: 0 kB
+ Shared_Hugetlb: 0 kB
+ Private_Hugetlb: 0 kB
+ Swap: 0 kB
+ SwapPss: 0 kB
+ KernelPageSize: 4 kB
+ MMUPageSize: 4 kB
+ Locked: 0 kB
+ THPeligible: 0
+ VmFlags: rd ex mr mw me dw
The first of these lines shows the same information as is displayed for the
mapping in /proc/PID/maps. Following lines show the size of the mapping
in memory, where each page is divided by the number of processes sharing it.
So if a process has 1000 pages all to itself, and 1000 shared with one other
process, its PSS will be 1500.
+
Note that even a page which is part of a MAP_SHARED mapping, but has only
a single pte mapped, i.e. is currently used by only one process, is accounted
as private and not as shared.
+
"Referenced" indicates the amount of memory currently marked as referenced or
accessed.
+
"Anonymous" shows the amount of memory that does not belong to any file. Even
a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE
and a page is modified, the file page is replaced by a private anonymous copy.
+
"LazyFree" shows the amount of memory which is marked by madvise(MADV_FREE).
The memory isn't freed immediately with madvise(). It's freed in memory
pressure if the memory is clean. Please note that the printed value might
be lower than the real value due to optimizations used in the current
implementation. If this is not desirable please file a bug report.
+
"AnonHugePages" shows the ammount of memory backed by transparent hugepage.
+
"ShmemPmdMapped" shows the ammount of shared (shmem/tmpfs) memory backed by
huge pages.
+
"Shared_Hugetlb" and "Private_Hugetlb" show the ammounts of memory backed by
hugetlbfs page which is *not* counted in "RSS" or "PSS" field for historical
reasons. And these are not included in {Shared,Private}_{Clean,Dirty} field.
+
"Swap" shows how much would-be-anonymous memory is also used, but out on swap.
+
For shmem mappings, "Swap" includes also the size of the mapped (and not
replaced by copy-on-write) part of the underlying shmem object out on swap.
"SwapPss" shows proportional swap share of this mapping. Unlike "Swap", this
"THPeligible" indicates whether the mapping is eligible for allocating THP
pages - 1 if true, 0 otherwise. It just shows the current status.
-"VmFlags" field deserves a separate description. This member represents the kernel
-flags associated with the particular virtual memory area in two letter encoded
-manner. The codes are the following:
- rd - readable
- wr - writeable
- ex - executable
- sh - shared
- mr - may read
- mw - may write
- me - may execute
- ms - may share
- gd - stack segment growns down
- pf - pure PFN range
- dw - disabled write to the mapped file
- lo - pages are locked in memory
- io - memory mapped I/O area
- sr - sequential read advise provided
- rr - random read advise provided
- dc - do not copy area on fork
- de - do not expand area on remapping
- ac - area is accountable
- nr - swap space is not reserved for the area
- ht - area uses huge tlb pages
- ar - architecture specific flag
- dd - do not include area into core dump
- sd - soft-dirty flag
- mm - mixed map area
- hg - huge page advise flag
- nh - no-huge page advise flag
- mg - mergable advise flag
+"VmFlags" field deserves a separate description. This member represents the
+kernel flags associated with the particular virtual memory area in two letter
+encoded manner. The codes are the following:
+
+ == =======================================
+ rd readable
+ wr writeable
+ ex executable
+ sh shared
+ mr may read
+ mw may write
+ me may execute
+ ms may share
+ gd stack segment growns down
+ pf pure PFN range
+ dw disabled write to the mapped file
+ lo pages are locked in memory
+ io memory mapped I/O area
+ sr sequential read advise provided
+ rr random read advise provided
+ dc do not copy area on fork
+ de do not expand area on remapping
+ ac area is accountable
+ nr swap space is not reserved for the area
+ ht area uses huge tlb pages
+ ar architecture specific flag
+ dd do not include area into core dump
+ sd soft dirty flag
+ mm mixed map area
+ hg huge page advise flag
+ nh no huge page advise flag
+ mg mergable advise flag
+ == =======================================
Note that there is no guarantee that every flag and associated mnemonic will
be present in all further kernel releases. Things get changed, the flags may
Note: reading /proc/PID/maps or /proc/PID/smaps is inherently racy (consistent
output can be achieved only in the single read call).
+
This typically manifests when doing partial reads of these files while the
memory map is being modified. Despite the races, we do provide the following
guarantees:
but their values are the sums of the corresponding values for all mappings of
the process. Additionally, it contains these fields:
-Pss_Anon
-Pss_File
-Pss_Shmem
+- Pss_Anon
+- Pss_File
+- Pss_Shmem
They represent the proportional shares of anonymous, file, and shmem pages, as
described for smaps above. These fields are omitted in smaps since each
bits on both physical and virtual pages associated with a process, and the
soft-dirty bit on pte (see Documentation/admin-guide/mm/soft-dirty.rst
for details).
-To clear the bits for all the pages associated with the process
+To clear the bits for all the pages associated with the process::
+
> echo 1 > /proc/PID/clear_refs
-To clear the bits for the anonymous pages associated with the process
+To clear the bits for the anonymous pages associated with the process::
+
> echo 2 > /proc/PID/clear_refs
-To clear the bits for the file mapped pages associated with the process
+To clear the bits for the file mapped pages associated with the process::
+
> echo 3 > /proc/PID/clear_refs
-To clear the soft-dirty bit
+To clear the soft-dirty bit::
+
> echo 4 > /proc/PID/clear_refs
To reset the peak resident set size ("high water mark") to the process's
-current value:
+current value::
+
> echo 5 > /proc/PID/clear_refs
Any other value written to /proc/PID/clear_refs will have no effect.
The /proc/pid/numa_maps is an extension based on maps, showing the memory
locality and binding policy, as well as the memory usage (in pages) of
each mapping. The output follows a general format where mapping details get
-summarized separated by blank spaces, one mapping per each file line:
-
-address policy mapping details
-
-00400000 default file=/usr/local/bin/app mapped=1 active=0 N3=1 kernelpagesize_kB=4
-00600000 default file=/usr/local/bin/app anon=1 dirty=1 N3=1 kernelpagesize_kB=4
-3206000000 default file=/lib64/ld-2.12.so mapped=26 mapmax=6 N0=24 N3=2 kernelpagesize_kB=4
-320621f000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
-3206220000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
-3206221000 default anon=1 dirty=1 N3=1 kernelpagesize_kB=4
-3206800000 default file=/lib64/libc-2.12.so mapped=59 mapmax=21 active=55 N0=41 N3=18 kernelpagesize_kB=4
-320698b000 default file=/lib64/libc-2.12.so
-3206b8a000 default file=/lib64/libc-2.12.so anon=2 dirty=2 N3=2 kernelpagesize_kB=4
-3206b8e000 default file=/lib64/libc-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
-3206b8f000 default anon=3 dirty=3 active=1 N3=3 kernelpagesize_kB=4
-7f4dc10a2000 default anon=3 dirty=3 N3=3 kernelpagesize_kB=4
-7f4dc10b4000 default anon=2 dirty=2 active=1 N3=2 kernelpagesize_kB=4
-7f4dc1200000 default file=/anon_hugepage\040(deleted) huge anon=1 dirty=1 N3=1 kernelpagesize_kB=2048
-7fff335f0000 default stack anon=3 dirty=3 N3=3 kernelpagesize_kB=4
-7fff3369d000 default mapped=1 mapmax=35 active=0 N3=1 kernelpagesize_kB=4
+summarized separated by blank spaces, one mapping per each file line::
+
+ address policy mapping details
+
+ 00400000 default file=/usr/local/bin/app mapped=1 active=0 N3=1 kernelpagesize_kB=4
+ 00600000 default file=/usr/local/bin/app anon=1 dirty=1 N3=1 kernelpagesize_kB=4
+ 3206000000 default file=/lib64/ld-2.12.so mapped=26 mapmax=6 N0=24 N3=2 kernelpagesize_kB=4
+ 320621f000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
+ 3206220000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
+ 3206221000 default anon=1 dirty=1 N3=1 kernelpagesize_kB=4
+ 3206800000 default file=/lib64/libc-2.12.so mapped=59 mapmax=21 active=55 N0=41 N3=18 kernelpagesize_kB=4
+ 320698b000 default file=/lib64/libc-2.12.so
+ 3206b8a000 default file=/lib64/libc-2.12.so anon=2 dirty=2 N3=2 kernelpagesize_kB=4
+ 3206b8e000 default file=/lib64/libc-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
+ 3206b8f000 default anon=3 dirty=3 active=1 N3=3 kernelpagesize_kB=4
+ 7f4dc10a2000 default anon=3 dirty=3 N3=3 kernelpagesize_kB=4
+ 7f4dc10b4000 default anon=2 dirty=2 active=1 N3=2 kernelpagesize_kB=4
+ 7f4dc1200000 default file=/anon_hugepage\040(deleted) huge anon=1 dirty=1 N3=1 kernelpagesize_kB=2048
+ 7fff335f0000 default stack anon=3 dirty=3 N3=3 kernelpagesize_kB=4
+ 7fff3369d000 default mapped=1 mapmax=35 active=0 N3=1 kernelpagesize_kB=4
Where:
+
"address" is the starting address for the mapping;
+
"policy" reports the NUMA memory policy set for the mapping (see Documentation/admin-guide/mm/numa_memory_policy.rst);
+
"mapping details" summarizes mapping data such as mapping type, page usage counters,
node locality page counters (N0 == node0, N1 == node1, ...) and the kernel page
size, in KB, that is backing the mapping up.
system. It depends on the kernel configuration and the loaded modules, which
files are there, and which are missing.
-Table 1-5: Kernel info in /proc
-..............................................................................
- File Content
- apm Advanced power management info
- buddyinfo Kernel memory allocator information (see text) (2.5)
- bus Directory containing bus specific information
- cmdline Kernel command line
- cpuinfo Info about the CPU
- devices Available devices (block and character)
- dma Used DMS channels
- filesystems Supported filesystems
- driver Various drivers grouped here, currently rtc (2.4)
- execdomains Execdomains, related to security (2.4)
- fb Frame Buffer devices (2.4)
- fs File system parameters, currently nfs/exports (2.4)
- ide Directory containing info about the IDE subsystem
- interrupts Interrupt usage
- iomem Memory map (2.4)
- ioports I/O port usage
- irq Masks for irq to cpu affinity (2.4)(smp?)
- isapnp ISA PnP (Plug&Play) Info (2.4)
- kcore Kernel core image (can be ELF or A.OUT(deprecated in 2.4))
- kmsg Kernel messages
- ksyms Kernel symbol table
- loadavg Load average of last 1, 5 & 15 minutes
- locks Kernel locks
- meminfo Memory info
- misc Miscellaneous
- modules List of loaded modules
- mounts Mounted filesystems
- net Networking info (see text)
+.. table:: Table 1-5: Kernel info in /proc
+
+ ============ ===============================================================
+ File Content
+ ============ ===============================================================
+ apm Advanced power management info
+ buddyinfo Kernel memory allocator information (see text) (2.5)
+ bus Directory containing bus specific information
+ cmdline Kernel command line
+ cpuinfo Info about the CPU
+ devices Available devices (block and character)
+ dma Used DMS channels
+ filesystems Supported filesystems
+ driver Various drivers grouped here, currently rtc (2.4)
+ execdomains Execdomains, related to security (2.4)
+ fb Frame Buffer devices (2.4)
+ fs File system parameters, currently nfs/exports (2.4)
+ ide Directory containing info about the IDE subsystem
+ interrupts Interrupt usage
+ iomem Memory map (2.4)
+ ioports I/O port usage
+ irq Masks for irq to cpu affinity (2.4)(smp?)
+ isapnp ISA PnP (Plug&Play) Info (2.4)
+ kcore Kernel core image (can be ELF or A.OUT(deprecated in 2.4))
+ kmsg Kernel messages
+ ksyms Kernel symbol table
+ loadavg Load average of last 1, 5 & 15 minutes
+ locks Kernel locks
+ meminfo Memory info
+ misc Miscellaneous
+ modules List of loaded modules
+ mounts Mounted filesystems
+ net Networking info (see text)
pagetypeinfo Additional page allocator information (see text) (2.5)
- partitions Table of partitions known to the system
- pci Deprecated info of PCI bus (new way -> /proc/bus/pci/,
- decoupled by lspci (2.4)
- rtc Real time clock
- scsi SCSI info (see text)
- slabinfo Slab pool info
- softirqs softirq usage
- stat Overall statistics
- swaps Swap space utilization
- sys See chapter 2
- sysvipc Info of SysVIPC Resources (msg, sem, shm) (2.4)
- tty Info of tty drivers
- uptime Wall clock since boot, combined idle time of all cpus
- version Kernel version
- video bttv info of video resources (2.4)
- vmallocinfo Show vmalloced areas
-..............................................................................
+ partitions Table of partitions known to the system
+ pci Deprecated info of PCI bus (new way -> /proc/bus/pci/,
+ decoupled by lspci (2.4)
+ rtc Real time clock
+ scsi SCSI info (see text)
+ slabinfo Slab pool info
+ softirqs softirq usage
+ stat Overall statistics
+ swaps Swap space utilization
+ sys See chapter 2
+ sysvipc Info of SysVIPC Resources (msg, sem, shm) (2.4)
+ tty Info of tty drivers
+ uptime Wall clock since boot, combined idle time of all cpus
+ version Kernel version
+ video bttv info of video resources (2.4)
+ vmallocinfo Show vmalloced areas
+ ============ ===============================================================
You can, for example, check which interrupts are currently in use and what
-they are used for by looking in the file /proc/interrupts:
-
- > cat /proc/interrupts
- CPU0
- 0: 8728810 XT-PIC timer
- 1: 895 XT-PIC keyboard
- 2: 0 XT-PIC cascade
- 3: 531695 XT-PIC aha152x
- 4: 2014133 XT-PIC serial
- 5: 44401 XT-PIC pcnet_cs
- 8: 2 XT-PIC rtc
- 11: 8 XT-PIC i82365
- 12: 182918 XT-PIC PS/2 Mouse
- 13: 1 XT-PIC fpu
- 14: 1232265 XT-PIC ide0
- 15: 7 XT-PIC ide1
- NMI: 0
+they are used for by looking in the file /proc/interrupts::
+
+ > cat /proc/interrupts
+ CPU0
+ 0: 8728810 XT-PIC timer
+ 1: 895 XT-PIC keyboard
+ 2: 0 XT-PIC cascade
+ 3: 531695 XT-PIC aha152x
+ 4: 2014133 XT-PIC serial
+ 5: 44401 XT-PIC pcnet_cs
+ 8: 2 XT-PIC rtc
+ 11: 8 XT-PIC i82365
+ 12: 182918 XT-PIC PS/2 Mouse
+ 13: 1 XT-PIC fpu
+ 14: 1232265 XT-PIC ide0
+ 15: 7 XT-PIC ide1
+ NMI: 0
In 2.4.* a couple of lines where added to this file LOC & ERR (this time is the
-output of a SMP machine):
+output of a SMP machine)::
- > cat /proc/interrupts
+ > cat /proc/interrupts
- CPU0 CPU1
+ CPU0 CPU1
0: 1243498 1214548 IO-APIC-edge timer
1: 8949 8958 IO-APIC-edge keyboard
2: 0 0 XT-PIC cascade
15: 2183 2415 IO-APIC-edge ide1
17: 30564 30414 IO-APIC-level eth0
18: 177 164 IO-APIC-level bttv
- NMI: 2457961 2457959
- LOC: 2457882 2457881
+ NMI: 2457961 2457959
+ LOC: 2457882 2457881
ERR: 2155
NMI is incremented in this case because every timer interrupt generates a NMI
/proc/interrupts to display every IRQ vector in use by the system, not
just those considered 'most important'. The new vectors are:
- THR -- interrupt raised when a machine check threshold counter
+THR
+ interrupt raised when a machine check threshold counter
(typically counting ECC corrected errors of memory or cache) exceeds
a configurable threshold. Only available on some systems.
- TRM -- a thermal event interrupt occurs when a temperature threshold
+TRM
+ a thermal event interrupt occurs when a temperature threshold
has been exceeded for the CPU. This interrupt may also be generated
when the temperature drops back to normal.
- SPU -- a spurious interrupt is some interrupt that was raised then lowered
+SPU
+ a spurious interrupt is some interrupt that was raised then lowered
by some IO device before it could be fully processed by the APIC. Hence
the APIC sees the interrupt but does not know what device it came from.
For this case the APIC will generate the interrupt with a IRQ vector
of 0xff. This might also be generated by chipset bugs.
- RES, CAL, TLB -- rescheduling, call and TLB flush interrupts are
+RES, CAL, TLB]
+ rescheduling, call and TLB flush interrupts are
sent from one CPU to another per the needs of the OS. Typically,
their statistics are used by kernel developers and interested users to
determine the occurrence of interrupts of the given type.
irq subdir is one subdir for each IRQ, and two files; default_smp_affinity and
prof_cpu_mask.
-For example
+For example::
+
> ls /proc/irq/
0 10 12 14 16 18 2 4 6 8 prof_cpu_mask
1 11 13 15 17 19 3 5 7 9 default_smp_affinity
smp_affinity
smp_affinity is a bitmask, in which you can specify which CPUs can handle the
-IRQ, you can set it by doing:
+IRQ, you can set it by doing::
> echo 1 > /proc/irq/10/smp_affinity
This means that only the first CPU will handle the IRQ, but you can also echo
5 which means that only the first and third CPU can handle the IRQ.
-The contents of each smp_affinity file is the same by default:
+The contents of each smp_affinity file is the same by default::
> cat /proc/irq/0/smp_affinity
ffffffff
There is an alternate interface, smp_affinity_list which allows specifying
-a cpu range instead of a bitmask:
+a cpu range instead of a bitmask::
> cat /proc/irq/0/smp_affinity_list
1024-1031
Commonly used objects have their own slab pool (such as network buffers,
directory cache, and so on).
-..............................................................................
+::
-> cat /proc/buddyinfo
+ > cat /proc/buddyinfo
-Node 0, zone DMA 0 4 5 4 4 3 ...
-Node 0, zone Normal 1 0 0 1 101 8 ...
-Node 0, zone HighMem 2 0 0 1 1 0 ...
+ Node 0, zone DMA 0 4 5 4 4 3 ...
+ Node 0, zone Normal 1 0 0 1 101 8 ...
+ Node 0, zone HighMem 2 0 0 1 1 0 ...
External fragmentation is a problem under some workloads, and buddyinfo is a
-useful tool for helping diagnose these problems. Buddyinfo will give you a
+useful tool for helping diagnose these problems. Buddyinfo will give you a
clue as to how big an area you can safely allocate, or why a previous
allocation failed.
-Each column represents the number of pages of a certain order which are
-available. In this case, there are 0 chunks of 2^0*PAGE_SIZE available in
-ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE
-available in ZONE_NORMAL, etc...
+Each column represents the number of pages of a certain order which are
+available. In this case, there are 0 chunks of 2^0*PAGE_SIZE available in
+ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE
+available in ZONE_NORMAL, etc...
More information relevant to external fragmentation can be found in
-pagetypeinfo.
-
-> cat /proc/pagetypeinfo
-Page block order: 9
-Pages per block: 512
-
-Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10
-Node 0, zone DMA, type Unmovable 0 0 0 1 1 1 1 1 1 1 0
-Node 0, zone DMA, type Reclaimable 0 0 0 0 0 0 0 0 0 0 0
-Node 0, zone DMA, type Movable 1 1 2 1 2 1 1 0 1 0 2
-Node 0, zone DMA, type Reserve 0 0 0 0 0 0 0 0 0 1 0
-Node 0, zone DMA, type Isolate 0 0 0 0 0 0 0 0 0 0 0
-Node 0, zone DMA32, type Unmovable 103 54 77 1 1 1 11 8 7 1 9
-Node 0, zone DMA32, type Reclaimable 0 0 2 1 0 0 0 0 1 0 0
-Node 0, zone DMA32, type Movable 169 152 113 91 77 54 39 13 6 1 452
-Node 0, zone DMA32, type Reserve 1 2 2 2 2 0 1 1 1 1 0
-Node 0, zone DMA32, type Isolate 0 0 0 0 0 0 0 0 0 0 0
-
-Number of blocks type Unmovable Reclaimable Movable Reserve Isolate
-Node 0, zone DMA 2 0 5 1 0
-Node 0, zone DMA32 41 6 967 2 0
+pagetypeinfo::
+
+ > cat /proc/pagetypeinfo
+ Page block order: 9
+ Pages per block: 512
+
+ Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10
+ Node 0, zone DMA, type Unmovable 0 0 0 1 1 1 1 1 1 1 0
+ Node 0, zone DMA, type Reclaimable 0 0 0 0 0 0 0 0 0 0 0
+ Node 0, zone DMA, type Movable 1 1 2 1 2 1 1 0 1 0 2
+ Node 0, zone DMA, type Reserve 0 0 0 0 0 0 0 0 0 1 0
+ Node 0, zone DMA, type Isolate 0 0 0 0 0 0 0 0 0 0 0
+ Node 0, zone DMA32, type Unmovable 103 54 77 1 1 1 11 8 7 1 9
+ Node 0, zone DMA32, type Reclaimable 0 0 2 1 0 0 0 0 1 0 0
+ Node 0, zone DMA32, type Movable 169 152 113 91 77 54 39 13 6 1 452
+ Node 0, zone DMA32, type Reserve 1 2 2 2 2 0 1 1 1 1 0
+ Node 0, zone DMA32, type Isolate 0 0 0 0 0 0 0 0 0 0 0
+
+ Number of blocks type Unmovable Reclaimable Movable Reserve Isolate
+ Node 0, zone DMA 2 0 5 1 0
+ Node 0, zone DMA32 41 6 967 2 0
Fragmentation avoidance in the kernel works by grouping pages of different
migrate types into the same contiguous regions of memory called page blocks.
also be allocatable although a lot of filesystem metadata may have to be
reclaimed to achieve this.
-..............................................................................
-meminfo:
+meminfo
+~~~~~~~
Provides information about distribution and utilization of memory. This
varies by architecture and compile options. The following is from a
16GB PIII, which has highmem enabled. You may not have all of these fields.
-> cat /proc/meminfo
-
-MemTotal: 16344972 kB
-MemFree: 13634064 kB
-MemAvailable: 14836172 kB
-Buffers: 3656 kB
-Cached: 1195708 kB
-SwapCached: 0 kB
-Active: 891636 kB
-Inactive: 1077224 kB
-HighTotal: 15597528 kB
-HighFree: 13629632 kB
-LowTotal: 747444 kB
-LowFree: 4432 kB
-SwapTotal: 0 kB
-SwapFree: 0 kB
-Dirty: 968 kB
-Writeback: 0 kB
-AnonPages: 861800 kB
-Mapped: 280372 kB
-Shmem: 644 kB
-KReclaimable: 168048 kB
-Slab: 284364 kB
-SReclaimable: 159856 kB
-SUnreclaim: 124508 kB
-PageTables: 24448 kB
-NFS_Unstable: 0 kB
-Bounce: 0 kB
-WritebackTmp: 0 kB
-CommitLimit: 7669796 kB
-Committed_AS: 100056 kB
-VmallocTotal: 112216 kB
-VmallocUsed: 428 kB
-VmallocChunk: 111088 kB
-Percpu: 62080 kB
-HardwareCorrupted: 0 kB
-AnonHugePages: 49152 kB
-ShmemHugePages: 0 kB
-ShmemPmdMapped: 0 kB
-
-
- MemTotal: Total usable ram (i.e. physical ram minus a few reserved
+::
+
+ > cat /proc/meminfo
+
+ MemTotal: 16344972 kB
+ MemFree: 13634064 kB
+ MemAvailable: 14836172 kB
+ Buffers: 3656 kB
+ Cached: 1195708 kB
+ SwapCached: 0 kB
+ Active: 891636 kB
+ Inactive: 1077224 kB
+ HighTotal: 15597528 kB
+ HighFree: 13629632 kB
+ LowTotal: 747444 kB
+ LowFree: 4432 kB
+ SwapTotal: 0 kB
+ SwapFree: 0 kB
+ Dirty: 968 kB
+ Writeback: 0 kB
+ AnonPages: 861800 kB
+ Mapped: 280372 kB
+ Shmem: 644 kB
+ KReclaimable: 168048 kB
+ Slab: 284364 kB
+ SReclaimable: 159856 kB
+ SUnreclaim: 124508 kB
+ PageTables: 24448 kB
+ NFS_Unstable: 0 kB
+ Bounce: 0 kB
+ WritebackTmp: 0 kB
+ CommitLimit: 7669796 kB
+ Committed_AS: 100056 kB
+ VmallocTotal: 112216 kB
+ VmallocUsed: 428 kB
+ VmallocChunk: 111088 kB
+ Percpu: 62080 kB
+ HardwareCorrupted: 0 kB
+ AnonHugePages: 49152 kB
+ ShmemHugePages: 0 kB
+ ShmemPmdMapped: 0 kB
+
+MemTotal
+ Total usable ram (i.e. physical ram minus a few reserved
bits and the kernel binary code)
- MemFree: The sum of LowFree+HighFree
-MemAvailable: An estimate of how much memory is available for starting new
+MemFree
+ The sum of LowFree+HighFree
+MemAvailable
+ An estimate of how much memory is available for starting new
applications, without swapping. Calculated from MemFree,
SReclaimable, the size of the file LRU lists, and the low
watermarks in each zone.
page cache to function well, and that not all reclaimable
slab will be reclaimable, due to items being in use. The
impact of those factors will vary from system to system.
- Buffers: Relatively temporary storage for raw disk blocks
+Buffers
+ Relatively temporary storage for raw disk blocks
shouldn't get tremendously large (20MB or so)
- Cached: in-memory cache for files read from the disk (the
+Cached
+ in-memory cache for files read from the disk (the
pagecache). Doesn't include SwapCached
- SwapCached: Memory that once was swapped out, is swapped back in but
+SwapCached
+ Memory that once was swapped out, is swapped back in but
still also is in the swapfile (if memory is needed it
doesn't need to be swapped out AGAIN because it is already
in the swapfile. This saves I/O)
- Active: Memory that has been used more recently and usually not
+Active
+ Memory that has been used more recently and usually not
reclaimed unless absolutely necessary.
- Inactive: Memory which has been less recently used. It is more
+Inactive
+ Memory which has been less recently used. It is more
eligible to be reclaimed for other purposes
- HighTotal:
- HighFree: Highmem is all memory above ~860MB of physical memory
+HighTotal, HighFree
+ Highmem is all memory above ~860MB of physical memory
Highmem areas are for use by userspace programs, or
for the pagecache. The kernel must use tricks to access
this memory, making it slower to access than lowmem.
- LowTotal:
- LowFree: Lowmem is memory which can be used for everything that
+LowTotal, LowFree
+ Lowmem is memory which can be used for everything that
highmem can be used for, but it is also available for the
kernel's use for its own data structures. Among many
other things, it is where everything from the Slab is
allocated. Bad things happen when you're out of lowmem.
- SwapTotal: total amount of swap space available
- SwapFree: Memory which has been evicted from RAM, and is temporarily
+SwapTotal
+ total amount of swap space available
+SwapFree
+ Memory which has been evicted from RAM, and is temporarily
on the disk
- Dirty: Memory which is waiting to get written back to the disk
- Writeback: Memory which is actively being written back to the disk
- AnonPages: Non-file backed pages mapped into userspace page tables
-HardwareCorrupted: The amount of RAM/memory in KB, the kernel identifies as
+Dirty
+ Memory which is waiting to get written back to the disk
+Writeback
+ Memory which is actively being written back to the disk
+AnonPages
+ Non-file backed pages mapped into userspace page tables
+HardwareCorrupted
+ The amount of RAM/memory in KB, the kernel identifies as
corrupted.
-AnonHugePages: Non-file backed huge pages mapped into userspace page tables
- Mapped: files which have been mmaped, such as libraries
- Shmem: Total memory used by shared memory (shmem) and tmpfs
-ShmemHugePages: Memory used by shared memory (shmem) and tmpfs allocated
+AnonHugePages
+ Non-file backed huge pages mapped into userspace page tables
+Mapped
+ files which have been mmaped, such as libraries
+Shmem
+ Total memory used by shared memory (shmem) and tmpfs
+ShmemHugePages
+ Memory used by shared memory (shmem) and tmpfs allocated
with huge pages
-ShmemPmdMapped: Shared memory mapped into userspace with huge pages
-KReclaimable: Kernel allocations that the kernel will attempt to reclaim
+ShmemPmdMapped
+ Shared memory mapped into userspace with huge pages
+KReclaimable
+ Kernel allocations that the kernel will attempt to reclaim
under memory pressure. Includes SReclaimable (below), and other
direct allocations with a shrinker.
- Slab: in-kernel data structures cache
-SReclaimable: Part of Slab, that might be reclaimed, such as caches
- SUnreclaim: Part of Slab, that cannot be reclaimed on memory pressure
- PageTables: amount of memory dedicated to the lowest level of page
+Slab
+ in-kernel data structures cache
+SReclaimable
+ Part of Slab, that might be reclaimed, such as caches
+SUnreclaim
+ Part of Slab, that cannot be reclaimed on memory pressure
+PageTables
+ amount of memory dedicated to the lowest level of page
tables.
-NFS_Unstable: NFS pages sent to the server, but not yet committed to stable
+NFS_Unstable
+ NFS pages sent to the server, but not yet committed to stable
storage
- Bounce: Memory used for block device "bounce buffers"
-WritebackTmp: Memory used by FUSE for temporary writeback buffers
- CommitLimit: Based on the overcommit ratio ('vm.overcommit_ratio'),
+Bounce
+ Memory used for block device "bounce buffers"
+WritebackTmp
+ Memory used by FUSE for temporary writeback buffers
+CommitLimit
+ Based on the overcommit ratio ('vm.overcommit_ratio'),
this is the total amount of memory currently available to
be allocated on the system. This limit is only adhered to
if strict overcommit accounting is enabled (mode 2 in
'vm.overcommit_memory').
- The CommitLimit is calculated with the following formula:
- CommitLimit = ([total RAM pages] - [total huge TLB pages]) *
- overcommit_ratio / 100 + [total swap pages]
+
+ The CommitLimit is calculated with the following formula::
+
+ CommitLimit = ([total RAM pages] - [total huge TLB pages]) *
+ overcommit_ratio / 100 + [total swap pages]
+
For example, on a system with 1G of physical RAM and 7G
of swap with a `vm.overcommit_ratio` of 30 it would
yield a CommitLimit of 7.3G.
+
For more details, see the memory overcommit documentation
in vm/overcommit-accounting.
-Committed_AS: The amount of memory presently allocated on the system.
+Committed_AS
+ The amount of memory presently allocated on the system.
The committed memory is a sum of all of the memory which
has been allocated by processes, even if it has not been
"used" by them as of yet. A process which malloc()'s 1G
This is useful if one needs to guarantee that processes will
not fail due to lack of memory once that memory has been
successfully allocated.
-VmallocTotal: total size of vmalloc memory area
- VmallocUsed: amount of vmalloc area which is used
-VmallocChunk: largest contiguous block of vmalloc area which is free
- Percpu: Memory allocated to the percpu allocator used to back percpu
+VmallocTotal
+ total size of vmalloc memory area
+VmallocUsed
+ amount of vmalloc area which is used
+VmallocChunk
+ largest contiguous block of vmalloc area which is free
+Percpu
+ Memory allocated to the percpu allocator used to back percpu
allocations. This stat excludes the cost of metadata.
-..............................................................................
-
-vmallocinfo:
+vmallocinfo
+~~~~~~~~~~~
Provides information about vmalloced/vmaped areas. One line per area,
containing the virtual address range of the area, size in bytes,
caller information of the creator, and optional information depending
on the kind of area :
+ ========== ===================================================
pages=nr number of pages
phys=addr if a physical address was specified
ioremap I/O mapping (ioremap() and friends)
vpages buffer for pages pointers was vmalloced (huge area)
N<node>=nr (Only on NUMA kernels)
Number of pages allocated on memory node <node>
-
-> cat /proc/vmallocinfo
-0xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204 ...
- /0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128
-0xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204 ...
- /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64
-0xffffc20000302000-0xffffc20000304000 8192 acpi_tb_verify_table+0x21/0x4f...
- phys=7fee8000 ioremap
-0xffffc20000304000-0xffffc20000307000 12288 acpi_tb_verify_table+0x21/0x4f...
- phys=7fee7000 ioremap
-0xffffc2000031d000-0xffffc2000031f000 8192 init_vdso_vars+0x112/0x210
-0xffffc2000031f000-0xffffc2000032b000 49152 cramfs_uncompress_init+0x2e ...
- /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3
-0xffffc2000033a000-0xffffc2000033d000 12288 sys_swapon+0x640/0xac0 ...
- pages=2 vmalloc N1=2
-0xffffc20000347000-0xffffc2000034c000 20480 xt_alloc_table_info+0xfe ...
- /0x130 [x_tables] pages=4 vmalloc N0=4
-0xffffffffa0000000-0xffffffffa000f000 61440 sys_init_module+0xc27/0x1d00 ...
- pages=14 vmalloc N2=14
-0xffffffffa000f000-0xffffffffa0014000 20480 sys_init_module+0xc27/0x1d00 ...
- pages=4 vmalloc N1=4
-0xffffffffa0014000-0xffffffffa0017000 12288 sys_init_module+0xc27/0x1d00 ...
- pages=2 vmalloc N1=2
-0xffffffffa0017000-0xffffffffa0022000 45056 sys_init_module+0xc27/0x1d00 ...
- pages=10 vmalloc N0=10
-
-..............................................................................
-
-softirqs:
+ ========== ===================================================
+
+::
+
+ > cat /proc/vmallocinfo
+ 0xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204 ...
+ /0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128
+ 0xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204 ...
+ /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64
+ 0xffffc20000302000-0xffffc20000304000 8192 acpi_tb_verify_table+0x21/0x4f...
+ phys=7fee8000 ioremap
+ 0xffffc20000304000-0xffffc20000307000 12288 acpi_tb_verify_table+0x21/0x4f...
+ phys=7fee7000 ioremap
+ 0xffffc2000031d000-0xffffc2000031f000 8192 init_vdso_vars+0x112/0x210
+ 0xffffc2000031f000-0xffffc2000032b000 49152 cramfs_uncompress_init+0x2e ...
+ /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3
+ 0xffffc2000033a000-0xffffc2000033d000 12288 sys_swapon+0x640/0xac0 ...
+ pages=2 vmalloc N1=2
+ 0xffffc20000347000-0xffffc2000034c000 20480 xt_alloc_table_info+0xfe ...
+ /0x130 [x_tables] pages=4 vmalloc N0=4
+ 0xffffffffa0000000-0xffffffffa000f000 61440 sys_init_module+0xc27/0x1d00 ...
+ pages=14 vmalloc N2=14
+ 0xffffffffa000f000-0xffffffffa0014000 20480 sys_init_module+0xc27/0x1d00 ...
+ pages=4 vmalloc N1=4
+ 0xffffffffa0014000-0xffffffffa0017000 12288 sys_init_module+0xc27/0x1d00 ...
+ pages=2 vmalloc N1=2
+ 0xffffffffa0017000-0xffffffffa0022000 45056 sys_init_module+0xc27/0x1d00 ...
+ pages=10 vmalloc N0=10
+
+
+softirqs
+~~~~~~~~
Provides counts of softirq handlers serviced since boot time, for each cpu.
-> cat /proc/softirqs
- CPU0 CPU1 CPU2 CPU3
- HI: 0 0 0 0
- TIMER: 27166 27120 27097 27034
- NET_TX: 0 0 0 17
- NET_RX: 42 0 0 39
- BLOCK: 0 0 107 1121
- TASKLET: 0 0 0 290
- SCHED: 27035 26983 26971 26746
- HRTIMER: 0 0 0 0
- RCU: 1678 1769 2178 2250
+::
+
+ > cat /proc/softirqs
+ CPU0 CPU1 CPU2 CPU3
+ HI: 0 0 0 0
+ TIMER: 27166 27120 27097 27034
+ NET_TX: 0 0 0 17
+ NET_RX: 42 0 0 39
+ BLOCK: 0 0 107 1121
+ TASKLET: 0 0 0 290
+ SCHED: 27035 26983 26971 26746
+ HRTIMER: 0 0 0 0
+ RCU: 1678 1769 2178 2250
1.3 IDE devices in /proc/ide
in the controller specific subtree.
The file drivers contains general information about the drivers used for the
-IDE devices:
+IDE devices::
> cat /proc/ide/drivers
ide-cdrom version 4.53
directories contains the files shown in table 1-6.
-Table 1-6: IDE controller info in /proc/ide/ide?
-..............................................................................
- File Content
- channel IDE channel (0 or 1)
- config Configuration (only for PCI/IDE bridge)
- mate Mate name
- model Type/Chipset of IDE controller
-..............................................................................
+.. table:: Table 1-6: IDE controller info in /proc/ide/ide?
+
+ ======= =======================================
+ File Content
+ ======= =======================================
+ channel IDE channel (0 or 1)
+ config Configuration (only for PCI/IDE bridge)
+ mate Mate name
+ model Type/Chipset of IDE controller
+ ======= =======================================
Each device connected to a controller has a separate subdirectory in the
controllers directory. The files listed in table 1-7 are contained in these
directories.
-Table 1-7: IDE device information
-..............................................................................
- File Content
- cache The cache
- capacity Capacity of the medium (in 512Byte blocks)
- driver driver and version
- geometry physical and logical geometry
- identify device identify block
- media media type
- model device identifier
- settings device setup
- smart_thresholds IDE disk management thresholds
- smart_values IDE disk management values
-..............................................................................
-
-The most interesting file is settings. This file contains a nice overview of
-the drive parameters:
-
- # cat /proc/ide/ide0/hda/settings
- name value min max mode
- ---- ----- --- --- ----
- bios_cyl 526 0 65535 rw
- bios_head 255 0 255 rw
- bios_sect 63 0 63 rw
- breada_readahead 4 0 127 rw
- bswap 0 0 1 r
- file_readahead 72 0 2097151 rw
- io_32bit 0 0 3 rw
- keepsettings 0 0 1 rw
- max_kb_per_request 122 1 127 rw
- multcount 0 0 8 rw
- nice1 1 0 1 rw
- nowerr 0 0 1 rw
- pio_mode write-only 0 255 w
- slow 0 0 1 rw
- unmaskirq 0 0 1 rw
- using_dma 0 0 1 rw
+.. table:: Table 1-7: IDE device information
+
+ ================ ==========================================
+ File Content
+ ================ ==========================================
+ cache The cache
+ capacity Capacity of the medium (in 512Byte blocks)
+ driver driver and version
+ geometry physical and logical geometry
+ identify device identify block
+ media media type
+ model device identifier
+ settings device setup
+ smart_thresholds IDE disk management thresholds
+ smart_values IDE disk management values
+ ================ ==========================================
+
+The most interesting file is ``settings``. This file contains a nice
+overview of the drive parameters::
+
+ # cat /proc/ide/ide0/hda/settings
+ name value min max mode
+ ---- ----- --- --- ----
+ bios_cyl 526 0 65535 rw
+ bios_head 255 0 255 rw
+ bios_sect 63 0 63 rw
+ breada_readahead 4 0 127 rw
+ bswap 0 0 1 r
+ file_readahead 72 0 2097151 rw
+ io_32bit 0 0 3 rw
+ keepsettings 0 0 1 rw
+ max_kb_per_request 122 1 127 rw
+ multcount 0 0 8 rw
+ nice1 1 0 1 rw
+ nowerr 0 0 1 rw
+ pio_mode write-only 0 255 w
+ slow 0 0 1 rw
+ unmaskirq 0 0 1 rw
+ using_dma 0 0 1 rw
1.4 Networking info in /proc/net
support this. Table 1-9 lists the files and their meaning.
-Table 1-8: IPv6 info in /proc/net
-..............................................................................
- File Content
- udp6 UDP sockets (IPv6)
- tcp6 TCP sockets (IPv6)
- raw6 Raw device statistics (IPv6)
- igmp6 IP multicast addresses, which this host joined (IPv6)
- if_inet6 List of IPv6 interface addresses
- ipv6_route Kernel routing table for IPv6
- rt6_stats Global IPv6 routing tables statistics
- sockstat6 Socket statistics (IPv6)
- snmp6 Snmp data (IPv6)
-..............................................................................
-
-
-Table 1-9: Network info in /proc/net
-..............................................................................
- File Content
- arp Kernel ARP table
- dev network devices with statistics
+.. table:: Table 1-8: IPv6 info in /proc/net
+
+ ========== =====================================================
+ File Content
+ ========== =====================================================
+ udp6 UDP sockets (IPv6)
+ tcp6 TCP sockets (IPv6)
+ raw6 Raw device statistics (IPv6)
+ igmp6 IP multicast addresses, which this host joined (IPv6)
+ if_inet6 List of IPv6 interface addresses
+ ipv6_route Kernel routing table for IPv6
+ rt6_stats Global IPv6 routing tables statistics
+ sockstat6 Socket statistics (IPv6)
+ snmp6 Snmp data (IPv6)
+ ========== =====================================================
+
+.. table:: Table 1-9: Network info in /proc/net
+
+ ============= ================================================================
+ File Content
+ ============= ================================================================
+ arp Kernel ARP table
+ dev network devices with statistics
dev_mcast the Layer2 multicast groups a device is listening too
(interface index, label, number of references, number of bound
- addresses).
- dev_stat network device status
- ip_fwchains Firewall chain linkage
- ip_fwnames Firewall chain names
- ip_masq Directory containing the masquerading tables
- ip_masquerade Major masquerading table
- netstat Network statistics
- raw raw device statistics
- route Kernel routing table
- rpc Directory containing rpc info
- rt_cache Routing cache
- snmp SNMP data
- sockstat Socket statistics
- tcp TCP sockets
- udp UDP sockets
- unix UNIX domain sockets
- wireless Wireless interface data (Wavelan etc)
- igmp IP multicast addresses, which this host joined
- psched Global packet scheduler parameters.
- netlink List of PF_NETLINK sockets
- ip_mr_vifs List of multicast virtual interfaces
- ip_mr_cache List of multicast routing cache
-..............................................................................
+ addresses).
+ dev_stat network device status
+ ip_fwchains Firewall chain linkage
+ ip_fwnames Firewall chain names
+ ip_masq Directory containing the masquerading tables
+ ip_masquerade Major masquerading table
+ netstat Network statistics
+ raw raw device statistics
+ route Kernel routing table
+ rpc Directory containing rpc info
+ rt_cache Routing cache
+ snmp SNMP data
+ sockstat Socket statistics
+ tcp TCP sockets
+ udp UDP sockets
+ unix UNIX domain sockets
+ wireless Wireless interface data (Wavelan etc)
+ igmp IP multicast addresses, which this host joined
+ psched Global packet scheduler parameters.
+ netlink List of PF_NETLINK sockets
+ ip_mr_vifs List of multicast virtual interfaces
+ ip_mr_cache List of multicast routing cache
+ ============= ================================================================
You can use this information to see which network devices are available in
-your system and how much traffic was routed over those devices:
-
- > cat /proc/net/dev
- Inter-|Receive |[...
- face |bytes packets errs drop fifo frame compressed multicast|[...
- lo: 908188 5596 0 0 0 0 0 0 [...
- ppp0:15475140 20721 410 0 0 410 0 0 [...
- eth0: 614530 7085 0 0 0 0 0 1 [...
-
- ...] Transmit
- ...] bytes packets errs drop fifo colls carrier compressed
- ...] 908188 5596 0 0 0 0 0 0
- ...] 1375103 17405 0 0 0 0 0 0
- ...] 1703981 5535 0 0 0 3 0 0
+your system and how much traffic was routed over those devices::
+
+ > cat /proc/net/dev
+ Inter-|Receive |[...
+ face |bytes packets errs drop fifo frame compressed multicast|[...
+ lo: 908188 5596 0 0 0 0 0 0 [...
+ ppp0:15475140 20721 410 0 0 410 0 0 [...
+ eth0: 614530 7085 0 0 0 0 0 1 [...
+
+ ...] Transmit
+ ...] bytes packets errs drop fifo colls carrier compressed
+ ...] 908188 5596 0 0 0 0 0 0
+ ...] 1375103 17405 0 0 0 0 0 0
+ ...] 1703981 5535 0 0 0 3 0 0
In addition, each Channel Bond interface has its own directory. For
example, the bond0 device will have a directory called /proc/net/bond0/.
If you have a SCSI host adapter in your system, you'll find a subdirectory
named after the driver for this adapter in /proc/scsi. You'll also see a list
-of all recognized SCSI devices in /proc/scsi:
+of all recognized SCSI devices in /proc/scsi::
- >cat /proc/scsi/scsi
- Attached devices:
- Host: scsi0 Channel: 00 Id: 00 Lun: 00
- Vendor: IBM Model: DGHS09U Rev: 03E0
- Type: Direct-Access ANSI SCSI revision: 03
- Host: scsi0 Channel: 00 Id: 06 Lun: 00
- Vendor: PIONEER Model: CD-ROM DR-U06S Rev: 1.04
- Type: CD-ROM ANSI SCSI revision: 02
+ >cat /proc/scsi/scsi
+ Attached devices:
+ Host: scsi0 Channel: 00 Id: 00 Lun: 00
+ Vendor: IBM Model: DGHS09U Rev: 03E0
+ Type: Direct-Access ANSI SCSI revision: 03
+ Host: scsi0 Channel: 00 Id: 06 Lun: 00
+ Vendor: PIONEER Model: CD-ROM DR-U06S Rev: 1.04
+ Type: CD-ROM ANSI SCSI revision: 02
The directory named after the driver has one file for each adapter found in
the system. These files contain information about the controller, including
the used IRQ and the IO address range. The amount of information shown is
dependent on the adapter you use. The example shows the output for an Adaptec
-AHA-2940 SCSI adapter:
-
- > cat /proc/scsi/aic7xxx/0
-
- Adaptec AIC7xxx driver version: 5.1.19/3.2.4
- Compile Options:
- TCQ Enabled By Default : Disabled
- AIC7XXX_PROC_STATS : Disabled
- AIC7XXX_RESET_DELAY : 5
- Adapter Configuration:
- SCSI Adapter: Adaptec AHA-294X Ultra SCSI host adapter
- Ultra Wide Controller
- PCI MMAPed I/O Base: 0xeb001000
- Adapter SEEPROM Config: SEEPROM found and used.
- Adaptec SCSI BIOS: Enabled
- IRQ: 10
- SCBs: Active 0, Max Active 2,
- Allocated 15, HW 16, Page 255
- Interrupts: 160328
- BIOS Control Word: 0x18b6
- Adapter Control Word: 0x005b
- Extended Translation: Enabled
- Disconnect Enable Flags: 0xffff
- Ultra Enable Flags: 0x0001
- Tag Queue Enable Flags: 0x0000
- Ordered Queue Tag Flags: 0x0000
- Default Tag Queue Depth: 8
- Tagged Queue By Device array for aic7xxx host instance 0:
- {255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255}
- Actual queue depth per device for aic7xxx host instance 0:
- {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}
- Statistics:
- (scsi0:0:0:0)
- Device using Wide/Sync transfers at 40.0 MByte/sec, offset 8
- Transinfo settings: current(12/8/1/0), goal(12/8/1/0), user(12/15/1/0)
- Total transfers 160151 (74577 reads and 85574 writes)
- (scsi0:0:6:0)
- Device using Narrow/Sync transfers at 5.0 MByte/sec, offset 15
- Transinfo settings: current(50/15/0/0), goal(50/15/0/0), user(50/15/0/0)
- Total transfers 0 (0 reads and 0 writes)
+AHA-2940 SCSI adapter::
+
+ > cat /proc/scsi/aic7xxx/0
+
+ Adaptec AIC7xxx driver version: 5.1.19/3.2.4
+ Compile Options:
+ TCQ Enabled By Default : Disabled
+ AIC7XXX_PROC_STATS : Disabled
+ AIC7XXX_RESET_DELAY : 5
+ Adapter Configuration:
+ SCSI Adapter: Adaptec AHA-294X Ultra SCSI host adapter
+ Ultra Wide Controller
+ PCI MMAPed I/O Base: 0xeb001000
+ Adapter SEEPROM Config: SEEPROM found and used.
+ Adaptec SCSI BIOS: Enabled
+ IRQ: 10
+ SCBs: Active 0, Max Active 2,
+ Allocated 15, HW 16, Page 255
+ Interrupts: 160328
+ BIOS Control Word: 0x18b6
+ Adapter Control Word: 0x005b
+ Extended Translation: Enabled
+ Disconnect Enable Flags: 0xffff
+ Ultra Enable Flags: 0x0001
+ Tag Queue Enable Flags: 0x0000
+ Ordered Queue Tag Flags: 0x0000
+ Default Tag Queue Depth: 8
+ Tagged Queue By Device array for aic7xxx host instance 0:
+ {255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255}
+ Actual queue depth per device for aic7xxx host instance 0:
+ {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}
+ Statistics:
+ (scsi0:0:0:0)
+ Device using Wide/Sync transfers at 40.0 MByte/sec, offset 8
+ Transinfo settings: current(12/8/1/0), goal(12/8/1/0), user(12/15/1/0)
+ Total transfers 160151 (74577 reads and 85574 writes)
+ (scsi0:0:6:0)
+ Device using Narrow/Sync transfers at 5.0 MByte/sec, offset 15
+ Transinfo settings: current(50/15/0/0), goal(50/15/0/0), user(50/15/0/0)
+ Total transfers 0 (0 reads and 0 writes)
1.6 Parallel port info in /proc/parport
These directories contain the four files shown in Table 1-10.
-Table 1-10: Files in /proc/parport
-..............................................................................
- File Content
- autoprobe Any IEEE-1284 device ID information that has been acquired.
+.. table:: Table 1-10: Files in /proc/parport
+
+ ========= ====================================================================
+ File Content
+ ========= ====================================================================
+ autoprobe Any IEEE-1284 device ID information that has been acquired.
devices list of the device drivers using that port. A + will appear by the
name of the device currently using the port (it might not appear
- against any).
- hardware Parallel port's base address, IRQ line and DMA channel.
+ against any).
+ hardware Parallel port's base address, IRQ line and DMA channel.
irq IRQ that parport is using for that port. This is in a separate
file to allow you to alter it by writing a new value in (IRQ
- number or none).
-..............................................................................
+ number or none).
+ ========= ====================================================================
1.7 TTY info in /proc/tty
-------------------------
this directory, as shown in Table 1-11.
-Table 1-11: Files in /proc/tty
-..............................................................................
- File Content
- drivers list of drivers and their usage
- ldiscs registered line disciplines
- driver/serial usage statistic and status of single tty lines
-..............................................................................
+.. table:: Table 1-11: Files in /proc/tty
+
+ ============= ==============================================
+ File Content
+ ============= ==============================================
+ drivers list of drivers and their usage
+ ldiscs registered line disciplines
+ driver/serial usage statistic and status of single tty lines
+ ============= ==============================================
To see which tty's are currently in use, you can simply look into the file
-/proc/tty/drivers:
-
- > cat /proc/tty/drivers
- pty_slave /dev/pts 136 0-255 pty:slave
- pty_master /dev/ptm 128 0-255 pty:master
- pty_slave /dev/ttyp 3 0-255 pty:slave
- pty_master /dev/pty 2 0-255 pty:master
- serial /dev/cua 5 64-67 serial:callout
- serial /dev/ttyS 4 64-67 serial
- /dev/tty0 /dev/tty0 4 0 system:vtmaster
- /dev/ptmx /dev/ptmx 5 2 system
- /dev/console /dev/console 5 1 system:console
- /dev/tty /dev/tty 5 0 system:/dev/tty
- unknown /dev/tty 4 1-63 console
+/proc/tty/drivers::
+
+ > cat /proc/tty/drivers
+ pty_slave /dev/pts 136 0-255 pty:slave
+ pty_master /dev/ptm 128 0-255 pty:master
+ pty_slave /dev/ttyp 3 0-255 pty:slave
+ pty_master /dev/pty 2 0-255 pty:master
+ serial /dev/cua 5 64-67 serial:callout
+ serial /dev/ttyS 4 64-67 serial
+ /dev/tty0 /dev/tty0 4 0 system:vtmaster
+ /dev/ptmx /dev/ptmx 5 2 system
+ /dev/console /dev/console 5 1 system:console
+ /dev/tty /dev/tty 5 0 system:/dev/tty
+ unknown /dev/tty 4 1-63 console
1.8 Miscellaneous kernel statistics in /proc/stat
Various pieces of information about kernel activity are available in the
/proc/stat file. All of the numbers reported in this file are aggregates
-since the system first booted. For a quick look, simply cat the file:
+since the system first booted. For a quick look, simply cat the file::
> cat /proc/stat
cpu 2255 34 2290 22625563 6290 127 456 0 0 0
- idle: twiddling thumbs
- iowait: In a word, iowait stands for waiting for I/O to complete. But there
are several problems:
+
1. Cpu will not wait for I/O to complete, iowait is the time that a task is
waiting for I/O to complete. When cpu goes into idle state for
outstanding task io, another task will be scheduled on this CPU.
on any CPU, so the iowait of each CPU is difficult to calculate.
3. The value of iowait field in /proc/stat will decrease in certain
conditions.
+
So, the iowait is not reliable by reading from /proc/stat.
- irq: servicing interrupts
- softirq: servicing softirqs
/proc/fs/ext4/dm-0). The files in each per-device directory are shown
in Table 1-12, below.
-Table 1-12: Files in /proc/fs/ext4/<devname>
-..............................................................................
- File Content
+.. table:: Table 1-12: Files in /proc/fs/ext4/<devname>
+
+ ============== ==========================================================
+ File Content
mb_groups details of multiblock allocator buddy cache of free blocks
-..............................................................................
+ ============== ==========================================================
2.0 /proc/consoles
------------------
Shows registered system console lines.
To see which character device lines are currently used for the system console
-/dev/console, you may simply look into the file /proc/consoles:
+/dev/console, you may simply look into the file /proc/consoles::
> cat /proc/consoles
tty0 -WU (ECp) 4:7
The columns are:
- device name of the device
- operations R = can do read operations
- W = can do write operations
- U = can do unblank
- flags E = it is enabled
- C = it is preferred console
- B = it is primary boot console
- p = it is used for printk buffer
- b = it is not a TTY but a Braille device
- a = it is safe to use when cpu is offline
- major:minor major and minor number of the device separated by a colon
++--------------------+-------------------------------------------------------+
+| device | name of the device |
++====================+=======================================================+
+| operations | * R = can do read operations |
+| | * W = can do write operations |
+| | * U = can do unblank |
++--------------------+-------------------------------------------------------+
+| flags | * E = it is enabled |
+| | * C = it is preferred console |
+| | * B = it is primary boot console |
+| | * p = it is used for printk buffer |
+| | * b = it is not a TTY but a Braille device |
+| | * a = it is safe to use when cpu is offline |
++--------------------+-------------------------------------------------------+
+| major:minor | major and minor number of the device separated by a |
+| | colon |
++--------------------+-------------------------------------------------------+
-------------------------------------------------------------------------------
Summary
-------------------------------------------------------------------------------
+-------
+
The /proc file system serves information about the running system. It not only
allows access to process data but also allows you to request the kernel status
by reading files in the hierarchy.
The directory structure of /proc reflects the types of information and makes
it easy, if not obvious, where to look for specific data.
-------------------------------------------------------------------------------
-------------------------------------------------------------------------------
-CHAPTER 2: MODIFYING SYSTEM PARAMETERS
-------------------------------------------------------------------------------
+Chapter 2: Modifying System Parameters
+======================================
-------------------------------------------------------------------------------
In This Chapter
-------------------------------------------------------------------------------
+---------------
+
* Modifying kernel parameters by writing into files found in /proc/sys
* Exploring the files which modify certain parameters
* Review of the /proc/sys file tree
-------------------------------------------------------------------------------
+------------------------------------------------------------------------------
A very interesting part of /proc is the directory /proc/sys. This is not only
a source of information, it also allows you to change parameters within the
Please see: Documentation/admin-guide/sysctl/ directory for descriptions of these
entries.
-------------------------------------------------------------------------------
Summary
-------------------------------------------------------------------------------
+-------
+
Certain aspects of kernel behavior can be modified at runtime, without the
need to recompile the kernel, or even to reboot the system. The files in the
/proc/sys tree can not only be read, but also modified. You can use the echo
command to write value into these files, thereby changing the default settings
of the kernel.
-------------------------------------------------------------------------------
-------------------------------------------------------------------------------
-CHAPTER 3: PER-PROCESS PARAMETERS
-------------------------------------------------------------------------------
+
+Chapter 3: Per-process Parameters
+=================================
3.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj- Adjust the oom-killer score
--------------------------------------------------------------------------------
This file contains IO statistics for each running process
Example
--------
+~~~~~~~
+
+::
-test:/tmp # dd if=/dev/zero of=/tmp/test.dat &
-[1] 3828
+ test:/tmp # dd if=/dev/zero of=/tmp/test.dat &
+ [1] 3828
-test:/tmp # cat /proc/3828/io
-rchar: 323934931
-wchar: 323929600
-syscr: 632687
-syscw: 632675
-read_bytes: 0
-write_bytes: 323932160
-cancelled_write_bytes: 0
+ test:/tmp # cat /proc/3828/io
+ rchar: 323934931
+ wchar: 323929600
+ syscr: 632687
+ syscw: 632675
+ read_bytes: 0
+ write_bytes: 323932160
+ cancelled_write_bytes: 0
Description
------------
+~~~~~~~~~~~
rchar
------
+^^^^^
I/O counter: chars read
The number of bytes which this task has caused to be read from storage. This
wchar
------
+^^^^^
I/O counter: chars written
The number of bytes which this task has caused, or shall cause to be written
syscr
------
+^^^^^
I/O counter: read syscalls
Attempt to count the number of read I/O operations, i.e. syscalls like read()
syscw
------
+^^^^^
I/O counter: write syscalls
Attempt to count the number of write I/O operations, i.e. syscalls like
read_bytes
-----------
+^^^^^^^^^^
I/O counter: bytes read
Attempt to count the number of bytes which this process really did cause to
write_bytes
------------
+^^^^^^^^^^^
I/O counter: bytes written
Attempt to count the number of bytes which this process caused to be sent to
cancelled_write_bytes
----------------------
+^^^^^^^^^^^^^^^^^^^^^
The big inaccuracy here is truncate. If a process writes 1MB to a file and
then deletes the file, it will in fact perform no writeout. But it will have
that.
-Note
-----
+.. Note::
-At its current implementation state, this is a bit racy on 32-bit machines: if
-process A reads process B's /proc/pid/io while process B is updating one of
-those 64-bit counters, process A could see an intermediate result.
+ At its current implementation state, this is a bit racy on 32-bit machines:
+ if process A reads process B's /proc/pid/io while process B is updating one
+ of those 64-bit counters, process A could see an intermediate result.
More information about this can be found within the taskstats documentation in
corresponding memory type are dumped, otherwise they are not dumped.
The following 9 memory types are supported:
+
- (bit 0) anonymous private memory
- (bit 1) anonymous shared memory
- (bit 2) file-backed private memory
- (bit 3) file-backed shared memory
- (bit 4) ELF header pages in file-backed private memory areas (it is
- effective only if the bit 2 is cleared)
+ effective only if the bit 2 is cleared)
- (bit 5) hugetlb private memory
- (bit 6) hugetlb shared memory
- (bit 7) DAX private memory
segments, ELF header pages and hugetlb private memory are dumped.
If you don't want to dump all shared memory segments attached to pid 1234,
-write 0x31 to the process's proc file.
+write 0x31 to the process's proc file::
$ echo 0x31 > /proc/1234/coredump_filter
When a new process is created, the process inherits the bitmask status from its
parent. It is useful to set up coredump_filter before the program runs.
-For example:
+For example::
$ echo 0x7 > /proc/self/coredump_filter
$ ./some_program
3.5 /proc/<pid>/mountinfo - Information about mounts
--------------------------------------------------------
-This file contains lines of the form:
+This file contains lines of the form::
-36 35 98:0 /mnt1 /mnt2 rw,noatime master:1 - ext3 /dev/root rw,errors=continue
-(1)(2)(3) (4) (5) (6) (7) (8) (9) (10) (11)
+ 36 35 98:0 /mnt1 /mnt2 rw,noatime master:1 - ext3 /dev/root rw,errors=continue
+ (1)(2)(3) (4) (5) (6) (7) (8) (9) (10) (11)
-(1) mount ID: unique identifier of the mount (may be reused after umount)
-(2) parent ID: ID of parent (or of self for the top of the mount tree)
-(3) major:minor: value of st_dev for files on filesystem
-(4) root: root of the mount within the filesystem
-(5) mount point: mount point relative to the process's root
-(6) mount options: per mount options
-(7) optional fields: zero or more fields of the form "tag[:value]"
-(8) separator: marks the end of the optional fields
-(9) filesystem type: name of filesystem of the form "type[.subtype]"
-(10) mount source: filesystem specific information or "none"
-(11) super options: per super block options
+ (1) mount ID: unique identifier of the mount (may be reused after umount)
+ (2) parent ID: ID of parent (or of self for the top of the mount tree)
+ (3) major:minor: value of st_dev for files on filesystem
+ (4) root: root of the mount within the filesystem
+ (5) mount point: mount point relative to the process's root
+ (6) mount options: per mount options
+ (7) optional fields: zero or more fields of the form "tag[:value]"
+ (8) separator: marks the end of the optional fields
+ (9) filesystem type: name of filesystem of the form "type[.subtype]"
+ (10) mount source: filesystem specific information or "none"
+ (11) super options: per super block options
Parsers should ignore all unrecognised optional fields. Currently the
possible optional fields are:
-shared:X mount is shared in peer group X
-master:X mount is slave to peer group X
-propagate_from:X mount is slave and receives propagation from peer group X (*)
-unbindable mount is unbindable
+================ ==============================================================
+shared:X mount is shared in peer group X
+master:X mount is slave to peer group X
+propagate_from:X mount is slave and receives propagation from peer group X [#]_
+unbindable mount is unbindable
+================ ==============================================================
-(*) X is the closest dominant peer group under the process's root. If
-X is the immediate master of the mount, or if there's no dominant peer
-group under the same root, then only the "master:X" field is present
-and not the "propagate_from:X" field.
+.. [#] X is the closest dominant peer group under the process's root. If
+ X is the immediate master of the mount, or if there's no dominant peer
+ group under the same root, then only the "master:X" field is present
+ and not the "propagate_from:X" field.
For more information on mount propagation see:
the file system containing the opened file [see 3.5 /proc/<pid>/mountinfo
for details].
-A typical output is
+A typical output is::
pos: 0
flags: 0100002
mnt_id: 19
-All locks associated with a file descriptor are shown in its fdinfo too.
+All locks associated with a file descriptor are shown in its fdinfo too::
-lock: 1: FLOCK ADVISORY WRITE 359 00:13:11691 0 EOF
+ lock: 1: FLOCK ADVISORY WRITE 359 00:13:11691 0 EOF
The files such as eventfd, fsnotify, signalfd, epoll among the regular pos/flags
pair provide additional information particular to the objects they represent.
- Eventfd files
- ~~~~~~~~~~~~~
+Eventfd files
+~~~~~~~~~~~~~
+
+::
+
pos: 0
flags: 04002
mnt_id: 9
eventfd-count: 5a
- where 'eventfd-count' is hex value of a counter.
+where 'eventfd-count' is hex value of a counter.
+
+Signalfd files
+~~~~~~~~~~~~~~
+
+::
- Signalfd files
- ~~~~~~~~~~~~~~
pos: 0
flags: 04002
mnt_id: 9
sigmask: 0000000000000200
- where 'sigmask' is hex value of the signal mask associated
- with a file.
+where 'sigmask' is hex value of the signal mask associated
+with a file.
+
+Epoll files
+~~~~~~~~~~~
+
+::
- Epoll files
- ~~~~~~~~~~~
pos: 0
flags: 02
mnt_id: 9
tfd: 5 events: 1d data: ffffffffffffffff pos:0 ino:61af sdev:7
- where 'tfd' is a target file descriptor number in decimal form,
- 'events' is events mask being watched and the 'data' is data
- associated with a target [see epoll(7) for more details].
+where 'tfd' is a target file descriptor number in decimal form,
+'events' is events mask being watched and the 'data' is data
+associated with a target [see epoll(7) for more details].
- The 'pos' is current offset of the target file in decimal form
- [see lseek(2)], 'ino' and 'sdev' are inode and device numbers
- where target file resides, all in hex format.
+The 'pos' is current offset of the target file in decimal form
+[see lseek(2)], 'ino' and 'sdev' are inode and device numbers
+where target file resides, all in hex format.
- Fsnotify files
- ~~~~~~~~~~~~~~
- For inotify files the format is the following
+Fsnotify files
+~~~~~~~~~~~~~~
+For inotify files the format is the following::
pos: 0
flags: 02000000
inotify wd:3 ino:9e7e sdev:800013 mask:800afce ignored_mask:0 fhandle-bytes:8 fhandle-type:1 f_handle:7e9e0000640d1b6d
- where 'wd' is a watch descriptor in decimal form, ie a target file
- descriptor number, 'ino' and 'sdev' are inode and device where the
- target file resides and the 'mask' is the mask of events, all in hex
- form [see inotify(7) for more details].
+where 'wd' is a watch descriptor in decimal form, ie a target file
+descriptor number, 'ino' and 'sdev' are inode and device where the
+target file resides and the 'mask' is the mask of events, all in hex
+form [see inotify(7) for more details].
- If the kernel was built with exportfs support, the path to the target
- file is encoded as a file handle. The file handle is provided by three
- fields 'fhandle-bytes', 'fhandle-type' and 'f_handle', all in hex
- format.
+If the kernel was built with exportfs support, the path to the target
+file is encoded as a file handle. The file handle is provided by three
+fields 'fhandle-bytes', 'fhandle-type' and 'f_handle', all in hex
+format.
- If the kernel is built without exportfs support the file handle won't be
- printed out.
+If the kernel is built without exportfs support the file handle won't be
+printed out.
- If there is no inotify mark attached yet the 'inotify' line will be omitted.
+If there is no inotify mark attached yet the 'inotify' line will be omitted.
- For fanotify files the format is
+For fanotify files the format is::
pos: 0
flags: 02
fanotify mnt_id:12 mflags:40 mask:38 ignored_mask:40000003
fanotify ino:4f969 sdev:800013 mflags:0 mask:3b ignored_mask:40000000 fhandle-bytes:8 fhandle-type:1 f_handle:69f90400c275b5b4
- where fanotify 'flags' and 'event-flags' are values used in fanotify_init
- call, 'mnt_id' is the mount point identifier, 'mflags' is the value of
- flags associated with mark which are tracked separately from events
- mask. 'ino', 'sdev' are target inode and device, 'mask' is the events
- mask and 'ignored_mask' is the mask of events which are to be ignored.
- All in hex format. Incorporation of 'mflags', 'mask' and 'ignored_mask'
- does provide information about flags and mask used in fanotify_mark
- call [see fsnotify manpage for details].
+where fanotify 'flags' and 'event-flags' are values used in fanotify_init
+call, 'mnt_id' is the mount point identifier, 'mflags' is the value of
+flags associated with mark which are tracked separately from events
+mask. 'ino', 'sdev' are target inode and device, 'mask' is the events
+mask and 'ignored_mask' is the mask of events which are to be ignored.
+All in hex format. Incorporation of 'mflags', 'mask' and 'ignored_mask'
+does provide information about flags and mask used in fanotify_mark
+call [see fsnotify manpage for details].
+
+While the first three lines are mandatory and always printed, the rest is
+optional and may be omitted if no marks created yet.
- While the first three lines are mandatory and always printed, the rest is
- optional and may be omitted if no marks created yet.
+Timerfd files
+~~~~~~~~~~~~~
- Timerfd files
- ~~~~~~~~~~~~~
+::
pos: 0
flags: 02
it_value: (0, 49406829)
it_interval: (1, 0)
- where 'clockid' is the clock type and 'ticks' is the number of the timer expirations
- that have occurred [see timerfd_create(2) for details]. 'settime flags' are
- flags in octal form been used to setup the timer [see timerfd_settime(2) for
- details]. 'it_value' is remaining time until the timer exiration.
- 'it_interval' is the interval for the timer. Note the timer might be set up
- with TIMER_ABSTIME option which will be shown in 'settime flags', but 'it_value'
- still exhibits timer's remaining time.
+where 'clockid' is the clock type and 'ticks' is the number of the timer expirations
+that have occurred [see timerfd_create(2) for details]. 'settime flags' are
+flags in octal form been used to setup the timer [see timerfd_settime(2) for
+details]. 'it_value' is remaining time until the timer exiration.
+'it_interval' is the interval for the timer. Note the timer might be set up
+with TIMER_ABSTIME option which will be shown in 'settime flags', but 'it_value'
+still exhibits timer's remaining time.
3.9 /proc/<pid>/map_files - Information about memory mapped files
---------------------------------------------------------------------
This directory contains symbolic links which represent memory mapped files
-the process is maintaining. Example output:
+the process is maintaining. Example output::
| lr-------- 1 root root 64 Jan 27 11:24 333c600000-333c620000 -> /usr/lib64/ld-2.18.so
| lr-------- 1 root root 64 Jan 27 11:24 333c81f000-333c820000 -> /usr/lib64/ld-2.18.so
architecture specific status of the task.
Example
--------
+~~~~~~~
+
+::
+
$ cat /proc/6753/arch_status
AVX512_elapsed_ms: 8
Description
------------
+~~~~~~~~~~~
x86 specific entries:
----------------------
- AVX512_elapsed_ms:
- ------------------
+~~~~~~~~~~~~~~~~~~~~~
+
+AVX512_elapsed_ms:
+^^^^^^^^^^^^^^^^^^
+
If AVX512 is supported on the machine, this entry shows the milliseconds
elapsed since the last time AVX512 usage was recorded. The recording
happens on a best effort basis when a task is scheduled out. This means
the task is unlikely an AVX512 user, but depends on the workload and the
scheduling scenario, it also could be a false negative mentioned above.
-------------------------------------------------------------------------------
Configuring procfs
-------------------------------------------------------------------------------
+------------------
4.1 Mount options
---------------------
The following mount options are supported:
+ ========= ========================================================
hidepid= Set /proc/<pid>/ access mode.
gid= Set the group authorized to learn processes information.
+ ========= ========================================================
hidepid=0 means classic mode - everybody may access all /proc/<pid>/ directories
(default).
+.. SPDX-License-Identifier: GPL-2.0
+
+===================
The QNX6 Filesystem
===================
qnx6fs shares many properties with traditional Unix filesystems. It has the
concepts of blocks, inodes and directories.
+
On QNX it is possible to create little endian and big endian qnx6 filesystems.
This feature makes it possible to create and use a different endianness fs
for the target (QNX is used on quite a range of embedded systems) platform
running on a different endianness.
+
The Linux driver handles endianness transparently. (LE and BE)
Blocks
The space in the device or file is split up into blocks. These are a fixed
size of 512, 1024, 2048 or 4096, which is decided when the filesystem is
created.
+
Blockpointers are 32bit, so the maximum space that can be addressed is
2^32 * 4096 bytes or 16TB
data and the addressing levels in that specific tree.
If the level value is 0, up to 16 direct blocks can be addressed by each
node.
+
Level 1 adds an additional indirect addressing level where each indirect
addressing block holds up to blocksize / 4 bytes pointers to data blocks.
Level 2 adds an additional indirect addressing block level (so, already up
Unused block pointers are always set to ~0 - regardless of root node,
indirect addressing blocks or inodes.
+
Data leaves are always on the lowest level. So no data is stored on upper
tree levels.
The first Superblock is located at 0x2000. (0x2000 is the bootblock size)
The Audi MMI 3G first superblock directly starts at byte 0.
+
Second superblock position can either be calculated from the superblock
information (total number of filesystem blocks) or by taking the highest
device address, zeroing the last 3 bytes and then subtracting 0x1000 from
There are also pointers to the first 16 blocks, if the object data can be
addressed with 16 direct blocks.
+
For more than 16 blocks an indirect addressing in form of another tree is
used. (scheme is the same as the one used for the superblock root nodes)
A directory is a filesystem object and has an inode just like a file.
It is a specially formatted file containing records which associate each
name with an inode number.
+
'.' inode number points to the directory inode
+
'..' inode number points to the parent directory inode
+
Eeach filename record additionally got a filename length field.
One special case are long filenames or subdirectory names.
+
These got set a filename length field of 0xff in the corresponding directory
record plus the longfile inode number also stored in that record.
+
With that longfilename inode number, the longfilename tree can be walked
starting with the superblock longfilename root node pointers.
Symbolic links are also filesystem objects with inodes. They got a specific
bit in the inode mode field identifying them as symbolic link.
+
The directory entry file inode pointer points to the target file inode.
Hard links got an inode, a directory entry, but a specific mode bit set,
Long filenames are stored in a separate addressing tree. The staring point
is the longfilename root node in the active superblock.
+
Each data block (tree leaves) holds one long filename. That filename is
limited to 510 bytes. The first two starting bytes are used as length field
for the actual filename.
+
If that structure shall fit for all allowed blocksizes, it is clear why there
is a limit of 510 bytes for the actual filename stored.
The qnx6fs filesystem allocation bitmap is stored in a tree under bitmap
root node in the superblock and each bit in the bitmap represents one
filesystem block.
+
The first block is block 0, which starts 0x1000 after superblock start.
So for a normal qnx6fs 0x3000 (bootblock + superblock) is the physical
address at which block 0 is located.
------------------
The bitmap itself is divided into three parts.
+
First the system area, that is split into two halves.
+
Then userspace.
The requirement for a static, fixed preallocated system area comes from how
qnx6fs deals with writes.
+
Each superblock got it's own half of the system area. So superblock #1
always uses blocks from the lower half while superblock #2 just writes to
blocks represented by the upper half bitmap system area bits.
-ramfs, rootfs and initramfs
+.. SPDX-License-Identifier: GPL-2.0
+
+===========================
+Ramfs, rootfs and initramfs
+===========================
+
October 17, 2005
+
Rob Landley <rob@landley.net>
=============================
All this differs from the old initrd in several ways:
- The old initrd was always a separate file, while the initramfs archive is
- linked into the linux kernel image. (The directory linux-*/usr is devoted
- to generating this archive during the build.)
+ linked into the linux kernel image. (The directory ``linux-*/usr`` is
+ devoted to generating this archive during the build.)
- The old initrd file was a gzipped filesystem image (in some file format,
such as ext2, that needed a driver built into the kernel), while the new
initramfs archive is a gzipped cpio archive (like tar only simpler,
- see cpio(1) and Documentation/driver-api/early-userspace/buffer-format.rst). The
- kernel's cpio extraction code is not only extremely small, it's also
+ see cpio(1) and Documentation/driver-api/early-userspace/buffer-format.rst).
+ The kernel's cpio extraction code is not only extremely small, it's also
__init text and data that can be discarded during the boot process.
- The program run by the old initrd (which was called /initrd, not /init) did
initramfs archive, which will automatically be incorporated into the
resulting binary. This option can point to an existing gzipped cpio
archive, a directory containing files to be archived, or a text file
-specification such as the following example:
+specification such as the following example::
dir /dev 755 0 0
nod /dev/console 644 0 0 c 5 1
(instead of a config file or directory).
The following command line can extract a cpio image (either by the above script
-or by the kernel build) back into its component files:
+or by the kernel build) back into its component files::
cpio -i -d -H newc -F initramfs_data.cpio --no-absolute-filenames
The following shell script can create a prebuilt cpio archive you can
-use in place of the above config file:
+use in place of the above config file::
#!/bin/sh
exit 1
fi
-Note: The cpio man page contains some bad advice that will break your initramfs
-archive if you follow it. It says "A typical way to generate the list
-of filenames is with the find command; you should give find the -depth option
-to minimize problems with permissions on directories that are unwritable or not
-searchable." Don't do this when creating initramfs.cpio.gz images, it won't
-work. The Linux kernel cpio extractor won't create files in a directory that
-doesn't exist, so the directory entries must go before the files that go in
-those directories. The above script gets them in the right order.
+.. Note::
+
+ The cpio man page contains some bad advice that will break your initramfs
+ archive if you follow it. It says "A typical way to generate the list
+ of filenames is with the find command; you should give find the -depth
+ option to minimize problems with permissions on directories that are
+ unwritable or not searchable." Don't do this when creating
+ initramfs.cpio.gz images, it won't work. The Linux kernel cpio extractor
+ won't create files in a directory that doesn't exist, so the directory
+ entries must go before the files that go in those directories.
+ The above script gets them in the right order.
External initramfs images:
--------------------------
If you don't already understand what shared libraries, devices, and paths
you need to get a minimal root filesystem up and running, here are some
references:
-http://www.tldp.org/HOWTO/Bootdisk-HOWTO/
-http://www.tldp.org/HOWTO/From-PowerUp-To-Bash-Prompt-HOWTO.html
-http://www.linuxfromscratch.org/lfs/view/stable/
+
+- http://www.tldp.org/HOWTO/Bootdisk-HOWTO/
+- http://www.tldp.org/HOWTO/From-PowerUp-To-Bash-Prompt-HOWTO.html
+- http://www.linuxfromscratch.org/lfs/view/stable/
The "klibc" package (http://www.kernel.org/pub/linux/libs/klibc) is
designed to be a tiny C library to statically link early userspace
A good first step is to get initramfs to run a statically linked "hello world"
program as init, and test it under an emulator like qemu (www.qemu.org) or
-User Mode Linux, like so:
+User Mode Linux, like so::
cat > hello.c << EOF
#include <stdio.h>
explained his reasoning:
- http://www.uwsg.iu.edu/hypermail/linux/kernel/0112.2/1550.html
- http://www.uwsg.iu.edu/hypermail/linux/kernel/0112.2/1638.html
+ - http://www.uwsg.iu.edu/hypermail/linux/kernel/0112.2/1550.html
+ - http://www.uwsg.iu.edu/hypermail/linux/kernel/0112.2/1638.html
and, most importantly, designed and implemented the initramfs code.
+.. SPDX-License-Identifier: GPL-2.0
+
+==================================
relay interface (formerly relayfs)
==================================
access to relay channel buffer data. Here are the file operations
that are available and some comments regarding their behavior:
+=========== ============================================================
open() enables user to open an _existing_ channel buffer.
mmap() results in channel buffer being mapped into the caller's
close() decrements the channel buffer's refcount. When the refcount
reaches 0, i.e. when no process or kernel client has the
buffer open, the channel buffer is freed.
+=========== ============================================================
In order for a user application to make use of relay files, the
-host filesystem must be mounted. For example,
+host filesystem must be mounted. For example::
mount -t debugfs debugfs /sys/kernel/debug
-NOTE: the host filesystem doesn't need to be mounted for kernel
+.. Note::
+
+ the host filesystem doesn't need to be mounted for kernel
clients to create or use channels - it only needs to be
mounted when user space applications need access to the buffer
data.
Here's a summary of the API the relay interface provides to in-kernel clients:
TBD(curr. line MT:/API/)
- channel management functions:
+ channel management functions::
relay_open(base_filename, parent, subbuf_size, n_subbufs,
callbacks, private_data)
relay_flush(chan)
relay_reset(chan)
- channel management typically called on instigation of userspace:
+ channel management typically called on instigation of userspace::
relay_subbufs_consumed(chan, cpu, subbufs_consumed)
- write functions:
+ write functions::
relay_write(chan, data, length)
__relay_write(chan, data, length)
relay_reserve(chan, length)
- callbacks:
+ callbacks::
subbuf_start(buf, subbuf, prev_subbuf, prev_padding)
buf_mapped(buf, filp)
create_buf_file(filename, parent, mode, buf, is_global)
remove_buf_file(dentry)
- helper functions:
+ helper functions::
relay_buf_full(buf)
subbuf_start_reserve(buf, length)
relay_close().
Here are some typical definitions for these callbacks, in this case
-using debugfs:
-
-/*
- * create_buf_file() callback. Creates relay file in debugfs.
- */
-static struct dentry *create_buf_file_handler(const char *filename,
- struct dentry *parent,
- umode_t mode,
- struct rchan_buf *buf,
- int *is_global)
-{
- return debugfs_create_file(filename, mode, parent, buf,
- &relay_file_operations);
-}
-
-/*
- * remove_buf_file() callback. Removes relay file from debugfs.
- */
-static int remove_buf_file_handler(struct dentry *dentry)
-{
- debugfs_remove(dentry);
-
- return 0;
-}
-
-/*
- * relay interface callbacks
- */
-static struct rchan_callbacks relay_callbacks =
-{
- .create_buf_file = create_buf_file_handler,
- .remove_buf_file = remove_buf_file_handler,
-};
-
-And an example relay_open() invocation using them:
+using debugfs::
+
+ /*
+ * create_buf_file() callback. Creates relay file in debugfs.
+ */
+ static struct dentry *create_buf_file_handler(const char *filename,
+ struct dentry *parent,
+ umode_t mode,
+ struct rchan_buf *buf,
+ int *is_global)
+ {
+ return debugfs_create_file(filename, mode, parent, buf,
+ &relay_file_operations);
+ }
+
+ /*
+ * remove_buf_file() callback. Removes relay file from debugfs.
+ */
+ static int remove_buf_file_handler(struct dentry *dentry)
+ {
+ debugfs_remove(dentry);
+
+ return 0;
+ }
+
+ /*
+ * relay interface callbacks
+ */
+ static struct rchan_callbacks relay_callbacks =
+ {
+ .create_buf_file = create_buf_file_handler,
+ .remove_buf_file = remove_buf_file_handler,
+ };
+
+And an example relay_open() invocation using them::
chan = relay_open("cpu", NULL, SUBBUF_SIZE, N_SUBBUFS, &relay_callbacks, NULL);
To implement 'no-overwrite' mode, the userspace client would provide
an implementation of the subbuf_start() callback something like the
-following:
+following::
-static int subbuf_start(struct rchan_buf *buf,
- void *subbuf,
- void *prev_subbuf,
- unsigned int prev_padding)
-{
- if (prev_subbuf)
- *((unsigned *)prev_subbuf) = prev_padding;
+ static int subbuf_start(struct rchan_buf *buf,
+ void *subbuf,
+ void *prev_subbuf,
+ unsigned int prev_padding)
+ {
+ if (prev_subbuf)
+ *((unsigned *)prev_subbuf) = prev_padding;
- if (relay_buf_full(buf))
- return 0;
+ if (relay_buf_full(buf))
+ return 0;
- subbuf_start_reserve(buf, sizeof(unsigned int));
+ subbuf_start_reserve(buf, sizeof(unsigned int));
- return 1;
-}
+ return 1;
+ }
If the current buffer is full, i.e. all sub-buffers remain unconsumed,
the callback returns 0 to indicate that the buffer switch should not
buffer switch can continue.
The implementation of the subbuf_start() callback for 'overwrite' mode
-would be very similar:
+would be very similar::
-static int subbuf_start(struct rchan_buf *buf,
- void *subbuf,
- void *prev_subbuf,
- size_t prev_padding)
-{
- if (prev_subbuf)
- *((unsigned *)prev_subbuf) = prev_padding;
+ static int subbuf_start(struct rchan_buf *buf,
+ void *subbuf,
+ void *prev_subbuf,
+ size_t prev_padding)
+ {
+ if (prev_subbuf)
+ *((unsigned *)prev_subbuf) = prev_padding;
- subbuf_start_reserve(buf, sizeof(unsigned int));
+ subbuf_start_reserve(buf, sizeof(unsigned int));
- return 1;
-}
+ return 1;
+ }
In this case, the relay_buf_full() check is meaningless and the
callback always returns 1, causing the buffer switch to occur
-ROMFS - ROM FILE SYSTEM
+.. SPDX-License-Identifier: GPL-2.0
+
+=======================
+ROMFS - ROM File System
+=======================
This is a quite dumb, read only filesystem, mainly for initial RAM
disks of installation disks. It has grown up by the need of having
bytes. This is quite rare however, since most file names are longer
than 3 bytes, and shorter than 15 bytes.
-The layout of the filesystem is the following:
+The layout of the filesystem is the following::
-offset content
+ offset content
+---+---+---+---+
0 | - | r | o | m | \
reliable, it does not require any tables, and it is very simple.
The following bytes are now part of the file system; each file header
-must begin on a 16 byte boundary.
+must begin on a 16 byte boundary::
-offset content
+ offset content
+---+---+---+---+
0 | next filehdr|X| The offset of the next file header
intended use. The mapping of the 8 possible values to file types is
the following:
+== =============== ============================================
mapping spec.info means
+== =============== ============================================
0 hard link link destination [file header]
1 directory first file's header
2 regular file unused, must be zero [MBZ]
5 char device - " -
6 socket unused, MBZ
7 fifo unused, MBZ
+== =============== ============================================
Note that hard links are specifically marked in this filesystem, but
they will behave as you can expect (i.e. share the inode number).
Pending issues:
- Permissions and owner information are pretty essential features of a
-Un*x like system, but romfs does not provide the full possibilities.
-I have never found this limiting, but others might.
+ Un*x like system, but romfs does not provide the full possibilities.
+ I have never found this limiting, but others might.
- The file system is read only, so it can be very small, but in case
-one would want to write _anything_ to a file system, he still needs
-a writable file system, thus negating the size advantages. Possible
-solutions: implement write access as a compile-time option, or a new,
-similarly small writable filesystem for RAM disks.
+ one would want to write _anything_ to a file system, he still needs
+ a writable file system, thus negating the size advantages. Possible
+ solutions: implement write access as a compile-time option, or a new,
+ similarly small writable filesystem for RAM disks.
- Since the files are only required to have alignment on a 16 byte
-boundary, it is currently possibly suboptimal to read or execute files
-from the filesystem. It might be resolved by reordering file data to
-have most of it (i.e. except the start and the end) laying at "natural"
-boundaries, thus it would be possible to directly map a big portion of
-the file contents to the mm subsystem.
+ boundary, it is currently possibly suboptimal to read or execute files
+ from the filesystem. It might be resolved by reordering file data to
+ have most of it (i.e. except the start and the end) laying at "natural"
+ boundaries, thus it would be possible to directly map a big portion of
+ the file contents to the mm subsystem.
- Compression might be an useful feature, but memory is quite a
-limiting factor in my eyes.
+ limiting factor in my eyes.
- Where it is used?
Have fun,
+
Janos Farkas <chexum@shadow.banki.hu>
-SQUASHFS 4.0 FILESYSTEM
+.. SPDX-License-Identifier: GPL-2.0
+
+=======================
+Squashfs 4.0 Filesystem
=======================
Squashfs is a compressed read-only filesystem for Linux.
+
It uses zlib, lz4, lzo, or xz compression to compress files, inodes and
directories. Inodes in the system are very small and all blocks are packed to
minimise data overhead. Block sizes greater than 4K are supported up to a
Mailing list: squashfs-devel@lists.sourceforge.net
Web site: www.squashfs.org
-1. FILESYSTEM FEATURES
+1. Filesystem Features
----------------------
Squashfs filesystem features versus Cramfs:
+============================== ========= ==========
Squashfs Cramfs
-
-Max filesystem size: 2^64 256 MiB
-Max file size: ~ 2 TiB 16 MiB
-Max files: unlimited unlimited
-Max directories: unlimited unlimited
-Max entries per directory: unlimited unlimited
-Max block size: 1 MiB 4 KiB
-Metadata compression: yes no
-Directory indexes: yes no
-Sparse file support: yes no
-Tail-end packing (fragments): yes no
-Exportable (NFS etc.): yes no
-Hard link support: yes no
-"." and ".." in readdir: yes no
-Real inode numbers: yes no
-32-bit uids/gids: yes no
-File creation time: yes no
-Xattr support: yes no
-ACL support: no no
+============================== ========= ==========
+Max filesystem size 2^64 256 MiB
+Max file size ~ 2 TiB 16 MiB
+Max files unlimited unlimited
+Max directories unlimited unlimited
+Max entries per directory unlimited unlimited
+Max block size 1 MiB 4 KiB
+Metadata compression yes no
+Directory indexes yes no
+Sparse file support yes no
+Tail-end packing (fragments) yes no
+Exportable (NFS etc.) yes no
+Hard link support yes no
+"." and ".." in readdir yes no
+Real inode numbers yes no
+32-bit uids/gids yes no
+File creation time yes no
+Xattr support yes no
+ACL support no no
+============================== ========= ==========
Squashfs compresses data, inodes and directories. In addition, inode and
directory data are highly compacted, and packed on byte boundaries. Each
file type, i.e. regular file, directory, symbolic link, and block/char device
inodes have different sizes).
-2. USING SQUASHFS
+2. Using Squashfs
-----------------
As squashfs is a read-only filesystem, the mksquashfs program must be used to
The squashfs-tools development tree is now located on kernel.org
git://git.kernel.org/pub/scm/fs/squashfs/squashfs-tools.git
-3. SQUASHFS FILESYSTEM DESIGN
+3. Squashfs Filesystem Design
-----------------------------
A squashfs filesystem consists of a maximum of nine parts, packed together on a
-byte alignment:
+byte alignment::
---------------
| superblock |
is stored. This xattr id is mapped into the location of the xattr
list using a second xattr id lookup table.
-4. TODOS AND OUTSTANDING ISSUES
+4. TODOs and Outstanding Issues
-------------------------------
-4.1 Todo list
+4.1 TODO list
-------------
Implement ACL support.
-4.2 Squashfs internal cache
+4.2 Squashfs Internal Cache
---------------------------
Blocks in Squashfs are compressed. To avoid repeatedly decompressing
+.. SPDX-License-Identifier: GPL-2.0
-sysfs - _The_ filesystem for exporting kernel objects.
+=====================================================
+sysfs - _The_ filesystem for exporting kernel objects
+=====================================================
Patrick Mochel <mochel@osdl.org>
+
Mike Murphy <mamurph@cs.clemson.edu>
-Revised: 16 August 2011
-Original: 10 January 2003
+:Revised: 16 August 2011
+:Original: 10 January 2003
What it is:
~~~~~~~~~~~
sysfs is a ram-based filesystem initially based on ramfs. It provides
-a means to export kernel data structures, their attributes, and the
-linkages between them to userspace.
+a means to export kernel data structures, their attributes, and the
+linkages between them to userspace.
sysfs is tied inherently to the kobject infrastructure. Please read
Documentation/kobject.txt for more information concerning the kobject
-interface.
+interface.
Using sysfs
~~~~~~~~~~~
sysfs is always compiled in if CONFIG_SYSFS is defined. You can access
-it by doing:
+it by doing::
- mount -t sysfs sysfs /sys
+ mount -t sysfs sysfs /sys
Directory Creation
of the kobject's parent, expressing internal object hierarchies to
userspace. Top-level directories in sysfs represent the common
ancestors of object hierarchies; i.e. the subsystems the objects
-belong to.
+belong to.
Sysfs internally stores a pointer to the kobject that implements a
directory in the kernfs_node object associated with the directory. In
Attributes should be ASCII text files, preferably with only one value
per file. It is noted that it may not be efficient to contain only one
value per file, so it is socially acceptable to express an array of
-values of the same type.
+values of the same type.
Mixing types, expressing multiple lines of data, and doing fancy
formatting of data is heavily frowned upon. Doing these things may get
-you publicly humiliated and your code rewritten without notice.
+you publicly humiliated and your code rewritten without notice.
-An attribute definition is simply:
+An attribute definition is simply::
-struct attribute {
- char * name;
- struct module *owner;
- umode_t mode;
-};
+ struct attribute {
+ char * name;
+ struct module *owner;
+ umode_t mode;
+ };
-int sysfs_create_file(struct kobject * kobj, const struct attribute * attr);
-void sysfs_remove_file(struct kobject * kobj, const struct attribute * attr);
+ int sysfs_create_file(struct kobject * kobj, const struct attribute * attr);
+ void sysfs_remove_file(struct kobject * kobj, const struct attribute * attr);
A bare attribute contains no means to read or write the value of the
attribute. Subsystems are encouraged to define their own attribute
structure and wrapper functions for adding and removing attributes for
-a specific object type.
+a specific object type.
-For example, the driver model defines struct device_attribute like:
+For example, the driver model defines struct device_attribute like::
-struct device_attribute {
- struct attribute attr;
- ssize_t (*show)(struct device *dev, struct device_attribute *attr,
- char *buf);
- ssize_t (*store)(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count);
-};
+ struct device_attribute {
+ struct attribute attr;
+ ssize_t (*show)(struct device *dev, struct device_attribute *attr,
+ char *buf);
+ ssize_t (*store)(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count);
+ };
-int device_create_file(struct device *, const struct device_attribute *);
-void device_remove_file(struct device *, const struct device_attribute *);
+ int device_create_file(struct device *, const struct device_attribute *);
+ void device_remove_file(struct device *, const struct device_attribute *);
-It also defines this helper for defining device attributes:
+It also defines this helper for defining device attributes::
-#define DEVICE_ATTR(_name, _mode, _show, _store) \
-struct device_attribute dev_attr_##_name = __ATTR(_name, _mode, _show, _store)
+ #define DEVICE_ATTR(_name, _mode, _show, _store) \
+ struct device_attribute dev_attr_##_name = __ATTR(_name, _mode, _show, _store)
-For example, declaring
+For example, declaring::
-static DEVICE_ATTR(foo, S_IWUSR | S_IRUGO, show_foo, store_foo);
+ static DEVICE_ATTR(foo, S_IWUSR | S_IRUGO, show_foo, store_foo);
-is equivalent to doing:
+is equivalent to doing::
-static struct device_attribute dev_attr_foo = {
- .attr = {
- .name = "foo",
- .mode = S_IWUSR | S_IRUGO,
- },
- .show = show_foo,
- .store = store_foo,
-};
+ static struct device_attribute dev_attr_foo = {
+ .attr = {
+ .name = "foo",
+ .mode = S_IWUSR | S_IRUGO,
+ },
+ .show = show_foo,
+ .store = store_foo,
+ };
Note as stated in include/linux/kernel.h "OTHER_WRITABLE? Generally
considered a bad idea." so trying to set a sysfs file writable for
static struct device_attribute dev_attr_foo = __ATTR_RW(foo);
the list of helpers available to define your wrapper function is:
-__ATTR_RO(name): assumes default name_show and mode 0444
-__ATTR_WO(name): assumes a name_store only and is restricted to mode
+
+__ATTR_RO(name):
+ assumes default name_show and mode 0444
+__ATTR_WO(name):
+ assumes a name_store only and is restricted to mode
0200 that is root write access only.
-__ATTR_RO_MODE(name, mode): fore more restrictive RO access currently
+__ATTR_RO_MODE(name, mode):
+ fore more restrictive RO access currently
only use case is the EFI System Resource Table
(see drivers/firmware/efi/esrt.c)
-__ATTR_RW(name): assumes default name_show, name_store and setting
+__ATTR_RW(name):
+ assumes default name_show, name_store and setting
mode to 0644.
-__ATTR_NULL: which sets the name to NULL and is used as end of list
+__ATTR_NULL:
+ which sets the name to NULL and is used as end of list
indicator (see: kernel/workqueue.c)
Subsystem-Specific Callbacks
When a subsystem defines a new attribute type, it must implement a
set of sysfs operations for forwarding read and write calls to the
-show and store methods of the attribute owners.
+show and store methods of the attribute owners::
-struct sysfs_ops {
- ssize_t (*show)(struct kobject *, struct attribute *, char *);
- ssize_t (*store)(struct kobject *, struct attribute *, const char *, size_t);
-};
+ struct sysfs_ops {
+ ssize_t (*show)(struct kobject *, struct attribute *, char *);
+ ssize_t (*store)(struct kobject *, struct attribute *, const char *, size_t);
+ };
[ Subsystems should have already defined a struct kobj_type as a
descriptor for this type, which is where the sysfs_ops pointer is
When a file is read or written, sysfs calls the appropriate method
for the type. The method then translates the generic struct kobject
and struct attribute pointers to the appropriate pointer types, and
-calls the associated methods.
+calls the associated methods.
-To illustrate:
+To illustrate::
-#define to_dev(obj) container_of(obj, struct device, kobj)
-#define to_dev_attr(_attr) container_of(_attr, struct device_attribute, attr)
+ #define to_dev(obj) container_of(obj, struct device, kobj)
+ #define to_dev_attr(_attr) container_of(_attr, struct device_attribute, attr)
-static ssize_t dev_attr_show(struct kobject *kobj, struct attribute *attr,
- char *buf)
-{
- struct device_attribute *dev_attr = to_dev_attr(attr);
- struct device *dev = to_dev(kobj);
- ssize_t ret = -EIO;
+ static ssize_t dev_attr_show(struct kobject *kobj, struct attribute *attr,
+ char *buf)
+ {
+ struct device_attribute *dev_attr = to_dev_attr(attr);
+ struct device *dev = to_dev(kobj);
+ ssize_t ret = -EIO;
- if (dev_attr->show)
- ret = dev_attr->show(dev, dev_attr, buf);
- if (ret >= (ssize_t)PAGE_SIZE) {
- printk("dev_attr_show: %pS returned bad count\n",
- dev_attr->show);
- }
- return ret;
-}
+ if (dev_attr->show)
+ ret = dev_attr->show(dev, dev_attr, buf);
+ if (ret >= (ssize_t)PAGE_SIZE) {
+ printk("dev_attr_show: %pS returned bad count\n",
+ dev_attr->show);
+ }
+ return ret;
+ }
To read or write attributes, show() or store() methods must be
specified when declaring the attribute. The method types should be as
-simple as those defined for device attributes:
+simple as those defined for device attributes::
-ssize_t (*show)(struct device *dev, struct device_attribute *attr, char *buf);
-ssize_t (*store)(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count);
+ ssize_t (*show)(struct device *dev, struct device_attribute *attr, char *buf);
+ ssize_t (*store)(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count);
IOW, they should take only an object, an attribute, and a buffer as parameters.
sysfs allocates a buffer of size (PAGE_SIZE) and passes it to the
method. Sysfs will call the method exactly once for each read or
write. This forces the following behavior on the method
-implementations:
+implementations:
-- On read(2), the show() method should fill the entire buffer.
+- On read(2), the show() method should fill the entire buffer.
Recall that an attribute should only be exporting one value, or an
- array of similar values, so this shouldn't be that expensive.
+ array of similar values, so this shouldn't be that expensive.
This allows userspace to do partial reads and forward seeks
arbitrarily over the entire file at will. If userspace seeks back to
When writing sysfs files, userspace processes should first read the
entire file, modify the values it wishes to change, then write the
- entire buffer back.
+ entire buffer back.
Attribute method implementations should operate on an identical
- buffer when reading and writing values.
+ buffer when reading and writing values.
Other notes:
file position.
- The buffer will always be PAGE_SIZE bytes in length. On i386, this
- is 4096.
+ is 4096.
- show() methods should return the number of bytes printed into the
buffer. This is the return value of scnprintf().
through, be sure to return an error.
- The object passed to the methods will be pinned in memory via sysfs
- referencing counting its embedded object. However, the physical
- entity (e.g. device) the object represents may not be present. Be
- sure to have a way to check this, if necessary.
+ referencing counting its embedded object. However, the physical
+ entity (e.g. device) the object represents may not be present. Be
+ sure to have a way to check this, if necessary.
-A very simple (and naive) implementation of a device attribute is:
+A very simple (and naive) implementation of a device attribute is::
-static ssize_t show_name(struct device *dev, struct device_attribute *attr,
- char *buf)
-{
- return scnprintf(buf, PAGE_SIZE, "%s\n", dev->name);
-}
+ static ssize_t show_name(struct device *dev, struct device_attribute *attr,
+ char *buf)
+ {
+ return scnprintf(buf, PAGE_SIZE, "%s\n", dev->name);
+ }
-static ssize_t store_name(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
-{
- snprintf(dev->name, sizeof(dev->name), "%.*s",
- (int)min(count, sizeof(dev->name) - 1), buf);
- return count;
-}
+ static ssize_t store_name(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+ {
+ snprintf(dev->name, sizeof(dev->name), "%.*s",
+ (int)min(count, sizeof(dev->name) - 1), buf);
+ return count;
+ }
-static DEVICE_ATTR(name, S_IRUGO, show_name, store_name);
+ static DEVICE_ATTR(name, S_IRUGO, show_name, store_name);
-(Note that the real implementation doesn't allow userspace to set the
+(Note that the real implementation doesn't allow userspace to set the
name for a device.)
~~~~~~~~~~~~~~~~~~~~~~~~~~
The sysfs directory arrangement exposes the relationship of kernel
-data structures.
+data structures.
-The top level sysfs directory looks like:
+The top level sysfs directory looks like::
-block/
-bus/
-class/
-dev/
-devices/
-firmware/
-net/
-fs/
+ block/
+ bus/
+ class/
+ dev/
+ devices/
+ firmware/
+ net/
+ fs/
devices/ contains a filesystem representation of the device tree. It maps
directly to the internal kernel device tree, which is a hierarchy of
-struct device.
+struct device.
bus/ contains flat directory layout of the various bus types in the
-kernel. Each bus's directory contains two subdirectories:
+kernel. Each bus's directory contains two subdirectories::
devices/
drivers/
The following interface layers currently exist in sysfs:
-- devices (include/linux/device.h)
-----------------------------------
-Structure:
+devices (include/linux/device.h)
+--------------------------------
+Structure::
-struct device_attribute {
- struct attribute attr;
- ssize_t (*show)(struct device *dev, struct device_attribute *attr,
- char *buf);
- ssize_t (*store)(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count);
-};
+ struct device_attribute {
+ struct attribute attr;
+ ssize_t (*show)(struct device *dev, struct device_attribute *attr,
+ char *buf);
+ ssize_t (*store)(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count);
+ };
-Declaring:
+Declaring::
-DEVICE_ATTR(_name, _mode, _show, _store);
+ DEVICE_ATTR(_name, _mode, _show, _store);
-Creation/Removal:
+Creation/Removal::
-int device_create_file(struct device *dev, const struct device_attribute * attr);
-void device_remove_file(struct device *dev, const struct device_attribute * attr);
+ int device_create_file(struct device *dev, const struct device_attribute * attr);
+ void device_remove_file(struct device *dev, const struct device_attribute * attr);
-- bus drivers (include/linux/device.h)
---------------------------------------
-Structure:
+bus drivers (include/linux/device.h)
+------------------------------------
+Structure::
-struct bus_attribute {
- struct attribute attr;
- ssize_t (*show)(struct bus_type *, char * buf);
- ssize_t (*store)(struct bus_type *, const char * buf, size_t count);
-};
+ struct bus_attribute {
+ struct attribute attr;
+ ssize_t (*show)(struct bus_type *, char * buf);
+ ssize_t (*store)(struct bus_type *, const char * buf, size_t count);
+ };
-Declaring:
+Declaring::
-static BUS_ATTR_RW(name);
-static BUS_ATTR_RO(name);
-static BUS_ATTR_WO(name);
+ static BUS_ATTR_RW(name);
+ static BUS_ATTR_RO(name);
+ static BUS_ATTR_WO(name);
-Creation/Removal:
+Creation/Removal::
-int bus_create_file(struct bus_type *, struct bus_attribute *);
-void bus_remove_file(struct bus_type *, struct bus_attribute *);
+ int bus_create_file(struct bus_type *, struct bus_attribute *);
+ void bus_remove_file(struct bus_type *, struct bus_attribute *);
-- device drivers (include/linux/device.h)
------------------------------------------
+device drivers (include/linux/device.h)
+---------------------------------------
-Structure:
+Structure::
-struct driver_attribute {
- struct attribute attr;
- ssize_t (*show)(struct device_driver *, char * buf);
- ssize_t (*store)(struct device_driver *, const char * buf,
- size_t count);
-};
+ struct driver_attribute {
+ struct attribute attr;
+ ssize_t (*show)(struct device_driver *, char * buf);
+ ssize_t (*store)(struct device_driver *, const char * buf,
+ size_t count);
+ };
-Declaring:
+Declaring::
-DRIVER_ATTR_RO(_name)
-DRIVER_ATTR_RW(_name)
+ DRIVER_ATTR_RO(_name)
+ DRIVER_ATTR_RW(_name)
-Creation/Removal:
+Creation/Removal::
-int driver_create_file(struct device_driver *, const struct driver_attribute *);
-void driver_remove_file(struct device_driver *, const struct driver_attribute *);
+ int driver_create_file(struct device_driver *, const struct driver_attribute *);
+ void driver_remove_file(struct device_driver *, const struct driver_attribute *);
Documentation
+.. SPDX-License-Identifier: GPL-2.0
+
+==================
+SystemV Filesystem
+==================
+
It implements all of
- Xenix FS,
- SystemV/386 FS,
- Coherent FS.
To install:
+
* Answer the 'System V and Coherent filesystem support' question with 'y'
when configuring the kernel.
-* To mount a disk or a partition, use
+* To mount a disk or a partition, use::
+
mount [-r] -t sysv device mountpoint
- The file system type names
+
+ The file system type names::
+
-t sysv
-t xenix
-t coherent
+
may be used interchangeably, but the last two will eventually disappear.
Bugs in the present implementation:
+
- Coherent FS:
+
- The "free list interleave" n:m is currently ignored.
- Only file systems with no filesystem name and no pack name are recognized.
- (See Coherent "man mkfs" for a description of these features.)
+ (See Coherent "man mkfs" for a description of these features.)
+
- SystemV Release 2 FS:
+
The superblock is only searched in the blocks 9, 15, 18, which
corresponds to the beginning of track 1 on floppy disks. No support
for this FS on hard disk yet.
These filesystems are rather similar. Here is a comparison with Minix FS:
* Linux fdisk reports on partitions
+
- Minix FS 0x81 Linux/Minix
- Xenix FS ??
- SystemV FS ??
- Coherent FS 0x08 AIX bootable
* Size of a block or zone (data allocation unit on disk)
+
- Minix FS 1024
- Xenix FS 1024 (also 512 ??)
- SystemV FS 1024 (also 512 and 2048)
all the block numbers (including the super block) are offset by one track.
* Byte ordering of "short" (16 bit entities) on disk:
+
- Minix FS little endian 0 1
- Xenix FS little endian 0 1
- SystemV FS little endian 0 1
- Coherent FS little endian 0 1
+
Of course, this affects only the file system, not the data of files on it!
* Byte ordering of "long" (32 bit entities) on disk:
+
- Minix FS little endian 0 1 2 3
- Xenix FS little endian 0 1 2 3
- SystemV FS little endian 0 1 2 3
- Coherent FS PDP-11 2 3 0 1
+
Of course, this affects only the file system, not the data of files on it!
* Inode on disk: "short", 0 means non-existent, the root dir ino is:
- - Minix FS 1
- - Xenix FS, SystemV FS, Coherent FS 2
+
+ ================================= ==
+ Minix FS 1
+ Xenix FS, SystemV FS, Coherent FS 2
+ ================================= ==
* Maximum number of hard links to a file:
- - Minix FS 250
- - Xenix FS ??
- - SystemV FS ??
- - Coherent FS >=10000
+
+ =========== =========
+ Minix FS 250
+ Xenix FS ??
+ SystemV FS ??
+ Coherent FS >=10000
+ =========== =========
* Free inode management:
- - Minix FS a bitmap
+
+ - Minix FS
+ a bitmap
- Xenix FS, SystemV FS, Coherent FS
There is a cache of a certain number of free inodes in the super-block.
When it is exhausted, new free inodes are found using a linear search.
* Free block management:
- - Minix FS a bitmap
+
+ - Minix FS
+ a bitmap
- Xenix FS, SystemV FS, Coherent FS
Free blocks are organized in a "free list". Maybe a misleading term,
since it is not true that every free block contains a pointer to
0 on Xenix FS and SystemV FS, with a block zeroed out on Coherent FS.
* Super-block location:
- - Minix FS block 1 = bytes 1024..2047
- - Xenix FS block 1 = bytes 1024..2047
- - SystemV FS bytes 512..1023
- - Coherent FS block 1 = bytes 512..1023
+
+ =========== ==========================
+ Minix FS block 1 = bytes 1024..2047
+ Xenix FS block 1 = bytes 1024..2047
+ SystemV FS bytes 512..1023
+ Coherent FS block 1 = bytes 512..1023
+ =========== ==========================
* Super-block layout:
- - Minix FS
+
+ - Minix FS::
+
unsigned short s_ninodes;
unsigned short s_nzones;
unsigned short s_imap_blocks;
unsigned short s_log_zone_size;
unsigned long s_max_size;
unsigned short s_magic;
- - Xenix FS, SystemV FS, Coherent FS
+
+ - Xenix FS, SystemV FS, Coherent FS::
+
unsigned short s_firstdatazone;
unsigned long s_nzones;
unsigned short s_fzone_count;
unsigned short s_interleave_m,s_interleave_n; -- Coherent FS only
char s_fname[6];
char s_fpack[6];
+
then they differ considerably:
- Xenix FS
+
+ Xenix FS::
+
char s_clean;
char s_fill[371];
long s_magic;
long s_type;
- SystemV FS
+
+ SystemV FS::
+
long s_fill[12 or 14];
long s_state;
long s_magic;
long s_type;
- Coherent FS
+
+ Coherent FS::
+
unsigned long s_unique;
+
Note that Coherent FS has no magic.
* Inode layout:
- - Minix FS
+
+ - Minix FS::
+
unsigned short i_mode;
unsigned short i_uid;
unsigned long i_size;
unsigned char i_gid;
unsigned char i_nlinks;
unsigned short i_zone[7+1+1];
- - Xenix FS, SystemV FS, Coherent FS
+
+ - Xenix FS, SystemV FS, Coherent FS::
+
unsigned short i_mode;
unsigned short i_nlink;
unsigned short i_uid;
unsigned long i_mtime;
unsigned long i_ctime;
+
* Regular file data blocks are organized as
- - Minix FS
- 7 direct blocks
- 1 indirect block (pointers to blocks)
- 1 double-indirect block (pointer to pointers to blocks)
- - Xenix FS, SystemV FS, Coherent FS
- 10 direct blocks
- 1 indirect block (pointers to blocks)
- 1 double-indirect block (pointer to pointers to blocks)
- 1 triple-indirect block (pointer to pointers to pointers to blocks)
-* Inode size, inodes per block
- - Minix FS 32 32
- - Xenix FS 64 16
- - SystemV FS 64 16
- - Coherent FS 64 8
+ - Minix FS:
+
+ - 7 direct blocks
+ - 1 indirect block (pointers to blocks)
+ - 1 double-indirect block (pointer to pointers to blocks)
+
+ - Xenix FS, SystemV FS, Coherent FS:
+
+ - 10 direct blocks
+ - 1 indirect block (pointers to blocks)
+ - 1 double-indirect block (pointer to pointers to blocks)
+ - 1 triple-indirect block (pointer to pointers to pointers to blocks)
+
+
+ =========== ========== ================
+ Inode size inodes per block
+ =========== ========== ================
+ Minix FS 32 32
+ Xenix FS 64 16
+ SystemV FS 64 16
+ Coherent FS 64 8
+ =========== ========== ================
* Directory entry on disk
- - Minix FS
+
+ - Minix FS::
+
unsigned short inode;
char name[14/30];
- - Xenix FS, SystemV FS, Coherent FS
+
+ - Xenix FS, SystemV FS, Coherent FS::
+
unsigned short inode;
char name[14];
-* Dir entry size, dir entries per block
- - Minix FS 16/32 64/32
- - Xenix FS 16 64
- - SystemV FS 16 64
- - Coherent FS 16 32
+ =========== ============== =====================
+ Dir entry size dir entries per block
+ =========== ============== =====================
+ Minix FS 16/32 64/32
+ Xenix FS 16 64
+ SystemV FS 16 64
+ Coherent FS 16 32
+ =========== ============== =====================
* How to implement symbolic links such that the host fsck doesn't scream:
+
- Minix FS normal
- Xenix FS kludge: as regular files with chmod 1000
- SystemV FS ??
+.. SPDX-License-Identifier: GPL-2.0
+
+=====
+Tmpfs
+=====
+
Tmpfs is a file system which keeps all files in virtual memory.
you gain swapping and limit checking. Another similar thing is the RAM
disk (/dev/ram*), which simulates a fixed size hard disk in physical
RAM, where you have to create an ordinary filesystem on top. Ramdisks
-cannot swap and you do not have the possibility to resize them.
+cannot swap and you do not have the possibility to resize them.
Since tmpfs lives completely in the page cache and on swap, all tmpfs
pages will be shown as "Shmem" in /proc/meminfo and "Shared" in
1) There is always a kernel internal mount which you will not see at
all. This is used for shared anonymous mappings and SYSV shared
- memory.
+ memory.
This mount does not depend on CONFIG_TMPFS. If CONFIG_TMPFS is not
set, the user visible part of tmpfs is not build. But the internal
2) glibc 2.2 and above expects tmpfs to be mounted at /dev/shm for
POSIX shared memory (shm_open, shm_unlink). Adding the following
- line to /etc/fstab should take care of this:
+ line to /etc/fstab should take care of this::
tmpfs /dev/shm tmpfs defaults 0 0
tmpfs has three mount options for sizing:
-size: The limit of allocated bytes for this tmpfs instance. The
+========= ============================================================
+size The limit of allocated bytes for this tmpfs instance. The
default is half of your physical RAM without swap. If you
oversize your tmpfs instances the machine will deadlock
since the OOM handler will not be able to free that memory.
-nr_blocks: The same as size, but in blocks of PAGE_SIZE.
-nr_inodes: The maximum number of inodes for this instance. The default
+nr_blocks The same as size, but in blocks of PAGE_SIZE.
+nr_inodes The maximum number of inodes for this instance. The default
is half of the number of your physical RAM pages, or (on a
machine with highmem) the number of lowmem RAM pages,
whichever is the lower.
+========= ============================================================
These parameters accept a suffix k, m or g for kilo, mega and giga and
can be changed on remount. The size parameter also accepts a suffix %
all files in that instance (if CONFIG_NUMA is enabled) - which can be
adjusted on the fly via 'mount -o remount ...'
+======================== ==============================================
mpol=default use the process allocation policy
(see set_mempolicy(2))
mpol=prefer:Node prefers to allocate memory from the given Node
mpol=interleave prefers to allocate from each node in turn
mpol=interleave:NodeList allocates from each node of NodeList in turn
mpol=local prefers to allocate memory from the local node
+======================== ==============================================
NodeList format is a comma-separated list of decimal numbers and ranges,
a range being two hyphen-separated decimal numbers, the smallest and
use at file creation time. When a task allocates a file in the file
system, the mount option memory policy will be applied with a NodeList,
if any, modified by the calling task's cpuset constraints
-[See Documentation/admin-guide/cgroup-v1/cpusets.rst] and any optional flags, listed
-below. If the resulting NodeLists is the empty set, the effective memory
-policy for the file will revert to "default" policy.
+[See Documentation/admin-guide/cgroup-v1/cpusets.rst] and any optional flags,
+listed below. If the resulting NodeLists is the empty set, the effective
+memory policy for the file will revert to "default" policy.
NUMA memory allocation policies have optional flags that can be used in
conjunction with their modes. These optional flags can be specified
all available memory allocation policy mode flags and their effect on
memory policy.
+::
+
=static is equivalent to MPOL_F_STATIC_NODES
=relative is equivalent to MPOL_F_RELATIVE_NODES
To specify the initial root directory you can use the following mount
options:
-mode: The permissions as an octal number
-uid: The user id
-gid: The group id
+==== ==================================
+mode The permissions as an octal number
+uid The user id
+gid The group id
+==== ==================================
These options do not have any effect on remount. You can change these
parameters with chmod(1), chown(1) and chgrp(1) on a mounted filesystem.
RAM/SWAP in 10240 inodes and it is only accessible by root.
-Author:
+:Author:
Christoph Rohland <cr@sap.com>, 1.12.01
-Updated:
+:Updated:
Hugh Dickins, 4 June 2007
-Updated:
+:Updated:
KOSAKI Motohiro, 16 Mar 2010
+.. SPDX-License-Identifier: GPL-2.0
+
:orphan:
.. UBIFS Authentication
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Basic on-flash UBIFS entities are called *nodes*. UBIFS knows different types
-of nodes. Eg. data nodes (`struct ubifs_data_node`) which store chunks of file
-contents or inode nodes (`struct ubifs_ino_node`) which represent VFS inodes.
-Almost all types of nodes share a common header (`ubifs_ch`) containing basic
+of nodes. Eg. data nodes (``struct ubifs_data_node``) which store chunks of file
+contents or inode nodes (``struct ubifs_ino_node``) which represent VFS inodes.
+Almost all types of nodes share a common header (``ubifs_ch``) containing basic
information like node type, node length, a sequence number, etc. (see
-`fs/ubifs/ubifs-media.h`in kernel source). Exceptions are entries of the LPT
+``fs/ubifs/ubifs-media.h`` in kernel source). Exceptions are entries of the LPT
and some less important node types like padding nodes which are used to pad
unusable content at the end of LEBs.
+.. SPDX-License-Identifier: GPL-2.0
+
+===============
+UBI File System
+===============
+
Introduction
-=============
+============
UBIFS file-system stands for UBI File System. UBI stands for "Unsorted
Block Images". UBIFS is a flash file system, which means it is designed
(*) == default.
+==================== =======================================================
bulk_read read more in one go to take advantage of flash
media that read faster sequentially
no_bulk_read (*) do not bulk-read
auth_hash_name= The hash algorithm used for authentication. Used for
both hashing and for creating HMACs. Typical values
include "sha256" or "sha512"
+==================== =======================================================
Quick usage instructions
where "X" is UBI device number, "Y" is UBI volume number, and "NAME" is
UBI volume name.
-Mount volume 0 on UBI device 0 to /mnt/ubifs:
-$ mount -t ubifs ubi0_0 /mnt/ubifs
+Mount volume 0 on UBI device 0 to /mnt/ubifs::
+
+ $ mount -t ubifs ubi0_0 /mnt/ubifs
Mount "rootfs" volume of UBI device 0 to /mnt/ubifs ("rootfs" is volume
-name):
-$ mount -t ubifs ubi0:rootfs /mnt/ubifs
+name)::
+
+ $ mount -t ubifs ubi0:rootfs /mnt/ubifs
The following is an example of the kernel boot arguments to attach mtd0
to UBI and mount volume "rootfs":
==========
UBIFS documentation and FAQ/HOWTO at the MTD web site:
-http://www.linux-mtd.infradead.org/doc/ubifs.html
-http://www.linux-mtd.infradead.org/faq/ubifs.html
+
+- http://www.linux-mtd.infradead.org/doc/ubifs.html
+- http://www.linux-mtd.infradead.org/faq/ubifs.html
-*
-* Documentation/filesystems/udf.txt
-*
+.. SPDX-License-Identifier: GPL-2.0
+
+===============
+UDF file system
+===============
If you encounter problems with reading UDF discs using this driver,
please report them according to MAINTAINERS file.
by drive firmware.
-------------------------------------------------------------------------------
+
The following mount options are supported:
+ =========== ======================================
gid= Set the default group.
umask= Set the default umask.
mode= Set the default file permissions.
longad Use long ad's (default)
nostrict Unset strict conformance
iocharset= Set the NLS character set
+ =========== ======================================
The uid= and gid= options need a bit more explaining. They will accept a
decimal numeric value and all inodes on that mount will then appear as
The remaining are for debugging and disaster recovery:
- novrs Skip volume sequence recognition
+ ===== ================================
+ novrs Skip volume sequence recognition
+ ===== ================================
The following expect a offset from 0.
+ ========== =================================================
session= Set the CDROM session (default= last session)
anchor= Override standard anchor location. (default= 256)
lastblock= Set the last block of the filesystem/
+ ========== =================================================
-------------------------------------------------------------------------------
https://github.com/pali/udftools
Documentation on UDF and ECMA 167 is available FREE from:
- http://www.osta.org/
- http://www.ecma-international.org/
+ - http://www.osta.org/
+ - http://www.ecma-international.org/
.. SPDX-License-Identifier: GPL-2.0
+.. _virtiofs_index:
+
===================================================
virtiofs: virtio-fs host<->guest shared file system
===================================================
+.. SPDX-License-Identifier: GPL-2.0
+
+================================================
ZoneFS - Zone filesystem for Zoned block devices
+================================================
Introduction
============
Zoned storage devices belong to a class of storage devices with an address
space that is divided into zones. A zone is a group of consecutive LBAs and all
zones are contiguous (there are no LBA gaps). Zones may have different types.
+
* Conventional zones: there are no access constraints to LBAs belonging to
conventional zones. Any read or write access can be executed, similarly to a
regular block device.
--------------
Several optional features of zonefs can be enabled at format time.
+
* Conventional zone aggregation: ranges of contiguous conventional zones can be
aggregated into a single larger file instead of the default one file per zone.
* File ownership: The owner UID and GID of zone files is by default 0 (root)
Further action taken by zonefs I/O error recovery can be controlled by the user
with the "errors=xxx" mount option. The table below summarizes the result of
zonefs I/O error processing depending on the mount option and on the zone
-conditions.
+conditions::
+--------------+-----------+-----------------------------------------+
| | | Post error state |
+--------------+-----------+-----------------------------------------+
Further notes:
+
* The "errors=remount-ro" mount option is the default behavior of zonefs I/O
error processing if no errors mount option is specified.
* With the "errors=remount-ro" mount option, the change of the file access
zonefs define the "errors=<behavior>" mount option to allow the user to specify
zonefs behavior in response to I/O errors, inode size inconsistencies or zone
condition changes. The defined behaviors are as follow:
+
* remount-ro (default)
* zone-ro
* zone-offline
--------
The following formats a 15TB host-managed SMR HDD with 256 MB zones
-with the conventional zones aggregation feature enabled.
+with the conventional zones aggregation feature enabled::
-# mkzonefs -o aggr_cnv /dev/sdX
-# mount -t zonefs /dev/sdX /mnt
-# ls -l /mnt/
-total 0
-dr-xr-xr-x 2 root root 1 Nov 25 13:23 cnv
-dr-xr-xr-x 2 root root 55356 Nov 25 13:23 seq
+ # mkzonefs -o aggr_cnv /dev/sdX
+ # mount -t zonefs /dev/sdX /mnt
+ # ls -l /mnt/
+ total 0
+ dr-xr-xr-x 2 root root 1 Nov 25 13:23 cnv
+ dr-xr-xr-x 2 root root 55356 Nov 25 13:23 seq
The size of the zone files sub-directories indicate the number of files
existing for each type of zones. In this example, there is only one
conventional zone file (all conventional zones are aggregated under a single
-file).
+file)::
-# ls -l /mnt/cnv
-total 137101312
--rw-r----- 1 root root 140391743488 Nov 25 13:23 0
+ # ls -l /mnt/cnv
+ total 137101312
+ -rw-r----- 1 root root 140391743488 Nov 25 13:23 0
-This aggregated conventional zone file can be used as a regular file.
+This aggregated conventional zone file can be used as a regular file::
-# mkfs.ext4 /mnt/cnv/0
-# mount -o loop /mnt/cnv/0 /data
+ # mkfs.ext4 /mnt/cnv/0
+ # mount -o loop /mnt/cnv/0 /data
The "seq" sub-directory grouping files for sequential write zones has in this
-example 55356 zones.
+example 55356 zones::
-# ls -lv /mnt/seq
-total 14511243264
--rw-r----- 1 root root 0 Nov 25 13:23 0
--rw-r----- 1 root root 0 Nov 25 13:23 1
--rw-r----- 1 root root 0 Nov 25 13:23 2
-...
--rw-r----- 1 root root 0 Nov 25 13:23 55354
--rw-r----- 1 root root 0 Nov 25 13:23 55355
+ # ls -lv /mnt/seq
+ total 14511243264
+ -rw-r----- 1 root root 0 Nov 25 13:23 0
+ -rw-r----- 1 root root 0 Nov 25 13:23 1
+ -rw-r----- 1 root root 0 Nov 25 13:23 2
+ ...
+ -rw-r----- 1 root root 0 Nov 25 13:23 55354
+ -rw-r----- 1 root root 0 Nov 25 13:23 55355
For sequential write zone files, the file size changes as data is appended at
-the end of the file, similarly to any regular file system.
+the end of the file, similarly to any regular file system::
-# dd if=/dev/zero of=/mnt/seq/0 bs=4096 count=1 conv=notrunc oflag=direct
-1+0 records in
-1+0 records out
-4096 bytes (4.1 kB, 4.0 KiB) copied, 0.00044121 s, 9.3 MB/s
+ # dd if=/dev/zero of=/mnt/seq/0 bs=4096 count=1 conv=notrunc oflag=direct
+ 1+0 records in
+ 1+0 records out
+ 4096 bytes (4.1 kB, 4.0 KiB) copied, 0.00044121 s, 9.3 MB/s
-# ls -l /mnt/seq/0
--rw-r----- 1 root root 4096 Nov 25 13:23 /mnt/seq/0
+ # ls -l /mnt/seq/0
+ -rw-r----- 1 root root 4096 Nov 25 13:23 /mnt/seq/0
The written file can be truncated to the zone size, preventing any further
-write operation.
+write operation::
-# truncate -s 268435456 /mnt/seq/0
-# ls -l /mnt/seq/0
--rw-r----- 1 root root 268435456 Nov 25 13:49 /mnt/seq/0
+ # truncate -s 268435456 /mnt/seq/0
+ # ls -l /mnt/seq/0
+ -rw-r----- 1 root root 268435456 Nov 25 13:49 /mnt/seq/0
Truncation to 0 size allows freeing the file zone storage space and restart
-append-writes to the file.
+append-writes to the file::
-# truncate -s 0 /mnt/seq/0
-# ls -l /mnt/seq/0
--rw-r----- 1 root root 0 Nov 25 13:49 /mnt/seq/0
+ # truncate -s 0 /mnt/seq/0
+ # ls -l /mnt/seq/0
+ -rw-r----- 1 root root 0 Nov 25 13:49 /mnt/seq/0
Since files are statically mapped to zones on the disk, the number of blocks of
-a file as reported by stat() and fstat() indicates the size of the file zone.
-
-# stat /mnt/seq/0
- File: /mnt/seq/0
- Size: 0 Blocks: 524288 IO Block: 4096 regular empty file
-Device: 870h/2160d Inode: 50431 Links: 1
-Access: (0640/-rw-r-----) Uid: ( 0/ root) Gid: ( 0/ root)
-Access: 2019-11-25 13:23:57.048971997 +0900
-Modify: 2019-11-25 13:52:25.553805765 +0900
-Change: 2019-11-25 13:52:25.553805765 +0900
- Birth: -
+a file as reported by stat() and fstat() indicates the size of the file zone::
+
+ # stat /mnt/seq/0
+ File: /mnt/seq/0
+ Size: 0 Blocks: 524288 IO Block: 4096 regular empty file
+ Device: 870h/2160d Inode: 50431 Links: 1
+ Access: (0640/-rw-r-----) Uid: ( 0/ root) Gid: ( 0/ root)
+ Access: 2019-11-25 13:23:57.048971997 +0900
+ Modify: 2019-11-25 13:52:25.553805765 +0900
+ Change: 2019-11-25 13:52:25.553805765 +0900
+ Birth: -
The number of blocks of the file ("Blocks") in units of 512B blocks gives the
maximum file size of 524288 * 512 B = 256 MB, corresponding to the device zone
CSR firmware support for DMC
----------------------------
-.. kernel-doc:: drivers/gpu/drm/i915/intel_csr.c
+.. kernel-doc:: drivers/gpu/drm/i915/display/intel_csr.c
:doc: csr support for dmc
-.. kernel-doc:: drivers/gpu/drm/i915/intel_csr.c
+.. kernel-doc:: drivers/gpu/drm/i915/display/intel_csr.c
:internal:
Video BIOS Table (VBT)
usb/index
PCI/index
misc-devices/index
- mic/index
scheduler/index
Architecture-agnostic documentation
apt-get install gcc-4.9-plugin-dev
+Or on Fedora::
+
+ dnf install gcc-plugin-devel
+
Enable a GCC plugin based feature in the kernel config::
CONFIG_GCC_PLUGIN_CYC_COMPLEXITY = y
issues
reproducible-builds
+ gcc-plugins
.. only:: subproject and html
This is the variant of `EXPORT_SYMBOL()` that allows specifying a symbol
namespace. Symbol Namespaces are documented in
-``Documentation/core-api/symbol-namespaces.rst``.
+:doc:`../core-api/symbol-namespaces`
:c:func:`EXPORT_SYMBOL_NS_GPL()`
--------------------------------
This is the variant of `EXPORT_SYMBOL_GPL()` that allows specifying a symbol
namespace. Symbol Namespaces are documented in
-``Documentation/core-api/symbol-namespaces.rst``.
+:doc:`../core-api/symbol-namespaces`
Routines and Conventions
========================
If you have a data structure which is only ever accessed from user
context, then you can use a simple mutex (``include/linux/mutex.h``) to
protect it. This is the most trivial case: you initialize the mutex.
-Then you can call :c:func:`mutex_lock_interruptible()` to grab the
-mutex, and :c:func:`mutex_unlock()` to release it. There is also a
-:c:func:`mutex_lock()`, which should be avoided, because it will
+Then you can call mutex_lock_interruptible() to grab the
+mutex, and mutex_unlock() to release it. There is also a
+mutex_lock(), which should be avoided, because it will
not return if a signal is received.
Example: ``net/netfilter/nf_sockopt.c`` allows registration of new
-:c:func:`setsockopt()` and :c:func:`getsockopt()` calls, with
-:c:func:`nf_register_sockopt()`. Registration and de-registration
+setsockopt() and getsockopt() calls, with
+nf_register_sockopt(). Registration and de-registration
are only done on module load and unload (and boot time, where there is
no concurrency), and the list of registrations is only consulted for an
-unknown :c:func:`setsockopt()` or :c:func:`getsockopt()` system
+unknown setsockopt() or getsockopt() system
call. The ``nf_sockopt_mutex`` is perfect to protect this, especially
since the setsockopt and getsockopt calls may well sleep.
If a softirq shares data with user context, you have two problems.
Firstly, the current user context can be interrupted by a softirq, and
secondly, the critical region could be entered from another CPU. This is
-where :c:func:`spin_lock_bh()` (``include/linux/spinlock.h``) is
+where spin_lock_bh() (``include/linux/spinlock.h``) is
used. It disables softirqs on that CPU, then grabs the lock.
-:c:func:`spin_unlock_bh()` does the reverse. (The '_bh' suffix is
+spin_unlock_bh() does the reverse. (The '_bh' suffix is
a historical reference to "Bottom Halves", the old name for software
interrupts. It should really be called spin_lock_softirq()' in a
perfect world).
-Note that you can also use :c:func:`spin_lock_irq()` or
-:c:func:`spin_lock_irqsave()` here, which stop hardware interrupts
+Note that you can also use spin_lock_irq() or
+spin_lock_irqsave() here, which stop hardware interrupts
as well: see `Hard IRQ Context <#hard-irq-context>`__.
This works perfectly for UP as well: the spin lock vanishes, and this
-macro simply becomes :c:func:`local_bh_disable()`
+macro simply becomes local_bh_disable()
(``include/linux/interrupt.h``), which protects you from the softirq
being run.
~~~~~~~~~~~~~~~~~~~~~~~~~
If another tasklet/timer wants to share data with your tasklet or timer
-, you will both need to use :c:func:`spin_lock()` and
-:c:func:`spin_unlock()` calls. :c:func:`spin_lock_bh()` is
+, you will both need to use spin_lock() and
+spin_unlock() calls. spin_lock_bh() is
unnecessary here, as you are already in a tasklet, and none will be run
on the same CPU.
going so far as to use a softirq, you probably care about scalable
performance enough to justify the extra complexity.
-You'll need to use :c:func:`spin_lock()` and
-:c:func:`spin_unlock()` for shared data.
+You'll need to use spin_lock() and
+spin_unlock() for shared data.
Different Softirqs
~~~~~~~~~~~~~~~~~~
-You'll need to use :c:func:`spin_lock()` and
-:c:func:`spin_unlock()` for shared data, whether it be a timer,
+You'll need to use spin_lock() and
+spin_unlock() for shared data, whether it be a timer,
tasklet, different softirq or the same or another softirq: any of them
could be running on a different CPU.
concerns. Firstly, the softirq processing can be interrupted by a
hardware interrupt, and secondly, the critical region could be entered
by a hardware interrupt on another CPU. This is where
-:c:func:`spin_lock_irq()` is used. It is defined to disable
+spin_lock_irq() is used. It is defined to disable
interrupts on that cpu, then grab the lock.
-:c:func:`spin_unlock_irq()` does the reverse.
+spin_unlock_irq() does the reverse.
-The irq handler does not to use :c:func:`spin_lock_irq()`, because
+The irq handler does not need to use spin_lock_irq(), because
the softirq cannot run while the irq handler is running: it can use
-:c:func:`spin_lock()`, which is slightly faster. The only exception
+spin_lock(), which is slightly faster. The only exception
would be if a different hardware irq handler uses the same lock:
-:c:func:`spin_lock_irq()` will stop that from interrupting us.
+spin_lock_irq() will stop that from interrupting us.
This works perfectly for UP as well: the spin lock vanishes, and this
-macro simply becomes :c:func:`local_irq_disable()`
+macro simply becomes local_irq_disable()
(``include/asm/smp.h``), which protects you from the softirq/tasklet/BH
being run.
-:c:func:`spin_lock_irqsave()` (``include/linux/spinlock.h``) is a
+spin_lock_irqsave() (``include/linux/spinlock.h``) is a
variant which saves whether interrupts were on or off in a flags word,
-which is passed to :c:func:`spin_unlock_irqrestore()`. This means
+which is passed to spin_unlock_irqrestore(). This means
that the same code can be used inside an hard irq handler (where
interrupts are already off) and in softirqs (where the irq disabling is
required).
Note that softirqs (and hence tasklets and timers) are run on return
-from hardware interrupts, so :c:func:`spin_lock_irq()` also stops
-these. In that sense, :c:func:`spin_lock_irqsave()` is the most
+from hardware interrupts, so spin_lock_irq() also stops
+these. In that sense, spin_lock_irqsave() is the most
general and powerful locking function.
Locking Between Two Hard IRQ Handlers
-------------------------------------
It is rare to have to share data between two IRQ handlers, but if you
-do, :c:func:`spin_lock_irqsave()` should be used: it is
+do, spin_lock_irqsave() should be used: it is
architecture-specific whether all interrupts are disabled inside irq
handlers themselves.
(``copy_from_user*(`` or ``kmalloc(x,GFP_KERNEL)``).
- Otherwise (== data can be touched in an interrupt), use
- :c:func:`spin_lock_irqsave()` and
- :c:func:`spin_unlock_irqrestore()`.
+ spin_lock_irqsave() and
+ spin_unlock_irqrestore().
- Avoid holding spinlock for more than 5 lines of code and across any
- function call (except accessors like :c:func:`readb()`).
+ function call (except accessors like readb()).
Table of Minimum Requirements
-----------------------------
shares data with another thread, locking is required).
Remember the advice above: you can always use
-:c:func:`spin_lock_irqsave()`, which is a superset of all other
+spin_lock_irqsave(), which is a superset of all other
spinlock primitives.
============== ============= ============= ========= ========= ========= ========= ======= ======= ============== ==============
lock when some other thread is holding the lock. You should acquire the
lock later if you then need access to the data protected with the lock.
-:c:func:`spin_trylock()` does not spin but returns non-zero if it
+spin_trylock() does not spin but returns non-zero if it
acquires the spinlock on the first try or 0 if not. This function can be
-used in all contexts like :c:func:`spin_lock()`: you must have
+used in all contexts like spin_lock(): you must have
disabled the contexts that might interrupt you and acquire the spin
lock.
-:c:func:`mutex_trylock()` does not suspend your task but returns
+mutex_trylock() does not suspend your task but returns
non-zero if it could lock the mutex on the first try or 0 if not. This
function cannot be safely used in hardware or software interrupt
contexts despite not sleeping.
objects directly.
There is a slight (and common) optimization here: in
-:c:func:`cache_add()` we set up the fields of the object before
+cache_add() we set up the fields of the object before
grabbing the lock. This is safe, as no-one else can access it until we
put it in cache.
Accessing From Interrupt Context
--------------------------------
-Now consider the case where :c:func:`cache_find()` can be called
+Now consider the case where cache_find() can be called
from interrupt context: either a hardware interrupt or a softirq. An
example would be a timer which deletes object from the cache.
return ret;
}
-Note that the :c:func:`spin_lock_irqsave()` will turn off
+Note that the spin_lock_irqsave() will turn off
interrupts if they are on, otherwise does nothing (if we are already in
an interrupt handler), hence these functions are safe to call from any
context.
-Unfortunately, :c:func:`cache_add()` calls :c:func:`kmalloc()`
+Unfortunately, cache_add() calls kmalloc()
with the ``GFP_KERNEL`` flag, which is only legal in user context. I
-have assumed that :c:func:`cache_add()` is still only called in
+have assumed that cache_add() is still only called in
user context, otherwise this should become a parameter to
-:c:func:`cache_add()`.
+cache_add().
Exposing Objects Outside This File
----------------------------------
The second problem is the lifetime problem: if another structure keeps a
pointer to an object, it presumably expects that pointer to remain
valid. Unfortunately, this is only guaranteed while you hold the lock,
-otherwise someone might call :c:func:`cache_delete()` and even
+otherwise someone might call cache_delete() and even
worse, add another object, re-using the same address.
As there is only one lock, you can't hold it forever: no-one else would
We encapsulate the reference counting in the standard 'get' and 'put'
functions. Now we can return the object itself from
-:c:func:`cache_find()` which has the advantage that the user can
-now sleep holding the object (eg. to :c:func:`copy_to_user()` to
+cache_find() which has the advantage that the user can
+now sleep holding the object (eg. to copy_to_user() to
name to userspace).
The other point to note is that I said a reference should be held for
are guaranteed to be seen atomically from all CPUs in the system, so no
lock is required. In this case, it is simpler than using spinlocks,
although for anything non-trivial using spinlocks is clearer. The
-:c:func:`atomic_inc()` and :c:func:`atomic_dec_and_test()`
+atomic_inc() and atomic_dec_and_test()
are used instead of the standard increment and decrement operators, and
the lock is no longer used to protect the reference count itself.
- You can make ``cache_lock`` non-static, and tell people to grab that
lock before changing the name in any object.
-- You can provide a :c:func:`cache_obj_rename()` which grabs this
+- You can provide a cache_obj_rename() which grabs this
lock and changes the name for the caller, and tell everyone to use
that function.
``cache_lock`` rather than the per-object lock: this is because it (like
the :c:type:`struct list_head <list_head>` inside the object)
is logically part of the infrastructure. This way, I don't need to grab
-the lock of every object in :c:func:`__cache_add()` when seeking
+the lock of every object in __cache_add() when seeking
the least popular.
I also decided that the id member is unchangeable, so I don't need to
-grab each object lock in :c:func:`__cache_find()` to examine the
+grab each object lock in __cache_find() to examine the
id: the object lock is only used by a caller who wants to read or write
the name field.
stay-up-five-nights-talk-to-fluffy-code-bunnies kind of problem.
For a slightly more complex case, imagine you have a region shared by a
-softirq and user context. If you use a :c:func:`spin_lock()` call
+softirq and user context. If you use a spin_lock() call
to protect it, it is possible that the user context will be interrupted
by the softirq while it holds the lock, and the softirq will then spin
forever trying to get the same lock.
Sooner or later, this will crash on SMP, because a timer can have just
-gone off before the :c:func:`spin_lock_bh()`, and it will only get
-the lock after we :c:func:`spin_unlock_bh()`, and then try to free
+gone off before the spin_lock_bh(), and it will only get
+the lock after we spin_unlock_bh(), and then try to free
the element (which has already been freed!).
This can be avoided by checking the result of
-:c:func:`del_timer()`: if it returns 1, the timer has been deleted.
+del_timer(): if it returns 1, the timer has been deleted.
If 0, it means (in this case) that it is currently running, so we can
do::
Another common problem is deleting timers which restart themselves (by
-calling :c:func:`add_timer()` at the end of their timer function).
+calling add_timer() at the end of their timer function).
Because this is a fairly common case which is prone to races, you should
-use :c:func:`del_timer_sync()` (``include/linux/timer.h``) to
+use del_timer_sync() (``include/linux/timer.h``) to
handle this case. It returns the number of times the timer had to be
deleted before we finally stopped it from adding itself back in.
list->next = new;
-The :c:func:`wmb()` is a write memory barrier. It ensures that the
+The wmb() is a write memory barrier. It ensures that the
first operation (setting the new element's ``next`` pointer) is complete
and will be seen by all CPUs, before the second operation is (putting
the new element into the list). This is important, since modern
Fortunately, there is a function to do this for standard
:c:type:`struct list_head <list_head>` lists:
-:c:func:`list_add_rcu()` (``include/linux/list.h``).
+list_add_rcu() (``include/linux/list.h``).
Removing an element from the list is even simpler: we replace the
pointer to the old element with a pointer to its successor, and readers
list->next = old->next;
-There is :c:func:`list_del_rcu()` (``include/linux/list.h``) which
+There is list_del_rcu() (``include/linux/list.h``) which
does this (the normal version poisons the old object, which we don't
want).
pointer to start reading the contents of the next element early, but
don't realize that the pre-fetched contents is wrong when the ``next``
pointer changes underneath them. Once again, there is a
-:c:func:`list_for_each_entry_rcu()` (``include/linux/list.h``)
+list_for_each_entry_rcu() (``include/linux/list.h``)
to help you. Of course, writers can just use
-:c:func:`list_for_each_entry()`, since there cannot be two
+list_for_each_entry(), since there cannot be two
simultaneous writers.
Our final dilemma is this: when can we actually destroy the removed
changes, the reader will jump off into garbage and crash. We need to
wait until we know that all the readers who were traversing the list
when we deleted the element are finished. We use
-:c:func:`call_rcu()` to register a callback which will actually
+call_rcu() to register a callback which will actually
destroy the object once all pre-existing readers are finished.
-Alternatively, :c:func:`synchronize_rcu()` may be used to block
+Alternatively, synchronize_rcu() may be used to block
until all pre-existing are finished.
But how does Read Copy Update know when the readers are finished? The
method is this: firstly, the readers always traverse the list inside
-:c:func:`rcu_read_lock()`/:c:func:`rcu_read_unlock()` pairs:
+rcu_read_lock()/rcu_read_unlock() pairs:
these simply disable preemption so the reader won't go to sleep while
reading the list.
}
Note that the reader will alter the popularity member in
-:c:func:`__cache_find()`, and now it doesn't hold a lock. One
+__cache_find(), and now it doesn't hold a lock. One
solution would be to make it an ``atomic_t``, but for this usage, we
don't really care about races: an approximate result is good enough, so
I didn't change it.
-The result is that :c:func:`cache_find()` requires no
+The result is that cache_find() requires no
synchronization with any other functions, so is almost as fast on SMP as
it would be on UP.
Now, because the 'read lock' in RCU is simply disabling preemption, a
caller which always has preemption disabled between calling
-:c:func:`cache_find()` and :c:func:`object_put()` does not
+cache_find() and object_put() does not
need to actually get and put the reference count: we could expose
-:c:func:`__cache_find()` by making it non-static, and such
+__cache_find() by making it non-static, and such
callers could simply call that.
The benefit here is that the reference count is not written to: the
If that was too slow (it's usually not, but if you've got a really big
machine to test on and can show that it is), you could instead use a
counter for each CPU, then none of them need an exclusive lock. See
-:c:func:`DEFINE_PER_CPU()`, :c:func:`get_cpu_var()` and
-:c:func:`put_cpu_var()` (``include/linux/percpu.h``).
+DEFINE_PER_CPU(), get_cpu_var() and
+put_cpu_var() (``include/linux/percpu.h``).
Of particular use for simple per-cpu counters is the ``local_t`` type,
-and the :c:func:`cpu_local_inc()` and related functions, which are
+and the cpu_local_inc() and related functions, which are
more efficient than simple code on some architectures
(``include/asm/local.h``).
enable_irq(irq);
spin_unlock(&lock);
-The :c:func:`disable_irq()` prevents the irq handler from running
+The disable_irq() prevents the irq handler from running
(and waits for it to finish if it's currently running on other CPUs).
The spinlock prevents any other accesses happening at the same time.
-Naturally, this is slower than just a :c:func:`spin_lock_irq()`
+Naturally, this is slower than just a spin_lock_irq()
call, so it only makes sense if this type of access happens extremely
rarely.
- Accesses to userspace:
- - :c:func:`copy_from_user()`
+ - copy_from_user()
- - :c:func:`copy_to_user()`
+ - copy_to_user()
- - :c:func:`get_user()`
+ - get_user()
- - :c:func:`put_user()`
+ - put_user()
-- :c:func:`kmalloc(GFP_KERNEL) <kmalloc>`
+- kmalloc(GP_KERNEL) <kmalloc>`
-- :c:func:`mutex_lock_interruptible()` and
- :c:func:`mutex_lock()`
+- mutex_lock_interruptible() and
+ mutex_lock()
- There is a :c:func:`mutex_trylock()` which does not sleep.
+ There is a mutex_trylock() which does not sleep.
Still, it must not be used inside interrupt context since its
- implementation is not safe for that. :c:func:`mutex_unlock()`
+ implementation is not safe for that. mutex_unlock()
will also never sleep. It cannot be used in interrupt context either
since a mutex must be released by the same task that acquired it.
Some functions are safe to call from any context, or holding almost any
lock.
-- :c:func:`printk()`
+- printk()
-- :c:func:`kfree()`
+- kfree()
-- :c:func:`add_timer()` and :c:func:`del_timer()`
+- add_timer() and del_timer()
Mutex API reference
===================
bh
Bottom Half: for historical reasons, functions with '_bh' in them often
- now refer to any software interrupt, e.g. :c:func:`spin_lock_bh()`
+ now refer to any software interrupt, e.g. spin_lock_bh()
blocks any software interrupt on the current CPU. Bottom halves are
deprecated, and will eventually be replaced by tasklets. Only one bottom
half will be running at any time.
Hardware Interrupt / Hardware IRQ
- Hardware interrupt request. :c:func:`in_irq()` returns true in a
+ Hardware interrupt request. in_irq() returns true in a
hardware interrupt handler.
Interrupt Context
Not user context: processing a hardware irq or software irq. Indicated
- by the :c:func:`in_interrupt()` macro returning true.
+ by the in_interrupt() macro returning true.
SMP
Symmetric Multi-Processor: kernels compiled for multiple-CPU machines.
(``CONFIG_SMP=y``).
Software Interrupt / softirq
- Software interrupt handler. :c:func:`in_irq()` returns false;
- :c:func:`in_softirq()` returns true. Tasklets and softirqs both
+ Software interrupt handler. in_irq() returns false;
+ in_softirq() returns true. Tasklets and softirqs both
fall into the category of 'software interrupts'.
Strictly speaking a softirq is one of up to 32 enumerated software
put needs no lock because nothing tries to get the data without
already holding a pointer.
+In the above example, kref_put() will be called 2 times in both success
+and error paths. This is necessary because the reference count got
+incremented 2 times by kref_init() and kref_get().
+
Note that the "before" in rule 1 is very important. You should never
do something like::
In practice the basic usage as described above is sufficient for most drivers.
-Inheriting Controls
--------------------
+Inheriting Sub-device Controls
+------------------------------
When a sub-device is registered with a V4L2 driver by calling
v4l2_device_register_subdev() and the ctrl_handler fields of both v4l2_subdev
It is recommended not to use this function from inside the control ops.
-Inheriting Controls
--------------------
+Preventing Controls inheritance
+-------------------------------
When one control handler is added to another using v4l2_ctrl_add_handler, then
by default all controls from one are merged to the other. But a subdev might
isl29003
lis3lv02d
max6875
+ mic/index
xilinx_sdfec
A packet loss is detected and recovered by TLP.
-TCP Fast Open
-=============
+TCP Fast Open description
+=========================
TCP Fast Open is a technology which allows data transfer before the
3-way handshake complete. Please refer the `TCP Fast Open wiki`_ for a
general description.
.. contents::
:depth: 3
-Protected Execution Facility
-############################
+Introduction
+############
Protected Execution Facility (PEF) is an architectural change for
POWER 9 that enables Secure Virtual Machines (SVMs). DD2.3 chips
release history looks like this:
====== =================
- 4.11 April 30, 2017
- 4.12 July 2, 2017
- 4.13 September 3, 2017
- 4.14 November 12, 2017
- 4.15 January 28, 2018
- 4.16 April 1, 2018
+ 5.0 March 3, 2019
+ 5.1 May 5, 2019
+ 5.2 July 7, 2019
+ 5.3 September 15, 2019
+ 5.4 November 24, 2019
+ 5.5 January 6, 2020
====== =================
-Every 4.x release is a major kernel release with new features, internal
-API changes, and more. A typical 4.x release contain about 13,000
-changesets with changes to several hundred thousand lines of code. 4.x is
-thus the leading edge of Linux kernel development; the kernel uses a
+Every 5.x release is a major kernel release with new features, internal
+API changes, and more. A typical release can contain about 13,000
+changesets with changes to several hundred thousand lines of code. 5.x is
+the leading edge of Linux kernel development; the kernel uses a
rolling development model which is continually integrating major changes.
A relatively straightforward discipline is followed with regard to the
The merge window lasts for approximately two weeks. At the end of this
time, Linus Torvalds will declare that the window is closed and release the
-first of the "rc" kernels. For the kernel which is destined to be 2.6.40,
+first of the "rc" kernels. For the kernel which is destined to be 5.6,
for example, the release which happens at the end of the merge window will
-be called 2.6.40-rc1. The -rc1 release is the signal that the time to
+be called 5.6-rc1. The -rc1 release is the signal that the time to
merge new features has passed, and that the time to stabilize the next
kernel has begun.
As fixes make their way into the mainline, the patch rate will slow over
time. Linus releases new -rc kernels about once a week; a normal series
will get up to somewhere between -rc6 and -rc9 before the kernel is
-considered to be sufficiently stable and the final 2.6.x release is made.
+considered to be sufficiently stable and the final release is made.
At that point the whole process starts over again.
-As an example, here is how the 4.16 development cycle went (all dates in
-2018):
+As an example, here is how the 5.4 development cycle went (all dates in
+2019):
============== ===============================
- January 28 4.15 stable release
- February 11 4.16-rc1, merge window closes
- February 18 4.16-rc2
- February 25 4.16-rc3
- March 4 4.16-rc4
- March 11 4.16-rc5
- March 18 4.16-rc6
- March 25 4.16-rc7
- April 1 4.16 stable release
+ September 15 5.3 stable release
+ September 30 5.4-rc1, merge window closes
+ October 6 5.4-rc2
+ October 13 5.4-rc3
+ October 20 5.4-rc4
+ October 27 5.4-rc5
+ November 3 5.4-rc6
+ November 10 5.4-rc7
+ November 17 5.4-rc8
+ November 24 5.4 stable release
============== ===============================
How do the developers decide when to close the development cycle and create
achieve; there are just too many variables in a project of this size.
There comes a point where delaying the final release just makes the problem
worse; the pile of changes waiting for the next merge window will grow
-larger, creating even more regressions the next time around. So most 4.x
+larger, creating even more regressions the next time around. So most 5.x
kernels go out with a handful of known regressions though, hopefully, none
of them are serious.
Once a stable release is made, its ongoing maintenance is passed off to the
-"stable team," currently consisting of Greg Kroah-Hartman. The stable team
-will release occasional updates to the stable release using the 4.x.y
-numbering scheme. To be considered for an update release, a patch must (1)
-fix a significant bug, and (2) already be merged into the mainline for the
-next development kernel. Kernels will typically receive stable updates for
-a little more than one development cycle past their initial release. So,
-for example, the 4.13 kernel's history looked like:
+"stable team," currently Greg Kroah-Hartman. The stable team will release
+occasional updates to the stable release using the 5.x.y numbering scheme.
+To be considered for an update release, a patch must (1) fix a significant
+bug, and (2) already be merged into the mainline for the next development
+kernel. Kernels will typically receive stable updates for a little more
+than one development cycle past their initial release. So, for example, the
+5.2 kernel's history looked like this (all dates in 2019):
============== ===============================
- September 3 4.13 stable release
- September 13 4.13.1
- September 20 4.13.2
- September 27 4.13.3
- October 5 4.13.4
- October 12 4.13.5
+ September 15 5.2 stable release
+ July 14 5.2.1
+ July 21 5.2.2
+ July 26 5.2.3
+ July 28 5.2.4
+ July 31 5.2.5
... ...
- November 24 4.13.16
+ October 11 5.2.21
============== ===============================
-4.13.16 was the final stable update of the 4.13 release.
+5.2.21 was the final stable update of the 5.2 release.
Some kernels are designated "long term" kernels; they will receive support
for a longer period. As of this writing, the current long term kernels
and their maintainers are:
- ====== ====================== ==============================
- 3.16 Ben Hutchings (very long-term stable kernel)
- 4.1 Sasha Levin
- 4.4 Greg Kroah-Hartman (very long-term stable kernel)
- 4.9 Greg Kroah-Hartman
- 4.14 Greg Kroah-Hartman
- ====== ====================== ==============================
+ ====== ================================ =======================
+ 3.16 Ben Hutchings (very long-term kernel)
+ 4.4 Greg Kroah-Hartman & Sasha Levin (very long-term kernel)
+ 4.9 Greg Kroah-Hartman & Sasha Levin
+ 4.14 Greg Kroah-Hartman & Sasha Levin
+ 4.19 Greg Kroah-Hartman & Sasha Levin
+ 5.4 Greg Kroah-Hartman & Sasha Levin
+ ====== ================================ =======================
The selection of a kernel for long-term support is purely a matter of a
maintainer having the need and the time to maintain that release. There
-------------------------------
There is exactly one person who can merge patches into the mainline kernel
-repository: Linus Torvalds. But, of the over 9,500 patches which went
-into the 2.6.38 kernel, only 112 (around 1.3%) were directly chosen by Linus
-himself. The kernel project has long since grown to a size where no single
-developer could possibly inspect and select every patch unassisted. The
-way the kernel developers have addressed this growth is through the use of
-a lieutenant system built around a chain of trust.
+repository: Linus Torvalds. But, for example, of the over 9,500 patches
+which went into the 2.6.38 kernel, only 112 (around 1.3%) were directly
+chosen by Linus himself. The kernel project has long since grown to a size
+where no single developer could possibly inspect and select every patch
+unassisted. The way the kernel developers have addressed this growth is
+through the use of a lieutenant system built around a chain of trust.
The kernel code base is logically broken down into a set of subsystems:
networking, specific architecture support, memory management, video
4) Naming
---------
-C is a Spartan language, and so should your naming be. Unlike Modula-2
-and Pascal programmers, C programmers do not use cute names like
-ThisVariableIsATemporaryCounter. A C programmer would call that
+C is a Spartan language, and your naming conventions should follow suit.
+Unlike Modula-2 and Pascal programmers, C programmers do not use cute
+names like ThisVariableIsATemporaryCounter. A C programmer would call that
variable ``tmp``, which is much easier to write, and not the least more
difficult to understand.
``count_active_users()`` or similar, you should **not** call it ``cntusr()``.
Encoding the type of a function into the name (so-called Hungarian
-notation) is brain damaged - the compiler knows the types anyway and can
-check those, and it only confuses the programmer. No wonder MicroSoft
-makes buggy programs.
+notation) is asinine - the compiler knows the types anyway and can check
+those, and it only confuses the programmer. No wonder Microsoft makes buggy
+programs.
LOCAL variable names should be short, and to the point. If you have
some random integer loop counter, it should probably be called ``i``.
----------------------------
Kernel developers like to be seen as literate. Do mind the spelling
-of kernel messages to make a good impression. Do not use crippled
-words like ``dont``; use ``do not`` or ``don't`` instead. Make the messages
-concise, clear, and unambiguous.
+of kernel messages to make a good impression. Do not use incorrect
+contractions like ``dont``; use ``do not`` or ``don't`` instead. Make the
+messages concise, clear, and unambiguous.
Kernel messages do not have to be terminated with a period.
be fully removed from the kernel, or added to this file to discourage
others from using them in the future.
+BUG() and BUG_ON()
+------------------
+Use WARN() and WARN_ON() instead, and handle the "impossible"
+error condition as gracefully as possible. While the BUG()-family
+of APIs were originally designed to act as an "impossible situation"
+assert and to kill a kernel thread "safely", they turn out to just be
+too risky. (e.g. "In what order do locks need to be released? Have
+various states been restored?") Very commonly, using BUG() will
+destabilize a system or entirely break it, which makes it impossible
+to debug or even get viable crash reports. Linus has `very strong
+<https://lore.kernel.org/lkml/CA+55aFy6jNLsywVYdGp83AMrXBo_P-pkjkphPGrO=82SPKCpLQ@mail.gmail.com/>`_
+feelings `about this
+<https://lore.kernel.org/lkml/CAHk-=whDHsbK3HTOpTF=ue_o04onRwTEaK_ZoJp_fjbqq4+=Jw@mail.gmail.com/>`_.
+
+Note that the WARN()-family should only be used for "expected to
+be unreachable" situations. If you want to warn about "reachable
+but undesirable" situations, please use the pr_warn()-family of
+functions. System owners may have set the *panic_on_warn* sysctl,
+to make sure their systems do not continue running in the face of
+"unreachable" conditions. (For example, see commits like `this one
+<https://git.kernel.org/linus/d4689846881d160a4d12a514e991a740bcb5d65a>`_.)
+
open-coded arithmetic in allocator arguments
--------------------------------------------
Dynamic size calculations (especially multiplication) should not be
header = kzalloc(struct_size(header, item, count), GFP_KERNEL);
-See :c:func:`array_size`, :c:func:`array3_size`, and :c:func:`struct_size`,
-for more details as well as the related :c:func:`check_add_overflow` and
-:c:func:`check_mul_overflow` family of functions.
+See array_size(), array3_size(), and struct_size(),
+for more details as well as the related check_add_overflow() and
+check_mul_overflow() family of functions.
simple_strtol(), simple_strtoll(), simple_strtoul(), simple_strtoull()
----------------------------------------------------------------------
-The :c:func:`simple_strtol`, :c:func:`simple_strtoll`,
-:c:func:`simple_strtoul`, and :c:func:`simple_strtoull` functions
+The simple_strtol(), simple_strtoll(),
+simple_strtoul(), and simple_strtoull() functions
explicitly ignore overflows, which may lead to unexpected results
-in callers. The respective :c:func:`kstrtol`, :c:func:`kstrtoll`,
-:c:func:`kstrtoul`, and :c:func:`kstrtoull` functions tend to be the
+in callers. The respective kstrtol(), kstrtoll(),
+kstrtoul(), and kstrtoull() functions tend to be the
correct replacements, though note that those require the string to be
NUL or newline terminated.
strcpy()
--------
-:c:func:`strcpy` performs no bounds checking on the destination
+strcpy() performs no bounds checking on the destination
buffer. This could result in linear overflows beyond the
end of the buffer, leading to all kinds of misbehaviors. While
`CONFIG_FORTIFY_SOURCE=y` and various compiler flags help reduce the
risk of using this function, there is no good reason to add new uses of
-this function. The safe replacement is :c:func:`strscpy`.
+this function. The safe replacement is strscpy().
strncpy() on NUL-terminated strings
-----------------------------------
-Use of :c:func:`strncpy` does not guarantee that the destination buffer
+Use of strncpy() does not guarantee that the destination buffer
will be NUL terminated. This can lead to various linear read overflows
and other misbehavior due to the missing termination. It also NUL-pads the
destination buffer if the source contents are shorter than the destination
buffer size, which may be a needless performance penalty for callers using
-only NUL-terminated strings. The safe replacement is :c:func:`strscpy`.
-(Users of :c:func:`strscpy` still needing NUL-padding will need an
-explicit :c:func:`memset` added.)
+only NUL-terminated strings. The safe replacement is strscpy().
+(Users of strscpy() still needing NUL-padding should instead
+use strscpy_pad().)
-If a caller is using non-NUL-terminated strings, :c:func:`strncpy()` can
+If a caller is using non-NUL-terminated strings, strncpy()() can
still be used, but destinations should be marked with the `__nonstring
<https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html>`_
attribute to avoid future compiler warnings.
strlcpy()
---------
-:c:func:`strlcpy` reads the entire source buffer first, possibly exceeding
+strlcpy() reads the entire source buffer first, possibly exceeding
the given limit of bytes to copy. This is inefficient and can lead to
linear read overflows if a source string is not NUL-terminated. The
-safe replacement is :c:func:`strscpy`.
+safe replacement is strscpy().
+
+%p format specifier
+-------------------
+Traditionally, using "%p" in format strings would lead to regular address
+exposure flaws in dmesg, proc, sysfs, etc. Instead of leaving these to
+be exploitable, all "%p" uses in the kernel are being printed as a hashed
+value, rendering them unusable for addressing. New uses of "%p" should not
+be added to the kernel. For text addresses, using "%pS" is likely better,
+as it produces the more useful symbol name instead. For nearly everything
+else, just do not add "%p" at all.
+
+Paraphrasing Linus's current `guidance <https://lore.kernel.org/lkml/CA+55aFwQEd_d40g4mUCSsVRZzrFPUJt74vc6PPpb675hYNXcKw@mail.gmail.com/>`_:
+
+- If the hashed "%p" value is pointless, ask yourself whether the pointer
+ itself is important. Maybe it should be removed entirely?
+- If you really think the true pointer value is important, why is some
+ system state or user privilege level considered "special"? If you think
+ you can justify it (in comments and commit log) well enough to stand
+ up to Linus's scrutiny, maybe you can use "%px", along with making sure
+ you have sensible permissions.
+
+And finally, know that a toggle for "%p" hashing will `not be accepted <https://lore.kernel.org/lkml/CA+55aFwieC1-nAs+NFq9RTwaR8ef9hWa4MjNBWL41F-8wM49eA@mail.gmail.com/>`_.
Variable Length Arrays (VLAs)
-----------------------------
Implicit switch case fall-through
---------------------------------
-The C language allows switch cases to "fall-through" when a "break" statement
-is missing at the end of a case. This, however, introduces ambiguity in the
-code, as it's not always clear if the missing break is intentional or a bug.
+The C language allows switch cases to fall through to the next case
+when a "break" statement is missing at the end of a case. This, however,
+introduces ambiguity in the code, as it's not always clear if the missing
+break is intentional or a bug. For example, it's not obvious just from
+looking at the code if `STATE_ONE` is intentionally designed to fall
+through into `STATE_TWO`::
+
+ switch (value) {
+ case STATE_ONE:
+ do_something();
+ case STATE_TWO:
+ do_other();
+ break;
+ default:
+ WARN("unknown state");
+ }
As there have been a long list of flaws `due to missing "break" statements
<https://cwe.mitre.org/data/definitions/484.html>`_, we no longer allow
-"implicit fall-through".
-
-In order to identify intentional fall-through cases, we have adopted a
-pseudo-keyword macro 'fallthrough' which expands to gcc's extension
-__attribute__((__fallthrough__)). `Statement Attributes
-<https://gcc.gnu.org/onlinedocs/gcc/Statement-Attributes.html>`_
-
-When the C17/C18 [[fallthrough]] syntax is more commonly supported by
+implicit fall-through. In order to identify intentional fall-through
+cases, we have adopted a pseudo-keyword macro "fallthrough" which
+expands to gcc's extension `__attribute__((__fallthrough__))
+<https://gcc.gnu.org/onlinedocs/gcc/Statement-Attributes.html>`_.
+(When the C17/C18 `[[fallthrough]]` syntax is more commonly supported by
C compilers, static analyzers, and IDEs, we can switch to using that syntax
-for the macro pseudo-keyword.
+for the macro pseudo-keyword.)
All switch/case blocks must end in one of:
- break;
- fallthrough;
- continue;
- goto <label>;
- return [expression];
+* break;
+* fallthrough;
+* continue;
+* goto <label>;
+* return [expression];
The Mutt docs have lots more information:
- http://dev.mutt.org/trac/wiki/UseCases/Gmail
+ https://gitlab.com/muttmua/mutt/-/wikis/UseCases/Gmail
- http://dev.mutt.org/doc/manual.html
+ http://www.mutt.org/doc/manual/
Pine (TUI)
**********
Mainline tree
~~~~~~~~~~~~~
-Mainline tree are maintained by Linus Torvalds, and can be found at
+The mainline tree is maintained by Linus Torvalds, and can be found at
https://kernel.org or in the repo. Its development process is as follows:
- - As soon as a new kernel is released a two weeks window is open,
+ - As soon as a new kernel is released a two week window is open,
during this period of time maintainers can submit big diffs to
Linus, usually the patches that have already been included in the
linux-next for a few weeks. The preferred way to submit big changes
Kernels with 3-part versions are -stable kernels. They contain
relatively small and critical fixes for security problems or significant
-regressions discovered in a given major mainline release, with the first
-2-part of version number are the same correspondingly.
+regressions discovered in a given major mainline release. Each release
+in a major stable series increments the third part of the version
+number, keeping the first two parts the same.
This is the recommended branch for users who want the most recent stable
kernel and are not interested in helping test development/experimental
One of the best ways to put into practice your hacking skills is by fixing
bugs reported by other people. Not only you will help to make the kernel
-more stable, you'll learn to fix real world problems and you will improve
-your skills, and other developers will be aware of your presence. Fixing
-bugs is one of the best ways to get merits among other developers, because
-not many people like wasting time fixing other people's bugs.
+more stable, but you'll also learn to fix real world problems and you will
+improve your skills, and other developers will be aware of your presence.
+Fixing bugs is one of the best ways to get merits among other developers,
+because not many people like wasting time fixing other people's bugs.
To work in the already reported bug reports, go to https://bugzilla.kernel.org.
:URL: http://www.linuxjournal.com/article.php?sid=2391
:Date: 1997
:Keywords: RAID, MD driver.
- :Description: Linux Journal Kernel Korner article. Here is its
+ :Description: Linux Journal Kernel Korner article.
:Abstract: *A description of the implementation of the RAID-1,
RAID-4 and RAID-5 personalities of the MD device driver in the
Linux kernel, providing users with high performance and reliable,
:Date: 1996
:Keywords: device driver, module, loading/unloading modules,
allocating resources.
- :Description: Linux Journal Kernel Korner article. Here is its
+ :Description: Linux Journal Kernel Korner article.
:Abstract: *This is the first of a series of four articles
co-authored by Alessandro Rubini and Georg Zezchwitz which present
a practical approach to writing Linux device drivers as kernel
:Keywords: character driver, init_module, clean_up module,
autodetection, mayor number, minor number, file operations,
open(), close().
- :Description: Linux Journal Kernel Korner article. Here is its
+ :Description: Linux Journal Kernel Korner article.
:Abstract: *This article, the second of four, introduces part of
the actual code to create custom module implementing a character
device driver. It describes the code for module initialization and
:Date: 1996
:Keywords: read(), write(), select(), ioctl(), blocking/non
blocking mode, interrupt handler.
- :Description: Linux Journal Kernel Korner article. Here is its
+ :Description: Linux Journal Kernel Korner article.
:Abstract: *This article, the third of four on writing character
device drivers, introduces concepts of reading, writing, and using
ioctl-calls*.
:URL: http://www.linuxjournal.com/article.php?sid=1222
:Date: 1996
:Keywords: interrupts, irqs, DMA, bottom halves, task queues.
- :Description: Linux Journal Kernel Korner article. Here is its
+ :Description: Linux Journal Kernel Korner article.
:Abstract: *This is the fourth in a series of articles about
writing character device drivers as loadable kernel modules. This
month, we further investigate the field of interrupt handling.
out of it.
Then make the developer who really screwed up (if you can find them) know
-**in_private** that they screwed up. Not just so they can avoid it in the
+**in private** that they screwed up. Not just so they can avoid it in the
future, but so that they know they owe you one. And, perhaps even more
importantly, they're also likely the person who can fix it. Because, let's
face it, it sure ain't you.
scsi_host_alloc - return a new scsi_host instance whose refcount==1
scsi_host_get - increments Scsi_Host instance's refcount
scsi_host_put - decrements Scsi_Host instance's refcount (free if 0)
- scsi_partsize - parse partition table into cylinders, heads + sectors
scsi_register - create and register a scsi host adapter instance.
scsi_remove_device - detach and remove a SCSI device
scsi_remove_host - detach and remove all SCSI devices owned by host
/**
- * scsi_partsize - parse partition table into cylinders, heads + sectors
- * @buf: pointer to partition table
- * @capacity: size of (total) disk in 512 byte sectors
- * @cyls: outputs number of cylinders calculated via this pointer
- * @hds: outputs number of heads calculated via this pointer
- * @secs: outputs number of sectors calculated via this pointer
- *
- * Returns 0 on success, -1 on failure
- *
- * Might block: no
- *
- * Notes: Caller owns memory returned (free with kfree() )
- *
- * Defined in: drivers/scsi/scsicam.c
- **/
-int scsi_partsize(unsigned char *buf, unsigned long capacity,
- unsigned int *cyls, unsigned int *hds, unsigned int *secs)
-
-
-/**
* scsi_register - create and register a scsi host adapter instance.
* @sht: pointer to scsi host template
* @privsize: extra bytes to allocate in hostdata array (which is the
transmitted out of the kernel. This is only remotely useful over `jhash` as a
means of mitigating hashtable flooding denial of service attacks.
-Generating a key
-================
+Generating a HalfSipHash key
+============================
Keys should always be generated from a cryptographically secure source of
random numbers, either using get_random_bytes or get_random_once:
If you're not deriving your key from here, you're doing it wrong.
-Using the functions
-===================
+Using the HalfSipHash functions
+===============================
There are two variants of the function, one that takes a list of integers, and
one that takes a buffer::
.. Contents:
- 1) TCM Userspace Design
+ 1) Design
a) Background
b) Benefits
c) Design constraints
3) A final note
-TCM Userspace Design
-====================
+Design
+======
TCM is another name for LIO, an in-kernel iSCSI target (server).
Existing TCM targets run in the kernel. TCMU (TCM in Userspace)
differences and the implementation isn't currently tied to it in any
way, so beware about making generalizations between the two.
-Note: Writing into trace_marker (See Documentation/trace/ftrace.rst)
+.. Note::
+ Writing into trace_marker (See Documentation/trace/ftrace.rst)
can also enable triggers that are written into
/sys/kernel/tracing/events/ftrace/print/trigger
In this method, the name of the event to create and an array defining
the fields is supplied to synth_event_create(). If successful, a
synthetic event with that name and fields will exist following that
-call. For example, to create a new "schedtest" synthetic event:
+call. For example, to create a new "schedtest" synthetic event::
ret = synth_event_create("schedtest", sched_fields,
ARRAY_SIZE(sched_fields), THIS_MODULE);
The sched_fields param in this example points to an array of struct
synth_field_desc, each of which describes an event field by type and
-name:
+name::
static struct synth_field_desc sched_fields[] = {
{ .type = "pid_t", .name = "next_pid_field" },
initialize a dynevent_cmd object using synth_event_cmd_init().
For example, to create a new "schedtest" synthetic event with two
-fields:
+fields::
struct dynevent_cmd cmd;
char *buf;
"u64", "ts_ns");
Alternatively, using an array of struct synth_field_desc fields
-containing the same information:
+containing the same information::
ret = synth_event_gen_cmd_array_start(&cmd, "schedtest", THIS_MODULE,
fields, n_fields);
populated with more fields. Fields are added one by one using
synth_event_add_field(), supplying the dynevent_cmd object, a field
type, and a field name. For example, to add a new int field named
-"intfield", the following call should be made:
+"intfield", the following call should be made::
ret = synth_event_add_field(&cmd, "int", "intfield");
A group of fields can also be added all at once using an array of
synth_field_desc with add_synth_fields(). For example, this would add
-just the first four sched_fields:
+just the first four sched_fields::
ret = synth_event_add_fields(&cmd, sched_fields, 4);
also automatically append a ';' to the string.
Once all the fields have been added, the event should be finalized and
-registered by calling the synth_event_gen_cmd_end() function:
+registered by calling the synth_event_gen_cmd_end() function::
ret = synth_event_gen_cmd_end(&cmd);
synthetic event field, and the number of values being passed.
So, to trace an event corresponding to the synthetic event definition
-above, code like the following could be used:
+above, code like the following could be used::
ret = synth_event_trace(create_synth_test, 7, /* number of values */
444, /* next_pid_field */
event field.
To trace an event corresponding to the synthetic event definition
-above, code like the following could be used:
+above, code like the following could be used::
u64 vals[7];
is needed. The trace_get_event_file() function can be used to get
it - it will find the file in the given trace instance (in this case
NULL since the top trace array is being used) while at the same time
-preventing the instance containing it from going away:
+preventing the instance containing it from going away::
schedtest_event_file = trace_get_event_file(NULL, "synthetic",
"schedtest");
can be used (which is not specific to synthetic events, so does need
the "synthetic" system name to be specified explicitly).
-To enable the event, pass 'true' to it:
+To enable the event, pass 'true' to it::
trace_array_set_clr_event(schedtest_event_file->tr,
"synthetic", "schedtest", true);
-To disable it pass false:
+To disable it pass false::
trace_array_set_clr_event(schedtest_event_file->tr,
"synthetic", "schedtest", false);
Finally, synth_event_trace_array() can be used to actually trace the
-event, which should be visible in the trace buffer afterwards:
+event, which should be visible in the trace buffer afterwards::
ret = synth_event_trace_array(schedtest_event_file, vals,
ARRAY_SIZE(vals));
To remove the synthetic event, the event should be disabled, and the
-trace instance should be 'put' back using trace_put_event_file():
+trace instance should be 'put' back using trace_put_event_file()::
trace_array_set_clr_event(schedtest_event_file->tr,
"synthetic", "schedtest", false);
trace_put_event_file(schedtest_event_file);
If those have been successful, synth_event_delete() can be called to
-remove the event:
+remove the event::
ret = synth_event_delete("schedtest");
To trace a synthetic using the piecewise method described above, the
synth_event_trace_start() function is used to 'open' the synthetic
-event trace:
+event trace::
struct synth_trace_state trace_state;
field is set, the 'cursor' points to the next field, which will be set
by the subsequent call, continuing until all the fields have been set
in order. The same sequence of calls as in the above examples using
-this method would be (without error-handling code):
+this method would be (without error-handling code)::
/* next_pid_field */
ret = synth_event_add_next_val(777, &trace_state);
the synth_event_trace_start(), along with the field name of the field
to set and the value to set it to. The same sequence of calls as in
the above examples using this method would be (without error-handling
-code):
+code)::
ret = synth_event_add_val("next_pid_field", 777, &trace_state);
ret = synth_event_add_val("next_comm_field", (u64)"silly putty",
Finally, the event won't be actually traced until it's 'closed',
which is done using synth_event_trace_end(), which takes only the
-struct synth_trace_state object used in the previous calls:
+struct synth_trace_state object used in the previous calls::
ret = synth_event_trace_end(&trace_state);
should create and initialize a dynevent_cmd object using
kprobe_event_cmd_init().
-For example, to create a new "schedtest" kprobe event with two fields:
+For example, to create a new "schedtest" kprobe event with two fields::
struct dynevent_cmd cmd;
char *buf;
populated with more fields. Fields can be added using
kprobe_event_add_fields(), supplying the dynevent_cmd object along
with a variable arg list of probe fields. For example, to add a
-couple additional fields, the following call could be made:
+couple additional fields, the following call could be made::
ret = kprobe_event_add_fields(&cmd, "flags=%cx", "mode=+4($stack)");
Once all the fields have been added, the event should be finalized and
registered by calling the kprobe_event_gen_cmd_end() or
kretprobe_event_gen_cmd_end() functions, depending on whether a kprobe
-or kretprobe command was started:
+or kretprobe command was started::
ret = kprobe_event_gen_cmd_end(&cmd);
-or
+or::
ret = kretprobe_event_gen_cmd_end(&cmd);
Similarly, a kretprobe event can be created using
kretprobe_event_gen_cmd_start() with a probe name and location and
-additional params such as $retval:
+additional params such as $retval::
ret = kretprobe_event_gen_cmd_start(&cmd, "gen_kretprobe_test",
"do_sys_open", "$retval");
Similar to the synthetic event case, code like the following can be
-used to enable the newly created kprobe event:
+used to enable the newly created kprobe event::
gen_kprobe_test = trace_get_event_file(NULL, "kprobes", "gen_kprobe_test");
"kprobes", "gen_kprobe_test", true);
Finally, also similar to synthetic events, the following code can be
-used to give the kprobe event file back and delete the event:
+used to give the kprobe event file back and delete the event::
trace_put_event_file(gen_kprobe_test);
The first step in building a new command string is to create and
initialize an instance of a dynevent_cmd. Here, for instance, we
-create a dynevent_cmd on the stack and initialize it:
+create a dynevent_cmd on the stack and initialize it::
struct dynevent_cmd cmd;
char *buf;
To add a single argument, define and initialize a struct dynevent_arg
or struct dynevent_arg_pair object. Here's an example of the simplest
possible arg addition, which is simply to append the given string as
-a whitespace-separated argument to the command:
+a whitespace-separated argument to the command::
struct dynevent_arg arg;
Here's another more complicated example using an 'arg pair', which is
used to create an argument that consists of a couple components added
together as a unit, for example, a 'type field_name;' arg or a simple
-expression arg e.g. 'flags=%cx':
+expression arg e.g. 'flags=%cx'::
struct dynevent_arg_pair arg_pair;
(until its length surpasses cmd->maxlen). When all the arguments have
been added and the command string is complete, the only thing left to
do is run the command, which happens by simply calling
-dynevent_create():
+dynevent_create()::
ret = dynevent_create(&cmd);
.. include:: ../disclaimer-ita.rst
-:Original: :ref:`Documentation/process/stable-kernel-rules.rst <stable_kernel_rules>`
+:Original: :ref:`Documentation/networking/netdev-FAQ.rst <netdev-FAQ>`
.. _it_netdev-FAQ:
Linguaggio di programmazione
============================
-Il kernel è scritto nel linguaggio di programmazione C [c-language]_.
-Più precisamente, il kernel viene compilato con ``gcc`` [gcc]_ usando
-l'opzione ``-std=gnu89`` [gcc-c-dialect-options]_: il dialetto GNU
+Il kernel è scritto nel linguaggio di programmazione C [it-c-language]_.
+Più precisamente, il kernel viene compilato con ``gcc`` [it-gcc]_ usando
+l'opzione ``-std=gnu89`` [it-gcc-c-dialect-options]_: il dialetto GNU
dello standard ISO C90 (con l'aggiunta di alcune funzionalità da C99)
-Questo dialetto contiene diverse estensioni al linguaggio [gnu-extensions]_,
+Questo dialetto contiene diverse estensioni al linguaggio [it-gnu-extensions]_,
e molte di queste vengono usate sistematicamente dal kernel.
Il kernel offre un certo livello di supporto per la compilazione con ``clang``
-[clang]_ e ``icc`` [icc]_ su diverse architetture, tuttavia in questo momento
+[it-clang]_ e ``icc`` [it-icc]_ su diverse architetture, tuttavia in questo momento
il supporto non è completo e richiede delle patch aggiuntive.
Attributi
---------
Una delle estensioni più comuni e usate nel kernel sono gli attributi
-[gcc-attribute-syntax]_. Gli attributi permettono di aggiungere una semantica,
+[it-gcc-attribute-syntax]_. Gli attributi permettono di aggiungere una semantica,
definita dell'implementazione, alle entità del linguaggio (come le variabili,
le funzioni o i tipi) senza dover fare importanti modifiche sintattiche al
-linguaggio stesso (come l'aggiunta di nuove parole chiave) [n2049]_.
+linguaggio stesso (come l'aggiunta di nuove parole chiave) [it-n2049]_.
In alcuni casi, gli attributi sono opzionali (ovvero un compilatore che non
dovesse supportarli dovrebbe produrre comunque codice corretto, anche se
Per maggiori informazioni consultate il file d'intestazione
``include/linux/compiler_attributes.h``.
-.. [c-language] http://www.open-std.org/jtc1/sc22/wg14/www/standards
-.. [gcc] https://gcc.gnu.org
-.. [clang] https://clang.llvm.org
-.. [icc] https://software.intel.com/en-us/c-compilers
-.. [gcc-c-dialect-options] https://gcc.gnu.org/onlinedocs/gcc/C-Dialect-Options.html
-.. [gnu-extensions] https://gcc.gnu.org/onlinedocs/gcc/C-Extensions.html
-.. [gcc-attribute-syntax] https://gcc.gnu.org/onlinedocs/gcc/Attribute-Syntax.html
-.. [n2049] http://www.open-std.org/jtc1/sc22/wg14/www/docs/n2049.pdf
+.. [it-c-language] http://www.open-std.org/jtc1/sc22/wg14/www/standards
+.. [it-gcc] https://gcc.gnu.org
+.. [it-clang] https://clang.llvm.org
+.. [it-icc] https://software.intel.com/en-us/c-compilers
+.. [it-gcc-c-dialect-options] https://gcc.gnu.org/onlinedocs/gcc/C-Dialect-Options.html
+.. [it-gnu-extensions] https://gcc.gnu.org/onlinedocs/gcc/C-Extensions.html
+.. [it-gcc-attribute-syntax] https://gcc.gnu.org/onlinedocs/gcc/Attribute-Syntax.html
+.. [it-n2049] http://www.open-std.org/jtc1/sc22/wg14/www/docs/n2049.pdf
--- /dev/null
+.. SPDX-License-Identifier: GPL-2.0
+
+.. include:: ../disclaimer-zh_CN.rst
+
+:Original: :ref:`Documentation/filesystems/index.rst <filesystems_index>`
+:Translator: Wang Wenhu <wenhu.wang@vivo.com>
+
+.. _cn_filesystems_index:
+
+========================
+Linux Kernel中的文件系统
+========================
+
+这份正在开发的手册或许在未来某个辉煌的日子里以易懂的形式将Linux虚拟\
+文件系统(VFS)层以及基于其上的各种文件系统如何工作呈现给大家。当前\
+可以看到下面的内容。
+
+文件系统
+========
+
+文件系统实现文档。
+
+.. toctree::
+ :maxdepth: 2
+
+ virtiofs
+
--- /dev/null
+.. SPDX-License-Identifier: GPL-2.0
+
+.. include:: ../disclaimer-zh_CN.rst
+
+:Original: :ref:`Documentation/filesystems/virtiofs.rst <virtiofs_index>`
+
+译者
+::
+
+ 中文版维护者: 王文虎 Wang Wenhu <wenhu.wang@vivo.com>
+ 中文版翻译者: 王文虎 Wang Wenhu <wenhu.wang@vivo.com>
+ 中文版校译者: 王文虎 Wang Wenhu <wenhu.wang@vivo.com>
+
+===========================================
+virtiofs: virtio-fs 主机<->客机共享文件系统
+===========================================
+
+- Copyright (C) 2020 Vivo Communication Technology Co. Ltd.
+
+介绍
+====
+Linux的virtiofs文件系统实现了一个半虚拟化VIRTIO类型“virtio-fs”设备的驱动,通过该\
+类型设备实现客机<->主机文件系统共享。它允许客机挂载一个已经导出到主机的目录。
+
+客机通常需要访问主机或者远程系统上的文件。使用场景包括:在新客机安装时让文件对其\
+可见;从主机上的根文件系统启动;对无状态或临时客机提供持久存储和在客机之间共享目录。
+
+尽管在某些任务可能通过使用已有的网络文件系统完成,但是却需要非常难以自动化的配置\
+步骤,且将存储网络暴露给客机。而virtio-fs设备通过提供不经过网络的文件系统访问文件\
+的设计方式解决了这些问题。
+
+另外,virto-fs设备发挥了主客机共存的优点提高了性能,并且提供了网络文件系统所不具备
+的一些语义功能。
+
+用法
+====
+以``myfs``标签将文件系统挂载到``/mnt``:
+
+.. code-block:: sh
+
+ guest# mount -t virtiofs myfs /mnt
+
+请查阅 https://virtio-fs.gitlab.io/ 了解配置QEMU和virtiofsd守护程序的详细信息。
+
+内幕
+====
+由于virtio-fs设备将FUSE协议用于文件系统请求,因此Linux的virtiofs文件系统与FUSE文\
+件系统客户端紧密集成在一起。客机充当FUSE客户端而主机充当FUSE服务器,内核与用户空\
+间之间的/dev/fuse接口由virtio-fs设备接口代替。
+
+FUSE请求被置于虚拟队列中由主机处理。主机填充缓冲区中的响应部分,而客机处理请求的完成部分。
+
+将/dev/fuse映射到虚拟队列需要解决/dev/fuse和虚拟队列之间语义上的差异。每次读取\
+/dev/fuse设备时,FUSE客户端都可以选择要传输的请求,从而可以使某些请求优先于其他\
+请求。虚拟队列有其队列语义,无法更改已入队请求的顺序。在虚拟队列已满的情况下尤
+其关键,因为此时不可能加入高优先级的请求。为了解决此差异,virtio-fs设备采用“hiprio”\
+(高优先级)虚拟队列,专门用于有别于普通请求的高优先级请求。
+
:maxdepth: 2
process/index
+ filesystems/index
目录和表格
----------
-Chinese translated version of Documentation/io_ordering.txt
+Chinese translated version of Documentation/driver-api/io_ordering.rst
If you have any comment or update to the content, please contact the
original document maintainer directly. However, if you have a problem
Chinese maintainer: Lin Yongting <linyongting@gmail.com>
---------------------------------------------------------------------
-Documentation/io_ordering.txt 的中文翻译
+Documentation/driver-api/io_ordering.rst 的中文翻译
如果想评论或更新本文的内容,请直接联系原文档的维护者。如果你使用英文
交流有困难的话,也可以向中文版维护者求助。如果本翻译更新不及时或者翻
.. _cn_development_posting:
-发送补丁
+发布补丁
========
迟早,当您的工作准备好提交给社区进行审查,并最终包含到主线内核中时。不出所料,
'o' 01-A1 `linux/dvb/*.h` DVB
'p' 00-0F linux/phantom.h conflict! (OpenHaptics needs this)
'p' 00-1F linux/rtc.h conflict!
-'p' 00-3F linux/mc146818rtc.h conflict!
'p' 40-7F linux/nvram.h
'p' 80-9F linux/ppdev.h user-space parport
<mailto:tim@cyberelk.net>
the original assembly code: > 3: movl $-14,%eax
and linked in vmlinux : > c0199ff5 <.fixup+10b5> movl $0xfffffff2,%eax
+If the fixup was able to handle the exception, control flow may be returned
+to the instruction after the one that triggered the fault, ie. local label 2b.
+
The assembly code::
> .section __ex_table,"a"
it as special.
More functions can easily be added.
+
+CONFIG_BUILDTIME_TABLE_SORT allows the __ex_table section to be sorted post
+link of the kernel image, via a host utility scripts/sorttable. It will set the
+symbol main_extable_sort_needed to 0, avoiding sorting the __ex_table section
+at boot time. With the exception table sorted, at runtime when an exception
+occurs we can quickly lookup the __ex_table entry via binary search.
+
+This is not just a boot time optimization, some architectures require this
+table to be sorted in order to handle exceptions relatively early in the boot
+process. For example, i386 makes use of this form of exception handling before
+paging support is even enabled!
When DMAR is enabled for use, you will notice..
PCI-DMA: Using DMAR IOMMU
+-------------------------
Fault reporting
----------------
+^^^^^^^^^^^^^^^
::
T: git git://git.kernel.org/pub/scm/linux/kernel/git/ericvh/v9fs.git
T: git git://github.com/martinetd/linux.git
S: Maintained
-F: Documentation/filesystems/9p.txt
+F: Documentation/filesystems/9p.rst
F: fs/9p/
F: net/9p/
F: include/net/9p/
M: David Sterba <dsterba@suse.com>
L: linux-fsdevel@vger.kernel.org
S: Odd Fixes
-F: Documentation/filesystems/affs.txt
+F: Documentation/filesystems/affs.rst
F: fs/affs/
AFS FILESYSTEM
S: Supported
F: fs/afs/
F: include/trace/events/afs.h
-F: Documentation/filesystems/afs.txt
+F: Documentation/filesystems/afs.rst
W: https://www.infradead.org/~dhowells/kafs/
AGPGART DRIVER
M: Salah Triki <salah.triki@gmail.com>
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/luisbg/linux-befs.git
-F: Documentation/filesystems/befs.txt
+F: Documentation/filesystems/befs.rst
F: fs/befs/
BFQ I/O SCHEDULER
BFS FILE SYSTEM
M: "Tigran A. Aivazian" <aivazian.tigran@gmail.com>
S: Maintained
-F: Documentation/filesystems/bfs.txt
+F: Documentation/filesystems/bfs.rst
F: fs/bfs/
F: include/uapi/linux/bfs_fs.h
Q: http://patchwork.kernel.org/project/linux-btrfs/list/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs.git
S: Maintained
-F: Documentation/filesystems/btrfs.txt
+F: Documentation/filesystems/btrfs.rst
F: fs/btrfs/
F: include/linux/btrfs*
F: include/uapi/linux/btrfs*
T: git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
T: git git://github.com/ceph/ceph-client.git
S: Supported
-F: Documentation/filesystems/ceph.txt
+F: Documentation/filesystems/ceph.rst
F: fs/ceph/
CERTIFICATE HANDLING
CRAMFS FILESYSTEM
M: Nicolas Pitre <nico@fluxnic.net>
S: Maintained
-F: Documentation/filesystems/cramfs.txt
+F: Documentation/filesystems/cramfs.rst
F: fs/cramfs/
CREATIVE SB0540
R: "Rafael J. Wysocki" <rafael@kernel.org>
T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
S: Supported
-F: Documentation/kobject.txt
+F: Documentation/core-api/kobject.rst
F: drivers/base/
F: fs/debugfs/
F: fs/sysfs/
W: https://launchpad.net/ecryptfs
T: git git://git.kernel.org/pub/scm/linux/kernel/git/tyhicks/ecryptfs.git
S: Odd Fixes
-F: Documentation/filesystems/ecryptfs.txt
+F: Documentation/filesystems/ecryptfs.rst
F: fs/ecryptfs/
EDAC-AMD64
F: include/video/s1d13xxxfb.h
EROFS FILE SYSTEM
-M: Gao Xiang <gaoxiang25@huawei.com>
+M: Gao Xiang <xiang@kernel.org>
M: Chao Yu <yuchao0@huawei.com>
L: linux-erofs@lists.ozlabs.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs.git
-F: Documentation/filesystems/erofs.txt
+F: Documentation/filesystems/erofs.rst
F: fs/erofs/
F: include/trace/events/erofs.h
M: Jan Kara <jack@suse.com>
L: linux-ext4@vger.kernel.org
S: Maintained
-F: Documentation/filesystems/ext2.txt
+F: Documentation/filesystems/ext2.rst
F: fs/ext2/
F: include/linux/ext2*
W: https://f2fs.wiki.kernel.org/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs.git
S: Maintained
-F: Documentation/filesystems/f2fs.txt
+F: Documentation/filesystems/f2fs.rst
F: Documentation/ABI/testing/sysfs-fs-f2fs
F: fs/f2fs/
F: include/linux/f2fs_fs.h
F: scripts/gcc-plugins/
F: scripts/gcc-plugin.sh
F: scripts/Makefile.gcc-plugins
-F: Documentation/core-api/gcc-plugins.rst
+F: Documentation/kbuild/gcc-plugins.rst
GASKET DRIVER FRAMEWORK
M: Rob Springer <rspringer@google.com>
HFS FILESYSTEM
L: linux-fsdevel@vger.kernel.org
S: Orphan
-F: Documentation/filesystems/hfs.txt
+F: Documentation/filesystems/hfs.rst
F: fs/hfs/
HFSPLUS FILESYSTEM
L: linux-fsdevel@vger.kernel.org
S: Orphan
-F: Documentation/filesystems/hfsplus.txt
+F: Documentation/filesystems/hfsplus.rst
F: fs/hfsplus/
HGA FRAMEBUFFER DRIVER
R: Amir Goldstein <amir73il@gmail.com>
L: linux-fsdevel@vger.kernel.org
S: Maintained
-F: Documentation/filesystems/inotify.txt
+F: Documentation/filesystems/inotify.rst
F: fs/notify/inotify/
F: include/linux/inotify.h
F: include/uapi/linux/inotify.h
S: Supported
W: https://github.com/sudeepdutt/mic
W: http://software.intel.com/en-us/mic-developer
+F: Documentation/misc-devices/mic/
+F: drivers/dma/mic_x100_dma.c
+F: drivers/dma/mic_x100_dma.h
+F: drivers/misc/mic/
F: include/linux/mic_bus.h
F: include/linux/scif.h
F: include/uapi/linux/mic_common.h
F: include/uapi/linux/mic_ioctl.h
F: include/uapi/linux/scif_ioctl.h
-F: drivers/misc/mic/
-F: drivers/dma/mic_x100_dma.c
-F: drivers/dma/mic_x100_dma.h
-F: Documentation/mic/
INTEL PMC CORE DRIVER
M: Rajneesh Bhardwaj <rajneesh.bhardwaj@intel.com>
S: Supported
F: Documentation/security/keys/trusted-encrypted.rst
F: include/keys/trusted-type.h
-F: security/keys/trusted.c
-F: include/keys/trusted.h
+F: include/keys/trusted_tpm.h
+F: security/keys/trusted-keys/
KEYS/KEYRINGS
M: David Howells <dhowells@redhat.com>
W: https://nilfs.osdn.jp/
T: git git://github.com/konis/nilfs2.git
S: Supported
-F: Documentation/filesystems/nilfs2.txt
+F: Documentation/filesystems/nilfs2.rst
F: fs/nilfs2/
F: include/trace/events/nilfs2.h
F: include/uapi/linux/nilfs2_api.h
W: http://www.tuxera.com/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/aia21/ntfs.git
S: Supported
-F: Documentation/filesystems/ntfs.txt
+F: Documentation/filesystems/ntfs.rst
F: fs/ntfs/
NUBUS SUBSYSTEM
M: Bob Copeland <me@bobcopeland.com>
L: linux-karma-devel@lists.sourceforge.net
S: Maintained
-F: Documentation/filesystems/omfs.txt
+F: Documentation/filesystems/omfs.rst
F: fs/omfs/
OMNIKEY CARDMAN 4000 DRIVER
L: ocfs2-devel@oss.oracle.com (moderated for non-subscribers)
W: http://ocfs2.wiki.kernel.org
S: Supported
-F: Documentation/filesystems/ocfs2.txt
-F: Documentation/filesystems/dlmfs.txt
+F: Documentation/filesystems/ocfs2.rst
+F: Documentation/filesystems/dlmfs.rst
F: fs/ocfs2/
ORANGEFS FILESYSTEM
T: git git://git.kernel.org/pub/scm/linux/kernel/git/hubcap/linux.git
S: Supported
F: fs/orangefs/
-F: Documentation/filesystems/orangefs.txt
+F: Documentation/filesystems/orangefs.rst
ORINOCO DRIVER
L: linux-wireless@vger.kernel.org
F: fs/proc/
F: include/linux/proc_fs.h
F: tools/testing/selftests/proc/
-F: Documentation/filesystems/proc.txt
+F: Documentation/filesystems/proc.rst
PROC SYSCTL
M: Luis Chamberlain <mcgrof@kernel.org>
W: http://squashfs.org.uk
T: git git://git.kernel.org/pub/scm/linux/kernel/git/pkl/squashfs-next.git
S: Maintained
-F: Documentation/filesystems/squashfs.txt
+F: Documentation/filesystems/squashfs.rst
F: fs/squashfs/
SRM (Alpha) environment access
SYSV FILESYSTEM
M: Christoph Hellwig <hch@infradead.org>
S: Maintained
-F: Documentation/filesystems/sysv-fs.txt
+F: Documentation/filesystems/sysv-fs.rst
F: fs/sysv/
F: include/linux/sysv_fs.h
T: git git://git.kernel.org/pub/scm/linux/kernel/git/rw/ubifs.git fixes
W: http://www.linux-mtd.infradead.org/doc/ubifs.html
S: Supported
-F: Documentation/filesystems/ubifs.txt
+F: Documentation/filesystems/ubifs.rst
F: fs/ubifs/
UCLINUX (M68KNOMMU AND COLDFIRE)
UDF FILESYSTEM
M: Jan Kara <jack@suse.com>
S: Maintained
-F: Documentation/filesystems/udf.txt
+F: Documentation/filesystems/udf.rst
F: fs/udf/
UDRAW TABLET
T: git git://git.kernel.org/pub/scm/linux/kernel/git/dlemoal/zonefs.git
S: Maintained
F: fs/zonefs/
-F: Documentation/filesystems/zonefs.txt
+F: Documentation/filesystems/zonefs.rst
ZPOOL COMPRESSED PAGE STORAGE API
M: Dan Streetman <ddstreet@ieee.org>
*/
#ifndef __ASM_ARM_FLOPPY_H
#define __ASM_ARM_FLOPPY_H
-#if 0
-#include <mach/floppy.h>
-#endif
-#define fd_outb(val,port) \
- do { \
- if ((port) == (u32)FD_DOR) \
- fd_setdor((val)); \
- else \
- outb((val),(port)); \
+#define fd_outb(val,port) \
+ do { \
+ int new_val = (val); \
+ if (((port) & 7) == FD_DOR) { \
+ if (new_val & 0xf0) \
+ new_val = (new_val & 0x0c) | \
+ floppy_selects[new_val & 3]; \
+ else \
+ new_val &= 0x0c; \
+ } \
+ outb(new_val, (port)); \
} while(0)
#define fd_inb(port) inb((port))
* to a non-zero track, and then restoring it to track 0. If an error occurs,
* then there is no floppy drive present. [to be put back in again]
*/
-static unsigned char floppy_selects[2][4] =
-{
- { 0x10, 0x21, 0x23, 0x33 },
- { 0x10, 0x21, 0x23, 0x33 }
-};
-
-#define fd_setdor(dor) \
-do { \
- int new_dor = (dor); \
- if (new_dor & 0xf0) \
- new_dor = (new_dor & 0x0c) | floppy_selects[fdc][new_dor & 3]; \
- else \
- new_dor &= 0x0c; \
- outb(new_dor, FD_DOR); \
-} while (0)
-
-/*
- * Someday, we'll automatically detect which drives are present...
- */
-static inline void fd_scandrives (void)
-{
-#if 0
- int floppy, drive_count;
-
- fd_disable_irq();
- raw_cmd = &default_raw_cmd;
- raw_cmd->flags = FD_RAW_SPIN | FD_RAW_NEED_SEEK;
- raw_cmd->track = 0;
- raw_cmd->rate = ?;
- drive_count = 0;
- for (floppy = 0; floppy < 4; floppy ++) {
- current_drive = drive_count;
- /*
- * Turn on floppy motor
- */
- if (start_motor(redo_fd_request))
- continue;
- /*
- * Set up FDC
- */
- fdc_specify();
- /*
- * Tell FDC to recalibrate
- */
- output_byte(FD_RECALIBRATE);
- LAST_OUT(UNIT(floppy));
- /* wait for command to complete */
- if (!successful) {
- int i;
- for (i = drive_count; i < 3; i--)
- floppy_selects[fdc][i] = floppy_selects[fdc][i + 1];
- floppy_selects[fdc][3] = 0;
- floppy -= 1;
- } else
- drive_count++;
- }
-#else
- floppy_selects[0][0] = 0x10;
- floppy_selects[0][1] = 0x21;
- floppy_selects[0][2] = 0x23;
- floppy_selects[0][3] = 0x33;
-#endif
-}
+static unsigned char floppy_selects[4] = { 0x10, 0x21, 0x23, 0x33 };
#define FDC1 (0x3f0)
*/
static void driveswap(int *ints, int dummy, int dummy2)
{
- floppy_selects[0][0] ^= floppy_selects[0][1];
- floppy_selects[0][1] ^= floppy_selects[0][0];
- floppy_selects[0][0] ^= floppy_selects[0][1];
+ swap(floppy_selects[0], floppy_selects[1]);
}
#define EXTRA_FLOPPY_PARAMS ,{ "driveswap", &driveswap, NULL, 0, 0 }
dev->bsize = bsize;
dev->bshift = ffs(bsize) - 10;
- dev->queue = blk_alloc_queue(GFP_KERNEL);
+ dev->queue = blk_alloc_queue(nfhd_make_request, NUMA_NO_NODE);
if (dev->queue == NULL)
goto free_dev;
dev->queue->queuedata = dev;
- blk_queue_make_request(dev->queue, nfhd_make_request);
blk_queue_logical_block_size(dev->queue, bsize);
dev->disk = alloc_disk(16);
* ioremap and friends.
*
* ioremap takes a PCI memory address, as specified in
- * Documentation/io-mapping.txt.
+ * Documentation/driver-api/io-mapping.rst.
*
*/
#define ioremap(cookie, size) __uc32_ioremap(cookie, size)
spin_lock_init(&dev->lock);
dev->users = 0;
- dev->queue = blk_alloc_queue(GFP_KERNEL);
+ dev->queue = blk_alloc_queue(simdisk_make_request, NUMA_NO_NODE);
if (dev->queue == NULL) {
pr_err("blk_alloc_queue failed\n");
goto out_alloc_queue;
}
- blk_queue_make_request(dev->queue, simdisk_make_request);
dev->queue->queuedata = dev;
dev->gd = alloc_disk(SIMDISK_MINORS);
blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \
- genhd.o partition-generic.o ioprio.o \
- badblocks.o partitions/ blk-rq-qos.o
+ genhd.o ioprio.o badblocks.o partitions/ blk-rq-qos.o
obj-$(CONFIG_BOUNCE) += bounce.o
obj-$(CONFIG_BLK_SCSI_REQUEST) += scsi_ioctl.o
{
struct bfq_entity *entity = &bfqq->entity;
+ /*
+ * Get extra reference to prevent bfqq from being freed in
+ * next possible expire or deactivate.
+ */
+ bfqq->ref++;
+
/* 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
bfq_bfqq_expire(bfqd, bfqd->in_service_queue,
false, BFQQE_PREEMPTED);
- /*
- * get extra reference to prevent bfqq from being freed in
- * next possible deactivate
- */
- bfqq->ref++;
-
if (bfq_bfqq_busy(bfqq))
bfq_deactivate_bfqq(bfqd, bfqq, false, false);
else if (entity->on_st_or_in_serv)
if (!bfqd->in_service_queue && !bfqd->rq_in_driver)
bfq_schedule_dispatch(bfqd);
- /* release extra ref taken above */
+ /* release extra ref taken above, bfqq may happen to be freed now */
bfq_put_queue(bfqq);
}
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);
+ bfq_release_process_ref(bfqd, async_bfqq);
}
}
/**
* 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.
+ * @entity: the entity to move, if entity is a leaf; or the parent entity
+ * of an active leaf entity to move, if entity is not a leaf.
*/
static void bfq_reparent_leaf_entity(struct bfq_data *bfqd,
- struct bfq_entity *entity)
+ struct bfq_entity *entity,
+ int ioprio_class)
{
- struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+ struct bfq_queue *bfqq;
+ struct bfq_entity *child_entity = entity;
+ while (child_entity->my_sched_data) { /* leaf not reached yet */
+ struct bfq_sched_data *child_sd = child_entity->my_sched_data;
+ struct bfq_service_tree *child_st = child_sd->service_tree +
+ ioprio_class;
+ struct rb_root *child_active = &child_st->active;
+
+ child_entity = bfq_entity_of(rb_first(child_active));
+
+ if (!child_entity)
+ child_entity = child_sd->in_service_entity;
+ }
+
+ bfqq = bfq_entity_to_bfqq(child_entity);
bfq_bfqq_move(bfqd, bfqq, bfqd->root_group);
}
/**
- * bfq_reparent_active_entities - move to the root group all active
- * entities.
+ * bfq_reparent_active_queues - move to the root group all active queues.
* @bfqd: the device data structure with the root group.
* @bfqg: the group to move from.
- * @st: the service tree with the entities.
+ * @st: the service tree to start the search from.
*/
-static void bfq_reparent_active_entities(struct bfq_data *bfqd,
- struct bfq_group *bfqg,
- struct bfq_service_tree *st)
+static void bfq_reparent_active_queues(struct bfq_data *bfqd,
+ struct bfq_group *bfqg,
+ struct bfq_service_tree *st,
+ int ioprio_class)
{
struct rb_root *active = &st->active;
- struct bfq_entity *entity = NULL;
-
- if (!RB_EMPTY_ROOT(&st->active))
- entity = bfq_entity_of(rb_first(active));
+ struct bfq_entity *entity;
- for (; entity ; entity = bfq_entity_of(rb_first(active)))
- bfq_reparent_leaf_entity(bfqd, entity);
+ while ((entity = bfq_entity_of(rb_first(active))))
+ bfq_reparent_leaf_entity(bfqd, entity, ioprio_class);
if (bfqg->sched_data.in_service_entity)
bfq_reparent_leaf_entity(bfqd,
- bfqg->sched_data.in_service_entity);
+ bfqg->sched_data.in_service_entity,
+ ioprio_class);
}
/**
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.
- */
- 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
* There is no need to put the sync queues, as the
* scheduler has taken no reference.
*/
- bfq_reparent_active_entities(bfqd, bfqg, st);
+ bfq_reparent_active_queues(bfqd, bfqg, st, 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. In addition, even
+ * bfq_reparent_active_queues() may happen to add some
+ * entities to the idle tree. It happens if, in some
+ * of the calls to bfq_bfqq_move() performed by
+ * bfq_reparent_active_queues(), the queue to move is
+ * empty and gets expired.
+ */
+ bfq_flush_idle_tree(st);
}
__bfq_deactivate_entity(entity, false);
}
}
-
-static
void bfq_release_process_ref(struct bfq_data *bfqd, struct bfq_queue *bfqq)
{
/*
return bfqq;
}
-static void bfq_idle_slice_timer_body(struct bfq_queue *bfqq)
+static void
+bfq_idle_slice_timer_body(struct bfq_data *bfqd, 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);
+ /*
+ * Considering that bfqq may be in race, we should firstly check
+ * whether bfqq is in service before doing something on it. If
+ * the bfqq in race is not in service, it has already been expired
+ * through __bfq_bfqq_expire func and its wait_request flags has
+ * been cleared in __bfq_bfqd_reset_in_service func.
+ */
if (bfqq != bfqd->in_service_queue) {
spin_unlock_irqrestore(&bfqd->lock, flags);
return;
}
+ bfq_clear_bfqq_wait_request(bfqq);
+
if (bfq_bfqq_budget_timeout(bfqq))
/*
* Also here the queue can be safely expired
* early.
*/
if (bfqq)
- bfq_idle_slice_timer_body(bfqq);
+ bfq_idle_slice_timer_body(bfqd, bfqq);
return HRTIMER_NORESTART;
}
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_release_process_ref(struct bfq_data *bfqd, struct bfq_queue *bfqq);
void bfq_schedule_dispatch(struct bfq_data *bfqd);
void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
#include <linux/cgroup.h>
#include <linux/blk-cgroup.h>
#include <linux/highmem.h>
+#include <linux/sched/sysctl.h>
#include <trace/events/block.h>
#include "blk.h"
}
/**
+ * guard_bio_eod - truncate a BIO to fit the block device
+ * @bio: bio to truncate
+ *
+ * This allows us to do IO even on the odd last sectors of a device, even if the
+ * block size is some multiple of the physical sector size.
+ *
+ * We'll just truncate the bio to the size of the device, and clear the end of
+ * the buffer head manually. Truly out-of-range accesses will turn into actual
+ * I/O errors, this only handles the "we need to be able to do I/O at the final
+ * sector" case.
+ */
+void guard_bio_eod(struct bio *bio)
+{
+ sector_t maxsector;
+ struct hd_struct *part;
+
+ rcu_read_lock();
+ part = __disk_get_part(bio->bi_disk, bio->bi_partno);
+ if (part)
+ maxsector = part_nr_sects_read(part);
+ else
+ maxsector = get_capacity(bio->bi_disk);
+ rcu_read_unlock();
+
+ if (!maxsector)
+ return;
+
+ /*
+ * If the *whole* IO is past the end of the device,
+ * let it through, and the IO layer will turn it into
+ * an EIO.
+ */
+ if (unlikely(bio->bi_iter.bi_sector >= maxsector))
+ return;
+
+ maxsector -= bio->bi_iter.bi_sector;
+ if (likely((bio->bi_iter.bi_size >> 9) <= maxsector))
+ return;
+
+ bio_truncate(bio, maxsector << 9);
+}
+
+/**
* bio_put - release a reference to a bio
* @bio: bio to release reference to
*
}
EXPORT_SYMBOL(bio_clone_fast);
+const char *bio_devname(struct bio *bio, char *buf)
+{
+ return disk_name(bio->bi_disk, bio->bi_partno, buf);
+}
+EXPORT_SYMBOL(bio_devname);
+
static inline bool page_is_mergeable(const struct bio_vec *bv,
struct page *page, unsigned int len, unsigned int off,
bool *same_page)
*
* This should only be used by passthrough bios.
*/
-static int __bio_add_pc_page(struct request_queue *q, struct bio *bio,
+int __bio_add_pc_page(struct request_queue *q, struct bio *bio,
struct page *page, unsigned int len, unsigned int offset,
bool *same_page)
{
int submit_bio_wait(struct bio *bio)
{
DECLARE_COMPLETION_ONSTACK_MAP(done, bio->bi_disk->lockdep_map);
+ unsigned long hang_check;
bio->bi_private = &done;
bio->bi_end_io = submit_bio_wait_endio;
bio->bi_opf |= REQ_SYNC;
submit_bio(bio);
- wait_for_completion_io(&done);
+
+ /* Prevent hang_check timer from firing at us during very long I/O */
+ hang_check = sysctl_hung_task_timeout_secs;
+ if (hang_check)
+ while (!wait_for_completion_io_timeout(&done,
+ hang_check * (HZ/2)))
+ ;
+ else
+ wait_for_completion_io(&done);
return blk_status_to_errno(bio->bi_status);
}
}
EXPORT_SYMBOL(bio_list_copy_data);
-struct bio_map_data {
- int is_our_pages;
- struct iov_iter iter;
- struct iovec iov[];
-};
-
-static struct bio_map_data *bio_alloc_map_data(struct iov_iter *data,
- gfp_t gfp_mask)
-{
- struct bio_map_data *bmd;
- if (data->nr_segs > UIO_MAXIOV)
- return NULL;
-
- bmd = kmalloc(struct_size(bmd, iov, data->nr_segs), gfp_mask);
- if (!bmd)
- return NULL;
- memcpy(bmd->iov, data->iov, sizeof(struct iovec) * data->nr_segs);
- bmd->iter = *data;
- bmd->iter.iov = bmd->iov;
- return bmd;
-}
-
-/**
- * bio_copy_from_iter - copy all pages from iov_iter to bio
- * @bio: The &struct bio which describes the I/O as destination
- * @iter: iov_iter as source
- *
- * Copy all pages from iov_iter to bio.
- * Returns 0 on success, or error on failure.
- */
-static int bio_copy_from_iter(struct bio *bio, struct iov_iter *iter)
-{
- struct bio_vec *bvec;
- struct bvec_iter_all iter_all;
-
- bio_for_each_segment_all(bvec, bio, iter_all) {
- ssize_t ret;
-
- ret = copy_page_from_iter(bvec->bv_page,
- bvec->bv_offset,
- bvec->bv_len,
- iter);
-
- if (!iov_iter_count(iter))
- break;
-
- if (ret < bvec->bv_len)
- return -EFAULT;
- }
-
- return 0;
-}
-
-/**
- * bio_copy_to_iter - copy all pages from bio to iov_iter
- * @bio: The &struct bio which describes the I/O as source
- * @iter: iov_iter as destination
- *
- * Copy all pages from bio to iov_iter.
- * Returns 0 on success, or error on failure.
- */
-static int bio_copy_to_iter(struct bio *bio, struct iov_iter iter)
-{
- struct bio_vec *bvec;
- struct bvec_iter_all iter_all;
-
- bio_for_each_segment_all(bvec, bio, iter_all) {
- ssize_t ret;
-
- ret = copy_page_to_iter(bvec->bv_page,
- bvec->bv_offset,
- bvec->bv_len,
- &iter);
-
- if (!iov_iter_count(&iter))
- break;
-
- if (ret < bvec->bv_len)
- return -EFAULT;
- }
-
- return 0;
-}
-
void bio_free_pages(struct bio *bio)
{
struct bio_vec *bvec;
}
EXPORT_SYMBOL(bio_free_pages);
-/**
- * bio_uncopy_user - finish previously mapped bio
- * @bio: bio being terminated
- *
- * Free pages allocated from bio_copy_user_iov() and write back data
- * to user space in case of a read.
- */
-int bio_uncopy_user(struct bio *bio)
-{
- struct bio_map_data *bmd = bio->bi_private;
- int ret = 0;
-
- if (!bio_flagged(bio, BIO_NULL_MAPPED)) {
- /*
- * if we're in a workqueue, the request is orphaned, so
- * don't copy into a random user address space, just free
- * and return -EINTR so user space doesn't expect any data.
- */
- if (!current->mm)
- ret = -EINTR;
- else if (bio_data_dir(bio) == READ)
- ret = bio_copy_to_iter(bio, bmd->iter);
- if (bmd->is_our_pages)
- bio_free_pages(bio);
- }
- kfree(bmd);
- bio_put(bio);
- return ret;
-}
-
-/**
- * bio_copy_user_iov - copy user data to bio
- * @q: destination block queue
- * @map_data: pointer to the rq_map_data holding pages (if necessary)
- * @iter: iovec iterator
- * @gfp_mask: memory allocation flags
- *
- * Prepares and returns a bio for indirect user io, bouncing data
- * to/from kernel pages as necessary. Must be paired with
- * call bio_uncopy_user() on io completion.
- */
-struct bio *bio_copy_user_iov(struct request_queue *q,
- struct rq_map_data *map_data,
- struct iov_iter *iter,
- gfp_t gfp_mask)
-{
- struct bio_map_data *bmd;
- struct page *page;
- struct bio *bio;
- int i = 0, ret;
- int nr_pages;
- unsigned int len = iter->count;
- unsigned int offset = map_data ? offset_in_page(map_data->offset) : 0;
-
- bmd = bio_alloc_map_data(iter, gfp_mask);
- if (!bmd)
- return ERR_PTR(-ENOMEM);
-
- /*
- * We need to do a deep copy of the iov_iter including the iovecs.
- * The caller provided iov might point to an on-stack or otherwise
- * shortlived one.
- */
- bmd->is_our_pages = map_data ? 0 : 1;
-
- nr_pages = DIV_ROUND_UP(offset + len, PAGE_SIZE);
- if (nr_pages > BIO_MAX_PAGES)
- nr_pages = BIO_MAX_PAGES;
-
- ret = -ENOMEM;
- bio = bio_kmalloc(gfp_mask, nr_pages);
- if (!bio)
- goto out_bmd;
-
- ret = 0;
-
- if (map_data) {
- nr_pages = 1 << map_data->page_order;
- i = map_data->offset / PAGE_SIZE;
- }
- while (len) {
- unsigned int bytes = PAGE_SIZE;
-
- bytes -= offset;
-
- if (bytes > len)
- bytes = len;
-
- if (map_data) {
- if (i == map_data->nr_entries * nr_pages) {
- ret = -ENOMEM;
- break;
- }
-
- page = map_data->pages[i / nr_pages];
- page += (i % nr_pages);
-
- i++;
- } else {
- page = alloc_page(q->bounce_gfp | gfp_mask);
- if (!page) {
- ret = -ENOMEM;
- break;
- }
- }
-
- if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes) {
- if (!map_data)
- __free_page(page);
- break;
- }
-
- len -= bytes;
- offset = 0;
- }
-
- if (ret)
- goto cleanup;
-
- if (map_data)
- map_data->offset += bio->bi_iter.bi_size;
-
- /*
- * success
- */
- if ((iov_iter_rw(iter) == WRITE && (!map_data || !map_data->null_mapped)) ||
- (map_data && map_data->from_user)) {
- ret = bio_copy_from_iter(bio, iter);
- if (ret)
- goto cleanup;
- } else {
- if (bmd->is_our_pages)
- zero_fill_bio(bio);
- iov_iter_advance(iter, bio->bi_iter.bi_size);
- }
-
- bio->bi_private = bmd;
- if (map_data && map_data->null_mapped)
- bio_set_flag(bio, BIO_NULL_MAPPED);
- return bio;
-cleanup:
- if (!map_data)
- bio_free_pages(bio);
- bio_put(bio);
-out_bmd:
- kfree(bmd);
- return ERR_PTR(ret);
-}
-
-/**
- * bio_map_user_iov - map user iovec into bio
- * @q: the struct request_queue for the bio
- * @iter: iovec iterator
- * @gfp_mask: memory allocation flags
- *
- * Map the user space address into a bio suitable for io to a block
- * device. Returns an error pointer in case of error.
- */
-struct bio *bio_map_user_iov(struct request_queue *q,
- struct iov_iter *iter,
- gfp_t gfp_mask)
-{
- int j;
- struct bio *bio;
- int ret;
-
- if (!iov_iter_count(iter))
- return ERR_PTR(-EINVAL);
-
- bio = bio_kmalloc(gfp_mask, iov_iter_npages(iter, BIO_MAX_PAGES));
- if (!bio)
- return ERR_PTR(-ENOMEM);
-
- while (iov_iter_count(iter)) {
- struct page **pages;
- ssize_t bytes;
- size_t offs, added = 0;
- int npages;
-
- bytes = iov_iter_get_pages_alloc(iter, &pages, LONG_MAX, &offs);
- if (unlikely(bytes <= 0)) {
- ret = bytes ? bytes : -EFAULT;
- goto out_unmap;
- }
-
- npages = DIV_ROUND_UP(offs + bytes, PAGE_SIZE);
-
- if (unlikely(offs & queue_dma_alignment(q))) {
- ret = -EINVAL;
- j = 0;
- } else {
- for (j = 0; j < npages; j++) {
- struct page *page = pages[j];
- unsigned int n = PAGE_SIZE - offs;
- bool same_page = false;
-
- if (n > bytes)
- n = bytes;
-
- if (!__bio_add_pc_page(q, bio, page, n, offs,
- &same_page)) {
- if (same_page)
- put_page(page);
- break;
- }
-
- added += n;
- bytes -= n;
- offs = 0;
- }
- iov_iter_advance(iter, added);
- }
- /*
- * release the pages we didn't map into the bio, if any
- */
- while (j < npages)
- put_page(pages[j++]);
- kvfree(pages);
- /* couldn't stuff something into bio? */
- if (bytes)
- break;
- }
-
- bio_set_flag(bio, BIO_USER_MAPPED);
-
- /*
- * subtle -- if bio_map_user_iov() ended up bouncing a bio,
- * it would normally disappear when its bi_end_io is run.
- * however, we need it for the unmap, so grab an extra
- * reference to it
- */
- bio_get(bio);
- return bio;
-
- out_unmap:
- bio_release_pages(bio, false);
- bio_put(bio);
- return ERR_PTR(ret);
-}
-
-/**
- * bio_unmap_user - unmap a bio
- * @bio: the bio being unmapped
- *
- * Unmap a bio previously mapped by bio_map_user_iov(). Must be called from
- * process context.
- *
- * bio_unmap_user() may sleep.
- */
-void bio_unmap_user(struct bio *bio)
-{
- bio_release_pages(bio, bio_data_dir(bio) == READ);
- bio_put(bio);
- bio_put(bio);
-}
-
-static void bio_invalidate_vmalloc_pages(struct bio *bio)
-{
-#ifdef ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
- if (bio->bi_private && !op_is_write(bio_op(bio))) {
- unsigned long i, len = 0;
-
- for (i = 0; i < bio->bi_vcnt; i++)
- len += bio->bi_io_vec[i].bv_len;
- invalidate_kernel_vmap_range(bio->bi_private, len);
- }
-#endif
-}
-
-static void bio_map_kern_endio(struct bio *bio)
-{
- bio_invalidate_vmalloc_pages(bio);
- bio_put(bio);
-}
-
-/**
- * bio_map_kern - map kernel address into bio
- * @q: the struct request_queue for the bio
- * @data: pointer to buffer to map
- * @len: length in bytes
- * @gfp_mask: allocation flags for bio allocation
- *
- * Map the kernel address into a bio suitable for io to a block
- * device. Returns an error pointer in case of error.
- */
-struct bio *bio_map_kern(struct request_queue *q, void *data, unsigned int len,
- gfp_t gfp_mask)
-{
- unsigned long kaddr = (unsigned long)data;
- unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
- unsigned long start = kaddr >> PAGE_SHIFT;
- const int nr_pages = end - start;
- bool is_vmalloc = is_vmalloc_addr(data);
- struct page *page;
- int offset, i;
- struct bio *bio;
-
- bio = bio_kmalloc(gfp_mask, nr_pages);
- if (!bio)
- return ERR_PTR(-ENOMEM);
-
- if (is_vmalloc) {
- flush_kernel_vmap_range(data, len);
- bio->bi_private = data;
- }
-
- offset = offset_in_page(kaddr);
- for (i = 0; i < nr_pages; i++) {
- unsigned int bytes = PAGE_SIZE - offset;
-
- if (len <= 0)
- break;
-
- if (bytes > len)
- bytes = len;
-
- if (!is_vmalloc)
- page = virt_to_page(data);
- else
- page = vmalloc_to_page(data);
- if (bio_add_pc_page(q, bio, page, bytes,
- offset) < bytes) {
- /* we don't support partial mappings */
- bio_put(bio);
- return ERR_PTR(-EINVAL);
- }
-
- data += bytes;
- len -= bytes;
- offset = 0;
- }
-
- bio->bi_end_io = bio_map_kern_endio;
- return bio;
-}
-
-static void bio_copy_kern_endio(struct bio *bio)
-{
- bio_free_pages(bio);
- bio_put(bio);
-}
-
-static void bio_copy_kern_endio_read(struct bio *bio)
-{
- char *p = bio->bi_private;
- struct bio_vec *bvec;
- struct bvec_iter_all iter_all;
-
- bio_for_each_segment_all(bvec, bio, iter_all) {
- memcpy(p, page_address(bvec->bv_page), bvec->bv_len);
- p += bvec->bv_len;
- }
-
- bio_copy_kern_endio(bio);
-}
-
-/**
- * bio_copy_kern - copy kernel address into bio
- * @q: the struct request_queue for the bio
- * @data: pointer to buffer to copy
- * @len: length in bytes
- * @gfp_mask: allocation flags for bio and page allocation
- * @reading: data direction is READ
- *
- * copy the kernel address into a bio suitable for io to a block
- * device. Returns an error pointer in case of error.
- */
-struct bio *bio_copy_kern(struct request_queue *q, void *data, unsigned int len,
- gfp_t gfp_mask, int reading)
-{
- unsigned long kaddr = (unsigned long)data;
- unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
- unsigned long start = kaddr >> PAGE_SHIFT;
- struct bio *bio;
- void *p = data;
- int nr_pages = 0;
-
- /*
- * Overflow, abort
- */
- if (end < start)
- return ERR_PTR(-EINVAL);
-
- nr_pages = end - start;
- bio = bio_kmalloc(gfp_mask, nr_pages);
- if (!bio)
- return ERR_PTR(-ENOMEM);
-
- while (len) {
- struct page *page;
- unsigned int bytes = PAGE_SIZE;
-
- if (bytes > len)
- bytes = len;
-
- page = alloc_page(q->bounce_gfp | gfp_mask);
- if (!page)
- goto cleanup;
-
- if (!reading)
- memcpy(page_address(page), p, bytes);
-
- if (bio_add_pc_page(q, bio, page, bytes, 0) < bytes)
- break;
-
- len -= bytes;
- p += bytes;
- }
-
- if (reading) {
- bio->bi_end_io = bio_copy_kern_endio_read;
- bio->bi_private = data;
- } else {
- bio->bi_end_io = bio_copy_kern_endio;
- }
-
- return bio;
-
-cleanup:
- bio_free_pages(bio);
- bio_put(bio);
- return ERR_PTR(-ENOMEM);
-}
-
/*
* bio_set_pages_dirty() and bio_check_pages_dirty() are support functions
* for performing direct-IO in BIOs.
schedule_work(&bio_dirty_work);
}
-void update_io_ticks(struct hd_struct *part, unsigned long now)
+void update_io_ticks(struct hd_struct *part, unsigned long now, bool end)
{
unsigned long stamp;
again:
stamp = READ_ONCE(part->stamp);
if (unlikely(stamp != now)) {
if (likely(cmpxchg(&part->stamp, stamp, now) == stamp)) {
- __part_stat_add(part, io_ticks, 1);
+ __part_stat_add(part, io_ticks, end ? now - stamp : 1);
}
}
if (part->partno) {
part_stat_lock();
- update_io_ticks(part, jiffies);
+ update_io_ticks(part, jiffies, false);
part_stat_inc(part, ios[sgrp]);
part_stat_add(part, sectors[sgrp], sectors);
part_inc_in_flight(q, part, op_is_write(op));
part_stat_lock();
- update_io_ticks(part, now);
+ update_io_ticks(part, now, true);
part_stat_add(part, nsecs[sgrp], jiffies_to_nsecs(duration));
- part_stat_add(part, time_in_queue, duration);
part_dec_in_flight(q, part, op_is_write(req_op));
part_stat_unlock();
* blkcg_init_queue - initialize blkcg part of request queue
* @q: request_queue to initialize
*
- * Called from blk_alloc_queue_node(). Responsible for initializing blkcg
+ * Called from __blk_alloc_queue(). Responsible for initializing blkcg
* part of new request_queue @q.
*
* RETURNS:
blk_queue_flag_set(QUEUE_FLAG_NOMERGES, q);
blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, q);
- blk_queue_flag_set(QUEUE_FLAG_DYING, q);
/*
* Drain all requests queued before DYING marking. Set DEAD flag to
}
EXPORT_SYMBOL(blk_cleanup_queue);
-struct request_queue *blk_alloc_queue(gfp_t gfp_mask)
-{
- return blk_alloc_queue_node(gfp_mask, NUMA_NO_NODE);
-}
-EXPORT_SYMBOL(blk_alloc_queue);
-
/**
* blk_queue_enter() - try to increase q->q_usage_counter
* @q: request queue pointer
{
}
-/**
- * blk_alloc_queue_node - allocate a request queue
- * @gfp_mask: memory allocation flags
- * @node_id: NUMA node to allocate memory from
- */
-struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
+struct request_queue *__blk_alloc_queue(int node_id)
{
struct request_queue *q;
int ret;
q = kmem_cache_alloc_node(blk_requestq_cachep,
- gfp_mask | __GFP_ZERO, node_id);
+ GFP_KERNEL | __GFP_ZERO, node_id);
if (!q)
return NULL;
q->last_merge = NULL;
- q->id = ida_simple_get(&blk_queue_ida, 0, 0, gfp_mask);
+ q->id = ida_simple_get(&blk_queue_ida, 0, 0, GFP_KERNEL);
if (q->id < 0)
goto fail_q;
if (ret)
goto fail_id;
- q->backing_dev_info = bdi_alloc_node(gfp_mask, node_id);
+ q->backing_dev_info = bdi_alloc_node(GFP_KERNEL, node_id);
if (!q->backing_dev_info)
goto fail_split;
if (blkcg_init_queue(q))
goto fail_ref;
+ blk_queue_dma_alignment(q, 511);
+ blk_set_default_limits(&q->limits);
+
return q;
fail_ref:
kmem_cache_free(blk_requestq_cachep, q);
return NULL;
}
-EXPORT_SYMBOL(blk_alloc_queue_node);
+
+struct request_queue *blk_alloc_queue(make_request_fn make_request, int node_id)
+{
+ struct request_queue *q;
+
+ if (WARN_ON_ONCE(!make_request))
+ return NULL;
+
+ q = __blk_alloc_queue(node_id);
+ if (!q)
+ return NULL;
+ q->make_request_fn = make_request;
+ q->nr_requests = BLKDEV_MAX_RQ;
+ return q;
+}
+EXPORT_SYMBOL(blk_alloc_queue);
bool blk_get_queue(struct request_queue *q)
{
if (unlikely(blk_queue_enter(q, nowait ? BLK_MQ_REQ_NOWAIT : 0))) {
if (nowait && !blk_queue_dying(q))
- bio->bi_status = BLK_STS_AGAIN;
+ bio_wouldblock_error(bio);
else
- bio->bi_status = BLK_STS_IOERR;
- bio_endio(bio);
+ bio_io_error(bio);
return BLK_QC_T_NONE;
}
/**
* blk_cloned_rq_check_limits - Helper function to check a cloned request
- * for new the queue limits
+ * for the new queue limits
* @q: the queue
* @rq: the request being checked
*
part_stat_lock();
part = req->part;
- update_io_ticks(part, jiffies);
+ update_io_ticks(part, jiffies, true);
part_stat_inc(part, ios[sgrp]);
part_stat_add(part, nsecs[sgrp], now - req->start_time_ns);
- part_stat_add(part, time_in_queue, nsecs_to_jiffies64(now - req->start_time_ns));
part_dec_in_flight(req->q, part, rq_data_dir(req));
hd_struct_put(part);
rq->part = part;
}
- update_io_ticks(part, jiffies);
+ update_io_ticks(part, jiffies, false);
part_stat_unlock();
}
}
EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);
-/*
- * Copy attributes of the original request to the clone request.
- * The actual data parts (e.g. ->cmd, ->sense) are not copied.
- */
-static void __blk_rq_prep_clone(struct request *dst, struct request *src)
-{
- dst->__sector = blk_rq_pos(src);
- dst->__data_len = blk_rq_bytes(src);
- if (src->rq_flags & RQF_SPECIAL_PAYLOAD) {
- dst->rq_flags |= RQF_SPECIAL_PAYLOAD;
- dst->special_vec = src->special_vec;
- }
- dst->nr_phys_segments = src->nr_phys_segments;
- dst->ioprio = src->ioprio;
- dst->extra_len = src->extra_len;
-}
-
/**
* blk_rq_prep_clone - Helper function to setup clone request
* @rq: the request to be setup
*
* Description:
* Clones bios in @rq_src to @rq, and copies attributes of @rq_src to @rq.
- * The actual data parts of @rq_src (e.g. ->cmd, ->sense)
- * are not copied, and copying such parts is the caller's responsibility.
* Also, pages which the original bios are pointing to are not copied
* and the cloned bios just point same pages.
* So cloned bios must be completed before original bios, which means
rq->bio = rq->biotail = bio;
}
- __blk_rq_prep_clone(rq, rq_src);
+ /* Copy attributes of the original request to the clone request. */
+ rq->__sector = blk_rq_pos(rq_src);
+ rq->__data_len = blk_rq_bytes(rq_src);
+ if (rq_src->rq_flags & RQF_SPECIAL_PAYLOAD) {
+ rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
+ rq->special_vec = rq_src->special_vec;
+ }
+ rq->nr_phys_segments = rq_src->nr_phys_segments;
+ rq->ioprio = rq_src->ioprio;
+ rq->extra_len = rq_src->extra_len;
return 0;
*
* CONTEXT:
* spin_lock_irq(fq->mq_flush_lock)
- *
- * RETURNS:
- * %true if requests were added to the dispatch queue, %false otherwise.
*/
static void blk_flush_complete_seq(struct request *rq,
struct blk_flush_queue *fq,
if (!q)
return -ENXIO;
- /*
- * some block devices may not have their queue correctly set up here
- * (e.g. loop device without a backing file) and so issuing a flush
- * here will panic. Ensure there is a request function before issuing
- * the flush.
- */
- if (!q->make_request_fn)
- return -ENXIO;
-
bio = bio_alloc(gfp_mask, 0);
bio_set_dev(bio, bdev);
bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
}
EXPORT_SYMBOL(blkdev_issue_flush);
-struct blk_flush_queue *blk_alloc_flush_queue(struct request_queue *q,
- int node, int cmd_size, gfp_t flags)
+struct blk_flush_queue *blk_alloc_flush_queue(int node, int cmd_size,
+ gfp_t flags)
{
struct blk_flush_queue *fq;
int rq_sz = sizeof(struct request);
* making it impossible to determine icq_cache. Record it in @icq.
*/
icq->__rcu_icq_cache = et->icq_cache;
+ icq->flags |= ICQ_DESTROYED;
call_rcu(&icq->__rcu_head, icq_free_icq_rcu);
}
{
unsigned long flags;
+ rcu_read_lock();
while (!list_empty(icq_list)) {
struct io_cq *icq = list_entry(icq_list->next,
struct io_cq, q_node);
struct io_context *ioc = icq->ioc;
spin_lock_irqsave(&ioc->lock, flags);
+ if (icq->flags & ICQ_DESTROYED) {
+ spin_unlock_irqrestore(&ioc->lock, flags);
+ continue;
+ }
ioc_destroy_icq(icq);
spin_unlock_irqrestore(&ioc->lock, flags);
}
+ rcu_read_unlock();
}
/**
* If needed, tools/cgroup/iocost_coef_gen.py can be used to generate
* device-specific coefficients.
*
- * If needed, tools/cgroup/iocost_coef_gen.py can be used to generate
- * device-specific coefficients.
- *
* 2. Control Strategy
*
* The device virtual time (vtime) is used as the primary control metric.
#include "blk.h"
+struct bio_map_data {
+ int is_our_pages;
+ struct iov_iter iter;
+ struct iovec iov[];
+};
+
+static struct bio_map_data *bio_alloc_map_data(struct iov_iter *data,
+ gfp_t gfp_mask)
+{
+ struct bio_map_data *bmd;
+
+ if (data->nr_segs > UIO_MAXIOV)
+ return NULL;
+
+ bmd = kmalloc(struct_size(bmd, iov, data->nr_segs), gfp_mask);
+ if (!bmd)
+ return NULL;
+ memcpy(bmd->iov, data->iov, sizeof(struct iovec) * data->nr_segs);
+ bmd->iter = *data;
+ bmd->iter.iov = bmd->iov;
+ return bmd;
+}
+
+/**
+ * bio_copy_from_iter - copy all pages from iov_iter to bio
+ * @bio: The &struct bio which describes the I/O as destination
+ * @iter: iov_iter as source
+ *
+ * Copy all pages from iov_iter to bio.
+ * Returns 0 on success, or error on failure.
+ */
+static int bio_copy_from_iter(struct bio *bio, struct iov_iter *iter)
+{
+ struct bio_vec *bvec;
+ struct bvec_iter_all iter_all;
+
+ bio_for_each_segment_all(bvec, bio, iter_all) {
+ ssize_t ret;
+
+ ret = copy_page_from_iter(bvec->bv_page,
+ bvec->bv_offset,
+ bvec->bv_len,
+ iter);
+
+ if (!iov_iter_count(iter))
+ break;
+
+ if (ret < bvec->bv_len)
+ return -EFAULT;
+ }
+
+ return 0;
+}
+
+/**
+ * bio_copy_to_iter - copy all pages from bio to iov_iter
+ * @bio: The &struct bio which describes the I/O as source
+ * @iter: iov_iter as destination
+ *
+ * Copy all pages from bio to iov_iter.
+ * Returns 0 on success, or error on failure.
+ */
+static int bio_copy_to_iter(struct bio *bio, struct iov_iter iter)
+{
+ struct bio_vec *bvec;
+ struct bvec_iter_all iter_all;
+
+ bio_for_each_segment_all(bvec, bio, iter_all) {
+ ssize_t ret;
+
+ ret = copy_page_to_iter(bvec->bv_page,
+ bvec->bv_offset,
+ bvec->bv_len,
+ &iter);
+
+ if (!iov_iter_count(&iter))
+ break;
+
+ if (ret < bvec->bv_len)
+ return -EFAULT;
+ }
+
+ return 0;
+}
+
+/**
+ * bio_uncopy_user - finish previously mapped bio
+ * @bio: bio being terminated
+ *
+ * Free pages allocated from bio_copy_user_iov() and write back data
+ * to user space in case of a read.
+ */
+static int bio_uncopy_user(struct bio *bio)
+{
+ struct bio_map_data *bmd = bio->bi_private;
+ int ret = 0;
+
+ if (!bio_flagged(bio, BIO_NULL_MAPPED)) {
+ /*
+ * if we're in a workqueue, the request is orphaned, so
+ * don't copy into a random user address space, just free
+ * and return -EINTR so user space doesn't expect any data.
+ */
+ if (!current->mm)
+ ret = -EINTR;
+ else if (bio_data_dir(bio) == READ)
+ ret = bio_copy_to_iter(bio, bmd->iter);
+ if (bmd->is_our_pages)
+ bio_free_pages(bio);
+ }
+ kfree(bmd);
+ bio_put(bio);
+ return ret;
+}
+
+/**
+ * bio_copy_user_iov - copy user data to bio
+ * @q: destination block queue
+ * @map_data: pointer to the rq_map_data holding pages (if necessary)
+ * @iter: iovec iterator
+ * @gfp_mask: memory allocation flags
+ *
+ * Prepares and returns a bio for indirect user io, bouncing data
+ * to/from kernel pages as necessary. Must be paired with
+ * call bio_uncopy_user() on io completion.
+ */
+static struct bio *bio_copy_user_iov(struct request_queue *q,
+ struct rq_map_data *map_data, struct iov_iter *iter,
+ gfp_t gfp_mask)
+{
+ struct bio_map_data *bmd;
+ struct page *page;
+ struct bio *bio;
+ int i = 0, ret;
+ int nr_pages;
+ unsigned int len = iter->count;
+ unsigned int offset = map_data ? offset_in_page(map_data->offset) : 0;
+
+ bmd = bio_alloc_map_data(iter, gfp_mask);
+ if (!bmd)
+ return ERR_PTR(-ENOMEM);
+
+ /*
+ * We need to do a deep copy of the iov_iter including the iovecs.
+ * The caller provided iov might point to an on-stack or otherwise
+ * shortlived one.
+ */
+ bmd->is_our_pages = map_data ? 0 : 1;
+
+ nr_pages = DIV_ROUND_UP(offset + len, PAGE_SIZE);
+ if (nr_pages > BIO_MAX_PAGES)
+ nr_pages = BIO_MAX_PAGES;
+
+ ret = -ENOMEM;
+ bio = bio_kmalloc(gfp_mask, nr_pages);
+ if (!bio)
+ goto out_bmd;
+
+ ret = 0;
+
+ if (map_data) {
+ nr_pages = 1 << map_data->page_order;
+ i = map_data->offset / PAGE_SIZE;
+ }
+ while (len) {
+ unsigned int bytes = PAGE_SIZE;
+
+ bytes -= offset;
+
+ if (bytes > len)
+ bytes = len;
+
+ if (map_data) {
+ if (i == map_data->nr_entries * nr_pages) {
+ ret = -ENOMEM;
+ break;
+ }
+
+ page = map_data->pages[i / nr_pages];
+ page += (i % nr_pages);
+
+ i++;
+ } else {
+ page = alloc_page(q->bounce_gfp | gfp_mask);
+ if (!page) {
+ ret = -ENOMEM;
+ break;
+ }
+ }
+
+ if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes) {
+ if (!map_data)
+ __free_page(page);
+ break;
+ }
+
+ len -= bytes;
+ offset = 0;
+ }
+
+ if (ret)
+ goto cleanup;
+
+ if (map_data)
+ map_data->offset += bio->bi_iter.bi_size;
+
+ /*
+ * success
+ */
+ if ((iov_iter_rw(iter) == WRITE &&
+ (!map_data || !map_data->null_mapped)) ||
+ (map_data && map_data->from_user)) {
+ ret = bio_copy_from_iter(bio, iter);
+ if (ret)
+ goto cleanup;
+ } else {
+ if (bmd->is_our_pages)
+ zero_fill_bio(bio);
+ iov_iter_advance(iter, bio->bi_iter.bi_size);
+ }
+
+ bio->bi_private = bmd;
+ if (map_data && map_data->null_mapped)
+ bio_set_flag(bio, BIO_NULL_MAPPED);
+ return bio;
+cleanup:
+ if (!map_data)
+ bio_free_pages(bio);
+ bio_put(bio);
+out_bmd:
+ kfree(bmd);
+ return ERR_PTR(ret);
+}
+
+/**
+ * bio_map_user_iov - map user iovec into bio
+ * @q: the struct request_queue for the bio
+ * @iter: iovec iterator
+ * @gfp_mask: memory allocation flags
+ *
+ * Map the user space address into a bio suitable for io to a block
+ * device. Returns an error pointer in case of error.
+ */
+static struct bio *bio_map_user_iov(struct request_queue *q,
+ struct iov_iter *iter, gfp_t gfp_mask)
+{
+ int j;
+ struct bio *bio;
+ int ret;
+
+ if (!iov_iter_count(iter))
+ return ERR_PTR(-EINVAL);
+
+ bio = bio_kmalloc(gfp_mask, iov_iter_npages(iter, BIO_MAX_PAGES));
+ if (!bio)
+ return ERR_PTR(-ENOMEM);
+
+ while (iov_iter_count(iter)) {
+ struct page **pages;
+ ssize_t bytes;
+ size_t offs, added = 0;
+ int npages;
+
+ bytes = iov_iter_get_pages_alloc(iter, &pages, LONG_MAX, &offs);
+ if (unlikely(bytes <= 0)) {
+ ret = bytes ? bytes : -EFAULT;
+ goto out_unmap;
+ }
+
+ npages = DIV_ROUND_UP(offs + bytes, PAGE_SIZE);
+
+ if (unlikely(offs & queue_dma_alignment(q))) {
+ ret = -EINVAL;
+ j = 0;
+ } else {
+ for (j = 0; j < npages; j++) {
+ struct page *page = pages[j];
+ unsigned int n = PAGE_SIZE - offs;
+ bool same_page = false;
+
+ if (n > bytes)
+ n = bytes;
+
+ if (!__bio_add_pc_page(q, bio, page, n, offs,
+ &same_page)) {
+ if (same_page)
+ put_page(page);
+ break;
+ }
+
+ added += n;
+ bytes -= n;
+ offs = 0;
+ }
+ iov_iter_advance(iter, added);
+ }
+ /*
+ * release the pages we didn't map into the bio, if any
+ */
+ while (j < npages)
+ put_page(pages[j++]);
+ kvfree(pages);
+ /* couldn't stuff something into bio? */
+ if (bytes)
+ break;
+ }
+
+ bio_set_flag(bio, BIO_USER_MAPPED);
+
+ /*
+ * subtle -- if bio_map_user_iov() ended up bouncing a bio,
+ * it would normally disappear when its bi_end_io is run.
+ * however, we need it for the unmap, so grab an extra
+ * reference to it
+ */
+ bio_get(bio);
+ return bio;
+
+ out_unmap:
+ bio_release_pages(bio, false);
+ bio_put(bio);
+ return ERR_PTR(ret);
+}
+
+/**
+ * bio_unmap_user - unmap a bio
+ * @bio: the bio being unmapped
+ *
+ * Unmap a bio previously mapped by bio_map_user_iov(). Must be called from
+ * process context.
+ *
+ * bio_unmap_user() may sleep.
+ */
+static void bio_unmap_user(struct bio *bio)
+{
+ bio_release_pages(bio, bio_data_dir(bio) == READ);
+ bio_put(bio);
+ bio_put(bio);
+}
+
+static void bio_invalidate_vmalloc_pages(struct bio *bio)
+{
+#ifdef ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
+ if (bio->bi_private && !op_is_write(bio_op(bio))) {
+ unsigned long i, len = 0;
+
+ for (i = 0; i < bio->bi_vcnt; i++)
+ len += bio->bi_io_vec[i].bv_len;
+ invalidate_kernel_vmap_range(bio->bi_private, len);
+ }
+#endif
+}
+
+static void bio_map_kern_endio(struct bio *bio)
+{
+ bio_invalidate_vmalloc_pages(bio);
+ bio_put(bio);
+}
+
+/**
+ * bio_map_kern - map kernel address into bio
+ * @q: the struct request_queue for the bio
+ * @data: pointer to buffer to map
+ * @len: length in bytes
+ * @gfp_mask: allocation flags for bio allocation
+ *
+ * Map the kernel address into a bio suitable for io to a block
+ * device. Returns an error pointer in case of error.
+ */
+static struct bio *bio_map_kern(struct request_queue *q, void *data,
+ unsigned int len, gfp_t gfp_mask)
+{
+ unsigned long kaddr = (unsigned long)data;
+ unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ unsigned long start = kaddr >> PAGE_SHIFT;
+ const int nr_pages = end - start;
+ bool is_vmalloc = is_vmalloc_addr(data);
+ struct page *page;
+ int offset, i;
+ struct bio *bio;
+
+ bio = bio_kmalloc(gfp_mask, nr_pages);
+ if (!bio)
+ return ERR_PTR(-ENOMEM);
+
+ if (is_vmalloc) {
+ flush_kernel_vmap_range(data, len);
+ bio->bi_private = data;
+ }
+
+ offset = offset_in_page(kaddr);
+ for (i = 0; i < nr_pages; i++) {
+ unsigned int bytes = PAGE_SIZE - offset;
+
+ if (len <= 0)
+ break;
+
+ if (bytes > len)
+ bytes = len;
+
+ if (!is_vmalloc)
+ page = virt_to_page(data);
+ else
+ page = vmalloc_to_page(data);
+ if (bio_add_pc_page(q, bio, page, bytes,
+ offset) < bytes) {
+ /* we don't support partial mappings */
+ bio_put(bio);
+ return ERR_PTR(-EINVAL);
+ }
+
+ data += bytes;
+ len -= bytes;
+ offset = 0;
+ }
+
+ bio->bi_end_io = bio_map_kern_endio;
+ return bio;
+}
+
+static void bio_copy_kern_endio(struct bio *bio)
+{
+ bio_free_pages(bio);
+ bio_put(bio);
+}
+
+static void bio_copy_kern_endio_read(struct bio *bio)
+{
+ char *p = bio->bi_private;
+ struct bio_vec *bvec;
+ struct bvec_iter_all iter_all;
+
+ bio_for_each_segment_all(bvec, bio, iter_all) {
+ memcpy(p, page_address(bvec->bv_page), bvec->bv_len);
+ p += bvec->bv_len;
+ }
+
+ bio_copy_kern_endio(bio);
+}
+
+/**
+ * bio_copy_kern - copy kernel address into bio
+ * @q: the struct request_queue for the bio
+ * @data: pointer to buffer to copy
+ * @len: length in bytes
+ * @gfp_mask: allocation flags for bio and page allocation
+ * @reading: data direction is READ
+ *
+ * copy the kernel address into a bio suitable for io to a block
+ * device. Returns an error pointer in case of error.
+ */
+static struct bio *bio_copy_kern(struct request_queue *q, void *data,
+ unsigned int len, gfp_t gfp_mask, int reading)
+{
+ unsigned long kaddr = (unsigned long)data;
+ unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ unsigned long start = kaddr >> PAGE_SHIFT;
+ struct bio *bio;
+ void *p = data;
+ int nr_pages = 0;
+
+ /*
+ * Overflow, abort
+ */
+ if (end < start)
+ return ERR_PTR(-EINVAL);
+
+ nr_pages = end - start;
+ bio = bio_kmalloc(gfp_mask, nr_pages);
+ if (!bio)
+ return ERR_PTR(-ENOMEM);
+
+ while (len) {
+ struct page *page;
+ unsigned int bytes = PAGE_SIZE;
+
+ if (bytes > len)
+ bytes = len;
+
+ page = alloc_page(q->bounce_gfp | gfp_mask);
+ if (!page)
+ goto cleanup;
+
+ if (!reading)
+ memcpy(page_address(page), p, bytes);
+
+ if (bio_add_pc_page(q, bio, page, bytes, 0) < bytes)
+ break;
+
+ len -= bytes;
+ p += bytes;
+ }
+
+ if (reading) {
+ bio->bi_end_io = bio_copy_kern_endio_read;
+ bio->bi_private = data;
+ } else {
+ bio->bi_end_io = bio_copy_kern_endio;
+ }
+
+ return bio;
+
+cleanup:
+ bio_free_pages(bio);
+ bio_put(bio);
+ return ERR_PTR(-ENOMEM);
+}
+
/*
* Append a bio to a passthrough request. Only works if the bio can be merged
* into the request based on the driver constraints.
#define BLK_MQ_RESOURCE_DELAY 3 /* ms units */
+static void blk_mq_handle_dev_resource(struct request *rq,
+ struct list_head *list)
+{
+ struct request *next =
+ list_first_entry_or_null(list, struct request, queuelist);
+
+ /*
+ * If an I/O scheduler has been configured and we got a driver tag for
+ * the next request already, free it.
+ */
+ if (next)
+ blk_mq_put_driver_tag(next);
+
+ list_add(&rq->queuelist, list);
+ __blk_mq_requeue_request(rq);
+}
+
/*
* Returns true if we did some work AND can potentially do more.
*/
ret = q->mq_ops->queue_rq(hctx, &bd);
if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) {
- /*
- * If an I/O scheduler has been configured and we got a
- * driver tag for the next request already, free it
- * again.
- */
- if (!list_empty(list)) {
- nxt = list_first_entry(list, struct request, queuelist);
- blk_mq_put_driver_tag(nxt);
- }
- list_add(&rq->queuelist, list);
- __blk_mq_requeue_request(rq);
+ blk_mq_handle_dev_resource(rq, list);
break;
}
init_waitqueue_func_entry(&hctx->dispatch_wait, blk_mq_dispatch_wake);
INIT_LIST_HEAD(&hctx->dispatch_wait.entry);
- hctx->fq = blk_alloc_flush_queue(q, hctx->numa_node, set->cmd_size,
- gfp);
+ hctx->fq = blk_alloc_flush_queue(hctx->numa_node, set->cmd_size, gfp);
if (!hctx->fq)
goto free_bitmap;
blk_mq_sysfs_deinit(q);
}
-struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
+struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set,
+ void *queuedata)
{
struct request_queue *uninit_q, *q;
- uninit_q = blk_alloc_queue_node(GFP_KERNEL, set->numa_node);
+ uninit_q = __blk_alloc_queue(set->numa_node);
if (!uninit_q)
return ERR_PTR(-ENOMEM);
+ uninit_q->queuedata = queuedata;
/*
* Initialize the queue without an elevator. device_add_disk() will do
return q;
}
+EXPORT_SYMBOL_GPL(blk_mq_init_queue_data);
+
+struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
+{
+ return blk_mq_init_queue_data(set, NULL);
+}
EXPORT_SYMBOL(blk_mq_init_queue);
/*
memcpy(new_hctxs, hctxs, q->nr_hw_queues *
sizeof(*hctxs));
q->queue_hw_ctx = new_hctxs;
- q->nr_hw_queues = set->nr_hw_queues;
kfree(hctxs);
hctxs = new_hctxs;
}
INIT_LIST_HEAD(&q->requeue_list);
spin_lock_init(&q->requeue_lock);
- blk_queue_make_request(q, blk_mq_make_request);
-
- /*
- * Do this after blk_queue_make_request() overrides it...
- */
+ q->make_request_fn = blk_mq_make_request;
q->nr_requests = set->queue_depth;
/*
static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
{
+ /*
+ * blk_mq_map_queues() and multiple .map_queues() implementations
+ * expect that set->map[HCTX_TYPE_DEFAULT].nr_queues is set to the
+ * number of hardware queues.
+ */
+ if (set->nr_maps == 1)
+ set->map[HCTX_TYPE_DEFAULT].nr_queues = set->nr_hw_queues;
+
if (set->ops->map_queues && !is_kdump_kernel()) {
int i;
EXPORT_SYMBOL(blk_set_stacking_limits);
/**
- * blk_queue_make_request - define an alternate make_request function for a device
- * @q: the request queue for the device to be affected
- * @mfn: the alternate make_request function
- *
- * Description:
- * The normal way for &struct bios to be passed to a device
- * driver is for them to be collected into requests on a request
- * queue, and then to allow the device driver to select requests
- * off that queue when it is ready. This works well for many block
- * devices. However some block devices (typically virtual devices
- * such as md or lvm) do not benefit from the processing on the
- * request queue, and are served best by having the requests passed
- * directly to them. This can be achieved by providing a function
- * to blk_queue_make_request().
- *
- * Caveat:
- * The driver that does this *must* be able to deal appropriately
- * with buffers in "highmemory". This can be accomplished by either calling
- * kmap_atomic() to get a temporary kernel mapping, or by calling
- * blk_queue_bounce() to create a buffer in normal memory.
- **/
-void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn)
-{
- /*
- * set defaults
- */
- q->nr_requests = BLKDEV_MAX_RQ;
-
- q->make_request_fn = mfn;
- blk_queue_dma_alignment(q, 511);
-
- blk_set_default_limits(&q->limits);
-}
-EXPORT_SYMBOL(blk_queue_make_request);
-
-/**
* blk_queue_bounce_limit - set bounce buffer limit for queue
* @q: the request queue for the device
* @max_addr: the maximum address the device can handle
printk(KERN_NOTICE "%s: Warning: Device %s is misaligned\n",
top, bottom);
}
+
+ t->backing_dev_info->io_pages =
+ t->limits.max_sectors >> (PAGE_SHIFT - 9);
}
EXPORT_SYMBOL(disk_stack_limits);
#include "blk.h"
+#define ZONE_COND_NAME(name) [BLK_ZONE_COND_##name] = #name
+static const char *const zone_cond_name[] = {
+ ZONE_COND_NAME(NOT_WP),
+ ZONE_COND_NAME(EMPTY),
+ ZONE_COND_NAME(IMP_OPEN),
+ ZONE_COND_NAME(EXP_OPEN),
+ ZONE_COND_NAME(CLOSED),
+ ZONE_COND_NAME(READONLY),
+ ZONE_COND_NAME(FULL),
+ ZONE_COND_NAME(OFFLINE),
+};
+#undef ZONE_COND_NAME
+
+/**
+ * blk_zone_cond_str - Return string XXX in BLK_ZONE_COND_XXX.
+ * @zone_cond: BLK_ZONE_COND_XXX.
+ *
+ * Description: Centralize block layer function to convert BLK_ZONE_COND_XXX
+ * into string format. Useful in the debugging and tracing zone conditions. For
+ * invalid BLK_ZONE_COND_XXX it returns string "UNKNOWN".
+ */
+const char *blk_zone_cond_str(enum blk_zone_cond zone_cond)
+{
+ static const char *zone_cond_str = "UNKNOWN";
+
+ if (zone_cond < ARRAY_SIZE(zone_cond_name) && zone_cond_name[zone_cond])
+ zone_cond_str = zone_cond_name[zone_cond];
+
+ return zone_cond_str;
+}
+EXPORT_SYMBOL_GPL(blk_zone_cond_str);
+
static inline sector_t blk_zone_start(struct request_queue *q,
sector_t sector)
{
if (!op_is_zone_mgmt(op))
return -EOPNOTSUPP;
- if (!nr_sectors || end_sector > capacity)
+ if (end_sector <= sector || end_sector > capacity)
/* Out of range */
return -EINVAL;
#include <linux/idr.h>
#include <linux/blk-mq.h>
+#include <linux/part_stat.h>
#include <xen/xen.h>
#include "blk-mq.h"
#include "blk-mq-sched.h"
return hctx->fq->flush_rq == req;
}
-struct blk_flush_queue *blk_alloc_flush_queue(struct request_queue *q,
- int node, int cmd_size, gfp_t flags);
+struct blk_flush_queue *blk_alloc_flush_queue(int node, int cmd_size,
+ gfp_t flags);
void blk_free_flush_queue(struct blk_flush_queue *q);
void blk_freeze_queue(struct request_queue *q);
return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1],
bip_next->bip_vec[0].bv_offset);
}
+
+void blk_integrity_add(struct gendisk *);
+void blk_integrity_del(struct gendisk *);
#else /* CONFIG_BLK_DEV_INTEGRITY */
static inline bool integrity_req_gap_back_merge(struct request *req,
struct bio *next)
static inline void bio_integrity_free(struct bio *bio)
{
}
+static inline void blk_integrity_add(struct gendisk *disk)
+{
+}
+static inline void blk_integrity_del(struct gendisk *disk)
+{
+}
#endif /* CONFIG_BLK_DEV_INTEGRITY */
unsigned long blk_rq_timeout(unsigned long timeout);
struct hd_struct *__disk_get_part(struct gendisk *disk, int partno);
+ssize_t part_size_show(struct device *dev, struct device_attribute *attr,
+ char *buf);
+ssize_t part_stat_show(struct device *dev, struct device_attribute *attr,
+ char *buf);
+ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,
+ char *buf);
+ssize_t part_fail_show(struct device *dev, struct device_attribute *attr,
+ char *buf);
+ssize_t part_fail_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count);
+
#ifdef CONFIG_FAIL_IO_TIMEOUT
int blk_should_fake_timeout(struct request_queue *);
ssize_t part_timeout_show(struct device *, struct device_attribute *, char *);
static inline void blk_queue_free_zone_bitmaps(struct request_queue *q) {}
#endif
+void part_dec_in_flight(struct request_queue *q, struct hd_struct *part,
+ int rw);
+void part_inc_in_flight(struct request_queue *q, struct hd_struct *part,
+ int rw);
+void update_io_ticks(struct hd_struct *part, unsigned long now, bool end);
+struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector);
+
+int blk_alloc_devt(struct hd_struct *part, dev_t *devt);
+void blk_free_devt(dev_t devt);
+void blk_invalidate_devt(dev_t devt);
+char *disk_name(struct gendisk *hd, int partno, char *buf);
+#define ADDPART_FLAG_NONE 0
+#define ADDPART_FLAG_RAID 1
+#define ADDPART_FLAG_WHOLEDISK 2
+struct hd_struct *__must_check add_partition(struct gendisk *disk, int partno,
+ sector_t start, sector_t len, int flags,
+ struct partition_meta_info *info);
+void __delete_partition(struct percpu_ref *ref);
+void delete_partition(struct gendisk *disk, int partno);
+int disk_expand_part_tbl(struct gendisk *disk, int target);
+
+static inline int hd_ref_init(struct hd_struct *part)
+{
+ if (percpu_ref_init(&part->ref, __delete_partition, 0,
+ GFP_KERNEL))
+ return -ENOMEM;
+ return 0;
+}
+
+static inline void hd_struct_get(struct hd_struct *part)
+{
+ percpu_ref_get(&part->ref);
+}
+
+static inline int hd_struct_try_get(struct hd_struct *part)
+{
+ return percpu_ref_tryget_live(&part->ref);
+}
+
+static inline void hd_struct_put(struct hd_struct *part)
+{
+ percpu_ref_put(&part->ref);
+}
+
+static inline void hd_struct_kill(struct hd_struct *part)
+{
+ percpu_ref_kill(&part->ref);
+}
+
+static inline void hd_free_part(struct hd_struct *part)
+{
+ free_part_stats(part);
+ kfree(part->info);
+ percpu_ref_exit(&part->ref);
+}
+
+/*
+ * Any access of part->nr_sects which is not protected by partition
+ * bd_mutex or gendisk bdev bd_mutex, should be done using this
+ * accessor function.
+ *
+ * Code written along the lines of i_size_read() and i_size_write().
+ * CONFIG_PREEMPTION case optimizes the case of UP kernel with preemption
+ * on.
+ */
+static inline sector_t part_nr_sects_read(struct hd_struct *part)
+{
+#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
+ sector_t nr_sects;
+ unsigned seq;
+ do {
+ seq = read_seqcount_begin(&part->nr_sects_seq);
+ nr_sects = part->nr_sects;
+ } while (read_seqcount_retry(&part->nr_sects_seq, seq));
+ return nr_sects;
+#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
+ sector_t nr_sects;
+
+ preempt_disable();
+ nr_sects = part->nr_sects;
+ preempt_enable();
+ return nr_sects;
+#else
+ return part->nr_sects;
+#endif
+}
+
+/*
+ * Should be called with mutex lock held (typically bd_mutex) of partition
+ * to provide mutual exlusion among writers otherwise seqcount might be
+ * left in wrong state leaving the readers spinning infinitely.
+ */
+static inline void part_nr_sects_write(struct hd_struct *part, sector_t size)
+{
+#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
+ write_seqcount_begin(&part->nr_sects_seq);
+ part->nr_sects = size;
+ write_seqcount_end(&part->nr_sects_seq);
+#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
+ preempt_disable();
+ part->nr_sects = size;
+ preempt_enable();
+#else
+ part->nr_sects = size;
+#endif
+}
+
+struct request_queue *__blk_alloc_queue(int node_id);
+
+int __bio_add_pc_page(struct request_queue *q, struct bio *bio,
+ struct page *page, unsigned int len, unsigned int offset,
+ bool *same_page);
+
#endif /* BLK_INTERNAL_H */
*/
#include <linux/module.h>
+#include <linux/ctype.h>
#include <linux/fs.h>
#include <linux/genhd.h>
#include <linux/kdev_t.h>
#include "blk.h"
static DEFINE_MUTEX(block_class_lock);
-struct kobject *block_depr;
+static struct kobject *block_depr;
/* for extended dynamic devt allocation, currently only one major is used */
#define NR_EXT_DEVT (1 << MINORBITS)
static void disk_del_events(struct gendisk *disk);
static void disk_release_events(struct gendisk *disk);
+/*
+ * Set disk capacity and notify if the size is not currently
+ * zero and will not be set to zero
+ */
+void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
+ bool revalidate)
+{
+ sector_t capacity = get_capacity(disk);
+
+ set_capacity(disk, size);
+
+ if (revalidate)
+ revalidate_disk(disk);
+
+ if (capacity != size && capacity != 0 && size != 0) {
+ char *envp[] = { "RESIZE=1", NULL };
+
+ kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp);
+ }
+}
+
+EXPORT_SYMBOL_GPL(set_capacity_revalidate_and_notify);
+
+/*
+ * Format the device name of the indicated disk into the supplied buffer and
+ * return a pointer to that same buffer for convenience.
+ */
+char *disk_name(struct gendisk *hd, int partno, char *buf)
+{
+ if (!partno)
+ snprintf(buf, BDEVNAME_SIZE, "%s", hd->disk_name);
+ else if (isdigit(hd->disk_name[strlen(hd->disk_name)-1]))
+ snprintf(buf, BDEVNAME_SIZE, "%sp%d", hd->disk_name, partno);
+ else
+ snprintf(buf, BDEVNAME_SIZE, "%s%d", hd->disk_name, partno);
+
+ return buf;
+}
+
+const char *bdevname(struct block_device *bdev, char *buf)
+{
+ return disk_name(bdev->bd_disk, bdev->bd_part->partno, buf);
+}
+EXPORT_SYMBOL(bdevname);
+
+#ifdef CONFIG_SMP
+static void part_stat_read_all(struct hd_struct *part, struct disk_stats *stat)
+{
+ int cpu;
+
+ memset(stat, 0, sizeof(struct disk_stats));
+ for_each_possible_cpu(cpu) {
+ struct disk_stats *ptr = per_cpu_ptr(part->dkstats, cpu);
+ int group;
+
+ for (group = 0; group < NR_STAT_GROUPS; group++) {
+ stat->nsecs[group] += ptr->nsecs[group];
+ stat->sectors[group] += ptr->sectors[group];
+ stat->ios[group] += ptr->ios[group];
+ stat->merges[group] += ptr->merges[group];
+ }
+
+ stat->io_ticks += ptr->io_ticks;
+ }
+}
+#else /* CONFIG_SMP */
+static void part_stat_read_all(struct hd_struct *part, struct disk_stats *stat)
+{
+ memcpy(stat, &part->dkstats, sizeof(struct disk_stats));
+}
+#endif /* CONFIG_SMP */
+
void part_inc_in_flight(struct request_queue *q, struct hd_struct *part, int rw)
{
if (queue_is_mq(q))
part_stat_local_dec(&part_to_disk(part)->part0, in_flight[rw]);
}
-unsigned int part_in_flight(struct request_queue *q, struct hd_struct *part)
+static unsigned int part_in_flight(struct request_queue *q,
+ struct hd_struct *part)
{
int cpu;
unsigned int inflight;
return inflight;
}
-void part_in_flight_rw(struct request_queue *q, struct hd_struct *part,
- unsigned int inflight[2])
+static void part_in_flight_rw(struct request_queue *q, struct hd_struct *part,
+ unsigned int inflight[2])
{
int cpu;
return part;
}
-EXPORT_SYMBOL_GPL(disk_get_part);
/**
* disk_part_iter_init - initialize partition iterator
}
return &disk->part0;
}
-EXPORT_SYMBOL_GPL(disk_map_sector_rcu);
/**
* disk_has_partitions
}
return disk;
}
-EXPORT_SYMBOL(get_gendisk);
/**
* bdget_disk - do bdget() by gendisk and partition number
return sprintf(buf, "%d\n", get_disk_ro(disk) ? 1 : 0);
}
+ssize_t part_size_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct hd_struct *p = dev_to_part(dev);
+
+ return sprintf(buf, "%llu\n",
+ (unsigned long long)part_nr_sects_read(p));
+}
+
+ssize_t part_stat_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct hd_struct *p = dev_to_part(dev);
+ struct request_queue *q = part_to_disk(p)->queue;
+ struct disk_stats stat;
+ unsigned int inflight;
+
+ part_stat_read_all(p, &stat);
+ inflight = part_in_flight(q, p);
+
+ return sprintf(buf,
+ "%8lu %8lu %8llu %8u "
+ "%8lu %8lu %8llu %8u "
+ "%8u %8u %8u "
+ "%8lu %8lu %8llu %8u "
+ "%8lu %8u"
+ "\n",
+ stat.ios[STAT_READ],
+ stat.merges[STAT_READ],
+ (unsigned long long)stat.sectors[STAT_READ],
+ (unsigned int)div_u64(stat.nsecs[STAT_READ], NSEC_PER_MSEC),
+ stat.ios[STAT_WRITE],
+ stat.merges[STAT_WRITE],
+ (unsigned long long)stat.sectors[STAT_WRITE],
+ (unsigned int)div_u64(stat.nsecs[STAT_WRITE], NSEC_PER_MSEC),
+ inflight,
+ jiffies_to_msecs(stat.io_ticks),
+ (unsigned int)div_u64(stat.nsecs[STAT_READ] +
+ stat.nsecs[STAT_WRITE] +
+ stat.nsecs[STAT_DISCARD] +
+ stat.nsecs[STAT_FLUSH],
+ NSEC_PER_MSEC),
+ stat.ios[STAT_DISCARD],
+ stat.merges[STAT_DISCARD],
+ (unsigned long long)stat.sectors[STAT_DISCARD],
+ (unsigned int)div_u64(stat.nsecs[STAT_DISCARD], NSEC_PER_MSEC),
+ stat.ios[STAT_FLUSH],
+ (unsigned int)div_u64(stat.nsecs[STAT_FLUSH], NSEC_PER_MSEC));
+}
+
+ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct hd_struct *p = dev_to_part(dev);
+ struct request_queue *q = part_to_disk(p)->queue;
+ unsigned int inflight[2];
+
+ part_in_flight_rw(q, p, inflight);
+ return sprintf(buf, "%8u %8u\n", inflight[0], inflight[1]);
+}
+
static ssize_t disk_capability_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
static DEVICE_ATTR(stat, 0444, part_stat_show, NULL);
static DEVICE_ATTR(inflight, 0444, part_inflight_show, NULL);
static DEVICE_ATTR(badblocks, 0644, disk_badblocks_show, disk_badblocks_store);
+
#ifdef CONFIG_FAIL_MAKE_REQUEST
+ssize_t part_fail_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct hd_struct *p = dev_to_part(dev);
+
+ return sprintf(buf, "%d\n", p->make_it_fail);
+}
+
+ssize_t part_fail_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct hd_struct *p = dev_to_part(dev);
+ int i;
+
+ if (count > 0 && sscanf(buf, "%d", &i) > 0)
+ p->make_it_fail = (i == 0) ? 0 : 1;
+
+ return count;
+}
+
static struct device_attribute dev_attr_fail =
__ATTR(make-it-fail, 0644, part_fail_show, part_fail_store);
-#endif
+#endif /* CONFIG_FAIL_MAKE_REQUEST */
+
#ifdef CONFIG_FAIL_IO_TIMEOUT
static struct device_attribute dev_attr_fail_timeout =
__ATTR(io-timeout-fail, 0644, part_timeout_show, part_timeout_store);
{
struct gendisk *disk = dev_to_disk(dev);
- if (disk->devnode)
- return disk->devnode(disk, mode);
+ if (disk->fops->devnode)
+ return disk->fops->devnode(disk, mode);
return NULL;
}
struct hd_struct *hd;
char buf[BDEVNAME_SIZE];
unsigned int inflight;
+ struct disk_stats stat;
/*
if (&disk_to_dev(gp)->kobj.entry == block_class.devices.next)
disk_part_iter_init(&piter, gp, DISK_PITER_INCL_EMPTY_PART0);
while ((hd = disk_part_iter_next(&piter))) {
+ part_stat_read_all(hd, &stat);
inflight = part_in_flight(gp->queue, hd);
+
seq_printf(seqf, "%4d %7d %s "
"%lu %lu %lu %u "
"%lu %lu %lu %u "
"\n",
MAJOR(part_devt(hd)), MINOR(part_devt(hd)),
disk_name(gp, hd->partno, buf),
- part_stat_read(hd, ios[STAT_READ]),
- part_stat_read(hd, merges[STAT_READ]),
- part_stat_read(hd, sectors[STAT_READ]),
- (unsigned int)part_stat_read_msecs(hd, STAT_READ),
- part_stat_read(hd, ios[STAT_WRITE]),
- part_stat_read(hd, merges[STAT_WRITE]),
- part_stat_read(hd, sectors[STAT_WRITE]),
- (unsigned int)part_stat_read_msecs(hd, STAT_WRITE),
+ stat.ios[STAT_READ],
+ stat.merges[STAT_READ],
+ stat.sectors[STAT_READ],
+ (unsigned int)div_u64(stat.nsecs[STAT_READ],
+ NSEC_PER_MSEC),
+ stat.ios[STAT_WRITE],
+ stat.merges[STAT_WRITE],
+ stat.sectors[STAT_WRITE],
+ (unsigned int)div_u64(stat.nsecs[STAT_WRITE],
+ NSEC_PER_MSEC),
inflight,
- jiffies_to_msecs(part_stat_read(hd, io_ticks)),
- jiffies_to_msecs(part_stat_read(hd, time_in_queue)),
- part_stat_read(hd, ios[STAT_DISCARD]),
- part_stat_read(hd, merges[STAT_DISCARD]),
- part_stat_read(hd, sectors[STAT_DISCARD]),
- (unsigned int)part_stat_read_msecs(hd, STAT_DISCARD),
- part_stat_read(hd, ios[STAT_FLUSH]),
- (unsigned int)part_stat_read_msecs(hd, STAT_FLUSH)
+ jiffies_to_msecs(stat.io_ticks),
+ (unsigned int)div_u64(stat.nsecs[STAT_READ] +
+ stat.nsecs[STAT_WRITE] +
+ stat.nsecs[STAT_DISCARD] +
+ stat.nsecs[STAT_FLUSH],
+ NSEC_PER_MSEC),
+ stat.ios[STAT_DISCARD],
+ stat.merges[STAT_DISCARD],
+ stat.sectors[STAT_DISCARD],
+ (unsigned int)div_u64(stat.nsecs[STAT_DISCARD],
+ NSEC_PER_MSEC),
+ stat.ios[STAT_FLUSH],
+ (unsigned int)div_u64(stat.nsecs[STAT_FLUSH],
+ NSEC_PER_MSEC)
);
}
disk_part_iter_exit(&piter);
class_dev_iter_exit(&iter);
return devt;
}
-EXPORT_SYMBOL(blk_lookup_devt);
struct gendisk *__alloc_disk_node(int minors, int node_id)
{
#include <linux/blktrace_api.h>
#include <linux/pr.h>
#include <linux/uaccess.h>
+#include "blk.h"
static int blkpg_do_ioctl(struct block_device *bdev,
struct blkpg_partition __user *upart, int op)
#define DTAERROR_NO_METHOD_STATUS 0x89
#define GENERIC_HOST_SESSION_NUM 0x41
+#define FIRST_TPER_SESSION_NUM 4096
#define TPER_SYNC_SUPPORTED 0x01
#define MBR_ENABLED_MASK 0x10
# Makefile for the linux kernel.
#
-obj-$(CONFIG_BLOCK) := check.o
-
+obj-$(CONFIG_BLOCK) += core.o
obj-$(CONFIG_ACORN_PARTITION) += acorn.o
obj-$(CONFIG_AMIGA_PARTITION) += amiga.o
obj-$(CONFIG_ATARI_PARTITION) += atari.o
#include <linux/adfs_fs.h>
#include "check.h"
-#include "acorn.h"
/*
* Partition types. (Oh for reusability)
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * linux/fs/partitions/acorn.h
- *
- * Copyright (C) 1996-2001 Russell King.
- *
- * I _hate_ this partitioning mess - why can't we have one defined
- * format, and everyone stick to it?
- */
-
-int adfspart_check_CUMANA(struct parsed_partitions *state);
-int adfspart_check_ADFS(struct parsed_partitions *state);
-int adfspart_check_ICS(struct parsed_partitions *state);
-int adfspart_check_POWERTEC(struct parsed_partitions *state);
-int adfspart_check_EESOX(struct parsed_partitions *state);
*/
#include "check.h"
-#include "aix.h"
struct lvm_rec {
char lvm_id[4]; /* "_LVM" */
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-extern int aix_partition(struct parsed_partitions *state);
#include <linux/affs_hardblocks.h>
#include "check.h"
-#include "amiga.h"
static __inline__ u32
checksum_block(__be32 *m, int size)
goto rdb_done;
data = read_part_sector(state, blk, §);
if (!data) {
- if (warn_no_part)
- pr_err("Dev %s: unable to read RDB block %d\n",
- bdevname(state->bdev, b), blk);
+ pr_err("Dev %s: unable to read RDB block %d\n",
+ bdevname(state->bdev, b), blk);
res = -1;
goto rdb_done;
}
blk *= blksize; /* Read in terms partition table understands */
data = read_part_sector(state, blk, §);
if (!data) {
- if (warn_no_part)
- pr_err("Dev %s: unable to read partition block %d\n",
- bdevname(state->bdev, b), blk);
+ pr_err("Dev %s: unable to read partition block %d\n",
+ bdevname(state->bdev, b), blk);
res = -1;
goto rdb_done;
}
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * fs/partitions/amiga.h
- */
-
-int amiga_partition(struct parsed_partitions *state);
-
u16 checksum; /* checksum for bootable disks */
} __packed;
-int atari_partition(struct parsed_partitions *state);
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0
-/*
- * fs/partitions/check.c
- *
- * Code extracted from drivers/block/genhd.c
- * Copyright (C) 1991-1998 Linus Torvalds
- * Re-organised Feb 1998 Russell King
- *
- * We now have independent partition support from the
- * block drivers, which allows all the partition code to
- * be grouped in one location, and it to be mostly self
- * contained.
- *
- * Added needed MAJORS for new pairs, {hdi,hdj}, {hdk,hdl}
- */
-
-#include <linux/slab.h>
-#include <linux/vmalloc.h>
-#include <linux/ctype.h>
-#include <linux/genhd.h>
-
-#include "check.h"
-
-#include "acorn.h"
-#include "amiga.h"
-#include "atari.h"
-#include "ldm.h"
-#include "mac.h"
-#include "msdos.h"
-#include "osf.h"
-#include "sgi.h"
-#include "sun.h"
-#include "ibm.h"
-#include "ultrix.h"
-#include "efi.h"
-#include "karma.h"
-#include "sysv68.h"
-#include "cmdline.h"
-
-int warn_no_part = 1; /*This is ugly: should make genhd removable media aware*/
-
-static int (*check_part[])(struct parsed_partitions *) = {
- /*
- * Probe partition formats with tables at disk address 0
- * that also have an ADFS boot block at 0xdc0.
- */
-#ifdef CONFIG_ACORN_PARTITION_ICS
- adfspart_check_ICS,
-#endif
-#ifdef CONFIG_ACORN_PARTITION_POWERTEC
- adfspart_check_POWERTEC,
-#endif
-#ifdef CONFIG_ACORN_PARTITION_EESOX
- adfspart_check_EESOX,
-#endif
-
- /*
- * Now move on to formats that only have partition info at
- * disk address 0xdc0. Since these may also have stale
- * PC/BIOS partition tables, they need to come before
- * the msdos entry.
- */
-#ifdef CONFIG_ACORN_PARTITION_CUMANA
- adfspart_check_CUMANA,
-#endif
-#ifdef CONFIG_ACORN_PARTITION_ADFS
- adfspart_check_ADFS,
-#endif
-
-#ifdef CONFIG_CMDLINE_PARTITION
- cmdline_partition,
-#endif
-#ifdef CONFIG_EFI_PARTITION
- efi_partition, /* this must come before msdos */
-#endif
-#ifdef CONFIG_SGI_PARTITION
- sgi_partition,
-#endif
-#ifdef CONFIG_LDM_PARTITION
- ldm_partition, /* this must come before msdos */
-#endif
-#ifdef CONFIG_MSDOS_PARTITION
- msdos_partition,
-#endif
-#ifdef CONFIG_OSF_PARTITION
- osf_partition,
-#endif
-#ifdef CONFIG_SUN_PARTITION
- sun_partition,
-#endif
-#ifdef CONFIG_AMIGA_PARTITION
- amiga_partition,
-#endif
-#ifdef CONFIG_ATARI_PARTITION
- atari_partition,
-#endif
-#ifdef CONFIG_MAC_PARTITION
- mac_partition,
-#endif
-#ifdef CONFIG_ULTRIX_PARTITION
- ultrix_partition,
-#endif
-#ifdef CONFIG_IBM_PARTITION
- ibm_partition,
-#endif
-#ifdef CONFIG_KARMA_PARTITION
- karma_partition,
-#endif
-#ifdef CONFIG_SYSV68_PARTITION
- sysv68_partition,
-#endif
- NULL
-};
-
-static struct parsed_partitions *allocate_partitions(struct gendisk *hd)
-{
- struct parsed_partitions *state;
- int nr;
-
- state = kzalloc(sizeof(*state), GFP_KERNEL);
- if (!state)
- return NULL;
-
- nr = disk_max_parts(hd);
- state->parts = vzalloc(array_size(nr, sizeof(state->parts[0])));
- if (!state->parts) {
- kfree(state);
- return NULL;
- }
-
- state->limit = nr;
-
- return state;
-}
-
-void free_partitions(struct parsed_partitions *state)
-{
- vfree(state->parts);
- kfree(state);
-}
-
-struct parsed_partitions *
-check_partition(struct gendisk *hd, struct block_device *bdev)
-{
- struct parsed_partitions *state;
- int i, res, err;
-
- state = allocate_partitions(hd);
- if (!state)
- return NULL;
- state->pp_buf = (char *)__get_free_page(GFP_KERNEL);
- if (!state->pp_buf) {
- free_partitions(state);
- return NULL;
- }
- state->pp_buf[0] = '\0';
-
- state->bdev = bdev;
- disk_name(hd, 0, state->name);
- snprintf(state->pp_buf, PAGE_SIZE, " %s:", state->name);
- if (isdigit(state->name[strlen(state->name)-1]))
- sprintf(state->name, "p");
-
- i = res = err = 0;
- while (!res && check_part[i]) {
- memset(state->parts, 0, state->limit * sizeof(state->parts[0]));
- res = check_part[i++](state);
- if (res < 0) {
- /* We have hit an I/O error which we don't report now.
- * But record it, and let the others do their job.
- */
- err = res;
- res = 0;
- }
-
- }
- if (res > 0) {
- printk(KERN_INFO "%s", state->pp_buf);
-
- free_page((unsigned long)state->pp_buf);
- return state;
- }
- if (state->access_beyond_eod)
- err = -ENOSPC;
- if (err)
- /* The partition is unrecognized. So report I/O errors if there were any */
- res = err;
- if (res) {
- if (warn_no_part)
- strlcat(state->pp_buf,
- " unable to read partition table\n", PAGE_SIZE);
- printk(KERN_INFO "%s", state->pp_buf);
- }
-
- free_page((unsigned long)state->pp_buf);
- free_partitions(state);
- return ERR_PTR(res);
-}
#include <linux/pagemap.h>
#include <linux/blkdev.h>
#include <linux/genhd.h>
+#include "../blk.h"
/*
* add_gd_partition adds a partitions details to the devices partition
char *pp_buf;
};
-void free_partitions(struct parsed_partitions *state);
+typedef struct {
+ struct page *v;
+} Sector;
-struct parsed_partitions *
-check_partition(struct gendisk *, struct block_device *);
-
-static inline void *read_part_sector(struct parsed_partitions *state,
- sector_t n, Sector *p)
+void *read_part_sector(struct parsed_partitions *state, sector_t n, Sector *p);
+static inline void put_dev_sector(Sector p)
{
- if (n >= get_capacity(state->bdev->bd_disk)) {
- state->access_beyond_eod = true;
- return NULL;
- }
- return read_dev_sector(state->bdev, n, p);
+ put_page(p.v);
}
static inline void
}
}
-extern int warn_no_part;
-
+/* detection routines go here in alphabetical order: */
+int adfspart_check_ADFS(struct parsed_partitions *state);
+int adfspart_check_CUMANA(struct parsed_partitions *state);
+int adfspart_check_EESOX(struct parsed_partitions *state);
+int adfspart_check_ICS(struct parsed_partitions *state);
+int adfspart_check_POWERTEC(struct parsed_partitions *state);
+int aix_partition(struct parsed_partitions *state);
+int amiga_partition(struct parsed_partitions *state);
+int atari_partition(struct parsed_partitions *state);
+int cmdline_partition(struct parsed_partitions *state);
+int efi_partition(struct parsed_partitions *state);
+int ibm_partition(struct parsed_partitions *);
+int karma_partition(struct parsed_partitions *state);
+int ldm_partition(struct parsed_partitions *state);
+int mac_partition(struct parsed_partitions *state);
+int msdos_partition(struct parsed_partitions *state);
+int osf_partition(struct parsed_partitions *state);
+int sgi_partition(struct parsed_partitions *state);
+int sun_partition(struct parsed_partitions *state);
+int sysv68_partition(struct parsed_partitions *state);
+int ultrix_partition(struct parsed_partitions *state);
#include <linux/cmdline-parser.h>
#include "check.h"
-#include "cmdline.h"
static char *cmdline;
static struct cmdline_parts *bdev_parts;
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-
-int cmdline_partition(struct parsed_partitions *state);
// SPDX-License-Identifier: GPL-2.0
/*
- * Code extracted from drivers/block/genhd.c
- * Copyright (C) 1991-1998 Linus Torvalds
- * Re-organised Feb 1998 Russell King
- *
- * We now have independent partition support from the
- * block drivers, which allows all the partition code to
- * be grouped in one location, and it to be mostly self
- * contained.
+ * Copyright (C) 1991-1998 Linus Torvalds
+ * Re-organised Feb 1998 Russell King
*/
-
-#include <linux/init.h>
-#include <linux/module.h>
#include <linux/fs.h>
#include <linux/slab.h>
-#include <linux/kmod.h>
#include <linux/ctype.h>
#include <linux/genhd.h>
+#include <linux/vmalloc.h>
#include <linux/blktrace_api.h>
+#include <linux/raid/detect.h>
+#include "check.h"
-#include "partitions/check.h"
+static int (*check_part[])(struct parsed_partitions *) = {
+ /*
+ * Probe partition formats with tables at disk address 0
+ * that also have an ADFS boot block at 0xdc0.
+ */
+#ifdef CONFIG_ACORN_PARTITION_ICS
+ adfspart_check_ICS,
+#endif
+#ifdef CONFIG_ACORN_PARTITION_POWERTEC
+ adfspart_check_POWERTEC,
+#endif
+#ifdef CONFIG_ACORN_PARTITION_EESOX
+ adfspart_check_EESOX,
+#endif
-#ifdef CONFIG_BLK_DEV_MD
-extern void md_autodetect_dev(dev_t dev);
+ /*
+ * Now move on to formats that only have partition info at
+ * disk address 0xdc0. Since these may also have stale
+ * PC/BIOS partition tables, they need to come before
+ * the msdos entry.
+ */
+#ifdef CONFIG_ACORN_PARTITION_CUMANA
+ adfspart_check_CUMANA,
+#endif
+#ifdef CONFIG_ACORN_PARTITION_ADFS
+ adfspart_check_ADFS,
#endif
-
-/*
- * disk_name() is used by partition check code and the genhd driver.
- * It formats the devicename of the indicated disk into
- * the supplied buffer (of size at least 32), and returns
- * a pointer to that same buffer (for convenience).
- */
-char *disk_name(struct gendisk *hd, int partno, char *buf)
+#ifdef CONFIG_CMDLINE_PARTITION
+ cmdline_partition,
+#endif
+#ifdef CONFIG_EFI_PARTITION
+ efi_partition, /* this must come before msdos */
+#endif
+#ifdef CONFIG_SGI_PARTITION
+ sgi_partition,
+#endif
+#ifdef CONFIG_LDM_PARTITION
+ ldm_partition, /* this must come before msdos */
+#endif
+#ifdef CONFIG_MSDOS_PARTITION
+ msdos_partition,
+#endif
+#ifdef CONFIG_OSF_PARTITION
+ osf_partition,
+#endif
+#ifdef CONFIG_SUN_PARTITION
+ sun_partition,
+#endif
+#ifdef CONFIG_AMIGA_PARTITION
+ amiga_partition,
+#endif
+#ifdef CONFIG_ATARI_PARTITION
+ atari_partition,
+#endif
+#ifdef CONFIG_MAC_PARTITION
+ mac_partition,
+#endif
+#ifdef CONFIG_ULTRIX_PARTITION
+ ultrix_partition,
+#endif
+#ifdef CONFIG_IBM_PARTITION
+ ibm_partition,
+#endif
+#ifdef CONFIG_KARMA_PARTITION
+ karma_partition,
+#endif
+#ifdef CONFIG_SYSV68_PARTITION
+ sysv68_partition,
+#endif
+ NULL
+};
+
+static struct parsed_partitions *allocate_partitions(struct gendisk *hd)
{
- if (!partno)
- snprintf(buf, BDEVNAME_SIZE, "%s", hd->disk_name);
- else if (isdigit(hd->disk_name[strlen(hd->disk_name)-1]))
- snprintf(buf, BDEVNAME_SIZE, "%sp%d", hd->disk_name, partno);
- else
- snprintf(buf, BDEVNAME_SIZE, "%s%d", hd->disk_name, partno);
+ struct parsed_partitions *state;
+ int nr;
- return buf;
-}
+ state = kzalloc(sizeof(*state), GFP_KERNEL);
+ if (!state)
+ return NULL;
-const char *bdevname(struct block_device *bdev, char *buf)
-{
- return disk_name(bdev->bd_disk, bdev->bd_part->partno, buf);
-}
+ nr = disk_max_parts(hd);
+ state->parts = vzalloc(array_size(nr, sizeof(state->parts[0])));
+ if (!state->parts) {
+ kfree(state);
+ return NULL;
+ }
-EXPORT_SYMBOL(bdevname);
+ state->limit = nr;
-const char *bio_devname(struct bio *bio, char *buf)
-{
- return disk_name(bio->bi_disk, bio->bi_partno, buf);
+ return state;
}
-EXPORT_SYMBOL(bio_devname);
-/*
- * There's very little reason to use this, you should really
- * have a struct block_device just about everywhere and use
- * bdevname() instead.
- */
-const char *__bdevname(dev_t dev, char *buffer)
+static void free_partitions(struct parsed_partitions *state)
{
- scnprintf(buffer, BDEVNAME_SIZE, "unknown-block(%u,%u)",
- MAJOR(dev), MINOR(dev));
- return buffer;
+ vfree(state->parts);
+ kfree(state);
}
-EXPORT_SYMBOL(__bdevname);
+static struct parsed_partitions *check_partition(struct gendisk *hd,
+ struct block_device *bdev)
+{
+ struct parsed_partitions *state;
+ int i, res, err;
+
+ state = allocate_partitions(hd);
+ if (!state)
+ return NULL;
+ state->pp_buf = (char *)__get_free_page(GFP_KERNEL);
+ if (!state->pp_buf) {
+ free_partitions(state);
+ return NULL;
+ }
+ state->pp_buf[0] = '\0';
+
+ state->bdev = bdev;
+ disk_name(hd, 0, state->name);
+ snprintf(state->pp_buf, PAGE_SIZE, " %s:", state->name);
+ if (isdigit(state->name[strlen(state->name)-1]))
+ sprintf(state->name, "p");
+
+ i = res = err = 0;
+ while (!res && check_part[i]) {
+ memset(state->parts, 0, state->limit * sizeof(state->parts[0]));
+ res = check_part[i++](state);
+ if (res < 0) {
+ /*
+ * We have hit an I/O error which we don't report now.
+ * But record it, and let the others do their job.
+ */
+ err = res;
+ res = 0;
+ }
+
+ }
+ if (res > 0) {
+ printk(KERN_INFO "%s", state->pp_buf);
+
+ free_page((unsigned long)state->pp_buf);
+ return state;
+ }
+ if (state->access_beyond_eod)
+ err = -ENOSPC;
+ /*
+ * The partition is unrecognized. So report I/O errors if there were any
+ */
+ if (err)
+ res = err;
+ if (res) {
+ strlcat(state->pp_buf,
+ " unable to read partition table\n", PAGE_SIZE);
+ printk(KERN_INFO "%s", state->pp_buf);
+ }
+
+ free_page((unsigned long)state->pp_buf);
+ free_partitions(state);
+ return ERR_PTR(res);
+}
static ssize_t part_partition_show(struct device *dev,
struct device_attribute *attr, char *buf)
return sprintf(buf, "%llu\n",(unsigned long long)p->start_sect);
}
-ssize_t part_size_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct hd_struct *p = dev_to_part(dev);
- return sprintf(buf, "%llu\n",(unsigned long long)part_nr_sects_read(p));
-}
-
static ssize_t part_ro_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
return sprintf(buf, "%u\n", p->discard_alignment);
}
-ssize_t part_stat_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct hd_struct *p = dev_to_part(dev);
- struct request_queue *q = part_to_disk(p)->queue;
- unsigned int inflight;
-
- inflight = part_in_flight(q, p);
- return sprintf(buf,
- "%8lu %8lu %8llu %8u "
- "%8lu %8lu %8llu %8u "
- "%8u %8u %8u "
- "%8lu %8lu %8llu %8u "
- "%8lu %8u"
- "\n",
- part_stat_read(p, ios[STAT_READ]),
- part_stat_read(p, merges[STAT_READ]),
- (unsigned long long)part_stat_read(p, sectors[STAT_READ]),
- (unsigned int)part_stat_read_msecs(p, STAT_READ),
- part_stat_read(p, ios[STAT_WRITE]),
- part_stat_read(p, merges[STAT_WRITE]),
- (unsigned long long)part_stat_read(p, sectors[STAT_WRITE]),
- (unsigned int)part_stat_read_msecs(p, STAT_WRITE),
- inflight,
- jiffies_to_msecs(part_stat_read(p, io_ticks)),
- jiffies_to_msecs(part_stat_read(p, time_in_queue)),
- part_stat_read(p, ios[STAT_DISCARD]),
- part_stat_read(p, merges[STAT_DISCARD]),
- (unsigned long long)part_stat_read(p, sectors[STAT_DISCARD]),
- (unsigned int)part_stat_read_msecs(p, STAT_DISCARD),
- part_stat_read(p, ios[STAT_FLUSH]),
- (unsigned int)part_stat_read_msecs(p, STAT_FLUSH));
-}
-
-ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,
- char *buf)
-{
- struct hd_struct *p = dev_to_part(dev);
- struct request_queue *q = part_to_disk(p)->queue;
- unsigned int inflight[2];
-
- part_in_flight_rw(q, p, inflight);
- return sprintf(buf, "%8u %8u\n", inflight[0], inflight[1]);
-}
-
-#ifdef CONFIG_FAIL_MAKE_REQUEST
-ssize_t part_fail_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct hd_struct *p = dev_to_part(dev);
-
- return sprintf(buf, "%d\n", p->make_it_fail);
-}
-
-ssize_t part_fail_store(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct hd_struct *p = dev_to_part(dev);
- int i;
-
- if (count > 0 && sscanf(buf, "%d", &i) > 0)
- p->make_it_fail = (i == 0) ? 0 : 1;
-
- return count;
-}
-#endif
-
static DEVICE_ATTR(partition, 0444, part_partition_show, NULL);
static DEVICE_ATTR(start, 0444, part_start_show, NULL);
static DEVICE_ATTR(size, 0444, part_size_show, NULL);
p->policy = get_disk_ro(disk);
if (info) {
- struct partition_meta_info *pinfo = alloc_part_info(disk);
+ struct partition_meta_info *pinfo;
+
+ pinfo = kzalloc_node(sizeof(*pinfo), GFP_KERNEL, disk->node_id);
if (!pinfo) {
err = -ENOMEM;
goto out_free_stats;
return p;
out_free_info:
- free_part_info(p);
+ kfree(p->info);
out_free_stats:
free_part_stats(p);
out_free:
return true;
}
-#ifdef CONFIG_BLK_DEV_MD
- if (state->parts[p].flags & ADDPART_FLAG_RAID)
+ if (IS_BUILTIN(CONFIG_BLK_DEV_MD) &&
+ (state->parts[p].flags & ADDPART_FLAG_RAID))
md_autodetect_dev(part_to_dev(part)->devt);
-#endif
+
return true;
}
return ret;
}
-unsigned char *read_dev_sector(struct block_device *bdev, sector_t n, Sector *p)
+void *read_part_sector(struct parsed_partitions *state, sector_t n, Sector *p)
{
- struct address_space *mapping = bdev->bd_inode->i_mapping;
+ struct address_space *mapping = state->bdev->bd_inode->i_mapping;
struct page *page;
- page = read_mapping_page(mapping, (pgoff_t)(n >> (PAGE_SHIFT-9)), NULL);
- if (!IS_ERR(page)) {
- if (PageError(page))
- goto fail;
- p->v = page;
- return (unsigned char *)page_address(page) + ((n & ((1 << (PAGE_SHIFT - 9)) - 1)) << 9);
-fail:
- put_page(page);
+ if (n >= get_capacity(state->bdev->bd_disk)) {
+ state->access_beyond_eod = true;
+ return NULL;
}
+
+ page = read_mapping_page(mapping,
+ (pgoff_t)(n >> (PAGE_SHIFT - 9)), NULL);
+ if (IS_ERR(page))
+ goto out;
+ if (PageError(page))
+ goto out_put_page;
+
+ p->v = page;
+ return (unsigned char *)page_address(page) +
+ ((n & ((1 << (PAGE_SHIFT - 9)) - 1)) << SECTOR_SHIFT);
+out_put_page:
+ put_page(page);
+out:
p->v = NULL;
return NULL;
}
-
-EXPORT_SYMBOL(read_dev_sector);
__le16 signature;
} __packed legacy_mbr;
-/* Functions */
-extern int efi_partition(struct parsed_partitions *state);
-
#endif
#include <asm/vtoc.h>
#include "check.h"
-#include "ibm.h"
union label_t {
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-int ibm_partition(struct parsed_partitions *);
*/
#include "check.h"
-#include "karma.h"
#include <linux/compiler.h>
+#define KARMA_LABEL_MAGIC 0xAB56
+
int karma_partition(struct parsed_partitions *state)
{
int i;
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * fs/partitions/karma.h
- */
-
-#define KARMA_LABEL_MAGIC 0xAB56
-
-int karma_partition(struct parsed_partitions *state);
-
#include <linux/stringify.h>
#include <linux/kernel.h>
#include <linux/uuid.h>
+#include <linux/msdos_partition.h>
#include "ldm.h"
#include "check.h"
-#include "msdos.h"
/*
* ldm_debug/info/error/crit - Output an error message
{
Sector sect;
u8 *data;
- struct partition *p;
+ struct msdos_partition *p;
int i;
bool result = false;
if (*(__le16*) (data + 0x01FE) != cpu_to_le16 (MSDOS_LABEL_MAGIC))
goto out;
- p = (struct partition*)(data + 0x01BE);
+ p = (struct msdos_partition *)(data + 0x01BE);
for (i = 0; i < 4; i++, p++)
if (SYS_IND (p) == LDM_PARTITION) {
result = true;
struct list_head v_part;
};
-int ldm_partition(struct parsed_partitions *state);
-
#endif /* _FS_PT_LDM_H_ */
/* ... more stuff */
};
-int mac_partition(struct parsed_partitions *state);
* Check partition table on IDE disks for common CHS translations
*
* Re-organised Feb 1998 Russell King
+ *
+ * BSD disklabel support by Yossi Gottlieb <yogo@math.tau.ac.il>
+ * updated by Marc Espie <Marc.Espie@openbsd.org>
+ *
+ * Unixware slices support by Andrzej Krzysztofowicz <ankry@mif.pg.gda.pl>
+ * and Krzysztof G. Baranowski <kgb@knm.org.pl>
*/
#include <linux/msdos_fs.h>
+#include <linux/msdos_partition.h>
#include "check.h"
-#include "msdos.h"
#include "efi.h"
-#include "aix.h"
/*
* Many architectures don't like unaligned accesses, while
#define SYS_IND(p) get_unaligned(&p->sys_ind)
-static inline sector_t nr_sects(struct partition *p)
+static inline sector_t nr_sects(struct msdos_partition *p)
{
return (sector_t)get_unaligned_le32(&p->nr_sects);
}
-static inline sector_t start_sect(struct partition *p)
+static inline sector_t start_sect(struct msdos_partition *p)
{
return (sector_t)get_unaligned_le32(&p->start_sect);
}
-static inline int is_extended_partition(struct partition *p)
+static inline int is_extended_partition(struct msdos_partition *p)
{
return (SYS_IND(p) == DOS_EXTENDED_PARTITION ||
SYS_IND(p) == WIN98_EXTENDED_PARTITION ||
#define AIX_LABEL_MAGIC4 0xC1
static int aix_magic_present(struct parsed_partitions *state, unsigned char *p)
{
- struct partition *pt = (struct partition *) (p + 0x1be);
+ struct msdos_partition *pt = (struct msdos_partition *) (p + 0x1be);
Sector sect;
unsigned char *d;
int slot, ret = 0;
p[2] == AIX_LABEL_MAGIC3 &&
p[3] == AIX_LABEL_MAGIC4))
return 0;
- /* Assume the partition table is valid if Linux partitions exists */
+
+ /*
+ * Assume the partition table is valid if Linux partitions exists.
+ * Note that old Solaris/x86 partitions use the same indicator as
+ * Linux swap partitions, so we consider that a Linux partition as
+ * well.
+ */
for (slot = 1; slot <= 4; slot++, pt++) {
- if (pt->sys_ind == LINUX_SWAP_PARTITION ||
- pt->sys_ind == LINUX_RAID_PARTITION ||
- pt->sys_ind == LINUX_DATA_PARTITION ||
- pt->sys_ind == LINUX_LVM_PARTITION ||
- is_extended_partition(pt))
+ if (pt->sys_ind == SOLARIS_X86_PARTITION ||
+ pt->sys_ind == LINUX_RAID_PARTITION ||
+ pt->sys_ind == LINUX_DATA_PARTITION ||
+ pt->sys_ind == LINUX_LVM_PARTITION ||
+ is_extended_partition(pt))
return 0;
}
d = read_part_sector(state, 7, §);
sector_t first_sector, sector_t first_size,
u32 disksig)
{
- struct partition *p;
+ struct msdos_partition *p;
Sector sect;
unsigned char *data;
sector_t this_sector, this_size;
if (!msdos_magic_present(data + 510))
goto done;
- p = (struct partition *) (data + 0x1be);
+ p = (struct msdos_partition *) (data + 0x1be);
/*
* Usually, the first entry is the real data partition,
put_dev_sector(sect);
}
+#define SOLARIS_X86_NUMSLICE 16
+#define SOLARIS_X86_VTOC_SANE (0x600DDEEEUL)
+
+struct solaris_x86_slice {
+ __le16 s_tag; /* ID tag of partition */
+ __le16 s_flag; /* permission flags */
+ __le32 s_start; /* start sector no of partition */
+ __le32 s_size; /* # of blocks in partition */
+};
+
+struct solaris_x86_vtoc {
+ unsigned int v_bootinfo[3]; /* info needed by mboot */
+ __le32 v_sanity; /* to verify vtoc sanity */
+ __le32 v_version; /* layout version */
+ char v_volume[8]; /* volume name */
+ __le16 v_sectorsz; /* sector size in bytes */
+ __le16 v_nparts; /* number of partitions */
+ unsigned int v_reserved[10]; /* free space */
+ struct solaris_x86_slice
+ v_slice[SOLARIS_X86_NUMSLICE]; /* slice headers */
+ unsigned int timestamp[SOLARIS_X86_NUMSLICE]; /* timestamp */
+ char v_asciilabel[128]; /* for compatibility */
+};
+
/* james@bpgc.com: Solaris has a nasty indicator: 0x82 which also
indicates linux swap. Be careful before believing this is Solaris. */
#endif
}
+/* check against BSD src/sys/sys/disklabel.h for consistency */
+#define BSD_DISKMAGIC (0x82564557UL) /* The disk magic number */
+#define BSD_MAXPARTITIONS 16
+#define OPENBSD_MAXPARTITIONS 16
+#define BSD_FS_UNUSED 0 /* disklabel unused partition entry ID */
+struct bsd_disklabel {
+ __le32 d_magic; /* the magic number */
+ __s16 d_type; /* drive type */
+ __s16 d_subtype; /* controller/d_type specific */
+ char d_typename[16]; /* type name, e.g. "eagle" */
+ char d_packname[16]; /* pack identifier */
+ __u32 d_secsize; /* # of bytes per sector */
+ __u32 d_nsectors; /* # of data sectors per track */
+ __u32 d_ntracks; /* # of tracks per cylinder */
+ __u32 d_ncylinders; /* # of data cylinders per unit */
+ __u32 d_secpercyl; /* # of data sectors per cylinder */
+ __u32 d_secperunit; /* # of data sectors per unit */
+ __u16 d_sparespertrack; /* # of spare sectors per track */
+ __u16 d_sparespercyl; /* # of spare sectors per cylinder */
+ __u32 d_acylinders; /* # of alt. cylinders per unit */
+ __u16 d_rpm; /* rotational speed */
+ __u16 d_interleave; /* hardware sector interleave */
+ __u16 d_trackskew; /* sector 0 skew, per track */
+ __u16 d_cylskew; /* sector 0 skew, per cylinder */
+ __u32 d_headswitch; /* head switch time, usec */
+ __u32 d_trkseek; /* track-to-track seek, usec */
+ __u32 d_flags; /* generic flags */
+#define NDDATA 5
+ __u32 d_drivedata[NDDATA]; /* drive-type specific information */
+#define NSPARE 5
+ __u32 d_spare[NSPARE]; /* reserved for future use */
+ __le32 d_magic2; /* the magic number (again) */
+ __le16 d_checksum; /* xor of data incl. partitions */
+
+ /* filesystem and partition information: */
+ __le16 d_npartitions; /* number of partitions in following */
+ __le32 d_bbsize; /* size of boot area at sn0, bytes */
+ __le32 d_sbsize; /* max size of fs superblock, bytes */
+ struct bsd_partition { /* the partition table */
+ __le32 p_size; /* number of sectors in partition */
+ __le32 p_offset; /* starting sector */
+ __le32 p_fsize; /* filesystem basic fragment size */
+ __u8 p_fstype; /* filesystem type, see below */
+ __u8 p_frag; /* filesystem fragments per block */
+ __le16 p_cpg; /* filesystem cylinders per group */
+ } d_partitions[BSD_MAXPARTITIONS]; /* actually may be more */
+};
+
#if defined(CONFIG_BSD_DISKLABEL)
/*
* Create devices for BSD partitions listed in a disklabel, under a
#endif
}
+#define UNIXWARE_DISKMAGIC (0xCA5E600DUL) /* The disk magic number */
+#define UNIXWARE_DISKMAGIC2 (0x600DDEEEUL) /* The slice table magic nr */
+#define UNIXWARE_NUMSLICE 16
+#define UNIXWARE_FS_UNUSED 0 /* Unused slice entry ID */
+
+struct unixware_slice {
+ __le16 s_label; /* label */
+ __le16 s_flags; /* permission flags */
+ __le32 start_sect; /* starting sector */
+ __le32 nr_sects; /* number of sectors in slice */
+};
+
+struct unixware_disklabel {
+ __le32 d_type; /* drive type */
+ __le32 d_magic; /* the magic number */
+ __le32 d_version; /* version number */
+ char d_serial[12]; /* serial number of the device */
+ __le32 d_ncylinders; /* # of data cylinders per device */
+ __le32 d_ntracks; /* # of tracks per cylinder */
+ __le32 d_nsectors; /* # of data sectors per track */
+ __le32 d_secsize; /* # of bytes per sector */
+ __le32 d_part_start; /* # of first sector of this partition*/
+ __le32 d_unknown1[12]; /* ? */
+ __le32 d_alt_tbl; /* byte offset of alternate table */
+ __le32 d_alt_len; /* byte length of alternate table */
+ __le32 d_phys_cyl; /* # of physical cylinders per device */
+ __le32 d_phys_trk; /* # of physical tracks per cylinder */
+ __le32 d_phys_sec; /* # of physical sectors per track */
+ __le32 d_phys_bytes; /* # of physical bytes per sector */
+ __le32 d_unknown2; /* ? */
+ __le32 d_unknown3; /* ? */
+ __le32 d_pad[8]; /* pad */
+
+ struct unixware_vtoc {
+ __le32 v_magic; /* the magic number */
+ __le32 v_version; /* version number */
+ char v_name[8]; /* volume name */
+ __le16 v_nslices; /* # of slices */
+ __le16 v_unknown1; /* ? */
+ __le32 v_reserved[10]; /* reserved */
+ struct unixware_slice
+ v_slice[UNIXWARE_NUMSLICE]; /* slice headers */
+ } vtoc;
+}; /* 408 */
+
/*
* Create devices for Unixware partitions listed in a disklabel, under a
* dos-like partition. See parse_extended() for more information.
#endif
}
+#define MINIX_NR_SUBPARTITIONS 4
+
/*
* Minix 2.0.0/2.0.2 subpartition support.
* Anand Krishnamurthy <anandk@wiproge.med.ge.com>
#ifdef CONFIG_MINIX_SUBPARTITION
Sector sect;
unsigned char *data;
- struct partition *p;
+ struct msdos_partition *p;
int i;
data = read_part_sector(state, offset, §);
if (!data)
return;
- p = (struct partition *)(data + 0x1be);
+ p = (struct msdos_partition *)(data + 0x1be);
/* The first sector of a Minix partition can have either
* a secondary MBR describing its subpartitions, or
sector_t sector_size = bdev_logical_block_size(state->bdev) / 512;
Sector sect;
unsigned char *data;
- struct partition *p;
+ struct msdos_partition *p;
struct fat_boot_sector *fb;
int slot;
u32 disksig;
* partition table. Reject this in case the boot indicator
* is not 0 or 0x80.
*/
- p = (struct partition *) (data + 0x1be);
+ p = (struct msdos_partition *) (data + 0x1be);
for (slot = 1; slot <= 4; slot++, p++) {
if (p->boot_ind != 0 && p->boot_ind != 0x80) {
/*
}
#ifdef CONFIG_EFI_PARTITION
- p = (struct partition *) (data + 0x1be);
+ p = (struct msdos_partition *) (data + 0x1be);
for (slot = 1 ; slot <= 4 ; slot++, p++) {
/* If this is an EFI GPT disk, msdos should ignore it. */
if (SYS_IND(p) == EFI_PMBR_OSTYPE_EFI_GPT) {
}
}
#endif
- p = (struct partition *) (data + 0x1be);
+ p = (struct msdos_partition *) (data + 0x1be);
disksig = le32_to_cpup((__le32 *)(data + 0x1b8));
strlcat(state->pp_buf, "\n", PAGE_SIZE);
/* second pass - output for each on a separate line */
- p = (struct partition *) (0x1be + data);
+ p = (struct msdos_partition *) (0x1be + data);
for (slot = 1 ; slot <= 4 ; slot++, p++) {
unsigned char id = SYS_IND(p);
int n;
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * fs/partitions/msdos.h
- */
-
-#define MSDOS_LABEL_MAGIC 0xAA55
-
-int msdos_partition(struct parsed_partitions *state);
-
*/
#include "check.h"
-#include "osf.h"
#define MAX_OSF_PARTITIONS 18
+#define DISKLABELMAGIC (0x82564557UL)
int osf_partition(struct parsed_partitions *state)
{
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * fs/partitions/osf.h
- */
-
-#define DISKLABELMAGIC (0x82564557UL)
-
-int osf_partition(struct parsed_partitions *state);
*/
#include "check.h"
-#include "sgi.h"
+
+#define SGI_LABEL_MAGIC 0x0be5a941
+
+enum {
+ LINUX_RAID_PARTITION = 0xfd, /* autodetect RAID partition */
+};
struct sgi_disklabel {
__be32 magic_mushroom; /* Big fat spliff... */
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * fs/partitions/sgi.h
- */
-
-extern int sgi_partition(struct parsed_partitions *state);
-
-#define SGI_LABEL_MAGIC 0x0be5a941
-
*/
#include "check.h"
-#include "sun.h"
+
+#define SUN_LABEL_MAGIC 0xDABE
+#define SUN_VTOC_SANITY 0x600DDEEE
+
+enum {
+ SUN_WHOLE_DISK = 5,
+ LINUX_RAID_PARTITION = 0xfd, /* autodetect RAID partition */
+};
int sun_partition(struct parsed_partitions *state)
{
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * fs/partitions/sun.h
- */
-
-#define SUN_LABEL_MAGIC 0xDABE
-#define SUN_VTOC_SANITY 0x600DDEEE
-
-int sun_partition(struct parsed_partitions *state);
*/
#include "check.h"
-#include "sysv68.h"
/*
* Volume ID structure: on first 256-bytes sector of disk
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-extern int sysv68_partition(struct parsed_partitions *state);
*/
#include "check.h"
-#include "ultrix.h"
int ultrix_partition(struct parsed_partitions *state)
{
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * fs/partitions/ultrix.h
- */
-
-int ultrix_partition(struct parsed_partitions *state);
hsn = response_get_u64(&dev->parsed, 4);
tsn = response_get_u64(&dev->parsed, 5);
- if (hsn == 0 && tsn == 0) {
+ if (hsn != GENERIC_HOST_SESSION_NUM || tsn < FIRST_TPER_SESSION_NUM) {
pr_debug("Couldn't authenticate session\n");
return -EPERM;
}
config ATA_NONSTANDARD
bool
+config SATA_HOST
+ bool
+
+config PATA_TIMINGS
+ bool
+
config ATA_VERBOSE_ERROR
bool "Verbose ATA error reporting"
default y
If unsure, say Y.
+config ATA_FORCE
+ bool "\"libata.force=\" kernel parameter support" if EXPERT
+ default y
+ help
+ This option adds support for "libata.force=" kernel parameter for
+ forcing configuration settings.
+
+ For further information, please read
+ <file:Documentation/admin-guide/kernel-parameters.txt>.
+
+ This option will enlarge the kernel by approx. 3KB. Disable it if
+ kernel size is more important than ability to override the default
+ configuration settings.
+
+ If unsure, say Y.
+
config ATA_ACPI
bool "ATA ACPI Support"
depends on ACPI
+ select PATA_TIMINGS
default y
help
This option adds support for ATA-related ACPI objects.
config SATA_PMP
bool "SATA Port Multiplier support"
+ depends on SATA_HOST
default y
help
This option adds support for SATA Port Multipliers
config SATA_AHCI
tristate "AHCI SATA support"
depends on PCI
+ select SATA_HOST
help
This option enables support for AHCI Serial ATA.
config SATA_AHCI_PLATFORM
tristate "Platform AHCI SATA support"
+ select SATA_HOST
help
This option enables support for Platform AHCI Serial ATA
controllers.
tristate "Broadcom AHCI SATA support"
depends on ARCH_BRCMSTB || BMIPS_GENERIC || ARCH_BCM_NSP || \
ARCH_BCM_63XX
+ select SATA_HOST
help
This option enables support for the AHCI SATA3 controller found on
Broadcom SoC's.
config AHCI_DA850
tristate "DaVinci DA850 AHCI SATA support"
depends on ARCH_DAVINCI_DA850
+ select SATA_HOST
help
This option enables support for the DaVinci DA850 SoC's
onboard AHCI SATA.
config AHCI_DM816
tristate "DaVinci DM816 AHCI SATA support"
depends on ARCH_OMAP2PLUS
+ select SATA_HOST
help
This option enables support for the DaVinci DM816 SoC's
onboard AHCI SATA controller.
config AHCI_ST
tristate "ST AHCI SATA support"
depends on ARCH_STI
+ select SATA_HOST
help
This option enables support for ST AHCI SATA controller.
tristate "Freescale i.MX AHCI SATA support"
depends on MFD_SYSCON && (ARCH_MXC || COMPILE_TEST)
depends on (HWMON && (THERMAL || !THERMAL_OF)) || !HWMON
+ select SATA_HOST
help
This option enables support for the Freescale i.MX SoC's
onboard AHCI SATA.
config AHCI_CEVA
tristate "CEVA AHCI SATA support"
depends on OF
+ select SATA_HOST
help
This option enables support for the CEVA AHCI SATA.
It can be found on the Xilinx Zynq UltraScale+ MPSoC.
tristate "MediaTek AHCI SATA support"
depends on ARCH_MEDIATEK
select MFD_SYSCON
+ select SATA_HOST
help
This option enables support for the MediaTek SoC's
onboard AHCI SATA controller.
config AHCI_MVEBU
tristate "Marvell EBU AHCI SATA support"
depends on ARCH_MVEBU
+ select SATA_HOST
help
This option enables support for the Marvebu EBU SoC's
onboard AHCI SATA.
config AHCI_SUNXI
tristate "Allwinner sunxi AHCI SATA support"
depends on ARCH_SUNXI
+ select SATA_HOST
help
This option enables support for the Allwinner sunxi SoC's
onboard AHCI SATA.
config AHCI_TEGRA
tristate "NVIDIA Tegra AHCI SATA support"
depends on ARCH_TEGRA
+ select SATA_HOST
help
This option enables support for the NVIDIA Tegra SoC's
onboard AHCI SATA.
config AHCI_XGENE
tristate "APM X-Gene 6.0Gbps AHCI SATA host controller support"
depends on PHY_XGENE
+ select SATA_HOST
help
This option enables support for APM X-Gene SoC SATA host controller.
config AHCI_QORIQ
tristate "Freescale QorIQ AHCI SATA support"
depends on OF
+ select SATA_HOST
help
This option enables support for the Freescale QorIQ AHCI SoC's
onboard AHCI SATA.
config SATA_FSL
tristate "Freescale 3.0Gbps SATA support"
depends on FSL_SOC
+ select SATA_HOST
help
This option enables support for Freescale 3.0Gbps SATA controller.
It can be found on MPC837x and MPC8315.
config SATA_GEMINI
tristate "Gemini SATA bridge support"
depends on ARCH_GEMINI || COMPILE_TEST
+ select SATA_HOST
default ARCH_GEMINI
help
This enabled support for the FTIDE010 to SATA bridge
config SATA_AHCI_SEATTLE
tristate "AMD Seattle 6.0Gbps AHCI SATA host controller support"
depends on ARCH_SEATTLE
+ select SATA_HOST
help
This option enables support for AMD Seattle SATA host controller.
config SATA_INIC162X
tristate "Initio 162x SATA support (Very Experimental)"
depends on PCI
+ select SATA_HOST
help
This option enables support for Initio 162x Serial ATA.
config SATA_ACARD_AHCI
tristate "ACard AHCI variant (ATP 8620)"
depends on PCI
+ select SATA_HOST
help
This option enables support for Acard.
config SATA_SIL24
tristate "Silicon Image 3124/3132 SATA support"
depends on PCI
+ select SATA_HOST
help
This option enables support for Silicon Image 3124/3132 Serial ATA.
config PATA_OCTEON_CF
tristate "OCTEON Boot Bus Compact Flash support"
depends on CAVIUM_OCTEON_SOC
+ select PATA_TIMINGS
help
This option enables a polled compact flash driver for use with
compact flash cards attached to the OCTEON boot bus.
config SATA_QSTOR
tristate "Pacific Digital SATA QStor support"
depends on PCI
+ select SATA_HOST
help
This option enables support for Pacific Digital Serial ATA QStor.
config SATA_SX4
tristate "Promise SATA SX4 support (Experimental)"
depends on PCI
+ select SATA_HOST
help
This option enables support for Promise Serial ATA SX4.
config ATA_PIIX
tristate "Intel ESB, ICH, PIIX3, PIIX4 PATA/SATA support"
depends on PCI
+ select SATA_HOST
help
This option enables support for ICH5/6/7/8 Serial ATA
and support for PATA on the Intel ESB/ICH/PIIX3/PIIX4 series
tristate "DesignWare Cores SATA support"
depends on DMADEVICES
select GENERIC_PHY
+ select SATA_HOST
help
This option enables support for the on-chip SATA controller of the
AppliedMicro processor 460EX.
config SATA_HIGHBANK
tristate "Calxeda Highbank SATA support"
depends on ARCH_HIGHBANK || COMPILE_TEST
+ select SATA_HOST
help
This option enables support for the Calxeda Highbank SoC's
onboard SATA.
depends on PCI || ARCH_DOVE || ARCH_MV78XX0 || \
ARCH_MVEBU || ARCH_ORION5X || COMPILE_TEST
select GENERIC_PHY
+ select SATA_HOST
help
This option enables support for the Marvell Serial ATA family.
Currently supports 88SX[56]0[48][01] PCI(-X) chips,
config SATA_NV
tristate "NVIDIA SATA support"
depends on PCI
+ select SATA_HOST
help
This option enables support for NVIDIA Serial ATA.
config SATA_PROMISE
tristate "Promise SATA TX2/TX4 support"
depends on PCI
+ select SATA_HOST
help
This option enables support for Promise Serial ATA TX2/TX4.
config SATA_RCAR
tristate "Renesas R-Car SATA support"
depends on ARCH_RENESAS || COMPILE_TEST
+ select SATA_HOST
help
This option enables support for Renesas R-Car Serial ATA.
config SATA_SIL
tristate "Silicon Image SATA support"
depends on PCI
+ select SATA_HOST
help
This option enables support for Silicon Image Serial ATA.
tristate "SiS 964/965/966/180 SATA support"
depends on PCI
select PATA_SIS
+ select SATA_HOST
help
This option enables support for SiS Serial ATA on
SiS 964/965/966/180 and Parallel ATA on SiS 180.
config SATA_SVW
tristate "ServerWorks Frodo / Apple K2 SATA support"
depends on PCI
+ select SATA_HOST
help
This option enables support for Broadcom/Serverworks/Apple K2
SATA support.
config SATA_ULI
tristate "ULi Electronics SATA support"
depends on PCI
+ select SATA_HOST
help
This option enables support for ULi Electronics SATA.
config SATA_VIA
tristate "VIA SATA support"
depends on PCI
+ select SATA_HOST
help
This option enables support for VIA Serial ATA.
config SATA_VITESSE
tristate "VITESSE VSC-7174 / INTEL 31244 SATA support"
depends on PCI
+ select SATA_HOST
help
This option enables support for Vitesse VSC7174 and Intel 31244 Serial ATA.
config PATA_ALI
tristate "ALi PATA support"
depends on PCI
+ select PATA_TIMINGS
help
This option enables support for the ALi ATA interfaces
found on the many ALi chipsets.
config PATA_AMD
tristate "AMD/NVidia PATA support"
depends on PCI
+ select PATA_TIMINGS
help
This option enables support for the AMD and NVidia PATA
interfaces found on the chipsets for Athlon/Athlon64.
config PATA_ATP867X
tristate "ARTOP/Acard ATP867X PATA support"
depends on PCI
+ select PATA_TIMINGS
help
This option enables support for ARTOP/Acard ATP867X PATA
controllers.
config PATA_BK3710
tristate "Palmchip BK3710 PATA support"
depends on ARCH_DAVINCI
+ select PATA_TIMINGS
help
This option enables support for the integrated IDE controller on
the TI DaVinci SoC.
config PATA_CMD64X
tristate "CMD64x PATA support"
depends on PCI
+ select PATA_TIMINGS
help
This option enables support for the CMD64x series chips
except for the CMD640.
config PATA_CYPRESS
tristate "Cypress CY82C693 PATA support (Very Experimental)"
depends on PCI
+ select PATA_TIMINGS
help
This option enables support for the Cypress/Contaq CY82C693
chipset found in some Alpha systems
config PATA_EP93XX
tristate "Cirrus Logic EP93xx PATA support"
depends on ARCH_EP93XX
+ select PATA_TIMINGS
help
This option enables support for the PATA controller in
the Cirrus Logic EP9312 and EP9315 ARM CPU.
config PATA_ICSIDE
tristate "Acorn ICS PATA support"
depends on ARM && ARCH_ACORN
+ select PATA_TIMINGS
help
On Acorn systems, say Y here if you wish to use the ICS PATA
interface card. This is not required for ICS partition support.
config PATA_IMX
tristate "PATA support for Freescale iMX"
depends on ARCH_MXC
+ select PATA_TIMINGS
help
This option enables support for the PATA host available on Freescale
iMX SoCs.
config PATA_NS87415
tristate "Nat Semi NS87415 PATA support"
depends on PCI
+ select PATA_TIMINGS
help
This option enables support for the National Semiconductor
NS87415 PCI-IDE controller.
config PATA_VIA
tristate "VIA PATA support"
depends on PCI
+ select PATA_TIMINGS
help
This option enables support for the VIA PATA interfaces
found on the many VIA chipsets.
config PATA_CMD640_PCI
tristate "CMD640 PCI PATA support (Experimental)"
depends on PCI
+ select PATA_TIMINGS
help
This option enables support for the CMD640 PCI IDE
interface chip. Only the primary channel is currently
config PATA_NS87410
tristate "Nat Semi NS87410 PATA support"
depends on PCI
+ select PATA_TIMINGS
help
This option enables support for the National Semiconductor
NS87410 PCI-IDE controller.
config PATA_SAMSUNG_CF
tristate "Samsung SoC PATA support"
depends on SAMSUNG_DEV_IDE
+ select PATA_TIMINGS
help
This option enables basic support for Samsung's S3C/S5P board
PATA controllers via the new ATA layer
config PATA_ACPI
tristate "ACPI firmware driver for PATA"
depends on ATA_ACPI && ATA_BMDMA && PCI
+ select PATA_TIMINGS
help
This option enables an ACPI method driver which drives
motherboard PATA controller interfaces through the ACPI
config ATA_GENERIC
tristate "Generic ATA support"
depends on PCI && ATA_BMDMA
+ select SATA_HOST
help
This option enables support for generic BIOS configured
ATA controllers via the new ATA layer
config PATA_LEGACY
tristate "Legacy ISA PATA support (Experimental)"
depends on (ISA || PCI)
+ select PATA_TIMINGS
help
This option enables support for ISA/VLB/PCI bus legacy PATA
ports and allows them to be accessed via the new ATA layer.
libata-y := libata-core.o libata-scsi.o libata-eh.o \
libata-transport.o libata-trace.o
+libata-$(CONFIG_SATA_HOST) += libata-sata.o
libata-$(CONFIG_ATA_SFF) += libata-sff.o
libata-$(CONFIG_SATA_PMP) += libata-pmp.o
libata-$(CONFIG_ATA_ACPI) += libata-acpi.o
libata-$(CONFIG_SATA_ZPODD) += libata-zpodd.o
+libata-$(CONFIG_PATA_TIMINGS) += libata-pata-timings.o
enum {
AHCI_PCI_BAR_STA2X11 = 0,
AHCI_PCI_BAR_CAVIUM = 0,
+ AHCI_PCI_BAR_LOONGSON = 0,
AHCI_PCI_BAR_ENMOTUS = 2,
AHCI_PCI_BAR_CAVIUM_GEN5 = 4,
AHCI_PCI_BAR_STANDARD = 5,
static const struct pci_device_id ahci_pci_tbl[] = {
/* Intel */
+ { PCI_VDEVICE(INTEL, 0x06d6), board_ahci }, /* Comet Lake PCH-H RAID */
{ PCI_VDEVICE(INTEL, 0x2652), board_ahci }, /* ICH6 */
{ PCI_VDEVICE(INTEL, 0x2653), board_ahci }, /* ICH6M */
{ PCI_VDEVICE(INTEL, 0x27c1), board_ahci }, /* ICH7 */
{ PCI_VDEVICE(INTEL, 0xa252), board_ahci }, /* Lewisburg RAID*/
{ PCI_VDEVICE(INTEL, 0xa256), board_ahci }, /* Lewisburg RAID*/
{ PCI_VDEVICE(INTEL, 0xa356), board_ahci }, /* Cannon Lake PCH-H RAID */
+ { PCI_VDEVICE(INTEL, 0x06d7), board_ahci }, /* Comet Lake-H RAID */
+ { PCI_VDEVICE(INTEL, 0xa386), board_ahci }, /* Comet Lake PCH-V RAID */
{ PCI_VDEVICE(INTEL, 0x0f22), board_ahci_mobile }, /* Bay Trail AHCI */
{ PCI_VDEVICE(INTEL, 0x0f23), board_ahci_mobile }, /* Bay Trail AHCI */
{ PCI_VDEVICE(INTEL, 0x22a3), board_ahci_mobile }, /* Cherry Tr. AHCI */
/* Enmotus */
{ PCI_DEVICE(0x1c44, 0x8000), board_ahci },
+ /* Loongson */
+ { PCI_VDEVICE(LOONGSON, 0x7a08), board_ahci },
+
/* Generic, PCI class code for AHCI */
{ PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
PCI_CLASS_STORAGE_SATA_AHCI, 0xffffff, board_ahci },
ahci_pci_bar = AHCI_PCI_BAR_CAVIUM;
if (pdev->device == 0xa084)
ahci_pci_bar = AHCI_PCI_BAR_CAVIUM_GEN5;
+ } else if (pdev->vendor == PCI_VENDOR_ID_LOONGSON) {
+ if (pdev->device == 0x7a08)
+ ahci_pci_bar = AHCI_PCI_BAR_LOONGSON;
}
/* acquire resources */
/*
* libata-core.c - helper library for ATA
*
- * Maintained by: Tejun Heo <tj@kernel.org>
- * Please ALWAYS copy linux-ide@vger.kernel.org
- * on emails.
- *
* Copyright 2003-2004 Red Hat, Inc. All rights reserved.
* Copyright 2003-2004 Jeff Garzik
*
* http://www.compactflash.org (CF)
* http://www.qic.org (QIC157 - Tape and DSC)
* http://www.ce-ata.org (CE-ATA: not supported)
+ *
+ * libata is essentially a library of internal helper functions for
+ * low-level ATA host controller drivers. As such, the API/ABI is
+ * likely to change as new drivers are added and updated.
+ * Do not depend on ABI/API stability.
*/
#include <linux/kernel.h>
#include <linux/leds.h>
#include <linux/pm_runtime.h>
#include <linux/platform_device.h>
+#include <asm/setup.h>
#define CREATE_TRACE_POINTS
#include <trace/events/libata.h>
#include "libata.h"
#include "libata-transport.h"
-/* debounce timing parameters in msecs { interval, duration, timeout } */
-const unsigned long sata_deb_timing_normal[] = { 5, 100, 2000 };
-const unsigned long sata_deb_timing_hotplug[] = { 25, 500, 2000 };
-const unsigned long sata_deb_timing_long[] = { 100, 2000, 5000 };
-
const struct ata_port_operations ata_base_port_ops = {
.prereset = ata_std_prereset,
.postreset = ata_std_postreset,
.qc_defer = ata_std_qc_defer,
.hardreset = sata_std_hardreset,
};
+EXPORT_SYMBOL_GPL(sata_port_ops);
static unsigned int ata_dev_init_params(struct ata_device *dev,
u16 heads, u16 sectors);
atomic_t ata_print_id = ATOMIC_INIT(0);
+#ifdef CONFIG_ATA_FORCE
struct ata_force_param {
const char *name;
- unsigned int cbl;
- int spd_limit;
+ u8 cbl;
+ u8 spd_limit;
unsigned long xfer_mask;
unsigned int horkage_on;
unsigned int horkage_off;
- unsigned int lflags;
+ u16 lflags;
};
struct ata_force_ent {
static struct ata_force_ent *ata_force_tbl;
static int ata_force_tbl_size;
-static char ata_force_param_buf[PAGE_SIZE] __initdata;
+static char ata_force_param_buf[COMMAND_LINE_SIZE] __initdata;
/* param_buf is thrown away after initialization, disallow read */
module_param_string(force, ata_force_param_buf, sizeof(ata_force_param_buf), 0);
MODULE_PARM_DESC(force, "Force ATA configurations including cable type, link speed and transfer mode (see Documentation/admin-guide/kernel-parameters.rst for details)");
+#endif
static int atapi_enabled = 1;
module_param(atapi_enabled, int, 0444);
return NULL;
}
+EXPORT_SYMBOL_GPL(ata_link_next);
/**
* ata_dev_next - device iteration helper
goto next;
return dev;
}
+EXPORT_SYMBOL_GPL(ata_dev_next);
/**
* ata_dev_phys_link - find physical link for a device
return ap->slave_link;
}
+#ifdef CONFIG_ATA_FORCE
/**
* ata_force_cbl - force cable type according to libata.force
* @ap: ATA port of interest
fe->param.name);
}
}
+#else
+static inline void ata_force_link_limits(struct ata_link *link) { }
+static inline void ata_force_xfermask(struct ata_device *dev) { }
+static inline void ata_force_horkage(struct ata_device *dev) { }
+#endif
/**
* atapi_cmd_type - Determine ATAPI command type from SCSI opcode
return ATAPI_MISC;
}
}
-
-/**
- * ata_tf_to_fis - Convert ATA taskfile to SATA FIS structure
- * @tf: Taskfile to convert
- * @pmp: Port multiplier port
- * @is_cmd: This FIS is for command
- * @fis: Buffer into which data will output
- *
- * Converts a standard ATA taskfile to a Serial ATA
- * FIS structure (Register - Host to Device).
- *
- * LOCKING:
- * Inherited from caller.
- */
-void ata_tf_to_fis(const struct ata_taskfile *tf, u8 pmp, int is_cmd, u8 *fis)
-{
- fis[0] = 0x27; /* Register - Host to Device FIS */
- fis[1] = pmp & 0xf; /* Port multiplier number*/
- if (is_cmd)
- fis[1] |= (1 << 7); /* bit 7 indicates Command FIS */
-
- fis[2] = tf->command;
- fis[3] = tf->feature;
-
- fis[4] = tf->lbal;
- fis[5] = tf->lbam;
- fis[6] = tf->lbah;
- fis[7] = tf->device;
-
- fis[8] = tf->hob_lbal;
- fis[9] = tf->hob_lbam;
- fis[10] = tf->hob_lbah;
- fis[11] = tf->hob_feature;
-
- fis[12] = tf->nsect;
- fis[13] = tf->hob_nsect;
- fis[14] = 0;
- fis[15] = tf->ctl;
-
- fis[16] = tf->auxiliary & 0xff;
- fis[17] = (tf->auxiliary >> 8) & 0xff;
- fis[18] = (tf->auxiliary >> 16) & 0xff;
- fis[19] = (tf->auxiliary >> 24) & 0xff;
-}
-
-/**
- * ata_tf_from_fis - Convert SATA FIS to ATA taskfile
- * @fis: Buffer from which data will be input
- * @tf: Taskfile to output
- *
- * Converts a serial ATA FIS structure to a standard ATA taskfile.
- *
- * LOCKING:
- * Inherited from caller.
- */
-
-void ata_tf_from_fis(const u8 *fis, struct ata_taskfile *tf)
-{
- tf->command = fis[2]; /* status */
- tf->feature = fis[3]; /* error */
-
- tf->lbal = fis[4];
- tf->lbam = fis[5];
- tf->lbah = fis[6];
- tf->device = fis[7];
-
- tf->hob_lbal = fis[8];
- tf->hob_lbam = fis[9];
- tf->hob_lbah = fis[10];
-
- tf->nsect = fis[12];
- tf->hob_nsect = fis[13];
-}
+EXPORT_SYMBOL_GPL(atapi_cmd_type);
static const u8 ata_rw_cmds[] = {
/* pio multi */
((mwdma_mask << ATA_SHIFT_MWDMA) & ATA_MASK_MWDMA) |
((udma_mask << ATA_SHIFT_UDMA) & ATA_MASK_UDMA);
}
+EXPORT_SYMBOL_GPL(ata_pack_xfermask);
/**
* ata_unpack_xfermask - Unpack xfer_mask into pio, mwdma and udma masks
return ent->base + highbit - ent->shift;
return 0xff;
}
+EXPORT_SYMBOL_GPL(ata_xfer_mask2mode);
/**
* ata_xfer_mode2mask - Find matching xfer_mask for XFER_*
& ~((1 << ent->shift) - 1);
return 0;
}
+EXPORT_SYMBOL_GPL(ata_xfer_mode2mask);
/**
* ata_xfer_mode2shift - Find matching xfer_shift for XFER_*
return ent->shift;
return -1;
}
+EXPORT_SYMBOL_GPL(ata_xfer_mode2shift);
/**
* ata_mode_string - convert xfer_mask to string
return xfer_mode_str[highbit];
return "<n/a>";
}
+EXPORT_SYMBOL_GPL(ata_mode_string);
const char *sata_spd_string(unsigned int spd)
{
DPRINTK("unknown device\n");
return ATA_DEV_UNKNOWN;
}
+EXPORT_SYMBOL_GPL(ata_dev_classify);
/**
* ata_id_string - Convert IDENTIFY DEVICE page into string
len -= 2;
}
}
+EXPORT_SYMBOL_GPL(ata_id_string);
/**
* ata_id_c_string - Convert IDENTIFY DEVICE page into C string
p--;
*p = '\0';
}
+EXPORT_SYMBOL_GPL(ata_id_c_string);
static u64 ata_id_n_sectors(const u16 *id)
{
return ata_pack_xfermask(pio_mask, mwdma_mask, udma_mask);
}
+EXPORT_SYMBOL_GPL(ata_id_xfermask);
static void ata_qc_complete_internal(struct ata_queued_cmd *qc)
{
return 1;
return 0;
}
+EXPORT_SYMBOL_GPL(ata_pio_need_iordy);
/**
* ata_pio_mask_no_iordy - Return the non IORDY mask
return ata_exec_internal(dev, tf, NULL, DMA_FROM_DEVICE,
id, sizeof(id[0]) * ATA_ID_WORDS, 0);
}
+EXPORT_SYMBOL_GPL(ata_do_dev_read_id);
/**
* ata_dev_read_id - Read ID data from the specified device
desc[0] = '\0';
return 0;
}
+ if (!IS_ENABLED(CONFIG_SATA_HOST))
+ return 0;
if (dev->horkage & ATA_HORKAGE_NONCQ) {
snprintf(desc, desc_sz, "NCQ (not used)");
return 0;
{
return ATA_CBL_PATA40;
}
+EXPORT_SYMBOL_GPL(ata_cable_40wire);
/**
* ata_cable_80wire - return 80 wire cable type
{
return ATA_CBL_PATA80;
}
+EXPORT_SYMBOL_GPL(ata_cable_80wire);
/**
* ata_cable_unknown - return unknown PATA cable.
{
return ATA_CBL_PATA_UNK;
}
+EXPORT_SYMBOL_GPL(ata_cable_unknown);
/**
* ata_cable_ignore - return ignored PATA cable.
{
return ATA_CBL_PATA_IGN;
}
+EXPORT_SYMBOL_GPL(ata_cable_ignore);
/**
* ata_cable_sata - return SATA cable type
{
return ATA_CBL_SATA;
}
+EXPORT_SYMBOL_GPL(ata_cable_sata);
/**
* ata_bus_probe - Reset and probe ATA bus
return NULL;
return pair;
}
+EXPORT_SYMBOL_GPL(ata_dev_pair);
/**
* sata_down_spd_limit - adjust SATA spd limit downward
return 0;
}
-static int __sata_set_spd_needed(struct ata_link *link, u32 *scontrol)
-{
- struct ata_link *host_link = &link->ap->link;
- u32 limit, target, spd;
-
- limit = link->sata_spd_limit;
-
- /* Don't configure downstream link faster than upstream link.
- * It doesn't speed up anything and some PMPs choke on such
- * configuration.
- */
- if (!ata_is_host_link(link) && host_link->sata_spd)
- limit &= (1 << host_link->sata_spd) - 1;
-
- if (limit == UINT_MAX)
- target = 0;
- else
- target = fls(limit);
-
- spd = (*scontrol >> 4) & 0xf;
- *scontrol = (*scontrol & ~0xf0) | ((target & 0xf) << 4);
-
- return spd != target;
-}
-
-/**
- * sata_set_spd_needed - is SATA spd configuration needed
- * @link: Link in question
- *
- * Test whether the spd limit in SControl matches
- * @link->sata_spd_limit. This function is used to determine
- * whether hardreset is necessary to apply SATA spd
- * configuration.
- *
- * LOCKING:
- * Inherited from caller.
- *
- * RETURNS:
- * 1 if SATA spd configuration is needed, 0 otherwise.
- */
-static int sata_set_spd_needed(struct ata_link *link)
-{
- u32 scontrol;
-
- if (sata_scr_read(link, SCR_CONTROL, &scontrol))
- return 1;
-
- return __sata_set_spd_needed(link, &scontrol);
-}
-
-/**
- * sata_set_spd - set SATA spd according to spd limit
- * @link: Link to set SATA spd for
- *
- * Set SATA spd of @link according to sata_spd_limit.
- *
- * LOCKING:
- * Inherited from caller.
- *
- * RETURNS:
- * 0 if spd doesn't need to be changed, 1 if spd has been
- * changed. Negative errno if SCR registers are inaccessible.
- */
-int sata_set_spd(struct ata_link *link)
-{
- u32 scontrol;
- int rc;
-
- if ((rc = sata_scr_read(link, SCR_CONTROL, &scontrol)))
- return rc;
-
- if (!__sata_set_spd_needed(link, &scontrol))
- return 0;
-
- if ((rc = sata_scr_write(link, SCR_CONTROL, scontrol)))
- return rc;
-
- return 1;
-}
-
-/*
- * This mode timing computation functionality is ported over from
- * drivers/ide/ide-timing.h and was originally written by Vojtech Pavlik
- */
-/*
- * PIO 0-4, MWDMA 0-2 and UDMA 0-6 timings (in nanoseconds).
- * These were taken from ATA/ATAPI-6 standard, rev 0a, except
- * for UDMA6, which is currently supported only by Maxtor drives.
- *
- * For PIO 5/6 MWDMA 3/4 see the CFA specification 3.0.
- */
-
-static const struct ata_timing ata_timing[] = {
-/* { XFER_PIO_SLOW, 120, 290, 240, 960, 290, 240, 0, 960, 0 }, */
- { XFER_PIO_0, 70, 290, 240, 600, 165, 150, 0, 600, 0 },
- { XFER_PIO_1, 50, 290, 93, 383, 125, 100, 0, 383, 0 },
- { XFER_PIO_2, 30, 290, 40, 330, 100, 90, 0, 240, 0 },
- { XFER_PIO_3, 30, 80, 70, 180, 80, 70, 0, 180, 0 },
- { XFER_PIO_4, 25, 70, 25, 120, 70, 25, 0, 120, 0 },
- { XFER_PIO_5, 15, 65, 25, 100, 65, 25, 0, 100, 0 },
- { XFER_PIO_6, 10, 55, 20, 80, 55, 20, 0, 80, 0 },
-
- { XFER_SW_DMA_0, 120, 0, 0, 0, 480, 480, 50, 960, 0 },
- { XFER_SW_DMA_1, 90, 0, 0, 0, 240, 240, 30, 480, 0 },
- { XFER_SW_DMA_2, 60, 0, 0, 0, 120, 120, 20, 240, 0 },
-
- { XFER_MW_DMA_0, 60, 0, 0, 0, 215, 215, 20, 480, 0 },
- { XFER_MW_DMA_1, 45, 0, 0, 0, 80, 50, 5, 150, 0 },
- { XFER_MW_DMA_2, 25, 0, 0, 0, 70, 25, 5, 120, 0 },
- { XFER_MW_DMA_3, 25, 0, 0, 0, 65, 25, 5, 100, 0 },
- { XFER_MW_DMA_4, 25, 0, 0, 0, 55, 20, 5, 80, 0 },
-
-/* { XFER_UDMA_SLOW, 0, 0, 0, 0, 0, 0, 0, 0, 150 }, */
- { XFER_UDMA_0, 0, 0, 0, 0, 0, 0, 0, 0, 120 },
- { XFER_UDMA_1, 0, 0, 0, 0, 0, 0, 0, 0, 80 },
- { XFER_UDMA_2, 0, 0, 0, 0, 0, 0, 0, 0, 60 },
- { XFER_UDMA_3, 0, 0, 0, 0, 0, 0, 0, 0, 45 },
- { XFER_UDMA_4, 0, 0, 0, 0, 0, 0, 0, 0, 30 },
- { XFER_UDMA_5, 0, 0, 0, 0, 0, 0, 0, 0, 20 },
- { XFER_UDMA_6, 0, 0, 0, 0, 0, 0, 0, 0, 15 },
-
- { 0xFF }
-};
-
-#define ENOUGH(v, unit) (((v)-1)/(unit)+1)
-#define EZ(v, unit) ((v)?ENOUGH(((v) * 1000), unit):0)
-
-static void ata_timing_quantize(const struct ata_timing *t, struct ata_timing *q, int T, int UT)
-{
- q->setup = EZ(t->setup, T);
- q->act8b = EZ(t->act8b, T);
- q->rec8b = EZ(t->rec8b, T);
- q->cyc8b = EZ(t->cyc8b, T);
- q->active = EZ(t->active, T);
- q->recover = EZ(t->recover, T);
- q->dmack_hold = EZ(t->dmack_hold, T);
- q->cycle = EZ(t->cycle, T);
- q->udma = EZ(t->udma, UT);
-}
-
-void ata_timing_merge(const struct ata_timing *a, const struct ata_timing *b,
- struct ata_timing *m, unsigned int what)
-{
- if (what & ATA_TIMING_SETUP ) m->setup = max(a->setup, b->setup);
- if (what & ATA_TIMING_ACT8B ) m->act8b = max(a->act8b, b->act8b);
- if (what & ATA_TIMING_REC8B ) m->rec8b = max(a->rec8b, b->rec8b);
- if (what & ATA_TIMING_CYC8B ) m->cyc8b = max(a->cyc8b, b->cyc8b);
- if (what & ATA_TIMING_ACTIVE ) m->active = max(a->active, b->active);
- if (what & ATA_TIMING_RECOVER) m->recover = max(a->recover, b->recover);
- if (what & ATA_TIMING_DMACK_HOLD) m->dmack_hold = max(a->dmack_hold, b->dmack_hold);
- if (what & ATA_TIMING_CYCLE ) m->cycle = max(a->cycle, b->cycle);
- if (what & ATA_TIMING_UDMA ) m->udma = max(a->udma, b->udma);
-}
-
-const struct ata_timing *ata_timing_find_mode(u8 xfer_mode)
-{
- const struct ata_timing *t = ata_timing;
-
- while (xfer_mode > t->mode)
- t++;
-
- if (xfer_mode == t->mode)
- return t;
-
- WARN_ONCE(true, "%s: unable to find timing for xfer_mode 0x%x\n",
- __func__, xfer_mode);
-
- return NULL;
-}
-
-int ata_timing_compute(struct ata_device *adev, unsigned short speed,
- struct ata_timing *t, int T, int UT)
-{
- const u16 *id = adev->id;
- const struct ata_timing *s;
- struct ata_timing p;
-
- /*
- * Find the mode.
- */
-
- if (!(s = ata_timing_find_mode(speed)))
- return -EINVAL;
-
- memcpy(t, s, sizeof(*s));
-
- /*
- * If the drive is an EIDE drive, it can tell us it needs extended
- * PIO/MW_DMA cycle timing.
- */
-
- if (id[ATA_ID_FIELD_VALID] & 2) { /* EIDE drive */
- memset(&p, 0, sizeof(p));
-
- if (speed >= XFER_PIO_0 && speed < XFER_SW_DMA_0) {
- if (speed <= XFER_PIO_2)
- p.cycle = p.cyc8b = id[ATA_ID_EIDE_PIO];
- else if ((speed <= XFER_PIO_4) ||
- (speed == XFER_PIO_5 && !ata_id_is_cfa(id)))
- p.cycle = p.cyc8b = id[ATA_ID_EIDE_PIO_IORDY];
- } else if (speed >= XFER_MW_DMA_0 && speed <= XFER_MW_DMA_2)
- p.cycle = id[ATA_ID_EIDE_DMA_MIN];
-
- ata_timing_merge(&p, t, t, ATA_TIMING_CYCLE | ATA_TIMING_CYC8B);
- }
-
- /*
- * Convert the timing to bus clock counts.
- */
-
- ata_timing_quantize(t, t, T, UT);
-
- /*
- * Even in DMA/UDMA modes we still use PIO access for IDENTIFY,
- * S.M.A.R.T * and some other commands. We have to ensure that the
- * DMA cycle timing is slower/equal than the fastest PIO timing.
- */
-
- if (speed > XFER_PIO_6) {
- ata_timing_compute(adev, adev->pio_mode, &p, T, UT);
- ata_timing_merge(&p, t, t, ATA_TIMING_ALL);
- }
-
- /*
- * Lengthen active & recovery time so that cycle time is correct.
- */
-
- if (t->act8b + t->rec8b < t->cyc8b) {
- t->act8b += (t->cyc8b - (t->act8b + t->rec8b)) / 2;
- t->rec8b = t->cyc8b - t->act8b;
- }
-
- if (t->active + t->recover < t->cycle) {
- t->active += (t->cycle - (t->active + t->recover)) / 2;
- t->recover = t->cycle - t->active;
- }
-
- /* In a few cases quantisation may produce enough errors to
- leave t->cycle too low for the sum of active and recovery
- if so we must correct this */
- if (t->active + t->recover > t->cycle)
- t->cycle = t->active + t->recover;
-
- return 0;
-}
-
+#ifdef CONFIG_ATA_ACPI
/**
* ata_timing_cycle2mode - find xfer mode for the specified cycle duration
* @xfer_shift: ATA_SHIFT_* value for transfer type to examine.
return last_mode;
}
+#endif
/**
* ata_down_xfermask_limit - adjust dev xfer masks downward
*r_failed_dev = dev;
return rc;
}
+EXPORT_SYMBOL_GPL(ata_do_set_mode);
/**
* ata_wait_ready - wait for link to become ready
return ata_wait_ready(link, deadline, check_ready);
}
-
-/**
- * sata_link_debounce - debounce SATA phy status
- * @link: ATA link to debounce SATA phy status for
- * @params: timing parameters { interval, duration, timeout } in msec
- * @deadline: deadline jiffies for the operation
- *
- * Make sure SStatus of @link reaches stable state, determined by
- * holding the same value where DET is not 1 for @duration polled
- * every @interval, before @timeout. Timeout constraints the
- * beginning of the stable state. Because DET gets stuck at 1 on
- * some controllers after hot unplugging, this functions waits
- * until timeout then returns 0 if DET is stable at 1.
- *
- * @timeout is further limited by @deadline. The sooner of the
- * two is used.
- *
- * LOCKING:
- * Kernel thread context (may sleep)
- *
- * RETURNS:
- * 0 on success, -errno on failure.
- */
-int sata_link_debounce(struct ata_link *link, const unsigned long *params,
- unsigned long deadline)
-{
- unsigned long interval = params[0];
- unsigned long duration = params[1];
- unsigned long last_jiffies, t;
- u32 last, cur;
- int rc;
-
- t = ata_deadline(jiffies, params[2]);
- if (time_before(t, deadline))
- deadline = t;
-
- if ((rc = sata_scr_read(link, SCR_STATUS, &cur)))
- return rc;
- cur &= 0xf;
-
- last = cur;
- last_jiffies = jiffies;
-
- while (1) {
- ata_msleep(link->ap, interval);
- if ((rc = sata_scr_read(link, SCR_STATUS, &cur)))
- return rc;
- cur &= 0xf;
-
- /* DET stable? */
- if (cur == last) {
- if (cur == 1 && time_before(jiffies, deadline))
- continue;
- if (time_after(jiffies,
- ata_deadline(last_jiffies, duration)))
- return 0;
- continue;
- }
-
- /* unstable, start over */
- last = cur;
- last_jiffies = jiffies;
-
- /* Check deadline. If debouncing failed, return
- * -EPIPE to tell upper layer to lower link speed.
- */
- if (time_after(jiffies, deadline))
- return -EPIPE;
- }
-}
-
-/**
- * sata_link_resume - resume SATA link
- * @link: ATA link to resume SATA
- * @params: timing parameters { interval, duration, timeout } in msec
- * @deadline: deadline jiffies for the operation
- *
- * Resume SATA phy @link and debounce it.
- *
- * LOCKING:
- * Kernel thread context (may sleep)
- *
- * RETURNS:
- * 0 on success, -errno on failure.
- */
-int sata_link_resume(struct ata_link *link, const unsigned long *params,
- unsigned long deadline)
-{
- int tries = ATA_LINK_RESUME_TRIES;
- u32 scontrol, serror;
- int rc;
-
- if ((rc = sata_scr_read(link, SCR_CONTROL, &scontrol)))
- return rc;
-
- /*
- * Writes to SControl sometimes get ignored under certain
- * controllers (ata_piix SIDPR). Make sure DET actually is
- * cleared.
- */
- do {
- scontrol = (scontrol & 0x0f0) | 0x300;
- if ((rc = sata_scr_write(link, SCR_CONTROL, scontrol)))
- return rc;
- /*
- * Some PHYs react badly if SStatus is pounded
- * immediately after resuming. Delay 200ms before
- * debouncing.
- */
- if (!(link->flags & ATA_LFLAG_NO_DB_DELAY))
- ata_msleep(link->ap, 200);
-
- /* is SControl restored correctly? */
- if ((rc = sata_scr_read(link, SCR_CONTROL, &scontrol)))
- return rc;
- } while ((scontrol & 0xf0f) != 0x300 && --tries);
-
- if ((scontrol & 0xf0f) != 0x300) {
- ata_link_warn(link, "failed to resume link (SControl %X)\n",
- scontrol);
- return 0;
- }
-
- if (tries < ATA_LINK_RESUME_TRIES)
- ata_link_warn(link, "link resume succeeded after %d retries\n",
- ATA_LINK_RESUME_TRIES - tries);
-
- if ((rc = sata_link_debounce(link, params, deadline)))
- return rc;
-
- /* clear SError, some PHYs require this even for SRST to work */
- if (!(rc = sata_scr_read(link, SCR_ERROR, &serror)))
- rc = sata_scr_write(link, SCR_ERROR, serror);
-
- return rc != -EINVAL ? rc : 0;
-}
-
-/**
- * sata_link_scr_lpm - manipulate SControl IPM and SPM fields
- * @link: ATA link to manipulate SControl for
- * @policy: LPM policy to configure
- * @spm_wakeup: initiate LPM transition to active state
- *
- * Manipulate the IPM field of the SControl register of @link
- * according to @policy. If @policy is ATA_LPM_MAX_POWER and
- * @spm_wakeup is %true, the SPM field is manipulated to wake up
- * the link. This function also clears PHYRDY_CHG before
- * returning.
- *
- * LOCKING:
- * EH context.
- *
- * RETURNS:
- * 0 on success, -errno otherwise.
- */
-int sata_link_scr_lpm(struct ata_link *link, enum ata_lpm_policy policy,
- bool spm_wakeup)
-{
- struct ata_eh_context *ehc = &link->eh_context;
- bool woken_up = false;
- u32 scontrol;
- int rc;
-
- rc = sata_scr_read(link, SCR_CONTROL, &scontrol);
- if (rc)
- return rc;
-
- switch (policy) {
- case ATA_LPM_MAX_POWER:
- /* disable all LPM transitions */
- scontrol |= (0x7 << 8);
- /* initiate transition to active state */
- if (spm_wakeup) {
- scontrol |= (0x4 << 12);
- woken_up = true;
- }
- break;
- case ATA_LPM_MED_POWER:
- /* allow LPM to PARTIAL */
- scontrol &= ~(0x1 << 8);
- scontrol |= (0x6 << 8);
- break;
- case ATA_LPM_MED_POWER_WITH_DIPM:
- case ATA_LPM_MIN_POWER_WITH_PARTIAL:
- case ATA_LPM_MIN_POWER:
- if (ata_link_nr_enabled(link) > 0)
- /* no restrictions on LPM transitions */
- scontrol &= ~(0x7 << 8);
- else {
- /* empty port, power off */
- scontrol &= ~0xf;
- scontrol |= (0x1 << 2);
- }
- break;
- default:
- WARN_ON(1);
- }
-
- rc = sata_scr_write(link, SCR_CONTROL, scontrol);
- if (rc)
- return rc;
-
- /* give the link time to transit out of LPM state */
- if (woken_up)
- msleep(10);
-
- /* clear PHYRDY_CHG from SError */
- ehc->i.serror &= ~SERR_PHYRDY_CHG;
- return sata_scr_write(link, SCR_ERROR, SERR_PHYRDY_CHG);
-}
+EXPORT_SYMBOL_GPL(ata_wait_after_reset);
/**
* ata_std_prereset - prepare for reset
return 0;
}
-
-/**
- * sata_link_hardreset - reset link via SATA phy reset
- * @link: link to reset
- * @timing: timing parameters { interval, duration, timeout } in msec
- * @deadline: deadline jiffies for the operation
- * @online: optional out parameter indicating link onlineness
- * @check_ready: optional callback to check link readiness
- *
- * SATA phy-reset @link using DET bits of SControl register.
- * After hardreset, link readiness is waited upon using
- * ata_wait_ready() if @check_ready is specified. LLDs are
- * allowed to not specify @check_ready and wait itself after this
- * function returns. Device classification is LLD's
- * responsibility.
- *
- * *@online is set to one iff reset succeeded and @link is online
- * after reset.
- *
- * LOCKING:
- * Kernel thread context (may sleep)
- *
- * RETURNS:
- * 0 on success, -errno otherwise.
- */
-int sata_link_hardreset(struct ata_link *link, const unsigned long *timing,
- unsigned long deadline,
- bool *online, int (*check_ready)(struct ata_link *))
-{
- u32 scontrol;
- int rc;
-
- DPRINTK("ENTER\n");
-
- if (online)
- *online = false;
-
- if (sata_set_spd_needed(link)) {
- /* SATA spec says nothing about how to reconfigure
- * spd. To be on the safe side, turn off phy during
- * reconfiguration. This works for at least ICH7 AHCI
- * and Sil3124.
- */
- if ((rc = sata_scr_read(link, SCR_CONTROL, &scontrol)))
- goto out;
-
- scontrol = (scontrol & 0x0f0) | 0x304;
-
- if ((rc = sata_scr_write(link, SCR_CONTROL, scontrol)))
- goto out;
-
- sata_set_spd(link);
- }
-
- /* issue phy wake/reset */
- if ((rc = sata_scr_read(link, SCR_CONTROL, &scontrol)))
- goto out;
-
- scontrol = (scontrol & 0x0f0) | 0x301;
-
- if ((rc = sata_scr_write_flush(link, SCR_CONTROL, scontrol)))
- goto out;
-
- /* Couldn't find anything in SATA I/II specs, but AHCI-1.1
- * 10.4.2 says at least 1 ms.
- */
- ata_msleep(link->ap, 1);
-
- /* bring link back */
- rc = sata_link_resume(link, timing, deadline);
- if (rc)
- goto out;
- /* if link is offline nothing more to do */
- if (ata_phys_link_offline(link))
- goto out;
-
- /* Link is online. From this point, -ENODEV too is an error. */
- if (online)
- *online = true;
-
- if (sata_pmp_supported(link->ap) && ata_is_host_link(link)) {
- /* If PMP is supported, we have to do follow-up SRST.
- * Some PMPs don't send D2H Reg FIS after hardreset if
- * the first port is empty. Wait only for
- * ATA_TMOUT_PMP_SRST_WAIT.
- */
- if (check_ready) {
- unsigned long pmp_deadline;
-
- pmp_deadline = ata_deadline(jiffies,
- ATA_TMOUT_PMP_SRST_WAIT);
- if (time_after(pmp_deadline, deadline))
- pmp_deadline = deadline;
- ata_wait_ready(link, pmp_deadline, check_ready);
- }
- rc = -EAGAIN;
- goto out;
- }
-
- rc = 0;
- if (check_ready)
- rc = ata_wait_ready(link, deadline, check_ready);
- out:
- if (rc && rc != -EAGAIN) {
- /* online is set iff link is online && reset succeeded */
- if (online)
- *online = false;
- ata_link_err(link, "COMRESET failed (errno=%d)\n", rc);
- }
- DPRINTK("EXIT, rc=%d\n", rc);
- return rc;
-}
+EXPORT_SYMBOL_GPL(ata_std_prereset);
/**
* sata_std_hardreset - COMRESET w/o waiting or classification
rc = sata_link_hardreset(link, timing, deadline, &online, NULL);
return online ? -EAGAIN : rc;
}
+EXPORT_SYMBOL_GPL(sata_std_hardreset);
/**
* ata_std_postreset - standard postreset callback
DPRINTK("EXIT\n");
}
+EXPORT_SYMBOL_GPL(ata_std_postreset);
/**
* ata_dev_same_device - Determine whether new ID matches configured device
return ATA_DEFER_LINK;
}
+EXPORT_SYMBOL_GPL(ata_std_qc_defer);
enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc)
{
return AC_ERR_OK;
}
+EXPORT_SYMBOL_GPL(ata_noop_qc_prep);
/**
* ata_sg_init - Associate command with scatter-gather table.
__ata_qc_complete(qc);
}
}
+EXPORT_SYMBOL_GPL(ata_qc_complete);
/**
* ata_qc_get_active - get bitmask of active qcs
EXPORT_SYMBOL_GPL(ata_qc_get_active);
/**
- * ata_qc_complete_multiple - Complete multiple qcs successfully
- * @ap: port in question
- * @qc_active: new qc_active mask
- *
- * Complete in-flight commands. This functions is meant to be
- * called from low-level driver's interrupt routine to complete
- * requests normally. ap->qc_active and @qc_active is compared
- * and commands are completed accordingly.
- *
- * Always use this function when completing multiple NCQ commands
- * from IRQ handlers instead of calling ata_qc_complete()
- * multiple times to keep IRQ expect status properly in sync.
- *
- * LOCKING:
- * spin_lock_irqsave(host lock)
- *
- * RETURNS:
- * Number of completed commands on success, -errno otherwise.
- */
-int ata_qc_complete_multiple(struct ata_port *ap, u64 qc_active)
-{
- u64 done_mask, ap_qc_active = ap->qc_active;
- int nr_done = 0;
-
- /*
- * If the internal tag is set on ap->qc_active, then we care about
- * bit0 on the passed in qc_active mask. Move that bit up to match
- * the internal tag.
- */
- if (ap_qc_active & (1ULL << ATA_TAG_INTERNAL)) {
- qc_active |= (qc_active & 0x01) << ATA_TAG_INTERNAL;
- qc_active ^= qc_active & 0x01;
- }
-
- done_mask = ap_qc_active ^ qc_active;
-
- if (unlikely(done_mask & qc_active)) {
- ata_port_err(ap, "illegal qc_active transition (%08llx->%08llx)\n",
- ap->qc_active, qc_active);
- return -EINVAL;
- }
-
- while (done_mask) {
- struct ata_queued_cmd *qc;
- unsigned int tag = __ffs64(done_mask);
-
- qc = ata_qc_from_tag(ap, tag);
- if (qc) {
- ata_qc_complete(qc);
- nr_done++;
- }
- done_mask &= ~(1ULL << tag);
- }
-
- return nr_done;
-}
-
-/**
* ata_qc_issue - issue taskfile to device
* @qc: command to issue to device
*
}
/**
- * sata_scr_valid - test whether SCRs are accessible
- * @link: ATA link to test SCR accessibility for
- *
- * Test whether SCRs are accessible for @link.
- *
- * LOCKING:
- * None.
- *
- * RETURNS:
- * 1 if SCRs are accessible, 0 otherwise.
- */
-int sata_scr_valid(struct ata_link *link)
-{
- struct ata_port *ap = link->ap;
-
- return (ap->flags & ATA_FLAG_SATA) && ap->ops->scr_read;
-}
-
-/**
- * sata_scr_read - read SCR register of the specified port
- * @link: ATA link to read SCR for
- * @reg: SCR to read
- * @val: Place to store read value
- *
- * Read SCR register @reg of @link into *@val. This function is
- * guaranteed to succeed if @link is ap->link, the cable type of
- * the port is SATA and the port implements ->scr_read.
- *
- * LOCKING:
- * None if @link is ap->link. Kernel thread context otherwise.
- *
- * RETURNS:
- * 0 on success, negative errno on failure.
- */
-int sata_scr_read(struct ata_link *link, int reg, u32 *val)
-{
- if (ata_is_host_link(link)) {
- if (sata_scr_valid(link))
- return link->ap->ops->scr_read(link, reg, val);
- return -EOPNOTSUPP;
- }
-
- return sata_pmp_scr_read(link, reg, val);
-}
-
-/**
- * sata_scr_write - write SCR register of the specified port
- * @link: ATA link to write SCR for
- * @reg: SCR to write
- * @val: value to write
- *
- * Write @val to SCR register @reg of @link. This function is
- * guaranteed to succeed if @link is ap->link, the cable type of
- * the port is SATA and the port implements ->scr_read.
- *
- * LOCKING:
- * None if @link is ap->link. Kernel thread context otherwise.
- *
- * RETURNS:
- * 0 on success, negative errno on failure.
- */
-int sata_scr_write(struct ata_link *link, int reg, u32 val)
-{
- if (ata_is_host_link(link)) {
- if (sata_scr_valid(link))
- return link->ap->ops->scr_write(link, reg, val);
- return -EOPNOTSUPP;
- }
-
- return sata_pmp_scr_write(link, reg, val);
-}
-
-/**
- * sata_scr_write_flush - write SCR register of the specified port and flush
- * @link: ATA link to write SCR for
- * @reg: SCR to write
- * @val: value to write
- *
- * This function is identical to sata_scr_write() except that this
- * function performs flush after writing to the register.
- *
- * LOCKING:
- * None if @link is ap->link. Kernel thread context otherwise.
- *
- * RETURNS:
- * 0 on success, negative errno on failure.
- */
-int sata_scr_write_flush(struct ata_link *link, int reg, u32 val)
-{
- if (ata_is_host_link(link)) {
- int rc;
-
- if (sata_scr_valid(link)) {
- rc = link->ap->ops->scr_write(link, reg, val);
- if (rc == 0)
- rc = link->ap->ops->scr_read(link, reg, &val);
- return rc;
- }
- return -EOPNOTSUPP;
- }
-
- return sata_pmp_scr_write(link, reg, val);
-}
-
-/**
* ata_phys_link_online - test whether the given link is online
* @link: ATA link to test
*
return ata_phys_link_online(link) ||
(slave && ata_phys_link_online(slave));
}
+EXPORT_SYMBOL_GPL(ata_link_online);
/**
* ata_link_offline - test whether the given link is offline
return ata_phys_link_offline(link) &&
(!slave || ata_phys_link_offline(slave));
}
+EXPORT_SYMBOL_GPL(ata_link_offline);
#ifdef CONFIG_PM
static void ata_port_request_pm(struct ata_port *ap, pm_message_t mesg,
host->dev->power.power_state = mesg;
return 0;
}
+EXPORT_SYMBOL_GPL(ata_host_suspend);
/**
* ata_host_resume - resume host
{
host->dev->power.power_state = PMSG_ON;
}
+EXPORT_SYMBOL_GPL(ata_host_resume);
#endif
const struct device_type ata_port_type = {
{
kref_put(&host->kref, ata_host_release);
}
+EXPORT_SYMBOL_GPL(ata_host_put);
/**
* ata_host_alloc - allocate and init basic ATA host resources
kfree(host);
return NULL;
}
+EXPORT_SYMBOL_GPL(ata_host_alloc);
/**
* ata_host_alloc_pinfo - alloc host and init with port_info array
return host;
}
-
-/**
- * ata_slave_link_init - initialize slave link
- * @ap: port to initialize slave link for
- *
- * Create and initialize slave link for @ap. This enables slave
- * link handling on the port.
- *
- * In libata, a port contains links and a link contains devices.
- * There is single host link but if a PMP is attached to it,
- * there can be multiple fan-out links. On SATA, there's usually
- * a single device connected to a link but PATA and SATA
- * controllers emulating TF based interface can have two - master
- * and slave.
- *
- * However, there are a few controllers which don't fit into this
- * abstraction too well - SATA controllers which emulate TF
- * interface with both master and slave devices but also have
- * separate SCR register sets for each device. These controllers
- * need separate links for physical link handling
- * (e.g. onlineness, link speed) but should be treated like a
- * traditional M/S controller for everything else (e.g. command
- * issue, softreset).
- *
- * slave_link is libata's way of handling this class of
- * controllers without impacting core layer too much. For
- * anything other than physical link handling, the default host
- * link is used for both master and slave. For physical link
- * handling, separate @ap->slave_link is used. All dirty details
- * are implemented inside libata core layer. From LLD's POV, the
- * only difference is that prereset, hardreset and postreset are
- * called once more for the slave link, so the reset sequence
- * looks like the following.
- *
- * prereset(M) -> prereset(S) -> hardreset(M) -> hardreset(S) ->
- * softreset(M) -> postreset(M) -> postreset(S)
- *
- * Note that softreset is called only for the master. Softreset
- * resets both M/S by definition, so SRST on master should handle
- * both (the standard method will work just fine).
- *
- * LOCKING:
- * Should be called before host is registered.
- *
- * RETURNS:
- * 0 on success, -errno on failure.
- */
-int ata_slave_link_init(struct ata_port *ap)
-{
- struct ata_link *link;
-
- WARN_ON(ap->slave_link);
- WARN_ON(ap->flags & ATA_FLAG_PMP);
-
- link = kzalloc(sizeof(*link), GFP_KERNEL);
- if (!link)
- return -ENOMEM;
-
- ata_link_init(ap, link, 1);
- ap->slave_link = link;
- return 0;
-}
+EXPORT_SYMBOL_GPL(ata_host_alloc_pinfo);
static void ata_host_stop(struct device *gendev, void *res)
{
devres_free(start_dr);
return rc;
}
+EXPORT_SYMBOL_GPL(ata_host_start);
/**
* ata_sas_host_init - Initialize a host struct for sas (ipr, libsas)
host->ops = ops;
kref_init(&host->kref);
}
+EXPORT_SYMBOL_GPL(ata_host_init);
void __ata_port_probe(struct ata_port *ap)
{
return rc;
}
+EXPORT_SYMBOL_GPL(ata_host_register);
/**
* ata_host_activate - start host, request IRQ and register it
return rc;
}
+EXPORT_SYMBOL_GPL(ata_host_activate);
/**
* ata_port_detach - Detach ATA port in preparation of device removal
/* the host is dead now, dissociate ACPI */
ata_acpi_dissociate(host);
}
+EXPORT_SYMBOL_GPL(ata_host_detach);
#ifdef CONFIG_PCI
ata_host_detach(host);
}
+EXPORT_SYMBOL_GPL(ata_pci_remove_one);
void ata_pci_shutdown_one(struct pci_dev *pdev)
{
ap->ops->port_stop(ap);
}
}
+EXPORT_SYMBOL_GPL(ata_pci_shutdown_one);
/* move to PCI subsystem */
int pci_test_config_bits(struct pci_dev *pdev, const struct pci_bits *bits)
return (tmp == bits->val) ? 1 : 0;
}
+EXPORT_SYMBOL_GPL(pci_test_config_bits);
#ifdef CONFIG_PM
void ata_pci_device_do_suspend(struct pci_dev *pdev, pm_message_t mesg)
if (mesg.event & PM_EVENT_SLEEP)
pci_set_power_state(pdev, PCI_D3hot);
}
+EXPORT_SYMBOL_GPL(ata_pci_device_do_suspend);
int ata_pci_device_do_resume(struct pci_dev *pdev)
{
pci_set_master(pdev);
return 0;
}
+EXPORT_SYMBOL_GPL(ata_pci_device_do_resume);
int ata_pci_device_suspend(struct pci_dev *pdev, pm_message_t mesg)
{
return 0;
}
+EXPORT_SYMBOL_GPL(ata_pci_device_suspend);
int ata_pci_device_resume(struct pci_dev *pdev)
{
ata_host_resume(host);
return rc;
}
+EXPORT_SYMBOL_GPL(ata_pci_device_resume);
#endif /* CONFIG_PM */
-
#endif /* CONFIG_PCI */
/**
return 0;
}
+EXPORT_SYMBOL_GPL(ata_platform_remove_one);
+#ifdef CONFIG_ATA_FORCE
static int __init ata_parse_force_one(char **cur,
struct ata_force_ent *force_ent,
const char **reason)
ata_force_tbl_size = idx;
}
+static void ata_free_force_param(void)
+{
+ kfree(ata_force_tbl);
+}
+#else
+static inline void ata_parse_force_param(void) { }
+static inline void ata_free_force_param(void) { }
+#endif
+
static int __init ata_init(void)
{
int rc;
rc = ata_sff_init();
if (rc) {
- kfree(ata_force_tbl);
+ ata_free_force_param();
return rc;
}
ata_release_transport(ata_scsi_transport_template);
libata_transport_exit();
ata_sff_exit();
- kfree(ata_force_tbl);
+ ata_free_force_param();
}
subsys_initcall(ata_init);
{
return __ratelimit(&ratelimit);
}
+EXPORT_SYMBOL_GPL(ata_ratelimit);
/**
* ata_msleep - ATA EH owner aware msleep
if (owns_eh)
ata_eh_acquire(ap);
}
+EXPORT_SYMBOL_GPL(ata_msleep);
/**
* ata_wait_register - wait until register value changes
return tmp;
}
-
-/**
- * sata_lpm_ignore_phy_events - test if PHY event should be ignored
- * @link: Link receiving the event
- *
- * Test whether the received PHY event has to be ignored or not.
- *
- * LOCKING:
- * None:
- *
- * RETURNS:
- * True if the event has to be ignored.
- */
-bool sata_lpm_ignore_phy_events(struct ata_link *link)
-{
- unsigned long lpm_timeout = link->last_lpm_change +
- msecs_to_jiffies(ATA_TMOUT_SPURIOUS_PHY);
-
- /* if LPM is enabled, PHYRDY doesn't mean anything */
- if (link->lpm_policy > ATA_LPM_MAX_POWER)
- return true;
-
- /* ignore the first PHY event after the LPM policy changed
- * as it is might be spurious
- */
- if ((link->flags & ATA_LFLAG_CHANGED) &&
- time_before(jiffies, lpm_timeout))
- return true;
-
- return false;
-}
-EXPORT_SYMBOL_GPL(sata_lpm_ignore_phy_events);
+EXPORT_SYMBOL_GPL(ata_wait_register);
/*
* Dummy port_ops
.sched_eh = ata_std_sched_eh,
.end_eh = ata_std_end_eh,
};
+EXPORT_SYMBOL_GPL(ata_dummy_port_ops);
const struct ata_port_info ata_dummy_port_info = {
.port_ops = &ata_dummy_port_ops,
};
+EXPORT_SYMBOL_GPL(ata_dummy_port_info);
/*
* Utility print functions
dev_printk(KERN_DEBUG, dev, "version %s\n", version);
}
EXPORT_SYMBOL(ata_print_version);
-
-/*
- * libata is essentially a library of internal helper functions for
- * low-level ATA host controller drivers. As such, the API/ABI is
- * likely to change as new drivers are added and updated.
- * Do not depend on ABI/API stability.
- */
-EXPORT_SYMBOL_GPL(sata_deb_timing_normal);
-EXPORT_SYMBOL_GPL(sata_deb_timing_hotplug);
-EXPORT_SYMBOL_GPL(sata_deb_timing_long);
-EXPORT_SYMBOL_GPL(ata_base_port_ops);
-EXPORT_SYMBOL_GPL(sata_port_ops);
-EXPORT_SYMBOL_GPL(ata_dummy_port_ops);
-EXPORT_SYMBOL_GPL(ata_dummy_port_info);
-EXPORT_SYMBOL_GPL(ata_link_next);
-EXPORT_SYMBOL_GPL(ata_dev_next);
-EXPORT_SYMBOL_GPL(ata_std_bios_param);
-EXPORT_SYMBOL_GPL(ata_scsi_unlock_native_capacity);
-EXPORT_SYMBOL_GPL(ata_host_init);
-EXPORT_SYMBOL_GPL(ata_host_alloc);
-EXPORT_SYMBOL_GPL(ata_host_alloc_pinfo);
-EXPORT_SYMBOL_GPL(ata_slave_link_init);
-EXPORT_SYMBOL_GPL(ata_host_start);
-EXPORT_SYMBOL_GPL(ata_host_register);
-EXPORT_SYMBOL_GPL(ata_host_activate);
-EXPORT_SYMBOL_GPL(ata_host_detach);
-EXPORT_SYMBOL_GPL(ata_sg_init);
-EXPORT_SYMBOL_GPL(ata_qc_complete);
-EXPORT_SYMBOL_GPL(ata_qc_complete_multiple);
-EXPORT_SYMBOL_GPL(atapi_cmd_type);
-EXPORT_SYMBOL_GPL(ata_tf_to_fis);
-EXPORT_SYMBOL_GPL(ata_tf_from_fis);
-EXPORT_SYMBOL_GPL(ata_pack_xfermask);
-EXPORT_SYMBOL_GPL(ata_unpack_xfermask);
-EXPORT_SYMBOL_GPL(ata_xfer_mask2mode);
-EXPORT_SYMBOL_GPL(ata_xfer_mode2mask);
-EXPORT_SYMBOL_GPL(ata_xfer_mode2shift);
-EXPORT_SYMBOL_GPL(ata_mode_string);
-EXPORT_SYMBOL_GPL(ata_id_xfermask);
-EXPORT_SYMBOL_GPL(ata_do_set_mode);
-EXPORT_SYMBOL_GPL(ata_std_qc_defer);
-EXPORT_SYMBOL_GPL(ata_noop_qc_prep);
-EXPORT_SYMBOL_GPL(ata_dev_disable);
-EXPORT_SYMBOL_GPL(sata_set_spd);
-EXPORT_SYMBOL_GPL(ata_wait_after_reset);
-EXPORT_SYMBOL_GPL(sata_link_debounce);
-EXPORT_SYMBOL_GPL(sata_link_resume);
-EXPORT_SYMBOL_GPL(sata_link_scr_lpm);
-EXPORT_SYMBOL_GPL(ata_std_prereset);
-EXPORT_SYMBOL_GPL(sata_link_hardreset);
-EXPORT_SYMBOL_GPL(sata_std_hardreset);
-EXPORT_SYMBOL_GPL(ata_std_postreset);
-EXPORT_SYMBOL_GPL(ata_dev_classify);
-EXPORT_SYMBOL_GPL(ata_dev_pair);
-EXPORT_SYMBOL_GPL(ata_ratelimit);
-EXPORT_SYMBOL_GPL(ata_msleep);
-EXPORT_SYMBOL_GPL(ata_wait_register);
-EXPORT_SYMBOL_GPL(ata_scsi_queuecmd);
-EXPORT_SYMBOL_GPL(ata_scsi_slave_config);
-EXPORT_SYMBOL_GPL(ata_scsi_slave_destroy);
-EXPORT_SYMBOL_GPL(ata_scsi_change_queue_depth);
-EXPORT_SYMBOL_GPL(__ata_change_queue_depth);
-EXPORT_SYMBOL_GPL(sata_scr_valid);
-EXPORT_SYMBOL_GPL(sata_scr_read);
-EXPORT_SYMBOL_GPL(sata_scr_write);
-EXPORT_SYMBOL_GPL(sata_scr_write_flush);
-EXPORT_SYMBOL_GPL(ata_link_online);
-EXPORT_SYMBOL_GPL(ata_link_offline);
-#ifdef CONFIG_PM
-EXPORT_SYMBOL_GPL(ata_host_suspend);
-EXPORT_SYMBOL_GPL(ata_host_resume);
-#endif /* CONFIG_PM */
-EXPORT_SYMBOL_GPL(ata_id_string);
-EXPORT_SYMBOL_GPL(ata_id_c_string);
-EXPORT_SYMBOL_GPL(ata_do_dev_read_id);
-EXPORT_SYMBOL_GPL(ata_scsi_simulate);
-
-EXPORT_SYMBOL_GPL(ata_pio_need_iordy);
-EXPORT_SYMBOL_GPL(ata_timing_find_mode);
-EXPORT_SYMBOL_GPL(ata_timing_compute);
-EXPORT_SYMBOL_GPL(ata_timing_merge);
-EXPORT_SYMBOL_GPL(ata_timing_cycle2mode);
-
-#ifdef CONFIG_PCI
-EXPORT_SYMBOL_GPL(pci_test_config_bits);
-EXPORT_SYMBOL_GPL(ata_pci_shutdown_one);
-EXPORT_SYMBOL_GPL(ata_pci_remove_one);
-#ifdef CONFIG_PM
-EXPORT_SYMBOL_GPL(ata_pci_device_do_suspend);
-EXPORT_SYMBOL_GPL(ata_pci_device_do_resume);
-EXPORT_SYMBOL_GPL(ata_pci_device_suspend);
-EXPORT_SYMBOL_GPL(ata_pci_device_resume);
-#endif /* CONFIG_PM */
-#endif /* CONFIG_PCI */
-
-EXPORT_SYMBOL_GPL(ata_platform_remove_one);
-
-EXPORT_SYMBOL_GPL(__ata_ehi_push_desc);
-EXPORT_SYMBOL_GPL(ata_ehi_push_desc);
-EXPORT_SYMBOL_GPL(ata_ehi_clear_desc);
-EXPORT_SYMBOL_GPL(ata_port_desc);
-#ifdef CONFIG_PCI
-EXPORT_SYMBOL_GPL(ata_port_pbar_desc);
-#endif /* CONFIG_PCI */
-EXPORT_SYMBOL_GPL(ata_port_schedule_eh);
-EXPORT_SYMBOL_GPL(ata_link_abort);
-EXPORT_SYMBOL_GPL(ata_port_abort);
-EXPORT_SYMBOL_GPL(ata_port_freeze);
-EXPORT_SYMBOL_GPL(sata_async_notification);
-EXPORT_SYMBOL_GPL(ata_eh_freeze_port);
-EXPORT_SYMBOL_GPL(ata_eh_thaw_port);
-EXPORT_SYMBOL_GPL(ata_eh_qc_complete);
-EXPORT_SYMBOL_GPL(ata_eh_qc_retry);
-EXPORT_SYMBOL_GPL(ata_eh_analyze_ncq_error);
-EXPORT_SYMBOL_GPL(ata_do_eh);
-EXPORT_SYMBOL_GPL(ata_std_error_handler);
-
-EXPORT_SYMBOL_GPL(ata_cable_40wire);
-EXPORT_SYMBOL_GPL(ata_cable_80wire);
-EXPORT_SYMBOL_GPL(ata_cable_unknown);
-EXPORT_SYMBOL_GPL(ata_cable_ignore);
-EXPORT_SYMBOL_GPL(ata_cable_sata);
-EXPORT_SYMBOL_GPL(ata_host_get);
-EXPORT_SYMBOL_GPL(ata_host_put);
/*
* libata-eh.c - libata error handling
*
- * Maintained by: Tejun Heo <tj@kernel.org>
- * Please ALWAYS copy linux-ide@vger.kernel.org
- * on emails.
- *
* Copyright 2006 Tejun Heo <htejun@gmail.com>
*
* libata documentation is available via 'make {ps|pdf}docs',
__ata_ehi_pushv_desc(ehi, fmt, args);
va_end(args);
}
+EXPORT_SYMBOL_GPL(__ata_ehi_push_desc);
/**
* ata_ehi_push_desc - push error description with separator
__ata_ehi_pushv_desc(ehi, fmt, args);
va_end(args);
}
+EXPORT_SYMBOL_GPL(ata_ehi_push_desc);
/**
* ata_ehi_clear_desc - clean error description
ehi->desc[0] = '\0';
ehi->desc_len = 0;
}
+EXPORT_SYMBOL_GPL(ata_ehi_clear_desc);
/**
* ata_port_desc - append port description
__ata_ehi_pushv_desc(&ap->link.eh_info, fmt, args);
va_end(args);
}
+EXPORT_SYMBOL_GPL(ata_port_desc);
#ifdef CONFIG_PCI
-
/**
* ata_port_pbar_desc - append PCI BAR description
* @ap: target ATA port
ata_port_desc(ap, "%s 0x%llx", name,
start + (unsigned long long)offset);
}
-
+EXPORT_SYMBOL_GPL(ata_port_pbar_desc);
#endif /* CONFIG_PCI */
static int ata_lookup_timeout_table(u8 cmd)
/* see: ata_std_sched_eh, unless you know better */
ap->ops->sched_eh(ap);
}
+EXPORT_SYMBOL_GPL(ata_port_schedule_eh);
static int ata_do_link_abort(struct ata_port *ap, struct ata_link *link)
{
{
return ata_do_link_abort(link->ap, link);
}
+EXPORT_SYMBOL_GPL(ata_link_abort);
/**
* ata_port_abort - abort all qc's on the port
{
return ata_do_link_abort(ap, NULL);
}
+EXPORT_SYMBOL_GPL(ata_port_abort);
/**
* __ata_port_freeze - freeze port
return nr_aborted;
}
-
-/**
- * sata_async_notification - SATA async notification handler
- * @ap: ATA port where async notification is received
- *
- * Handler to be called when async notification via SDB FIS is
- * received. This function schedules EH if necessary.
- *
- * LOCKING:
- * spin_lock_irqsave(host lock)
- *
- * RETURNS:
- * 1 if EH is scheduled, 0 otherwise.
- */
-int sata_async_notification(struct ata_port *ap)
-{
- u32 sntf;
- int rc;
-
- if (!(ap->flags & ATA_FLAG_AN))
- return 0;
-
- rc = sata_scr_read(&ap->link, SCR_NOTIFICATION, &sntf);
- if (rc == 0)
- sata_scr_write(&ap->link, SCR_NOTIFICATION, sntf);
-
- if (!sata_pmp_attached(ap) || rc) {
- /* PMP is not attached or SNTF is not available */
- if (!sata_pmp_attached(ap)) {
- /* PMP is not attached. Check whether ATAPI
- * AN is configured. If so, notify media
- * change.
- */
- struct ata_device *dev = ap->link.device;
-
- if ((dev->class == ATA_DEV_ATAPI) &&
- (dev->flags & ATA_DFLAG_AN))
- ata_scsi_media_change_notify(dev);
- return 0;
- } else {
- /* PMP is attached but SNTF is not available.
- * ATAPI async media change notification is
- * not used. The PMP must be reporting PHY
- * status change, schedule EH.
- */
- ata_port_schedule_eh(ap);
- return 1;
- }
- } else {
- /* PMP is attached and SNTF is available */
- struct ata_link *link;
-
- /* check and notify ATAPI AN */
- ata_for_each_link(link, ap, EDGE) {
- if (!(sntf & (1 << link->pmp)))
- continue;
-
- if ((link->device->class == ATA_DEV_ATAPI) &&
- (link->device->flags & ATA_DFLAG_AN))
- ata_scsi_media_change_notify(link->device);
- }
-
- /* If PMP is reporting that PHY status of some
- * downstream ports has changed, schedule EH.
- */
- if (sntf & (1 << SATA_PMP_CTRL_PORT)) {
- ata_port_schedule_eh(ap);
- return 1;
- }
-
- return 0;
- }
-}
+EXPORT_SYMBOL_GPL(ata_port_freeze);
/**
* ata_eh_freeze_port - EH helper to freeze port
__ata_port_freeze(ap);
spin_unlock_irqrestore(ap->lock, flags);
}
+EXPORT_SYMBOL_GPL(ata_eh_freeze_port);
/**
* ata_port_thaw_port - EH helper to thaw port
*/
ata_ering_clear(&dev->ering);
}
+EXPORT_SYMBOL_GPL(ata_dev_disable);
/**
* ata_eh_detach_dev - detach ATA device
}
/**
- * ata_eh_read_log_10h - Read log page 10h for NCQ error details
- * @dev: Device to read log page 10h from
- * @tag: Resulting tag of the failed command
- * @tf: Resulting taskfile registers of the failed command
- *
- * Read log page 10h to obtain NCQ error details and clear error
- * condition.
- *
- * LOCKING:
- * Kernel thread context (may sleep).
- *
- * RETURNS:
- * 0 on success, -errno otherwise.
- */
-static int ata_eh_read_log_10h(struct ata_device *dev,
- int *tag, struct ata_taskfile *tf)
-{
- u8 *buf = dev->link->ap->sector_buf;
- unsigned int err_mask;
- u8 csum;
- int i;
-
- err_mask = ata_read_log_page(dev, ATA_LOG_SATA_NCQ, 0, buf, 1);
- if (err_mask)
- return -EIO;
-
- csum = 0;
- for (i = 0; i < ATA_SECT_SIZE; i++)
- csum += buf[i];
- if (csum)
- ata_dev_warn(dev, "invalid checksum 0x%x on log page 10h\n",
- csum);
-
- if (buf[0] & 0x80)
- return -ENOENT;
-
- *tag = buf[0] & 0x1f;
-
- tf->command = buf[2];
- tf->feature = buf[3];
- tf->lbal = buf[4];
- tf->lbam = buf[5];
- tf->lbah = buf[6];
- tf->device = buf[7];
- tf->hob_lbal = buf[8];
- tf->hob_lbam = buf[9];
- tf->hob_lbah = buf[10];
- tf->nsect = buf[12];
- tf->hob_nsect = buf[13];
- if (dev->class == ATA_DEV_ZAC && ata_id_has_ncq_autosense(dev->id))
- tf->auxiliary = buf[14] << 16 | buf[15] << 8 | buf[16];
-
- return 0;
-}
-
-/**
* atapi_eh_tur - perform ATAPI TEST_UNIT_READY
* @dev: target ATAPI device
* @r_sense_key: out parameter for sense_key
}
/**
- * ata_eh_analyze_ncq_error - analyze NCQ error
- * @link: ATA link to analyze NCQ error for
- *
- * Read log page 10h, determine the offending qc and acquire
- * error status TF. For NCQ device errors, all LLDDs have to do
- * is setting AC_ERR_DEV in ehi->err_mask. This function takes
- * care of the rest.
- *
- * LOCKING:
- * Kernel thread context (may sleep).
- */
-void ata_eh_analyze_ncq_error(struct ata_link *link)
-{
- struct ata_port *ap = link->ap;
- struct ata_eh_context *ehc = &link->eh_context;
- struct ata_device *dev = link->device;
- struct ata_queued_cmd *qc;
- struct ata_taskfile tf;
- int tag, rc;
-
- /* if frozen, we can't do much */
- if (ap->pflags & ATA_PFLAG_FROZEN)
- return;
-
- /* is it NCQ device error? */
- if (!link->sactive || !(ehc->i.err_mask & AC_ERR_DEV))
- return;
-
- /* has LLDD analyzed already? */
- ata_qc_for_each_raw(ap, qc, tag) {
- if (!(qc->flags & ATA_QCFLAG_FAILED))
- continue;
-
- if (qc->err_mask)
- return;
- }
-
- /* okay, this error is ours */
- memset(&tf, 0, sizeof(tf));
- rc = ata_eh_read_log_10h(dev, &tag, &tf);
- if (rc) {
- ata_link_err(link, "failed to read log page 10h (errno=%d)\n",
- rc);
- return;
- }
-
- if (!(link->sactive & (1 << tag))) {
- ata_link_err(link, "log page 10h reported inactive tag %d\n",
- tag);
- return;
- }
-
- /* we've got the perpetrator, condemn it */
- qc = __ata_qc_from_tag(ap, tag);
- memcpy(&qc->result_tf, &tf, sizeof(tf));
- qc->result_tf.flags = ATA_TFLAG_ISADDR | ATA_TFLAG_LBA | ATA_TFLAG_LBA48;
- qc->err_mask |= AC_ERR_DEV | AC_ERR_NCQ;
- if (dev->class == ATA_DEV_ZAC &&
- ((qc->result_tf.command & ATA_SENSE) || qc->result_tf.auxiliary)) {
- char sense_key, asc, ascq;
-
- sense_key = (qc->result_tf.auxiliary >> 16) & 0xff;
- asc = (qc->result_tf.auxiliary >> 8) & 0xff;
- ascq = qc->result_tf.auxiliary & 0xff;
- ata_scsi_set_sense(dev, qc->scsicmd, sense_key, asc, ascq);
- ata_scsi_set_sense_information(dev, qc->scsicmd,
- &qc->result_tf);
- qc->flags |= ATA_QCFLAG_SENSE_VALID;
- }
-
- ehc->i.err_mask &= ~AC_ERR_DEV;
-}
-
-/**
* ata_eh_analyze_tf - analyze taskfile of a failed qc
* @qc: qc to analyze
* @tf: Taskfile registers to analyze
int rc;
/* if the link or host doesn't do LPM, noop */
- if ((link->flags & ATA_LFLAG_NO_LPM) || (ap && !ap->ops->set_lpm))
+ if (!IS_ENABLED(CONFIG_SATA_HOST) ||
+ (link->flags & ATA_LFLAG_NO_LPM) || (ap && !ap->ops->set_lpm))
return 0;
/*
ata_do_eh(ap, ops->prereset, ops->softreset, hardreset, ops->postreset);
}
+EXPORT_SYMBOL_GPL(ata_std_error_handler);
#ifdef CONFIG_PM
/**
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Helper library for PATA timings
+ *
+ * Copyright 2003-2004 Red Hat, Inc. All rights reserved.
+ * Copyright 2003-2004 Jeff Garzik
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/libata.h>
+
+/*
+ * This mode timing computation functionality is ported over from
+ * drivers/ide/ide-timing.h and was originally written by Vojtech Pavlik
+ */
+/*
+ * PIO 0-4, MWDMA 0-2 and UDMA 0-6 timings (in nanoseconds).
+ * These were taken from ATA/ATAPI-6 standard, rev 0a, except
+ * for UDMA6, which is currently supported only by Maxtor drives.
+ *
+ * For PIO 5/6 MWDMA 3/4 see the CFA specification 3.0.
+ */
+
+static const struct ata_timing ata_timing[] = {
+/* { XFER_PIO_SLOW, 120, 290, 240, 960, 290, 240, 0, 960, 0 }, */
+ { XFER_PIO_0, 70, 290, 240, 600, 165, 150, 0, 600, 0 },
+ { XFER_PIO_1, 50, 290, 93, 383, 125, 100, 0, 383, 0 },
+ { XFER_PIO_2, 30, 290, 40, 330, 100, 90, 0, 240, 0 },
+ { XFER_PIO_3, 30, 80, 70, 180, 80, 70, 0, 180, 0 },
+ { XFER_PIO_4, 25, 70, 25, 120, 70, 25, 0, 120, 0 },
+ { XFER_PIO_5, 15, 65, 25, 100, 65, 25, 0, 100, 0 },
+ { XFER_PIO_6, 10, 55, 20, 80, 55, 20, 0, 80, 0 },
+
+ { XFER_SW_DMA_0, 120, 0, 0, 0, 480, 480, 50, 960, 0 },
+ { XFER_SW_DMA_1, 90, 0, 0, 0, 240, 240, 30, 480, 0 },
+ { XFER_SW_DMA_2, 60, 0, 0, 0, 120, 120, 20, 240, 0 },
+
+ { XFER_MW_DMA_0, 60, 0, 0, 0, 215, 215, 20, 480, 0 },
+ { XFER_MW_DMA_1, 45, 0, 0, 0, 80, 50, 5, 150, 0 },
+ { XFER_MW_DMA_2, 25, 0, 0, 0, 70, 25, 5, 120, 0 },
+ { XFER_MW_DMA_3, 25, 0, 0, 0, 65, 25, 5, 100, 0 },
+ { XFER_MW_DMA_4, 25, 0, 0, 0, 55, 20, 5, 80, 0 },
+
+/* { XFER_UDMA_SLOW, 0, 0, 0, 0, 0, 0, 0, 0, 150 }, */
+ { XFER_UDMA_0, 0, 0, 0, 0, 0, 0, 0, 0, 120 },
+ { XFER_UDMA_1, 0, 0, 0, 0, 0, 0, 0, 0, 80 },
+ { XFER_UDMA_2, 0, 0, 0, 0, 0, 0, 0, 0, 60 },
+ { XFER_UDMA_3, 0, 0, 0, 0, 0, 0, 0, 0, 45 },
+ { XFER_UDMA_4, 0, 0, 0, 0, 0, 0, 0, 0, 30 },
+ { XFER_UDMA_5, 0, 0, 0, 0, 0, 0, 0, 0, 20 },
+ { XFER_UDMA_6, 0, 0, 0, 0, 0, 0, 0, 0, 15 },
+
+ { 0xFF }
+};
+
+#define ENOUGH(v, unit) (((v)-1)/(unit)+1)
+#define EZ(v, unit) ((v)?ENOUGH(((v) * 1000), unit):0)
+
+static void ata_timing_quantize(const struct ata_timing *t,
+ struct ata_timing *q, int T, int UT)
+{
+ q->setup = EZ(t->setup, T);
+ q->act8b = EZ(t->act8b, T);
+ q->rec8b = EZ(t->rec8b, T);
+ q->cyc8b = EZ(t->cyc8b, T);
+ q->active = EZ(t->active, T);
+ q->recover = EZ(t->recover, T);
+ q->dmack_hold = EZ(t->dmack_hold, T);
+ q->cycle = EZ(t->cycle, T);
+ q->udma = EZ(t->udma, UT);
+}
+
+void ata_timing_merge(const struct ata_timing *a, const struct ata_timing *b,
+ struct ata_timing *m, unsigned int what)
+{
+ if (what & ATA_TIMING_SETUP)
+ m->setup = max(a->setup, b->setup);
+ if (what & ATA_TIMING_ACT8B)
+ m->act8b = max(a->act8b, b->act8b);
+ if (what & ATA_TIMING_REC8B)
+ m->rec8b = max(a->rec8b, b->rec8b);
+ if (what & ATA_TIMING_CYC8B)
+ m->cyc8b = max(a->cyc8b, b->cyc8b);
+ if (what & ATA_TIMING_ACTIVE)
+ m->active = max(a->active, b->active);
+ if (what & ATA_TIMING_RECOVER)
+ m->recover = max(a->recover, b->recover);
+ if (what & ATA_TIMING_DMACK_HOLD)
+ m->dmack_hold = max(a->dmack_hold, b->dmack_hold);
+ if (what & ATA_TIMING_CYCLE)
+ m->cycle = max(a->cycle, b->cycle);
+ if (what & ATA_TIMING_UDMA)
+ m->udma = max(a->udma, b->udma);
+}
+EXPORT_SYMBOL_GPL(ata_timing_merge);
+
+const struct ata_timing *ata_timing_find_mode(u8 xfer_mode)
+{
+ const struct ata_timing *t = ata_timing;
+
+ while (xfer_mode > t->mode)
+ t++;
+
+ if (xfer_mode == t->mode)
+ return t;
+
+ WARN_ONCE(true, "%s: unable to find timing for xfer_mode 0x%x\n",
+ __func__, xfer_mode);
+
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(ata_timing_find_mode);
+
+int ata_timing_compute(struct ata_device *adev, unsigned short speed,
+ struct ata_timing *t, int T, int UT)
+{
+ const u16 *id = adev->id;
+ const struct ata_timing *s;
+ struct ata_timing p;
+
+ /*
+ * Find the mode.
+ */
+ s = ata_timing_find_mode(speed);
+ if (!s)
+ return -EINVAL;
+
+ memcpy(t, s, sizeof(*s));
+
+ /*
+ * If the drive is an EIDE drive, it can tell us it needs extended
+ * PIO/MW_DMA cycle timing.
+ */
+
+ if (id[ATA_ID_FIELD_VALID] & 2) { /* EIDE drive */
+ memset(&p, 0, sizeof(p));
+
+ if (speed >= XFER_PIO_0 && speed < XFER_SW_DMA_0) {
+ if (speed <= XFER_PIO_2)
+ p.cycle = p.cyc8b = id[ATA_ID_EIDE_PIO];
+ else if ((speed <= XFER_PIO_4) ||
+ (speed == XFER_PIO_5 && !ata_id_is_cfa(id)))
+ p.cycle = p.cyc8b = id[ATA_ID_EIDE_PIO_IORDY];
+ } else if (speed >= XFER_MW_DMA_0 && speed <= XFER_MW_DMA_2)
+ p.cycle = id[ATA_ID_EIDE_DMA_MIN];
+
+ ata_timing_merge(&p, t, t, ATA_TIMING_CYCLE | ATA_TIMING_CYC8B);
+ }
+
+ /*
+ * Convert the timing to bus clock counts.
+ */
+
+ ata_timing_quantize(t, t, T, UT);
+
+ /*
+ * Even in DMA/UDMA modes we still use PIO access for IDENTIFY,
+ * S.M.A.R.T * and some other commands. We have to ensure that the
+ * DMA cycle timing is slower/equal than the fastest PIO timing.
+ */
+
+ if (speed > XFER_PIO_6) {
+ ata_timing_compute(adev, adev->pio_mode, &p, T, UT);
+ ata_timing_merge(&p, t, t, ATA_TIMING_ALL);
+ }
+
+ /*
+ * Lengthen active & recovery time so that cycle time is correct.
+ */
+
+ if (t->act8b + t->rec8b < t->cyc8b) {
+ t->act8b += (t->cyc8b - (t->act8b + t->rec8b)) / 2;
+ t->rec8b = t->cyc8b - t->act8b;
+ }
+
+ if (t->active + t->recover < t->cycle) {
+ t->active += (t->cycle - (t->active + t->recover)) / 2;
+ t->recover = t->cycle - t->active;
+ }
+
+ /*
+ * In a few cases quantisation may produce enough errors to
+ * leave t->cycle too low for the sum of active and recovery
+ * if so we must correct this.
+ */
+ if (t->active + t->recover > t->cycle)
+ t->cycle = t->active + t->recover;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ata_timing_compute);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * SATA specific part of ATA helper library
+ *
+ * Copyright 2003-2004 Red Hat, Inc. All rights reserved.
+ * Copyright 2003-2004 Jeff Garzik
+ * Copyright 2006 Tejun Heo <htejun@gmail.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_device.h>
+#include <linux/libata.h>
+
+#include "libata.h"
+#include "libata-transport.h"
+
+/* debounce timing parameters in msecs { interval, duration, timeout } */
+const unsigned long sata_deb_timing_normal[] = { 5, 100, 2000 };
+EXPORT_SYMBOL_GPL(sata_deb_timing_normal);
+const unsigned long sata_deb_timing_hotplug[] = { 25, 500, 2000 };
+EXPORT_SYMBOL_GPL(sata_deb_timing_hotplug);
+const unsigned long sata_deb_timing_long[] = { 100, 2000, 5000 };
+EXPORT_SYMBOL_GPL(sata_deb_timing_long);
+
+/**
+ * sata_scr_valid - test whether SCRs are accessible
+ * @link: ATA link to test SCR accessibility for
+ *
+ * Test whether SCRs are accessible for @link.
+ *
+ * LOCKING:
+ * None.
+ *
+ * RETURNS:
+ * 1 if SCRs are accessible, 0 otherwise.
+ */
+int sata_scr_valid(struct ata_link *link)
+{
+ struct ata_port *ap = link->ap;
+
+ return (ap->flags & ATA_FLAG_SATA) && ap->ops->scr_read;
+}
+EXPORT_SYMBOL_GPL(sata_scr_valid);
+
+/**
+ * sata_scr_read - read SCR register of the specified port
+ * @link: ATA link to read SCR for
+ * @reg: SCR to read
+ * @val: Place to store read value
+ *
+ * Read SCR register @reg of @link into *@val. This function is
+ * guaranteed to succeed if @link is ap->link, the cable type of
+ * the port is SATA and the port implements ->scr_read.
+ *
+ * LOCKING:
+ * None if @link is ap->link. Kernel thread context otherwise.
+ *
+ * RETURNS:
+ * 0 on success, negative errno on failure.
+ */
+int sata_scr_read(struct ata_link *link, int reg, u32 *val)
+{
+ if (ata_is_host_link(link)) {
+ if (sata_scr_valid(link))
+ return link->ap->ops->scr_read(link, reg, val);
+ return -EOPNOTSUPP;
+ }
+
+ return sata_pmp_scr_read(link, reg, val);
+}
+EXPORT_SYMBOL_GPL(sata_scr_read);
+
+/**
+ * sata_scr_write - write SCR register of the specified port
+ * @link: ATA link to write SCR for
+ * @reg: SCR to write
+ * @val: value to write
+ *
+ * Write @val to SCR register @reg of @link. This function is
+ * guaranteed to succeed if @link is ap->link, the cable type of
+ * the port is SATA and the port implements ->scr_read.
+ *
+ * LOCKING:
+ * None if @link is ap->link. Kernel thread context otherwise.
+ *
+ * RETURNS:
+ * 0 on success, negative errno on failure.
+ */
+int sata_scr_write(struct ata_link *link, int reg, u32 val)
+{
+ if (ata_is_host_link(link)) {
+ if (sata_scr_valid(link))
+ return link->ap->ops->scr_write(link, reg, val);
+ return -EOPNOTSUPP;
+ }
+
+ return sata_pmp_scr_write(link, reg, val);
+}
+EXPORT_SYMBOL_GPL(sata_scr_write);
+
+/**
+ * sata_scr_write_flush - write SCR register of the specified port and flush
+ * @link: ATA link to write SCR for
+ * @reg: SCR to write
+ * @val: value to write
+ *
+ * This function is identical to sata_scr_write() except that this
+ * function performs flush after writing to the register.
+ *
+ * LOCKING:
+ * None if @link is ap->link. Kernel thread context otherwise.
+ *
+ * RETURNS:
+ * 0 on success, negative errno on failure.
+ */
+int sata_scr_write_flush(struct ata_link *link, int reg, u32 val)
+{
+ if (ata_is_host_link(link)) {
+ int rc;
+
+ if (sata_scr_valid(link)) {
+ rc = link->ap->ops->scr_write(link, reg, val);
+ if (rc == 0)
+ rc = link->ap->ops->scr_read(link, reg, &val);
+ return rc;
+ }
+ return -EOPNOTSUPP;
+ }
+
+ return sata_pmp_scr_write(link, reg, val);
+}
+EXPORT_SYMBOL_GPL(sata_scr_write_flush);
+
+/**
+ * ata_tf_to_fis - Convert ATA taskfile to SATA FIS structure
+ * @tf: Taskfile to convert
+ * @pmp: Port multiplier port
+ * @is_cmd: This FIS is for command
+ * @fis: Buffer into which data will output
+ *
+ * Converts a standard ATA taskfile to a Serial ATA
+ * FIS structure (Register - Host to Device).
+ *
+ * LOCKING:
+ * Inherited from caller.
+ */
+void ata_tf_to_fis(const struct ata_taskfile *tf, u8 pmp, int is_cmd, u8 *fis)
+{
+ fis[0] = 0x27; /* Register - Host to Device FIS */
+ fis[1] = pmp & 0xf; /* Port multiplier number*/
+ if (is_cmd)
+ fis[1] |= (1 << 7); /* bit 7 indicates Command FIS */
+
+ fis[2] = tf->command;
+ fis[3] = tf->feature;
+
+ fis[4] = tf->lbal;
+ fis[5] = tf->lbam;
+ fis[6] = tf->lbah;
+ fis[7] = tf->device;
+
+ fis[8] = tf->hob_lbal;
+ fis[9] = tf->hob_lbam;
+ fis[10] = tf->hob_lbah;
+ fis[11] = tf->hob_feature;
+
+ fis[12] = tf->nsect;
+ fis[13] = tf->hob_nsect;
+ fis[14] = 0;
+ fis[15] = tf->ctl;
+
+ fis[16] = tf->auxiliary & 0xff;
+ fis[17] = (tf->auxiliary >> 8) & 0xff;
+ fis[18] = (tf->auxiliary >> 16) & 0xff;
+ fis[19] = (tf->auxiliary >> 24) & 0xff;
+}
+EXPORT_SYMBOL_GPL(ata_tf_to_fis);
+
+/**
+ * ata_tf_from_fis - Convert SATA FIS to ATA taskfile
+ * @fis: Buffer from which data will be input
+ * @tf: Taskfile to output
+ *
+ * Converts a serial ATA FIS structure to a standard ATA taskfile.
+ *
+ * LOCKING:
+ * Inherited from caller.
+ */
+
+void ata_tf_from_fis(const u8 *fis, struct ata_taskfile *tf)
+{
+ tf->command = fis[2]; /* status */
+ tf->feature = fis[3]; /* error */
+
+ tf->lbal = fis[4];
+ tf->lbam = fis[5];
+ tf->lbah = fis[6];
+ tf->device = fis[7];
+
+ tf->hob_lbal = fis[8];
+ tf->hob_lbam = fis[9];
+ tf->hob_lbah = fis[10];
+
+ tf->nsect = fis[12];
+ tf->hob_nsect = fis[13];
+}
+EXPORT_SYMBOL_GPL(ata_tf_from_fis);
+
+/**
+ * sata_link_debounce - debounce SATA phy status
+ * @link: ATA link to debounce SATA phy status for
+ * @params: timing parameters { interval, duration, timeout } in msec
+ * @deadline: deadline jiffies for the operation
+ *
+ * Make sure SStatus of @link reaches stable state, determined by
+ * holding the same value where DET is not 1 for @duration polled
+ * every @interval, before @timeout. Timeout constraints the
+ * beginning of the stable state. Because DET gets stuck at 1 on
+ * some controllers after hot unplugging, this functions waits
+ * until timeout then returns 0 if DET is stable at 1.
+ *
+ * @timeout is further limited by @deadline. The sooner of the
+ * two is used.
+ *
+ * LOCKING:
+ * Kernel thread context (may sleep)
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+int sata_link_debounce(struct ata_link *link, const unsigned long *params,
+ unsigned long deadline)
+{
+ unsigned long interval = params[0];
+ unsigned long duration = params[1];
+ unsigned long last_jiffies, t;
+ u32 last, cur;
+ int rc;
+
+ t = ata_deadline(jiffies, params[2]);
+ if (time_before(t, deadline))
+ deadline = t;
+
+ if ((rc = sata_scr_read(link, SCR_STATUS, &cur)))
+ return rc;
+ cur &= 0xf;
+
+ last = cur;
+ last_jiffies = jiffies;
+
+ while (1) {
+ ata_msleep(link->ap, interval);
+ if ((rc = sata_scr_read(link, SCR_STATUS, &cur)))
+ return rc;
+ cur &= 0xf;
+
+ /* DET stable? */
+ if (cur == last) {
+ if (cur == 1 && time_before(jiffies, deadline))
+ continue;
+ if (time_after(jiffies,
+ ata_deadline(last_jiffies, duration)))
+ return 0;
+ continue;
+ }
+
+ /* unstable, start over */
+ last = cur;
+ last_jiffies = jiffies;
+
+ /* Check deadline. If debouncing failed, return
+ * -EPIPE to tell upper layer to lower link speed.
+ */
+ if (time_after(jiffies, deadline))
+ return -EPIPE;
+ }
+}
+EXPORT_SYMBOL_GPL(sata_link_debounce);
+
+/**
+ * sata_link_resume - resume SATA link
+ * @link: ATA link to resume SATA
+ * @params: timing parameters { interval, duration, timeout } in msec
+ * @deadline: deadline jiffies for the operation
+ *
+ * Resume SATA phy @link and debounce it.
+ *
+ * LOCKING:
+ * Kernel thread context (may sleep)
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+int sata_link_resume(struct ata_link *link, const unsigned long *params,
+ unsigned long deadline)
+{
+ int tries = ATA_LINK_RESUME_TRIES;
+ u32 scontrol, serror;
+ int rc;
+
+ if ((rc = sata_scr_read(link, SCR_CONTROL, &scontrol)))
+ return rc;
+
+ /*
+ * Writes to SControl sometimes get ignored under certain
+ * controllers (ata_piix SIDPR). Make sure DET actually is
+ * cleared.
+ */
+ do {
+ scontrol = (scontrol & 0x0f0) | 0x300;
+ if ((rc = sata_scr_write(link, SCR_CONTROL, scontrol)))
+ return rc;
+ /*
+ * Some PHYs react badly if SStatus is pounded
+ * immediately after resuming. Delay 200ms before
+ * debouncing.
+ */
+ if (!(link->flags & ATA_LFLAG_NO_DB_DELAY))
+ ata_msleep(link->ap, 200);
+
+ /* is SControl restored correctly? */
+ if ((rc = sata_scr_read(link, SCR_CONTROL, &scontrol)))
+ return rc;
+ } while ((scontrol & 0xf0f) != 0x300 && --tries);
+
+ if ((scontrol & 0xf0f) != 0x300) {
+ ata_link_warn(link, "failed to resume link (SControl %X)\n",
+ scontrol);
+ return 0;
+ }
+
+ if (tries < ATA_LINK_RESUME_TRIES)
+ ata_link_warn(link, "link resume succeeded after %d retries\n",
+ ATA_LINK_RESUME_TRIES - tries);
+
+ if ((rc = sata_link_debounce(link, params, deadline)))
+ return rc;
+
+ /* clear SError, some PHYs require this even for SRST to work */
+ if (!(rc = sata_scr_read(link, SCR_ERROR, &serror)))
+ rc = sata_scr_write(link, SCR_ERROR, serror);
+
+ return rc != -EINVAL ? rc : 0;
+}
+EXPORT_SYMBOL_GPL(sata_link_resume);
+
+/**
+ * sata_link_scr_lpm - manipulate SControl IPM and SPM fields
+ * @link: ATA link to manipulate SControl for
+ * @policy: LPM policy to configure
+ * @spm_wakeup: initiate LPM transition to active state
+ *
+ * Manipulate the IPM field of the SControl register of @link
+ * according to @policy. If @policy is ATA_LPM_MAX_POWER and
+ * @spm_wakeup is %true, the SPM field is manipulated to wake up
+ * the link. This function also clears PHYRDY_CHG before
+ * returning.
+ *
+ * LOCKING:
+ * EH context.
+ *
+ * RETURNS:
+ * 0 on success, -errno otherwise.
+ */
+int sata_link_scr_lpm(struct ata_link *link, enum ata_lpm_policy policy,
+ bool spm_wakeup)
+{
+ struct ata_eh_context *ehc = &link->eh_context;
+ bool woken_up = false;
+ u32 scontrol;
+ int rc;
+
+ rc = sata_scr_read(link, SCR_CONTROL, &scontrol);
+ if (rc)
+ return rc;
+
+ switch (policy) {
+ case ATA_LPM_MAX_POWER:
+ /* disable all LPM transitions */
+ scontrol |= (0x7 << 8);
+ /* initiate transition to active state */
+ if (spm_wakeup) {
+ scontrol |= (0x4 << 12);
+ woken_up = true;
+ }
+ break;
+ case ATA_LPM_MED_POWER:
+ /* allow LPM to PARTIAL */
+ scontrol &= ~(0x1 << 8);
+ scontrol |= (0x6 << 8);
+ break;
+ case ATA_LPM_MED_POWER_WITH_DIPM:
+ case ATA_LPM_MIN_POWER_WITH_PARTIAL:
+ case ATA_LPM_MIN_POWER:
+ if (ata_link_nr_enabled(link) > 0)
+ /* no restrictions on LPM transitions */
+ scontrol &= ~(0x7 << 8);
+ else {
+ /* empty port, power off */
+ scontrol &= ~0xf;
+ scontrol |= (0x1 << 2);
+ }
+ break;
+ default:
+ WARN_ON(1);
+ }
+
+ rc = sata_scr_write(link, SCR_CONTROL, scontrol);
+ if (rc)
+ return rc;
+
+ /* give the link time to transit out of LPM state */
+ if (woken_up)
+ msleep(10);
+
+ /* clear PHYRDY_CHG from SError */
+ ehc->i.serror &= ~SERR_PHYRDY_CHG;
+ return sata_scr_write(link, SCR_ERROR, SERR_PHYRDY_CHG);
+}
+EXPORT_SYMBOL_GPL(sata_link_scr_lpm);
+
+static int __sata_set_spd_needed(struct ata_link *link, u32 *scontrol)
+{
+ struct ata_link *host_link = &link->ap->link;
+ u32 limit, target, spd;
+
+ limit = link->sata_spd_limit;
+
+ /* Don't configure downstream link faster than upstream link.
+ * It doesn't speed up anything and some PMPs choke on such
+ * configuration.
+ */
+ if (!ata_is_host_link(link) && host_link->sata_spd)
+ limit &= (1 << host_link->sata_spd) - 1;
+
+ if (limit == UINT_MAX)
+ target = 0;
+ else
+ target = fls(limit);
+
+ spd = (*scontrol >> 4) & 0xf;
+ *scontrol = (*scontrol & ~0xf0) | ((target & 0xf) << 4);
+
+ return spd != target;
+}
+
+/**
+ * sata_set_spd_needed - is SATA spd configuration needed
+ * @link: Link in question
+ *
+ * Test whether the spd limit in SControl matches
+ * @link->sata_spd_limit. This function is used to determine
+ * whether hardreset is necessary to apply SATA spd
+ * configuration.
+ *
+ * LOCKING:
+ * Inherited from caller.
+ *
+ * RETURNS:
+ * 1 if SATA spd configuration is needed, 0 otherwise.
+ */
+static int sata_set_spd_needed(struct ata_link *link)
+{
+ u32 scontrol;
+
+ if (sata_scr_read(link, SCR_CONTROL, &scontrol))
+ return 1;
+
+ return __sata_set_spd_needed(link, &scontrol);
+}
+
+/**
+ * sata_set_spd - set SATA spd according to spd limit
+ * @link: Link to set SATA spd for
+ *
+ * Set SATA spd of @link according to sata_spd_limit.
+ *
+ * LOCKING:
+ * Inherited from caller.
+ *
+ * RETURNS:
+ * 0 if spd doesn't need to be changed, 1 if spd has been
+ * changed. Negative errno if SCR registers are inaccessible.
+ */
+int sata_set_spd(struct ata_link *link)
+{
+ u32 scontrol;
+ int rc;
+
+ if ((rc = sata_scr_read(link, SCR_CONTROL, &scontrol)))
+ return rc;
+
+ if (!__sata_set_spd_needed(link, &scontrol))
+ return 0;
+
+ if ((rc = sata_scr_write(link, SCR_CONTROL, scontrol)))
+ return rc;
+
+ return 1;
+}
+EXPORT_SYMBOL_GPL(sata_set_spd);
+
+/**
+ * sata_link_hardreset - reset link via SATA phy reset
+ * @link: link to reset
+ * @timing: timing parameters { interval, duration, timeout } in msec
+ * @deadline: deadline jiffies for the operation
+ * @online: optional out parameter indicating link onlineness
+ * @check_ready: optional callback to check link readiness
+ *
+ * SATA phy-reset @link using DET bits of SControl register.
+ * After hardreset, link readiness is waited upon using
+ * ata_wait_ready() if @check_ready is specified. LLDs are
+ * allowed to not specify @check_ready and wait itself after this
+ * function returns. Device classification is LLD's
+ * responsibility.
+ *
+ * *@online is set to one iff reset succeeded and @link is online
+ * after reset.
+ *
+ * LOCKING:
+ * Kernel thread context (may sleep)
+ *
+ * RETURNS:
+ * 0 on success, -errno otherwise.
+ */
+int sata_link_hardreset(struct ata_link *link, const unsigned long *timing,
+ unsigned long deadline,
+ bool *online, int (*check_ready)(struct ata_link *))
+{
+ u32 scontrol;
+ int rc;
+
+ DPRINTK("ENTER\n");
+
+ if (online)
+ *online = false;
+
+ if (sata_set_spd_needed(link)) {
+ /* SATA spec says nothing about how to reconfigure
+ * spd. To be on the safe side, turn off phy during
+ * reconfiguration. This works for at least ICH7 AHCI
+ * and Sil3124.
+ */
+ if ((rc = sata_scr_read(link, SCR_CONTROL, &scontrol)))
+ goto out;
+
+ scontrol = (scontrol & 0x0f0) | 0x304;
+
+ if ((rc = sata_scr_write(link, SCR_CONTROL, scontrol)))
+ goto out;
+
+ sata_set_spd(link);
+ }
+
+ /* issue phy wake/reset */
+ if ((rc = sata_scr_read(link, SCR_CONTROL, &scontrol)))
+ goto out;
+
+ scontrol = (scontrol & 0x0f0) | 0x301;
+
+ if ((rc = sata_scr_write_flush(link, SCR_CONTROL, scontrol)))
+ goto out;
+
+ /* Couldn't find anything in SATA I/II specs, but AHCI-1.1
+ * 10.4.2 says at least 1 ms.
+ */
+ ata_msleep(link->ap, 1);
+
+ /* bring link back */
+ rc = sata_link_resume(link, timing, deadline);
+ if (rc)
+ goto out;
+ /* if link is offline nothing more to do */
+ if (ata_phys_link_offline(link))
+ goto out;
+
+ /* Link is online. From this point, -ENODEV too is an error. */
+ if (online)
+ *online = true;
+
+ if (sata_pmp_supported(link->ap) && ata_is_host_link(link)) {
+ /* If PMP is supported, we have to do follow-up SRST.
+ * Some PMPs don't send D2H Reg FIS after hardreset if
+ * the first port is empty. Wait only for
+ * ATA_TMOUT_PMP_SRST_WAIT.
+ */
+ if (check_ready) {
+ unsigned long pmp_deadline;
+
+ pmp_deadline = ata_deadline(jiffies,
+ ATA_TMOUT_PMP_SRST_WAIT);
+ if (time_after(pmp_deadline, deadline))
+ pmp_deadline = deadline;
+ ata_wait_ready(link, pmp_deadline, check_ready);
+ }
+ rc = -EAGAIN;
+ goto out;
+ }
+
+ rc = 0;
+ if (check_ready)
+ rc = ata_wait_ready(link, deadline, check_ready);
+ out:
+ if (rc && rc != -EAGAIN) {
+ /* online is set iff link is online && reset succeeded */
+ if (online)
+ *online = false;
+ ata_link_err(link, "COMRESET failed (errno=%d)\n", rc);
+ }
+ DPRINTK("EXIT, rc=%d\n", rc);
+ return rc;
+}
+EXPORT_SYMBOL_GPL(sata_link_hardreset);
+
+/**
+ * ata_qc_complete_multiple - Complete multiple qcs successfully
+ * @ap: port in question
+ * @qc_active: new qc_active mask
+ *
+ * Complete in-flight commands. This functions is meant to be
+ * called from low-level driver's interrupt routine to complete
+ * requests normally. ap->qc_active and @qc_active is compared
+ * and commands are completed accordingly.
+ *
+ * Always use this function when completing multiple NCQ commands
+ * from IRQ handlers instead of calling ata_qc_complete()
+ * multiple times to keep IRQ expect status properly in sync.
+ *
+ * LOCKING:
+ * spin_lock_irqsave(host lock)
+ *
+ * RETURNS:
+ * Number of completed commands on success, -errno otherwise.
+ */
+int ata_qc_complete_multiple(struct ata_port *ap, u64 qc_active)
+{
+ u64 done_mask, ap_qc_active = ap->qc_active;
+ int nr_done = 0;
+
+ /*
+ * If the internal tag is set on ap->qc_active, then we care about
+ * bit0 on the passed in qc_active mask. Move that bit up to match
+ * the internal tag.
+ */
+ if (ap_qc_active & (1ULL << ATA_TAG_INTERNAL)) {
+ qc_active |= (qc_active & 0x01) << ATA_TAG_INTERNAL;
+ qc_active ^= qc_active & 0x01;
+ }
+
+ done_mask = ap_qc_active ^ qc_active;
+
+ if (unlikely(done_mask & qc_active)) {
+ ata_port_err(ap, "illegal qc_active transition (%08llx->%08llx)\n",
+ ap->qc_active, qc_active);
+ return -EINVAL;
+ }
+
+ while (done_mask) {
+ struct ata_queued_cmd *qc;
+ unsigned int tag = __ffs64(done_mask);
+
+ qc = ata_qc_from_tag(ap, tag);
+ if (qc) {
+ ata_qc_complete(qc);
+ nr_done++;
+ }
+ done_mask &= ~(1ULL << tag);
+ }
+
+ return nr_done;
+}
+EXPORT_SYMBOL_GPL(ata_qc_complete_multiple);
+
+/**
+ * ata_slave_link_init - initialize slave link
+ * @ap: port to initialize slave link for
+ *
+ * Create and initialize slave link for @ap. This enables slave
+ * link handling on the port.
+ *
+ * In libata, a port contains links and a link contains devices.
+ * There is single host link but if a PMP is attached to it,
+ * there can be multiple fan-out links. On SATA, there's usually
+ * a single device connected to a link but PATA and SATA
+ * controllers emulating TF based interface can have two - master
+ * and slave.
+ *
+ * However, there are a few controllers which don't fit into this
+ * abstraction too well - SATA controllers which emulate TF
+ * interface with both master and slave devices but also have
+ * separate SCR register sets for each device. These controllers
+ * need separate links for physical link handling
+ * (e.g. onlineness, link speed) but should be treated like a
+ * traditional M/S controller for everything else (e.g. command
+ * issue, softreset).
+ *
+ * slave_link is libata's way of handling this class of
+ * controllers without impacting core layer too much. For
+ * anything other than physical link handling, the default host
+ * link is used for both master and slave. For physical link
+ * handling, separate @ap->slave_link is used. All dirty details
+ * are implemented inside libata core layer. From LLD's POV, the
+ * only difference is that prereset, hardreset and postreset are
+ * called once more for the slave link, so the reset sequence
+ * looks like the following.
+ *
+ * prereset(M) -> prereset(S) -> hardreset(M) -> hardreset(S) ->
+ * softreset(M) -> postreset(M) -> postreset(S)
+ *
+ * Note that softreset is called only for the master. Softreset
+ * resets both M/S by definition, so SRST on master should handle
+ * both (the standard method will work just fine).
+ *
+ * LOCKING:
+ * Should be called before host is registered.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+int ata_slave_link_init(struct ata_port *ap)
+{
+ struct ata_link *link;
+
+ WARN_ON(ap->slave_link);
+ WARN_ON(ap->flags & ATA_FLAG_PMP);
+
+ link = kzalloc(sizeof(*link), GFP_KERNEL);
+ if (!link)
+ return -ENOMEM;
+
+ ata_link_init(ap, link, 1);
+ ap->slave_link = link;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ata_slave_link_init);
+
+/**
+ * sata_lpm_ignore_phy_events - test if PHY event should be ignored
+ * @link: Link receiving the event
+ *
+ * Test whether the received PHY event has to be ignored or not.
+ *
+ * LOCKING:
+ * None:
+ *
+ * RETURNS:
+ * True if the event has to be ignored.
+ */
+bool sata_lpm_ignore_phy_events(struct ata_link *link)
+{
+ unsigned long lpm_timeout = link->last_lpm_change +
+ msecs_to_jiffies(ATA_TMOUT_SPURIOUS_PHY);
+
+ /* if LPM is enabled, PHYRDY doesn't mean anything */
+ if (link->lpm_policy > ATA_LPM_MAX_POWER)
+ return true;
+
+ /* ignore the first PHY event after the LPM policy changed
+ * as it is might be spurious
+ */
+ if ((link->flags & ATA_LFLAG_CHANGED) &&
+ time_before(jiffies, lpm_timeout))
+ return true;
+
+ return false;
+}
+EXPORT_SYMBOL_GPL(sata_lpm_ignore_phy_events);
+
+static const char *ata_lpm_policy_names[] = {
+ [ATA_LPM_UNKNOWN] = "max_performance",
+ [ATA_LPM_MAX_POWER] = "max_performance",
+ [ATA_LPM_MED_POWER] = "medium_power",
+ [ATA_LPM_MED_POWER_WITH_DIPM] = "med_power_with_dipm",
+ [ATA_LPM_MIN_POWER_WITH_PARTIAL] = "min_power_with_partial",
+ [ATA_LPM_MIN_POWER] = "min_power",
+};
+
+static ssize_t ata_scsi_lpm_store(struct device *device,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct Scsi_Host *shost = class_to_shost(device);
+ struct ata_port *ap = ata_shost_to_port(shost);
+ struct ata_link *link;
+ struct ata_device *dev;
+ enum ata_lpm_policy policy;
+ unsigned long flags;
+
+ /* UNKNOWN is internal state, iterate from MAX_POWER */
+ for (policy = ATA_LPM_MAX_POWER;
+ policy < ARRAY_SIZE(ata_lpm_policy_names); policy++) {
+ const char *name = ata_lpm_policy_names[policy];
+
+ if (strncmp(name, buf, strlen(name)) == 0)
+ break;
+ }
+ if (policy == ARRAY_SIZE(ata_lpm_policy_names))
+ return -EINVAL;
+
+ spin_lock_irqsave(ap->lock, flags);
+
+ ata_for_each_link(link, ap, EDGE) {
+ ata_for_each_dev(dev, &ap->link, ENABLED) {
+ if (dev->horkage & ATA_HORKAGE_NOLPM) {
+ count = -EOPNOTSUPP;
+ goto out_unlock;
+ }
+ }
+ }
+
+ ap->target_lpm_policy = policy;
+ ata_port_schedule_eh(ap);
+out_unlock:
+ spin_unlock_irqrestore(ap->lock, flags);
+ return count;
+}
+
+static ssize_t ata_scsi_lpm_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct Scsi_Host *shost = class_to_shost(dev);
+ struct ata_port *ap = ata_shost_to_port(shost);
+
+ if (ap->target_lpm_policy >= ARRAY_SIZE(ata_lpm_policy_names))
+ return -EINVAL;
+
+ return snprintf(buf, PAGE_SIZE, "%s\n",
+ ata_lpm_policy_names[ap->target_lpm_policy]);
+}
+DEVICE_ATTR(link_power_management_policy, S_IRUGO | S_IWUSR,
+ ata_scsi_lpm_show, ata_scsi_lpm_store);
+EXPORT_SYMBOL_GPL(dev_attr_link_power_management_policy);
+
+static ssize_t ata_ncq_prio_enable_show(struct device *device,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct scsi_device *sdev = to_scsi_device(device);
+ struct ata_port *ap;
+ struct ata_device *dev;
+ bool ncq_prio_enable;
+ int rc = 0;
+
+ ap = ata_shost_to_port(sdev->host);
+
+ spin_lock_irq(ap->lock);
+ dev = ata_scsi_find_dev(ap, sdev);
+ if (!dev) {
+ rc = -ENODEV;
+ goto unlock;
+ }
+
+ ncq_prio_enable = dev->flags & ATA_DFLAG_NCQ_PRIO_ENABLE;
+
+unlock:
+ spin_unlock_irq(ap->lock);
+
+ return rc ? rc : snprintf(buf, 20, "%u\n", ncq_prio_enable);
+}
+
+static ssize_t ata_ncq_prio_enable_store(struct device *device,
+ struct device_attribute *attr,
+ const char *buf, size_t len)
+{
+ struct scsi_device *sdev = to_scsi_device(device);
+ struct ata_port *ap;
+ struct ata_device *dev;
+ long int input;
+ int rc;
+
+ rc = kstrtol(buf, 10, &input);
+ if (rc)
+ return rc;
+ if ((input < 0) || (input > 1))
+ return -EINVAL;
+
+ ap = ata_shost_to_port(sdev->host);
+ dev = ata_scsi_find_dev(ap, sdev);
+ if (unlikely(!dev))
+ return -ENODEV;
+
+ spin_lock_irq(ap->lock);
+ if (input)
+ dev->flags |= ATA_DFLAG_NCQ_PRIO_ENABLE;
+ else
+ dev->flags &= ~ATA_DFLAG_NCQ_PRIO_ENABLE;
+
+ dev->link->eh_info.action |= ATA_EH_REVALIDATE;
+ dev->link->eh_info.flags |= ATA_EHI_QUIET;
+ ata_port_schedule_eh(ap);
+ spin_unlock_irq(ap->lock);
+
+ ata_port_wait_eh(ap);
+
+ if (input) {
+ spin_lock_irq(ap->lock);
+ if (!(dev->flags & ATA_DFLAG_NCQ_PRIO)) {
+ dev->flags &= ~ATA_DFLAG_NCQ_PRIO_ENABLE;
+ rc = -EIO;
+ }
+ spin_unlock_irq(ap->lock);
+ }
+
+ return rc ? rc : len;
+}
+
+DEVICE_ATTR(ncq_prio_enable, S_IRUGO | S_IWUSR,
+ ata_ncq_prio_enable_show, ata_ncq_prio_enable_store);
+EXPORT_SYMBOL_GPL(dev_attr_ncq_prio_enable);
+
+struct device_attribute *ata_ncq_sdev_attrs[] = {
+ &dev_attr_unload_heads,
+ &dev_attr_ncq_prio_enable,
+ NULL
+};
+EXPORT_SYMBOL_GPL(ata_ncq_sdev_attrs);
+
+static ssize_t
+ata_scsi_em_message_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct Scsi_Host *shost = class_to_shost(dev);
+ struct ata_port *ap = ata_shost_to_port(shost);
+ if (ap->ops->em_store && (ap->flags & ATA_FLAG_EM))
+ return ap->ops->em_store(ap, buf, count);
+ return -EINVAL;
+}
+
+static ssize_t
+ata_scsi_em_message_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct Scsi_Host *shost = class_to_shost(dev);
+ struct ata_port *ap = ata_shost_to_port(shost);
+
+ if (ap->ops->em_show && (ap->flags & ATA_FLAG_EM))
+ return ap->ops->em_show(ap, buf);
+ return -EINVAL;
+}
+DEVICE_ATTR(em_message, S_IRUGO | S_IWUSR,
+ ata_scsi_em_message_show, ata_scsi_em_message_store);
+EXPORT_SYMBOL_GPL(dev_attr_em_message);
+
+static ssize_t
+ata_scsi_em_message_type_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct Scsi_Host *shost = class_to_shost(dev);
+ struct ata_port *ap = ata_shost_to_port(shost);
+
+ return snprintf(buf, 23, "%d\n", ap->em_message_type);
+}
+DEVICE_ATTR(em_message_type, S_IRUGO,
+ ata_scsi_em_message_type_show, NULL);
+EXPORT_SYMBOL_GPL(dev_attr_em_message_type);
+
+static ssize_t
+ata_scsi_activity_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct scsi_device *sdev = to_scsi_device(dev);
+ struct ata_port *ap = ata_shost_to_port(sdev->host);
+ struct ata_device *atadev = ata_scsi_find_dev(ap, sdev);
+
+ if (atadev && ap->ops->sw_activity_show &&
+ (ap->flags & ATA_FLAG_SW_ACTIVITY))
+ return ap->ops->sw_activity_show(atadev, buf);
+ return -EINVAL;
+}
+
+static ssize_t
+ata_scsi_activity_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct scsi_device *sdev = to_scsi_device(dev);
+ struct ata_port *ap = ata_shost_to_port(sdev->host);
+ struct ata_device *atadev = ata_scsi_find_dev(ap, sdev);
+ enum sw_activity val;
+ int rc;
+
+ if (atadev && ap->ops->sw_activity_store &&
+ (ap->flags & ATA_FLAG_SW_ACTIVITY)) {
+ val = simple_strtoul(buf, NULL, 0);
+ switch (val) {
+ case OFF: case BLINK_ON: case BLINK_OFF:
+ rc = ap->ops->sw_activity_store(atadev, val);
+ if (!rc)
+ return count;
+ else
+ return rc;
+ }
+ }
+ return -EINVAL;
+}
+DEVICE_ATTR(sw_activity, S_IWUSR | S_IRUGO, ata_scsi_activity_show,
+ ata_scsi_activity_store);
+EXPORT_SYMBOL_GPL(dev_attr_sw_activity);
+
+/**
+ * __ata_change_queue_depth - helper for ata_scsi_change_queue_depth
+ * @ap: ATA port to which the device change the queue depth
+ * @sdev: SCSI device to configure queue depth for
+ * @queue_depth: new queue depth
+ *
+ * libsas and libata have different approaches for associating a sdev to
+ * its ata_port.
+ *
+ */
+int __ata_change_queue_depth(struct ata_port *ap, struct scsi_device *sdev,
+ int queue_depth)
+{
+ struct ata_device *dev;
+ unsigned long flags;
+
+ if (queue_depth < 1 || queue_depth == sdev->queue_depth)
+ return sdev->queue_depth;
+
+ dev = ata_scsi_find_dev(ap, sdev);
+ if (!dev || !ata_dev_enabled(dev))
+ return sdev->queue_depth;
+
+ /* NCQ enabled? */
+ spin_lock_irqsave(ap->lock, flags);
+ dev->flags &= ~ATA_DFLAG_NCQ_OFF;
+ if (queue_depth == 1 || !ata_ncq_enabled(dev)) {
+ dev->flags |= ATA_DFLAG_NCQ_OFF;
+ queue_depth = 1;
+ }
+ spin_unlock_irqrestore(ap->lock, flags);
+
+ /* limit and apply queue depth */
+ queue_depth = min(queue_depth, sdev->host->can_queue);
+ queue_depth = min(queue_depth, ata_id_queue_depth(dev->id));
+ queue_depth = min(queue_depth, ATA_MAX_QUEUE);
+
+ if (sdev->queue_depth == queue_depth)
+ return -EINVAL;
+
+ return scsi_change_queue_depth(sdev, queue_depth);
+}
+EXPORT_SYMBOL_GPL(__ata_change_queue_depth);
+
+/**
+ * ata_scsi_change_queue_depth - SCSI callback for queue depth config
+ * @sdev: SCSI device to configure queue depth for
+ * @queue_depth: new queue depth
+ *
+ * This is libata standard hostt->change_queue_depth callback.
+ * SCSI will call into this callback when user tries to set queue
+ * depth via sysfs.
+ *
+ * LOCKING:
+ * SCSI layer (we don't care)
+ *
+ * RETURNS:
+ * Newly configured queue depth.
+ */
+int ata_scsi_change_queue_depth(struct scsi_device *sdev, int queue_depth)
+{
+ struct ata_port *ap = ata_shost_to_port(sdev->host);
+
+ return __ata_change_queue_depth(ap, sdev, queue_depth);
+}
+EXPORT_SYMBOL_GPL(ata_scsi_change_queue_depth);
+
+/**
+ * port_alloc - Allocate port for a SAS attached SATA device
+ * @host: ATA host container for all SAS ports
+ * @port_info: Information from low-level host driver
+ * @shost: SCSI host that the scsi device is attached to
+ *
+ * LOCKING:
+ * PCI/etc. bus probe sem.
+ *
+ * RETURNS:
+ * ata_port pointer on success / NULL on failure.
+ */
+
+struct ata_port *ata_sas_port_alloc(struct ata_host *host,
+ struct ata_port_info *port_info,
+ struct Scsi_Host *shost)
+{
+ struct ata_port *ap;
+
+ ap = ata_port_alloc(host);
+ if (!ap)
+ return NULL;
+
+ ap->port_no = 0;
+ ap->lock = &host->lock;
+ ap->pio_mask = port_info->pio_mask;
+ ap->mwdma_mask = port_info->mwdma_mask;
+ ap->udma_mask = port_info->udma_mask;
+ ap->flags |= port_info->flags;
+ ap->ops = port_info->port_ops;
+ ap->cbl = ATA_CBL_SATA;
+
+ return ap;
+}
+EXPORT_SYMBOL_GPL(ata_sas_port_alloc);
+
+/**
+ * ata_sas_port_start - Set port up for dma.
+ * @ap: Port to initialize
+ *
+ * Called just after data structures for each port are
+ * initialized.
+ *
+ * May be used as the port_start() entry in ata_port_operations.
+ *
+ * LOCKING:
+ * Inherited from caller.
+ */
+int ata_sas_port_start(struct ata_port *ap)
+{
+ /*
+ * the port is marked as frozen at allocation time, but if we don't
+ * have new eh, we won't thaw it
+ */
+ if (!ap->ops->error_handler)
+ ap->pflags &= ~ATA_PFLAG_FROZEN;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ata_sas_port_start);
+
+/**
+ * ata_port_stop - Undo ata_sas_port_start()
+ * @ap: Port to shut down
+ *
+ * May be used as the port_stop() entry in ata_port_operations.
+ *
+ * LOCKING:
+ * Inherited from caller.
+ */
+
+void ata_sas_port_stop(struct ata_port *ap)
+{
+}
+EXPORT_SYMBOL_GPL(ata_sas_port_stop);
+
+/**
+ * ata_sas_async_probe - simply schedule probing and return
+ * @ap: Port to probe
+ *
+ * For batch scheduling of probe for sas attached ata devices, assumes
+ * the port has already been through ata_sas_port_init()
+ */
+void ata_sas_async_probe(struct ata_port *ap)
+{
+ __ata_port_probe(ap);
+}
+EXPORT_SYMBOL_GPL(ata_sas_async_probe);
+
+int ata_sas_sync_probe(struct ata_port *ap)
+{
+ return ata_port_probe(ap);
+}
+EXPORT_SYMBOL_GPL(ata_sas_sync_probe);
+
+
+/**
+ * ata_sas_port_init - Initialize a SATA device
+ * @ap: SATA port to initialize
+ *
+ * LOCKING:
+ * PCI/etc. bus probe sem.
+ *
+ * RETURNS:
+ * Zero on success, non-zero on error.
+ */
+
+int ata_sas_port_init(struct ata_port *ap)
+{
+ int rc = ap->ops->port_start(ap);
+
+ if (rc)
+ return rc;
+ ap->print_id = atomic_inc_return(&ata_print_id);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ata_sas_port_init);
+
+int ata_sas_tport_add(struct device *parent, struct ata_port *ap)
+{
+ return ata_tport_add(parent, ap);
+}
+EXPORT_SYMBOL_GPL(ata_sas_tport_add);
+
+void ata_sas_tport_delete(struct ata_port *ap)
+{
+ ata_tport_delete(ap);
+}
+EXPORT_SYMBOL_GPL(ata_sas_tport_delete);
+
+/**
+ * ata_sas_port_destroy - Destroy a SATA port allocated by ata_sas_port_alloc
+ * @ap: SATA port to destroy
+ *
+ */
+
+void ata_sas_port_destroy(struct ata_port *ap)
+{
+ if (ap->ops->port_stop)
+ ap->ops->port_stop(ap);
+ kfree(ap);
+}
+EXPORT_SYMBOL_GPL(ata_sas_port_destroy);
+
+/**
+ * ata_sas_slave_configure - Default slave_config routine for libata devices
+ * @sdev: SCSI device to configure
+ * @ap: ATA port to which SCSI device is attached
+ *
+ * RETURNS:
+ * Zero.
+ */
+
+int ata_sas_slave_configure(struct scsi_device *sdev, struct ata_port *ap)
+{
+ ata_scsi_sdev_config(sdev);
+ ata_scsi_dev_config(sdev, ap->link.device);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ata_sas_slave_configure);
+
+/**
+ * ata_sas_queuecmd - Issue SCSI cdb to libata-managed device
+ * @cmd: SCSI command to be sent
+ * @ap: ATA port to which the command is being sent
+ *
+ * RETURNS:
+ * Return value from __ata_scsi_queuecmd() if @cmd can be queued,
+ * 0 otherwise.
+ */
+
+int ata_sas_queuecmd(struct scsi_cmnd *cmd, struct ata_port *ap)
+{
+ int rc = 0;
+
+ ata_scsi_dump_cdb(ap, cmd);
+
+ if (likely(ata_dev_enabled(ap->link.device)))
+ rc = __ata_scsi_queuecmd(cmd, ap->link.device);
+ else {
+ cmd->result = (DID_BAD_TARGET << 16);
+ cmd->scsi_done(cmd);
+ }
+ return rc;
+}
+EXPORT_SYMBOL_GPL(ata_sas_queuecmd);
+
+int ata_sas_allocate_tag(struct ata_port *ap)
+{
+ unsigned int max_queue = ap->host->n_tags;
+ unsigned int i, tag;
+
+ for (i = 0, tag = ap->sas_last_tag + 1; i < max_queue; i++, tag++) {
+ tag = tag < max_queue ? tag : 0;
+
+ /* the last tag is reserved for internal command. */
+ if (ata_tag_internal(tag))
+ continue;
+
+ if (!test_and_set_bit(tag, &ap->sas_tag_allocated)) {
+ ap->sas_last_tag = tag;
+ return tag;
+ }
+ }
+ return -1;
+}
+
+void ata_sas_free_tag(unsigned int tag, struct ata_port *ap)
+{
+ clear_bit(tag, &ap->sas_tag_allocated);
+}
+
+/**
+ * sata_async_notification - SATA async notification handler
+ * @ap: ATA port where async notification is received
+ *
+ * Handler to be called when async notification via SDB FIS is
+ * received. This function schedules EH if necessary.
+ *
+ * LOCKING:
+ * spin_lock_irqsave(host lock)
+ *
+ * RETURNS:
+ * 1 if EH is scheduled, 0 otherwise.
+ */
+int sata_async_notification(struct ata_port *ap)
+{
+ u32 sntf;
+ int rc;
+
+ if (!(ap->flags & ATA_FLAG_AN))
+ return 0;
+
+ rc = sata_scr_read(&ap->link, SCR_NOTIFICATION, &sntf);
+ if (rc == 0)
+ sata_scr_write(&ap->link, SCR_NOTIFICATION, sntf);
+
+ if (!sata_pmp_attached(ap) || rc) {
+ /* PMP is not attached or SNTF is not available */
+ if (!sata_pmp_attached(ap)) {
+ /* PMP is not attached. Check whether ATAPI
+ * AN is configured. If so, notify media
+ * change.
+ */
+ struct ata_device *dev = ap->link.device;
+
+ if ((dev->class == ATA_DEV_ATAPI) &&
+ (dev->flags & ATA_DFLAG_AN))
+ ata_scsi_media_change_notify(dev);
+ return 0;
+ } else {
+ /* PMP is attached but SNTF is not available.
+ * ATAPI async media change notification is
+ * not used. The PMP must be reporting PHY
+ * status change, schedule EH.
+ */
+ ata_port_schedule_eh(ap);
+ return 1;
+ }
+ } else {
+ /* PMP is attached and SNTF is available */
+ struct ata_link *link;
+
+ /* check and notify ATAPI AN */
+ ata_for_each_link(link, ap, EDGE) {
+ if (!(sntf & (1 << link->pmp)))
+ continue;
+
+ if ((link->device->class == ATA_DEV_ATAPI) &&
+ (link->device->flags & ATA_DFLAG_AN))
+ ata_scsi_media_change_notify(link->device);
+ }
+
+ /* If PMP is reporting that PHY status of some
+ * downstream ports has changed, schedule EH.
+ */
+ if (sntf & (1 << SATA_PMP_CTRL_PORT)) {
+ ata_port_schedule_eh(ap);
+ return 1;
+ }
+
+ return 0;
+ }
+}
+EXPORT_SYMBOL_GPL(sata_async_notification);
+
+/**
+ * ata_eh_read_log_10h - Read log page 10h for NCQ error details
+ * @dev: Device to read log page 10h from
+ * @tag: Resulting tag of the failed command
+ * @tf: Resulting taskfile registers of the failed command
+ *
+ * Read log page 10h to obtain NCQ error details and clear error
+ * condition.
+ *
+ * LOCKING:
+ * Kernel thread context (may sleep).
+ *
+ * RETURNS:
+ * 0 on success, -errno otherwise.
+ */
+static int ata_eh_read_log_10h(struct ata_device *dev,
+ int *tag, struct ata_taskfile *tf)
+{
+ u8 *buf = dev->link->ap->sector_buf;
+ unsigned int err_mask;
+ u8 csum;
+ int i;
+
+ err_mask = ata_read_log_page(dev, ATA_LOG_SATA_NCQ, 0, buf, 1);
+ if (err_mask)
+ return -EIO;
+
+ csum = 0;
+ for (i = 0; i < ATA_SECT_SIZE; i++)
+ csum += buf[i];
+ if (csum)
+ ata_dev_warn(dev, "invalid checksum 0x%x on log page 10h\n",
+ csum);
+
+ if (buf[0] & 0x80)
+ return -ENOENT;
+
+ *tag = buf[0] & 0x1f;
+
+ tf->command = buf[2];
+ tf->feature = buf[3];
+ tf->lbal = buf[4];
+ tf->lbam = buf[5];
+ tf->lbah = buf[6];
+ tf->device = buf[7];
+ tf->hob_lbal = buf[8];
+ tf->hob_lbam = buf[9];
+ tf->hob_lbah = buf[10];
+ tf->nsect = buf[12];
+ tf->hob_nsect = buf[13];
+ if (dev->class == ATA_DEV_ZAC && ata_id_has_ncq_autosense(dev->id))
+ tf->auxiliary = buf[14] << 16 | buf[15] << 8 | buf[16];
+
+ return 0;
+}
+
+/**
+ * ata_eh_analyze_ncq_error - analyze NCQ error
+ * @link: ATA link to analyze NCQ error for
+ *
+ * Read log page 10h, determine the offending qc and acquire
+ * error status TF. For NCQ device errors, all LLDDs have to do
+ * is setting AC_ERR_DEV in ehi->err_mask. This function takes
+ * care of the rest.
+ *
+ * LOCKING:
+ * Kernel thread context (may sleep).
+ */
+void ata_eh_analyze_ncq_error(struct ata_link *link)
+{
+ struct ata_port *ap = link->ap;
+ struct ata_eh_context *ehc = &link->eh_context;
+ struct ata_device *dev = link->device;
+ struct ata_queued_cmd *qc;
+ struct ata_taskfile tf;
+ int tag, rc;
+
+ /* if frozen, we can't do much */
+ if (ap->pflags & ATA_PFLAG_FROZEN)
+ return;
+
+ /* is it NCQ device error? */
+ if (!link->sactive || !(ehc->i.err_mask & AC_ERR_DEV))
+ return;
+
+ /* has LLDD analyzed already? */
+ ata_qc_for_each_raw(ap, qc, tag) {
+ if (!(qc->flags & ATA_QCFLAG_FAILED))
+ continue;
+
+ if (qc->err_mask)
+ return;
+ }
+
+ /* okay, this error is ours */
+ memset(&tf, 0, sizeof(tf));
+ rc = ata_eh_read_log_10h(dev, &tag, &tf);
+ if (rc) {
+ ata_link_err(link, "failed to read log page 10h (errno=%d)\n",
+ rc);
+ return;
+ }
+
+ if (!(link->sactive & (1 << tag))) {
+ ata_link_err(link, "log page 10h reported inactive tag %d\n",
+ tag);
+ return;
+ }
+
+ /* we've got the perpetrator, condemn it */
+ qc = __ata_qc_from_tag(ap, tag);
+ memcpy(&qc->result_tf, &tf, sizeof(tf));
+ qc->result_tf.flags = ATA_TFLAG_ISADDR | ATA_TFLAG_LBA | ATA_TFLAG_LBA48;
+ qc->err_mask |= AC_ERR_DEV | AC_ERR_NCQ;
+ if (dev->class == ATA_DEV_ZAC &&
+ ((qc->result_tf.command & ATA_SENSE) || qc->result_tf.auxiliary)) {
+ char sense_key, asc, ascq;
+
+ sense_key = (qc->result_tf.auxiliary >> 16) & 0xff;
+ asc = (qc->result_tf.auxiliary >> 8) & 0xff;
+ ascq = qc->result_tf.auxiliary & 0xff;
+ ata_scsi_set_sense(dev, qc->scsicmd, sense_key, asc, ascq);
+ ata_scsi_set_sense_information(dev, qc->scsicmd,
+ &qc->result_tf);
+ qc->flags |= ATA_QCFLAG_SENSE_VALID;
+ }
+
+ ehc->i.err_mask &= ~AC_ERR_DEV;
+}
+EXPORT_SYMBOL_GPL(ata_eh_analyze_ncq_error);
/*
* libata-scsi.c - helper library for ATA
*
- * Maintained by: Tejun Heo <tj@kernel.org>
- * Please ALWAYS copy linux-ide@vger.kernel.org
- * on emails.
- *
* Copyright 2003-2004 Red Hat, Inc. All rights reserved.
* Copyright 2003-2004 Jeff Garzik
*
#include <linux/suspend.h>
#include <asm/unaligned.h>
#include <linux/ioprio.h>
+#include <linux/of.h>
#include "libata.h"
#include "libata-transport.h"
-#define ATA_SCSI_RBUF_SIZE 4096
+#define ATA_SCSI_RBUF_SIZE 576
static DEFINE_SPINLOCK(ata_scsi_rbuf_lock);
static u8 ata_scsi_rbuf[ATA_SCSI_RBUF_SIZE];
static struct ata_device *__ata_scsi_find_dev(struct ata_port *ap,
const struct scsi_device *scsidev);
-static struct ata_device *ata_scsi_find_dev(struct ata_port *ap,
- const struct scsi_device *scsidev);
#define RW_RECOVERY_MPAGE 0x1
#define RW_RECOVERY_MPAGE_LEN 12
0, 30 /* extended self test time, see 05-359r1 */
};
-static const char *ata_lpm_policy_names[] = {
- [ATA_LPM_UNKNOWN] = "max_performance",
- [ATA_LPM_MAX_POWER] = "max_performance",
- [ATA_LPM_MED_POWER] = "medium_power",
- [ATA_LPM_MED_POWER_WITH_DIPM] = "med_power_with_dipm",
- [ATA_LPM_MIN_POWER_WITH_PARTIAL] = "min_power_with_partial",
- [ATA_LPM_MIN_POWER] = "min_power",
-};
-
-static ssize_t ata_scsi_lpm_store(struct device *device,
- struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct Scsi_Host *shost = class_to_shost(device);
- struct ata_port *ap = ata_shost_to_port(shost);
- struct ata_link *link;
- struct ata_device *dev;
- enum ata_lpm_policy policy;
- unsigned long flags;
-
- /* UNKNOWN is internal state, iterate from MAX_POWER */
- for (policy = ATA_LPM_MAX_POWER;
- policy < ARRAY_SIZE(ata_lpm_policy_names); policy++) {
- const char *name = ata_lpm_policy_names[policy];
-
- if (strncmp(name, buf, strlen(name)) == 0)
- break;
- }
- if (policy == ARRAY_SIZE(ata_lpm_policy_names))
- return -EINVAL;
-
- spin_lock_irqsave(ap->lock, flags);
-
- ata_for_each_link(link, ap, EDGE) {
- ata_for_each_dev(dev, &ap->link, ENABLED) {
- if (dev->horkage & ATA_HORKAGE_NOLPM) {
- count = -EOPNOTSUPP;
- goto out_unlock;
- }
- }
- }
-
- ap->target_lpm_policy = policy;
- ata_port_schedule_eh(ap);
-out_unlock:
- spin_unlock_irqrestore(ap->lock, flags);
- return count;
-}
-
-static ssize_t ata_scsi_lpm_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct Scsi_Host *shost = class_to_shost(dev);
- struct ata_port *ap = ata_shost_to_port(shost);
-
- if (ap->target_lpm_policy >= ARRAY_SIZE(ata_lpm_policy_names))
- return -EINVAL;
-
- return snprintf(buf, PAGE_SIZE, "%s\n",
- ata_lpm_policy_names[ap->target_lpm_policy]);
-}
-DEVICE_ATTR(link_power_management_policy, S_IRUGO | S_IWUSR,
- ata_scsi_lpm_show, ata_scsi_lpm_store);
-EXPORT_SYMBOL_GPL(dev_attr_link_power_management_policy);
-
static ssize_t ata_scsi_park_show(struct device *device,
struct device_attribute *attr, char *buf)
{
ata_scsi_park_show, ata_scsi_park_store);
EXPORT_SYMBOL_GPL(dev_attr_unload_heads);
-static ssize_t ata_ncq_prio_enable_show(struct device *device,
- struct device_attribute *attr,
- char *buf)
-{
- struct scsi_device *sdev = to_scsi_device(device);
- struct ata_port *ap;
- struct ata_device *dev;
- bool ncq_prio_enable;
- int rc = 0;
-
- ap = ata_shost_to_port(sdev->host);
-
- spin_lock_irq(ap->lock);
- dev = ata_scsi_find_dev(ap, sdev);
- if (!dev) {
- rc = -ENODEV;
- goto unlock;
- }
-
- ncq_prio_enable = dev->flags & ATA_DFLAG_NCQ_PRIO_ENABLE;
-
-unlock:
- spin_unlock_irq(ap->lock);
-
- return rc ? rc : snprintf(buf, 20, "%u\n", ncq_prio_enable);
-}
-
-static ssize_t ata_ncq_prio_enable_store(struct device *device,
- struct device_attribute *attr,
- const char *buf, size_t len)
-{
- struct scsi_device *sdev = to_scsi_device(device);
- struct ata_port *ap;
- struct ata_device *dev;
- long int input;
- int rc;
-
- rc = kstrtol(buf, 10, &input);
- if (rc)
- return rc;
- if ((input < 0) || (input > 1))
- return -EINVAL;
-
- ap = ata_shost_to_port(sdev->host);
- dev = ata_scsi_find_dev(ap, sdev);
- if (unlikely(!dev))
- return -ENODEV;
-
- spin_lock_irq(ap->lock);
- if (input)
- dev->flags |= ATA_DFLAG_NCQ_PRIO_ENABLE;
- else
- dev->flags &= ~ATA_DFLAG_NCQ_PRIO_ENABLE;
-
- dev->link->eh_info.action |= ATA_EH_REVALIDATE;
- dev->link->eh_info.flags |= ATA_EHI_QUIET;
- ata_port_schedule_eh(ap);
- spin_unlock_irq(ap->lock);
-
- ata_port_wait_eh(ap);
-
- if (input) {
- spin_lock_irq(ap->lock);
- if (!(dev->flags & ATA_DFLAG_NCQ_PRIO)) {
- dev->flags &= ~ATA_DFLAG_NCQ_PRIO_ENABLE;
- rc = -EIO;
- }
- spin_unlock_irq(ap->lock);
- }
-
- return rc ? rc : len;
-}
-
-DEVICE_ATTR(ncq_prio_enable, S_IRUGO | S_IWUSR,
- ata_ncq_prio_enable_show, ata_ncq_prio_enable_store);
-EXPORT_SYMBOL_GPL(dev_attr_ncq_prio_enable);
-
void ata_scsi_set_sense(struct ata_device *dev, struct scsi_cmnd *cmd,
u8 sk, u8 asc, u8 ascq)
{
field, 0xff, 0);
}
-static ssize_t
-ata_scsi_em_message_store(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct Scsi_Host *shost = class_to_shost(dev);
- struct ata_port *ap = ata_shost_to_port(shost);
- if (ap->ops->em_store && (ap->flags & ATA_FLAG_EM))
- return ap->ops->em_store(ap, buf, count);
- return -EINVAL;
-}
-
-static ssize_t
-ata_scsi_em_message_show(struct device *dev, struct device_attribute *attr,
- char *buf)
-{
- struct Scsi_Host *shost = class_to_shost(dev);
- struct ata_port *ap = ata_shost_to_port(shost);
-
- if (ap->ops->em_show && (ap->flags & ATA_FLAG_EM))
- return ap->ops->em_show(ap, buf);
- return -EINVAL;
-}
-DEVICE_ATTR(em_message, S_IRUGO | S_IWUSR,
- ata_scsi_em_message_show, ata_scsi_em_message_store);
-EXPORT_SYMBOL_GPL(dev_attr_em_message);
-
-static ssize_t
-ata_scsi_em_message_type_show(struct device *dev, struct device_attribute *attr,
- char *buf)
-{
- struct Scsi_Host *shost = class_to_shost(dev);
- struct ata_port *ap = ata_shost_to_port(shost);
-
- return snprintf(buf, 23, "%d\n", ap->em_message_type);
-}
-DEVICE_ATTR(em_message_type, S_IRUGO,
- ata_scsi_em_message_type_show, NULL);
-EXPORT_SYMBOL_GPL(dev_attr_em_message_type);
-
-static ssize_t
-ata_scsi_activity_show(struct device *dev, struct device_attribute *attr,
- char *buf)
-{
- struct scsi_device *sdev = to_scsi_device(dev);
- struct ata_port *ap = ata_shost_to_port(sdev->host);
- struct ata_device *atadev = ata_scsi_find_dev(ap, sdev);
-
- if (atadev && ap->ops->sw_activity_show &&
- (ap->flags & ATA_FLAG_SW_ACTIVITY))
- return ap->ops->sw_activity_show(atadev, buf);
- return -EINVAL;
-}
-
-static ssize_t
-ata_scsi_activity_store(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct scsi_device *sdev = to_scsi_device(dev);
- struct ata_port *ap = ata_shost_to_port(sdev->host);
- struct ata_device *atadev = ata_scsi_find_dev(ap, sdev);
- enum sw_activity val;
- int rc;
-
- if (atadev && ap->ops->sw_activity_store &&
- (ap->flags & ATA_FLAG_SW_ACTIVITY)) {
- val = simple_strtoul(buf, NULL, 0);
- switch (val) {
- case OFF: case BLINK_ON: case BLINK_OFF:
- rc = ap->ops->sw_activity_store(atadev, val);
- if (!rc)
- return count;
- else
- return rc;
- }
- }
- return -EINVAL;
-}
-DEVICE_ATTR(sw_activity, S_IWUSR | S_IRUGO, ata_scsi_activity_show,
- ata_scsi_activity_store);
-EXPORT_SYMBOL_GPL(dev_attr_sw_activity);
-
struct device_attribute *ata_common_sdev_attrs[] = {
&dev_attr_unload_heads,
- &dev_attr_ncq_prio_enable,
NULL
};
EXPORT_SYMBOL_GPL(ata_common_sdev_attrs);
return 0;
}
+EXPORT_SYMBOL_GPL(ata_std_bios_param);
/**
* ata_scsi_unlock_native_capacity - unlock native capacity
spin_unlock_irqrestore(ap->lock, flags);
ata_port_wait_eh(ap);
}
+EXPORT_SYMBOL_GPL(ata_scsi_unlock_native_capacity);
/**
* ata_get_identity - Handler for HDIO_GET_IDENTITY ioctl
scsi_set_sense_information(sb, SCSI_SENSE_BUFFERSIZE, block);
}
-static void ata_scsi_sdev_config(struct scsi_device *sdev)
+void ata_scsi_sdev_config(struct scsi_device *sdev)
{
sdev->use_10_for_rw = 1;
sdev->use_10_for_ms = 1;
return atapi_cmd_type(scsi_req(rq)->cmd[0]) == ATAPI_MISC;
}
-static int ata_scsi_dev_config(struct scsi_device *sdev,
- struct ata_device *dev)
+int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev)
{
struct request_queue *q = sdev->request_queue;
return rc;
}
+EXPORT_SYMBOL_GPL(ata_scsi_slave_config);
/**
* ata_scsi_slave_destroy - SCSI device is about to be destroyed
q->dma_drain_buffer = NULL;
q->dma_drain_size = 0;
}
-
-/**
- * __ata_change_queue_depth - helper for ata_scsi_change_queue_depth
- * @ap: ATA port to which the device change the queue depth
- * @sdev: SCSI device to configure queue depth for
- * @queue_depth: new queue depth
- *
- * libsas and libata have different approaches for associating a sdev to
- * its ata_port.
- *
- */
-int __ata_change_queue_depth(struct ata_port *ap, struct scsi_device *sdev,
- int queue_depth)
-{
- struct ata_device *dev;
- unsigned long flags;
-
- if (queue_depth < 1 || queue_depth == sdev->queue_depth)
- return sdev->queue_depth;
-
- dev = ata_scsi_find_dev(ap, sdev);
- if (!dev || !ata_dev_enabled(dev))
- return sdev->queue_depth;
-
- /* NCQ enabled? */
- spin_lock_irqsave(ap->lock, flags);
- dev->flags &= ~ATA_DFLAG_NCQ_OFF;
- if (queue_depth == 1 || !ata_ncq_enabled(dev)) {
- dev->flags |= ATA_DFLAG_NCQ_OFF;
- queue_depth = 1;
- }
- spin_unlock_irqrestore(ap->lock, flags);
-
- /* limit and apply queue depth */
- queue_depth = min(queue_depth, sdev->host->can_queue);
- queue_depth = min(queue_depth, ata_id_queue_depth(dev->id));
- queue_depth = min(queue_depth, ATA_MAX_QUEUE);
-
- if (sdev->queue_depth == queue_depth)
- return -EINVAL;
-
- return scsi_change_queue_depth(sdev, queue_depth);
-}
-
-/**
- * ata_scsi_change_queue_depth - SCSI callback for queue depth config
- * @sdev: SCSI device to configure queue depth for
- * @queue_depth: new queue depth
- *
- * This is libata standard hostt->change_queue_depth callback.
- * SCSI will call into this callback when user tries to set queue
- * depth via sysfs.
- *
- * LOCKING:
- * SCSI layer (we don't care)
- *
- * RETURNS:
- * Newly configured queue depth.
- */
-int ata_scsi_change_queue_depth(struct scsi_device *sdev, int queue_depth)
-{
- struct ata_port *ap = ata_shost_to_port(sdev->host);
-
- return __ata_change_queue_depth(ap, sdev, queue_depth);
-}
+EXPORT_SYMBOL_GPL(ata_scsi_slave_destroy);
/**
* ata_scsi_start_stop_xlat - Translate SCSI START STOP UNIT command
*/
static unsigned int ata_scsiop_inq_89(struct ata_scsi_args *args, u8 *rbuf)
{
- struct ata_taskfile tf;
-
- memset(&tf, 0, sizeof(tf));
-
rbuf[1] = 0x89; /* our page code */
rbuf[2] = (0x238 >> 8); /* page size fixed at 238h */
rbuf[3] = (0x238 & 0xff);
memcpy(&rbuf[16], "libata ", 16);
memcpy(&rbuf[32], DRV_VERSION, 4);
- /* we don't store the ATA device signature, so we fake it */
-
- tf.command = ATA_DRDY; /* really, this is Status reg */
- tf.lbal = 0x1;
- tf.nsect = 0x1;
-
- ata_tf_to_fis(&tf, 0, 1, &rbuf[36]); /* TODO: PMP? */
rbuf[36] = 0x34; /* force D2H Reg FIS (34h) */
+ rbuf[37] = (1 << 7); /* bit 7 indicates Command FIS */
+ /* TODO: PMP? */
+
+ /* we don't store the ATA device signature, so we fake it */
+ rbuf[38] = ATA_DRDY; /* really, this is Status reg */
+ rbuf[40] = 0x1;
+ rbuf[48] = 0x1;
rbuf[56] = ATA_CMD_ID_ATA;
* RETURNS:
* Associated ATA device, or %NULL if not found.
*/
-static struct ata_device *
+struct ata_device *
ata_scsi_find_dev(struct ata_port *ap, const struct scsi_device *scsidev)
{
struct ata_device *dev = __ata_scsi_find_dev(ap, scsidev);
* Prints the contents of a SCSI command via printk().
*/
-static inline void ata_scsi_dump_cdb(struct ata_port *ap,
- struct scsi_cmnd *cmd)
+void ata_scsi_dump_cdb(struct ata_port *ap, struct scsi_cmnd *cmd)
{
#ifdef ATA_VERBOSE_DEBUG
struct scsi_device *scsidev = cmd->device;
#endif
}
-static inline int __ata_scsi_queuecmd(struct scsi_cmnd *scmd,
- struct ata_device *dev)
+int __ata_scsi_queuecmd(struct scsi_cmnd *scmd, struct ata_device *dev)
{
u8 scsi_op = scmd->cmnd[0];
ata_xlat_func_t xlat_func;
return rc;
}
+EXPORT_SYMBOL_GPL(ata_scsi_queuecmd);
/**
* ata_scsi_simulate - simulate SCSI command on ATA device
*/
shost->max_host_blocked = 1;
- rc = scsi_add_host_with_dma(ap->scsi_host,
- &ap->tdev, ap->host->dev);
+ rc = scsi_add_host_with_dma(shost, &ap->tdev, ap->host->dev);
if (rc)
- goto err_add;
+ goto err_alloc;
}
return 0;
- err_add:
- scsi_host_put(host->ports[i]->scsi_host);
err_alloc:
while (--i >= 0) {
struct Scsi_Host *shost = host->ports[i]->scsi_host;
+ /* scsi_host_put() is in ata_devres_release() */
scsi_remove_host(shost);
- scsi_host_put(shost);
}
return rc;
}
+#ifdef CONFIG_OF
+static void ata_scsi_assign_ofnode(struct ata_device *dev, struct ata_port *ap)
+{
+ struct scsi_device *sdev = dev->sdev;
+ struct device *d = ap->host->dev;
+ struct device_node *np = d->of_node;
+ struct device_node *child;
+
+ for_each_available_child_of_node(np, child) {
+ int ret;
+ u32 val;
+
+ ret = of_property_read_u32(child, "reg", &val);
+ if (ret)
+ continue;
+ if (val == dev->devno) {
+ dev_dbg(d, "found matching device node\n");
+ sdev->sdev_gendev.of_node = child;
+ return;
+ }
+ }
+}
+#else
+static void ata_scsi_assign_ofnode(struct ata_device *dev, struct ata_port *ap)
+{
+}
+#endif
+
void ata_scsi_scan_host(struct ata_port *ap, int sync)
{
int tries = 5;
NULL);
if (!IS_ERR(sdev)) {
dev->sdev = sdev;
+ ata_scsi_assign_ofnode(dev, ap);
scsi_device_put(sdev);
} else {
dev->sdev = NULL;
spin_unlock_irqrestore(ap->lock, flags);
mutex_unlock(&ap->scsi_scan_mutex);
}
-
-/**
- * ata_sas_port_alloc - Allocate port for a SAS attached SATA device
- * @host: ATA host container for all SAS ports
- * @port_info: Information from low-level host driver
- * @shost: SCSI host that the scsi device is attached to
- *
- * LOCKING:
- * PCI/etc. bus probe sem.
- *
- * RETURNS:
- * ata_port pointer on success / NULL on failure.
- */
-
-struct ata_port *ata_sas_port_alloc(struct ata_host *host,
- struct ata_port_info *port_info,
- struct Scsi_Host *shost)
-{
- struct ata_port *ap;
-
- ap = ata_port_alloc(host);
- if (!ap)
- return NULL;
-
- ap->port_no = 0;
- ap->lock = &host->lock;
- ap->pio_mask = port_info->pio_mask;
- ap->mwdma_mask = port_info->mwdma_mask;
- ap->udma_mask = port_info->udma_mask;
- ap->flags |= port_info->flags;
- ap->ops = port_info->port_ops;
- ap->cbl = ATA_CBL_SATA;
-
- return ap;
-}
-EXPORT_SYMBOL_GPL(ata_sas_port_alloc);
-
-/**
- * ata_sas_port_start - Set port up for dma.
- * @ap: Port to initialize
- *
- * Called just after data structures for each port are
- * initialized.
- *
- * May be used as the port_start() entry in ata_port_operations.
- *
- * LOCKING:
- * Inherited from caller.
- */
-int ata_sas_port_start(struct ata_port *ap)
-{
- /*
- * the port is marked as frozen at allocation time, but if we don't
- * have new eh, we won't thaw it
- */
- if (!ap->ops->error_handler)
- ap->pflags &= ~ATA_PFLAG_FROZEN;
- return 0;
-}
-EXPORT_SYMBOL_GPL(ata_sas_port_start);
-
-/**
- * ata_port_stop - Undo ata_sas_port_start()
- * @ap: Port to shut down
- *
- * May be used as the port_stop() entry in ata_port_operations.
- *
- * LOCKING:
- * Inherited from caller.
- */
-
-void ata_sas_port_stop(struct ata_port *ap)
-{
-}
-EXPORT_SYMBOL_GPL(ata_sas_port_stop);
-
-/**
- * ata_sas_async_probe - simply schedule probing and return
- * @ap: Port to probe
- *
- * For batch scheduling of probe for sas attached ata devices, assumes
- * the port has already been through ata_sas_port_init()
- */
-void ata_sas_async_probe(struct ata_port *ap)
-{
- __ata_port_probe(ap);
-}
-EXPORT_SYMBOL_GPL(ata_sas_async_probe);
-
-int ata_sas_sync_probe(struct ata_port *ap)
-{
- return ata_port_probe(ap);
-}
-EXPORT_SYMBOL_GPL(ata_sas_sync_probe);
-
-
-/**
- * ata_sas_port_init - Initialize a SATA device
- * @ap: SATA port to initialize
- *
- * LOCKING:
- * PCI/etc. bus probe sem.
- *
- * RETURNS:
- * Zero on success, non-zero on error.
- */
-
-int ata_sas_port_init(struct ata_port *ap)
-{
- int rc = ap->ops->port_start(ap);
-
- if (rc)
- return rc;
- ap->print_id = atomic_inc_return(&ata_print_id);
- return 0;
-}
-EXPORT_SYMBOL_GPL(ata_sas_port_init);
-
-int ata_sas_tport_add(struct device *parent, struct ata_port *ap)
-{
- return ata_tport_add(parent, ap);
-}
-EXPORT_SYMBOL_GPL(ata_sas_tport_add);
-
-void ata_sas_tport_delete(struct ata_port *ap)
-{
- ata_tport_delete(ap);
-}
-EXPORT_SYMBOL_GPL(ata_sas_tport_delete);
-
-/**
- * ata_sas_port_destroy - Destroy a SATA port allocated by ata_sas_port_alloc
- * @ap: SATA port to destroy
- *
- */
-
-void ata_sas_port_destroy(struct ata_port *ap)
-{
- if (ap->ops->port_stop)
- ap->ops->port_stop(ap);
- kfree(ap);
-}
-EXPORT_SYMBOL_GPL(ata_sas_port_destroy);
-
-/**
- * ata_sas_slave_configure - Default slave_config routine for libata devices
- * @sdev: SCSI device to configure
- * @ap: ATA port to which SCSI device is attached
- *
- * RETURNS:
- * Zero.
- */
-
-int ata_sas_slave_configure(struct scsi_device *sdev, struct ata_port *ap)
-{
- ata_scsi_sdev_config(sdev);
- ata_scsi_dev_config(sdev, ap->link.device);
- return 0;
-}
-EXPORT_SYMBOL_GPL(ata_sas_slave_configure);
-
-/**
- * ata_sas_queuecmd - Issue SCSI cdb to libata-managed device
- * @cmd: SCSI command to be sent
- * @ap: ATA port to which the command is being sent
- *
- * RETURNS:
- * Return value from __ata_scsi_queuecmd() if @cmd can be queued,
- * 0 otherwise.
- */
-
-int ata_sas_queuecmd(struct scsi_cmnd *cmd, struct ata_port *ap)
-{
- int rc = 0;
-
- ata_scsi_dump_cdb(ap, cmd);
-
- if (likely(ata_dev_enabled(ap->link.device)))
- rc = __ata_scsi_queuecmd(cmd, ap->link.device);
- else {
- cmd->result = (DID_BAD_TARGET << 16);
- cmd->scsi_done(cmd);
- }
- return rc;
-}
-EXPORT_SYMBOL_GPL(ata_sas_queuecmd);
-
-int ata_sas_allocate_tag(struct ata_port *ap)
-{
- unsigned int max_queue = ap->host->n_tags;
- unsigned int i, tag;
-
- for (i = 0, tag = ap->sas_last_tag + 1; i < max_queue; i++, tag++) {
- tag = tag < max_queue ? tag : 0;
-
- /* the last tag is reserved for internal command. */
- if (ata_tag_internal(tag))
- continue;
-
- if (!test_and_set_bit(tag, &ap->sas_tag_allocated)) {
- ap->sas_last_tag = tag;
- return tag;
- }
- }
- return -1;
-}
-
-void ata_sas_free_tag(unsigned int tag, struct ata_port *ap)
-{
- clear_bit(tag, &ap->sas_tag_allocated);
-}
/*
* libata-sff.c - helper library for PCI IDE BMDMA
*
- * Maintained by: Tejun Heo <tj@kernel.org>
- * Please ALWAYS copy linux-ide@vger.kernel.org
- * on emails.
- *
* Copyright 2003-2006 Red Hat, Inc. All rights reserved.
* Copyright 2003-2006 Jeff Garzik
*
{ \
struct ata_port *ap = transport_class_to_port(dev); \
\
- return snprintf(buf, 20, format_string, cast ap->field); \
+ return scnprintf(buf, 20, format_string, cast ap->field); \
}
#define ata_port_simple_attr(field, name, format_string, type) \
{ \
struct ata_device *ata_dev = transport_class_to_dev(dev); \
\
- return snprintf(buf, 20, format_string, cast ata_dev->field); \
+ return scnprintf(buf, 20, format_string, cast ata_dev->field); \
}
#define ata_dev_simple_attr(field, format_string, type) \
if (ata_dev->class == ATA_DEV_PMP)
return 0;
for(i=0;i<ATA_ID_WORDS;i++) {
- written += snprintf(buf+written, 20, "%04x%c",
+ written += scnprintf(buf+written, 20, "%04x%c",
ata_dev->id[i],
((i+1) & 7) ? ' ' : '\n');
}
if (ata_dev->class != ATA_DEV_PMP)
return 0;
for(i=0;i<SATA_PMP_GSCR_DWORDS;i++) {
- written += snprintf(buf+written, 20, "%08x%c",
+ written += scnprintf(buf+written, 20, "%08x%c",
ata_dev->gscr[i],
((i+1) & 3) ? ' ' : '\n');
}
else
mode = "unqueued";
- return snprintf(buf, 20, "%s\n", mode);
+ return scnprintf(buf, 20, "%s\n", mode);
}
static DEVICE_ATTR(trim, S_IRUGO, show_ata_dev_trim, NULL);
extern int libata_allow_tpm;
extern const struct device_type ata_port_type;
extern struct ata_link *ata_dev_phys_link(struct ata_device *dev);
+#ifdef CONFIG_ATA_FORCE
extern void ata_force_cbl(struct ata_port *ap);
+#else
+static inline void ata_force_cbl(struct ata_port *ap) { }
+#endif
extern u64 ata_tf_to_lba(const struct ata_taskfile *tf);
extern u64 ata_tf_to_lba48(const struct ata_taskfile *tf);
extern struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev, int tag);
#define to_ata_port(d) container_of(d, struct ata_port, tdev)
+/* libata-sata.c */
+#ifdef CONFIG_SATA_HOST
+int ata_sas_allocate_tag(struct ata_port *ap);
+void ata_sas_free_tag(unsigned int tag, struct ata_port *ap);
+#else
+static inline int ata_sas_allocate_tag(struct ata_port *ap)
+{
+ return -EOPNOTSUPP;
+}
+static inline void ata_sas_free_tag(unsigned int tag, struct ata_port *ap) { }
+#endif
+
/* libata-acpi.c */
#ifdef CONFIG_ATA_ACPI
extern unsigned int ata_acpi_gtf_filter;
#endif
/* libata-scsi.c */
+extern struct ata_device *ata_scsi_find_dev(struct ata_port *ap,
+ const struct scsi_device *scsidev);
extern int ata_scsi_add_hosts(struct ata_host *host,
struct scsi_host_template *sht);
extern void ata_scsi_scan_host(struct ata_port *ap, int sync);
extern int ata_bus_probe(struct ata_port *ap);
extern int ata_scsi_user_scan(struct Scsi_Host *shost, unsigned int channel,
unsigned int id, u64 lun);
-int ata_sas_allocate_tag(struct ata_port *ap);
-void ata_sas_free_tag(unsigned int tag, struct ata_port *ap);
-
+void ata_scsi_sdev_config(struct scsi_device *sdev);
+int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev);
+void ata_scsi_dump_cdb(struct ata_port *ap, struct scsi_cmnd *cmd);
+int __ata_scsi_queuecmd(struct scsi_cmnd *scmd, struct ata_device *dev);
/* libata-eh.c */
extern unsigned long ata_internal_cmd_timeout(struct ata_device *dev, u8 cmd);
static void pdc_error_handler(struct ata_port *ap);
static void pdc_post_internal_cmd(struct ata_queued_cmd *qc);
static int pdc_pata_cable_detect(struct ata_port *ap);
-static int pdc_sata_cable_detect(struct ata_port *ap);
static struct scsi_host_template pdc_ata_sht = {
ATA_BASE_SHT(DRV_NAME),
static struct ata_port_operations pdc_sata_ops = {
.inherits = &pdc_common_ops,
- .cable_detect = pdc_sata_cable_detect,
+ .cable_detect = ata_cable_sata,
.freeze = pdc_sata_freeze,
.thaw = pdc_sata_thaw,
.scr_read = pdc_sata_scr_read,
return ATA_CBL_PATA80;
}
-static int pdc_sata_cable_detect(struct ata_port *ap)
-{
- return ATA_CBL_SATA;
-}
-
static int pdc_sata_scr_read(struct ata_link *link,
unsigned int sc_reg, u32 *val)
{
# Rewritten to use lists instead of if-statements.
#
+# needed for trace events
+ccflags-y += -I$(src)
+
obj-$(CONFIG_MAC_FLOPPY) += swim3.o
obj-$(CONFIG_BLK_DEV_SWIM) += swim_mod.o
obj-$(CONFIG_BLK_DEV_FD) += floppy.o
obj-$(CONFIG_BLK_DEV_NULL_BLK) += null_blk.o
null_blk-objs := null_blk_main.o
+ifeq ($(CONFIG_BLK_DEV_ZONED), y)
+null_blk-$(CONFIG_TRACING) += null_blk_trace.o
+endif
null_blk-$(CONFIG_BLK_DEV_ZONED) += null_blk_zoned.o
skd-y := skd_main.o
if (*nd == NULL)
return snprintf(page, PAGE_SIZE, "none\n");
for (p = page; nd < ne; nd++)
- p += snprintf(p, PAGE_SIZE - (p-page), "%s%s",
+ p += scnprintf(p, PAGE_SIZE - (p-page), "%s%s",
p == page ? "" : ",", (*nd)->name);
- p += snprintf(p, PAGE_SIZE - (p-page), "\n");
+ p += scnprintf(p, PAGE_SIZE - (p-page), "\n");
return p-page;
}
/* firmware version */
spin_lock_init(&brd->brd_lock);
INIT_RADIX_TREE(&brd->brd_pages, GFP_ATOMIC);
- brd->brd_queue = blk_alloc_queue(GFP_KERNEL);
+ brd->brd_queue = blk_alloc_queue(brd_make_request, NUMA_NO_NODE);
if (!brd->brd_queue)
goto out_free_dev;
- blk_queue_make_request(brd->brd_queue, brd_make_request);
-
/* This is so fdisk will align partitions on 4k, because of
* direct_access API needing 4k alignment, returning a PFN
* (This is only a problem on very small devices <= 4M,
drbd_init_set_defaults(device);
- q = blk_alloc_queue_node(GFP_KERNEL, NUMA_NO_NODE);
+ q = blk_alloc_queue(drbd_make_request, NUMA_NO_NODE);
if (!q)
goto out_no_q;
device->rq_queue = q;
q->backing_dev_info->congested_fn = drbd_congested;
q->backing_dev_info->congested_data = device;
- blk_queue_make_request(q, drbd_make_request);
blk_queue_write_cache(q, true, true);
/* Setting the max_hw_sectors to an odd value of 8kibyte here
This triggers a max_bio_size message upon first attach or connect */
* the meta-data super block. This function sets MD_DIRTY, and starts a
* timer that ensures that within five seconds you have to call drbd_md_sync().
*/
-#ifdef DEBUG
-void drbd_md_mark_dirty_(struct drbd_device *device, unsigned int line, const char *func)
-{
- if (!test_and_set_bit(MD_DIRTY, &device->flags)) {
- mod_timer(&device->md_sync_timer, jiffies + HZ);
- device->last_md_mark_dirty.line = line;
- device->last_md_mark_dirty.func = func;
- }
-}
-#else
void drbd_md_mark_dirty(struct drbd_device *device)
{
if (!test_and_set_bit(MD_DIRTY, &device->flags))
mod_timer(&device->md_sync_timer, jiffies + 5*HZ);
}
-#endif
void drbd_uuid_move_history(struct drbd_device *device) __must_hold(local)
{
#include <linux/random.h>
#include <linux/string.h>
#include <linux/scatterlist.h>
+#include <linux/part_stat.h>
#include "drbd_int.h"
#include "drbd_protocol.h"
#include "drbd_req.h"
#include <linux/random.h>
#include <linux/string.h>
#include <linux/scatterlist.h>
+#include <linux/part_stat.h>
#include "drbd_int.h"
#include "drbd_protocol.h"
#include <linux/kernel.h>
#include <linux/timer.h>
#include <linux/workqueue.h>
-#define FDPATCHES
#include <linux/fdreg.h>
#include <linux/fd.h>
#include <linux/hdreg.h>
/* reverse mapping from unit and fdc to drive */
#define REVDRIVE(fdc, unit) ((unit) + ((fdc) << 2))
-#define DP (&drive_params[current_drive])
-#define DRS (&drive_state[current_drive])
-#define DRWE (&write_errors[current_drive])
-#define FDCS (&fdc_state[fdc])
-
-#define UDP (&drive_params[drive])
-#define UDRS (&drive_state[drive])
-#define UDRWE (&write_errors[drive])
-#define UFDCS (&fdc_state[FDC(drive)])
-
#define PH_HEAD(floppy, head) (((((floppy)->stretch & 2) >> 1) ^ head) << 2)
#define STRETCH(floppy) ((floppy)->stretch & FD_STRETCH)
-/* read/write */
-#define COMMAND (raw_cmd->cmd[0])
-#define DR_SELECT (raw_cmd->cmd[1])
-#define TRACK (raw_cmd->cmd[2])
-#define HEAD (raw_cmd->cmd[3])
-#define SECTOR (raw_cmd->cmd[4])
-#define SIZECODE (raw_cmd->cmd[5])
-#define SECT_PER_TRACK (raw_cmd->cmd[6])
-#define GAP (raw_cmd->cmd[7])
-#define SIZECODE2 (raw_cmd->cmd[8])
+/* read/write commands */
+#define COMMAND 0
+#define DR_SELECT 1
+#define TRACK 2
+#define HEAD 3
+#define SECTOR 4
+#define SIZECODE 5
+#define SECT_PER_TRACK 6
+#define GAP 7
+#define SIZECODE2 8
#define NR_RW 9
-/* format */
-#define F_SIZECODE (raw_cmd->cmd[2])
-#define F_SECT_PER_TRACK (raw_cmd->cmd[3])
-#define F_GAP (raw_cmd->cmd[4])
-#define F_FILL (raw_cmd->cmd[5])
+/* format commands */
+#define F_SIZECODE 2
+#define F_SECT_PER_TRACK 3
+#define F_GAP 4
+#define F_FILL 5
#define NR_F 6
/*
#define MAX_REPLIES 16
static unsigned char reply_buffer[MAX_REPLIES];
static int inr; /* size of reply buffer, when called from interrupt */
-#define ST0 (reply_buffer[0])
-#define ST1 (reply_buffer[1])
-#define ST2 (reply_buffer[2])
-#define ST3 (reply_buffer[0]) /* result of GETSTATUS */
-#define R_TRACK (reply_buffer[3])
-#define R_HEAD (reply_buffer[4])
-#define R_SECTOR (reply_buffer[5])
-#define R_SIZECODE (reply_buffer[6])
+#define ST0 0
+#define ST1 1
+#define ST2 2
+#define ST3 0 /* result of GETSTATUS */
+#define R_TRACK 3
+#define R_HEAD 4
+#define R_SECTOR 5
+#define R_SIZECODE 6
#define SEL_DLY (2 * HZ / 100)
/* fdc related variables, should end up in a struct */
static struct floppy_fdc_state fdc_state[N_FDC];
-static int fdc; /* current fdc */
+static int current_fdc; /* current fdc */
static struct workqueue_struct *floppy_wq;
static unsigned char in_sector_offset; /* offset within physical sector,
* expressed in units of 512 bytes */
+static inline unsigned char fdc_inb(int fdc, int reg)
+{
+ return fd_inb(fdc_state[fdc].address + reg);
+}
+
+static inline void fdc_outb(unsigned char value, int fdc, int reg)
+{
+ fd_outb(value, fdc_state[fdc].address + reg);
+}
+
static inline bool drive_no_geom(int drive)
{
- return !current_type[drive] && !ITYPE(UDRS->fd_device);
+ return !current_type[drive] && !ITYPE(drive_state[drive].fd_device);
}
#ifndef fd_eject
static inline void debugt(const char *func, const char *msg)
{
- if (DP->flags & DEBUGT)
+ if (drive_params[current_drive].flags & DEBUGT)
pr_info("%s:%s dtime=%lu\n", func, msg, jiffies - debugtimer);
}
#else
delay = 20UL * HZ;
drive = 0;
} else
- delay = UDP->timeout;
+ delay = drive_params[drive].timeout;
mod_delayed_work(floppy_wq, &fd_timeout, delay);
- if (UDP->flags & FD_DEBUG)
+ if (drive_params[drive].flags & FD_DEBUG)
DPRINT("reschedule timeout %s\n", message);
timeout_message = message;
}
{
int fdc = FDC(drive);
- if (time_before(jiffies, UDRS->select_date + UDP->select_delay))
+ if (time_before(jiffies, drive_state[drive].select_date + drive_params[drive].select_delay))
DPRINT("WARNING disk change called early\n");
- if (!(FDCS->dor & (0x10 << UNIT(drive))) ||
- (FDCS->dor & 3) != UNIT(drive) || fdc != FDC(drive)) {
+ if (!(fdc_state[fdc].dor & (0x10 << UNIT(drive))) ||
+ (fdc_state[fdc].dor & 3) != UNIT(drive) || fdc != FDC(drive)) {
DPRINT("probing disk change on unselected drive\n");
DPRINT("drive=%d fdc=%d dor=%x\n", drive, FDC(drive),
- (unsigned int)FDCS->dor);
+ (unsigned int)fdc_state[fdc].dor);
}
- debug_dcl(UDP->flags,
+ debug_dcl(drive_params[drive].flags,
"checking disk change line for drive %d\n", drive);
- debug_dcl(UDP->flags, "jiffies=%lu\n", jiffies);
- debug_dcl(UDP->flags, "disk change line=%x\n", fd_inb(FD_DIR) & 0x80);
- debug_dcl(UDP->flags, "flags=%lx\n", UDRS->flags);
-
- if (UDP->flags & FD_BROKEN_DCL)
- return test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags);
- if ((fd_inb(FD_DIR) ^ UDP->flags) & 0x80) {
- set_bit(FD_VERIFY_BIT, &UDRS->flags);
+ debug_dcl(drive_params[drive].flags, "jiffies=%lu\n", jiffies);
+ debug_dcl(drive_params[drive].flags, "disk change line=%x\n",
+ fdc_inb(fdc, FD_DIR) & 0x80);
+ debug_dcl(drive_params[drive].flags, "flags=%lx\n",
+ drive_state[drive].flags);
+
+ if (drive_params[drive].flags & FD_BROKEN_DCL)
+ return test_bit(FD_DISK_CHANGED_BIT,
+ &drive_state[drive].flags);
+ if ((fdc_inb(fdc, FD_DIR) ^ drive_params[drive].flags) & 0x80) {
+ set_bit(FD_VERIFY_BIT, &drive_state[drive].flags);
/* verify write protection */
- if (UDRS->maxblock) /* mark it changed */
- set_bit(FD_DISK_CHANGED_BIT, &UDRS->flags);
+ if (drive_state[drive].maxblock) /* mark it changed */
+ set_bit(FD_DISK_CHANGED_BIT,
+ &drive_state[drive].flags);
/* invalidate its geometry */
- if (UDRS->keep_data >= 0) {
- if ((UDP->flags & FTD_MSG) &&
+ if (drive_state[drive].keep_data >= 0) {
+ if ((drive_params[drive].flags & FTD_MSG) &&
current_type[drive] != NULL)
DPRINT("Disk type is undefined after disk change\n");
current_type[drive] = NULL;
return 1;
} else {
- UDRS->last_checked = jiffies;
- clear_bit(FD_DISK_NEWCHANGE_BIT, &UDRS->flags);
+ drive_state[drive].last_checked = jiffies;
+ clear_bit(FD_DISK_NEWCHANGE_BIT, &drive_state[drive].flags);
}
return 0;
}
unsigned char newdor;
unsigned char olddor;
- if (FDCS->address == -1)
+ if (fdc_state[fdc].address == -1)
return -1;
- olddor = FDCS->dor;
+ olddor = fdc_state[fdc].dor;
newdor = (olddor & mask) | data;
if (newdor != olddor) {
unit = olddor & 0x3;
if (is_selected(olddor, unit) && !is_selected(newdor, unit)) {
drive = REVDRIVE(fdc, unit);
- debug_dcl(UDP->flags,
+ debug_dcl(drive_params[drive].flags,
"calling disk change from set_dor\n");
disk_change(drive);
}
- FDCS->dor = newdor;
- fd_outb(newdor, FD_DOR);
+ fdc_state[fdc].dor = newdor;
+ fdc_outb(newdor, fdc, FD_DOR);
unit = newdor & 0x3;
if (!is_selected(olddor, unit) && is_selected(newdor, unit)) {
drive = REVDRIVE(fdc, unit);
- UDRS->select_date = jiffies;
+ drive_state[drive].select_date = jiffies;
}
}
return olddor;
static void twaddle(void)
{
- if (DP->select_delay)
+ if (drive_params[current_drive].select_delay)
return;
- fd_outb(FDCS->dor & ~(0x10 << UNIT(current_drive)), FD_DOR);
- fd_outb(FDCS->dor, FD_DOR);
- DRS->select_date = jiffies;
+ fdc_outb(fdc_state[current_fdc].dor & ~(0x10 << UNIT(current_drive)),
+ current_fdc, FD_DOR);
+ fdc_outb(fdc_state[current_fdc].dor, current_fdc, FD_DOR);
+ drive_state[current_drive].select_date = jiffies;
}
/*
{
int drive;
- FDCS->spec1 = FDCS->spec2 = -1;
- FDCS->need_configure = 1;
- FDCS->perp_mode = 1;
- FDCS->rawcmd = 0;
+ fdc_state[current_fdc].spec1 = fdc_state[current_fdc].spec2 = -1;
+ fdc_state[current_fdc].need_configure = 1;
+ fdc_state[current_fdc].perp_mode = 1;
+ fdc_state[current_fdc].rawcmd = 0;
for (drive = 0; drive < N_DRIVE; drive++)
- if (FDC(drive) == fdc && (mode || UDRS->track != NEED_1_RECAL))
- UDRS->track = NEED_2_RECAL;
+ if (FDC(drive) == current_fdc &&
+ (mode || drive_state[drive].track != NEED_1_RECAL))
+ drive_state[drive].track = NEED_2_RECAL;
}
/* selects the fdc and drive, and enables the fdc's input/dma. */
static void set_fdc(int drive)
{
- unsigned int new_fdc = fdc;
+ unsigned int new_fdc = current_fdc;
if (drive >= 0 && drive < N_DRIVE) {
new_fdc = FDC(drive);
pr_info("bad fdc value\n");
return;
}
- fdc = new_fdc;
- set_dor(fdc, ~0, 8);
+ current_fdc = new_fdc;
+ set_dor(current_fdc, ~0, 8);
#if N_FDC > 1
- set_dor(1 - fdc, ~8, 0);
+ set_dor(1 - current_fdc, ~8, 0);
#endif
- if (FDCS->rawcmd == 2)
+ if (fdc_state[current_fdc].rawcmd == 2)
reset_fdc_info(1);
- if (fd_inb(FD_STATUS) != STATUS_READY)
- FDCS->reset = 1;
+ if (fdc_inb(current_fdc, FD_STATUS) != STATUS_READY)
+ fdc_state[current_fdc].reset = 1;
}
/* locks the driver */
unsigned long volatile delta;
int fdc = FDC(drive);
- if (!(FDCS->dor & (0x10 << UNIT(drive))))
+ if (!(fdc_state[fdc].dor & (0x10 << UNIT(drive))))
return;
del_timer(motor_off_timer + drive);
/* make spindle stop in a position which minimizes spinup time
* next time */
- if (UDP->rps) {
- delta = jiffies - UDRS->first_read_date + HZ -
- UDP->spindown_offset;
- delta = ((delta * UDP->rps) % HZ) / UDP->rps;
+ if (drive_params[drive].rps) {
+ delta = jiffies - drive_state[drive].first_read_date + HZ -
+ drive_params[drive].spindown_offset;
+ delta = ((delta * drive_params[drive].rps) % HZ) / drive_params[drive].rps;
motor_off_timer[drive].expires =
- jiffies + UDP->spindown - delta;
+ jiffies + drive_params[drive].spindown - delta;
}
add_timer(motor_off_timer + drive);
}
int drive;
int saved_drive;
- if (DP->select_delay)
+ if (drive_params[current_drive].select_delay)
return;
saved_drive = current_drive;
for (i = 0; i < N_DRIVE; i++) {
drive = (saved_drive + i + 1) % N_DRIVE;
- if (UDRS->fd_ref == 0 || UDP->select_delay != 0)
+ if (drive_state[drive].fd_ref == 0 || drive_params[drive].select_delay != 0)
continue; /* skip closed drives */
set_fdc(drive);
- if (!(set_dor(fdc, ~3, UNIT(drive) | (0x10 << UNIT(drive))) &
+ if (!(set_dor(current_fdc, ~3, UNIT(drive) | (0x10 << UNIT(drive))) &
(0x10 << UNIT(drive))))
/* switch the motor off again, if it was off to
* begin with */
- set_dor(fdc, ~(0x10 << UNIT(drive)), 0);
+ set_dor(current_fdc, ~(0x10 << UNIT(drive)), 0);
}
set_fdc(saved_drive);
}
* transfer */
static void fd_watchdog(void)
{
- debug_dcl(DP->flags, "calling disk change from watchdog\n");
+ debug_dcl(drive_params[current_drive].flags,
+ "calling disk change from watchdog\n");
if (disk_change(current_drive)) {
DPRINT("disk removed during i/o\n");
static int fd_wait_for_completion(unsigned long expires,
void (*function)(void))
{
- if (FDCS->reset) {
+ if (fdc_state[current_fdc].reset) {
reset_fdc(); /* do the reset during sleep to win time
* if we don't need to sleep, it's a good
* occasion anyways */
pr_cont("%x,", raw_cmd->cmd[i]);
pr_cont("\n");
cont->done(0);
- FDCS->reset = 1;
+ fdc_state[current_fdc].reset = 1;
return;
}
if (((unsigned long)raw_cmd->kernel_data) % 512) {
pr_info("non aligned address: %p\n", raw_cmd->kernel_data);
cont->done(0);
- FDCS->reset = 1;
+ fdc_state[current_fdc].reset = 1;
return;
}
f = claim_dma_lock();
#ifdef fd_dma_setup
if (fd_dma_setup(raw_cmd->kernel_data, raw_cmd->length,
(raw_cmd->flags & FD_RAW_READ) ?
- DMA_MODE_READ : DMA_MODE_WRITE, FDCS->address) < 0) {
+ DMA_MODE_READ : DMA_MODE_WRITE,
+ fdc_state[current_fdc].address) < 0) {
release_dma_lock(f);
cont->done(0);
- FDCS->reset = 1;
+ fdc_state[current_fdc].reset = 1;
return;
}
release_dma_lock(f);
DMA_MODE_READ : DMA_MODE_WRITE);
fd_set_dma_addr(raw_cmd->kernel_data);
fd_set_dma_count(raw_cmd->length);
- virtual_dma_port = FDCS->address;
+ virtual_dma_port = fdc_state[current_fdc].address;
fd_enable_dma();
release_dma_lock(f);
#endif
int status;
int counter;
- if (FDCS->reset)
+ if (fdc_state[current_fdc].reset)
return -1;
for (counter = 0; counter < 10000; counter++) {
- status = fd_inb(FD_STATUS);
+ status = fdc_inb(current_fdc, FD_STATUS);
if (status & STATUS_READY)
return status;
}
if (initialized) {
- DPRINT("Getstatus times out (%x) on fdc %d\n", status, fdc);
+ DPRINT("Getstatus times out (%x) on fdc %d\n", status, current_fdc);
show_floppy();
}
- FDCS->reset = 1;
+ fdc_state[current_fdc].reset = 1;
return -1;
}
return -1;
if (is_ready_state(status)) {
- fd_outb(byte, FD_DATA);
+ fdc_outb(byte, current_fdc, FD_DATA);
output_log[output_log_pos].data = byte;
output_log[output_log_pos].status = status;
output_log[output_log_pos].jiffies = jiffies;
output_log_pos = (output_log_pos + 1) % OLOGSIZE;
return 0;
}
- FDCS->reset = 1;
+ fdc_state[current_fdc].reset = 1;
if (initialized) {
DPRINT("Unable to send byte %x to FDC. Fdc=%x Status=%x\n",
- byte, fdc, status);
+ byte, current_fdc, status);
show_floppy();
}
return -1;
return i;
}
if (status == (STATUS_DIR | STATUS_READY | STATUS_BUSY))
- reply_buffer[i] = fd_inb(FD_DATA);
+ reply_buffer[i] = fdc_inb(current_fdc, FD_DATA);
else
break;
}
if (initialized) {
DPRINT("get result error. Fdc=%d Last status=%x Read bytes=%d\n",
- fdc, status, i);
+ current_fdc, status, i);
show_floppy();
}
- FDCS->reset = 1;
+ fdc_state[current_fdc].reset = 1;
return -1;
}
default:
DPRINT("Invalid data rate for perpendicular mode!\n");
cont->done(0);
- FDCS->reset = 1;
+ fdc_state[current_fdc].reset = 1;
/*
* convenient way to return to
* redo without too much hassle
} else
perp_mode = 0;
- if (FDCS->perp_mode == perp_mode)
+ if (fdc_state[current_fdc].perp_mode == perp_mode)
return;
- if (FDCS->version >= FDC_82077_ORIG) {
+ if (fdc_state[current_fdc].version >= FDC_82077_ORIG) {
output_byte(FD_PERPENDICULAR);
output_byte(perp_mode);
- FDCS->perp_mode = perp_mode;
+ fdc_state[current_fdc].perp_mode = perp_mode;
} else if (perp_mode) {
DPRINT("perpendicular mode not supported by this FDC.\n");
}
int hlt_max_code = 0x7f;
int hut_max_code = 0xf;
- if (FDCS->need_configure && FDCS->version >= FDC_82072A) {
+ if (fdc_state[current_fdc].need_configure &&
+ fdc_state[current_fdc].version >= FDC_82072A) {
fdc_configure();
- FDCS->need_configure = 0;
+ fdc_state[current_fdc].need_configure = 0;
}
switch (raw_cmd->rate & 0x03) {
break;
case 1:
dtr = 300;
- if (FDCS->version >= FDC_82078) {
+ if (fdc_state[current_fdc].version >= FDC_82078) {
/* chose the default rate table, not the one
* where 1 = 2 Mbps */
output_byte(FD_DRIVESPEC);
break;
}
- if (FDCS->version >= FDC_82072) {
+ if (fdc_state[current_fdc].version >= FDC_82072) {
scale_dtr = dtr;
hlt_max_code = 0x00; /* 0==256msec*dtr0/dtr (not linear!) */
hut_max_code = 0x0; /* 0==256msec*dtr0/dtr (not linear!) */
}
/* Convert step rate from microseconds to milliseconds and 4 bits */
- srt = 16 - DIV_ROUND_UP(DP->srt * scale_dtr / 1000, NOMINAL_DTR);
+ srt = 16 - DIV_ROUND_UP(drive_params[current_drive].srt * scale_dtr / 1000,
+ NOMINAL_DTR);
if (slow_floppy)
srt = srt / 4;
SUPBOUND(srt, 0xf);
INFBOUND(srt, 0);
- hlt = DIV_ROUND_UP(DP->hlt * scale_dtr / 2, NOMINAL_DTR);
+ hlt = DIV_ROUND_UP(drive_params[current_drive].hlt * scale_dtr / 2,
+ NOMINAL_DTR);
if (hlt < 0x01)
hlt = 0x01;
else if (hlt > 0x7f)
hlt = hlt_max_code;
- hut = DIV_ROUND_UP(DP->hut * scale_dtr / 16, NOMINAL_DTR);
+ hut = DIV_ROUND_UP(drive_params[current_drive].hut * scale_dtr / 16,
+ NOMINAL_DTR);
if (hut < 0x1)
hut = 0x1;
else if (hut > 0xf)
spec2 = (hlt << 1) | (use_virtual_dma & 1);
/* If these parameters did not change, just return with success */
- if (FDCS->spec1 != spec1 || FDCS->spec2 != spec2) {
+ if (fdc_state[current_fdc].spec1 != spec1 ||
+ fdc_state[current_fdc].spec2 != spec2) {
/* Go ahead and set spec1 and spec2 */
output_byte(FD_SPECIFY);
- output_byte(FDCS->spec1 = spec1);
- output_byte(FDCS->spec2 = spec2);
+ output_byte(fdc_state[current_fdc].spec1 = spec1);
+ output_byte(fdc_state[current_fdc].spec2 = spec2);
}
} /* fdc_specify */
static int fdc_dtr(void)
{
/* If data rate not already set to desired value, set it. */
- if ((raw_cmd->rate & 3) == FDCS->dtr)
+ if ((raw_cmd->rate & 3) == fdc_state[current_fdc].dtr)
return 0;
/* Set dtr */
- fd_outb(raw_cmd->rate & 3, FD_DCR);
+ fdc_outb(raw_cmd->rate & 3, current_fdc, FD_DCR);
/* TODO: some FDC/drive combinations (C&T 82C711 with TEAC 1.2MB)
* need a stabilization period of several milliseconds to be
* enforced after data rate changes before R/W operations.
* Pause 5 msec to avoid trouble. (Needs to be 2 jiffies)
*/
- FDCS->dtr = raw_cmd->rate & 3;
+ fdc_state[current_fdc].dtr = raw_cmd->rate & 3;
return fd_wait_for_completion(jiffies + 2UL * HZ / 100, floppy_ready);
} /* fdc_dtr */
static void tell_sector(void)
{
pr_cont(": track %d, head %d, sector %d, size %d",
- R_TRACK, R_HEAD, R_SECTOR, R_SIZECODE);
+ reply_buffer[R_TRACK], reply_buffer[R_HEAD],
+ reply_buffer[R_SECTOR],
+ reply_buffer[R_SIZECODE]);
} /* tell_sector */
static void print_errors(void)
{
DPRINT("");
- if (ST0 & ST0_ECE) {
+ if (reply_buffer[ST0] & ST0_ECE) {
pr_cont("Recalibrate failed!");
- } else if (ST2 & ST2_CRC) {
+ } else if (reply_buffer[ST2] & ST2_CRC) {
pr_cont("data CRC error");
tell_sector();
- } else if (ST1 & ST1_CRC) {
+ } else if (reply_buffer[ST1] & ST1_CRC) {
pr_cont("CRC error");
tell_sector();
- } else if ((ST1 & (ST1_MAM | ST1_ND)) ||
- (ST2 & ST2_MAM)) {
+ } else if ((reply_buffer[ST1] & (ST1_MAM | ST1_ND)) ||
+ (reply_buffer[ST2] & ST2_MAM)) {
if (!probing) {
pr_cont("sector not found");
tell_sector();
} else
pr_cont("probe failed...");
- } else if (ST2 & ST2_WC) { /* seek error */
+ } else if (reply_buffer[ST2] & ST2_WC) { /* seek error */
pr_cont("wrong cylinder");
- } else if (ST2 & ST2_BC) { /* cylinder marked as bad */
+ } else if (reply_buffer[ST2] & ST2_BC) { /* cylinder marked as bad */
pr_cont("bad cylinder");
} else {
pr_cont("unknown error. ST[0..2] are: 0x%x 0x%x 0x%x",
- ST0, ST1, ST2);
+ reply_buffer[ST0], reply_buffer[ST1],
+ reply_buffer[ST2]);
tell_sector();
}
pr_cont("\n");
if (inr != 7) {
DPRINT("-- FDC reply error\n");
- FDCS->reset = 1;
+ fdc_state[current_fdc].reset = 1;
return 1;
}
/* check IC to find cause of interrupt */
- switch (ST0 & ST0_INTR) {
+ switch (reply_buffer[ST0] & ST0_INTR) {
case 0x40: /* error occurred during command execution */
- if (ST1 & ST1_EOC)
+ if (reply_buffer[ST1] & ST1_EOC)
return 0; /* occurs with pseudo-DMA */
bad = 1;
- if (ST1 & ST1_WP) {
+ if (reply_buffer[ST1] & ST1_WP) {
DPRINT("Drive is write protected\n");
- clear_bit(FD_DISK_WRITABLE_BIT, &DRS->flags);
+ clear_bit(FD_DISK_WRITABLE_BIT,
+ &drive_state[current_drive].flags);
cont->done(0);
bad = 2;
- } else if (ST1 & ST1_ND) {
- set_bit(FD_NEED_TWADDLE_BIT, &DRS->flags);
- } else if (ST1 & ST1_OR) {
- if (DP->flags & FTD_MSG)
+ } else if (reply_buffer[ST1] & ST1_ND) {
+ set_bit(FD_NEED_TWADDLE_BIT,
+ &drive_state[current_drive].flags);
+ } else if (reply_buffer[ST1] & ST1_OR) {
+ if (drive_params[current_drive].flags & FTD_MSG)
DPRINT("Over/Underrun - retrying\n");
bad = 0;
- } else if (*errors >= DP->max_errors.reporting) {
+ } else if (*errors >= drive_params[current_drive].max_errors.reporting) {
print_errors();
}
- if (ST2 & ST2_WC || ST2 & ST2_BC)
+ if (reply_buffer[ST2] & ST2_WC || reply_buffer[ST2] & ST2_BC)
/* wrong cylinder => recal */
- DRS->track = NEED_2_RECAL;
+ drive_state[current_drive].track = NEED_2_RECAL;
return bad;
case 0x80: /* invalid command given */
DPRINT("Invalid FDC command given!\n");
flags |= FD_RAW_INTR;
if ((flags & FD_RAW_SPIN) && !(flags & FD_RAW_NO_MOTOR)) {
- ready_date = DRS->spinup_date + DP->spinup;
+ ready_date = drive_state[current_drive].spinup_date + drive_params[current_drive].spinup;
/* If spinup will take a long time, rerun scandrives
* again just before spinup completion. Beware that
* after scandrives, we must again wait for selection.
*/
- if (time_after(ready_date, jiffies + DP->select_delay)) {
- ready_date -= DP->select_delay;
+ if (time_after(ready_date, jiffies + drive_params[current_drive].select_delay)) {
+ ready_date -= drive_params[current_drive].select_delay;
function = floppy_start;
} else
function = setup_rw_floppy;
static void seek_interrupt(void)
{
debugt(__func__, "");
- if (inr != 2 || (ST0 & 0xF8) != 0x20) {
+ if (inr != 2 || (reply_buffer[ST0] & 0xF8) != 0x20) {
DPRINT("seek failed\n");
- DRS->track = NEED_2_RECAL;
+ drive_state[current_drive].track = NEED_2_RECAL;
cont->error();
cont->redo();
return;
}
- if (DRS->track >= 0 && DRS->track != ST1 && !blind_seek) {
- debug_dcl(DP->flags,
+ if (drive_state[current_drive].track >= 0 &&
+ drive_state[current_drive].track != reply_buffer[ST1] &&
+ !blind_seek) {
+ debug_dcl(drive_params[current_drive].flags,
"clearing NEWCHANGE flag because of effective seek\n");
- debug_dcl(DP->flags, "jiffies=%lu\n", jiffies);
- clear_bit(FD_DISK_NEWCHANGE_BIT, &DRS->flags);
+ debug_dcl(drive_params[current_drive].flags, "jiffies=%lu\n",
+ jiffies);
+ clear_bit(FD_DISK_NEWCHANGE_BIT,
+ &drive_state[current_drive].flags);
/* effective seek */
- DRS->select_date = jiffies;
+ drive_state[current_drive].select_date = jiffies;
}
- DRS->track = ST1;
+ drive_state[current_drive].track = reply_buffer[ST1];
floppy_ready();
}
static void check_wp(void)
{
- if (test_bit(FD_VERIFY_BIT, &DRS->flags)) {
+ if (test_bit(FD_VERIFY_BIT, &drive_state[current_drive].flags)) {
/* check write protection */
output_byte(FD_GETSTATUS);
output_byte(UNIT(current_drive));
if (result() != 1) {
- FDCS->reset = 1;
+ fdc_state[current_fdc].reset = 1;
return;
}
- clear_bit(FD_VERIFY_BIT, &DRS->flags);
- clear_bit(FD_NEED_TWADDLE_BIT, &DRS->flags);
- debug_dcl(DP->flags,
+ clear_bit(FD_VERIFY_BIT, &drive_state[current_drive].flags);
+ clear_bit(FD_NEED_TWADDLE_BIT,
+ &drive_state[current_drive].flags);
+ debug_dcl(drive_params[current_drive].flags,
"checking whether disk is write protected\n");
- debug_dcl(DP->flags, "wp=%x\n", ST3 & 0x40);
- if (!(ST3 & 0x40))
- set_bit(FD_DISK_WRITABLE_BIT, &DRS->flags);
+ debug_dcl(drive_params[current_drive].flags, "wp=%x\n",
+ reply_buffer[ST3] & 0x40);
+ if (!(reply_buffer[ST3] & 0x40))
+ set_bit(FD_DISK_WRITABLE_BIT,
+ &drive_state[current_drive].flags);
else
- clear_bit(FD_DISK_WRITABLE_BIT, &DRS->flags);
+ clear_bit(FD_DISK_WRITABLE_BIT,
+ &drive_state[current_drive].flags);
}
}
blind_seek = 0;
- debug_dcl(DP->flags, "calling disk change from %s\n", __func__);
+ debug_dcl(drive_params[current_drive].flags,
+ "calling disk change from %s\n", __func__);
- if (!test_bit(FD_DISK_NEWCHANGE_BIT, &DRS->flags) &&
+ if (!test_bit(FD_DISK_NEWCHANGE_BIT, &drive_state[current_drive].flags) &&
disk_change(current_drive) && (raw_cmd->flags & FD_RAW_NEED_DISK)) {
/* the media changed flag should be cleared after the seek.
* If it isn't, this means that there is really no disk in
* the drive.
*/
- set_bit(FD_DISK_CHANGED_BIT, &DRS->flags);
+ set_bit(FD_DISK_CHANGED_BIT,
+ &drive_state[current_drive].flags);
cont->done(0);
cont->redo();
return;
}
- if (DRS->track <= NEED_1_RECAL) {
+ if (drive_state[current_drive].track <= NEED_1_RECAL) {
recalibrate_floppy();
return;
- } else if (test_bit(FD_DISK_NEWCHANGE_BIT, &DRS->flags) &&
+ } else if (test_bit(FD_DISK_NEWCHANGE_BIT, &drive_state[current_drive].flags) &&
(raw_cmd->flags & FD_RAW_NEED_DISK) &&
- (DRS->track <= NO_TRACK || DRS->track == raw_cmd->track)) {
+ (drive_state[current_drive].track <= NO_TRACK || drive_state[current_drive].track == raw_cmd->track)) {
/* we seek to clear the media-changed condition. Does anybody
* know a more elegant way, which works on all drives? */
if (raw_cmd->track)
track = raw_cmd->track - 1;
else {
- if (DP->flags & FD_SILENT_DCL_CLEAR) {
- set_dor(fdc, ~(0x10 << UNIT(current_drive)), 0);
+ if (drive_params[current_drive].flags & FD_SILENT_DCL_CLEAR) {
+ set_dor(current_fdc, ~(0x10 << UNIT(current_drive)), 0);
blind_seek = 1;
raw_cmd->flags |= FD_RAW_NEED_SEEK;
}
}
} else {
check_wp();
- if (raw_cmd->track != DRS->track &&
+ if (raw_cmd->track != drive_state[current_drive].track &&
(raw_cmd->flags & FD_RAW_NEED_SEEK))
track = raw_cmd->track;
else {
{
debugt(__func__, "");
if (inr != 2)
- FDCS->reset = 1;
- else if (ST0 & ST0_ECE) {
- switch (DRS->track) {
+ fdc_state[current_fdc].reset = 1;
+ else if (reply_buffer[ST0] & ST0_ECE) {
+ switch (drive_state[current_drive].track) {
case NEED_1_RECAL:
debugt(__func__, "need 1 recal");
/* after a second recalibrate, we still haven't
* not to move at recalibration is to
* be already at track 0.) Clear the
* new change flag */
- debug_dcl(DP->flags,
+ debug_dcl(drive_params[current_drive].flags,
"clearing NEWCHANGE flag because of second recalibrate\n");
- clear_bit(FD_DISK_NEWCHANGE_BIT, &DRS->flags);
- DRS->select_date = jiffies;
+ clear_bit(FD_DISK_NEWCHANGE_BIT,
+ &drive_state[current_drive].flags);
+ drive_state[current_drive].select_date = jiffies;
/* fall through */
default:
debugt(__func__, "default");
* track 0, this might mean that we
* started beyond track 80. Try
* again. */
- DRS->track = NEED_1_RECAL;
+ drive_state[current_drive].track = NEED_1_RECAL;
break;
}
} else
- DRS->track = ST1;
+ drive_state[current_drive].track = reply_buffer[ST1];
floppy_ready();
}
release_dma_lock(f);
do_floppy = NULL;
- if (fdc >= N_FDC || FDCS->address == -1) {
+ if (current_fdc >= N_FDC || fdc_state[current_fdc].address == -1) {
/* we don't even know which FDC is the culprit */
pr_info("DOR0=%x\n", fdc_state[0].dor);
- pr_info("floppy interrupt on bizarre fdc %d\n", fdc);
+ pr_info("floppy interrupt on bizarre fdc %d\n", current_fdc);
pr_info("handler=%ps\n", handler);
is_alive(__func__, "bizarre fdc");
return IRQ_NONE;
}
- FDCS->reset = 0;
+ fdc_state[current_fdc].reset = 0;
/* We have to clear the reset flag here, because apparently on boxes
* with level triggered interrupts (PS/2, Sparc, ...), it is needed to
- * emit SENSEI's to clear the interrupt line. And FDCS->reset blocks the
- * emission of the SENSEI's.
+ * emit SENSEI's to clear the interrupt line. And fdc_state[fdc].reset
+ * blocks the emission of the SENSEI's.
* It is OK to emit floppy commands because we are in an interrupt
* handler here, and thus we have to fear no interference of other
* activity.
if (do_print)
print_result("sensei", inr);
max_sensei--;
- } while ((ST0 & 0x83) != UNIT(current_drive) &&
+ } while ((reply_buffer[ST0] & 0x83) != UNIT(current_drive) &&
inr == 2 && max_sensei);
}
if (!handler) {
- FDCS->reset = 1;
+ fdc_state[current_fdc].reset = 1;
return IRQ_NONE;
}
schedule_bh(handler);
{
debugt(__func__, "");
result(); /* get the status ready for set_fdc */
- if (FDCS->reset) {
+ if (fdc_state[current_fdc].reset) {
pr_info("reset set in interrupt, calling %ps\n", cont->error);
cont->error(); /* a reset just after a reset. BAD! */
}
unsigned long flags;
do_floppy = reset_interrupt;
- FDCS->reset = 0;
+ fdc_state[current_fdc].reset = 0;
reset_fdc_info(0);
/* Pseudo-DMA may intercept 'reset finished' interrupt. */
fd_disable_dma();
release_dma_lock(flags);
- if (FDCS->version >= FDC_82072A)
- fd_outb(0x80 | (FDCS->dtr & 3), FD_STATUS);
+ if (fdc_state[current_fdc].version >= FDC_82072A)
+ fdc_outb(0x80 | (fdc_state[current_fdc].dtr & 3),
+ current_fdc, FD_STATUS);
else {
- fd_outb(FDCS->dor & ~0x04, FD_DOR);
+ fdc_outb(fdc_state[current_fdc].dor & ~0x04, current_fdc, FD_DOR);
udelay(FD_RESET_DELAY);
- fd_outb(FDCS->dor, FD_DOR);
+ fdc_outb(fdc_state[current_fdc].dor, current_fdc, FD_DOR);
}
}
print_hex_dump(KERN_INFO, "", DUMP_PREFIX_NONE, 16, 1,
reply_buffer, resultsize, true);
- pr_info("status=%x\n", fd_inb(FD_STATUS));
+ pr_info("status=%x\n", fdc_inb(current_fdc, FD_STATUS));
pr_info("fdc_busy=%lu\n", fdc_busy);
if (do_floppy)
pr_info("do_floppy=%ps\n", do_floppy);
if (initialized)
DPRINT("floppy timeout called\n");
- FDCS->reset = 1;
+ fdc_state[current_fdc].reset = 1;
if (cont) {
cont->done(0);
cont->redo(); /* this will recall reset when needed */
mask = 0xfc;
data = UNIT(current_drive);
if (!(raw_cmd->flags & FD_RAW_NO_MOTOR)) {
- if (!(FDCS->dor & (0x10 << UNIT(current_drive)))) {
+ if (!(fdc_state[current_fdc].dor & (0x10 << UNIT(current_drive)))) {
set_debugt();
/* no read since this drive is running */
- DRS->first_read_date = 0;
+ drive_state[current_drive].first_read_date = 0;
/* note motor start time if motor is not yet running */
- DRS->spinup_date = jiffies;
+ drive_state[current_drive].spinup_date = jiffies;
data |= (0x10 << UNIT(current_drive));
}
- } else if (FDCS->dor & (0x10 << UNIT(current_drive)))
+ } else if (fdc_state[current_fdc].dor & (0x10 << UNIT(current_drive)))
mask &= ~(0x10 << UNIT(current_drive));
/* starts motor and selects floppy */
del_timer(motor_off_timer + current_drive);
- set_dor(fdc, mask, data);
+ set_dor(current_fdc, mask, data);
/* wait_for_completion also schedules reset if needed. */
- return fd_wait_for_completion(DRS->select_date + DP->select_delay,
+ return fd_wait_for_completion(drive_state[current_drive].select_date + drive_params[current_drive].select_delay,
function);
}
static void floppy_ready(void)
{
- if (FDCS->reset) {
+ if (fdc_state[current_fdc].reset) {
reset_fdc();
return;
}
if (fdc_dtr())
return;
- debug_dcl(DP->flags, "calling disk change from floppy_ready\n");
+ debug_dcl(drive_params[current_drive].flags,
+ "calling disk change from floppy_ready\n");
if (!(raw_cmd->flags & FD_RAW_NO_MOTOR) &&
- disk_change(current_drive) && !DP->select_delay)
+ disk_change(current_drive) && !drive_params[current_drive].select_delay)
twaddle(); /* this clears the dcl on certain
* drive/controller combinations */
reschedule_timeout(current_reqD, "floppy start");
scandrives();
- debug_dcl(DP->flags, "setting NEWCHANGE in floppy_start\n");
- set_bit(FD_DISK_NEWCHANGE_BIT, &DRS->flags);
+ debug_dcl(drive_params[current_drive].flags,
+ "setting NEWCHANGE in floppy_start\n");
+ set_bit(FD_DISK_NEWCHANGE_BIT, &drive_state[current_drive].flags);
floppy_ready();
}
return -EINTR;
}
- if (FDCS->reset)
+ if (fdc_state[current_fdc].reset)
command_status = FD_COMMAND_ERROR;
if (command_status == FD_COMMAND_OKAY)
ret = 0;
{
int probed_format;
- probed_format = DRS->probed_format;
+ probed_format = drive_state[current_drive].probed_format;
while (1) {
- if (probed_format >= 8 || !DP->autodetect[probed_format]) {
- DRS->probed_format = 0;
+ if (probed_format >= 8 || !drive_params[current_drive].autodetect[probed_format]) {
+ drive_state[current_drive].probed_format = 0;
return 1;
}
- if (floppy_type[DP->autodetect[probed_format]].sect) {
- DRS->probed_format = probed_format;
+ if (floppy_type[drive_params[current_drive].autodetect[probed_format]].sect) {
+ drive_state[current_drive].probed_format = probed_format;
return 0;
}
probed_format++;
int err_count;
if (probing) {
- DRS->probed_format++;
+ drive_state[current_drive].probed_format++;
if (!next_valid_format())
return;
}
err_count = ++(*errors);
- INFBOUND(DRWE->badness, err_count);
- if (err_count > DP->max_errors.abort)
+ INFBOUND(write_errors[current_drive].badness, err_count);
+ if (err_count > drive_params[current_drive].max_errors.abort)
cont->done(0);
- if (err_count > DP->max_errors.reset)
- FDCS->reset = 1;
- else if (err_count > DP->max_errors.recal)
- DRS->track = NEED_2_RECAL;
+ if (err_count > drive_params[current_drive].max_errors.reset)
+ fdc_state[current_fdc].reset = 1;
+ else if (err_count > drive_params[current_drive].max_errors.recal)
+ drive_state[current_drive].track = NEED_2_RECAL;
}
static void set_floppy(int drive)
{
- int type = ITYPE(UDRS->fd_device);
+ int type = ITYPE(drive_state[drive].fd_device);
if (type)
_floppy = floppy_type + type;
FD_RAW_NEED_DISK | FD_RAW_NEED_SEEK);
raw_cmd->rate = _floppy->rate & 0x43;
raw_cmd->cmd_count = NR_F;
- COMMAND = FM_MODE(_floppy, FD_FORMAT);
- DR_SELECT = UNIT(current_drive) + PH_HEAD(_floppy, format_req.head);
- F_SIZECODE = FD_SIZECODE(_floppy);
- F_SECT_PER_TRACK = _floppy->sect << 2 >> F_SIZECODE;
- F_GAP = _floppy->fmt_gap;
- F_FILL = FD_FILL_BYTE;
+ raw_cmd->cmd[COMMAND] = FM_MODE(_floppy, FD_FORMAT);
+ raw_cmd->cmd[DR_SELECT] = UNIT(current_drive) + PH_HEAD(_floppy, format_req.head);
+ raw_cmd->cmd[F_SIZECODE] = FD_SIZECODE(_floppy);
+ raw_cmd->cmd[F_SECT_PER_TRACK] = _floppy->sect << 2 >> raw_cmd->cmd[F_SIZECODE];
+ raw_cmd->cmd[F_GAP] = _floppy->fmt_gap;
+ raw_cmd->cmd[F_FILL] = FD_FILL_BYTE;
raw_cmd->kernel_data = floppy_track_buffer;
- raw_cmd->length = 4 * F_SECT_PER_TRACK;
+ raw_cmd->length = 4 * raw_cmd->cmd[F_SECT_PER_TRACK];
- if (!F_SECT_PER_TRACK)
+ if (!raw_cmd->cmd[F_SECT_PER_TRACK])
return;
/* allow for about 30ms for data transport per track */
- head_shift = (F_SECT_PER_TRACK + 5) / 6;
+ head_shift = (raw_cmd->cmd[F_SECT_PER_TRACK] + 5) / 6;
/* a ``cylinder'' is two tracks plus a little stepping time */
track_shift = 2 * head_shift + 3;
/* position of logical sector 1 on this track */
n = (track_shift * format_req.track + head_shift * format_req.head)
- % F_SECT_PER_TRACK;
+ % raw_cmd->cmd[F_SECT_PER_TRACK];
/* determine interleave */
il = 1;
il++;
/* initialize field */
- for (count = 0; count < F_SECT_PER_TRACK; ++count) {
+ for (count = 0; count < raw_cmd->cmd[F_SECT_PER_TRACK]; ++count) {
here[count].track = format_req.track;
here[count].head = format_req.head;
here[count].sect = 0;
- here[count].size = F_SIZECODE;
+ here[count].size = raw_cmd->cmd[F_SIZECODE];
}
/* place logical sectors */
- for (count = 1; count <= F_SECT_PER_TRACK; ++count) {
+ for (count = 1; count <= raw_cmd->cmd[F_SECT_PER_TRACK]; ++count) {
here[n].sect = count;
- n = (n + il) % F_SECT_PER_TRACK;
+ n = (n + il) % raw_cmd->cmd[F_SECT_PER_TRACK];
if (here[n].sect) { /* sector busy, find next free sector */
++n;
- if (n >= F_SECT_PER_TRACK) {
- n -= F_SECT_PER_TRACK;
+ if (n >= raw_cmd->cmd[F_SECT_PER_TRACK]) {
+ n -= raw_cmd->cmd[F_SECT_PER_TRACK];
while (here[n].sect)
++n;
}
}
}
if (_floppy->stretch & FD_SECTBASEMASK) {
- for (count = 0; count < F_SECT_PER_TRACK; count++)
+ for (count = 0; count < raw_cmd->cmd[F_SECT_PER_TRACK]; count++)
here[count].sect += FD_SECTBASE(_floppy) - 1;
}
}
set_floppy(drive);
if (!_floppy ||
- _floppy->track > DP->tracks ||
+ _floppy->track > drive_params[current_drive].tracks ||
tmp_format_req->track >= _floppy->track ||
tmp_format_req->head >= _floppy->head ||
(_floppy->sect << 2) % (1 << FD_SIZECODE(_floppy)) ||
/* maintain values for invalidation on geometry
* change */
block = current_count_sectors + blk_rq_pos(req);
- INFBOUND(DRS->maxblock, block);
+ INFBOUND(drive_state[current_drive].maxblock, block);
if (block > _floppy->sect)
- DRS->maxtrack = 1;
+ drive_state[current_drive].maxtrack = 1;
floppy_end_request(req, 0);
} else {
if (rq_data_dir(req) == WRITE) {
/* record write error information */
- DRWE->write_errors++;
- if (DRWE->write_errors == 1) {
- DRWE->first_error_sector = blk_rq_pos(req);
- DRWE->first_error_generation = DRS->generation;
+ write_errors[current_drive].write_errors++;
+ if (write_errors[current_drive].write_errors == 1) {
+ write_errors[current_drive].first_error_sector = blk_rq_pos(req);
+ write_errors[current_drive].first_error_generation = drive_state[current_drive].generation;
}
- DRWE->last_error_sector = blk_rq_pos(req);
- DRWE->last_error_generation = DRS->generation;
+ write_errors[current_drive].last_error_sector = blk_rq_pos(req);
+ write_errors[current_drive].last_error_generation = drive_state[current_drive].generation;
}
floppy_end_request(req, BLK_STS_IOERR);
}
int heads;
int nr_sectors;
- if (R_HEAD >= 2) {
+ if (reply_buffer[R_HEAD] >= 2) {
/* some Toshiba floppy controllers occasionnally seem to
* return bogus interrupts after read/write operations, which
* can be recognized by a bad head number (>= 2) */
return;
}
- if (!DRS->first_read_date)
- DRS->first_read_date = jiffies;
+ if (!drive_state[current_drive].first_read_date)
+ drive_state[current_drive].first_read_date = jiffies;
nr_sectors = 0;
- ssize = DIV_ROUND_UP(1 << SIZECODE, 4);
+ ssize = DIV_ROUND_UP(1 << raw_cmd->cmd[SIZECODE], 4);
- if (ST1 & ST1_EOC)
+ if (reply_buffer[ST1] & ST1_EOC)
eoc = 1;
else
eoc = 0;
- if (COMMAND & 0x80)
+ if (raw_cmd->cmd[COMMAND] & 0x80)
heads = 2;
else
heads = 1;
- nr_sectors = (((R_TRACK - TRACK) * heads +
- R_HEAD - HEAD) * SECT_PER_TRACK +
- R_SECTOR - SECTOR + eoc) << SIZECODE >> 2;
+ nr_sectors = (((reply_buffer[R_TRACK] - raw_cmd->cmd[TRACK]) * heads +
+ reply_buffer[R_HEAD] - raw_cmd->cmd[HEAD]) * raw_cmd->cmd[SECT_PER_TRACK] +
+ reply_buffer[R_SECTOR] - raw_cmd->cmd[SECTOR] + eoc) << raw_cmd->cmd[SIZECODE] >> 2;
if (nr_sectors / ssize >
DIV_ROUND_UP(in_sector_offset + current_count_sectors, ssize)) {
DPRINT("long rw: %x instead of %lx\n",
nr_sectors, current_count_sectors);
- pr_info("rs=%d s=%d\n", R_SECTOR, SECTOR);
- pr_info("rh=%d h=%d\n", R_HEAD, HEAD);
- pr_info("rt=%d t=%d\n", R_TRACK, TRACK);
+ pr_info("rs=%d s=%d\n", reply_buffer[R_SECTOR],
+ raw_cmd->cmd[SECTOR]);
+ pr_info("rh=%d h=%d\n", reply_buffer[R_HEAD],
+ raw_cmd->cmd[HEAD]);
+ pr_info("rt=%d t=%d\n", reply_buffer[R_TRACK],
+ raw_cmd->cmd[TRACK]);
pr_info("heads=%d eoc=%d\n", heads, eoc);
pr_info("spt=%d st=%d ss=%d\n",
- SECT_PER_TRACK, fsector_t, ssize);
+ raw_cmd->cmd[SECT_PER_TRACK], fsector_t, ssize);
pr_info("in_sector_offset=%d\n", in_sector_offset);
}
}
if (probing) {
- if (DP->flags & FTD_MSG)
+ if (drive_params[current_drive].flags & FTD_MSG)
DPRINT("Auto-detected floppy type %s in fd%d\n",
_floppy->name, current_drive);
current_type[current_drive] = _floppy;
probing = 0;
}
- if (CT(COMMAND) != FD_READ ||
+ if (CT(raw_cmd->cmd[COMMAND]) != FD_READ ||
raw_cmd->kernel_data == bio_data(current_req->bio)) {
/* transfer directly from buffer */
cont->done(1);
- } else if (CT(COMMAND) == FD_READ) {
+ } else if (CT(raw_cmd->cmd[COMMAND]) == FD_READ) {
buffer_track = raw_cmd->track;
buffer_drive = current_drive;
INFBOUND(buffer_max, nr_sectors + fsector_t);
min(max_sector, max_sector_2),
blk_rq_sectors(current_req));
- if (current_count_sectors <= 0 && CT(COMMAND) == FD_WRITE &&
+ if (current_count_sectors <= 0 && CT(raw_cmd->cmd[COMMAND]) == FD_WRITE &&
buffer_max > fsector_t + blk_rq_sectors(current_req))
current_count_sectors = min_t(int, buffer_max - fsector_t,
blk_rq_sectors(current_req));
remaining = current_count_sectors << 9;
- if (remaining > blk_rq_bytes(current_req) && CT(COMMAND) == FD_WRITE) {
+ if (remaining > blk_rq_bytes(current_req) && CT(raw_cmd->cmd[COMMAND]) == FD_WRITE) {
DPRINT("in copy buffer\n");
pr_info("current_count_sectors=%ld\n", current_count_sectors);
pr_info("remaining=%d\n", remaining >> 9);
fsector_t, buffer_min);
pr_info("current_count_sectors=%ld\n",
current_count_sectors);
- if (CT(COMMAND) == FD_READ)
+ if (CT(raw_cmd->cmd[COMMAND]) == FD_READ)
pr_info("read\n");
- if (CT(COMMAND) == FD_WRITE)
+ if (CT(raw_cmd->cmd[COMMAND]) == FD_WRITE)
pr_info("write\n");
break;
}
if (((unsigned long)buffer) % 512)
DPRINT("%p buffer not aligned\n", buffer);
- if (CT(COMMAND) == FD_READ)
+ if (CT(raw_cmd->cmd[COMMAND]) == FD_READ)
memcpy(buffer, dma_buffer, size);
else
memcpy(dma_buffer, buffer, size);
/* work around a bug in pseudo DMA
* (on some FDCs) pseudo DMA does not stop when the CPU stops
* sending data. Hence we need a different way to signal the
- * transfer length: We use SECT_PER_TRACK. Unfortunately, this
+ * transfer length: We use raw_cmd->cmd[SECT_PER_TRACK]. Unfortunately, this
* does not work with MT, hence we can only transfer one head at
* a time
*/
int hard_sectors;
int end_sector;
- if (CT(COMMAND) == FD_WRITE) {
- COMMAND &= ~0x80; /* switch off multiple track mode */
+ if (CT(raw_cmd->cmd[COMMAND]) == FD_WRITE) {
+ raw_cmd->cmd[COMMAND] &= ~0x80; /* switch off multiple track mode */
- hard_sectors = raw_cmd->length >> (7 + SIZECODE);
- end_sector = SECTOR + hard_sectors - 1;
- if (end_sector > SECT_PER_TRACK) {
+ hard_sectors = raw_cmd->length >> (7 + raw_cmd->cmd[SIZECODE]);
+ end_sector = raw_cmd->cmd[SECTOR] + hard_sectors - 1;
+ if (end_sector > raw_cmd->cmd[SECT_PER_TRACK]) {
pr_info("too many sectors %d > %d\n",
- end_sector, SECT_PER_TRACK);
+ end_sector, raw_cmd->cmd[SECT_PER_TRACK]);
return;
}
- SECT_PER_TRACK = end_sector;
- /* make sure SECT_PER_TRACK
+ raw_cmd->cmd[SECT_PER_TRACK] = end_sector;
+ /* make sure raw_cmd->cmd[SECT_PER_TRACK]
* points to end of transfer */
}
}
raw_cmd->cmd_count = NR_RW;
if (rq_data_dir(current_req) == READ) {
raw_cmd->flags |= FD_RAW_READ;
- COMMAND = FM_MODE(_floppy, FD_READ);
+ raw_cmd->cmd[COMMAND] = FM_MODE(_floppy, FD_READ);
} else if (rq_data_dir(current_req) == WRITE) {
raw_cmd->flags |= FD_RAW_WRITE;
- COMMAND = FM_MODE(_floppy, FD_WRITE);
+ raw_cmd->cmd[COMMAND] = FM_MODE(_floppy, FD_WRITE);
} else {
DPRINT("%s: unknown command\n", __func__);
return 0;
max_sector = _floppy->sect * _floppy->head;
- TRACK = (int)blk_rq_pos(current_req) / max_sector;
+ raw_cmd->cmd[TRACK] = (int)blk_rq_pos(current_req) / max_sector;
fsector_t = (int)blk_rq_pos(current_req) % max_sector;
- if (_floppy->track && TRACK >= _floppy->track) {
+ if (_floppy->track && raw_cmd->cmd[TRACK] >= _floppy->track) {
if (blk_rq_cur_sectors(current_req) & 1) {
current_count_sectors = 1;
return 1;
} else
return 0;
}
- HEAD = fsector_t / _floppy->sect;
+ raw_cmd->cmd[HEAD] = fsector_t / _floppy->sect;
if (((_floppy->stretch & (FD_SWAPSIDES | FD_SECTBASEMASK)) ||
- test_bit(FD_NEED_TWADDLE_BIT, &DRS->flags)) &&
+ test_bit(FD_NEED_TWADDLE_BIT, &drive_state[current_drive].flags)) &&
fsector_t < _floppy->sect)
max_sector = _floppy->sect;
/* 2M disks have phantom sectors on the first track */
- if ((_floppy->rate & FD_2M) && (!TRACK) && (!HEAD)) {
+ if ((_floppy->rate & FD_2M) && (!raw_cmd->cmd[TRACK]) && (!raw_cmd->cmd[HEAD])) {
max_sector = 2 * _floppy->sect / 3;
if (fsector_t >= max_sector) {
current_count_sectors =
blk_rq_sectors(current_req));
return 1;
}
- SIZECODE = 2;
+ raw_cmd->cmd[SIZECODE] = 2;
} else
- SIZECODE = FD_SIZECODE(_floppy);
+ raw_cmd->cmd[SIZECODE] = FD_SIZECODE(_floppy);
raw_cmd->rate = _floppy->rate & 0x43;
- if ((_floppy->rate & FD_2M) && (TRACK || HEAD) && raw_cmd->rate == 2)
+ if ((_floppy->rate & FD_2M) &&
+ (raw_cmd->cmd[TRACK] || raw_cmd->cmd[HEAD]) && raw_cmd->rate == 2)
raw_cmd->rate = 1;
- if (SIZECODE)
- SIZECODE2 = 0xff;
+ if (raw_cmd->cmd[SIZECODE])
+ raw_cmd->cmd[SIZECODE2] = 0xff;
else
- SIZECODE2 = 0x80;
- raw_cmd->track = TRACK << STRETCH(_floppy);
- DR_SELECT = UNIT(current_drive) + PH_HEAD(_floppy, HEAD);
- GAP = _floppy->gap;
- ssize = DIV_ROUND_UP(1 << SIZECODE, 4);
- SECT_PER_TRACK = _floppy->sect << 2 >> SIZECODE;
- SECTOR = ((fsector_t % _floppy->sect) << 2 >> SIZECODE) +
+ raw_cmd->cmd[SIZECODE2] = 0x80;
+ raw_cmd->track = raw_cmd->cmd[TRACK] << STRETCH(_floppy);
+ raw_cmd->cmd[DR_SELECT] = UNIT(current_drive) + PH_HEAD(_floppy, raw_cmd->cmd[HEAD]);
+ raw_cmd->cmd[GAP] = _floppy->gap;
+ ssize = DIV_ROUND_UP(1 << raw_cmd->cmd[SIZECODE], 4);
+ raw_cmd->cmd[SECT_PER_TRACK] = _floppy->sect << 2 >> raw_cmd->cmd[SIZECODE];
+ raw_cmd->cmd[SECTOR] = ((fsector_t % _floppy->sect) << 2 >> raw_cmd->cmd[SIZECODE]) +
FD_SECTBASE(_floppy);
/* tracksize describes the size which can be filled up with sectors
*/
tracksize = _floppy->sect - _floppy->sect % ssize;
if (tracksize < _floppy->sect) {
- SECT_PER_TRACK++;
+ raw_cmd->cmd[SECT_PER_TRACK]++;
if (tracksize <= fsector_t % _floppy->sect)
- SECTOR--;
+ raw_cmd->cmd[SECTOR]--;
/* if we are beyond tracksize, fill up using smaller sectors */
while (tracksize <= fsector_t % _floppy->sect) {
while (tracksize + ssize > _floppy->sect) {
- SIZECODE--;
+ raw_cmd->cmd[SIZECODE]--;
ssize >>= 1;
}
- SECTOR++;
- SECT_PER_TRACK++;
+ raw_cmd->cmd[SECTOR]++;
+ raw_cmd->cmd[SECT_PER_TRACK]++;
tracksize += ssize;
}
- max_sector = HEAD * _floppy->sect + tracksize;
- } else if (!TRACK && !HEAD && !(_floppy->rate & FD_2M) && probing) {
+ max_sector = raw_cmd->cmd[HEAD] * _floppy->sect + tracksize;
+ } else if (!raw_cmd->cmd[TRACK] && !raw_cmd->cmd[HEAD] && !(_floppy->rate & FD_2M) && probing) {
max_sector = _floppy->sect;
- } else if (!HEAD && CT(COMMAND) == FD_WRITE) {
+ } else if (!raw_cmd->cmd[HEAD] && CT(raw_cmd->cmd[COMMAND]) == FD_WRITE) {
/* for virtual DMA bug workaround */
max_sector = _floppy->sect;
}
(current_drive == buffer_drive) &&
(fsector_t >= buffer_min) && (fsector_t < buffer_max)) {
/* data already in track buffer */
- if (CT(COMMAND) == FD_READ) {
+ if (CT(raw_cmd->cmd[COMMAND]) == FD_READ) {
copy_buffer(1, max_sector, buffer_max);
return 1;
}
} else if (in_sector_offset || blk_rq_sectors(current_req) < ssize) {
- if (CT(COMMAND) == FD_WRITE) {
+ if (CT(raw_cmd->cmd[COMMAND]) == FD_WRITE) {
unsigned int sectors;
sectors = fsector_t + blk_rq_sectors(current_req);
}
raw_cmd->flags &= ~FD_RAW_WRITE;
raw_cmd->flags |= FD_RAW_READ;
- COMMAND = FM_MODE(_floppy, FD_READ);
+ raw_cmd->cmd[COMMAND] = FM_MODE(_floppy, FD_READ);
} else if ((unsigned long)bio_data(current_req->bio) < MAX_DMA_ADDRESS) {
unsigned long dma_limit;
int direct, indirect;
*/
if (!direct ||
(indirect * 2 > direct * 3 &&
- *errors < DP->max_errors.read_track &&
+ *errors < drive_params[current_drive].max_errors.read_track &&
((!probing ||
- (DP->read_track & (1 << DRS->probed_format)))))) {
+ (drive_params[current_drive].read_track & (1 << drive_state[current_drive].probed_format)))))) {
max_size = blk_rq_sectors(current_req);
} else {
raw_cmd->kernel_data = bio_data(current_req->bio);
}
}
- if (CT(COMMAND) == FD_READ)
+ if (CT(raw_cmd->cmd[COMMAND]) == FD_READ)
max_size = max_sector; /* unbounded */
/* claim buffer track if needed */
buffer_drive != current_drive || /* bad drive */
fsector_t > buffer_max ||
fsector_t < buffer_min ||
- ((CT(COMMAND) == FD_READ ||
+ ((CT(raw_cmd->cmd[COMMAND]) == FD_READ ||
(!in_sector_offset && blk_rq_sectors(current_req) >= ssize)) &&
max_sector > 2 * max_buffer_sectors + buffer_min &&
max_size + fsector_t > 2 * max_buffer_sectors + buffer_min)) {
raw_cmd->kernel_data = floppy_track_buffer +
((aligned_sector_t - buffer_min) << 9);
- if (CT(COMMAND) == FD_WRITE) {
+ if (CT(raw_cmd->cmd[COMMAND]) == FD_WRITE) {
/* copy write buffer to track buffer.
* if we get here, we know that the write
* is either aligned or the data already in the buffer
raw_cmd->length <<= 9;
if ((raw_cmd->length < current_count_sectors << 9) ||
(raw_cmd->kernel_data != bio_data(current_req->bio) &&
- CT(COMMAND) == FD_WRITE &&
+ CT(raw_cmd->cmd[COMMAND]) == FD_WRITE &&
(aligned_sector_t + (raw_cmd->length >> 9) > buffer_max ||
aligned_sector_t < buffer_min)) ||
- raw_cmd->length % (128 << SIZECODE) ||
+ raw_cmd->length % (128 << raw_cmd->cmd[SIZECODE]) ||
raw_cmd->length <= 0 || current_count_sectors <= 0) {
DPRINT("fractionary current count b=%lx s=%lx\n",
raw_cmd->length, current_count_sectors);
current_count_sectors);
pr_info("st=%d ast=%d mse=%d msi=%d\n",
fsector_t, aligned_sector_t, max_sector, max_size);
- pr_info("ssize=%x SIZECODE=%d\n", ssize, SIZECODE);
+ pr_info("ssize=%x SIZECODE=%d\n", ssize, raw_cmd->cmd[SIZECODE]);
pr_info("command=%x SECTOR=%d HEAD=%d, TRACK=%d\n",
- COMMAND, SECTOR, HEAD, TRACK);
+ raw_cmd->cmd[COMMAND], raw_cmd->cmd[SECTOR],
+ raw_cmd->cmd[HEAD], raw_cmd->cmd[TRACK]);
pr_info("buffer drive=%d\n", buffer_drive);
pr_info("buffer track=%d\n", buffer_track);
pr_info("buffer_min=%d\n", buffer_min);
fsector_t, buffer_min, raw_cmd->length >> 9);
pr_info("current_count_sectors=%ld\n",
current_count_sectors);
- if (CT(COMMAND) == FD_READ)
+ if (CT(raw_cmd->cmd[COMMAND]) == FD_READ)
pr_info("read\n");
- if (CT(COMMAND) == FD_WRITE)
+ if (CT(raw_cmd->cmd[COMMAND]) == FD_WRITE)
pr_info("write\n");
return 0;
}
disk_change(current_drive);
if (test_bit(current_drive, &fake_change) ||
- test_bit(FD_DISK_CHANGED_BIT, &DRS->flags)) {
+ test_bit(FD_DISK_CHANGED_BIT, &drive_state[current_drive].flags)) {
DPRINT("disk absent or changed during operation\n");
request_done(0);
goto do_request;
}
if (!_floppy) { /* Autodetection */
if (!probing) {
- DRS->probed_format = 0;
+ drive_state[current_drive].probed_format = 0;
if (next_valid_format()) {
DPRINT("no autodetectable formats\n");
_floppy = NULL;
}
}
probing = 1;
- _floppy = floppy_type + DP->autodetect[DRS->probed_format];
+ _floppy = floppy_type + drive_params[current_drive].autodetect[drive_state[current_drive].probed_format];
} else
probing = 0;
errors = &(current_req->error_count);
goto do_request;
}
- if (test_bit(FD_NEED_TWADDLE_BIT, &DRS->flags))
+ if (test_bit(FD_NEED_TWADDLE_BIT, &drive_state[current_drive].flags))
twaddle();
schedule_bh(floppy_start);
debugt(__func__, "queue fd request");
raw_cmd->track = 0;
raw_cmd->cmd_count = 0;
cont = &poll_cont;
- debug_dcl(DP->flags, "setting NEWCHANGE in poll_drive\n");
- set_bit(FD_DISK_NEWCHANGE_BIT, &DRS->flags);
+ debug_dcl(drive_params[current_drive].flags,
+ "setting NEWCHANGE in poll_drive\n");
+ set_bit(FD_DISK_NEWCHANGE_BIT, &drive_state[current_drive].flags);
return wait_til_done(floppy_ready, interruptible);
}
return -EINTR;
if (arg == FD_RESET_ALWAYS)
- FDCS->reset = 1;
- if (FDCS->reset) {
+ fdc_state[current_fdc].reset = 1;
+ if (fdc_state[current_fdc].reset) {
cont = &reset_cont;
ret = wait_til_done(reset_fdc, interruptible);
if (ret == -EINTR)
if (type)
floppy = floppy_type + type;
else {
- if (UDP->native_format)
- floppy = floppy_type + UDP->native_format;
+ if (drive_params[drive].native_format)
+ floppy = floppy_type + drive_params[drive].native_format;
else
return "(null)";
}
int ret2;
int ret;
- if (FDCS->rawcmd <= 1)
- FDCS->rawcmd = 1;
+ if (fdc_state[current_fdc].rawcmd <= 1)
+ fdc_state[current_fdc].rawcmd = 1;
for (drive = 0; drive < N_DRIVE; drive++) {
- if (FDC(drive) != fdc)
+ if (FDC(drive) != current_fdc)
continue;
if (drive == current_drive) {
- if (UDRS->fd_ref > 1) {
- FDCS->rawcmd = 2;
+ if (drive_state[drive].fd_ref > 1) {
+ fdc_state[current_fdc].rawcmd = 2;
break;
}
- } else if (UDRS->fd_ref) {
- FDCS->rawcmd = 2;
+ } else if (drive_state[drive].fd_ref) {
+ fdc_state[current_fdc].rawcmd = 2;
break;
}
}
- if (FDCS->reset)
+ if (fdc_state[current_fdc].reset)
return -EIO;
ret = raw_cmd_copyin(cmd, param, &my_raw_cmd);
raw_cmd = my_raw_cmd;
cont = &raw_cmd_cont;
ret = wait_til_done(floppy_start, true);
- debug_dcl(DP->flags, "calling disk change from raw_cmd ioctl\n");
+ debug_dcl(drive_params[current_drive].flags,
+ "calling disk change from raw_cmd ioctl\n");
- if (ret != -EINTR && FDCS->reset)
+ if (ret != -EINTR && fdc_state[current_fdc].reset)
ret = -EIO;
- DRS->track = NO_TRACK;
+ drive_state[current_drive].track = NO_TRACK;
ret2 = raw_cmd_copyout(cmd, param, my_raw_cmd);
if (!ret)
(int)g->head <= 0 ||
/* check for overflow in max_sector */
(int)(g->sect * g->head) <= 0 ||
- /* check for zero in F_SECT_PER_TRACK */
+ /* check for zero in raw_cmd->cmd[F_SECT_PER_TRACK] */
(unsigned char)((g->sect << 2) >> FD_SIZECODE(g)) == 0 ||
- g->track <= 0 || g->track > UDP->tracks >> STRETCH(g) ||
+ g->track <= 0 || g->track > drive_params[drive].tracks >> STRETCH(g) ||
/* check if reserved bits are set */
(g->stretch & ~(FD_STRETCH | FD_SWAPSIDES | FD_SECTBASEMASK)) != 0)
return -EINVAL;
current_type[drive] = &user_params[drive];
floppy_sizes[drive] = user_params[drive].size;
if (cmd == FDDEFPRM)
- DRS->keep_data = -1;
+ drive_state[current_drive].keep_data = -1;
else
- DRS->keep_data = 1;
+ drive_state[current_drive].keep_data = 1;
/* invalidation. Invalidate only when needed, i.e.
* when there are already sectors in the buffer cache
* whose number will change. This is useful, because
* mtools often changes the geometry of the disk after
* looking at the boot block */
- if (DRS->maxblock > user_params[drive].sect ||
- DRS->maxtrack ||
+ if (drive_state[current_drive].maxblock > user_params[drive].sect ||
+ drive_state[current_drive].maxtrack ||
((user_params[drive].sect ^ oldStretch) &
(FD_SWAPSIDES | FD_SECTBASEMASK)))
invalidate_drive(bdev);
unsigned long param)
{
int drive = (long)bdev->bd_disk->private_data;
- int type = ITYPE(UDRS->fd_device);
+ int type = ITYPE(drive_state[drive].fd_device);
int i;
int ret;
int size;
switch (cmd) {
case FDEJECT:
- if (UDRS->fd_ref != 1)
+ if (drive_state[drive].fd_ref != 1)
/* somebody else has this drive open */
return -EBUSY;
if (lock_fdc(drive))
* non-Sparc architectures */
ret = fd_eject(UNIT(drive));
- set_bit(FD_DISK_CHANGED_BIT, &UDRS->flags);
- set_bit(FD_VERIFY_BIT, &UDRS->flags);
+ set_bit(FD_DISK_CHANGED_BIT, &drive_state[drive].flags);
+ set_bit(FD_VERIFY_BIT, &drive_state[drive].flags);
process_fd_request();
return ret;
case FDCLRPRM:
return -EINTR;
current_type[drive] = NULL;
floppy_sizes[drive] = MAX_DISK_SIZE << 1;
- UDRS->keep_data = 0;
+ drive_state[drive].keep_data = 0;
return invalidate_drive(bdev);
case FDSETPRM:
case FDDEFPRM:
outparam = &inparam.g;
break;
case FDMSGON:
- UDP->flags |= FTD_MSG;
+ drive_params[drive].flags |= FTD_MSG;
return 0;
case FDMSGOFF:
- UDP->flags &= ~FTD_MSG;
+ drive_params[drive].flags &= ~FTD_MSG;
return 0;
case FDFMTBEG:
if (lock_fdc(drive))
return -EINTR;
if (poll_drive(true, FD_RAW_NEED_DISK) == -EINTR)
return -EINTR;
- ret = UDRS->flags;
+ ret = drive_state[drive].flags;
process_fd_request();
if (ret & FD_VERIFY)
return -ENODEV;
return -EROFS;
return 0;
case FDFMTTRK:
- if (UDRS->fd_ref != 1)
+ if (drive_state[drive].fd_ref != 1)
return -EBUSY;
return do_format(drive, &inparam.f);
case FDFMTEND:
return -EINTR;
return invalidate_drive(bdev);
case FDSETEMSGTRESH:
- UDP->max_errors.reporting = (unsigned short)(param & 0x0f);
+ drive_params[drive].max_errors.reporting = (unsigned short)(param & 0x0f);
return 0;
case FDGETMAXERRS:
- outparam = &UDP->max_errors;
+ outparam = &drive_params[drive].max_errors;
break;
case FDSETMAXERRS:
- UDP->max_errors = inparam.max_errors;
+ drive_params[drive].max_errors = inparam.max_errors;
break;
case FDGETDRVTYP:
outparam = drive_name(type, drive);
if (!valid_floppy_drive_params(inparam.dp.autodetect,
inparam.dp.native_format))
return -EINVAL;
- *UDP = inparam.dp;
+ drive_params[drive] = inparam.dp;
break;
case FDGETDRVPRM:
- outparam = UDP;
+ outparam = &drive_params[drive];
break;
case FDPOLLDRVSTAT:
if (lock_fdc(drive))
process_fd_request();
/* fall through */
case FDGETDRVSTAT:
- outparam = UDRS;
+ outparam = &drive_state[drive];
break;
case FDRESET:
return user_reset_fdc(drive, (int)param, true);
case FDGETFDCSTAT:
- outparam = UFDCS;
+ outparam = &fdc_state[FDC(drive)];
break;
case FDWERRORCLR:
- memset(UDRWE, 0, sizeof(*UDRWE));
+ memset(&write_errors[drive], 0, sizeof(write_errors[drive]));
return 0;
case FDWERRORGET:
- outparam = UDRWE;
+ outparam = &write_errors[drive];
break;
case FDRAWCMD:
if (type)
mutex_lock(&floppy_mutex);
drive = (long)bdev->bd_disk->private_data;
- type = ITYPE(UDRS->fd_device);
+ type = ITYPE(drive_state[drive].fd_device);
err = set_geometry(cmd == FDSETPRM32 ? FDSETPRM : FDDEFPRM,
&v, drive, type, bdev);
mutex_unlock(&floppy_mutex);
memset(&v, 0, sizeof(v));
mutex_lock(&floppy_mutex);
- err = get_floppy_geometry(drive, ITYPE(UDRS->fd_device), &p);
+ err = get_floppy_geometry(drive, ITYPE(drive_state[drive].fd_device),
+ &p);
if (err) {
mutex_unlock(&floppy_mutex);
return err;
if (!valid_floppy_drive_params(v.autodetect, v.native_format))
return -EINVAL;
mutex_lock(&floppy_mutex);
- UDP->cmos = v.cmos;
- UDP->max_dtr = v.max_dtr;
- UDP->hlt = v.hlt;
- UDP->hut = v.hut;
- UDP->srt = v.srt;
- UDP->spinup = v.spinup;
- UDP->spindown = v.spindown;
- UDP->spindown_offset = v.spindown_offset;
- UDP->select_delay = v.select_delay;
- UDP->rps = v.rps;
- UDP->tracks = v.tracks;
- UDP->timeout = v.timeout;
- UDP->interleave_sect = v.interleave_sect;
- UDP->max_errors = v.max_errors;
- UDP->flags = v.flags;
- UDP->read_track = v.read_track;
- memcpy(UDP->autodetect, v.autodetect, sizeof(v.autodetect));
- UDP->checkfreq = v.checkfreq;
- UDP->native_format = v.native_format;
+ drive_params[drive].cmos = v.cmos;
+ drive_params[drive].max_dtr = v.max_dtr;
+ drive_params[drive].hlt = v.hlt;
+ drive_params[drive].hut = v.hut;
+ drive_params[drive].srt = v.srt;
+ drive_params[drive].spinup = v.spinup;
+ drive_params[drive].spindown = v.spindown;
+ drive_params[drive].spindown_offset = v.spindown_offset;
+ drive_params[drive].select_delay = v.select_delay;
+ drive_params[drive].rps = v.rps;
+ drive_params[drive].tracks = v.tracks;
+ drive_params[drive].timeout = v.timeout;
+ drive_params[drive].interleave_sect = v.interleave_sect;
+ drive_params[drive].max_errors = v.max_errors;
+ drive_params[drive].flags = v.flags;
+ drive_params[drive].read_track = v.read_track;
+ memcpy(drive_params[drive].autodetect, v.autodetect,
+ sizeof(v.autodetect));
+ drive_params[drive].checkfreq = v.checkfreq;
+ drive_params[drive].native_format = v.native_format;
mutex_unlock(&floppy_mutex);
return 0;
}
memset(&v, 0, sizeof(struct compat_floppy_drive_params));
mutex_lock(&floppy_mutex);
- v.cmos = UDP->cmos;
- v.max_dtr = UDP->max_dtr;
- v.hlt = UDP->hlt;
- v.hut = UDP->hut;
- v.srt = UDP->srt;
- v.spinup = UDP->spinup;
- v.spindown = UDP->spindown;
- v.spindown_offset = UDP->spindown_offset;
- v.select_delay = UDP->select_delay;
- v.rps = UDP->rps;
- v.tracks = UDP->tracks;
- v.timeout = UDP->timeout;
- v.interleave_sect = UDP->interleave_sect;
- v.max_errors = UDP->max_errors;
- v.flags = UDP->flags;
- v.read_track = UDP->read_track;
- memcpy(v.autodetect, UDP->autodetect, sizeof(v.autodetect));
- v.checkfreq = UDP->checkfreq;
- v.native_format = UDP->native_format;
+ v.cmos = drive_params[drive].cmos;
+ v.max_dtr = drive_params[drive].max_dtr;
+ v.hlt = drive_params[drive].hlt;
+ v.hut = drive_params[drive].hut;
+ v.srt = drive_params[drive].srt;
+ v.spinup = drive_params[drive].spinup;
+ v.spindown = drive_params[drive].spindown;
+ v.spindown_offset = drive_params[drive].spindown_offset;
+ v.select_delay = drive_params[drive].select_delay;
+ v.rps = drive_params[drive].rps;
+ v.tracks = drive_params[drive].tracks;
+ v.timeout = drive_params[drive].timeout;
+ v.interleave_sect = drive_params[drive].interleave_sect;
+ v.max_errors = drive_params[drive].max_errors;
+ v.flags = drive_params[drive].flags;
+ v.read_track = drive_params[drive].read_track;
+ memcpy(v.autodetect, drive_params[drive].autodetect,
+ sizeof(v.autodetect));
+ v.checkfreq = drive_params[drive].checkfreq;
+ v.native_format = drive_params[drive].native_format;
mutex_unlock(&floppy_mutex);
if (copy_to_user(arg, &v, sizeof(struct compat_floppy_drive_params)))
goto Eintr;
process_fd_request();
}
- v.spinup_date = UDRS->spinup_date;
- v.select_date = UDRS->select_date;
- v.first_read_date = UDRS->first_read_date;
- v.probed_format = UDRS->probed_format;
- v.track = UDRS->track;
- v.maxblock = UDRS->maxblock;
- v.maxtrack = UDRS->maxtrack;
- v.generation = UDRS->generation;
- v.keep_data = UDRS->keep_data;
- v.fd_ref = UDRS->fd_ref;
- v.fd_device = UDRS->fd_device;
- v.last_checked = UDRS->last_checked;
- v.dmabuf = (uintptr_t)UDRS->dmabuf;
- v.bufblocks = UDRS->bufblocks;
+ v.spinup_date = drive_state[drive].spinup_date;
+ v.select_date = drive_state[drive].select_date;
+ v.first_read_date = drive_state[drive].first_read_date;
+ v.probed_format = drive_state[drive].probed_format;
+ v.track = drive_state[drive].track;
+ v.maxblock = drive_state[drive].maxblock;
+ v.maxtrack = drive_state[drive].maxtrack;
+ v.generation = drive_state[drive].generation;
+ v.keep_data = drive_state[drive].keep_data;
+ v.fd_ref = drive_state[drive].fd_ref;
+ v.fd_device = drive_state[drive].fd_device;
+ v.last_checked = drive_state[drive].last_checked;
+ v.dmabuf = (uintptr_t) drive_state[drive].dmabuf;
+ v.bufblocks = drive_state[drive].bufblocks;
mutex_unlock(&floppy_mutex);
if (copy_to_user(arg, &v, sizeof(struct compat_floppy_drive_struct)))
struct floppy_fdc_state v;
mutex_lock(&floppy_mutex);
- v = *UFDCS;
+ v = fdc_state[FDC(drive)];
mutex_unlock(&floppy_mutex);
memset(&v32, 0, sizeof(struct compat_floppy_fdc_state));
memset(&v32, 0, sizeof(struct compat_floppy_write_errors));
mutex_lock(&floppy_mutex);
- v = *UDRWE;
+ v = write_errors[drive];
mutex_unlock(&floppy_mutex);
v32.write_errors = v.write_errors;
v32.first_error_sector = v.first_error_sector;
/* read drive info out of physical CMOS */
drive = 0;
- if (!UDP->cmos)
- UDP->cmos = FLOPPY0_TYPE;
+ if (!drive_params[drive].cmos)
+ drive_params[drive].cmos = FLOPPY0_TYPE;
drive = 1;
- if (!UDP->cmos)
- UDP->cmos = FLOPPY1_TYPE;
+ if (!drive_params[drive].cmos)
+ drive_params[drive].cmos = FLOPPY1_TYPE;
/* FIXME: additional physical CMOS drive detection should go here */
for (drive = 0; drive < N_DRIVE; drive++) {
- unsigned int type = UDP->cmos;
+ unsigned int type = drive_params[drive].cmos;
struct floppy_drive_params *params;
const char *name = NULL;
char temparea[32];
pr_cont("%s fd%d is %s", prepend, drive, name);
}
- *UDP = *params;
+ drive_params[drive] = *params;
}
if (has_drive)
mutex_lock(&floppy_mutex);
mutex_lock(&open_lock);
- if (!UDRS->fd_ref--) {
+ if (!drive_state[drive].fd_ref--) {
DPRINT("floppy_release with fd_ref == 0");
- UDRS->fd_ref = 0;
+ drive_state[drive].fd_ref = 0;
}
- if (!UDRS->fd_ref)
+ if (!drive_state[drive].fd_ref)
opened_bdev[drive] = NULL;
mutex_unlock(&open_lock);
mutex_unlock(&floppy_mutex);
mutex_lock(&floppy_mutex);
mutex_lock(&open_lock);
- old_dev = UDRS->fd_device;
+ old_dev = drive_state[drive].fd_device;
if (opened_bdev[drive] && opened_bdev[drive] != bdev)
goto out2;
- if (!UDRS->fd_ref && (UDP->flags & FD_BROKEN_DCL)) {
- set_bit(FD_DISK_CHANGED_BIT, &UDRS->flags);
- set_bit(FD_VERIFY_BIT, &UDRS->flags);
+ if (!drive_state[drive].fd_ref && (drive_params[drive].flags & FD_BROKEN_DCL)) {
+ set_bit(FD_DISK_CHANGED_BIT, &drive_state[drive].flags);
+ set_bit(FD_VERIFY_BIT, &drive_state[drive].flags);
}
- UDRS->fd_ref++;
+ drive_state[drive].fd_ref++;
opened_bdev[drive] = bdev;
if (!floppy_track_buffer) {
/* if opening an ED drive, reserve a big buffer,
* else reserve a small one */
- if ((UDP->cmos == 6) || (UDP->cmos == 5))
+ if ((drive_params[drive].cmos == 6) || (drive_params[drive].cmos == 5))
try = 64; /* Only 48 actually useful */
else
try = 32; /* Only 24 actually useful */
}
new_dev = MINOR(bdev->bd_dev);
- UDRS->fd_device = new_dev;
+ drive_state[drive].fd_device = new_dev;
set_capacity(disks[drive], floppy_sizes[new_dev]);
if (old_dev != -1 && old_dev != new_dev) {
if (buffer_drive == drive)
buffer_track = -1;
}
- if (UFDCS->rawcmd == 1)
- UFDCS->rawcmd = 2;
+ if (fdc_state[FDC(drive)].rawcmd == 1)
+ fdc_state[FDC(drive)].rawcmd = 2;
if (!(mode & FMODE_NDELAY)) {
if (mode & (FMODE_READ|FMODE_WRITE)) {
- UDRS->last_checked = 0;
- clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags);
+ drive_state[drive].last_checked = 0;
+ clear_bit(FD_OPEN_SHOULD_FAIL_BIT,
+ &drive_state[drive].flags);
check_disk_change(bdev);
- if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags))
+ if (test_bit(FD_DISK_CHANGED_BIT, &drive_state[drive].flags))
goto out;
- if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags))
+ if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &drive_state[drive].flags))
goto out;
}
res = -EROFS;
if ((mode & FMODE_WRITE) &&
- !test_bit(FD_DISK_WRITABLE_BIT, &UDRS->flags))
+ !test_bit(FD_DISK_WRITABLE_BIT, &drive_state[drive].flags))
goto out;
}
mutex_unlock(&open_lock);
mutex_unlock(&floppy_mutex);
return 0;
out:
- UDRS->fd_ref--;
+ drive_state[drive].fd_ref--;
- if (!UDRS->fd_ref)
+ if (!drive_state[drive].fd_ref)
opened_bdev[drive] = NULL;
out2:
mutex_unlock(&open_lock);
{
int drive = (long)disk->private_data;
- if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags) ||
- test_bit(FD_VERIFY_BIT, &UDRS->flags))
+ if (test_bit(FD_DISK_CHANGED_BIT, &drive_state[drive].flags) ||
+ test_bit(FD_VERIFY_BIT, &drive_state[drive].flags))
return DISK_EVENT_MEDIA_CHANGE;
- if (time_after(jiffies, UDRS->last_checked + UDP->checkfreq)) {
+ if (time_after(jiffies, drive_state[drive].last_checked + drive_params[drive].checkfreq)) {
if (lock_fdc(drive))
return 0;
poll_drive(false, 0);
process_fd_request();
}
- if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags) ||
- test_bit(FD_VERIFY_BIT, &UDRS->flags) ||
+ if (test_bit(FD_DISK_CHANGED_BIT, &drive_state[drive].flags) ||
+ test_bit(FD_VERIFY_BIT, &drive_state[drive].flags) ||
test_bit(drive, &fake_change) ||
drive_no_geom(drive))
return DISK_EVENT_MEDIA_CHANGE;
if (bio->bi_status) {
pr_info("floppy: error %d while reading block 0\n",
bio->bi_status);
- set_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags);
+ set_bit(FD_OPEN_SHOULD_FAIL_BIT, &drive_state[drive].flags);
}
complete(&cbdata->complete);
}
int cf;
int res = 0;
- if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags) ||
- test_bit(FD_VERIFY_BIT, &UDRS->flags) ||
+ if (test_bit(FD_DISK_CHANGED_BIT, &drive_state[drive].flags) ||
+ test_bit(FD_VERIFY_BIT, &drive_state[drive].flags) ||
test_bit(drive, &fake_change) ||
drive_no_geom(drive)) {
if (WARN(atomic_read(&usage_count) == 0,
res = lock_fdc(drive);
if (res)
return res;
- cf = (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags) ||
- test_bit(FD_VERIFY_BIT, &UDRS->flags));
+ cf = (test_bit(FD_DISK_CHANGED_BIT, &drive_state[drive].flags) ||
+ test_bit(FD_VERIFY_BIT, &drive_state[drive].flags));
if (!(cf || test_bit(drive, &fake_change) || drive_no_geom(drive))) {
process_fd_request(); /*already done by another thread */
return 0;
}
- UDRS->maxblock = 0;
- UDRS->maxtrack = 0;
+ drive_state[drive].maxblock = 0;
+ drive_state[drive].maxtrack = 0;
if (buffer_drive == drive)
buffer_track = -1;
clear_bit(drive, &fake_change);
- clear_bit(FD_DISK_CHANGED_BIT, &UDRS->flags);
+ clear_bit(FD_DISK_CHANGED_BIT, &drive_state[drive].flags);
if (cf)
- UDRS->generation++;
+ drive_state[drive].generation++;
if (drive_no_geom(drive)) {
/* auto-sensing */
res = __floppy_read_block_0(opened_bdev[drive], drive);
process_fd_request();
}
}
- set_capacity(disk, floppy_sizes[UDRS->fd_device]);
+ set_capacity(disk, floppy_sizes[drive_state[drive].fd_device]);
return res;
}
int r;
output_byte(FD_DUMPREGS); /* 82072 and better know DUMPREGS */
- if (FDCS->reset)
+ if (fdc_state[current_fdc].reset)
return FDC_NONE;
r = result();
if (r <= 0x00)
return FDC_NONE; /* No FDC present ??? */
if ((r == 1) && (reply_buffer[0] == 0x80)) {
- pr_info("FDC %d is an 8272A\n", fdc);
+ pr_info("FDC %d is an 8272A\n", current_fdc);
return FDC_8272A; /* 8272a/765 don't know DUMPREGS */
}
if (r != 10) {
pr_info("FDC %d init: DUMPREGS: unexpected return of %d bytes.\n",
- fdc, r);
+ current_fdc, r);
return FDC_UNKNOWN;
}
if (!fdc_configure()) {
- pr_info("FDC %d is an 82072\n", fdc);
+ pr_info("FDC %d is an 82072\n", current_fdc);
return FDC_82072; /* 82072 doesn't know CONFIGURE */
}
if (need_more_output() == MORE_OUTPUT) {
output_byte(0);
} else {
- pr_info("FDC %d is an 82072A\n", fdc);
+ pr_info("FDC %d is an 82072A\n", current_fdc);
return FDC_82072A; /* 82072A as found on Sparcs. */
}
output_byte(FD_UNLOCK);
r = result();
if ((r == 1) && (reply_buffer[0] == 0x80)) {
- pr_info("FDC %d is a pre-1991 82077\n", fdc);
+ pr_info("FDC %d is a pre-1991 82077\n", current_fdc);
return FDC_82077_ORIG; /* Pre-1991 82077, doesn't know
* LOCK/UNLOCK */
}
if ((r != 1) || (reply_buffer[0] != 0x00)) {
pr_info("FDC %d init: UNLOCK: unexpected return of %d bytes.\n",
- fdc, r);
+ current_fdc, r);
return FDC_UNKNOWN;
}
output_byte(FD_PARTID);
r = result();
if (r != 1) {
pr_info("FDC %d init: PARTID: unexpected return of %d bytes.\n",
- fdc, r);
+ current_fdc, r);
return FDC_UNKNOWN;
}
if (reply_buffer[0] == 0x80) {
- pr_info("FDC %d is a post-1991 82077\n", fdc);
+ pr_info("FDC %d is a post-1991 82077\n", current_fdc);
return FDC_82077; /* Revised 82077AA passes all the tests */
}
switch (reply_buffer[0] >> 5) {
case 0x0:
/* Either a 82078-1 or a 82078SL running at 5Volt */
- pr_info("FDC %d is an 82078.\n", fdc);
+ pr_info("FDC %d is an 82078.\n", current_fdc);
return FDC_82078;
case 0x1:
- pr_info("FDC %d is a 44pin 82078\n", fdc);
+ pr_info("FDC %d is a 44pin 82078\n", current_fdc);
return FDC_82078;
case 0x2:
- pr_info("FDC %d is a S82078B\n", fdc);
+ pr_info("FDC %d is a S82078B\n", current_fdc);
return FDC_S82078B;
case 0x3:
- pr_info("FDC %d is a National Semiconductor PC87306\n", fdc);
+ pr_info("FDC %d is a National Semiconductor PC87306\n", current_fdc);
return FDC_87306;
default:
pr_info("FDC %d init: 82078 variant with unknown PARTID=%d.\n",
- fdc, reply_buffer[0] >> 5);
+ current_fdc, reply_buffer[0] >> 5);
return FDC_82078_UNKN;
}
} /* get_fdc_version */
if (current_drive >= 4 && !FDC2)
FDC2 = 0x370;
#endif
- DP->cmos = ints[2];
+ drive_params[current_drive].cmos = ints[2];
DPRINT("setting CMOS code to %d\n", ints[2]);
}
int drive;
drive = p->id;
- return sprintf(buf, "%X\n", UDP->cmos);
+ return sprintf(buf, "%X\n", drive_params[drive].cmos);
}
static DEVICE_ATTR(cmos, 0444, floppy_cmos_show, NULL);
int fdc;
for (fdc = 0; fdc < N_FDC; fdc++)
- if (FDCS->address != -1)
+ if (fdc_state[fdc].address != -1)
user_reset_fdc(-1, FD_RESET_ALWAYS, false);
return 0;
config_types();
for (i = 0; i < N_FDC; i++) {
- fdc = i;
- memset(FDCS, 0, sizeof(*FDCS));
- FDCS->dtr = -1;
- FDCS->dor = 0x4;
+ current_fdc = i;
+ memset(&fdc_state[current_fdc], 0, sizeof(*fdc_state));
+ fdc_state[current_fdc].dtr = -1;
+ fdc_state[current_fdc].dor = 0x4;
#if defined(__sparc__) || defined(__mc68000__)
/*sparcs/sun3x don't have a DOR reset which we can fall back on to */
#ifdef __mc68000__
if (MACH_IS_SUN3X)
#endif
- FDCS->version = FDC_82072A;
+ fdc_state[current_fdc].version = FDC_82072A;
#endif
}
fdc_state[1].address = FDC2;
#endif
- fdc = 0; /* reset fdc in case of unexpected interrupt */
+ current_fdc = 0; /* reset fdc in case of unexpected interrupt */
err = floppy_grab_irq_and_dma();
if (err) {
cancel_delayed_work(&fd_timeout);
/* initialise drive state */
for (drive = 0; drive < N_DRIVE; drive++) {
- memset(UDRS, 0, sizeof(*UDRS));
- memset(UDRWE, 0, sizeof(*UDRWE));
- set_bit(FD_DISK_NEWCHANGE_BIT, &UDRS->flags);
- set_bit(FD_DISK_CHANGED_BIT, &UDRS->flags);
- set_bit(FD_VERIFY_BIT, &UDRS->flags);
- UDRS->fd_device = -1;
+ memset(&drive_state[drive], 0, sizeof(drive_state[drive]));
+ memset(&write_errors[drive], 0, sizeof(write_errors[drive]));
+ set_bit(FD_DISK_NEWCHANGE_BIT, &drive_state[drive].flags);
+ set_bit(FD_DISK_CHANGED_BIT, &drive_state[drive].flags);
+ set_bit(FD_VERIFY_BIT, &drive_state[drive].flags);
+ drive_state[drive].fd_device = -1;
floppy_track_buffer = NULL;
max_buffer_sectors = 0;
}
msleep(10);
for (i = 0; i < N_FDC; i++) {
- fdc = i;
- FDCS->driver_version = FD_DRIVER_VERSION;
+ current_fdc = i;
+ fdc_state[current_fdc].driver_version = FD_DRIVER_VERSION;
for (unit = 0; unit < 4; unit++)
- FDCS->track[unit] = 0;
- if (FDCS->address == -1)
+ fdc_state[current_fdc].track[unit] = 0;
+ if (fdc_state[current_fdc].address == -1)
continue;
- FDCS->rawcmd = 2;
+ fdc_state[current_fdc].rawcmd = 2;
if (user_reset_fdc(-1, FD_RESET_ALWAYS, false)) {
/* free ioports reserved by floppy_grab_irq_and_dma() */
- floppy_release_regions(fdc);
- FDCS->address = -1;
- FDCS->version = FDC_NONE;
+ floppy_release_regions(current_fdc);
+ fdc_state[current_fdc].address = -1;
+ fdc_state[current_fdc].version = FDC_NONE;
continue;
}
/* Try to determine the floppy controller type */
- FDCS->version = get_fdc_version();
- if (FDCS->version == FDC_NONE) {
+ fdc_state[current_fdc].version = get_fdc_version();
+ if (fdc_state[current_fdc].version == FDC_NONE) {
/* free ioports reserved by floppy_grab_irq_and_dma() */
- floppy_release_regions(fdc);
- FDCS->address = -1;
+ floppy_release_regions(current_fdc);
+ fdc_state[current_fdc].address = -1;
continue;
}
- if (can_use_virtual_dma == 2 && FDCS->version < FDC_82072A)
+ if (can_use_virtual_dma == 2 &&
+ fdc_state[current_fdc].version < FDC_82072A)
can_use_virtual_dma = 0;
have_no_fdc = 0;
*/
user_reset_fdc(-1, FD_RESET_ALWAYS, false);
}
- fdc = 0;
+ current_fdc = 0;
cancel_delayed_work(&fd_timeout);
current_drive = 0;
initialized = true;
{
while (p != io_regions) {
p--;
- release_region(FDCS->address + p->offset, p->size);
+ release_region(fdc_state[fdc].address + p->offset, p->size);
}
}
const struct io_region *p;
for (p = io_regions; p < ARRAY_END(io_regions); p++) {
- if (!request_region(FDCS->address + p->offset,
+ if (!request_region(fdc_state[fdc].address + p->offset,
p->size, "floppy")) {
DPRINT("Floppy io-port 0x%04lx in use\n",
- FDCS->address + p->offset);
+ fdc_state[fdc].address + p->offset);
floppy_release_allocated_regions(fdc, p);
return -EBUSY;
}
}
}
- for (fdc = 0; fdc < N_FDC; fdc++) {
- if (FDCS->address != -1) {
- if (floppy_request_regions(fdc))
+ for (current_fdc = 0; current_fdc < N_FDC; current_fdc++) {
+ if (fdc_state[current_fdc].address != -1) {
+ if (floppy_request_regions(current_fdc))
goto cleanup;
}
}
- for (fdc = 0; fdc < N_FDC; fdc++) {
- if (FDCS->address != -1) {
+ for (current_fdc = 0; current_fdc < N_FDC; current_fdc++) {
+ if (fdc_state[current_fdc].address != -1) {
reset_fdc_info(1);
- fd_outb(FDCS->dor, FD_DOR);
+ fdc_outb(fdc_state[current_fdc].dor, current_fdc, FD_DOR);
}
}
- fdc = 0;
+ current_fdc = 0;
set_dor(0, ~0, 8); /* avoid immediate interrupt */
- for (fdc = 0; fdc < N_FDC; fdc++)
- if (FDCS->address != -1)
- fd_outb(FDCS->dor, FD_DOR);
+ for (current_fdc = 0; current_fdc < N_FDC; current_fdc++)
+ if (fdc_state[current_fdc].address != -1)
+ fdc_outb(fdc_state[current_fdc].dor, current_fdc, FD_DOR);
/*
* The driver will try and free resources and relies on us
* to know if they were allocated or not.
*/
- fdc = 0;
+ current_fdc = 0;
irqdma_allocated = 1;
return 0;
cleanup:
fd_free_irq();
fd_free_dma();
- while (--fdc >= 0)
- floppy_release_regions(fdc);
+ while (--current_fdc >= 0)
+ floppy_release_regions(current_fdc);
atomic_dec(&usage_count);
return -1;
}
pr_info("auxiliary floppy timer still active\n");
if (work_pending(&floppy_work))
pr_info("work still pending\n");
- old_fdc = fdc;
- for (fdc = 0; fdc < N_FDC; fdc++)
- if (FDCS->address != -1)
- floppy_release_regions(fdc);
- fdc = old_fdc;
+ old_fdc = current_fdc;
+ for (current_fdc = 0; current_fdc < N_FDC; current_fdc++)
+ if (fdc_state[current_fdc].address != -1)
+ floppy_release_regions(current_fdc);
+ current_fdc = old_fdc;
}
#ifdef MODULE
* LO_FLAGS_READ_ONLY, both are set from kernel, and losetup
* will get updated by ioctl(LOOP_GET_STATUS)
*/
- blk_mq_freeze_queue(lo->lo_queue);
+ if (lo->lo_state == Lo_bound)
+ blk_mq_freeze_queue(lo->lo_queue);
lo->use_dio = use_dio;
if (use_dio) {
blk_queue_flag_clear(QUEUE_FLAG_NOMERGES, lo->lo_queue);
blk_queue_flag_set(QUEUE_FLAG_NOMERGES, lo->lo_queue);
lo->lo_flags &= ~LO_FLAGS_DIRECT_IO;
}
- blk_mq_unfreeze_queue(lo->lo_queue);
+ if (lo->lo_state == Lo_bound)
+ blk_mq_unfreeze_queue(lo->lo_queue);
}
static int
if (arg < 512 || arg > PAGE_SIZE || !is_power_of_2(arg))
return -EINVAL;
- if (lo->lo_queue->limits.logical_block_size != arg) {
- sync_blockdev(lo->lo_device);
- kill_bdev(lo->lo_device);
- }
+ if (lo->lo_queue->limits.logical_block_size == arg)
+ return 0;
+
+ sync_blockdev(lo->lo_device);
+ kill_bdev(lo->lo_device);
blk_mq_freeze_queue(lo->lo_queue);
/* kill_bdev should have truncated all the pages */
- if (lo->lo_queue->limits.logical_block_size != arg &&
- lo->lo_device->bd_inode->i_mapping->nrpages) {
+ if (lo->lo_device->bd_inode->i_mapping->nrpages) {
err = -EAGAIN;
pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n",
__func__, lo->lo_number, lo->lo_file_name,
}
config = nbd->config;
- if (config->num_connections > 1) {
+ if (config->num_connections > 1 ||
+ (config->num_connections == 1 && nbd->tag_set.timeout)) {
dev_err_ratelimited(nbd_to_dev(nbd),
"Connection timed out, retrying (%d/%d alive)\n",
atomic_read(&config->live_connections),
config->num_connections);
/*
* Hooray we have more connections, requeue this IO, the submit
- * path will put it on a real connection.
+ * path will put it on a real connection. Or if only one
+ * connection is configured, the submit path will wait util
+ * a new connection is reconfigured or util dead timeout.
*/
- if (config->socks && config->num_connections > 1) {
+ if (config->socks) {
if (cmd->index < config->num_connections) {
struct nbd_sock *nsock =
config->socks[cmd->index];
* Userspace sets timeout=0 to disable socket disconnection,
* so just warn and reset the timer.
*/
+ struct nbd_sock *nsock = config->socks[cmd->index];
cmd->retries++;
dev_info(nbd_to_dev(nbd), "Possible stuck request %p: control (%s@%llu,%uB). Runtime %u seconds\n",
req, nbdcmd_to_ascii(req_to_nbd_cmd_type(req)),
(unsigned long long)blk_rq_pos(req) << 9,
blk_rq_bytes(req), (req->timeout / HZ) * cmd->retries);
+ mutex_lock(&nsock->tx_lock);
+ if (cmd->cookie != nsock->cookie) {
+ nbd_requeue_cmd(cmd);
+ mutex_unlock(&nsock->tx_lock);
+ mutex_unlock(&cmd->lock);
+ nbd_config_put(nbd);
+ return BLK_EH_DONE;
+ }
+ mutex_unlock(&nsock->tx_lock);
mutex_unlock(&cmd->lock);
nbd_config_put(nbd);
return BLK_EH_RESET_TIMER;
dev_err(disk_to_dev(nbd->disk), "Receive data failed (result %d)\n",
result);
/*
- * If we've disconnected or we only have 1
- * connection then we need to make sure we
+ * If we've disconnected, 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) {
+ if (nbd_disconnected(config)) {
cmd->status = BLK_STS_IOERR;
goto out;
}
if (config->num_connections <= 1) {
dev_err_ratelimited(disk_to_dev(nbd->disk),
- "Attempted send on invalid socket\n");
+ "Dead connection, failed to find a fallback\n");
return new_index;
}
#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
static DECLARE_FAULT_ATTR(null_timeout_attr);
static DECLARE_FAULT_ATTR(null_requeue_attr);
+static DECLARE_FAULT_ATTR(null_init_hctx_attr);
#endif
static inline u64 mb_per_tick(int mbps)
MODULE_PARM_DESC(home_node, "Home node for the device");
#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
+/*
+ * For more details about fault injection, please refer to
+ * Documentation/fault-injection/fault-injection.rst.
+ */
static char g_timeout_str[80];
module_param_string(timeout, g_timeout_str, sizeof(g_timeout_str), 0444);
+MODULE_PARM_DESC(timeout, "Fault injection. timeout=<interval>,<probability>,<space>,<times>");
static char g_requeue_str[80];
module_param_string(requeue, g_requeue_str, sizeof(g_requeue_str), 0444);
+MODULE_PARM_DESC(requeue, "Fault injection. requeue=<interval>,<probability>,<space>,<times>");
+
+static char g_init_hctx_str[80];
+module_param_string(init_hctx, g_init_hctx_str, sizeof(g_init_hctx_str), 0444);
+MODULE_PARM_DESC(init_hctx, "Fault injection to fail hctx init. init_hctx=<interval>,<probability>,<space>,<times>");
#endif
static int g_queue_mode = NULL_Q_MQ;
{ \
int (*apply_fn)(struct nullb_device *dev, TYPE new_value) = APPLY;\
struct nullb_device *dev = to_nullb_device(item); \
- TYPE uninitialized_var(new_value); \
+ TYPE new_value = 0; \
int ret; \
\
ret = nullb_device_##TYPE##_attr_store(&new_value, page, count);\
if (!nullb)
return 0;
+ /*
+ * Make sure that null_init_hctx() does not access nullb->queues[] past
+ * the end of that array.
+ */
+ if (submit_queues > nr_cpu_ids)
+ return -EINVAL;
set = nullb->tag_set;
blk_mq_update_nr_hw_queues(set, submit_queues);
return set->nr_hw_queues == submit_queues ? 0 : -ENOMEM;
if (tag != -1U) {
cmd = &nq->cmds[tag];
cmd->tag = tag;
+ cmd->error = BLK_STS_OK;
cmd->nq = nq;
if (nq->dev->irqmode == NULL_IRQ_TIMER) {
hrtimer_init(&cmd->timer, CLOCK_MONOTONIC,
cmd->timer.function = null_cmd_timer_expired;
}
cmd->rq = bd->rq;
+ cmd->error = BLK_STS_OK;
cmd->nq = nq;
blk_mq_start_request(bd->rq);
return null_handle_cmd(cmd, sector, nr_sectors, req_op(bd->rq));
}
-static const struct blk_mq_ops null_mq_ops = {
- .queue_rq = null_queue_rq,
- .complete = null_complete_rq,
- .timeout = null_timeout_rq,
-};
-
static void cleanup_queue(struct nullb_queue *nq)
{
kfree(nq->tag_map);
kfree(nullb->queues);
}
+static void null_exit_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
+{
+ struct nullb_queue *nq = hctx->driver_data;
+ struct nullb *nullb = nq->dev->nullb;
+
+ nullb->nr_queues--;
+}
+
+static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq)
+{
+ init_waitqueue_head(&nq->wait);
+ nq->queue_depth = nullb->queue_depth;
+ nq->dev = nullb->dev;
+}
+
+static int null_init_hctx(struct blk_mq_hw_ctx *hctx, void *driver_data,
+ unsigned int hctx_idx)
+{
+ struct nullb *nullb = hctx->queue->queuedata;
+ struct nullb_queue *nq;
+
+#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
+ if (g_init_hctx_str[0] && should_fail(&null_init_hctx_attr, 1))
+ return -EFAULT;
+#endif
+
+ nq = &nullb->queues[hctx_idx];
+ hctx->driver_data = nq;
+ null_init_queue(nullb, nq);
+ nullb->nr_queues++;
+
+ return 0;
+}
+
+static const struct blk_mq_ops null_mq_ops = {
+ .queue_rq = null_queue_rq,
+ .complete = null_complete_rq,
+ .timeout = null_timeout_rq,
+ .init_hctx = null_init_hctx,
+ .exit_hctx = null_exit_hctx,
+};
+
static void null_del_dev(struct nullb *nullb)
{
- struct nullb_device *dev = nullb->dev;
+ struct nullb_device *dev;
+
+ if (!nullb)
+ return;
+
+ dev = nullb->dev;
ida_simple_remove(&nullb_indexes, nullb->index);
.report_zones = null_report_zones,
};
-static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq)
-{
- BUG_ON(!nullb);
- BUG_ON(!nq);
-
- init_waitqueue_head(&nq->wait);
- nq->queue_depth = nullb->queue_depth;
- nq->dev = nullb->dev;
-}
-
-static void null_init_queues(struct nullb *nullb)
-{
- struct request_queue *q = nullb->q;
- struct blk_mq_hw_ctx *hctx;
- struct nullb_queue *nq;
- int i;
-
- queue_for_each_hw_ctx(q, hctx, i) {
- if (!hctx->nr_ctx || !hctx->tags)
- continue;
- nq = &nullb->queues[i];
- hctx->driver_data = nq;
- null_init_queue(nullb, nq);
- nullb->nr_queues++;
- }
-}
-
static int setup_commands(struct nullb_queue *nq)
{
struct nullb_cmd *cmd;
static int setup_queues(struct nullb *nullb)
{
- nullb->queues = kcalloc(nullb->dev->submit_queues,
- sizeof(struct nullb_queue),
+ nullb->queues = kcalloc(nr_cpu_ids, sizeof(struct nullb_queue),
GFP_KERNEL);
if (!nullb->queues)
return -ENOMEM;
return false;
if (!__null_setup_fault(&null_requeue_attr, g_requeue_str))
return false;
+ if (!__null_setup_fault(&null_init_hctx_attr, g_init_hctx_str))
+ return false;
#endif
return true;
}
goto out_cleanup_queues;
nullb->tag_set->timeout = 5 * HZ;
- nullb->q = blk_mq_init_queue(nullb->tag_set);
+ nullb->q = blk_mq_init_queue_data(nullb->tag_set, nullb);
if (IS_ERR(nullb->q)) {
rv = -ENOMEM;
goto out_cleanup_tags;
}
- null_init_queues(nullb);
} else if (dev->queue_mode == NULL_Q_BIO) {
- nullb->q = blk_alloc_queue_node(GFP_KERNEL, dev->home_node);
+ nullb->q = blk_alloc_queue(null_queue_bio, dev->home_node);
if (!nullb->q) {
rv = -ENOMEM;
goto out_cleanup_queues;
}
- blk_queue_make_request(nullb->q, null_queue_bio);
rv = init_driver_queues(nullb);
if (rv)
goto out_cleanup_blk_queue;
cleanup_queues(nullb);
out_free_nullb:
kfree(nullb);
+ dev->nullb = NULL;
out:
return rv;
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * null_blk trace related helpers.
+ *
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+#include "null_blk_trace.h"
+
+/*
+ * Helper to use for all null_blk traces to extract disk name.
+ */
+const char *nullb_trace_disk_name(struct trace_seq *p, char *name)
+{
+ const char *ret = trace_seq_buffer_ptr(p);
+
+ if (name && *name)
+ trace_seq_printf(p, "disk=%s, ", name);
+ trace_seq_putc(p, 0);
+
+ return ret;
+}
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * null_blk device driver tracepoints.
+ *
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM nullb
+
+#if !defined(_TRACE_NULLB_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_NULLB_H
+
+#include <linux/tracepoint.h>
+#include <linux/trace_seq.h>
+
+#include "null_blk.h"
+
+const char *nullb_trace_disk_name(struct trace_seq *p, char *name);
+
+#define __print_disk_name(name) nullb_trace_disk_name(p, name)
+
+#ifndef TRACE_HEADER_MULTI_READ
+static inline void __assign_disk_name(char *name, struct gendisk *disk)
+{
+ if (disk)
+ memcpy(name, disk->disk_name, DISK_NAME_LEN);
+ else
+ memset(name, 0, DISK_NAME_LEN);
+}
+#endif
+
+TRACE_EVENT(nullb_zone_op,
+ TP_PROTO(struct nullb_cmd *cmd, unsigned int zone_no,
+ unsigned int zone_cond),
+ TP_ARGS(cmd, zone_no, zone_cond),
+ TP_STRUCT__entry(
+ __array(char, disk, DISK_NAME_LEN)
+ __field(enum req_opf, op)
+ __field(unsigned int, zone_no)
+ __field(unsigned int, zone_cond)
+ ),
+ TP_fast_assign(
+ __entry->op = req_op(cmd->rq);
+ __entry->zone_no = zone_no;
+ __entry->zone_cond = zone_cond;
+ __assign_disk_name(__entry->disk, cmd->rq->rq_disk);
+ ),
+ TP_printk("%s req=%-15s zone_no=%u zone_cond=%-10s",
+ __print_disk_name(__entry->disk),
+ blk_op_str(__entry->op),
+ __entry->zone_no,
+ blk_zone_cond_str(__entry->zone_cond))
+);
+
+TRACE_EVENT(nullb_report_zones,
+ TP_PROTO(struct nullb *nullb, unsigned int nr_zones),
+ TP_ARGS(nullb, nr_zones),
+ TP_STRUCT__entry(
+ __array(char, disk, DISK_NAME_LEN)
+ __field(unsigned int, nr_zones)
+ ),
+ TP_fast_assign(
+ __entry->nr_zones = nr_zones;
+ __assign_disk_name(__entry->disk, nullb->disk);
+ ),
+ TP_printk("%s nr_zones=%u",
+ __print_disk_name(__entry->disk), __entry->nr_zones)
+);
+
+#endif /* _TRACE_NULLB_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE null_blk_trace
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
#include <linux/vmalloc.h>
#include "null_blk.h"
+#define CREATE_TRACE_POINTS
+#include "null_blk_trace.h"
+
/* zone_size in MBs to sectors. */
#define ZONE_SIZE_SHIFT 11
return 0;
nr_zones = min(nr_zones, dev->nr_zones - first_zone);
+ trace_nullb_report_zones(nullb, nr_zones);
+
for (i = 0; i < nr_zones; i++) {
/*
* Stacked DM target drivers will remap the zone information by
/* Invalid zone condition */
return BLK_STS_IOERR;
}
+
+ trace_nullb_zone_op(cmd, zno, zone->cond);
return BLK_STS_OK;
}
sector_t sector)
{
struct nullb_device *dev = cmd->nq->dev;
- struct blk_zone *zone = &dev->zones[null_zone_no(dev, sector)];
+ unsigned int zone_no = null_zone_no(dev, sector);
+ struct blk_zone *zone = &dev->zones[zone_no];
size_t i;
switch (op) {
default:
return BLK_STS_NOTSUPP;
}
+
+ trace_nullb_zone_op(cmd, zone_no, zone->cond);
return BLK_STS_OK;
}
{
struct request_queue *q = pd->disk->queue;
- blk_queue_make_request(q, pkt_make_request);
blk_queue_logical_block_size(q, CD_FRAMESIZE);
blk_queue_max_hw_sectors(q, PACKET_MAX_SECTORS);
q->queuedata = pd;
return attached_disk->fops->check_events(attached_disk, clearing);
}
+static char *pkt_devnode(struct gendisk *disk, umode_t *mode)
+{
+ return kasprintf(GFP_KERNEL, "pktcdvd/%s", disk->disk_name);
+}
+
static const struct block_device_operations pktcdvd_ops = {
.owner = THIS_MODULE,
.open = pkt_open,
.ioctl = pkt_ioctl,
.compat_ioctl = blkdev_compat_ptr_ioctl,
.check_events = pkt_check_events,
+ .devnode = pkt_devnode,
};
-static char *pktcdvd_devnode(struct gendisk *gd, umode_t *mode)
-{
- return kasprintf(GFP_KERNEL, "pktcdvd/%s", gd->disk_name);
-}
-
/*
* Set up mapping from pktcdvd device to CD-ROM device.
*/
disk->fops = &pktcdvd_ops;
disk->flags = GENHD_FL_REMOVABLE;
strcpy(disk->disk_name, pd->name);
- disk->devnode = pktcdvd_devnode;
disk->private_data = pd;
- disk->queue = blk_alloc_queue(GFP_KERNEL);
+ disk->queue = blk_alloc_queue(pkt_make_request, NUMA_NO_NODE);
if (!disk->queue)
goto out_mem2;
ps3vram_proc_init(dev);
- queue = blk_alloc_queue(GFP_KERNEL);
+ queue = blk_alloc_queue(ps3vram_make_request, NUMA_NO_NODE);
if (!queue) {
dev_err(&dev->core, "blk_alloc_queue failed\n");
error = -ENOMEM;
priv->queue = queue;
queue->queuedata = dev;
- blk_queue_make_request(queue, ps3vram_make_request);
blk_queue_max_segments(queue, BLK_MAX_SEGMENTS);
blk_queue_max_segment_size(queue, BLK_MAX_SEGMENT_SIZE);
blk_queue_max_hw_sectors(queue, BLK_SAFE_MAX_SECTORS);
return -ENOMEM;
}
- card->queue = blk_alloc_queue(GFP_KERNEL);
+ card->queue = blk_alloc_queue(rsxx_make_request, NUMA_NO_NODE);
if (!card->queue) {
dev_err(CARD_TO_DEV(card), "Failed queue alloc\n");
unregister_blkdev(card->major, DRIVER_NAME);
blk_queue_logical_block_size(card->queue, blk_size);
}
- blk_queue_make_request(card->queue, rsxx_make_request);
blk_queue_max_hw_sectors(card->queue, blkdev_max_hw_sectors);
blk_queue_physical_block_size(card->queue, RSXX_HW_BLK_SIZE);
struct dma_tracker_list {
spinlock_t lock;
int head;
- struct dma_tracker list[0];
+ struct dma_tracker list[];
};
card->biotail = &card->bio;
spin_lock_init(&card->lock);
- card->queue = blk_alloc_queue_node(GFP_KERNEL, NUMA_NO_NODE);
+ card->queue = blk_alloc_queue(mm_make_request, NUMA_NO_NODE);
if (!card->queue)
goto failed_alloc;
-
- blk_queue_make_request(card->queue, mm_make_request);
card->queue->queuedata = card;
tasklet_init(&card->tasklet, process_page, (unsigned long)card);
cap_str_10,
cap_str_2);
- set_capacity(vblk->disk, capacity);
+ set_capacity_revalidate_and_notify(vblk->disk, capacity, true);
}
static void virtblk_config_changed_work(struct work_struct *work)
{
struct virtio_blk *vblk =
container_of(work, struct virtio_blk, config_work);
- char *envp[] = { "RESIZE=1", NULL };
virtblk_update_capacity(vblk, true);
- revalidate_disk(vblk->disk);
- kobject_uevent_env(&disk_to_dev(vblk->disk)->kobj, KOBJ_CHANGE, envp);
}
static void virtblk_config_changed(struct virtio_device *vdev)
unsigned long sector_size;
unsigned int physical_sector_size;
unsigned int binfo;
- char *envp[] = { "RESIZE=1", NULL };
int err, i;
struct blkfront_ring_info *rinfo;
return;
printk(KERN_INFO "Setting capacity to %Lu\n",
sectors);
- set_capacity(info->gd, sectors);
- revalidate_disk(info->gd);
- kobject_uevent_env(&disk_to_dev(info->gd)->kobj,
- KOBJ_CHANGE, envp);
+ set_capacity_revalidate_and_notify(info->gd, sectors, true);
return;
case BLKIF_STATE_SUSPENDED:
#include <linux/sysfs.h>
#include <linux/debugfs.h>
#include <linux/cpuhotplug.h>
+#include <linux/part_stat.h>
#include "zram_drv.h"
#ifdef CONFIG_ZRAM_WRITEBACK
spin_lock_init(&zram->wb_limit_lock);
#endif
- queue = blk_alloc_queue(GFP_KERNEL);
+ queue = blk_alloc_queue(zram_make_request, NUMA_NO_NODE);
if (!queue) {
pr_err("Error allocating disk queue for device %d\n",
device_id);
goto out_free_idr;
}
- blk_queue_make_request(queue, zram_make_request);
-
/* gendisk structure */
zram->disk = alloc_disk(1);
if (!zram->disk) {
*
* If an event log is found then the securityfs files are setup to
* export it to userspace, otherwise nothing is done.
- *
- * Returns -ENODEV if the firmware has no event log or securityfs is not
- * supported.
*/
-int tpm_bios_log_setup(struct tpm_chip *chip)
+void tpm_bios_log_setup(struct tpm_chip *chip)
{
const char *name = dev_name(&chip->dev);
unsigned int cnt;
rc = tpm_read_log(chip);
if (rc < 0)
- return rc;
+ return;
log_version = rc;
cnt = 0;
cnt++;
}
- return 0;
+ return;
err:
- rc = PTR_ERR(chip->bios_dir[cnt]);
chip->bios_dir[cnt] = NULL;
tpm_bios_log_teardown(chip);
- return rc;
+ return;
}
void tpm_bios_log_teardown(struct tpm_chip *chip)
* endian format. For this reason, vtpm doesn't need conversion
* but physical tpm needs the conversion.
*/
- if (of_property_match_string(np, "compatible", "IBM,vtpm") < 0) {
+ if (of_property_match_string(np, "compatible", "IBM,vtpm") < 0 &&
+ of_property_match_string(np, "compatible", "IBM,vtpm20") < 0) {
size = be32_to_cpup((__force __be32 *)sizep);
base = be64_to_cpup((__force __be64 *)basep);
} else {
u32 converted_event_size;
u32 converted_event_type;
+ (*pos)++;
converted_event_size = do_endian_conversion(event->event_size);
v += sizeof(struct tcpa_event) + converted_event_size;
((v + sizeof(struct tcpa_event) + converted_event_size) > limit))
return NULL;
- (*pos)++;
return v;
}
size_t event_size;
void *marker;
+ (*pos)++;
event_header = log->bios_event_log;
if (v == SEQ_START_TOKEN) {
if (((v + event_size) >= limit) || (event_size == 0))
return NULL;
- (*pos)++;
return v;
}
tpm_sysfs_add_device(chip);
- rc = tpm_bios_log_setup(chip);
- if (rc != 0 && rc != -ENODEV)
- return rc;
+ tpm_bios_log_setup(chip);
tpm_add_ppi(chip);
void tpm2_shutdown(struct tpm_chip *chip, u16 shutdown_type);
unsigned long tpm2_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal);
int tpm2_probe(struct tpm_chip *chip);
+int tpm2_get_cc_attrs_tbl(struct tpm_chip *chip);
int tpm2_find_cc(struct tpm_chip *chip, u32 cc);
int tpm2_init_space(struct tpm_space *space);
void tpm2_del_space(struct tpm_chip *chip, struct tpm_space *space);
int tpm2_commit_space(struct tpm_chip *chip, struct tpm_space *space, void *buf,
size_t *bufsiz);
-int tpm_bios_log_setup(struct tpm_chip *chip);
+void tpm_bios_log_setup(struct tpm_chip *chip);
void tpm_bios_log_teardown(struct tpm_chip *chip);
int tpm_dev_common_init(void);
void tpm_dev_common_exit(void);
return rc;
}
-static int tpm2_get_cc_attrs_tbl(struct tpm_chip *chip)
+int tpm2_get_cc_attrs_tbl(struct tpm_chip *chip)
{
struct tpm_buf buf;
u32 nr_commands;
static const struct vio_device_id tpm_ibmvtpm_device_table[] = {
{ "IBM,vtpm", "IBM,vtpm"},
+ { "IBM,vtpm", "IBM,vtpm20"},
{ "", "" }
};
MODULE_DEVICE_TABLE(vio, tpm_ibmvtpm_device_table);
*/
while ((crq = ibmvtpm_crq_get_next(ibmvtpm)) != NULL) {
ibmvtpm_crq_process(crq, ibmvtpm);
+ wake_up_interruptible(&ibmvtpm->crq_queue.wq);
crq->valid = 0;
smp_wmb();
}
}
crq_q->num_entry = CRQ_RES_BUF_SIZE / sizeof(*crq_q->crq_addr);
+ init_waitqueue_head(&crq_q->wq);
ibmvtpm->crq_dma_handle = dma_map_single(dev, crq_q->crq_addr,
CRQ_RES_BUF_SIZE,
DMA_BIDIRECTIONAL);
if (rc)
goto init_irq_cleanup;
+ if (!strcmp(id->compat, "IBM,vtpm20")) {
+ chip->flags |= TPM_CHIP_FLAG_TPM2;
+ rc = tpm2_get_cc_attrs_tbl(chip);
+ if (rc)
+ goto init_irq_cleanup;
+ }
+
+ if (!wait_event_timeout(ibmvtpm->crq_queue.wq,
+ ibmvtpm->rtce_buf != NULL,
+ HZ)) {
+ dev_err(dev, "CRQ response timed out\n");
+ goto init_irq_cleanup;
+ }
+
return tpm_chip_register(chip);
init_irq_cleanup:
do {
struct ibmvtpm_crq *crq_addr;
u32 index;
u32 num_entry;
+ wait_queue_head_t wq;
};
struct ibmvtpm_dev {
if (cr50_needs_waking(cr50_phy)) {
/* Assert CS, wait 1 msec, deassert CS */
- struct spi_transfer spi_cs_wake = { .delay_usecs = 1000 };
+ struct spi_transfer spi_cs_wake = {
+ .delay = {
+ .value = 1000,
+ .unit = SPI_DELAY_UNIT_USECS
+ }
+ };
spi_sync_transfer(phy->spi_device, &spi_cs_wake, 1);
/* Wait for it to fully wake */
spi_xfer.cs_change = 0;
spi_xfer.len = transfer_len;
- spi_xfer.delay_usecs = 5;
+ spi_xfer.delay.value = 5;
+ spi_xfer.delay.unit = SPI_DELAY_UNIT_USECS;
if (in) {
spi_xfer.tx_buf = NULL;
{
struct i3c_device_info devinfo;
const struct i3c_device_id *id;
+ u16 manuf, part, ext_info;
+ bool rndpid;
i3c_device_get_info(i3cdev, &devinfo);
- /*
- * The lower 32bits of the provisional ID is just filled with a random
- * value, try to match using DCR info.
- */
- if (!I3C_PID_RND_LOWER_32BITS(devinfo.pid)) {
- u16 manuf = I3C_PID_MANUF_ID(devinfo.pid);
- u16 part = I3C_PID_PART_ID(devinfo.pid);
- u16 ext_info = I3C_PID_EXTRA_INFO(devinfo.pid);
-
- /* First try to match by manufacturer/part ID. */
- for (id = id_table; id->match_flags != 0; id++) {
- if ((id->match_flags & I3C_MATCH_MANUF_AND_PART) !=
- I3C_MATCH_MANUF_AND_PART)
- continue;
-
- if (manuf != id->manuf_id || part != id->part_id)
- continue;
-
- if ((id->match_flags & I3C_MATCH_EXTRA_INFO) &&
- ext_info != id->extra_info)
- continue;
-
- return id;
- }
- }
+ manuf = I3C_PID_MANUF_ID(devinfo.pid);
+ part = I3C_PID_PART_ID(devinfo.pid);
+ ext_info = I3C_PID_EXTRA_INFO(devinfo.pid);
+ rndpid = I3C_PID_RND_LOWER_32BITS(devinfo.pid);
- /* Fallback to DCR match. */
for (id = id_table; id->match_flags != 0; id++) {
if ((id->match_flags & I3C_MATCH_DCR) &&
- id->dcr == devinfo.dcr)
- return id;
+ id->dcr != devinfo.dcr)
+ continue;
+
+ if ((id->match_flags & I3C_MATCH_MANUF) &&
+ id->manuf_id != manuf)
+ continue;
+
+ if ((id->match_flags & I3C_MATCH_PART) &&
+ (rndpid || id->part_id != part))
+ continue;
+
+ if ((id->match_flags & I3C_MATCH_EXTRA_INFO) &&
+ (rndpid || id->extra_info != ext_info))
+ continue;
+
+ return id;
}
return NULL;
}
static DEVICE_ATTR_RO(hdrcap);
+static ssize_t modalias_show(struct device *dev,
+ struct device_attribute *da, char *buf)
+{
+ struct i3c_device *i3c = dev_to_i3cdev(dev);
+ struct i3c_device_info devinfo;
+ u16 manuf, part, ext;
+
+ i3c_device_get_info(i3c, &devinfo);
+ manuf = I3C_PID_MANUF_ID(devinfo.pid);
+ part = I3C_PID_PART_ID(devinfo.pid);
+ ext = I3C_PID_EXTRA_INFO(devinfo.pid);
+
+ if (I3C_PID_RND_LOWER_32BITS(devinfo.pid))
+ return sprintf(buf, "i3c:dcr%02Xmanuf%04X", devinfo.dcr,
+ manuf);
+
+ return sprintf(buf, "i3c:dcr%02Xmanuf%04Xpart%04Xext%04X",
+ devinfo.dcr, manuf, part, ext);
+}
+static DEVICE_ATTR_RO(modalias);
+
static struct attribute *i3c_device_attrs[] = {
&dev_attr_bcr.attr,
&dev_attr_dcr.attr,
&dev_attr_pid.attr,
&dev_attr_dynamic_address.attr,
&dev_attr_hdrcap.attr,
+ &dev_attr_modalias.attr,
NULL,
};
ATTRIBUTE_GROUPS(i3c_device);
devinfo.dcr, manuf);
return add_uevent_var(env,
- "MODALIAS=i3c:dcr%02Xmanuf%04Xpart%04xext%04x",
+ "MODALIAS=i3c:dcr%02Xmanuf%04Xpart%04Xext%04X",
devinfo.dcr, manuf, part, ext);
}
* DEFSLVS command.
*/
if (boardinfo->base.flags & I2C_CLIENT_TEN) {
- dev_err(&master->dev, "I2C device with 10 bit address not supported.");
+ dev_err(dev, "I2C device with 10 bit address not supported.");
return -ENOTSUPP;
}
* correctly even if one or more i2c devices are not registered.
*/
i3c_bus_for_each_i2cdev(&master->bus, i2cdev)
- i2cdev->dev = i2c_new_device(adap, &i2cdev->boardinfo->base);
+ i2cdev->dev = i2c_new_client_device(adap, &i2cdev->boardinfo->base);
return 0;
}
struct completion comp;
int ret;
unsigned int ncmds;
- struct dw_i3c_cmd cmds[0];
+ struct dw_i3c_cmd cmds[];
};
struct dw_i3c_master {
struct completion comp;
int ret;
unsigned int ncmds;
- struct cdns_i3c_cmd cmds[0];
+ struct cdns_i3c_cmd cmds[];
};
struct cdns_i3c_data {
goto err_dev;
}
- tqueue = blk_alloc_queue_node(GFP_KERNEL, dev->q->node);
+ tqueue = blk_alloc_queue(tt->make_rq, dev->q->node);
if (!tqueue) {
ret = -ENOMEM;
goto err_disk;
}
- blk_queue_make_request(tqueue, tt->make_rq);
strlcpy(tdisk->disk_name, create->tgtname, sizeof(tdisk->disk_name));
tdisk->flags = GENHD_FL_EXT_DEVT;
active = 0;
up(&rlun->wr_sem);
}
- sz += snprintf(page + sz, PAGE_SIZE - sz,
+ sz += scnprintf(page + sz, PAGE_SIZE - sz,
"pblk: pos:%d, ch:%d, lun:%d - %d\n",
i,
rlun->bppa.a.ch,
struct nvm_addrf_12 *ppaf = (struct nvm_addrf_12 *)&pblk->addrf;
struct nvm_addrf_12 *gppaf = (struct nvm_addrf_12 *)&geo->addrf;
- sz = snprintf(page, PAGE_SIZE,
+ sz = scnprintf(page, PAGE_SIZE,
"g:(b:%d)blk:%d/%d,pg:%d/%d,lun:%d/%d,ch:%d/%d,pl:%d/%d,sec:%d/%d\n",
pblk->addrf_len,
ppaf->blk_offset, ppaf->blk_len,
ppaf->pln_offset, ppaf->pln_len,
ppaf->sec_offset, ppaf->sec_len);
- sz += snprintf(page + sz, PAGE_SIZE - sz,
+ sz += scnprintf(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",
gppaf->blk_offset, gppaf->blk_len,
gppaf->pg_offset, gppaf->pg_len,
struct nvm_addrf *ppaf = &pblk->addrf;
struct nvm_addrf *gppaf = &geo->addrf;
- sz = snprintf(page, PAGE_SIZE,
+ sz = scnprintf(page, PAGE_SIZE,
"pblk:(s:%d)ch:%d/%d,lun:%d/%d,chk:%d/%d/sec:%d/%d\n",
pblk->addrf_len,
ppaf->ch_offset, ppaf->ch_len,
ppaf->chk_offset, ppaf->chk_len,
ppaf->sec_offset, ppaf->sec_len);
- sz += snprintf(page + sz, PAGE_SIZE - sz,
+ sz += scnprintf(page + sz, PAGE_SIZE - sz,
"device:ch:%d/%d,lun:%d/%d,chk:%d/%d,sec:%d/%d\n",
gppaf->ch_offset, gppaf->ch_len,
gppaf->lun_offset, gppaf->lun_len,
pblk_err(pblk, "corrupted free line list:%d/%d\n",
nr_free_lines, free_line_cnt);
- sz = snprintf(page, PAGE_SIZE - sz,
+ sz = scnprintf(page, PAGE_SIZE - sz,
"line: nluns:%d, nblks:%d, nsecs:%d\n",
geo->all_luns, lm->blk_per_line, lm->sec_per_line);
- sz += snprintf(page + sz, PAGE_SIZE - sz,
+ sz += scnprintf(page + sz, PAGE_SIZE - sz,
"lines:d:%d,l:%d-f:%d,m:%d/%d,c:%d,b:%d,co:%d(d:%d,l:%d)t:%d\n",
cur_data, cur_log,
nr_free_lines,
d_line_cnt, l_line_cnt,
l_mg->nr_lines);
- sz += snprintf(page + sz, PAGE_SIZE - sz,
+ sz += scnprintf(page + sz, PAGE_SIZE - sz,
"GC: full:%d, high:%d, mid:%d, low:%d, empty:%d, werr: %d, queue:%d\n",
gc_full, gc_high, gc_mid, gc_low, gc_empty, gc_werr,
atomic_read(&pblk->gc.read_inflight_gc));
- sz += snprintf(page + sz, PAGE_SIZE - sz,
+ sz += scnprintf(page + sz, PAGE_SIZE - sz,
"data (%d) cur:%d, left:%d, vsc:%d, s:%d, map:%d/%d (%d)\n",
cur_data, cur_sec, msecs, vsc, sec_in_line,
map_weight, lm->sec_per_line,
struct pblk_line_meta *lm = &pblk->lm;
ssize_t sz = 0;
- sz = snprintf(page, PAGE_SIZE - sz,
+ sz = scnprintf(page, PAGE_SIZE - sz,
"smeta - len:%d, secs:%d\n",
lm->smeta_len, lm->smeta_sec);
- sz += snprintf(page + sz, PAGE_SIZE - sz,
+ sz += scnprintf(page + sz, PAGE_SIZE - sz,
"emeta - len:%d, sec:%d, bb_start:%d\n",
lm->emeta_len[0], lm->emeta_sec[0],
lm->emeta_bb);
- sz += snprintf(page + sz, PAGE_SIZE - sz,
+ sz += scnprintf(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,
+ sz += scnprintf(page + sz, PAGE_SIZE - sz,
"blk_line:%d, sec_line:%d, sec_blk:%d\n",
lm->blk_per_line,
lm->sec_per_line,
{
int sz;
- sz = snprintf(page, PAGE_SIZE,
+ sz = scnprintf(page, PAGE_SIZE,
"user:%lld gc:%lld pad:%lld WA:",
user, gc, pad);
if (!user) {
- sz += snprintf(page + sz, PAGE_SIZE - sz, "NaN\n");
+ sz += scnprintf(page + sz, PAGE_SIZE - sz, "NaN\n");
} else {
u64 wa_int;
u32 wa_frac;
wa_int = div64_u64(wa_int, user);
wa_int = div_u64_rem(wa_int, 100000, &wa_frac);
- sz += snprintf(page + sz, PAGE_SIZE - sz, "%llu.%05u\n",
+ sz += scnprintf(page + sz, PAGE_SIZE - sz, "%llu.%05u\n",
wa_int, wa_frac);
}
total = atomic64_read(&pblk->nr_flush) - pblk->nr_flush_rst;
if (!total) {
for (i = 0; i < (buckets + 1); i++)
- sz += snprintf(page + sz, PAGE_SIZE - sz,
+ sz += scnprintf(page + sz, PAGE_SIZE - sz,
"%d:0 ", i);
- sz += snprintf(page + sz, PAGE_SIZE - sz, "\n");
+ sz += scnprintf(page + sz, PAGE_SIZE - sz, "\n");
return sz;
}
for (i = 0; i < buckets; i++)
total_buckets += atomic64_read(&pblk->pad_dist[i]);
- sz += snprintf(page + sz, PAGE_SIZE - sz, "0:%lld%% ",
+ sz += scnprintf(page + sz, PAGE_SIZE - sz, "0:%lld%% ",
bucket_percentage(total - total_buckets, total));
for (i = 0; i < buckets; i++) {
p = bucket_percentage(atomic64_read(&pblk->pad_dist[i]),
total);
- sz += snprintf(page + sz, PAGE_SIZE - sz, "%d:%lld%% ",
+ sz += scnprintf(page + sz, PAGE_SIZE - sz, "%d:%lld%% ",
i + 1, p);
}
- sz += snprintf(page + sz, PAGE_SIZE - sz, "\n");
+ sz += scnprintf(page + sz, PAGE_SIZE - sz, "\n");
return sz;
}
#define insert_lock(s, b) ((b)->level <= (s)->lock)
-/*
- * These macros are for recursing down the btree - they handle the details of
- * locking and looking up nodes in the cache for you. They're best treated as
- * mere syntax when reading code that uses them.
- *
- * op->lock determines whether we take a read or a write lock at a given depth.
- * If you've got a read lock and find that you need a write lock (i.e. you're
- * going to have to split), set op->lock and return -EINTR; btree_root() will
- * call you again and you'll have the correct lock.
- */
-
-/**
- * btree - recurse down the btree on a specified key
- * @fn: function to call, which will be passed the child node
- * @key: key to recurse on
- * @b: parent btree node
- * @op: pointer to struct btree_op
- */
-#define btree(fn, key, b, op, ...) \
-({ \
- int _r, l = (b)->level - 1; \
- bool _w = l <= (op)->lock; \
- struct btree *_child = bch_btree_node_get((b)->c, op, key, l, \
- _w, b); \
- if (!IS_ERR(_child)) { \
- _r = bch_btree_ ## fn(_child, op, ##__VA_ARGS__); \
- rw_unlock(_w, _child); \
- } else \
- _r = PTR_ERR(_child); \
- _r; \
-})
-
-/**
- * btree_root - call a function on the root of the btree
- * @fn: function to call, which will be passed the child node
- * @c: cache set
- * @op: pointer to struct btree_op
- */
-#define btree_root(fn, c, op, ...) \
-({ \
- int _r = -EINTR; \
- do { \
- struct btree *_b = (c)->root; \
- bool _w = insert_lock(op, _b); \
- rw_lock(_w, _b, _b->level); \
- if (_b == (c)->root && \
- _w == insert_lock(op, _b)) { \
- _r = bch_btree_ ## fn(_b, op, ##__VA_ARGS__); \
- } \
- rw_unlock(_w, _b); \
- bch_cannibalize_unlock(c); \
- if (_r == -EINTR) \
- schedule(); \
- } while (_r == -EINTR); \
- \
- finish_wait(&(c)->btree_cache_wait, &(op)->wait); \
- _r; \
-})
static inline struct bset *write_block(struct btree *b)
{
/* if CACHE_SET_IO_DISABLE set, gc thread should stop too */
do {
- ret = btree_root(gc_root, c, &op, &writes, &stats);
+ ret = bcache_btree_root(gc_root, c, &op, &writes, &stats);
closure_sync(&writes);
cond_resched();
}
if (p)
- ret = btree(check_recurse, p, b, op);
+ ret = bcache_btree(check_recurse, p, b, op);
p = k;
} while (p && !ret);
return ret;
}
+
+static int bch_btree_check_thread(void *arg)
+{
+ int ret;
+ struct btree_check_info *info = arg;
+ struct btree_check_state *check_state = info->state;
+ struct cache_set *c = check_state->c;
+ struct btree_iter iter;
+ struct bkey *k, *p;
+ int cur_idx, prev_idx, skip_nr;
+ int i, n;
+
+ k = p = NULL;
+ i = n = 0;
+ cur_idx = prev_idx = 0;
+ ret = 0;
+
+ /* root node keys are checked before thread created */
+ bch_btree_iter_init(&c->root->keys, &iter, NULL);
+ k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad);
+ BUG_ON(!k);
+
+ p = k;
+ while (k) {
+ /*
+ * Fetch a root node key index, skip the keys which
+ * should be fetched by other threads, then check the
+ * sub-tree indexed by the fetched key.
+ */
+ spin_lock(&check_state->idx_lock);
+ cur_idx = check_state->key_idx;
+ check_state->key_idx++;
+ spin_unlock(&check_state->idx_lock);
+
+ skip_nr = cur_idx - prev_idx;
+
+ while (skip_nr) {
+ k = bch_btree_iter_next_filter(&iter,
+ &c->root->keys,
+ bch_ptr_bad);
+ if (k)
+ p = k;
+ else {
+ /*
+ * No more keys to check in root node,
+ * current checking threads are enough,
+ * stop creating more.
+ */
+ atomic_set(&check_state->enough, 1);
+ /* Update check_state->enough earlier */
+ smp_mb__after_atomic();
+ goto out;
+ }
+ skip_nr--;
+ cond_resched();
+ }
+
+ if (p) {
+ struct btree_op op;
+
+ btree_node_prefetch(c->root, p);
+ c->gc_stats.nodes++;
+ bch_btree_op_init(&op, 0);
+ ret = bcache_btree(check_recurse, p, c->root, &op);
+ if (ret)
+ goto out;
+ }
+ p = NULL;
+ prev_idx = cur_idx;
+ cond_resched();
+ }
+
+out:
+ info->result = ret;
+ /* update check_state->started among all CPUs */
+ smp_mb__before_atomic();
+ if (atomic_dec_and_test(&check_state->started))
+ wake_up(&check_state->wait);
+
+ return ret;
+}
+
+
+
+static int bch_btree_chkthread_nr(void)
+{
+ int n = num_online_cpus()/2;
+
+ if (n == 0)
+ n = 1;
+ else if (n > BCH_BTR_CHKTHREAD_MAX)
+ n = BCH_BTR_CHKTHREAD_MAX;
+
+ return n;
+}
+
int bch_btree_check(struct cache_set *c)
{
- struct btree_op op;
+ int ret = 0;
+ int i;
+ struct bkey *k = NULL;
+ struct btree_iter iter;
+ struct btree_check_state *check_state;
+ char name[32];
- bch_btree_op_init(&op, SHRT_MAX);
+ /* check and mark root node keys */
+ for_each_key_filter(&c->root->keys, k, &iter, bch_ptr_invalid)
+ bch_initial_mark_key(c, c->root->level, k);
+
+ bch_initial_mark_key(c, c->root->level + 1, &c->root->key);
+
+ if (c->root->level == 0)
+ return 0;
+
+ check_state = kzalloc(sizeof(struct btree_check_state), GFP_KERNEL);
+ if (!check_state)
+ return -ENOMEM;
- return btree_root(check_recurse, c, &op);
+ check_state->c = c;
+ check_state->total_threads = bch_btree_chkthread_nr();
+ check_state->key_idx = 0;
+ spin_lock_init(&check_state->idx_lock);
+ atomic_set(&check_state->started, 0);
+ atomic_set(&check_state->enough, 0);
+ init_waitqueue_head(&check_state->wait);
+
+ /*
+ * Run multiple threads to check btree nodes in parallel,
+ * if check_state->enough is non-zero, it means current
+ * running check threads are enough, unncessary to create
+ * more.
+ */
+ for (i = 0; i < check_state->total_threads; i++) {
+ /* fetch latest check_state->enough earlier */
+ smp_mb__before_atomic();
+ if (atomic_read(&check_state->enough))
+ break;
+
+ check_state->infos[i].result = 0;
+ check_state->infos[i].state = check_state;
+ snprintf(name, sizeof(name), "bch_btrchk[%u]", i);
+ atomic_inc(&check_state->started);
+
+ check_state->infos[i].thread =
+ kthread_run(bch_btree_check_thread,
+ &check_state->infos[i],
+ name);
+ if (IS_ERR(check_state->infos[i].thread)) {
+ pr_err("fails to run thread bch_btrchk[%d]", i);
+ for (--i; i >= 0; i--)
+ kthread_stop(check_state->infos[i].thread);
+ ret = -ENOMEM;
+ goto out;
+ }
+ }
+
+ wait_event_interruptible(check_state->wait,
+ atomic_read(&check_state->started) == 0 ||
+ test_bit(CACHE_SET_IO_DISABLE, &c->flags));
+
+ for (i = 0; i < check_state->total_threads; i++) {
+ if (check_state->infos[i].result) {
+ ret = check_state->infos[i].result;
+ goto out;
+ }
+ }
+
+out:
+ kfree(check_state);
+ return ret;
}
void bch_initial_gc_finish(struct cache_set *c)
while ((k = bch_btree_iter_next_filter(&iter, &b->keys,
bch_ptr_bad))) {
- ret = btree(map_nodes_recurse, k, b,
+ ret = bcache_btree(map_nodes_recurse, k, b,
op, from, fn, flags);
from = NULL;
int __bch_btree_map_nodes(struct btree_op *op, struct cache_set *c,
struct bkey *from, btree_map_nodes_fn *fn, int flags)
{
- return btree_root(map_nodes_recurse, c, op, from, fn, flags);
+ return bcache_btree_root(map_nodes_recurse, c, op, from, fn, flags);
}
-static int bch_btree_map_keys_recurse(struct btree *b, struct btree_op *op,
+int bch_btree_map_keys_recurse(struct btree *b, struct btree_op *op,
struct bkey *from, btree_map_keys_fn *fn,
int flags)
{
while ((k = bch_btree_iter_next_filter(&iter, &b->keys, bch_ptr_bad))) {
ret = !b->level
? fn(op, b, k)
- : btree(map_keys_recurse, k, b, op, from, fn, flags);
+ : bcache_btree(map_keys_recurse, k,
+ b, op, from, fn, flags);
from = NULL;
if (ret != MAP_CONTINUE)
int bch_btree_map_keys(struct btree_op *op, struct cache_set *c,
struct bkey *from, btree_map_keys_fn *fn, int flags)
{
- return btree_root(map_keys_recurse, c, op, from, fn, flags);
+ return bcache_btree_root(map_keys_recurse, c, op, from, fn, flags);
}
/* Keybuf code */
struct bio *bio;
};
+
+
+
#define BTREE_FLAG(flag) \
static inline bool btree_node_ ## flag(struct btree *b) \
{ return test_bit(BTREE_NODE_ ## flag, &b->flags); } \
unsigned int insert_collision:1;
};
+struct btree_check_state;
+struct btree_check_info {
+ struct btree_check_state *state;
+ struct task_struct *thread;
+ int result;
+};
+
+#define BCH_BTR_CHKTHREAD_MAX 64
+struct btree_check_state {
+ struct cache_set *c;
+ int total_threads;
+ int key_idx;
+ spinlock_t idx_lock;
+ atomic_t started;
+ atomic_t enough;
+ wait_queue_head_t wait;
+ struct btree_check_info infos[BCH_BTR_CHKTHREAD_MAX];
+};
+
static inline void bch_btree_op_init(struct btree_op *op, int write_lock_level)
{
memset(op, 0, sizeof(struct btree_op));
wake_up_gc(c);
}
+/*
+ * These macros are for recursing down the btree - they handle the details of
+ * locking and looking up nodes in the cache for you. They're best treated as
+ * mere syntax when reading code that uses them.
+ *
+ * op->lock determines whether we take a read or a write lock at a given depth.
+ * If you've got a read lock and find that you need a write lock (i.e. you're
+ * going to have to split), set op->lock and return -EINTR; btree_root() will
+ * call you again and you'll have the correct lock.
+ */
+
+/**
+ * btree - recurse down the btree on a specified key
+ * @fn: function to call, which will be passed the child node
+ * @key: key to recurse on
+ * @b: parent btree node
+ * @op: pointer to struct btree_op
+ */
+#define bcache_btree(fn, key, b, op, ...) \
+({ \
+ int _r, l = (b)->level - 1; \
+ bool _w = l <= (op)->lock; \
+ struct btree *_child = bch_btree_node_get((b)->c, op, key, l, \
+ _w, b); \
+ if (!IS_ERR(_child)) { \
+ _r = bch_btree_ ## fn(_child, op, ##__VA_ARGS__); \
+ rw_unlock(_w, _child); \
+ } else \
+ _r = PTR_ERR(_child); \
+ _r; \
+})
+
+/**
+ * btree_root - call a function on the root of the btree
+ * @fn: function to call, which will be passed the child node
+ * @c: cache set
+ * @op: pointer to struct btree_op
+ */
+#define bcache_btree_root(fn, c, op, ...) \
+({ \
+ int _r = -EINTR; \
+ do { \
+ struct btree *_b = (c)->root; \
+ bool _w = insert_lock(op, _b); \
+ rw_lock(_w, _b, _b->level); \
+ if (_b == (c)->root && \
+ _w == insert_lock(op, _b)) { \
+ _r = bch_btree_ ## fn(_b, op, ##__VA_ARGS__); \
+ } \
+ rw_unlock(_w, _b); \
+ bch_cannibalize_unlock(c); \
+ if (_r == -EINTR) \
+ schedule(); \
+ } while (_r == -EINTR); \
+ \
+ finish_wait(&(c)->btree_cache_wait, &(op)->wait); \
+ _r; \
+})
+
#define MAP_DONE 0
#define MAP_CONTINUE 1
struct bkey *k);
int bch_btree_map_keys(struct btree_op *op, struct cache_set *c,
struct bkey *from, btree_map_keys_fn *fn, int flags);
+int bch_btree_map_keys_recurse(struct btree *b, struct btree_op *op,
+ struct bkey *from, btree_map_keys_fn *fn,
+ int flags);
typedef bool (keybuf_pred_fn)(struct keybuf *buf, struct bkey *k);
/* Cached devices - read & write stuff */
-static blk_qc_t cached_dev_make_request(struct request_queue *q,
- struct bio *bio)
+blk_qc_t cached_dev_make_request(struct request_queue *q, struct bio *bio)
{
struct search *s;
struct bcache_device *d = bio->bi_disk->private_data;
{
struct gendisk *g = dc->disk.disk;
- g->queue->make_request_fn = cached_dev_make_request;
g->queue->backing_dev_info->congested_fn = cached_dev_congested;
dc->disk.cache_miss = cached_dev_cache_miss;
dc->disk.ioctl = cached_dev_ioctl;
continue_at(cl, search_free, NULL);
}
-static blk_qc_t flash_dev_make_request(struct request_queue *q,
- struct bio *bio)
+blk_qc_t flash_dev_make_request(struct request_queue *q, struct bio *bio)
{
struct search *s;
struct closure *cl;
void bch_data_insert(struct closure *cl);
void bch_cached_dev_request_init(struct cached_dev *dc);
+blk_qc_t cached_dev_make_request(struct request_queue *q, struct bio *bio);
+
void bch_flash_dev_request_init(struct bcache_device *d);
+blk_qc_t flash_dev_make_request(struct request_queue *q, struct bio *bio);
extern struct kmem_cache *bch_search_cache;
}
static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
- sector_t sectors)
+ sector_t sectors, make_request_fn make_request_fn)
{
struct request_queue *q;
const size_t max_stripes = min_t(size_t, INT_MAX,
d->disk->fops = &bcache_ops;
d->disk->private_data = d;
- q = blk_alloc_queue(GFP_KERNEL);
+ q = blk_alloc_queue(make_request_fn, NUMA_NO_NODE);
if (!q)
return -ENOMEM;
- blk_queue_make_request(q, NULL);
d->disk->queue = q;
q->queuedata = d;
q->backing_dev_info->congested_data = d;
q->limits.raid_partial_stripes_expensive;
ret = bcache_device_init(&dc->disk, block_size,
- dc->bdev->bd_part->nr_sects - dc->sb.data_offset);
+ dc->bdev->bd_part->nr_sects - dc->sb.data_offset,
+ cached_dev_make_request);
if (ret)
return ret;
kobject_init(&d->kobj, &bch_flash_dev_ktype);
- if (bcache_device_init(d, block_bytes(c), u->sectors))
+ if (bcache_device_init(d, block_bytes(c), u->sectors,
+ flash_dev_make_request))
goto err;
bcache_device_attach(d, c, u - c->uuids);
size_t i;
for (i = 0; list[i]; i++)
- out += snprintf(out, buf + size - out,
+ out += scnprintf(out, buf + size - out,
i == selected ? "[%s] " : "%s ", list[i]);
out[-1] = '\n';
*/
set_bit(BCACHE_DEV_RATE_DW_RUNNING, &dc->disk.flags);
/* paired with where BCACHE_DEV_RATE_DW_RUNNING is tested */
- smp_mb();
+ smp_mb__after_atomic();
/*
* CACHE_SET_IO_DISABLE might be set via sysfs interface,
test_bit(CACHE_SET_IO_DISABLE, &c->flags)) {
clear_bit(BCACHE_DEV_RATE_DW_RUNNING, &dc->disk.flags);
/* paired with where BCACHE_DEV_RATE_DW_RUNNING is tested */
- smp_mb();
+ smp_mb__after_atomic();
return;
}
*/
clear_bit(BCACHE_DEV_RATE_DW_RUNNING, &dc->disk.flags);
/* paired with where BCACHE_DEV_RATE_DW_RUNNING is tested */
- smp_mb();
+ smp_mb__after_atomic();
}
static unsigned int writeback_delay(struct cached_dev *dc,
return MAP_CONTINUE;
}
-void bch_sectors_dirty_init(struct bcache_device *d)
+static int bch_root_node_dirty_init(struct cache_set *c,
+ struct bcache_device *d,
+ struct bkey *k)
{
struct sectors_dirty_init op;
int ret;
op.start = KEY(op.inode, 0, 0);
do {
- ret = bch_btree_map_keys(&op.op, d->c, &op.start,
- sectors_dirty_init_fn, 0);
+ ret = bcache_btree(map_keys_recurse,
+ k,
+ c->root,
+ &op.op,
+ &op.start,
+ sectors_dirty_init_fn,
+ 0);
if (ret == -EAGAIN)
schedule_timeout_interruptible(
msecs_to_jiffies(INIT_KEYS_SLEEP_MS));
break;
}
} while (ret == -EAGAIN);
+
+ return ret;
+}
+
+static int bch_dirty_init_thread(void *arg)
+{
+ struct dirty_init_thrd_info *info = arg;
+ struct bch_dirty_init_state *state = info->state;
+ struct cache_set *c = state->c;
+ struct btree_iter iter;
+ struct bkey *k, *p;
+ int cur_idx, prev_idx, skip_nr;
+ int i;
+
+ k = p = NULL;
+ i = 0;
+ cur_idx = prev_idx = 0;
+
+ bch_btree_iter_init(&c->root->keys, &iter, NULL);
+ k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad);
+ BUG_ON(!k);
+
+ p = k;
+
+ while (k) {
+ spin_lock(&state->idx_lock);
+ cur_idx = state->key_idx;
+ state->key_idx++;
+ spin_unlock(&state->idx_lock);
+
+ skip_nr = cur_idx - prev_idx;
+
+ while (skip_nr) {
+ k = bch_btree_iter_next_filter(&iter,
+ &c->root->keys,
+ bch_ptr_bad);
+ if (k)
+ p = k;
+ else {
+ atomic_set(&state->enough, 1);
+ /* Update state->enough earlier */
+ smp_mb__after_atomic();
+ goto out;
+ }
+ skip_nr--;
+ cond_resched();
+ }
+
+ if (p) {
+ if (bch_root_node_dirty_init(c, state->d, p) < 0)
+ goto out;
+ }
+
+ p = NULL;
+ prev_idx = cur_idx;
+ cond_resched();
+ }
+
+out:
+ /* In order to wake up state->wait in time */
+ smp_mb__before_atomic();
+ if (atomic_dec_and_test(&state->started))
+ wake_up(&state->wait);
+
+ return 0;
+}
+
+static int bch_btre_dirty_init_thread_nr(void)
+{
+ int n = num_online_cpus()/2;
+
+ if (n == 0)
+ n = 1;
+ else if (n > BCH_DIRTY_INIT_THRD_MAX)
+ n = BCH_DIRTY_INIT_THRD_MAX;
+
+ return n;
+}
+
+void bch_sectors_dirty_init(struct bcache_device *d)
+{
+ int i;
+ struct bkey *k = NULL;
+ struct btree_iter iter;
+ struct sectors_dirty_init op;
+ struct cache_set *c = d->c;
+ struct bch_dirty_init_state *state;
+ char name[32];
+
+ /* Just count root keys if no leaf node */
+ if (c->root->level == 0) {
+ bch_btree_op_init(&op.op, -1);
+ op.inode = d->id;
+ op.count = 0;
+ op.start = KEY(op.inode, 0, 0);
+
+ for_each_key_filter(&c->root->keys,
+ k, &iter, bch_ptr_invalid)
+ sectors_dirty_init_fn(&op.op, c->root, k);
+ return;
+ }
+
+ state = kzalloc(sizeof(struct bch_dirty_init_state), GFP_KERNEL);
+ if (!state) {
+ pr_warn("sectors dirty init failed: cannot allocate memory");
+ return;
+ }
+
+ state->c = c;
+ state->d = d;
+ state->total_threads = bch_btre_dirty_init_thread_nr();
+ state->key_idx = 0;
+ spin_lock_init(&state->idx_lock);
+ atomic_set(&state->started, 0);
+ atomic_set(&state->enough, 0);
+ init_waitqueue_head(&state->wait);
+
+ for (i = 0; i < state->total_threads; i++) {
+ /* Fetch latest state->enough earlier */
+ smp_mb__before_atomic();
+ if (atomic_read(&state->enough))
+ break;
+
+ state->infos[i].state = state;
+ atomic_inc(&state->started);
+ snprintf(name, sizeof(name), "bch_dirty_init[%d]", i);
+
+ state->infos[i].thread =
+ kthread_run(bch_dirty_init_thread,
+ &state->infos[i],
+ name);
+ if (IS_ERR(state->infos[i].thread)) {
+ pr_err("fails to run thread bch_dirty_init[%d]", i);
+ for (--i; i >= 0; i--)
+ kthread_stop(state->infos[i].thread);
+ goto out;
+ }
+ }
+
+ wait_event_interruptible(state->wait,
+ atomic_read(&state->started) == 0 ||
+ test_bit(CACHE_SET_IO_DISABLE, &c->flags));
+
+out:
+ kfree(state);
}
void bch_cached_dev_writeback_init(struct cached_dev *dc)
#define BCH_AUTO_GC_DIRTY_THRESHOLD 50
+#define BCH_DIRTY_INIT_THRD_MAX 64
/*
* 14 (16384ths) is chosen here as something that each backing device
* should be a reasonable fraction of the share, and not to blow up
*/
#define WRITEBACK_SHARE_SHIFT 14
+struct bch_dirty_init_state;
+struct dirty_init_thrd_info {
+ struct bch_dirty_init_state *state;
+ struct task_struct *thread;
+};
+
+struct bch_dirty_init_state {
+ struct cache_set *c;
+ struct bcache_device *d;
+ int total_threads;
+ int key_idx;
+ spinlock_t idx_lock;
+ atomic_t started;
+ atomic_t enough;
+ wait_queue_head_t wait;
+ struct dirty_init_thrd_info infos[BCH_DIRTY_INIT_THRD_MAX];
+};
+
static inline uint64_t bcache_dev_sectors_dirty(struct bcache_device *d)
{
uint64_t i, ret = 0;
#include <linux/wait.h>
#include <linux/pr.h>
#include <linux/refcount.h>
+#include <linux/part_stat.h>
#define DM_MSG_PREFIX "core"
INIT_LIST_HEAD(&md->table_devices);
spin_lock_init(&md->uevent_lock);
- md->queue = blk_alloc_queue_node(GFP_KERNEL, numa_node_id);
- if (!md->queue)
- goto bad;
- md->queue->queuedata = md;
/*
* default to bio-based required ->make_request_fn until DM
* table is loaded and md->type established. If request-based
* table is loaded: blk-mq will override accordingly.
*/
- blk_queue_make_request(md->queue, dm_make_request);
+ md->queue = blk_alloc_queue(dm_make_request, numa_node_id);
+ if (!md->queue)
+ goto bad;
+ md->queue->queuedata = md;
md->disk = alloc_disk_node(1, md->numa_node_id);
if (!md->disk)
#include <linux/delay.h>
#include <linux/raid/md_p.h>
#include <linux/raid/md_u.h>
+#include <linux/raid/detect.h>
#include <linux/slab.h>
#include <linux/percpu-refcount.h>
+#include <linux/part_stat.h>
#include <trace/events/block.h>
#include "md.h"
{
int err = 0;
struct block_device *bdev;
- char b[BDEVNAME_SIZE];
bdev = blkdev_get_by_dev(dev, FMODE_READ|FMODE_WRITE|FMODE_EXCL,
shared ? (struct md_rdev *)lock_rdev : rdev);
if (IS_ERR(bdev)) {
- pr_warn("md: could not open %s.\n", __bdevname(dev, b));
+ pr_warn("md: could not open device unknown-block(%u,%u).\n",
+ MAJOR(dev), MINOR(dev));
return PTR_ERR(bdev);
}
rdev->bdev = bdev;
mddev->hold_active = UNTIL_STOP;
error = -ENOMEM;
- mddev->queue = blk_alloc_queue(GFP_KERNEL);
+ mddev->queue = blk_alloc_queue(md_make_request, NUMA_NO_NODE);
if (!mddev->queue)
goto abort;
mddev->queue->queuedata = mddev;
- blk_queue_make_request(mddev->queue, md_make_request);
blk_set_stacking_limits(&mddev->queue->limits);
disk = alloc_disk(1 << shift);
static void mddev_detach(struct mddev *mddev)
{
md_bitmap_wait_behind_writes(mddev);
- if (mddev->pers && mddev->pers->quiesce) {
+ if (mddev->pers && mddev->pers->quiesce && !mddev->suspended) {
mddev->pers->quiesce(mddev, 1);
mddev->pers->quiesce(mddev, 0);
}
internal_nlba = div_u64(nsblk->size, nsblk_internal_lbasize(nsblk));
available_disk_size = internal_nlba * nsblk_sector_size(nsblk);
- q = blk_alloc_queue(GFP_KERNEL);
+ q = blk_alloc_queue(nd_blk_make_request, NUMA_NO_NODE);
if (!q)
return -ENOMEM;
if (devm_add_action_or_reset(dev, nd_blk_release_queue, q))
return -ENOMEM;
- blk_queue_make_request(q, nd_blk_make_request);
blk_queue_max_hw_sectors(q, UINT_MAX);
blk_queue_logical_block_size(q, nsblk_sector_size(nsblk));
blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
struct nd_namespace_common *ndns = nd_btt->ndns;
/* create a new disk and request queue for btt */
- btt->btt_queue = blk_alloc_queue(GFP_KERNEL);
+ btt->btt_queue = blk_alloc_queue(btt_make_request, NUMA_NO_NODE);
if (!btt->btt_queue)
return -ENOMEM;
btt->btt_disk->queue->backing_dev_info->capabilities |=
BDI_CAP_SYNCHRONOUS_IO;
- blk_queue_make_request(btt->btt_queue, btt_make_request);
blk_queue_logical_block_size(btt->btt_queue, btt->sector_size);
blk_queue_max_hw_sectors(btt->btt_queue, UINT_MAX);
blk_queue_flag_set(QUEUE_FLAG_NONROT, btt->btt_queue);
return -EBUSY;
}
- q = blk_alloc_queue_node(GFP_KERNEL, dev_to_node(dev));
+ q = blk_alloc_queue(pmem_make_request, dev_to_node(dev));
if (!q)
return -ENOMEM;
pmem->virt_addr = addr;
blk_queue_write_cache(q, true, fua);
- blk_queue_make_request(q, pmem_make_request);
blk_queue_physical_block_size(q, PAGE_SIZE);
blk_queue_logical_block_size(q, pmem_sector_size(ndns));
blk_queue_max_hw_sectors(q, UINT_MAX);
a hardware monitoring device will be created for each NVMe drive
in the system.
- If unsure, say N.
-
config NVME_FABRICS
tristate
nvme_remove_namespaces(ctrl);
ctrl->ops->delete_ctrl(ctrl);
nvme_uninit_ctrl(ctrl);
- nvme_put_ctrl(ctrl);
}
static void nvme_delete_ctrl_work(struct work_struct *work)
}
EXPORT_SYMBOL_GPL(nvme_delete_ctrl);
-static int nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl)
+static void nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl)
{
- int ret = 0;
-
/*
* Keep a reference until nvme_do_delete_ctrl() complete,
* since ->delete_ctrl can free the controller.
*/
nvme_get_ctrl(ctrl);
- if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_DELETING))
- ret = -EBUSY;
- if (!ret)
+ if (nvme_change_ctrl_state(ctrl, NVME_CTRL_DELETING))
nvme_do_delete_ctrl(ctrl);
nvme_put_ctrl(ctrl);
- return ret;
}
static inline bool nvme_ns_has_pi(struct nvme_ns *ns)
nvme_req(req)->ctrl->comp_seen = true;
if (unlikely(status != BLK_STS_OK && nvme_req_needs_retry(req))) {
- if ((req->cmd_flags & REQ_NVME_MPATH) &&
- blk_path_error(status)) {
- nvme_failover_req(req);
+ if ((req->cmd_flags & REQ_NVME_MPATH) && nvme_failover_req(req))
return;
- }
if (!blk_queue_dying(req->q)) {
nvme_retry_req(req);
return error;
}
+static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids,
+ struct nvme_ns_id_desc *cur)
+{
+ const char *warn_str = "ctrl returned bogus length:";
+ void *data = cur;
+
+ switch (cur->nidt) {
+ case NVME_NIDT_EUI64:
+ if (cur->nidl != NVME_NIDT_EUI64_LEN) {
+ dev_warn(ctrl->device, "%s %d for NVME_NIDT_EUI64\n",
+ warn_str, cur->nidl);
+ return -1;
+ }
+ memcpy(ids->eui64, data + sizeof(*cur), NVME_NIDT_EUI64_LEN);
+ return NVME_NIDT_EUI64_LEN;
+ case NVME_NIDT_NGUID:
+ if (cur->nidl != NVME_NIDT_NGUID_LEN) {
+ dev_warn(ctrl->device, "%s %d for NVME_NIDT_NGUID\n",
+ warn_str, cur->nidl);
+ return -1;
+ }
+ memcpy(ids->nguid, data + sizeof(*cur), NVME_NIDT_NGUID_LEN);
+ return NVME_NIDT_NGUID_LEN;
+ case NVME_NIDT_UUID:
+ if (cur->nidl != NVME_NIDT_UUID_LEN) {
+ dev_warn(ctrl->device, "%s %d for NVME_NIDT_UUID\n",
+ warn_str, cur->nidl);
+ return -1;
+ }
+ uuid_copy(&ids->uuid, data + sizeof(*cur));
+ return NVME_NIDT_UUID_LEN;
+ default:
+ /* Skip unknown types */
+ return cur->nidl;
+ }
+}
+
static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid,
struct nvme_ns_ids *ids)
{
status = nvme_submit_sync_cmd(ctrl->admin_q, &c, data,
NVME_IDENTIFY_DATA_SIZE);
- if (status)
+ if (status) {
+ dev_warn(ctrl->device,
+ "Identify Descriptors failed (%d)\n", status);
+ /*
+ * Don't treat an error as fatal, as we potentially already
+ * have a NGUID or EUI-64.
+ */
+ if (status > 0)
+ status = 0;
goto free_data;
+ }
for (pos = 0; pos < NVME_IDENTIFY_DATA_SIZE; pos += len) {
struct nvme_ns_id_desc *cur = data + pos;
if (cur->nidl == 0)
break;
- switch (cur->nidt) {
- case NVME_NIDT_EUI64:
- if (cur->nidl != NVME_NIDT_EUI64_LEN) {
- dev_warn(ctrl->device,
- "ctrl returned bogus length: %d for NVME_NIDT_EUI64\n",
- cur->nidl);
- goto free_data;
- }
- len = NVME_NIDT_EUI64_LEN;
- memcpy(ids->eui64, data + pos + sizeof(*cur), len);
- break;
- case NVME_NIDT_NGUID:
- if (cur->nidl != NVME_NIDT_NGUID_LEN) {
- dev_warn(ctrl->device,
- "ctrl returned bogus length: %d for NVME_NIDT_NGUID\n",
- cur->nidl);
- goto free_data;
- }
- len = NVME_NIDT_NGUID_LEN;
- memcpy(ids->nguid, data + pos + sizeof(*cur), len);
- break;
- case NVME_NIDT_UUID:
- if (cur->nidl != NVME_NIDT_UUID_LEN) {
- dev_warn(ctrl->device,
- "ctrl returned bogus length: %d for NVME_NIDT_UUID\n",
- cur->nidl);
- goto free_data;
- }
- len = NVME_NIDT_UUID_LEN;
- uuid_copy(&ids->uuid, data + pos + sizeof(*cur));
- break;
- default:
- /* Skip unknown types */
- len = cur->nidl;
- break;
- }
+ len = nvme_process_ns_desc(ctrl, ids, cur);
+ if (len < 0)
+ goto free_data;
len += sizeof(*cur);
}
return ret;
}
+#ifdef CONFIG_COMPAT
+struct nvme_user_io32 {
+ __u8 opcode;
+ __u8 flags;
+ __u16 control;
+ __u16 nblocks;
+ __u16 rsvd;
+ __u64 metadata;
+ __u64 addr;
+ __u64 slba;
+ __u32 dsmgmt;
+ __u32 reftag;
+ __u16 apptag;
+ __u16 appmask;
+} __attribute__((__packed__));
+
+#define NVME_IOCTL_SUBMIT_IO32 _IOW('N', 0x42, struct nvme_user_io32)
+
+static int nvme_compat_ioctl(struct block_device *bdev, fmode_t mode,
+ unsigned int cmd, unsigned long arg)
+{
+ /*
+ * Corresponds to the difference of NVME_IOCTL_SUBMIT_IO
+ * between 32 bit programs and 64 bit kernel.
+ * The cause is that the results of sizeof(struct nvme_user_io),
+ * which is used to define NVME_IOCTL_SUBMIT_IO,
+ * are not same between 32 bit compiler and 64 bit compiler.
+ * NVME_IOCTL_SUBMIT_IO32 is for 64 bit kernel handling
+ * NVME_IOCTL_SUBMIT_IO issued from 32 bit programs.
+ * Other IOCTL numbers are same between 32 bit and 64 bit.
+ * So there is nothing to do regarding to other IOCTL numbers.
+ */
+ if (cmd == NVME_IOCTL_SUBMIT_IO32)
+ return nvme_ioctl(bdev, mode, NVME_IOCTL_SUBMIT_IO, arg);
+
+ return nvme_ioctl(bdev, mode, cmd, arg);
+}
+#else
+#define nvme_compat_ioctl NULL
+#endif /* CONFIG_COMPAT */
+
static int nvme_open(struct block_device *bdev, fmode_t mode)
{
struct nvme_ns *ns = bdev->bd_disk->private_data;
static int nvme_report_ns_ids(struct nvme_ctrl *ctrl, unsigned int nsid,
struct nvme_id_ns *id, struct nvme_ns_ids *ids)
{
- int ret = 0;
-
memset(ids, 0, sizeof(*ids));
if (ctrl->vs >= NVME_VS(1, 1, 0))
memcpy(ids->eui64, id->eui64, sizeof(id->eui64));
if (ctrl->vs >= NVME_VS(1, 2, 0))
memcpy(ids->nguid, id->nguid, sizeof(id->nguid));
- if (ctrl->vs >= NVME_VS(1, 3, 0)) {
- /* Don't treat error as fatal we potentially
- * already have a NGUID or EUI-64
- */
- ret = nvme_identify_ns_descs(ctrl, nsid, ids);
- if (ret)
- dev_warn(ctrl->device,
- "Identify Descriptors failed (%d)\n", ret);
- if (ret > 0)
- ret = 0;
- }
- return ret;
+ if (ctrl->vs >= NVME_VS(1, 3, 0))
+ return nvme_identify_ns_descs(ctrl, nsid, ids);
+ return 0;
}
static bool nvme_ns_ids_valid(struct nvme_ns_ids *ids)
ns->lba_shift > PAGE_SHIFT)
capacity = 0;
- set_capacity(disk, capacity);
+ set_capacity_revalidate_and_notify(disk, capacity, false);
nvme_config_discard(disk, ns);
nvme_config_write_zeroes(disk, ns);
static const struct block_device_operations nvme_fops = {
.owner = THIS_MODULE,
.ioctl = nvme_ioctl,
- .compat_ioctl = nvme_ioctl,
+ .compat_ioctl = nvme_compat_ioctl,
.open = nvme_open,
.release = nvme_release,
.getgeo = nvme_getgeo,
.open = nvme_ns_head_open,
.release = nvme_ns_head_release,
.ioctl = nvme_ioctl,
- .compat_ioctl = nvme_ioctl,
+ .compat_ioctl = nvme_compat_ioctl,
.getgeo = nvme_getgeo,
.pr_ops = &nvme_pr_ops,
};
if ((csts & NVME_CSTS_RDY) == bit)
break;
- msleep(100);
+ usleep_range(1000, 2000);
if (fatal_signal_pending(current))
return -EINTR;
if (time_after(jiffies, timeout)) {
dev_err(ctrl->device,
- "Device not ready; aborting %s\n", enabled ?
- "initialisation" : "reset");
+ "Device not ready; aborting %s, CSTS=0x%x\n",
+ enabled ? "initialisation" : "reset", csts);
return -ENODEV;
}
}
lockdep_assert_held(&nvme_subsystems_lock);
list_for_each_entry(tmp, &subsys->ctrls, subsys_entry) {
- if (tmp->state == NVME_CTRL_DELETING ||
- tmp->state == NVME_CTRL_DEAD)
+ if (nvme_state_terminal(tmp))
continue;
if (tmp->cntlid == ctrl->cntlid) {
{
struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+ /* Can't delete non-created controllers */
+ if (!ctrl->created)
+ return -EBUSY;
+
if (device_remove_file_self(dev, attr))
nvme_delete_ctrl_sync(ctrl);
return count;
}
static DEVICE_ATTR(subsysnqn, S_IRUGO, nvme_sysfs_show_subsysnqn, NULL);
+static ssize_t nvme_sysfs_show_hostnqn(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+ return snprintf(buf, PAGE_SIZE, "%s\n", ctrl->opts->host->nqn);
+}
+static DEVICE_ATTR(hostnqn, S_IRUGO, nvme_sysfs_show_hostnqn, NULL);
+
+static ssize_t nvme_sysfs_show_hostid(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+ return snprintf(buf, PAGE_SIZE, "%pU\n", &ctrl->opts->host->id);
+}
+static DEVICE_ATTR(hostid, S_IRUGO, nvme_sysfs_show_hostid, NULL);
+
static ssize_t nvme_sysfs_show_address(struct device *dev,
struct device_attribute *attr,
char *buf)
&dev_attr_numa_node.attr,
&dev_attr_queue_count.attr,
&dev_attr_sqsize.attr,
+ &dev_attr_hostnqn.attr,
+ &dev_attr_hostid.attr,
NULL
};
return 0;
if (a == &dev_attr_address.attr && !ctrl->ops->get_address)
return 0;
+ if (a == &dev_attr_hostnqn.attr && !ctrl->opts)
+ return 0;
+ if (a == &dev_attr_hostid.attr && !ctrl->opts)
+ return 0;
return a->mode;
}
NULL,
};
-static struct nvme_ns_head *__nvme_find_ns_head(struct nvme_subsystem *subsys,
+static struct nvme_ns_head *nvme_find_ns_head(struct nvme_subsystem *subsys,
unsigned nsid)
{
struct nvme_ns_head *h;
}
static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
- unsigned nsid, struct nvme_id_ns *id)
+ unsigned nsid, struct nvme_id_ns *id,
+ struct nvme_ns_ids *ids)
{
struct nvme_ns_head *head;
size_t size = sizeof(*head);
goto out_ida_remove;
head->subsys = ctrl->subsys;
head->ns_id = nsid;
+ head->ids = *ids;
kref_init(&head->ref);
- ret = nvme_report_ns_ids(ctrl, nsid, id, &head->ids);
- if (ret)
- goto out_cleanup_srcu;
-
ret = __nvme_check_ids(ctrl->subsys, head);
if (ret) {
dev_err(ctrl->device,
struct nvme_ctrl *ctrl = ns->ctrl;
bool is_shared = id->nmic & (1 << 0);
struct nvme_ns_head *head = NULL;
+ struct nvme_ns_ids ids;
int ret = 0;
+ ret = nvme_report_ns_ids(ctrl, nsid, id, &ids);
+ if (ret)
+ goto out;
+
mutex_lock(&ctrl->subsys->lock);
if (is_shared)
- head = __nvme_find_ns_head(ctrl->subsys, nsid);
+ head = nvme_find_ns_head(ctrl->subsys, nsid);
if (!head) {
- head = nvme_alloc_ns_head(ctrl, nsid, id);
+ head = nvme_alloc_ns_head(ctrl, nsid, id, &ids);
if (IS_ERR(head)) {
ret = PTR_ERR(head);
goto out_unlock;
}
} else {
- struct nvme_ns_ids ids;
-
- ret = nvme_report_ns_ids(ctrl, nsid, id, &ids);
- if (ret)
- goto out_unlock;
-
if (!nvme_ns_ids_equal(&head->ids, &ids)) {
dev_err(ctrl->device,
"IDs don't match for shared namespace %d\n",
out_unlock:
mutex_unlock(&ctrl->subsys->lock);
+out:
if (ret > 0)
ret = blk_status_to_errno(nvme_error_status(ret));
return ret;
return 0;
}
-static int nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
+static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
{
struct nvme_ns *ns;
struct gendisk *disk;
ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node);
if (!ns)
- return -ENOMEM;
+ return;
ns->queue = blk_mq_init_queue(ctrl->tagset);
- if (IS_ERR(ns->queue)) {
- ret = PTR_ERR(ns->queue);
+ if (IS_ERR(ns->queue))
goto out_free_ns;
- }
if (ctrl->opts && ctrl->opts->data_digest)
ns->queue->backing_dev_info->capabilities
if (ret)
goto out_free_queue;
- if (id->ncap == 0) {
- ret = -EINVAL;
+ if (id->ncap == 0) /* no namespace (legacy quirk) */
goto out_free_id;
- }
ret = nvme_init_ns_head(ns, nsid, id);
if (ret)
nvme_set_disk_name(disk_name, ns, ctrl, &flags);
disk = alloc_disk_node(0, node);
- if (!disk) {
- ret = -ENOMEM;
+ if (!disk)
goto out_unlink_ns;
- }
disk->fops = &nvme_fops;
disk->private_data = ns;
nvme_fault_inject_init(&ns->fault_inject, ns->disk->disk_name);
kfree(id);
- return 0;
+ return;
out_put_disk:
put_disk(ns->disk);
out_unlink_ns:
blk_cleanup_queue(ns->queue);
out_free_ns:
kfree(ns);
- if (ret > 0)
- ret = blk_status_to_errno(nvme_error_status(ret));
- return ret;
}
static void nvme_ns_remove(struct nvme_ns *ns)
nvme_queue_scan(ctrl);
nvme_start_queues(ctrl);
}
+ ctrl->created = true;
}
EXPORT_SYMBOL_GPL(nvme_start_ctrl);
nvme_fault_inject_fini(&ctrl->fault_inject);
dev_pm_qos_hide_latency_tolerance(ctrl->device);
cdev_device_del(&ctrl->cdev, ctrl->device);
+ nvme_put_ctrl(ctrl);
}
EXPORT_SYMBOL_GPL(nvme_uninit_ctrl);
if (ret)
goto out_release_instance;
+ nvme_get_ctrl(ctrl);
cdev_init(&ctrl->cdev, &nvme_dev_fops);
ctrl->cdev.owner = ops->module;
ret = cdev_device_add(&ctrl->cdev, ctrl->device);
return 0;
out_free_name:
+ nvme_put_ctrl(ctrl);
kfree_const(ctrl->device->kobj.name);
out_release_instance:
ida_simple_remove(&nvme_instance_ida, ctrl->instance);
destroy_workqueue(nvme_delete_wq);
destroy_workqueue(nvme_reset_wq);
destroy_workqueue(nvme_wq);
+ ida_destroy(&nvme_instance_ida);
}
MODULE_LICENSE("GPL");
int len = 0;
if (ctrl->opts->mask & NVMF_OPT_TRADDR)
- len += snprintf(buf, size, "traddr=%s", ctrl->opts->traddr);
+ len += scnprintf(buf, size, "traddr=%s", ctrl->opts->traddr);
if (ctrl->opts->mask & NVMF_OPT_TRSVCID)
- len += snprintf(buf + len, size - len, "%strsvcid=%s",
+ len += scnprintf(buf + len, size - len, "%strsvcid=%s",
(len) ? "," : "", ctrl->opts->trsvcid);
if (ctrl->opts->mask & NVMF_OPT_HOST_TRADDR)
- len += snprintf(buf + len, size - len, "%shost_traddr=%s",
+ len += scnprintf(buf + len, size - len, "%shost_traddr=%s",
(len) ? "," : "", ctrl->opts->host_traddr);
- len += snprintf(buf + len, size - len, "\n");
+ len += scnprintf(buf + len, size - len, "\n");
return len;
}
goto fail_ctrl;
}
- nvme_get_ctrl(&ctrl->ctrl);
-
if (!queue_delayed_work(nvme_wq, &ctrl->connect_work, 0)) {
- nvme_put_ctrl(&ctrl->ctrl);
dev_err(ctrl->ctrl.device,
"NVME-FC{%d}: failed to schedule initial connect\n",
ctrl->cnum);
}
}
-void nvme_failover_req(struct request *req)
+bool nvme_failover_req(struct request *req)
{
struct nvme_ns *ns = req->q->queuedata;
u16 status = nvme_req(req)->status;
unsigned long flags;
- spin_lock_irqsave(&ns->head->requeue_lock, flags);
- blk_steal_bios(&ns->head->requeue_list, req);
- spin_unlock_irqrestore(&ns->head->requeue_lock, flags);
- blk_mq_end_request(req, 0);
-
switch (status & 0x7ff) {
case NVME_SC_ANA_TRANSITION:
case NVME_SC_ANA_INACCESSIBLE:
nvme_mpath_clear_current_path(ns);
break;
default:
- /*
- * Reset the controller for any non-ANA error as we don't know
- * what caused the error.
- */
- nvme_reset_ctrl(ns->ctrl);
- break;
+ /* This was a non-ANA error so follow the normal error path. */
+ return false;
}
+ spin_lock_irqsave(&ns->head->requeue_lock, flags);
+ blk_steal_bios(&ns->head->requeue_list, req);
+ spin_unlock_irqrestore(&ns->head->requeue_lock, flags);
+ blk_mq_end_request(req, 0);
+
kblockd_schedule_work(&ns->head->requeue_work);
+ return true;
}
void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
if (!(ctrl->subsys->cmic & (1 << 1)) || !multipath)
return 0;
- q = blk_alloc_queue_node(GFP_KERNEL, ctrl->numa_node);
+ q = blk_alloc_queue(nvme_ns_head_make_request, ctrl->numa_node);
if (!q)
goto out;
q->queuedata = head;
- blk_queue_make_request(q, nvme_ns_head_make_request);
blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
/* set to a default value for 512 until disk is validated */
blk_queue_logical_block_size(q, 512);
struct nvme_command ka_cmd;
struct work_struct fw_act_work;
unsigned long events;
+ bool created;
#ifdef CONFIG_NVME_MULTIPATH
/* asymmetric namespace access: */
void nvme_mpath_start_freeze(struct nvme_subsystem *subsys);
void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
struct nvme_ctrl *ctrl, int *flags);
-void nvme_failover_req(struct request *req);
+bool nvme_failover_req(struct request *req);
void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl);
int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head);
void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id);
sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->head->instance);
}
-static inline void nvme_failover_req(struct request *req)
+static inline bool nvme_failover_req(struct request *req)
{
+ return false;
}
static inline void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
{
nvme_end_request(req, cqe->status, cqe->result);
}
-static void nvme_complete_cqes(struct nvme_queue *nvmeq, u16 start, u16 end)
-{
- while (start != end) {
- nvme_handle_cqe(nvmeq, start);
- if (++start == nvmeq->q_depth)
- start = 0;
- }
-}
-
static inline void nvme_update_cq_head(struct nvme_queue *nvmeq)
{
- if (nvmeq->cq_head == nvmeq->q_depth - 1) {
+ if (++nvmeq->cq_head == nvmeq->q_depth) {
nvmeq->cq_head = 0;
- nvmeq->cq_phase = !nvmeq->cq_phase;
- } else {
- nvmeq->cq_head++;
+ nvmeq->cq_phase ^= 1;
}
}
-static inline int nvme_process_cq(struct nvme_queue *nvmeq, u16 *start,
- u16 *end, unsigned int tag)
+static inline int nvme_process_cq(struct nvme_queue *nvmeq)
{
int found = 0;
- *start = nvmeq->cq_head;
while (nvme_cqe_pending(nvmeq)) {
- if (tag == -1U || nvmeq->cqes[nvmeq->cq_head].command_id == tag)
- found++;
+ found++;
+ nvme_handle_cqe(nvmeq, nvmeq->cq_head);
nvme_update_cq_head(nvmeq);
}
- *end = nvmeq->cq_head;
- if (*start != *end)
+ if (found)
nvme_ring_cq_doorbell(nvmeq);
return found;
}
{
struct nvme_queue *nvmeq = data;
irqreturn_t ret = IRQ_NONE;
- u16 start, end;
/*
* The rmb/wmb pair ensures we see all updates from a previous run of
* the irq handler, even if that was on another CPU.
*/
rmb();
- nvme_process_cq(nvmeq, &start, &end, -1);
+ if (nvme_process_cq(nvmeq))
+ ret = IRQ_HANDLED;
wmb();
- if (start != end) {
- nvme_complete_cqes(nvmeq, start, end);
- return IRQ_HANDLED;
- }
-
return ret;
}
}
/*
- * Poll for completions any queue, including those not dedicated to polling.
+ * Poll for completions for any interrupt driven queue
* Can be called from any context.
*/
-static int nvme_poll_irqdisable(struct nvme_queue *nvmeq, unsigned int tag)
+static void nvme_poll_irqdisable(struct nvme_queue *nvmeq)
{
struct pci_dev *pdev = to_pci_dev(nvmeq->dev->dev);
- u16 start, end;
- int found;
- /*
- * For a poll queue we need to protect against the polling thread
- * using the CQ lock. For normal interrupt driven threads we have
- * to disable the interrupt to avoid racing with it.
- */
- if (test_bit(NVMEQ_POLLED, &nvmeq->flags)) {
- spin_lock(&nvmeq->cq_poll_lock);
- found = nvme_process_cq(nvmeq, &start, &end, tag);
- spin_unlock(&nvmeq->cq_poll_lock);
- } else {
- disable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
- found = nvme_process_cq(nvmeq, &start, &end, tag);
- enable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
- }
+ WARN_ON_ONCE(test_bit(NVMEQ_POLLED, &nvmeq->flags));
- nvme_complete_cqes(nvmeq, start, end);
- return found;
+ disable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
+ nvme_process_cq(nvmeq);
+ enable_irq(pci_irq_vector(pdev, nvmeq->cq_vector));
}
static int nvme_poll(struct blk_mq_hw_ctx *hctx)
{
struct nvme_queue *nvmeq = hctx->driver_data;
- u16 start, end;
bool found;
if (!nvme_cqe_pending(nvmeq))
return 0;
spin_lock(&nvmeq->cq_poll_lock);
- found = nvme_process_cq(nvmeq, &start, &end, -1);
- nvme_complete_cqes(nvmeq, start, end);
+ found = nvme_process_cq(nvmeq);
spin_unlock(&nvmeq->cq_poll_lock);
return found;
/*
* Did we miss an interrupt?
*/
- if (nvme_poll_irqdisable(nvmeq, req->tag)) {
+ if (test_bit(NVMEQ_POLLED, &nvmeq->flags))
+ nvme_poll(req->mq_hctx);
+ else
+ nvme_poll_irqdisable(nvmeq);
+
+ if (blk_mq_request_completed(req)) {
dev_warn(dev->ctrl.device,
"I/O %d QID %d timeout, completion polled\n",
req->tag, nvmeq->qid);
else
nvme_disable_ctrl(&dev->ctrl);
- nvme_poll_irqdisable(nvmeq, -1);
+ nvme_poll_irqdisable(nvmeq);
}
/*
*/
static void nvme_reap_pending_cqes(struct nvme_dev *dev)
{
- u16 start, end;
int i;
- for (i = dev->ctrl.queue_count - 1; i > 0; i--) {
- nvme_process_cq(&dev->queues[i], &start, &end, -1);
- nvme_complete_cqes(&dev->queues[i], start, end);
- }
+ for (i = dev->ctrl.queue_count - 1; i > 0; i--)
+ nvme_process_cq(&dev->queues[i]);
}
static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues,
struct nvme_dev *dev = to_nvme_dev(ctrl);
nvme_dbbuf_dma_free(dev);
- put_device(dev->dev);
nvme_free_tagset(dev);
if (dev->ctrl.admin_q)
blk_put_queue(dev->ctrl.admin_q);
- kfree(dev->queues);
free_opal_dev(dev->ctrl.opal_dev);
mempool_destroy(dev->iod_mempool);
+ put_device(dev->dev);
+ kfree(dev->queues);
kfree(dev);
}
{
struct pci_dev *pdev = to_pci_dev(to_nvme_dev(ctrl)->dev);
- return snprintf(buf, size, "%s", dev_name(&pdev->dev));
+ return snprintf(buf, size, "%s\n", dev_name(&pdev->dev));
}
static const struct nvme_ctrl_ops nvme_pci_ctrl_ops = {
dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev));
nvme_reset_ctrl(&dev->ctrl);
- nvme_get_ctrl(&dev->ctrl);
async_schedule(nvme_async_probe, dev);
return 0;
nvme_free_host_mem(dev);
nvme_dev_remove_admin(dev);
nvme_free_queues(dev, 0);
- nvme_uninit_ctrl(&dev->ctrl);
nvme_release_prp_pools(dev);
nvme_dev_unmap(dev);
- nvme_put_ctrl(&dev->ctrl);
+ nvme_uninit_ctrl(&dev->ctrl);
}
#ifdef CONFIG_PM_SLEEP
changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
if (!changed) {
- /* state change failure is ok if we're in DELETING state */
+ /*
+ * state change failure is ok if we're in DELETING state,
+ * unless we're during creation of a new controller to
+ * avoid races with teardown flow.
+ */
WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING);
+ WARN_ON_ONCE(new);
ret = -EINVAL;
goto destroy_io;
}
dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs\n",
ctrl->ctrl.opts->subsysnqn, &ctrl->addr);
- nvme_get_ctrl(&ctrl->ctrl);
-
mutex_lock(&nvme_rdma_ctrl_mutex);
list_add_tail(&ctrl->list, &nvme_rdma_ctrl_list);
mutex_unlock(&nvme_rdma_ctrl_mutex);
struct nvme_tcp_queue;
+/* Define the socket priority to use for connections were it is desirable
+ * that the NIC consider performing optimized packet processing or filtering.
+ * A non-zero value being sufficient to indicate general consideration of any
+ * possible optimization. Making it a module param allows for alternative
+ * values that may be unique for some NIC implementations.
+ */
+static int so_priority;
+module_param(so_priority, int, 0644);
+MODULE_PARM_DESC(so_priority, "nvme tcp socket optimize priority");
+
enum nvme_tcp_send_state {
NVME_TCP_SEND_CMD_PDU = 0,
NVME_TCP_SEND_H2C_PDU,
if (req->state == NVME_TCP_SEND_DDGST)
ret = nvme_tcp_try_send_ddgst(req);
done:
- if (ret == -EAGAIN)
+ if (ret == -EAGAIN) {
ret = 0;
+ } else if (ret < 0) {
+ dev_err(queue->ctrl->ctrl.device,
+ "failed to send request %d\n", ret);
+ if (ret != -EPIPE && ret != -ECONNRESET)
+ nvme_tcp_fail_request(queue->request);
+ nvme_tcp_done_send_req(queue);
+ }
return ret;
}
int result;
result = nvme_tcp_try_send(queue);
- if (result > 0) {
+ if (result > 0)
pending = true;
- } else if (unlikely(result < 0)) {
- dev_err(queue->ctrl->ctrl.device,
- "failed to send request %d\n", result);
-
- /*
- * Fail the request unless peer closed the connection,
- * in which case error recovery flow will complete all.
- */
- if ((result != -EPIPE) && (result != -ECONNRESET))
- nvme_tcp_fail_request(queue->request);
- nvme_tcp_done_send_req(queue);
- return;
- }
+ else if (unlikely(result < 0))
+ break;
result = nvme_tcp_try_recv(queue);
if (result > 0)
pending = true;
+ else if (unlikely(result < 0))
+ break;
if (!pending)
return;
return ret;
}
+static bool nvme_tcp_admin_queue(struct nvme_tcp_queue *queue)
+{
+ return nvme_tcp_queue_id(queue) == 0;
+}
+
+static bool nvme_tcp_default_queue(struct nvme_tcp_queue *queue)
+{
+ struct nvme_tcp_ctrl *ctrl = queue->ctrl;
+ int qid = nvme_tcp_queue_id(queue);
+
+ return !nvme_tcp_admin_queue(queue) &&
+ qid < 1 + ctrl->io_queues[HCTX_TYPE_DEFAULT];
+}
+
+static bool nvme_tcp_read_queue(struct nvme_tcp_queue *queue)
+{
+ struct nvme_tcp_ctrl *ctrl = queue->ctrl;
+ int qid = nvme_tcp_queue_id(queue);
+
+ return !nvme_tcp_admin_queue(queue) &&
+ !nvme_tcp_default_queue(queue) &&
+ qid < 1 + ctrl->io_queues[HCTX_TYPE_DEFAULT] +
+ ctrl->io_queues[HCTX_TYPE_READ];
+}
+
+static bool nvme_tcp_poll_queue(struct nvme_tcp_queue *queue)
+{
+ struct nvme_tcp_ctrl *ctrl = queue->ctrl;
+ int qid = nvme_tcp_queue_id(queue);
+
+ return !nvme_tcp_admin_queue(queue) &&
+ !nvme_tcp_default_queue(queue) &&
+ !nvme_tcp_read_queue(queue) &&
+ qid < 1 + ctrl->io_queues[HCTX_TYPE_DEFAULT] +
+ ctrl->io_queues[HCTX_TYPE_READ] +
+ ctrl->io_queues[HCTX_TYPE_POLL];
+}
+
+static void nvme_tcp_set_queue_io_cpu(struct nvme_tcp_queue *queue)
+{
+ struct nvme_tcp_ctrl *ctrl = queue->ctrl;
+ int qid = nvme_tcp_queue_id(queue);
+ int n = 0;
+
+ if (nvme_tcp_default_queue(queue))
+ n = qid - 1;
+ else if (nvme_tcp_read_queue(queue))
+ n = qid - ctrl->io_queues[HCTX_TYPE_DEFAULT] - 1;
+ else if (nvme_tcp_poll_queue(queue))
+ n = qid - ctrl->io_queues[HCTX_TYPE_DEFAULT] -
+ ctrl->io_queues[HCTX_TYPE_READ] - 1;
+ queue->io_cpu = cpumask_next_wrap(n - 1, cpu_online_mask, -1, false);
+}
+
static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
int qid, size_t queue_size)
{
struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
struct nvme_tcp_queue *queue = &ctrl->queues[qid];
struct linger sol = { .l_onoff = 1, .l_linger = 0 };
- int ret, opt, rcv_pdu_size, n;
+ int ret, opt, rcv_pdu_size;
queue->ctrl = ctrl;
INIT_LIST_HEAD(&queue->send_list);
goto err_sock;
}
+ if (so_priority > 0) {
+ ret = kernel_setsockopt(queue->sock, SOL_SOCKET, SO_PRIORITY,
+ (char *)&so_priority, sizeof(so_priority));
+ if (ret) {
+ dev_err(ctrl->ctrl.device,
+ "failed to set SO_PRIORITY sock opt, ret %d\n",
+ ret);
+ goto err_sock;
+ }
+ }
+
/* Set socket type of service */
if (nctrl->opts->tos >= 0) {
opt = nctrl->opts->tos;
}
queue->sock->sk->sk_allocation = GFP_ATOMIC;
- if (!qid)
- n = 0;
- else
- n = (qid - 1) % num_online_cpus();
- queue->io_cpu = cpumask_next_wrap(n - 1, cpu_online_mask, -1, false);
+ nvme_tcp_set_queue_io_cpu(queue);
queue->request = NULL;
queue->data_remaining = 0;
queue->ddgst_remaining = 0;
}
if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE)) {
- /* state change failure is ok if we're in DELETING state */
+ /*
+ * state change failure is ok if we're in DELETING state,
+ * unless we're during creation of a new controller to
+ * avoid races with teardown flow.
+ */
WARN_ON_ONCE(ctrl->state != NVME_CTRL_DELETING);
+ WARN_ON_ONCE(new);
ret = -EINVAL;
goto destroy_io;
}
dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISp\n",
ctrl->ctrl.opts->subsysnqn, &ctrl->addr);
- nvme_get_ctrl(&ctrl->ctrl);
-
mutex_lock(&nvme_tcp_ctrl_mutex);
list_add_tail(&ctrl->list, &nvme_tcp_ctrl_list);
mutex_unlock(&nvme_tcp_ctrl_mutex);
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/rculist.h>
+#include <linux/part_stat.h>
#include <generated/utsrelease.h>
#include <asm/unaligned.h>
nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR);
}
+static void nvmet_id_set_model_number(struct nvme_id_ctrl *id,
+ struct nvmet_subsys *subsys)
+{
+ const char *model = NVMET_DEFAULT_CTRL_MODEL;
+ struct nvmet_subsys_model *subsys_model;
+
+ rcu_read_lock();
+ subsys_model = rcu_dereference(subsys->model);
+ if (subsys_model)
+ model = subsys_model->number;
+ memcpy_and_pad(id->mn, sizeof(id->mn), model, strlen(model), ' ');
+ rcu_read_unlock();
+}
+
static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
{
struct nvmet_ctrl *ctrl = req->sq->ctrl;
struct nvme_id_ctrl *id;
u16 status = 0;
- const char model[] = "Linux";
id = kzalloc(sizeof(*id), GFP_KERNEL);
if (!id) {
memset(id->sn, ' ', sizeof(id->sn));
bin2hex(id->sn, &ctrl->subsys->serial,
min(sizeof(ctrl->subsys->serial), sizeof(id->sn) / 2));
- memcpy_and_pad(id->mn, sizeof(id->mn), model, sizeof(model) - 1, ' ');
+ nvmet_id_set_model_number(id, ctrl->subsys);
memcpy_and_pad(id->fr, sizeof(id->fr),
UTS_RELEASE, strlen(UTS_RELEASE), ' ');
/* we support multiple ports, multiples hosts and ANA: */
id->cmic = (1 << 0) | (1 << 1) | (1 << 3);
- /* no limit on data transfer sizes for now */
- id->mdts = 0;
+ /* Limit MDTS according to transport capability */
+ if (ctrl->ops->get_mdts)
+ id->mdts = ctrl->ops->get_mdts(ctrl);
+ else
+ id->mdts = 0;
+
id->cntlid = cpu_to_le16(ctrl->cntlid);
id->ver = cpu_to_le32(ctrl->subsys->ver);
{
struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
u32 cdw10 = le32_to_cpu(req->cmd->common.cdw10);
+ u32 cdw11 = le32_to_cpu(req->cmd->common.cdw11);
u16 status = 0;
+ u16 nsqr;
+ u16 ncqr;
if (!nvmet_check_data_len(req, 0))
return;
switch (cdw10 & 0xff) {
case NVME_FEAT_NUM_QUEUES:
+ ncqr = (cdw11 >> 16) & 0xffff;
+ nsqr = cdw11 & 0xffff;
+ if (ncqr == 0xffff || nsqr == 0xffff) {
+ status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+ break;
+ }
nvmet_set_result(req,
(subsys->max_qid - 1) | ((subsys->max_qid - 1) << 16));
break;
struct nvmet_subsys *subsys = ns->subsys;
int ret = 0;
-
mutex_lock(&subsys->lock);
if (ns->enabled) {
ret = -EBUSY;
goto out_unlock;
}
-
if (uuid_parse(page, &ns->uuid))
ret = -EINVAL;
(int)NVME_MAJOR(subsys->ver),
(int)NVME_MINOR(subsys->ver),
(int)NVME_TERTIARY(subsys->ver));
- else
- return snprintf(page, PAGE_SIZE, "%d.%d\n",
- (int)NVME_MAJOR(subsys->ver),
- (int)NVME_MINOR(subsys->ver));
+
+ return snprintf(page, PAGE_SIZE, "%d.%d\n",
+ (int)NVME_MAJOR(subsys->ver),
+ (int)NVME_MINOR(subsys->ver));
}
static ssize_t nvmet_subsys_attr_version_store(struct config_item *item,
int major, minor, tertiary = 0;
int ret;
-
ret = sscanf(page, "%d.%d.%d\n", &major, &minor, &tertiary);
if (ret != 2 && ret != 3)
return -EINVAL;
static ssize_t nvmet_subsys_attr_serial_store(struct config_item *item,
const char *page, size_t count)
{
- struct nvmet_subsys *subsys = to_subsys(item);
+ u64 serial;
+
+ if (sscanf(page, "%llx\n", &serial) != 1)
+ return -EINVAL;
down_write(&nvmet_config_sem);
- sscanf(page, "%llx\n", &subsys->serial);
+ to_subsys(item)->serial = serial;
up_write(&nvmet_config_sem);
return count;
}
CONFIGFS_ATTR(nvmet_subsys_, attr_serial);
+static ssize_t nvmet_subsys_attr_cntlid_min_show(struct config_item *item,
+ char *page)
+{
+ return snprintf(page, PAGE_SIZE, "%u\n", to_subsys(item)->cntlid_min);
+}
+
+static ssize_t nvmet_subsys_attr_cntlid_min_store(struct config_item *item,
+ const char *page, size_t cnt)
+{
+ u16 cntlid_min;
+
+ if (sscanf(page, "%hu\n", &cntlid_min) != 1)
+ return -EINVAL;
+
+ if (cntlid_min == 0)
+ return -EINVAL;
+
+ down_write(&nvmet_config_sem);
+ if (cntlid_min >= to_subsys(item)->cntlid_max)
+ goto out_unlock;
+ to_subsys(item)->cntlid_min = cntlid_min;
+ up_write(&nvmet_config_sem);
+ return cnt;
+
+out_unlock:
+ up_write(&nvmet_config_sem);
+ return -EINVAL;
+}
+CONFIGFS_ATTR(nvmet_subsys_, attr_cntlid_min);
+
+static ssize_t nvmet_subsys_attr_cntlid_max_show(struct config_item *item,
+ char *page)
+{
+ return snprintf(page, PAGE_SIZE, "%u\n", to_subsys(item)->cntlid_max);
+}
+
+static ssize_t nvmet_subsys_attr_cntlid_max_store(struct config_item *item,
+ const char *page, size_t cnt)
+{
+ u16 cntlid_max;
+
+ if (sscanf(page, "%hu\n", &cntlid_max) != 1)
+ return -EINVAL;
+
+ if (cntlid_max == 0)
+ return -EINVAL;
+
+ down_write(&nvmet_config_sem);
+ if (cntlid_max <= to_subsys(item)->cntlid_min)
+ goto out_unlock;
+ to_subsys(item)->cntlid_max = cntlid_max;
+ up_write(&nvmet_config_sem);
+ return cnt;
+
+out_unlock:
+ up_write(&nvmet_config_sem);
+ return -EINVAL;
+}
+CONFIGFS_ATTR(nvmet_subsys_, attr_cntlid_max);
+
+static ssize_t nvmet_subsys_attr_model_show(struct config_item *item,
+ char *page)
+{
+ struct nvmet_subsys *subsys = to_subsys(item);
+ struct nvmet_subsys_model *subsys_model;
+ char *model = NVMET_DEFAULT_CTRL_MODEL;
+ int ret;
+
+ rcu_read_lock();
+ subsys_model = rcu_dereference(subsys->model);
+ if (subsys_model)
+ model = subsys_model->number;
+ ret = snprintf(page, PAGE_SIZE, "%s\n", model);
+ rcu_read_unlock();
+
+ return ret;
+}
+
+/* See Section 1.5 of NVMe 1.4 */
+static bool nvmet_is_ascii(const char c)
+{
+ return c >= 0x20 && c <= 0x7e;
+}
+
+static ssize_t nvmet_subsys_attr_model_store(struct config_item *item,
+ const char *page, size_t count)
+{
+ struct nvmet_subsys *subsys = to_subsys(item);
+ struct nvmet_subsys_model *new_model;
+ char *new_model_number;
+ int pos = 0, len;
+
+ len = strcspn(page, "\n");
+ if (!len)
+ return -EINVAL;
+
+ for (pos = 0; pos < len; pos++) {
+ if (!nvmet_is_ascii(page[pos]))
+ return -EINVAL;
+ }
+
+ new_model_number = kstrndup(page, len, GFP_KERNEL);
+ if (!new_model_number)
+ return -ENOMEM;
+
+ new_model = kzalloc(sizeof(*new_model) + len + 1, GFP_KERNEL);
+ if (!new_model) {
+ kfree(new_model_number);
+ return -ENOMEM;
+ }
+ memcpy(new_model->number, new_model_number, len);
+
+ down_write(&nvmet_config_sem);
+ mutex_lock(&subsys->lock);
+ new_model = rcu_replace_pointer(subsys->model, new_model,
+ mutex_is_locked(&subsys->lock));
+ mutex_unlock(&subsys->lock);
+ up_write(&nvmet_config_sem);
+
+ kfree_rcu(new_model, rcuhead);
+
+ return count;
+}
+CONFIGFS_ATTR(nvmet_subsys_, attr_model);
+
static struct configfs_attribute *nvmet_subsys_attrs[] = {
&nvmet_subsys_attr_attr_allow_any_host,
&nvmet_subsys_attr_attr_version,
&nvmet_subsys_attr_attr_serial,
+ &nvmet_subsys_attr_attr_cntlid_min,
+ &nvmet_subsys_attr_attr_cntlid_max,
+ &nvmet_subsys_attr_attr_model,
NULL,
};
if (!ctrl->sqs)
goto out_free_cqs;
+ if (subsys->cntlid_min > subsys->cntlid_max)
+ goto out_free_cqs;
+
ret = ida_simple_get(&cntlid_ida,
- NVME_CNTLID_MIN, NVME_CNTLID_MAX,
+ subsys->cntlid_min, subsys->cntlid_max,
GFP_KERNEL);
if (ret < 0) {
status = NVME_SC_CONNECT_CTRL_BUSY | NVME_SC_DNR;
kfree(subsys);
return ERR_PTR(-ENOMEM);
}
-
+ subsys->cntlid_min = NVME_CNTLID_MIN;
+ subsys->cntlid_max = NVME_CNTLID_MAX;
kref_init(&subsys->ref);
mutex_init(&subsys->lock);
WARN_ON_ONCE(!list_empty(&subsys->namespaces));
kfree(subsys->subsysnqn);
+ kfree_rcu(subsys->model, rcuhead);
kfree(subsys);
}
out_disable:
dev_warn(ctrl->ctrl.device, "Removing after reset failure\n");
nvme_uninit_ctrl(&ctrl->ctrl);
- nvme_put_ctrl(&ctrl->ctrl);
}
static const struct nvme_ctrl_ops nvme_loop_ctrl_ops = {
dev_info(ctrl->ctrl.device,
"new ctrl: \"%s\"\n", ctrl->ctrl.opts->subsysnqn);
- nvme_get_ctrl(&ctrl->ctrl);
-
changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
WARN_ON_ONCE(!changed);
#define NVMET_ASYNC_EVENTS 4
#define NVMET_ERROR_LOG_SLOTS 128
#define NVMET_NO_ERROR_LOC ((u16)-1)
+#define NVMET_DEFAULT_CTRL_MODEL "Linux"
/*
* Supported optional AENs:
struct nvme_error_slot slots[NVMET_ERROR_LOG_SLOTS];
};
+struct nvmet_subsys_model {
+ struct rcu_head rcuhead;
+ char number[];
+};
+
struct nvmet_subsys {
enum nvme_subsys_type type;
struct list_head namespaces;
unsigned int nr_namespaces;
unsigned int max_nsid;
+ u16 cntlid_min;
+ u16 cntlid_max;
struct list_head ctrls;
struct config_group namespaces_group;
struct config_group allowed_hosts_group;
+
+ struct nvmet_subsys_model __rcu *model;
};
static inline struct nvmet_subsys *to_subsys(struct config_item *item)
struct nvmet_port *port, char *traddr);
u16 (*install_queue)(struct nvmet_sq *nvme_sq);
void (*discovery_chg)(struct nvmet_port *port);
+ u8 (*get_mdts)(const struct nvmet_ctrl *ctrl);
};
#define NVMET_MAX_INLINE_BIOVEC 8
#define NVMET_RDMA_MAX_INLINE_SGE 4
#define NVMET_RDMA_MAX_INLINE_DATA_SIZE max_t(int, SZ_16K, PAGE_SIZE)
+/* Assume mpsmin == device_page_size == 4KB */
+#define NVMET_RDMA_MAX_MDTS 8
+
struct nvmet_rdma_cmd {
struct ib_sge sge[NVMET_RDMA_MAX_INLINE_SGE + 1];
struct ib_cqe cqe;
{
struct ib_qp_init_attr qp_attr;
struct nvmet_rdma_device *ndev = queue->dev;
- int comp_vector, nr_cqe, ret, i;
+ int comp_vector, nr_cqe, ret, i, factor;
/*
* Spread the io queues across completion vectors,
qp_attr.qp_type = IB_QPT_RC;
/* +1 for drain */
qp_attr.cap.max_send_wr = queue->send_queue_size + 1;
- qp_attr.cap.max_rdma_ctxs = queue->send_queue_size;
+ factor = rdma_rw_mr_factor(ndev->device, queue->cm_id->port_num,
+ 1 << NVMET_RDMA_MAX_MDTS);
+ qp_attr.cap.max_rdma_ctxs = queue->send_queue_size * factor;
qp_attr.cap.max_send_sge = max(ndev->device->attrs.max_sge_rd,
ndev->device->attrs.max_send_sge);
}
}
+static u8 nvmet_rdma_get_mdts(const struct nvmet_ctrl *ctrl)
+{
+ return NVMET_RDMA_MAX_MDTS;
+}
+
static const struct nvmet_fabrics_ops nvmet_rdma_ops = {
.owner = THIS_MODULE,
.type = NVMF_TRTYPE_RDMA,
.queue_response = nvmet_rdma_queue_response,
.delete_ctrl = nvmet_rdma_delete_ctrl,
.disc_traddr = nvmet_rdma_disc_port_addr,
+ .get_mdts = nvmet_rdma_get_mdts,
};
static void nvmet_rdma_remove_one(struct ib_device *ib_device, void *client_data)
#define NVMET_TCP_DEF_INLINE_DATA_SIZE (4 * PAGE_SIZE)
+/* Define the socket priority to use for connections were it is desirable
+ * that the NIC consider performing optimized packet processing or filtering.
+ * A non-zero value being sufficient to indicate general consideration of any
+ * possible optimization. Making it a module param allows for alternative
+ * values that may be unique for some NIC implementations.
+ */
+static int so_priority;
+module_param(so_priority, int, 0644);
+MODULE_PARM_DESC(so_priority, "nvmet tcp socket optimize priority");
+
#define NVMET_TCP_RECV_BUDGET 8
#define NVMET_TCP_SEND_BUDGET 8
#define NVMET_TCP_IO_WORK_BUDGET 64
return 1;
}
-static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd)
+static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
{
struct nvmet_tcp_queue *queue = cmd->queue;
struct msghdr msg = { .msg_flags = MSG_DONTWAIT };
};
int ret;
+ if (!last_in_batch && cmd->queue->send_list_len)
+ msg.msg_flags |= MSG_MORE;
+
ret = kernel_sendmsg(queue->sock, &msg, &iov, 1, iov.iov_len);
if (unlikely(ret <= 0))
return ret;
}
if (cmd->state == NVMET_TCP_SEND_DDGST) {
- ret = nvmet_try_send_ddgst(cmd);
+ ret = nvmet_try_send_ddgst(cmd, last_in_batch);
if (ret <= 0)
goto done_send;
}
icresp->hdr.pdo = 0;
icresp->hdr.plen = cpu_to_le32(icresp->hdr.hlen);
icresp->pfv = cpu_to_le16(NVME_TCP_PFV_1_0);
- icresp->maxdata = cpu_to_le32(0xffff); /* FIXME: support r2t */
+ icresp->maxdata = cpu_to_le32(0x400000); /* 16M arbitrary limit */
icresp->cpda = 0;
if (queue->hdr_digest)
icresp->digest |= NVME_TCP_HDR_DIGEST_ENABLE;
if (ret)
return ret;
+ if (so_priority > 0) {
+ ret = kernel_setsockopt(sock, SOL_SOCKET, SO_PRIORITY,
+ (char *)&so_priority, sizeof(so_priority));
+ if (ret)
+ return ret;
+ }
+
/* Set socket type of service */
if (inet->rcv_tos > 0) {
int tos = inet->rcv_tos;
goto err_sock;
}
+ if (so_priority > 0) {
+ ret = kernel_setsockopt(port->sock, SOL_SOCKET, SO_PRIORITY,
+ (char *)&so_priority, sizeof(so_priority));
+ if (ret) {
+ pr_err("failed to set SO_PRIORITY sock opt %d\n", ret);
+ goto err_sock;
+ }
+ }
+
ret = kernel_bind(port->sock, (struct sockaddr *)&port->addr,
sizeof(port->addr));
if (ret) {
}
dev_info->gd->major = dcssblk_major;
dev_info->gd->fops = &dcssblk_devops;
- dev_info->dcssblk_queue = blk_alloc_queue(GFP_KERNEL);
+ dev_info->dcssblk_queue =
+ blk_alloc_queue(dcssblk_make_request, NUMA_NO_NODE);
dev_info->gd->queue = dev_info->dcssblk_queue;
dev_info->gd->private_data = dev_info;
- blk_queue_make_request(dev_info->dcssblk_queue, dcssblk_make_request);
blk_queue_logical_block_size(dev_info->dcssblk_queue, 4096);
blk_queue_flag_set(QUEUE_FLAG_DAX, dev_info->dcssblk_queue);
xpram_disks[i] = alloc_disk(1);
if (!xpram_disks[i])
goto out;
- xpram_queues[i] = blk_alloc_queue(GFP_KERNEL);
+ xpram_queues[i] = blk_alloc_queue(xpram_make_request,
+ NUMA_NO_NODE);
if (!xpram_queues[i]) {
put_disk(xpram_disks[i]);
goto out;
}
blk_queue_flag_set(QUEUE_FLAG_NONROT, xpram_queues[i]);
blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, xpram_queues[i]);
- blk_queue_make_request(xpram_queues[i], xpram_make_request);
blk_queue_logical_block_size(xpram_queues[i], 4096);
}
#include <linux/jiffies.h>
#include <linux/dma-mapping.h>
#include <linux/slab.h>
+#include <linux/msdos_partition.h>
#include <scsi/scsicam.h>
#include <asm/dma.h>
a partition table entry whose end_head matches one of the
standard BusLogic geometry translations (64/32, 128/32, or 255/63).
*/
- if (*(unsigned short *) (buf + 64) == 0xAA55) {
- struct partition *part1_entry = (struct partition *) buf;
- struct partition *part_entry = part1_entry;
+ if (*(unsigned short *) (buf + 64) == MSDOS_LABEL_MAGIC) {
+ struct msdos_partition *part1_entry =
+ (struct msdos_partition *)buf;
+ struct msdos_partition *part_entry = part1_entry;
int saved_cyl = diskparam->cylinders, part_no;
unsigned char part_end_head = 0, part_end_sector = 0;
config SCSI_IPR
tristate "IBM Power Linux RAID adapter support"
depends on PCI && SCSI && ATA
+ select SATA_HOST
select FW_LOADER
select IRQ_POLL
select SGL_ALLOC
#include <linux/syscalls.h>
#include <linux/delay.h>
#include <linux/kthread.h>
+#include <linux/msdos_partition.h>
#include <scsi/scsi.h>
#include <scsi/scsi_cmnd.h>
buf = scsi_bios_ptable(bdev);
if (!buf)
return 0;
- if(*(__le16 *)(buf + 0x40) == cpu_to_le16(0xaa55)) {
- struct partition *first = (struct partition * )buf;
- struct partition *entry = first;
+ if (*(__le16 *)(buf + 0x40) == cpu_to_le16(MSDOS_LABEL_MAGIC)) {
+ struct msdos_partition *first = (struct msdos_partition *)buf;
+ struct msdos_partition *entry = first;
int saved_cylinders = param->cylinders;
int num;
unsigned char end_head, end_sec;
ahd_linux_biosparam(struct scsi_device *sdev, struct block_device *bdev,
sector_t capacity, int geom[])
{
- uint8_t *bh;
int heads;
int sectors;
int cylinders;
- int ret;
int extended;
struct ahd_softc *ahd;
ahd = *((struct ahd_softc **)sdev->host->hostdata);
- bh = scsi_bios_ptable(bdev);
- if (bh) {
- ret = scsi_partsize(bh, capacity,
- &geom[2], &geom[0], &geom[1]);
- kfree(bh);
- if (ret != -1)
- return (ret);
- }
+ if (scsi_partsize(bdev, capacity, geom))
+ return 0;
+
heads = 64;
sectors = 32;
cylinders = aic_sector_div(capacity, heads, sectors);
ahc_linux_biosparam(struct scsi_device *sdev, struct block_device *bdev,
sector_t capacity, int geom[])
{
- uint8_t *bh;
int heads;
int sectors;
int cylinders;
- int ret;
int extended;
struct ahc_softc *ahc;
u_int channel;
ahc = *((struct ahc_softc **)sdev->host->hostdata);
channel = sdev_channel(sdev);
- bh = scsi_bios_ptable(bdev);
- if (bh) {
- ret = scsi_partsize(bh, capacity,
- &geom[2], &geom[0], &geom[1]);
- kfree(bh);
- if (ret != -1)
- return (ret);
- }
+ if (scsi_partsize(bdev, capacity, geom))
+ return 0;
+
heads = 64;
sectors = 32;
cylinders = aic_sector_div(capacity, heads, sectors);
static int arcmsr_bios_param(struct scsi_device *sdev,
struct block_device *bdev, sector_t capacity, int *geom)
{
- int ret, heads, sectors, cylinders, total_capacity;
- unsigned char *buffer;/* return copy of block device's partition table */
+ int heads, sectors, cylinders, total_capacity;
+
+ if (scsi_partsize(bdev, capacity, geom))
+ return 0;
- buffer = scsi_bios_ptable(bdev);
- if (buffer) {
- ret = scsi_partsize(buffer, capacity, &geom[2], &geom[0], &geom[1]);
- kfree(buffer);
- if (ret != -1)
- return ret;
- }
total_capacity = capacity;
heads = 64;
sectors = 32;
bool "ATA support for libsas (requires libata)"
depends on SCSI_SAS_LIBSAS
depends on ATA = y || ATA = SCSI_SAS_LIBSAS
+ select SATA_HOST
help
Builds in ATA support into libsas. Will necessitate
the loading of libata along with libsas.
sector_t capacity, int geom[])
{
adapter_t *adapter;
- unsigned char *bh;
int heads;
int sectors;
int cylinders;
- int rval;
/* Get pointer to host config structure */
adapter = (adapter_t *)sdev->host->hostdata;
geom[2] = cylinders;
}
else {
- bh = scsi_bios_ptable(bdev);
-
- if( bh ) {
- rval = scsi_partsize(bh, capacity,
- &geom[2], &geom[0], &geom[1]);
- kfree(bh);
- if( rval != -1 )
- return rval;
- }
+ if (scsi_partsize(bdev, capacity, geom))
+ return 0;
dev_info(&adapter->dev->dev,
"invalid partition on this disk on channel %d\n",
#include <linux/hrtimer.h>
#include <linux/uuid.h>
#include <linux/t10-pi.h>
+#include <linux/msdos_partition.h>
#include <net/checksum.h>
static void __init sdebug_build_parts(unsigned char *ramp,
unsigned long store_size)
{
- struct partition *pp;
+ struct msdos_partition *pp;
int starts[SDEBUG_MAX_PARTS + 2];
int sectors_per_part, num_sectors, k;
int heads_by_sects, start_sec, end_sec;
ramp[510] = 0x55; /* magic partition markings */
ramp[511] = 0xAA;
- pp = (struct partition *)(ramp + 0x1be);
+ pp = (struct msdos_partition *)(ramp + 0x1be);
for (k = 0; starts[k + 1]; ++k, ++pp) {
start_sec = starts[k];
end_sec = starts[k + 1] - 1;
#include <linux/genhd.h>
#include <linux/kernel.h>
#include <linux/blkdev.h>
+#include <linux/msdos_partition.h>
#include <asm/unaligned.h>
#include <scsi/scsicam.h>
-
-static int setsize(unsigned long capacity, unsigned int *cyls, unsigned int *hds,
- unsigned int *secs);
-
/**
* scsi_bios_ptable - Read PC partition table out of first sector of device.
* @dev: from this device
*/
unsigned char *scsi_bios_ptable(struct block_device *dev)
{
- unsigned char *res = kmalloc(66, GFP_KERNEL);
- if (res) {
- struct block_device *bdev = dev->bd_contains;
- Sector sect;
- void *data = read_dev_sector(bdev, 0, §);
- if (data) {
- memcpy(res, data + 0x1be, 66);
- put_dev_sector(sect);
- } else {
- kfree(res);
- res = NULL;
- }
- }
- return res;
-}
-EXPORT_SYMBOL(scsi_bios_ptable);
-
-/**
- * scsicam_bios_param - Determine geometry of a disk in cylinders/heads/sectors.
- * @bdev: which device
- * @capacity: size of the disk in sectors
- * @ip: return value: ip[0]=heads, ip[1]=sectors, ip[2]=cylinders
- *
- * Description : determine the BIOS mapping/geometry used for a drive in a
- * SCSI-CAM system, storing the results in ip as required
- * by the HDIO_GETGEO ioctl().
- *
- * Returns : -1 on failure, 0 on success.
- */
-
-int scsicam_bios_param(struct block_device *bdev, sector_t capacity, int *ip)
-{
- unsigned char *p;
- u64 capacity64 = capacity; /* Suppress gcc warning */
- int ret;
-
- p = scsi_bios_ptable(bdev);
- if (!p)
- return -1;
-
- /* try to infer mapping from partition table */
- ret = scsi_partsize(p, (unsigned long)capacity, (unsigned int *)ip + 2,
- (unsigned int *)ip + 0, (unsigned int *)ip + 1);
- kfree(p);
-
- if (ret == -1 && capacity64 < (1ULL << 32)) {
- /* pick some standard mapping with at most 1024 cylinders,
- and at most 62 sectors per track - this works up to
- 7905 MB */
- ret = setsize((unsigned long)capacity, (unsigned int *)ip + 2,
- (unsigned int *)ip + 0, (unsigned int *)ip + 1);
- }
-
- /* if something went wrong, then apparently we have to return
- a geometry with more than 1024 cylinders */
- if (ret || ip[0] > 255 || ip[1] > 63) {
- if ((capacity >> 11) > 65534) {
- ip[0] = 255;
- ip[1] = 63;
- } else {
- ip[0] = 64;
- ip[1] = 32;
- }
+ struct address_space *mapping = dev->bd_contains->bd_inode->i_mapping;
+ unsigned char *res = NULL;
+ struct page *page;
- if (capacity > 65535*63*255)
- ip[2] = 65535;
- else
- ip[2] = (unsigned long)capacity / (ip[0] * ip[1]);
- }
+ page = read_mapping_page(mapping, 0, NULL);
+ if (IS_ERR(page))
+ return NULL;
- return 0;
+ if (!PageError(page))
+ res = kmemdup(page_address(page) + 0x1be, 66, GFP_KERNEL);
+ put_page(page);
+ return res;
}
-EXPORT_SYMBOL(scsicam_bios_param);
+EXPORT_SYMBOL(scsi_bios_ptable);
/**
* scsi_partsize - Parse cylinders/heads/sectors from PC partition table
- * @buf: partition table, see scsi_bios_ptable()
+ * @bdev: block device to parse
* @capacity: size of the disk in sectors
- * @cyls: put cylinders here
- * @hds: put heads here
- * @secs: put sectors here
+ * @geom: output in form of [hds, cylinders, sectors]
*
* Determine the BIOS mapping/geometry used to create the partition
- * table, storing the results in @cyls, @hds, and @secs
+ * table, storing the results in @geom.
*
- * Returns: -1 on failure, 0 on success.
+ * Returns: %false on failure, %true on success.
*/
-
-int scsi_partsize(unsigned char *buf, unsigned long capacity,
- unsigned int *cyls, unsigned int *hds, unsigned int *secs)
+bool scsi_partsize(struct block_device *bdev, sector_t capacity, int geom[3])
{
- struct partition *p = (struct partition *)buf, *largest = NULL;
- int i, largest_cyl;
int cyl, ext_cyl, end_head, end_cyl, end_sector;
unsigned int logical_end, physical_end, ext_physical_end;
+ struct msdos_partition *p, *largest = NULL;
+ void *buf;
+ int ret = false;
+ buf = scsi_bios_ptable(bdev);
+ if (!buf)
+ return false;
if (*(unsigned short *) (buf + 64) == 0xAA55) {
- for (largest_cyl = -1, i = 0; i < 4; ++i, ++p) {
+ int largest_cyl = -1, i;
+
+ for (i = 0, p = buf; i < 4; i++, p++) {
if (!p->sys_ind)
continue;
#ifdef DEBUG
end_sector = largest->end_sector & 0x3f;
if (end_head + 1 == 0 || end_sector == 0)
- return -1;
+ goto out_free_buf;
#ifdef DEBUG
printk("scsicam_bios_param : end at h = %d, c = %d, s = %d\n",
,logical_end, physical_end, ext_physical_end, ext_cyl);
#endif
- if ((logical_end == physical_end) ||
- (end_cyl == 1023 && ext_physical_end == logical_end)) {
- *secs = end_sector;
- *hds = end_head + 1;
- *cyls = capacity / ((end_head + 1) * end_sector);
- return 0;
+ if (logical_end == physical_end ||
+ (end_cyl == 1023 && ext_physical_end == logical_end)) {
+ geom[0] = end_head + 1;
+ geom[1] = end_sector;
+ geom[2] = (unsigned long)capacity /
+ ((end_head + 1) * end_sector);
+ ret = true;
+ goto out_free_buf;
}
#ifdef DEBUG
printk("scsicam_bios_param : logical (%u) != physical (%u)\n",
logical_end, physical_end);
#endif
}
- return -1;
+
+out_free_buf:
+ kfree(buf);
+ return ret;
}
EXPORT_SYMBOL(scsi_partsize);
*hds = (unsigned int) heads;
return (rv);
}
+
+/**
+ * scsicam_bios_param - Determine geometry of a disk in cylinders/heads/sectors.
+ * @bdev: which device
+ * @capacity: size of the disk in sectors
+ * @ip: return value: ip[0]=heads, ip[1]=sectors, ip[2]=cylinders
+ *
+ * Description : determine the BIOS mapping/geometry used for a drive in a
+ * SCSI-CAM system, storing the results in ip as required
+ * by the HDIO_GETGEO ioctl().
+ *
+ * Returns : -1 on failure, 0 on success.
+ */
+int scsicam_bios_param(struct block_device *bdev, sector_t capacity, int *ip)
+{
+ u64 capacity64 = capacity; /* Suppress gcc warning */
+ int ret = 0;
+
+ /* try to infer mapping from partition table */
+ if (scsi_partsize(bdev, capacity, ip))
+ return 0;
+
+ if (capacity64 < (1ULL << 32)) {
+ /*
+ * Pick some standard mapping with at most 1024 cylinders, and
+ * at most 62 sectors per track - this works up to 7905 MB.
+ */
+ ret = setsize((unsigned long)capacity, (unsigned int *)ip + 2,
+ (unsigned int *)ip + 0, (unsigned int *)ip + 1);
+ }
+
+ /*
+ * If something went wrong, then apparently we have to return a geometry
+ * with more than 1024 cylinders.
+ */
+ if (ret || ip[0] > 255 || ip[1] > 63) {
+ if ((capacity >> 11) > 65534) {
+ ip[0] = 255;
+ ip[1] = 63;
+ } else {
+ ip[0] = 64;
+ ip[1] = 32;
+ }
+
+ if (capacity > 65535*63*255)
+ ip[2] = 65535;
+ else
+ ip[2] = (unsigned long)capacity / (ip[0] * ip[1]);
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(scsicam_bios_param);
sdkp->first_scan = 0;
- set_capacity(disk, logical_to_sectors(sdp, sdkp->capacity));
+ set_capacity_revalidate_and_notify(disk,
+ logical_to_sectors(sdp, sdkp->capacity), false);
sd_config_write_same(sdkp);
kfree(buffer);
if (ret)
return ret;
- if (invalidate)
- set_capacity(disk, 0);
- else if (disk->fops->revalidate_disk)
- disk->fops->revalidate_disk(disk);
+ /*
+ * Historically we only set the capacity to zero for devices that
+ * support partitions (independ of actually having partitions created).
+ * Doing that is rather inconsistent, but changing it broke legacy
+ * udisks polling for legacy ide-cdrom devices. Use the crude check
+ * below to get the sane behavior for most device while not breaking
+ * userspace for this particular setup.
+ */
+ if (invalidate) {
+ if (disk_part_scan_enabled(disk) ||
+ !(disk->flags & GENHD_FL_REMOVABLE))
+ set_capacity(disk, 0);
+ } else {
+ if (disk->fops->revalidate_disk)
+ disk->fops->revalidate_disk(disk);
+ }
check_disk_size_change(disk, bdev, !invalidate);
bio_put(bio);
}
-/*
- * This allows us to do IO even on the odd last sectors
- * of a device, even if the block size is some multiple
- * of the physical sector size.
- *
- * We'll just truncate the bio to the size of the device,
- * and clear the end of the buffer head manually.
- *
- * Truly out-of-range accesses will turn into actual IO
- * errors, this only handles the "we need to be able to
- * do IO at the final sector" case.
- */
-void guard_bio_eod(struct bio *bio)
-{
- sector_t maxsector;
- struct hd_struct *part;
-
- rcu_read_lock();
- part = __disk_get_part(bio->bi_disk, bio->bi_partno);
- if (part)
- maxsector = part_nr_sects_read(part);
- else
- maxsector = get_capacity(bio->bi_disk);
- rcu_read_unlock();
-
- if (!maxsector)
- return;
-
- /*
- * If the *whole* IO is past the end of the device,
- * let it through, and the IO layer will turn it into
- * an EIO.
- */
- if (unlikely(bio->bi_iter.bi_sector >= maxsector))
- return;
-
- maxsector -= bio->bi_iter.bi_sector;
- if (likely((bio->bi_iter.bi_size >> 9) <= maxsector))
- return;
-
- bio_truncate(bio, maxsector << 9);
-}
-
static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
enum rw_hint write_hint, struct writeback_control *wbc)
{
}
}
- ret = LZ4_decompress_safe_partial(src + inputmargin, out,
- inlen, rq->outputsize,
- rq->outputsize);
- if (ret < 0) {
- erofs_err(rq->sb, "failed to decompress, in[%u, %u] out[%u]",
- inlen, inputmargin, rq->outputsize);
+ /* legacy format could compress extra data in a pcluster. */
+ if (rq->partial_decoding || !support_0padding)
+ ret = LZ4_decompress_safe_partial(src + inputmargin, out,
+ inlen, rq->outputsize,
+ rq->outputsize);
+ else
+ ret = LZ4_decompress_safe(src + inputmargin, out,
+ inlen, rq->outputsize);
+
+ if (ret != rq->outputsize) {
+ erofs_err(rq->sb, "failed to decompress %d in[%u, %u] out[%u]",
+ ret, inlen, inputmargin, rq->outputsize);
+
WARN_ON(1);
print_hex_dump(KERN_DEBUG, "[ in]: ", DUMP_PREFIX_OFFSET,
16, 1, src + inputmargin, inlen, true);
print_hex_dump(KERN_DEBUG, "[out]: ", DUMP_PREFIX_OFFSET,
16, 1, out, rq->outputsize, true);
+
+ if (ret >= 0)
+ memset(out + ret, 0, rq->outputsize - ret);
ret = -EIO;
}
struct list_head list;
struct mutex umount_mutex;
- /* the dedicated workstation for compression */
- struct radix_tree_root workstn_tree;
+ /* managed XArray arranged in physical block number */
+ struct xarray managed_pslots;
/* threshold for decompression synchronously */
unsigned int max_sync_decompress_pages;
int erofs_workgroup_put(struct erofs_workgroup *grp);
struct erofs_workgroup *erofs_find_workgroup(struct super_block *sb,
pgoff_t index);
-int erofs_register_workgroup(struct super_block *sb,
- struct erofs_workgroup *grp);
+struct erofs_workgroup *erofs_insert_workgroup(struct super_block *sb,
+ struct erofs_workgroup *grp);
void erofs_workgroup_free_rcu(struct erofs_workgroup *grp);
void erofs_shrinker_register(struct super_block *sb);
void erofs_shrinker_unregister(struct super_block *sb);
sb->s_flags &= ~SB_POSIXACL;
#ifdef CONFIG_EROFS_FS_ZIP
- INIT_RADIX_TREE(&sbi->workstn_tree, GFP_ATOMIC);
+ xa_init(&sbi->managed_pslots);
#endif
/* get the root inode */
/* global shrink count (for all mounted EROFS instances) */
static atomic_long_t erofs_global_shrink_cnt;
-#define __erofs_workgroup_get(grp) atomic_inc(&(grp)->refcount)
-#define __erofs_workgroup_put(grp) atomic_dec(&(grp)->refcount)
-
static int erofs_workgroup_get(struct erofs_workgroup *grp)
{
int o;
repeat:
rcu_read_lock();
- grp = radix_tree_lookup(&sbi->workstn_tree, index);
+ grp = xa_load(&sbi->managed_pslots, index);
if (grp) {
if (erofs_workgroup_get(grp)) {
/* prefer to relax rcu read side */
return grp;
}
-int erofs_register_workgroup(struct super_block *sb,
- struct erofs_workgroup *grp)
+struct erofs_workgroup *erofs_insert_workgroup(struct super_block *sb,
+ struct erofs_workgroup *grp)
{
- struct erofs_sb_info *sbi;
- int err;
-
- /* grp shouldn't be broken or used before */
- if (atomic_read(&grp->refcount) != 1) {
- DBG_BUGON(1);
- return -EINVAL;
- }
-
- err = radix_tree_preload(GFP_NOFS);
- if (err)
- return err;
-
- sbi = EROFS_SB(sb);
- xa_lock(&sbi->workstn_tree);
+ struct erofs_sb_info *const sbi = EROFS_SB(sb);
+ struct erofs_workgroup *pre;
/*
- * Bump up reference count before making this workgroup
- * visible to other users in order to avoid potential UAF
- * without serialized by workstn_lock.
+ * Bump up a reference count before making this visible
+ * to others for the XArray in order to avoid potential
+ * UAF without serialized by xa_lock.
*/
- __erofs_workgroup_get(grp);
-
- err = radix_tree_insert(&sbi->workstn_tree, grp->index, grp);
- if (err)
- /*
- * it's safe to decrease since the workgroup isn't visible
- * and refcount >= 2 (cannot be freezed).
- */
- __erofs_workgroup_put(grp);
+ atomic_inc(&grp->refcount);
- xa_unlock(&sbi->workstn_tree);
- radix_tree_preload_end();
- return err;
+repeat:
+ xa_lock(&sbi->managed_pslots);
+ pre = __xa_cmpxchg(&sbi->managed_pslots, grp->index,
+ NULL, grp, GFP_NOFS);
+ if (pre) {
+ if (xa_is_err(pre)) {
+ pre = ERR_PTR(xa_err(pre));
+ } else if (erofs_workgroup_get(pre)) {
+ /* try to legitimize the current in-tree one */
+ xa_unlock(&sbi->managed_pslots);
+ cond_resched();
+ goto repeat;
+ }
+ atomic_dec(&grp->refcount);
+ grp = pre;
+ }
+ xa_unlock(&sbi->managed_pslots);
+ return grp;
}
static void __erofs_workgroup_free(struct erofs_workgroup *grp)
/*
* Note that all cached pages should be unattached
- * before deleted from the radix tree. Otherwise some
+ * before deleted from the XArray. Otherwise some
* cached pages could be still attached to the orphan
* old workgroup when the new one is available in the tree.
*/
* however in order to avoid some race conditions, add a
* DBG_BUGON to observe this in advance.
*/
- DBG_BUGON(radix_tree_delete(&sbi->workstn_tree, grp->index) != grp);
+ DBG_BUGON(xa_erase(&sbi->managed_pslots, grp->index) != grp);
/*
* If managed cache is on, last refcount should indicate
static unsigned long erofs_shrink_workstation(struct erofs_sb_info *sbi,
unsigned long nr_shrink)
{
- pgoff_t first_index = 0;
- void *batch[PAGEVEC_SIZE];
+ struct erofs_workgroup *grp;
unsigned int freed = 0;
+ unsigned long index;
- int i, found;
-repeat:
- xa_lock(&sbi->workstn_tree);
-
- found = radix_tree_gang_lookup(&sbi->workstn_tree,
- batch, first_index, PAGEVEC_SIZE);
-
- for (i = 0; i < found; ++i) {
- struct erofs_workgroup *grp = batch[i];
-
- first_index = grp->index + 1;
-
+ xa_for_each(&sbi->managed_pslots, index, grp) {
/* try to shrink each valid workgroup */
if (!erofs_try_to_release_workgroup(sbi, grp))
continue;
if (!--nr_shrink)
break;
}
- xa_unlock(&sbi->workstn_tree);
-
- if (i && nr_shrink)
- goto repeat;
return freed;
}
spin_unlock(&erofs_sb_list_lock);
sbi->shrinker_run_no = run_no;
- freed += erofs_shrink_workstation(sbi, nr);
+ freed += erofs_shrink_workstation(sbi, nr - freed);
spin_lock(&erofs_sb_list_lock);
/* Get the next list element before we move this one */
pcl->compressed_pages[i] = NULL;
}
-static void z_erofs_pcluster_init_always(struct z_erofs_pcluster *pcl)
-{
- struct z_erofs_collection *cl = z_erofs_primarycollection(pcl);
-
- atomic_set(&pcl->obj.refcount, 1);
-
- DBG_BUGON(cl->nr_pages);
- DBG_BUGON(cl->vcnt);
-}
-
int __init z_erofs_init_zip_subsystem(void)
{
pcluster_cachep = kmem_cache_create("erofs_compress",
struct inode *inode,
struct erofs_map_blocks *map)
{
- struct erofs_workgroup *grp;
- struct z_erofs_pcluster *pcl;
+ struct z_erofs_pcluster *pcl = clt->pcl;
struct z_erofs_collection *cl;
unsigned int length;
- grp = erofs_find_workgroup(inode->i_sb, map->m_pa >> PAGE_SHIFT);
- if (!grp)
- return -ENOENT;
-
- pcl = container_of(grp, struct z_erofs_pcluster, obj);
+ /* to avoid unexpected loop formed by corrupted images */
if (clt->owned_head == &pcl->next || pcl == clt->tailpcl) {
DBG_BUGON(1);
- erofs_workgroup_put(grp);
return -EFSCORRUPTED;
}
cl = z_erofs_primarycollection(pcl);
if (cl->pageofs != (map->m_la & ~PAGE_MASK)) {
DBG_BUGON(1);
- erofs_workgroup_put(grp);
return -EFSCORRUPTED;
}
if (length & Z_EROFS_PCLUSTER_FULL_LENGTH) {
if ((map->m_llen << Z_EROFS_PCLUSTER_LENGTH_BIT) > length) {
DBG_BUGON(1);
- erofs_workgroup_put(grp);
return -EFSCORRUPTED;
}
} else {
/* clean tailpcl if the current owned_head is Z_EROFS_PCLUSTER_TAIL */
if (clt->owned_head == Z_EROFS_PCLUSTER_TAIL)
clt->tailpcl = NULL;
- clt->pcl = pcl;
clt->cl = cl;
return 0;
}
{
struct z_erofs_pcluster *pcl;
struct z_erofs_collection *cl;
+ struct erofs_workgroup *grp;
int err;
/* no available workgroup, let's allocate one */
if (!pcl)
return -ENOMEM;
- z_erofs_pcluster_init_always(pcl);
+ atomic_set(&pcl->obj.refcount, 1);
pcl->obj.index = map->m_pa >> PAGE_SHIFT;
pcl->length = (map->m_llen << Z_EROFS_PCLUSTER_LENGTH_BIT) |
clt->mode = COLLECT_PRIMARY_FOLLOWED;
cl = z_erofs_primarycollection(pcl);
+
+ /* must be cleaned before freeing to slab */
+ DBG_BUGON(cl->nr_pages);
+ DBG_BUGON(cl->vcnt);
+
cl->pageofs = map->m_la & ~PAGE_MASK;
/*
* lock all primary followed works before visible to others
* and mutex_trylock *never* fails for a new pcluster.
*/
- mutex_trylock(&cl->lock);
+ DBG_BUGON(!mutex_trylock(&cl->lock));
- err = erofs_register_workgroup(inode->i_sb, &pcl->obj);
- if (err) {
- mutex_unlock(&cl->lock);
- kmem_cache_free(pcluster_cachep, pcl);
- return -EAGAIN;
+ grp = erofs_insert_workgroup(inode->i_sb, &pcl->obj);
+ if (IS_ERR(grp)) {
+ err = PTR_ERR(grp);
+ goto err_out;
+ }
+
+ if (grp != &pcl->obj) {
+ clt->pcl = container_of(grp, struct z_erofs_pcluster, obj);
+ err = -EEXIST;
+ goto err_out;
}
/* used to check tail merging loop due to corrupted images */
if (clt->owned_head == Z_EROFS_PCLUSTER_TAIL)
clt->pcl = pcl;
clt->cl = cl;
return 0;
+
+err_out:
+ mutex_unlock(&cl->lock);
+ kmem_cache_free(pcluster_cachep, pcl);
+ return err;
}
static int z_erofs_collector_begin(struct z_erofs_collector *clt,
struct inode *inode,
struct erofs_map_blocks *map)
{
+ struct erofs_workgroup *grp;
int ret;
DBG_BUGON(clt->cl);
return -EINVAL;
}
-repeat:
- ret = z_erofs_lookup_collection(clt, inode, map);
- if (ret == -ENOENT) {
+ grp = erofs_find_workgroup(inode->i_sb, map->m_pa >> PAGE_SHIFT);
+ if (grp) {
+ clt->pcl = container_of(grp, struct z_erofs_pcluster, obj);
+ } else {
ret = z_erofs_register_collection(clt, inode, map);
- /* someone registered at the same time, give another try */
- if (ret == -EAGAIN) {
- cond_resched();
- goto repeat;
- }
+ if (!ret)
+ goto out;
+ if (ret != -EEXIST)
+ return ret;
}
- if (ret)
+ ret = z_erofs_lookup_collection(clt, inode, map);
+ if (ret) {
+ erofs_workgroup_put(&clt->pcl->obj);
return ret;
+ }
+out:
z_erofs_pagevec_ctor_init(&clt->vector, Z_EROFS_NR_INLINE_PAGEVECS,
clt->cl->pagevec, clt->cl->vcnt);
#include <linux/uaccess.h>
#include <linux/iversion.h>
#include <linux/unicode.h>
-
+#include <linux/part_stat.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
static struct block_device *ext4_blkdev_get(dev_t dev, struct super_block *sb)
{
struct block_device *bdev;
- char b[BDEVNAME_SIZE];
bdev = blkdev_get_by_dev(dev, FMODE_READ|FMODE_WRITE|FMODE_EXCL, sb);
if (IS_ERR(bdev))
return bdev;
fail:
- ext4_msg(sb, KERN_ERR, "failed to open journal device %s: %ld",
- __bdevname(dev, b), PTR_ERR(bdev));
+ ext4_msg(sb, KERN_ERR,
+ "failed to open journal device unknown-block(%u,%u) %ld",
+ MAJOR(dev), MINOR(dev), PTR_ERR(bdev));
return NULL;
}
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/proc_fs.h>
+#include <linux/part_stat.h>
#include "ext4.h"
#include "ext4_jbd2.h"
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/quotaops.h>
+#include <linux/part_stat.h>
#include <crypto/hash.h>
#include <linux/fscrypt.h>
#include <linux/sysfs.h>
#include <linux/quota.h>
#include <linux/unicode.h>
+#include <linux/part_stat.h>
#include "f2fs.h"
#include "node.h"
/*
* buffer.c
*/
-extern void guard_bio_eod(struct bio *bio);
extern int __block_write_begin_int(struct page *page, loff_t pos, unsigned len,
get_block_t *get_block, struct iomap *iomap);
#define IO_WQ_HASH_ORDER 5
#endif
+#define IO_WQ_NR_HASH_BUCKETS (1u << IO_WQ_HASH_ORDER)
+
struct io_wqe_acct {
unsigned nr_workers;
unsigned max_workers;
struct list_head all_list;
struct io_wq *wq;
+ struct io_wq_work *hash_tail[IO_WQ_NR_HASH_BUCKETS];
};
/*
struct io_wqe **wqes;
unsigned long state;
- get_work_fn *get_work;
- put_work_fn *put_work;
+ free_work_fn *free_work;
struct task_struct *manager;
struct user_struct *user;
return __io_worker_unuse(wqe, worker);
}
-static struct io_wq_work *io_get_next_work(struct io_wqe *wqe, unsigned *hash)
+static inline unsigned int io_get_work_hash(struct io_wq_work *work)
+{
+ return work->flags >> IO_WQ_HASH_SHIFT;
+}
+
+static struct io_wq_work *io_get_next_work(struct io_wqe *wqe)
__must_hold(wqe->lock)
{
struct io_wq_work_node *node, *prev;
- struct io_wq_work *work;
+ struct io_wq_work *work, *tail;
+ unsigned int hash;
wq_list_for_each(node, prev, &wqe->work_list) {
work = container_of(node, struct io_wq_work, list);
/* not hashed, can run anytime */
- if (!(work->flags & IO_WQ_WORK_HASHED)) {
- wq_node_del(&wqe->work_list, node, prev);
+ if (!io_wq_is_hashed(work)) {
+ wq_list_del(&wqe->work_list, node, prev);
return work;
}
/* hashed, can run if not already running */
- *hash = work->flags >> IO_WQ_HASH_SHIFT;
- if (!(wqe->hash_map & BIT_ULL(*hash))) {
- wqe->hash_map |= BIT_ULL(*hash);
- wq_node_del(&wqe->work_list, node, prev);
+ hash = io_get_work_hash(work);
+ if (!(wqe->hash_map & BIT(hash))) {
+ wqe->hash_map |= BIT(hash);
+ /* all items with this hash lie in [work, tail] */
+ tail = wqe->hash_tail[hash];
+ wqe->hash_tail[hash] = NULL;
+ wq_list_cut(&wqe->work_list, &tail->list, prev);
return work;
}
}
worker->saved_creds = old_creds;
}
+static void io_impersonate_work(struct io_worker *worker,
+ struct io_wq_work *work)
+{
+ if (work->files && current->files != work->files) {
+ task_lock(current);
+ current->files = work->files;
+ task_unlock(current);
+ }
+ if (work->fs && current->fs != work->fs)
+ current->fs = work->fs;
+ if (work->mm != worker->mm)
+ io_wq_switch_mm(worker, work);
+ if (worker->cur_creds != work->creds)
+ io_wq_switch_creds(worker, work);
+}
+
+static void io_assign_current_work(struct io_worker *worker,
+ struct io_wq_work *work)
+{
+ if (work) {
+ /* flush pending signals before assigning new work */
+ if (signal_pending(current))
+ flush_signals(current);
+ cond_resched();
+ }
+
+ spin_lock_irq(&worker->lock);
+ worker->cur_work = work;
+ spin_unlock_irq(&worker->lock);
+}
+
+static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work);
+
static void io_worker_handle_work(struct io_worker *worker)
__releases(wqe->lock)
{
- struct io_wq_work *work, *old_work = NULL, *put_work = NULL;
struct io_wqe *wqe = worker->wqe;
struct io_wq *wq = wqe->wq;
do {
- unsigned hash = -1U;
-
+ struct io_wq_work *work;
+ unsigned int hash;
+get_next:
/*
* If we got some work, mark us as busy. If we didn't, but
* the list isn't empty, it means we stalled on hashed work.
* can't make progress, any work completion or insertion will
* clear the stalled flag.
*/
- work = io_get_next_work(wqe, &hash);
+ work = io_get_next_work(wqe);
if (work)
__io_worker_busy(wqe, worker, work);
else if (!wq_list_empty(&wqe->work_list))
wqe->flags |= IO_WQE_FLAG_STALLED;
spin_unlock_irq(&wqe->lock);
- if (put_work && wq->put_work)
- wq->put_work(old_work);
if (!work)
break;
-next:
- /* flush any pending signals before assigning new work */
- if (signal_pending(current))
- flush_signals(current);
-
- cond_resched();
-
- spin_lock_irq(&worker->lock);
- worker->cur_work = work;
- spin_unlock_irq(&worker->lock);
-
- if (work->flags & IO_WQ_WORK_CB)
- work->func(&work);
-
- if (work->files && current->files != work->files) {
- task_lock(current);
- current->files = work->files;
- task_unlock(current);
- }
- if (work->fs && current->fs != work->fs)
- current->fs = work->fs;
- if (work->mm != worker->mm)
- io_wq_switch_mm(worker, work);
- if (worker->cur_creds != work->creds)
- io_wq_switch_creds(worker, work);
- /*
- * OK to set IO_WQ_WORK_CANCEL even for uncancellable work,
- * the worker function will do the right thing.
- */
- if (test_bit(IO_WQ_BIT_CANCEL, &wq->state))
- work->flags |= IO_WQ_WORK_CANCEL;
- if (worker->mm)
- work->flags |= IO_WQ_WORK_HAS_MM;
-
- if (wq->get_work) {
- put_work = work;
- wq->get_work(work);
- }
-
- old_work = work;
- work->func(&work);
-
- spin_lock_irq(&worker->lock);
- worker->cur_work = NULL;
- spin_unlock_irq(&worker->lock);
-
- spin_lock_irq(&wqe->lock);
-
- if (hash != -1U) {
- wqe->hash_map &= ~BIT_ULL(hash);
- wqe->flags &= ~IO_WQE_FLAG_STALLED;
- }
- if (work && work != old_work) {
- spin_unlock_irq(&wqe->lock);
-
- if (put_work && wq->put_work) {
- wq->put_work(put_work);
- put_work = NULL;
+ io_assign_current_work(worker, work);
+
+ /* handle a whole dependent link */
+ do {
+ struct io_wq_work *old_work, *next_hashed, *linked;
+
+ next_hashed = wq_next_work(work);
+ io_impersonate_work(worker, work);
+ /*
+ * OK to set IO_WQ_WORK_CANCEL even for uncancellable
+ * work, the worker function will do the right thing.
+ */
+ if (test_bit(IO_WQ_BIT_CANCEL, &wq->state))
+ work->flags |= IO_WQ_WORK_CANCEL;
+
+ hash = io_get_work_hash(work);
+ linked = old_work = work;
+ linked->func(&linked);
+ linked = (old_work == linked) ? NULL : linked;
+
+ work = next_hashed;
+ if (!work && linked && !io_wq_is_hashed(linked)) {
+ work = linked;
+ linked = NULL;
}
+ io_assign_current_work(worker, work);
+ wq->free_work(old_work);
+
+ if (linked)
+ io_wqe_enqueue(wqe, linked);
+
+ if (hash != -1U && !next_hashed) {
+ spin_lock_irq(&wqe->lock);
+ wqe->hash_map &= ~BIT_ULL(hash);
+ wqe->flags &= ~IO_WQE_FLAG_STALLED;
+ /* dependent work is not hashed */
+ hash = -1U;
+ /* skip unnecessary unlock-lock wqe->lock */
+ if (!work)
+ goto get_next;
+ spin_unlock_irq(&wqe->lock);
+ }
+ } while (work);
- /* dependent work not hashed */
- hash = -1U;
- goto next;
- }
+ spin_lock_irq(&wqe->lock);
} while (1);
}
return true;
}
-static void io_run_cancel(struct io_wq_work *work)
+static void io_run_cancel(struct io_wq_work *work, struct io_wqe *wqe)
{
+ struct io_wq *wq = wqe->wq;
+
do {
struct io_wq_work *old_work = work;
work->flags |= IO_WQ_WORK_CANCEL;
work->func(&work);
work = (work == old_work) ? NULL : work;
+ wq->free_work(old_work);
} while (work);
}
+static void io_wqe_insert_work(struct io_wqe *wqe, struct io_wq_work *work)
+{
+ unsigned int hash;
+ struct io_wq_work *tail;
+
+ if (!io_wq_is_hashed(work)) {
+append:
+ wq_list_add_tail(&work->list, &wqe->work_list);
+ return;
+ }
+
+ hash = io_get_work_hash(work);
+ tail = wqe->hash_tail[hash];
+ wqe->hash_tail[hash] = work;
+ if (!tail)
+ goto append;
+
+ wq_list_add_after(&work->list, &tail->list, &wqe->work_list);
+}
+
static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work)
{
struct io_wqe_acct *acct = io_work_get_acct(wqe, work);
* It's close enough to not be an issue, fork() has the same delay.
*/
if (unlikely(!io_wq_can_queue(wqe, acct, work))) {
- io_run_cancel(work);
+ io_run_cancel(work, wqe);
return;
}
work_flags = work->flags;
spin_lock_irqsave(&wqe->lock, flags);
- wq_list_add_tail(&work->list, &wqe->work_list);
+ io_wqe_insert_work(wqe, work);
wqe->flags &= ~IO_WQE_FLAG_STALLED;
spin_unlock_irqrestore(&wqe->lock, flags);
}
/*
- * Enqueue work, hashed by some key. Work items that hash to the same value
- * will not be done in parallel. Used to limit concurrent writes, generally
- * hashed by inode.
+ * Work items that hash to the same value will not be done in parallel.
+ * Used to limit concurrent writes, generally hashed by inode.
*/
-void io_wq_enqueue_hashed(struct io_wq *wq, struct io_wq_work *work, void *val)
+void io_wq_hash_work(struct io_wq_work *work, void *val)
{
- struct io_wqe *wqe = wq->wqes[numa_node_id()];
- unsigned bit;
-
+ unsigned int bit;
bit = hash_ptr(val, IO_WQ_HASH_ORDER);
work->flags |= (IO_WQ_WORK_HASHED | (bit << IO_WQ_HASH_SHIFT));
- io_wqe_enqueue(wqe, work);
}
static bool io_wqe_worker_send_sig(struct io_worker *worker, void *data)
}
struct io_cb_cancel_data {
- struct io_wqe *wqe;
- work_cancel_fn *cancel;
- void *caller_data;
+ work_cancel_fn *fn;
+ void *data;
};
-static bool io_work_cancel(struct io_worker *worker, void *cancel_data)
+static bool io_wq_worker_cancel(struct io_worker *worker, void *data)
{
- struct io_cb_cancel_data *data = cancel_data;
+ struct io_cb_cancel_data *match = data;
unsigned long flags;
bool ret = false;
spin_lock_irqsave(&worker->lock, flags);
if (worker->cur_work &&
!(worker->cur_work->flags & IO_WQ_WORK_NO_CANCEL) &&
- data->cancel(worker->cur_work, data->caller_data)) {
- send_sig(SIGINT, worker->task, 1);
- ret = true;
- }
- spin_unlock_irqrestore(&worker->lock, flags);
-
- return ret;
-}
-
-static enum io_wq_cancel io_wqe_cancel_cb_work(struct io_wqe *wqe,
- work_cancel_fn *cancel,
- void *cancel_data)
-{
- struct io_cb_cancel_data data = {
- .wqe = wqe,
- .cancel = cancel,
- .caller_data = cancel_data,
- };
- struct io_wq_work_node *node, *prev;
- struct io_wq_work *work;
- unsigned long flags;
- bool found = false;
-
- spin_lock_irqsave(&wqe->lock, flags);
- wq_list_for_each(node, prev, &wqe->work_list) {
- work = container_of(node, struct io_wq_work, list);
-
- if (cancel(work, cancel_data)) {
- wq_node_del(&wqe->work_list, node, prev);
- found = true;
- break;
- }
- }
- spin_unlock_irqrestore(&wqe->lock, flags);
-
- if (found) {
- io_run_cancel(work);
- return IO_WQ_CANCEL_OK;
- }
-
- rcu_read_lock();
- found = io_wq_for_each_worker(wqe, io_work_cancel, &data);
- rcu_read_unlock();
- return found ? IO_WQ_CANCEL_RUNNING : IO_WQ_CANCEL_NOTFOUND;
-}
-
-enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel,
- void *data)
-{
- enum io_wq_cancel ret = IO_WQ_CANCEL_NOTFOUND;
- int node;
-
- for_each_node(node) {
- struct io_wqe *wqe = wq->wqes[node];
-
- ret = io_wqe_cancel_cb_work(wqe, cancel, data);
- if (ret != IO_WQ_CANCEL_NOTFOUND)
- break;
- }
-
- return ret;
-}
-
-struct work_match {
- bool (*fn)(struct io_wq_work *, void *data);
- void *data;
-};
-
-static bool io_wq_worker_cancel(struct io_worker *worker, void *data)
-{
- struct work_match *match = data;
- unsigned long flags;
- bool ret = false;
-
- spin_lock_irqsave(&worker->lock, flags);
- if (match->fn(worker->cur_work, match->data) &&
- !(worker->cur_work->flags & IO_WQ_WORK_NO_CANCEL)) {
+ match->fn(worker->cur_work, match->data)) {
send_sig(SIGINT, worker->task, 1);
ret = true;
}
}
static enum io_wq_cancel io_wqe_cancel_work(struct io_wqe *wqe,
- struct work_match *match)
+ struct io_cb_cancel_data *match)
{
struct io_wq_work_node *node, *prev;
struct io_wq_work *work;
work = container_of(node, struct io_wq_work, list);
if (match->fn(work, match->data)) {
- wq_node_del(&wqe->work_list, node, prev);
+ wq_list_del(&wqe->work_list, node, prev);
found = true;
break;
}
spin_unlock_irqrestore(&wqe->lock, flags);
if (found) {
- io_run_cancel(work);
+ io_run_cancel(work, wqe);
return IO_WQ_CANCEL_OK;
}
return found ? IO_WQ_CANCEL_RUNNING : IO_WQ_CANCEL_NOTFOUND;
}
-static bool io_wq_work_match(struct io_wq_work *work, void *data)
-{
- return work == data;
-}
-
-enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork)
+enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel,
+ void *data)
{
- struct work_match match = {
- .fn = io_wq_work_match,
- .data = cwork
+ struct io_cb_cancel_data match = {
+ .fn = cancel,
+ .data = data,
};
enum io_wq_cancel ret = IO_WQ_CANCEL_NOTFOUND;
int node;
- cwork->flags |= IO_WQ_WORK_CANCEL;
-
for_each_node(node) {
struct io_wqe *wqe = wq->wqes[node];
return ret;
}
+static bool io_wq_io_cb_cancel_data(struct io_wq_work *work, void *data)
+{
+ return work == data;
+}
+
+enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork)
+{
+ return io_wq_cancel_cb(wq, io_wq_io_cb_cancel_data, (void *)cwork);
+}
+
static bool io_wq_pid_match(struct io_wq_work *work, void *data)
{
pid_t pid = (pid_t) (unsigned long) data;
- if (work)
- return work->task_pid == pid;
- return false;
+ return work->task_pid == pid;
}
enum io_wq_cancel io_wq_cancel_pid(struct io_wq *wq, pid_t pid)
{
- struct work_match match = {
- .fn = io_wq_pid_match,
- .data = (void *) (unsigned long) pid
- };
- enum io_wq_cancel ret = IO_WQ_CANCEL_NOTFOUND;
- int node;
-
- for_each_node(node) {
- struct io_wqe *wqe = wq->wqes[node];
+ void *data = (void *) (unsigned long) pid;
- ret = io_wqe_cancel_work(wqe, &match);
- if (ret != IO_WQ_CANCEL_NOTFOUND)
- break;
- }
-
- return ret;
+ return io_wq_cancel_cb(wq, io_wq_pid_match, data);
}
struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
int ret = -ENOMEM, node;
struct io_wq *wq;
+ if (WARN_ON_ONCE(!data->free_work))
+ return ERR_PTR(-EINVAL);
+
wq = kzalloc(sizeof(*wq), GFP_KERNEL);
if (!wq)
return ERR_PTR(-ENOMEM);
return ERR_PTR(-ENOMEM);
}
- wq->get_work = data->get_work;
- wq->put_work = data->put_work;
+ wq->free_work = data->free_work;
/* caller must already hold a reference to this */
wq->user = data->user;
bool io_wq_get(struct io_wq *wq, struct io_wq_data *data)
{
- if (data->get_work != wq->get_work || data->put_work != wq->put_work)
+ if (data->free_work != wq->free_work)
return false;
return refcount_inc_not_zero(&wq->use_refs);
enum {
IO_WQ_WORK_CANCEL = 1,
- IO_WQ_WORK_HAS_MM = 2,
IO_WQ_WORK_HASHED = 4,
IO_WQ_WORK_UNBOUND = 32,
- IO_WQ_WORK_CB = 128,
IO_WQ_WORK_NO_CANCEL = 256,
IO_WQ_WORK_CONCURRENT = 512,
struct io_wq_work_node *last;
};
+static inline void wq_list_add_after(struct io_wq_work_node *node,
+ struct io_wq_work_node *pos,
+ struct io_wq_work_list *list)
+{
+ struct io_wq_work_node *next = pos->next;
+
+ pos->next = node;
+ node->next = next;
+ if (!next)
+ list->last = node;
+}
+
static inline void wq_list_add_tail(struct io_wq_work_node *node,
struct io_wq_work_list *list)
{
}
}
-static inline void wq_node_del(struct io_wq_work_list *list,
- struct io_wq_work_node *node,
+static inline void wq_list_cut(struct io_wq_work_list *list,
+ struct io_wq_work_node *last,
struct io_wq_work_node *prev)
{
- if (node == list->first)
- WRITE_ONCE(list->first, node->next);
- if (node == list->last)
+ /* first in the list, if prev==NULL */
+ if (!prev)
+ WRITE_ONCE(list->first, last->next);
+ else
+ prev->next = last->next;
+
+ if (last == list->last)
list->last = prev;
- if (prev)
- prev->next = node->next;
- node->next = NULL;
+ last->next = NULL;
+}
+
+static inline void wq_list_del(struct io_wq_work_list *list,
+ struct io_wq_work_node *node,
+ struct io_wq_work_node *prev)
+{
+ wq_list_cut(list, node, prev);
}
#define wq_list_for_each(pos, prv, head) \
} while (0)
struct io_wq_work {
- union {
- struct io_wq_work_node list;
- void *data;
- };
+ struct io_wq_work_node list;
void (*func)(struct io_wq_work **);
struct files_struct *files;
struct mm_struct *mm;
*(work) = (struct io_wq_work){ .func = _func }; \
} while (0) \
-typedef void (get_work_fn)(struct io_wq_work *);
-typedef void (put_work_fn)(struct io_wq_work *);
+static inline struct io_wq_work *wq_next_work(struct io_wq_work *work)
+{
+ if (!work->list.next)
+ return NULL;
+
+ return container_of(work->list.next, struct io_wq_work, list);
+}
+
+typedef void (free_work_fn)(struct io_wq_work *);
struct io_wq_data {
struct user_struct *user;
- get_work_fn *get_work;
- put_work_fn *put_work;
+ free_work_fn *free_work;
};
struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data);
void io_wq_destroy(struct io_wq *wq);
void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work);
-void io_wq_enqueue_hashed(struct io_wq *wq, struct io_wq_work *work, void *val);
+void io_wq_hash_work(struct io_wq_work *work, void *val);
+
+static inline bool io_wq_is_hashed(struct io_wq_work *work)
+{
+ return work->flags & IO_WQ_WORK_HASHED;
+}
void io_wq_cancel_all(struct io_wq *wq);
enum io_wq_cancel io_wq_cancel_work(struct io_wq *wq, struct io_wq_work *cwork);
#include <linux/errno.h>
#include <linux/syscalls.h>
#include <linux/compat.h>
+#include <net/compat.h>
#include <linux/refcount.h>
#include <linux/uio.h>
#include <linux/bits.h>
#include <linux/fadvise.h>
#include <linux/eventpoll.h>
#include <linux/fs_struct.h>
+#include <linux/splice.h>
+#include <linux/task_work.h>
#define CREATE_TRACE_POINTS
#include <trace/events/io_uring.h>
struct completion done;
};
+struct io_buffer {
+ struct list_head list;
+ __u64 addr;
+ __s32 len;
+ __u16 bid;
+};
+
struct io_ring_ctx {
struct {
struct percpu_ref refs;
struct socket *ring_sock;
#endif
+ struct idr io_buffer_idr;
+
struct idr personality_idr;
struct {
struct {
spinlock_t completion_lock;
- struct llist_head poll_llist;
/*
* ->poll_list is protected by the ctx->uring_lock for
void __user *buf;
};
int msg_flags;
+ int bgid;
size_t len;
+ struct io_buffer *kbuf;
};
struct io_open {
struct epoll_event event;
};
+struct io_splice {
+ struct file *file_out;
+ struct file *file_in;
+ loff_t off_out;
+ loff_t off_in;
+ u64 len;
+ unsigned int flags;
+};
+
+struct io_provide_buf {
+ struct file *file;
+ __u64 addr;
+ __s32 len;
+ __u32 bgid;
+ __u16 nbufs;
+ __u16 bid;
+};
+
struct io_async_connect {
struct sockaddr_storage address;
};
REQ_F_LINK_BIT = IOSQE_IO_LINK_BIT,
REQ_F_HARDLINK_BIT = IOSQE_IO_HARDLINK_BIT,
REQ_F_FORCE_ASYNC_BIT = IOSQE_ASYNC_BIT,
+ REQ_F_BUFFER_SELECT_BIT = IOSQE_BUFFER_SELECT_BIT,
REQ_F_LINK_NEXT_BIT,
REQ_F_FAIL_LINK_BIT,
REQ_F_COMP_LOCKED_BIT,
REQ_F_NEED_CLEANUP_BIT,
REQ_F_OVERFLOW_BIT,
+ REQ_F_POLLED_BIT,
+ REQ_F_BUFFER_SELECTED_BIT,
+
+ /* not a real bit, just to check we're not overflowing the space */
+ __REQ_F_LAST_BIT,
};
enum {
REQ_F_HARDLINK = BIT(REQ_F_HARDLINK_BIT),
/* IOSQE_ASYNC */
REQ_F_FORCE_ASYNC = BIT(REQ_F_FORCE_ASYNC_BIT),
+ /* IOSQE_BUFFER_SELECT */
+ REQ_F_BUFFER_SELECT = BIT(REQ_F_BUFFER_SELECT_BIT),
/* already grabbed next link */
REQ_F_LINK_NEXT = BIT(REQ_F_LINK_NEXT_BIT),
REQ_F_NEED_CLEANUP = BIT(REQ_F_NEED_CLEANUP_BIT),
/* in overflow list */
REQ_F_OVERFLOW = BIT(REQ_F_OVERFLOW_BIT),
+ /* already went through poll handler */
+ REQ_F_POLLED = BIT(REQ_F_POLLED_BIT),
+ /* buffer already selected */
+ REQ_F_BUFFER_SELECTED = BIT(REQ_F_BUFFER_SELECTED_BIT),
+};
+
+struct async_poll {
+ struct io_poll_iocb poll;
+ struct io_wq_work work;
};
/*
struct io_fadvise fadvise;
struct io_madvise madvise;
struct io_epoll epoll;
+ struct io_splice splice;
+ struct io_provide_buf pbuf;
};
struct io_async_ctx *io;
- /*
- * llist_node is only used for poll deferred completions
- */
- struct llist_node llist_node;
- bool in_async;
bool needs_fixed_file;
u8 opcode;
struct io_ring_ctx *ctx;
- union {
- struct list_head list;
- struct hlist_node hash_node;
- };
- struct list_head link_list;
+ struct list_head list;
unsigned int flags;
refcount_t refs;
+ union {
+ struct task_struct *task;
+ unsigned long fsize;
+ };
u64 user_data;
u32 result;
u32 sequence;
+ struct list_head link_list;
+
struct list_head inflight_entry;
- struct io_wq_work work;
+ union {
+ /*
+ * Only commands that never go async can use the below fields,
+ * obviously. Right now only IORING_OP_POLL_ADD uses them, and
+ * async armed poll handlers for regular commands. The latter
+ * restore the work, if needed.
+ */
+ struct {
+ struct callback_head task_work;
+ struct hlist_node hash_node;
+ struct async_poll *apoll;
+ int cflags;
+ };
+ struct io_wq_work work;
+ };
};
#define IO_PLUG_THRESHOLD 2
unsigned file_table : 1;
/* needs ->fs */
unsigned needs_fs : 1;
+ /* set if opcode supports polled "wait" */
+ unsigned pollin : 1;
+ unsigned pollout : 1;
+ /* op supports buffer selection */
+ unsigned buffer_select : 1;
};
static const struct io_op_def io_op_defs[] = {
.needs_mm = 1,
.needs_file = 1,
.unbound_nonreg_file = 1,
+ .pollin = 1,
+ .buffer_select = 1,
},
[IORING_OP_WRITEV] = {
.async_ctx = 1,
.needs_file = 1,
.hash_reg_file = 1,
.unbound_nonreg_file = 1,
+ .pollout = 1,
},
[IORING_OP_FSYNC] = {
.needs_file = 1,
[IORING_OP_READ_FIXED] = {
.needs_file = 1,
.unbound_nonreg_file = 1,
+ .pollin = 1,
},
[IORING_OP_WRITE_FIXED] = {
.needs_file = 1,
.hash_reg_file = 1,
.unbound_nonreg_file = 1,
+ .pollout = 1,
},
[IORING_OP_POLL_ADD] = {
.needs_file = 1,
.needs_file = 1,
.unbound_nonreg_file = 1,
.needs_fs = 1,
+ .pollout = 1,
},
[IORING_OP_RECVMSG] = {
.async_ctx = 1,
.needs_file = 1,
.unbound_nonreg_file = 1,
.needs_fs = 1,
+ .pollin = 1,
+ .buffer_select = 1,
},
[IORING_OP_TIMEOUT] = {
.async_ctx = 1,
.needs_file = 1,
.unbound_nonreg_file = 1,
.file_table = 1,
+ .pollin = 1,
},
[IORING_OP_ASYNC_CANCEL] = {},
[IORING_OP_LINK_TIMEOUT] = {
.needs_mm = 1,
.needs_file = 1,
.unbound_nonreg_file = 1,
+ .pollout = 1,
},
[IORING_OP_FALLOCATE] = {
.needs_file = 1,
.needs_mm = 1,
.needs_file = 1,
.unbound_nonreg_file = 1,
+ .pollin = 1,
+ .buffer_select = 1,
},
[IORING_OP_WRITE] = {
.needs_mm = 1,
.needs_file = 1,
.unbound_nonreg_file = 1,
+ .pollout = 1,
},
[IORING_OP_FADVISE] = {
.needs_file = 1,
.needs_mm = 1,
.needs_file = 1,
.unbound_nonreg_file = 1,
+ .pollout = 1,
},
[IORING_OP_RECV] = {
.needs_mm = 1,
.needs_file = 1,
.unbound_nonreg_file = 1,
+ .pollin = 1,
+ .buffer_select = 1,
},
[IORING_OP_OPENAT2] = {
.needs_file = 1,
.unbound_nonreg_file = 1,
.file_table = 1,
},
+ [IORING_OP_SPLICE] = {
+ .needs_file = 1,
+ .hash_reg_file = 1,
+ .unbound_nonreg_file = 1,
+ },
+ [IORING_OP_PROVIDE_BUFFERS] = {},
+ [IORING_OP_REMOVE_BUFFERS] = {},
};
static void io_wq_submit_work(struct io_wq_work **workptr);
static int io_grab_files(struct io_kiocb *req);
static void io_ring_file_ref_flush(struct fixed_file_data *data);
static void io_cleanup_req(struct io_kiocb *req);
+static int io_file_get(struct io_submit_state *state, struct io_kiocb *req,
+ int fd, struct file **out_file, bool fixed);
+static void __io_queue_sqe(struct io_kiocb *req,
+ const struct io_uring_sqe *sqe);
static struct kmem_cache *req_cachep;
INIT_LIST_HEAD(&ctx->cq_overflow_list);
init_completion(&ctx->completions[0]);
init_completion(&ctx->completions[1]);
+ idr_init(&ctx->io_buffer_idr);
idr_init(&ctx->personality_idr);
mutex_init(&ctx->uring_lock);
init_waitqueue_head(&ctx->wait);
spin_lock_init(&ctx->completion_lock);
- init_llist_head(&ctx->poll_llist);
INIT_LIST_HEAD(&ctx->poll_list);
INIT_LIST_HEAD(&ctx->defer_list);
INIT_LIST_HEAD(&ctx->timeout_list);
}
}
-static inline bool io_prep_async_work(struct io_kiocb *req,
+static inline void io_prep_async_work(struct io_kiocb *req,
struct io_kiocb **link)
{
const struct io_op_def *def = &io_op_defs[req->opcode];
- bool do_hashed = false;
if (req->flags & REQ_F_ISREG) {
if (def->hash_reg_file)
- do_hashed = true;
+ io_wq_hash_work(&req->work, file_inode(req->file));
} else {
if (def->unbound_nonreg_file)
req->work.flags |= IO_WQ_WORK_UNBOUND;
io_req_work_grab_env(req, def);
*link = io_prep_linked_timeout(req);
- return do_hashed;
}
static inline void io_queue_async_work(struct io_kiocb *req)
{
struct io_ring_ctx *ctx = req->ctx;
struct io_kiocb *link;
- bool do_hashed;
- do_hashed = io_prep_async_work(req, &link);
+ io_prep_async_work(req, &link);
- trace_io_uring_queue_async_work(ctx, do_hashed, req, &req->work,
- req->flags);
- if (!do_hashed) {
- io_wq_enqueue(ctx->io_wq, &req->work);
- } else {
- io_wq_enqueue_hashed(ctx->io_wq, &req->work,
- file_inode(req->file));
- }
+ trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req,
+ &req->work, req->flags);
+ io_wq_enqueue(ctx->io_wq, &req->work);
if (link)
io_queue_linked_timeout(link);
return false;
if (!ctx->eventfd_async)
return true;
- return io_wq_current_is_worker() || in_interrupt();
+ return io_wq_current_is_worker();
}
-static void __io_cqring_ev_posted(struct io_ring_ctx *ctx, bool trigger_ev)
+static void io_cqring_ev_posted(struct io_ring_ctx *ctx)
{
if (waitqueue_active(&ctx->wait))
wake_up(&ctx->wait);
if (waitqueue_active(&ctx->sqo_wait))
wake_up(&ctx->sqo_wait);
- if (trigger_ev)
+ if (io_should_trigger_evfd(ctx))
eventfd_signal(ctx->cq_ev_fd, 1);
}
-static void io_cqring_ev_posted(struct io_ring_ctx *ctx)
-{
- __io_cqring_ev_posted(ctx, io_should_trigger_evfd(ctx));
-}
-
/* Returns true if there are no backlogged entries after the flush */
static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
{
if (cqe) {
WRITE_ONCE(cqe->user_data, req->user_data);
WRITE_ONCE(cqe->res, req->result);
- WRITE_ONCE(cqe->flags, 0);
+ WRITE_ONCE(cqe->flags, req->cflags);
} else {
WRITE_ONCE(ctx->rings->cq_overflow,
atomic_inc_return(&ctx->cached_cq_overflow));
return cqe != NULL;
}
-static void io_cqring_fill_event(struct io_kiocb *req, long res)
+static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags)
{
struct io_ring_ctx *ctx = req->ctx;
struct io_uring_cqe *cqe;
if (likely(cqe)) {
WRITE_ONCE(cqe->user_data, req->user_data);
WRITE_ONCE(cqe->res, res);
- WRITE_ONCE(cqe->flags, 0);
+ WRITE_ONCE(cqe->flags, cflags);
} else if (ctx->cq_overflow_flushed) {
WRITE_ONCE(ctx->rings->cq_overflow,
atomic_inc_return(&ctx->cached_cq_overflow));
req->flags |= REQ_F_OVERFLOW;
refcount_inc(&req->refs);
req->result = res;
+ req->cflags = cflags;
list_add_tail(&req->list, &ctx->cq_overflow_list);
}
}
-static void io_cqring_add_event(struct io_kiocb *req, long res)
+static void io_cqring_fill_event(struct io_kiocb *req, long res)
+{
+ __io_cqring_fill_event(req, res, 0);
+}
+
+static void __io_cqring_add_event(struct io_kiocb *req, long res, long cflags)
{
struct io_ring_ctx *ctx = req->ctx;
unsigned long flags;
spin_lock_irqsave(&ctx->completion_lock, flags);
- io_cqring_fill_event(req, res);
+ __io_cqring_fill_event(req, res, cflags);
io_commit_cqring(ctx);
spin_unlock_irqrestore(&ctx->completion_lock, flags);
io_cqring_ev_posted(ctx);
}
+static void io_cqring_add_event(struct io_kiocb *req, long res)
+{
+ __io_cqring_add_event(req, res, 0);
+}
+
static inline bool io_is_fallback_req(struct io_kiocb *req)
{
return req == (struct io_kiocb *)
return NULL;
}
+static inline void io_put_file(struct io_kiocb *req, struct file *file,
+ bool fixed)
+{
+ if (fixed)
+ percpu_ref_put(&req->ctx->file_data->refs);
+ else
+ fput(file);
+}
+
static void __io_req_do_free(struct io_kiocb *req)
{
if (likely(!io_is_fallback_req(req)))
static void __io_req_aux_free(struct io_kiocb *req)
{
- struct io_ring_ctx *ctx = req->ctx;
-
if (req->flags & REQ_F_NEED_CLEANUP)
io_cleanup_req(req);
kfree(req->io);
- if (req->file) {
- if (req->flags & REQ_F_FIXED_FILE)
- percpu_ref_put(&ctx->file_data->refs);
- else
- fput(req->file);
- }
+ if (req->file)
+ io_put_file(req, req->file, (req->flags & REQ_F_FIXED_FILE));
io_req_work_drop_env(req);
}
io_queue_async_work(nxt);
}
+static void io_link_work_cb(struct io_wq_work **workptr)
+{
+ struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
+ struct io_kiocb *link;
+
+ link = list_first_entry(&req->link_list, struct io_kiocb, link_list);
+ io_queue_linked_timeout(link);
+ io_wq_submit_work(workptr);
+}
+
+static void io_wq_assign_next(struct io_wq_work **workptr, struct io_kiocb *nxt)
+{
+ struct io_kiocb *link;
+ const struct io_op_def *def = &io_op_defs[nxt->opcode];
+
+ if ((nxt->flags & REQ_F_ISREG) && def->hash_reg_file)
+ io_wq_hash_work(&nxt->work, file_inode(nxt->file));
+
+ *workptr = &nxt->work;
+ link = io_prep_linked_timeout(nxt);
+ if (link)
+ nxt->work.func = io_link_work_cb;
+}
+
/*
* Drop reference to request, return next in chain (if there is one) if this
* was the last reference to this request.
io_free_req(req);
}
+static void io_steal_work(struct io_kiocb *req,
+ struct io_wq_work **workptr)
+{
+ /*
+ * It's in an io-wq worker, so there always should be at least
+ * one reference, which will be dropped in io_put_work() just
+ * after the current handler returns.
+ *
+ * It also means, that if the counter dropped to 1, then there is
+ * no asynchronous users left, so it's safe to steal the next work.
+ */
+ if (refcount_read(&req->refs) == 1) {
+ struct io_kiocb *nxt = NULL;
+
+ io_req_find_next(req, &nxt);
+ if (nxt)
+ io_wq_assign_next(workptr, nxt);
+ }
+}
+
/*
* Must only be used if we don't need to care about links, usually from
* within the completion handling itself.
return true;
}
+static int io_put_kbuf(struct io_kiocb *req)
+{
+ struct io_buffer *kbuf;
+ int cflags;
+
+ kbuf = (struct io_buffer *) (unsigned long) req->rw.addr;
+ cflags = kbuf->bid << IORING_CQE_BUFFER_SHIFT;
+ cflags |= IORING_CQE_F_BUFFER;
+ req->rw.addr = 0;
+ kfree(kbuf);
+ return cflags;
+}
+
/*
* Find and free completed poll iocbs
*/
rb.to_free = rb.need_iter = 0;
while (!list_empty(done)) {
+ int cflags = 0;
+
req = list_first_entry(done, struct io_kiocb, list);
list_del(&req->list);
- io_cqring_fill_event(req, req->result);
+ if (req->flags & REQ_F_BUFFER_SELECTED)
+ cflags = io_put_kbuf(req);
+
+ __io_cqring_fill_event(req, req->result, cflags);
(*nr_events)++;
if (refcount_dec_and_test(&req->refs) &&
}
io_commit_cqring(ctx);
+ if (ctx->flags & IORING_SETUP_SQPOLL)
+ io_cqring_ev_posted(ctx);
io_free_req_many(ctx, &rb);
}
static void io_complete_rw_common(struct kiocb *kiocb, long res)
{
struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);
+ int cflags = 0;
if (kiocb->ki_flags & IOCB_WRITE)
kiocb_end_write(req);
if (res != req->result)
req_set_fail_links(req);
- io_cqring_add_event(req, res);
+ if (req->flags & REQ_F_BUFFER_SELECTED)
+ cflags = io_put_kbuf(req);
+ __io_cqring_add_event(req, res, cflags);
}
static void io_complete_rw(struct kiocb *kiocb, long res, long res2)
io_put_req(req);
}
-static struct io_kiocb *__io_complete_rw(struct kiocb *kiocb, long res)
-{
- struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);
- struct io_kiocb *nxt = NULL;
-
- io_complete_rw_common(kiocb, res);
- io_put_req_find_next(req, &nxt);
-
- return nxt;
-}
-
static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)
{
struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);
* assuming most submissions are for one file, or at least that each file
* has more than one submission.
*/
-static struct file *io_file_get(struct io_submit_state *state, int fd)
+static struct file *__io_file_get(struct io_submit_state *state, int fd)
{
if (!state)
return fget(fd);
req->rw.addr = READ_ONCE(sqe->addr);
req->rw.len = READ_ONCE(sqe->len);
- /* we own ->private, reuse it for the buffer index */
+ /* we own ->private, reuse it for the buffer index / buffer ID */
req->rw.kiocb.private = (void *) (unsigned long)
READ_ONCE(sqe->buf_index);
return 0;
}
}
-static void kiocb_done(struct kiocb *kiocb, ssize_t ret, struct io_kiocb **nxt,
- bool in_async)
+static void kiocb_done(struct kiocb *kiocb, ssize_t ret)
{
struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);
if (req->flags & REQ_F_CUR_POS)
req->file->f_pos = kiocb->ki_pos;
- if (in_async && ret >= 0 && kiocb->ki_complete == io_complete_rw)
- *nxt = __io_complete_rw(kiocb, ret);
+ if (ret >= 0 && kiocb->ki_complete == io_complete_rw)
+ io_complete_rw(kiocb, ret, 0);
else
io_rw_done(kiocb, ret);
}
return len;
}
+static void io_ring_submit_unlock(struct io_ring_ctx *ctx, bool needs_lock)
+{
+ if (needs_lock)
+ mutex_unlock(&ctx->uring_lock);
+}
+
+static void io_ring_submit_lock(struct io_ring_ctx *ctx, bool needs_lock)
+{
+ /*
+ * "Normal" inline submissions always hold the uring_lock, since we
+ * grab it from the system call. Same is true for the SQPOLL offload.
+ * The only exception is when we've detached the request and issue it
+ * from an async worker thread, grab the lock for that case.
+ */
+ if (needs_lock)
+ mutex_lock(&ctx->uring_lock);
+}
+
+static struct io_buffer *io_buffer_select(struct io_kiocb *req, size_t *len,
+ int bgid, struct io_buffer *kbuf,
+ bool needs_lock)
+{
+ struct io_buffer *head;
+
+ if (req->flags & REQ_F_BUFFER_SELECTED)
+ return kbuf;
+
+ io_ring_submit_lock(req->ctx, needs_lock);
+
+ lockdep_assert_held(&req->ctx->uring_lock);
+
+ head = idr_find(&req->ctx->io_buffer_idr, bgid);
+ if (head) {
+ if (!list_empty(&head->list)) {
+ kbuf = list_last_entry(&head->list, struct io_buffer,
+ list);
+ list_del(&kbuf->list);
+ } else {
+ kbuf = head;
+ idr_remove(&req->ctx->io_buffer_idr, bgid);
+ }
+ if (*len > kbuf->len)
+ *len = kbuf->len;
+ } else {
+ kbuf = ERR_PTR(-ENOBUFS);
+ }
+
+ io_ring_submit_unlock(req->ctx, needs_lock);
+
+ return kbuf;
+}
+
+static void __user *io_rw_buffer_select(struct io_kiocb *req, size_t *len,
+ bool needs_lock)
+{
+ struct io_buffer *kbuf;
+ int bgid;
+
+ kbuf = (struct io_buffer *) (unsigned long) req->rw.addr;
+ bgid = (int) (unsigned long) req->rw.kiocb.private;
+ kbuf = io_buffer_select(req, len, bgid, kbuf, needs_lock);
+ if (IS_ERR(kbuf))
+ return kbuf;
+ req->rw.addr = (u64) (unsigned long) kbuf;
+ req->flags |= REQ_F_BUFFER_SELECTED;
+ return u64_to_user_ptr(kbuf->addr);
+}
+
+#ifdef CONFIG_COMPAT
+static ssize_t io_compat_import(struct io_kiocb *req, struct iovec *iov,
+ bool needs_lock)
+{
+ struct compat_iovec __user *uiov;
+ compat_ssize_t clen;
+ void __user *buf;
+ ssize_t len;
+
+ uiov = u64_to_user_ptr(req->rw.addr);
+ if (!access_ok(uiov, sizeof(*uiov)))
+ return -EFAULT;
+ if (__get_user(clen, &uiov->iov_len))
+ return -EFAULT;
+ if (clen < 0)
+ return -EINVAL;
+
+ len = clen;
+ buf = io_rw_buffer_select(req, &len, needs_lock);
+ if (IS_ERR(buf))
+ return PTR_ERR(buf);
+ iov[0].iov_base = buf;
+ iov[0].iov_len = (compat_size_t) len;
+ return 0;
+}
+#endif
+
+static ssize_t __io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
+ bool needs_lock)
+{
+ struct iovec __user *uiov = u64_to_user_ptr(req->rw.addr);
+ void __user *buf;
+ ssize_t len;
+
+ if (copy_from_user(iov, uiov, sizeof(*uiov)))
+ return -EFAULT;
+
+ len = iov[0].iov_len;
+ if (len < 0)
+ return -EINVAL;
+ buf = io_rw_buffer_select(req, &len, needs_lock);
+ if (IS_ERR(buf))
+ return PTR_ERR(buf);
+ iov[0].iov_base = buf;
+ iov[0].iov_len = len;
+ return 0;
+}
+
+static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
+ bool needs_lock)
+{
+ if (req->flags & REQ_F_BUFFER_SELECTED)
+ return 0;
+ if (!req->rw.len)
+ return 0;
+ else if (req->rw.len > 1)
+ return -EINVAL;
+
+#ifdef CONFIG_COMPAT
+ if (req->ctx->compat)
+ return io_compat_import(req, iov, needs_lock);
+#endif
+
+ return __io_iov_buffer_select(req, iov, needs_lock);
+}
+
static ssize_t io_import_iovec(int rw, struct io_kiocb *req,
- struct iovec **iovec, struct iov_iter *iter)
+ struct iovec **iovec, struct iov_iter *iter,
+ bool needs_lock)
{
void __user *buf = u64_to_user_ptr(req->rw.addr);
size_t sqe_len = req->rw.len;
+ ssize_t ret;
u8 opcode;
opcode = req->opcode;
return io_import_fixed(req, rw, iter);
}
- /* buffer index only valid with fixed read/write */
- if (req->rw.kiocb.private)
+ /* buffer index only valid with fixed read/write, or buffer select */
+ if (req->rw.kiocb.private && !(req->flags & REQ_F_BUFFER_SELECT))
return -EINVAL;
if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) {
- ssize_t ret;
+ if (req->flags & REQ_F_BUFFER_SELECT) {
+ buf = io_rw_buffer_select(req, &sqe_len, needs_lock);
+ if (IS_ERR(buf)) {
+ *iovec = NULL;
+ return PTR_ERR(buf);
+ }
+ req->rw.len = sqe_len;
+ }
+
ret = import_single_range(rw, buf, sqe_len, *iovec, iter);
*iovec = NULL;
return ret < 0 ? ret : sqe_len;
return iorw->size;
}
+ if (req->flags & REQ_F_BUFFER_SELECT) {
+ ret = io_iov_buffer_select(req, *iovec, needs_lock);
+ if (!ret) {
+ ret = (*iovec)->iov_len;
+ iov_iter_init(iter, rw, *iovec, 1, ret);
+ }
+ *iovec = NULL;
+ return ret;
+ }
+
#ifdef CONFIG_COMPAT
if (req->ctx->compat)
return compat_import_iovec(rw, buf, sqe_len, UIO_FASTIOV,
}
}
+static inline int __io_alloc_async_ctx(struct io_kiocb *req)
+{
+ req->io = kmalloc(sizeof(*req->io), GFP_KERNEL);
+ return req->io == NULL;
+}
+
static int io_alloc_async_ctx(struct io_kiocb *req)
{
if (!io_op_defs[req->opcode].async_ctx)
return 0;
- req->io = kmalloc(sizeof(*req->io), GFP_KERNEL);
- return req->io == NULL;
+
+ return __io_alloc_async_ctx(req);
}
static int io_setup_async_rw(struct io_kiocb *req, ssize_t io_size,
if (!io_op_defs[req->opcode].async_ctx)
return 0;
if (!req->io) {
- if (io_alloc_async_ctx(req))
+ if (__io_alloc_async_ctx(req))
return -ENOMEM;
io_req_map_rw(req, io_size, iovec, fast_iov, iter);
io = req->io;
io->rw.iov = io->rw.fast_iov;
req->io = NULL;
- ret = io_import_iovec(READ, req, &io->rw.iov, &iter);
+ ret = io_import_iovec(READ, req, &io->rw.iov, &iter, !force_nonblock);
req->io = io;
if (ret < 0)
return ret;
return 0;
}
-static int io_read(struct io_kiocb *req, struct io_kiocb **nxt,
- bool force_nonblock)
+static int io_read(struct io_kiocb *req, bool force_nonblock)
{
struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
struct kiocb *kiocb = &req->rw.kiocb;
size_t iov_count;
ssize_t io_size, ret;
- ret = io_import_iovec(READ, req, &iovec, &iter);
+ ret = io_import_iovec(READ, req, &iovec, &iter, !force_nonblock);
if (ret < 0)
return ret;
/* Ensure we clear previously set non-block flag */
if (!force_nonblock)
- req->rw.kiocb.ki_flags &= ~IOCB_NOWAIT;
+ kiocb->ki_flags &= ~IOCB_NOWAIT;
req->result = 0;
io_size = ret;
* If the file doesn't support async, mark it as REQ_F_MUST_PUNT so
* we know to async punt it even if it was opened O_NONBLOCK
*/
- if (force_nonblock && !io_file_supports_async(req->file)) {
- req->flags |= REQ_F_MUST_PUNT;
+ if (force_nonblock && !io_file_supports_async(req->file))
goto copy_iov;
- }
iov_count = iov_iter_count(&iter);
ret = rw_verify_area(READ, req->file, &kiocb->ki_pos, iov_count);
/* Catch -EAGAIN return for forced non-blocking submission */
if (!force_nonblock || ret2 != -EAGAIN) {
- kiocb_done(kiocb, ret2, nxt, req->in_async);
+ kiocb_done(kiocb, ret2);
} else {
copy_iov:
ret = io_setup_async_rw(req, io_size, iovec,
inline_vecs, &iter);
if (ret)
goto out_free;
+ /* any defer here is final, must blocking retry */
+ if (!(req->flags & REQ_F_NOWAIT))
+ req->flags |= REQ_F_MUST_PUNT;
return -EAGAIN;
}
}
if (unlikely(!(req->file->f_mode & FMODE_WRITE)))
return -EBADF;
+ req->fsize = rlimit(RLIMIT_FSIZE);
+
/* either don't need iovec imported or already have it */
if (!req->io || req->flags & REQ_F_NEED_CLEANUP)
return 0;
io = req->io;
io->rw.iov = io->rw.fast_iov;
req->io = NULL;
- ret = io_import_iovec(WRITE, req, &io->rw.iov, &iter);
+ ret = io_import_iovec(WRITE, req, &io->rw.iov, &iter, !force_nonblock);
req->io = io;
if (ret < 0)
return ret;
return 0;
}
-static int io_write(struct io_kiocb *req, struct io_kiocb **nxt,
- bool force_nonblock)
+static int io_write(struct io_kiocb *req, bool force_nonblock)
{
struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
struct kiocb *kiocb = &req->rw.kiocb;
size_t iov_count;
ssize_t ret, io_size;
- ret = io_import_iovec(WRITE, req, &iovec, &iter);
+ ret = io_import_iovec(WRITE, req, &iovec, &iter, !force_nonblock);
if (ret < 0)
return ret;
* If the file doesn't support async, mark it as REQ_F_MUST_PUNT so
* we know to async punt it even if it was opened O_NONBLOCK
*/
- if (force_nonblock && !io_file_supports_async(req->file)) {
- req->flags |= REQ_F_MUST_PUNT;
+ if (force_nonblock && !io_file_supports_async(req->file))
goto copy_iov;
- }
/* file path doesn't support NOWAIT for non-direct_IO */
if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT) &&
}
kiocb->ki_flags |= IOCB_WRITE;
+ if (!force_nonblock)
+ current->signal->rlim[RLIMIT_FSIZE].rlim_cur = req->fsize;
+
if (req->file->f_op->write_iter)
ret2 = call_write_iter(req->file, kiocb, &iter);
else
ret2 = loop_rw_iter(WRITE, req->file, kiocb, &iter);
+
+ if (!force_nonblock)
+ current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY;
+
/*
- * Raw bdev writes will -EOPNOTSUPP for IOCB_NOWAIT. Just
+ * Raw bdev writes will return -EOPNOTSUPP for IOCB_NOWAIT. Just
* retry them without IOCB_NOWAIT.
*/
if (ret2 == -EOPNOTSUPP && (kiocb->ki_flags & IOCB_NOWAIT))
ret2 = -EAGAIN;
if (!force_nonblock || ret2 != -EAGAIN) {
- kiocb_done(kiocb, ret2, nxt, req->in_async);
+ kiocb_done(kiocb, ret2);
} else {
copy_iov:
ret = io_setup_async_rw(req, io_size, iovec,
inline_vecs, &iter);
if (ret)
goto out_free;
+ /* any defer here is final, must blocking retry */
+ req->flags |= REQ_F_MUST_PUNT;
return -EAGAIN;
}
}
return ret;
}
+static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+ struct io_splice* sp = &req->splice;
+ unsigned int valid_flags = SPLICE_F_FD_IN_FIXED | SPLICE_F_ALL;
+ int ret;
+
+ if (req->flags & REQ_F_NEED_CLEANUP)
+ return 0;
+
+ sp->file_in = NULL;
+ sp->off_in = READ_ONCE(sqe->splice_off_in);
+ sp->off_out = READ_ONCE(sqe->off);
+ sp->len = READ_ONCE(sqe->len);
+ sp->flags = READ_ONCE(sqe->splice_flags);
+
+ if (unlikely(sp->flags & ~valid_flags))
+ return -EINVAL;
+
+ ret = io_file_get(NULL, req, READ_ONCE(sqe->splice_fd_in), &sp->file_in,
+ (sp->flags & SPLICE_F_FD_IN_FIXED));
+ if (ret)
+ return ret;
+ req->flags |= REQ_F_NEED_CLEANUP;
+
+ if (!S_ISREG(file_inode(sp->file_in)->i_mode))
+ req->work.flags |= IO_WQ_WORK_UNBOUND;
+
+ return 0;
+}
+
+static bool io_splice_punt(struct file *file)
+{
+ if (get_pipe_info(file))
+ return false;
+ if (!io_file_supports_async(file))
+ return true;
+ return !(file->f_mode & O_NONBLOCK);
+}
+
+static int io_splice(struct io_kiocb *req, bool force_nonblock)
+{
+ struct io_splice *sp = &req->splice;
+ struct file *in = sp->file_in;
+ struct file *out = sp->file_out;
+ unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
+ loff_t *poff_in, *poff_out;
+ long ret;
+
+ if (force_nonblock) {
+ if (io_splice_punt(in) || io_splice_punt(out))
+ return -EAGAIN;
+ flags |= SPLICE_F_NONBLOCK;
+ }
+
+ poff_in = (sp->off_in == -1) ? NULL : &sp->off_in;
+ poff_out = (sp->off_out == -1) ? NULL : &sp->off_out;
+ ret = do_splice(in, poff_in, out, poff_out, sp->len, flags);
+ if (force_nonblock && ret == -EAGAIN)
+ return -EAGAIN;
+
+ io_put_file(req, in, (sp->flags & SPLICE_F_FD_IN_FIXED));
+ req->flags &= ~REQ_F_NEED_CLEANUP;
+
+ io_cqring_add_event(req, ret);
+ if (ret != sp->len)
+ req_set_fail_links(req);
+ io_put_req(req);
+ return 0;
+}
+
/*
* IORING_OP_NOP just posts a completion event, nothing else.
*/
return false;
}
-static void io_link_work_cb(struct io_wq_work **workptr)
-{
- struct io_wq_work *work = *workptr;
- struct io_kiocb *link = work->data;
-
- io_queue_linked_timeout(link);
- work->func = io_wq_submit_work;
-}
-
-static void io_wq_assign_next(struct io_wq_work **workptr, struct io_kiocb *nxt)
-{
- struct io_kiocb *link;
-
- io_prep_async_work(nxt, &link);
- *workptr = &nxt->work;
- if (link) {
- nxt->work.flags |= IO_WQ_WORK_CB;
- nxt->work.func = io_link_work_cb;
- nxt->work.data = link;
- }
-}
-
-static void io_fsync_finish(struct io_wq_work **workptr)
+static void __io_fsync(struct io_kiocb *req)
{
- struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
loff_t end = req->sync.off + req->sync.len;
- struct io_kiocb *nxt = NULL;
int ret;
- if (io_req_cancelled(req))
- return;
-
ret = vfs_fsync_range(req->file, req->sync.off,
end > 0 ? end : LLONG_MAX,
req->sync.flags & IORING_FSYNC_DATASYNC);
if (ret < 0)
req_set_fail_links(req);
io_cqring_add_event(req, ret);
- io_put_req_find_next(req, &nxt);
- if (nxt)
- io_wq_assign_next(workptr, nxt);
+ io_put_req(req);
}
-static int io_fsync(struct io_kiocb *req, struct io_kiocb **nxt,
- bool force_nonblock)
+static void io_fsync_finish(struct io_wq_work **workptr)
{
- struct io_wq_work *work, *old_work;
+ struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
+
+ if (io_req_cancelled(req))
+ return;
+ __io_fsync(req);
+ io_steal_work(req, workptr);
+}
+static int io_fsync(struct io_kiocb *req, bool force_nonblock)
+{
/* fsync always requires a blocking context */
if (force_nonblock) {
- io_put_req(req);
req->work.func = io_fsync_finish;
return -EAGAIN;
}
-
- work = old_work = &req->work;
- io_fsync_finish(&work);
- if (work && work != old_work)
- *nxt = container_of(work, struct io_kiocb, work);
+ __io_fsync(req);
return 0;
}
-static void io_fallocate_finish(struct io_wq_work **workptr)
+static void __io_fallocate(struct io_kiocb *req)
{
- struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
- struct io_kiocb *nxt = NULL;
int ret;
- if (io_req_cancelled(req))
- return;
-
+ current->signal->rlim[RLIMIT_FSIZE].rlim_cur = req->fsize;
ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off,
req->sync.len);
+ current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY;
if (ret < 0)
req_set_fail_links(req);
io_cqring_add_event(req, ret);
- io_put_req_find_next(req, &nxt);
- if (nxt)
- io_wq_assign_next(workptr, nxt);
+ io_put_req(req);
+}
+
+static void io_fallocate_finish(struct io_wq_work **workptr)
+{
+ struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
+
+ if (io_req_cancelled(req))
+ return;
+ __io_fallocate(req);
+ io_steal_work(req, workptr);
}
static int io_fallocate_prep(struct io_kiocb *req,
req->sync.off = READ_ONCE(sqe->off);
req->sync.len = READ_ONCE(sqe->addr);
req->sync.mode = READ_ONCE(sqe->len);
+ req->fsize = rlimit(RLIMIT_FSIZE);
return 0;
}
-static int io_fallocate(struct io_kiocb *req, struct io_kiocb **nxt,
- bool force_nonblock)
+static int io_fallocate(struct io_kiocb *req, bool force_nonblock)
{
- struct io_wq_work *work, *old_work;
-
/* fallocate always requiring blocking context */
if (force_nonblock) {
- io_put_req(req);
req->work.func = io_fallocate_finish;
return -EAGAIN;
}
- work = old_work = &req->work;
- io_fallocate_finish(&work);
- if (work && work != old_work)
- *nxt = container_of(work, struct io_kiocb, work);
-
+ __io_fallocate(req);
return 0;
}
return 0;
}
-static int io_openat2(struct io_kiocb *req, struct io_kiocb **nxt,
- bool force_nonblock)
+static int io_openat2(struct io_kiocb *req, bool force_nonblock)
{
struct open_flags op;
struct file *file;
if (ret < 0)
req_set_fail_links(req);
io_cqring_add_event(req, ret);
- io_put_req_find_next(req, nxt);
+ io_put_req(req);
return 0;
}
-static int io_openat(struct io_kiocb *req, struct io_kiocb **nxt,
- bool force_nonblock)
+static int io_openat(struct io_kiocb *req, bool force_nonblock)
{
req->open.how = build_open_how(req->open.how.flags, req->open.how.mode);
- return io_openat2(req, nxt, force_nonblock);
+ return io_openat2(req, force_nonblock);
+}
+
+static int io_remove_buffers_prep(struct io_kiocb *req,
+ const struct io_uring_sqe *sqe)
+{
+ struct io_provide_buf *p = &req->pbuf;
+ u64 tmp;
+
+ if (sqe->ioprio || sqe->rw_flags || sqe->addr || sqe->len || sqe->off)
+ return -EINVAL;
+
+ tmp = READ_ONCE(sqe->fd);
+ if (!tmp || tmp > USHRT_MAX)
+ return -EINVAL;
+
+ memset(p, 0, sizeof(*p));
+ p->nbufs = tmp;
+ p->bgid = READ_ONCE(sqe->buf_group);
+ return 0;
+}
+
+static int __io_remove_buffers(struct io_ring_ctx *ctx, struct io_buffer *buf,
+ int bgid, unsigned nbufs)
+{
+ unsigned i = 0;
+
+ /* shouldn't happen */
+ if (!nbufs)
+ return 0;
+
+ /* the head kbuf is the list itself */
+ while (!list_empty(&buf->list)) {
+ struct io_buffer *nxt;
+
+ nxt = list_first_entry(&buf->list, struct io_buffer, list);
+ list_del(&nxt->list);
+ kfree(nxt);
+ if (++i == nbufs)
+ return i;
+ }
+ i++;
+ kfree(buf);
+ idr_remove(&ctx->io_buffer_idr, bgid);
+
+ return i;
+}
+
+static int io_remove_buffers(struct io_kiocb *req, bool force_nonblock)
+{
+ struct io_provide_buf *p = &req->pbuf;
+ struct io_ring_ctx *ctx = req->ctx;
+ struct io_buffer *head;
+ int ret = 0;
+
+ io_ring_submit_lock(ctx, !force_nonblock);
+
+ lockdep_assert_held(&ctx->uring_lock);
+
+ ret = -ENOENT;
+ head = idr_find(&ctx->io_buffer_idr, p->bgid);
+ if (head)
+ ret = __io_remove_buffers(ctx, head, p->bgid, p->nbufs);
+
+ io_ring_submit_lock(ctx, !force_nonblock);
+ if (ret < 0)
+ req_set_fail_links(req);
+ io_cqring_add_event(req, ret);
+ io_put_req(req);
+ return 0;
+}
+
+static int io_provide_buffers_prep(struct io_kiocb *req,
+ const struct io_uring_sqe *sqe)
+{
+ struct io_provide_buf *p = &req->pbuf;
+ u64 tmp;
+
+ if (sqe->ioprio || sqe->rw_flags)
+ return -EINVAL;
+
+ tmp = READ_ONCE(sqe->fd);
+ if (!tmp || tmp > USHRT_MAX)
+ return -E2BIG;
+ p->nbufs = tmp;
+ p->addr = READ_ONCE(sqe->addr);
+ p->len = READ_ONCE(sqe->len);
+
+ if (!access_ok(u64_to_user_ptr(p->addr), p->len))
+ return -EFAULT;
+
+ p->bgid = READ_ONCE(sqe->buf_group);
+ tmp = READ_ONCE(sqe->off);
+ if (tmp > USHRT_MAX)
+ return -E2BIG;
+ p->bid = tmp;
+ return 0;
+}
+
+static int io_add_buffers(struct io_provide_buf *pbuf, struct io_buffer **head)
+{
+ struct io_buffer *buf;
+ u64 addr = pbuf->addr;
+ int i, bid = pbuf->bid;
+
+ for (i = 0; i < pbuf->nbufs; i++) {
+ buf = kmalloc(sizeof(*buf), GFP_KERNEL);
+ if (!buf)
+ break;
+
+ buf->addr = addr;
+ buf->len = pbuf->len;
+ buf->bid = bid;
+ addr += pbuf->len;
+ bid++;
+ if (!*head) {
+ INIT_LIST_HEAD(&buf->list);
+ *head = buf;
+ } else {
+ list_add_tail(&buf->list, &(*head)->list);
+ }
+ }
+
+ return i ? i : -ENOMEM;
+}
+
+static int io_provide_buffers(struct io_kiocb *req, bool force_nonblock)
+{
+ struct io_provide_buf *p = &req->pbuf;
+ struct io_ring_ctx *ctx = req->ctx;
+ struct io_buffer *head, *list;
+ int ret = 0;
+
+ io_ring_submit_lock(ctx, !force_nonblock);
+
+ lockdep_assert_held(&ctx->uring_lock);
+
+ list = head = idr_find(&ctx->io_buffer_idr, p->bgid);
+
+ ret = io_add_buffers(p, &head);
+ if (ret < 0)
+ goto out;
+
+ if (!list) {
+ ret = idr_alloc(&ctx->io_buffer_idr, head, p->bgid, p->bgid + 1,
+ GFP_KERNEL);
+ if (ret < 0) {
+ __io_remove_buffers(ctx, head, p->bgid, -1U);
+ goto out;
+ }
+ }
+out:
+ io_ring_submit_unlock(ctx, !force_nonblock);
+ if (ret < 0)
+ req_set_fail_links(req);
+ io_cqring_add_event(req, ret);
+ io_put_req(req);
+ return 0;
}
static int io_epoll_ctl_prep(struct io_kiocb *req,
#endif
}
-static int io_epoll_ctl(struct io_kiocb *req, struct io_kiocb **nxt,
- bool force_nonblock)
+static int io_epoll_ctl(struct io_kiocb *req, bool force_nonblock)
{
#if defined(CONFIG_EPOLL)
struct io_epoll *ie = &req->epoll;
if (ret < 0)
req_set_fail_links(req);
io_cqring_add_event(req, ret);
- io_put_req_find_next(req, nxt);
+ io_put_req(req);
return 0;
#else
return -EOPNOTSUPP;
#endif
}
-static int io_madvise(struct io_kiocb *req, struct io_kiocb **nxt,
- bool force_nonblock)
+static int io_madvise(struct io_kiocb *req, bool force_nonblock)
{
#if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU)
struct io_madvise *ma = &req->madvise;
if (ret < 0)
req_set_fail_links(req);
io_cqring_add_event(req, ret);
- io_put_req_find_next(req, nxt);
+ io_put_req(req);
return 0;
#else
return -EOPNOTSUPP;
return 0;
}
-static int io_fadvise(struct io_kiocb *req, struct io_kiocb **nxt,
- bool force_nonblock)
+static int io_fadvise(struct io_kiocb *req, bool force_nonblock)
{
struct io_fadvise *fa = &req->fadvise;
int ret;
if (ret < 0)
req_set_fail_links(req);
io_cqring_add_event(req, ret);
- io_put_req_find_next(req, nxt);
+ io_put_req(req);
return 0;
}
return 0;
}
-static int io_statx(struct io_kiocb *req, struct io_kiocb **nxt,
- bool force_nonblock)
+static int io_statx(struct io_kiocb *req, bool force_nonblock)
{
struct io_open *ctx = &req->open;
unsigned lookup_flags;
if (ret < 0)
req_set_fail_links(req);
io_cqring_add_event(req, ret);
- io_put_req_find_next(req, nxt);
+ io_put_req(req);
return 0;
}
}
/* only called when __close_fd_get_file() is done */
-static void __io_close_finish(struct io_kiocb *req, struct io_kiocb **nxt)
+static void __io_close_finish(struct io_kiocb *req)
{
int ret;
req_set_fail_links(req);
io_cqring_add_event(req, ret);
fput(req->close.put_file);
- io_put_req_find_next(req, nxt);
+ io_put_req(req);
}
static void io_close_finish(struct io_wq_work **workptr)
{
struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
- struct io_kiocb *nxt = NULL;
/* not cancellable, don't do io_req_cancelled() */
- __io_close_finish(req, &nxt);
- if (nxt)
- io_wq_assign_next(workptr, nxt);
+ __io_close_finish(req);
+ io_steal_work(req, workptr);
}
-static int io_close(struct io_kiocb *req, struct io_kiocb **nxt,
- bool force_nonblock)
+static int io_close(struct io_kiocb *req, bool force_nonblock)
{
int ret;
return ret;
/* if the file has a flush method, be safe and punt to async */
- if (req->close.put_file->f_op->flush && !io_wq_current_is_worker())
- goto eagain;
+ if (req->close.put_file->f_op->flush && force_nonblock) {
+ /* submission ref will be dropped, take it for async */
+ refcount_inc(&req->refs);
+
+ req->work.func = io_close_finish;
+ /*
+ * Do manual async queue here to avoid grabbing files - we don't
+ * need the files, and it'll cause io_close_finish() to close
+ * the file again and cause a double CQE entry for this request
+ */
+ io_queue_async_work(req);
+ return 0;
+ }
/*
* No ->flush(), safely close from here and just punt the
* fput() to async context.
*/
- __io_close_finish(req, nxt);
- return 0;
-eagain:
- req->work.func = io_close_finish;
- /*
- * Do manual async queue here to avoid grabbing files - we don't
- * need the files, and it'll cause io_close_finish() to close
- * the file again and cause a double CQE entry for this request
- */
- io_queue_async_work(req);
+ __io_close_finish(req);
return 0;
}
return 0;
}
-static void io_sync_file_range_finish(struct io_wq_work **workptr)
+static void __io_sync_file_range(struct io_kiocb *req)
{
- struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
- struct io_kiocb *nxt = NULL;
int ret;
- if (io_req_cancelled(req))
- return;
-
ret = sync_file_range(req->file, req->sync.off, req->sync.len,
req->sync.flags);
if (ret < 0)
req_set_fail_links(req);
io_cqring_add_event(req, ret);
- io_put_req_find_next(req, &nxt);
+ io_put_req(req);
+}
+
+
+static void io_sync_file_range_finish(struct io_wq_work **workptr)
+{
+ struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
+ struct io_kiocb *nxt = NULL;
+
+ if (io_req_cancelled(req))
+ return;
+ __io_sync_file_range(req);
+ io_put_req(req); /* put submission ref */
if (nxt)
io_wq_assign_next(workptr, nxt);
}
-static int io_sync_file_range(struct io_kiocb *req, struct io_kiocb **nxt,
- bool force_nonblock)
+static int io_sync_file_range(struct io_kiocb *req, bool force_nonblock)
{
- struct io_wq_work *work, *old_work;
-
/* sync_file_range always requires a blocking context */
if (force_nonblock) {
- io_put_req(req);
req->work.func = io_sync_file_range_finish;
return -EAGAIN;
}
- work = old_work = &req->work;
- io_sync_file_range_finish(&work);
- if (work && work != old_work)
- *nxt = container_of(work, struct io_kiocb, work);
+ __io_sync_file_range(req);
return 0;
}
+#if defined(CONFIG_NET)
+static int io_setup_async_msg(struct io_kiocb *req,
+ struct io_async_msghdr *kmsg)
+{
+ if (req->io)
+ return -EAGAIN;
+ if (io_alloc_async_ctx(req)) {
+ if (kmsg->iov != kmsg->fast_iov)
+ kfree(kmsg->iov);
+ return -ENOMEM;
+ }
+ req->flags |= REQ_F_NEED_CLEANUP;
+ memcpy(&req->io->msg, kmsg, sizeof(*kmsg));
+ return -EAGAIN;
+}
+
static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
-#if defined(CONFIG_NET)
struct io_sr_msg *sr = &req->sr_msg;
struct io_async_ctx *io = req->io;
int ret;
if (!ret)
req->flags |= REQ_F_NEED_CLEANUP;
return ret;
-#else
- return -EOPNOTSUPP;
-#endif
}
-static int io_sendmsg(struct io_kiocb *req, struct io_kiocb **nxt,
- bool force_nonblock)
+static int io_sendmsg(struct io_kiocb *req, bool force_nonblock)
{
-#if defined(CONFIG_NET)
struct io_async_msghdr *kmsg = NULL;
struct socket *sock;
int ret;
flags |= MSG_DONTWAIT;
ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags);
- if (force_nonblock && ret == -EAGAIN) {
- if (req->io)
- return -EAGAIN;
- if (io_alloc_async_ctx(req)) {
- if (kmsg->iov != kmsg->fast_iov)
- kfree(kmsg->iov);
- return -ENOMEM;
- }
- req->flags |= REQ_F_NEED_CLEANUP;
- memcpy(&req->io->msg, &io.msg, sizeof(io.msg));
- return -EAGAIN;
- }
+ if (force_nonblock && ret == -EAGAIN)
+ return io_setup_async_msg(req, kmsg);
if (ret == -ERESTARTSYS)
ret = -EINTR;
}
io_cqring_add_event(req, ret);
if (ret < 0)
req_set_fail_links(req);
- io_put_req_find_next(req, nxt);
+ io_put_req(req);
return 0;
-#else
- return -EOPNOTSUPP;
-#endif
}
-static int io_send(struct io_kiocb *req, struct io_kiocb **nxt,
- bool force_nonblock)
+static int io_send(struct io_kiocb *req, bool force_nonblock)
{
-#if defined(CONFIG_NET)
struct socket *sock;
int ret;
io_cqring_add_event(req, ret);
if (ret < 0)
req_set_fail_links(req);
- io_put_req_find_next(req, nxt);
+ io_put_req(req);
return 0;
-#else
- return -EOPNOTSUPP;
+}
+
+static int __io_recvmsg_copy_hdr(struct io_kiocb *req, struct io_async_ctx *io)
+{
+ struct io_sr_msg *sr = &req->sr_msg;
+ struct iovec __user *uiov;
+ size_t iov_len;
+ int ret;
+
+ ret = __copy_msghdr_from_user(&io->msg.msg, sr->msg, &io->msg.uaddr,
+ &uiov, &iov_len);
+ if (ret)
+ return ret;
+
+ if (req->flags & REQ_F_BUFFER_SELECT) {
+ if (iov_len > 1)
+ return -EINVAL;
+ if (copy_from_user(io->msg.iov, uiov, sizeof(*uiov)))
+ return -EFAULT;
+ sr->len = io->msg.iov[0].iov_len;
+ iov_iter_init(&io->msg.msg.msg_iter, READ, io->msg.iov, 1,
+ sr->len);
+ io->msg.iov = NULL;
+ } else {
+ ret = import_iovec(READ, uiov, iov_len, UIO_FASTIOV,
+ &io->msg.iov, &io->msg.msg.msg_iter);
+ if (ret > 0)
+ ret = 0;
+ }
+
+ return ret;
+}
+
+#ifdef CONFIG_COMPAT
+static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req,
+ struct io_async_ctx *io)
+{
+ struct compat_msghdr __user *msg_compat;
+ struct io_sr_msg *sr = &req->sr_msg;
+ struct compat_iovec __user *uiov;
+ compat_uptr_t ptr;
+ compat_size_t len;
+ int ret;
+
+ msg_compat = (struct compat_msghdr __user *) sr->msg;
+ ret = __get_compat_msghdr(&io->msg.msg, msg_compat, &io->msg.uaddr,
+ &ptr, &len);
+ if (ret)
+ return ret;
+
+ uiov = compat_ptr(ptr);
+ if (req->flags & REQ_F_BUFFER_SELECT) {
+ compat_ssize_t clen;
+
+ if (len > 1)
+ return -EINVAL;
+ if (!access_ok(uiov, sizeof(*uiov)))
+ return -EFAULT;
+ if (__get_user(clen, &uiov->iov_len))
+ return -EFAULT;
+ if (clen < 0)
+ return -EINVAL;
+ sr->len = io->msg.iov[0].iov_len;
+ io->msg.iov = NULL;
+ } else {
+ ret = compat_import_iovec(READ, uiov, len, UIO_FASTIOV,
+ &io->msg.iov,
+ &io->msg.msg.msg_iter);
+ if (ret < 0)
+ return ret;
+ }
+
+ return 0;
+}
+#endif
+
+static int io_recvmsg_copy_hdr(struct io_kiocb *req, struct io_async_ctx *io)
+{
+ io->msg.iov = io->msg.fast_iov;
+
+#ifdef CONFIG_COMPAT
+ if (req->ctx->compat)
+ return __io_compat_recvmsg_copy_hdr(req, io);
#endif
+
+ return __io_recvmsg_copy_hdr(req, io);
+}
+
+static struct io_buffer *io_recv_buffer_select(struct io_kiocb *req,
+ int *cflags, bool needs_lock)
+{
+ struct io_sr_msg *sr = &req->sr_msg;
+ struct io_buffer *kbuf;
+
+ if (!(req->flags & REQ_F_BUFFER_SELECT))
+ return NULL;
+
+ kbuf = io_buffer_select(req, &sr->len, sr->bgid, sr->kbuf, needs_lock);
+ if (IS_ERR(kbuf))
+ return kbuf;
+
+ sr->kbuf = kbuf;
+ req->flags |= REQ_F_BUFFER_SELECTED;
+
+ *cflags = kbuf->bid << IORING_CQE_BUFFER_SHIFT;
+ *cflags |= IORING_CQE_F_BUFFER;
+ return kbuf;
}
static int io_recvmsg_prep(struct io_kiocb *req,
const struct io_uring_sqe *sqe)
{
-#if defined(CONFIG_NET)
struct io_sr_msg *sr = &req->sr_msg;
struct io_async_ctx *io = req->io;
int ret;
sr->msg_flags = READ_ONCE(sqe->msg_flags);
sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr));
sr->len = READ_ONCE(sqe->len);
+ sr->bgid = READ_ONCE(sqe->buf_group);
#ifdef CONFIG_COMPAT
if (req->ctx->compat)
if (req->flags & REQ_F_NEED_CLEANUP)
return 0;
- io->msg.iov = io->msg.fast_iov;
- ret = recvmsg_copy_msghdr(&io->msg.msg, sr->msg, sr->msg_flags,
- &io->msg.uaddr, &io->msg.iov);
+ ret = io_recvmsg_copy_hdr(req, io);
if (!ret)
req->flags |= REQ_F_NEED_CLEANUP;
return ret;
-#else
- return -EOPNOTSUPP;
-#endif
}
-static int io_recvmsg(struct io_kiocb *req, struct io_kiocb **nxt,
- bool force_nonblock)
+static int io_recvmsg(struct io_kiocb *req, bool force_nonblock)
{
-#if defined(CONFIG_NET)
struct io_async_msghdr *kmsg = NULL;
struct socket *sock;
- int ret;
+ int ret, cflags = 0;
if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
return -EINVAL;
sock = sock_from_file(req->file, &ret);
if (sock) {
+ struct io_buffer *kbuf;
struct io_async_ctx io;
unsigned flags;
kmsg->iov = kmsg->fast_iov;
kmsg->msg.msg_iter.iov = kmsg->iov;
} else {
- struct io_sr_msg *sr = &req->sr_msg;
-
kmsg = &io.msg;
kmsg->msg.msg_name = &io.msg.addr;
- io.msg.iov = io.msg.fast_iov;
- ret = recvmsg_copy_msghdr(&io.msg.msg, sr->msg,
- sr->msg_flags, &io.msg.uaddr,
- &io.msg.iov);
+ ret = io_recvmsg_copy_hdr(req, &io);
if (ret)
return ret;
}
+ kbuf = io_recv_buffer_select(req, &cflags, !force_nonblock);
+ if (IS_ERR(kbuf)) {
+ return PTR_ERR(kbuf);
+ } else if (kbuf) {
+ kmsg->fast_iov[0].iov_base = u64_to_user_ptr(kbuf->addr);
+ iov_iter_init(&kmsg->msg.msg_iter, READ, kmsg->iov,
+ 1, req->sr_msg.len);
+ }
+
flags = req->sr_msg.msg_flags;
if (flags & MSG_DONTWAIT)
req->flags |= REQ_F_NOWAIT;
ret = __sys_recvmsg_sock(sock, &kmsg->msg, req->sr_msg.msg,
kmsg->uaddr, flags);
- if (force_nonblock && ret == -EAGAIN) {
- if (req->io)
- return -EAGAIN;
- if (io_alloc_async_ctx(req)) {
- if (kmsg->iov != kmsg->fast_iov)
- kfree(kmsg->iov);
- return -ENOMEM;
- }
- memcpy(&req->io->msg, &io.msg, sizeof(io.msg));
- req->flags |= REQ_F_NEED_CLEANUP;
- return -EAGAIN;
- }
+ if (force_nonblock && ret == -EAGAIN)
+ return io_setup_async_msg(req, kmsg);
if (ret == -ERESTARTSYS)
ret = -EINTR;
}
if (kmsg && kmsg->iov != kmsg->fast_iov)
kfree(kmsg->iov);
req->flags &= ~REQ_F_NEED_CLEANUP;
- io_cqring_add_event(req, ret);
+ __io_cqring_add_event(req, ret, cflags);
if (ret < 0)
req_set_fail_links(req);
- io_put_req_find_next(req, nxt);
+ io_put_req(req);
return 0;
-#else
- return -EOPNOTSUPP;
-#endif
}
-static int io_recv(struct io_kiocb *req, struct io_kiocb **nxt,
- bool force_nonblock)
+static int io_recv(struct io_kiocb *req, bool force_nonblock)
{
-#if defined(CONFIG_NET)
+ struct io_buffer *kbuf = NULL;
struct socket *sock;
- int ret;
+ int ret, cflags = 0;
if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
return -EINVAL;
sock = sock_from_file(req->file, &ret);
if (sock) {
struct io_sr_msg *sr = &req->sr_msg;
+ void __user *buf = sr->buf;
struct msghdr msg;
struct iovec iov;
unsigned flags;
- ret = import_single_range(READ, sr->buf, sr->len, &iov,
+ kbuf = io_recv_buffer_select(req, &cflags, !force_nonblock);
+ if (IS_ERR(kbuf))
+ return PTR_ERR(kbuf);
+ else if (kbuf)
+ buf = u64_to_user_ptr(kbuf->addr);
+
+ ret = import_single_range(READ, buf, sr->len, &iov,
&msg.msg_iter);
- if (ret)
+ if (ret) {
+ kfree(kbuf);
return ret;
+ }
+ req->flags |= REQ_F_NEED_CLEANUP;
msg.msg_name = NULL;
msg.msg_control = NULL;
msg.msg_controllen = 0;
ret = -EINTR;
}
- io_cqring_add_event(req, ret);
+ kfree(kbuf);
+ req->flags &= ~REQ_F_NEED_CLEANUP;
+ __io_cqring_add_event(req, ret, cflags);
if (ret < 0)
req_set_fail_links(req);
- io_put_req_find_next(req, nxt);
+ io_put_req(req);
return 0;
-#else
- return -EOPNOTSUPP;
-#endif
}
-
static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
-#if defined(CONFIG_NET)
struct io_accept *accept = &req->accept;
if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL)))
accept->flags = READ_ONCE(sqe->accept_flags);
accept->nofile = rlimit(RLIMIT_NOFILE);
return 0;
-#else
- return -EOPNOTSUPP;
-#endif
}
-#if defined(CONFIG_NET)
-static int __io_accept(struct io_kiocb *req, struct io_kiocb **nxt,
- bool force_nonblock)
+static int __io_accept(struct io_kiocb *req, bool force_nonblock)
{
struct io_accept *accept = &req->accept;
unsigned file_flags;
if (ret < 0)
req_set_fail_links(req);
io_cqring_add_event(req, ret);
- io_put_req_find_next(req, nxt);
+ io_put_req(req);
return 0;
}
static void io_accept_finish(struct io_wq_work **workptr)
{
struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
- struct io_kiocb *nxt = NULL;
if (io_req_cancelled(req))
return;
- __io_accept(req, &nxt, false);
- if (nxt)
- io_wq_assign_next(workptr, nxt);
+ __io_accept(req, false);
+ io_steal_work(req, workptr);
}
-#endif
-static int io_accept(struct io_kiocb *req, struct io_kiocb **nxt,
- bool force_nonblock)
+static int io_accept(struct io_kiocb *req, bool force_nonblock)
{
-#if defined(CONFIG_NET)
int ret;
- ret = __io_accept(req, nxt, force_nonblock);
+ ret = __io_accept(req, force_nonblock);
if (ret == -EAGAIN && force_nonblock) {
req->work.func = io_accept_finish;
- io_put_req(req);
return -EAGAIN;
}
return 0;
-#else
- return -EOPNOTSUPP;
-#endif
}
static int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
-#if defined(CONFIG_NET)
struct io_connect *conn = &req->connect;
struct io_async_ctx *io = req->io;
return move_addr_to_kernel(conn->addr, conn->addr_len,
&io->connect.address);
-#else
- return -EOPNOTSUPP;
-#endif
}
-static int io_connect(struct io_kiocb *req, struct io_kiocb **nxt,
- bool force_nonblock)
+static int io_connect(struct io_kiocb *req, bool force_nonblock)
{
-#if defined(CONFIG_NET)
struct io_async_ctx __io, *io;
unsigned file_flags;
int ret;
if (ret < 0)
req_set_fail_links(req);
io_cqring_add_event(req, ret);
- io_put_req_find_next(req, nxt);
+ io_put_req(req);
return 0;
-#else
+}
+#else /* !CONFIG_NET */
+static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
return -EOPNOTSUPP;
-#endif
}
-static void io_poll_remove_one(struct io_kiocb *req)
+static int io_sendmsg(struct io_kiocb *req, bool force_nonblock)
+{
+ return -EOPNOTSUPP;
+}
+
+static int io_send(struct io_kiocb *req, bool force_nonblock)
+{
+ return -EOPNOTSUPP;
+}
+
+static int io_recvmsg_prep(struct io_kiocb *req,
+ const struct io_uring_sqe *sqe)
+{
+ return -EOPNOTSUPP;
+}
+
+static int io_recvmsg(struct io_kiocb *req, bool force_nonblock)
+{
+ return -EOPNOTSUPP;
+}
+
+static int io_recv(struct io_kiocb *req, bool force_nonblock)
+{
+ return -EOPNOTSUPP;
+}
+
+static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+ return -EOPNOTSUPP;
+}
+
+static int io_accept(struct io_kiocb *req, bool force_nonblock)
+{
+ return -EOPNOTSUPP;
+}
+
+static int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+ return -EOPNOTSUPP;
+}
+
+static int io_connect(struct io_kiocb *req, bool force_nonblock)
+{
+ return -EOPNOTSUPP;
+}
+#endif /* CONFIG_NET */
+
+struct io_poll_table {
+ struct poll_table_struct pt;
+ struct io_kiocb *req;
+ int error;
+};
+
+static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt,
+ struct wait_queue_head *head)
+{
+ if (unlikely(poll->head)) {
+ pt->error = -EINVAL;
+ return;
+ }
+
+ pt->error = 0;
+ poll->head = head;
+ add_wait_queue(head, &poll->wait);
+}
+
+static void io_async_queue_proc(struct file *file, struct wait_queue_head *head,
+ struct poll_table_struct *p)
+{
+ struct io_poll_table *pt = container_of(p, struct io_poll_table, pt);
+
+ __io_queue_proc(&pt->req->apoll->poll, pt, head);
+}
+
+static int __io_async_wake(struct io_kiocb *req, struct io_poll_iocb *poll,
+ __poll_t mask, task_work_func_t func)
+{
+ struct task_struct *tsk;
+
+ /* for instances that support it check for an event match first: */
+ if (mask && !(mask & poll->events))
+ return 0;
+
+ trace_io_uring_task_add(req->ctx, req->opcode, req->user_data, mask);
+
+ list_del_init(&poll->wait.entry);
+
+ tsk = req->task;
+ req->result = mask;
+ init_task_work(&req->task_work, func);
+ /*
+ * If this fails, then the task is exiting. If that is the case, then
+ * the exit check will ultimately cancel these work items. Hence we
+ * don't need to check here and handle it specifically.
+ */
+ task_work_add(tsk, &req->task_work, true);
+ wake_up_process(tsk);
+ return 1;
+}
+
+static void io_async_task_func(struct callback_head *cb)
+{
+ struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work);
+ struct async_poll *apoll = req->apoll;
+ struct io_ring_ctx *ctx = req->ctx;
+
+ trace_io_uring_task_run(req->ctx, req->opcode, req->user_data);
+
+ WARN_ON_ONCE(!list_empty(&req->apoll->poll.wait.entry));
+
+ if (hash_hashed(&req->hash_node)) {
+ spin_lock_irq(&ctx->completion_lock);
+ hash_del(&req->hash_node);
+ spin_unlock_irq(&ctx->completion_lock);
+ }
+
+ /* restore ->work in case we need to retry again */
+ memcpy(&req->work, &apoll->work, sizeof(req->work));
+
+ __set_current_state(TASK_RUNNING);
+ mutex_lock(&ctx->uring_lock);
+ __io_queue_sqe(req, NULL);
+ mutex_unlock(&ctx->uring_lock);
+
+ kfree(apoll);
+}
+
+static int io_async_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
+ void *key)
+{
+ struct io_kiocb *req = wait->private;
+ struct io_poll_iocb *poll = &req->apoll->poll;
+
+ trace_io_uring_poll_wake(req->ctx, req->opcode, req->user_data,
+ key_to_poll(key));
+
+ return __io_async_wake(req, poll, key_to_poll(key), io_async_task_func);
+}
+
+static void io_poll_req_insert(struct io_kiocb *req)
+{
+ struct io_ring_ctx *ctx = req->ctx;
+ struct hlist_head *list;
+
+ list = &ctx->cancel_hash[hash_long(req->user_data, ctx->cancel_hash_bits)];
+ hlist_add_head(&req->hash_node, list);
+}
+
+static __poll_t __io_arm_poll_handler(struct io_kiocb *req,
+ struct io_poll_iocb *poll,
+ struct io_poll_table *ipt, __poll_t mask,
+ wait_queue_func_t wake_func)
+ __acquires(&ctx->completion_lock)
+{
+ struct io_ring_ctx *ctx = req->ctx;
+ bool cancel = false;
+
+ poll->file = req->file;
+ poll->head = NULL;
+ poll->done = poll->canceled = false;
+ poll->events = mask;
+
+ ipt->pt._key = mask;
+ ipt->req = req;
+ ipt->error = -EINVAL;
+
+ INIT_LIST_HEAD(&poll->wait.entry);
+ init_waitqueue_func_entry(&poll->wait, wake_func);
+ poll->wait.private = req;
+
+ mask = vfs_poll(req->file, &ipt->pt) & poll->events;
+
+ spin_lock_irq(&ctx->completion_lock);
+ if (likely(poll->head)) {
+ spin_lock(&poll->head->lock);
+ if (unlikely(list_empty(&poll->wait.entry))) {
+ if (ipt->error)
+ cancel = true;
+ ipt->error = 0;
+ mask = 0;
+ }
+ if (mask || ipt->error)
+ list_del_init(&poll->wait.entry);
+ else if (cancel)
+ WRITE_ONCE(poll->canceled, true);
+ else if (!poll->done) /* actually waiting for an event */
+ io_poll_req_insert(req);
+ spin_unlock(&poll->head->lock);
+ }
+
+ return mask;
+}
+
+static bool io_arm_poll_handler(struct io_kiocb *req)
+{
+ const struct io_op_def *def = &io_op_defs[req->opcode];
+ struct io_ring_ctx *ctx = req->ctx;
+ struct async_poll *apoll;
+ struct io_poll_table ipt;
+ __poll_t mask, ret;
+
+ if (!req->file || !file_can_poll(req->file))
+ return false;
+ if (req->flags & (REQ_F_MUST_PUNT | REQ_F_POLLED))
+ return false;
+ if (!def->pollin && !def->pollout)
+ return false;
+
+ apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC);
+ if (unlikely(!apoll))
+ return false;
+
+ req->flags |= REQ_F_POLLED;
+ memcpy(&apoll->work, &req->work, sizeof(req->work));
+
+ /*
+ * Don't need a reference here, as we're adding it to the task
+ * task_works list. If the task exits, the list is pruned.
+ */
+ req->task = current;
+ req->apoll = apoll;
+ INIT_HLIST_NODE(&req->hash_node);
+
+ mask = 0;
+ if (def->pollin)
+ mask |= POLLIN | POLLRDNORM;
+ if (def->pollout)
+ mask |= POLLOUT | POLLWRNORM;
+ mask |= POLLERR | POLLPRI;
+
+ ipt.pt._qproc = io_async_queue_proc;
+
+ ret = __io_arm_poll_handler(req, &apoll->poll, &ipt, mask,
+ io_async_wake);
+ if (ret) {
+ ipt.error = 0;
+ apoll->poll.done = true;
+ spin_unlock_irq(&ctx->completion_lock);
+ memcpy(&req->work, &apoll->work, sizeof(req->work));
+ kfree(apoll);
+ return false;
+ }
+ spin_unlock_irq(&ctx->completion_lock);
+ trace_io_uring_poll_arm(ctx, req->opcode, req->user_data, mask,
+ apoll->poll.events);
+ return true;
+}
+
+static bool __io_poll_remove_one(struct io_kiocb *req,
+ struct io_poll_iocb *poll)
{
- struct io_poll_iocb *poll = &req->poll;
+ bool do_complete = false;
spin_lock(&poll->head->lock);
WRITE_ONCE(poll->canceled, true);
if (!list_empty(&poll->wait.entry)) {
list_del_init(&poll->wait.entry);
- io_queue_async_work(req);
+ do_complete = true;
}
spin_unlock(&poll->head->lock);
+ return do_complete;
+}
+
+static bool io_poll_remove_one(struct io_kiocb *req)
+{
+ bool do_complete;
+
+ if (req->opcode == IORING_OP_POLL_ADD) {
+ do_complete = __io_poll_remove_one(req, &req->poll);
+ } else {
+ /* non-poll requests have submit ref still */
+ do_complete = __io_poll_remove_one(req, &req->apoll->poll);
+ if (do_complete)
+ io_put_req(req);
+ }
+
hash_del(&req->hash_node);
+
+ if (do_complete) {
+ io_cqring_fill_event(req, -ECANCELED);
+ io_commit_cqring(req->ctx);
+ req->flags |= REQ_F_COMP_LOCKED;
+ io_put_req(req);
+ }
+
+ return do_complete;
}
static void io_poll_remove_all(struct io_ring_ctx *ctx)
io_poll_remove_one(req);
}
spin_unlock_irq(&ctx->completion_lock);
+
+ io_cqring_ev_posted(ctx);
}
static int io_poll_cancel(struct io_ring_ctx *ctx, __u64 sqe_addr)
list = &ctx->cancel_hash[hash_long(sqe_addr, ctx->cancel_hash_bits)];
hlist_for_each_entry(req, list, hash_node) {
- if (sqe_addr == req->user_data) {
- io_poll_remove_one(req);
+ if (sqe_addr != req->user_data)
+ continue;
+ if (io_poll_remove_one(req))
return 0;
- }
+ return -EALREADY;
}
return -ENOENT;
struct io_ring_ctx *ctx = req->ctx;
req->poll.done = true;
- if (error)
- io_cqring_fill_event(req, error);
- else
- io_cqring_fill_event(req, mangle_poll(mask));
+ io_cqring_fill_event(req, error ? error : mangle_poll(mask));
io_commit_cqring(ctx);
}
-static void io_poll_complete_work(struct io_wq_work **workptr)
+static void io_poll_task_handler(struct io_kiocb *req, struct io_kiocb **nxt)
{
- struct io_wq_work *work = *workptr;
- struct io_kiocb *req = container_of(work, struct io_kiocb, work);
- struct io_poll_iocb *poll = &req->poll;
- struct poll_table_struct pt = { ._key = poll->events };
struct io_ring_ctx *ctx = req->ctx;
- struct io_kiocb *nxt = NULL;
- __poll_t mask = 0;
- int ret = 0;
-
- if (work->flags & IO_WQ_WORK_CANCEL) {
- WRITE_ONCE(poll->canceled, true);
- ret = -ECANCELED;
- } else if (READ_ONCE(poll->canceled)) {
- ret = -ECANCELED;
- }
-
- if (ret != -ECANCELED)
- mask = vfs_poll(poll->file, &pt) & poll->events;
- /*
- * Note that ->ki_cancel callers also delete iocb from active_reqs after
- * calling ->ki_cancel. We need the ctx_lock roundtrip here to
- * synchronize with them. In the cancellation case the list_del_init
- * itself is not actually needed, but harmless so we keep it in to
- * avoid further branches in the fast path.
- */
spin_lock_irq(&ctx->completion_lock);
- if (!mask && ret != -ECANCELED) {
- add_wait_queue(poll->head, &poll->wait);
- spin_unlock_irq(&ctx->completion_lock);
- return;
- }
hash_del(&req->hash_node);
- io_poll_complete(req, mask, ret);
+ io_poll_complete(req, req->result, 0);
+ req->flags |= REQ_F_COMP_LOCKED;
+ io_put_req_find_next(req, nxt);
spin_unlock_irq(&ctx->completion_lock);
io_cqring_ev_posted(ctx);
-
- if (ret < 0)
- req_set_fail_links(req);
- io_put_req_find_next(req, &nxt);
- if (nxt)
- io_wq_assign_next(workptr, nxt);
}
-static void __io_poll_flush(struct io_ring_ctx *ctx, struct llist_node *nodes)
+static void io_poll_task_func(struct callback_head *cb)
{
- struct io_kiocb *req, *tmp;
- struct req_batch rb;
+ struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work);
+ struct io_kiocb *nxt = NULL;
- rb.to_free = rb.need_iter = 0;
- spin_lock_irq(&ctx->completion_lock);
- llist_for_each_entry_safe(req, tmp, nodes, llist_node) {
- hash_del(&req->hash_node);
- io_poll_complete(req, req->result, 0);
+ io_poll_task_handler(req, &nxt);
+ if (nxt) {
+ struct io_ring_ctx *ctx = nxt->ctx;
- if (refcount_dec_and_test(&req->refs) &&
- !io_req_multi_free(&rb, req)) {
- req->flags |= REQ_F_COMP_LOCKED;
- io_free_req(req);
- }
+ mutex_lock(&ctx->uring_lock);
+ __io_queue_sqe(nxt, NULL);
+ mutex_unlock(&ctx->uring_lock);
}
- spin_unlock_irq(&ctx->completion_lock);
-
- io_cqring_ev_posted(ctx);
- io_free_req_many(ctx, &rb);
-}
-
-static void io_poll_flush(struct io_wq_work **workptr)
-{
- struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
- struct llist_node *nodes;
-
- nodes = llist_del_all(&req->ctx->poll_llist);
- if (nodes)
- __io_poll_flush(req->ctx, nodes);
-}
-
-static void io_poll_trigger_evfd(struct io_wq_work **workptr)
-{
- struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
-
- eventfd_signal(req->ctx->cq_ev_fd, 1);
- io_put_req(req);
}
static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
void *key)
{
- struct io_poll_iocb *poll = wait->private;
- struct io_kiocb *req = container_of(poll, struct io_kiocb, poll);
- struct io_ring_ctx *ctx = req->ctx;
- __poll_t mask = key_to_poll(key);
-
- /* for instances that support it check for an event match first: */
- if (mask && !(mask & poll->events))
- return 0;
-
- list_del_init(&poll->wait.entry);
-
- /*
- * Run completion inline if we can. We're using trylock here because
- * we are violating the completion_lock -> poll wq lock ordering.
- * If we have a link timeout we're going to need the completion_lock
- * for finalizing the request, mark us as having grabbed that already.
- */
- if (mask) {
- unsigned long flags;
-
- if (llist_empty(&ctx->poll_llist) &&
- spin_trylock_irqsave(&ctx->completion_lock, flags)) {
- bool trigger_ev;
-
- hash_del(&req->hash_node);
- io_poll_complete(req, mask, 0);
-
- trigger_ev = io_should_trigger_evfd(ctx);
- if (trigger_ev && eventfd_signal_count()) {
- trigger_ev = false;
- req->work.func = io_poll_trigger_evfd;
- } else {
- req->flags |= REQ_F_COMP_LOCKED;
- io_put_req(req);
- req = NULL;
- }
- spin_unlock_irqrestore(&ctx->completion_lock, flags);
- __io_cqring_ev_posted(ctx, trigger_ev);
- } else {
- req->result = mask;
- req->llist_node.next = NULL;
- /* if the list wasn't empty, we're done */
- if (!llist_add(&req->llist_node, &ctx->poll_llist))
- req = NULL;
- else
- req->work.func = io_poll_flush;
- }
- }
- if (req)
- io_queue_async_work(req);
+ struct io_kiocb *req = wait->private;
+ struct io_poll_iocb *poll = &req->poll;
- return 1;
+ return __io_async_wake(req, poll, key_to_poll(key), io_poll_task_func);
}
-struct io_poll_table {
- struct poll_table_struct pt;
- struct io_kiocb *req;
- int error;
-};
-
static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head,
struct poll_table_struct *p)
{
struct io_poll_table *pt = container_of(p, struct io_poll_table, pt);
- if (unlikely(pt->req->poll.head)) {
- pt->error = -EINVAL;
- return;
- }
-
- pt->error = 0;
- pt->req->poll.head = head;
- add_wait_queue(head, &pt->req->poll.wait);
-}
-
-static void io_poll_req_insert(struct io_kiocb *req)
-{
- struct io_ring_ctx *ctx = req->ctx;
- struct hlist_head *list;
-
- list = &ctx->cancel_hash[hash_long(req->user_data, ctx->cancel_hash_bits)];
- hlist_add_head(&req->hash_node, list);
+ __io_queue_proc(&pt->req->poll, pt, head);
}
static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
events = READ_ONCE(sqe->poll_events);
poll->events = demangle_poll(events) | EPOLLERR | EPOLLHUP;
+
+ /*
+ * Don't need a reference here, as we're adding it to the task
+ * task_works list. If the task exits, the list is pruned.
+ */
+ req->task = current;
return 0;
}
-static int io_poll_add(struct io_kiocb *req, struct io_kiocb **nxt)
+static int io_poll_add(struct io_kiocb *req)
{
struct io_poll_iocb *poll = &req->poll;
struct io_ring_ctx *ctx = req->ctx;
struct io_poll_table ipt;
- bool cancel = false;
__poll_t mask;
- INIT_IO_WORK(&req->work, io_poll_complete_work);
INIT_HLIST_NODE(&req->hash_node);
-
- poll->head = NULL;
- poll->done = false;
- poll->canceled = false;
-
- ipt.pt._qproc = io_poll_queue_proc;
- ipt.pt._key = poll->events;
- ipt.req = req;
- ipt.error = -EINVAL; /* same as no support for IOCB_CMD_POLL */
-
- /* initialized the list so that we can do list_empty checks */
- INIT_LIST_HEAD(&poll->wait.entry);
- init_waitqueue_func_entry(&poll->wait, io_poll_wake);
- poll->wait.private = poll;
-
INIT_LIST_HEAD(&req->list);
+ ipt.pt._qproc = io_poll_queue_proc;
- mask = vfs_poll(poll->file, &ipt.pt) & poll->events;
+ mask = __io_arm_poll_handler(req, &req->poll, &ipt, poll->events,
+ io_poll_wake);
- spin_lock_irq(&ctx->completion_lock);
- if (likely(poll->head)) {
- spin_lock(&poll->head->lock);
- if (unlikely(list_empty(&poll->wait.entry))) {
- if (ipt.error)
- cancel = true;
- ipt.error = 0;
- mask = 0;
- }
- if (mask || ipt.error)
- list_del_init(&poll->wait.entry);
- else if (cancel)
- WRITE_ONCE(poll->canceled, true);
- else if (!poll->done) /* actually waiting for an event */
- io_poll_req_insert(req);
- spin_unlock(&poll->head->lock);
- }
if (mask) { /* no async, we'd stolen it */
ipt.error = 0;
io_poll_complete(req, mask, 0);
if (mask) {
io_cqring_ev_posted(ctx);
- io_put_req_find_next(req, nxt);
+ io_put_req(req);
}
return ipt.error;
}
static void io_async_find_and_cancel(struct io_ring_ctx *ctx,
struct io_kiocb *req, __u64 sqe_addr,
- struct io_kiocb **nxt, int success_ret)
+ int success_ret)
{
unsigned long flags;
int ret;
if (ret < 0)
req_set_fail_links(req);
- io_put_req_find_next(req, nxt);
+ io_put_req(req);
}
static int io_async_cancel_prep(struct io_kiocb *req,
return 0;
}
-static int io_async_cancel(struct io_kiocb *req, struct io_kiocb **nxt)
+static int io_async_cancel(struct io_kiocb *req)
{
struct io_ring_ctx *ctx = req->ctx;
- io_async_find_and_cancel(ctx, req, req->cancel.addr, nxt, 0);
+ io_async_find_and_cancel(ctx, req, req->cancel.addr, 0);
return 0;
}
case IORING_OP_EPOLL_CTL:
ret = io_epoll_ctl_prep(req, sqe);
break;
+ case IORING_OP_SPLICE:
+ ret = io_splice_prep(req, sqe);
+ break;
+ case IORING_OP_PROVIDE_BUFFERS:
+ ret = io_provide_buffers_prep(req, sqe);
+ break;
+ case IORING_OP_REMOVE_BUFFERS:
+ ret = io_remove_buffers_prep(req, sqe);
+ break;
default:
printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
req->opcode);
case IORING_OP_READV:
case IORING_OP_READ_FIXED:
case IORING_OP_READ:
+ if (req->flags & REQ_F_BUFFER_SELECTED)
+ kfree((void *)(unsigned long)req->rw.addr);
+ /* fallthrough */
case IORING_OP_WRITEV:
case IORING_OP_WRITE_FIXED:
case IORING_OP_WRITE:
if (io->rw.iov != io->rw.fast_iov)
kfree(io->rw.iov);
break;
- case IORING_OP_SENDMSG:
case IORING_OP_RECVMSG:
+ if (req->flags & REQ_F_BUFFER_SELECTED)
+ kfree(req->sr_msg.kbuf);
+ /* fallthrough */
+ case IORING_OP_SENDMSG:
if (io->msg.iov != io->msg.fast_iov)
kfree(io->msg.iov);
break;
+ case IORING_OP_RECV:
+ if (req->flags & REQ_F_BUFFER_SELECTED)
+ kfree(req->sr_msg.kbuf);
+ break;
case IORING_OP_OPENAT:
case IORING_OP_OPENAT2:
case IORING_OP_STATX:
putname(req->open.filename);
break;
+ case IORING_OP_SPLICE:
+ io_put_file(req, req->splice.file_in,
+ (req->splice.flags & SPLICE_F_FD_IN_FIXED));
+ break;
}
req->flags &= ~REQ_F_NEED_CLEANUP;
}
static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
- struct io_kiocb **nxt, bool force_nonblock)
+ bool force_nonblock)
{
struct io_ring_ctx *ctx = req->ctx;
int ret;
if (ret < 0)
break;
}
- ret = io_read(req, nxt, force_nonblock);
+ ret = io_read(req, force_nonblock);
break;
case IORING_OP_WRITEV:
case IORING_OP_WRITE_FIXED:
if (ret < 0)
break;
}
- ret = io_write(req, nxt, force_nonblock);
+ ret = io_write(req, force_nonblock);
break;
case IORING_OP_FSYNC:
if (sqe) {
if (ret < 0)
break;
}
- ret = io_fsync(req, nxt, force_nonblock);
+ ret = io_fsync(req, force_nonblock);
break;
case IORING_OP_POLL_ADD:
if (sqe) {
if (ret)
break;
}
- ret = io_poll_add(req, nxt);
+ ret = io_poll_add(req);
break;
case IORING_OP_POLL_REMOVE:
if (sqe) {
if (ret < 0)
break;
}
- ret = io_sync_file_range(req, nxt, force_nonblock);
+ ret = io_sync_file_range(req, force_nonblock);
break;
case IORING_OP_SENDMSG:
case IORING_OP_SEND:
break;
}
if (req->opcode == IORING_OP_SENDMSG)
- ret = io_sendmsg(req, nxt, force_nonblock);
+ ret = io_sendmsg(req, force_nonblock);
else
- ret = io_send(req, nxt, force_nonblock);
+ ret = io_send(req, force_nonblock);
break;
case IORING_OP_RECVMSG:
case IORING_OP_RECV:
break;
}
if (req->opcode == IORING_OP_RECVMSG)
- ret = io_recvmsg(req, nxt, force_nonblock);
+ ret = io_recvmsg(req, force_nonblock);
else
- ret = io_recv(req, nxt, force_nonblock);
+ ret = io_recv(req, force_nonblock);
break;
case IORING_OP_TIMEOUT:
if (sqe) {
if (ret)
break;
}
- ret = io_accept(req, nxt, force_nonblock);
+ ret = io_accept(req, force_nonblock);
break;
case IORING_OP_CONNECT:
if (sqe) {
if (ret)
break;
}
- ret = io_connect(req, nxt, force_nonblock);
+ ret = io_connect(req, force_nonblock);
break;
case IORING_OP_ASYNC_CANCEL:
if (sqe) {
if (ret)
break;
}
- ret = io_async_cancel(req, nxt);
+ ret = io_async_cancel(req);
break;
case IORING_OP_FALLOCATE:
if (sqe) {
if (ret)
break;
}
- ret = io_fallocate(req, nxt, force_nonblock);
+ ret = io_fallocate(req, force_nonblock);
break;
case IORING_OP_OPENAT:
if (sqe) {
if (ret)
break;
}
- ret = io_openat(req, nxt, force_nonblock);
+ ret = io_openat(req, force_nonblock);
break;
case IORING_OP_CLOSE:
if (sqe) {
if (ret)
break;
}
- ret = io_close(req, nxt, force_nonblock);
+ ret = io_close(req, force_nonblock);
break;
case IORING_OP_FILES_UPDATE:
if (sqe) {
if (ret)
break;
}
- ret = io_statx(req, nxt, force_nonblock);
+ ret = io_statx(req, force_nonblock);
break;
case IORING_OP_FADVISE:
if (sqe) {
if (ret)
break;
}
- ret = io_fadvise(req, nxt, force_nonblock);
+ ret = io_fadvise(req, force_nonblock);
break;
case IORING_OP_MADVISE:
if (sqe) {
if (ret)
break;
}
- ret = io_madvise(req, nxt, force_nonblock);
+ ret = io_madvise(req, force_nonblock);
break;
case IORING_OP_OPENAT2:
if (sqe) {
if (ret)
break;
}
- ret = io_openat2(req, nxt, force_nonblock);
+ ret = io_openat2(req, force_nonblock);
break;
case IORING_OP_EPOLL_CTL:
if (sqe) {
if (ret)
break;
}
- ret = io_epoll_ctl(req, nxt, force_nonblock);
+ ret = io_epoll_ctl(req, force_nonblock);
+ break;
+ case IORING_OP_SPLICE:
+ if (sqe) {
+ ret = io_splice_prep(req, sqe);
+ if (ret < 0)
+ break;
+ }
+ ret = io_splice(req, force_nonblock);
+ break;
+ case IORING_OP_PROVIDE_BUFFERS:
+ if (sqe) {
+ ret = io_provide_buffers_prep(req, sqe);
+ if (ret)
+ break;
+ }
+ ret = io_provide_buffers(req, force_nonblock);
+ break;
+ case IORING_OP_REMOVE_BUFFERS:
+ if (sqe) {
+ ret = io_remove_buffers_prep(req, sqe);
+ if (ret)
+ break;
+ }
+ ret = io_remove_buffers(req, force_nonblock);
break;
default:
ret = -EINVAL;
{
struct io_wq_work *work = *workptr;
struct io_kiocb *req = container_of(work, struct io_kiocb, work);
- struct io_kiocb *nxt = NULL;
int ret = 0;
/* if NO_CANCEL is set, we must still run the work */
}
if (!ret) {
- req->in_async = true;
do {
- ret = io_issue_sqe(req, NULL, &nxt, false);
+ ret = io_issue_sqe(req, NULL, false);
/*
* We can get EAGAIN for polled IO even though we're
* forcing a sync submission from here, since we can't
} while (1);
}
- /* drop submission reference */
- io_put_req(req);
-
if (ret) {
req_set_fail_links(req);
io_cqring_add_event(req, ret);
io_put_req(req);
}
- /* if a dependent link is ready, pass it back */
- if (!ret && nxt)
- io_wq_assign_next(workptr, nxt);
+ io_steal_work(req, workptr);
}
static int io_req_needs_file(struct io_kiocb *req, int fd)
return table->files[index & IORING_FILE_TABLE_MASK];;
}
-static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req,
- const struct io_uring_sqe *sqe)
+static int io_file_get(struct io_submit_state *state, struct io_kiocb *req,
+ int fd, struct file **out_file, bool fixed)
{
struct io_ring_ctx *ctx = req->ctx;
- unsigned flags;
- int fd;
-
- flags = READ_ONCE(sqe->flags);
- fd = READ_ONCE(sqe->fd);
-
- if (!io_req_needs_file(req, fd))
- return 0;
+ struct file *file;
- if (flags & IOSQE_FIXED_FILE) {
+ if (fixed) {
if (unlikely(!ctx->file_data ||
(unsigned) fd >= ctx->nr_user_files))
return -EBADF;
fd = array_index_nospec(fd, ctx->nr_user_files);
- req->file = io_file_from_index(ctx, fd);
- if (!req->file)
+ file = io_file_from_index(ctx, fd);
+ if (!file)
return -EBADF;
- req->flags |= REQ_F_FIXED_FILE;
percpu_ref_get(&ctx->file_data->refs);
} else {
- if (req->needs_fixed_file)
- return -EBADF;
trace_io_uring_file_get(ctx, fd);
- req->file = io_file_get(state, fd);
- if (unlikely(!req->file))
+ file = __io_file_get(state, fd);
+ if (unlikely(!file))
return -EBADF;
}
+ *out_file = file;
return 0;
}
+static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req,
+ const struct io_uring_sqe *sqe)
+{
+ unsigned flags;
+ int fd;
+ bool fixed;
+
+ flags = READ_ONCE(sqe->flags);
+ fd = READ_ONCE(sqe->fd);
+
+ if (!io_req_needs_file(req, fd))
+ return 0;
+
+ fixed = (flags & IOSQE_FIXED_FILE);
+ if (unlikely(!fixed && req->needs_fixed_file))
+ return -EBADF;
+
+ return io_file_get(state, req, fd, &req->file, fixed);
+}
+
static int io_grab_files(struct io_kiocb *req)
{
int ret = -EBADF;
if (prev) {
req_set_fail_links(prev);
- io_async_find_and_cancel(ctx, req, prev->user_data, NULL,
- -ETIME);
+ io_async_find_and_cancel(ctx, req, prev->user_data, -ETIME);
io_put_req(prev);
} else {
io_cqring_add_event(req, -ETIME);
if (!(req->flags & REQ_F_LINK))
return NULL;
+ /* for polled retry, if flag is set, we already went through here */
+ if (req->flags & REQ_F_POLLED)
+ return NULL;
nxt = list_first_entry_or_null(&req->link_list, struct io_kiocb,
link_list);
static void __io_queue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
struct io_kiocb *linked_timeout;
- struct io_kiocb *nxt = NULL;
+ struct io_kiocb *nxt;
const struct cred *old_creds = NULL;
int ret;
old_creds = override_creds(req->work.creds);
}
- ret = io_issue_sqe(req, sqe, &nxt, true);
+ ret = io_issue_sqe(req, sqe, true);
/*
* We async punt it if the file wasn't marked NOWAIT, or if the file
*/
if (ret == -EAGAIN && (!(req->flags & REQ_F_NOWAIT) ||
(req->flags & REQ_F_MUST_PUNT))) {
+ if (io_arm_poll_handler(req)) {
+ if (linked_timeout)
+ io_queue_linked_timeout(linked_timeout);
+ goto exit;
+ }
punt:
if (io_op_defs[req->opcode].file_table) {
ret = io_grab_files(req);
* submit reference when the iocb is actually submitted.
*/
io_queue_async_work(req);
- goto done_req;
+ goto exit;
}
err:
+ nxt = NULL;
/* drop submission reference */
io_put_req_find_next(req, &nxt);
req_set_fail_links(req);
io_put_req(req);
}
-done_req:
if (nxt) {
req = nxt;
- nxt = NULL;
if (req->flags & REQ_F_FORCE_ASYNC)
goto punt;
goto again;
}
+exit:
if (old_creds)
revert_creds(old_creds);
}
}
#define SQE_VALID_FLAGS (IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK| \
- IOSQE_IO_HARDLINK | IOSQE_ASYNC)
+ IOSQE_IO_HARDLINK | IOSQE_ASYNC | \
+ IOSQE_BUFFER_SELECT)
static bool io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
struct io_submit_state *state, struct io_kiocb **link)
goto err_req;
}
+ if ((sqe_flags & IOSQE_BUFFER_SELECT) &&
+ !io_op_defs[req->opcode].buffer_select) {
+ ret = -EOPNOTSUPP;
+ goto err_req;
+ }
+
id = READ_ONCE(sqe->personality);
if (id) {
req->work.creds = idr_find(&ctx->personality_idr, id);
}
/* same numerical values with corresponding REQ_F_*, safe to copy */
- req->flags |= sqe_flags & (IOSQE_IO_DRAIN|IOSQE_IO_HARDLINK|
- IOSQE_ASYNC);
+ req->flags |= sqe_flags & (IOSQE_IO_DRAIN | IOSQE_IO_HARDLINK |
+ IOSQE_ASYNC | IOSQE_FIXED_FILE |
+ IOSQE_BUFFER_SELECT);
ret = io_req_set_file(state, req, sqe);
if (unlikely(ret)) {
*mm = ctx->sqo_mm;
}
- req->in_async = async;
req->needs_fixed_file = async;
trace_io_uring_submit_sqe(ctx, req->opcode, req->user_data,
true, async);
if (!list_empty(&ctx->poll_list) ||
(!time_after(jiffies, timeout) && ret != -EBUSY &&
!percpu_ref_is_dying(&ctx->refs))) {
+ if (current->task_works)
+ task_work_run();
cond_resched();
continue;
}
finish_wait(&ctx->sqo_wait, &wait);
break;
}
+ if (current->task_works) {
+ task_work_run();
+ continue;
+ }
if (signal_pending(current))
flush_signals(current);
schedule();
timeout = jiffies + ctx->sq_thread_idle;
}
+ if (current->task_works)
+ task_work_run();
+
set_fs(old_fs);
if (cur_mm) {
unuse_mm(cur_mm);
struct io_rings *rings = ctx->rings;
int ret = 0;
- if (io_cqring_events(ctx, false) >= min_events)
- return 0;
+ do {
+ if (io_cqring_events(ctx, false) >= min_events)
+ return 0;
+ if (!current->task_works)
+ break;
+ task_work_run();
+ } while (1);
if (sig) {
#ifdef CONFIG_COMPAT
do {
prepare_to_wait_exclusive(&ctx->wait, &iowq.wq,
TASK_INTERRUPTIBLE);
+ if (current->task_works)
+ task_work_run();
if (io_should_wake(&iowq, false))
break;
schedule();
struct io_file_put {
struct llist_node llist;
struct file *file;
- struct completion *done;
};
static void io_ring_file_ref_flush(struct fixed_file_data *data)
while ((node = llist_del_all(&data->put_llist)) != NULL) {
llist_for_each_entry_safe(pfile, tmp, node, llist) {
io_ring_file_put(data->ctx, pfile->file);
- if (pfile->done)
- complete(pfile->done);
- else
- kfree(pfile);
+ kfree(pfile);
}
}
}
percpu_ref_get(&data->refs);
}
-static bool io_queue_file_removal(struct fixed_file_data *data,
+static int io_queue_file_removal(struct fixed_file_data *data,
struct file *file)
{
- struct io_file_put *pfile, pfile_stack;
- DECLARE_COMPLETION_ONSTACK(done);
+ struct io_file_put *pfile;
- /*
- * If we fail allocating the struct we need for doing async reomval
- * of this file, just punt to sync and wait for it.
- */
pfile = kzalloc(sizeof(*pfile), GFP_KERNEL);
- if (!pfile) {
- pfile = &pfile_stack;
- pfile->done = &done;
- }
+ if (!pfile)
+ return -ENOMEM;
pfile->file = file;
llist_add(&pfile->llist, &data->put_llist);
-
- if (pfile == &pfile_stack) {
- percpu_ref_switch_to_atomic(&data->refs, io_atomic_switch);
- wait_for_completion(&done);
- flush_work(&data->ref_work);
- return false;
- }
-
- return true;
+ return 0;
}
static int __io_sqe_files_update(struct io_ring_ctx *ctx,
index = i & IORING_FILE_TABLE_MASK;
if (table->files[index]) {
file = io_file_from_index(ctx, index);
+ err = io_queue_file_removal(data, file);
+ if (err)
+ break;
table->files[index] = NULL;
- if (io_queue_file_removal(data, file))
- ref_switch = true;
+ ref_switch = true;
}
if (fd != -1) {
file = fget(fd);
return __io_sqe_files_update(ctx, &up, nr_args);
}
-static void io_put_work(struct io_wq_work *work)
+static void io_free_work(struct io_wq_work *work)
{
struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+ /* Consider that io_steal_work() relies on this ref */
io_put_req(req);
}
-static void io_get_work(struct io_wq_work *work)
-{
- struct io_kiocb *req = container_of(work, struct io_kiocb, work);
-
- refcount_inc(&req->refs);
-}
-
static int io_init_wq_offload(struct io_ring_ctx *ctx,
struct io_uring_params *p)
{
int ret = 0;
data.user = ctx->user;
- data.get_work = io_get_work;
- data.put_work = io_put_work;
+ data.free_work = io_free_work;
if (!(p->flags & IORING_SETUP_ATTACH_WQ)) {
/* Do QD, or 4 * CPUS, whatever is smallest */
return -ENXIO;
}
+static int __io_destroy_buffers(int id, void *p, void *data)
+{
+ struct io_ring_ctx *ctx = data;
+ struct io_buffer *buf = p;
+
+ __io_remove_buffers(ctx, buf, id, -1U);
+ return 0;
+}
+
+static void io_destroy_buffers(struct io_ring_ctx *ctx)
+{
+ idr_for_each(&ctx->io_buffer_idr, __io_destroy_buffers, ctx);
+ idr_destroy(&ctx->io_buffer_idr);
+}
+
static void io_ring_ctx_free(struct io_ring_ctx *ctx)
{
io_finish_async(ctx);
io_sqe_buffer_unregister(ctx);
io_sqe_files_unregister(ctx);
io_eventfd_unregister(ctx);
+ io_destroy_buffers(ctx);
idr_destroy(&ctx->personality_idr);
#if defined(CONFIG_UNIX)
int submitted = 0;
struct fd f;
+ if (current->task_works)
+ task_work_run();
+
if (flags & ~(IORING_ENTER_GETEVENTS | IORING_ENTER_SQ_WAKEUP))
return -EINVAL;
min_complete = min(min_complete, ctx->cq_entries);
- if (ctx->flags & IORING_SETUP_IOPOLL) {
+ /*
+ * When SETUP_IOPOLL and SETUP_SQPOLL are both enabled, user
+ * space applications don't need to do io completion events
+ * polling again, they can rely on io_sq_thread to do polling
+ * work, which can reduce cpu usage and uring_lock contention.
+ */
+ if (ctx->flags & IORING_SETUP_IOPOLL &&
+ !(ctx->flags & IORING_SETUP_SQPOLL)) {
ret = io_iopoll_check(ctx, &nr_events, min_complete);
} else {
ret = io_cqring_wait(ctx, min_complete, sig, sigsz);
seq_printf(m, "Personalities:\n");
idr_for_each(&ctx->personality_idr, io_uring_show_cred, m);
}
+ seq_printf(m, "PollList:\n");
+ spin_lock_irq(&ctx->completion_lock);
+ for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) {
+ struct hlist_head *list = &ctx->cancel_hash[i];
+ struct io_kiocb *req;
+
+ hlist_for_each_entry(req, list, hash_node)
+ seq_printf(m, " op=%d, task_works=%d\n", req->opcode,
+ req->task->task_works != NULL);
+ }
+ spin_unlock_irq(&ctx->completion_lock);
mutex_unlock(&ctx->uring_lock);
}
p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP |
IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS |
- IORING_FEAT_CUR_PERSONALITY;
+ IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL;
trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags);
return ret;
err:
BUILD_BUG_SQE_ELEM(8, __u64, off);
BUILD_BUG_SQE_ELEM(8, __u64, addr2);
BUILD_BUG_SQE_ELEM(16, __u64, addr);
+ BUILD_BUG_SQE_ELEM(16, __u64, splice_off_in);
BUILD_BUG_SQE_ELEM(24, __u32, len);
BUILD_BUG_SQE_ELEM(28, __kernel_rwf_t, rw_flags);
BUILD_BUG_SQE_ELEM(28, /* compat */ int, rw_flags);
BUILD_BUG_SQE_ELEM(28, __u32, open_flags);
BUILD_BUG_SQE_ELEM(28, __u32, statx_flags);
BUILD_BUG_SQE_ELEM(28, __u32, fadvise_advice);
+ BUILD_BUG_SQE_ELEM(28, __u32, splice_flags);
BUILD_BUG_SQE_ELEM(32, __u64, user_data);
BUILD_BUG_SQE_ELEM(40, __u16, buf_index);
BUILD_BUG_SQE_ELEM(42, __u16, personality);
+ BUILD_BUG_SQE_ELEM(44, __s32, splice_fd_in);
BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST);
+ BUILD_BUG_ON(__REQ_F_LAST_BIT >= 8 * sizeof(int));
req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC);
return 0;
};
If you want your system to mount its root file system via NFS,
choose Y here. This is common practice for managing systems
without local permanent storage. For details, read
- <file:Documentation/filesystems/nfs/nfsroot.txt>.
+ <file:Documentation/admin-guide/nfs/nfsroot.rst>.
Most people say N here.
struct pstore_private *ps = s->private;
struct pstore_ftrace_seq_data *data = v;
+ (*pos)++;
data->off += REC_SIZE;
if (data->off + REC_SIZE > ps->total_size)
return NULL;
- (*pos)++;
return data;
}
struct pstore_ftrace_seq_data *data = v;
struct pstore_ftrace_record *rec;
+ if (!data)
+ return 0;
+
rec = (struct pstore_ftrace_record *)(ps->record->buf + data->off);
seq_printf(s, "CPU:%d ts:%llu %08lx %08lx %ps <- %pS\n",
ret = pstore_init_fs();
if (ret)
- return ret;
+ free_buf_for_compression();
- return 0;
+ return ret;
}
late_initcall(pstore_init);
pr_info("could not create platform device: %ld\n",
PTR_ERR(dummy));
dummy = NULL;
- ramoops_unregister_dummy();
}
}
uint32_t sig;
atomic_t start;
atomic_t size;
- uint8_t data[0];
+ uint8_t data[];
};
#define PERSISTENT_RAM_SIG (0x43474244) /* DBGC */
int result;
dev_t jdev;
fmode_t blkdev_mode = FMODE_READ | FMODE_WRITE | FMODE_EXCL;
- char b[BDEVNAME_SIZE];
result = 0;
result = PTR_ERR(journal->j_dev_bd);
journal->j_dev_bd = NULL;
reiserfs_warning(super, "sh-458",
- "cannot init journal device '%s': %i",
- __bdevname(jdev, b), result);
+ "cannot init journal device unknown-block(%u,%u): %i",
+ MAJOR(jdev), MINOR(jdev), result);
return result;
} else if (jdev != super->s_dev)
set_blocksize(journal->j_dev_bd, super->s_blocksize);
/*
* Determine where to splice to/from.
*/
-static long do_splice(struct file *in, loff_t __user *off_in,
- struct file *out, loff_t __user *off_out,
- size_t len, unsigned int flags)
+long do_splice(struct file *in, loff_t __user *off_in,
+ struct file *out, loff_t __user *off_out,
+ size_t len, unsigned int flags)
{
struct pipe_inode_info *ipipe;
struct pipe_inode_info *opipe;
unsigned int len, unsigned int off);
int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter);
void bio_release_pages(struct bio *bio, bool mark_dirty);
-struct rq_map_data;
-extern struct bio *bio_map_user_iov(struct request_queue *,
- struct iov_iter *, gfp_t);
-extern void bio_unmap_user(struct bio *);
-extern struct bio *bio_map_kern(struct request_queue *, void *, unsigned int,
- gfp_t);
-extern struct bio *bio_copy_kern(struct request_queue *, void *, unsigned int,
- gfp_t, int);
extern void bio_set_pages_dirty(struct bio *bio);
extern void bio_check_pages_dirty(struct bio *bio);
extern void bio_copy_data(struct bio *dst, struct bio *src);
extern void bio_list_copy_data(struct bio *dst, struct bio *src);
extern void bio_free_pages(struct bio *bio);
-
-extern struct bio *bio_copy_user_iov(struct request_queue *,
- struct rq_map_data *,
- struct iov_iter *,
- gfp_t);
-extern int bio_uncopy_user(struct bio *);
void zero_fill_bio_iter(struct bio *bio, struct bvec_iter iter);
void bio_truncate(struct bio *bio, unsigned new_size);
+void guard_bio_eod(struct bio *bio);
static inline void zero_fill_bio(struct bio *bio)
{
struct dentry *sched_debugfs_dir;
#endif
- /** @hctx_list: List of all hardware queues. */
+ /**
+ * @hctx_list: if this hctx is not in use, this is an entry in
+ * q->unused_hctx_list.
+ */
struct list_head hctx_list;
/**
<< BLK_MQ_F_ALLOC_POLICY_START_BIT)
struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *);
+struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set,
+ void *queuedata);
struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
struct request_queue *q,
bool elevator_init);
}
#ifdef CONFIG_BLK_DEV_ZONED
+
+/* Helper to convert BLK_ZONE_ZONE_XXX to its string format XXX */
+const char *blk_zone_cond_str(enum blk_zone_cond zone_cond);
+
static inline unsigned int blk_rq_zone_no(struct request *rq)
{
return blk_queue_zone_no(rq->q, blk_rq_pos(rq));
* Access functions for manipulating queue properties
*/
extern void blk_cleanup_queue(struct request_queue *);
-extern void blk_queue_make_request(struct request_queue *, make_request_fn *);
extern void blk_queue_bounce_limit(struct request_queue *, u64);
extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int);
extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int);
extern long nr_blockdev_pages(void);
bool __must_check blk_get_queue(struct request_queue *);
-struct request_queue *blk_alloc_queue(gfp_t);
-struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id);
+struct request_queue *blk_alloc_queue(make_request_fn make_request, int node_id);
extern void blk_put_queue(struct request_queue *);
extern void blk_set_queue_dying(struct request_queue *);
return bdev->bd_block_size;
}
-typedef struct {struct page *v;} Sector;
-
-unsigned char *read_dev_sector(struct block_device *, sector_t, Sector *);
-
-static inline void put_dev_sector(Sector p)
-{
- put_page(p.v);
-}
-
int kblockd_schedule_work(struct work_struct *work);
int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay);
void (*swap_slot_free_notify) (struct block_device *, unsigned long);
int (*report_zones)(struct gendisk *, sector_t sector,
unsigned int nr_zones, report_zones_cb cb, void *data);
+ char *(*devnode)(struct gendisk *disk, umode_t *mode);
struct module *owner;
const struct pr_ops *pr_ops;
};
#ifdef CONFIG_BLOCK
#define BLKDEV_MAJOR_MAX 512
-extern const char *__bdevname(dev_t, char *buffer);
extern const char *bdevname(struct block_device *bdev, char *buffer);
extern struct block_device *lookup_bdev(const char *);
extern void blkdev_show(struct seq_file *,off_t);
#define part_to_dev(part) (&((part)->__dev))
extern struct device_type part_type;
-extern struct kobject *block_depr;
extern struct class block_class;
-enum {
-/* These three have identical behaviour; use the second one if DOS FDISK gets
- confused about extended/logical partitions starting past cylinder 1023. */
- DOS_EXTENDED_PARTITION = 5,
- LINUX_EXTENDED_PARTITION = 0x85,
- WIN98_EXTENDED_PARTITION = 0x0f,
-
- SUN_WHOLE_DISK = DOS_EXTENDED_PARTITION,
-
- LINUX_SWAP_PARTITION = 0x82,
- LINUX_DATA_PARTITION = 0x83,
- LINUX_LVM_PARTITION = 0x8e,
- LINUX_RAID_PARTITION = 0xfd, /* autodetect RAID partition */
-
- SOLARIS_X86_PARTITION = LINUX_SWAP_PARTITION,
- NEW_SOLARIS_X86_PARTITION = 0xbf,
-
- DM6_AUX1PARTITION = 0x51, /* no DDO: use xlated geom */
- DM6_AUX3PARTITION = 0x53, /* no DDO: use xlated geom */
- DM6_PARTITION = 0x54, /* has DDO: use xlated geom & offset */
- EZD_PARTITION = 0x55, /* EZ-DRIVE */
-
- FREEBSD_PARTITION = 0xa5, /* FreeBSD Partition ID */
- OPENBSD_PARTITION = 0xa6, /* OpenBSD Partition ID */
- NETBSD_PARTITION = 0xa9, /* NetBSD Partition ID */
- BSDI_PARTITION = 0xb7, /* BSDI Partition ID */
- MINIX_PARTITION = 0x81, /* Minix Partition ID */
- UNIXWARE_PARTITION = 0x63, /* Same as GNU_HURD and SCO Unix */
-};
-
#define DISK_MAX_PARTS 256
#define DISK_NAME_LEN 32
#include <linux/fs.h>
#include <linux/workqueue.h>
-struct partition {
- unsigned char boot_ind; /* 0x80 - active */
- unsigned char head; /* starting head */
- unsigned char sector; /* starting sector */
- unsigned char cyl; /* starting cylinder */
- unsigned char sys_ind; /* What partition type */
- unsigned char end_head; /* end head */
- unsigned char end_sector; /* end sector */
- unsigned char end_cyl; /* end cylinder */
- __le32 start_sect; /* starting sector counting from 0 */
- __le32 nr_sects; /* nr of sectors in partition */
-} __attribute__((packed));
-
struct disk_stats {
u64 nsecs[NR_STAT_GROUPS];
unsigned long sectors[NR_STAT_GROUPS];
unsigned long ios[NR_STAT_GROUPS];
unsigned long merges[NR_STAT_GROUPS];
unsigned long io_ticks;
- unsigned long time_in_queue;
local_t in_flight[2];
};
struct rcu_work rcu_work;
};
-#define GENHD_FL_REMOVABLE 1
-/* 2 is unused */
-#define GENHD_FL_MEDIA_CHANGE_NOTIFY 4
-#define GENHD_FL_CD 8
-#define GENHD_FL_UP 16
-#define GENHD_FL_SUPPRESS_PARTITION_INFO 32
-#define GENHD_FL_EXT_DEVT 64 /* allow extended devt */
-#define GENHD_FL_NATIVE_CAPACITY 128
-#define GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE 256
-#define GENHD_FL_NO_PART_SCAN 512
-#define GENHD_FL_HIDDEN 1024
+/**
+ * DOC: genhd capability flags
+ *
+ * ``GENHD_FL_REMOVABLE`` (0x0001): indicates that the block device
+ * gives access to removable media.
+ * When set, the device remains present even when media is not
+ * inserted.
+ * Must not be set for devices which are removed entirely when the
+ * media is removed.
+ *
+ * ``GENHD_FL_CD`` (0x0008): the block device is a CD-ROM-style
+ * device.
+ * Affects responses to the ``CDROM_GET_CAPABILITY`` ioctl.
+ *
+ * ``GENHD_FL_UP`` (0x0010): indicates that the block device is "up",
+ * with a similar meaning to network interfaces.
+ *
+ * ``GENHD_FL_SUPPRESS_PARTITION_INFO`` (0x0020): don't include
+ * partition information in ``/proc/partitions`` or in the output of
+ * printk_all_partitions().
+ * Used for the null block device and some MMC devices.
+ *
+ * ``GENHD_FL_EXT_DEVT`` (0x0040): the driver supports extended
+ * dynamic ``dev_t``, i.e. it wants extended device numbers
+ * (``BLOCK_EXT_MAJOR``).
+ * This affects the maximum number of partitions.
+ *
+ * ``GENHD_FL_NATIVE_CAPACITY`` (0x0080): based on information in the
+ * partition table, the device's capacity has been extended to its
+ * native capacity; i.e. the device has hidden capacity used by one
+ * of the partitions (this is a flag used so that native capacity is
+ * only ever unlocked once).
+ *
+ * ``GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE`` (0x0100): event polling is
+ * blocked whenever a writer holds an exclusive lock.
+ *
+ * ``GENHD_FL_NO_PART_SCAN`` (0x0200): partition scanning is disabled.
+ * Used for loop devices in their default settings and some MMC
+ * devices.
+ *
+ * ``GENHD_FL_HIDDEN`` (0x0400): the block device is hidden; it
+ * doesn't produce events, doesn't appear in sysfs, and doesn't have
+ * an associated ``bdev``.
+ * Implies ``GENHD_FL_SUPPRESS_PARTITION_INFO`` and
+ * ``GENHD_FL_NO_PART_SCAN``.
+ * Used for multipath devices.
+ */
+#define GENHD_FL_REMOVABLE 0x0001
+/* 2 is unused (used to be GENHD_FL_DRIVERFS) */
+/* 4 is unused (used to be GENHD_FL_MEDIA_CHANGE_NOTIFY) */
+#define GENHD_FL_CD 0x0008
+#define GENHD_FL_UP 0x0010
+#define GENHD_FL_SUPPRESS_PARTITION_INFO 0x0020
+#define GENHD_FL_EXT_DEVT 0x0040
+#define GENHD_FL_NATIVE_CAPACITY 0x0080
+#define GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE 0x0100
+#define GENHD_FL_NO_PART_SCAN 0x0200
+#define GENHD_FL_HIDDEN 0x0400
enum {
DISK_EVENT_MEDIA_CHANGE = 1 << 0, /* media changed */
* disks that can't be partitioned. */
char disk_name[DISK_NAME_LEN]; /* name of major driver */
- char *(*devnode)(struct gendisk *gd, umode_t *mode);
unsigned short events; /* supported events */
unsigned short event_flags; /* flags related to event processing */
struct gendisk *disk, unsigned int flags);
extern struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter);
extern void disk_part_iter_exit(struct disk_part_iter *piter);
-
-extern struct hd_struct *disk_map_sector_rcu(struct gendisk *disk,
- sector_t sector);
-bool disk_has_partitions(struct gendisk *disk);
-
-/*
- * Macros to operate on percpu disk statistics:
- *
- * {disk|part|all}_stat_{add|sub|inc|dec}() modify the stat counters
- * and should be called between disk_stat_lock() and
- * disk_stat_unlock().
- *
- * part_stat_read() can be called at any time.
- *
- * part_stat_{add|set_all}() and {init|free}_part_stats are for
- * internal use only.
- */
-#ifdef CONFIG_SMP
-#define part_stat_lock() ({ rcu_read_lock(); get_cpu(); })
-#define part_stat_unlock() do { put_cpu(); rcu_read_unlock(); } while (0)
-
-#define part_stat_get_cpu(part, field, cpu) \
- (per_cpu_ptr((part)->dkstats, (cpu))->field)
-
-#define part_stat_get(part, field) \
- part_stat_get_cpu(part, field, smp_processor_id())
-
-#define part_stat_read(part, field) \
-({ \
- typeof((part)->dkstats->field) res = 0; \
- unsigned int _cpu; \
- for_each_possible_cpu(_cpu) \
- res += per_cpu_ptr((part)->dkstats, _cpu)->field; \
- res; \
-})
-
-static inline void part_stat_set_all(struct hd_struct *part, int value)
-{
- int i;
-
- for_each_possible_cpu(i)
- memset(per_cpu_ptr(part->dkstats, i), value,
- sizeof(struct disk_stats));
-}
-
-static inline int init_part_stats(struct hd_struct *part)
-{
- part->dkstats = alloc_percpu(struct disk_stats);
- if (!part->dkstats)
- return 0;
- return 1;
-}
-
-static inline void free_part_stats(struct hd_struct *part)
-{
- free_percpu(part->dkstats);
-}
-
-#else /* !CONFIG_SMP */
-#define part_stat_lock() ({ rcu_read_lock(); 0; })
-#define part_stat_unlock() rcu_read_unlock()
-
-#define part_stat_get(part, field) ((part)->dkstats.field)
-#define part_stat_get_cpu(part, field, cpu) part_stat_get(part, field)
-#define part_stat_read(part, field) part_stat_get(part, field)
-
-static inline void part_stat_set_all(struct hd_struct *part, int value)
-{
- memset(&part->dkstats, value, sizeof(struct disk_stats));
-}
-
-static inline int init_part_stats(struct hd_struct *part)
-{
- return 1;
-}
-
-static inline void free_part_stats(struct hd_struct *part)
-{
-}
-
-#endif /* CONFIG_SMP */
-
-#define part_stat_read_msecs(part, which) \
- div_u64(part_stat_read(part, nsecs[which]), NSEC_PER_MSEC)
-
-#define part_stat_read_accum(part, field) \
- (part_stat_read(part, field[STAT_READ]) + \
- part_stat_read(part, field[STAT_WRITE]) + \
- part_stat_read(part, field[STAT_DISCARD]))
-
-#define __part_stat_add(part, field, addnd) \
- (part_stat_get(part, field) += (addnd))
-
-#define part_stat_add(part, field, addnd) do { \
- __part_stat_add((part), field, addnd); \
- if ((part)->partno) \
- __part_stat_add(&part_to_disk((part))->part0, \
- field, addnd); \
-} while (0)
-
-#define part_stat_dec(gendiskp, field) \
- part_stat_add(gendiskp, field, -1)
-#define part_stat_inc(gendiskp, field) \
- part_stat_add(gendiskp, field, 1)
-#define part_stat_sub(gendiskp, field, subnd) \
- part_stat_add(gendiskp, field, -subnd)
-
-#define part_stat_local_dec(gendiskp, field) \
- local_dec(&(part_stat_get(gendiskp, field)))
-#define part_stat_local_inc(gendiskp, field) \
- local_inc(&(part_stat_get(gendiskp, field)))
-#define part_stat_local_read(gendiskp, field) \
- local_read(&(part_stat_get(gendiskp, field)))
-#define part_stat_local_read_cpu(gendiskp, field, cpu) \
- local_read(&(part_stat_get_cpu(gendiskp, field, cpu)))
-
-unsigned int part_in_flight(struct request_queue *q, struct hd_struct *part);
-void part_in_flight_rw(struct request_queue *q, struct hd_struct *part,
- unsigned int inflight[2]);
-void part_dec_in_flight(struct request_queue *q, struct hd_struct *part,
- int rw);
-void part_inc_in_flight(struct request_queue *q, struct hd_struct *part,
- int rw);
-
-static inline struct partition_meta_info *alloc_part_info(struct gendisk *disk)
-{
- if (disk)
- return kzalloc_node(sizeof(struct partition_meta_info),
- GFP_KERNEL, disk->node_id);
- return kzalloc(sizeof(struct partition_meta_info), GFP_KERNEL);
-}
-
-static inline void free_part_info(struct hd_struct *part)
-{
- kfree(part->info);
-}
-
-void update_io_ticks(struct hd_struct *part, unsigned long now);
+extern bool disk_has_partitions(struct gendisk *disk);
/* block/genhd.c */
extern void device_add_disk(struct device *parent, struct gendisk *disk,
extern void disk_block_events(struct gendisk *disk);
extern void disk_unblock_events(struct gendisk *disk);
extern void disk_flush_events(struct gendisk *disk, unsigned int mask);
+extern void set_capacity_revalidate_and_notify(struct gendisk *disk,
+ sector_t size, bool revalidate);
extern unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask);
/* drivers/char/random.c */
disk->part0.nr_sects = size;
}
-#ifdef CONFIG_SOLARIS_X86_PARTITION
-
-#define SOLARIS_X86_NUMSLICE 16
-#define SOLARIS_X86_VTOC_SANE (0x600DDEEEUL)
-
-struct solaris_x86_slice {
- __le16 s_tag; /* ID tag of partition */
- __le16 s_flag; /* permission flags */
- __le32 s_start; /* start sector no of partition */
- __le32 s_size; /* # of blocks in partition */
-};
-
-struct solaris_x86_vtoc {
- unsigned int v_bootinfo[3]; /* info needed by mboot (unsupported) */
- __le32 v_sanity; /* to verify vtoc sanity */
- __le32 v_version; /* layout version */
- char v_volume[8]; /* volume name */
- __le16 v_sectorsz; /* sector size in bytes */
- __le16 v_nparts; /* number of partitions */
- unsigned int v_reserved[10]; /* free space */
- struct solaris_x86_slice
- v_slice[SOLARIS_X86_NUMSLICE]; /* slice headers */
- unsigned int timestamp[SOLARIS_X86_NUMSLICE]; /* timestamp (unsupported) */
- char v_asciilabel[128]; /* for compatibility */
-};
-
-#endif /* CONFIG_SOLARIS_X86_PARTITION */
-
-#ifdef CONFIG_BSD_DISKLABEL
-/*
- * BSD disklabel support by Yossi Gottlieb <yogo@math.tau.ac.il>
- * updated by Marc Espie <Marc.Espie@openbsd.org>
- */
-
-/* check against BSD src/sys/sys/disklabel.h for consistency */
-
-#define BSD_DISKMAGIC (0x82564557UL) /* The disk magic number */
-#define BSD_MAXPARTITIONS 16
-#define OPENBSD_MAXPARTITIONS 16
-#define BSD_FS_UNUSED 0 /* disklabel unused partition entry ID */
-struct bsd_disklabel {
- __le32 d_magic; /* the magic number */
- __s16 d_type; /* drive type */
- __s16 d_subtype; /* controller/d_type specific */
- char d_typename[16]; /* type name, e.g. "eagle" */
- char d_packname[16]; /* pack identifier */
- __u32 d_secsize; /* # of bytes per sector */
- __u32 d_nsectors; /* # of data sectors per track */
- __u32 d_ntracks; /* # of tracks per cylinder */
- __u32 d_ncylinders; /* # of data cylinders per unit */
- __u32 d_secpercyl; /* # of data sectors per cylinder */
- __u32 d_secperunit; /* # of data sectors per unit */
- __u16 d_sparespertrack; /* # of spare sectors per track */
- __u16 d_sparespercyl; /* # of spare sectors per cylinder */
- __u32 d_acylinders; /* # of alt. cylinders per unit */
- __u16 d_rpm; /* rotational speed */
- __u16 d_interleave; /* hardware sector interleave */
- __u16 d_trackskew; /* sector 0 skew, per track */
- __u16 d_cylskew; /* sector 0 skew, per cylinder */
- __u32 d_headswitch; /* head switch time, usec */
- __u32 d_trkseek; /* track-to-track seek, usec */
- __u32 d_flags; /* generic flags */
-#define NDDATA 5
- __u32 d_drivedata[NDDATA]; /* drive-type specific information */
-#define NSPARE 5
- __u32 d_spare[NSPARE]; /* reserved for future use */
- __le32 d_magic2; /* the magic number (again) */
- __le16 d_checksum; /* xor of data incl. partitions */
-
- /* filesystem and partition information: */
- __le16 d_npartitions; /* number of partitions in following */
- __le32 d_bbsize; /* size of boot area at sn0, bytes */
- __le32 d_sbsize; /* max size of fs superblock, bytes */
- struct bsd_partition { /* the partition table */
- __le32 p_size; /* number of sectors in partition */
- __le32 p_offset; /* starting sector */
- __le32 p_fsize; /* filesystem basic fragment size */
- __u8 p_fstype; /* filesystem type, see below */
- __u8 p_frag; /* filesystem fragments per block */
- __le16 p_cpg; /* filesystem cylinders per group */
- } d_partitions[BSD_MAXPARTITIONS]; /* actually may be more */
-};
-
-#endif /* CONFIG_BSD_DISKLABEL */
-
-#ifdef CONFIG_UNIXWARE_DISKLABEL
-/*
- * Unixware slices support by Andrzej Krzysztofowicz <ankry@mif.pg.gda.pl>
- * and Krzysztof G. Baranowski <kgb@knm.org.pl>
- */
-
-#define UNIXWARE_DISKMAGIC (0xCA5E600DUL) /* The disk magic number */
-#define UNIXWARE_DISKMAGIC2 (0x600DDEEEUL) /* The slice table magic nr */
-#define UNIXWARE_NUMSLICE 16
-#define UNIXWARE_FS_UNUSED 0 /* Unused slice entry ID */
-
-struct unixware_slice {
- __le16 s_label; /* label */
- __le16 s_flags; /* permission flags */
- __le32 start_sect; /* starting sector */
- __le32 nr_sects; /* number of sectors in slice */
-};
-
-struct unixware_disklabel {
- __le32 d_type; /* drive type */
- __le32 d_magic; /* the magic number */
- __le32 d_version; /* version number */
- char d_serial[12]; /* serial number of the device */
- __le32 d_ncylinders; /* # of data cylinders per device */
- __le32 d_ntracks; /* # of tracks per cylinder */
- __le32 d_nsectors; /* # of data sectors per track */
- __le32 d_secsize; /* # of bytes per sector */
- __le32 d_part_start; /* # of first sector of this partition */
- __le32 d_unknown1[12]; /* ? */
- __le32 d_alt_tbl; /* byte offset of alternate table */
- __le32 d_alt_len; /* byte length of alternate table */
- __le32 d_phys_cyl; /* # of physical cylinders per device */
- __le32 d_phys_trk; /* # of physical tracks per cylinder */
- __le32 d_phys_sec; /* # of physical sectors per track */
- __le32 d_phys_bytes; /* # of physical bytes per sector */
- __le32 d_unknown2; /* ? */
- __le32 d_unknown3; /* ? */
- __le32 d_pad[8]; /* pad */
-
- struct unixware_vtoc {
- __le32 v_magic; /* the magic number */
- __le32 v_version; /* version number */
- char v_name[8]; /* volume name */
- __le16 v_nslices; /* # of slices */
- __le16 v_unknown1; /* ? */
- __le32 v_reserved[10]; /* reserved */
- struct unixware_slice
- v_slice[UNIXWARE_NUMSLICE]; /* slice headers */
- } vtoc;
-
-}; /* 408 */
-
-#endif /* CONFIG_UNIXWARE_DISKLABEL */
-
-#ifdef CONFIG_MINIX_SUBPARTITION
-# define MINIX_NR_SUBPARTITIONS 4
-#endif /* CONFIG_MINIX_SUBPARTITION */
-
-#define ADDPART_FLAG_NONE 0
-#define ADDPART_FLAG_RAID 1
-#define ADDPART_FLAG_WHOLEDISK 2
-
-extern int blk_alloc_devt(struct hd_struct *part, dev_t *devt);
-extern void blk_free_devt(dev_t devt);
-extern void blk_invalidate_devt(dev_t devt);
extern dev_t blk_lookup_devt(const char *name, int partno);
-extern char *disk_name (struct gendisk *hd, int partno, char *buf);
int bdev_disk_changed(struct block_device *bdev, bool invalidate);
int blk_add_partitions(struct gendisk *disk, struct block_device *bdev);
int blk_drop_partitions(struct gendisk *disk, struct block_device *bdev);
-extern int disk_expand_part_tbl(struct gendisk *disk, int target);
-extern struct hd_struct * __must_check add_partition(struct gendisk *disk,
- int partno, sector_t start,
- sector_t len, int flags,
- struct partition_meta_info
- *info);
-extern void __delete_partition(struct percpu_ref *);
-extern void delete_partition(struct gendisk *, int);
extern void printk_all_partitions(void);
extern struct gendisk *__alloc_disk_node(int minors, int node_id);
void *data);
extern void blk_unregister_region(dev_t devt, unsigned long range);
-extern ssize_t part_size_show(struct device *dev,
- struct device_attribute *attr, char *buf);
-extern ssize_t part_stat_show(struct device *dev,
- struct device_attribute *attr, char *buf);
-extern ssize_t part_inflight_show(struct device *dev,
- struct device_attribute *attr, char *buf);
-#ifdef CONFIG_FAIL_MAKE_REQUEST
-extern ssize_t part_fail_show(struct device *dev,
- struct device_attribute *attr, char *buf);
-extern ssize_t part_fail_store(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count);
-#endif /* CONFIG_FAIL_MAKE_REQUEST */
-
#define alloc_disk_node(minors, node_id) \
({ \
static struct lock_class_key __key; \
#define alloc_disk(minors) alloc_disk_node(minors, NUMA_NO_NODE)
-static inline int hd_ref_init(struct hd_struct *part)
-{
- if (percpu_ref_init(&part->ref, __delete_partition, 0,
- GFP_KERNEL))
- return -ENOMEM;
- return 0;
-}
-
-static inline void hd_struct_get(struct hd_struct *part)
-{
- percpu_ref_get(&part->ref);
-}
-
-static inline int hd_struct_try_get(struct hd_struct *part)
-{
- return percpu_ref_tryget_live(&part->ref);
-}
-
-static inline void hd_struct_put(struct hd_struct *part)
-{
- percpu_ref_put(&part->ref);
-}
-
-static inline void hd_struct_kill(struct hd_struct *part)
-{
- percpu_ref_kill(&part->ref);
-}
-
-static inline void hd_free_part(struct hd_struct *part)
-{
- free_part_stats(part);
- free_part_info(part);
- percpu_ref_exit(&part->ref);
-}
-
-/*
- * Any access of part->nr_sects which is not protected by partition
- * bd_mutex or gendisk bdev bd_mutex, should be done using this
- * accessor function.
- *
- * Code written along the lines of i_size_read() and i_size_write().
- * CONFIG_PREEMPTION case optimizes the case of UP kernel with preemption
- * on.
- */
-static inline sector_t part_nr_sects_read(struct hd_struct *part)
-{
-#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
- sector_t nr_sects;
- unsigned seq;
- do {
- seq = read_seqcount_begin(&part->nr_sects_seq);
- nr_sects = part->nr_sects;
- } while (read_seqcount_retry(&part->nr_sects_seq, seq));
- return nr_sects;
-#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
- sector_t nr_sects;
-
- preempt_disable();
- nr_sects = part->nr_sects;
- preempt_enable();
- return nr_sects;
-#else
- return part->nr_sects;
-#endif
-}
-
-/*
- * Should be called with mutex lock held (typically bd_mutex) of partition
- * to provide mutual exlusion among writers otherwise seqcount might be
- * left in wrong state leaving the readers spinning infinitely.
- */
-static inline void part_nr_sects_write(struct hd_struct *part, sector_t size)
-{
-#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
- write_seqcount_begin(&part->nr_sects_seq);
- part->nr_sects = size;
- write_seqcount_end(&part->nr_sects_seq);
-#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
- preempt_disable();
- part->nr_sects = size;
- preempt_enable();
-#else
- part->nr_sects = size;
-#endif
-}
-
-#if defined(CONFIG_BLK_DEV_INTEGRITY)
-extern void blk_integrity_add(struct gendisk *);
-extern void blk_integrity_del(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) { }
-#endif /* CONFIG_BLK_DEV_INTEGRITY */
-
#else /* CONFIG_BLOCK */
static inline void printk_all_partitions(void) { }
* The io_mapping mechanism provides an abstraction for mapping
* individual pages from an io device to the CPU in an efficient fashion.
*
- * See Documentation/io-mapping.txt
+ * See Documentation/driver-api/io-mapping.rst
*/
struct io_mapping {
enum {
ICQ_EXITED = 1 << 2,
+ ICQ_DESTROYED = 1 << 3,
};
/*
#define VPRINTK(fmt, args...)
#endif /* ATA_DEBUG */
-#define BPRINTK(fmt, args...) if (ap->flags & ATA_FLAG_DEBUGMSG) printk(KERN_ERR "%s: " fmt, __func__, ## args)
-
#define ata_print_version_once(dev, version) \
({ \
static bool __print_once; \
ATA_DEV_NONE = 11, /* no device */
/* struct ata_link flags */
+ /* NOTE: struct ata_force_param currently stores lflags in u16 */
ATA_LFLAG_NO_HRST = (1 << 1), /* avoid hardreset */
ATA_LFLAG_NO_SRST = (1 << 2), /* avoid softreset */
ATA_LFLAG_ASSUME_ATA = (1 << 3), /* assume ATA class */
unsigned long deadline);
typedef void (*ata_postreset_fn_t)(struct ata_link *link, unsigned int *classes);
-extern struct device_attribute dev_attr_link_power_management_policy;
extern struct device_attribute dev_attr_unload_heads;
+#ifdef CONFIG_SATA_HOST
+extern struct device_attribute dev_attr_link_power_management_policy;
extern struct device_attribute dev_attr_ncq_prio_enable;
extern struct device_attribute dev_attr_em_message_type;
extern struct device_attribute dev_attr_em_message;
extern struct device_attribute dev_attr_sw_activity;
+#endif
enum sw_activity {
OFF,
/*
* Core layer - drivers/ata/libata-core.c
*/
-extern const unsigned long sata_deb_timing_normal[];
-extern const unsigned long sata_deb_timing_hotplug[];
-extern const unsigned long sata_deb_timing_long[];
-
extern struct ata_port_operations ata_dummy_port_ops;
extern const struct ata_port_info ata_dummy_port_info;
(tf->command == ATA_CMD_WRITE_MULTI_FUA_EXT);
}
-static inline const unsigned long *
-sata_ehc_deb_timing(struct ata_eh_context *ehc)
-{
- if (ehc->i.flags & ATA_EHI_HOTPLUGGED)
- return sata_deb_timing_hotplug;
- else
- return sata_deb_timing_normal;
-}
-
static inline int ata_port_is_dummy(struct ata_port *ap)
{
return ap->ops == &ata_dummy_port_ops;
}
-extern int sata_set_spd(struct ata_link *link);
extern int ata_std_prereset(struct ata_link *link, unsigned long deadline);
extern int ata_wait_after_reset(struct ata_link *link, unsigned long deadline,
int (*check_ready)(struct ata_link *link));
-extern int sata_link_debounce(struct ata_link *link,
- const unsigned long *params, unsigned long deadline);
-extern int sata_link_resume(struct ata_link *link, const unsigned long *params,
- unsigned long deadline);
-extern int sata_link_scr_lpm(struct ata_link *link, enum ata_lpm_policy policy,
- bool spm_wakeup);
-extern int sata_link_hardreset(struct ata_link *link,
- const unsigned long *timing, unsigned long deadline,
- bool *online, int (*check_ready)(struct ata_link *));
extern int sata_std_hardreset(struct ata_link *link, unsigned int *class,
unsigned long deadline);
extern void ata_std_postreset(struct ata_link *link, unsigned int *classes);
extern struct ata_host *ata_host_alloc(struct device *dev, int max_ports);
extern struct ata_host *ata_host_alloc_pinfo(struct device *dev,
const struct ata_port_info * const * ppi, int n_ports);
-extern int ata_slave_link_init(struct ata_port *ap);
extern void ata_host_get(struct ata_host *host);
extern void ata_host_put(struct ata_host *host);
extern int ata_host_start(struct ata_host *host);
extern int ata_scsi_queuecmd(struct Scsi_Host *h, struct scsi_cmnd *cmd);
extern int ata_sas_scsi_ioctl(struct ata_port *ap, struct scsi_device *dev,
unsigned int cmd, void __user *arg);
-extern void ata_sas_port_destroy(struct ata_port *);
-extern struct ata_port *ata_sas_port_alloc(struct ata_host *,
- struct ata_port_info *, struct Scsi_Host *);
-extern void ata_sas_async_probe(struct ata_port *ap);
-extern int ata_sas_sync_probe(struct ata_port *ap);
-extern int ata_sas_port_init(struct ata_port *);
-extern int ata_sas_port_start(struct ata_port *ap);
-extern int ata_sas_tport_add(struct device *parent, struct ata_port *ap);
-extern void ata_sas_tport_delete(struct ata_port *ap);
-extern void ata_sas_port_stop(struct ata_port *ap);
-extern int ata_sas_slave_configure(struct scsi_device *, struct ata_port *);
-extern int ata_sas_queuecmd(struct scsi_cmnd *cmd, struct ata_port *ap);
-extern int sata_scr_valid(struct ata_link *link);
-extern int sata_scr_read(struct ata_link *link, int reg, u32 *val);
-extern int sata_scr_write(struct ata_link *link, int reg, u32 val);
-extern int sata_scr_write_flush(struct ata_link *link, int reg, u32 val);
extern bool ata_link_online(struct ata_link *link);
extern bool ata_link_offline(struct ata_link *link);
#ifdef CONFIG_PM
extern u32 ata_wait_register(struct ata_port *ap, void __iomem *reg, u32 mask,
u32 val, unsigned long interval, unsigned long timeout);
extern int atapi_cmd_type(u8 opcode);
-extern void ata_tf_to_fis(const struct ata_taskfile *tf,
- u8 pmp, int is_cmd, u8 *fis);
-extern void ata_tf_from_fis(const u8 *fis, struct ata_taskfile *tf);
extern unsigned long ata_pack_xfermask(unsigned long pio_mask,
unsigned long mwdma_mask, unsigned long udma_mask);
extern void ata_unpack_xfermask(unsigned long xfer_mask,
extern unsigned int ata_do_dev_read_id(struct ata_device *dev,
struct ata_taskfile *tf, u16 *id);
extern void ata_qc_complete(struct ata_queued_cmd *qc);
-extern int ata_qc_complete_multiple(struct ata_port *ap, u64 qc_active);
extern u64 ata_qc_get_active(struct ata_port *ap);
extern void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd);
extern int ata_std_bios_param(struct scsi_device *sdev,
extern int ata_do_set_mode(struct ata_link *link, struct ata_device **r_failed_dev);
extern void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap);
extern void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap, struct list_head *eh_q);
+
+/*
+ * SATA specific code - drivers/ata/libata-sata.c
+ */
+#ifdef CONFIG_SATA_HOST
+extern const unsigned long sata_deb_timing_normal[];
+extern const unsigned long sata_deb_timing_hotplug[];
+extern const unsigned long sata_deb_timing_long[];
+
+static inline const unsigned long *
+sata_ehc_deb_timing(struct ata_eh_context *ehc)
+{
+ if (ehc->i.flags & ATA_EHI_HOTPLUGGED)
+ return sata_deb_timing_hotplug;
+ else
+ return sata_deb_timing_normal;
+}
+
+extern int sata_scr_valid(struct ata_link *link);
+extern int sata_scr_read(struct ata_link *link, int reg, u32 *val);
+extern int sata_scr_write(struct ata_link *link, int reg, u32 val);
+extern int sata_scr_write_flush(struct ata_link *link, int reg, u32 val);
+extern int sata_set_spd(struct ata_link *link);
+extern int sata_link_hardreset(struct ata_link *link,
+ const unsigned long *timing, unsigned long deadline,
+ bool *online, int (*check_ready)(struct ata_link *));
+extern int sata_link_resume(struct ata_link *link, const unsigned long *params,
+ unsigned long deadline);
+extern void ata_eh_analyze_ncq_error(struct ata_link *link);
+#else
+static inline const unsigned long *
+sata_ehc_deb_timing(struct ata_eh_context *ehc)
+{
+ return NULL;
+}
+static inline int sata_scr_valid(struct ata_link *link) { return 0; }
+static inline int sata_scr_read(struct ata_link *link, int reg, u32 *val)
+{
+ return -EOPNOTSUPP;
+}
+static inline int sata_scr_write(struct ata_link *link, int reg, u32 val)
+{
+ return -EOPNOTSUPP;
+}
+static inline int sata_scr_write_flush(struct ata_link *link, int reg, u32 val)
+{
+ return -EOPNOTSUPP;
+}
+static inline int sata_set_spd(struct ata_link *link) { return -EOPNOTSUPP; }
+static inline int sata_link_hardreset(struct ata_link *link,
+ const unsigned long *timing,
+ unsigned long deadline,
+ bool *online,
+ int (*check_ready)(struct ata_link *))
+{
+ if (online)
+ *online = false;
+ return -EOPNOTSUPP;
+}
+static inline int sata_link_resume(struct ata_link *link,
+ const unsigned long *params,
+ unsigned long deadline)
+{
+ return -EOPNOTSUPP;
+}
+static inline void ata_eh_analyze_ncq_error(struct ata_link *link) { }
+#endif
+extern int sata_link_debounce(struct ata_link *link,
+ const unsigned long *params, unsigned long deadline);
+extern int sata_link_scr_lpm(struct ata_link *link, enum ata_lpm_policy policy,
+ bool spm_wakeup);
+extern int ata_slave_link_init(struct ata_port *ap);
+extern void ata_sas_port_destroy(struct ata_port *);
+extern struct ata_port *ata_sas_port_alloc(struct ata_host *,
+ struct ata_port_info *, struct Scsi_Host *);
+extern void ata_sas_async_probe(struct ata_port *ap);
+extern int ata_sas_sync_probe(struct ata_port *ap);
+extern int ata_sas_port_init(struct ata_port *);
+extern int ata_sas_port_start(struct ata_port *ap);
+extern int ata_sas_tport_add(struct device *parent, struct ata_port *ap);
+extern void ata_sas_tport_delete(struct ata_port *ap);
+extern void ata_sas_port_stop(struct ata_port *ap);
+extern int ata_sas_slave_configure(struct scsi_device *, struct ata_port *);
+extern int ata_sas_queuecmd(struct scsi_cmnd *cmd, struct ata_port *ap);
+extern void ata_tf_to_fis(const struct ata_taskfile *tf,
+ u8 pmp, int is_cmd, u8 *fis);
+extern void ata_tf_from_fis(const u8 *fis, struct ata_taskfile *tf);
+extern int ata_qc_complete_multiple(struct ata_port *ap, u64 qc_active);
extern bool sata_lpm_ignore_phy_events(struct ata_link *link);
+extern int sata_async_notification(struct ata_port *ap);
extern int ata_cable_40wire(struct ata_port *ap);
extern int ata_cable_80wire(struct ata_port *ap);
/* Timing helpers */
extern unsigned int ata_pio_need_iordy(const struct ata_device *);
-extern const struct ata_timing *ata_timing_find_mode(u8 xfer_mode);
-extern int ata_timing_compute(struct ata_device *, unsigned short,
- struct ata_timing *, int, int);
-extern void ata_timing_merge(const struct ata_timing *,
- const struct ata_timing *, struct ata_timing *,
- unsigned int);
extern u8 ata_timing_cycle2mode(unsigned int xfer_shift, int cycle);
/* PCI */
extern int ata_link_abort(struct ata_link *link);
extern int ata_port_abort(struct ata_port *ap);
extern int ata_port_freeze(struct ata_port *ap);
-extern int sata_async_notification(struct ata_port *ap);
extern void ata_eh_freeze_port(struct ata_port *ap);
extern void ata_eh_thaw_port(struct ata_port *ap);
extern void ata_eh_qc_complete(struct ata_queued_cmd *qc);
extern void ata_eh_qc_retry(struct ata_queued_cmd *qc);
-extern void ata_eh_analyze_ncq_error(struct ata_link *link);
extern void ata_do_eh(struct ata_port *ap, ata_prereset_fn_t prereset,
ata_reset_fn_t softreset, ata_reset_fn_t hardreset,
* edge driver's module reference, otherwise the driver can be unloaded
* even if the scsi_device is being accessed.
*/
-#define ATA_BASE_SHT(drv_name) \
+#define __ATA_BASE_SHT(drv_name) \
.module = THIS_MODULE, \
.name = drv_name, \
.ioctl = ata_scsi_ioctl, \
.slave_configure = ata_scsi_slave_config, \
.slave_destroy = ata_scsi_slave_destroy, \
.bios_param = ata_std_bios_param, \
- .unlock_native_capacity = ata_scsi_unlock_native_capacity, \
+ .unlock_native_capacity = ata_scsi_unlock_native_capacity
+
+#define ATA_BASE_SHT(drv_name) \
+ __ATA_BASE_SHT(drv_name), \
.sdev_attrs = ata_common_sdev_attrs
+#ifdef CONFIG_SATA_HOST
+extern struct device_attribute *ata_ncq_sdev_attrs[];
+
#define ATA_NCQ_SHT(drv_name) \
- ATA_BASE_SHT(drv_name), \
+ __ATA_BASE_SHT(drv_name), \
+ .sdev_attrs = ata_ncq_sdev_attrs, \
.change_queue_depth = ata_scsi_change_queue_depth
+#endif
/*
* PMP helpers
*/
static inline int ata_ncq_enabled(struct ata_device *dev)
{
+ if (!IS_ENABLED(CONFIG_SATA_HOST))
+ return 0;
return (dev->flags & (ATA_DFLAG_PIO | ATA_DFLAG_NCQ_OFF |
ATA_DFLAG_NCQ)) == ATA_DFLAG_NCQ;
}
}
/**************************************************************************
+ * PATA timings - drivers/ata/libata-pata-timings.c
+ */
+extern const struct ata_timing *ata_timing_find_mode(u8 xfer_mode);
+extern int ata_timing_compute(struct ata_device *, unsigned short,
+ struct ata_timing *, int, int);
+extern void ata_timing_merge(const struct ata_timing *,
+ const struct ata_timing *, struct ata_timing *,
+ unsigned int);
+
+/**************************************************************************
* PMP - drivers/ata/libata-pmp.c
*/
#ifdef CONFIG_SATA_PMP
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_MSDOS_PARTITION_H
+#define _LINUX_MSDOS_PARTITION_H
+
+#define MSDOS_LABEL_MAGIC 0xAA55
+
+struct msdos_partition {
+ u8 boot_ind; /* 0x80 - active */
+ u8 head; /* starting head */
+ u8 sector; /* starting sector */
+ u8 cyl; /* starting cylinder */
+ u8 sys_ind; /* What partition type */
+ u8 end_head; /* end head */
+ u8 end_sector; /* end sector */
+ u8 end_cyl; /* end cylinder */
+ __le32 start_sect; /* starting sector counting from 0 */
+ __le32 nr_sects; /* nr of sectors in partition */
+} __packed;
+
+enum msdos_sys_ind {
+ /*
+ * These three have identical behaviour; use the second one if DOS FDISK
+ * gets confused about extended/logical partitions starting past
+ * cylinder 1023.
+ */
+ DOS_EXTENDED_PARTITION = 5,
+ LINUX_EXTENDED_PARTITION = 0x85,
+ WIN98_EXTENDED_PARTITION = 0x0f,
+
+ LINUX_DATA_PARTITION = 0x83,
+ LINUX_LVM_PARTITION = 0x8e,
+ LINUX_RAID_PARTITION = 0xfd, /* autodetect RAID partition */
+
+ SOLARIS_X86_PARTITION = 0x82, /* also Linux swap partitions */
+ NEW_SOLARIS_X86_PARTITION = 0xbf,
+
+ DM6_AUX1PARTITION = 0x51, /* no DDO: use xlated geom */
+ DM6_AUX3PARTITION = 0x53, /* no DDO: use xlated geom */
+ DM6_PARTITION = 0x54, /* has DDO: use xlated geom & offset */
+ EZD_PARTITION = 0x55, /* EZ-DRIVE */
+
+ FREEBSD_PARTITION = 0xa5, /* FreeBSD Partition ID */
+ OPENBSD_PARTITION = 0xa6, /* OpenBSD Partition ID */
+ NETBSD_PARTITION = 0xa9, /* NetBSD Partition ID */
+ BSDI_PARTITION = 0xb7, /* BSDI Partition ID */
+ MINIX_PARTITION = 0x81, /* Minix Partition ID */
+ UNIXWARE_PARTITION = 0x63, /* Same as GNU_HURD and SCO Unix */
+};
+
+#endif /* LINUX_MSDOS_PARTITION_H */
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_PART_STAT_H
+#define _LINUX_PART_STAT_H
+
+#include <linux/genhd.h>
+
+/*
+ * Macros to operate on percpu disk statistics:
+ *
+ * {disk|part|all}_stat_{add|sub|inc|dec}() modify the stat counters
+ * and should be called between disk_stat_lock() and
+ * disk_stat_unlock().
+ *
+ * part_stat_read() can be called at any time.
+ *
+ * part_stat_{add|set_all}() and {init|free}_part_stats are for
+ * internal use only.
+ */
+#ifdef CONFIG_SMP
+#define part_stat_lock() ({ rcu_read_lock(); get_cpu(); })
+#define part_stat_unlock() do { put_cpu(); rcu_read_unlock(); } while (0)
+
+#define part_stat_get_cpu(part, field, cpu) \
+ (per_cpu_ptr((part)->dkstats, (cpu))->field)
+
+#define part_stat_get(part, field) \
+ part_stat_get_cpu(part, field, smp_processor_id())
+
+#define part_stat_read(part, field) \
+({ \
+ typeof((part)->dkstats->field) res = 0; \
+ unsigned int _cpu; \
+ for_each_possible_cpu(_cpu) \
+ res += per_cpu_ptr((part)->dkstats, _cpu)->field; \
+ res; \
+})
+
+static inline void part_stat_set_all(struct hd_struct *part, int value)
+{
+ int i;
+
+ for_each_possible_cpu(i)
+ memset(per_cpu_ptr(part->dkstats, i), value,
+ sizeof(struct disk_stats));
+}
+
+static inline int init_part_stats(struct hd_struct *part)
+{
+ part->dkstats = alloc_percpu(struct disk_stats);
+ if (!part->dkstats)
+ return 0;
+ return 1;
+}
+
+static inline void free_part_stats(struct hd_struct *part)
+{
+ free_percpu(part->dkstats);
+}
+
+#else /* !CONFIG_SMP */
+#define part_stat_lock() ({ rcu_read_lock(); 0; })
+#define part_stat_unlock() rcu_read_unlock()
+
+#define part_stat_get(part, field) ((part)->dkstats.field)
+#define part_stat_get_cpu(part, field, cpu) part_stat_get(part, field)
+#define part_stat_read(part, field) part_stat_get(part, field)
+
+static inline void part_stat_set_all(struct hd_struct *part, int value)
+{
+ memset(&part->dkstats, value, sizeof(struct disk_stats));
+}
+
+static inline int init_part_stats(struct hd_struct *part)
+{
+ return 1;
+}
+
+static inline void free_part_stats(struct hd_struct *part)
+{
+}
+
+#endif /* CONFIG_SMP */
+
+#define part_stat_read_accum(part, field) \
+ (part_stat_read(part, field[STAT_READ]) + \
+ part_stat_read(part, field[STAT_WRITE]) + \
+ part_stat_read(part, field[STAT_DISCARD]))
+
+#define __part_stat_add(part, field, addnd) \
+ (part_stat_get(part, field) += (addnd))
+
+#define part_stat_add(part, field, addnd) do { \
+ __part_stat_add((part), field, addnd); \
+ if ((part)->partno) \
+ __part_stat_add(&part_to_disk((part))->part0, \
+ field, addnd); \
+} while (0)
+
+#define part_stat_dec(gendiskp, field) \
+ part_stat_add(gendiskp, field, -1)
+#define part_stat_inc(gendiskp, field) \
+ part_stat_add(gendiskp, field, 1)
+#define part_stat_sub(gendiskp, field, subnd) \
+ part_stat_add(gendiskp, field, -subnd)
+
+#define part_stat_local_dec(gendiskp, field) \
+ local_dec(&(part_stat_get(gendiskp, field)))
+#define part_stat_local_inc(gendiskp, field) \
+ local_inc(&(part_stat_get(gendiskp, field)))
+#define part_stat_local_read(gendiskp, field) \
+ local_read(&(part_stat_get(gendiskp, field)))
+#define part_stat_local_read_cpu(gendiskp, field, cpu) \
+ local_read(&(part_stat_get_cpu(gendiskp, field, cpu)))
+
+#endif /* _LINUX_PART_STAT_H */
/* Vendors and devices. Sort key: vendor first, device next. */
+#define PCI_VENDOR_ID_LOONGSON 0x0014
+
#define PCI_VENDOR_ID_TTTECH 0x0357
#define PCI_DEVICE_ID_TTTECH_MC322 0x000a
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+
+void md_autodetect_dev(dev_t dev);
#define SECCOMP_FILTER_FLAG_MASK (SECCOMP_FILTER_FLAG_TSYNC | \
SECCOMP_FILTER_FLAG_LOG | \
SECCOMP_FILTER_FLAG_SPEC_ALLOW | \
- SECCOMP_FILTER_FLAG_NEW_LISTENER)
+ SECCOMP_FILTER_FLAG_NEW_LISTENER | \
+ SECCOMP_FILTER_FLAG_TSYNC_ESRCH)
#ifdef CONFIG_SECCOMP
struct user_msghdr __user *umsg, unsigned flags,
struct sockaddr __user **uaddr,
struct iovec **iov);
+extern int __copy_msghdr_from_user(struct msghdr *kmsg,
+ struct user_msghdr __user *umsg,
+ struct sockaddr __user **save_addr,
+ struct iovec __user **uiov, size_t *nsegs);
/* helpers which do the actual work for syscalls */
extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size,
struct pipe_buffer *);
extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *,
splice_direct_actor *);
+extern long do_splice(struct file *in, loff_t __user *off_in,
+ struct file *out, loff_t __user *off_out,
+ size_t len, unsigned int flags);
/*
* for dynamic pipe sizing
#define compat_mmsghdr mmsghdr
#endif /* defined(CONFIG_COMPAT) */
+int __get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr __user *umsg,
+ struct sockaddr __user **save_addr, compat_uptr_t *ptr,
+ compat_size_t *len);
int get_compat_msghdr(struct msghdr *, struct compat_msghdr __user *,
struct sockaddr __user **, struct iovec **);
struct sock_fprog __user *get_compat_bpf_fprog(char __user *optval);
#ifndef SCSICAM_H
#define SCSICAM_H
-extern int scsicam_bios_param (struct block_device *bdev, sector_t capacity, int *ip);
-extern int scsi_partsize(unsigned char *buf, unsigned long capacity,
- unsigned int *cyls, unsigned int *hds, unsigned int *secs);
-extern unsigned char *scsi_bios_ptable(struct block_device *bdev);
+int scsicam_bios_param(struct block_device *bdev, sector_t capacity, int *ip);
+bool scsi_partsize(struct block_device *bdev, sector_t capacity, int geom[3]);
+unsigned char *scsi_bios_ptable(struct block_device *bdev);
#endif /* def SCSICAM_H */
__entry->force_nonblock, __entry->sq_thread)
);
+TRACE_EVENT(io_uring_poll_arm,
+
+ TP_PROTO(void *ctx, u8 opcode, u64 user_data, int mask, int events),
+
+ TP_ARGS(ctx, opcode, user_data, mask, events),
+
+ TP_STRUCT__entry (
+ __field( void *, ctx )
+ __field( u8, opcode )
+ __field( u64, user_data )
+ __field( int, mask )
+ __field( int, events )
+ ),
+
+ TP_fast_assign(
+ __entry->ctx = ctx;
+ __entry->opcode = opcode;
+ __entry->user_data = user_data;
+ __entry->mask = mask;
+ __entry->events = events;
+ ),
+
+ TP_printk("ring %p, op %d, data 0x%llx, mask 0x%x, events 0x%x",
+ __entry->ctx, __entry->opcode,
+ (unsigned long long) __entry->user_data,
+ __entry->mask, __entry->events)
+);
+
+TRACE_EVENT(io_uring_poll_wake,
+
+ TP_PROTO(void *ctx, u8 opcode, u64 user_data, int mask),
+
+ TP_ARGS(ctx, opcode, user_data, mask),
+
+ TP_STRUCT__entry (
+ __field( void *, ctx )
+ __field( u8, opcode )
+ __field( u64, user_data )
+ __field( int, mask )
+ ),
+
+ TP_fast_assign(
+ __entry->ctx = ctx;
+ __entry->opcode = opcode;
+ __entry->user_data = user_data;
+ __entry->mask = mask;
+ ),
+
+ TP_printk("ring %p, op %d, data 0x%llx, mask 0x%x",
+ __entry->ctx, __entry->opcode,
+ (unsigned long long) __entry->user_data,
+ __entry->mask)
+);
+
+TRACE_EVENT(io_uring_task_add,
+
+ TP_PROTO(void *ctx, u8 opcode, u64 user_data, int mask),
+
+ TP_ARGS(ctx, opcode, user_data, mask),
+
+ TP_STRUCT__entry (
+ __field( void *, ctx )
+ __field( u8, opcode )
+ __field( u64, user_data )
+ __field( int, mask )
+ ),
+
+ TP_fast_assign(
+ __entry->ctx = ctx;
+ __entry->opcode = opcode;
+ __entry->user_data = user_data;
+ __entry->mask = mask;
+ ),
+
+ TP_printk("ring %p, op %d, data 0x%llx, mask %x",
+ __entry->ctx, __entry->opcode,
+ (unsigned long long) __entry->user_data,
+ __entry->mask)
+);
+
+TRACE_EVENT(io_uring_task_run,
+
+ TP_PROTO(void *ctx, u8 opcode, u64 user_data),
+
+ TP_ARGS(ctx, opcode, user_data),
+
+ TP_STRUCT__entry (
+ __field( void *, ctx )
+ __field( u8, opcode )
+ __field( u64, user_data )
+ ),
+
+ TP_fast_assign(
+ __entry->ctx = ctx;
+ __entry->opcode = opcode;
+ __entry->user_data = user_data;
+ ),
+
+ TP_printk("ring %p, op %d, data 0x%llx",
+ __entry->ctx, __entry->opcode,
+ (unsigned long long) __entry->user_data)
+);
+
#endif /* _TRACE_IO_URING_H */
/* This part must be outside protection */
* Handbook", Sanches and Canton.
*/
-#ifdef FDPATCHES
-#define FD_IOPORT fdc_state[fdc].address
-#else
-/* It would be a lot saner just to force fdc_state[fdc].address to always
- be set ! FIXME */
-#define FD_IOPORT 0x3f0
-#endif
-
/* Fd controller regs. S&C, about page 340 */
-#define FD_STATUS (4 + FD_IOPORT )
-#define FD_DATA (5 + FD_IOPORT )
+#define FD_STATUS 4
+#define FD_DATA 5
/* Digital Output Register */
-#define FD_DOR (2 + FD_IOPORT )
+#define FD_DOR 2
/* Digital Input Register (read) */
-#define FD_DIR (7 + FD_IOPORT )
+#define FD_DIR 7
/* Diskette Control Register (write)*/
-#define FD_DCR (7 + FD_IOPORT )
+#define FD_DCR 7
/* Bits of main status register */
#define STATUS_BUSYMASK 0x0F /* drive busy mask */
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR MIT */
/*
* Header file for the io_uring interface.
*
__u64 off; /* offset into file */
__u64 addr2;
};
- __u64 addr; /* pointer to buffer or iovecs */
+ union {
+ __u64 addr; /* pointer to buffer or iovecs */
+ __u64 splice_off_in;
+ };
__u32 len; /* buffer size or number of iovecs */
union {
__kernel_rwf_t rw_flags;
__u32 open_flags;
__u32 statx_flags;
__u32 fadvise_advice;
+ __u32 splice_flags;
};
__u64 user_data; /* data to be passed back at completion time */
union {
struct {
- /* index into fixed buffers, if used */
- __u16 buf_index;
+ /* pack this to avoid bogus arm OABI complaints */
+ union {
+ /* index into fixed buffers, if used */
+ __u16 buf_index;
+ /* for grouped buffer selection */
+ __u16 buf_group;
+ } __attribute__((packed));
/* personality to use, if used */
__u16 personality;
+ __s32 splice_fd_in;
};
__u64 __pad2[3];
};
IOSQE_IO_LINK_BIT,
IOSQE_IO_HARDLINK_BIT,
IOSQE_ASYNC_BIT,
+ IOSQE_BUFFER_SELECT_BIT,
};
/*
#define IOSQE_IO_HARDLINK (1U << IOSQE_IO_HARDLINK_BIT)
/* always go async */
#define IOSQE_ASYNC (1U << IOSQE_ASYNC_BIT)
+/* select buffer from sqe->buf_group */
+#define IOSQE_BUFFER_SELECT (1U << IOSQE_BUFFER_SELECT_BIT)
/*
* io_uring_setup() flags
IORING_OP_RECV,
IORING_OP_OPENAT2,
IORING_OP_EPOLL_CTL,
+ IORING_OP_SPLICE,
+ IORING_OP_PROVIDE_BUFFERS,
+ IORING_OP_REMOVE_BUFFERS,
/* this goes last, obviously */
IORING_OP_LAST,
#define IORING_TIMEOUT_ABS (1U << 0)
/*
+ * sqe->splice_flags
+ * extends splice(2) flags
+ */
+#define SPLICE_F_FD_IN_FIXED (1U << 31) /* the last bit of __u32 */
+
+/*
* IO completion data structure (Completion Queue Entry)
*/
struct io_uring_cqe {
};
/*
+ * cqe->flags
+ *
+ * IORING_CQE_F_BUFFER If set, the upper 16 bits are the buffer ID
+ */
+#define IORING_CQE_F_BUFFER (1U << 0)
+
+enum {
+ IORING_CQE_BUFFER_SHIFT = 16,
+};
+
+/*
* Magic offsets for the application to mmap the data it needs
*/
#define IORING_OFF_SQ_RING 0ULL
#define IORING_FEAT_SUBMIT_STABLE (1U << 2)
#define IORING_FEAT_RW_CUR_POS (1U << 3)
#define IORING_FEAT_CUR_PERSONALITY (1U << 4)
+#define IORING_FEAT_FAST_POLL (1U << 5)
/*
* io_uring_register(2) opcodes and arguments
#define SECCOMP_FILTER_FLAG_LOG (1UL << 1)
#define SECCOMP_FILTER_FLAG_SPEC_ALLOW (1UL << 2)
#define SECCOMP_FILTER_FLAG_NEW_LISTENER (1UL << 3)
+#define SECCOMP_FILTER_FLAG_TSYNC_ESRCH (1UL << 4)
/*
* All BPF programs must return a 32-bit value.
struct page *page = alloc_page(GFP_KERNEL);
char *fs_names = page_address(page);
char *p;
-#ifdef CONFIG_BLOCK
char b[BDEVNAME_SIZE];
-#else
- const char *b = name;
-#endif
+ scnprintf(b, BDEVNAME_SIZE, "unknown-block(%u,%u)",
+ MAJOR(ROOT_DEV), MINOR(ROOT_DEV));
get_fs_names(fs_names);
retry:
for (p = fs_names; *p; p += strlen(p)+1) {
* and bad superblock on root device.
* and give them a list of the available devices
*/
-#ifdef CONFIG_BLOCK
- __bdevname(ROOT_DEV, b);
-#endif
printk("VFS: Cannot open root device \"%s\" or %s: error %d\n",
root_device_name, b, err);
printk("Please append a correct \"root=\" boot option; here are the available partitions:\n");
for (p = fs_names; *p; p += strlen(p)+1)
printk(" %s", p);
printk("\n");
-#ifdef CONFIG_BLOCK
- __bdevname(ROOT_DEV, b);
-#endif
panic("VFS: Unable to mount root fs on %s", b);
out:
put_page(page);
int ret;
ret = seccomp_can_sync_threads();
- if (ret)
- return ret;
+ if (ret) {
+ if (flags & SECCOMP_FILTER_FLAG_TSYNC_ESRCH)
+ return -ESRCH;
+ else
+ return ret;
+ }
}
/* Set log flag, if present. */
.poll = seccomp_notify_poll,
.release = seccomp_notify_release,
.unlocked_ioctl = seccomp_notify_ioctl,
+ .compat_ioctl = seccomp_notify_ioctl,
};
static struct file *init_listener(struct seccomp_filter *filter)
* In the successful case, NEW_LISTENER returns the new listener fd.
* But in the failure case, TSYNC returns the thread that died. If you
* combine these two flags, there's no way to tell whether something
- * succeeded or failed. So, let's disallow this combination.
+ * succeeded or failed. So, let's disallow this combination if the user
+ * has not explicitly requested no errors from TSYNC.
*/
if ((flags & SECCOMP_FILTER_FLAG_TSYNC) &&
- (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER))
+ (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) &&
+ ((flags & SECCOMP_FILTER_FLAG_TSYNC_ESRCH) == 0))
return -EINVAL;
/* Prepare the new filter before holding any locks. */
* work->func() can do task_work_add(), do not set
* work_exited unless the list is empty.
*/
- raw_spin_lock_irq(&task->pi_lock);
do {
+ head = NULL;
work = READ_ONCE(task->task_works);
- head = !work && (task->flags & PF_EXITING) ?
- &work_exited : NULL;
+ if (!work) {
+ if (task->flags & PF_EXITING)
+ head = &work_exited;
+ else
+ break;
+ }
} while (cmpxchg(&task->task_works, work, head) != work);
- raw_spin_unlock_irq(&task->pi_lock);
if (!work)
break;
+ /*
+ * Synchronize with task_work_cancel(). It can not remove
+ * the first entry == work, cmpxchg(task_works) must fail.
+ * But it can remove another entry from the ->next list.
+ */
+ raw_spin_lock_irq(&task->pi_lock);
+ raw_spin_unlock_irq(&task->pi_lock);
do {
next = work->next;
#include <linux/uaccess.h>
#include <net/compat.h>
-int get_compat_msghdr(struct msghdr *kmsg,
- struct compat_msghdr __user *umsg,
- struct sockaddr __user **save_addr,
- struct iovec **iov)
+int __get_compat_msghdr(struct msghdr *kmsg,
+ struct compat_msghdr __user *umsg,
+ struct sockaddr __user **save_addr,
+ compat_uptr_t *ptr, compat_size_t *len)
{
struct compat_msghdr msg;
ssize_t err;
return -EMSGSIZE;
kmsg->msg_iocb = NULL;
+ *ptr = msg.msg_iov;
+ *len = msg.msg_iovlen;
+ return 0;
+}
+
+int get_compat_msghdr(struct msghdr *kmsg,
+ struct compat_msghdr __user *umsg,
+ struct sockaddr __user **save_addr,
+ struct iovec **iov)
+{
+ compat_uptr_t ptr;
+ compat_size_t len;
+ ssize_t err;
+
+ err = __get_compat_msghdr(kmsg, umsg, save_addr, &ptr, &len);
+ if (err)
+ return err;
- err = compat_import_iovec(save_addr ? READ : WRITE,
- compat_ptr(msg.msg_iov), msg.msg_iovlen,
- UIO_FASTIOV, iov, &kmsg->msg_iter);
+ err = compat_import_iovec(save_addr ? READ : WRITE, compat_ptr(ptr),
+ len, UIO_FASTIOV, iov, &kmsg->msg_iter);
return err < 0 ? err : 0;
}
If unsure, say Y. Note that if you want to use DHCP, a DHCP server
must be operating on your network. Read
- <file:Documentation/filesystems/nfs/nfsroot.txt> for details.
+ <file:Documentation/admin-guide/nfs/nfsroot.rst> for details.
config IP_PNP_BOOTP
bool "IP: BOOTP support"
does BOOTP itself, providing all necessary information on the kernel
command line, you can say N here. If unsure, say Y. Note that if you
want to use BOOTP, a BOOTP server must be operating on your network.
- Read <file:Documentation/filesystems/nfs/nfsroot.txt> for details.
+ Read <file:Documentation/admin-guide/nfs/nfsroot.rst> for details.
config IP_PNP_RARP
bool "IP: RARP support"
older protocol which is being obsoleted by BOOTP and DHCP), say Y
here. Note that if you want to use RARP, a RARP server must be
operating on your network. Read
- <file:Documentation/filesystems/nfs/nfsroot.txt> for details.
+ <file:Documentation/admin-guide/nfs/nfsroot.rst> for details.
config NET_IPIP
tristate "IP: tunneling"
/*
* Decode any IP configuration options in the "ip=" or "nfsaddrs=" kernel
- * command line parameter. See Documentation/filesystems/nfs/nfsroot.txt.
+ * command line parameter. See Documentation/admin-guide/nfs/nfsroot.rst.
*/
static int __init ic_proto_name(char *name)
{
unsigned int name_len;
};
-static int copy_msghdr_from_user(struct msghdr *kmsg,
- struct user_msghdr __user *umsg,
- struct sockaddr __user **save_addr,
- struct iovec **iov)
+int __copy_msghdr_from_user(struct msghdr *kmsg,
+ struct user_msghdr __user *umsg,
+ struct sockaddr __user **save_addr,
+ struct iovec __user **uiov, size_t *nsegs)
{
struct user_msghdr msg;
ssize_t err;
return -EMSGSIZE;
kmsg->msg_iocb = NULL;
+ *uiov = msg.msg_iov;
+ *nsegs = msg.msg_iovlen;
+ return 0;
+}
+
+static int copy_msghdr_from_user(struct msghdr *kmsg,
+ struct user_msghdr __user *umsg,
+ struct sockaddr __user **save_addr,
+ struct iovec **iov)
+{
+ struct user_msghdr msg;
+ ssize_t err;
+
+ err = __copy_msghdr_from_user(kmsg, umsg, save_addr, &msg.msg_iov,
+ &msg.msg_iovlen);
+ if (err)
+ return err;
err = import_iovec(save_addr ? READ : WRITE,
msg.msg_iov, msg.msg_iovlen,
--- /dev/null
+#!/usr/bin/gawk -f
+# SPDX-License-Identifier: GPL-2.0
+
+# Script to check sysctl documentation against source files
+#
+# Copyright (c) 2020 Stephen Kitt
+
+# Example invocation:
+# scripts/check-sysctl-docs -vtable="kernel" \
+# Documentation/admin-guide/sysctl/kernel.rst \
+# $(git grep -l register_sysctl_)
+#
+# Specify -vdebug=1 to see debugging information
+
+BEGIN {
+ if (!table) {
+ print "Please specify the table to look for using the table variable" > "/dev/stderr"
+ exit 1
+ }
+}
+
+# The following globals are used:
+# children: maps ctl_table names and procnames to child ctl_table names
+# documented: maps documented entries (each key is an entry)
+# entries: maps ctl_table names and procnames to counts (so
+# enumerating the subkeys for a given ctl_table lists its
+# procnames)
+# files: maps procnames to source file names
+# paths: maps ctl_path names to paths
+# curpath: the name of the current ctl_path struct
+# curtable: the name of the current ctl_table struct
+# curentry: the name of the current proc entry (procname when parsing
+# a ctl_table, constructed path when parsing a ctl_path)
+
+
+# Remove punctuation from the given value
+function trimpunct(value) {
+ while (value ~ /^["&]/) {
+ value = substr(value, 2)
+ }
+ while (value ~ /[]["&,}]$/) {
+ value = substr(value, 1, length(value) - 1)
+ }
+ return value
+}
+
+# Print the information for the given entry
+function printentry(entry) {
+ seen[entry]++
+ printf "* %s from %s", entry, file[entry]
+ if (documented[entry]) {
+ printf " (documented)"
+ }
+ print ""
+}
+
+
+# Stage 1: build the list of documented entries
+FNR == NR && /^=+$/ {
+ if (prevline ~ /Documentation for/) {
+ # This is the main title
+ next
+ }
+
+ # The previous line is a section title, parse it
+ $0 = prevline
+ if (debug) print "Parsing " $0
+ inbrackets = 0
+ for (i = 1; i <= NF; i++) {
+ if (length($i) == 0) {
+ continue
+ }
+ if (!inbrackets && substr($i, 1, 1) == "(") {
+ inbrackets = 1
+ }
+ if (!inbrackets) {
+ token = trimpunct($i)
+ if (length(token) > 0 && token != "and") {
+ if (debug) print trimpunct($i)
+ documented[trimpunct($i)]++
+ }
+ }
+ if (inbrackets && substr($i, length($i), 1) == ")") {
+ inbrackets = 0
+ }
+ }
+}
+
+FNR == NR {
+ prevline = $0
+ next
+}
+
+
+# Stage 2: process each file and find all sysctl tables
+BEGINFILE {
+ delete children
+ delete entries
+ delete paths
+ curpath = ""
+ curtable = ""
+ curentry = ""
+ if (debug) print "Processing file " FILENAME
+}
+
+/^static struct ctl_path/ {
+ match($0, /static struct ctl_path ([^][]+)/, tables)
+ curpath = tables[1]
+ if (debug) print "Processing path " curpath
+}
+
+/^static struct ctl_table/ {
+ match($0, /static struct ctl_table ([^][]+)/, tables)
+ curtable = tables[1]
+ if (debug) print "Processing table " curtable
+}
+
+/^};$/ {
+ curpath = ""
+ curtable = ""
+ curentry = ""
+}
+
+curpath && /\.procname[\t ]*=[\t ]*".+"/ {
+ match($0, /.procname[\t ]*=[\t ]*"([^"]+)"/, names)
+ if (curentry) {
+ curentry = curentry "/" names[1]
+ } else {
+ curentry = names[1]
+ }
+ if (debug) print "Setting path " curpath " to " curentry
+ paths[curpath] = curentry
+}
+
+curtable && /\.procname[\t ]*=[\t ]*".+"/ {
+ match($0, /.procname[\t ]*=[\t ]*"([^"]+)"/, names)
+ curentry = names[1]
+ if (debug) print "Adding entry " curentry " to table " curtable
+ entries[curtable][curentry]++
+ file[curentry] = FILENAME
+}
+
+/\.child[\t ]*=/ {
+ child = trimpunct($NF)
+ if (debug) print "Linking child " child " to table " curtable " entry " curentry
+ children[curtable][curentry] = child
+}
+
+/register_sysctl_table\(.*\)/ {
+ match($0, /register_sysctl_table\(([^)]+)\)/, tables)
+ if (debug) print "Registering table " tables[1]
+ if (children[tables[1]][table]) {
+ for (entry in entries[children[tables[1]][table]]) {
+ printentry(entry)
+ }
+ }
+}
+
+/register_sysctl_paths\(.*\)/ {
+ match($0, /register_sysctl_paths\(([^)]+), ([^)]+)\)/, tables)
+ if (debug) print "Attaching table " tables[2] " to path " tables[1]
+ if (paths[tables[1]] == table) {
+ for (entry in entries[tables[2]]) {
+ printentry(entry)
+ }
+ }
+ split(paths[tables[1]], components, "/")
+ if (length(components) > 1 && components[1] == table) {
+ # Count the first subdirectory as seen
+ seen[components[2]]++
+ }
+}
+
+
+END {
+ for (entry in documented) {
+ if (!seen[entry]) {
+ print "No implementation for " entry
+ }
+ }
+}
or die "Failed to run git grep";
while (<IN>) {
next if (!m,^([^:]+):.*\:doc\:\`([^\`]+)\`,);
+ next if (m,sphinx/,);
+ my $file = $1;
my $d = $1;
my $doc_ref = $2;
$d =~ s,(.*/).*,$1,;
$f =~ s,.*\<([^\>]+)\>,$1,;
- $f ="$d$f.rst";
+ if ($f =~ m,^/,) {
+ $f = "$f.rst";
+ $f =~ s,^/,Documentation/,;
+ } else {
+ $f = "$d$f.rst";
+ }
next if (grep -e, glob("$f"));
}
$doc_fix++;
- print STDERR "$f: :doc:`$doc_ref`\n";
+ print STDERR "$file: :doc:`$doc_ref`\n";
}
close IN;
GCC plugins are loadable modules that provide extra features to the
compiler. They are useful for runtime instrumentation and static analysis.
- See Documentation/core-api/gcc-plugins.rst for details.
+ See Documentation/kbuild/gcc-plugins.rst for details.
if GCC_PLUGINS
DEVID(i2c_device_id);
DEVID_FIELD(i2c_device_id, name);
+ DEVID(i3c_device_id);
+ DEVID_FIELD(i3c_device_id, match_flags);
+ DEVID_FIELD(i3c_device_id, dcr);
+ DEVID_FIELD(i3c_device_id, manuf_id);
+ DEVID_FIELD(i3c_device_id, part_id);
+ DEVID_FIELD(i3c_device_id, extra_info);
+
DEVID(spi_device_id);
DEVID_FIELD(spi_device_id, name);
return 1;
}
+static int do_i3c_entry(const char *filename, void *symval,
+ char *alias)
+{
+ DEF_FIELD(symval, i3c_device_id, match_flags);
+ DEF_FIELD(symval, i3c_device_id, dcr);
+ DEF_FIELD(symval, i3c_device_id, manuf_id);
+ DEF_FIELD(symval, i3c_device_id, part_id);
+ DEF_FIELD(symval, i3c_device_id, extra_info);
+
+ strcpy(alias, "i3c:");
+ ADD(alias, "dcr", match_flags & I3C_MATCH_DCR, dcr);
+ ADD(alias, "manuf", match_flags & I3C_MATCH_MANUF, manuf_id);
+ ADD(alias, "part", match_flags & I3C_MATCH_PART, part_id);
+ ADD(alias, "ext", match_flags & I3C_MATCH_EXTRA_INFO, extra_info);
+
+ return 1;
+}
+
/* Looks like: spi:S */
static int do_spi_entry(const char *filename, void *symval,
char *alias)
{"vmbus", SIZE_hv_vmbus_device_id, do_vmbus_entry},
{"rpmsg", SIZE_rpmsg_device_id, do_rpmsg_entry},
{"i2c", SIZE_i2c_device_id, do_i2c_entry},
+ {"i3c", SIZE_i3c_device_id, do_i3c_entry},
{"spi", SIZE_spi_device_id, do_spi_entry},
{"dmi", SIZE_dmi_system_id, do_dmi_entry},
{"platform", SIZE_platform_device_id, do_platform_entry},
} else {
my $rec_activate = "$virtenv_dir/bin/activate";
my $virtualenv = findprog("virtualenv-3");
+ my $rec_python3 = "";
$virtualenv = findprog("virtualenv-3.5") if (!$virtualenv);
$virtualenv = findprog("virtualenv") if (!$virtualenv);
$virtualenv = "virtualenv" if (!$virtualenv);
- printf "\t$virtualenv $virtenv_dir\n";
+ my $rel = "";
+ if (index($system_release, "Ubuntu") != -1) {
+ $rel = $1 if ($system_release =~ /Ubuntu\s+(\d+)[.]/);
+ if ($rel && $rel >= 16) {
+ $rec_python3 = " -p python3";
+ }
+ }
+ if (index($system_release, "Debian") != -1) {
+ $rel = $1 if ($system_release =~ /Debian\s+(\d+)/);
+ if ($rel && $rel >= 7) {
+ $rec_python3 = " -p python3";
+ }
+ }
+
+ printf "\t$virtualenv$rec_python3 $virtenv_dir\n";
printf "\t. $rec_activate\n";
printf "\tpip install -r $requirement_file\n";
deactivate_help();
spin_lock(&key->user->lock);
if (delta > 0 &&
- (key->user->qnbytes + delta >= maxbytes ||
+ (key->user->qnbytes + delta > maxbytes ||
key->user->qnbytes + delta < key->user->qnbytes)) {
ret = -EDQUOT;
}
key_quota_root_maxbytes : key_quota_maxbytes;
spin_lock(&newowner->lock);
- if (newowner->qnkeys + 1 >= maxkeys ||
- newowner->qnbytes + key->quotalen >= maxbytes ||
+ if (newowner->qnkeys + 1 > maxkeys ||
+ newowner->qnbytes + key->quotalen > maxbytes ||
newowner->qnbytes + key->quotalen <
newowner->qnbytes)
goto quota_overrun;
#define SECCOMP_USER_NOTIF_FLAG_CONTINUE 0x00000001
#endif
+#ifndef SECCOMP_FILTER_FLAG_TSYNC_ESRCH
+#define SECCOMP_FILTER_FLAG_TSYNC_ESRCH (1UL << 4)
+#endif
+
#ifndef seccomp
int seccomp(unsigned int op, unsigned int flags, void *args)
{
unsigned int flags[] = { SECCOMP_FILTER_FLAG_TSYNC,
SECCOMP_FILTER_FLAG_LOG,
SECCOMP_FILTER_FLAG_SPEC_ALLOW,
- SECCOMP_FILTER_FLAG_NEW_LISTENER };
+ SECCOMP_FILTER_FLAG_NEW_LISTENER,
+ SECCOMP_FILTER_FLAG_TSYNC_ESRCH };
unsigned int exclusive[] = {
SECCOMP_FILTER_FLAG_TSYNC,
SECCOMP_FILTER_FLAG_NEW_LISTENER };
EXPECT_EQ(SIBLING_EXIT_UNKILLED, (long)status);
}
+TEST_F(TSYNC, two_siblings_with_one_divergence_no_tid_in_err)
+{
+ long ret, flags;
+ void *status;
+
+ ASSERT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) {
+ TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
+ }
+
+ ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &self->root_prog);
+ ASSERT_NE(ENOSYS, errno) {
+ TH_LOG("Kernel does not support seccomp syscall!");
+ }
+ ASSERT_EQ(0, ret) {
+ TH_LOG("Kernel does not support SECCOMP_SET_MODE_FILTER!");
+ }
+ self->sibling[0].diverge = 1;
+ tsync_start_sibling(&self->sibling[0]);
+ tsync_start_sibling(&self->sibling[1]);
+
+ while (self->sibling_count < TSYNC_SIBLINGS) {
+ sem_wait(&self->started);
+ self->sibling_count++;
+ }
+
+ flags = SECCOMP_FILTER_FLAG_TSYNC | \
+ SECCOMP_FILTER_FLAG_TSYNC_ESRCH;
+ ret = seccomp(SECCOMP_SET_MODE_FILTER, flags, &self->apply_prog);
+ ASSERT_EQ(ESRCH, errno) {
+ TH_LOG("Did not return ESRCH for diverged sibling.");
+ }
+ ASSERT_EQ(-1, ret) {
+ TH_LOG("Did not fail on diverged sibling.");
+ }
+
+ /* Wake the threads */
+ pthread_mutex_lock(&self->mutex);
+ ASSERT_EQ(0, pthread_cond_broadcast(&self->cond)) {
+ TH_LOG("cond broadcast non-zero");
+ }
+ pthread_mutex_unlock(&self->mutex);
+
+ /* Ensure they are both unkilled. */
+ PTHREAD_JOIN(self->sibling[0].tid, &status);
+ EXPECT_EQ(SIBLING_EXIT_UNKILLED, (long)status);
+ PTHREAD_JOIN(self->sibling[1].tid, &status);
+ EXPECT_EQ(SIBLING_EXIT_UNKILLED, (long)status);
+}
+
TEST_F(TSYNC, two_siblings_not_under_filter)
{
long ret, sib;
EXPECT_EQ(0, WEXITSTATUS(status));
}
+TEST(user_notification_with_tsync)
+{
+ int ret;
+ unsigned int flags;
+
+ /* these were exclusive */
+ flags = SECCOMP_FILTER_FLAG_NEW_LISTENER |
+ SECCOMP_FILTER_FLAG_TSYNC;
+ ASSERT_EQ(-1, user_trap_syscall(__NR_getppid, flags));
+ ASSERT_EQ(EINVAL, errno);
+
+ /* but now they're not */
+ flags |= SECCOMP_FILTER_FLAG_TSYNC_ESRCH;
+ ret = user_trap_syscall(__NR_getppid, flags);
+ close(ret);
+ ASSERT_LE(0, ret);
+}
+
TEST(user_notification_kill_in_middle)
{
pid_t pid;