Ricardo Ribalda <ribalda@kernel.org> <ricardo@ribalda.com>
Ricardo Ribalda <ribalda@kernel.org> Ricardo Ribalda Delgado <ribalda@kernel.org>
Ricardo Ribalda <ribalda@kernel.org> <ricardo.ribalda@gmail.com>
+Robert Foss <rfoss@kernel.org> <robert.foss@linaro.org>
Roman Gushchin <roman.gushchin@linux.dev> <guro@fb.com>
Roman Gushchin <roman.gushchin@linux.dev> <guroan@gmail.com>
Roman Gushchin <roman.gushchin@linux.dev> <klamm@yandex-team.ru>
TripleX Chung <xxx.phy@gmail.com> <triplex@zh-kernel.org>
TripleX Chung <xxx.phy@gmail.com> <zhongyu@18mail.cn>
Tsuneo Yoshioka <Tsuneo.Yoshioka@f-secure.com>
+Tudor Ambarus <tudor.ambarus@linaro.org> <tudor.ambarus@microchip.com>
Tycho Andersen <tycho@tycho.pizza> <tycho@tycho.ws>
Tzung-Bi Shih <tzungbi@kernel.org> <tzungbi@google.com>
Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de>
--- /dev/null
+What: /sys/kernel/debug/pktcdvd/pktcdvd[0-7]
+Date: Oct. 2006
+KernelVersion: 2.6.20
+Contact: Thomas Maier <balagi@justmail.de>
+Description:
+
+The pktcdvd module (packet writing driver) creates
+these files in debugfs:
+
+/sys/kernel/debug/pktcdvd/pktcdvd[0-7]/
+
+ ==== ====== ====================================
+ info 0444 Lots of driver statistics and infos.
+ ==== ====== ====================================
+
+Example::
+
+ cat /sys/kernel/debug/pktcdvd/pktcdvd0/info
--- /dev/null
+sysfs interface
+---------------
+The pktcdvd module (packet writing driver) creates the following files in the
+sysfs: (<devid> is in the format major:minor)
+
+What: /sys/class/pktcdvd/add
+What: /sys/class/pktcdvd/remove
+What: /sys/class/pktcdvd/device_map
+Date: Oct. 2006
+KernelVersion: 2.6.20
+Contact: Thomas Maier <balagi@justmail.de>
+Description:
+
+ ========== ==============================================
+ add (WO) Write a block device id (major:minor) to
+ create a new pktcdvd device and map it to the
+ block device.
+
+ remove (WO) Write the pktcdvd device id (major:minor)
+ to remove the pktcdvd device.
+
+ device_map (RO) Shows the device mapping in format:
+ pktcdvd[0-7] <pktdevid> <blkdevid>
+ ========== ==============================================
+
+
+What: /sys/class/pktcdvd/pktcdvd[0-7]/dev
+What: /sys/class/pktcdvd/pktcdvd[0-7]/uevent
+Date: Oct. 2006
+KernelVersion: 2.6.20
+Contact: Thomas Maier <balagi@justmail.de>
+Description:
+ dev: (RO) Device id
+
+ uevent: (WO) To send a uevent
+
+
+What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/packets_started
+What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/packets_finished
+What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/kb_written
+What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/kb_read
+What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/kb_read_gather
+What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/reset
+Date: Oct. 2006
+KernelVersion: 2.6.20
+Contact: Thomas Maier <balagi@justmail.de>
+Description:
+ packets_started: (RO) Number of started packets.
+
+ packets_finished: (RO) Number of finished packets.
+
+ kb_written: (RO) kBytes written.
+
+ kb_read: (RO) kBytes read.
+
+ kb_read_gather: (RO) kBytes read to fill write packets.
+
+ reset: (WO) Write any value to it to reset
+ pktcdvd device statistic values, like
+ bytes read/written.
+
+
+What: /sys/class/pktcdvd/pktcdvd[0-7]/write_queue/size
+What: /sys/class/pktcdvd/pktcdvd[0-7]/write_queue/congestion_off
+What: /sys/class/pktcdvd/pktcdvd[0-7]/write_queue/congestion_on
+Date: Oct. 2006
+KernelVersion: 2.6.20
+Contact: Thomas Maier <balagi@justmail.de>
+Description:
+ ============== ================================================
+ size (RO) Contains the size of the bio write queue.
+
+ congestion_off (RW) If bio write queue size is below this mark,
+ accept new bio requests from the block layer.
+
+ congestion_on (RW) If bio write queue size is higher as this
+ mark, do no longer accept bio write requests
+ from the block layer and wait till the pktcdvd
+ device has processed enough bio's so that bio
+ write queue size is below congestion off mark.
+ A value of <= 0 disables congestion control.
+ ============== ================================================
+
+
+Example:
+--------
+To use the pktcdvd sysfs interface directly, you can do::
+
+ # create a new pktcdvd device mapped to /dev/hdc
+ echo "22:0" >/sys/class/pktcdvd/add
+ cat /sys/class/pktcdvd/device_map
+ # assuming device pktcdvd0 was created, look at stat's
+ cat /sys/class/pktcdvd/pktcdvd0/stat/kb_written
+ # print the device id of the mapped block device
+ fgrep pktcdvd0 /sys/class/pktcdvd/device_map
+ # remove device, using pktcdvd0 device id 253:0
+ echo "253:0" >/sys/class/pktcdvd/remove
The zbud type zpool allocates exactly 1 page to store 2 compressed pages, which
means the compression ratio will always be 2:1 or worse (because of half-full
zbud pages). The zsmalloc type zpool has a more complex compressed page
-storage method, and it can achieve greater storage densities. However,
-zsmalloc does not implement compressed page eviction, so once zswap fills it
-cannot evict the oldest page, it can only reject new pages.
+storage method, and it can achieve greater storage densities.
When a swap page is passed from frontswap to zswap, zswap maintains a mapping
of the swap entry, a combination of the swap type and swap offset, to the zpool
+----------------+-----------------+-----------------+-----------------------------+
| ARM | Cortex-A710 | #2224489 | ARM64_ERRATUM_2224489 |
+----------------+-----------------+-----------------+-----------------------------+
+| ARM | Cortex-A715 | #2645198 | ARM64_ERRATUM_2645198 |
++----------------+-----------------+-----------------+-----------------------------+
| ARM | Cortex-X2 | #2119858 | ARM64_ERRATUM_2119858 |
+----------------+-----------------+-----------------+-----------------------------+
| ARM | Cortex-X2 | #2224489 | ARM64_ERRATUM_2224489 |
# Get Sphinx version
major, minor, patch = sphinx.version_info[:3]
+#
+# Warn about older versions that we don't want to support for much
+# longer.
+#
+if (major < 2) or (major == 2 and minor < 4):
+ print('WARNING: support for Sphinx < 2.4 will be removed soon.')
# If extensions (or modules to document with autodoc) are in another directory,
# add these directories to sys.path here. If the directory is relative to the
# Custom sidebar templates, maps document names to template names.
# Note that the RTD theme ignores this
-html_sidebars = { '**': ["about.html", 'searchbox.html', 'localtoc.html', 'sourcelink.html']}
+html_sidebars = { '**': ['searchbox.html', 'localtoc.html', 'sourcelink.html']}
+
+# about.html is available for alabaster theme. Add it at the front.
+if html_theme == 'alabaster':
+ html_sidebars['**'].insert(0, 'about.html')
# Output file base name for HTML help builder.
htmlhelp_basename = 'TheLinuxKerneldoc'
- const: xo
- const: alternate
+ interrupts:
+ minItems: 1
+ maxItems: 3
+
+ interrupt-names:
+ minItems: 1
+ items:
+ - const: dcvsh-irq-0
+ - const: dcvsh-irq-1
+ - const: dcvsh-irq-2
+
'#freq-domain-cells':
const: 1
title: Atmel Advanced Encryption Standard (AES) HW cryptographic accelerator
maintainers:
- - Tudor Ambarus <tudor.ambarus@microchip.com>
+ - Tudor Ambarus <tudor.ambarus@linaro.org>
properties:
compatible:
title: Atmel Secure Hash Algorithm (SHA) HW cryptographic accelerator
maintainers:
- - Tudor Ambarus <tudor.ambarus@microchip.com>
+ - Tudor Ambarus <tudor.ambarus@linaro.org>
properties:
compatible:
title: Atmel Triple Data Encryption Standard (TDES) HW cryptographic accelerator
maintainers:
- - Tudor Ambarus <tudor.ambarus@microchip.com>
+ - Tudor Ambarus <tudor.ambarus@linaro.org>
properties:
compatible:
- description: Display byte clock
- description: Display byte interface clock
- description: Display pixel clock
- - description: Display escape clock
+ - description: Display core clock
- description: Display AHB clock
- description: Display AXI clock
- phys
- assigned-clocks
- assigned-clock-parents
- - power-domains
- - operating-points-v2
- ports
additionalProperties: false
- compatible
- reg
- reg-names
- - vdds-supply
unevaluatedProperties: false
- compatible
- reg
- reg-names
- - vcca-supply
unevaluatedProperties: false
vddio-supply:
description: Phandle to vdd-io regulator device node.
+ qcom,dsi-phy-regulator-ldo-mode:
+ type: boolean
+ description: Indicates if the LDO mode PHY regulator is wanted.
+
required:
- compatible
- reg
#include <dt-bindings/interconnect/qcom,qcm2290.h>
#include <dt-bindings/power/qcom-rpmpd.h>
- mdss@5e00000 {
+ display-subsystem@5e00000 {
#address-cells = <1>;
#size-cells = <1>;
compatible = "qcom,qcm2290-mdss";
#include <dt-bindings/interrupt-controller/arm-gic.h>
#include <dt-bindings/power/qcom-rpmpd.h>
- mdss@5e00000 {
+ display-subsystem@5e00000 {
#address-cells = <1>;
#size-cells = <1>;
compatible = "qcom,sm6115-mdss";
clock-names:
const: stmmaceth
+ phy-supply:
+ description: PHY regulator
+
syscon:
$ref: /schemas/types.yaml#/definitions/phandle
description:
8k has a second unit which provides an interface with the xMDIO bus. This
driver handles these interfaces.
-allOf:
- - $ref: "mdio.yaml#"
-
properties:
compatible:
enum:
- compatible
- reg
+allOf:
+ - $ref: mdio.yaml#
+
+ - if:
+ required:
+ - interrupts
+
+ then:
+ properties:
+ reg:
+ items:
+ - items:
+ - $ref: /schemas/types.yaml#/definitions/cell
+ - const: 0x84
+
+ else:
+ properties:
+ reg:
+ items:
+ - items:
+ - $ref: /schemas/types.yaml#/definitions/cell
+ - enum:
+ - 0x4
+ - 0x10
+
unevaluatedProperties: false
examples:
- |
mdio@d0072004 {
compatible = "marvell,orion-mdio";
- reg = <0xd0072004 0x4>;
+ reg = <0xd0072004 0x84>;
#address-cells = <1>;
#size-cells = <0>;
interrupts = <30>;
compatible:
enum:
- mediatek,mt8186-mt6366-rt1019-rt5682s-sound
+ - mediatek,mt8186-mt6366-rt5682s-max98360-sound
mediatek,platform:
$ref: "/schemas/types.yaml#/definitions/phandle"
const: 0
clocks:
- maxItems: 5
+ oneOf:
+ - maxItems: 3
+ - maxItems: 5
clock-names:
oneOf:
maintainers:
- Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
-allOf:
- - $ref: dai-common.yaml#
-
properties:
compatible:
enum:
const: 0
clocks:
- maxItems: 5
+ minItems: 5
+ maxItems: 6
clock-names:
- items:
- - const: mclk
- - const: npl
- - const: macro
- - const: dcodec
- - const: fsgen
+ minItems: 5
+ maxItems: 6
clock-output-names:
maxItems: 1
- reg
- "#sound-dai-cells"
+allOf:
+ - $ref: dai-common.yaml#
+
+ - if:
+ properties:
+ compatible:
+ enum:
+ - qcom,sc7280-lpass-wsa-macro
+ - qcom,sm8450-lpass-wsa-macro
+ - qcom,sc8280xp-lpass-wsa-macro
+ then:
+ properties:
+ clocks:
+ maxItems: 5
+ clock-names:
+ items:
+ - const: mclk
+ - const: npl
+ - const: macro
+ - const: dcodec
+ - const: fsgen
+
+ - if:
+ properties:
+ compatible:
+ enum:
+ - qcom,sm8250-lpass-wsa-macro
+ then:
+ properties:
+ clocks:
+ minItems: 6
+ clock-names:
+ items:
+ - const: mclk
+ - const: npl
+ - const: macro
+ - const: dcodec
+ - const: va
+ - const: fsgen
+
unevaluatedProperties: false
examples:
- |
+ #include <dt-bindings/clock/qcom,sm8250-lpass-aoncc.h>
#include <dt-bindings/sound/qcom,q6afe.h>
codec@3240000 {
compatible = "qcom,sm8250-lpass-wsa-macro";
<&audiocc 0>,
<&q6afecc LPASS_HW_MACRO_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
<&q6afecc LPASS_HW_DCODEC_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>,
+ <&aoncc LPASS_CDC_VA_MCLK>,
<&vamacro>;
- clock-names = "mclk", "npl", "macro", "dcodec", "fsgen";
+ clock-names = "mclk", "npl", "macro", "dcodec", "va", "fsgen";
clock-output-names = "mclk";
};
or applicable for the respective data port.
More info in MIPI Alliance SoundWire 1.0 Specifications.
minItems: 3
- maxItems: 5
+ maxItems: 8
qcom,ports-sinterval-low:
$ref: /schemas/types.yaml#/definitions/uint8-array
or applicable for the respective data port.
More info in MIPI Alliance SoundWire 1.0 Specifications.
minItems: 3
- maxItems: 5
+ maxItems: 8
qcom,ports-block-pack-mode:
$ref: /schemas/types.yaml#/definitions/uint8-array
or applicable for the respective data port.
More info in MIPI Alliance SoundWire 1.0 Specifications.
minItems: 3
- maxItems: 5
+ maxItems: 8
items:
oneOf:
- minimum: 0
or applicable for the respective data port.
More info in MIPI Alliance SoundWire 1.0 Specifications.
minItems: 3
- maxItems: 5
+ maxItems: 8
items:
oneOf:
- minimum: 0
or applicable for the respective data port.
More info in MIPI Alliance SoundWire 1.0 Specifications.
minItems: 3
- maxItems: 5
+ maxItems: 8
items:
oneOf:
- minimum: 0
title: Atmel SPI device
maintainers:
- - Tudor Ambarus <tudor.ambarus@microchip.com>
+ - Tudor Ambarus <tudor.ambarus@linaro.org>
allOf:
- $ref: spi-controller.yaml#
title: Atmel Quad Serial Peripheral Interface (QSPI)
maintainers:
- - Tudor Ambarus <tudor.ambarus@microchip.com>
+ - Tudor Ambarus <tudor.ambarus@linaro.org>
allOf:
- $ref: spi-controller.yaml#
description:
Maximum SPI clocking speed of the device in Hz.
- spi-cs-setup-ns:
+ spi-cs-setup-delay-ns:
description:
- Delay in nanosecods to be introduced by the controller after CS is
+ Delay in nanoseconds to be introduced by the controller after CS is
asserted.
spi-rx-bus-width:
dax A legacy option which is an alias for ``dax=always``.
device=%s Specify a path to an extra device to be used together.
fsid=%s Specify a filesystem image ID for Fscache back-end.
+domain_id=%s Specify a domain ID in fscache mode so that different images
+ with the same blobs under a given domain ID can share storage.
=================== =========================================================
Sysfs Entries
notify_end_rx can be NULL or it can be used to specify a function to be
called when the call changes state to end the Tx phase. This function is
- called with the call-state spinlock held to prevent any reply or final ACK
- from being delivered first.
+ called with a spinlock held to prevent the last DATA packet from being
+ transmitted until the function returns.
(#) Receive data from a call::
.. _netdev-FAQ:
-==========
-netdev FAQ
-==========
+=============================
+Networking subsystem (netdev)
+=============================
tl;dr
-----
- don't repost your patches within one 24h period
- reverse xmas tree
-What is netdev?
----------------
-It is a mailing list for all network-related Linux stuff. This
+netdev
+------
+
+netdev is a mailing list for all network-related Linux stuff. This
includes anything found under net/ (i.e. core code like IPv6) and
drivers/net (i.e. hardware specific drivers) in the Linux source tree.
Note that some subsystems (e.g. wireless drivers) which have a high
-volume of traffic have their own specific mailing lists.
+volume of traffic have their own specific mailing lists and trees.
The netdev list is managed (like many other Linux mailing lists) through
VGER (http://vger.kernel.org/) with archives available at
Linux development (i.e. RFC, review, comments, etc.) takes place on
netdev.
-How do the changes posted to netdev make their way into Linux?
---------------------------------------------------------------
-There are always two trees (git repositories) in play. Both are
-driven by David Miller, the main network maintainer. There is the
-``net`` tree, and the ``net-next`` tree. As you can probably guess from
-the names, the ``net`` tree is for fixes to existing code already in the
-mainline tree from Linus, and ``net-next`` is where the new code goes
-for the future release. You can find the trees here:
-
-- https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
-- https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
-
-How do I indicate which tree (net vs. net-next) my patch should be in?
-----------------------------------------------------------------------
-To help maintainers and CI bots you should explicitly mark which tree
-your patch is targeting. Assuming that you use git, use the prefix
-flag::
-
- git format-patch --subject-prefix='PATCH net-next' start..finish
+Development cycle
+-----------------
-Use ``net`` instead of ``net-next`` (always lower case) in the above for
-bug-fix ``net`` content.
-
-How often do changes from these trees make it to the mainline Linus tree?
--------------------------------------------------------------------------
-To understand this, you need to know a bit of background information on
+Here is a bit of background information on
the cadence of Linux development. Each new release starts off with a
two week "merge window" where the main maintainers feed their new stuff
to Linus for merging into the mainline tree. After the two weeks, the
state of churn), and a week after the last vX.Y-rcN was done, the
official vX.Y is released.
-Relating that to netdev: At the beginning of the 2-week merge window,
-the ``net-next`` tree will be closed - no new changes/features. The
-accumulated new content of the past ~10 weeks will be passed onto
+To find out where we are now in the cycle - load the mainline (Linus)
+page here:
+
+ https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
+
+and note the top of the "tags" section. If it is rc1, it is early in
+the dev cycle. If it was tagged rc7 a week ago, then a release is
+probably imminent. If the most recent tag is a final release tag
+(without an ``-rcN`` suffix) - we are most likely in a merge window
+and ``net-next`` is closed.
+
+git trees and patch flow
+------------------------
+
+There are two networking trees (git repositories) in play. Both are
+driven by David Miller, the main network maintainer. There is the
+``net`` tree, and the ``net-next`` tree. As you can probably guess from
+the names, the ``net`` tree is for fixes to existing code already in the
+mainline tree from Linus, and ``net-next`` is where the new code goes
+for the future release. You can find the trees here:
+
+- https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
+- https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
+
+Relating that to kernel development: At the beginning of the 2-week
+merge window, the ``net-next`` tree will be closed - no new changes/features.
+The accumulated new content of the past ~10 weeks will be passed onto
mainline/Linus via a pull request for vX.Y -- at the same time, the
``net`` tree will start accumulating fixes for this pulled content
relating to vX.Y
Finally, the vX.Y gets released, and the whole cycle starts over.
-So where are we now in this cycle?
-----------------------------------
+netdev patch review
+-------------------
-Load the mainline (Linus) page here:
+Patch status
+~~~~~~~~~~~~
- https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
-
-and note the top of the "tags" section. If it is rc1, it is early in
-the dev cycle. If it was tagged rc7 a week ago, then a release is
-probably imminent. If the most recent tag is a final release tag
-(without an ``-rcN`` suffix) - we are most likely in a merge window
-and ``net-next`` is closed.
-
-How can I tell the status of a patch I've sent?
------------------------------------------------
-Start by looking at the main patchworks queue for netdev:
+Status of a patch can be checked by looking at the main patchwork
+queue for netdev:
https://patchwork.kernel.org/project/netdevbpf/list/
which carried them so if you have trouble finding your patch append
the value of ``Message-ID`` to the URL above.
-How long before my patch is accepted?
--------------------------------------
-Generally speaking, the patches get triaged quickly (in less than
-48h). But be patient, if your patch is active in patchwork (i.e. it's
-listed on the project's patch list) the chances it was missed are close to zero.
-Asking the maintainer for status updates on your
-patch is a good way to ensure your patch is ignored or pushed to the
-bottom of the priority list.
+Updating patch status
+~~~~~~~~~~~~~~~~~~~~~
-Should I directly update patchwork state of my own patches?
------------------------------------------------------------
It may be tempting to help the maintainers and update the state of your
-own patches when you post a new version or spot a bug. Please do not do that.
+own patches when you post a new version or spot a bug. Please **do not**
+do that.
Interfering with the patch status on patchwork will only cause confusion. Leave
it to the maintainer to figure out what is the most recent and current
version that should be applied. If there is any doubt, the maintainer
will reply and ask what should be done.
-How do I divide my work into patches?
--------------------------------------
+Review timelines
+~~~~~~~~~~~~~~~~
-Put yourself in the shoes of the reviewer. Each patch is read separately
-and therefore should constitute a comprehensible step towards your stated
-goal.
+Generally speaking, the patches get triaged quickly (in less than
+48h). But be patient, if your patch is active in patchwork (i.e. it's
+listed on the project's patch list) the chances it was missed are close to zero.
+Asking the maintainer for status updates on your
+patch is a good way to ensure your patch is ignored or pushed to the
+bottom of the priority list.
-Avoid sending series longer than 15 patches. Larger series takes longer
-to review as reviewers will defer looking at it until they find a large
-chunk of time. A small series can be reviewed in a short time, so Maintainers
-just do it. As a result, a sequence of smaller series gets merged quicker and
-with better review coverage. Re-posting large series also increases the mailing
-list traffic.
+Partial resends
+~~~~~~~~~~~~~~~
-I made changes to only a few patches in a patch series should I resend only those changed?
-------------------------------------------------------------------------------------------
-No, please resend the entire patch series and make sure you do number your
+Please always resend the entire patch series and make sure you do number your
patches such that it is clear this is the latest and greatest set of patches
-that can be applied.
-
-I have received review feedback, when should I post a revised version of the patches?
--------------------------------------------------------------------------------------
-Allow at least 24 hours to pass between postings. This will ensure reviewers
-from all geographical locations have a chance to chime in. Do not wait
-too long (weeks) between postings either as it will make it harder for reviewers
-to recall all the context.
+that can be applied. Do not try to resend just the patches which changed.
-Make sure you address all the feedback in your new posting. Do not post a new
-version of the code if the discussion about the previous version is still
-ongoing, unless directly instructed by a reviewer.
+Handling misapplied patches
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
-I submitted multiple versions of a patch series and it looks like a version other than the last one has been accepted, what should I do?
-----------------------------------------------------------------------------------------------------------------------------------------
+Occasionally a patch series gets applied before receiving critical feedback,
+or the wrong version of a series gets applied.
There is no revert possible, once it is pushed out, it stays like that.
Please send incremental versions on top of what has been merged in order to fix
the patches the way they would look like if your latest patch series was to be
merged.
-Are there special rules regarding stable submissions on netdev?
----------------------------------------------------------------
+Stable tree
+~~~~~~~~~~~
+
While it used to be the case that netdev submissions were not supposed
to carry explicit ``CC: stable@vger.kernel.org`` tags that is no longer
the case today. Please follow the standard stable rules in
:ref:`Documentation/process/stable-kernel-rules.rst <stable_kernel_rules>`,
and make sure you include appropriate Fixes tags!
-Is the comment style convention different for the networking content?
----------------------------------------------------------------------
-Yes, in a largely trivial way. Instead of this::
+Security fixes
+~~~~~~~~~~~~~~
+
+Do not email netdev maintainers directly if you think you discovered
+a bug that might have possible security implications.
+The current netdev maintainer has consistently requested that
+people use the mailing lists and not reach out directly. If you aren't
+OK with that, then perhaps consider mailing security@kernel.org or
+reading about http://oss-security.openwall.org/wiki/mailing-lists/distros
+as possible alternative mechanisms.
+
+
+Co-posting changes to user space components
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+User space code exercising kernel features should be posted
+alongside kernel patches. This gives reviewers a chance to see
+how any new interface is used and how well it works.
+
+When user space tools reside in the kernel repo itself all changes
+should generally come as one series. If series becomes too large
+or the user space project is not reviewed on netdev include a link
+to a public repo where user space patches can be seen.
+
+In case user space tooling lives in a separate repository but is
+reviewed on netdev (e.g. patches to ``iproute2`` tools) kernel and
+user space patches should form separate series (threads) when posted
+to the mailing list, e.g.::
+
+ [PATCH net-next 0/3] net: some feature cover letter
+ └─ [PATCH net-next 1/3] net: some feature prep
+ └─ [PATCH net-next 2/3] net: some feature do it
+ └─ [PATCH net-next 3/3] selftest: net: some feature
+
+ [PATCH iproute2-next] ip: add support for some feature
+
+Posting as one thread is discouraged because it confuses patchwork
+(as of patchwork 2.2.2).
+
+Preparing changes
+-----------------
+
+Attention to detail is important. Re-read your own work as if you were the
+reviewer. You can start with using ``checkpatch.pl``, perhaps even with
+the ``--strict`` flag. But do not be mindlessly robotic in doing so.
+If your change is a bug fix, make sure your commit log indicates the
+end-user visible symptom, the underlying reason as to why it happens,
+and then if necessary, explain why the fix proposed is the best way to
+get things done. Don't mangle whitespace, and as is common, don't
+mis-indent function arguments that span multiple lines. If it is your
+first patch, mail it to yourself so you can test apply it to an
+unpatched tree to confirm infrastructure didn't mangle it.
+
+Finally, go back and read
+:ref:`Documentation/process/submitting-patches.rst <submittingpatches>`
+to be sure you are not repeating some common mistake documented there.
+
+Indicating target tree
+~~~~~~~~~~~~~~~~~~~~~~
+
+To help maintainers and CI bots you should explicitly mark which tree
+your patch is targeting. Assuming that you use git, use the prefix
+flag::
+
+ git format-patch --subject-prefix='PATCH net-next' start..finish
+
+Use ``net`` instead of ``net-next`` (always lower case) in the above for
+bug-fix ``net`` content.
+
+Dividing work into patches
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Put yourself in the shoes of the reviewer. Each patch is read separately
+and therefore should constitute a comprehensible step towards your stated
+goal.
+
+Avoid sending series longer than 15 patches. Larger series takes longer
+to review as reviewers will defer looking at it until they find a large
+chunk of time. A small series can be reviewed in a short time, so Maintainers
+just do it. As a result, a sequence of smaller series gets merged quicker and
+with better review coverage. Re-posting large series also increases the mailing
+list traffic.
+
+Multi-line comments
+~~~~~~~~~~~~~~~~~~~
+
+Comment style convention is slightly different for networking and most of
+the tree. Instead of this::
/*
* foobar blah blah blah
* another line of text
*/
-What is "reverse xmas tree"?
-----------------------------
+Local variable ordering ("reverse xmas tree", "RCS")
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Netdev has a convention for ordering local variables in functions.
Order the variable declaration lines longest to shortest, e.g.::
If there are dependencies between the variables preventing the ordering
move the initialization out of line.
-I am working in existing code which uses non-standard formatting. Which formatting should I use?
-------------------------------------------------------------------------------------------------
-Make your code follow the most recent guidelines, so that eventually all code
+Format precedence
+~~~~~~~~~~~~~~~~~
+
+When working in existing code which uses nonstandard formatting make
+your code follow the most recent guidelines, so that eventually all code
in the domain of netdev is in the preferred format.
-I found a bug that might have possible security implications or similar. Should I mail the main netdev maintainer off-list?
----------------------------------------------------------------------------------------------------------------------------
-No. The current netdev maintainer has consistently requested that
-people use the mailing lists and not reach out directly. If you aren't
-OK with that, then perhaps consider mailing security@kernel.org or
-reading about http://oss-security.openwall.org/wiki/mailing-lists/distros
-as possible alternative mechanisms.
+Resending after review
+~~~~~~~~~~~~~~~~~~~~~~
+
+Allow at least 24 hours to pass between postings. This will ensure reviewers
+from all geographical locations have a chance to chime in. Do not wait
+too long (weeks) between postings either as it will make it harder for reviewers
+to recall all the context.
+
+Make sure you address all the feedback in your new posting. Do not post a new
+version of the code if the discussion about the previous version is still
+ongoing, unless directly instructed by a reviewer.
+
+Testing
+-------
+
+Expected level of testing
+~~~~~~~~~~~~~~~~~~~~~~~~~
-What level of testing is expected before I submit my change?
-------------------------------------------------------------
At the very minimum your changes must survive an ``allyesconfig`` and an
``allmodconfig`` build with ``W=1`` set without new warnings or failures.
You are expected to test your changes on top of the relevant networking
tree (``net`` or ``net-next``) and not e.g. a stable tree or ``linux-next``.
-How do I post corresponding changes to user space components?
--------------------------------------------------------------
-User space code exercising kernel features should be posted
-alongside kernel patches. This gives reviewers a chance to see
-how any new interface is used and how well it works.
-
-When user space tools reside in the kernel repo itself all changes
-should generally come as one series. If series becomes too large
-or the user space project is not reviewed on netdev include a link
-to a public repo where user space patches can be seen.
-
-In case user space tooling lives in a separate repository but is
-reviewed on netdev (e.g. patches to ``iproute2`` tools) kernel and
-user space patches should form separate series (threads) when posted
-to the mailing list, e.g.::
-
- [PATCH net-next 0/3] net: some feature cover letter
- └─ [PATCH net-next 1/3] net: some feature prep
- └─ [PATCH net-next 2/3] net: some feature do it
- └─ [PATCH net-next 3/3] selftest: net: some feature
-
- [PATCH iproute2-next] ip: add support for some feature
-
-Posting as one thread is discouraged because it confuses patchwork
-(as of patchwork 2.2.2).
-
-Can I reproduce the checks from patchwork on my local machine?
---------------------------------------------------------------
+patchwork checks
+~~~~~~~~~~~~~~~~
Checks in patchwork are mostly simple wrappers around existing kernel
scripts, the sources are available at:
https://github.com/kuba-moo/nipa/tree/master/tests
-Running all the builds and checks locally is a pain, can I post my patches and have the patchwork bot validate them?
---------------------------------------------------------------------------------------------------------------------
-
-No, you must ensure that your patches are ready by testing them locally
+**Do not** post your patches just to run them through the checks.
+You must ensure that your patches are ready by testing them locally
before posting to the mailing list. The patchwork build bot instance
gets overloaded very easily and netdev@vger really doesn't need more
traffic if we can help it.
-netdevsim is great, can I extend it for my out-of-tree tests?
--------------------------------------------------------------
+netdevsim
+~~~~~~~~~
-No, ``netdevsim`` is a test vehicle solely for upstream tests.
-(Please add your tests under ``tools/testing/selftests/``.)
+``netdevsim`` is a test driver which can be used to exercise driver
+configuration APIs without requiring capable hardware.
+Mock-ups and tests based on ``netdevsim`` are strongly encouraged when
+adding new APIs, but ``netdevsim`` in itself is **not** considered
+a use case/user. You must also implement the new APIs in a real driver.
-We also give no guarantees that ``netdevsim`` won't change in the future
+We give no guarantees that ``netdevsim`` won't change in the future
in a way which would break what would normally be considered uAPI.
-Is netdevsim considered a "user" of an API?
--------------------------------------------
-
-Linux kernel has a long standing rule that no API should be added unless
-it has a real, in-tree user. Mock-ups and tests based on ``netdevsim`` are
-strongly encouraged when adding new APIs, but ``netdevsim`` in itself
-is **not** considered a use case/user.
-
-Any other tips to help ensure my net/net-next patch gets OK'd?
---------------------------------------------------------------
-Attention to detail. Re-read your own work as if you were the
-reviewer. You can start with using ``checkpatch.pl``, perhaps even with
-the ``--strict`` flag. But do not be mindlessly robotic in doing so.
-If your change is a bug fix, make sure your commit log indicates the
-end-user visible symptom, the underlying reason as to why it happens,
-and then if necessary, explain why the fix proposed is the best way to
-get things done. Don't mangle whitespace, and as is common, don't
-mis-indent function arguments that span multiple lines. If it is your
-first patch, mail it to yourself so you can test apply it to an
-unpatched tree to confirm infrastructure didn't mangle it.
-
-Finally, go back and read
-:ref:`Documentation/process/submitting-patches.rst <submittingpatches>`
-to be sure you are not repeating some common mistake documented there.
+``netdevsim`` is reserved for use by upstream tests only, so any
+new ``netdevsim`` features must be accompanied by selftests under
+``tools/testing/selftests/``.
-My company uses peer feedback in employee performance reviews. Can I ask netdev maintainers for feedback?
----------------------------------------------------------------------------------------------------------
+Testimonials / feedback
+-----------------------
-Yes, especially if you spend significant amount of time reviewing code
+Some companies use peer feedback in employee performance reviews.
+Please feel free to request feedback from netdev maintainers,
+especially if you spend significant amount of time reviewing code
and go out of your way to improve shared infrastructure.
The feedback must be requested by you, the contributor, and will always
import os
import sys
-from sphinx.util.pycompat import execfile_
+from sphinx.util.osutil import fs_encoding
# ------------------------------------------------------------------------------
def loadConfig(namespace):
sys.stdout.write("load additional sphinx-config: %s\n" % config_file)
config = namespace.copy()
config['__file__'] = config_file
- execfile_(config_file, config)
+ with open(config_file, 'rb') as f:
+ code = compile(f.read(), fs_encoding, 'exec')
+ exec(code, config)
del config['__file__']
namespace.update(config)
else:
mmap() that affects the region will be made visible immediately. Another
example is madvise(MADV_DROP).
+Note: On arm64, a write generated by the page-table walker (to update
+the Access and Dirty flags, for example) never results in a
+KVM_EXIT_MMIO exit when the slot has the KVM_MEM_READONLY flag. This
+is because KVM cannot provide the data that would be written by the
+page-table walker, making it impossible to emulate the access.
+Instead, an abort (data abort if the cause of the page-table update
+was a load or a store, instruction abort if it was an instruction
+fetch) is injected in the guest.
4.36 KVM_SET_TSS_ADDR
---------------------
It can be enabled if ``KVM_CAP_TSC_DEADLINE_TIMER`` is present and the kernel
has enabled in-kernel emulation of the local APIC.
+CPU topology
+~~~~~~~~~~~~
+
+Several CPUID values include topology information for the host CPU:
+0x0b and 0x1f for Intel systems, 0x8000001e for AMD systems. Different
+versions of KVM return different values for this information and userspace
+should not rely on it. Currently they return all zeroes.
+
+If userspace wishes to set up a guest topology, it should be careful that
+the values of these three leaves differ for each CPU. In particular,
+the APIC ID is found in EDX for all subleaves of 0x0b and 0x1f, and in EAX
+for 0x8000001e; the latter also encodes the core id and node id in bits
+7:0 of EBX and ECX respectively.
+
Obsolete ioctls and capabilities
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
For SRCU:
-- ``synchronize_srcu(&kvm->srcu)`` is called _inside_
- the kvm->slots_lock critical section, therefore kvm->slots_lock
- cannot be taken inside a kvm->srcu read-side critical section.
- Instead, kvm->slots_arch_lock is released before the call
- to ``synchronize_srcu()`` and _can_ be taken inside a
- kvm->srcu read-side critical section.
-
-- kvm->lock is taken inside kvm->srcu, therefore
- ``synchronize_srcu(&kvm->srcu)`` cannot be called inside
- a kvm->lock critical section. If you cannot delay the
- call until after kvm->lock is released, use ``call_srcu``.
+- ``synchronize_srcu(&kvm->srcu)`` is called inside critical sections
+ for kvm->lock, vcpu->mutex and kvm->slots_lock. These locks _cannot_
+ be taken inside a kvm->srcu read-side critical section; that is, the
+ following is broken::
+
+ srcu_read_lock(&kvm->srcu);
+ mutex_lock(&kvm->slots_lock);
+
+- kvm->slots_arch_lock instead is released before the call to
+ ``synchronize_srcu()``. It _can_ therefore be taken inside a
+ kvm->srcu read-side critical section, for example while processing
+ a vmexit.
On x86:
-- vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock
+- vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock and kvm->arch.xen.xen_lock
- kvm->arch.mmu_lock is an rwlock. kvm->arch.tdp_mmu_pages_lock and
kvm->arch.mmu_unsync_pages_lock are taken inside kvm->arch.mmu_lock, and
DRM DRIVERS FOR BRIDGE CHIPS
M: Andrzej Hajda <andrzej.hajda@intel.com>
M: Neil Armstrong <neil.armstrong@linaro.org>
-M: Robert Foss <robert.foss@linaro.org>
+M: Robert Foss <rfoss@kernel.org>
R: Laurent Pinchart <Laurent.pinchart@ideasonboard.com>
R: Jonas Karlman <jonas@kwiboo.se>
R: Jernej Skrabec <jernej.skrabec@gmail.com>
KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64)
M: Marc Zyngier <maz@kernel.org>
R: James Morse <james.morse@arm.com>
-R: Alexandru Elisei <alexandru.elisei@arm.com>
R: Suzuki K Poulose <suzuki.poulose@arm.com>
R: Oliver Upton <oliver.upton@linux.dev>
+R: Zenghui Yu <yuzenghui@huawei.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
L: kvmarm@lists.linux.dev
L: kvmarm@lists.cs.columbia.edu (deprecated, moderated for non-subscribers)
MICROCHIP AT91 DMA DRIVERS
M: Ludovic Desroches <ludovic.desroches@microchip.com>
-M: Tudor Ambarus <tudor.ambarus@microchip.com>
+M: Tudor Ambarus <tudor.ambarus@linaro.org>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
L: dmaengine@vger.kernel.org
S: Supported
F: drivers/media/platform/microchip/microchip-csi2dc.c
MICROCHIP ECC DRIVER
-M: Tudor Ambarus <tudor.ambarus@microchip.com>
+M: Tudor Ambarus <tudor.ambarus@linaro.org>
L: linux-crypto@vger.kernel.org
S: Maintained
F: drivers/crypto/atmel-ecc.*
F: drivers/mmc/host/atmel-mci.c
MICROCHIP NAND DRIVER
-M: Tudor Ambarus <tudor.ambarus@microchip.com>
+M: Tudor Ambarus <tudor.ambarus@linaro.org>
L: linux-mtd@lists.infradead.org
S: Supported
F: Documentation/devicetree/bindings/mtd/atmel-nand.txt
F: drivers/power/reset/at91-sama5d2_shdwc.c
MICROCHIP SPI DRIVER
-M: Tudor Ambarus <tudor.ambarus@microchip.com>
+M: Tudor Ambarus <tudor.ambarus@linaro.org>
S: Supported
F: drivers/spi/spi-atmel.*
F: Documentation/nvme/
F: drivers/nvme/host/
F: drivers/nvme/common/
-F: include/linux/nvme*
+F: include/linux/nvme.h
+F: include/linux/nvme-*.h
F: include/uapi/linux/nvme_ioctl.h
NVM EXPRESS FABRICS AUTHENTICATION
F: Documentation/devicetree/bindings/input/pine64,pinephone-keyboard.yaml
F: drivers/input/keyboard/pinephone-keyboard.c
+PKTCDVD DRIVER
+M: linux-block@vger.kernel.org
+S: Orphan
+F: drivers/block/pktcdvd.c
+F: include/linux/pktcdvd.h
+F: include/uapi/linux/pktcdvd.h
+
PLANTOWER PMS7003 AIR POLLUTION SENSOR DRIVER
M: Tomasz Duszynski <tduszyns@gmail.com>
S: Maintained
F: drivers/net/wwan/qcom_bam_dmux.c
QUALCOMM CAMERA SUBSYSTEM DRIVER
-M: Robert Foss <robert.foss@linaro.org>
+M: Robert Foss <rfoss@kernel.org>
M: Todor Tomov <todor.too@gmail.com>
L: linux-media@vger.kernel.org
S: Maintained
QUALCOMM I2C CCI DRIVER
M: Loic Poulain <loic.poulain@linaro.org>
-M: Robert Foss <robert.foss@linaro.org>
+M: Robert Foss <rfoss@kernel.org>
L: linux-i2c@vger.kernel.org
L: linux-arm-msm@vger.kernel.org
S: Maintained
F: drivers/pinctrl/spear/
SPI NOR SUBSYSTEM
-M: Tudor Ambarus <tudor.ambarus@microchip.com>
+M: Tudor Ambarus <tudor.ambarus@linaro.org>
M: Pratyush Yadav <pratyush@kernel.org>
R: Michael Walle <michael@walle.cc>
L: linux-mtd@lists.infradead.org
F: drivers/scsi/vmw_pvscsi.h
VMWARE VIRTUAL PTP CLOCK DRIVER
-M: Vivek Thampi <vithampi@vmware.com>
+M: Srivatsa S. Bhat (VMware) <srivatsa@csail.mit.edu>
+M: Deep Shah <sdeep@vmware.com>
+R: Alexey Makhalov <amakhalov@vmware.com>
R: VMware PV-Drivers Reviewers <pv-drivers@vmware.com>
L: netdev@vger.kernel.org
S: Supported
VERSION = 6
PATCHLEVEL = 2
SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc4
NAME = Hurr durr I'ma ninja sloth
# *DOCUMENTATION*
# Remove MODORDER when done because it is not the real one.
PHONY += single_modules
single_modules: $(single-no-ko) modules_prepare
- $(Q){ $(foreach m, $(single-ko), echo $(extmod_prefix)$m;) } > $(MODORDER)
+ $(Q){ $(foreach m, $(single-ko), echo $(extmod_prefix)$(m:%.ko=%.o);) } > $(MODORDER)
$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modpost
ifneq ($(KBUILD_MODPOST_NOFINAL),1)
$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modfinal
#define TIF_NEED_RESCHED 1 /* rescheduling necessary */
#define TIF_NOTIFY_RESUME 2 /* callback before returning to user */
#define TIF_UPROBE 3 /* breakpointed or singlestepping */
-#define TIF_SYSCALL_TRACE 4 /* syscall trace active */
-#define TIF_SYSCALL_AUDIT 5 /* syscall auditing active */
-#define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */
-#define TIF_SECCOMP 7 /* seccomp syscall filtering active */
-#define TIF_NOTIFY_SIGNAL 8 /* signal notifications exist */
+#define TIF_NOTIFY_SIGNAL 4 /* signal notifications exist */
#define TIF_USING_IWMMXT 17
#define TIF_MEMDIE 18 /* is terminating due to OOM killer */
-#define TIF_RESTORE_SIGMASK 20
+#define TIF_RESTORE_SIGMASK 19
+#define TIF_SYSCALL_TRACE 20 /* syscall trace active */
+#define TIF_SYSCALL_AUDIT 21 /* syscall auditing active */
+#define TIF_SYSCALL_TRACEPOINT 22 /* syscall tracepoint instrumentation */
+#define TIF_SECCOMP 23 /* seccomp syscall filtering active */
+
#define _TIF_SIGPENDING (1 << TIF_SIGPENDING)
#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
select HAVE_DEBUG_KMEMLEAK
select HAVE_DMA_CONTIGUOUS
select HAVE_DYNAMIC_FTRACE
- select HAVE_DYNAMIC_FTRACE_WITH_ARGS \
- if $(cc-option,-fpatchable-function-entry=2)
select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \
if DYNAMIC_FTRACE_WITH_ARGS
select HAVE_EFFICIENT_UNALIGNED_ACCESS
If unsure, say Y.
+config ARM64_ERRATUM_2645198
+ bool "Cortex-A715: 2645198: Workaround possible [ESR|FAR]_ELx corruption"
+ default y
+ help
+ This option adds the workaround for ARM Cortex-A715 erratum 2645198.
+
+ If a Cortex-A715 cpu sees a page mapping permissions change from executable
+ to non-executable, it may corrupt the ESR_ELx and FAR_ELx registers on the
+ next instruction abort caused by permission fault.
+
+ Only user-space does executable to non-executable permission transition via
+ mprotect() system call. Workaround the problem by doing a break-before-make
+ TLB invalidation, for all changes to executable user space mappings.
+
+ If unsure, say Y.
+
config CAVIUM_ERRATUM_22375
bool "Cavium erratum 22375, 24313"
default y
*/
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
#include <asm/assembler.h>
#include "sm4-ce-asm.h"
SYM_FUNC_END(sm4_ce_ccm_final)
.align 3
-SYM_FUNC_START(sm4_ce_ccm_enc)
+SYM_TYPED_FUNC_START(sm4_ce_ccm_enc)
/* input:
* x0: round key array, CTX
* x1: dst
SYM_FUNC_END(sm4_ce_ccm_enc)
.align 3
-SYM_FUNC_START(sm4_ce_ccm_dec)
+SYM_TYPED_FUNC_START(sm4_ce_ccm_dec)
/* input:
* x0: round key array, CTX
* x1: dst
*/
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
#include <asm/assembler.h>
#include "sm4-ce-asm.h"
SYM_FUNC_END(pmull_ghash_update)
.align 3
-SYM_FUNC_START(sm4_ce_pmull_gcm_enc)
+SYM_TYPED_FUNC_START(sm4_ce_pmull_gcm_enc)
/* input:
* x0: round key array, CTX
* x1: dst
#define RH3 v20
.align 3
-SYM_FUNC_START(sm4_ce_pmull_gcm_dec)
+SYM_TYPED_FUNC_START(sm4_ce_pmull_gcm_dec)
/* input:
* x0: round key array, CTX
* x1: dst
" cbnz %w0, 1b\n" \
" " #mb "\n" \
"2:" \
- : "=&r" (tmp), "=&r" (ret), "+Q" (*(unsigned long *)ptr) \
+ : "=&r" (tmp), "=&r" (ret), "+Q" (*(__uint128_t *)ptr) \
: "r" (old1), "r" (old2), "r" (new1), "r" (new2) \
: cl); \
\
" eor %[old2], %[old2], %[oldval2]\n" \
" orr %[old1], %[old1], %[old2]" \
: [old1] "+&r" (x0), [old2] "+&r" (x1), \
- [v] "+Q" (*(unsigned long *)ptr) \
+ [v] "+Q" (*(__uint128_t *)ptr) \
: [new1] "r" (x2), [new2] "r" (x3), [ptr] "r" (x4), \
[oldval1] "r" (oldval1), [oldval2] "r" (oldval2) \
: cl); \
#define APPLE_CPU_PART_M1_FIRESTORM_PRO 0x025
#define APPLE_CPU_PART_M1_ICESTORM_MAX 0x028
#define APPLE_CPU_PART_M1_FIRESTORM_MAX 0x029
+#define APPLE_CPU_PART_M2_BLIZZARD 0x032
+#define APPLE_CPU_PART_M2_AVALANCHE 0x033
#define AMPERE_CPU_PART_AMPERE1 0xAC3
#define MIDR_APPLE_M1_FIRESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_PRO)
#define MIDR_APPLE_M1_ICESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_MAX)
#define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX)
+#define MIDR_APPLE_M2_BLIZZARD MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD)
+#define MIDR_APPLE_M2_AVALANCHE MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE)
#define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1)
/* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */
#define ESR_ELx_FSC_ACCESS (0x08)
#define ESR_ELx_FSC_FAULT (0x04)
#define ESR_ELx_FSC_PERM (0x0C)
+#define ESR_ELx_FSC_SEA_TTW0 (0x14)
+#define ESR_ELx_FSC_SEA_TTW1 (0x15)
+#define ESR_ELx_FSC_SEA_TTW2 (0x16)
+#define ESR_ELx_FSC_SEA_TTW3 (0x17)
+#define ESR_ELx_FSC_SECC (0x18)
+#define ESR_ELx_FSC_SECC_TTW0 (0x1c)
+#define ESR_ELx_FSC_SECC_TTW1 (0x1d)
+#define ESR_ELx_FSC_SECC_TTW2 (0x1e)
+#define ESR_ELx_FSC_SECC_TTW3 (0x1f)
/* ISS field definitions for Data Aborts */
#define ESR_ELx_ISV_SHIFT (24)
void __init arm64_hugetlb_cma_reserve(void);
+#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start
+extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep);
+
+#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit
+extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep,
+ pte_t old_pte, pte_t new_pte);
+
#include <asm-generic/hugetlb.h>
#endif /* __ASM_HUGETLB_H */
BIT(18) | \
GENMASK(16, 15))
-/* For compatibility with fault code shared with 32-bit */
-#define FSC_FAULT ESR_ELx_FSC_FAULT
-#define FSC_ACCESS ESR_ELx_FSC_ACCESS
-#define FSC_PERM ESR_ELx_FSC_PERM
-#define FSC_SEA ESR_ELx_FSC_EXTABT
-#define FSC_SEA_TTW0 (0x14)
-#define FSC_SEA_TTW1 (0x15)
-#define FSC_SEA_TTW2 (0x16)
-#define FSC_SEA_TTW3 (0x17)
-#define FSC_SECC (0x18)
-#define FSC_SECC_TTW0 (0x1c)
-#define FSC_SECC_TTW1 (0x1d)
-#define FSC_SECC_TTW2 (0x1e)
-#define FSC_SECC_TTW3 (0x1f)
-
/* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
#define HPFAR_MASK (~UL(0xf))
/*
static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu)
{
switch (kvm_vcpu_trap_get_fault(vcpu)) {
- case FSC_SEA:
- case FSC_SEA_TTW0:
- case FSC_SEA_TTW1:
- case FSC_SEA_TTW2:
- case FSC_SEA_TTW3:
- case FSC_SECC:
- case FSC_SECC_TTW0:
- case FSC_SECC_TTW1:
- case FSC_SECC_TTW2:
- case FSC_SECC_TTW3:
+ case ESR_ELx_FSC_EXTABT:
+ case ESR_ELx_FSC_SEA_TTW0:
+ case ESR_ELx_FSC_SEA_TTW1:
+ case ESR_ELx_FSC_SEA_TTW2:
+ case ESR_ELx_FSC_SEA_TTW3:
+ case ESR_ELx_FSC_SECC:
+ case ESR_ELx_FSC_SECC_TTW0:
+ case ESR_ELx_FSC_SECC_TTW1:
+ case ESR_ELx_FSC_SECC_TTW2:
+ case ESR_ELx_FSC_SECC_TTW3:
return true;
default:
return false;
static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
{
- if (kvm_vcpu_abt_iss1tw(vcpu))
- return true;
+ if (kvm_vcpu_abt_iss1tw(vcpu)) {
+ /*
+ * Only a permission fault on a S1PTW should be
+ * considered as a write. Otherwise, page tables baked
+ * in a read-only memslot will result in an exception
+ * being delivered in the guest.
+ *
+ * The drawback is that we end-up faulting twice if the
+ * guest is using any of HW AF/DB: a translation fault
+ * to map the page containing the PT (read only at
+ * first), then a permission fault to allow the flags
+ * to be set.
+ */
+ switch (kvm_vcpu_trap_get_fault_type(vcpu)) {
+ case ESR_ELx_FSC_PERM:
+ return true;
+ default:
+ return false;
+ }
+ }
if (kvm_vcpu_trap_is_iabt(vcpu))
return false;
#define pud_leaf(pud) (pud_present(pud) && !pud_table(pud))
#define pud_valid(pud) pte_valid(pud_pte(pud))
#define pud_user(pud) pte_user(pud_pte(pud))
-
+#define pud_user_exec(pud) pte_user_exec(pud_pte(pud))
static inline void set_pud(pud_t *pudp, pud_t pud)
{
#else
#define pud_page_paddr(pud) ({ BUILD_BUG(); 0; })
+#define pud_user_exec(pud) pud_user(pud) /* Always 0 with folding */
/* Match pmd_offset folding in <asm/generic/pgtable-nopmd.h> */
#define pmd_set_fixmap(addr) NULL
static inline bool pmd_user_accessible_page(pmd_t pmd)
{
- return pmd_leaf(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd));
+ return pmd_leaf(pmd) && !pmd_present_invalid(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd));
}
static inline bool pud_user_accessible_page(pud_t pud)
{
- return pud_leaf(pud) && pud_user(pud);
+ return pud_leaf(pud) && (pud_user(pud) || pud_user_exec(pud));
}
#endif
}
+#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
+#define ptep_modify_prot_start ptep_modify_prot_start
+extern pte_t ptep_modify_prot_start(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep);
+
+#define ptep_modify_prot_commit ptep_modify_prot_commit
+extern void ptep_modify_prot_commit(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep,
+ pte_t old_pte, pte_t new_pte);
#endif /* !__ASSEMBLY__ */
#endif /* __ASM_PGTABLE_H */
#define UPROBE_SWBP_INSN_SIZE AARCH64_INSN_SIZE
#define UPROBE_XOL_SLOT_BYTES MAX_UINSN_BYTES
-typedef u32 uprobe_opcode_t;
+typedef __le32 uprobe_opcode_t;
struct arch_uprobe_task {
};
CAP_MIDR_RANGE_LIST(trbe_write_out_of_range_cpus),
},
#endif
+#ifdef CONFIG_ARM64_ERRATUM_2645198
+ {
+ .desc = "ARM erratum 2645198",
+ .capability = ARM64_WORKAROUND_2645198,
+ ERRATA_MIDR_ALL_VERSIONS(MIDR_CORTEX_A715)
+ },
+#endif
#ifdef CONFIG_ARM64_ERRATUM_2077057
{
.desc = "ARM erratum 2077057",
*/
#include <linux/linkage.h>
+#include <asm/assembler.h>
SYM_FUNC_START(__efi_rt_asm_wrapper)
stp x29, x30, [sp, #-112]!
#include <asm/cpufeature.h>
#include <asm/mte.h>
-#define for_each_mte_vma(vmi, vma) \
+#define for_each_mte_vma(cprm, i, m) \
if (system_supports_mte()) \
- for_each_vma(vmi, vma) \
- if (vma->vm_flags & VM_MTE)
+ for (i = 0, m = cprm->vma_meta; \
+ i < cprm->vma_count; \
+ i++, m = cprm->vma_meta + i) \
+ if (m->flags & VM_MTE)
-static unsigned long mte_vma_tag_dump_size(struct vm_area_struct *vma)
+static unsigned long mte_vma_tag_dump_size(struct core_vma_metadata *m)
{
- if (vma->vm_flags & VM_DONTDUMP)
- return 0;
-
- return vma_pages(vma) * MTE_PAGE_TAG_STORAGE;
+ return (m->dump_size >> PAGE_SHIFT) * MTE_PAGE_TAG_STORAGE;
}
/* Derived from dump_user_range(); start/end must be page-aligned */
static int mte_dump_tag_range(struct coredump_params *cprm,
- unsigned long start, unsigned long end)
+ unsigned long start, unsigned long len)
{
int ret = 1;
unsigned long addr;
void *tags = NULL;
- for (addr = start; addr < end; addr += PAGE_SIZE) {
+ for (addr = start; addr < start + len; addr += PAGE_SIZE) {
struct page *page = get_dump_page(addr);
/*
mte_save_page_tags(page_address(page), tags);
put_page(page);
if (!dump_emit(cprm, tags, MTE_PAGE_TAG_STORAGE)) {
- mte_free_tag_storage(tags);
ret = 0;
break;
}
return ret;
}
-Elf_Half elf_core_extra_phdrs(void)
+Elf_Half elf_core_extra_phdrs(struct coredump_params *cprm)
{
- struct vm_area_struct *vma;
+ int i;
+ struct core_vma_metadata *m;
int vma_count = 0;
- VMA_ITERATOR(vmi, current->mm, 0);
- for_each_mte_vma(vmi, vma)
+ for_each_mte_vma(cprm, i, m)
vma_count++;
return vma_count;
int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset)
{
- struct vm_area_struct *vma;
- VMA_ITERATOR(vmi, current->mm, 0);
+ int i;
+ struct core_vma_metadata *m;
- for_each_mte_vma(vmi, vma) {
+ for_each_mte_vma(cprm, i, m) {
struct elf_phdr phdr;
phdr.p_type = PT_AARCH64_MEMTAG_MTE;
phdr.p_offset = offset;
- phdr.p_vaddr = vma->vm_start;
+ phdr.p_vaddr = m->start;
phdr.p_paddr = 0;
- phdr.p_filesz = mte_vma_tag_dump_size(vma);
- phdr.p_memsz = vma->vm_end - vma->vm_start;
+ phdr.p_filesz = mte_vma_tag_dump_size(m);
+ phdr.p_memsz = m->end - m->start;
offset += phdr.p_filesz;
phdr.p_flags = 0;
phdr.p_align = 0;
return 1;
}
-size_t elf_core_extra_data_size(void)
+size_t elf_core_extra_data_size(struct coredump_params *cprm)
{
- struct vm_area_struct *vma;
+ int i;
+ struct core_vma_metadata *m;
size_t data_size = 0;
- VMA_ITERATOR(vmi, current->mm, 0);
- for_each_mte_vma(vmi, vma)
- data_size += mte_vma_tag_dump_size(vma);
+ for_each_mte_vma(cprm, i, m)
+ data_size += mte_vma_tag_dump_size(m);
return data_size;
}
int elf_core_write_extra_data(struct coredump_params *cprm)
{
- struct vm_area_struct *vma;
- VMA_ITERATOR(vmi, current->mm, 0);
-
- for_each_mte_vma(vmi, vma) {
- if (vma->vm_flags & VM_DONTDUMP)
- continue;
+ int i;
+ struct core_vma_metadata *m;
- if (!mte_dump_tag_range(cprm, vma->vm_start, vma->vm_end))
+ for_each_mte_vma(cprm, i, m) {
+ if (!mte_dump_tag_range(cprm, m->start, m->dump_size))
return 0;
}
WARN_ON(!system_supports_fpsimd());
WARN_ON(!have_cpu_fpsimd_context());
- if (system_supports_sve()) {
+ if (system_supports_sve() || system_supports_sme()) {
switch (current->thread.fp_type) {
case FP_STATE_FPSIMD:
/* Stop tracking SVE for this task until next use. */
#ifdef CONFIG_ARM64_SVE
REGSET_SVE,
#endif
-#ifdef CONFIG_ARM64_SVE
+#ifdef CONFIG_ARM64_SME
REGSET_SSVE,
REGSET_ZA,
#endif
vl = task_get_sme_vl(current);
} else {
- if (!system_supports_sve())
+ /*
+ * A SME only system use SVE for streaming mode so can
+ * have a SVE formatted context with a zero VL and no
+ * payload data.
+ */
+ if (!system_supports_sve() && !system_supports_sme())
return -EINVAL;
vl = task_get_sve_vl(current);
return err;
}
- if (system_supports_sve()) {
+ if (system_supports_sve() || system_supports_sme()) {
unsigned int vq = 0;
if (add_all || test_thread_flag(TIF_SVE) ||
*/
if (!(esr & ESR_ELx_S1PTW) &&
(cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
- (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
+ (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_PERM)) {
if (!__translate_far_to_hpfar(far, &hpfar))
return false;
} else {
if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
bool valid;
- valid = kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
+ valid = kvm_vcpu_trap_get_fault_type(vcpu) == ESR_ELx_FSC_FAULT &&
kvm_vcpu_dabt_isvalid(vcpu) &&
!kvm_vcpu_abt_issea(vcpu) &&
!kvm_vcpu_abt_iss1tw(vcpu);
exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu);
VM_BUG_ON(write_fault && exec_fault);
- if (fault_status == FSC_PERM && !write_fault && !exec_fault) {
+ if (fault_status == ESR_ELx_FSC_PERM && !write_fault && !exec_fault) {
kvm_err("Unexpected L2 read permission error\n");
return -EFAULT;
}
* only exception to this is when dirty logging is enabled at runtime
* and a write fault needs to collapse a block entry into a table.
*/
- if (fault_status != FSC_PERM || (logging_active && write_fault)) {
+ if (fault_status != ESR_ELx_FSC_PERM ||
+ (logging_active && write_fault)) {
ret = kvm_mmu_topup_memory_cache(memcache,
kvm_mmu_cache_min_pages(kvm));
if (ret)
* backed by a THP and thus use block mapping if possible.
*/
if (vma_pagesize == PAGE_SIZE && !(force_pte || device)) {
- if (fault_status == FSC_PERM && fault_granule > PAGE_SIZE)
+ if (fault_status == ESR_ELx_FSC_PERM &&
+ fault_granule > PAGE_SIZE)
vma_pagesize = fault_granule;
else
vma_pagesize = transparent_hugepage_adjust(kvm, memslot,
&fault_ipa);
}
- if (fault_status != FSC_PERM && !device && kvm_has_mte(kvm)) {
+ if (fault_status != ESR_ELx_FSC_PERM && !device && kvm_has_mte(kvm)) {
/* Check the VMM hasn't introduced a new disallowed VMA */
if (kvm_vma_mte_allowed(vma)) {
sanitise_mte_tags(kvm, pfn, vma_pagesize);
* permissions only if vma_pagesize equals fault_granule. Otherwise,
* kvm_pgtable_stage2_map() should be called to change block size.
*/
- if (fault_status == FSC_PERM && vma_pagesize == fault_granule)
+ if (fault_status == ESR_ELx_FSC_PERM && vma_pagesize == fault_granule)
ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot);
else
ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize,
fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
- if (fault_status == FSC_FAULT) {
+ if (fault_status == ESR_ELx_FSC_FAULT) {
/* Beyond sanitised PARange (which is the IPA limit) */
if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) {
kvm_inject_size_fault(vcpu);
kvm_vcpu_get_hfar(vcpu), fault_ipa);
/* Check the stage-2 fault is trans. fault or write fault */
- if (fault_status != FSC_FAULT && fault_status != FSC_PERM &&
- fault_status != FSC_ACCESS) {
+ if (fault_status != ESR_ELx_FSC_FAULT &&
+ fault_status != ESR_ELx_FSC_PERM &&
+ fault_status != ESR_ELx_FSC_ACCESS) {
kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n",
kvm_vcpu_trap_get_class(vcpu),
(unsigned long)kvm_vcpu_trap_get_fault(vcpu),
/* Userspace should not be able to register out-of-bounds IPAs */
VM_BUG_ON(fault_ipa >= kvm_phys_size(vcpu->kvm));
- if (fault_status == FSC_ACCESS) {
+ if (fault_status == ESR_ELx_FSC_ACCESS) {
handle_access_fault(vcpu, fault_ipa);
ret = 1;
goto out_unlock;
return;
/* Only preserve PMCR_EL0.N, and reset the rest to 0 */
- pmcr = read_sysreg(pmcr_el0) & ARMV8_PMU_PMCR_N_MASK;
+ pmcr = read_sysreg(pmcr_el0) & (ARMV8_PMU_PMCR_N_MASK << ARMV8_PMU_PMCR_N_SHIFT);
if (!kvm_supports_32bit_el0())
pmcr |= ARMV8_PMU_PMCR_LC;
MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_PRO),
MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM_MAX),
MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_MAX),
+ MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD),
+ MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE),
{},
};
{
return __hugetlb_valid_size(size);
}
+
+pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
+{
+ if (IS_ENABLED(CONFIG_ARM64_ERRATUM_2645198) &&
+ cpus_have_const_cap(ARM64_WORKAROUND_2645198)) {
+ /*
+ * Break-before-make (BBM) is required for all user space mappings
+ * when the permission changes from executable to non-executable
+ * in cases where cpu is affected with errata #2645198.
+ */
+ if (pte_user_exec(READ_ONCE(*ptep)))
+ return huge_ptep_clear_flush(vma, addr, ptep);
+ }
+ return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+}
+
+void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
+ pte_t old_pte, pte_t pte)
+{
+ set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+}
}
early_initcall(prevent_bootmem_remove_init);
#endif
+
+pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
+{
+ if (IS_ENABLED(CONFIG_ARM64_ERRATUM_2645198) &&
+ cpus_have_const_cap(ARM64_WORKAROUND_2645198)) {
+ /*
+ * Break-before-make (BBM) is required for all user space mappings
+ * when the permission changes from executable to non-executable
+ * in cases where cpu is affected with errata #2645198.
+ */
+ if (pte_user_exec(READ_ONCE(*ptep)))
+ return ptep_clear_flush(vma, addr, ptep);
+ }
+ return ptep_get_and_clear(vma->vm_mm, addr, ptep);
+}
+
+void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
+ pte_t old_pte, pte_t pte)
+{
+ set_pte_at(vma->vm_mm, addr, ptep, pte);
+}
WORKAROUND_2064142
WORKAROUND_2077057
WORKAROUND_2457168
+WORKAROUND_2645198
WORKAROUND_2658417
WORKAROUND_TRBE_OVERWRITE_FILL_MODE
WORKAROUND_TSB_FLUSH_FAILURE
#include <asm/elf.h>
-Elf64_Half elf_core_extra_phdrs(void)
+Elf64_Half elf_core_extra_phdrs(struct coredump_params *cprm)
{
return GATE_EHDR->e_phnum;
}
return 1;
}
-size_t elf_core_extra_data_size(void)
+size_t elf_core_extra_data_size(struct coredump_params *cprm)
{
const struct elf_phdr *const gate_phdrs =
(const struct elf_phdr *) (GATE_ADDR + GATE_EHDR->e_phoff);
#define FTRACE_REGS_PLT_IDX 1
#define NR_FTRACE_PLTS 2
-#define GRAPH_FAKE_OFFSET (sizeof(struct pt_regs) - offsetof(struct pt_regs, regs[1]))
-
#ifdef CONFIG_FUNCTION_TRACER
#define MCOUNT_INSN_SIZE 4 /* sizeof mcount call */
return val < (1UL << bit);
}
-static inline unsigned long sign_extend(unsigned long val, unsigned int idx)
-{
- if (!is_imm_negative(val, idx + 1))
- return ((1UL << idx) - 1) & val;
- else
- return ~((1UL << idx) - 1) | val;
-}
-
#define DEF_EMIT_REG0I26_FORMAT(NAME, OP) \
static inline void emit_##NAME(union loongarch_instruction *insn, \
int offset) \
}
DEF_EMIT_REG0I26_FORMAT(b, b_op)
+DEF_EMIT_REG0I26_FORMAT(bl, bl_op)
#define DEF_EMIT_REG1I20_FORMAT(NAME, OP) \
static inline void emit_##NAME(union loongarch_instruction *insn, \
#define _ASM_UNWIND_H
#include <linux/sched.h>
+#include <linux/ftrace.h>
+#include <asm/ptrace.h>
#include <asm/stacktrace.h>
enum unwinder_type {
char type; /* UNWINDER_XXX */
struct stack_info stack_info;
struct task_struct *task;
- bool first, error, is_ftrace;
+ bool first, error, reset;
int graph_idx;
unsigned long sp, pc, ra;
};
+bool default_next_frame(struct unwind_state *state);
+
void unwind_start(struct unwind_state *state,
struct task_struct *task, struct pt_regs *regs);
bool unwind_next_frame(struct unwind_state *state);
return state->error;
}
+#define GRAPH_FAKE_OFFSET (sizeof(struct pt_regs) - offsetof(struct pt_regs, regs[1]))
+
+static inline unsigned long unwind_graph_addr(struct unwind_state *state,
+ unsigned long pc, unsigned long cfa)
+{
+ return ftrace_graph_ret_addr(state->task, &state->graph_idx,
+ pc, (unsigned long *)(cfa - GRAPH_FAKE_OFFSET));
+}
+
+static __always_inline void __unwind_start(struct unwind_state *state,
+ struct task_struct *task, struct pt_regs *regs)
+{
+ memset(state, 0, sizeof(*state));
+ if (regs) {
+ state->sp = regs->regs[3];
+ state->pc = regs->csr_era;
+ state->ra = regs->regs[1];
+ } else if (task && task != current) {
+ state->sp = thread_saved_fp(task);
+ state->pc = thread_saved_ra(task);
+ state->ra = 0;
+ } else {
+ state->sp = (unsigned long)__builtin_frame_address(0);
+ state->pc = (unsigned long)__builtin_return_address(0);
+ state->ra = 0;
+ }
+ state->task = task;
+ get_stack_info(state->sp, state->task, &state->stack_info);
+ state->pc = unwind_graph_addr(state, state->pc, state->sp);
+}
+
+static __always_inline unsigned long __unwind_get_return_address(struct unwind_state *state)
+{
+ return unwind_done(state) ? 0 : state->pc;
+}
#endif /* _ASM_UNWIND_H */
obj-y += head.o cpu-probe.o cacheinfo.o env.o setup.o entry.o genex.o \
traps.o irq.o idle.o process.o dma.o mem.o io.o reset.o switch.o \
elf.o syscall.o signal.o time.o topology.o inst.o ptrace.o vdso.o \
- alternative.o unaligned.o
+ alternative.o unaligned.o unwind.o
obj-$(CONFIG_ACPI) += acpi.o
obj-$(CONFIG_EFI) += efi.o
switch (src->reg0i26_format.opcode) {
case b_op:
case bl_op:
- jump_addr = cur_pc + sign_extend((si_h << 16 | si_l) << 2, 27);
+ jump_addr = cur_pc + sign_extend64((si_h << 16 | si_l) << 2, 27);
if (in_alt_jump(jump_addr, start, end))
return;
offset = jump_addr - pc;
fallthrough;
case beqz_op:
case bnez_op:
- jump_addr = cur_pc + sign_extend((si_h << 16 | si_l) << 2, 22);
+ jump_addr = cur_pc + sign_extend64((si_h << 16 | si_l) << 2, 22);
if (in_alt_jump(jump_addr, start, end))
return;
offset = jump_addr - pc;
case bge_op:
case bltu_op:
case bgeu_op:
- jump_addr = cur_pc + sign_extend(si << 2, 17);
+ jump_addr = cur_pc + sign_extend64(si << 2, 17);
if (in_alt_jump(jump_addr, start, end))
return;
offset = jump_addr - pc;
c->options = LOONGARCH_CPU_CPUCFG | LOONGARCH_CPU_CSR |
LOONGARCH_CPU_TLB | LOONGARCH_CPU_VINT | LOONGARCH_CPU_WATCH;
- elf_hwcap |= HWCAP_LOONGARCH_CRC32;
+ elf_hwcap = HWCAP_LOONGARCH_CPUCFG | HWCAP_LOONGARCH_CRC32;
config = read_cpucfg(LOONGARCH_CPUCFG1);
if (config & CPUCFG1_UAL) {
.macro BUILD_HANDLER exception handler prep
.align 5
SYM_FUNC_START(handle_\exception)
+ 666:
BACKUP_T0T1
SAVE_ALL
build_prep_\prep
move a0, sp
la.abs t0, do_\handler
jirl ra, t0, 0
+ 668:
RESTORE_ALL_AND_RET
SYM_FUNC_END(handle_\exception)
+ SYM_DATA(unwind_hint_\exception, .word 668b - 666b)
.endm
BUILD_HANDLER ade ade badv
u32 larch_insn_gen_b(unsigned long pc, unsigned long dest)
{
long offset = dest - pc;
- unsigned int immediate_l, immediate_h;
union loongarch_instruction insn;
if ((offset & 3) || offset < -SZ_128M || offset >= SZ_128M) {
return INSN_BREAK;
}
- offset >>= 2;
-
- immediate_l = offset & 0xffff;
- offset >>= 16;
- immediate_h = offset & 0x3ff;
-
- insn.reg0i26_format.opcode = b_op;
- insn.reg0i26_format.immediate_l = immediate_l;
- insn.reg0i26_format.immediate_h = immediate_h;
+ emit_b(&insn, offset >> 2);
return insn.word;
}
u32 larch_insn_gen_bl(unsigned long pc, unsigned long dest)
{
long offset = dest - pc;
- unsigned int immediate_l, immediate_h;
union loongarch_instruction insn;
if ((offset & 3) || offset < -SZ_128M || offset >= SZ_128M) {
return INSN_BREAK;
}
- offset >>= 2;
-
- immediate_l = offset & 0xffff;
- offset >>= 16;
- immediate_h = offset & 0x3ff;
-
- insn.reg0i26_format.opcode = bl_op;
- insn.reg0i26_format.immediate_l = immediate_l;
- insn.reg0i26_format.immediate_h = immediate_h;
+ emit_bl(&insn, offset >> 2);
return insn.word;
}
{
union loongarch_instruction insn;
- insn.reg3_format.opcode = or_op;
- insn.reg3_format.rd = rd;
- insn.reg3_format.rj = rj;
- insn.reg3_format.rk = rk;
+ emit_or(&insn, rd, rj, rk);
return insn.word;
}
{
union loongarch_instruction insn;
- insn.reg1i20_format.opcode = lu12iw_op;
- insn.reg1i20_format.rd = rd;
- insn.reg1i20_format.immediate = imm;
+ emit_lu12iw(&insn, rd, imm);
return insn.word;
}
{
union loongarch_instruction insn;
- insn.reg1i20_format.opcode = lu32id_op;
- insn.reg1i20_format.rd = rd;
- insn.reg1i20_format.immediate = imm;
+ emit_lu32id(&insn, rd, imm);
return insn.word;
}
{
union loongarch_instruction insn;
- insn.reg2i12_format.opcode = lu52id_op;
- insn.reg2i12_format.rd = rd;
- insn.reg2i12_format.rj = rj;
- insn.reg2i12_format.immediate = imm;
+ emit_lu52id(&insn, rd, rj, imm);
return insn.word;
}
{
union loongarch_instruction insn;
- insn.reg2i16_format.opcode = jirl_op;
- insn.reg2i16_format.rd = rd;
- insn.reg2i16_format.rj = rj;
- insn.reg2i16_format.immediate = (dest - pc) >> 2;
+ emit_jirl(&insn, rj, rd, (dest - pc) >> 2);
return insn.word;
}
unsigned long __get_wchan(struct task_struct *task)
{
- unsigned long pc;
+ unsigned long pc = 0;
struct unwind_state state;
if (!try_get_task_stack(task))
return 0;
- unwind_start(&state, task, NULL);
- state.sp = thread_saved_fp(task);
- get_stack_info(state.sp, state.task, &state.stack_info);
- state.pc = thread_saved_ra(task);
-#ifdef CONFIG_UNWINDER_PROLOGUE
- state.type = UNWINDER_PROLOGUE;
-#endif
- for (; !unwind_done(&state); unwind_next_frame(&state)) {
+ for (unwind_start(&state, task, NULL);
+ !unwind_done(&state); unwind_next_frame(&state)) {
pc = unwind_get_return_address(&state);
if (!pc)
break;
if (!task)
task = current;
- if (user_mode(regs))
- state.type = UNWINDER_GUESS;
-
printk("%sCall Trace:", loglvl);
for (unwind_start(&state, task, pregs);
!unwind_done(&state); unwind_next_frame(&state)) {
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022-2023 Loongson Technology Corporation Limited
+ */
+#include <linux/kernel.h>
+#include <linux/ftrace.h>
+
+#include <asm/unwind.h>
+
+bool default_next_frame(struct unwind_state *state)
+{
+ struct stack_info *info = &state->stack_info;
+ unsigned long addr;
+
+ if (unwind_done(state))
+ return false;
+
+ do {
+ for (state->sp += sizeof(unsigned long);
+ state->sp < info->end; state->sp += sizeof(unsigned long)) {
+ addr = *(unsigned long *)(state->sp);
+ state->pc = unwind_graph_addr(state, addr, state->sp + 8);
+ if (__kernel_text_address(state->pc))
+ return true;
+ }
+
+ state->sp = info->next_sp;
+
+ } while (!get_stack_info(state->sp, state->task, info));
+
+ return false;
+}
/*
* Copyright (C) 2022 Loongson Technology Corporation Limited
*/
-#include <linux/kernel.h>
-#include <linux/ftrace.h>
-
#include <asm/unwind.h>
unsigned long unwind_get_return_address(struct unwind_state *state)
{
- if (unwind_done(state))
- return 0;
- else if (state->first)
- return state->pc;
-
- return *(unsigned long *)(state->sp);
+ return __unwind_get_return_address(state);
}
EXPORT_SYMBOL_GPL(unwind_get_return_address);
void unwind_start(struct unwind_state *state, struct task_struct *task,
struct pt_regs *regs)
{
- memset(state, 0, sizeof(*state));
-
- if (regs) {
- state->sp = regs->regs[3];
- state->pc = regs->csr_era;
- }
-
- state->task = task;
- state->first = true;
-
- get_stack_info(state->sp, state->task, &state->stack_info);
-
+ __unwind_start(state, task, regs);
if (!unwind_done(state) && !__kernel_text_address(state->pc))
unwind_next_frame(state);
}
bool unwind_next_frame(struct unwind_state *state)
{
- struct stack_info *info = &state->stack_info;
- unsigned long addr;
-
- if (unwind_done(state))
- return false;
-
- if (state->first)
- state->first = false;
-
- do {
- for (state->sp += sizeof(unsigned long);
- state->sp < info->end;
- state->sp += sizeof(unsigned long)) {
- addr = *(unsigned long *)(state->sp);
- state->pc = ftrace_graph_ret_addr(state->task, &state->graph_idx,
- addr, (unsigned long *)(state->sp - GRAPH_FAKE_OFFSET));
- if (__kernel_text_address(addr))
- return true;
- }
-
- state->sp = info->next_sp;
-
- } while (!get_stack_info(state->sp, state->task, info));
-
- return false;
+ return default_next_frame(state);
}
EXPORT_SYMBOL_GPL(unwind_next_frame);
/*
* Copyright (C) 2022 Loongson Technology Corporation Limited
*/
+#include <linux/cpumask.h>
#include <linux/ftrace.h>
#include <linux/kallsyms.h>
#include <asm/inst.h>
+#include <asm/loongson.h>
#include <asm/ptrace.h>
+#include <asm/setup.h>
#include <asm/unwind.h>
-static inline void unwind_state_fixup(struct unwind_state *state)
-{
-#ifdef CONFIG_DYNAMIC_FTRACE
- static unsigned long ftrace = (unsigned long)ftrace_call + 4;
-
- if (state->pc == ftrace)
- state->is_ftrace = true;
+extern const int unwind_hint_ade;
+extern const int unwind_hint_ale;
+extern const int unwind_hint_bp;
+extern const int unwind_hint_fpe;
+extern const int unwind_hint_fpu;
+extern const int unwind_hint_lsx;
+extern const int unwind_hint_lasx;
+extern const int unwind_hint_lbt;
+extern const int unwind_hint_ri;
+extern const int unwind_hint_watch;
+extern unsigned long eentry;
+#ifdef CONFIG_NUMA
+extern unsigned long pcpu_handlers[NR_CPUS];
#endif
-}
-unsigned long unwind_get_return_address(struct unwind_state *state)
+static inline bool scan_handlers(unsigned long entry_offset)
{
+ int idx, offset;
- if (unwind_done(state))
- return 0;
- else if (state->type)
- return state->pc;
- else if (state->first)
- return state->pc;
-
- return *(unsigned long *)(state->sp);
+ if (entry_offset >= EXCCODE_INT_START * VECSIZE)
+ return false;
+ idx = entry_offset / VECSIZE;
+ offset = entry_offset % VECSIZE;
+ switch (idx) {
+ case EXCCODE_ADE:
+ return offset == unwind_hint_ade;
+ case EXCCODE_ALE:
+ return offset == unwind_hint_ale;
+ case EXCCODE_BP:
+ return offset == unwind_hint_bp;
+ case EXCCODE_FPE:
+ return offset == unwind_hint_fpe;
+ case EXCCODE_FPDIS:
+ return offset == unwind_hint_fpu;
+ case EXCCODE_LSXDIS:
+ return offset == unwind_hint_lsx;
+ case EXCCODE_LASXDIS:
+ return offset == unwind_hint_lasx;
+ case EXCCODE_BTDIS:
+ return offset == unwind_hint_lbt;
+ case EXCCODE_INE:
+ return offset == unwind_hint_ri;
+ case EXCCODE_WATCH:
+ return offset == unwind_hint_watch;
+ default:
+ return false;
+ }
}
-EXPORT_SYMBOL_GPL(unwind_get_return_address);
-static bool unwind_by_guess(struct unwind_state *state)
+static inline bool fix_exception(unsigned long pc)
{
- struct stack_info *info = &state->stack_info;
- unsigned long addr;
-
- for (state->sp += sizeof(unsigned long);
- state->sp < info->end;
- state->sp += sizeof(unsigned long)) {
- addr = *(unsigned long *)(state->sp);
- state->pc = ftrace_graph_ret_addr(state->task, &state->graph_idx,
- addr, (unsigned long *)(state->sp - GRAPH_FAKE_OFFSET));
- if (__kernel_text_address(addr))
+#ifdef CONFIG_NUMA
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ if (!pcpu_handlers[cpu])
+ continue;
+ if (scan_handlers(pc - pcpu_handlers[cpu]))
return true;
}
+#endif
+ return scan_handlers(pc - eentry);
+}
+/*
+ * As we meet ftrace_regs_entry, reset first flag like first doing
+ * tracing. Prologue analysis will stop soon because PC is at entry.
+ */
+static inline bool fix_ftrace(unsigned long pc)
+{
+#ifdef CONFIG_DYNAMIC_FTRACE
+ return pc == (unsigned long)ftrace_call + LOONGARCH_INSN_SIZE;
+#else
return false;
+#endif
}
+static inline bool unwind_state_fixup(struct unwind_state *state)
+{
+ if (!fix_exception(state->pc) && !fix_ftrace(state->pc))
+ return false;
+
+ state->reset = true;
+ return true;
+}
+
+/*
+ * LoongArch function prologue is like follows,
+ * [instructions not use stack var]
+ * addi.d sp, sp, -imm
+ * st.d xx, sp, offset <- save callee saved regs and
+ * st.d yy, sp, offset save ra if function is nest.
+ * [others instructions]
+ */
static bool unwind_by_prologue(struct unwind_state *state)
{
long frame_ra = -1;
unsigned long frame_size = 0;
- unsigned long size, offset, pc = state->pc;
+ unsigned long size, offset, pc;
struct pt_regs *regs;
struct stack_info *info = &state->stack_info;
union loongarch_instruction *ip, *ip_end;
if (state->sp >= info->end || state->sp < info->begin)
return false;
- if (state->is_ftrace) {
- /*
- * As we meet ftrace_regs_entry, reset first flag like first doing
- * tracing. Prologue analysis will stop soon because PC is at entry.
- */
+ if (state->reset) {
regs = (struct pt_regs *)state->sp;
state->first = true;
- state->is_ftrace = false;
+ state->reset = false;
state->pc = regs->csr_era;
state->ra = regs->regs[1];
state->sp = regs->regs[3];
return true;
}
+ /*
+ * When first is not set, the PC is a return address in the previous frame.
+ * We need to adjust its value in case overflow to the next symbol.
+ */
+ pc = state->pc - (state->first ? 0 : LOONGARCH_INSN_SIZE);
if (!kallsyms_lookup_size_offset(pc, &size, &offset))
return false;
ip++;
}
+ /*
+ * Can't find stack alloc action, PC may be in a leaf function. Only the
+ * first being true is reasonable, otherwise indicate analysis is broken.
+ */
if (!frame_size) {
if (state->first)
goto first;
ip++;
}
+ /* Can't find save $ra action, PC may be in a leaf function, too. */
if (frame_ra < 0) {
if (state->first) {
state->sp = state->sp + frame_size;
return false;
}
- if (state->first)
- state->first = false;
-
state->pc = *(unsigned long *)(state->sp + frame_ra);
state->sp = state->sp + frame_size;
goto out;
first:
- state->first = false;
- if (state->pc == state->ra)
- return false;
-
state->pc = state->ra;
out:
- unwind_state_fixup(state);
- return !!__kernel_text_address(state->pc);
-}
-
-void unwind_start(struct unwind_state *state, struct task_struct *task,
- struct pt_regs *regs)
-{
- memset(state, 0, sizeof(*state));
-
- if (regs && __kernel_text_address(regs->csr_era)) {
- state->pc = regs->csr_era;
- state->sp = regs->regs[3];
- state->ra = regs->regs[1];
- state->type = UNWINDER_PROLOGUE;
- }
-
- state->task = task;
- state->first = true;
-
- get_stack_info(state->sp, state->task, &state->stack_info);
-
- if (!unwind_done(state) && !__kernel_text_address(state->pc))
- unwind_next_frame(state);
+ state->first = false;
+ return unwind_state_fixup(state) || __kernel_text_address(state->pc);
}
-EXPORT_SYMBOL_GPL(unwind_start);
-bool unwind_next_frame(struct unwind_state *state)
+static bool next_frame(struct unwind_state *state)
{
- struct stack_info *info = &state->stack_info;
- struct pt_regs *regs;
unsigned long pc;
+ struct pt_regs *regs;
+ struct stack_info *info = &state->stack_info;
if (unwind_done(state))
return false;
do {
- switch (state->type) {
- case UNWINDER_GUESS:
- state->first = false;
- if (unwind_by_guess(state))
- return true;
- break;
+ if (unwind_by_prologue(state)) {
+ state->pc = unwind_graph_addr(state, state->pc, state->sp);
+ return true;
+ }
+
+ if (info->type == STACK_TYPE_IRQ && info->end == state->sp) {
+ regs = (struct pt_regs *)info->next_sp;
+ pc = regs->csr_era;
+
+ if (user_mode(regs) || !__kernel_text_address(pc))
+ return false;
+
+ state->first = true;
+ state->pc = pc;
+ state->ra = regs->regs[1];
+ state->sp = regs->regs[3];
+ get_stack_info(state->sp, state->task, info);
- case UNWINDER_PROLOGUE:
- if (unwind_by_prologue(state)) {
- state->pc = ftrace_graph_ret_addr(state->task, &state->graph_idx,
- state->pc, (unsigned long *)(state->sp - GRAPH_FAKE_OFFSET));
- return true;
- }
-
- if (info->type == STACK_TYPE_IRQ &&
- info->end == state->sp) {
- regs = (struct pt_regs *)info->next_sp;
- pc = regs->csr_era;
-
- if (user_mode(regs) || !__kernel_text_address(pc))
- return false;
-
- state->first = true;
- state->ra = regs->regs[1];
- state->sp = regs->regs[3];
- state->pc = ftrace_graph_ret_addr(state->task, &state->graph_idx,
- pc, (unsigned long *)(state->sp - GRAPH_FAKE_OFFSET));
- get_stack_info(state->sp, state->task, info);
-
- return true;
- }
+ return true;
}
state->sp = info->next_sp;
return false;
}
+
+unsigned long unwind_get_return_address(struct unwind_state *state)
+{
+ return __unwind_get_return_address(state);
+}
+EXPORT_SYMBOL_GPL(unwind_get_return_address);
+
+void unwind_start(struct unwind_state *state, struct task_struct *task,
+ struct pt_regs *regs)
+{
+ __unwind_start(state, task, regs);
+ state->type = UNWINDER_PROLOGUE;
+ state->first = true;
+
+ /*
+ * The current PC is not kernel text address, we cannot find its
+ * relative symbol. Thus, prologue analysis will be broken. Luckily,
+ * we can use the default_next_frame().
+ */
+ if (!__kernel_text_address(state->pc)) {
+ state->type = UNWINDER_GUESS;
+ if (!unwind_done(state))
+ unwind_next_frame(state);
+ }
+}
+EXPORT_SYMBOL_GPL(unwind_start);
+
+bool unwind_next_frame(struct unwind_state *state)
+{
+ return state->type == UNWINDER_PROLOGUE ?
+ next_frame(state) : default_next_frame(state);
+}
EXPORT_SYMBOL_GPL(unwind_next_frame);
}
#ifdef CONFIG_NUMA
-static unsigned long pcpu_handlers[NR_CPUS];
+unsigned long pcpu_handlers[NR_CPUS];
#endif
extern long exception_handlers[VECSIZE * 128 / sizeof(long)];
dtb = get_fdt();
__dt_setup_arch(dtb);
- if (!early_init_dt_scan_memory())
+ if (early_init_dt_scan_memory())
return;
if (soc_info.mem_detect)
interrupts = <16 2 1 9>;
};
};
+
+&fman0_rx_0x08 {
+ /delete-property/ fsl,fman-10g-port;
+};
+
+&fman0_tx_0x28 {
+ /delete-property/ fsl,fman-10g-port;
+};
+
+&fman0_rx_0x09 {
+ /delete-property/ fsl,fman-10g-port;
+};
+
+&fman0_tx_0x29 {
+ /delete-property/ fsl,fman-10g-port;
+};
gsub(".*version ", "");
gsub("-.*", "");
split($1,a, ".");
+ if( length(a[3]) == "8" )
+ # a[3] is probably a date of format yyyymmdd used for release snapshots. We
+ # can assume it to be zero as it does not signify a new version as such.
+ a[3] = 0;
print a[1]*100000000 + a[2]*1000000 + a[3]*10000;
exit
}'
* are inited.
*/
struct imc_pmu_ref {
- struct mutex lock;
+ spinlock_t lock;
unsigned int id;
int refc;
};
#define BSS_FIRST_SECTIONS *(.bss.prominit)
#define EMITS_PT_NOTE
#define RO_EXCEPTION_TABLE_ALIGN 0
+#define RUNTIME_DISCARD_EXIT
#define SOFT_MASK_TABLE(align) \
. = ALIGN(align); \
DISCARDS
/DISCARD/ : {
*(*.EMB.apuinfo)
- *(.glink .iplt .plt .rela* .comment)
+ *(.glink .iplt .plt)
*(.gnu.version*)
*(.gnu.attributes)
*(.eh_frame)
+#ifndef CONFIG_RELOCATABLE
+ *(.rela*)
+#endif
}
}
void hpt_clear_stress(void);
static struct timer_list stress_hpt_timer;
-void stress_hpt_timer_fn(struct timer_list *timer)
+static void stress_hpt_timer_fn(struct timer_list *timer)
{
int next_cpu;
#include <asm/cputhreads.h>
#include <asm/smp.h>
#include <linux/string.h>
+#include <linux/spinlock.h>
/* Nest IMC data structures and variables */
* Used to avoid races in counting the nest-pmu units during hotplug
* register and unregister
*/
-static DEFINE_MUTEX(nest_init_lock);
+static DEFINE_SPINLOCK(nest_init_lock);
static DEFINE_PER_CPU(struct imc_pmu_ref *, local_nest_imc_refc);
static struct imc_pmu **per_nest_pmu_arr;
static cpumask_t nest_imc_cpumask;
* core and trace-imc
*/
static struct imc_pmu_ref imc_global_refc = {
- .lock = __MUTEX_INITIALIZER(imc_global_refc.lock),
+ .lock = __SPIN_LOCK_INITIALIZER(imc_global_refc.lock),
.id = 0,
.refc = 0,
};
get_hard_smp_processor_id(cpu));
/*
* If this is the last cpu in this chip then, skip the reference
- * count mutex lock and make the reference count on this chip zero.
+ * count lock and make the reference count on this chip zero.
*/
ref = get_nest_pmu_ref(cpu);
if (!ref)
/*
* See if we need to disable the nest PMU.
* If no events are currently in use, then we have to take a
- * mutex to ensure that we don't race with another task doing
+ * lock to ensure that we don't race with another task doing
* enable or disable the nest counters.
*/
ref = get_nest_pmu_ref(event->cpu);
if (!ref)
return;
- /* Take the mutex lock for this node and then decrement the reference count */
- mutex_lock(&ref->lock);
+ /* Take the lock for this node and then decrement the reference count */
+ spin_lock(&ref->lock);
if (ref->refc == 0) {
/*
* The scenario where this is true is, when perf session is
* an OPAL call to disable the engine in that node.
*
*/
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
return;
}
ref->refc--;
rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST,
get_hard_smp_processor_id(event->cpu));
if (rc) {
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
pr_err("nest-imc: Unable to stop the counters for core %d\n", node_id);
return;
}
WARN(1, "nest-imc: Invalid event reference count\n");
ref->refc = 0;
}
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
}
static int nest_imc_event_init(struct perf_event *event)
/*
* Get the imc_pmu_ref struct for this node.
- * Take the mutex lock and then increment the count of nest pmu events
- * inited.
+ * Take the lock and then increment the count of nest pmu events inited.
*/
ref = get_nest_pmu_ref(event->cpu);
if (!ref)
return -EINVAL;
- mutex_lock(&ref->lock);
+ spin_lock(&ref->lock);
if (ref->refc == 0) {
rc = opal_imc_counters_start(OPAL_IMC_COUNTERS_NEST,
get_hard_smp_processor_id(event->cpu));
if (rc) {
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
pr_err("nest-imc: Unable to start the counters for node %d\n",
node_id);
return rc;
}
}
++ref->refc;
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
event->destroy = nest_imc_counters_release;
return 0;
return -ENOMEM;
mem_info->vbase = page_address(page);
- /* Init the mutex */
core_imc_refc[core_id].id = core_id;
- mutex_init(&core_imc_refc[core_id].lock);
+ spin_lock_init(&core_imc_refc[core_id].lock);
rc = opal_imc_counters_init(OPAL_IMC_COUNTERS_CORE,
__pa((void *)mem_info->vbase),
perf_pmu_migrate_context(&core_imc_pmu->pmu, cpu, ncpu);
} else {
/*
- * If this is the last cpu in this core then, skip taking refernce
- * count mutex lock for this core and directly zero "refc" for
- * this core.
+ * If this is the last cpu in this core then skip taking reference
+ * count lock for this core and directly zero "refc" for this core.
*/
opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE,
get_hard_smp_processor_id(cpu));
* last cpu in this core and core-imc event running
* in this cpu.
*/
- mutex_lock(&imc_global_refc.lock);
+ spin_lock(&imc_global_refc.lock);
if (imc_global_refc.id == IMC_DOMAIN_CORE)
imc_global_refc.refc--;
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
}
return 0;
}
static void reset_global_refc(struct perf_event *event)
{
- mutex_lock(&imc_global_refc.lock);
+ spin_lock(&imc_global_refc.lock);
imc_global_refc.refc--;
/*
imc_global_refc.refc = 0;
imc_global_refc.id = 0;
}
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
}
static void core_imc_counters_release(struct perf_event *event)
/*
* See if we need to disable the IMC PMU.
* If no events are currently in use, then we have to take a
- * mutex to ensure that we don't race with another task doing
+ * lock to ensure that we don't race with another task doing
* enable or disable the core counters.
*/
core_id = event->cpu / threads_per_core;
- /* Take the mutex lock and decrement the refernce count for this core */
+ /* Take the lock and decrement the refernce count for this core */
ref = &core_imc_refc[core_id];
if (!ref)
return;
- mutex_lock(&ref->lock);
+ spin_lock(&ref->lock);
if (ref->refc == 0) {
/*
* The scenario where this is true is, when perf session is
* an OPAL call to disable the engine in that core.
*
*/
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
return;
}
ref->refc--;
rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE,
get_hard_smp_processor_id(event->cpu));
if (rc) {
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
pr_err("IMC: Unable to stop the counters for core %d\n", core_id);
return;
}
WARN(1, "core-imc: Invalid event reference count\n");
ref->refc = 0;
}
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
reset_global_refc(event);
}
if ((!pcmi->vbase))
return -ENODEV;
- /* Get the core_imc mutex for this core */
ref = &core_imc_refc[core_id];
if (!ref)
return -EINVAL;
/*
* Core pmu units are enabled only when it is used.
* See if this is triggered for the first time.
- * If yes, take the mutex lock and enable the core counters.
+ * If yes, take the lock and enable the core counters.
* If not, just increment the count in core_imc_refc struct.
*/
- mutex_lock(&ref->lock);
+ spin_lock(&ref->lock);
if (ref->refc == 0) {
rc = opal_imc_counters_start(OPAL_IMC_COUNTERS_CORE,
get_hard_smp_processor_id(event->cpu));
if (rc) {
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
pr_err("core-imc: Unable to start the counters for core %d\n",
core_id);
return rc;
}
}
++ref->refc;
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
/*
* Since the system can run either in accumulation or trace-mode
* to know whether any other trace/thread imc
* events are running.
*/
- mutex_lock(&imc_global_refc.lock);
+ spin_lock(&imc_global_refc.lock);
if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_CORE) {
/*
* No other trace/thread imc events are running in
imc_global_refc.id = IMC_DOMAIN_CORE;
imc_global_refc.refc++;
} else {
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
return -EBUSY;
}
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
event->hw.event_base = (u64)pcmi->vbase + (config & IMC_EVENT_OFFSET_MASK);
event->destroy = core_imc_counters_release;
mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63))));
/* Reduce the refc if thread-imc event running on this cpu */
- mutex_lock(&imc_global_refc.lock);
+ spin_lock(&imc_global_refc.lock);
if (imc_global_refc.id == IMC_DOMAIN_THREAD)
imc_global_refc.refc--;
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
return 0;
}
if (!target)
return -EINVAL;
- mutex_lock(&imc_global_refc.lock);
+ spin_lock(&imc_global_refc.lock);
/*
* Check if any other trace/core imc events are running in the
* system, if not set the global id to thread-imc.
imc_global_refc.id = IMC_DOMAIN_THREAD;
imc_global_refc.refc++;
} else {
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
return -EBUSY;
}
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
event->pmu->task_ctx_nr = perf_sw_context;
event->destroy = reset_global_refc;
/*
* imc pmus are enabled only when it is used.
* See if this is triggered for the first time.
- * If yes, take the mutex lock and enable the counters.
+ * If yes, take the lock and enable the counters.
* If not, just increment the count in ref count struct.
*/
ref = &core_imc_refc[core_id];
if (!ref)
return -EINVAL;
- mutex_lock(&ref->lock);
+ spin_lock(&ref->lock);
if (ref->refc == 0) {
if (opal_imc_counters_start(OPAL_IMC_COUNTERS_CORE,
get_hard_smp_processor_id(smp_processor_id()))) {
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
pr_err("thread-imc: Unable to start the counter\
for core %d\n", core_id);
return -EINVAL;
}
}
++ref->refc;
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
return 0;
}
return;
}
- mutex_lock(&ref->lock);
+ spin_lock(&ref->lock);
ref->refc--;
if (ref->refc == 0) {
if (opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE,
get_hard_smp_processor_id(smp_processor_id()))) {
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
pr_err("thread-imc: Unable to stop the counters\
for core %d\n", core_id);
return;
} else if (ref->refc < 0) {
ref->refc = 0;
}
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
/* Set bit 0 of LDBAR to zero, to stop posting updates to memory */
mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63))));
}
}
- /* Init the mutex, if not already */
trace_imc_refc[core_id].id = core_id;
- mutex_init(&trace_imc_refc[core_id].lock);
+ spin_lock_init(&trace_imc_refc[core_id].lock);
mtspr(SPRN_LDBAR, 0);
return 0;
* Reduce the refc if any trace-imc event running
* on this cpu.
*/
- mutex_lock(&imc_global_refc.lock);
+ spin_lock(&imc_global_refc.lock);
if (imc_global_refc.id == IMC_DOMAIN_TRACE)
imc_global_refc.refc--;
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
return 0;
}
}
mtspr(SPRN_LDBAR, ldbar_value);
- mutex_lock(&ref->lock);
+ spin_lock(&ref->lock);
if (ref->refc == 0) {
if (opal_imc_counters_start(OPAL_IMC_COUNTERS_TRACE,
get_hard_smp_processor_id(smp_processor_id()))) {
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
pr_err("trace-imc: Unable to start the counters for core %d\n", core_id);
return -EINVAL;
}
}
++ref->refc;
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
return 0;
}
return;
}
- mutex_lock(&ref->lock);
+ spin_lock(&ref->lock);
ref->refc--;
if (ref->refc == 0) {
if (opal_imc_counters_stop(OPAL_IMC_COUNTERS_TRACE,
get_hard_smp_processor_id(smp_processor_id()))) {
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
pr_err("trace-imc: Unable to stop the counters for core %d\n", core_id);
return;
}
} else if (ref->refc < 0) {
ref->refc = 0;
}
- mutex_unlock(&ref->lock);
+ spin_unlock(&ref->lock);
trace_imc_event_stop(event, flags);
}
* no other thread is running any core/thread imc
* events
*/
- mutex_lock(&imc_global_refc.lock);
+ spin_lock(&imc_global_refc.lock);
if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_TRACE) {
/*
* No core/thread imc events are running in the
imc_global_refc.id = IMC_DOMAIN_TRACE;
imc_global_refc.refc++;
} else {
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
return -EBUSY;
}
- mutex_unlock(&imc_global_refc.lock);
+ spin_unlock(&imc_global_refc.lock);
event->hw.idx = -1;
i = 0;
for_each_node(nid) {
/*
- * Mutex lock to avoid races while tracking the number of
+ * Take the lock to avoid races while tracking the number of
* sessions using the chip's nest pmu units.
*/
- mutex_init(&nest_imc_refc[i].lock);
+ spin_lock_init(&nest_imc_refc[i].lock);
/*
* Loop to init the "id" with the node_id. Variable "i" initialized to
static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr)
{
if (pmu_ptr->domain == IMC_DOMAIN_NEST) {
- mutex_lock(&nest_init_lock);
+ spin_lock(&nest_init_lock);
if (nest_pmus == 1) {
cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE);
kfree(nest_imc_refc);
if (nest_pmus > 0)
nest_pmus--;
- mutex_unlock(&nest_init_lock);
+ spin_unlock(&nest_init_lock);
}
/* Free core_imc memory */
* rest. To handle the cpuhotplug callback unregister, we track
* the number of nest pmus in "nest_pmus".
*/
- mutex_lock(&nest_init_lock);
+ spin_lock(&nest_init_lock);
if (nest_pmus == 0) {
ret = init_nest_pmu_ref();
if (ret) {
- mutex_unlock(&nest_init_lock);
+ spin_unlock(&nest_init_lock);
kfree(per_nest_pmu_arr);
per_nest_pmu_arr = NULL;
goto err_free_mem;
/* Register for cpu hotplug notification. */
ret = nest_pmu_cpumask_init();
if (ret) {
- mutex_unlock(&nest_init_lock);
+ spin_unlock(&nest_init_lock);
kfree(nest_imc_refc);
kfree(per_nest_pmu_arr);
per_nest_pmu_arr = NULL;
}
}
nest_pmus++;
- mutex_unlock(&nest_init_lock);
+ spin_unlock(&nest_init_lock);
break;
case IMC_DOMAIN_CORE:
ret = core_imc_pmu_cpumask_init();
might_fault(); \
access_ok(__p, sizeof(*__p)) ? \
__get_user((x), __p) : \
- ((x) = 0, -EFAULT); \
+ ((x) = (__force __typeof__(x))0, -EFAULT); \
})
#define __put_user_asm(insn, x, ptr, err) \
} while (0)
__RISCV_INSN_FUNCS(c_j, 0xe003, 0xa001);
-__RISCV_INSN_FUNCS(c_jr, 0xf007, 0x8002);
+__RISCV_INSN_FUNCS(c_jr, 0xf07f, 0x8002);
__RISCV_INSN_FUNCS(c_jal, 0xe003, 0x2001);
-__RISCV_INSN_FUNCS(c_jalr, 0xf007, 0x9002);
+__RISCV_INSN_FUNCS(c_jalr, 0xf07f, 0x9002);
__RISCV_INSN_FUNCS(c_beqz, 0xe003, 0xc001);
__RISCV_INSN_FUNCS(c_bnez, 0xe003, 0xe001);
__RISCV_INSN_FUNCS(c_ebreak, 0xffff, 0x9002);
#define pmd_ERROR(e) \
printk("%s:%d: bad pmd %016llx.\n", __FILE__, __LINE__, pmd_val(e))
-typedef struct {
+typedef union {
struct {
unsigned long pmd_low;
unsigned long pmd_high;
movw %dx, %si
movw %sp, %di
movw $11, %cx
- rep; movsd
+ rep; movsl
/* Pop full state from the stack */
popal
jz 4f
movw %sp, %si
movw $11, %cx
- rep; movsd
+ rep; movsl
4: addw $44, %sp
/* Restore state and return */
{
unsigned long *reg, val, vaddr;
char buffer[MAX_INSN_SIZE];
+ enum insn_mmio_type mmio;
struct insn insn = {};
- enum mmio_type mmio;
int size, extend_size;
u8 extend_val = 0;
return -EINVAL;
mmio = insn_decode_mmio(&insn, &size);
- if (WARN_ON_ONCE(mmio == MMIO_DECODE_FAILED))
+ if (WARN_ON_ONCE(mmio == INSN_MMIO_DECODE_FAILED))
return -EINVAL;
- if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) {
+ if (mmio != INSN_MMIO_WRITE_IMM && mmio != INSN_MMIO_MOVS) {
reg = insn_get_modrm_reg_ptr(&insn, regs);
if (!reg)
return -EINVAL;
/* Handle writes first */
switch (mmio) {
- case MMIO_WRITE:
+ case INSN_MMIO_WRITE:
memcpy(&val, reg, size);
if (!mmio_write(size, ve->gpa, val))
return -EIO;
return insn.length;
- case MMIO_WRITE_IMM:
+ case INSN_MMIO_WRITE_IMM:
val = insn.immediate.value;
if (!mmio_write(size, ve->gpa, val))
return -EIO;
return insn.length;
- case MMIO_READ:
- case MMIO_READ_ZERO_EXTEND:
- case MMIO_READ_SIGN_EXTEND:
+ case INSN_MMIO_READ:
+ case INSN_MMIO_READ_ZERO_EXTEND:
+ case INSN_MMIO_READ_SIGN_EXTEND:
/* Reads are handled below */
break;
- case MMIO_MOVS:
- case MMIO_DECODE_FAILED:
+ case INSN_MMIO_MOVS:
+ case INSN_MMIO_DECODE_FAILED:
/*
* MMIO was accessed with an instruction that could not be
* decoded or handled properly. It was likely not using io.h
return -EIO;
switch (mmio) {
- case MMIO_READ:
+ case INSN_MMIO_READ:
/* Zero-extend for 32-bit operation */
extend_size = size == 4 ? sizeof(*reg) : 0;
break;
- case MMIO_READ_ZERO_EXTEND:
+ case INSN_MMIO_READ_ZERO_EXTEND:
/* Zero extend based on operand size */
extend_size = insn.opnd_bytes;
break;
- case MMIO_READ_SIGN_EXTEND:
+ case INSN_MMIO_READ_SIGN_EXTEND:
/* Sign extend based on operand size */
extend_size = insn.opnd_bytes;
if (size == 1 && val & BIT(7))
* MSR_CORE_C1_RES: CORE C1 Residency Counter
* perf code: 0x00
* Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL,RPL
+ * MTL
* Scope: Core (each processor core has a MSR)
* MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
* perf code: 0x01
* perf code: 0x02
* Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
* SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX,
- * TGL,TNT,RKL,ADL,RPL,SPR
+ * TGL,TNT,RKL,ADL,RPL,SPR,MTL
* Scope: Core
* MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
* perf code: 0x03
* Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML,
- * ICL,TGL,RKL,ADL,RPL
+ * ICL,TGL,RKL,ADL,RPL,MTL
* Scope: Core
* MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter.
* perf code: 0x00
* Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL,
* KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL,
- * RPL,SPR
+ * RPL,SPR,MTL
* Scope: Package (physical package)
* MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter.
* perf code: 0x01
* Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL,
* GLM,CNL,KBL,CML,ICL,TGL,TNT,RKL,
- * ADL,RPL
+ * ADL,RPL,MTL
* Scope: Package (physical package)
* MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter.
* perf code: 0x02
* Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
* SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX,
- * TGL,TNT,RKL,ADL,RPL,SPR
+ * TGL,TNT,RKL,ADL,RPL,SPR,MTL
* Scope: Package (physical package)
* MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter.
* perf code: 0x03
* Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL,
- * KBL,CML,ICL,TGL,RKL,ADL,RPL
+ * KBL,CML,ICL,TGL,RKL,ADL,RPL,MTL
* Scope: Package (physical package)
* MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter.
* perf code: 0x04
* Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL,
- * ADL,RPL
+ * ADL,RPL,MTL
* Scope: Package (physical package)
* MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter.
* perf code: 0x05
* Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL,
- * ADL,RPL
+ * ADL,RPL,MTL
* Scope: Package (physical package)
* MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
* perf code: 0x06
* Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL,
- * TNT,RKL,ADL,RPL
+ * TNT,RKL,ADL,RPL,MTL
* Scope: Package (physical package)
*
*/
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_cstates),
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &adl_cstates),
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &adl_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, &adl_cstates),
+ X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, &adl_cstates),
{ },
};
MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &adl_uncore_init),
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &adl_uncore_init),
X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &spr_uncore_init),
+ X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &spr_uncore_init),
X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &snr_uncore_init),
{},
};
case INTEL_FAM6_BROADWELL_G:
case INTEL_FAM6_BROADWELL_X:
case INTEL_FAM6_SAPPHIRERAPIDS_X:
+ case INTEL_FAM6_EMERALDRAPIDS_X:
case INTEL_FAM6_ATOM_SILVERMONT:
case INTEL_FAM6_ATOM_SILVERMONT_D:
case INTEL_FAM6_RAPTORLAKE:
case INTEL_FAM6_RAPTORLAKE_P:
case INTEL_FAM6_RAPTORLAKE_S:
+ case INTEL_FAM6_METEORLAKE:
+ case INTEL_FAM6_METEORLAKE_L:
if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
return true;
break;
X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &model_hsx),
X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &model_spr),
+ X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &model_spr),
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, &model_skl),
{},
};
MODULE_DEVICE_TABLE(x86cpu, rapl_model_match);
bool insn_decode_from_regs(struct insn *insn, struct pt_regs *regs,
unsigned char buf[MAX_INSN_SIZE], int buf_size);
-enum mmio_type {
- MMIO_DECODE_FAILED,
- MMIO_WRITE,
- MMIO_WRITE_IMM,
- MMIO_READ,
- MMIO_READ_ZERO_EXTEND,
- MMIO_READ_SIGN_EXTEND,
- MMIO_MOVS,
+enum insn_mmio_type {
+ INSN_MMIO_DECODE_FAILED,
+ INSN_MMIO_WRITE,
+ INSN_MMIO_WRITE_IMM,
+ INSN_MMIO_READ,
+ INSN_MMIO_READ_ZERO_EXTEND,
+ INSN_MMIO_READ_SIGN_EXTEND,
+ INSN_MMIO_MOVS,
};
-enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes);
+enum insn_mmio_type insn_decode_mmio(struct insn *insn, int *bytes);
#endif /* _ASM_X86_INSN_EVAL_H */
/* Xen emulation context */
struct kvm_xen {
+ struct mutex xen_lock;
u32 xen_version;
bool long_mode;
bool runstate_update_flag;
if (ctrl == PR_SPEC_FORCE_DISABLE)
task_set_spec_ib_force_disable(task);
task_update_spec_tif(task);
+ if (task == current)
+ indirect_branch_prediction_barrier();
break;
default:
return -ERANGE;
return entry;
}
+static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
+{
+ u64 msr_val;
+
+ /*
+ * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured
+ * with a valid event code for supported resource type and the bits
+ * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID,
+ * IA32_QM_CTR.data (bits 61:0) reports the monitored data.
+ * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62)
+ * are error bits.
+ */
+ wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
+ rdmsrl(MSR_IA32_QM_CTR, msr_val);
+
+ if (msr_val & RMID_VAL_ERROR)
+ return -EIO;
+ if (msr_val & RMID_VAL_UNAVAIL)
+ return -EINVAL;
+
+ *val = msr_val;
+ return 0;
+}
+
static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom,
u32 rmid,
enum resctrl_event_id eventid)
struct arch_mbm_state *am;
am = get_arch_mbm_state(hw_dom, rmid, eventid);
- if (am)
+ if (am) {
memset(am, 0, sizeof(*am));
+
+ /* Record any initial, non-zero count value. */
+ __rmid_read(rmid, eventid, &am->prev_msr);
+ }
}
static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
struct arch_mbm_state *am;
u64 msr_val, chunks;
+ int ret;
if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
return -EINVAL;
- /*
- * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured
- * with a valid event code for supported resource type and the bits
- * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID,
- * IA32_QM_CTR.data (bits 61:0) reports the monitored data.
- * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62)
- * are error bits.
- */
- wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
- rdmsrl(MSR_IA32_QM_CTR, msr_val);
-
- if (msr_val & RMID_VAL_ERROR)
- return -EIO;
- if (msr_val & RMID_VAL_UNAVAIL)
- return -EINVAL;
+ ret = __rmid_read(rmid, eventid, &msr_val);
+ if (ret)
+ return ret;
am = get_arch_mbm_state(hw_dom, rmid, eventid);
if (am) {
/*
* Ensure the task's closid and rmid are written before determining if
* the task is current that will decide if it will be interrupted.
+ * This pairs with the full barrier between the rq->curr update and
+ * resctrl_sched_in() during context switch.
*/
- barrier();
+ smp_mb();
/*
* By now, the task's closid and rmid are set. If the task is current
WRITE_ONCE(t->rmid, to->mon.rmid);
/*
+ * Order the closid/rmid stores above before the loads
+ * in task_curr(). This pairs with the full barrier
+ * between the rq->curr update and resctrl_sched_in()
+ * during context switch.
+ */
+ smp_mb();
+
+ /*
* If the task is on a CPU, set the CPU in the mask.
* The detection is inaccurate as tasks might move or
* schedule before the smp function call takes place.
kbuf.buf_align = ELF_CORE_HEADER_ALIGN;
kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
ret = kexec_add_buffer(&kbuf);
- if (ret) {
- vfree((void *)image->elf_headers);
+ if (ret)
return ret;
- }
image->elf_load_addr = kbuf.mem;
pr_debug("Loaded ELF headers at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
image->elf_load_addr, kbuf.bufsz, kbuf.memsz);
static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
{
struct insn *insn = &ctxt->insn;
+ enum insn_mmio_type mmio;
unsigned int bytes = 0;
- enum mmio_type mmio;
enum es_result ret;
u8 sign_byte;
long *reg_data;
mmio = insn_decode_mmio(insn, &bytes);
- if (mmio == MMIO_DECODE_FAILED)
+ if (mmio == INSN_MMIO_DECODE_FAILED)
return ES_DECODE_FAILED;
- if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) {
+ if (mmio != INSN_MMIO_WRITE_IMM && mmio != INSN_MMIO_MOVS) {
reg_data = insn_get_modrm_reg_ptr(insn, ctxt->regs);
if (!reg_data)
return ES_DECODE_FAILED;
}
switch (mmio) {
- case MMIO_WRITE:
+ case INSN_MMIO_WRITE:
memcpy(ghcb->shared_buffer, reg_data, bytes);
ret = vc_do_mmio(ghcb, ctxt, bytes, false);
break;
- case MMIO_WRITE_IMM:
+ case INSN_MMIO_WRITE_IMM:
memcpy(ghcb->shared_buffer, insn->immediate1.bytes, bytes);
ret = vc_do_mmio(ghcb, ctxt, bytes, false);
break;
- case MMIO_READ:
+ case INSN_MMIO_READ:
ret = vc_do_mmio(ghcb, ctxt, bytes, true);
if (ret)
break;
memcpy(reg_data, ghcb->shared_buffer, bytes);
break;
- case MMIO_READ_ZERO_EXTEND:
+ case INSN_MMIO_READ_ZERO_EXTEND:
ret = vc_do_mmio(ghcb, ctxt, bytes, true);
if (ret)
break;
memset(reg_data, 0, insn->opnd_bytes);
memcpy(reg_data, ghcb->shared_buffer, bytes);
break;
- case MMIO_READ_SIGN_EXTEND:
+ case INSN_MMIO_READ_SIGN_EXTEND:
ret = vc_do_mmio(ghcb, ctxt, bytes, true);
if (ret)
break;
memset(reg_data, sign_byte, insn->opnd_bytes);
memcpy(reg_data, ghcb->shared_buffer, bytes);
break;
- case MMIO_MOVS:
+ case INSN_MMIO_MOVS:
ret = vc_handle_mmio_movs(ctxt, bytes);
break;
default:
int nent;
};
+static struct kvm_cpuid_entry2 *get_next_cpuid(struct kvm_cpuid_array *array)
+{
+ if (array->nent >= array->maxnent)
+ return NULL;
+
+ return &array->entries[array->nent++];
+}
+
static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array,
u32 function, u32 index)
{
- struct kvm_cpuid_entry2 *entry;
+ struct kvm_cpuid_entry2 *entry = get_next_cpuid(array);
- if (array->nent >= array->maxnent)
+ if (!entry)
return NULL;
- entry = &array->entries[array->nent++];
-
memset(entry, 0, sizeof(*entry));
entry->function = function;
entry->index = index;
entry->edx = edx.full;
break;
}
- /*
- * Per Intel's SDM, the 0x1f is a superset of 0xb,
- * thus they can be handled by common code.
- */
case 0x1f:
case 0xb:
/*
- * Populate entries until the level type (ECX[15:8]) of the
- * previous entry is zero. Note, CPUID EAX.{0x1f,0xb}.0 is
- * the starting entry, filled by the primary do_host_cpuid().
+ * No topology; a valid topology is indicated by the presence
+ * of subleaf 1.
*/
- for (i = 1; entry->ecx & 0xff00; ++i) {
- entry = do_host_cpuid(array, function, i);
- if (!entry)
- goto out;
- }
+ entry->eax = entry->ebx = entry->ecx = 0;
break;
case 0xd: {
u64 permitted_xcr0 = kvm_caps.supported_xcr0 & xstate_get_guest_group_perm();
entry->ebx = entry->ecx = entry->edx = 0;
break;
case 0x8000001e:
+ /* Do not return host topology information. */
+ entry->eax = entry->ebx = entry->ecx = 0;
+ entry->edx = 0; /* reserved */
break;
case 0x8000001F:
if (!kvm_cpu_cap_has(X86_FEATURE_SEV)) {
c->intercepts[i] = h->intercepts[i];
if (g->int_ctl & V_INTR_MASKING_MASK) {
- /* We only want the cr8 intercept bits of L1 */
- vmcb_clr_intercept(c, INTERCEPT_CR8_READ);
- vmcb_clr_intercept(c, INTERCEPT_CR8_WRITE);
-
/*
- * Once running L2 with HF_VINTR_MASK, EFLAGS.IF does not
- * affect any interrupt we may want to inject; therefore,
- * interrupt window vmexits are irrelevant to L0.
+ * Once running L2 with HF_VINTR_MASK, EFLAGS.IF and CR8
+ * does not affect any interrupt we may want to inject;
+ * therefore, writes to CR8 are irrelevant to L0, as are
+ * interrupt window vmexits.
*/
+ vmcb_clr_intercept(c, INTERCEPT_CR8_WRITE);
vmcb_clr_intercept(c, INTERCEPT_VINTR);
}
* Attempt to obtain the GPC lock on *both* (if there are two)
* gfn_to_pfn caches that cover the region.
*/
- read_lock_irqsave(&gpc1->lock, flags);
+ if (atomic) {
+ local_irq_save(flags);
+ if (!read_trylock(&gpc1->lock)) {
+ local_irq_restore(flags);
+ return;
+ }
+ } else {
+ read_lock_irqsave(&gpc1->lock, flags);
+ }
while (!kvm_gpc_check(gpc1, user_len1)) {
read_unlock_irqrestore(&gpc1->lock, flags);
* The guest's runstate_info is split across two pages and we
* need to hold and validate both GPCs simultaneously. We can
* declare a lock ordering GPC1 > GPC2 because nothing else
- * takes them more than one at a time.
+ * takes them more than one at a time. Set a subclass on the
+ * gpc1 lock to make lockdep shut up about it.
*/
- read_lock(&gpc2->lock);
+ lock_set_subclass(&gpc1->lock.dep_map, 1, _THIS_IP_);
+ if (atomic) {
+ if (!read_trylock(&gpc2->lock)) {
+ read_unlock_irqrestore(&gpc1->lock, flags);
+ return;
+ }
+ } else {
+ read_lock(&gpc2->lock);
+ }
if (!kvm_gpc_check(gpc2, user_len2)) {
read_unlock(&gpc2->lock);
if (!IS_ENABLED(CONFIG_64BIT) && data->u.long_mode) {
r = -EINVAL;
} else {
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
kvm->arch.xen.long_mode = !!data->u.long_mode;
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
r = 0;
}
break;
case KVM_XEN_ATTR_TYPE_SHARED_INFO:
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
r = kvm_xen_shared_info_init(kvm, data->u.shared_info.gfn);
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
break;
case KVM_XEN_ATTR_TYPE_UPCALL_VECTOR:
if (data->u.vector && data->u.vector < 0x10)
r = -EINVAL;
else {
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
kvm->arch.xen.upcall_vector = data->u.vector;
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
r = 0;
}
break;
break;
case KVM_XEN_ATTR_TYPE_XEN_VERSION:
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
kvm->arch.xen.xen_version = data->u.xen_version;
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
r = 0;
break;
r = -EOPNOTSUPP;
break;
}
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
kvm->arch.xen.runstate_update_flag = !!data->u.runstate_update_flag;
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
r = 0;
break;
{
int r = -ENOENT;
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
switch (data->type) {
case KVM_XEN_ATTR_TYPE_LONG_MODE:
break;
}
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
return r;
}
{
int idx, r = -ENOENT;
- mutex_lock(&vcpu->kvm->lock);
+ mutex_lock(&vcpu->kvm->arch.xen.xen_lock);
idx = srcu_read_lock(&vcpu->kvm->srcu);
switch (data->type) {
}
srcu_read_unlock(&vcpu->kvm->srcu, idx);
- mutex_unlock(&vcpu->kvm->lock);
+ mutex_unlock(&vcpu->kvm->arch.xen.xen_lock);
return r;
}
{
int r = -ENOENT;
- mutex_lock(&vcpu->kvm->lock);
+ mutex_lock(&vcpu->kvm->arch.xen.xen_lock);
switch (data->type) {
case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO:
break;
}
- mutex_unlock(&vcpu->kvm->lock);
+ mutex_unlock(&vcpu->kvm->arch.xen.xen_lock);
return r;
}
xhc->blob_size_32 || xhc->blob_size_64))
return -EINVAL;
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
if (xhc->msr && !kvm->arch.xen_hvm_config.msr)
static_branch_inc(&kvm_xen_enabled.key);
memcpy(&kvm->arch.xen_hvm_config, xhc, sizeof(*xhc));
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
return 0;
}
mm_borrowed = true;
}
- /*
- * For the irqfd workqueue, using the main kvm->lock mutex is
- * fine since this function is invoked from kvm_set_irq() with
- * no other lock held, no srcu. In future if it will be called
- * directly from a vCPU thread (e.g. on hypercall for an IPI)
- * then it may need to switch to using a leaf-node mutex for
- * serializing the shared_info mapping.
- */
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
/*
* It is theoretically possible for the page to be unmapped
srcu_read_unlock(&kvm->srcu, idx);
} while(!rc);
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
if (mm_borrowed)
kthread_unuse_mm(kvm->mm);
int ret;
/* Protect writes to evtchnfd as well as the idr lookup. */
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
evtchnfd = idr_find(&kvm->arch.xen.evtchn_ports, port);
ret = -ENOENT;
}
ret = 0;
out_unlock:
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
return ret;
}
evtchnfd->deliver.port.priority = data->u.evtchn.deliver.port.priority;
}
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
ret = idr_alloc(&kvm->arch.xen.evtchn_ports, evtchnfd, port, port + 1,
GFP_KERNEL);
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
if (ret >= 0)
return 0;
{
struct evtchnfd *evtchnfd;
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
evtchnfd = idr_remove(&kvm->arch.xen.evtchn_ports, port);
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
if (!evtchnfd)
return -ENOENT;
int i;
int n = 0;
- mutex_lock(&kvm->lock);
+ mutex_lock(&kvm->arch.xen.xen_lock);
/*
* Because synchronize_srcu() cannot be called inside the
all_evtchnfds = kmalloc_array(n, sizeof(struct evtchnfd *), GFP_KERNEL);
if (!all_evtchnfds) {
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
return -ENOMEM;
}
all_evtchnfds[n++] = evtchnfd;
idr_remove(&kvm->arch.xen.evtchn_ports, evtchnfd->send_port);
}
- mutex_unlock(&kvm->lock);
+ mutex_unlock(&kvm->arch.xen.xen_lock);
synchronize_srcu(&kvm->srcu);
void kvm_xen_init_vm(struct kvm *kvm)
{
+ mutex_init(&kvm->arch.xen.xen_lock);
idr_init(&kvm->arch.xen.evtchn_ports);
kvm_gpc_init(&kvm->arch.xen.shinfo_cache, kvm, NULL, KVM_HOST_USES_PFN);
}
* Returns:
*
* Type of the instruction. Size of the memory operand is stored in
- * @bytes. If decode failed, MMIO_DECODE_FAILED returned.
+ * @bytes. If decode failed, INSN_MMIO_DECODE_FAILED returned.
*/
-enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes)
+enum insn_mmio_type insn_decode_mmio(struct insn *insn, int *bytes)
{
- enum mmio_type type = MMIO_DECODE_FAILED;
+ enum insn_mmio_type type = INSN_MMIO_DECODE_FAILED;
*bytes = 0;
if (insn_get_opcode(insn))
- return MMIO_DECODE_FAILED;
+ return INSN_MMIO_DECODE_FAILED;
switch (insn->opcode.bytes[0]) {
case 0x88: /* MOV m8,r8 */
case 0x89: /* MOV m16/m32/m64, r16/m32/m64 */
if (!*bytes)
*bytes = insn->opnd_bytes;
- type = MMIO_WRITE;
+ type = INSN_MMIO_WRITE;
break;
case 0xc6: /* MOV m8, imm8 */
case 0xc7: /* MOV m16/m32/m64, imm16/imm32/imm64 */
if (!*bytes)
*bytes = insn->opnd_bytes;
- type = MMIO_WRITE_IMM;
+ type = INSN_MMIO_WRITE_IMM;
break;
case 0x8a: /* MOV r8, m8 */
case 0x8b: /* MOV r16/r32/r64, m16/m32/m64 */
if (!*bytes)
*bytes = insn->opnd_bytes;
- type = MMIO_READ;
+ type = INSN_MMIO_READ;
break;
case 0xa4: /* MOVS m8, m8 */
case 0xa5: /* MOVS m16/m32/m64, m16/m32/m64 */
if (!*bytes)
*bytes = insn->opnd_bytes;
- type = MMIO_MOVS;
+ type = INSN_MMIO_MOVS;
break;
case 0x0f: /* Two-byte instruction */
case 0xb7: /* MOVZX r32/r64, m16 */
if (!*bytes)
*bytes = 2;
- type = MMIO_READ_ZERO_EXTEND;
+ type = INSN_MMIO_READ_ZERO_EXTEND;
break;
case 0xbe: /* MOVSX r16/r32/r64, m8 */
case 0xbf: /* MOVSX r32/r64, m16 */
if (!*bytes)
*bytes = 2;
- type = MMIO_READ_SIGN_EXTEND;
+ type = INSN_MMIO_READ_SIGN_EXTEND;
break;
}
break;
*/
SYM_FUNC_START(__iowrite32_copy)
movl %edx,%ecx
- rep movsd
+ rep movsl
RET
SYM_FUNC_END(__iowrite32_copy)
#include <asm/pti.h>
#include <asm/text-patching.h>
#include <asm/memtype.h>
+#include <asm/paravirt.h>
/*
* We need to define the tracepoints somewhere, and tlb.c
poking_mm = mm_alloc();
BUG_ON(!poking_mm);
+ /* Xen PV guests need the PGD to be pinned. */
+ paravirt_arch_dup_mmap(NULL, poking_mm);
+
/*
* Randomize the poking address, but make sure that the following page
* will be mapped at the same PMD. We need 2 pages, so find space for 3,
u8 mtrr_type, uniform;
mtrr_type = mtrr_type_lookup(start, end, &uniform);
- if (mtrr_type != MTRR_TYPE_WRBACK)
+ if (mtrr_type != MTRR_TYPE_WRBACK &&
+ mtrr_type != MTRR_TYPE_INVALID)
return _PAGE_CACHE_MODE_UC_MINUS;
return _PAGE_CACHE_MODE_WB;
*/
#include <linux/acpi.h>
+#include <linux/efi.h>
#include <linux/pci.h>
#include <linux/init.h>
#include <linux/bitmap.h>
return mcfg_res.flags;
}
+static bool is_efi_mmio(u64 start, u64 end, enum e820_type not_used)
+{
+#ifdef CONFIG_EFI
+ efi_memory_desc_t *md;
+ u64 size, mmio_start, mmio_end;
+
+ for_each_efi_memory_desc(md) {
+ if (md->type == EFI_MEMORY_MAPPED_IO) {
+ size = md->num_pages << EFI_PAGE_SHIFT;
+ mmio_start = md->phys_addr;
+ mmio_end = mmio_start + size;
+
+ /*
+ * N.B. Caller supplies (start, start + size),
+ * so to match, mmio_end is the first address
+ * *past* the EFI_MEMORY_MAPPED_IO area.
+ */
+ if (mmio_start <= start && end <= mmio_end)
+ return true;
+ }
+ }
+#endif
+
+ return false;
+}
+
typedef bool (*check_reserved_t)(u64 start, u64 end, enum e820_type type);
static bool __ref is_mmconf_reserved(check_reserved_t is_reserved,
struct pci_mmcfg_region *cfg,
- struct device *dev, int with_e820)
+ struct device *dev, const char *method)
{
u64 addr = cfg->res.start;
u64 size = resource_size(&cfg->res);
u64 old_size = size;
int num_buses;
- char *method = with_e820 ? "E820" : "ACPI motherboard resources";
while (!is_reserved(addr, addr + size, E820_TYPE_RESERVED)) {
size >>= 1;
return false;
if (dev)
- dev_info(dev, "MMCONFIG at %pR reserved in %s\n",
+ dev_info(dev, "MMCONFIG at %pR reserved as %s\n",
&cfg->res, method);
else
- pr_info(PREFIX "MMCONFIG at %pR reserved in %s\n",
+ pr_info(PREFIX "MMCONFIG at %pR reserved as %s\n",
&cfg->res, method);
if (old_size != size) {
pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int early)
{
if (!early && !acpi_disabled) {
- if (is_mmconf_reserved(is_acpi_reserved, cfg, dev, 0))
+ if (is_mmconf_reserved(is_acpi_reserved, cfg, dev,
+ "ACPI motherboard resource"))
return true;
if (dev)
"MMCONFIG at %pR not reserved in "
"ACPI motherboard resources\n",
&cfg->res);
+
+ if (is_mmconf_reserved(is_efi_mmio, cfg, dev,
+ "EfiMemoryMappedIO"))
+ return true;
}
/*
/* Don't try to do this check unless configuration
type 1 is available. how about type 2 ?*/
if (raw_pci_ops)
- return is_mmconf_reserved(e820__mapped_all, cfg, dev, 1);
+ return is_mmconf_reserved(e820__mapped_all, cfg, dev,
+ "E820 entry");
return false;
}
#include <asm/elf.h>
-Elf32_Half elf_core_extra_phdrs(void)
+Elf32_Half elf_core_extra_phdrs(struct coredump_params *cprm)
{
return vsyscall_ehdr ? (((struct elfhdr *)vsyscall_ehdr)->e_phnum) : 0;
}
return 1;
}
-size_t elf_core_extra_data_size(void)
+size_t elf_core_extra_data_size(struct coredump_params *cprm)
{
if ( vsyscall_ehdr ) {
const struct elfhdr *const ehdrp =
return (pfn / P2M_PER_PAGE) % P2M_MID_PER_PAGE;
}
-static inline unsigned p2m_index(unsigned long pfn)
-{
- return pfn % P2M_PER_PAGE;
-}
-
static void p2m_top_mfn_init(unsigned long *top)
{
unsigned i;
unsigned long ra; /* kernel's a0: return address and window call size */
unsigned long sp; /* kernel's a1: stack pointer */
- /* struct xtensa_cpuinfo info; */
-
- unsigned long bad_vaddr; /* last user fault */
- unsigned long bad_uaddr; /* last kernel fault accessing user space */
- unsigned long error_code;
#ifdef CONFIG_HAVE_HW_BREAKPOINT
struct perf_event *ptrace_bp[XCHAL_NUM_IBREAK];
struct perf_event *ptrace_wp[XCHAL_NUM_DBREAK];
{ \
ra: 0, \
sp: sizeof(init_stack) + (long) &init_stack, \
- /*info: {0}, */ \
- bad_vaddr: 0, \
- bad_uaddr: 0, \
- error_code: 0, \
}
__die_if_kernel("Unhandled unaligned exception in kernel",
regs, SIGKILL);
- current->thread.bad_vaddr = regs->excvaddr;
- current->thread.error_code = -3;
pr_info_ratelimited("Unaligned memory access to %08lx in '%s' "
"(pid = %d, pc = %#010lx)\n",
regs->excvaddr, current->comm,
bad_area:
mmap_read_unlock(mm);
if (user_mode(regs)) {
- current->thread.bad_vaddr = address;
- current->thread.error_code = is_write;
force_sig_fault(SIGSEGV, code, (void *) address);
return;
}
/* Send a sigbus, regardless of whether we were in kernel
* or user mode.
*/
- current->thread.bad_vaddr = address;
force_sig_fault(SIGBUS, BUS_ADRERR, (void *) address);
/* Kernel mode? Handle exceptions or die */
if ((entry = search_exception_tables(regs->pc)) != NULL) {
pr_debug("%s: Exception at pc=%#010lx (%lx)\n",
current->comm, regs->pc, entry->fixup);
- current->thread.bad_uaddr = address;
regs->pc = entry->fixup;
return;
}
bool "Enable the block layer" if EXPERT
default y
select SBITMAP
- select SRCU
help
Provide block layer support for the kernel.
}
EXPORT_SYMBOL(__bio_advance);
+void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter,
+ struct bio *src, struct bvec_iter *src_iter)
+{
+ while (src_iter->bi_size && dst_iter->bi_size) {
+ struct bio_vec src_bv = bio_iter_iovec(src, *src_iter);
+ struct bio_vec dst_bv = bio_iter_iovec(dst, *dst_iter);
+ unsigned int bytes = min(src_bv.bv_len, dst_bv.bv_len);
+ void *src_buf = bvec_kmap_local(&src_bv);
+ void *dst_buf = bvec_kmap_local(&dst_bv);
+
+ memcpy(dst_buf, src_buf, bytes);
+
+ kunmap_local(dst_buf);
+ kunmap_local(src_buf);
+
+ bio_advance_iter_single(src, src_iter, bytes);
+ bio_advance_iter_single(dst, dst_iter, bytes);
+ }
+}
+EXPORT_SYMBOL(bio_copy_data_iter);
+
/**
* bio_copy_data - copy contents of data buffers from one bio to another
* @src: source bio
struct bvec_iter src_iter = src->bi_iter;
struct bvec_iter dst_iter = dst->bi_iter;
- while (src_iter.bi_size && dst_iter.bi_size) {
- struct bio_vec src_bv = bio_iter_iovec(src, src_iter);
- struct bio_vec dst_bv = bio_iter_iovec(dst, dst_iter);
- unsigned int bytes = min(src_bv.bv_len, dst_bv.bv_len);
- void *src_buf = bvec_kmap_local(&src_bv);
- void *dst_buf = bvec_kmap_local(&dst_bv);
-
- memcpy(dst_buf, src_buf, bytes);
-
- kunmap_local(dst_buf);
- kunmap_local(src_buf);
-
- bio_advance_iter_single(src, &src_iter, bytes);
- bio_advance_iter_single(dst, &dst_iter, bytes);
- }
+ bio_copy_data_iter(dst, &dst_iter, src, &src_iter);
}
EXPORT_SYMBOL(bio_copy_data);
*
* Decrements the refcount of the request_queue and free it when the refcount
* reaches 0.
- *
- * Context: Can sleep.
*/
void blk_put_queue(struct request_queue *q)
{
- might_sleep();
if (refcount_dec_and_test(&q->refs))
blk_free_queue(q);
}
*segs = nsegs;
return NULL;
split:
+ /*
+ * We can't sanely support splitting for a REQ_NOWAIT bio. End it
+ * with EAGAIN if splitting is required and return an error pointer.
+ */
+ if (bio->bi_opf & REQ_NOWAIT) {
+ bio->bi_status = BLK_STS_AGAIN;
+ bio_endio(bio);
+ return ERR_PTR(-EAGAIN);
+ }
+
*segs = nsegs;
/*
default:
split = bio_split_rw(bio, lim, nr_segs, bs,
get_max_io_size(bio, lim) << SECTOR_SHIFT);
+ if (IS_ERR(split))
+ return NULL;
break;
}
if (split) {
- /* there isn't chance to merge the splitted bio */
+ /* there isn't chance to merge the split bio */
split->bi_opf |= REQ_NOMERGE;
blkcg_bio_issue_init(split);
blk_status_t ret;
bio = blk_queue_bounce(bio, q);
- if (bio_may_exceed_limits(bio, &q->limits))
+ if (bio_may_exceed_limits(bio, &q->limits)) {
bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
+ if (!bio)
+ return;
+ }
if (!bio_integrity_prep(bio))
return;
.dev_uevent = block_uevent,
};
+static char *block_devnode(struct device *dev, umode_t *mode,
+ kuid_t *uid, kgid_t *gid)
+{
+ struct gendisk *disk = dev_to_disk(dev);
+
+ if (disk->fops->devnode)
+ return disk->fops->devnode(disk, mode);
+ return NULL;
+}
+
const struct device_type disk_type = {
.name = "disk",
.groups = disk_attr_groups,
.release = disk_release,
+ .devnode = block_devnode,
};
#ifdef CONFIG_PROC_FS
}
#define FIND_CHILD_MIN_SCORE 1
-#define FIND_CHILD_MAX_SCORE 2
+#define FIND_CHILD_MID_SCORE 2
+#define FIND_CHILD_MAX_SCORE 3
static int match_any(struct acpi_device *adev, void *not_used)
{
return -ENODEV;
status = acpi_evaluate_integer(adev->handle, "_STA", NULL, &sta);
- if (status == AE_NOT_FOUND)
+ if (status == AE_NOT_FOUND) {
+ /*
+ * Special case: backlight device objects without _STA are
+ * preferred to other objects with the same _ADR value, because
+ * it is more likely that they are actually useful.
+ */
+ if (adev->pnp.type.backlight)
+ return FIND_CHILD_MID_SCORE;
+
return FIND_CHILD_MIN_SCORE;
+ }
if (ACPI_FAILURE(status) || !(sta & ACPI_STA_DEVICE_ENABLED))
return -ENODEV;
},
},
{
+ .ident = "Asus ExpertBook B2402CBA",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_BOARD_NAME, "B2402CBA"),
+ },
+ },
+ {
.ident = "Asus ExpertBook B2502",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
* Some devices don't reliably have _HIDs & _CIDs, so add
* synthetic HIDs to make sure drivers can find them.
*/
- if (acpi_is_video_device(handle))
+ if (acpi_is_video_device(handle)) {
acpi_add_id(pnp, ACPI_VIDEO_HID);
- else if (acpi_bay_match(handle))
+ pnp->type.backlight = 1;
+ break;
+ }
+ if (acpi_bay_match(handle))
acpi_add_id(pnp, ACPI_BAY_HID);
else if (acpi_dock_match(handle))
acpi_add_id(pnp, ACPI_DOCK_HID);
acpi_backlight_cmdline = acpi_backlight_video;
if (!strcmp("native", acpi_video_backlight_string))
acpi_backlight_cmdline = acpi_backlight_native;
+ if (!strcmp("nvidia_wmi_ec", acpi_video_backlight_string))
+ acpi_backlight_cmdline = acpi_backlight_nvidia_wmi_ec;
+ if (!strcmp("apple_gmux", acpi_video_backlight_string))
+ acpi_backlight_cmdline = acpi_backlight_apple_gmux;
if (!strcmp("none", acpi_video_backlight_string))
acpi_backlight_cmdline = acpi_backlight_none;
}
config PATA_CS5535
tristate "CS5535 PATA support (Experimental)"
depends on PCI && (X86_32 || (X86_64 && COMPILE_TEST))
+ depends on !UML
help
This option enables support for the NatSemi/AMD CS5535
companion chip used with the Geode processor family.
The default value is 4096 kilobytes. Only change this if you know
what you are doing.
+config CDROM_PKTCDVD
+ tristate "Packet writing on CD/DVD media (DEPRECATED)"
+ depends on !UML
+ depends on SCSI
+ select CDROM
+ help
+ Note: This driver is deprecated and will be removed from the
+ kernel in the near future!
+
+ If you have a CDROM/DVD drive that supports packet writing, say
+ Y to include support. It should work with any MMC/Mt Fuji
+ compliant ATAPI or SCSI drive, which is just about any newer
+ DVD/CD writer.
+
+ Currently only writing to CD-RW, DVD-RW, DVD+RW and DVDRAM discs
+ is possible.
+ DVD-RW disks must be in restricted overwrite mode.
+
+ See the file <file:Documentation/cdrom/packet-writing.rst>
+ for further information on the use of this driver.
+
+ To compile this driver as a module, choose M here: the
+ module will be called pktcdvd.
+
+config CDROM_PKTCDVD_BUFFERS
+ int "Free buffers for data gathering"
+ depends on CDROM_PKTCDVD
+ default "8"
+ help
+ This controls the maximum number of active concurrent packets. More
+ concurrent packets can increase write performance, but also require
+ more memory. Each concurrent packet will require approximately 64Kb
+ of non-swappable kernel memory, memory which will be allocated when
+ a disc is opened for writing.
+
+config CDROM_PKTCDVD_WCACHE
+ bool "Enable write caching"
+ depends on CDROM_PKTCDVD
+ help
+ If enabled, write caching will be set for the CD-R/W device. For now
+ this option is dangerous unless the CD-RW media is known good, as we
+ don't do deferred write error handling yet.
+
config ATA_OVER_ETH
tristate "ATA over Ethernet support"
depends on NET
obj-$(CONFIG_N64CART) += n64cart.o
obj-$(CONFIG_BLK_DEV_RAM) += brd.o
obj-$(CONFIG_BLK_DEV_LOOP) += loop.o
+obj-$(CONFIG_CDROM_PKTCDVD) += pktcdvd.o
obj-$(CONFIG_SUNVDC) += sunvdc.o
obj-$(CONFIG_BLK_DEV_NBD) += nbd.o
struct drbd_device *device = bio->bi_bdev->bd_disk->private_data;
bio = bio_split_to_limits(bio);
+ if (!bio)
+ return;
/*
* what we "blindly" assume:
--- /dev/null
+/*
+ * Copyright (C) 2000 Jens Axboe <axboe@suse.de>
+ * Copyright (C) 2001-2004 Peter Osterlund <petero2@telia.com>
+ * Copyright (C) 2006 Thomas Maier <balagi@justmail.de>
+ *
+ * May be copied or modified under the terms of the GNU General Public
+ * License. See linux/COPYING for more information.
+ *
+ * Packet writing layer for ATAPI and SCSI CD-RW, DVD+RW, DVD-RW and
+ * DVD-RAM devices.
+ *
+ * Theory of operation:
+ *
+ * At the lowest level, there is the standard driver for the CD/DVD device,
+ * such as drivers/scsi/sr.c. This driver can handle read and write requests,
+ * but it doesn't know anything about the special restrictions that apply to
+ * packet writing. One restriction is that write requests must be aligned to
+ * packet boundaries on the physical media, and the size of a write request
+ * must be equal to the packet size. Another restriction is that a
+ * GPCMD_FLUSH_CACHE command has to be issued to the drive before a read
+ * command, if the previous command was a write.
+ *
+ * The purpose of the packet writing driver is to hide these restrictions from
+ * higher layers, such as file systems, and present a block device that can be
+ * randomly read and written using 2kB-sized blocks.
+ *
+ * The lowest layer in the packet writing driver is the packet I/O scheduler.
+ * Its data is defined by the struct packet_iosched and includes two bio
+ * queues with pending read and write requests. These queues are processed
+ * by the pkt_iosched_process_queue() function. The write requests in this
+ * queue are already properly aligned and sized. This layer is responsible for
+ * issuing the flush cache commands and scheduling the I/O in a good order.
+ *
+ * The next layer transforms unaligned write requests to aligned writes. This
+ * transformation requires reading missing pieces of data from the underlying
+ * block device, assembling the pieces to full packets and queuing them to the
+ * packet I/O scheduler.
+ *
+ * At the top layer there is a custom ->submit_bio function that forwards
+ * read requests directly to the iosched queue and puts write requests in the
+ * unaligned write queue. A kernel thread performs the necessary read
+ * gathering to convert the unaligned writes to aligned writes and then feeds
+ * them to the packet I/O scheduler.
+ *
+ *************************************************************************/
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/pktcdvd.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/compat.h>
+#include <linux/kthread.h>
+#include <linux/errno.h>
+#include <linux/spinlock.h>
+#include <linux/file.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/miscdevice.h>
+#include <linux/freezer.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/backing-dev.h>
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_ioctl.h>
+#include <scsi/scsi.h>
+#include <linux/debugfs.h>
+#include <linux/device.h>
+#include <linux/nospec.h>
+#include <linux/uaccess.h>
+
+#define DRIVER_NAME "pktcdvd"
+
+#define pkt_err(pd, fmt, ...) \
+ pr_err("%s: " fmt, pd->name, ##__VA_ARGS__)
+#define pkt_notice(pd, fmt, ...) \
+ pr_notice("%s: " fmt, pd->name, ##__VA_ARGS__)
+#define pkt_info(pd, fmt, ...) \
+ pr_info("%s: " fmt, pd->name, ##__VA_ARGS__)
+
+#define pkt_dbg(level, pd, fmt, ...) \
+do { \
+ if (level == 2 && PACKET_DEBUG >= 2) \
+ pr_notice("%s: %s():" fmt, \
+ pd->name, __func__, ##__VA_ARGS__); \
+ else if (level == 1 && PACKET_DEBUG >= 1) \
+ pr_notice("%s: " fmt, pd->name, ##__VA_ARGS__); \
+} while (0)
+
+#define MAX_SPEED 0xffff
+
+static DEFINE_MUTEX(pktcdvd_mutex);
+static struct pktcdvd_device *pkt_devs[MAX_WRITERS];
+static struct proc_dir_entry *pkt_proc;
+static int pktdev_major;
+static int write_congestion_on = PKT_WRITE_CONGESTION_ON;
+static int write_congestion_off = PKT_WRITE_CONGESTION_OFF;
+static struct mutex ctl_mutex; /* Serialize open/close/setup/teardown */
+static mempool_t psd_pool;
+static struct bio_set pkt_bio_set;
+
+static struct class *class_pktcdvd = NULL; /* /sys/class/pktcdvd */
+static struct dentry *pkt_debugfs_root = NULL; /* /sys/kernel/debug/pktcdvd */
+
+/* forward declaration */
+static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev);
+static int pkt_remove_dev(dev_t pkt_dev);
+static int pkt_seq_show(struct seq_file *m, void *p);
+
+static sector_t get_zone(sector_t sector, struct pktcdvd_device *pd)
+{
+ return (sector + pd->offset) & ~(sector_t)(pd->settings.size - 1);
+}
+
+/**********************************************************
+ * sysfs interface for pktcdvd
+ * by (C) 2006 Thomas Maier <balagi@justmail.de>
+
+ /sys/class/pktcdvd/pktcdvd[0-7]/
+ stat/reset
+ stat/packets_started
+ stat/packets_finished
+ stat/kb_written
+ stat/kb_read
+ stat/kb_read_gather
+ write_queue/size
+ write_queue/congestion_off
+ write_queue/congestion_on
+ **********************************************************/
+
+static ssize_t packets_started_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+
+ return sysfs_emit(buf, "%lu\n", pd->stats.pkt_started);
+}
+static DEVICE_ATTR_RO(packets_started);
+
+static ssize_t packets_finished_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+
+ return sysfs_emit(buf, "%lu\n", pd->stats.pkt_ended);
+}
+static DEVICE_ATTR_RO(packets_finished);
+
+static ssize_t kb_written_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+
+ return sysfs_emit(buf, "%lu\n", pd->stats.secs_w >> 1);
+}
+static DEVICE_ATTR_RO(kb_written);
+
+static ssize_t kb_read_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+
+ return sysfs_emit(buf, "%lu\n", pd->stats.secs_r >> 1);
+}
+static DEVICE_ATTR_RO(kb_read);
+
+static ssize_t kb_read_gather_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+
+ return sysfs_emit(buf, "%lu\n", pd->stats.secs_rg >> 1);
+}
+static DEVICE_ATTR_RO(kb_read_gather);
+
+static ssize_t reset_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t len)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+
+ if (len > 0) {
+ pd->stats.pkt_started = 0;
+ pd->stats.pkt_ended = 0;
+ pd->stats.secs_w = 0;
+ pd->stats.secs_rg = 0;
+ pd->stats.secs_r = 0;
+ }
+ return len;
+}
+static DEVICE_ATTR_WO(reset);
+
+static struct attribute *pkt_stat_attrs[] = {
+ &dev_attr_packets_finished.attr,
+ &dev_attr_packets_started.attr,
+ &dev_attr_kb_read.attr,
+ &dev_attr_kb_written.attr,
+ &dev_attr_kb_read_gather.attr,
+ &dev_attr_reset.attr,
+ NULL,
+};
+
+static const struct attribute_group pkt_stat_group = {
+ .name = "stat",
+ .attrs = pkt_stat_attrs,
+};
+
+static ssize_t size_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+ int n;
+
+ spin_lock(&pd->lock);
+ n = sysfs_emit(buf, "%d\n", pd->bio_queue_size);
+ spin_unlock(&pd->lock);
+ return n;
+}
+static DEVICE_ATTR_RO(size);
+
+static void init_write_congestion_marks(int* lo, int* hi)
+{
+ if (*hi > 0) {
+ *hi = max(*hi, 500);
+ *hi = min(*hi, 1000000);
+ if (*lo <= 0)
+ *lo = *hi - 100;
+ else {
+ *lo = min(*lo, *hi - 100);
+ *lo = max(*lo, 100);
+ }
+ } else {
+ *hi = -1;
+ *lo = -1;
+ }
+}
+
+static ssize_t congestion_off_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+ int n;
+
+ spin_lock(&pd->lock);
+ n = sysfs_emit(buf, "%d\n", pd->write_congestion_off);
+ spin_unlock(&pd->lock);
+ return n;
+}
+
+static ssize_t congestion_off_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t len)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+ int val;
+
+ if (sscanf(buf, "%d", &val) == 1) {
+ spin_lock(&pd->lock);
+ pd->write_congestion_off = val;
+ init_write_congestion_marks(&pd->write_congestion_off,
+ &pd->write_congestion_on);
+ spin_unlock(&pd->lock);
+ }
+ return len;
+}
+static DEVICE_ATTR_RW(congestion_off);
+
+static ssize_t congestion_on_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+ int n;
+
+ spin_lock(&pd->lock);
+ n = sysfs_emit(buf, "%d\n", pd->write_congestion_on);
+ spin_unlock(&pd->lock);
+ return n;
+}
+
+static ssize_t congestion_on_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t len)
+{
+ struct pktcdvd_device *pd = dev_get_drvdata(dev);
+ int val;
+
+ if (sscanf(buf, "%d", &val) == 1) {
+ spin_lock(&pd->lock);
+ pd->write_congestion_on = val;
+ init_write_congestion_marks(&pd->write_congestion_off,
+ &pd->write_congestion_on);
+ spin_unlock(&pd->lock);
+ }
+ return len;
+}
+static DEVICE_ATTR_RW(congestion_on);
+
+static struct attribute *pkt_wq_attrs[] = {
+ &dev_attr_congestion_on.attr,
+ &dev_attr_congestion_off.attr,
+ &dev_attr_size.attr,
+ NULL,
+};
+
+static const struct attribute_group pkt_wq_group = {
+ .name = "write_queue",
+ .attrs = pkt_wq_attrs,
+};
+
+static const struct attribute_group *pkt_groups[] = {
+ &pkt_stat_group,
+ &pkt_wq_group,
+ NULL,
+};
+
+static void pkt_sysfs_dev_new(struct pktcdvd_device *pd)
+{
+ if (class_pktcdvd) {
+ pd->dev = device_create_with_groups(class_pktcdvd, NULL,
+ MKDEV(0, 0), pd, pkt_groups,
+ "%s", pd->name);
+ if (IS_ERR(pd->dev))
+ pd->dev = NULL;
+ }
+}
+
+static void pkt_sysfs_dev_remove(struct pktcdvd_device *pd)
+{
+ if (class_pktcdvd)
+ device_unregister(pd->dev);
+}
+
+
+/********************************************************************
+ /sys/class/pktcdvd/
+ add map block device
+ remove unmap packet dev
+ device_map show mappings
+ *******************************************************************/
+
+static void class_pktcdvd_release(struct class *cls)
+{
+ kfree(cls);
+}
+
+static ssize_t device_map_show(struct class *c, struct class_attribute *attr,
+ char *data)
+{
+ int n = 0;
+ int idx;
+ mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+ for (idx = 0; idx < MAX_WRITERS; idx++) {
+ struct pktcdvd_device *pd = pkt_devs[idx];
+ if (!pd)
+ continue;
+ n += sprintf(data+n, "%s %u:%u %u:%u\n",
+ pd->name,
+ MAJOR(pd->pkt_dev), MINOR(pd->pkt_dev),
+ MAJOR(pd->bdev->bd_dev),
+ MINOR(pd->bdev->bd_dev));
+ }
+ mutex_unlock(&ctl_mutex);
+ return n;
+}
+static CLASS_ATTR_RO(device_map);
+
+static ssize_t add_store(struct class *c, struct class_attribute *attr,
+ const char *buf, size_t count)
+{
+ unsigned int major, minor;
+
+ if (sscanf(buf, "%u:%u", &major, &minor) == 2) {
+ /* pkt_setup_dev() expects caller to hold reference to self */
+ if (!try_module_get(THIS_MODULE))
+ return -ENODEV;
+
+ pkt_setup_dev(MKDEV(major, minor), NULL);
+
+ module_put(THIS_MODULE);
+
+ return count;
+ }
+
+ return -EINVAL;
+}
+static CLASS_ATTR_WO(add);
+
+static ssize_t remove_store(struct class *c, struct class_attribute *attr,
+ const char *buf, size_t count)
+{
+ unsigned int major, minor;
+ if (sscanf(buf, "%u:%u", &major, &minor) == 2) {
+ pkt_remove_dev(MKDEV(major, minor));
+ return count;
+ }
+ return -EINVAL;
+}
+static CLASS_ATTR_WO(remove);
+
+static struct attribute *class_pktcdvd_attrs[] = {
+ &class_attr_add.attr,
+ &class_attr_remove.attr,
+ &class_attr_device_map.attr,
+ NULL,
+};
+ATTRIBUTE_GROUPS(class_pktcdvd);
+
+static int pkt_sysfs_init(void)
+{
+ int ret = 0;
+
+ /*
+ * create control files in sysfs
+ * /sys/class/pktcdvd/...
+ */
+ class_pktcdvd = kzalloc(sizeof(*class_pktcdvd), GFP_KERNEL);
+ if (!class_pktcdvd)
+ return -ENOMEM;
+ class_pktcdvd->name = DRIVER_NAME;
+ class_pktcdvd->owner = THIS_MODULE;
+ class_pktcdvd->class_release = class_pktcdvd_release;
+ class_pktcdvd->class_groups = class_pktcdvd_groups;
+ ret = class_register(class_pktcdvd);
+ if (ret) {
+ kfree(class_pktcdvd);
+ class_pktcdvd = NULL;
+ pr_err("failed to create class pktcdvd\n");
+ return ret;
+ }
+ return 0;
+}
+
+static void pkt_sysfs_cleanup(void)
+{
+ if (class_pktcdvd)
+ class_destroy(class_pktcdvd);
+ class_pktcdvd = NULL;
+}
+
+/********************************************************************
+ entries in debugfs
+
+ /sys/kernel/debug/pktcdvd[0-7]/
+ info
+
+ *******************************************************************/
+
+static int pkt_debugfs_seq_show(struct seq_file *m, void *p)
+{
+ return pkt_seq_show(m, p);
+}
+
+static int pkt_debugfs_fops_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, pkt_debugfs_seq_show, inode->i_private);
+}
+
+static const struct file_operations debug_fops = {
+ .open = pkt_debugfs_fops_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+ .owner = THIS_MODULE,
+};
+
+static void pkt_debugfs_dev_new(struct pktcdvd_device *pd)
+{
+ if (!pkt_debugfs_root)
+ return;
+ pd->dfs_d_root = debugfs_create_dir(pd->name, pkt_debugfs_root);
+ if (!pd->dfs_d_root)
+ return;
+
+ pd->dfs_f_info = debugfs_create_file("info", 0444,
+ pd->dfs_d_root, pd, &debug_fops);
+}
+
+static void pkt_debugfs_dev_remove(struct pktcdvd_device *pd)
+{
+ if (!pkt_debugfs_root)
+ return;
+ debugfs_remove(pd->dfs_f_info);
+ debugfs_remove(pd->dfs_d_root);
+ pd->dfs_f_info = NULL;
+ pd->dfs_d_root = NULL;
+}
+
+static void pkt_debugfs_init(void)
+{
+ pkt_debugfs_root = debugfs_create_dir(DRIVER_NAME, NULL);
+}
+
+static void pkt_debugfs_cleanup(void)
+{
+ debugfs_remove(pkt_debugfs_root);
+ pkt_debugfs_root = NULL;
+}
+
+/* ----------------------------------------------------------*/
+
+
+static void pkt_bio_finished(struct pktcdvd_device *pd)
+{
+ BUG_ON(atomic_read(&pd->cdrw.pending_bios) <= 0);
+ if (atomic_dec_and_test(&pd->cdrw.pending_bios)) {
+ pkt_dbg(2, pd, "queue empty\n");
+ atomic_set(&pd->iosched.attention, 1);
+ wake_up(&pd->wqueue);
+ }
+}
+
+/*
+ * Allocate a packet_data struct
+ */
+static struct packet_data *pkt_alloc_packet_data(int frames)
+{
+ int i;
+ struct packet_data *pkt;
+
+ pkt = kzalloc(sizeof(struct packet_data), GFP_KERNEL);
+ if (!pkt)
+ goto no_pkt;
+
+ pkt->frames = frames;
+ pkt->w_bio = bio_kmalloc(frames, GFP_KERNEL);
+ if (!pkt->w_bio)
+ goto no_bio;
+
+ for (i = 0; i < frames / FRAMES_PER_PAGE; i++) {
+ pkt->pages[i] = alloc_page(GFP_KERNEL|__GFP_ZERO);
+ if (!pkt->pages[i])
+ goto no_page;
+ }
+
+ spin_lock_init(&pkt->lock);
+ bio_list_init(&pkt->orig_bios);
+
+ for (i = 0; i < frames; i++) {
+ pkt->r_bios[i] = bio_kmalloc(1, GFP_KERNEL);
+ if (!pkt->r_bios[i])
+ goto no_rd_bio;
+ }
+
+ return pkt;
+
+no_rd_bio:
+ for (i = 0; i < frames; i++)
+ kfree(pkt->r_bios[i]);
+no_page:
+ for (i = 0; i < frames / FRAMES_PER_PAGE; i++)
+ if (pkt->pages[i])
+ __free_page(pkt->pages[i]);
+ kfree(pkt->w_bio);
+no_bio:
+ kfree(pkt);
+no_pkt:
+ return NULL;
+}
+
+/*
+ * Free a packet_data struct
+ */
+static void pkt_free_packet_data(struct packet_data *pkt)
+{
+ int i;
+
+ for (i = 0; i < pkt->frames; i++)
+ kfree(pkt->r_bios[i]);
+ for (i = 0; i < pkt->frames / FRAMES_PER_PAGE; i++)
+ __free_page(pkt->pages[i]);
+ kfree(pkt->w_bio);
+ kfree(pkt);
+}
+
+static void pkt_shrink_pktlist(struct pktcdvd_device *pd)
+{
+ struct packet_data *pkt, *next;
+
+ BUG_ON(!list_empty(&pd->cdrw.pkt_active_list));
+
+ list_for_each_entry_safe(pkt, next, &pd->cdrw.pkt_free_list, list) {
+ pkt_free_packet_data(pkt);
+ }
+ INIT_LIST_HEAD(&pd->cdrw.pkt_free_list);
+}
+
+static int pkt_grow_pktlist(struct pktcdvd_device *pd, int nr_packets)
+{
+ struct packet_data *pkt;
+
+ BUG_ON(!list_empty(&pd->cdrw.pkt_free_list));
+
+ while (nr_packets > 0) {
+ pkt = pkt_alloc_packet_data(pd->settings.size >> 2);
+ if (!pkt) {
+ pkt_shrink_pktlist(pd);
+ return 0;
+ }
+ pkt->id = nr_packets;
+ pkt->pd = pd;
+ list_add(&pkt->list, &pd->cdrw.pkt_free_list);
+ nr_packets--;
+ }
+ return 1;
+}
+
+static inline struct pkt_rb_node *pkt_rbtree_next(struct pkt_rb_node *node)
+{
+ struct rb_node *n = rb_next(&node->rb_node);
+ if (!n)
+ return NULL;
+ return rb_entry(n, struct pkt_rb_node, rb_node);
+}
+
+static void pkt_rbtree_erase(struct pktcdvd_device *pd, struct pkt_rb_node *node)
+{
+ rb_erase(&node->rb_node, &pd->bio_queue);
+ mempool_free(node, &pd->rb_pool);
+ pd->bio_queue_size--;
+ BUG_ON(pd->bio_queue_size < 0);
+}
+
+/*
+ * Find the first node in the pd->bio_queue rb tree with a starting sector >= s.
+ */
+static struct pkt_rb_node *pkt_rbtree_find(struct pktcdvd_device *pd, sector_t s)
+{
+ struct rb_node *n = pd->bio_queue.rb_node;
+ struct rb_node *next;
+ struct pkt_rb_node *tmp;
+
+ if (!n) {
+ BUG_ON(pd->bio_queue_size > 0);
+ return NULL;
+ }
+
+ for (;;) {
+ tmp = rb_entry(n, struct pkt_rb_node, rb_node);
+ if (s <= tmp->bio->bi_iter.bi_sector)
+ next = n->rb_left;
+ else
+ next = n->rb_right;
+ if (!next)
+ break;
+ n = next;
+ }
+
+ if (s > tmp->bio->bi_iter.bi_sector) {
+ tmp = pkt_rbtree_next(tmp);
+ if (!tmp)
+ return NULL;
+ }
+ BUG_ON(s > tmp->bio->bi_iter.bi_sector);
+ return tmp;
+}
+
+/*
+ * Insert a node into the pd->bio_queue rb tree.
+ */
+static void pkt_rbtree_insert(struct pktcdvd_device *pd, struct pkt_rb_node *node)
+{
+ struct rb_node **p = &pd->bio_queue.rb_node;
+ struct rb_node *parent = NULL;
+ sector_t s = node->bio->bi_iter.bi_sector;
+ struct pkt_rb_node *tmp;
+
+ while (*p) {
+ parent = *p;
+ tmp = rb_entry(parent, struct pkt_rb_node, rb_node);
+ if (s < tmp->bio->bi_iter.bi_sector)
+ p = &(*p)->rb_left;
+ else
+ p = &(*p)->rb_right;
+ }
+ rb_link_node(&node->rb_node, parent, p);
+ rb_insert_color(&node->rb_node, &pd->bio_queue);
+ pd->bio_queue_size++;
+}
+
+/*
+ * Send a packet_command to the underlying block device and
+ * wait for completion.
+ */
+static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *cgc)
+{
+ struct request_queue *q = bdev_get_queue(pd->bdev);
+ struct scsi_cmnd *scmd;
+ struct request *rq;
+ int ret = 0;
+
+ rq = scsi_alloc_request(q, (cgc->data_direction == CGC_DATA_WRITE) ?
+ REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
+ if (IS_ERR(rq))
+ return PTR_ERR(rq);
+ scmd = blk_mq_rq_to_pdu(rq);
+
+ if (cgc->buflen) {
+ ret = blk_rq_map_kern(q, rq, cgc->buffer, cgc->buflen,
+ GFP_NOIO);
+ if (ret)
+ goto out;
+ }
+
+ scmd->cmd_len = COMMAND_SIZE(cgc->cmd[0]);
+ memcpy(scmd->cmnd, cgc->cmd, CDROM_PACKET_SIZE);
+
+ rq->timeout = 60*HZ;
+ if (cgc->quiet)
+ rq->rq_flags |= RQF_QUIET;
+
+ blk_execute_rq(rq, false);
+ if (scmd->result)
+ ret = -EIO;
+out:
+ blk_mq_free_request(rq);
+ return ret;
+}
+
+static const char *sense_key_string(__u8 index)
+{
+ static const char * const info[] = {
+ "No sense", "Recovered error", "Not ready",
+ "Medium error", "Hardware error", "Illegal request",
+ "Unit attention", "Data protect", "Blank check",
+ };
+
+ return index < ARRAY_SIZE(info) ? info[index] : "INVALID";
+}
+
+/*
+ * A generic sense dump / resolve mechanism should be implemented across
+ * all ATAPI + SCSI devices.
+ */
+static void pkt_dump_sense(struct pktcdvd_device *pd,
+ struct packet_command *cgc)
+{
+ struct scsi_sense_hdr *sshdr = cgc->sshdr;
+
+ if (sshdr)
+ pkt_err(pd, "%*ph - sense %02x.%02x.%02x (%s)\n",
+ CDROM_PACKET_SIZE, cgc->cmd,
+ sshdr->sense_key, sshdr->asc, sshdr->ascq,
+ sense_key_string(sshdr->sense_key));
+ else
+ pkt_err(pd, "%*ph - no sense\n", CDROM_PACKET_SIZE, cgc->cmd);
+}
+
+/*
+ * flush the drive cache to media
+ */
+static int pkt_flush_cache(struct pktcdvd_device *pd)
+{
+ struct packet_command cgc;
+
+ init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
+ cgc.cmd[0] = GPCMD_FLUSH_CACHE;
+ cgc.quiet = 1;
+
+ /*
+ * the IMMED bit -- we default to not setting it, although that
+ * would allow a much faster close, this is safer
+ */
+#if 0
+ cgc.cmd[1] = 1 << 1;
+#endif
+ return pkt_generic_packet(pd, &cgc);
+}
+
+/*
+ * speed is given as the normal factor, e.g. 4 for 4x
+ */
+static noinline_for_stack int pkt_set_speed(struct pktcdvd_device *pd,
+ unsigned write_speed, unsigned read_speed)
+{
+ struct packet_command cgc;
+ struct scsi_sense_hdr sshdr;
+ int ret;
+
+ init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
+ cgc.sshdr = &sshdr;
+ cgc.cmd[0] = GPCMD_SET_SPEED;
+ cgc.cmd[2] = (read_speed >> 8) & 0xff;
+ cgc.cmd[3] = read_speed & 0xff;
+ cgc.cmd[4] = (write_speed >> 8) & 0xff;
+ cgc.cmd[5] = write_speed & 0xff;
+
+ ret = pkt_generic_packet(pd, &cgc);
+ if (ret)
+ pkt_dump_sense(pd, &cgc);
+
+ return ret;
+}
+
+/*
+ * Queue a bio for processing by the low-level CD device. Must be called
+ * from process context.
+ */
+static void pkt_queue_bio(struct pktcdvd_device *pd, struct bio *bio)
+{
+ spin_lock(&pd->iosched.lock);
+ if (bio_data_dir(bio) == READ)
+ bio_list_add(&pd->iosched.read_queue, bio);
+ else
+ bio_list_add(&pd->iosched.write_queue, bio);
+ spin_unlock(&pd->iosched.lock);
+
+ atomic_set(&pd->iosched.attention, 1);
+ wake_up(&pd->wqueue);
+}
+
+/*
+ * Process the queued read/write requests. This function handles special
+ * requirements for CDRW drives:
+ * - A cache flush command must be inserted before a read request if the
+ * previous request was a write.
+ * - Switching between reading and writing is slow, so don't do it more often
+ * than necessary.
+ * - Optimize for throughput at the expense of latency. This means that streaming
+ * writes will never be interrupted by a read, but if the drive has to seek
+ * before the next write, switch to reading instead if there are any pending
+ * read requests.
+ * - Set the read speed according to current usage pattern. When only reading
+ * from the device, it's best to use the highest possible read speed, but
+ * when switching often between reading and writing, it's better to have the
+ * same read and write speeds.
+ */
+static void pkt_iosched_process_queue(struct pktcdvd_device *pd)
+{
+
+ if (atomic_read(&pd->iosched.attention) == 0)
+ return;
+ atomic_set(&pd->iosched.attention, 0);
+
+ for (;;) {
+ struct bio *bio;
+ int reads_queued, writes_queued;
+
+ spin_lock(&pd->iosched.lock);
+ reads_queued = !bio_list_empty(&pd->iosched.read_queue);
+ writes_queued = !bio_list_empty(&pd->iosched.write_queue);
+ spin_unlock(&pd->iosched.lock);
+
+ if (!reads_queued && !writes_queued)
+ break;
+
+ if (pd->iosched.writing) {
+ int need_write_seek = 1;
+ spin_lock(&pd->iosched.lock);
+ bio = bio_list_peek(&pd->iosched.write_queue);
+ spin_unlock(&pd->iosched.lock);
+ if (bio && (bio->bi_iter.bi_sector ==
+ pd->iosched.last_write))
+ need_write_seek = 0;
+ if (need_write_seek && reads_queued) {
+ if (atomic_read(&pd->cdrw.pending_bios) > 0) {
+ pkt_dbg(2, pd, "write, waiting\n");
+ break;
+ }
+ pkt_flush_cache(pd);
+ pd->iosched.writing = 0;
+ }
+ } else {
+ if (!reads_queued && writes_queued) {
+ if (atomic_read(&pd->cdrw.pending_bios) > 0) {
+ pkt_dbg(2, pd, "read, waiting\n");
+ break;
+ }
+ pd->iosched.writing = 1;
+ }
+ }
+
+ spin_lock(&pd->iosched.lock);
+ if (pd->iosched.writing)
+ bio = bio_list_pop(&pd->iosched.write_queue);
+ else
+ bio = bio_list_pop(&pd->iosched.read_queue);
+ spin_unlock(&pd->iosched.lock);
+
+ if (!bio)
+ continue;
+
+ if (bio_data_dir(bio) == READ)
+ pd->iosched.successive_reads +=
+ bio->bi_iter.bi_size >> 10;
+ else {
+ pd->iosched.successive_reads = 0;
+ pd->iosched.last_write = bio_end_sector(bio);
+ }
+ if (pd->iosched.successive_reads >= HI_SPEED_SWITCH) {
+ if (pd->read_speed == pd->write_speed) {
+ pd->read_speed = MAX_SPEED;
+ pkt_set_speed(pd, pd->write_speed, pd->read_speed);
+ }
+ } else {
+ if (pd->read_speed != pd->write_speed) {
+ pd->read_speed = pd->write_speed;
+ pkt_set_speed(pd, pd->write_speed, pd->read_speed);
+ }
+ }
+
+ atomic_inc(&pd->cdrw.pending_bios);
+ submit_bio_noacct(bio);
+ }
+}
+
+/*
+ * Special care is needed if the underlying block device has a small
+ * max_phys_segments value.
+ */
+static int pkt_set_segment_merging(struct pktcdvd_device *pd, struct request_queue *q)
+{
+ if ((pd->settings.size << 9) / CD_FRAMESIZE
+ <= queue_max_segments(q)) {
+ /*
+ * The cdrom device can handle one segment/frame
+ */
+ clear_bit(PACKET_MERGE_SEGS, &pd->flags);
+ return 0;
+ } else if ((pd->settings.size << 9) / PAGE_SIZE
+ <= queue_max_segments(q)) {
+ /*
+ * We can handle this case at the expense of some extra memory
+ * copies during write operations
+ */
+ set_bit(PACKET_MERGE_SEGS, &pd->flags);
+ return 0;
+ } else {
+ pkt_err(pd, "cdrom max_phys_segments too small\n");
+ return -EIO;
+ }
+}
+
+static void pkt_end_io_read(struct bio *bio)
+{
+ struct packet_data *pkt = bio->bi_private;
+ struct pktcdvd_device *pd = pkt->pd;
+ BUG_ON(!pd);
+
+ pkt_dbg(2, pd, "bio=%p sec0=%llx sec=%llx err=%d\n",
+ bio, (unsigned long long)pkt->sector,
+ (unsigned long long)bio->bi_iter.bi_sector, bio->bi_status);
+
+ if (bio->bi_status)
+ atomic_inc(&pkt->io_errors);
+ bio_uninit(bio);
+ if (atomic_dec_and_test(&pkt->io_wait)) {
+ atomic_inc(&pkt->run_sm);
+ wake_up(&pd->wqueue);
+ }
+ pkt_bio_finished(pd);
+}
+
+static void pkt_end_io_packet_write(struct bio *bio)
+{
+ struct packet_data *pkt = bio->bi_private;
+ struct pktcdvd_device *pd = pkt->pd;
+ BUG_ON(!pd);
+
+ pkt_dbg(2, pd, "id=%d, err=%d\n", pkt->id, bio->bi_status);
+
+ pd->stats.pkt_ended++;
+
+ bio_uninit(bio);
+ pkt_bio_finished(pd);
+ atomic_dec(&pkt->io_wait);
+ atomic_inc(&pkt->run_sm);
+ wake_up(&pd->wqueue);
+}
+
+/*
+ * Schedule reads for the holes in a packet
+ */
+static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt)
+{
+ int frames_read = 0;
+ struct bio *bio;
+ int f;
+ char written[PACKET_MAX_SIZE];
+
+ BUG_ON(bio_list_empty(&pkt->orig_bios));
+
+ atomic_set(&pkt->io_wait, 0);
+ atomic_set(&pkt->io_errors, 0);
+
+ /*
+ * Figure out which frames we need to read before we can write.
+ */
+ memset(written, 0, sizeof(written));
+ spin_lock(&pkt->lock);
+ bio_list_for_each(bio, &pkt->orig_bios) {
+ int first_frame = (bio->bi_iter.bi_sector - pkt->sector) /
+ (CD_FRAMESIZE >> 9);
+ int num_frames = bio->bi_iter.bi_size / CD_FRAMESIZE;
+ pd->stats.secs_w += num_frames * (CD_FRAMESIZE >> 9);
+ BUG_ON(first_frame < 0);
+ BUG_ON(first_frame + num_frames > pkt->frames);
+ for (f = first_frame; f < first_frame + num_frames; f++)
+ written[f] = 1;
+ }
+ spin_unlock(&pkt->lock);
+
+ if (pkt->cache_valid) {
+ pkt_dbg(2, pd, "zone %llx cached\n",
+ (unsigned long long)pkt->sector);
+ goto out_account;
+ }
+
+ /*
+ * Schedule reads for missing parts of the packet.
+ */
+ for (f = 0; f < pkt->frames; f++) {
+ int p, offset;
+
+ if (written[f])
+ continue;
+
+ bio = pkt->r_bios[f];
+ bio_init(bio, pd->bdev, bio->bi_inline_vecs, 1, REQ_OP_READ);
+ bio->bi_iter.bi_sector = pkt->sector + f * (CD_FRAMESIZE >> 9);
+ bio->bi_end_io = pkt_end_io_read;
+ bio->bi_private = pkt;
+
+ p = (f * CD_FRAMESIZE) / PAGE_SIZE;
+ offset = (f * CD_FRAMESIZE) % PAGE_SIZE;
+ pkt_dbg(2, pd, "Adding frame %d, page:%p offs:%d\n",
+ f, pkt->pages[p], offset);
+ if (!bio_add_page(bio, pkt->pages[p], CD_FRAMESIZE, offset))
+ BUG();
+
+ atomic_inc(&pkt->io_wait);
+ pkt_queue_bio(pd, bio);
+ frames_read++;
+ }
+
+out_account:
+ pkt_dbg(2, pd, "need %d frames for zone %llx\n",
+ frames_read, (unsigned long long)pkt->sector);
+ pd->stats.pkt_started++;
+ pd->stats.secs_rg += frames_read * (CD_FRAMESIZE >> 9);
+}
+
+/*
+ * Find a packet matching zone, or the least recently used packet if
+ * there is no match.
+ */
+static struct packet_data *pkt_get_packet_data(struct pktcdvd_device *pd, int zone)
+{
+ struct packet_data *pkt;
+
+ list_for_each_entry(pkt, &pd->cdrw.pkt_free_list, list) {
+ if (pkt->sector == zone || pkt->list.next == &pd->cdrw.pkt_free_list) {
+ list_del_init(&pkt->list);
+ if (pkt->sector != zone)
+ pkt->cache_valid = 0;
+ return pkt;
+ }
+ }
+ BUG();
+ return NULL;
+}
+
+static void pkt_put_packet_data(struct pktcdvd_device *pd, struct packet_data *pkt)
+{
+ if (pkt->cache_valid) {
+ list_add(&pkt->list, &pd->cdrw.pkt_free_list);
+ } else {
+ list_add_tail(&pkt->list, &pd->cdrw.pkt_free_list);
+ }
+}
+
+static inline void pkt_set_state(struct packet_data *pkt, enum packet_data_state state)
+{
+#if PACKET_DEBUG > 1
+ static const char *state_name[] = {
+ "IDLE", "WAITING", "READ_WAIT", "WRITE_WAIT", "RECOVERY", "FINISHED"
+ };
+ enum packet_data_state old_state = pkt->state;
+ pkt_dbg(2, pd, "pkt %2d : s=%6llx %s -> %s\n",
+ pkt->id, (unsigned long long)pkt->sector,
+ state_name[old_state], state_name[state]);
+#endif
+ pkt->state = state;
+}
+
+/*
+ * Scan the work queue to see if we can start a new packet.
+ * returns non-zero if any work was done.
+ */
+static int pkt_handle_queue(struct pktcdvd_device *pd)
+{
+ struct packet_data *pkt, *p;
+ struct bio *bio = NULL;
+ sector_t zone = 0; /* Suppress gcc warning */
+ struct pkt_rb_node *node, *first_node;
+ struct rb_node *n;
+
+ atomic_set(&pd->scan_queue, 0);
+
+ if (list_empty(&pd->cdrw.pkt_free_list)) {
+ pkt_dbg(2, pd, "no pkt\n");
+ return 0;
+ }
+
+ /*
+ * Try to find a zone we are not already working on.
+ */
+ spin_lock(&pd->lock);
+ first_node = pkt_rbtree_find(pd, pd->current_sector);
+ if (!first_node) {
+ n = rb_first(&pd->bio_queue);
+ if (n)
+ first_node = rb_entry(n, struct pkt_rb_node, rb_node);
+ }
+ node = first_node;
+ while (node) {
+ bio = node->bio;
+ zone = get_zone(bio->bi_iter.bi_sector, pd);
+ list_for_each_entry(p, &pd->cdrw.pkt_active_list, list) {
+ if (p->sector == zone) {
+ bio = NULL;
+ goto try_next_bio;
+ }
+ }
+ break;
+try_next_bio:
+ node = pkt_rbtree_next(node);
+ if (!node) {
+ n = rb_first(&pd->bio_queue);
+ if (n)
+ node = rb_entry(n, struct pkt_rb_node, rb_node);
+ }
+ if (node == first_node)
+ node = NULL;
+ }
+ spin_unlock(&pd->lock);
+ if (!bio) {
+ pkt_dbg(2, pd, "no bio\n");
+ return 0;
+ }
+
+ pkt = pkt_get_packet_data(pd, zone);
+
+ pd->current_sector = zone + pd->settings.size;
+ pkt->sector = zone;
+ BUG_ON(pkt->frames != pd->settings.size >> 2);
+ pkt->write_size = 0;
+
+ /*
+ * Scan work queue for bios in the same zone and link them
+ * to this packet.
+ */
+ spin_lock(&pd->lock);
+ pkt_dbg(2, pd, "looking for zone %llx\n", (unsigned long long)zone);
+ while ((node = pkt_rbtree_find(pd, zone)) != NULL) {
+ bio = node->bio;
+ pkt_dbg(2, pd, "found zone=%llx\n", (unsigned long long)
+ get_zone(bio->bi_iter.bi_sector, pd));
+ if (get_zone(bio->bi_iter.bi_sector, pd) != zone)
+ break;
+ pkt_rbtree_erase(pd, node);
+ spin_lock(&pkt->lock);
+ bio_list_add(&pkt->orig_bios, bio);
+ pkt->write_size += bio->bi_iter.bi_size / CD_FRAMESIZE;
+ spin_unlock(&pkt->lock);
+ }
+ /* check write congestion marks, and if bio_queue_size is
+ * below, wake up any waiters
+ */
+ if (pd->congested &&
+ pd->bio_queue_size <= pd->write_congestion_off) {
+ pd->congested = false;
+ wake_up_var(&pd->congested);
+ }
+ spin_unlock(&pd->lock);
+
+ pkt->sleep_time = max(PACKET_WAIT_TIME, 1);
+ pkt_set_state(pkt, PACKET_WAITING_STATE);
+ atomic_set(&pkt->run_sm, 1);
+
+ spin_lock(&pd->cdrw.active_list_lock);
+ list_add(&pkt->list, &pd->cdrw.pkt_active_list);
+ spin_unlock(&pd->cdrw.active_list_lock);
+
+ return 1;
+}
+
+/**
+ * bio_list_copy_data - copy contents of data buffers from one chain of bios to
+ * another
+ * @src: source bio list
+ * @dst: destination bio list
+ *
+ * Stops when it reaches the end of either the @src list or @dst list - that is,
+ * copies min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of
+ * bios).
+ */
+static void bio_list_copy_data(struct bio *dst, struct bio *src)
+{
+ struct bvec_iter src_iter = src->bi_iter;
+ struct bvec_iter dst_iter = dst->bi_iter;
+
+ while (1) {
+ if (!src_iter.bi_size) {
+ src = src->bi_next;
+ if (!src)
+ break;
+
+ src_iter = src->bi_iter;
+ }
+
+ if (!dst_iter.bi_size) {
+ dst = dst->bi_next;
+ if (!dst)
+ break;
+
+ dst_iter = dst->bi_iter;
+ }
+
+ bio_copy_data_iter(dst, &dst_iter, src, &src_iter);
+ }
+}
+
+/*
+ * Assemble a bio to write one packet and queue the bio for processing
+ * by the underlying block device.
+ */
+static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt)
+{
+ int f;
+
+ bio_init(pkt->w_bio, pd->bdev, pkt->w_bio->bi_inline_vecs, pkt->frames,
+ REQ_OP_WRITE);
+ pkt->w_bio->bi_iter.bi_sector = pkt->sector;
+ pkt->w_bio->bi_end_io = pkt_end_io_packet_write;
+ pkt->w_bio->bi_private = pkt;
+
+ /* XXX: locking? */
+ for (f = 0; f < pkt->frames; f++) {
+ struct page *page = pkt->pages[(f * CD_FRAMESIZE) / PAGE_SIZE];
+ unsigned offset = (f * CD_FRAMESIZE) % PAGE_SIZE;
+
+ if (!bio_add_page(pkt->w_bio, page, CD_FRAMESIZE, offset))
+ BUG();
+ }
+ pkt_dbg(2, pd, "vcnt=%d\n", pkt->w_bio->bi_vcnt);
+
+ /*
+ * Fill-in bvec with data from orig_bios.
+ */
+ spin_lock(&pkt->lock);
+ bio_list_copy_data(pkt->w_bio, pkt->orig_bios.head);
+
+ pkt_set_state(pkt, PACKET_WRITE_WAIT_STATE);
+ spin_unlock(&pkt->lock);
+
+ pkt_dbg(2, pd, "Writing %d frames for zone %llx\n",
+ pkt->write_size, (unsigned long long)pkt->sector);
+
+ if (test_bit(PACKET_MERGE_SEGS, &pd->flags) || (pkt->write_size < pkt->frames))
+ pkt->cache_valid = 1;
+ else
+ pkt->cache_valid = 0;
+
+ /* Start the write request */
+ atomic_set(&pkt->io_wait, 1);
+ pkt_queue_bio(pd, pkt->w_bio);
+}
+
+static void pkt_finish_packet(struct packet_data *pkt, blk_status_t status)
+{
+ struct bio *bio;
+
+ if (status)
+ pkt->cache_valid = 0;
+
+ /* Finish all bios corresponding to this packet */
+ while ((bio = bio_list_pop(&pkt->orig_bios))) {
+ bio->bi_status = status;
+ bio_endio(bio);
+ }
+}
+
+static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data *pkt)
+{
+ pkt_dbg(2, pd, "pkt %d\n", pkt->id);
+
+ for (;;) {
+ switch (pkt->state) {
+ case PACKET_WAITING_STATE:
+ if ((pkt->write_size < pkt->frames) && (pkt->sleep_time > 0))
+ return;
+
+ pkt->sleep_time = 0;
+ pkt_gather_data(pd, pkt);
+ pkt_set_state(pkt, PACKET_READ_WAIT_STATE);
+ break;
+
+ case PACKET_READ_WAIT_STATE:
+ if (atomic_read(&pkt->io_wait) > 0)
+ return;
+
+ if (atomic_read(&pkt->io_errors) > 0) {
+ pkt_set_state(pkt, PACKET_RECOVERY_STATE);
+ } else {
+ pkt_start_write(pd, pkt);
+ }
+ break;
+
+ case PACKET_WRITE_WAIT_STATE:
+ if (atomic_read(&pkt->io_wait) > 0)
+ return;
+
+ if (!pkt->w_bio->bi_status) {
+ pkt_set_state(pkt, PACKET_FINISHED_STATE);
+ } else {
+ pkt_set_state(pkt, PACKET_RECOVERY_STATE);
+ }
+ break;
+
+ case PACKET_RECOVERY_STATE:
+ pkt_dbg(2, pd, "No recovery possible\n");
+ pkt_set_state(pkt, PACKET_FINISHED_STATE);
+ break;
+
+ case PACKET_FINISHED_STATE:
+ pkt_finish_packet(pkt, pkt->w_bio->bi_status);
+ return;
+
+ default:
+ BUG();
+ break;
+ }
+ }
+}
+
+static void pkt_handle_packets(struct pktcdvd_device *pd)
+{
+ struct packet_data *pkt, *next;
+
+ /*
+ * Run state machine for active packets
+ */
+ list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
+ if (atomic_read(&pkt->run_sm) > 0) {
+ atomic_set(&pkt->run_sm, 0);
+ pkt_run_state_machine(pd, pkt);
+ }
+ }
+
+ /*
+ * Move no longer active packets to the free list
+ */
+ spin_lock(&pd->cdrw.active_list_lock);
+ list_for_each_entry_safe(pkt, next, &pd->cdrw.pkt_active_list, list) {
+ if (pkt->state == PACKET_FINISHED_STATE) {
+ list_del(&pkt->list);
+ pkt_put_packet_data(pd, pkt);
+ pkt_set_state(pkt, PACKET_IDLE_STATE);
+ atomic_set(&pd->scan_queue, 1);
+ }
+ }
+ spin_unlock(&pd->cdrw.active_list_lock);
+}
+
+static void pkt_count_states(struct pktcdvd_device *pd, int *states)
+{
+ struct packet_data *pkt;
+ int i;
+
+ for (i = 0; i < PACKET_NUM_STATES; i++)
+ states[i] = 0;
+
+ spin_lock(&pd->cdrw.active_list_lock);
+ list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
+ states[pkt->state]++;
+ }
+ spin_unlock(&pd->cdrw.active_list_lock);
+}
+
+/*
+ * kcdrwd is woken up when writes have been queued for one of our
+ * registered devices
+ */
+static int kcdrwd(void *foobar)
+{
+ struct pktcdvd_device *pd = foobar;
+ struct packet_data *pkt;
+ long min_sleep_time, residue;
+
+ set_user_nice(current, MIN_NICE);
+ set_freezable();
+
+ for (;;) {
+ DECLARE_WAITQUEUE(wait, current);
+
+ /*
+ * Wait until there is something to do
+ */
+ add_wait_queue(&pd->wqueue, &wait);
+ for (;;) {
+ set_current_state(TASK_INTERRUPTIBLE);
+
+ /* Check if we need to run pkt_handle_queue */
+ if (atomic_read(&pd->scan_queue) > 0)
+ goto work_to_do;
+
+ /* Check if we need to run the state machine for some packet */
+ list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
+ if (atomic_read(&pkt->run_sm) > 0)
+ goto work_to_do;
+ }
+
+ /* Check if we need to process the iosched queues */
+ if (atomic_read(&pd->iosched.attention) != 0)
+ goto work_to_do;
+
+ /* Otherwise, go to sleep */
+ if (PACKET_DEBUG > 1) {
+ int states[PACKET_NUM_STATES];
+ pkt_count_states(pd, states);
+ pkt_dbg(2, pd, "i:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n",
+ states[0], states[1], states[2],
+ states[3], states[4], states[5]);
+ }
+
+ min_sleep_time = MAX_SCHEDULE_TIMEOUT;
+ list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
+ if (pkt->sleep_time && pkt->sleep_time < min_sleep_time)
+ min_sleep_time = pkt->sleep_time;
+ }
+
+ pkt_dbg(2, pd, "sleeping\n");
+ residue = schedule_timeout(min_sleep_time);
+ pkt_dbg(2, pd, "wake up\n");
+
+ /* make swsusp happy with our thread */
+ try_to_freeze();
+
+ list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
+ if (!pkt->sleep_time)
+ continue;
+ pkt->sleep_time -= min_sleep_time - residue;
+ if (pkt->sleep_time <= 0) {
+ pkt->sleep_time = 0;
+ atomic_inc(&pkt->run_sm);
+ }
+ }
+
+ if (kthread_should_stop())
+ break;
+ }
+work_to_do:
+ set_current_state(TASK_RUNNING);
+ remove_wait_queue(&pd->wqueue, &wait);
+
+ if (kthread_should_stop())
+ break;
+
+ /*
+ * if pkt_handle_queue returns true, we can queue
+ * another request.
+ */
+ while (pkt_handle_queue(pd))
+ ;
+
+ /*
+ * Handle packet state machine
+ */
+ pkt_handle_packets(pd);
+
+ /*
+ * Handle iosched queues
+ */
+ pkt_iosched_process_queue(pd);
+ }
+
+ return 0;
+}
+
+static void pkt_print_settings(struct pktcdvd_device *pd)
+{
+ pkt_info(pd, "%s packets, %u blocks, Mode-%c disc\n",
+ pd->settings.fp ? "Fixed" : "Variable",
+ pd->settings.size >> 2,
+ pd->settings.block_mode == 8 ? '1' : '2');
+}
+
+static int pkt_mode_sense(struct pktcdvd_device *pd, struct packet_command *cgc, int page_code, int page_control)
+{
+ memset(cgc->cmd, 0, sizeof(cgc->cmd));
+
+ cgc->cmd[0] = GPCMD_MODE_SENSE_10;
+ cgc->cmd[2] = page_code | (page_control << 6);
+ cgc->cmd[7] = cgc->buflen >> 8;
+ cgc->cmd[8] = cgc->buflen & 0xff;
+ cgc->data_direction = CGC_DATA_READ;
+ return pkt_generic_packet(pd, cgc);
+}
+
+static int pkt_mode_select(struct pktcdvd_device *pd, struct packet_command *cgc)
+{
+ memset(cgc->cmd, 0, sizeof(cgc->cmd));
+ memset(cgc->buffer, 0, 2);
+ cgc->cmd[0] = GPCMD_MODE_SELECT_10;
+ cgc->cmd[1] = 0x10; /* PF */
+ cgc->cmd[7] = cgc->buflen >> 8;
+ cgc->cmd[8] = cgc->buflen & 0xff;
+ cgc->data_direction = CGC_DATA_WRITE;
+ return pkt_generic_packet(pd, cgc);
+}
+
+static int pkt_get_disc_info(struct pktcdvd_device *pd, disc_information *di)
+{
+ struct packet_command cgc;
+ int ret;
+
+ /* set up command and get the disc info */
+ init_cdrom_command(&cgc, di, sizeof(*di), CGC_DATA_READ);
+ cgc.cmd[0] = GPCMD_READ_DISC_INFO;
+ cgc.cmd[8] = cgc.buflen = 2;
+ cgc.quiet = 1;
+
+ ret = pkt_generic_packet(pd, &cgc);
+ if (ret)
+ return ret;
+
+ /* not all drives have the same disc_info length, so requeue
+ * packet with the length the drive tells us it can supply
+ */
+ cgc.buflen = be16_to_cpu(di->disc_information_length) +
+ sizeof(di->disc_information_length);
+
+ if (cgc.buflen > sizeof(disc_information))
+ cgc.buflen = sizeof(disc_information);
+
+ cgc.cmd[8] = cgc.buflen;
+ return pkt_generic_packet(pd, &cgc);
+}
+
+static int pkt_get_track_info(struct pktcdvd_device *pd, __u16 track, __u8 type, track_information *ti)
+{
+ struct packet_command cgc;
+ int ret;
+
+ init_cdrom_command(&cgc, ti, 8, CGC_DATA_READ);
+ cgc.cmd[0] = GPCMD_READ_TRACK_RZONE_INFO;
+ cgc.cmd[1] = type & 3;
+ cgc.cmd[4] = (track & 0xff00) >> 8;
+ cgc.cmd[5] = track & 0xff;
+ cgc.cmd[8] = 8;
+ cgc.quiet = 1;
+
+ ret = pkt_generic_packet(pd, &cgc);
+ if (ret)
+ return ret;
+
+ cgc.buflen = be16_to_cpu(ti->track_information_length) +
+ sizeof(ti->track_information_length);
+
+ if (cgc.buflen > sizeof(track_information))
+ cgc.buflen = sizeof(track_information);
+
+ cgc.cmd[8] = cgc.buflen;
+ return pkt_generic_packet(pd, &cgc);
+}
+
+static noinline_for_stack int pkt_get_last_written(struct pktcdvd_device *pd,
+ long *last_written)
+{
+ disc_information di;
+ track_information ti;
+ __u32 last_track;
+ int ret;
+
+ ret = pkt_get_disc_info(pd, &di);
+ if (ret)
+ return ret;
+
+ last_track = (di.last_track_msb << 8) | di.last_track_lsb;
+ ret = pkt_get_track_info(pd, last_track, 1, &ti);
+ if (ret)
+ return ret;
+
+ /* if this track is blank, try the previous. */
+ if (ti.blank) {
+ last_track--;
+ ret = pkt_get_track_info(pd, last_track, 1, &ti);
+ if (ret)
+ return ret;
+ }
+
+ /* if last recorded field is valid, return it. */
+ if (ti.lra_v) {
+ *last_written = be32_to_cpu(ti.last_rec_address);
+ } else {
+ /* make it up instead */
+ *last_written = be32_to_cpu(ti.track_start) +
+ be32_to_cpu(ti.track_size);
+ if (ti.free_blocks)
+ *last_written -= (be32_to_cpu(ti.free_blocks) + 7);
+ }
+ return 0;
+}
+
+/*
+ * write mode select package based on pd->settings
+ */
+static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd)
+{
+ struct packet_command cgc;
+ struct scsi_sense_hdr sshdr;
+ write_param_page *wp;
+ char buffer[128];
+ int ret, size;
+
+ /* doesn't apply to DVD+RW or DVD-RAM */
+ if ((pd->mmc3_profile == 0x1a) || (pd->mmc3_profile == 0x12))
+ return 0;
+
+ memset(buffer, 0, sizeof(buffer));
+ init_cdrom_command(&cgc, buffer, sizeof(*wp), CGC_DATA_READ);
+ cgc.sshdr = &sshdr;
+ ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0);
+ if (ret) {
+ pkt_dump_sense(pd, &cgc);
+ return ret;
+ }
+
+ size = 2 + ((buffer[0] << 8) | (buffer[1] & 0xff));
+ pd->mode_offset = (buffer[6] << 8) | (buffer[7] & 0xff);
+ if (size > sizeof(buffer))
+ size = sizeof(buffer);
+
+ /*
+ * now get it all
+ */
+ init_cdrom_command(&cgc, buffer, size, CGC_DATA_READ);
+ cgc.sshdr = &sshdr;
+ ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0);
+ if (ret) {
+ pkt_dump_sense(pd, &cgc);
+ return ret;
+ }
+
+ /*
+ * write page is offset header + block descriptor length
+ */
+ wp = (write_param_page *) &buffer[sizeof(struct mode_page_header) + pd->mode_offset];
+
+ wp->fp = pd->settings.fp;
+ wp->track_mode = pd->settings.track_mode;
+ wp->write_type = pd->settings.write_type;
+ wp->data_block_type = pd->settings.block_mode;
+
+ wp->multi_session = 0;
+
+#ifdef PACKET_USE_LS
+ wp->link_size = 7;
+ wp->ls_v = 1;
+#endif
+
+ if (wp->data_block_type == PACKET_BLOCK_MODE1) {
+ wp->session_format = 0;
+ wp->subhdr2 = 0x20;
+ } else if (wp->data_block_type == PACKET_BLOCK_MODE2) {
+ wp->session_format = 0x20;
+ wp->subhdr2 = 8;
+#if 0
+ wp->mcn[0] = 0x80;
+ memcpy(&wp->mcn[1], PACKET_MCN, sizeof(wp->mcn) - 1);
+#endif
+ } else {
+ /*
+ * paranoia
+ */
+ pkt_err(pd, "write mode wrong %d\n", wp->data_block_type);
+ return 1;
+ }
+ wp->packet_size = cpu_to_be32(pd->settings.size >> 2);
+
+ cgc.buflen = cgc.cmd[8] = size;
+ ret = pkt_mode_select(pd, &cgc);
+ if (ret) {
+ pkt_dump_sense(pd, &cgc);
+ return ret;
+ }
+
+ pkt_print_settings(pd);
+ return 0;
+}
+
+/*
+ * 1 -- we can write to this track, 0 -- we can't
+ */
+static int pkt_writable_track(struct pktcdvd_device *pd, track_information *ti)
+{
+ switch (pd->mmc3_profile) {
+ case 0x1a: /* DVD+RW */
+ case 0x12: /* DVD-RAM */
+ /* The track is always writable on DVD+RW/DVD-RAM */
+ return 1;
+ default:
+ break;
+ }
+
+ if (!ti->packet || !ti->fp)
+ return 0;
+
+ /*
+ * "good" settings as per Mt Fuji.
+ */
+ if (ti->rt == 0 && ti->blank == 0)
+ return 1;
+
+ if (ti->rt == 0 && ti->blank == 1)
+ return 1;
+
+ if (ti->rt == 1 && ti->blank == 0)
+ return 1;
+
+ pkt_err(pd, "bad state %d-%d-%d\n", ti->rt, ti->blank, ti->packet);
+ return 0;
+}
+
+/*
+ * 1 -- we can write to this disc, 0 -- we can't
+ */
+static int pkt_writable_disc(struct pktcdvd_device *pd, disc_information *di)
+{
+ switch (pd->mmc3_profile) {
+ case 0x0a: /* CD-RW */
+ case 0xffff: /* MMC3 not supported */
+ break;
+ case 0x1a: /* DVD+RW */
+ case 0x13: /* DVD-RW */
+ case 0x12: /* DVD-RAM */
+ return 1;
+ default:
+ pkt_dbg(2, pd, "Wrong disc profile (%x)\n",
+ pd->mmc3_profile);
+ return 0;
+ }
+
+ /*
+ * for disc type 0xff we should probably reserve a new track.
+ * but i'm not sure, should we leave this to user apps? probably.
+ */
+ if (di->disc_type == 0xff) {
+ pkt_notice(pd, "unknown disc - no track?\n");
+ return 0;
+ }
+
+ if (di->disc_type != 0x20 && di->disc_type != 0) {
+ pkt_err(pd, "wrong disc type (%x)\n", di->disc_type);
+ return 0;
+ }
+
+ if (di->erasable == 0) {
+ pkt_notice(pd, "disc not erasable\n");
+ return 0;
+ }
+
+ if (di->border_status == PACKET_SESSION_RESERVED) {
+ pkt_err(pd, "can't write to last track (reserved)\n");
+ return 0;
+ }
+
+ return 1;
+}
+
+static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd)
+{
+ struct packet_command cgc;
+ unsigned char buf[12];
+ disc_information di;
+ track_information ti;
+ int ret, track;
+
+ init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_READ);
+ cgc.cmd[0] = GPCMD_GET_CONFIGURATION;
+ cgc.cmd[8] = 8;
+ ret = pkt_generic_packet(pd, &cgc);
+ pd->mmc3_profile = ret ? 0xffff : buf[6] << 8 | buf[7];
+
+ memset(&di, 0, sizeof(disc_information));
+ memset(&ti, 0, sizeof(track_information));
+
+ ret = pkt_get_disc_info(pd, &di);
+ if (ret) {
+ pkt_err(pd, "failed get_disc\n");
+ return ret;
+ }
+
+ if (!pkt_writable_disc(pd, &di))
+ return -EROFS;
+
+ pd->type = di.erasable ? PACKET_CDRW : PACKET_CDR;
+
+ track = 1; /* (di.last_track_msb << 8) | di.last_track_lsb; */
+ ret = pkt_get_track_info(pd, track, 1, &ti);
+ if (ret) {
+ pkt_err(pd, "failed get_track\n");
+ return ret;
+ }
+
+ if (!pkt_writable_track(pd, &ti)) {
+ pkt_err(pd, "can't write to this track\n");
+ return -EROFS;
+ }
+
+ /*
+ * we keep packet size in 512 byte units, makes it easier to
+ * deal with request calculations.
+ */
+ pd->settings.size = be32_to_cpu(ti.fixed_packet_size) << 2;
+ if (pd->settings.size == 0) {
+ pkt_notice(pd, "detected zero packet size!\n");
+ return -ENXIO;
+ }
+ if (pd->settings.size > PACKET_MAX_SECTORS) {
+ pkt_err(pd, "packet size is too big\n");
+ return -EROFS;
+ }
+ pd->settings.fp = ti.fp;
+ pd->offset = (be32_to_cpu(ti.track_start) << 2) & (pd->settings.size - 1);
+
+ if (ti.nwa_v) {
+ pd->nwa = be32_to_cpu(ti.next_writable);
+ set_bit(PACKET_NWA_VALID, &pd->flags);
+ }
+
+ /*
+ * in theory we could use lra on -RW media as well and just zero
+ * blocks that haven't been written yet, but in practice that
+ * is just a no-go. we'll use that for -R, naturally.
+ */
+ if (ti.lra_v) {
+ pd->lra = be32_to_cpu(ti.last_rec_address);
+ set_bit(PACKET_LRA_VALID, &pd->flags);
+ } else {
+ pd->lra = 0xffffffff;
+ set_bit(PACKET_LRA_VALID, &pd->flags);
+ }
+
+ /*
+ * fine for now
+ */
+ pd->settings.link_loss = 7;
+ pd->settings.write_type = 0; /* packet */
+ pd->settings.track_mode = ti.track_mode;
+
+ /*
+ * mode1 or mode2 disc
+ */
+ switch (ti.data_mode) {
+ case PACKET_MODE1:
+ pd->settings.block_mode = PACKET_BLOCK_MODE1;
+ break;
+ case PACKET_MODE2:
+ pd->settings.block_mode = PACKET_BLOCK_MODE2;
+ break;
+ default:
+ pkt_err(pd, "unknown data mode\n");
+ return -EROFS;
+ }
+ return 0;
+}
+
+/*
+ * enable/disable write caching on drive
+ */
+static noinline_for_stack int pkt_write_caching(struct pktcdvd_device *pd,
+ int set)
+{
+ struct packet_command cgc;
+ struct scsi_sense_hdr sshdr;
+ unsigned char buf[64];
+ int ret;
+
+ init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_READ);
+ cgc.sshdr = &sshdr;
+ cgc.buflen = pd->mode_offset + 12;
+
+ /*
+ * caching mode page might not be there, so quiet this command
+ */
+ cgc.quiet = 1;
+
+ ret = pkt_mode_sense(pd, &cgc, GPMODE_WCACHING_PAGE, 0);
+ if (ret)
+ return ret;
+
+ buf[pd->mode_offset + 10] |= (!!set << 2);
+
+ cgc.buflen = cgc.cmd[8] = 2 + ((buf[0] << 8) | (buf[1] & 0xff));
+ ret = pkt_mode_select(pd, &cgc);
+ if (ret) {
+ pkt_err(pd, "write caching control failed\n");
+ pkt_dump_sense(pd, &cgc);
+ } else if (!ret && set)
+ pkt_notice(pd, "enabled write caching\n");
+ return ret;
+}
+
+static int pkt_lock_door(struct pktcdvd_device *pd, int lockflag)
+{
+ struct packet_command cgc;
+
+ init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
+ cgc.cmd[0] = GPCMD_PREVENT_ALLOW_MEDIUM_REMOVAL;
+ cgc.cmd[4] = lockflag ? 1 : 0;
+ return pkt_generic_packet(pd, &cgc);
+}
+
+/*
+ * Returns drive maximum write speed
+ */
+static noinline_for_stack int pkt_get_max_speed(struct pktcdvd_device *pd,
+ unsigned *write_speed)
+{
+ struct packet_command cgc;
+ struct scsi_sense_hdr sshdr;
+ unsigned char buf[256+18];
+ unsigned char *cap_buf;
+ int ret, offset;
+
+ cap_buf = &buf[sizeof(struct mode_page_header) + pd->mode_offset];
+ init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_UNKNOWN);
+ cgc.sshdr = &sshdr;
+
+ ret = pkt_mode_sense(pd, &cgc, GPMODE_CAPABILITIES_PAGE, 0);
+ if (ret) {
+ cgc.buflen = pd->mode_offset + cap_buf[1] + 2 +
+ sizeof(struct mode_page_header);
+ ret = pkt_mode_sense(pd, &cgc, GPMODE_CAPABILITIES_PAGE, 0);
+ if (ret) {
+ pkt_dump_sense(pd, &cgc);
+ return ret;
+ }
+ }
+
+ offset = 20; /* Obsoleted field, used by older drives */
+ if (cap_buf[1] >= 28)
+ offset = 28; /* Current write speed selected */
+ if (cap_buf[1] >= 30) {
+ /* If the drive reports at least one "Logical Unit Write
+ * Speed Performance Descriptor Block", use the information
+ * in the first block. (contains the highest speed)
+ */
+ int num_spdb = (cap_buf[30] << 8) + cap_buf[31];
+ if (num_spdb > 0)
+ offset = 34;
+ }
+
+ *write_speed = (cap_buf[offset] << 8) | cap_buf[offset + 1];
+ return 0;
+}
+
+/* These tables from cdrecord - I don't have orange book */
+/* standard speed CD-RW (1-4x) */
+static char clv_to_speed[16] = {
+ /* 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 */
+ 0, 2, 4, 6, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+};
+/* high speed CD-RW (-10x) */
+static char hs_clv_to_speed[16] = {
+ /* 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 */
+ 0, 2, 4, 6, 10, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+};
+/* ultra high speed CD-RW */
+static char us_clv_to_speed[16] = {
+ /* 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 */
+ 0, 2, 4, 8, 0, 0,16, 0,24,32,40,48, 0, 0, 0, 0
+};
+
+/*
+ * reads the maximum media speed from ATIP
+ */
+static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd,
+ unsigned *speed)
+{
+ struct packet_command cgc;
+ struct scsi_sense_hdr sshdr;
+ unsigned char buf[64];
+ unsigned int size, st, sp;
+ int ret;
+
+ init_cdrom_command(&cgc, buf, 2, CGC_DATA_READ);
+ cgc.sshdr = &sshdr;
+ cgc.cmd[0] = GPCMD_READ_TOC_PMA_ATIP;
+ cgc.cmd[1] = 2;
+ cgc.cmd[2] = 4; /* READ ATIP */
+ cgc.cmd[8] = 2;
+ ret = pkt_generic_packet(pd, &cgc);
+ if (ret) {
+ pkt_dump_sense(pd, &cgc);
+ return ret;
+ }
+ size = ((unsigned int) buf[0]<<8) + buf[1] + 2;
+ if (size > sizeof(buf))
+ size = sizeof(buf);
+
+ init_cdrom_command(&cgc, buf, size, CGC_DATA_READ);
+ cgc.sshdr = &sshdr;
+ cgc.cmd[0] = GPCMD_READ_TOC_PMA_ATIP;
+ cgc.cmd[1] = 2;
+ cgc.cmd[2] = 4;
+ cgc.cmd[8] = size;
+ ret = pkt_generic_packet(pd, &cgc);
+ if (ret) {
+ pkt_dump_sense(pd, &cgc);
+ return ret;
+ }
+
+ if (!(buf[6] & 0x40)) {
+ pkt_notice(pd, "disc type is not CD-RW\n");
+ return 1;
+ }
+ if (!(buf[6] & 0x4)) {
+ pkt_notice(pd, "A1 values on media are not valid, maybe not CDRW?\n");
+ return 1;
+ }
+
+ st = (buf[6] >> 3) & 0x7; /* disc sub-type */
+
+ sp = buf[16] & 0xf; /* max speed from ATIP A1 field */
+
+ /* Info from cdrecord */
+ switch (st) {
+ case 0: /* standard speed */
+ *speed = clv_to_speed[sp];
+ break;
+ case 1: /* high speed */
+ *speed = hs_clv_to_speed[sp];
+ break;
+ case 2: /* ultra high speed */
+ *speed = us_clv_to_speed[sp];
+ break;
+ default:
+ pkt_notice(pd, "unknown disc sub-type %d\n", st);
+ return 1;
+ }
+ if (*speed) {
+ pkt_info(pd, "maximum media speed: %d\n", *speed);
+ return 0;
+ } else {
+ pkt_notice(pd, "unknown speed %d for sub-type %d\n", sp, st);
+ return 1;
+ }
+}
+
+static noinline_for_stack int pkt_perform_opc(struct pktcdvd_device *pd)
+{
+ struct packet_command cgc;
+ struct scsi_sense_hdr sshdr;
+ int ret;
+
+ pkt_dbg(2, pd, "Performing OPC\n");
+
+ init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
+ cgc.sshdr = &sshdr;
+ cgc.timeout = 60*HZ;
+ cgc.cmd[0] = GPCMD_SEND_OPC;
+ cgc.cmd[1] = 1;
+ ret = pkt_generic_packet(pd, &cgc);
+ if (ret)
+ pkt_dump_sense(pd, &cgc);
+ return ret;
+}
+
+static int pkt_open_write(struct pktcdvd_device *pd)
+{
+ int ret;
+ unsigned int write_speed, media_write_speed, read_speed;
+
+ ret = pkt_probe_settings(pd);
+ if (ret) {
+ pkt_dbg(2, pd, "failed probe\n");
+ return ret;
+ }
+
+ ret = pkt_set_write_settings(pd);
+ if (ret) {
+ pkt_dbg(1, pd, "failed saving write settings\n");
+ return -EIO;
+ }
+
+ pkt_write_caching(pd, USE_WCACHING);
+
+ ret = pkt_get_max_speed(pd, &write_speed);
+ if (ret)
+ write_speed = 16 * 177;
+ switch (pd->mmc3_profile) {
+ case 0x13: /* DVD-RW */
+ case 0x1a: /* DVD+RW */
+ case 0x12: /* DVD-RAM */
+ pkt_dbg(1, pd, "write speed %ukB/s\n", write_speed);
+ break;
+ default:
+ ret = pkt_media_speed(pd, &media_write_speed);
+ if (ret)
+ media_write_speed = 16;
+ write_speed = min(write_speed, media_write_speed * 177);
+ pkt_dbg(1, pd, "write speed %ux\n", write_speed / 176);
+ break;
+ }
+ read_speed = write_speed;
+
+ ret = pkt_set_speed(pd, write_speed, read_speed);
+ if (ret) {
+ pkt_dbg(1, pd, "couldn't set write speed\n");
+ return -EIO;
+ }
+ pd->write_speed = write_speed;
+ pd->read_speed = read_speed;
+
+ ret = pkt_perform_opc(pd);
+ if (ret) {
+ pkt_dbg(1, pd, "Optimum Power Calibration failed\n");
+ }
+
+ return 0;
+}
+
+/*
+ * called at open time.
+ */
+static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
+{
+ int ret;
+ long lba;
+ struct request_queue *q;
+ struct block_device *bdev;
+
+ /*
+ * We need to re-open the cdrom device without O_NONBLOCK to be able
+ * to read/write from/to it. It is already opened in O_NONBLOCK mode
+ * so open should not fail.
+ */
+ bdev = blkdev_get_by_dev(pd->bdev->bd_dev, FMODE_READ | FMODE_EXCL, pd);
+ if (IS_ERR(bdev)) {
+ ret = PTR_ERR(bdev);
+ goto out;
+ }
+
+ ret = pkt_get_last_written(pd, &lba);
+ if (ret) {
+ pkt_err(pd, "pkt_get_last_written failed\n");
+ goto out_putdev;
+ }
+
+ set_capacity(pd->disk, lba << 2);
+ set_capacity_and_notify(pd->bdev->bd_disk, lba << 2);
+
+ q = bdev_get_queue(pd->bdev);
+ if (write) {
+ ret = pkt_open_write(pd);
+ if (ret)
+ goto out_putdev;
+ /*
+ * Some CDRW drives can not handle writes larger than one packet,
+ * even if the size is a multiple of the packet size.
+ */
+ blk_queue_max_hw_sectors(q, pd->settings.size);
+ set_bit(PACKET_WRITABLE, &pd->flags);
+ } else {
+ pkt_set_speed(pd, MAX_SPEED, MAX_SPEED);
+ clear_bit(PACKET_WRITABLE, &pd->flags);
+ }
+
+ ret = pkt_set_segment_merging(pd, q);
+ if (ret)
+ goto out_putdev;
+
+ if (write) {
+ if (!pkt_grow_pktlist(pd, CONFIG_CDROM_PKTCDVD_BUFFERS)) {
+ pkt_err(pd, "not enough memory for buffers\n");
+ ret = -ENOMEM;
+ goto out_putdev;
+ }
+ pkt_info(pd, "%lukB available on disc\n", lba << 1);
+ }
+
+ return 0;
+
+out_putdev:
+ blkdev_put(bdev, FMODE_READ | FMODE_EXCL);
+out:
+ return ret;
+}
+
+/*
+ * called when the device is closed. makes sure that the device flushes
+ * the internal cache before we close.
+ */
+static void pkt_release_dev(struct pktcdvd_device *pd, int flush)
+{
+ if (flush && pkt_flush_cache(pd))
+ pkt_dbg(1, pd, "not flushing cache\n");
+
+ pkt_lock_door(pd, 0);
+
+ pkt_set_speed(pd, MAX_SPEED, MAX_SPEED);
+ blkdev_put(pd->bdev, FMODE_READ | FMODE_EXCL);
+
+ pkt_shrink_pktlist(pd);
+}
+
+static struct pktcdvd_device *pkt_find_dev_from_minor(unsigned int dev_minor)
+{
+ if (dev_minor >= MAX_WRITERS)
+ return NULL;
+
+ dev_minor = array_index_nospec(dev_minor, MAX_WRITERS);
+ return pkt_devs[dev_minor];
+}
+
+static int pkt_open(struct block_device *bdev, fmode_t mode)
+{
+ struct pktcdvd_device *pd = NULL;
+ int ret;
+
+ mutex_lock(&pktcdvd_mutex);
+ mutex_lock(&ctl_mutex);
+ pd = pkt_find_dev_from_minor(MINOR(bdev->bd_dev));
+ if (!pd) {
+ ret = -ENODEV;
+ goto out;
+ }
+ BUG_ON(pd->refcnt < 0);
+
+ pd->refcnt++;
+ if (pd->refcnt > 1) {
+ if ((mode & FMODE_WRITE) &&
+ !test_bit(PACKET_WRITABLE, &pd->flags)) {
+ ret = -EBUSY;
+ goto out_dec;
+ }
+ } else {
+ ret = pkt_open_dev(pd, mode & FMODE_WRITE);
+ if (ret)
+ goto out_dec;
+ /*
+ * needed here as well, since ext2 (among others) may change
+ * the blocksize at mount time
+ */
+ set_blocksize(bdev, CD_FRAMESIZE);
+ }
+
+ mutex_unlock(&ctl_mutex);
+ mutex_unlock(&pktcdvd_mutex);
+ return 0;
+
+out_dec:
+ pd->refcnt--;
+out:
+ mutex_unlock(&ctl_mutex);
+ mutex_unlock(&pktcdvd_mutex);
+ return ret;
+}
+
+static void pkt_close(struct gendisk *disk, fmode_t mode)
+{
+ struct pktcdvd_device *pd = disk->private_data;
+
+ mutex_lock(&pktcdvd_mutex);
+ mutex_lock(&ctl_mutex);
+ pd->refcnt--;
+ BUG_ON(pd->refcnt < 0);
+ if (pd->refcnt == 0) {
+ int flush = test_bit(PACKET_WRITABLE, &pd->flags);
+ pkt_release_dev(pd, flush);
+ }
+ mutex_unlock(&ctl_mutex);
+ mutex_unlock(&pktcdvd_mutex);
+}
+
+
+static void pkt_end_io_read_cloned(struct bio *bio)
+{
+ struct packet_stacked_data *psd = bio->bi_private;
+ struct pktcdvd_device *pd = psd->pd;
+
+ psd->bio->bi_status = bio->bi_status;
+ bio_put(bio);
+ bio_endio(psd->bio);
+ mempool_free(psd, &psd_pool);
+ pkt_bio_finished(pd);
+}
+
+static void pkt_make_request_read(struct pktcdvd_device *pd, struct bio *bio)
+{
+ struct bio *cloned_bio =
+ bio_alloc_clone(pd->bdev, bio, GFP_NOIO, &pkt_bio_set);
+ struct packet_stacked_data *psd = mempool_alloc(&psd_pool, GFP_NOIO);
+
+ psd->pd = pd;
+ psd->bio = bio;
+ cloned_bio->bi_private = psd;
+ cloned_bio->bi_end_io = pkt_end_io_read_cloned;
+ pd->stats.secs_r += bio_sectors(bio);
+ pkt_queue_bio(pd, cloned_bio);
+}
+
+static void pkt_make_request_write(struct request_queue *q, struct bio *bio)
+{
+ struct pktcdvd_device *pd = q->queuedata;
+ sector_t zone;
+ struct packet_data *pkt;
+ int was_empty, blocked_bio;
+ struct pkt_rb_node *node;
+
+ zone = get_zone(bio->bi_iter.bi_sector, pd);
+
+ /*
+ * If we find a matching packet in state WAITING or READ_WAIT, we can
+ * just append this bio to that packet.
+ */
+ spin_lock(&pd->cdrw.active_list_lock);
+ blocked_bio = 0;
+ list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
+ if (pkt->sector == zone) {
+ spin_lock(&pkt->lock);
+ if ((pkt->state == PACKET_WAITING_STATE) ||
+ (pkt->state == PACKET_READ_WAIT_STATE)) {
+ bio_list_add(&pkt->orig_bios, bio);
+ pkt->write_size +=
+ bio->bi_iter.bi_size / CD_FRAMESIZE;
+ if ((pkt->write_size >= pkt->frames) &&
+ (pkt->state == PACKET_WAITING_STATE)) {
+ atomic_inc(&pkt->run_sm);
+ wake_up(&pd->wqueue);
+ }
+ spin_unlock(&pkt->lock);
+ spin_unlock(&pd->cdrw.active_list_lock);
+ return;
+ } else {
+ blocked_bio = 1;
+ }
+ spin_unlock(&pkt->lock);
+ }
+ }
+ spin_unlock(&pd->cdrw.active_list_lock);
+
+ /*
+ * Test if there is enough room left in the bio work queue
+ * (queue size >= congestion on mark).
+ * If not, wait till the work queue size is below the congestion off mark.
+ */
+ spin_lock(&pd->lock);
+ if (pd->write_congestion_on > 0
+ && pd->bio_queue_size >= pd->write_congestion_on) {
+ struct wait_bit_queue_entry wqe;
+
+ init_wait_var_entry(&wqe, &pd->congested, 0);
+ for (;;) {
+ prepare_to_wait_event(__var_waitqueue(&pd->congested),
+ &wqe.wq_entry,
+ TASK_UNINTERRUPTIBLE);
+ if (pd->bio_queue_size <= pd->write_congestion_off)
+ break;
+ pd->congested = true;
+ spin_unlock(&pd->lock);
+ schedule();
+ spin_lock(&pd->lock);
+ }
+ }
+ spin_unlock(&pd->lock);
+
+ /*
+ * No matching packet found. Store the bio in the work queue.
+ */
+ node = mempool_alloc(&pd->rb_pool, GFP_NOIO);
+ node->bio = bio;
+ spin_lock(&pd->lock);
+ BUG_ON(pd->bio_queue_size < 0);
+ was_empty = (pd->bio_queue_size == 0);
+ pkt_rbtree_insert(pd, node);
+ spin_unlock(&pd->lock);
+
+ /*
+ * Wake up the worker thread.
+ */
+ atomic_set(&pd->scan_queue, 1);
+ if (was_empty) {
+ /* This wake_up is required for correct operation */
+ wake_up(&pd->wqueue);
+ } else if (!list_empty(&pd->cdrw.pkt_free_list) && !blocked_bio) {
+ /*
+ * This wake up is not required for correct operation,
+ * but improves performance in some cases.
+ */
+ wake_up(&pd->wqueue);
+ }
+}
+
+static void pkt_submit_bio(struct bio *bio)
+{
+ struct pktcdvd_device *pd = bio->bi_bdev->bd_disk->queue->queuedata;
+ struct bio *split;
+
+ bio = bio_split_to_limits(bio);
+
+ pkt_dbg(2, pd, "start = %6llx stop = %6llx\n",
+ (unsigned long long)bio->bi_iter.bi_sector,
+ (unsigned long long)bio_end_sector(bio));
+
+ /*
+ * Clone READ bios so we can have our own bi_end_io callback.
+ */
+ if (bio_data_dir(bio) == READ) {
+ pkt_make_request_read(pd, bio);
+ return;
+ }
+
+ if (!test_bit(PACKET_WRITABLE, &pd->flags)) {
+ pkt_notice(pd, "WRITE for ro device (%llu)\n",
+ (unsigned long long)bio->bi_iter.bi_sector);
+ goto end_io;
+ }
+
+ if (!bio->bi_iter.bi_size || (bio->bi_iter.bi_size % CD_FRAMESIZE)) {
+ pkt_err(pd, "wrong bio size\n");
+ goto end_io;
+ }
+
+ do {
+ sector_t zone = get_zone(bio->bi_iter.bi_sector, pd);
+ sector_t last_zone = get_zone(bio_end_sector(bio) - 1, pd);
+
+ if (last_zone != zone) {
+ BUG_ON(last_zone != zone + pd->settings.size);
+
+ split = bio_split(bio, last_zone -
+ bio->bi_iter.bi_sector,
+ GFP_NOIO, &pkt_bio_set);
+ bio_chain(split, bio);
+ } else {
+ split = bio;
+ }
+
+ pkt_make_request_write(bio->bi_bdev->bd_disk->queue, split);
+ } while (split != bio);
+
+ return;
+end_io:
+ bio_io_error(bio);
+}
+
+static void pkt_init_queue(struct pktcdvd_device *pd)
+{
+ struct request_queue *q = pd->disk->queue;
+
+ blk_queue_logical_block_size(q, CD_FRAMESIZE);
+ blk_queue_max_hw_sectors(q, PACKET_MAX_SECTORS);
+ q->queuedata = pd;
+}
+
+static int pkt_seq_show(struct seq_file *m, void *p)
+{
+ struct pktcdvd_device *pd = m->private;
+ char *msg;
+ int states[PACKET_NUM_STATES];
+
+ seq_printf(m, "Writer %s mapped to %pg:\n", pd->name, pd->bdev);
+
+ seq_printf(m, "\nSettings:\n");
+ seq_printf(m, "\tpacket size:\t\t%dkB\n", pd->settings.size / 2);
+
+ if (pd->settings.write_type == 0)
+ msg = "Packet";
+ else
+ msg = "Unknown";
+ seq_printf(m, "\twrite type:\t\t%s\n", msg);
+
+ seq_printf(m, "\tpacket type:\t\t%s\n", pd->settings.fp ? "Fixed" : "Variable");
+ seq_printf(m, "\tlink loss:\t\t%d\n", pd->settings.link_loss);
+
+ seq_printf(m, "\ttrack mode:\t\t%d\n", pd->settings.track_mode);
+
+ if (pd->settings.block_mode == PACKET_BLOCK_MODE1)
+ msg = "Mode 1";
+ else if (pd->settings.block_mode == PACKET_BLOCK_MODE2)
+ msg = "Mode 2";
+ else
+ msg = "Unknown";
+ seq_printf(m, "\tblock mode:\t\t%s\n", msg);
+
+ seq_printf(m, "\nStatistics:\n");
+ seq_printf(m, "\tpackets started:\t%lu\n", pd->stats.pkt_started);
+ seq_printf(m, "\tpackets ended:\t\t%lu\n", pd->stats.pkt_ended);
+ seq_printf(m, "\twritten:\t\t%lukB\n", pd->stats.secs_w >> 1);
+ seq_printf(m, "\tread gather:\t\t%lukB\n", pd->stats.secs_rg >> 1);
+ seq_printf(m, "\tread:\t\t\t%lukB\n", pd->stats.secs_r >> 1);
+
+ seq_printf(m, "\nMisc:\n");
+ seq_printf(m, "\treference count:\t%d\n", pd->refcnt);
+ seq_printf(m, "\tflags:\t\t\t0x%lx\n", pd->flags);
+ seq_printf(m, "\tread speed:\t\t%ukB/s\n", pd->read_speed);
+ seq_printf(m, "\twrite speed:\t\t%ukB/s\n", pd->write_speed);
+ seq_printf(m, "\tstart offset:\t\t%lu\n", pd->offset);
+ seq_printf(m, "\tmode page offset:\t%u\n", pd->mode_offset);
+
+ seq_printf(m, "\nQueue state:\n");
+ seq_printf(m, "\tbios queued:\t\t%d\n", pd->bio_queue_size);
+ seq_printf(m, "\tbios pending:\t\t%d\n", atomic_read(&pd->cdrw.pending_bios));
+ seq_printf(m, "\tcurrent sector:\t\t0x%llx\n", (unsigned long long)pd->current_sector);
+
+ pkt_count_states(pd, states);
+ seq_printf(m, "\tstate:\t\t\ti:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n",
+ states[0], states[1], states[2], states[3], states[4], states[5]);
+
+ seq_printf(m, "\twrite congestion marks:\toff=%d on=%d\n",
+ pd->write_congestion_off,
+ pd->write_congestion_on);
+ return 0;
+}
+
+static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
+{
+ int i;
+ struct block_device *bdev;
+ struct scsi_device *sdev;
+
+ if (pd->pkt_dev == dev) {
+ pkt_err(pd, "recursive setup not allowed\n");
+ return -EBUSY;
+ }
+ for (i = 0; i < MAX_WRITERS; i++) {
+ struct pktcdvd_device *pd2 = pkt_devs[i];
+ if (!pd2)
+ continue;
+ if (pd2->bdev->bd_dev == dev) {
+ pkt_err(pd, "%pg already setup\n", pd2->bdev);
+ return -EBUSY;
+ }
+ if (pd2->pkt_dev == dev) {
+ pkt_err(pd, "can't chain pktcdvd devices\n");
+ return -EBUSY;
+ }
+ }
+
+ bdev = blkdev_get_by_dev(dev, FMODE_READ | FMODE_NDELAY, NULL);
+ if (IS_ERR(bdev))
+ return PTR_ERR(bdev);
+ sdev = scsi_device_from_queue(bdev->bd_disk->queue);
+ if (!sdev) {
+ blkdev_put(bdev, FMODE_READ | FMODE_NDELAY);
+ return -EINVAL;
+ }
+ put_device(&sdev->sdev_gendev);
+
+ /* This is safe, since we have a reference from open(). */
+ __module_get(THIS_MODULE);
+
+ pd->bdev = bdev;
+ set_blocksize(bdev, CD_FRAMESIZE);
+
+ pkt_init_queue(pd);
+
+ atomic_set(&pd->cdrw.pending_bios, 0);
+ pd->cdrw.thread = kthread_run(kcdrwd, pd, "%s", pd->name);
+ if (IS_ERR(pd->cdrw.thread)) {
+ pkt_err(pd, "can't start kernel thread\n");
+ goto out_mem;
+ }
+
+ proc_create_single_data(pd->name, 0, pkt_proc, pkt_seq_show, pd);
+ pkt_dbg(1, pd, "writer mapped to %pg\n", bdev);
+ return 0;
+
+out_mem:
+ blkdev_put(bdev, FMODE_READ | FMODE_NDELAY);
+ /* This is safe: open() is still holding a reference. */
+ module_put(THIS_MODULE);
+ return -ENOMEM;
+}
+
+static int pkt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg)
+{
+ struct pktcdvd_device *pd = bdev->bd_disk->private_data;
+ int ret;
+
+ pkt_dbg(2, pd, "cmd %x, dev %d:%d\n",
+ cmd, MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev));
+
+ mutex_lock(&pktcdvd_mutex);
+ switch (cmd) {
+ case CDROMEJECT:
+ /*
+ * The door gets locked when the device is opened, so we
+ * have to unlock it or else the eject command fails.
+ */
+ if (pd->refcnt == 1)
+ pkt_lock_door(pd, 0);
+ fallthrough;
+ /*
+ * forward selected CDROM ioctls to CD-ROM, for UDF
+ */
+ case CDROMMULTISESSION:
+ case CDROMREADTOCENTRY:
+ case CDROM_LAST_WRITTEN:
+ case CDROM_SEND_PACKET:
+ case SCSI_IOCTL_SEND_COMMAND:
+ if (!bdev->bd_disk->fops->ioctl)
+ ret = -ENOTTY;
+ else
+ ret = bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg);
+ break;
+ default:
+ pkt_dbg(2, pd, "Unknown ioctl (%x)\n", cmd);
+ ret = -ENOTTY;
+ }
+ mutex_unlock(&pktcdvd_mutex);
+
+ return ret;
+}
+
+static unsigned int pkt_check_events(struct gendisk *disk,
+ unsigned int clearing)
+{
+ struct pktcdvd_device *pd = disk->private_data;
+ struct gendisk *attached_disk;
+
+ if (!pd)
+ return 0;
+ if (!pd->bdev)
+ return 0;
+ attached_disk = pd->bdev->bd_disk;
+ if (!attached_disk || !attached_disk->fops->check_events)
+ return 0;
+ 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,
+ .submit_bio = pkt_submit_bio,
+ .open = pkt_open,
+ .release = pkt_close,
+ .ioctl = pkt_ioctl,
+ .compat_ioctl = blkdev_compat_ptr_ioctl,
+ .check_events = pkt_check_events,
+ .devnode = pkt_devnode,
+};
+
+/*
+ * Set up mapping from pktcdvd device to CD-ROM device.
+ */
+static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
+{
+ int idx;
+ int ret = -ENOMEM;
+ struct pktcdvd_device *pd;
+ struct gendisk *disk;
+
+ mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+ for (idx = 0; idx < MAX_WRITERS; idx++)
+ if (!pkt_devs[idx])
+ break;
+ if (idx == MAX_WRITERS) {
+ pr_err("max %d writers supported\n", MAX_WRITERS);
+ ret = -EBUSY;
+ goto out_mutex;
+ }
+
+ pd = kzalloc(sizeof(struct pktcdvd_device), GFP_KERNEL);
+ if (!pd)
+ goto out_mutex;
+
+ ret = mempool_init_kmalloc_pool(&pd->rb_pool, PKT_RB_POOL_SIZE,
+ sizeof(struct pkt_rb_node));
+ if (ret)
+ goto out_mem;
+
+ INIT_LIST_HEAD(&pd->cdrw.pkt_free_list);
+ INIT_LIST_HEAD(&pd->cdrw.pkt_active_list);
+ spin_lock_init(&pd->cdrw.active_list_lock);
+
+ spin_lock_init(&pd->lock);
+ spin_lock_init(&pd->iosched.lock);
+ bio_list_init(&pd->iosched.read_queue);
+ bio_list_init(&pd->iosched.write_queue);
+ sprintf(pd->name, DRIVER_NAME"%d", idx);
+ init_waitqueue_head(&pd->wqueue);
+ pd->bio_queue = RB_ROOT;
+
+ pd->write_congestion_on = write_congestion_on;
+ pd->write_congestion_off = write_congestion_off;
+
+ ret = -ENOMEM;
+ disk = blk_alloc_disk(NUMA_NO_NODE);
+ if (!disk)
+ goto out_mem;
+ pd->disk = disk;
+ disk->major = pktdev_major;
+ disk->first_minor = idx;
+ disk->minors = 1;
+ disk->fops = &pktcdvd_ops;
+ disk->flags = GENHD_FL_REMOVABLE | GENHD_FL_NO_PART;
+ strcpy(disk->disk_name, pd->name);
+ disk->private_data = pd;
+
+ pd->pkt_dev = MKDEV(pktdev_major, idx);
+ ret = pkt_new_dev(pd, dev);
+ if (ret)
+ goto out_mem2;
+
+ /* inherit events of the host device */
+ disk->events = pd->bdev->bd_disk->events;
+
+ ret = add_disk(disk);
+ if (ret)
+ goto out_mem2;
+
+ pkt_sysfs_dev_new(pd);
+ pkt_debugfs_dev_new(pd);
+
+ pkt_devs[idx] = pd;
+ if (pkt_dev)
+ *pkt_dev = pd->pkt_dev;
+
+ mutex_unlock(&ctl_mutex);
+ return 0;
+
+out_mem2:
+ put_disk(disk);
+out_mem:
+ mempool_exit(&pd->rb_pool);
+ kfree(pd);
+out_mutex:
+ mutex_unlock(&ctl_mutex);
+ pr_err("setup of pktcdvd device failed\n");
+ return ret;
+}
+
+/*
+ * Tear down mapping from pktcdvd device to CD-ROM device.
+ */
+static int pkt_remove_dev(dev_t pkt_dev)
+{
+ struct pktcdvd_device *pd;
+ int idx;
+ int ret = 0;
+
+ mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+ for (idx = 0; idx < MAX_WRITERS; idx++) {
+ pd = pkt_devs[idx];
+ if (pd && (pd->pkt_dev == pkt_dev))
+ break;
+ }
+ if (idx == MAX_WRITERS) {
+ pr_debug("dev not setup\n");
+ ret = -ENXIO;
+ goto out;
+ }
+
+ if (pd->refcnt > 0) {
+ ret = -EBUSY;
+ goto out;
+ }
+ if (!IS_ERR(pd->cdrw.thread))
+ kthread_stop(pd->cdrw.thread);
+
+ pkt_devs[idx] = NULL;
+
+ pkt_debugfs_dev_remove(pd);
+ pkt_sysfs_dev_remove(pd);
+
+ blkdev_put(pd->bdev, FMODE_READ | FMODE_NDELAY);
+
+ remove_proc_entry(pd->name, pkt_proc);
+ pkt_dbg(1, pd, "writer unmapped\n");
+
+ del_gendisk(pd->disk);
+ put_disk(pd->disk);
+
+ mempool_exit(&pd->rb_pool);
+ kfree(pd);
+
+ /* This is safe: open() is still holding a reference. */
+ module_put(THIS_MODULE);
+
+out:
+ mutex_unlock(&ctl_mutex);
+ return ret;
+}
+
+static void pkt_get_status(struct pkt_ctrl_command *ctrl_cmd)
+{
+ struct pktcdvd_device *pd;
+
+ mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+ pd = pkt_find_dev_from_minor(ctrl_cmd->dev_index);
+ if (pd) {
+ ctrl_cmd->dev = new_encode_dev(pd->bdev->bd_dev);
+ ctrl_cmd->pkt_dev = new_encode_dev(pd->pkt_dev);
+ } else {
+ ctrl_cmd->dev = 0;
+ ctrl_cmd->pkt_dev = 0;
+ }
+ ctrl_cmd->num_devices = MAX_WRITERS;
+
+ mutex_unlock(&ctl_mutex);
+}
+
+static long pkt_ctl_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ void __user *argp = (void __user *)arg;
+ struct pkt_ctrl_command ctrl_cmd;
+ int ret = 0;
+ dev_t pkt_dev = 0;
+
+ if (cmd != PACKET_CTRL_CMD)
+ return -ENOTTY;
+
+ if (copy_from_user(&ctrl_cmd, argp, sizeof(struct pkt_ctrl_command)))
+ return -EFAULT;
+
+ switch (ctrl_cmd.command) {
+ case PKT_CTRL_CMD_SETUP:
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ ret = pkt_setup_dev(new_decode_dev(ctrl_cmd.dev), &pkt_dev);
+ ctrl_cmd.pkt_dev = new_encode_dev(pkt_dev);
+ break;
+ case PKT_CTRL_CMD_TEARDOWN:
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ ret = pkt_remove_dev(new_decode_dev(ctrl_cmd.pkt_dev));
+ break;
+ case PKT_CTRL_CMD_STATUS:
+ pkt_get_status(&ctrl_cmd);
+ break;
+ default:
+ return -ENOTTY;
+ }
+
+ if (copy_to_user(argp, &ctrl_cmd, sizeof(struct pkt_ctrl_command)))
+ return -EFAULT;
+ return ret;
+}
+
+#ifdef CONFIG_COMPAT
+static long pkt_ctl_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ return pkt_ctl_ioctl(file, cmd, (unsigned long)compat_ptr(arg));
+}
+#endif
+
+static const struct file_operations pkt_ctl_fops = {
+ .open = nonseekable_open,
+ .unlocked_ioctl = pkt_ctl_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = pkt_ctl_compat_ioctl,
+#endif
+ .owner = THIS_MODULE,
+ .llseek = no_llseek,
+};
+
+static struct miscdevice pkt_misc = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = DRIVER_NAME,
+ .nodename = "pktcdvd/control",
+ .fops = &pkt_ctl_fops
+};
+
+static int __init pkt_init(void)
+{
+ int ret;
+
+ mutex_init(&ctl_mutex);
+
+ ret = mempool_init_kmalloc_pool(&psd_pool, PSD_POOL_SIZE,
+ sizeof(struct packet_stacked_data));
+ if (ret)
+ return ret;
+ ret = bioset_init(&pkt_bio_set, BIO_POOL_SIZE, 0, 0);
+ if (ret) {
+ mempool_exit(&psd_pool);
+ return ret;
+ }
+
+ ret = register_blkdev(pktdev_major, DRIVER_NAME);
+ if (ret < 0) {
+ pr_err("unable to register block device\n");
+ goto out2;
+ }
+ if (!pktdev_major)
+ pktdev_major = ret;
+
+ ret = pkt_sysfs_init();
+ if (ret)
+ goto out;
+
+ pkt_debugfs_init();
+
+ ret = misc_register(&pkt_misc);
+ if (ret) {
+ pr_err("unable to register misc device\n");
+ goto out_misc;
+ }
+
+ pkt_proc = proc_mkdir("driver/"DRIVER_NAME, NULL);
+
+ return 0;
+
+out_misc:
+ pkt_debugfs_cleanup();
+ pkt_sysfs_cleanup();
+out:
+ unregister_blkdev(pktdev_major, DRIVER_NAME);
+out2:
+ mempool_exit(&psd_pool);
+ bioset_exit(&pkt_bio_set);
+ return ret;
+}
+
+static void __exit pkt_exit(void)
+{
+ remove_proc_entry("driver/"DRIVER_NAME, NULL);
+ misc_deregister(&pkt_misc);
+
+ pkt_debugfs_cleanup();
+ pkt_sysfs_cleanup();
+
+ unregister_blkdev(pktdev_major, DRIVER_NAME);
+ mempool_exit(&psd_pool);
+ bioset_exit(&pkt_bio_set);
+}
+
+MODULE_DESCRIPTION("Packet writing layer for CD/DVD drives");
+MODULE_AUTHOR("Jens Axboe <axboe@suse.de>");
+MODULE_LICENSE("GPL");
+
+module_init(pkt_init);
+module_exit(pkt_exit);
dev_dbg(&dev->core, "%s\n", __func__);
bio = bio_split_to_limits(bio);
+ if (!bio)
+ return;
spin_lock_irq(&priv->lock);
busy = !bio_list_empty(&priv->list);
struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd;
int ret = -EINVAL;
+ if (issue_flags & IO_URING_F_NONBLOCK)
+ return -EAGAIN;
+
ublk_ctrl_cmd_dump(cmd);
if (!(issue_flags & IO_URING_F_SQE128))
virtqueue_notify(vq->vq);
}
+static blk_status_t virtblk_fail_to_queue(struct request *req, int rc)
+{
+ virtblk_cleanup_cmd(req);
+ switch (rc) {
+ case -ENOSPC:
+ return BLK_STS_DEV_RESOURCE;
+ case -ENOMEM:
+ return BLK_STS_RESOURCE;
+ default:
+ return BLK_STS_IOERR;
+ }
+}
+
static blk_status_t virtblk_prep_rq(struct blk_mq_hw_ctx *hctx,
struct virtio_blk *vblk,
struct request *req,
struct virtblk_req *vbr)
{
blk_status_t status;
+ int num;
status = virtblk_setup_cmd(vblk->vdev, req, vbr);
if (unlikely(status))
return status;
- vbr->sg_table.nents = virtblk_map_data(hctx, req, vbr);
- if (unlikely(vbr->sg_table.nents < 0)) {
- virtblk_cleanup_cmd(req);
- return BLK_STS_RESOURCE;
- }
+ num = virtblk_map_data(hctx, req, vbr);
+ if (unlikely(num < 0))
+ return virtblk_fail_to_queue(req, -ENOMEM);
+ vbr->sg_table.nents = num;
blk_mq_start_request(req);
blk_mq_stop_hw_queue(hctx);
spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);
virtblk_unmap_data(req, vbr);
- virtblk_cleanup_cmd(req);
- switch (err) {
- case -ENOSPC:
- return BLK_STS_DEV_RESOURCE;
- case -ENOMEM:
- return BLK_STS_RESOURCE;
- default:
- return BLK_STS_IOERR;
- }
+ return virtblk_fail_to_queue(req, err);
}
if (bd->last && virtqueue_kick_prepare(vblk->vqs[qid].vq))
blk_queue_max_segments(q, sg_elems);
/* No real sector limit. */
- blk_queue_max_hw_sectors(q, -1U);
+ blk_queue_max_hw_sectors(q, UINT_MAX);
max_size = virtio_max_dma_size(vdev);
return 0;
}
-static int xen_blkbk_remove(struct xenbus_device *dev)
+static void xen_blkbk_remove(struct xenbus_device *dev)
{
struct backend_info *be = dev_get_drvdata(&dev->dev);
/* Put the reference we set in xen_blkif_alloc(). */
xen_blkif_put(be->blkif);
}
-
- return 0;
}
int xen_blkbk_flush_diskcache(struct xenbus_transaction xbt,
}
}
-static int blkfront_remove(struct xenbus_device *xbdev)
+static void blkfront_remove(struct xenbus_device *xbdev)
{
struct blkfront_info *info = dev_get_drvdata(&xbdev->dev);
}
kfree(info);
- return 0;
}
static int blkfront_is_ready(struct xenbus_device *dev)
}
suspended:
- return rc;
+ if (rc)
+ dev_err(dev, "Ignoring error %d while suspending\n", rc);
+ return 0;
}
EXPORT_SYMBOL_GPL(tpm_pm_suspend);
return tpm_chip_register(priv->chip);
}
-static int tpmfront_remove(struct xenbus_device *dev)
+static void tpmfront_remove(struct xenbus_device *dev)
{
struct tpm_chip *chip = dev_get_drvdata(&dev->dev);
struct tpm_private *priv = dev_get_drvdata(&chip->dev);
tpm_chip_unregister(chip);
ring_free(priv);
dev_set_drvdata(&chip->dev, NULL);
- return 0;
}
static int tpmfront_resume(struct xenbus_device *dev)
max_perf = min_perf;
amd_pstate_update(cpudata, min_perf, des_perf, max_perf, true);
+ cpufreq_cpu_put(policy);
}
static int amd_get_min_freq(struct amd_cpudata *cpudata)
policy->cpuinfo.transition_latency = transition_latency;
policy->dvfs_possible_from_any_cpu = true;
policy->fast_switch_possible = true;
+ policy->suspend_freq = freq_table[0].frequency;
if (policy_has_boost_freq(policy)) {
ret = cpufreq_enable_boost_support();
.flags = CPUFREQ_HAVE_GOVERNOR_PER_POLICY |
CPUFREQ_NEED_INITIAL_FREQ_CHECK | CPUFREQ_IS_COOLING_DEV,
.verify = cpufreq_generic_frequency_table_verify,
- .attr = cpufreq_generic_attr,
.get = apple_soc_cpufreq_get_rate,
.init = apple_soc_cpufreq_init,
.exit = apple_soc_cpufreq_exit,
.fast_switch = apple_soc_cpufreq_fast_switch,
.register_em = cpufreq_register_em_with_opp,
.attr = apple_soc_cpufreq_hw_attr,
+ .suspend = cpufreq_generic_suspend,
};
static int __init apple_soc_cpufreq_module_init(void)
return -ENODEV;
}
- clk = clk_get(cpu_dev, 0);
+ clk = clk_get(cpu_dev, NULL);
if (IS_ERR(clk)) {
dev_err(cpu_dev, "Cannot get clock for CPU0\n");
return PTR_ERR(clk);
cpu_data = policy->driver_data;
perf_caps = &cpu_data->perf_caps;
max_cap = arch_scale_cpu_capacity(cpu);
- min_cap = div_u64(max_cap * perf_caps->lowest_perf, perf_caps->highest_perf);
+ min_cap = div_u64((u64)max_cap * perf_caps->lowest_perf,
+ perf_caps->highest_perf);
if ((min_cap == 0) || (max_cap < min_cap))
return 0;
return 1 + max_cap / CPPC_EM_CAP_STEP - min_cap / CPPC_EM_CAP_STEP;
cpu_data = policy->driver_data;
perf_caps = &cpu_data->perf_caps;
max_cap = arch_scale_cpu_capacity(cpu_dev->id);
- min_cap = div_u64(max_cap * perf_caps->lowest_perf,
- perf_caps->highest_perf);
-
- perf_step = CPPC_EM_CAP_STEP * perf_caps->highest_perf / max_cap;
+ min_cap = div_u64((u64)max_cap * perf_caps->lowest_perf,
+ perf_caps->highest_perf);
+ perf_step = div_u64((u64)CPPC_EM_CAP_STEP * perf_caps->highest_perf,
+ max_cap);
min_step = min_cap / CPPC_EM_CAP_STEP;
max_step = max_cap / CPPC_EM_CAP_STEP;
{ .compatible = "nvidia,tegra30", },
{ .compatible = "nvidia,tegra124", },
{ .compatible = "nvidia,tegra210", },
+ { .compatible = "nvidia,tegra234", },
{ .compatible = "qcom,apq8096", },
{ .compatible = "qcom,msm8996", },
{ .compatible = "qcom,sdm845", },
{ .compatible = "qcom,sm6115", },
{ .compatible = "qcom,sm6350", },
+ { .compatible = "qcom,sm6375", },
{ .compatible = "qcom,sm8150", },
{ .compatible = "qcom,sm8250", },
{ .compatible = "qcom,sm8350", },
{
struct clk_hw_onecell_data *clk_data;
struct device *dev = &pdev->dev;
+ struct device_node *soc_node;
struct device *cpu_dev;
struct clk *clk;
- int ret, i, num_domains;
+ int ret, i, num_domains, reg_sz;
clk = clk_get(dev, "xo");
if (IS_ERR(clk))
return ret;
/* Allocate qcom_cpufreq_data based on the available frequency domains in DT */
- num_domains = of_property_count_elems_of_size(dev->of_node, "reg", sizeof(u32) * 4);
+ soc_node = of_get_parent(dev->of_node);
+ if (!soc_node)
+ return -EINVAL;
+
+ ret = of_property_read_u32(soc_node, "#address-cells", ®_sz);
+ if (ret)
+ goto of_exit;
+
+ ret = of_property_read_u32(soc_node, "#size-cells", &i);
+ if (ret)
+ goto of_exit;
+
+ reg_sz += i;
+
+ num_domains = of_property_count_elems_of_size(dev->of_node, "reg", sizeof(u32) * reg_sz);
if (num_domains <= 0)
return num_domains;
else
dev_dbg(dev, "QCOM CPUFreq HW driver initialized\n");
+of_exit:
+ of_node_put(soc_node);
+
return ret;
}
* Microchip / Atmel ECC (I2C) driver.
*
* Copyright (c) 2017, Microchip Technology Inc.
- * Author: Tudor Ambarus <tudor.ambarus@microchip.com>
+ * Author: Tudor Ambarus
*/
#include <linux/delay.h>
module_init(atmel_ecc_init);
module_exit(atmel_ecc_exit);
-MODULE_AUTHOR("Tudor Ambarus <tudor.ambarus@microchip.com>");
+MODULE_AUTHOR("Tudor Ambarus");
MODULE_DESCRIPTION("Microchip / Atmel ECC (I2C) driver");
MODULE_LICENSE("GPL v2");
* Microchip / Atmel ECC (I2C) driver.
*
* Copyright (c) 2017, Microchip Technology Inc.
- * Author: Tudor Ambarus <tudor.ambarus@microchip.com>
+ * Author: Tudor Ambarus
*/
#include <linux/bitrev.h>
module_init(atmel_i2c_init);
module_exit(atmel_i2c_exit);
-MODULE_AUTHOR("Tudor Ambarus <tudor.ambarus@microchip.com>");
+MODULE_AUTHOR("Tudor Ambarus");
MODULE_DESCRIPTION("Microchip / Atmel ECC (I2C) driver");
MODULE_LICENSE("GPL v2");
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (c) 2017, Microchip Technology Inc.
- * Author: Tudor Ambarus <tudor.ambarus@microchip.com>
+ * Author: Tudor Ambarus
*/
#ifndef __ATMEL_I2C_H__
}
ctrlpriv = dev_get_drvdata(jrdev->parent);
- moo = FIELD_GET(CSTA_MOO, ioread32(&ctrlpriv->ctrl->perfmon.status));
+ moo = FIELD_GET(CSTA_MOO, rd_reg32(&ctrlpriv->ctrl->perfmon.status));
if (moo != CSTA_MOO_SECURE && moo != CSTA_MOO_TRUSTED)
dev_warn(jrdev,
"using insecure test key, enable HAB to use unique device key!\n");
pr_err("virtio_crypto: Close session failed status: %u, session_id: 0x%llx\n",
ctrl_status->status, destroy_session->session_id);
- return -EINVAL;
+ err = -EINVAL;
+ goto out;
}
err = 0;
kset_unregister(dma_buf_stats_kset);
}
-int dma_buf_stats_setup(struct dma_buf *dmabuf)
+int dma_buf_stats_setup(struct dma_buf *dmabuf, struct file *file)
{
struct dma_buf_sysfs_entry *sysfs_entry;
int ret;
- if (!dmabuf || !dmabuf->file)
- return -EINVAL;
-
if (!dmabuf->exp_name) {
pr_err("exporter name must not be empty if stats needed\n");
return -EINVAL;
/* create the directory for buffer stats */
ret = kobject_init_and_add(&sysfs_entry->kobj, &dma_buf_ktype, NULL,
- "%lu", file_inode(dmabuf->file)->i_ino);
+ "%lu", file_inode(file)->i_ino);
if (ret)
goto err_sysfs_dmabuf;
int dma_buf_init_sysfs_statistics(void);
void dma_buf_uninit_sysfs_statistics(void);
-int dma_buf_stats_setup(struct dma_buf *dmabuf);
+int dma_buf_stats_setup(struct dma_buf *dmabuf, struct file *file);
void dma_buf_stats_teardown(struct dma_buf *dmabuf);
#else
static inline void dma_buf_uninit_sysfs_statistics(void) {}
-static inline int dma_buf_stats_setup(struct dma_buf *dmabuf)
+static inline int dma_buf_stats_setup(struct dma_buf *dmabuf, struct file *file)
{
return 0;
}
return -EINVAL;
dmabuf = file->private_data;
-
- mutex_lock(&db_list.lock);
- list_del(&dmabuf->list_node);
- mutex_unlock(&db_list.lock);
+ if (dmabuf) {
+ mutex_lock(&db_list.lock);
+ list_del(&dmabuf->list_node);
+ mutex_unlock(&db_list.lock);
+ }
return 0;
}
return file->f_op == &dma_buf_fops;
}
-static struct file *dma_buf_getfile(struct dma_buf *dmabuf, int flags)
+static struct file *dma_buf_getfile(size_t size, int flags)
{
static atomic64_t dmabuf_inode = ATOMIC64_INIT(0);
- struct file *file;
struct inode *inode = alloc_anon_inode(dma_buf_mnt->mnt_sb);
+ struct file *file;
if (IS_ERR(inode))
return ERR_CAST(inode);
- inode->i_size = dmabuf->size;
- inode_set_bytes(inode, dmabuf->size);
+ inode->i_size = size;
+ inode_set_bytes(inode, size);
/*
* The ->i_ino acquired from get_next_ino() is not unique thus
flags, &dma_buf_fops);
if (IS_ERR(file))
goto err_alloc_file;
- file->private_data = dmabuf;
- file->f_path.dentry->d_fsdata = dmabuf;
return file;
size_t alloc_size = sizeof(struct dma_buf);
int ret;
- if (!exp_info->resv)
- alloc_size += sizeof(struct dma_resv);
- else
- /* prevent &dma_buf[1] == dma_buf->resv */
- alloc_size += 1;
-
- if (WARN_ON(!exp_info->priv
- || !exp_info->ops
- || !exp_info->ops->map_dma_buf
- || !exp_info->ops->unmap_dma_buf
- || !exp_info->ops->release)) {
+ if (WARN_ON(!exp_info->priv || !exp_info->ops
+ || !exp_info->ops->map_dma_buf
+ || !exp_info->ops->unmap_dma_buf
+ || !exp_info->ops->release))
return ERR_PTR(-EINVAL);
- }
if (WARN_ON(exp_info->ops->cache_sgt_mapping &&
(exp_info->ops->pin || exp_info->ops->unpin)))
if (!try_module_get(exp_info->owner))
return ERR_PTR(-ENOENT);
+ file = dma_buf_getfile(exp_info->size, exp_info->flags);
+ if (IS_ERR(file)) {
+ ret = PTR_ERR(file);
+ goto err_module;
+ }
+
+ if (!exp_info->resv)
+ alloc_size += sizeof(struct dma_resv);
+ else
+ /* prevent &dma_buf[1] == dma_buf->resv */
+ alloc_size += 1;
dmabuf = kzalloc(alloc_size, GFP_KERNEL);
if (!dmabuf) {
ret = -ENOMEM;
- goto err_module;
+ goto err_file;
}
dmabuf->priv = exp_info->priv;
init_waitqueue_head(&dmabuf->poll);
dmabuf->cb_in.poll = dmabuf->cb_out.poll = &dmabuf->poll;
dmabuf->cb_in.active = dmabuf->cb_out.active = 0;
+ INIT_LIST_HEAD(&dmabuf->attachments);
if (!resv) {
- resv = (struct dma_resv *)&dmabuf[1];
- dma_resv_init(resv);
+ dmabuf->resv = (struct dma_resv *)&dmabuf[1];
+ dma_resv_init(dmabuf->resv);
+ } else {
+ dmabuf->resv = resv;
}
- dmabuf->resv = resv;
- file = dma_buf_getfile(dmabuf, exp_info->flags);
- if (IS_ERR(file)) {
- ret = PTR_ERR(file);
+ ret = dma_buf_stats_setup(dmabuf, file);
+ if (ret)
goto err_dmabuf;
- }
+ file->private_data = dmabuf;
+ file->f_path.dentry->d_fsdata = dmabuf;
dmabuf->file = file;
- INIT_LIST_HEAD(&dmabuf->attachments);
-
mutex_lock(&db_list.lock);
list_add(&dmabuf->list_node, &db_list.head);
mutex_unlock(&db_list.lock);
- ret = dma_buf_stats_setup(dmabuf);
- if (ret)
- goto err_sysfs;
-
return dmabuf;
-err_sysfs:
- /*
- * Set file->f_path.dentry->d_fsdata to NULL so that when
- * dma_buf_release() gets invoked by dentry_ops, it exits
- * early before calling the release() dma_buf op.
- */
- file->f_path.dentry->d_fsdata = NULL;
- fput(file);
err_dmabuf:
+ if (!resv)
+ dma_resv_fini(dmabuf->resv);
kfree(dmabuf);
+err_file:
+ fput(file);
err_module:
module_put(exp_info->owner);
return ERR_PTR(ret);
* Then restart the workq on the new delay
*/
void edac_device_reset_delay_period(struct edac_device_ctl_info *edac_dev,
- unsigned long value)
+ unsigned long msec)
{
- unsigned long jiffs = msecs_to_jiffies(value);
-
- if (value == 1000)
- jiffs = round_jiffies_relative(value);
-
- edac_dev->poll_msec = value;
- edac_dev->delay = jiffs;
+ edac_dev->poll_msec = msec;
+ edac_dev->delay = msecs_to_jiffies(msec);
- edac_mod_work(&edac_dev->work, jiffs);
+ /* See comment in edac_device_workq_setup() above */
+ if (edac_dev->poll_msec == 1000)
+ edac_mod_work(&edac_dev->work, round_jiffies_relative(edac_dev->delay));
+ else
+ edac_mod_work(&edac_dev->work, edac_dev->delay);
}
int edac_device_alloc_index(void)
bool edac_mod_work(struct delayed_work *work, unsigned long delay);
extern void edac_device_reset_delay_period(struct edac_device_ctl_info
- *edac_dev, unsigned long value);
+ *edac_dev, unsigned long msec);
extern void edac_mc_reset_delay_period(unsigned long value);
/*
drvdata = mci->pvt_info;
platform_set_drvdata(pdev, mci);
- if (!devres_open_group(&pdev->dev, NULL, GFP_KERNEL))
- return -ENOMEM;
+ if (!devres_open_group(&pdev->dev, NULL, GFP_KERNEL)) {
+ res = -ENOMEM;
+ goto free;
+ }
r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (!r) {
edac_mc_del_mc(&pdev->dev);
err:
devres_release_group(&pdev->dev, NULL);
+free:
edac_mc_free(mci);
return res;
}
efi_kobj = kobject_create_and_add("efi", firmware_kobj);
if (!efi_kobj) {
pr_err("efi: Firmware registration failed.\n");
- destroy_workqueue(efi_rts_wq);
- return -ENOMEM;
+ error = -ENOMEM;
+ goto err_destroy_wq;
}
if (efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE |
err_put:
kobject_put(efi_kobj);
efi_kobj = NULL;
- destroy_workqueue(efi_rts_wq);
+err_destroy_wq:
+ if (efi_rts_wq)
+ destroy_workqueue(efi_rts_wq);
+
return error;
}
\
if (!efi_enabled(EFI_RUNTIME_SERVICES)) { \
pr_warn_once("EFI Runtime Services are disabled!\n"); \
+ efi_rts_work.status = EFI_DEVICE_ERROR; \
goto exit; \
} \
\
for (i = 0; i < header->table_entries; i++) {
entry = ptr_entry;
- device = kzalloc(sizeof(struct device) + entry->size, GFP_KERNEL);
+ if (entry->size < sizeof(*entry)) {
+ dev_warn(dev, "coreboot table entry too small!\n");
+ return -EINVAL;
+ }
+
+ device = kzalloc(sizeof(device->dev) + entry->size, GFP_KERNEL);
if (!device)
return -ENOMEM;
device->dev.parent = dev;
device->dev.bus = &coreboot_bus_type;
device->dev.release = coreboot_device_release;
- memcpy(&device->entry, ptr_entry, entry->size);
+ memcpy(device->raw, ptr_entry, entry->size);
switch (device->entry.tag) {
case LB_TAG_CBMEM_ENTRY:
struct lb_cbmem_ref cbmem_ref;
struct lb_cbmem_entry cbmem_entry;
struct lb_framebuffer framebuffer;
+ DECLARE_FLEX_ARRAY(u8, raw);
};
};
static int __init psci_debugfs_init(void)
{
+ if (!invoke_psci_fn || !psci_ops.get_version)
+ return 0;
+
return PTR_ERR_OR_ZERO(debugfs_create_file("psci", 0444, NULL, NULL,
&psci_debugfs_ops));
}
struct sprd_eic {
struct gpio_chip chip;
- struct irq_chip intc;
void __iomem *base[SPRD_EIC_MAX_BANK];
enum sprd_eic_type type;
spinlock_t lock;
default:
dev_err(chip->parent, "Unsupported EIC type.\n");
}
+
+ gpiochip_disable_irq(chip, offset);
}
static void sprd_eic_irq_unmask(struct irq_data *data)
struct sprd_eic *sprd_eic = gpiochip_get_data(chip);
u32 offset = irqd_to_hwirq(data);
+ gpiochip_enable_irq(chip, offset);
+
switch (sprd_eic->type) {
case SPRD_EIC_DEBOUNCE:
sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IE, 1);
chained_irq_exit(ic, desc);
}
+static const struct irq_chip sprd_eic_irq = {
+ .name = "sprd-eic",
+ .irq_ack = sprd_eic_irq_ack,
+ .irq_mask = sprd_eic_irq_mask,
+ .irq_unmask = sprd_eic_irq_unmask,
+ .irq_set_type = sprd_eic_irq_set_type,
+ .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_IMMUTABLE,
+ GPIOCHIP_IRQ_RESOURCE_HELPERS,
+};
static int sprd_eic_probe(struct platform_device *pdev)
{
const struct sprd_eic_variant_data *pdata;
break;
}
- sprd_eic->intc.name = dev_name(&pdev->dev);
- sprd_eic->intc.irq_ack = sprd_eic_irq_ack;
- sprd_eic->intc.irq_mask = sprd_eic_irq_mask;
- sprd_eic->intc.irq_unmask = sprd_eic_irq_unmask;
- sprd_eic->intc.irq_set_type = sprd_eic_irq_set_type;
- sprd_eic->intc.flags = IRQCHIP_SKIP_SET_WAKE;
-
irq = &sprd_eic->chip.irq;
- irq->chip = &sprd_eic->intc;
+ gpio_irq_chip_set_chip(irq, &sprd_eic_irq);
irq->handler = handle_bad_irq;
irq->default_type = IRQ_TYPE_NONE;
irq->parent_handler = sprd_eic_irq_handler;
case PCAL6524_DEBOUNCE:
pinctrl = ((reg & PCAL_PINCTRL_MASK) >> 1) + 0x1c;
break;
+ default:
+ pinctrl = 0;
+ break;
}
return pinctrl + addr + (off / BANK_SZ);
/**
* struct sprd_pmic_eic - PMIC EIC controller
* @chip: the gpio_chip structure.
- * @intc: the irq_chip structure.
* @map: the regmap from the parent device.
* @offset: the EIC controller's offset address of the PMIC.
* @reg: the array to cache the EIC registers.
*/
struct sprd_pmic_eic {
struct gpio_chip chip;
- struct irq_chip intc;
struct regmap *map;
u32 offset;
u8 reg[CACHE_NR_REGS];
{
struct gpio_chip *chip = irq_data_get_irq_chip_data(data);
struct sprd_pmic_eic *pmic_eic = gpiochip_get_data(chip);
+ u32 offset = irqd_to_hwirq(data);
pmic_eic->reg[REG_IE] = 0;
pmic_eic->reg[REG_TRIG] = 0;
+
+ gpiochip_disable_irq(chip, offset);
}
static void sprd_pmic_eic_irq_unmask(struct irq_data *data)
{
struct gpio_chip *chip = irq_data_get_irq_chip_data(data);
struct sprd_pmic_eic *pmic_eic = gpiochip_get_data(chip);
+ u32 offset = irqd_to_hwirq(data);
+
+ gpiochip_enable_irq(chip, offset);
pmic_eic->reg[REG_IE] = 1;
pmic_eic->reg[REG_TRIG] = 1;
return IRQ_HANDLED;
}
+static const struct irq_chip pmic_eic_irq_chip = {
+ .name = "sprd-pmic-eic",
+ .irq_mask = sprd_pmic_eic_irq_mask,
+ .irq_unmask = sprd_pmic_eic_irq_unmask,
+ .irq_set_type = sprd_pmic_eic_irq_set_type,
+ .irq_bus_lock = sprd_pmic_eic_bus_lock,
+ .irq_bus_sync_unlock = sprd_pmic_eic_bus_sync_unlock,
+ .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_IMMUTABLE,
+ GPIOCHIP_IRQ_RESOURCE_HELPERS,
+};
+
static int sprd_pmic_eic_probe(struct platform_device *pdev)
{
struct gpio_irq_chip *irq;
pmic_eic->chip.set = sprd_pmic_eic_set;
pmic_eic->chip.get = sprd_pmic_eic_get;
- pmic_eic->intc.name = dev_name(&pdev->dev);
- pmic_eic->intc.irq_mask = sprd_pmic_eic_irq_mask;
- pmic_eic->intc.irq_unmask = sprd_pmic_eic_irq_unmask;
- pmic_eic->intc.irq_set_type = sprd_pmic_eic_irq_set_type;
- pmic_eic->intc.irq_bus_lock = sprd_pmic_eic_bus_lock;
- pmic_eic->intc.irq_bus_sync_unlock = sprd_pmic_eic_bus_sync_unlock;
- pmic_eic->intc.flags = IRQCHIP_SKIP_SET_WAKE;
-
irq = &pmic_eic->chip.irq;
- irq->chip = &pmic_eic->intc;
+ gpio_irq_chip_set_chip(irq, &pmic_eic_irq_chip);
irq->threaded = true;
ret = devm_gpiochip_add_data(&pdev->dev, &pmic_eic->chip, pmic_eic);
return -ENODEV;
}
parent = irq_find_host(irq_parent);
+ of_node_put(irq_parent);
if (!parent) {
dev_err(dev, "no IRQ parent domain\n");
return -ENODEV;
u32 offset = irqd_to_hwirq(data);
sprd_gpio_update(chip, offset, SPRD_GPIO_IE, 0);
+ gpiochip_disable_irq(chip, offset);
}
static void sprd_gpio_irq_ack(struct irq_data *data)
u32 offset = irqd_to_hwirq(data);
sprd_gpio_update(chip, offset, SPRD_GPIO_IE, 1);
+ gpiochip_enable_irq(chip, offset);
}
static int sprd_gpio_irq_set_type(struct irq_data *data,
chained_irq_exit(ic, desc);
}
-static struct irq_chip sprd_gpio_irqchip = {
+static const struct irq_chip sprd_gpio_irqchip = {
.name = "sprd-gpio",
.irq_ack = sprd_gpio_irq_ack,
.irq_mask = sprd_gpio_irq_mask,
.irq_unmask = sprd_gpio_irq_unmask,
.irq_set_type = sprd_gpio_irq_set_type,
- .flags = IRQCHIP_SKIP_SET_WAKE,
+ .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_IMMUTABLE,
+ GPIOCHIP_IRQ_RESOURCE_HELPERS,
};
static int sprd_gpio_probe(struct platform_device *pdev)
sprd_gpio->chip.direction_output = sprd_gpio_direction_output;
irq = &sprd_gpio->chip.irq;
- irq->chip = &sprd_gpio_irqchip;
+ gpio_irq_chip_set_chip(irq, &sprd_gpio_irqchip);
irq->handler = handle_bad_irq;
irq->default_type = IRQ_TYPE_NONE;
irq->parent_handler = sprd_gpio_irq_handler;
const char *label,
bool platform_lookup_allowed)
{
+ unsigned long lookupflags = GPIO_LOOKUP_FLAGS_DEFAULT;
struct gpio_desc *desc = ERR_PTR(-ENOENT);
- unsigned long lookupflags;
int ret;
if (!IS_ERR_OR_NULL(fwnode))
extern uint amdgpu_smu_memory_pool_size;
extern int amdgpu_smu_pptable_id;
extern uint amdgpu_dc_feature_mask;
+extern uint amdgpu_freesync_vid_mode;
extern uint amdgpu_dc_debug_mask;
extern uint amdgpu_dc_visual_confirm;
extern uint amdgpu_dm_abm_level;
}
amdgpu_amdkfd_remove_eviction_fence(
- bo, bo->kfd_bo->process_info->eviction_fence);
+ bo, bo->vm_bo->vm->process_info->eviction_fence);
amdgpu_bo_unreserve(bo);
amdgpu_ctx_put(p->ctx);
return -ECANCELED;
}
+
+ amdgpu_sync_create(&p->sync);
return 0;
}
}
r = amdgpu_sync_fence(&p->sync, fence);
- if (r)
- goto error;
-
- /*
- * When we have an explicit dependency it might be necessary to insert a
- * pipeline sync to make sure that all caches etc are flushed and the
- * next job actually sees the results from the previous one.
- */
- if (fence->context == p->gang_leader->base.entity->fence_context)
- r = amdgpu_sync_fence(&p->gang_leader->explicit_sync, fence);
-
-error:
dma_fence_put(fence);
return r;
}
static int amdgpu_cs_sync_rings(struct amdgpu_cs_parser *p)
{
struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
+ struct drm_gpu_scheduler *sched;
struct amdgpu_bo_list_entry *e;
+ struct dma_fence *fence;
unsigned int i;
int r;
+ r = amdgpu_ctx_wait_prev_fence(p->ctx, p->entities[p->gang_leader_idx]);
+ if (r) {
+ if (r != -ERESTARTSYS)
+ DRM_ERROR("amdgpu_ctx_wait_prev_fence failed.\n");
+ return r;
+ }
+
list_for_each_entry(e, &p->validated, tv.head) {
struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo);
struct dma_resv *resv = bo->tbo.base.resv;
return r;
}
- r = amdgpu_ctx_wait_prev_fence(p->ctx, p->entities[p->gang_leader_idx]);
- if (r && r != -ERESTARTSYS)
- DRM_ERROR("amdgpu_ctx_wait_prev_fence failed.\n");
- return r;
+ sched = p->gang_leader->base.entity->rq->sched;
+ while ((fence = amdgpu_sync_get_fence(&p->sync))) {
+ struct drm_sched_fence *s_fence = to_drm_sched_fence(fence);
+
+ /*
+ * When we have an dependency it might be necessary to insert a
+ * pipeline sync to make sure that all caches etc are flushed and the
+ * next job actually sees the results from the previous one
+ * before we start executing on the same scheduler ring.
+ */
+ if (!s_fence || s_fence->sched != sched)
+ continue;
+
+ r = amdgpu_sync_fence(&p->gang_leader->explicit_sync, fence);
+ if (r)
+ return r;
+ }
+ return 0;
}
static void amdgpu_cs_post_dependencies(struct amdgpu_cs_parser *p)
continue;
fence = &p->jobs[i]->base.s_fence->scheduled;
+ dma_fence_get(fence);
r = drm_sched_job_add_dependency(&leader->base, fence);
- if (r)
+ if (r) {
+ dma_fence_put(fence);
goto error_cleanup;
+ }
}
if (p->gang_size > 1) {
{
unsigned i;
+ amdgpu_sync_free(&parser->sync);
for (i = 0; i < parser->num_post_deps; i++) {
drm_syncobj_put(parser->post_deps[i].syncobj);
kfree(parser->post_deps[i].chain);
#include <generated/utsrelease.h>
#include <linux/pci-p2pdma.h>
+#include <drm/drm_aperture.h>
#include <drm/drm_atomic_helper.h>
#include <drm/drm_fb_helper.h>
#include <drm/drm_probe_helper.h>
#define AMDGPU_MAX_RETRY_LIMIT 2
#define AMDGPU_RETRY_SRIOV_RESET(r) ((r) == -EBUSY || (r) == -ETIMEDOUT || (r) == -EINVAL)
+static const struct drm_driver amdgpu_kms_driver;
+
const char *amdgpu_asic_name[] = {
"TAHITI",
"PITCAIRN",
if (r)
return r;
+ /* Get rid of things like offb */
+ r = drm_aperture_remove_conflicting_pci_framebuffers(adev->pdev, &amdgpu_kms_driver);
+ if (r)
+ return r;
+
/* Enable TMZ based on IP_VERSION */
amdgpu_gmc_tmz_set(adev);
*/
#include <drm/amdgpu_drm.h>
-#include <drm/drm_aperture.h>
#include <drm/drm_drv.h>
#include <drm/drm_fbdev_generic.h>
#include <drm/drm_gem.h>
int amdgpu_noretry = -1;
int amdgpu_force_asic_type = -1;
int amdgpu_tmz = -1; /* auto */
+uint amdgpu_freesync_vid_mode;
int amdgpu_reset_method = -1; /* auto */
int amdgpu_num_kcq = -1;
int amdgpu_smartshift_bias;
module_param_named(tmz, amdgpu_tmz, int, 0444);
/**
+ * DOC: freesync_video (uint)
+ * Enable the optimization to adjust front porch timing to achieve seamless
+ * mode change experience when setting a freesync supported mode for which full
+ * modeset is not needed.
+ *
+ * The Display Core will add a set of modes derived from the base FreeSync
+ * video mode into the corresponding connector's mode list based on commonly
+ * used refresh rates and VRR range of the connected display, when users enable
+ * this feature. From the userspace perspective, they can see a seamless mode
+ * change experience when the change between different refresh rates under the
+ * same resolution. Additionally, userspace applications such as Video playback
+ * can read this modeset list and change the refresh rate based on the video
+ * frame rate. Finally, the userspace can also derive an appropriate mode for a
+ * particular refresh rate based on the FreeSync Mode and add it to the
+ * connector's mode list.
+ *
+ * Note: This is an experimental feature.
+ *
+ * The default value: 0 (off).
+ */
+MODULE_PARM_DESC(
+ freesync_video,
+ "Enable freesync modesetting optimization feature (0 = off (default), 1 = on)");
+module_param_named(freesync_video, amdgpu_freesync_vid_mode, uint, 0444);
+
+/**
* DOC: reset_method (int)
* GPU reset method (-1 = auto (default), 0 = legacy, 1 = mode0, 2 = mode1, 3 = mode2, 4 = baco)
*/
}
#endif
- /* Get rid of things like offb */
- ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &amdgpu_kms_driver);
- if (ret)
- return ret;
-
adev = devm_drm_dev_alloc(&pdev->dev, &amdgpu_kms_driver, typeof(*adev), ddev);
if (IS_ERR(adev))
return PTR_ERR(adev);
return true;
fail:
- DRM_DEBUG("BO size %lu > total memory in domain: %llu\n", size,
- man->size);
+ if (man)
+ DRM_DEBUG("BO size %lu > total memory in domain: %llu\n", size,
+ man->size);
return false;
}
dma_fence_get(f);
r = drm_sched_job_add_dependency(&job->base, f);
- if (r)
+ if (r) {
+ dma_fence_put(f);
return r;
+ }
}
return 0;
}
kfree(rsv);
list_for_each_entry_safe(rsv, temp, &mgr->reserved_pages, blocks) {
- drm_buddy_free_list(&mgr->mm, &rsv->blocks);
+ drm_buddy_free_list(&mgr->mm, &rsv->allocated);
kfree(rsv);
}
drm_buddy_fini(&mgr->mm);
queue_input.wptr_addr = (uint64_t)q->properties.write_ptr;
if (q->wptr_bo) {
- wptr_addr_off = (uint64_t)q->properties.write_ptr - (uint64_t)q->wptr_bo->kfd_bo->va;
+ wptr_addr_off = (uint64_t)q->properties.write_ptr & (PAGE_SIZE - 1);
queue_input.wptr_mc_addr = ((uint64_t)q->wptr_bo->tbo.resource->start << PAGE_SHIFT) + wptr_addr_off;
}
goto reserve_bo_failed;
}
+ if (clear) {
+ r = amdgpu_bo_sync_wait(bo, AMDGPU_FENCE_OWNER_KFD, false);
+ if (r) {
+ pr_debug("failed %d to sync bo\n", r);
+ amdgpu_bo_unreserve(bo);
+ goto reserve_bo_failed;
+ }
+ }
+
r = dma_resv_reserve_fences(bo->tbo.base.resv, 1);
if (r) {
pr_debug("failed %d to reserve bo\n", r);
p2plink->attr.name = "properties";
p2plink->attr.mode = KFD_SYSFS_FILE_MODE;
- sysfs_attr_init(&iolink->attr);
+ sysfs_attr_init(&p2plink->attr);
ret = sysfs_create_file(p2plink->kobj, &p2plink->attr);
if (ret < 0)
return ret;
*/
DRM_DEBUG_DRIVER("No preferred mode found\n");
} else {
- recalculate_timing = is_freesync_video_mode(&mode, aconnector);
+ recalculate_timing = amdgpu_freesync_vid_mode &&
+ is_freesync_video_mode(&mode, aconnector);
if (recalculate_timing) {
freesync_mode = get_highest_refresh_rate_mode(aconnector, false);
drm_mode_copy(&saved_mode, &mode);
struct amdgpu_dm_connector *amdgpu_dm_connector =
to_amdgpu_dm_connector(connector);
- if (!edid)
+ if (!(amdgpu_freesync_vid_mode && edid))
return;
if (amdgpu_dm_connector->max_vfreq - amdgpu_dm_connector->min_vfreq > 10)
* TODO: Refactor this function to allow this check to work
* in all conditions.
*/
- if (dm_new_crtc_state->stream &&
+ if (amdgpu_freesync_vid_mode &&
+ dm_new_crtc_state->stream &&
is_timing_unchanged_for_freesync(new_crtc_state, old_crtc_state))
goto skip_modeset;
if (!dm_old_crtc_state->stream)
goto skip_modeset;
- if (dm_new_crtc_state->stream &&
+ if (amdgpu_freesync_vid_mode && dm_new_crtc_state->stream &&
is_timing_unchanged_for_freesync(new_crtc_state,
old_crtc_state)) {
new_crtc_state->mode_changed = false;
set_freesync_fixed_config(dm_new_crtc_state);
goto skip_modeset;
- } else if (aconnector &&
+ } else if (amdgpu_freesync_vid_mode && aconnector &&
is_freesync_video_mode(&new_crtc_state->mode,
aconnector)) {
struct drm_display_mode *high_mode;
double SwathSizePerSurfaceC[DC__NUM_DPP__MAX];
bool NotEnoughDETSwathFillLatencyHiding = false;
- /* calculate sum of single swath size for all pipes in bytes*/
+ /* calculate sum of single swath size for all pipes in bytes */
for (k = 0; k < NumberOfActiveSurfaces; k++) {
- SwathSizePerSurfaceY[k] += SwathHeightY[k] * SwathWidthY[k] * BytePerPixelInDETY[k] * NumOfDPP[k];
+ SwathSizePerSurfaceY[k] = SwathHeightY[k] * SwathWidthY[k] * BytePerPixelInDETY[k] * NumOfDPP[k];
if (SwathHeightC[k] != 0)
- SwathSizePerSurfaceC[k] += SwathHeightC[k] * SwathWidthC[k] * BytePerPixelInDETC[k] * NumOfDPP[k];
+ SwathSizePerSurfaceC[k] = SwathHeightC[k] * SwathWidthC[k] * BytePerPixelInDETC[k] * NumOfDPP[k];
else
SwathSizePerSurfaceC[k] = 0;
uint32_t speed)
{
struct amdgpu_device *adev = smu->adev;
- uint32_t tach_period, crystal_clock_freq;
+ uint32_t crystal_clock_freq = 2500;
+ uint32_t tach_period;
int ret;
if (!speed)
if (ret)
return ret;
- crystal_clock_freq = amdgpu_asic_get_xclk(adev);
tach_period = 60 * crystal_clock_freq * 10000 / (8 * speed);
WREG32_SOC15(THM, 0, regCG_TACH_CTRL,
REG_SET_FIELD(RREG32_SOC15(THM, 0, regCG_TACH_CTRL),
!smu_baco->platform_support)
return false;
+ /* return true if ASIC is in BACO state already */
+ if (smu_v13_0_baco_get_state(smu) == SMU_BACO_STATE_ENTER)
+ return true;
+
if (smu_cmn_feature_is_supported(smu, SMU_FEATURE_BACO_BIT) &&
!smu_cmn_feature_is_enabled(smu, SMU_FEATURE_BACO_BIT))
return false;
FEA_MAP(SOC_PCC),
[SMU_FEATURE_DPM_VCLK_BIT] = {1, FEATURE_MM_DPM_BIT},
[SMU_FEATURE_DPM_DCLK_BIT] = {1, FEATURE_MM_DPM_BIT},
+ [SMU_FEATURE_PPT_BIT] = {1, FEATURE_THROTTLERS_BIT},
};
static struct cmn2asic_mapping smu_v13_0_0_table_map[SMU_TABLE_COUNT] = {
FEA_MAP(SOC_PCC),
[SMU_FEATURE_DPM_VCLK_BIT] = {1, FEATURE_MM_DPM_BIT},
[SMU_FEATURE_DPM_DCLK_BIT] = {1, FEATURE_MM_DPM_BIT},
+ [SMU_FEATURE_PPT_BIT] = {1, FEATURE_THROTTLERS_BIT},
};
static struct cmn2asic_mapping smu_v13_0_7_table_map[SMU_TABLE_COUNT] = {
kmem_cache_free(slab_blocks, block);
}
+static void list_insert_sorted(struct drm_buddy *mm,
+ struct drm_buddy_block *block)
+{
+ struct drm_buddy_block *node;
+ struct list_head *head;
+
+ head = &mm->free_list[drm_buddy_block_order(block)];
+ if (list_empty(head)) {
+ list_add(&block->link, head);
+ return;
+ }
+
+ list_for_each_entry(node, head, link)
+ if (drm_buddy_block_offset(block) < drm_buddy_block_offset(node))
+ break;
+
+ __list_add(&block->link, node->link.prev, &node->link);
+}
+
static void mark_allocated(struct drm_buddy_block *block)
{
block->header &= ~DRM_BUDDY_HEADER_STATE;
block->header &= ~DRM_BUDDY_HEADER_STATE;
block->header |= DRM_BUDDY_FREE;
- list_add(&block->link,
- &mm->free_list[drm_buddy_block_order(block)]);
+ list_insert_sorted(mm, block);
}
static void mark_split(struct drm_buddy_block *block)
}
static struct drm_buddy_block *
-get_maxblock(struct list_head *head)
+get_maxblock(struct drm_buddy *mm, unsigned int order)
{
struct drm_buddy_block *max_block = NULL, *node;
+ unsigned int i;
- max_block = list_first_entry_or_null(head,
- struct drm_buddy_block,
- link);
- if (!max_block)
- return NULL;
+ for (i = order; i <= mm->max_order; ++i) {
+ if (!list_empty(&mm->free_list[i])) {
+ node = list_last_entry(&mm->free_list[i],
+ struct drm_buddy_block,
+ link);
+ if (!max_block) {
+ max_block = node;
+ continue;
+ }
- list_for_each_entry(node, head, link) {
- if (drm_buddy_block_offset(node) >
- drm_buddy_block_offset(max_block))
- max_block = node;
+ if (drm_buddy_block_offset(node) >
+ drm_buddy_block_offset(max_block)) {
+ max_block = node;
+ }
+ }
}
return max_block;
unsigned long flags)
{
struct drm_buddy_block *block = NULL;
- unsigned int i;
+ unsigned int tmp;
int err;
- for (i = order; i <= mm->max_order; ++i) {
- if (flags & DRM_BUDDY_TOPDOWN_ALLOCATION) {
- block = get_maxblock(&mm->free_list[i]);
- if (block)
- break;
- } else {
- block = list_first_entry_or_null(&mm->free_list[i],
- struct drm_buddy_block,
- link);
- if (block)
- break;
+ if (flags & DRM_BUDDY_TOPDOWN_ALLOCATION) {
+ block = get_maxblock(mm, order);
+ if (block)
+ /* Store the obtained block order */
+ tmp = drm_buddy_block_order(block);
+ } else {
+ for (tmp = order; tmp <= mm->max_order; ++tmp) {
+ if (!list_empty(&mm->free_list[tmp])) {
+ block = list_last_entry(&mm->free_list[tmp],
+ struct drm_buddy_block,
+ link);
+ if (block)
+ break;
+ }
}
}
BUG_ON(!drm_buddy_block_is_free(block));
- while (i != order) {
+ while (tmp != order) {
err = split_block(mm, block);
if (unlikely(err))
goto err_undo;
block = block->right;
- i--;
+ tmp--;
}
return block;
err_undo:
- if (i != order)
+ if (tmp != order)
__drm_buddy_free(mm, block);
return ERR_PTR(err);
}
DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad D330-10IGM"),
},
.driver_data = (void *)&lcd1200x1920_rightside_up,
+ }, { /* Lenovo Ideapad D330-10IGL (HD) */
+ .matches = {
+ DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad D330-10IGL"),
+ },
+ .driver_data = (void *)&lcd800x1280_rightside_up,
}, { /* Lenovo Yoga Book X90F / X91F / X91L */
.matches = {
/* Non exact match to match all versions */
init_contexts(&i915->gem.contexts);
}
+/*
+ * Note that this implicitly consumes the ctx reference, by placing
+ * the ctx in the context_xa.
+ */
static void gem_context_register(struct i915_gem_context *ctx,
struct drm_i915_file_private *fpriv,
u32 id)
snprintf(ctx->name, sizeof(ctx->name), "%s[%d]",
current->comm, pid_nr(ctx->pid));
- /* And finally expose ourselves to userspace via the idr */
- old = xa_store(&fpriv->context_xa, id, ctx, GFP_KERNEL);
- WARN_ON(old);
-
spin_lock(&ctx->client->ctx_lock);
list_add_tail_rcu(&ctx->client_link, &ctx->client->ctx_list);
spin_unlock(&ctx->client->ctx_lock);
spin_lock(&i915->gem.contexts.lock);
list_add_tail(&ctx->link, &i915->gem.contexts.list);
spin_unlock(&i915->gem.contexts.lock);
+
+ /* And finally expose ourselves to userspace via the idr */
+ old = xa_store(&fpriv->context_xa, id, ctx, GFP_KERNEL);
+ WARN_ON(old);
}
int i915_gem_context_open(struct drm_i915_private *i915,
if (IS_ERR(ctx))
return ctx;
+ /*
+ * One for the xarray and one for the caller. We need to grab
+ * the reference *prior* to making the ctx visble to userspace
+ * in gem_context_register(), as at any point after that
+ * userspace can try to race us with another thread destroying
+ * the context under our feet.
+ */
+ i915_gem_context_get(ctx);
+
gem_context_register(ctx, file_priv, id);
old = xa_erase(&file_priv->proto_context_xa, id);
GEM_BUG_ON(old != pc);
proto_context_close(file_priv->dev_priv, pc);
- /* One for the xarray and one for the caller */
- return i915_gem_context_get(ctx);
+ return ctx;
}
struct i915_gem_context *
#define GEN9_WM_CHICKEN3 _MMIO(0x5588)
#define GEN9_FACTOR_IN_CLR_VAL_HIZ (1 << 9)
-#define CHICKEN_RASTER_1 _MMIO(0x6204)
+#define CHICKEN_RASTER_1 MCR_REG(0x6204)
#define DIS_SF_ROUND_NEAREST_EVEN REG_BIT(8)
-#define CHICKEN_RASTER_2 _MMIO(0x6208)
+#define CHICKEN_RASTER_2 MCR_REG(0x6208)
#define TBIMR_FAST_CLIP REG_BIT(5)
#define VFLSKPD MCR_REG(0x62a8)
static int gen6_hw_domain_reset(struct intel_gt *gt, u32 hw_domain_mask)
{
struct intel_uncore *uncore = gt->uncore;
+ int loops = 2;
int err;
/*
* for fifo space for the write or forcewake the chip for
* the read
*/
- intel_uncore_write_fw(uncore, GEN6_GDRST, hw_domain_mask);
+ do {
+ intel_uncore_write_fw(uncore, GEN6_GDRST, hw_domain_mask);
- /* Wait for the device to ack the reset requests */
- err = __intel_wait_for_register_fw(uncore,
- GEN6_GDRST, hw_domain_mask, 0,
- 500, 0,
- NULL);
+ /*
+ * Wait for the device to ack the reset requests.
+ *
+ * On some platforms, e.g. Jasperlake, we see that the
+ * engine register state is not cleared until shortly after
+ * GDRST reports completion, causing a failure as we try
+ * to immediately resume while the internal state is still
+ * in flux. If we immediately repeat the reset, the second
+ * reset appears to serialise with the first, and since
+ * it is a no-op, the registers should retain their reset
+ * value. However, there is still a concern that upon
+ * leaving the second reset, the internal engine state
+ * is still in flux and not ready for resuming.
+ */
+ err = __intel_wait_for_register_fw(uncore, GEN6_GDRST,
+ hw_domain_mask, 0,
+ 2000, 0,
+ NULL);
+ } while (err == 0 && --loops);
if (err)
GT_TRACE(gt,
"Wait for 0x%08x engines reset failed\n",
hw_domain_mask);
+ /*
+ * As we have observed that the engine state is still volatile
+ * after GDRST is acked, impose a small delay to let everything settle.
+ */
+ udelay(50);
+
return err;
}
static void dg2_ctx_gt_tuning_init(struct intel_engine_cs *engine,
struct i915_wa_list *wal)
{
- wa_masked_en(wal, CHICKEN_RASTER_2, TBIMR_FAST_CLIP);
+ wa_mcr_masked_en(wal, CHICKEN_RASTER_2, TBIMR_FAST_CLIP);
wa_mcr_write_clr_set(wal, XEHP_L3SQCREG5, L3_PWM_TIMER_INIT_VAL_MASK,
REG_FIELD_PREP(L3_PWM_TIMER_INIT_VAL_MASK, 0x7f));
wa_mcr_add(wal,
wa_masked_field_set(wal, VF_PREEMPTION, PREEMPTION_VERTEX_COUNT, 0x4000);
/* Wa_15010599737:dg2 */
- wa_masked_en(wal, CHICKEN_RASTER_1, DIS_SF_ROUND_NEAREST_EVEN);
+ wa_mcr_masked_en(wal, CHICKEN_RASTER_1, DIS_SF_ROUND_NEAREST_EVEN);
}
static void fakewa_disable_nestedbb_mode(struct intel_engine_cs *engine,
vgpu_scan_nonprivbb_get, vgpu_scan_nonprivbb_set,
"0x%llx\n");
+static int vgpu_status_get(void *data, u64 *val)
+{
+ struct intel_vgpu *vgpu = (struct intel_vgpu *)data;
+
+ *val = 0;
+
+ if (test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
+ *val |= (1 << INTEL_VGPU_STATUS_ATTACHED);
+ if (test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status))
+ *val |= (1 << INTEL_VGPU_STATUS_ACTIVE);
+
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(vgpu_status_fops, vgpu_status_get, NULL, "0x%llx\n");
+
/**
* intel_gvt_debugfs_add_vgpu - register debugfs entries for a vGPU
* @vgpu: a vGPU
snprintf(name, 16, "vgpu%d", vgpu->id);
vgpu->debugfs = debugfs_create_dir(name, vgpu->gvt->debugfs_root);
- debugfs_create_bool("active", 0444, vgpu->debugfs, &vgpu->active);
debugfs_create_file("mmio_diff", 0444, vgpu->debugfs, vgpu,
&vgpu_mmio_diff_fops);
debugfs_create_file("scan_nonprivbb", 0644, vgpu->debugfs, vgpu,
&vgpu_scan_nonprivbb_fops);
+ debugfs_create_file("status", 0644, vgpu->debugfs, vgpu,
+ &vgpu_status_fops);
}
/**
*/
void intel_gvt_debugfs_remove_vgpu(struct intel_vgpu *vgpu)
{
- debugfs_remove_recursive(vgpu->debugfs);
- vgpu->debugfs = NULL;
+ struct intel_gvt *gvt = vgpu->gvt;
+ struct drm_minor *minor = gvt->gt->i915->drm.primary;
+
+ if (minor->debugfs_root && gvt->debugfs_root) {
+ debugfs_remove_recursive(vgpu->debugfs);
+ vgpu->debugfs = NULL;
+ }
}
/**
*/
void intel_gvt_debugfs_clean(struct intel_gvt *gvt)
{
- debugfs_remove_recursive(gvt->debugfs_root);
- gvt->debugfs_root = NULL;
+ struct drm_minor *minor = gvt->gt->i915->drm.primary;
+
+ if (minor->debugfs_root) {
+ debugfs_remove_recursive(gvt->debugfs_root);
+ gvt->debugfs_root = NULL;
+ }
}
struct list_head *pos;
struct intel_vgpu_dmabuf_obj *dmabuf_obj;
- if (vgpu && vgpu->active && !list_empty(&vgpu->dmabuf_obj_list_head)) {
+ if (vgpu && test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status) &&
+ !list_empty(&vgpu->dmabuf_obj_list_head)) {
list_for_each(pos, &vgpu->dmabuf_obj_list_head) {
dmabuf_obj = list_entry(pos, struct intel_vgpu_dmabuf_obj, list);
if (dmabuf_obj == obj) {
int idx;
bool ret;
- if (!vgpu->attached)
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
return false;
idx = srcu_read_lock(&kvm->srcu);
if (!HAS_PAGE_SIZES(vgpu->gvt->gt->i915, I915_GTT_PAGE_SIZE_2M))
return 0;
- if (!vgpu->attached)
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
return -EINVAL;
pfn = gfn_to_pfn(vgpu->vfio_device.kvm, ops->get_pfn(entry));
if (is_error_noslot_pfn(pfn))
for_each_shadow_entry(sub_spt, &sub_se, sub_index) {
ret = intel_gvt_dma_map_guest_page(vgpu, start_gfn + sub_index,
PAGE_SIZE, &dma_addr);
- if (ret) {
- ppgtt_invalidate_spt(spt);
- return ret;
- }
+ if (ret)
+ goto err;
sub_se.val64 = se->val64;
/* Copy the PAT field from PDE. */
ops->set_pfn(se, sub_spt->shadow_page.mfn);
ppgtt_set_shadow_entry(spt, se, index);
return 0;
+err:
+ /* Cancel the existing addess mappings of DMA addr. */
+ for_each_present_shadow_entry(sub_spt, &sub_se, sub_index) {
+ gvt_vdbg_mm("invalidate 4K entry\n");
+ ppgtt_invalidate_pte(sub_spt, &sub_se);
+ }
+ /* Release the new allocated spt. */
+ trace_spt_change(sub_spt->vgpu->id, "release", sub_spt,
+ sub_spt->guest_page.gfn, sub_spt->shadow_page.type);
+ ppgtt_free_spt(sub_spt);
+ return ret;
}
static int split_64KB_gtt_entry(struct intel_vgpu *vgpu,
#define KVMGT_DEBUGFS_FILENAME "kvmgt_nr_cache_entries"
+enum {
+ INTEL_VGPU_STATUS_ATTACHED = 0,
+ INTEL_VGPU_STATUS_ACTIVE,
+ INTEL_VGPU_STATUS_NR_BITS,
+};
+
struct intel_vgpu {
struct vfio_device vfio_device;
struct intel_gvt *gvt;
struct mutex vgpu_lock;
int id;
- bool active;
- bool attached;
+ DECLARE_BITMAP(status, INTEL_VGPU_STATUS_NR_BITS);
bool pv_notified;
bool failsafe;
unsigned int resetting_eng;
#define for_each_active_vgpu(gvt, vgpu, id) \
idr_for_each_entry((&(gvt)->vgpu_idr), (vgpu), (id)) \
- for_each_if(vgpu->active)
+ for_each_if(test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status))
static inline void intel_vgpu_write_pci_bar(struct intel_vgpu *vgpu,
u32 offset, u32 val, bool low)
static inline int intel_gvt_read_gpa(struct intel_vgpu *vgpu, unsigned long gpa,
void *buf, unsigned long len)
{
- if (!vgpu->attached)
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
return -ESRCH;
return vfio_dma_rw(&vgpu->vfio_device, gpa, buf, len, false);
}
static inline int intel_gvt_write_gpa(struct intel_vgpu *vgpu,
unsigned long gpa, void *buf, unsigned long len)
{
- if (!vgpu->attached)
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
return -ESRCH;
return vfio_dma_rw(&vgpu->vfio_device, gpa, buf, len, true);
}
* enabled by guest. so if msi_trigger is null, success is still
* returned and don't inject interrupt into guest.
*/
- if (!vgpu->attached)
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
return -ESRCH;
if (vgpu->msi_trigger && eventfd_signal(vgpu->msi_trigger, 1) != 1)
return -EFAULT;
mutex_lock(&vgpu->gvt->lock);
for_each_active_vgpu(vgpu->gvt, itr, id) {
- if (!itr->attached)
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, itr->status))
continue;
if (vgpu->vfio_device.kvm == itr->vfio_device.kvm) {
{
struct intel_vgpu *vgpu = vfio_dev_to_vgpu(vfio_dev);
- if (vgpu->attached)
- return -EEXIST;
-
if (!vgpu->vfio_device.kvm ||
vgpu->vfio_device.kvm->mm != current->mm) {
gvt_vgpu_err("KVM is required to use Intel vGPU\n");
if (__kvmgt_vgpu_exist(vgpu))
return -EEXIST;
- vgpu->attached = true;
-
vgpu->track_node.track_write = kvmgt_page_track_write;
vgpu->track_node.track_flush_slot = kvmgt_page_track_flush_slot;
kvm_get_kvm(vgpu->vfio_device.kvm);
kvm_page_track_register_notifier(vgpu->vfio_device.kvm,
&vgpu->track_node);
+ set_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status);
+
debugfs_create_ulong(KVMGT_DEBUGFS_FILENAME, 0444, vgpu->debugfs,
&vgpu->nr_cache_entries);
{
struct intel_vgpu *vgpu = vfio_dev_to_vgpu(vfio_dev);
- if (!vgpu->attached)
- return;
-
intel_gvt_release_vgpu(vgpu);
+ clear_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status);
+
debugfs_remove(debugfs_lookup(KVMGT_DEBUGFS_FILENAME, vgpu->debugfs));
kvm_page_track_unregister_notifier(vgpu->vfio_device.kvm,
vgpu->dma_addr_cache = RB_ROOT;
intel_vgpu_release_msi_eventfd_ctx(vgpu);
-
- vgpu->attached = false;
}
static u64 intel_vgpu_get_bar_addr(struct intel_vgpu *vgpu, int bar)
{
struct intel_vgpu *vgpu = dev_get_drvdata(&mdev->dev);
- if (WARN_ON_ONCE(vgpu->attached))
- return;
-
vfio_unregister_group_dev(&vgpu->vfio_device);
vfio_put_device(&vgpu->vfio_device);
}
struct kvm_memory_slot *slot;
int idx;
- if (!info->attached)
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, info->status))
return -ESRCH;
idx = srcu_read_lock(&kvm->srcu);
struct kvm_memory_slot *slot;
int idx;
- if (!info->attached)
- return 0;
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, info->status))
+ return -ESRCH;
idx = srcu_read_lock(&kvm->srcu);
slot = gfn_to_memslot(kvm, gfn);
struct gvt_dma *entry;
int ret;
- if (!vgpu->attached)
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
return -EINVAL;
mutex_lock(&vgpu->cache_lock);
struct gvt_dma *entry;
int ret = 0;
- if (!vgpu->attached)
- return -ENODEV;
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
+ return -EINVAL;
mutex_lock(&vgpu->cache_lock);
entry = __gvt_cache_find_dma_addr(vgpu, dma_addr);
{
struct gvt_dma *entry;
- if (!vgpu->attached)
+ if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
return;
mutex_lock(&vgpu->cache_lock);
idr_for_each_entry((&(gvt)->vgpu_idr), (vgpu), (id)) {
if (test_and_clear_bit(INTEL_GVT_REQUEST_EMULATE_VBLANK + id,
(void *)&gvt->service_request)) {
- if (vgpu->active)
+ if (test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status))
intel_vgpu_emulate_vblank(vgpu);
}
}
if (workload->shadow_mm->type != INTEL_GVT_MM_PPGTT ||
!workload->shadow_mm->ppgtt_mm.shadowed) {
+ intel_vgpu_unpin_mm(workload->shadow_mm);
gvt_vgpu_err("workload shadow ppgtt isn't ready\n");
return -EINVAL;
}
goto out;
}
- if (!scheduler->current_vgpu->active ||
+ if (!test_bit(INTEL_VGPU_STATUS_ACTIVE,
+ scheduler->current_vgpu->status) ||
list_empty(workload_q_head(scheduler->current_vgpu, engine)))
goto out;
*/
void intel_gvt_activate_vgpu(struct intel_vgpu *vgpu)
{
- mutex_lock(&vgpu->vgpu_lock);
- vgpu->active = true;
- mutex_unlock(&vgpu->vgpu_lock);
+ set_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status);
}
/**
{
mutex_lock(&vgpu->vgpu_lock);
- vgpu->active = false;
+ clear_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status);
if (atomic_read(&vgpu->submission.running_workload_num)) {
mutex_unlock(&vgpu->vgpu_lock);
struct intel_gvt *gvt = vgpu->gvt;
struct drm_i915_private *i915 = gvt->gt->i915;
- drm_WARN(&i915->drm, vgpu->active, "vGPU is still active!\n");
+ drm_WARN(&i915->drm, test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status),
+ "vGPU is still active!\n");
/*
* remove idr first so later clean can judge if need to stop
if (ret)
goto out_free_vgpu;
- vgpu->active = false;
-
+ clear_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status);
return vgpu;
out_free_vgpu:
if (!obj->mm.rsgt)
return -EBUSY;
- err = dma_resv_reserve_fences(obj->base.resv, 1);
+ err = dma_resv_reserve_fences(obj->base.resv, 2);
if (err)
return -EBUSY;
break;
}
+ if (ipu_plane->dp_flow == IPU_DP_FLOW_SYNC_BG)
+ width = ipu_src_rect_width(new_state);
+ else
+ width = drm_rect_width(&new_state->src) >> 16;
+
eba = drm_plane_state_to_eba(new_state, 0);
/*
*/
if (ipu_state->use_pre) {
axi_id = ipu_chan_assign_axi_id(ipu_plane->dma);
- ipu_prg_channel_configure(ipu_plane->ipu_ch, axi_id,
- ipu_src_rect_width(new_state),
+ ipu_prg_channel_configure(ipu_plane->ipu_ch, axi_id, width,
drm_rect_height(&new_state->src) >> 16,
fb->pitches[0], fb->format->format,
fb->modifier, &eba);
break;
}
- ipu_dmfc_config_wait4eot(ipu_plane->dmfc, ALIGN(drm_rect_width(dst), 8));
+ ipu_dmfc_config_wait4eot(ipu_plane->dmfc, width);
- width = ipu_src_rect_width(new_state);
height = drm_rect_height(&new_state->src) >> 16;
info = drm_format_info(fb->format->format);
ipu_calculate_bursts(width, info->cpp[0], fb->pitches[0],
ipu_cpmem_set_burstsize(ipu_plane->ipu_ch, 16);
ipu_cpmem_zero(ipu_plane->alpha_ch);
- ipu_cpmem_set_resolution(ipu_plane->alpha_ch,
- ipu_src_rect_width(new_state),
+ ipu_cpmem_set_resolution(ipu_plane->alpha_ch, width,
drm_rect_height(&new_state->src) >> 16);
ipu_cpmem_set_format_passthrough(ipu_plane->alpha_ch, 8);
ipu_cpmem_set_high_priority(ipu_plane->alpha_ch);
/* Initialize OSD1 fifo control register */
reg = VIU_OSD_DDR_PRIORITY_URGENT |
- VIU_OSD_HOLD_FIFO_LINES(31) |
VIU_OSD_FIFO_DEPTH_VAL(32) | /* fifo_depth_val: 32*8=256 */
VIU_OSD_WORDS_PER_BURST(4) | /* 4 words in 1 burst */
VIU_OSD_FIFO_LIMITS(2); /* fifo_lim: 2*16=32 */
if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A))
- reg |= VIU_OSD_BURST_LENGTH_32;
+ reg |= (VIU_OSD_BURST_LENGTH_32 | VIU_OSD_HOLD_FIFO_LINES(31));
else
- reg |= VIU_OSD_BURST_LENGTH_64;
+ reg |= (VIU_OSD_BURST_LENGTH_64 | VIU_OSD_HOLD_FIFO_LINES(4));
writel_relaxed(reg, priv->io_base + _REG(VIU_OSD1_FIFO_CTRL_STAT));
writel_relaxed(reg, priv->io_base + _REG(VIU_OSD2_FIFO_CTRL_STAT));
#define GBIF_CLIENT_HALT_MASK BIT(0)
#define GBIF_ARB_HALT_MASK BIT(1)
-static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu)
+static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu,
+ bool gx_off)
{
struct msm_gpu *gpu = &adreno_gpu->base;
return;
}
- /* Halt the gx side of GBIF */
- gpu_write(gpu, REG_A6XX_RBBM_GBIF_HALT, 1);
- spin_until(gpu_read(gpu, REG_A6XX_RBBM_GBIF_HALT_ACK) & 1);
+ if (gx_off) {
+ /* Halt the gx side of GBIF */
+ gpu_write(gpu, REG_A6XX_RBBM_GBIF_HALT, 1);
+ spin_until(gpu_read(gpu, REG_A6XX_RBBM_GBIF_HALT_ACK) & 1);
+ }
/* Halt new client requests on GBIF */
gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_CLIENT_HALT_MASK);
/* Halt the gmu cm3 core */
gmu_write(gmu, REG_A6XX_GMU_CM3_SYSRESET, 1);
- a6xx_bus_clear_pending_transactions(adreno_gpu);
+ a6xx_bus_clear_pending_transactions(adreno_gpu, true);
/* Reset GPU core blocks */
gpu_write(gpu, REG_A6XX_RBBM_SW_RESET_CMD, 1);
return;
}
- a6xx_bus_clear_pending_transactions(adreno_gpu);
+ a6xx_bus_clear_pending_transactions(adreno_gpu, a6xx_gpu->hung);
/* tell the GMU we want to slumber */
ret = a6xx_gmu_notify_slumber(gmu);
if (hang_debug)
a6xx_dump(gpu);
+ /*
+ * To handle recovery specific sequences during the rpm suspend we are
+ * about to trigger
+ */
+ a6xx_gpu->hung = true;
+
/* Halt SQE first */
gpu_write(gpu, REG_A6XX_CP_SQE_CNTL, 3);
mutex_unlock(&gpu->active_lock);
msm_gpu_hw_init(gpu);
+ a6xx_gpu->hung = false;
}
static const char *a6xx_uche_fault_block(struct msm_gpu *gpu, u32 mid)
void *llc_slice;
void *htw_llc_slice;
bool have_mmu500;
+ bool hung;
};
#define to_a6xx_gpu(x) container_of(x, struct a6xx_gpu, base)
ADRENO_FW_MAX,
};
-enum adreno_quirks {
- ADRENO_QUIRK_TWO_PASS_USE_WFI = 1,
- ADRENO_QUIRK_FAULT_DETECT_MASK = 2,
- ADRENO_QUIRK_LMLOADKILL_DISABLE = 3,
-};
+#define ADRENO_QUIRK_TWO_PASS_USE_WFI BIT(0)
+#define ADRENO_QUIRK_FAULT_DETECT_MASK BIT(1)
+#define ADRENO_QUIRK_LMLOADKILL_DISABLE BIT(2)
struct adreno_rev {
uint8_t core;
const char *name;
const char *fw[ADRENO_FW_MAX];
uint32_t gmem;
- enum adreno_quirks quirks;
+ u64 quirks;
struct msm_gpu *(*init)(struct drm_device *dev);
const char *zapfw;
u32 inactive_period;
* dpu_encoder_phys_wb_setup_fb - setup output framebuffer
* @phys_enc: Pointer to physical encoder
* @fb: Pointer to output framebuffer
- * @wb_roi: Pointer to output region of interest
*/
static void dpu_encoder_phys_wb_setup_fb(struct dpu_encoder_phys *phys_enc,
struct drm_framebuffer *fb)
/**
* dpu_encoder_phys_wb_init - initialize writeback encoder
- * @init: Pointer to init info structure with initialization params
+ * @p: Pointer to init info structure with initialization params
*/
struct dpu_encoder_phys *dpu_encoder_phys_wb_init(
struct dpu_enc_phys_init_params *p)
isr = dp_catalog_aux_get_irq(aux->catalog);
+ /* no interrupts pending, return immediately */
+ if (!isr)
+ return;
+
if (!aux->cmd_busy)
return;
ret = devm_pm_runtime_enable(&pdev->dev);
if (ret)
- return ret;
+ goto err_put_phy;
platform_set_drvdata(pdev, hdmi);
- return component_add(&pdev->dev, &msm_hdmi_ops);
+ ret = component_add(&pdev->dev, &msm_hdmi_ops);
+ if (ret)
+ goto err_put_phy;
+
+ return 0;
+
+err_put_phy:
+ msm_hdmi_put_phy(hdmi);
+ return ret;
}
static int msm_hdmi_dev_remove(struct platform_device *pdev)
* msm_drm_init, drm_dev->registered is used as an indicator that the
* shutdown will be successful.
*/
- if (drm && drm->registered)
+ if (drm && drm->registered && priv->kms)
drm_atomic_helper_shutdown(drm);
}
static int msm_mdss_parse_data_bus_icc_path(struct device *dev,
struct msm_mdss *msm_mdss)
{
- struct icc_path *path0 = of_icc_get(dev, "mdp0-mem");
- struct icc_path *path1 = of_icc_get(dev, "mdp1-mem");
+ struct icc_path *path0;
+ struct icc_path *path1;
+ path0 = of_icc_get(dev, "mdp0-mem");
if (IS_ERR_OR_NULL(path0))
return PTR_ERR_OR_ZERO(path0);
msm_mdss->path[0] = path0;
msm_mdss->num_paths = 1;
+ path1 = of_icc_get(dev, "mdp1-mem");
if (!IS_ERR_OR_NULL(path1)) {
msm_mdss->path[1] = path1;
msm_mdss->num_paths++;
+++ /dev/null
-/*
- * Copyright © 2007 David Airlie
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- *
- * Authors:
- * David Airlie
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/tty.h>
-#include <linux/sysrq.h>
-#include <linux/delay.h>
-#include <linux/init.h>
-#include <linux/screen_info.h>
-#include <linux/vga_switcheroo.h>
-#include <linux/console.h>
-
-#include <drm/drm_crtc.h>
-#include <drm/drm_crtc_helper.h>
-#include <drm/drm_probe_helper.h>
-#include <drm/drm_fb_helper.h>
-#include <drm/drm_fourcc.h>
-#include <drm/drm_atomic.h>
-
-#include "nouveau_drv.h"
-#include "nouveau_gem.h"
-#include "nouveau_bo.h"
-#include "nouveau_fbcon.h"
-#include "nouveau_chan.h"
-#include "nouveau_vmm.h"
-
-#include "nouveau_crtc.h"
-
-MODULE_PARM_DESC(nofbaccel, "Disable fbcon acceleration");
-int nouveau_nofbaccel = 0;
-module_param_named(nofbaccel, nouveau_nofbaccel, int, 0400);
-
-MODULE_PARM_DESC(fbcon_bpp, "fbcon bits-per-pixel (default: auto)");
-static int nouveau_fbcon_bpp;
-module_param_named(fbcon_bpp, nouveau_fbcon_bpp, int, 0400);
-
-static void
-nouveau_fbcon_fillrect(struct fb_info *info, const struct fb_fillrect *rect)
-{
- struct nouveau_fbdev *fbcon = info->par;
- struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev);
- struct nvif_device *device = &drm->client.device;
- int ret;
-
- if (info->state != FBINFO_STATE_RUNNING)
- return;
-
- ret = -ENODEV;
- if (!in_interrupt() && !(info->flags & FBINFO_HWACCEL_DISABLED) &&
- mutex_trylock(&drm->client.mutex)) {
- if (device->info.family < NV_DEVICE_INFO_V0_TESLA)
- ret = nv04_fbcon_fillrect(info, rect);
- else
- if (device->info.family < NV_DEVICE_INFO_V0_FERMI)
- ret = nv50_fbcon_fillrect(info, rect);
- else
- ret = nvc0_fbcon_fillrect(info, rect);
- mutex_unlock(&drm->client.mutex);
- }
-
- if (ret == 0)
- return;
-
- if (ret != -ENODEV)
- nouveau_fbcon_gpu_lockup(info);
- drm_fb_helper_cfb_fillrect(info, rect);
-}
-
-static void
-nouveau_fbcon_copyarea(struct fb_info *info, const struct fb_copyarea *image)
-{
- struct nouveau_fbdev *fbcon = info->par;
- struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev);
- struct nvif_device *device = &drm->client.device;
- int ret;
-
- if (info->state != FBINFO_STATE_RUNNING)
- return;
-
- ret = -ENODEV;
- if (!in_interrupt() && !(info->flags & FBINFO_HWACCEL_DISABLED) &&
- mutex_trylock(&drm->client.mutex)) {
- if (device->info.family < NV_DEVICE_INFO_V0_TESLA)
- ret = nv04_fbcon_copyarea(info, image);
- else
- if (device->info.family < NV_DEVICE_INFO_V0_FERMI)
- ret = nv50_fbcon_copyarea(info, image);
- else
- ret = nvc0_fbcon_copyarea(info, image);
- mutex_unlock(&drm->client.mutex);
- }
-
- if (ret == 0)
- return;
-
- if (ret != -ENODEV)
- nouveau_fbcon_gpu_lockup(info);
- drm_fb_helper_cfb_copyarea(info, image);
-}
-
-static void
-nouveau_fbcon_imageblit(struct fb_info *info, const struct fb_image *image)
-{
- struct nouveau_fbdev *fbcon = info->par;
- struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev);
- struct nvif_device *device = &drm->client.device;
- int ret;
-
- if (info->state != FBINFO_STATE_RUNNING)
- return;
-
- ret = -ENODEV;
- if (!in_interrupt() && !(info->flags & FBINFO_HWACCEL_DISABLED) &&
- mutex_trylock(&drm->client.mutex)) {
- if (device->info.family < NV_DEVICE_INFO_V0_TESLA)
- ret = nv04_fbcon_imageblit(info, image);
- else
- if (device->info.family < NV_DEVICE_INFO_V0_FERMI)
- ret = nv50_fbcon_imageblit(info, image);
- else
- ret = nvc0_fbcon_imageblit(info, image);
- mutex_unlock(&drm->client.mutex);
- }
-
- if (ret == 0)
- return;
-
- if (ret != -ENODEV)
- nouveau_fbcon_gpu_lockup(info);
- drm_fb_helper_cfb_imageblit(info, image);
-}
-
-static int
-nouveau_fbcon_sync(struct fb_info *info)
-{
- struct nouveau_fbdev *fbcon = info->par;
- struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev);
- struct nouveau_channel *chan = drm->channel;
- int ret;
-
- if (!chan || !chan->accel_done || in_interrupt() ||
- info->state != FBINFO_STATE_RUNNING ||
- info->flags & FBINFO_HWACCEL_DISABLED)
- return 0;
-
- if (!mutex_trylock(&drm->client.mutex))
- return 0;
-
- ret = nouveau_channel_idle(chan);
- mutex_unlock(&drm->client.mutex);
- if (ret) {
- nouveau_fbcon_gpu_lockup(info);
- return 0;
- }
-
- chan->accel_done = false;
- return 0;
-}
-
-static int
-nouveau_fbcon_open(struct fb_info *info, int user)
-{
- struct nouveau_fbdev *fbcon = info->par;
- struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev);
- int ret = pm_runtime_get_sync(drm->dev->dev);
- if (ret < 0 && ret != -EACCES) {
- pm_runtime_put(drm->dev->dev);
- return ret;
- }
- return 0;
-}
-
-static int
-nouveau_fbcon_release(struct fb_info *info, int user)
-{
- struct nouveau_fbdev *fbcon = info->par;
- struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev);
- pm_runtime_put(drm->dev->dev);
- return 0;
-}
-
-static const struct fb_ops nouveau_fbcon_ops = {
- .owner = THIS_MODULE,
- DRM_FB_HELPER_DEFAULT_OPS,
- .fb_open = nouveau_fbcon_open,
- .fb_release = nouveau_fbcon_release,
- .fb_fillrect = nouveau_fbcon_fillrect,
- .fb_copyarea = nouveau_fbcon_copyarea,
- .fb_imageblit = nouveau_fbcon_imageblit,
- .fb_sync = nouveau_fbcon_sync,
-};
-
-static const struct fb_ops nouveau_fbcon_sw_ops = {
- .owner = THIS_MODULE,
- DRM_FB_HELPER_DEFAULT_OPS,
- .fb_open = nouveau_fbcon_open,
- .fb_release = nouveau_fbcon_release,
- .fb_fillrect = drm_fb_helper_cfb_fillrect,
- .fb_copyarea = drm_fb_helper_cfb_copyarea,
- .fb_imageblit = drm_fb_helper_cfb_imageblit,
-};
-
-void
-nouveau_fbcon_accel_save_disable(struct drm_device *dev)
-{
- struct nouveau_drm *drm = nouveau_drm(dev);
- if (drm->fbcon && drm->fbcon->helper.info) {
- drm->fbcon->saved_flags = drm->fbcon->helper.info->flags;
- drm->fbcon->helper.info->flags |= FBINFO_HWACCEL_DISABLED;
- }
-}
-
-void
-nouveau_fbcon_accel_restore(struct drm_device *dev)
-{
- struct nouveau_drm *drm = nouveau_drm(dev);
- if (drm->fbcon && drm->fbcon->helper.info)
- drm->fbcon->helper.info->flags = drm->fbcon->saved_flags;
-}
-
-static void
-nouveau_fbcon_accel_fini(struct drm_device *dev)
-{
- struct nouveau_drm *drm = nouveau_drm(dev);
- struct nouveau_fbdev *fbcon = drm->fbcon;
- if (fbcon && drm->channel) {
- console_lock();
- if (fbcon->helper.info)
- fbcon->helper.info->flags |= FBINFO_HWACCEL_DISABLED;
- console_unlock();
- nouveau_channel_idle(drm->channel);
- nvif_object_dtor(&fbcon->twod);
- nvif_object_dtor(&fbcon->blit);
- nvif_object_dtor(&fbcon->gdi);
- nvif_object_dtor(&fbcon->patt);
- nvif_object_dtor(&fbcon->rop);
- nvif_object_dtor(&fbcon->clip);
- nvif_object_dtor(&fbcon->surf2d);
- }
-}
-
-static void
-nouveau_fbcon_accel_init(struct drm_device *dev)
-{
- struct nouveau_drm *drm = nouveau_drm(dev);
- struct nouveau_fbdev *fbcon = drm->fbcon;
- struct fb_info *info = fbcon->helper.info;
- int ret;
-
- if (drm->client.device.info.family < NV_DEVICE_INFO_V0_TESLA)
- ret = nv04_fbcon_accel_init(info);
- else
- if (drm->client.device.info.family < NV_DEVICE_INFO_V0_FERMI)
- ret = nv50_fbcon_accel_init(info);
- else
- ret = nvc0_fbcon_accel_init(info);
-
- if (ret == 0)
- info->fbops = &nouveau_fbcon_ops;
-}
-
-static void
-nouveau_fbcon_zfill(struct drm_device *dev, struct nouveau_fbdev *fbcon)
-{
- struct fb_info *info = fbcon->helper.info;
- struct fb_fillrect rect;
-
- /* Clear the entire fbcon. The drm will program every connector
- * with it's preferred mode. If the sizes differ, one display will
- * quite likely have garbage around the console.
- */
- rect.dx = rect.dy = 0;
- rect.width = info->var.xres_virtual;
- rect.height = info->var.yres_virtual;
- rect.color = 0;
- rect.rop = ROP_COPY;
- info->fbops->fb_fillrect(info, &rect);
-}
-
-static int
-nouveau_fbcon_create(struct drm_fb_helper *helper,
- struct drm_fb_helper_surface_size *sizes)
-{
- struct nouveau_fbdev *fbcon =
- container_of(helper, struct nouveau_fbdev, helper);
- struct drm_device *dev = fbcon->helper.dev;
- struct nouveau_drm *drm = nouveau_drm(dev);
- struct nvif_device *device = &drm->client.device;
- struct fb_info *info;
- struct drm_framebuffer *fb;
- struct nouveau_channel *chan;
- struct nouveau_bo *nvbo;
- struct drm_mode_fb_cmd2 mode_cmd = {};
- int ret;
-
- mode_cmd.width = sizes->surface_width;
- mode_cmd.height = sizes->surface_height;
-
- mode_cmd.pitches[0] = mode_cmd.width * (sizes->surface_bpp >> 3);
- mode_cmd.pitches[0] = roundup(mode_cmd.pitches[0], 256);
-
- mode_cmd.pixel_format = drm_mode_legacy_fb_format(sizes->surface_bpp,
- sizes->surface_depth);
-
- ret = nouveau_gem_new(&drm->client, mode_cmd.pitches[0] *
- mode_cmd.height, 0, NOUVEAU_GEM_DOMAIN_VRAM,
- 0, 0x0000, &nvbo);
- if (ret) {
- NV_ERROR(drm, "failed to allocate framebuffer\n");
- goto out;
- }
-
- ret = nouveau_framebuffer_new(dev, &mode_cmd, &nvbo->bo.base, &fb);
- if (ret)
- goto out_unref;
-
- ret = nouveau_bo_pin(nvbo, NOUVEAU_GEM_DOMAIN_VRAM, false);
- if (ret) {
- NV_ERROR(drm, "failed to pin fb: %d\n", ret);
- goto out_unref;
- }
-
- ret = nouveau_bo_map(nvbo);
- if (ret) {
- NV_ERROR(drm, "failed to map fb: %d\n", ret);
- goto out_unpin;
- }
-
- chan = nouveau_nofbaccel ? NULL : drm->channel;
- if (chan && device->info.family >= NV_DEVICE_INFO_V0_TESLA) {
- ret = nouveau_vma_new(nvbo, chan->vmm, &fbcon->vma);
- if (ret) {
- NV_ERROR(drm, "failed to map fb into chan: %d\n", ret);
- chan = NULL;
- }
- }
-
- info = drm_fb_helper_alloc_info(helper);
- if (IS_ERR(info)) {
- ret = PTR_ERR(info);
- goto out_unlock;
- }
-
- /* setup helper */
- fbcon->helper.fb = fb;
-
- if (!chan)
- info->flags = FBINFO_HWACCEL_DISABLED;
- else
- info->flags = FBINFO_HWACCEL_COPYAREA |
- FBINFO_HWACCEL_FILLRECT |
- FBINFO_HWACCEL_IMAGEBLIT;
- info->fbops = &nouveau_fbcon_sw_ops;
- info->fix.smem_start = nvbo->bo.resource->bus.offset;
- info->fix.smem_len = nvbo->bo.base.size;
-
- info->screen_base = nvbo_kmap_obj_iovirtual(nvbo);
- info->screen_size = nvbo->bo.base.size;
-
- drm_fb_helper_fill_info(info, &fbcon->helper, sizes);
-
- /* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */
-
- if (chan)
- nouveau_fbcon_accel_init(dev);
- nouveau_fbcon_zfill(dev, fbcon);
-
- /* To allow resizeing without swapping buffers */
- NV_INFO(drm, "allocated %dx%d fb: 0x%llx, bo %p\n",
- fb->width, fb->height, nvbo->offset, nvbo);
-
- if (dev_is_pci(dev->dev))
- vga_switcheroo_client_fb_set(to_pci_dev(dev->dev), info);
-
- return 0;
-
-out_unlock:
- if (chan)
- nouveau_vma_del(&fbcon->vma);
- nouveau_bo_unmap(nvbo);
-out_unpin:
- nouveau_bo_unpin(nvbo);
-out_unref:
- nouveau_bo_ref(NULL, &nvbo);
-out:
- return ret;
-}
-
-static int
-nouveau_fbcon_destroy(struct drm_device *dev, struct nouveau_fbdev *fbcon)
-{
- struct drm_framebuffer *fb = fbcon->helper.fb;
- struct nouveau_bo *nvbo;
-
- drm_fb_helper_unregister_info(&fbcon->helper);
- drm_fb_helper_fini(&fbcon->helper);
-
- if (fb && fb->obj[0]) {
- nvbo = nouveau_gem_object(fb->obj[0]);
- nouveau_vma_del(&fbcon->vma);
- nouveau_bo_unmap(nvbo);
- nouveau_bo_unpin(nvbo);
- drm_framebuffer_put(fb);
- }
-
- return 0;
-}
-
-void nouveau_fbcon_gpu_lockup(struct fb_info *info)
-{
- struct nouveau_fbdev *fbcon = info->par;
- struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev);
-
- NV_ERROR(drm, "GPU lockup - switching to software fbcon\n");
- info->flags |= FBINFO_HWACCEL_DISABLED;
-}
-
-static const struct drm_fb_helper_funcs nouveau_fbcon_helper_funcs = {
- .fb_probe = nouveau_fbcon_create,
-};
-
-static void
-nouveau_fbcon_set_suspend_work(struct work_struct *work)
-{
- struct nouveau_drm *drm = container_of(work, typeof(*drm), fbcon_work);
- int state = READ_ONCE(drm->fbcon_new_state);
-
- if (state == FBINFO_STATE_RUNNING)
- pm_runtime_get_sync(drm->dev->dev);
-
- console_lock();
- if (state == FBINFO_STATE_RUNNING)
- nouveau_fbcon_accel_restore(drm->dev);
- drm_fb_helper_set_suspend(&drm->fbcon->helper, state);
- if (state != FBINFO_STATE_RUNNING)
- nouveau_fbcon_accel_save_disable(drm->dev);
- console_unlock();
-
- if (state == FBINFO_STATE_RUNNING) {
- nouveau_fbcon_hotplug_resume(drm->fbcon);
- pm_runtime_mark_last_busy(drm->dev->dev);
- pm_runtime_put_autosuspend(drm->dev->dev);
- }
-}
-
-void
-nouveau_fbcon_set_suspend(struct drm_device *dev, int state)
-{
- struct nouveau_drm *drm = nouveau_drm(dev);
-
- if (!drm->fbcon)
- return;
-
- drm->fbcon_new_state = state;
- /* Since runtime resume can happen as a result of a sysfs operation,
- * it's possible we already have the console locked. So handle fbcon
- * init/deinit from a seperate work thread
- */
- schedule_work(&drm->fbcon_work);
-}
-
-void
-nouveau_fbcon_output_poll_changed(struct drm_device *dev)
-{
- struct nouveau_drm *drm = nouveau_drm(dev);
- struct nouveau_fbdev *fbcon = drm->fbcon;
- int ret;
-
- if (!fbcon)
- return;
-
- mutex_lock(&fbcon->hotplug_lock);
-
- ret = pm_runtime_get(dev->dev);
- if (ret == 1 || ret == -EACCES) {
- drm_fb_helper_hotplug_event(&fbcon->helper);
-
- pm_runtime_mark_last_busy(dev->dev);
- pm_runtime_put_autosuspend(dev->dev);
- } else if (ret == 0) {
- /* If the GPU was already in the process of suspending before
- * this event happened, then we can't block here as we'll
- * deadlock the runtime pmops since they wait for us to
- * finish. So, just defer this event for when we runtime
- * resume again. It will be handled by fbcon_work.
- */
- NV_DEBUG(drm, "fbcon HPD event deferred until runtime resume\n");
- fbcon->hotplug_waiting = true;
- pm_runtime_put_noidle(drm->dev->dev);
- } else {
- DRM_WARN("fbcon HPD event lost due to RPM failure: %d\n",
- ret);
- }
-
- mutex_unlock(&fbcon->hotplug_lock);
-}
-
-void
-nouveau_fbcon_hotplug_resume(struct nouveau_fbdev *fbcon)
-{
- struct nouveau_drm *drm;
-
- if (!fbcon)
- return;
- drm = nouveau_drm(fbcon->helper.dev);
-
- mutex_lock(&fbcon->hotplug_lock);
- if (fbcon->hotplug_waiting) {
- fbcon->hotplug_waiting = false;
-
- NV_DEBUG(drm, "Handling deferred fbcon HPD events\n");
- drm_fb_helper_hotplug_event(&fbcon->helper);
- }
- mutex_unlock(&fbcon->hotplug_lock);
-}
-
-int
-nouveau_fbcon_init(struct drm_device *dev)
-{
- struct nouveau_drm *drm = nouveau_drm(dev);
- struct nouveau_fbdev *fbcon;
- int preferred_bpp = nouveau_fbcon_bpp;
- int ret;
-
- if (!dev->mode_config.num_crtc ||
- (to_pci_dev(dev->dev)->class >> 8) != PCI_CLASS_DISPLAY_VGA)
- return 0;
-
- fbcon = kzalloc(sizeof(struct nouveau_fbdev), GFP_KERNEL);
- if (!fbcon)
- return -ENOMEM;
-
- drm->fbcon = fbcon;
- INIT_WORK(&drm->fbcon_work, nouveau_fbcon_set_suspend_work);
- mutex_init(&fbcon->hotplug_lock);
-
- drm_fb_helper_prepare(dev, &fbcon->helper, &nouveau_fbcon_helper_funcs);
-
- ret = drm_fb_helper_init(dev, &fbcon->helper);
- if (ret)
- goto free;
-
- if (preferred_bpp != 8 && preferred_bpp != 16 && preferred_bpp != 32) {
- if (drm->client.device.info.ram_size <= 32 * 1024 * 1024)
- preferred_bpp = 8;
- else
- if (drm->client.device.info.ram_size <= 64 * 1024 * 1024)
- preferred_bpp = 16;
- else
- preferred_bpp = 32;
- }
-
- /* disable all the possible outputs/crtcs before entering KMS mode */
- if (!drm_drv_uses_atomic_modeset(dev))
- drm_helper_disable_unused_functions(dev);
-
- ret = drm_fb_helper_initial_config(&fbcon->helper, preferred_bpp);
- if (ret)
- goto fini;
-
- if (fbcon->helper.info)
- fbcon->helper.info->pixmap.buf_align = 4;
- return 0;
-
-fini:
- drm_fb_helper_fini(&fbcon->helper);
-free:
- kfree(fbcon);
- drm->fbcon = NULL;
- return ret;
-}
-
-void
-nouveau_fbcon_fini(struct drm_device *dev)
-{
- struct nouveau_drm *drm = nouveau_drm(dev);
-
- if (!drm->fbcon)
- return;
-
- drm_kms_helper_poll_fini(dev);
- nouveau_fbcon_accel_fini(dev);
- nouveau_fbcon_destroy(dev, drm->fbcon);
- kfree(drm->fbcon);
- drm->fbcon = NULL;
-}
struct panfrost_gem_object *bo;
struct drm_panfrost_create_bo *args = data;
struct panfrost_gem_mapping *mapping;
+ int ret;
if (!args->size || args->pad ||
(args->flags & ~(PANFROST_BO_NOEXEC | PANFROST_BO_HEAP)))
!(args->flags & PANFROST_BO_NOEXEC))
return -EINVAL;
- bo = panfrost_gem_create_with_handle(file, dev, args->size, args->flags,
- &args->handle);
+ bo = panfrost_gem_create(dev, args->size, args->flags);
if (IS_ERR(bo))
return PTR_ERR(bo);
+ ret = drm_gem_handle_create(file, &bo->base.base, &args->handle);
+ if (ret)
+ goto out;
+
mapping = panfrost_gem_mapping_get(bo, priv);
- if (!mapping) {
- drm_gem_object_put(&bo->base.base);
- return -EINVAL;
+ if (mapping) {
+ args->offset = mapping->mmnode.start << PAGE_SHIFT;
+ panfrost_gem_mapping_put(mapping);
+ } else {
+ /* This can only happen if the handle from
+ * drm_gem_handle_create() has already been guessed and freed
+ * by user space
+ */
+ ret = -EINVAL;
}
- args->offset = mapping->mmnode.start << PAGE_SHIFT;
- panfrost_gem_mapping_put(mapping);
-
- return 0;
+out:
+ drm_gem_object_put(&bo->base.base);
+ return ret;
}
/**
}
struct panfrost_gem_object *
-panfrost_gem_create_with_handle(struct drm_file *file_priv,
- struct drm_device *dev, size_t size,
- u32 flags,
- uint32_t *handle)
+panfrost_gem_create(struct drm_device *dev, size_t size, u32 flags)
{
- int ret;
struct drm_gem_shmem_object *shmem;
struct panfrost_gem_object *bo;
bo->noexec = !!(flags & PANFROST_BO_NOEXEC);
bo->is_heap = !!(flags & PANFROST_BO_HEAP);
- /*
- * Allocate an id of idr table where the obj is registered
- * and handle has the id what user can see.
- */
- ret = drm_gem_handle_create(file_priv, &shmem->base, handle);
- /* drop reference from allocate - handle holds it now. */
- drm_gem_object_put(&shmem->base);
- if (ret)
- return ERR_PTR(ret);
-
return bo;
}
struct sg_table *sgt);
struct panfrost_gem_object *
-panfrost_gem_create_with_handle(struct drm_file *file_priv,
- struct drm_device *dev, size_t size,
- u32 flags,
- uint32_t *handle);
+panfrost_gem_create(struct drm_device *dev, size_t size, u32 flags);
int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv);
void panfrost_gem_close(struct drm_gem_object *obj,
init_completion(&entity->entity_idle);
/* We start in an idle state. */
- complete(&entity->entity_idle);
+ complete_all(&entity->entity_idle);
spin_lock_init(&entity->rq_lock);
spsc_queue_init(&entity->job_queue);
sched_job = drm_sched_entity_pop_job(entity);
if (!sched_job) {
- complete(&entity->entity_idle);
+ complete_all(&entity->entity_idle);
continue;
}
trace_drm_run_job(sched_job, entity);
fence = sched->ops->run_job(sched_job);
- complete(&entity->entity_idle);
+ complete_all(&entity->entity_idle);
drm_sched_fence_scheduled(s_fence);
if (!IS_ERR_OR_NULL(fence)) {
drm_mm_test.o \
drm_plane_helper_test.o \
drm_rect_test.o
+
+CFLAGS_drm_mm_test.o := $(DISABLE_STRUCTLEAK_PLUGIN)
return false;
}
-static bool check_reserve_boundaries(struct kunit *test, struct drm_mm *mm,
- unsigned int count,
- u64 size)
+static bool noinline_for_stack check_reserve_boundaries(struct kunit *test, struct drm_mm *mm,
+ unsigned int count,
+ u64 size)
{
const struct boundary {
u64 start, size;
clear = src_iter->ops->maps_tt && (!ttm || !ttm_tt_is_populated(ttm));
if (!(clear && ttm && !(ttm->page_flags & TTM_TT_FLAG_ZERO_ALLOC)))
- ttm_move_memcpy(clear, ttm->num_pages, dst_iter, src_iter);
+ ttm_move_memcpy(clear, PFN_UP(dst_mem->size), dst_iter, src_iter);
if (!src_iter->ops->maps_tt)
ttm_kmap_iter_linear_io_fini(&_src_iter.io, bdev, src_mem);
drm_gem_object_release(obj);
return ret;
}
- drm_gem_object_put(obj);
rc->res_handle = qobj->hw_res_handle; /* similiar to a VM address */
rc->bo_handle = handle;
+
+ /*
+ * The handle owns the reference now. But we must drop our
+ * remaining reference *after* we no longer need to dereference
+ * the obj. Otherwise userspace could guess the handle and
+ * race closing it from another thread.
+ */
+ drm_gem_object_put(obj);
+
return 0;
}
drm_gem_object_release(obj);
return ret;
}
- drm_gem_object_put(obj);
rc_blob->res_handle = bo->hw_res_handle;
rc_blob->bo_handle = handle;
+ /*
+ * The handle owns the reference now. But we must drop our
+ * remaining reference *after* we no longer need to dereference
+ * the obj. Otherwise userspace could guess the handle and
+ * race closing it from another thread.
+ */
+ drm_gem_object_put(obj);
+
return 0;
}
struct virtio_gpu_object_array *objs = NULL;
struct drm_gem_shmem_object *shmem_obj;
struct virtio_gpu_object *bo;
- struct virtio_gpu_mem_entry *ents;
+ struct virtio_gpu_mem_entry *ents = NULL;
unsigned int nents;
int ret;
ret = -ENOMEM;
objs = virtio_gpu_array_alloc(1);
if (!objs)
- goto err_put_id;
+ goto err_free_entry;
virtio_gpu_array_add_obj(objs, &bo->base.base);
ret = virtio_gpu_array_lock_resv(objs);
err_put_objs:
virtio_gpu_array_put_free(objs);
+err_free_entry:
+ kvfree(ents);
err_put_id:
virtio_gpu_resource_id_put(vgdev, bo->hw_res_handle);
err_free_gem:
kref_put(&base->refcount, ttm_release_base);
}
-/**
- * ttm_base_object_noref_lookup - look up a base object without reference
- * @tfile: The struct ttm_object_file the object is registered with.
- * @key: The object handle.
- *
- * This function looks up a ttm base object and returns a pointer to it
- * without refcounting the pointer. The returned pointer is only valid
- * until ttm_base_object_noref_release() is called, and the object
- * pointed to by the returned pointer may be doomed. Any persistent usage
- * of the object requires a refcount to be taken using kref_get_unless_zero().
- * Iff this function returns successfully it needs to be paired with
- * ttm_base_object_noref_release() and no sleeping- or scheduling functions
- * may be called inbetween these function callse.
- *
- * Return: A pointer to the object if successful or NULL otherwise.
- */
-struct ttm_base_object *
-ttm_base_object_noref_lookup(struct ttm_object_file *tfile, uint64_t key)
-{
- struct vmwgfx_hash_item *hash;
- int ret;
-
- rcu_read_lock();
- ret = ttm_tfile_find_ref_rcu(tfile, key, &hash);
- if (ret) {
- rcu_read_unlock();
- return NULL;
- }
-
- __release(RCU);
- return hlist_entry(hash, struct ttm_ref_object, hash)->obj;
-}
-EXPORT_SYMBOL(ttm_base_object_noref_lookup);
-
struct ttm_base_object *ttm_base_object_lookup(struct ttm_object_file *tfile,
uint64_t key)
{
struct vmwgfx_hash_item *hash;
int ret;
- rcu_read_lock();
- ret = ttm_tfile_find_ref_rcu(tfile, key, &hash);
+ spin_lock(&tfile->lock);
+ ret = ttm_tfile_find_ref(tfile, key, &hash);
if (likely(ret == 0)) {
base = hlist_entry(hash, struct ttm_ref_object, hash)->obj;
if (!kref_get_unless_zero(&base->refcount))
base = NULL;
}
- rcu_read_unlock();
+ spin_unlock(&tfile->lock);
+
return base;
}
#define ttm_prime_object_kfree(__obj, __prime) \
kfree_rcu(__obj, __prime.base.rhead)
-struct ttm_base_object *
-ttm_base_object_noref_lookup(struct ttm_object_file *tfile, uint64_t key);
-
-/**
- * ttm_base_object_noref_release - release a base object pointer looked up
- * without reference
- *
- * Releases a base object pointer looked up with ttm_base_object_noref_lookup().
- */
-static inline void ttm_base_object_noref_release(void)
-{
- __acquire(RCU);
- rcu_read_unlock();
-}
#endif
}
/**
- * vmw_user_bo_noref_lookup - Look up a vmw user buffer object without reference
- * @filp: The TTM object file the handle is registered with.
- * @handle: The user buffer object handle.
- *
- * This function looks up a struct vmw_bo and returns a pointer to the
- * struct vmw_buffer_object it derives from without refcounting the pointer.
- * The returned pointer is only valid until vmw_user_bo_noref_release() is
- * called, and the object pointed to by the returned pointer may be doomed.
- * Any persistent usage of the object requires a refcount to be taken using
- * ttm_bo_reference_unless_doomed(). Iff this function returns successfully it
- * needs to be paired with vmw_user_bo_noref_release() and no sleeping-
- * or scheduling functions may be called in between these function calls.
- *
- * Return: A struct vmw_buffer_object pointer if successful or negative
- * error pointer on failure.
- */
-struct vmw_buffer_object *
-vmw_user_bo_noref_lookup(struct drm_file *filp, u32 handle)
-{
- struct vmw_buffer_object *vmw_bo;
- struct ttm_buffer_object *bo;
- struct drm_gem_object *gobj = drm_gem_object_lookup(filp, handle);
-
- if (!gobj) {
- DRM_ERROR("Invalid buffer object handle 0x%08lx.\n",
- (unsigned long)handle);
- return ERR_PTR(-ESRCH);
- }
- vmw_bo = gem_to_vmw_bo(gobj);
- bo = ttm_bo_get_unless_zero(&vmw_bo->base);
- vmw_bo = vmw_buffer_object(bo);
- drm_gem_object_put(gobj);
-
- return vmw_bo;
-}
-
-
-/**
* vmw_bo_fence_single - Utility function to fence a single TTM buffer
* object without unreserving it.
*
uint32_t handle,
const struct vmw_user_resource_conv *converter,
struct vmw_resource **p_res);
-extern struct vmw_resource *
-vmw_user_resource_noref_lookup_handle(struct vmw_private *dev_priv,
- struct ttm_object_file *tfile,
- uint32_t handle,
- const struct vmw_user_resource_conv *
- converter);
+
extern int vmw_stream_claim_ioctl(struct drm_device *dev, void *data,
struct drm_file *file_priv);
extern int vmw_stream_unref_ioctl(struct drm_device *dev, void *data,
}
/**
- * vmw_user_resource_noref_release - release a user resource pointer looked up
- * without reference
- */
-static inline void vmw_user_resource_noref_release(void)
-{
- ttm_base_object_noref_release();
-}
-
-/**
* Buffer object helper functions - vmwgfx_bo.c
*/
extern int vmw_bo_pin_in_placement(struct vmw_private *vmw_priv,
extern void vmw_bo_move_notify(struct ttm_buffer_object *bo,
struct ttm_resource *mem);
extern void vmw_bo_swap_notify(struct ttm_buffer_object *bo);
-extern struct vmw_buffer_object *
-vmw_user_bo_noref_lookup(struct drm_file *filp, u32 handle);
/**
* vmw_bo_adjust_prio - Adjust the buffer object eviction priority
rcache->valid_handle = 0;
}
+enum vmw_val_add_flags {
+ vmw_val_add_flag_none = 0,
+ vmw_val_add_flag_noctx = 1 << 0,
+};
+
/**
- * vmw_execbuf_res_noref_val_add - Add a resource described by an unreferenced
- * rcu-protected pointer to the validation list.
+ * vmw_execbuf_res_val_add - Add a resource to the validation list.
*
* @sw_context: Pointer to the software context.
* @res: Unreferenced rcu-protected pointer to the resource.
* @dirty: Whether to change dirty status.
+ * @flags: specifies whether to use the context or not
*
* Returns: 0 on success. Negative error code on failure. Typical error codes
* are %-EINVAL on inconsistency and %-ESRCH if the resource was doomed.
*/
-static int vmw_execbuf_res_noref_val_add(struct vmw_sw_context *sw_context,
- struct vmw_resource *res,
- u32 dirty)
+static int vmw_execbuf_res_val_add(struct vmw_sw_context *sw_context,
+ struct vmw_resource *res,
+ u32 dirty,
+ u32 flags)
{
struct vmw_private *dev_priv = res->dev_priv;
int ret;
if (dirty)
vmw_validation_res_set_dirty(sw_context->ctx,
rcache->private, dirty);
- vmw_user_resource_noref_release();
return 0;
}
- priv_size = vmw_execbuf_res_size(dev_priv, res_type);
- ret = vmw_validation_add_resource(sw_context->ctx, res, priv_size,
- dirty, (void **)&ctx_info,
- &first_usage);
- vmw_user_resource_noref_release();
- if (ret)
- return ret;
+ if ((flags & vmw_val_add_flag_noctx) != 0) {
+ ret = vmw_validation_add_resource(sw_context->ctx, res, 0, dirty,
+ (void **)&ctx_info, NULL);
+ if (ret)
+ return ret;
- if (priv_size && first_usage) {
- ret = vmw_cmd_ctx_first_setup(dev_priv, sw_context, res,
- ctx_info);
- if (ret) {
- VMW_DEBUG_USER("Failed first usage context setup.\n");
+ } else {
+ priv_size = vmw_execbuf_res_size(dev_priv, res_type);
+ ret = vmw_validation_add_resource(sw_context->ctx, res, priv_size,
+ dirty, (void **)&ctx_info,
+ &first_usage);
+ if (ret)
return ret;
+
+ if (priv_size && first_usage) {
+ ret = vmw_cmd_ctx_first_setup(dev_priv, sw_context, res,
+ ctx_info);
+ if (ret) {
+ VMW_DEBUG_USER("Failed first usage context setup.\n");
+ return ret;
+ }
}
}
}
/**
- * vmw_execbuf_res_noctx_val_add - Add a non-context resource to the resource
- * validation list if it's not already on it
- *
- * @sw_context: Pointer to the software context.
- * @res: Pointer to the resource.
- * @dirty: Whether to change dirty status.
- *
- * Returns: Zero on success. Negative error code on failure.
- */
-static int vmw_execbuf_res_noctx_val_add(struct vmw_sw_context *sw_context,
- struct vmw_resource *res,
- u32 dirty)
-{
- struct vmw_res_cache_entry *rcache;
- enum vmw_res_type res_type = vmw_res_type(res);
- void *ptr;
- int ret;
-
- rcache = &sw_context->res_cache[res_type];
- if (likely(rcache->valid && rcache->res == res)) {
- if (dirty)
- vmw_validation_res_set_dirty(sw_context->ctx,
- rcache->private, dirty);
- return 0;
- }
-
- ret = vmw_validation_add_resource(sw_context->ctx, res, 0, dirty,
- &ptr, NULL);
- if (ret)
- return ret;
-
- vmw_execbuf_rcache_update(rcache, res, ptr);
-
- return 0;
-}
-
-/**
* vmw_view_res_val_add - Add a view and the surface it's pointing to to the
* validation list
*
* First add the resource the view is pointing to, otherwise it may be
* swapped out when the view is validated.
*/
- ret = vmw_execbuf_res_noctx_val_add(sw_context, vmw_view_srf(view),
- vmw_view_dirtying(view));
+ ret = vmw_execbuf_res_val_add(sw_context, vmw_view_srf(view),
+ vmw_view_dirtying(view), vmw_val_add_flag_noctx);
if (ret)
return ret;
- return vmw_execbuf_res_noctx_val_add(sw_context, view,
- VMW_RES_DIRTY_NONE);
+ return vmw_execbuf_res_val_add(sw_context, view, VMW_RES_DIRTY_NONE,
+ vmw_val_add_flag_noctx);
}
/**
if (IS_ERR(res))
continue;
- ret = vmw_execbuf_res_noctx_val_add(sw_context, res,
- VMW_RES_DIRTY_SET);
+ ret = vmw_execbuf_res_val_add(sw_context, res,
+ VMW_RES_DIRTY_SET,
+ vmw_val_add_flag_noctx);
if (unlikely(ret != 0))
return ret;
}
if (vmw_res_type(entry->res) == vmw_res_view)
ret = vmw_view_res_val_add(sw_context, entry->res);
else
- ret = vmw_execbuf_res_noctx_val_add
- (sw_context, entry->res,
- vmw_binding_dirtying(entry->bt));
+ ret = vmw_execbuf_res_val_add(sw_context, entry->res,
+ vmw_binding_dirtying(entry->bt),
+ vmw_val_add_flag_noctx);
if (unlikely(ret != 0))
break;
}
{
struct vmw_res_cache_entry *rcache = &sw_context->res_cache[res_type];
struct vmw_resource *res;
- int ret;
+ int ret = 0;
+ bool needs_unref = false;
if (p_res)
*p_res = NULL;
if (ret)
return ret;
- res = vmw_user_resource_noref_lookup_handle
- (dev_priv, sw_context->fp->tfile, *id_loc, converter);
- if (IS_ERR(res)) {
+ ret = vmw_user_resource_lookup_handle
+ (dev_priv, sw_context->fp->tfile, *id_loc, converter, &res);
+ if (ret != 0) {
VMW_DEBUG_USER("Could not find/use resource 0x%08x.\n",
(unsigned int) *id_loc);
- return PTR_ERR(res);
+ return ret;
}
+ needs_unref = true;
- ret = vmw_execbuf_res_noref_val_add(sw_context, res, dirty);
+ ret = vmw_execbuf_res_val_add(sw_context, res, dirty, vmw_val_add_flag_none);
if (unlikely(ret != 0))
- return ret;
+ goto res_check_done;
if (rcache->valid && rcache->res == res) {
rcache->valid_handle = true;
if (p_res)
*p_res = res;
- return 0;
+res_check_done:
+ if (needs_unref)
+ vmw_resource_unreference(&res);
+
+ return ret;
}
/**
int ret;
vmw_validation_preload_bo(sw_context->ctx);
- vmw_bo = vmw_user_bo_noref_lookup(sw_context->filp, handle);
- if (IS_ERR(vmw_bo)) {
- VMW_DEBUG_USER("Could not find or use MOB buffer.\n");
+ ret = vmw_user_bo_lookup(sw_context->filp, handle, &vmw_bo);
+ if (ret != 0) {
+ drm_dbg(&dev_priv->drm, "Could not find or use MOB buffer.\n");
return PTR_ERR(vmw_bo);
}
ret = vmw_validation_add_bo(sw_context->ctx, vmw_bo, true, false);
int ret;
vmw_validation_preload_bo(sw_context->ctx);
- vmw_bo = vmw_user_bo_noref_lookup(sw_context->filp, handle);
- if (IS_ERR(vmw_bo)) {
- VMW_DEBUG_USER("Could not find or use GMR region.\n");
+ ret = vmw_user_bo_lookup(sw_context->filp, handle, &vmw_bo);
+ if (ret != 0) {
+ drm_dbg(&dev_priv->drm, "Could not find or use GMR region.\n");
return PTR_ERR(vmw_bo);
}
ret = vmw_validation_add_bo(sw_context->ctx, vmw_bo, false, false);
res = vmw_shader_lookup(vmw_context_res_man(ctx),
cmd->body.shid, cmd->body.type);
if (!IS_ERR(res)) {
- ret = vmw_execbuf_res_noctx_val_add(sw_context, res,
- VMW_RES_DIRTY_NONE);
+ ret = vmw_execbuf_res_val_add(sw_context, res,
+ VMW_RES_DIRTY_NONE,
+ vmw_val_add_flag_noctx);
if (unlikely(ret != 0))
return ret;
return PTR_ERR(res);
}
- ret = vmw_execbuf_res_noctx_val_add(sw_context, res,
- VMW_RES_DIRTY_NONE);
+ ret = vmw_execbuf_res_val_add(sw_context, res,
+ VMW_RES_DIRTY_NONE,
+ vmw_val_add_flag_noctx);
if (ret)
return ret;
}
return PTR_ERR(res);
}
- ret = vmw_execbuf_res_noctx_val_add(sw_context, res,
- VMW_RES_DIRTY_NONE);
+ ret = vmw_execbuf_res_val_add(sw_context, res, VMW_RES_DIRTY_NONE,
+ vmw_val_add_flag_noctx);
if (ret) {
VMW_DEBUG_USER("Error creating resource validation node.\n");
return ret;
vmw_dx_streamoutput_set_size(res, cmd->body.sizeInBytes);
- ret = vmw_execbuf_res_noctx_val_add(sw_context, res,
- VMW_RES_DIRTY_NONE);
+ ret = vmw_execbuf_res_val_add(sw_context, res, VMW_RES_DIRTY_NONE,
+ vmw_val_add_flag_noctx);
if (ret) {
DRM_ERROR("Error creating resource validation node.\n");
return ret;
return 0;
}
- ret = vmw_execbuf_res_noctx_val_add(sw_context, res,
- VMW_RES_DIRTY_NONE);
+ ret = vmw_execbuf_res_val_add(sw_context, res, VMW_RES_DIRTY_NONE,
+ vmw_val_add_flag_noctx);
if (ret) {
DRM_ERROR("Error creating resource validation node.\n");
return ret;
if (ret)
return ret;
- res = vmw_user_resource_noref_lookup_handle
+ ret = vmw_user_resource_lookup_handle
(dev_priv, sw_context->fp->tfile, handle,
- user_context_converter);
- if (IS_ERR(res)) {
+ user_context_converter, &res);
+ if (ret != 0) {
VMW_DEBUG_USER("Could not find or user DX context 0x%08x.\n",
(unsigned int) handle);
- return PTR_ERR(res);
+ return ret;
}
- ret = vmw_execbuf_res_noref_val_add(sw_context, res, VMW_RES_DIRTY_SET);
- if (unlikely(ret != 0))
+ ret = vmw_execbuf_res_val_add(sw_context, res, VMW_RES_DIRTY_SET,
+ vmw_val_add_flag_none);
+ if (unlikely(ret != 0)) {
+ vmw_resource_unreference(&res);
return ret;
+ }
sw_context->dx_ctx_node = vmw_execbuf_info_from_res(sw_context, res);
sw_context->man = vmw_context_res_man(res);
+ vmw_resource_unreference(&res);
return 0;
}
return ret;
}
-/**
- * vmw_user_resource_noref_lookup_handle - lookup a struct resource from a
- * TTM user-space handle and perform basic type checks
- *
- * @dev_priv: Pointer to a device private struct
- * @tfile: Pointer to a struct ttm_object_file identifying the caller
- * @handle: The TTM user-space handle
- * @converter: Pointer to an object describing the resource type
- *
- * If the handle can't be found or is associated with an incorrect resource
- * type, -EINVAL will be returned.
- */
-struct vmw_resource *
-vmw_user_resource_noref_lookup_handle(struct vmw_private *dev_priv,
- struct ttm_object_file *tfile,
- uint32_t handle,
- const struct vmw_user_resource_conv
- *converter)
-{
- struct ttm_base_object *base;
-
- base = ttm_base_object_noref_lookup(tfile, handle);
- if (!base)
- return ERR_PTR(-ESRCH);
-
- if (unlikely(ttm_base_object_type(base) != converter->object_type)) {
- ttm_base_object_noref_release();
- return ERR_PTR(-EINVAL);
- }
-
- return converter->base_obj_to_res(base);
-}
-
/*
* Helper function that looks either a surface or bo.
*
return xenbus_switch_state(xb_dev, XenbusStateInitialising);
}
-static int xen_drv_remove(struct xenbus_device *dev)
+static void xen_drv_remove(struct xenbus_device *dev)
{
struct xen_drm_front_info *front_info = dev_get_drvdata(&dev->dev);
int to = 100;
xen_drm_drv_fini(front_info);
xenbus_frontend_closed(dev);
- return 0;
}
static const struct xenbus_device_id xen_driver_ids[] = {
}
rc = mp2_ops->get_rep_desc(cl_idx, cl_data->report_descr[i]);
if (rc)
- return rc;
+ goto cleanup;
mp2_ops->start(privdata, info);
status = amd_sfh_wait_for_response
(privdata, cl_data->sensor_idx[i], SENSOR_ENABLED);
}
rc = mp2_ops->get_rep_desc(cl_idx, cl_data->report_descr[i]);
if (rc)
- return rc;
+ goto cleanup;
writel(0, privdata->mmio + AMD_P2C_MSG(0));
mp2_ops->start(privdata, info);
struct list_head *report_list =
&hid->report_enum[HID_OUTPUT_REPORT].report_list;
struct input_dev *dev;
- int field_count = 0;
int error;
int i, j;
* -----------------------------------------
* Do init them with default value.
*/
+ if (report->maxfield < 4) {
+ hid_err(hid, "not enough fields in the report: %d\n",
+ report->maxfield);
+ return -ENODEV;
+ }
for (i = 0; i < report->maxfield; i++) {
+ if (report->field[i]->report_count < 1) {
+ hid_err(hid, "no values in the field\n");
+ return -ENODEV;
+ }
for (j = 0; j < report->field[i]->report_count; j++) {
report->field[i]->value[j] = 0x00;
- field_count++;
}
}
- if (field_count < 4) {
- hid_err(hid, "not enough fields in the report: %d\n",
- field_count);
- return -ENODEV;
- }
-
betopff = kzalloc(sizeof(*betopff), GFP_KERNEL);
if (!betopff)
return -ENOMEM;
}
report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
+ if (list_empty(report_list)) {
+ hid_err(hid, "no output report found\n");
+ error = -ENODEV;
+ goto error_hw_stop;
+ }
bigben->report = list_entry(report_list->next,
struct hid_report, list);
* Validating on id 0 means we should examine the first
* report in the list.
*/
- report = list_entry(
- hid->report_enum[type].report_list.next,
+ report = list_first_entry_or_null(
+ &hid->report_enum[type].report_list,
struct hid_report, list);
} else {
report = hid->report_enum[type].report_id_hash[id];
#define USB_DEVICE_ID_CH_AXIS_295 0x001c
#define USB_VENDOR_ID_CHERRY 0x046a
-#define USB_DEVICE_ID_CHERRY_MOUSE_000C 0x000c
#define USB_DEVICE_ID_CHERRY_CYMOTION 0x0023
#define USB_DEVICE_ID_CHERRY_CYMOTION_SOLAR 0x0027
#define USB_DEVICE_ID_UGEE_XPPEN_TABLET_G540 0x0075
#define USB_DEVICE_ID_UGEE_XPPEN_TABLET_G640 0x0094
#define USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO01 0x0042
+#define USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO01_V2 0x0905
#define USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO_L 0x0935
#define USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO_PRO_S 0x0909
#define USB_DEVICE_ID_UGEE_XPPEN_TABLET_STAR06 0x0078
static int dualsense_get_calibration_data(struct dualsense *ds)
{
+ struct hid_device *hdev = ds->base.hdev;
short gyro_pitch_bias, gyro_pitch_plus, gyro_pitch_minus;
short gyro_yaw_bias, gyro_yaw_plus, gyro_yaw_minus;
short gyro_roll_bias, gyro_roll_plus, gyro_roll_minus;
int speed_2x;
int range_2g;
int ret = 0;
+ int i;
uint8_t *buf;
buf = kzalloc(DS_FEATURE_REPORT_CALIBRATION_SIZE, GFP_KERNEL);
ds->gyro_calib_data[2].sens_denom = gyro_roll_plus - gyro_roll_minus;
/*
+ * Sanity check gyro calibration data. This is needed to prevent crashes
+ * during report handling of virtual, clone or broken devices not implementing
+ * calibration data properly.
+ */
+ for (i = 0; i < ARRAY_SIZE(ds->gyro_calib_data); i++) {
+ if (ds->gyro_calib_data[i].sens_denom == 0) {
+ hid_warn(hdev, "Invalid gyro calibration data for axis (%d), disabling calibration.",
+ ds->gyro_calib_data[i].abs_code);
+ ds->gyro_calib_data[i].bias = 0;
+ ds->gyro_calib_data[i].sens_numer = DS_GYRO_RANGE;
+ ds->gyro_calib_data[i].sens_denom = S16_MAX;
+ }
+ }
+
+ /*
* Set accelerometer calibration and normalization parameters.
* Data values will be normalized to 1/DS_ACC_RES_PER_G g.
*/
ds->accel_calib_data[2].sens_numer = 2*DS_ACC_RES_PER_G;
ds->accel_calib_data[2].sens_denom = range_2g;
+ /*
+ * Sanity check accelerometer calibration data. This is needed to prevent crashes
+ * during report handling of virtual, clone or broken devices not implementing calibration
+ * data properly.
+ */
+ for (i = 0; i < ARRAY_SIZE(ds->accel_calib_data); i++) {
+ if (ds->accel_calib_data[i].sens_denom == 0) {
+ hid_warn(hdev, "Invalid accelerometer calibration data for axis (%d), disabling calibration.",
+ ds->accel_calib_data[i].abs_code);
+ ds->accel_calib_data[i].bias = 0;
+ ds->accel_calib_data[i].sens_numer = DS_ACC_RANGE;
+ ds->accel_calib_data[i].sens_denom = S16_MAX;
+ }
+ }
+
err_free:
kfree(buf);
return ret;
int speed_2x;
int range_2g;
int ret = 0;
+ int i;
uint8_t *buf;
if (ds4->base.hdev->bus == BUS_USB) {
ds4->gyro_calib_data[2].sens_denom = gyro_roll_plus - gyro_roll_minus;
/*
+ * Sanity check gyro calibration data. This is needed to prevent crashes
+ * during report handling of virtual, clone or broken devices not implementing
+ * calibration data properly.
+ */
+ for (i = 0; i < ARRAY_SIZE(ds4->gyro_calib_data); i++) {
+ if (ds4->gyro_calib_data[i].sens_denom == 0) {
+ hid_warn(hdev, "Invalid gyro calibration data for axis (%d), disabling calibration.",
+ ds4->gyro_calib_data[i].abs_code);
+ ds4->gyro_calib_data[i].bias = 0;
+ ds4->gyro_calib_data[i].sens_numer = DS4_GYRO_RANGE;
+ ds4->gyro_calib_data[i].sens_denom = S16_MAX;
+ }
+ }
+
+ /*
* Set accelerometer calibration and normalization parameters.
* Data values will be normalized to 1/DS4_ACC_RES_PER_G g.
*/
ds4->accel_calib_data[2].sens_numer = 2*DS4_ACC_RES_PER_G;
ds4->accel_calib_data[2].sens_denom = range_2g;
+ /*
+ * Sanity check accelerometer calibration data. This is needed to prevent crashes
+ * during report handling of virtual, clone or broken devices not implementing calibration
+ * data properly.
+ */
+ for (i = 0; i < ARRAY_SIZE(ds4->accel_calib_data); i++) {
+ if (ds4->accel_calib_data[i].sens_denom == 0) {
+ hid_warn(hdev, "Invalid accelerometer calibration data for axis (%d), disabling calibration.",
+ ds4->accel_calib_data[i].abs_code);
+ ds4->accel_calib_data[i].bias = 0;
+ ds4->accel_calib_data[i].sens_numer = DS4_ACC_RANGE;
+ ds4->accel_calib_data[i].sens_denom = S16_MAX;
+ }
+ }
+
err_free:
kfree(buf);
return ret;
{ HID_USB_DEVICE(USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_FLIGHT_SIM_YOKE), HID_QUIRK_NOGET },
{ HID_USB_DEVICE(USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_PRO_PEDALS), HID_QUIRK_NOGET },
{ HID_USB_DEVICE(USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_PRO_THROTTLE), HID_QUIRK_NOGET },
- { HID_USB_DEVICE(USB_VENDOR_ID_CHERRY, USB_DEVICE_ID_CHERRY_MOUSE_000C), HID_QUIRK_ALWAYS_POLL },
{ HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K65RGB), HID_QUIRK_NO_INIT_REPORTS },
{ HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K65RGB_RAPIDFIRE), HID_QUIRK_NO_INIT_REPORTS | HID_QUIRK_ALWAYS_POLL },
{ HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K70RGB), HID_QUIRK_NO_INIT_REPORTS },
{ HID_USB_DEVICE(USB_VENDOR_ID_UGEE,
USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO01) },
{ HID_USB_DEVICE(USB_VENDOR_ID_UGEE,
+ USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO01_V2) },
+ { HID_USB_DEVICE(USB_VENDOR_ID_UGEE,
USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO_L) },
{ HID_USB_DEVICE(USB_VENDOR_ID_UGEE,
USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO_PRO_S) },
case VID_PID(USB_VENDOR_ID_UGEE,
USB_DEVICE_ID_UGEE_PARBLO_A610_PRO):
case VID_PID(USB_VENDOR_ID_UGEE,
+ USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO01_V2):
+ case VID_PID(USB_VENDOR_ID_UGEE,
USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO_L):
case VID_PID(USB_VENDOR_ID_UGEE,
USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO_PRO_S):
int required_slots = (size / DMA_SLOT_SIZE)
+ 1 * (size % DMA_SLOT_SIZE != 0);
+ if (!dev->ishtp_dma_tx_map) {
+ dev_err(dev->devc, "Fail to allocate Tx map\n");
+ return NULL;
+ }
+
spin_lock_irqsave(&dev->ishtp_dma_tx_lock, flags);
for (i = 0; i <= (dev->ishtp_dma_num_slots - required_slots); i++) {
free = 1;
return;
}
+ if (!dev->ishtp_dma_tx_map) {
+ dev_err(dev->devc, "Fail to allocate Tx map\n");
+ return;
+ }
+
i = (msg_addr - dev->ishtp_host_dma_tx_buf) / DMA_SLOT_SIZE;
spin_lock_irqsave(&dev->ishtp_dma_tx_lock, flags);
for (j = 0; j < acked_slots; j++) {
const struct mlx5_ib_counters *cnts = get_counters(dev, port_num - 1);
struct mlx5_core_dev *mdev;
int ret, num_counters;
- u32 mdev_port_num;
if (!stats)
return -EINVAL;
}
if (MLX5_CAP_GEN(dev->mdev, cc_query_allowed)) {
- mdev = mlx5_ib_get_native_port_mdev(dev, port_num,
- &mdev_port_num);
+ if (!port_num)
+ port_num = 1;
+ mdev = mlx5_ib_get_native_port_mdev(dev, port_num, NULL);
if (!mdev) {
/* If port is not affiliated yet, its in down state
* which doesn't have any counters yet, so it would be
return false;
}
+static int validate_rd_atomic(struct mlx5_ib_dev *dev, struct ib_qp_attr *attr,
+ int attr_mask, enum ib_qp_type qp_type)
+{
+ int log_max_ra_res;
+ int log_max_ra_req;
+
+ if (qp_type == MLX5_IB_QPT_DCI) {
+ log_max_ra_res = 1 << MLX5_CAP_GEN(dev->mdev,
+ log_max_ra_res_dc);
+ log_max_ra_req = 1 << MLX5_CAP_GEN(dev->mdev,
+ log_max_ra_req_dc);
+ } else {
+ log_max_ra_res = 1 << MLX5_CAP_GEN(dev->mdev,
+ log_max_ra_res_qp);
+ log_max_ra_req = 1 << MLX5_CAP_GEN(dev->mdev,
+ log_max_ra_req_qp);
+ }
+
+ if (attr_mask & IB_QP_MAX_QP_RD_ATOMIC &&
+ attr->max_rd_atomic > log_max_ra_res) {
+ mlx5_ib_dbg(dev, "invalid max_rd_atomic value %d\n",
+ attr->max_rd_atomic);
+ return false;
+ }
+
+ if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC &&
+ attr->max_dest_rd_atomic > log_max_ra_req) {
+ mlx5_ib_dbg(dev, "invalid max_dest_rd_atomic value %d\n",
+ attr->max_dest_rd_atomic);
+ return false;
+ }
+ return true;
+}
+
int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
int attr_mask, struct ib_udata *udata)
{
goto out;
}
- if (attr_mask & IB_QP_MAX_QP_RD_ATOMIC &&
- attr->max_rd_atomic >
- (1 << MLX5_CAP_GEN(dev->mdev, log_max_ra_res_qp))) {
- mlx5_ib_dbg(dev, "invalid max_rd_atomic value %d\n",
- attr->max_rd_atomic);
- goto out;
- }
-
- if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC &&
- attr->max_dest_rd_atomic >
- (1 << MLX5_CAP_GEN(dev->mdev, log_max_ra_req_qp))) {
- mlx5_ib_dbg(dev, "invalid max_dest_rd_atomic value %d\n",
- attr->max_dest_rd_atomic);
+ if (!validate_rd_atomic(dev, attr, attr_mask, qp_type))
goto out;
- }
if (cur_state == new_state && cur_state == IB_QPS_RESET) {
err = 0;
SRP_DEFAULT_CMD_SQ_SIZE = SRP_DEFAULT_QUEUE_SIZE - SRP_RSP_SQ_SIZE -
SRP_TSK_MGMT_SQ_SIZE,
- SRP_TAG_NO_REQ = ~0U,
- SRP_TAG_TSK_MGMT = 1U << 31,
-
SRP_MAX_PAGES_PER_MR = 512,
SRP_MAX_ADD_CDB_LEN = 16,
sizeof(struct srp_imm_buf),
};
+enum {
+ SRP_TAG_NO_REQ = ~0U,
+ SRP_TAG_TSK_MGMT = BIT(31),
+};
+
enum srp_target_state {
SRP_TARGET_SCANNING,
SRP_TARGET_LIVE,
MODULE_PARM_DESC(ptr_size,
"Pointing device width, height in pixels (default 800,600)");
-static int xenkbd_remove(struct xenbus_device *);
+static void xenkbd_remove(struct xenbus_device *);
static int xenkbd_connect_backend(struct xenbus_device *, struct xenkbd_info *);
static void xenkbd_disconnect_backend(struct xenkbd_info *);
return xenkbd_connect_backend(dev, info);
}
-static int xenkbd_remove(struct xenbus_device *dev)
+static void xenkbd_remove(struct xenbus_device *dev)
{
struct xenkbd_info *info = dev_get_drvdata(&dev->dev);
input_unregister_device(info->mtouch);
free_page((unsigned long)info->page);
kfree(info);
- return 0;
}
static int xenkbd_connect_backend(struct xenbus_device *dev,
static void arm_smmu_device_shutdown(struct platform_device *pdev)
{
- arm_smmu_device_remove(pdev);
+ struct arm_smmu_device *smmu = platform_get_drvdata(pdev);
+
+ arm_smmu_device_disable(smmu);
}
static const struct of_device_id arm_smmu_of_match[] = {
switch (cap) {
case IOMMU_CAP_CACHE_COHERENCY:
- /* Assume that a coherent TCU implies coherent TBUs */
- return cfg->smmu->features & ARM_SMMU_FEAT_COHERENT_WALK;
+ /*
+ * It's overwhelmingly the case in practice that when the pagetable
+ * walk interface is connected to a coherent interconnect, all the
+ * translation interfaces are too. Furthermore if the device is
+ * natively coherent, then its translation interface must also be.
+ */
+ return cfg->smmu->features & ARM_SMMU_FEAT_COHERENT_WALK ||
+ device_get_dma_attr(dev) == DEV_DMA_COHERENT;
case IOMMU_CAP_NOEXEC:
return true;
default:
return 0;
}
-static int arm_smmu_device_remove(struct platform_device *pdev)
+static void arm_smmu_device_shutdown(struct platform_device *pdev)
{
struct arm_smmu_device *smmu = platform_get_drvdata(pdev);
if (!smmu)
- return -ENODEV;
+ return;
if (!bitmap_empty(smmu->context_map, ARM_SMMU_MAX_CBS))
dev_notice(&pdev->dev, "disabling translation\n");
- iommu_device_unregister(&smmu->iommu);
- iommu_device_sysfs_remove(&smmu->iommu);
-
arm_smmu_rpm_get(smmu);
/* Turn the thing off */
arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sCR0, ARM_SMMU_sCR0_CLIENTPD);
clk_bulk_disable(smmu->num_clks, smmu->clks);
clk_bulk_unprepare(smmu->num_clks, smmu->clks);
- return 0;
}
-static void arm_smmu_device_shutdown(struct platform_device *pdev)
+static int arm_smmu_device_remove(struct platform_device *pdev)
{
- arm_smmu_device_remove(pdev);
+ struct arm_smmu_device *smmu = platform_get_drvdata(pdev);
+
+ if (!smmu)
+ return -ENODEV;
+
+ iommu_device_unregister(&smmu->iommu);
+ iommu_device_sysfs_remove(&smmu->iommu);
+
+ arm_smmu_device_shutdown(pdev);
+
+ return 0;
}
static int __maybe_unused arm_smmu_runtime_resume(struct device *dev)
*/
int iommu_device_claim_dma_owner(struct device *dev, void *owner)
{
- struct iommu_group *group = iommu_group_get(dev);
+ struct iommu_group *group;
int ret = 0;
- if (!group)
- return -ENODEV;
if (WARN_ON(!owner))
return -EINVAL;
+ group = iommu_group_get(dev);
+ if (!group)
+ return -ENODEV;
+
mutex_lock(&group->mutex);
if (group->owner_cnt) {
if (group->owner != owner) {
curr = __get_cached_rbnode(iovad, limit_pfn);
curr_iova = to_iova(curr);
- retry_pfn = curr_iova->pfn_hi + 1;
+ retry_pfn = curr_iova->pfn_hi;
retry:
do {
if (high_pfn < size || new_pfn < low_pfn) {
if (low_pfn == iovad->start_pfn && retry_pfn < limit_pfn) {
high_pfn = limit_pfn;
- low_pfn = retry_pfn;
+ low_pfn = retry_pfn + 1;
curr = iova_find_limit(iovad, limit_pfn);
curr_iova = to_iova(curr);
goto retry;
ret = iommu_device_sysfs_add(&data->iommu, &pdev->dev, NULL,
dev_name(&pdev->dev));
if (ret)
- return ret;
+ goto out_clk_unprepare;
ret = iommu_device_register(&data->iommu, &mtk_iommu_v1_ops, dev);
if (ret)
iommu_device_unregister(&data->iommu);
out_sysfs_remove:
iommu_device_sysfs_remove(&data->iommu);
+out_clk_unprepare:
+ clk_disable_unprepare(data->bclk);
return ret;
}
* otherwise associated queue_limits won't be imposed.
*/
bio = bio_split_to_limits(bio);
+ if (!bio)
+ return;
}
init_clone_info(&ci, md, map, bio, is_abnormal);
}
bio = bio_split_to_limits(bio);
+ if (!bio)
+ return;
if (mddev->ro == MD_RDONLY && unlikely(rw == WRITE)) {
if (bio_sectors(bio) != 0)
int cnt = 0;
int res = 0;
int res2;
- loff_t offs;
+ uint32_t offs;
size_t retlen;
struct sc_part_desc *pdesc = NULL;
struct sc_part_desc *tmpdesc;
buf = mtd_parser_tplink_safeloader_read_table(mtd);
if (!buf) {
err = -ENOENT;
- goto err_out;
+ goto err_free_parts;
}
for (idx = 0, offset = TPLINK_SAFELOADER_DATA_OFFSET;
err_free:
for (idx -= 1; idx >= 0; idx--)
kfree(parts[idx].name);
+err_free_parts:
+ kfree(parts);
err_out:
return err;
};
#include <linux/err.h>
#include <linux/errno.h>
#include <linux/module.h>
+#include <linux/delay.h>
#include <linux/device.h>
#include <linux/mutex.h>
#include <linux/math64.h>
slave_err(bond->dev, port->slave->dev,
"Port %d did not find a suitable aggregator\n",
port->actor_port_number);
+ return;
}
}
/* if all aggregator's ports are READY_N == TRUE, set ready=TRUE
static void bond_miimon_commit(struct bonding *bond)
{
- struct slave *slave, *primary;
+ struct slave *slave, *primary, *active;
bool do_failover = false;
struct list_head *iter;
+ ASSERT_RTNL();
+
bond_for_each_slave(bond, slave, iter) {
switch (slave->link_new_state) {
case BOND_LINK_NOCHANGE:
bond_miimon_link_change(bond, slave, BOND_LINK_UP);
- if (!rcu_access_pointer(bond->curr_active_slave) || slave == primary ||
- slave->prio > rcu_dereference(bond->curr_active_slave)->prio)
+ active = rtnl_dereference(bond->curr_active_slave);
+ if (!active || slave == primary || slave->prio > active->prio)
do_failover = true;
continue;
config NET_DSA_MV88E6XXX
tristate "Marvell 88E6xxx Ethernet switch fabric support"
depends on NET_DSA
- depends on PTP_1588_CLOCK_OPTIONAL
select IRQ_DOMAIN
select NET_DSA_TAG_EDSA
select NET_DSA_TAG_DSA
config NET_DSA_MV88E6XXX_PTP
bool "PTP support for Marvell 88E6xxx"
default n
- depends on NET_DSA_MV88E6XXX && PTP_1588_CLOCK
+ depends on (NET_DSA_MV88E6XXX = y && PTP_1588_CLOCK = y) || \
+ (NET_DSA_MV88E6XXX = m && PTP_1588_CLOCK)
help
Say Y to enable PTP hardware timestamping on Marvell 88E6xxx switch
chips that support it.
}
static int
-qca8k_set_lo(struct qca8k_priv *priv, int phy_id, u32 regnum, u16 lo)
+qca8k_mii_write_lo(struct mii_bus *bus, int phy_id, u32 regnum, u32 val)
{
- u16 *cached_lo = &priv->mdio_cache.lo;
- struct mii_bus *bus = priv->bus;
int ret;
+ u16 lo;
- if (lo == *cached_lo)
- return 0;
-
+ lo = val & 0xffff;
ret = bus->write(bus, phy_id, regnum, lo);
if (ret < 0)
dev_err_ratelimited(&bus->dev,
"failed to write qca8k 32bit lo register\n");
- *cached_lo = lo;
- return 0;
+ return ret;
}
static int
-qca8k_set_hi(struct qca8k_priv *priv, int phy_id, u32 regnum, u16 hi)
+qca8k_mii_write_hi(struct mii_bus *bus, int phy_id, u32 regnum, u32 val)
{
- u16 *cached_hi = &priv->mdio_cache.hi;
- struct mii_bus *bus = priv->bus;
int ret;
+ u16 hi;
- if (hi == *cached_hi)
- return 0;
-
+ hi = (u16)(val >> 16);
ret = bus->write(bus, phy_id, regnum, hi);
if (ret < 0)
dev_err_ratelimited(&bus->dev,
"failed to write qca8k 32bit hi register\n");
- *cached_hi = hi;
- return 0;
+ return ret;
}
static int
-qca8k_mii_read32(struct mii_bus *bus, int phy_id, u32 regnum, u32 *val)
+qca8k_mii_read_lo(struct mii_bus *bus, int phy_id, u32 regnum, u32 *val)
{
int ret;
ret = bus->read(bus, phy_id, regnum);
- if (ret >= 0) {
- *val = ret;
- ret = bus->read(bus, phy_id, regnum + 1);
- *val |= ret << 16;
- }
+ if (ret < 0)
+ goto err;
- if (ret < 0) {
- dev_err_ratelimited(&bus->dev,
- "failed to read qca8k 32bit register\n");
- *val = 0;
- return ret;
- }
+ *val = ret & 0xffff;
+ return 0;
+
+err:
+ dev_err_ratelimited(&bus->dev,
+ "failed to read qca8k 32bit lo register\n");
+ *val = 0;
+
+ return ret;
+}
+static int
+qca8k_mii_read_hi(struct mii_bus *bus, int phy_id, u32 regnum, u32 *val)
+{
+ int ret;
+
+ ret = bus->read(bus, phy_id, regnum);
+ if (ret < 0)
+ goto err;
+
+ *val = ret << 16;
return 0;
+
+err:
+ dev_err_ratelimited(&bus->dev,
+ "failed to read qca8k 32bit hi register\n");
+ *val = 0;
+
+ return ret;
}
-static void
-qca8k_mii_write32(struct qca8k_priv *priv, int phy_id, u32 regnum, u32 val)
+static int
+qca8k_mii_read32(struct mii_bus *bus, int phy_id, u32 regnum, u32 *val)
{
- u16 lo, hi;
+ u32 hi, lo;
int ret;
- lo = val & 0xffff;
- hi = (u16)(val >> 16);
+ *val = 0;
- ret = qca8k_set_lo(priv, phy_id, regnum, lo);
- if (ret >= 0)
- ret = qca8k_set_hi(priv, phy_id, regnum + 1, hi);
+ ret = qca8k_mii_read_lo(bus, phy_id, regnum, &lo);
+ if (ret < 0)
+ goto err;
+
+ ret = qca8k_mii_read_hi(bus, phy_id, regnum + 1, &hi);
+ if (ret < 0)
+ goto err;
+
+ *val = lo | hi;
+
+err:
+ return ret;
+}
+
+static void
+qca8k_mii_write32(struct mii_bus *bus, int phy_id, u32 regnum, u32 val)
+{
+ if (qca8k_mii_write_lo(bus, phy_id, regnum, val) < 0)
+ return;
+
+ qca8k_mii_write_hi(bus, phy_id, regnum + 1, val);
}
static int
command = get_unaligned_le32(&mgmt_ethhdr->command);
cmd = FIELD_GET(QCA_HDR_MGMT_CMD, command);
+
len = FIELD_GET(QCA_HDR_MGMT_LENGTH, command);
+ /* Special case for len of 15 as this is the max value for len and needs to
+ * be increased before converting it from word to dword.
+ */
+ if (len == 15)
+ len++;
+
+ /* We can ignore odd value, we always round up them in the alloc function. */
+ len *= sizeof(u16);
/* Make sure the seq match the requested packet */
if (get_unaligned_le32(&mgmt_ethhdr->seq) == mgmt_eth_data->seq)
if (!skb)
return NULL;
- /* Max value for len reg is 15 (0xf) but the switch actually return 16 byte
- * Actually for some reason the steps are:
- * 0: nothing
- * 1-4: first 4 byte
- * 5-6: first 12 byte
- * 7-15: all 16 byte
+ /* Hdr mgmt length value is in step of word size.
+ * As an example to process 4 byte of data the correct length to set is 2.
+ * To process 8 byte 4, 12 byte 6, 16 byte 8...
+ *
+ * Odd values will always return the next size on the ack packet.
+ * (length of 3 (6 byte) will always return 8 bytes of data)
+ *
+ * This means that a value of 15 (0xf) actually means reading/writing 32 bytes
+ * of data.
+ *
+ * To correctly calculate the length we devide the requested len by word and
+ * round up.
+ * On the ack function we can skip the odd check as we already handle the
+ * case here.
*/
- if (len == 16)
- real_len = 15;
- else
- real_len = len;
+ real_len = DIV_ROUND_UP(len, sizeof(u16));
+
+ /* We check if the result len is odd and we round up another time to
+ * the next size. (length of 3 will be increased to 4 as switch will always
+ * return 8 bytes)
+ */
+ if (real_len % sizeof(u16) != 0)
+ real_len++;
+
+ /* Max reg value is 0xf(15) but switch will always return the next size (32 byte) */
+ if (real_len == 16)
+ real_len--;
skb_reset_mac_header(skb);
skb_set_network_header(skb, skb->len);
if (ret < 0)
goto exit;
- qca8k_mii_write32(priv, 0x10 | r2, r1, val);
+ qca8k_mii_write32(bus, 0x10 | r2, r1, val);
exit:
mutex_unlock(&bus->mdio_lock);
val &= ~mask;
val |= write_val;
- qca8k_mii_write32(priv, 0x10 | r2, r1, val);
+ qca8k_mii_write32(bus, 0x10 | r2, r1, val);
exit:
mutex_unlock(&bus->mdio_lock);
qca8k_split_addr(reg, &r1, &r2, &page);
- ret = read_poll_timeout(qca8k_mii_read32, ret1, !(val & mask), 0,
+ ret = read_poll_timeout(qca8k_mii_read_hi, ret1, !(val & mask), 0,
QCA8K_BUSY_WAIT_TIMEOUT * USEC_PER_MSEC, false,
- bus, 0x10 | r2, r1, &val);
+ bus, 0x10 | r2, r1 + 1, &val);
/* Check if qca8k_read has failed for a different reason
* before returnting -ETIMEDOUT
if (ret)
goto exit;
- qca8k_mii_write32(priv, 0x10 | r2, r1, val);
+ qca8k_mii_write32(bus, 0x10 | r2, r1, val);
ret = qca8k_mdio_busy_wait(bus, QCA8K_MDIO_MASTER_CTRL,
QCA8K_MDIO_MASTER_BUSY);
exit:
/* even if the busy_wait timeouts try to clear the MASTER_EN */
- qca8k_mii_write32(priv, 0x10 | r2, r1, 0);
+ qca8k_mii_write_hi(bus, 0x10 | r2, r1 + 1, 0);
mutex_unlock(&bus->mdio_lock);
if (ret)
goto exit;
- qca8k_mii_write32(priv, 0x10 | r2, r1, val);
+ qca8k_mii_write_hi(bus, 0x10 | r2, r1 + 1, val);
ret = qca8k_mdio_busy_wait(bus, QCA8K_MDIO_MASTER_CTRL,
QCA8K_MDIO_MASTER_BUSY);
if (ret)
goto exit;
- ret = qca8k_mii_read32(bus, 0x10 | r2, r1, &val);
+ ret = qca8k_mii_read_lo(bus, 0x10 | r2, r1, &val);
exit:
/* even if the busy_wait timeouts try to clear the MASTER_EN */
- qca8k_mii_write32(priv, 0x10 | r2, r1, 0);
+ qca8k_mii_write_hi(bus, 0x10 | r2, r1 + 1, 0);
mutex_unlock(&bus->mdio_lock);
}
priv->mdio_cache.page = 0xffff;
- priv->mdio_cache.lo = 0xffff;
- priv->mdio_cache.hi = 0xffff;
/* Check the detected switch id */
ret = qca8k_read_switch_id(priv);
* mdio writes
*/
u16 page;
-/* lo and hi can also be cached and from Documentation we can skip one
- * extra mdio write if lo or hi is didn't change.
- */
- u16 lo;
- u16 hi;
};
struct qca8k_pcs {
return -EOPNOTSUPP;
}
- switch (func) {
- case ENA_ADMIN_TOEPLITZ:
- if (key) {
- if (key_len != sizeof(hash_key->key)) {
- netdev_err(ena_dev->net_device,
- "key len (%u) doesn't equal the supported size (%zu)\n",
- key_len, sizeof(hash_key->key));
- return -EINVAL;
- }
- memcpy(hash_key->key, key, key_len);
- rss->hash_init_val = init_val;
- hash_key->key_parts = key_len / sizeof(hash_key->key[0]);
+ if ((func == ENA_ADMIN_TOEPLITZ) && key) {
+ if (key_len != sizeof(hash_key->key)) {
+ netdev_err(ena_dev->net_device,
+ "key len (%u) doesn't equal the supported size (%zu)\n",
+ key_len, sizeof(hash_key->key));
+ return -EINVAL;
}
- break;
- case ENA_ADMIN_CRC32:
- rss->hash_init_val = init_val;
- break;
- default:
- netdev_err(ena_dev->net_device, "Invalid hash function (%d)\n",
- func);
- return -EINVAL;
+ memcpy(hash_key->key, key, key_len);
+ hash_key->key_parts = key_len / sizeof(hash_key->key[0]);
}
+ rss->hash_init_val = init_val;
old_func = rss->hash_func;
rss->hash_func = func;
rc = ena_com_set_hash_function(ena_dev);
switch (tuna->id) {
case ETHTOOL_RX_COPYBREAK:
len = *(u32 *)data;
- if (len > adapter->netdev->mtu) {
- ret = -EINVAL;
- break;
- }
- adapter->rx_copybreak = len;
+ ret = ena_set_rx_copybreak(adapter, len);
break;
default:
ret = -EINVAL;
static int ena_xdp_execute(struct ena_ring *rx_ring, struct xdp_buff *xdp)
{
+ u32 verdict = ENA_XDP_PASS;
struct bpf_prog *xdp_prog;
struct ena_ring *xdp_ring;
- u32 verdict = XDP_PASS;
struct xdp_frame *xdpf;
u64 *xdp_stat;
if (unlikely(!xdpf)) {
trace_xdp_exception(rx_ring->netdev, xdp_prog, verdict);
xdp_stat = &rx_ring->rx_stats.xdp_aborted;
- verdict = XDP_ABORTED;
+ verdict = ENA_XDP_DROP;
break;
}
spin_unlock(&xdp_ring->xdp_tx_lock);
xdp_stat = &rx_ring->rx_stats.xdp_tx;
+ verdict = ENA_XDP_TX;
break;
case XDP_REDIRECT:
if (likely(!xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog))) {
xdp_stat = &rx_ring->rx_stats.xdp_redirect;
+ verdict = ENA_XDP_REDIRECT;
break;
}
trace_xdp_exception(rx_ring->netdev, xdp_prog, verdict);
xdp_stat = &rx_ring->rx_stats.xdp_aborted;
- verdict = XDP_ABORTED;
+ verdict = ENA_XDP_DROP;
break;
case XDP_ABORTED:
trace_xdp_exception(rx_ring->netdev, xdp_prog, verdict);
xdp_stat = &rx_ring->rx_stats.xdp_aborted;
+ verdict = ENA_XDP_DROP;
break;
case XDP_DROP:
xdp_stat = &rx_ring->rx_stats.xdp_drop;
+ verdict = ENA_XDP_DROP;
break;
case XDP_PASS:
xdp_stat = &rx_ring->rx_stats.xdp_pass;
+ verdict = ENA_XDP_PASS;
break;
default:
bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, verdict);
xdp_stat = &rx_ring->rx_stats.xdp_invalid;
+ verdict = ENA_XDP_DROP;
}
ena_increase_stat(xdp_stat, 1, &rx_ring->syncp);
struct bpf_prog *prog,
int first, int count)
{
+ struct bpf_prog *old_bpf_prog;
struct ena_ring *rx_ring;
int i = 0;
for (i = first; i < count; i++) {
rx_ring = &adapter->rx_ring[i];
- xchg(&rx_ring->xdp_bpf_prog, prog);
- if (prog) {
+ old_bpf_prog = xchg(&rx_ring->xdp_bpf_prog, prog);
+
+ if (!old_bpf_prog && prog) {
ena_xdp_register_rxq_info(rx_ring);
rx_ring->rx_headroom = XDP_PACKET_HEADROOM;
- } else {
+ } else if (old_bpf_prog && !prog) {
ena_xdp_unregister_rxq_info(rx_ring);
rx_ring->rx_headroom = NET_SKB_PAD;
}
ring->ena_dev = adapter->ena_dev;
ring->per_napi_packets = 0;
ring->cpu = 0;
+ ring->numa_node = 0;
ring->no_interrupt_event_cnt = 0;
u64_stats_init(&ring->syncp);
}
tx_ring->next_to_use = 0;
tx_ring->next_to_clean = 0;
tx_ring->cpu = ena_irq->cpu;
+ tx_ring->numa_node = node;
return 0;
err_push_buf_intermediate_buf:
rx_ring->next_to_clean = 0;
rx_ring->next_to_use = 0;
rx_ring->cpu = ena_irq->cpu;
+ rx_ring->numa_node = node;
return 0;
}
* we expect, then we simply drop it
*/
if (unlikely(rx_ring->ena_bufs[0].len > ENA_XDP_MAX_MTU))
- return XDP_DROP;
+ return ENA_XDP_DROP;
ret = ena_xdp_execute(rx_ring, xdp);
/* The xdp program might expand the headers */
- if (ret == XDP_PASS) {
+ if (ret == ENA_XDP_PASS) {
rx_info->page_offset = xdp->data - xdp->data_hard_start;
rx_ring->ena_bufs[0].len = xdp->data_end - xdp->data;
}
xdp_init_buff(&xdp, ENA_PAGE_SIZE, &rx_ring->xdp_rxq);
do {
- xdp_verdict = XDP_PASS;
+ xdp_verdict = ENA_XDP_PASS;
skb = NULL;
ena_rx_ctx.ena_bufs = rx_ring->ena_bufs;
ena_rx_ctx.max_bufs = rx_ring->sgl_size;
xdp_verdict = ena_xdp_handle_buff(rx_ring, &xdp);
/* allocate skb and fill it */
- if (xdp_verdict == XDP_PASS)
+ if (xdp_verdict == ENA_XDP_PASS)
skb = ena_rx_skb(rx_ring,
rx_ring->ena_bufs,
ena_rx_ctx.descs,
/* Packets was passed for transmission, unmap it
* from RX side.
*/
- if (xdp_verdict == XDP_TX || xdp_verdict == XDP_REDIRECT) {
+ if (xdp_verdict & ENA_XDP_FORWARDED) {
ena_unmap_rx_buff(rx_ring,
&rx_ring->rx_buffer_info[req_id]);
rx_ring->rx_buffer_info[req_id].page = NULL;
}
}
- if (xdp_verdict != XDP_PASS) {
+ if (xdp_verdict != ENA_XDP_PASS) {
xdp_flags |= xdp_verdict;
+ total_len += ena_rx_ctx.ena_bufs[0].len;
res_budget--;
continue;
}
ena_refill_rx_bufs(rx_ring, refill_required);
}
- if (xdp_flags & XDP_REDIRECT)
+ if (xdp_flags & ENA_XDP_REDIRECT)
xdp_do_flush_map();
return work_done;
static void ena_unmask_interrupt(struct ena_ring *tx_ring,
struct ena_ring *rx_ring)
{
+ u32 rx_interval = tx_ring->smoothed_interval;
struct ena_eth_io_intr_reg intr_reg;
- u32 rx_interval = 0;
+
/* Rx ring can be NULL when for XDP tx queues which don't have an
* accompanying rx_ring pair.
*/
if (likely(tx_ring->cpu == cpu))
goto out;
+ tx_ring->cpu = cpu;
+ if (rx_ring)
+ rx_ring->cpu = cpu;
+
numa_node = cpu_to_node(cpu);
+
+ if (likely(tx_ring->numa_node == numa_node))
+ goto out;
+
put_cpu();
if (numa_node != NUMA_NO_NODE) {
ena_com_update_numa_node(tx_ring->ena_com_io_cq, numa_node);
- if (rx_ring)
+ tx_ring->numa_node = numa_node;
+ if (rx_ring) {
+ rx_ring->numa_node = numa_node;
ena_com_update_numa_node(rx_ring->ena_com_io_cq,
numa_node);
+ }
}
- tx_ring->cpu = cpu;
- if (rx_ring)
- rx_ring->cpu = cpu;
-
return;
out:
put_cpu();
if (ena_com_get_adaptive_moderation_enabled(rx_ring->ena_dev))
ena_adjust_adaptive_rx_intr_moderation(ena_napi);
+ ena_update_ring_numa_node(tx_ring, rx_ring);
ena_unmask_interrupt(tx_ring, rx_ring);
}
- ena_update_ring_numa_node(tx_ring, rx_ring);
-
ret = rx_work_done;
} else {
ret = budget;
ctx.mem_queue_type = ena_dev->tx_mem_queue_type;
ctx.msix_vector = msix_vector;
ctx.queue_size = tx_ring->ring_size;
- ctx.numa_node = cpu_to_node(tx_ring->cpu);
+ ctx.numa_node = tx_ring->numa_node;
rc = ena_com_create_io_queue(ena_dev, &ctx);
if (rc) {
ctx.mem_queue_type = ENA_ADMIN_PLACEMENT_POLICY_HOST;
ctx.msix_vector = msix_vector;
ctx.queue_size = rx_ring->ring_size;
- ctx.numa_node = cpu_to_node(rx_ring->cpu);
+ ctx.numa_node = rx_ring->numa_node;
rc = ena_com_create_io_queue(ena_dev, &ctx);
if (rc) {
return dev_was_up ? ena_up(adapter) : 0;
}
+int ena_set_rx_copybreak(struct ena_adapter *adapter, u32 rx_copybreak)
+{
+ struct ena_ring *rx_ring;
+ int i;
+
+ if (rx_copybreak > min_t(u16, adapter->netdev->mtu, ENA_PAGE_SIZE))
+ return -EINVAL;
+
+ adapter->rx_copybreak = rx_copybreak;
+
+ for (i = 0; i < adapter->num_io_queues; i++) {
+ rx_ring = &adapter->rx_ring[i];
+ rx_ring->rx_copybreak = rx_copybreak;
+ }
+
+ return 0;
+}
+
int ena_update_queue_count(struct ena_adapter *adapter, u32 new_channel_count)
{
struct ena_com_dev *ena_dev = adapter->ena_dev;
bool disable_meta_caching;
u16 no_interrupt_event_cnt;
- /* cpu for TPH */
+ /* cpu and NUMA for TPH */
int cpu;
- /* number of tx/rx_buffer_info's entries */
+ int numa_node;
+
+ /* number of tx/rx_buffer_info's entries */
int ring_size;
enum ena_admin_placement_policy_type tx_mem_queue_type;
int ena_update_queue_count(struct ena_adapter *adapter, u32 new_channel_count);
+int ena_set_rx_copybreak(struct ena_adapter *adapter, u32 rx_copybreak);
+
int ena_get_sset_count(struct net_device *netdev, int sset);
static inline void ena_reset_device(struct ena_adapter *adapter,
ENA_XDP_NO_ENOUGH_QUEUES,
};
+enum ENA_XDP_ACTIONS {
+ ENA_XDP_PASS = 0,
+ ENA_XDP_TX = BIT(0),
+ ENA_XDP_REDIRECT = BIT(1),
+ ENA_XDP_DROP = BIT(2)
+};
+
+#define ENA_XDP_FORWARDED (ENA_XDP_TX | ENA_XDP_REDIRECT)
+
static inline bool ena_xdp_present(struct ena_adapter *adapter)
{
return !!adapter->xdp_bpf_prog;
devm_free_irq(pdata->dev, pdata->dev_irq, pdata);
+ tasklet_kill(&pdata->tasklet_dev);
+ tasklet_kill(&pdata->tasklet_ecc);
+
if (pdata->vdata->ecc_support && (pdata->dev_irq != pdata->ecc_irq))
devm_free_irq(pdata->dev, pdata->ecc_irq, pdata);
xgbe_i2c_disable(pdata);
xgbe_i2c_clear_all_interrupts(pdata);
- if (pdata->dev_irq != pdata->i2c_irq)
+ if (pdata->dev_irq != pdata->i2c_irq) {
devm_free_irq(pdata->dev, pdata->i2c_irq, pdata);
+ tasklet_kill(&pdata->tasklet_i2c);
+ }
}
static int xgbe_i2c_start(struct xgbe_prv_data *pdata)
/* Disable auto-negotiation */
xgbe_an_disable_all(pdata);
- if (pdata->dev_irq != pdata->an_irq)
+ if (pdata->dev_irq != pdata->an_irq) {
devm_free_irq(pdata->dev, pdata->an_irq, pdata);
+ tasklet_kill(&pdata->tasklet_an);
+ }
pdata->phy_if.phy_impl.stop(pdata);
return 0;
}
-static int bcm_enet_shared_remove(struct platform_device *pdev)
-{
- return 0;
-}
-
/* this "shared" driver is needed because both macs share a single
* address space
*/
struct platform_driver bcm63xx_enet_shared_driver = {
.probe = bcm_enet_shared_probe,
- .remove = bcm_enet_shared_remove,
.driver = {
.name = "bcm63xx_enet_shared",
.owner = THIS_MODULE,
dma_addr -= bp->rx_dma_offset;
dma_unmap_page_attrs(&bp->pdev->dev, dma_addr, PAGE_SIZE, bp->rx_dir,
DMA_ATTR_WEAK_ORDERING);
- skb = build_skb(page_address(page), BNXT_PAGE_MODE_BUF_SIZE +
- bp->rx_dma_offset);
+ skb = build_skb(page_address(page), PAGE_SIZE);
if (!skb) {
- __free_page(page);
+ page_pool_recycle_direct(rxr->page_pool, page);
return NULL;
}
skb_mark_for_recycle(skb);
skb = napi_alloc_skb(&rxr->bnapi->napi, payload);
if (!skb) {
- __free_page(page);
+ page_pool_recycle_direct(rxr->page_pool, page);
return NULL;
}
dma_addr = rx_buf->mapping;
if (bnxt_xdp_attached(bp, rxr)) {
- bnxt_xdp_buff_init(bp, rxr, cons, &data_ptr, &len, &xdp);
+ bnxt_xdp_buff_init(bp, rxr, cons, data_ptr, len, &xdp);
if (agg_bufs) {
u32 frag_len = bnxt_rx_agg_pages_xdp(bp, cpr, &xdp,
cp_cons, agg_bufs,
}
if (xdp_active) {
- if (bnxt_rx_xdp(bp, rxr, cons, xdp, data, &len, event)) {
+ if (bnxt_rx_xdp(bp, rxr, cons, xdp, data, &data_ptr, &len, event)) {
rc = 1;
goto next_rx;
}
bp->rx_agg_ring_mask = (bp->rx_agg_nr_pages * RX_DESC_CNT) - 1;
if (BNXT_RX_PAGE_MODE(bp)) {
- rx_space = BNXT_PAGE_MODE_BUF_SIZE;
- rx_size = BNXT_MAX_PAGE_MODE_MTU;
+ rx_space = PAGE_SIZE;
+ rx_size = PAGE_SIZE -
+ ALIGN(max(NET_SKB_PAD, XDP_PACKET_HEADROOM), 8) -
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
} else {
rx_size = SKB_DATA_ALIGN(BNXT_RX_COPY_THRESH + NET_IP_ALIGN);
rx_space = rx_size + NET_SKB_PAD +
req->flags = cpu_to_le32(VNIC_PLCMODES_CFG_REQ_FLAGS_JUMBO_PLACEMENT);
req->enables = cpu_to_le32(VNIC_PLCMODES_CFG_REQ_ENABLES_JUMBO_THRESH_VALID);
- if (BNXT_RX_PAGE_MODE(bp) && !BNXT_RX_JUMBO_MODE(bp)) {
+ if (BNXT_RX_PAGE_MODE(bp)) {
+ req->jumbo_thresh = cpu_to_le16(bp->rx_buf_use_size);
+ } else {
req->flags |= cpu_to_le32(VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV4 |
VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV6);
req->enables |=
cpu_to_le32(VNIC_PLCMODES_CFG_REQ_ENABLES_HDS_THRESHOLD_VALID);
+ req->jumbo_thresh = cpu_to_le16(bp->rx_copy_thresh);
+ req->hds_threshold = cpu_to_le16(bp->rx_copy_thresh);
}
- /* thresholds not implemented in firmware yet */
- req->jumbo_thresh = cpu_to_le16(bp->rx_copy_thresh);
- req->hds_threshold = cpu_to_le16(bp->rx_copy_thresh);
req->vnic_id = cpu_to_le32(vnic->fw_vnic_id);
return hwrm_req_send(bp, req);
}
return -ENOMEM;
bp = netdev_priv(dev);
- SET_NETDEV_DEVLINK_PORT(dev, &bp->dl_port);
bp->board_idx = ent->driver_data;
bp->msg_enable = BNXT_DEF_MSG_ENABLE;
bnxt_set_max_func_irqs(bp, max_irqs);
if (bnxt_vf_pciid(bp->board_idx))
bp->flags |= BNXT_FLAG_VF;
+ /* No devlink port registration in case of a VF */
+ if (BNXT_PF(bp))
+ SET_NETDEV_DEVLINK_PORT(dev, &bp->dl_port);
+
if (pdev->msix_cap)
bp->flags |= BNXT_FLAG_MSIX_CAP;
#define BNXT_RX_PAGE_SIZE (1 << BNXT_RX_PAGE_SHIFT)
#define BNXT_MAX_MTU 9500
-#define BNXT_PAGE_MODE_BUF_SIZE \
+
+/* First RX buffer page in XDP multi-buf mode
+ *
+ * +-------------------------------------------------------------------------+
+ * | XDP_PACKET_HEADROOM | bp->rx_buf_use_size | skb_shared_info|
+ * | (bp->rx_dma_offset) | | |
+ * +-------------------------------------------------------------------------+
+ */
+#define BNXT_MAX_PAGE_MODE_MTU_SBUF \
((unsigned int)PAGE_SIZE - VLAN_ETH_HLEN - NET_IP_ALIGN - \
XDP_PACKET_HEADROOM)
#define BNXT_MAX_PAGE_MODE_MTU \
- BNXT_PAGE_MODE_BUF_SIZE - \
- SKB_DATA_ALIGN((unsigned int)sizeof(struct skb_shared_info))
+ (BNXT_MAX_PAGE_MODE_MTU_SBUF - \
+ SKB_DATA_ALIGN((unsigned int)sizeof(struct skb_shared_info)))
#define BNXT_MIN_PKT_SIZE 52
#define BNXT_DUMP_CRASH 1
struct bpf_prog *xdp_prog;
- u8 xdp_has_frags;
struct bnxt_ptp_cfg *ptp_cfg;
u8 ptp_all_rx_tstamp;
}
void bnxt_xdp_buff_init(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
- u16 cons, u8 **data_ptr, unsigned int *len,
+ u16 cons, u8 *data_ptr, unsigned int len,
struct xdp_buff *xdp)
{
struct bnxt_sw_rx_bd *rx_buf;
offset = bp->rx_offset;
mapping = rx_buf->mapping - bp->rx_dma_offset;
- dma_sync_single_for_cpu(&pdev->dev, mapping + offset, *len, bp->rx_dir);
-
- if (bp->xdp_has_frags)
- buflen = BNXT_PAGE_MODE_BUF_SIZE + offset;
+ dma_sync_single_for_cpu(&pdev->dev, mapping + offset, len, bp->rx_dir);
xdp_init_buff(xdp, buflen, &rxr->xdp_rxq);
- xdp_prepare_buff(xdp, *data_ptr - offset, offset, *len, false);
+ xdp_prepare_buff(xdp, data_ptr - offset, offset, len, false);
}
void bnxt_xdp_buff_frags_free(struct bnxt_rx_ring_info *rxr,
* false - packet should be passed to the stack.
*/
bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
- struct xdp_buff xdp, struct page *page, unsigned int *len, u8 *event)
+ struct xdp_buff xdp, struct page *page, u8 **data_ptr,
+ unsigned int *len, u8 *event)
{
struct bpf_prog *xdp_prog = READ_ONCE(rxr->xdp_prog);
struct bnxt_tx_ring_info *txr;
*event &= ~BNXT_RX_EVENT;
*len = xdp.data_end - xdp.data;
- if (orig_data != xdp.data)
+ if (orig_data != xdp.data) {
offset = xdp.data - xdp.data_hard_start;
+ *data_ptr = xdp.data_hard_start + offset;
+ }
switch (act) {
case XDP_PASS:
netdev_warn(dev, "ethtool rx/tx channels must be combined to support XDP.\n");
return -EOPNOTSUPP;
}
- if (prog) {
+ if (prog)
tx_xdp = bp->rx_nr_rings;
- bp->xdp_has_frags = prog->aux->xdp_has_frags;
- }
tc = netdev_get_num_tc(dev);
if (!tc)
struct xdp_buff *xdp);
void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts);
bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
- struct xdp_buff xdp, struct page *page, unsigned int *len,
- u8 *event);
+ struct xdp_buff xdp, struct page *page, u8 **data_ptr,
+ unsigned int *len, u8 *event);
int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp);
int bnxt_xdp_xmit(struct net_device *dev, int num_frames,
struct xdp_frame **frames, u32 flags);
bool bnxt_xdp_attached(struct bnxt *bp, struct bnxt_rx_ring_info *rxr);
void bnxt_xdp_buff_init(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
- u16 cons, u8 **data_ptr, unsigned int *len,
+ u16 cons, u8 *data_ptr, unsigned int len,
struct xdp_buff *xdp);
void bnxt_xdp_buff_frags_free(struct bnxt_rx_ring_info *rxr,
struct xdp_buff *xdp);
return 0;
}
-static int enetc_ierb_remove(struct platform_device *pdev)
-{
- return 0;
-}
-
static const struct of_device_id enetc_ierb_match[] = {
{ .compatible = "fsl,ls1028a-enetc-ierb", },
{},
.of_match_table = enetc_ierb_match,
},
.probe = enetc_ierb_probe,
- .remove = enetc_ierb_remove,
};
module_platform_driver(enetc_ierb_driver);
dtsec->dtsec_drv_param->tx_pad_crc = true;
phy_node = of_parse_phandle(mac_node, "tbi-handle", 0);
- if (!phy_node || of_device_is_available(phy_node)) {
+ if (!phy_node || !of_device_is_available(phy_node)) {
of_node_put(phy_node);
err = -EINVAL;
dev_err_probe(mac_dev->dev, err,
return 0;
}
-static bool hns3_checksum_complete(struct hns3_enet_ring *ring,
+static void hns3_checksum_complete(struct hns3_enet_ring *ring,
struct sk_buff *skb, u32 ptype, u16 csum)
{
if (ptype == HNS3_INVALID_PTYPE ||
hns3_rx_ptype_tbl[ptype].ip_summed != CHECKSUM_COMPLETE)
- return false;
+ return;
hns3_ring_stats_update(ring, csum_complete);
skb->ip_summed = CHECKSUM_COMPLETE;
skb->csum = csum_unfold((__force __sum16)csum);
-
- return true;
}
static void hns3_rx_handle_csum(struct sk_buff *skb, u32 l234info,
ptype = hnae3_get_field(ol_info, HNS3_RXD_PTYPE_M,
HNS3_RXD_PTYPE_S);
- if (hns3_checksum_complete(ring, skb, ptype, csum))
- return;
+ hns3_checksum_complete(ring, skb, ptype, csum);
/* check if hardware has done checksum */
if (!(bd_base_info & BIT(HNS3_RXD_L3L4P_B)))
if (unlikely(l234info & (BIT(HNS3_RXD_L3E_B) | BIT(HNS3_RXD_L4E_B) |
BIT(HNS3_RXD_OL3E_B) |
BIT(HNS3_RXD_OL4E_B)))) {
+ skb->ip_summed = CHECKSUM_NONE;
hns3_ring_stats_update(ring, l3l4_csum_err);
return;
return ret;
}
- if (!reset || !test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state))
+ if (!reset ||
+ !test_bit(HCLGE_VPORT_STATE_INITED, &vport->state))
continue;
+ if (!test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state) &&
+ hdev->reset_type == HNAE3_FUNC_RESET) {
+ set_bit(HCLGE_VPORT_NEED_NOTIFY_RESET,
+ &vport->need_notify);
+ continue;
+ }
+
/* Inform VF to process the reset.
* hclge_inform_reset_assert_to_vf may fail if VF
* driver is not loaded.
static void hclge_update_vport_alive(struct hclge_dev *hdev)
{
+#define HCLGE_ALIVE_SECONDS_NORMAL 8
+
+ unsigned long alive_time = HCLGE_ALIVE_SECONDS_NORMAL * HZ;
int i;
/* start from vport 1 for PF is always alive */
for (i = 1; i < hdev->num_alloc_vport; i++) {
struct hclge_vport *vport = &hdev->vport[i];
- if (time_after(jiffies, vport->last_active_jiffies + 8 * HZ))
+ if (!test_bit(HCLGE_VPORT_STATE_INITED, &vport->state) ||
+ !test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state))
+ continue;
+ if (time_after(jiffies, vport->last_active_jiffies +
+ alive_time)) {
clear_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
-
- /* If vf is not alive, set to default value */
- if (!test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state))
- vport->mps = HCLGE_MAC_DEFAULT_FRAME;
+ dev_warn(&hdev->pdev->dev,
+ "VF %u heartbeat timeout\n",
+ i - HCLGE_VF_VPORT_START_NUM);
+ }
}
}
{
struct hclge_dev *hdev = vport->back;
+ set_bit(HCLGE_VPORT_STATE_INITED, &vport->state);
set_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state);
vport->last_active_jiffies = jiffies;
+ vport->need_notify = 0;
if (test_bit(vport->vport_id, hdev->vport_config_block)) {
if (vport->vport_id) {
void hclge_vport_stop(struct hclge_vport *vport)
{
+ clear_bit(HCLGE_VPORT_STATE_INITED, &vport->state);
clear_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
+ vport->need_notify = 0;
}
static int hclge_client_start(struct hnae3_handle *handle)
return 0;
}
- dev_info(&hdev->pdev->dev, "MAC of VF %d has been set to %s\n",
+ dev_info(&hdev->pdev->dev,
+ "MAC of VF %d has been set to %s, will be active after VF reset\n",
vf, format_mac_addr);
return 0;
}
* for DEVICE_VERSION_V3, vf doesn't need to know about the port based
* VLAN state.
*/
- if (ae_dev->dev_version < HNAE3_DEVICE_VERSION_V3 &&
- test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state))
- (void)hclge_push_vf_port_base_vlan_info(&hdev->vport[0],
- vport->vport_id,
- state, &vlan_info);
-
+ if (ae_dev->dev_version < HNAE3_DEVICE_VERSION_V3) {
+ if (test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state))
+ (void)hclge_push_vf_port_base_vlan_info(&hdev->vport[0],
+ vport->vport_id,
+ state,
+ &vlan_info);
+ else
+ set_bit(HCLGE_VPORT_NEED_NOTIFY_VF_VLAN,
+ &vport->need_notify);
+ }
return 0;
}
int i;
for (i = 0; i < hdev->num_alloc_vport; i++) {
- hclge_vport_stop(vport);
+ clear_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
vport++;
}
}
return ret;
}
-static void hclge_sync_promisc_mode(struct hclge_dev *hdev)
+static int hclge_sync_vport_promisc_mode(struct hclge_vport *vport)
{
- struct hclge_vport *vport = &hdev->vport[0];
struct hnae3_handle *handle = &vport->nic;
+ struct hclge_dev *hdev = vport->back;
+ bool uc_en = false;
+ bool mc_en = false;
u8 tmp_flags;
+ bool bc_en;
int ret;
- u16 i;
if (vport->last_promisc_flags != vport->overflow_promisc_flags) {
set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state);
vport->last_promisc_flags = vport->overflow_promisc_flags;
}
- if (test_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state)) {
+ if (!test_and_clear_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE,
+ &vport->state))
+ return 0;
+
+ /* for PF */
+ if (!vport->vport_id) {
tmp_flags = handle->netdev_flags | vport->last_promisc_flags;
ret = hclge_set_promisc_mode(handle, tmp_flags & HNAE3_UPE,
tmp_flags & HNAE3_MPE);
- if (!ret) {
- clear_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE,
- &vport->state);
+ if (!ret)
set_bit(HCLGE_VPORT_STATE_VLAN_FLTR_CHANGE,
&vport->state);
- }
+ else
+ set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE,
+ &vport->state);
+ return ret;
}
- for (i = 1; i < hdev->num_alloc_vport; i++) {
- bool uc_en = false;
- bool mc_en = false;
- bool bc_en;
+ /* for VF */
+ if (vport->vf_info.trusted) {
+ uc_en = vport->vf_info.request_uc_en > 0 ||
+ vport->overflow_promisc_flags & HNAE3_OVERFLOW_UPE;
+ mc_en = vport->vf_info.request_mc_en > 0 ||
+ vport->overflow_promisc_flags & HNAE3_OVERFLOW_MPE;
+ }
+ bc_en = vport->vf_info.request_bc_en > 0;
- vport = &hdev->vport[i];
+ ret = hclge_cmd_set_promisc_mode(hdev, vport->vport_id, uc_en,
+ mc_en, bc_en);
+ if (ret) {
+ set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state);
+ return ret;
+ }
+ hclge_set_vport_vlan_fltr_change(vport);
- if (!test_and_clear_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE,
- &vport->state))
- continue;
+ return 0;
+}
- if (vport->vf_info.trusted) {
- uc_en = vport->vf_info.request_uc_en > 0 ||
- vport->overflow_promisc_flags &
- HNAE3_OVERFLOW_UPE;
- mc_en = vport->vf_info.request_mc_en > 0 ||
- vport->overflow_promisc_flags &
- HNAE3_OVERFLOW_MPE;
- }
- bc_en = vport->vf_info.request_bc_en > 0;
+static void hclge_sync_promisc_mode(struct hclge_dev *hdev)
+{
+ struct hclge_vport *vport;
+ int ret;
+ u16 i;
- ret = hclge_cmd_set_promisc_mode(hdev, vport->vport_id, uc_en,
- mc_en, bc_en);
- if (ret) {
- set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE,
- &vport->state);
+ for (i = 0; i < hdev->num_alloc_vport; i++) {
+ vport = &hdev->vport[i];
+
+ ret = hclge_sync_vport_promisc_mode(vport);
+ if (ret)
return;
- }
- hclge_set_vport_vlan_fltr_change(vport);
}
}
struct hclge_vlan_info vlan_info;
int ret;
+ clear_bit(HCLGE_VPORT_STATE_INITED, &vport->state);
+ clear_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
+ vport->need_notify = 0;
+ vport->mps = 0;
+
/* after disable sriov, clean VF rate configured by PF */
ret = hclge_tm_qs_shaper_cfg(vport, 0);
if (ret)
HCLGE_VPORT_STATE_MAC_TBL_CHANGE,
HCLGE_VPORT_STATE_PROMISC_CHANGE,
HCLGE_VPORT_STATE_VLAN_FLTR_CHANGE,
+ HCLGE_VPORT_STATE_INITED,
HCLGE_VPORT_STATE_MAX
};
+enum HCLGE_VPORT_NEED_NOTIFY {
+ HCLGE_VPORT_NEED_NOTIFY_RESET,
+ HCLGE_VPORT_NEED_NOTIFY_VF_VLAN,
+};
+
struct hclge_vlan_info {
u16 vlan_proto; /* so far support 802.1Q only */
u16 qos;
struct hnae3_handle roce;
unsigned long state;
+ unsigned long need_notify;
unsigned long last_active_jiffies;
u32 mps; /* Max packet size */
struct hclge_vf_info vf_info;
return status;
}
+static int hclge_inform_vf_reset(struct hclge_vport *vport, u16 reset_type)
+{
+ __le16 msg_data;
+ u8 dest_vfid;
+
+ dest_vfid = (u8)vport->vport_id;
+ msg_data = cpu_to_le16(reset_type);
+
+ /* send this requested info to VF */
+ return hclge_send_mbx_msg(vport, (u8 *)&msg_data, sizeof(msg_data),
+ HCLGE_MBX_ASSERTING_RESET, dest_vfid);
+}
+
int hclge_inform_reset_assert_to_vf(struct hclge_vport *vport)
{
struct hclge_dev *hdev = vport->back;
- __le16 msg_data;
u16 reset_type;
- u8 dest_vfid;
BUILD_BUG_ON(HNAE3_MAX_RESET > U16_MAX);
- dest_vfid = (u8)vport->vport_id;
-
if (hdev->reset_type == HNAE3_FUNC_RESET)
reset_type = HNAE3_VF_PF_FUNC_RESET;
else if (hdev->reset_type == HNAE3_FLR_RESET)
else
reset_type = HNAE3_VF_FUNC_RESET;
- msg_data = cpu_to_le16(reset_type);
-
- /* send this requested info to VF */
- return hclge_send_mbx_msg(vport, (u8 *)&msg_data, sizeof(msg_data),
- HCLGE_MBX_ASSERTING_RESET, dest_vfid);
+ return hclge_inform_vf_reset(vport, reset_type);
}
static void hclge_free_vector_ring_chain(struct hnae3_ring_chain_node *head)
return hclge_func_reset_cmd(hdev, vport->vport_id);
}
+static void hclge_notify_vf_config(struct hclge_vport *vport)
+{
+ struct hclge_dev *hdev = vport->back;
+ struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
+ struct hclge_port_base_vlan_config *vlan_cfg;
+ int ret;
+
+ hclge_push_vf_link_status(vport);
+ if (test_bit(HCLGE_VPORT_NEED_NOTIFY_RESET, &vport->need_notify)) {
+ ret = hclge_inform_vf_reset(vport, HNAE3_VF_PF_FUNC_RESET);
+ if (ret) {
+ dev_err(&hdev->pdev->dev,
+ "failed to inform VF %u reset!",
+ vport->vport_id - HCLGE_VF_VPORT_START_NUM);
+ return;
+ }
+ vport->need_notify = 0;
+ return;
+ }
+
+ if (ae_dev->dev_version < HNAE3_DEVICE_VERSION_V3 &&
+ test_bit(HCLGE_VPORT_NEED_NOTIFY_VF_VLAN, &vport->need_notify)) {
+ vlan_cfg = &vport->port_base_vlan_cfg;
+ ret = hclge_push_vf_port_base_vlan_info(&hdev->vport[0],
+ vport->vport_id,
+ vlan_cfg->state,
+ &vlan_cfg->vlan_info);
+ if (ret) {
+ dev_err(&hdev->pdev->dev,
+ "failed to inform VF %u port base vlan!",
+ vport->vport_id - HCLGE_VF_VPORT_START_NUM);
+ return;
+ }
+ clear_bit(HCLGE_VPORT_NEED_NOTIFY_VF_VLAN, &vport->need_notify);
+ }
+}
+
static void hclge_vf_keep_alive(struct hclge_vport *vport)
{
+ struct hclge_dev *hdev = vport->back;
+
vport->last_active_jiffies = jiffies;
+
+ if (test_bit(HCLGE_VPORT_STATE_INITED, &vport->state) &&
+ !test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state)) {
+ set_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
+ dev_info(&hdev->pdev->dev, "VF %u is alive!",
+ vport->vport_id - HCLGE_VF_VPORT_START_NUM);
+ hclge_notify_vf_config(vport);
+ }
}
static int hclge_set_vf_mtu(struct hclge_vport *vport,
hclge_rm_vport_all_mac_table(param->vport, true,
HCLGE_MAC_ADDR_MC);
hclge_rm_vport_all_vlan_table(param->vport, true);
+ param->vport->mps = 0;
return 0;
}
struct pci_dev *pdev = hdev->pdev;
int ret = 0;
- if (hdev->reset_type == HNAE3_VF_FULL_RESET &&
+ if ((hdev->reset_type == HNAE3_VF_FULL_RESET ||
+ hdev->reset_type == HNAE3_FLR_RESET) &&
test_bit(HCLGEVF_STATE_IRQ_INITED, &hdev->state)) {
hclgevf_misc_irq_uninit(hdev);
hclgevf_uninit_msi(hdev);
hclgevf_update_rss_size(handle, new_tqps_num);
- hclge_comm_get_rss_tc_info(cur_rss_size, hdev->hw_tc_map,
+ hclge_comm_get_rss_tc_info(kinfo->rss_size, hdev->hw_tc_map,
tc_offset, tc_valid, tc_size);
ret = hclge_comm_set_rss_tc_mode(&hdev->hw.hw, tc_offset,
tc_valid, tc_size);
field_flags |= IAVF_CLOUD_FIELD_IIP;
} else {
dev_err(&adapter->pdev->dev, "Bad ip src mask 0x%08x\n",
- be32_to_cpu(match.mask->dst));
+ be32_to_cpu(match.mask->src));
return -EINVAL;
}
}
/* Send the data out to a hardware port */
write_buf = kzalloc(sizeof(*write_buf), GFP_KERNEL);
if (!write_buf) {
+ kfree(cmd_buf);
err = -ENOMEM;
goto exit;
}
for (i = 0; i < ICE_GNSS_TTY_MINOR_DEVICES; i++) {
pf->gnss_tty_port[i] = kzalloc(sizeof(*pf->gnss_tty_port[i]),
GFP_KERNEL);
+ if (!pf->gnss_tty_port[i])
+ goto err_out;
+
pf->gnss_serial[i] = NULL;
tty_port_init(pf->gnss_tty_port[i]);
err = tty_register_driver(tty_driver);
if (err) {
dev_err(dev, "Failed to register TTY driver err=%d\n", err);
-
- for (i = 0; i < ICE_GNSS_TTY_MINOR_DEVICES; i++) {
- tty_port_destroy(pf->gnss_tty_port[i]);
- kfree(pf->gnss_tty_port[i]);
- }
- kfree(ttydrv_name);
- tty_driver_kref_put(pf->ice_gnss_tty_driver);
-
- return NULL;
+ goto err_out;
}
for (i = 0; i < ICE_GNSS_TTY_MINOR_DEVICES; i++)
dev_info(dev, "%s%d registered\n", ttydrv_name, i);
return tty_driver;
+
+err_out:
+ while (i--) {
+ tty_port_destroy(pf->gnss_tty_port[i]);
+ kfree(pf->gnss_tty_port[i]);
+ }
+ kfree(ttydrv_name);
+ tty_driver_kref_put(pf->ice_gnss_tty_driver);
+
+ return NULL;
}
/**
static void
ice_clean_xdp_tx_buf(struct ice_tx_ring *xdp_ring, struct ice_tx_buf *tx_buf)
{
- xdp_return_frame((struct xdp_frame *)tx_buf->raw_buf);
+ page_frag_free(tx_buf->raw_buf);
xdp_ring->xdp_tx_active--;
dma_unmap_single(xdp_ring->dev, dma_unmap_addr(tx_buf, dma),
dma_unmap_len(tx_buf, len), DMA_TO_DEVICE);
#define IGC_TSAUXC_EN_TT0 BIT(0) /* Enable target time 0. */
#define IGC_TSAUXC_EN_TT1 BIT(1) /* Enable target time 1. */
#define IGC_TSAUXC_EN_CLK0 BIT(2) /* Enable Configurable Frequency Clock 0. */
+#define IGC_TSAUXC_ST0 BIT(4) /* Start Clock 0 Toggle on Target Time 0. */
#define IGC_TSAUXC_EN_CLK1 BIT(5) /* Enable Configurable Frequency Clock 1. */
+#define IGC_TSAUXC_ST1 BIT(7) /* Start Clock 1 Toggle on Target Time 1. */
#define IGC_TSAUXC_EN_TS0 BIT(8) /* Enable hardware timestamp 0. */
#define IGC_TSAUXC_AUTT0 BIT(9) /* Auxiliary Timestamp Taken. */
#define IGC_TSAUXC_EN_TS1 BIT(10) /* Enable hardware timestamp 0. */
ts = ns_to_timespec64(ns);
if (rq->perout.index == 1) {
if (use_freq) {
- tsauxc_mask = IGC_TSAUXC_EN_CLK1;
+ tsauxc_mask = IGC_TSAUXC_EN_CLK1 | IGC_TSAUXC_ST1;
tsim_mask = 0;
} else {
tsauxc_mask = IGC_TSAUXC_EN_TT1;
freqout = IGC_FREQOUT1;
} else {
if (use_freq) {
- tsauxc_mask = IGC_TSAUXC_EN_CLK0;
+ tsauxc_mask = IGC_TSAUXC_EN_CLK0 | IGC_TSAUXC_ST0;
tsim_mask = 0;
} else {
tsauxc_mask = IGC_TSAUXC_EN_TT0;
tsauxc = rd32(IGC_TSAUXC);
tsim = rd32(IGC_TSIM);
if (rq->perout.index == 1) {
- tsauxc &= ~(IGC_TSAUXC_EN_TT1 | IGC_TSAUXC_EN_CLK1);
+ tsauxc &= ~(IGC_TSAUXC_EN_TT1 | IGC_TSAUXC_EN_CLK1 |
+ IGC_TSAUXC_ST1);
tsim &= ~IGC_TSICR_TT1;
} else {
- tsauxc &= ~(IGC_TSAUXC_EN_TT0 | IGC_TSAUXC_EN_CLK0);
+ tsauxc &= ~(IGC_TSAUXC_EN_TT0 | IGC_TSAUXC_EN_CLK0 |
+ IGC_TSAUXC_ST0);
tsim &= ~IGC_TSICR_TT0;
}
if (on) {
rp_pdev = pci_get_domain_bus_and_slot(0, 0, devfn);
if (rp_pdev && rp_pdev->subordinate) {
bus = rp_pdev->subordinate->number;
+ pci_dev_put(rp_pdev);
return pci_get_domain_bus_and_slot(0, bus, 0);
}
+ pci_dev_put(rp_pdev);
return NULL;
}
struct ixgbe_adapter *adapter = hw->back;
struct pci_dev *pdev = adapter->pdev;
struct pci_dev *func0_pdev;
+ bool has_mii = false;
/* For the C3000 family of SoCs (x550em_a) the internal ixgbe devices
* are always downstream of root ports @ 0000:00:16.0 & 0000:00:17.0
func0_pdev = ixgbe_get_first_secondary_devfn(PCI_DEVFN(0x16, 0));
if (func0_pdev) {
if (func0_pdev == pdev)
- return true;
- else
- return false;
+ has_mii = true;
+ goto out;
}
func0_pdev = ixgbe_get_first_secondary_devfn(PCI_DEVFN(0x17, 0));
if (func0_pdev == pdev)
- return true;
+ has_mii = true;
- return false;
+out:
+ pci_dev_put(func0_pdev);
+ return has_mii;
}
/**
cfg = cgx_read(cgx, lmac_id, CGXX_CMRX_CFG);
if (enable)
- cfg |= CMR_EN | DATA_PKT_RX_EN | DATA_PKT_TX_EN;
+ cfg |= DATA_PKT_RX_EN | DATA_PKT_TX_EN;
else
- cfg &= ~(CMR_EN | DATA_PKT_RX_EN | DATA_PKT_TX_EN);
+ cfg &= ~(DATA_PKT_RX_EN | DATA_PKT_TX_EN);
cgx_write(cgx, lmac_id, CGXX_CMRX_CFG, cfg);
return 0;
}
#define CMR_P2X_SEL_SHIFT 59ULL
#define CMR_P2X_SEL_NIX0 1ULL
#define CMR_P2X_SEL_NIX1 2ULL
-#define CMR_EN BIT_ULL(55)
#define DATA_PKT_TX_EN BIT_ULL(53)
#define DATA_PKT_RX_EN BIT_ULL(54)
#define CGX_LMAC_TYPE_SHIFT 40
u16 pcifunc = req->hdr.pcifunc;
struct mcs_rsrc_map *map;
struct mcs *mcs;
- int rc;
+ int rc = 0;
if (req->mcs_id >= rvu->mcs_blk_cnt)
return MCS_AF_ERR_INVALID_MCSID;
rbpool = cq->rbpool;
free_ptrs = cq->pool_ptrs;
+ get_cpu();
while (cq->pool_ptrs) {
if (otx2_alloc_rbuf(pfvf, rbpool, &bufptr)) {
/* Schedule a WQ if we fails to free atleast half of the
pfvf->hw_ops->aura_freeptr(pfvf, qidx, bufptr + OTX2_HEAD_ROOM);
cq->pool_ptrs--;
}
+ put_cpu();
cq->refill_task_sched = false;
}
if (err)
goto fail;
+ get_cpu();
/* Allocate pointers and free them to aura/pool */
for (qidx = 0; qidx < hw->tot_tx_queues; qidx++) {
pool_id = otx2_get_pool_idx(pfvf, AURA_NIX_SQ, qidx);
sq = &qset->sq[qidx];
sq->sqb_count = 0;
sq->sqb_ptrs = kcalloc(num_sqbs, sizeof(*sq->sqb_ptrs), GFP_KERNEL);
- if (!sq->sqb_ptrs)
- return -ENOMEM;
+ if (!sq->sqb_ptrs) {
+ err = -ENOMEM;
+ goto err_mem;
+ }
for (ptr = 0; ptr < num_sqbs; ptr++) {
- if (otx2_alloc_rbuf(pfvf, pool, &bufptr))
- return -ENOMEM;
+ err = otx2_alloc_rbuf(pfvf, pool, &bufptr);
+ if (err)
+ goto err_mem;
pfvf->hw_ops->aura_freeptr(pfvf, pool_id, bufptr);
sq->sqb_ptrs[sq->sqb_count++] = (u64)bufptr;
}
}
- return 0;
+err_mem:
+ put_cpu();
+ return err ? -ENOMEM : 0;
+
fail:
otx2_mbox_reset(&pfvf->mbox.mbox, 0);
otx2_aura_pool_free(pfvf);
if (err)
goto fail;
+ get_cpu();
/* Allocate pointers and free them to aura/pool */
for (pool_id = 0; pool_id < hw->rqpool_cnt; pool_id++) {
pool = &pfvf->qset.pool[pool_id];
for (ptr = 0; ptr < num_ptrs; ptr++) {
- if (otx2_alloc_rbuf(pfvf, pool, &bufptr))
- return -ENOMEM;
+ err = otx2_alloc_rbuf(pfvf, pool, &bufptr);
+ if (err)
+ goto err_mem;
pfvf->hw_ops->aura_freeptr(pfvf, pool_id,
bufptr + OTX2_HEAD_ROOM);
}
}
-
- return 0;
+err_mem:
+ put_cpu();
+ return err ? -ENOMEM : 0;
fail:
otx2_mbox_reset(&pfvf->mbox.mbox, 0);
otx2_aura_pool_free(pfvf);
if (vf->otx2_wq)
destroy_workqueue(vf->otx2_wq);
otx2_ptp_destroy(vf);
+ otx2_mcam_flow_del(vf);
+ otx2_shutdown_tc(vf);
otx2vf_disable_mbox_intr(vf);
otx2_detach_resources(&vf->mbox);
if (test_bit(CN10K_LMTST, &vf->hw.cap_flag))
return -EINVAL;
}
- cmd->stats = kvcalloc(MLX5_CMD_OP_MAX, sizeof(*cmd->stats), GFP_KERNEL);
- if (!cmd->stats)
- return -ENOMEM;
-
cmd->pool = dma_pool_create("mlx5_cmd", mlx5_core_dma_dev(dev), size, align, 0);
- if (!cmd->pool) {
- err = -ENOMEM;
- goto dma_pool_err;
- }
+ if (!cmd->pool)
+ return -ENOMEM;
err = alloc_cmd_page(dev, cmd);
if (err)
err_free_pool:
dma_pool_destroy(cmd->pool);
-dma_pool_err:
- kvfree(cmd->stats);
return err;
}
destroy_msg_cache(dev);
free_cmd_page(dev, cmd);
dma_pool_destroy(cmd->pool);
- kvfree(cmd->stats);
}
void mlx5_cmd_set_state(struct mlx5_core_dev *dev,
bool new_state = val.vbool;
if (new_state && !MLX5_CAP_GEN(dev, roce) &&
- !MLX5_CAP_GEN(dev, roce_rw_supported)) {
+ !(MLX5_CAP_GEN(dev, roce_rw_supported) && MLX5_CAP_GEN_MAX(dev, roce))) {
NL_SET_ERR_MSG_MOD(extack, "Device doesn't support RoCE");
return -EOPNOTSUPP;
}
union devlink_param_value val,
struct netlink_ext_ack *extack)
{
- return (val.vu16 >= 64 && val.vu16 <= 4096) ? 0 : -EINVAL;
+ return (val.vu32 >= 64 && val.vu32 <= 4096) ? 0 : -EINVAL;
}
static const struct devlink_param mlx5_devlink_params[] = {
goto unlock;
for (i = 0; i < priv->channels.num; i++) {
- struct mlx5e_rq *rq = &priv->channels.c[i]->rq;
+ struct mlx5e_channel *c = priv->channels.c[i];
+ struct mlx5e_rq *rq;
+
+ rq = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state) ?
+ &c->xskrq : &c->rq;
err = mlx5e_rx_reporter_build_diagnose_output(rq, fmsg);
if (err)
return -EOPNOTSUPP;
}
- if (act->police.rate_pkt_ps) {
- NL_SET_ERR_MSG_MOD(extack,
- "QoS offload not support packets per second");
- return -EOPNOTSUPP;
- }
-
return 0;
}
attr->counter = act_counter;
attr->flags |= MLX5_ATTR_FLAG_NO_IN_PORT;
+ attr->inner_match_level = MLX5_MATCH_NONE;
attr->outer_match_level = MLX5_MATCH_NONE;
attr->chain = 0;
attr->prio = 0;
static void
mlx5_ct_tc_create_dbgfs(struct mlx5_tc_ct_priv *ct_priv)
{
- bool is_fdb = ct_priv->ns_type == MLX5_FLOW_NAMESPACE_FDB;
struct mlx5_tc_ct_debugfs *ct_dbgfs = &ct_priv->debugfs;
- char dirname[16] = {};
- if (sscanf(dirname, "ct_%s", is_fdb ? "fdb" : "nic") < 0)
- return;
-
- ct_dbgfs->root = debugfs_create_dir(dirname, mlx5_debugfs_get_dev_root(ct_priv->dev));
+ ct_dbgfs->root = debugfs_create_dir("ct", mlx5_debugfs_get_dev_root(ct_priv->dev));
debugfs_create_atomic_t("offloaded", 0400, ct_dbgfs->root,
&ct_dbgfs->stats.offloaded);
debugfs_create_atomic_t("rx_dropped", 0400, ct_dbgfs->root,
int err;
list_for_each_entry(flow, flow_list, tmp_list) {
- if (!mlx5e_is_offloaded_flow(flow) || flow_flag_test(flow, SLOW))
+ if (!mlx5e_is_offloaded_flow(flow))
continue;
attr = mlx5e_tc_get_encap_attr(flow);
esw_attr->dests[flow->tmp_entry_index].flags &= ~MLX5_ESW_DEST_ENCAP_VALID;
esw_attr->dests[flow->tmp_entry_index].pkt_reformat = NULL;
+ /* Clear pkt_reformat before checking slow path flag. Because
+ * in next iteration, the same flow is already set slow path
+ * flag, but still need to clear the pkt_reformat.
+ */
+ if (flow_flag_test(flow, SLOW))
+ continue;
+
/* update from encap rule to slow path rule */
spec = &flow->attr->parse_attr->spec;
rule = mlx5e_tc_offload_to_slow_path(esw, flow, spec);
geneve_tlv_option_0_data, be32_to_cpu(opt_data_key));
MLX5_SET(fte_match_set_misc3, misc_3_c,
geneve_tlv_option_0_data, be32_to_cpu(opt_data_mask));
+ if (MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev,
+ ft_field_support.geneve_tlv_option_0_exist)) {
+ MLX5_SET_TO_ONES(fte_match_set_misc, misc_c, geneve_tlv_option_0_exist);
+ MLX5_SET_TO_ONES(fte_match_set_misc, misc_v, geneve_tlv_option_0_exist);
+ }
spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_3;
struct udphdr *udp = (struct udphdr *)(buf);
struct vxlanhdr *vxh;
+ if (tun_key->tun_flags & TUNNEL_VXLAN_OPT)
+ return -EOPNOTSUPP;
vxh = (struct vxlanhdr *)((char *)udp + sizeof(struct udphdr));
*ip_proto = IPPROTO_UDP;
u32 enc_key_id;
u32 next_pn;
sci_t sci;
+ ssci_t ssci;
salt_t salt;
struct rhash_head hash;
struct mlx5_core_dev *mdev = priv->mdev;
struct mlx5_macsec_obj_attrs obj_attrs;
union mlx5e_macsec_rule *macsec_rule;
- struct macsec_key *key;
int err;
obj_attrs.next_pn = sa->next_pn;
obj_attrs.aso_pdn = macsec->aso.pdn;
obj_attrs.epn_state = sa->epn_state;
- key = (is_tx) ? &ctx->sa.tx_sa->key : &ctx->sa.rx_sa->key;
-
if (sa->epn_state.epn_enabled) {
- obj_attrs.ssci = (is_tx) ? cpu_to_be32((__force u32)ctx->sa.tx_sa->ssci) :
- cpu_to_be32((__force u32)ctx->sa.rx_sa->ssci);
-
- memcpy(&obj_attrs.salt, &key->salt, sizeof(key->salt));
+ obj_attrs.ssci = cpu_to_be32((__force u32)sa->ssci);
+ memcpy(&obj_attrs.salt, &sa->salt, sizeof(sa->salt));
}
obj_attrs.replay_window = ctx->secy->replay_window;
}
static void update_macsec_epn(struct mlx5e_macsec_sa *sa, const struct macsec_key *key,
- const pn_t *next_pn_halves)
+ const pn_t *next_pn_halves, ssci_t ssci)
{
struct mlx5e_macsec_epn_state *epn_state = &sa->epn_state;
+ sa->ssci = ssci;
sa->salt = key->salt;
epn_state->epn_enabled = 1;
epn_state->epn_msb = next_pn_halves->upper;
tx_sa->assoc_num = assoc_num;
if (secy->xpn)
- update_macsec_epn(tx_sa, &ctx_tx_sa->key, &ctx_tx_sa->next_pn_halves);
+ update_macsec_epn(tx_sa, &ctx_tx_sa->key, &ctx_tx_sa->next_pn_halves,
+ ctx_tx_sa->ssci);
err = mlx5_create_encryption_key(mdev, ctx->sa.key, secy->key_len,
MLX5_ACCEL_OBJ_MACSEC_KEY,
rx_sa->fs_id = rx_sc->sc_xarray_element->fs_id;
if (ctx->secy->xpn)
- update_macsec_epn(rx_sa, &ctx_rx_sa->key, &ctx_rx_sa->next_pn_halves);
+ update_macsec_epn(rx_sa, &ctx_rx_sa->key, &ctx_rx_sa->next_pn_halves,
+ ctx_rx_sa->ssci);
err = mlx5_create_encryption_key(mdev, ctx->sa.key, ctx->secy->key_len,
MLX5_ACCEL_OBJ_MACSEC_KEY,
sq->channel = c;
sq->uar_map = mdev->mlx5e_res.hw_objs.bfreg.map;
sq->min_inline_mode = params->tx_min_inline_mode;
- sq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
+ sq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu) - ETH_FCS_LEN;
sq->xsk_pool = xsk_pool;
sq->stats = sq->xsk_pool ?
struct mlx5e_vlan_table *vlan;
struct mlx5e_params *params;
+ if (!netif_device_present(netdev))
+ return features;
+
vlan = mlx5e_fs_get_vlan(priv->fs);
mutex_lock(&priv->state_lock);
params = &priv->channels.params;
if (err) {
netdev_warn(priv->netdev, "vport %d error %d reading stats\n",
rep->vport, err);
- return;
+ goto out;
}
#define MLX5_GET_CTR(p, x) \
rep_stats->tx_vport_rdma_multicast_bytes =
MLX5_GET_CTR(out, received_ib_multicast.octets);
+out:
kvfree(out);
}
priv = mlx5i_epriv(netdev);
tstamp = &priv->tstamp;
- stats = rq->stats;
+ stats = &priv->channel_stats[rq->ix]->rq;
flags_rqpn = be32_to_cpu(cqe->flags_rqpn);
g = (flags_rqpn >> 28) & 3;
if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
err = mlx5e_attach_mod_hdr(priv, flow, parse_attr);
- mlx5e_mod_hdr_dealloc(&parse_attr->mod_hdr_acts);
if (err)
return err;
}
}
mutex_unlock(&tc->t_lock);
- if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
+ if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
+ mlx5e_mod_hdr_dealloc(&attr->parse_attr->mod_hdr_acts);
mlx5e_detach_mod_hdr(priv, flow);
+ }
if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT)
mlx5_fc_destroy(priv->mdev, attr->counter);
int esw_acl_egress_lgcy_setup(struct mlx5_eswitch *esw,
struct mlx5_vport *vport)
{
+ bool vst_mode_steering = esw_vst_mode_is_steering(esw);
struct mlx5_flow_destination drop_ctr_dst = {};
struct mlx5_flow_destination *dst = NULL;
struct mlx5_fc *drop_counter = NULL;
*/
int table_size = 2;
int dest_num = 0;
+ int actions_flag;
int err = 0;
if (vport->egress.legacy.drop_counter) {
vport->vport, vport->info.vlan, vport->info.qos);
/* Allowed vlan rule */
+ actions_flag = MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+ if (vst_mode_steering)
+ actions_flag |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
err = esw_egress_acl_vlan_create(esw, vport, NULL, vport->info.vlan,
- MLX5_FLOW_CONTEXT_ACTION_ALLOW);
+ actions_flag);
if (err)
goto out;
int esw_acl_ingress_lgcy_setup(struct mlx5_eswitch *esw,
struct mlx5_vport *vport)
{
+ bool vst_mode_steering = esw_vst_mode_is_steering(esw);
struct mlx5_flow_destination drop_ctr_dst = {};
struct mlx5_flow_destination *dst = NULL;
struct mlx5_flow_act flow_act = {};
struct mlx5_flow_spec *spec = NULL;
struct mlx5_fc *counter = NULL;
+ bool vst_check_cvlan = false;
+ bool vst_push_cvlan = false;
/* The ingress acl table contains 4 groups
* (2 active rules at the same time -
* 1 allow rule from one of the first 3 groups.
goto out;
}
- if (vport->info.vlan || vport->info.qos)
+ if ((vport->info.vlan || vport->info.qos)) {
+ if (vst_mode_steering)
+ vst_push_cvlan = true;
+ else if (!MLX5_CAP_ESW(esw->dev, vport_cvlan_insert_always))
+ vst_check_cvlan = true;
+ }
+
+ if (vst_check_cvlan || vport->info.spoofchk)
+ spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+
+ /* Create ingress allow rule */
+ flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+ if (vst_push_cvlan) {
+ flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH;
+ flow_act.vlan[0].prio = vport->info.qos;
+ flow_act.vlan[0].vid = vport->info.vlan;
+ flow_act.vlan[0].ethtype = ETH_P_8021Q;
+ }
+
+ if (vst_check_cvlan)
MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
outer_headers.cvlan_tag);
ether_addr_copy(smac_v, vport->info.mac);
}
- /* Create ingress allow rule */
- spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
- flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW;
vport->ingress.allow_rule = mlx5_add_flow_rules(vport->ingress.acl, spec,
&flow_act, NULL, 0);
if (IS_ERR(vport->ingress.allow_rule)) {
goto out;
}
+ if (!vst_check_cvlan && !vport->info.spoofchk)
+ goto out;
+
memset(&flow_act, 0, sizeof(flow_act));
flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP;
/* Attach drop flow counter */
return 0;
out:
- esw_acl_ingress_lgcy_cleanup(esw, vport);
+ if (err)
+ esw_acl_ingress_lgcy_cleanup(esw, vport);
kvfree(spec);
return err;
}
esw_vport_context.vport_cvlan_strip, 1);
if (set_flags & SET_VLAN_INSERT) {
- /* insert only if no vlan in packet */
- MLX5_SET(modify_esw_vport_context_in, in,
- esw_vport_context.vport_cvlan_insert, 1);
-
+ if (MLX5_CAP_ESW(dev, vport_cvlan_insert_always)) {
+ /* insert either if vlan exist in packet or not */
+ MLX5_SET(modify_esw_vport_context_in, in,
+ esw_vport_context.vport_cvlan_insert,
+ MLX5_VPORT_CVLAN_INSERT_ALWAYS);
+ } else {
+ /* insert only if no vlan in packet */
+ MLX5_SET(modify_esw_vport_context_in, in,
+ esw_vport_context.vport_cvlan_insert,
+ MLX5_VPORT_CVLAN_INSERT_WHEN_NO_CVLAN);
+ }
MLX5_SET(modify_esw_vport_context_in, in,
esw_vport_context.cvlan_pcp, qos);
MLX5_SET(modify_esw_vport_context_in, in,
static int esw_vport_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
{
+ bool vst_mode_steering = esw_vst_mode_is_steering(esw);
u16 vport_num = vport->vport;
int flags;
int err;
flags = (vport->info.vlan || vport->info.qos) ?
SET_VLAN_STRIP | SET_VLAN_INSERT : 0;
- modify_esw_vport_cvlan(esw->dev, vport_num, vport->info.vlan,
- vport->info.qos, flags);
+ if (esw->mode == MLX5_ESWITCH_OFFLOADS || !vst_mode_steering)
+ modify_esw_vport_cvlan(esw->dev, vport_num, vport->info.vlan,
+ vport->info.qos, flags);
return 0;
u16 vport, u16 vlan, u8 qos, u8 set_flags)
{
struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
+ bool vst_mode_steering = esw_vst_mode_is_steering(esw);
int err = 0;
if (IS_ERR(evport))
if (vlan > 4095 || qos > 7)
return -EINVAL;
- err = modify_esw_vport_cvlan(esw->dev, vport, vlan, qos, set_flags);
- if (err)
- return err;
+ if (esw->mode == MLX5_ESWITCH_OFFLOADS || !vst_mode_steering) {
+ err = modify_esw_vport_cvlan(esw->dev, vport, vlan, qos, set_flags);
+ if (err)
+ return err;
+ }
evport->info.vlan = vlan;
evport->info.qos = qos;
int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
u16 vport, u16 vlan, u8 qos, u8 set_flags);
+static inline bool esw_vst_mode_is_steering(struct mlx5_eswitch *esw)
+{
+ return (MLX5_CAP_ESW_EGRESS_ACL(esw->dev, pop_vlan) &&
+ MLX5_CAP_ESW_INGRESS_ACL(esw->dev, push_vlan));
+}
+
static inline bool mlx5_eswitch_vlan_actions_supported(struct mlx5_core_dev *dev,
u8 vlan_depth)
{
if (mlx5_esw_indir_table_decap_vport(attr))
vport = mlx5_esw_indir_table_decap_vport(attr);
- if (attr && !attr->chain && esw_attr->int_port)
+ if (!attr->chain && esw_attr && esw_attr->int_port)
metadata =
mlx5e_tc_int_port_get_metadata_for_match(esw_attr->int_port);
else
}
hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability);
- memcpy(hca_caps, MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability),
- MLX5_UN_SZ_BYTES(hca_cap_union));
MLX5_SET(cmd_hca_cap_2, hca_caps, migratable, 1);
err = mlx5_vport_set_other_func_cap(esw->dev, hca_caps, vport->vport,
}
hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability);
- memcpy(hca_caps, MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability),
- MLX5_UN_SZ_BYTES(hca_cap_union));
MLX5_SET(cmd_hca_cap, hca_caps, roce, enable);
err = mlx5_vport_set_other_func_cap(esw->dev, hca_caps, vport_num,
dev = container_of(priv, struct mlx5_core_dev, priv);
devlink = priv_to_devlink(dev);
+ mutex_lock(&dev->intf_state_mutex);
+ if (test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags)) {
+ mlx5_core_err(dev, "health works are not permitted at this stage\n");
+ return;
+ }
+ mutex_unlock(&dev->intf_state_mutex);
enter_error_state(dev, false);
if (IS_ERR_OR_NULL(health->fw_fatal_reporter)) {
devl_lock(devlink);
static int mlx5i_set_channels(struct net_device *dev,
struct ethtool_channels *ch)
{
- struct mlx5e_priv *priv = mlx5i_epriv(dev);
+ struct mlx5i_priv *ipriv = netdev_priv(dev);
+ struct mlx5e_priv *epriv = mlx5i_epriv(dev);
+
+ /* rtnl lock protects from race between this ethtool op and sub
+ * interface ndo_init/uninit.
+ */
+ ASSERT_RTNL();
+ if (ipriv->num_sub_interfaces > 0) {
+ mlx5_core_warn(epriv->mdev,
+ "can't change number of channels for interfaces with sub interfaces (%u)\n",
+ ipriv->num_sub_interfaces);
+ return -EINVAL;
+ }
- return mlx5e_ethtool_set_channels(priv, ch);
+ return mlx5e_ethtool_set_channels(epriv, ch);
}
static void mlx5i_get_channels(struct net_device *dev,
params->packet_merge.type = MLX5E_PACKET_MERGE_NONE;
params->hard_mtu = MLX5_IB_GRH_BYTES + MLX5_IPOIB_HARD_LEN;
params->tunneled_offload_en = false;
+
+ /* CQE compression is not supported for IPoIB */
+ params->rx_cqe_compress_def = false;
+ MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS, params->rx_cqe_compress_def);
}
/* Called directly after IPoIB netdevice was created to initialize SW structs */
stats->tx_dropped = sstats->tx_queue_dropped;
}
+struct net_device *mlx5i_parent_get(struct net_device *netdev)
+{
+ struct mlx5e_priv *priv = mlx5i_epriv(netdev);
+ struct mlx5i_priv *ipriv, *parent_ipriv;
+ struct net_device *parent_dev;
+ int parent_ifindex;
+
+ ipriv = priv->ppriv;
+
+ parent_ifindex = netdev->netdev_ops->ndo_get_iflink(netdev);
+ parent_dev = dev_get_by_index(dev_net(netdev), parent_ifindex);
+ if (!parent_dev)
+ return NULL;
+
+ parent_ipriv = netdev_priv(parent_dev);
+
+ ASSERT_RTNL();
+ parent_ipriv->num_sub_interfaces++;
+
+ ipriv->parent_dev = parent_dev;
+
+ return parent_dev;
+}
+
+void mlx5i_parent_put(struct net_device *netdev)
+{
+ struct mlx5e_priv *priv = mlx5i_epriv(netdev);
+ struct mlx5i_priv *ipriv, *parent_ipriv;
+
+ ipriv = priv->ppriv;
+ parent_ipriv = netdev_priv(ipriv->parent_dev);
+
+ ASSERT_RTNL();
+ parent_ipriv->num_sub_interfaces--;
+
+ dev_put(ipriv->parent_dev);
+}
+
int mlx5i_init_underlay_qp(struct mlx5e_priv *priv)
{
struct mlx5_core_dev *mdev = priv->mdev;
struct rdma_netdev rn; /* keep this first */
u32 qpn;
bool sub_interface;
+ u32 num_sub_interfaces;
u32 qkey;
u16 pkey_index;
struct mlx5i_pkey_qpn_ht *qpn_htbl;
+ struct net_device *parent_dev;
char *mlx5e_priv[];
};
struct mlx5_av *av, u32 dqpn, u32 dqkey, bool xmit_more);
void mlx5i_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats);
+/* Reference management for child to parent interfaces. */
+struct net_device *mlx5i_parent_get(struct net_device *netdev);
+void mlx5i_parent_put(struct net_device *netdev);
+
#endif /* CONFIG_MLX5_CORE_IPOIB */
#endif /* __MLX5E_IPOB_H__ */
struct mlx5e_priv *priv = mlx5i_epriv(dev);
struct mlx5i_priv *ipriv, *parent_ipriv;
struct net_device *parent_dev;
- int parent_ifindex;
ipriv = priv->ppriv;
- /* Get QPN to netdevice hash table from parent */
- parent_ifindex = dev->netdev_ops->ndo_get_iflink(dev);
- parent_dev = dev_get_by_index(dev_net(dev), parent_ifindex);
+ /* Link to parent */
+ parent_dev = mlx5i_parent_get(dev);
if (!parent_dev) {
mlx5_core_warn(priv->mdev, "failed to get parent device\n");
return -EINVAL;
}
+ if (dev->num_rx_queues < parent_dev->real_num_rx_queues) {
+ mlx5_core_warn(priv->mdev,
+ "failed to create child device with rx queues [%d] less than parent's [%d]\n",
+ dev->num_rx_queues,
+ parent_dev->real_num_rx_queues);
+ mlx5i_parent_put(dev);
+ return -EINVAL;
+ }
+
+ /* Get QPN to netdevice hash table from parent */
parent_ipriv = netdev_priv(parent_dev);
ipriv->qpn_htbl = parent_ipriv->qpn_htbl;
- dev_put(parent_dev);
return mlx5i_dev_init(dev);
}
static void mlx5i_pkey_dev_cleanup(struct net_device *netdev)
{
+ mlx5i_parent_put(netdev);
return mlx5i_dev_cleanup(netdev);
}
if (ldev->nb.notifier_call)
unregister_netdevice_notifier_net(&init_net, &ldev->nb);
mlx5_lag_mp_cleanup(ldev);
+ cancel_delayed_work_sync(&ldev->bond_work);
destroy_workqueue(ldev->wq);
mlx5_lag_mpesw_cleanup(ldev);
mutex_destroy(&ldev->lock);
static const struct ptp_clock_info mlx5_ptp_clock_info = {
.owner = THIS_MODULE,
.name = "mlx5_ptp",
- .max_adj = 100000000,
+ .max_adj = 50000000,
.n_alarm = 0,
.n_ext_ts = 0,
.n_per_out = 0,
MLX5_SET(cmd_hca_cap, set_hca_cap, num_total_dynamic_vf_msix,
MLX5_CAP_GEN_MAX(dev, num_total_dynamic_vf_msix));
- if (MLX5_CAP_GEN(dev, roce_rw_supported))
+ if (MLX5_CAP_GEN(dev, roce_rw_supported) && MLX5_CAP_GEN_MAX(dev, roce))
MLX5_SET(cmd_hca_cap, set_hca_cap, roce,
mlx5_is_roce_on(dev));
err_tables_cleanup:
mlx5_geneve_destroy(dev->geneve);
mlx5_vxlan_destroy(dev->vxlan);
+ mlx5_cleanup_clock(dev);
+ mlx5_cleanup_reserved_gids(dev);
mlx5_cq_debugfs_cleanup(dev);
mlx5_fw_reset_cleanup(dev);
err_events_cleanup:
#include "dr_types.h"
+#if defined(CONFIG_FRAME_WARN) && (CONFIG_FRAME_WARN < 2048)
+/* don't try to optimize STE allocation if the stack is too constaraining */
+#define DR_RULE_MAX_STES_OPTIMIZED 0
+#else
#define DR_RULE_MAX_STES_OPTIMIZED 5
+#endif
#define DR_RULE_MAX_STE_CHAIN_OPTIMIZED (DR_RULE_MAX_STES_OPTIMIZED + DR_ACTION_MAX_STES)
static int dr_rule_append_to_miss_list(struct mlx5dr_domain *dmn,
mlx5dr_domain_nic_unlock(nic_dmn);
- if (unlikely(!hw_ste_arr_is_opt))
- kfree(hw_ste_arr);
-
- return 0;
+ goto out;
free_rule:
dr_rule_clean_rule_members(rule, nic_rule);
free_hw_ste:
mlx5dr_domain_nic_unlock(nic_dmn);
+out:
if (unlikely(!hw_ste_arr_is_opt))
kfree(hw_ste_arr);
gateway:1, /* routes using the group use a gateway */
is_resilient:1;
struct list_head list; /* member in nh_res_grp_list */
- struct mlxsw_sp_nexthop nexthops[0];
+ struct mlxsw_sp_nexthop nexthops[];
#define nh_rif nexthops[0].rif
};
}
/* Take PCS out of reset */
- lan_rmw(DEV_CLOCK_CFG_LINK_SPEED_SET(2) |
+ lan_rmw(DEV_CLOCK_CFG_LINK_SPEED_SET(LAN966X_SPEED_1000) |
DEV_CLOCK_CFG_PCS_RX_RST_SET(0) |
DEV_CLOCK_CFG_PCS_TX_RST_SET(0),
DEV_CLOCK_CFG_LINK_SPEED |
struct lan966x_port *port;
int i;
+ if (!lan966x->ptp)
+ return;
+
for (i = 0; i < lan966x->num_phys_ports; i++) {
port = lan966x->ports[i];
if (!port)
bool found = false;
u32 val;
- /* Check if the port keyset selection is enabled */
val = lan_rd(lan966x, ANA_VCAP_S2_CFG(port->chip_port));
- if (!ANA_VCAP_S2_CFG_ENA_GET(val))
- return -ENOENT;
/* Collect all keysets for the port in a list */
if (l3_proto == ETH_P_ALL)
if (err)
goto cleanup_config;
- if (!of_get_mac_address(np, sparx5->base_mac)) {
+ if (of_get_mac_address(np, sparx5->base_mac)) {
dev_info(sparx5->dev, "MAC addr was not set, use random MAC\n");
eth_random_addr(sparx5->base_mac);
sparx5->base_mac[5] = 0;
* @vnic_no_name: For non-port PF vNIC make ndo_get_phys_port_name return
* -EOPNOTSUPP to keep backwards compatibility (set by app)
* @port: Pointer to nfp_port structure if vNIC is a port
+ * @mc_lock: Protect mc_addrs list
+ * @mc_addrs: List of mc addrs to add/del to HW
+ * @mc_work: Work to update mc addrs
* @app_priv: APP private data for this vNIC
*/
struct nfp_net {
struct nfp_port *port;
+ spinlock_t mc_lock;
+ struct list_head mc_addrs;
+ struct work_struct mc_work;
+
void *app_priv;
};
return err;
}
-static int nfp_net_mc_cfg(struct net_device *netdev, const unsigned char *addr, const u32 cmd)
+struct nfp_mc_addr_entry {
+ u8 addr[ETH_ALEN];
+ u32 cmd;
+ struct list_head list;
+};
+
+static int nfp_net_mc_cfg(struct nfp_net *nn, const unsigned char *addr, const u32 cmd)
{
- struct nfp_net *nn = netdev_priv(netdev);
int ret;
ret = nfp_net_mbox_lock(nn, NFP_NET_CFG_MULTICAST_SZ);
return nfp_net_mbox_reconfig_and_unlock(nn, cmd);
}
+static int nfp_net_mc_prep(struct nfp_net *nn, const unsigned char *addr, const u32 cmd)
+{
+ struct nfp_mc_addr_entry *entry;
+
+ entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
+ if (!entry)
+ return -ENOMEM;
+
+ ether_addr_copy(entry->addr, addr);
+ entry->cmd = cmd;
+ spin_lock_bh(&nn->mc_lock);
+ list_add_tail(&entry->list, &nn->mc_addrs);
+ spin_unlock_bh(&nn->mc_lock);
+
+ schedule_work(&nn->mc_work);
+
+ return 0;
+}
+
static int nfp_net_mc_sync(struct net_device *netdev, const unsigned char *addr)
{
struct nfp_net *nn = netdev_priv(netdev);
return -EINVAL;
}
- return nfp_net_mc_cfg(netdev, addr, NFP_NET_CFG_MBOX_CMD_MULTICAST_ADD);
+ return nfp_net_mc_prep(nn, addr, NFP_NET_CFG_MBOX_CMD_MULTICAST_ADD);
}
static int nfp_net_mc_unsync(struct net_device *netdev, const unsigned char *addr)
{
- return nfp_net_mc_cfg(netdev, addr, NFP_NET_CFG_MBOX_CMD_MULTICAST_DEL);
+ struct nfp_net *nn = netdev_priv(netdev);
+
+ return nfp_net_mc_prep(nn, addr, NFP_NET_CFG_MBOX_CMD_MULTICAST_DEL);
+}
+
+static void nfp_net_mc_addr_config(struct work_struct *work)
+{
+ struct nfp_net *nn = container_of(work, struct nfp_net, mc_work);
+ struct nfp_mc_addr_entry *entry, *tmp;
+ struct list_head tmp_list;
+
+ INIT_LIST_HEAD(&tmp_list);
+
+ spin_lock_bh(&nn->mc_lock);
+ list_splice_init(&nn->mc_addrs, &tmp_list);
+ spin_unlock_bh(&nn->mc_lock);
+
+ list_for_each_entry_safe(entry, tmp, &tmp_list, list) {
+ if (nfp_net_mc_cfg(nn, entry->addr, entry->cmd))
+ nn_err(nn, "Config mc address to HW failed.\n");
+
+ list_del(&entry->list);
+ kfree(entry);
+ }
}
static void nfp_net_set_rx_mode(struct net_device *netdev)
if (!nn->dp.netdev)
return 0;
+
+ spin_lock_init(&nn->mc_lock);
+ INIT_LIST_HEAD(&nn->mc_addrs);
+ INIT_WORK(&nn->mc_work, nfp_net_mc_addr_config);
+
return register_netdev(nn->dp.netdev);
err_clean_mbox:
unregister_netdev(nn->dp.netdev);
nfp_net_ipsec_clean(nn);
nfp_ccm_mbox_clean(nn);
+ flush_work(&nn->mc_work);
nfp_net_reconfig_wait_posted(nn);
}
struct qed_ptt *p_ptt,
u32 image_type,
u32 *nvram_offset_bytes,
- u32 *nvram_size_bytes)
+ u32 *nvram_size_bytes,
+ bool b_can_sleep)
{
u32 ret_mcp_resp, ret_mcp_param, ret_txn_size;
struct mcp_file_att file_att;
&ret_mcp_resp,
&ret_mcp_param,
&ret_txn_size,
- (u32 *)&file_att, false);
+ (u32 *)&file_att,
+ b_can_sleep);
/* Check response */
if (nvm_result || (ret_mcp_resp & FW_MSG_CODE_MASK) !=
static enum dbg_status qed_nvram_read(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt,
u32 nvram_offset_bytes,
- u32 nvram_size_bytes, u32 *ret_buf)
+ u32 nvram_size_bytes,
+ u32 *ret_buf,
+ bool b_can_sleep)
{
u32 ret_mcp_resp, ret_mcp_param, ret_read_size, bytes_to_copy;
s32 bytes_left = nvram_size_bytes;
&ret_mcp_resp,
&ret_mcp_param, &ret_read_size,
(u32 *)((u8 *)ret_buf + read_offset),
- false))
+ b_can_sleep))
return DBG_STATUS_NVRAM_READ_FAILED;
/* Check response */
p_ptt,
NVM_TYPE_HW_DUMP_OUT,
&hw_dump_offset_bytes,
- &hw_dump_size_bytes);
+ &hw_dump_size_bytes,
+ false);
if (status != DBG_STATUS_OK)
return 0;
status = qed_nvram_read(p_hwfn,
p_ptt,
hw_dump_offset_bytes,
- hw_dump_size_bytes, dump_buf + offset);
+ hw_dump_size_bytes,
+ dump_buf + offset,
+ false);
if (status != DBG_STATUS_OK) {
DP_NOTICE(p_hwfn,
"Failed to read MCP HW Dump image from NVRAM\n");
return qed_find_nvram_image(p_hwfn,
p_ptt,
nvram_image_type,
- trace_meta_offset, trace_meta_size);
+ trace_meta_offset,
+ trace_meta_size,
+ true);
}
/* Reads the MCP Trace meta data from NVRAM into the specified buffer */
/* Read meta data from NVRAM */
status = qed_nvram_read(p_hwfn,
p_ptt,
- nvram_offset_in_bytes, size_in_bytes, buf);
+ nvram_offset_in_bytes,
+ size_in_bytes,
+ buf,
+ true);
if (status != DBG_STATUS_OK)
return status;
goto disable_mbx_intr;
qlcnic_83xx_clear_function_resources(adapter);
- qlcnic_dcb_enable(adapter->dcb);
+
+ err = qlcnic_dcb_enable(adapter->dcb);
+ if (err) {
+ qlcnic_dcb_free(adapter->dcb);
+ goto disable_mbx_intr;
+ }
+
qlcnic_83xx_initialize_nic(adapter, 1);
qlcnic_dcb_get_info(adapter->dcb);
unsigned long state;
};
-static inline void qlcnic_clear_dcb_ops(struct qlcnic_dcb *dcb)
-{
- kfree(dcb);
-}
-
static inline int qlcnic_dcb_get_hw_capability(struct qlcnic_dcb *dcb)
{
if (dcb && dcb->ops->get_hw_capability)
dcb->ops->init_dcbnl_ops(dcb);
}
-static inline void qlcnic_dcb_enable(struct qlcnic_dcb *dcb)
+static inline int qlcnic_dcb_enable(struct qlcnic_dcb *dcb)
{
- if (dcb && qlcnic_dcb_attach(dcb))
- qlcnic_clear_dcb_ops(dcb);
+ return dcb ? qlcnic_dcb_attach(dcb) : 0;
}
#endif
"Device does not support MSI interrupts\n");
if (qlcnic_82xx_check(adapter)) {
- qlcnic_dcb_enable(adapter->dcb);
+ err = qlcnic_dcb_enable(adapter->dcb);
+ if (err) {
+ qlcnic_dcb_free(adapter->dcb);
+ dev_err(&pdev->dev, "Failed to enable DCB\n");
+ goto err_out_free_hw;
+ }
+
qlcnic_dcb_get_info(adapter->dcb);
err = qlcnic_setup_intr(adapter);
/* 8168F family. */
{ 0x7c8, 0x488, RTL_GIGA_MAC_VER_38 },
- /* It seems this chip version never made it to
- * the wild. Let's disable detection.
- * { 0x7cf, 0x481, RTL_GIGA_MAC_VER_36 },
- */
+ { 0x7cf, 0x481, RTL_GIGA_MAC_VER_36 },
{ 0x7cf, 0x480, RTL_GIGA_MAC_VER_35 },
/* 8168E family. */
return 0;
}
-static void rtl_wol_enable_rx(struct rtl8169_private *tp)
-{
- if (tp->mac_version >= RTL_GIGA_MAC_VER_25)
- RTL_W32(tp, RxConfig, RTL_R32(tp, RxConfig) |
- AcceptBroadcast | AcceptMulticast | AcceptMyPhys);
-}
-
-static void rtl_prepare_power_down(struct rtl8169_private *tp)
-{
- if (tp->dash_type != RTL_DASH_NONE)
- return;
-
- if (tp->mac_version == RTL_GIGA_MAC_VER_32 ||
- tp->mac_version == RTL_GIGA_MAC_VER_33)
- rtl_ephy_write(tp, 0x19, 0xff64);
-
- if (device_may_wakeup(tp_to_dev(tp))) {
- phy_speed_down(tp->phydev, false);
- rtl_wol_enable_rx(tp);
- }
-}
-
static void rtl_init_rxcfg(struct rtl8169_private *tp)
{
switch (tp->mac_version) {
rtl_wait_txrx_fifo_empty(tp);
}
+static void rtl_wol_enable_rx(struct rtl8169_private *tp)
+{
+ if (tp->mac_version >= RTL_GIGA_MAC_VER_25)
+ RTL_W32(tp, RxConfig, RTL_R32(tp, RxConfig) |
+ AcceptBroadcast | AcceptMulticast | AcceptMyPhys);
+
+ if (tp->mac_version >= RTL_GIGA_MAC_VER_40)
+ rtl_disable_rxdvgate(tp);
+}
+
+static void rtl_prepare_power_down(struct rtl8169_private *tp)
+{
+ if (tp->dash_type != RTL_DASH_NONE)
+ return;
+
+ if (tp->mac_version == RTL_GIGA_MAC_VER_32 ||
+ tp->mac_version == RTL_GIGA_MAC_VER_33)
+ rtl_ephy_write(tp, 0x19, 0xff64);
+
+ if (device_may_wakeup(tp_to_dev(tp))) {
+ phy_speed_down(tp->phydev, false);
+ rtl_wol_enable_rx(tp);
+ }
+}
+
static void rtl_set_tx_config_registers(struct rtl8169_private *tp)
{
u32 val = TX_DMA_BURST << TxDMAShift |
netdev_reset_queue(tp->dev);
}
-static void rtl8169_cleanup(struct rtl8169_private *tp, bool going_down)
+static void rtl8169_cleanup(struct rtl8169_private *tp)
{
napi_disable(&tp->napi);
rtl_rx_close(tp);
- if (going_down && tp->dev->wol_enabled)
- goto no_reset;
-
switch (tp->mac_version) {
case RTL_GIGA_MAC_VER_28:
case RTL_GIGA_MAC_VER_31:
}
rtl_hw_reset(tp);
-no_reset:
+
rtl8169_tx_clear(tp);
rtl8169_init_ring_indexes(tp);
}
netif_stop_queue(tp->dev);
- rtl8169_cleanup(tp, false);
+ rtl8169_cleanup(tp);
for (i = 0; i < NUM_RX_DESC; i++)
rtl8169_mark_to_asic(tp->RxDescArray + i);
pci_clear_master(tp->pci_dev);
rtl_pci_commit(tp);
- rtl8169_cleanup(tp, true);
+ rtl8169_cleanup(tp);
rtl_disable_exit_l1(tp);
rtl_prepare_power_down(tp);
}
{
struct platform_device *pdev = priv->pdev;
struct rswitch_device *rdev;
+ struct device_node *port;
struct net_device *ndev;
int err;
netif_napi_add(ndev, &rdev->napi, rswitch_poll);
- err = of_get_ethdev_address(pdev->dev.of_node, ndev);
+ port = rswitch_get_port_node(rdev);
+ err = of_get_ethdev_address(port, ndev);
+ of_node_put(port);
if (err) {
if (is_valid_ether_addr(rdev->etha->mac_addr))
eth_hw_addr_set(ndev, rdev->etha->mac_addr);
pm_runtime_get_sync(&pdev->dev);
ret = rswitch_init(priv);
+ if (ret < 0) {
+ pm_runtime_put(&pdev->dev);
+ pm_runtime_disable(&pdev->dev);
+ return ret;
+ }
device_set_wakeup_capable(&pdev->dev, 1);
struct mediatek_dwmac_variant {
int (*dwmac_set_phy_interface)(struct mediatek_dwmac_plat_data *plat);
int (*dwmac_set_delay)(struct mediatek_dwmac_plat_data *plat);
- void (*dwmac_fix_mac_speed)(void *priv, unsigned int speed);
/* clock ids to be requested */
const char * const *clk_list;
return 0;
}
-static void mt8195_fix_mac_speed(void *priv, unsigned int speed)
-{
- struct mediatek_dwmac_plat_data *priv_plat = priv;
-
- if ((phy_interface_mode_is_rgmii(priv_plat->phy_mode))) {
- /* prefer 2ns fixed delay which is controlled by TXC_PHASE_CTRL,
- * when link speed is 1Gbps with RGMII interface,
- * Fall back to delay macro circuit for 10/100Mbps link speed.
- */
- if (speed == SPEED_1000)
- regmap_update_bits(priv_plat->peri_regmap,
- MT8195_PERI_ETH_CTRL0,
- MT8195_RGMII_TXC_PHASE_CTRL |
- MT8195_DLY_GTXC_ENABLE |
- MT8195_DLY_GTXC_INV |
- MT8195_DLY_GTXC_STAGES,
- MT8195_RGMII_TXC_PHASE_CTRL);
- else
- mt8195_set_delay(priv_plat);
- }
-}
-
static const struct mediatek_dwmac_variant mt8195_gmac_variant = {
.dwmac_set_phy_interface = mt8195_set_interface,
.dwmac_set_delay = mt8195_set_delay,
- .dwmac_fix_mac_speed = mt8195_fix_mac_speed,
.clk_list = mt8195_dwmac_clk_l,
.num_clks = ARRAY_SIZE(mt8195_dwmac_clk_l),
.dma_bit_mask = 35,
plat->bsp_priv = priv_plat;
plat->init = mediatek_dwmac_init;
plat->clks_config = mediatek_dwmac_clks_config;
- if (priv_plat->variant->dwmac_fix_mac_speed)
- plat->fix_mac_speed = priv_plat->variant->dwmac_fix_mac_speed;
plat->safety_feat_cfg = devm_kzalloc(&pdev->dev,
sizeof(*plat->safety_feat_cfg),
}
writel(acr_value, ptpaddr + PTP_ACR);
mutex_unlock(&priv->aux_ts_lock);
- ret = 0;
+ /* wait for auxts fifo clear to finish */
+ ret = readl_poll_timeout(ptpaddr + PTP_ACR, acr_value,
+ !(acr_value & PTP_ACR_ATSFC),
+ 10, 10000);
break;
default:
static const struct ipa_mem_data ipa_mem_data = {
.local_count = ARRAY_SIZE(ipa_mem_local_data),
.local = ipa_mem_local_data,
- .imem_addr = 0x146a9000,
+ .imem_addr = 0x146a8000,
.imem_size = 0x00002000,
.smem_id = 497,
.smem_size = 0x00009000,
u32 endpoint_id, bool enable)
{
struct ipa *ipa = interrupt->ipa;
+ u32 mask = BIT(endpoint_id % 32);
u32 unit = endpoint_id / 32;
const struct ipa_reg *reg;
u32 offset;
- u32 mask;
u32 val;
WARN_ON(!test_bit(endpoint_id, ipa->available));
offset = ipa_reg_n_offset(reg, unit);
val = ioread32(ipa->reg_virt + offset);
- mask = BIT(endpoint_id);
if (enable)
val |= mask;
else
if (!priv->phy_dev->drv) {
dev_info(dev, "Attached phy not ready\n");
+ put_device(&priv->phy_dev->mdio.dev);
return -EPROBE_DEFER;
}
USB_CDC_PROTO_NONE),
.driver_info = (unsigned long)&wwan_info,
}, {
+ /* Cinterion PLS62-W modem by GEMALTO/THALES */
+ USB_DEVICE_AND_INTERFACE_INFO(0x1e2d, 0x005b, USB_CLASS_COMM,
+ USB_CDC_SUBCLASS_ETHERNET,
+ USB_CDC_PROTO_NONE),
+ .driver_info = (unsigned long)&wwan_info,
+}, {
/* Cinterion PLS83/PLS63 modem by GEMALTO/THALES */
USB_DEVICE_AND_INTERFACE_INFO(0x1e2d, 0x0069, USB_CLASS_COMM,
USB_CDC_SUBCLASS_ETHERNET,
REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07ab),
REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07c6),
REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x0927),
+ REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x0c5e),
REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101),
REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x304f),
REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x3054),
off = le32_to_cpu(u.get_c->offset);
len = le32_to_cpu(u.get_c->len);
- if (unlikely((8 + off + len) > CONTROL_BUFFER_SIZE))
+ if (unlikely((off > CONTROL_BUFFER_SIZE - 8) ||
+ (len > CONTROL_BUFFER_SIZE - 8 - off)))
goto response_error;
if (*reply_len != -1 && len != *reply_len)
xdp_set_return_frame_no_direct();
done = veth_xdp_rcv(rq, budget, &bq, &stats);
+ if (stats.xdp_redirect > 0)
+ xdp_do_flush();
+
if (done < budget && napi_complete_done(napi, done)) {
/* Write rx_notify_masked before reading ptr_ring */
smp_store_mb(rq->rx_notify_masked, false);
if (stats.xdp_tx > 0)
veth_xdp_flush(rq, &bq);
- if (stats.xdp_redirect > 0)
- xdp_do_flush();
xdp_clear_return_frame_no_direct();
return done;
(le32_to_cpu(gdesc->dword[3]) &
VMXNET3_RCD_CSUM_OK) == VMXNET3_RCD_CSUM_OK) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
+ if ((le32_to_cpu(gdesc->dword[0]) &
+ (1UL << VMXNET3_RCD_HDR_INNER_SHIFT))) {
+ skb->csum_level = 1;
+ }
WARN_ON_ONCE(!(gdesc->rcd.tcp || gdesc->rcd.udp) &&
!(le32_to_cpu(gdesc->dword[0]) &
(1UL << VMXNET3_RCD_HDR_INNER_SHIFT)));
} else if (gdesc->rcd.v6 && (le32_to_cpu(gdesc->dword[3]) &
(1 << VMXNET3_RCD_TUC_SHIFT))) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
+ if ((le32_to_cpu(gdesc->dword[0]) &
+ (1UL << VMXNET3_RCD_HDR_INNER_SHIFT))) {
+ skb->csum_level = 1;
+ }
WARN_ON_ONCE(!(gdesc->rcd.tcp || gdesc->rcd.udp) &&
!(le32_to_cpu(gdesc->dword[0]) &
(1UL << VMXNET3_RCD_HDR_INNER_SHIFT)));
/* loopback, multicast & non-ND link-local traffic; do not push through
* packet taps again. Reset pkt_type for upper layers to process skb.
- * For strict packets with a source LLA, determine the dst using the
- * original ifindex.
+ * For non-loopback strict packets, determine the dst using the original
+ * ifindex.
*/
if (skb->pkt_type == PACKET_LOOPBACK || (need_strict && !is_ndisc)) {
skb->dev = vrf_dev;
if (skb->pkt_type == PACKET_LOOPBACK)
skb->pkt_type = PACKET_HOST;
- else if (ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)
+ else
vrf_ip6_input_dst(skb, vrf_dev, orig_iif);
goto out;
vxlan_vnigroup_init(vxlan);
dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
- if (!dev->tstats)
- return -ENOMEM;
+ if (!dev->tstats) {
+ err = -ENOMEM;
+ goto err_vnigroup_uninit;
+ }
err = gro_cells_init(&vxlan->gro_cells, dev);
- if (err) {
- free_percpu(dev->tstats);
- return err;
- }
+ if (err)
+ goto err_free_percpu;
return 0;
+
+err_free_percpu:
+ free_percpu(dev->tstats);
+err_vnigroup_uninit:
+ if (vxlan->cfg.flags & VXLAN_F_VNIFILTER)
+ vxlan_vnigroup_uninit(vxlan);
+ return err;
}
static void vxlan_fdb_delete_default(struct vxlan_dev *vxlan, __be32 vni)
}
#ifdef CONFIG_ATH9K_HTC_DEBUGFS
-#define __STAT_SAFE(hif_dev, expr) ((hif_dev)->htc_handle->drv_priv ? (expr) : 0)
-#define CAB_STAT_INC(priv) ((priv)->debug.tx_stats.cab_queued++)
-#define TX_QSTAT_INC(priv, q) ((priv)->debug.tx_stats.queue_stats[q]++)
+#define __STAT_SAFE(hif_dev, expr) do { ((hif_dev)->htc_handle->drv_priv ? (expr) : 0); } while (0)
+#define CAB_STAT_INC(priv) do { ((priv)->debug.tx_stats.cab_queued++); } while (0)
+#define TX_QSTAT_INC(priv, q) do { ((priv)->debug.tx_stats.queue_stats[q]++); } while (0)
#define TX_STAT_INC(hif_dev, c) \
__STAT_SAFE((hif_dev), (hif_dev)->htc_handle->drv_priv->debug.tx_stats.c++)
struct ethtool_stats *stats, u64 *data);
#else
-#define TX_STAT_INC(hif_dev, c)
-#define TX_STAT_ADD(hif_dev, c, a)
-#define RX_STAT_INC(hif_dev, c)
-#define RX_STAT_ADD(hif_dev, c, a)
+#define TX_STAT_INC(hif_dev, c) do { } while (0)
+#define TX_STAT_ADD(hif_dev, c, a) do { } while (0)
+#define RX_STAT_INC(hif_dev, c) do { } while (0)
+#define RX_STAT_ADD(hif_dev, c, a) do { } while (0)
#define CAB_STAT_INC(priv)
#define TX_QSTAT_INC(priv, c)
/* Apple ARM64 platforms have their own idea of board type, passed in
* via the device tree. They also have an antenna SKU parameter
*/
- if (!of_property_read_string(np, "brcm,board-type", &prop))
+ err = of_property_read_string(np, "brcm,board-type", &prop);
+ if (!err)
settings->board_type = prop;
if (!of_property_read_string(np, "apple,antenna-sku", &prop))
/* Set board-type to the first string of the machine compatible prop */
root = of_find_node_by_path("/");
- if (root && !settings->board_type) {
+ if (root && err) {
char *board_type;
const char *tmp;
int i, j, num_sub_bands;
s8 *gain;
+ /* many firmware images for JF lie about this */
+ if (CSR_HW_RFID_TYPE(fwrt->trans->hw_rf_id) ==
+ CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_JF))
+ return -EOPNOTSUPP;
+
if (!fw_has_capa(&fwrt->fw->ucode_capa, IWL_UCODE_TLV_CAPA_SET_PPAG)) {
IWL_DEBUG_RADIO(fwrt,
"PPAG capability not supported by FW, command not sent.\n");
config MT7996E
tristate "MediaTek MT7996 (PCIe) support"
select MT76_CONNAC_LIB
+ select RELAY
depends on MAC80211
depends on PCI
help
obj-$(CONFIG_WL12XX) += wl12xx/
obj-$(CONFIG_WL1251) += wl1251/
obj-$(CONFIG_WL18XX) += wl18xx/
-
-# small builtin driver bit
-obj-$(CONFIG_WILINK_PLATFORM_DATA) += wilink_platform_data.o
return 0;
}
-static int netback_remove(struct xenbus_device *dev)
+static void netback_remove(struct xenbus_device *dev)
{
struct backend_info *be = dev_get_drvdata(&dev->dev);
kfree(be->hotplug_script);
kfree(be);
dev_set_drvdata(&dev->dev, NULL);
- return 0;
}
/*
} while (!ret);
}
-static int xennet_remove(struct xenbus_device *dev)
+static void xennet_remove(struct xenbus_device *dev)
{
struct netfront_info *info = dev_get_drvdata(&dev->dev);
rtnl_unlock();
}
xennet_free_netdev(info->netdev);
-
- return 0;
}
static const struct xenbus_device_id netfront_ids[] = {
return usb_submit_urb(phy->ack_urb, flags);
}
+struct pn533_out_arg {
+ struct pn533_usb_phy *phy;
+ struct completion done;
+};
+
static int pn533_usb_send_frame(struct pn533 *dev,
struct sk_buff *out)
{
struct pn533_usb_phy *phy = dev->phy;
+ struct pn533_out_arg arg;
+ void *cntx;
int rc;
if (phy->priv == NULL)
print_hex_dump_debug("PN533 TX: ", DUMP_PREFIX_NONE, 16, 1,
out->data, out->len, false);
+ init_completion(&arg.done);
+ cntx = phy->out_urb->context;
+ phy->out_urb->context = &arg;
+
rc = usb_submit_urb(phy->out_urb, GFP_KERNEL);
if (rc)
return rc;
+ wait_for_completion(&arg.done);
+ phy->out_urb->context = cntx;
+
if (dev->protocol_type == PN533_PROTO_REQ_RESP) {
/* request for response for sent packet directly */
rc = pn533_submit_urb_for_response(phy, GFP_KERNEL);
return arg.rc;
}
-static void pn533_send_complete(struct urb *urb)
+static void pn533_out_complete(struct urb *urb)
+{
+ struct pn533_out_arg *arg = urb->context;
+ struct pn533_usb_phy *phy = arg->phy;
+
+ switch (urb->status) {
+ case 0:
+ break; /* success */
+ case -ECONNRESET:
+ case -ENOENT:
+ dev_dbg(&phy->udev->dev,
+ "The urb has been stopped (status %d)\n",
+ urb->status);
+ break;
+ case -ESHUTDOWN:
+ default:
+ nfc_err(&phy->udev->dev,
+ "Urb failure (status %d)\n",
+ urb->status);
+ }
+
+ complete(&arg->done);
+}
+
+static void pn533_ack_complete(struct urb *urb)
{
struct pn533_usb_phy *phy = urb->context;
usb_fill_bulk_urb(phy->out_urb, phy->udev,
usb_sndbulkpipe(phy->udev, out_endpoint),
- NULL, 0, pn533_send_complete, phy);
+ NULL, 0, pn533_out_complete, phy);
usb_fill_bulk_urb(phy->ack_urb, phy->udev,
usb_sndbulkpipe(phy->udev, out_endpoint),
- NULL, 0, pn533_send_complete, phy);
+ NULL, 0, pn533_ack_complete, phy);
switch (id->driver_info) {
case PN533_DEVICE_STD:
}
ret = nvme_init_ctrl(&anv->ctrl, anv->dev, &nvme_ctrl_ops,
- NVME_QUIRK_SKIP_CID_GEN);
+ NVME_QUIRK_SKIP_CID_GEN | NVME_QUIRK_IDENTIFY_CNS);
if (ret) {
dev_err_probe(dev, ret, "Failed to initialize nvme_ctrl");
goto put_dev;
#include <linux/io_uring.h>
#include "nvme.h"
+enum {
+ NVME_IOCTL_VEC = (1 << 0),
+ NVME_IOCTL_PARTITION = (1 << 1),
+};
+
static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c,
- fmode_t mode)
+ unsigned int flags, fmode_t mode)
{
u32 effects;
return true;
/*
+ * Do not allow unprivileged passthrough on partitions, as that allows an
+ * escape from the containment of the partition.
+ */
+ if (flags & NVME_IOCTL_PARTITION)
+ return false;
+
+ /*
* Do not allow unprivileged processes to send vendor specific or fabrics
* commands as we can't be sure about their effects.
*/
static int nvme_map_user_request(struct request *req, u64 ubuffer,
unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
u32 meta_seed, void **metap, struct io_uring_cmd *ioucmd,
- bool vec)
+ unsigned int flags)
{
struct request_queue *q = req->q;
struct nvme_ns *ns = q->queuedata;
struct iov_iter iter;
/* fixedbufs is only for non-vectored io */
- if (WARN_ON_ONCE(vec))
+ if (WARN_ON_ONCE(flags & NVME_IOCTL_VEC))
return -EINVAL;
ret = io_uring_cmd_import_fixed(ubuffer, bufflen,
rq_data_dir(req), &iter, ioucmd);
ret = blk_rq_map_user_iov(q, req, NULL, &iter, GFP_KERNEL);
} else {
ret = blk_rq_map_user_io(req, NULL, nvme_to_user_ptr(ubuffer),
- bufflen, GFP_KERNEL, vec, 0, 0,
- rq_data_dir(req));
+ bufflen, GFP_KERNEL, flags & NVME_IOCTL_VEC, 0,
+ 0, rq_data_dir(req));
}
if (ret)
}
static int nvme_submit_user_cmd(struct request_queue *q,
- struct nvme_command *cmd, u64 ubuffer,
- unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
- u32 meta_seed, u64 *result, unsigned timeout, bool vec)
+ struct nvme_command *cmd, u64 ubuffer, unsigned bufflen,
+ void __user *meta_buffer, unsigned meta_len, u32 meta_seed,
+ u64 *result, unsigned timeout, unsigned int flags)
{
struct nvme_ctrl *ctrl;
struct request *req;
req->timeout = timeout;
if (ubuffer && bufflen) {
ret = nvme_map_user_request(req, ubuffer, bufflen, meta_buffer,
- meta_len, meta_seed, &meta, NULL, vec);
+ meta_len, meta_seed, &meta, NULL, flags);
if (ret)
return ret;
}
c.rw.apptag = cpu_to_le16(io.apptag);
c.rw.appmask = cpu_to_le16(io.appmask);
- return nvme_submit_user_cmd(ns->queue, &c,
- io.addr, length,
- metadata, meta_len, lower_32_bits(io.slba), NULL, 0,
- false);
+ return nvme_submit_user_cmd(ns->queue, &c, io.addr, length, metadata,
+ meta_len, lower_32_bits(io.slba), NULL, 0, 0);
}
static bool nvme_validate_passthru_nsid(struct nvme_ctrl *ctrl,
}
static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
- struct nvme_passthru_cmd __user *ucmd, fmode_t mode)
+ struct nvme_passthru_cmd __user *ucmd, unsigned int flags,
+ fmode_t mode)
{
struct nvme_passthru_cmd cmd;
struct nvme_command c;
c.common.cdw14 = cpu_to_le32(cmd.cdw14);
c.common.cdw15 = cpu_to_le32(cmd.cdw15);
- if (!nvme_cmd_allowed(ns, &c, mode))
+ if (!nvme_cmd_allowed(ns, &c, 0, mode))
return -EACCES;
if (cmd.timeout_ms)
timeout = msecs_to_jiffies(cmd.timeout_ms);
status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
- cmd.addr, cmd.data_len,
- nvme_to_user_ptr(cmd.metadata), cmd.metadata_len,
- 0, &result, timeout, false);
+ cmd.addr, cmd.data_len, nvme_to_user_ptr(cmd.metadata),
+ cmd.metadata_len, 0, &result, timeout, 0);
if (status >= 0) {
if (put_user(result, &ucmd->result))
}
static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
- struct nvme_passthru_cmd64 __user *ucmd, bool vec,
- fmode_t mode)
+ struct nvme_passthru_cmd64 __user *ucmd, unsigned int flags,
+ fmode_t mode)
{
struct nvme_passthru_cmd64 cmd;
struct nvme_command c;
c.common.cdw14 = cpu_to_le32(cmd.cdw14);
c.common.cdw15 = cpu_to_le32(cmd.cdw15);
- if (!nvme_cmd_allowed(ns, &c, mode))
+ if (!nvme_cmd_allowed(ns, &c, flags, mode))
return -EACCES;
if (cmd.timeout_ms)
timeout = msecs_to_jiffies(cmd.timeout_ms);
status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
- cmd.addr, cmd.data_len,
- nvme_to_user_ptr(cmd.metadata), cmd.metadata_len,
- 0, &cmd.result, timeout, vec);
+ cmd.addr, cmd.data_len, nvme_to_user_ptr(cmd.metadata),
+ cmd.metadata_len, 0, &cmd.result, timeout, flags);
if (status >= 0) {
if (put_user(cmd.result, &ucmd->result))
c.common.cdw14 = cpu_to_le32(READ_ONCE(cmd->cdw14));
c.common.cdw15 = cpu_to_le32(READ_ONCE(cmd->cdw15));
- if (!nvme_cmd_allowed(ns, &c, ioucmd->file->f_mode))
+ if (!nvme_cmd_allowed(ns, &c, 0, ioucmd->file->f_mode))
return -EACCES;
d.metadata = READ_ONCE(cmd->metadata);
{
switch (cmd) {
case NVME_IOCTL_ADMIN_CMD:
- return nvme_user_cmd(ctrl, NULL, argp, mode);
+ return nvme_user_cmd(ctrl, NULL, argp, 0, mode);
case NVME_IOCTL_ADMIN64_CMD:
- return nvme_user_cmd64(ctrl, NULL, argp, false, mode);
+ return nvme_user_cmd64(ctrl, NULL, argp, 0, mode);
default:
return sed_ioctl(ctrl->opal_dev, cmd, argp);
}
#endif /* COMPAT_FOR_U64_ALIGNMENT */
static int nvme_ns_ioctl(struct nvme_ns *ns, unsigned int cmd,
- void __user *argp, fmode_t mode)
+ void __user *argp, unsigned int flags, fmode_t mode)
{
switch (cmd) {
case NVME_IOCTL_ID:
force_successful_syscall_return();
return ns->head->ns_id;
case NVME_IOCTL_IO_CMD:
- return nvme_user_cmd(ns->ctrl, ns, argp, mode);
+ return nvme_user_cmd(ns->ctrl, ns, argp, flags, mode);
/*
* struct nvme_user_io can have different padding on some 32-bit ABIs.
* Just accept the compat version as all fields that are used are the
#endif
case NVME_IOCTL_SUBMIT_IO:
return nvme_submit_io(ns, argp);
- case NVME_IOCTL_IO64_CMD:
- return nvme_user_cmd64(ns->ctrl, ns, argp, false, mode);
case NVME_IOCTL_IO64_CMD_VEC:
- return nvme_user_cmd64(ns->ctrl, ns, argp, true, mode);
+ flags |= NVME_IOCTL_VEC;
+ fallthrough;
+ case NVME_IOCTL_IO64_CMD:
+ return nvme_user_cmd64(ns->ctrl, ns, argp, flags, mode);
default:
return -ENOTTY;
}
}
-static int __nvme_ioctl(struct nvme_ns *ns, unsigned int cmd, void __user *arg,
- fmode_t mode)
-{
- if (is_ctrl_ioctl(cmd))
- return nvme_ctrl_ioctl(ns->ctrl, cmd, arg, mode);
- return nvme_ns_ioctl(ns, cmd, arg, mode);
-}
-
int nvme_ioctl(struct block_device *bdev, fmode_t mode,
unsigned int cmd, unsigned long arg)
{
struct nvme_ns *ns = bdev->bd_disk->private_data;
+ void __user *argp = (void __user *)arg;
+ unsigned int flags = 0;
- return __nvme_ioctl(ns, cmd, (void __user *)arg, mode);
+ if (bdev_is_partition(bdev))
+ flags |= NVME_IOCTL_PARTITION;
+
+ if (is_ctrl_ioctl(cmd))
+ return nvme_ctrl_ioctl(ns->ctrl, cmd, argp, mode);
+ return nvme_ns_ioctl(ns, cmd, argp, flags, mode);
}
long nvme_ns_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
struct nvme_ns *ns =
container_of(file_inode(file)->i_cdev, struct nvme_ns, cdev);
+ void __user *argp = (void __user *)arg;
- return __nvme_ioctl(ns, cmd, (void __user *)arg, file->f_mode);
+ if (is_ctrl_ioctl(cmd))
+ return nvme_ctrl_ioctl(ns->ctrl, cmd, argp, file->f_mode);
+ return nvme_ns_ioctl(ns, cmd, argp, 0, file->f_mode);
}
static int nvme_uring_cmd_checks(unsigned int issue_flags)
void __user *argp = (void __user *)arg;
struct nvme_ns *ns;
int srcu_idx, ret = -EWOULDBLOCK;
+ unsigned int flags = 0;
+
+ if (bdev_is_partition(bdev))
+ flags |= NVME_IOCTL_PARTITION;
srcu_idx = srcu_read_lock(&head->srcu);
ns = nvme_find_path(head);
return nvme_ns_head_ctrl_ioctl(ns, cmd, argp, head, srcu_idx,
mode);
- ret = nvme_ns_ioctl(ns, cmd, argp, mode);
+ ret = nvme_ns_ioctl(ns, cmd, argp, flags, mode);
out_unlock:
srcu_read_unlock(&head->srcu, srcu_idx);
return ret;
return nvme_ns_head_ctrl_ioctl(ns, cmd, argp, head, srcu_idx,
file->f_mode);
- ret = nvme_ns_ioctl(ns, cmd, argp, file->f_mode);
+ ret = nvme_ns_ioctl(ns, cmd, argp, 0, file->f_mode);
out_unlock:
srcu_read_unlock(&head->srcu, srcu_idx);
return ret;
kref_get(&ns->kref);
up_read(&ctrl->namespaces_rwsem);
- ret = nvme_user_cmd(ctrl, ns, argp, mode);
+ ret = nvme_user_cmd(ctrl, ns, argp, 0, mode);
nvme_put_ns(ns);
return ret;
switch (cmd) {
case NVME_IOCTL_ADMIN_CMD:
- return nvme_user_cmd(ctrl, NULL, argp, file->f_mode);
+ return nvme_user_cmd(ctrl, NULL, argp, 0, file->f_mode);
case NVME_IOCTL_ADMIN64_CMD:
- return nvme_user_cmd64(ctrl, NULL, argp, false, file->f_mode);
+ return nvme_user_cmd64(ctrl, NULL, argp, 0, file->f_mode);
case NVME_IOCTL_IO_CMD:
return nvme_dev_user_cmd(ctrl, argp, file->f_mode);
case NVME_IOCTL_RESET:
* pool from the original queue to allocate the bvecs from.
*/
bio = bio_split_to_limits(bio);
+ if (!bio)
+ return;
srcu_idx = srcu_read_lock(&head->srcu);
ns = nvme_find_path(head);
*/
result = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
if (result < 0)
- return result;
+ goto disable;
dev->ctrl.cap = lo_hi_readq(dev->bar + NVME_REG_CAP);
pci_enable_pcie_error_reporting(pdev);
pci_save_state(pdev);
- return nvme_pci_configure_admin_queue(dev);
+ result = nvme_pci_configure_admin_queue(dev);
+ if (result)
+ goto free_irq;
+ return result;
+ free_irq:
+ pci_free_irq_vectors(pdev);
disable:
pci_disable_device(pdev);
return result;
.driver_data = NVME_QUIRK_SINGLE_VECTOR |
NVME_QUIRK_128_BYTES_SQES |
NVME_QUIRK_SHARED_TAGS |
- NVME_QUIRK_SKIP_CID_GEN },
+ NVME_QUIRK_SKIP_CID_GEN |
+ NVME_QUIRK_IDENTIFY_CNS },
{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
{ 0, }
};
*/
int __init early_init_dt_scan_memory(void)
{
- int node;
+ int node, found_memory = 0;
const void *fdt = initial_boot_params;
fdt_for_each_subnode(node, fdt, 0) {
early_init_dt_add_memory_arch(base, size);
+ found_memory = 1;
+
if (!hotpluggable)
continue;
base, base + size);
}
}
- return 0;
+ return found_memory;
}
int __init early_init_dt_scan_chosen(char *cmdline)
if (node < 0)
node = fdt_path_offset(fdt, "/chosen@0");
if (node < 0)
- return -ENOENT;
+ /* Handle the cmdline config options even if no /chosen node */
+ goto handle_cmdline;
chosen_node_offset = node;
early_init_dt_check_for_initrd(node);
early_init_dt_check_for_elfcorehdr(node);
- /* Retrieve command line */
- p = of_get_flat_dt_prop(node, "bootargs", &l);
- if (p != NULL && l > 0)
- strscpy(cmdline, p, min(l, COMMAND_LINE_SIZE));
-
rng_seed = of_get_flat_dt_prop(node, "rng-seed", &l);
if (rng_seed && l > 0) {
add_bootloader_randomness(rng_seed, l);
fdt_totalsize(initial_boot_params));
}
+ /* Retrieve command line */
+ p = of_get_flat_dt_prop(node, "bootargs", &l);
+ if (p != NULL && l > 0)
+ strscpy(cmdline, p, min(l, COMMAND_LINE_SIZE));
+
+handle_cmdline:
+ /*
+ * CONFIG_CMDLINE is meant to be a default in case nothing else
+ * managed to set the command line, unless CONFIG_CMDLINE_FORCE
+ * is set in which case we override whatever was found earlier.
+ */
+#ifdef CONFIG_CMDLINE
+#if defined(CONFIG_CMDLINE_EXTEND)
+ strlcat(cmdline, " ", COMMAND_LINE_SIZE);
+ strlcat(cmdline, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
+#elif defined(CONFIG_CMDLINE_FORCE)
+ strscpy(cmdline, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
+#else
+ /* No arguments from boot loader, use kernel's cmdl*/
+ if (!((char *)cmdline)[0])
+ strscpy(cmdline, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
+#endif
+#endif /* CONFIG_CMDLINE */
+
+ pr_debug("Command line is: %s\n", (char *)cmdline);
+
return 0;
}
if (rc)
pr_warn("No chosen node found, continuing without\n");
- /*
- * CONFIG_CMDLINE is meant to be a default in case nothing else
- * managed to set the command line, unless CONFIG_CMDLINE_FORCE
- * is set in which case we override whatever was found earlier.
- */
-#ifdef CONFIG_CMDLINE
-#if defined(CONFIG_CMDLINE_EXTEND)
- strlcat(boot_command_line, " ", COMMAND_LINE_SIZE);
- strlcat(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
-#elif defined(CONFIG_CMDLINE_FORCE)
- strscpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
-#else
- /* No arguments from boot loader, use kernel's cmdl */
- if (!boot_command_line[0])
- strscpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
-#endif
-#endif /* CONFIG_CMDLINE */
-
- pr_debug("Command line is: %s\n", boot_command_line);
-
/* Setup memory, calling early_init_dt_add_memory_arch */
early_init_dt_scan_memory();
config PCIE_BT1
tristate "Baikal-T1 PCIe controller"
depends on MIPS_BAIKAL_T1 || COMPILE_TEST
- depends on PCI_MSI_IRQ_DOMAIN
+ depends on PCI_MSI
select PCIE_DW_HOST
help
Enables support for the PCIe controller in the Baikal-T1 SoC to work
return err;
}
-static int pcifront_xenbus_remove(struct xenbus_device *xdev)
+static void pcifront_xenbus_remove(struct xenbus_device *xdev)
{
struct pcifront_device *pdev = dev_get_drvdata(&xdev->dev);
if (pdev)
free_pdev(pdev);
-
- return 0;
}
static const struct xenbus_device_id xenpci_ids[] = {
return status;
status = ssam_request_sync_init(rqst, spec->flags);
- if (status)
+ if (status) {
+ ssam_request_sync_free(rqst);
return status;
+ }
ssam_request_sync_set_resp(rqst, rsp);
if (sshp_parse_command(dev, data, &command, &command_data))
return;
+ /*
+ * Check if the message was intended for us. If not, drop it.
+ *
+ * Note: We will need to change this to handle debug messages. On newer
+ * generation devices, these seem to be sent to tid_out=0x03. We as
+ * host can still receive them as they can be forwarded via an override
+ * option on SAM, but doing so does not change tid_out=0x00.
+ */
+ if (command->tid_out != 0x00) {
+ rtl_warn(rtl, "rtl: dropping message not intended for us (tid = %#04x)\n",
+ command->tid_out);
+ return;
+ }
+
if (ssh_rqid_is_event(get_unaligned_le16(&command->rqid)))
ssh_rtl_rx_event(rtl, command, &command_data);
else
if (enable_stb && (dev->cpu_id == AMD_CPU_ID_YC || dev->cpu_id == AMD_CPU_ID_CB)) {
err = amd_pmc_s2d_init(dev);
if (err)
- return err;
+ goto err_pci_dev_put;
}
platform_set_drvdata(pdev, dev);
.tablet_switch_mode = asus_wmi_lid_flip_rog_devid,
};
+static struct quirk_entry quirk_asus_ignore_fan = {
+ .wmi_ignore_fan = true,
+};
+
static int dmi_matched(const struct dmi_system_id *dmi)
{
pr_info("Identified laptop model '%s'\n", dmi->ident);
},
.driver_data = &quirk_asus_tablet_mode,
},
+ {
+ .callback = dmi_matched,
+ .ident = "ASUS VivoBook E410MA",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "E410MA"),
+ },
+ .driver_data = &quirk_asus_ignore_fan,
+ },
{},
};
{ KE_KEY, 0x30, { KEY_VOLUMEUP } },
{ KE_KEY, 0x31, { KEY_VOLUMEDOWN } },
{ KE_KEY, 0x32, { KEY_MUTE } },
+ { KE_KEY, 0x33, { KEY_SCREENLOCK } },
{ KE_KEY, 0x35, { KEY_SCREENLOCK } },
{ KE_KEY, 0x38, { KEY_PROG3 } }, /* Armoury Crate */
{ KE_KEY, 0x40, { KEY_PREVIOUSSONG } },
{ KE_KEY, 0x7D, { KEY_BLUETOOTH } }, /* Bluetooth Enable */
{ KE_KEY, 0x7E, { KEY_BLUETOOTH } }, /* Bluetooth Disable */
{ KE_KEY, 0x82, { KEY_CAMERA } },
+ { KE_KEY, 0x85, { KEY_CAMERA } },
{ KE_KEY, 0x86, { KEY_PROG1 } }, /* MyASUS Key */
{ KE_KEY, 0x88, { KEY_RFKILL } }, /* Radio Toggle Key */
{ KE_KEY, 0x8A, { KEY_PROG1 } }, /* Color enhancement mode */
asus->fan_type = FAN_TYPE_NONE;
asus->agfn_pwm = -1;
- if (asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_CPU_FAN_CTRL))
+ if (asus->driver->quirks->wmi_ignore_fan)
+ asus->fan_type = FAN_TYPE_NONE;
+ else if (asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_CPU_FAN_CTRL))
asus->fan_type = FAN_TYPE_SPEC83;
else if (asus_wmi_has_agfn_fan(asus))
asus->fan_type = FAN_TYPE_AGFN;
*available = false;
+ if (asus->fan_type == FAN_TYPE_NONE)
+ return 0;
+
err = fan_curve_get_factory_default(asus, fan_dev);
if (err) {
return 0;
bool store_backlight_power;
bool wmi_backlight_set_devstate;
bool wmi_force_als_set;
+ bool wmi_ignore_fan;
enum asus_wmi_tablet_switch_mode tablet_switch_mode;
int wapf;
/*
/* privacy mic mute */
{ KE_KEY, 0x0001, { KEY_MICMUTE } },
/* privacy camera mute */
- { KE_SW, 0x0002, { SW_CAMERA_LENS_COVER } },
+ { KE_VSW, 0x0002, { SW_CAMERA_LENS_COVER } },
{ KE_END, 0},
};
switch (code) {
case DELL_PRIVACY_AUDIO_EVENT: /* Mic mute */
- case DELL_PRIVACY_CAMERA_EVENT: /* Camera mute */
priv->last_status = status;
sparse_keymap_report_entry(priv->input_dev, key, 1, true);
ret = true;
break;
+ case DELL_PRIVACY_CAMERA_EVENT: /* Camera mute */
+ priv->last_status = status;
+ sparse_keymap_report_entry(priv->input_dev, key, !(status & CAMERA_STATUS), false);
+ ret = true;
+ break;
default:
dev_dbg(&priv->wdev->dev, "unknown event type 0x%04x 0x%04x\n", type, code);
}
{
struct privacy_wmi_data *priv;
struct key_entry *keymap;
- int ret, i;
+ int ret, i, j;
ret = wmi_has_guid(DELL_PRIVACY_GUID);
if (!ret)
dev_set_drvdata(&wdev->dev, priv);
priv->wdev = wdev;
+
+ ret = get_current_status(priv->wdev);
+ if (ret)
+ return ret;
+
/* create evdev passing interface */
priv->input_dev = devm_input_allocate_device(&wdev->dev);
if (!priv->input_dev)
/* remap the keymap code with Dell privacy key type 0x12 as prefix
* KEY_MICMUTE scancode will be reported as 0x120001
*/
- for (i = 0; i < ARRAY_SIZE(dell_wmi_keymap_type_0012); i++) {
- keymap[i] = dell_wmi_keymap_type_0012[i];
- keymap[i].code |= (0x0012 << 16);
+ for (i = 0, j = 0; i < ARRAY_SIZE(dell_wmi_keymap_type_0012); i++) {
+ /*
+ * Unlike keys where only presses matter, userspace may act
+ * on switches in both of their positions. Only register
+ * SW_CAMERA_LENS_COVER if it is actually there.
+ */
+ if (dell_wmi_keymap_type_0012[i].type == KE_VSW &&
+ dell_wmi_keymap_type_0012[i].sw.code == SW_CAMERA_LENS_COVER &&
+ !(priv->features_present & BIT(DELL_PRIVACY_TYPE_CAMERA)))
+ continue;
+
+ keymap[j] = dell_wmi_keymap_type_0012[i];
+ keymap[j].code |= (0x0012 << 16);
+ j++;
}
ret = sparse_keymap_setup(priv->input_dev, keymap, NULL);
kfree(keymap);
priv->input_dev->name = "Dell Privacy Driver";
priv->input_dev->id.bustype = BUS_HOST;
- ret = input_register_device(priv->input_dev);
- if (ret)
- return ret;
+ /* Report initial camera-cover status */
+ if (priv->features_present & BIT(DELL_PRIVACY_TYPE_CAMERA))
+ input_report_switch(priv->input_dev, SW_CAMERA_LENS_COVER,
+ !(priv->last_status & CAMERA_STATUS));
- ret = get_current_status(priv->wdev);
+ ret = input_register_device(priv->input_dev);
if (ret)
return ret;
DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo Legion R7000P2020H"),
}
},
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo Legion 5 15ARH05"),
+ }
+ },
{}
};
return PTR_ERR(int3472->regulator.gpio);
}
+ /* Ensure the pin is in output mode and non-active state */
+ gpiod_direction_output(int3472->regulator.gpio, 0);
+
cfg.dev = &int3472->adev->dev;
cfg.init_data = &init_data;
cfg.ena_gpiod = int3472->regulator.gpio;
return (PTR_ERR(gpio));
int3472->clock.ena_gpio = gpio;
+ /* Ensure the pin is in output mode and non-active state */
+ gpiod_direction_output(int3472->clock.ena_gpio, 0);
break;
case INT3472_GPIO_TYPE_PRIVACY_LED:
gpio = acpi_get_and_request_gpiod(path, pin, "int3472,privacy-led");
return (PTR_ERR(gpio));
int3472->clock.led_gpio = gpio;
+ /* Ensure the pin is in output mode and non-active state */
+ gpiod_direction_output(int3472->clock.led_gpio, 0);
break;
default:
dev_err(int3472->dev, "Invalid GPIO type 0x%02x for clock\n", type);
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, adl_core_init),
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, adl_core_init),
X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, mtl_core_init),
+ X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, mtl_core_init),
{}
};
{SIMATIC_IPC_IPC427D, SIMATIC_IPC_DEVICE_427E, SIMATIC_IPC_DEVICE_NONE},
{SIMATIC_IPC_IPC427E, SIMATIC_IPC_DEVICE_427E, SIMATIC_IPC_DEVICE_427E},
{SIMATIC_IPC_IPC477E, SIMATIC_IPC_DEVICE_NONE, SIMATIC_IPC_DEVICE_427E},
- {SIMATIC_IPC_IPC427G, SIMATIC_IPC_DEVICE_227G, SIMATIC_IPC_DEVICE_227G},
+ {SIMATIC_IPC_IPCBX_39A, SIMATIC_IPC_DEVICE_227G, SIMATIC_IPC_DEVICE_227G},
+ {SIMATIC_IPC_IPCPX_39A, SIMATIC_IPC_DEVICE_NONE, SIMATIC_IPC_DEVICE_227G},
};
static int register_platform_devices(u32 station_id)
break;
}
- ret = sony_call_snc_handle(handle, probe_base, &result);
- if (ret)
- return ret;
+ /*
+ * Only probe if there is a separate probe_base, otherwise the probe call
+ * is equivalent to __sony_nc_kbd_backlight_mode_set(0), resulting in
+ * the keyboard backlight being turned off.
+ */
+ if (probe_base) {
+ ret = sony_call_snc_handle(handle, probe_base, &result);
+ if (ret)
+ return ret;
- if ((handle == 0x0137 && !(result & 0x02)) ||
- !(result & 0x01)) {
- dprintk("no backlight keyboard found\n");
- return 0;
+ if ((handle == 0x0137 && !(result & 0x02)) ||
+ !(result & 0x01)) {
+ dprintk("no backlight keyboard found\n");
+ return 0;
+ }
}
kbdbl_ctl = kzalloc(sizeof(*kbdbl_ctl), GFP_KERNEL);
static int dytc_capabilities;
static bool dytc_mmc_get_available;
-static int convert_dytc_to_profile(int dytcmode, enum platform_profile_option *profile)
+static int convert_dytc_to_profile(int funcmode, int dytcmode,
+ enum platform_profile_option *profile)
{
- if (dytc_capabilities & BIT(DYTC_FC_MMC)) {
+ switch (funcmode) {
+ case DYTC_FUNCTION_MMC:
switch (dytcmode) {
case DYTC_MODE_MMC_LOWPOWER:
*profile = PLATFORM_PROFILE_LOW_POWER;
return -EINVAL;
}
return 0;
- }
- if (dytc_capabilities & BIT(DYTC_FC_PSC)) {
+ case DYTC_FUNCTION_PSC:
switch (dytcmode) {
case DYTC_MODE_PSC_LOWPOWER:
*profile = PLATFORM_PROFILE_LOW_POWER;
default: /* Unknown mode */
return -EINVAL;
}
+ return 0;
+ case DYTC_FUNCTION_AMT:
+ /* For now return balanced. It's the closest we have to 'auto' */
+ *profile = PLATFORM_PROFILE_BALANCED;
+ return 0;
+ default:
+ /* Unknown function */
+ return -EOPNOTSUPP;
}
return 0;
}
err = dytc_command(DYTC_SET_COMMAND(DYTC_FUNCTION_PSC, perfmode, 1), &output);
if (err)
goto unlock;
+
/* system supports AMT, activate it when on balanced */
if (dytc_capabilities & BIT(DYTC_FC_AMT))
dytc_control_amt(profile == PLATFORM_PROFILE_BALANCED);
{
enum platform_profile_option profile;
int output, err = 0;
- int perfmode;
+ int perfmode, funcmode;
mutex_lock(&dytc_mutex);
if (dytc_capabilities & BIT(DYTC_FC_MMC)) {
if (err)
return;
+ funcmode = (output >> DYTC_GET_FUNCTION_BIT) & 0xF;
perfmode = (output >> DYTC_GET_MODE_BIT) & 0xF;
- convert_dytc_to_profile(perfmode, &profile);
+ convert_dytc_to_profile(funcmode, perfmode, &profile);
if (profile != dytc_current_profile) {
dytc_current_profile = profile;
platform_profile_notify();
.properties = connect_tablet9_props,
};
+static const struct property_entry csl_panther_tab_hd_props[] = {
+ PROPERTY_ENTRY_U32("touchscreen-min-x", 1),
+ PROPERTY_ENTRY_U32("touchscreen-min-y", 20),
+ PROPERTY_ENTRY_U32("touchscreen-size-x", 1980),
+ PROPERTY_ENTRY_U32("touchscreen-size-y", 1526),
+ PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"),
+ PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"),
+ PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-csl-panther-tab-hd.fw"),
+ PROPERTY_ENTRY_U32("silead,max-fingers", 10),
+ { }
+};
+
+static const struct ts_dmi_data csl_panther_tab_hd_data = {
+ .acpi_name = "MSSL1680:00",
+ .properties = csl_panther_tab_hd_props,
+};
+
static const struct property_entry cube_iwork8_air_props[] = {
PROPERTY_ENTRY_U32("touchscreen-min-x", 1),
PROPERTY_ENTRY_U32("touchscreen-min-y", 3),
},
},
{
+ /* CSL Panther Tab HD */
+ .driver_data = (void *)&csl_panther_tab_hd_data,
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "CSL Computer GmbH & Co. KG"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "CSL Panther Tab HD"),
+ },
+ },
+ {
/* CUBE iwork8 Air */
.driver_data = (void *)&cube_iwork8_air_data,
.matches = {
chip->chip_irq = i2c->irq;
+ ret = da9211_regulator_init(chip);
+ if (ret < 0) {
+ dev_err(chip->dev, "Failed to initialize regulator: %d\n", ret);
+ return ret;
+ }
+
if (chip->chip_irq != 0) {
ret = devm_request_threaded_irq(chip->dev, chip->chip_irq, NULL,
da9211_irq_handler,
dev_warn(chip->dev, "No IRQ configured\n");
}
- ret = da9211_regulator_init(chip);
-
- if (ret < 0)
- dev_err(chip->dev, "Failed to initialize regulator: %d\n", ret);
-
return ret;
}
RPMH_VREG("ldo8", "ldo%s8", &pmic5_pldo_lv, "vdd-l8-l9"),
RPMH_VREG("ldo9", "ldo%s9", &pmic5_pldo, "vdd-l8-l9"),
RPMH_VREG("ldo10", "ldo%s10", &pmic5_nldo, "vdd-l1-l4-l10"),
- RPMH_VREG("ldo11", "ldo%s11", &pmic5_pldo, "vdd-l11"),
+ RPMH_VREG("ldo11", "ldo%s11", &pmic5_nldo, "vdd-l11"),
RPMH_VREG("ldo12", "ldo%s12", &pmic5_pldo, "vdd-l12"),
RPMH_VREG("ldo13", "ldo%s13", &pmic5_pldo, "vdd-l2-l13-l14"),
RPMH_VREG("ldo14", "ldo%s14", &pmic5_pldo, "vdd-l2-l13-l14"),
unsigned long bytes_done;
bio = bio_split_to_limits(bio);
+ if (!bio)
+ return;
bytes_done = 0;
dev_info = bio->bi_bdev->bd_disk->private_data;
switch (card->options.isolation) {
case ISOLATION_MODE_NONE:
- return snprintf(buf, 6, "%s\n", ATTR_QETH_ISOLATION_NONE);
+ return sysfs_emit(buf, "%s\n", ATTR_QETH_ISOLATION_NONE);
case ISOLATION_MODE_FWD:
- return snprintf(buf, 9, "%s\n", ATTR_QETH_ISOLATION_FWD);
+ return sysfs_emit(buf, "%s\n", ATTR_QETH_ISOLATION_FWD);
case ISOLATION_MODE_DROP:
- return snprintf(buf, 6, "%s\n", ATTR_QETH_ISOLATION_DROP);
+ return sysfs_emit(buf, "%s\n", ATTR_QETH_ISOLATION_DROP);
default:
- return snprintf(buf, 5, "%s\n", "N/A");
+ return sysfs_emit(buf, "%s\n", "N/A");
}
}
struct qeth_card *card = dev_get_drvdata(dev);
if (card->info.hwtrap)
- return snprintf(buf, 5, "arm\n");
+ return sysfs_emit(buf, "arm\n");
else
- return snprintf(buf, 8, "disarm\n");
+ return sysfs_emit(buf, "disarm\n");
}
static ssize_t qeth_hw_trap_store(struct device *dev,
static void hisi_sas_slot_index_free(struct hisi_hba *hisi_hba, int slot_idx)
{
if (hisi_hba->hw->slot_index_alloc ||
- slot_idx >= HISI_SAS_UNRESERVED_IPTT) {
+ slot_idx < HISI_SAS_RESERVED_IPTT) {
spin_lock(&hisi_hba->lock);
hisi_sas_slot_index_clear(hisi_hba, slot_idx);
spin_unlock(&hisi_hba->lock);
int_to_scsilun(0, &lun);
while (retry-- > 0) {
- rc = sas_clear_task_set(device, lun.scsi_lun);
+ rc = sas_abort_task_set(device, lun.scsi_lun);
if (rc == TMF_RESP_FUNC_COMPLETE) {
hisi_sas_release_task(hisi_hba, device);
break;
device->linkrate = phy->sas_phy.linkrate;
hisi_hba->hw->setup_itct(hisi_hba, sas_dev);
- } else
+ } else if (!port->port_attached)
port->id = 0xff;
}
}
{
struct ata_port *ap = device->sata_dev.ap;
struct ata_link *link = &ap->link;
+ unsigned long flags;
+ spin_lock_irqsave(ap->lock, flags);
device->sata_dev.fis[2] = ATA_ERR | ATA_DRDY; /* tf status */
device->sata_dev.fis[3] = ATA_ABORTED; /* tf error */
if (force_reset)
link->eh_info.action |= ATA_EH_RESET;
ata_link_abort(link);
+ spin_unlock_irqrestore(ap->lock, flags);
}
EXPORT_SYMBOL_GPL(sas_ata_device_link_abort);
# mpi3mr makefile
-obj-m += mpi3mr.o
+obj-$(CONFIG_SCSI_MPI3MR) += mpi3mr.o
mpi3mr-y += mpi3mr_os.o \
mpi3mr_fw.o \
mpi3mr_app.o \
int i, retval = 0, capb = 0;
u16 message_control;
u64 dma_mask = mrioc->dma_mask ? mrioc->dma_mask :
- (((dma_get_required_mask(&pdev->dev) > DMA_BIT_MASK(32)) &&
- (sizeof(dma_addr_t) > 4)) ? DMA_BIT_MASK(64) : DMA_BIT_MASK(32));
+ ((sizeof(dma_addr_t) > 4) ? DMA_BIT_MASK(64) : DMA_BIT_MASK(32));
if (pci_enable_device_mem(pdev)) {
ioc_err(mrioc, "pci_enable_device_mem: failed\n");
struct sysinfo s;
u64 coherent_dma_mask, dma_mask;
- if (ioc->is_mcpu_endpoint || sizeof(dma_addr_t) == 4 ||
- dma_get_required_mask(&pdev->dev) <= DMA_BIT_MASK(32)) {
+ if (ioc->is_mcpu_endpoint || sizeof(dma_addr_t) == 4) {
ioc->dma_mask = 32;
coherent_dma_mask = dma_mask = DMA_BIT_MASK(32);
/* Set 63 bit DMA mask for all SAS3 and SAS35 controllers */
put_unaligned_be64(sdebug_write_same_length, &arr[32]);
return 0x3c; /* Mandatory page length for Logical Block Provisioning */
-
- return sizeof(vpdb0_data);
}
/* Block device characteristics VPD page (SBC-3) */
struct Scsi_Host *shost = sdev->host;
unsigned long flags;
+ if (!shost->hostt->eh_abort_handler) {
+ /* No abort handler, fail command directly */
+ return FAILED;
+ }
+
if (scmd->eh_eflags & SCSI_EH_ABORT_SCHEDULED) {
/*
* Retry after abort failed, escalate to next level.
return name;
}
+static char *iscsi_session_target_state_name[] = {
+ [ISCSI_SESSION_TARGET_UNBOUND] = "UNBOUND",
+ [ISCSI_SESSION_TARGET_ALLOCATED] = "ALLOCATED",
+ [ISCSI_SESSION_TARGET_SCANNED] = "SCANNED",
+ [ISCSI_SESSION_TARGET_UNBINDING] = "UNBINDING",
+};
+
int iscsi_session_chkready(struct iscsi_cls_session *session)
{
int err;
if ((scan_data->channel == SCAN_WILD_CARD ||
scan_data->channel == 0) &&
(scan_data->id == SCAN_WILD_CARD ||
- scan_data->id == id))
+ scan_data->id == id)) {
scsi_scan_target(&session->dev, 0, id,
scan_data->lun, scan_data->rescan);
+ spin_lock_irqsave(&session->lock, flags);
+ session->target_state = ISCSI_SESSION_TARGET_SCANNED;
+ spin_unlock_irqrestore(&session->lock, flags);
+ }
}
user_scan_exit:
struct iscsi_cls_host *ihost = shost->shost_data;
unsigned long flags;
unsigned int target_id;
+ bool remove_target = true;
ISCSI_DBG_TRANS_SESSION(session, "Unbinding session\n");
/* Prevent new scans and make sure scanning is not in progress */
mutex_lock(&ihost->mutex);
spin_lock_irqsave(&session->lock, flags);
- if (session->target_id == ISCSI_MAX_TARGET) {
+ if (session->target_state == ISCSI_SESSION_TARGET_ALLOCATED) {
+ remove_target = false;
+ } else if (session->target_state != ISCSI_SESSION_TARGET_SCANNED) {
spin_unlock_irqrestore(&session->lock, flags);
mutex_unlock(&ihost->mutex);
- goto unbind_session_exit;
+ ISCSI_DBG_TRANS_SESSION(session,
+ "Skipping target unbinding: Session is unbound/unbinding.\n");
+ return;
}
+ session->target_state = ISCSI_SESSION_TARGET_UNBINDING;
target_id = session->target_id;
session->target_id = ISCSI_MAX_TARGET;
spin_unlock_irqrestore(&session->lock, flags);
mutex_unlock(&ihost->mutex);
- scsi_remove_target(&session->dev);
+ if (remove_target)
+ scsi_remove_target(&session->dev);
if (session->ida_used)
ida_free(&iscsi_sess_ida, target_id);
-unbind_session_exit:
iscsi_session_event(session, ISCSI_KEVENT_UNBIND_SESSION);
ISCSI_DBG_TRANS_SESSION(session, "Completed target removal\n");
+
+ spin_lock_irqsave(&session->lock, flags);
+ session->target_state = ISCSI_SESSION_TARGET_UNBOUND;
+ spin_unlock_irqrestore(&session->lock, flags);
}
static void __iscsi_destroy_session(struct work_struct *work)
session->ida_used = true;
} else
session->target_id = target_id;
+ spin_lock_irqsave(&session->lock, flags);
+ session->target_state = ISCSI_SESSION_TARGET_ALLOCATED;
+ spin_unlock_irqrestore(&session->lock, flags);
dev_set_name(&session->dev, "session%u", session->sid);
err = device_add(&session->dev);
iscsi_session_attr(discovery_parent_type, ISCSI_PARAM_DISCOVERY_PARENT_TYPE, 0);
static ssize_t
+show_priv_session_target_state(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct iscsi_cls_session *session = iscsi_dev_to_session(dev->parent);
+
+ return sysfs_emit(buf, "%s\n",
+ iscsi_session_target_state_name[session->target_state]);
+}
+
+static ISCSI_CLASS_ATTR(priv_sess, target_state, S_IRUGO,
+ show_priv_session_target_state, NULL);
+
+static ssize_t
show_priv_session_state(struct device *dev, struct device_attribute *attr,
char *buf)
{
&dev_attr_sess_boot_target.attr,
&dev_attr_priv_sess_recovery_tmo.attr,
&dev_attr_priv_sess_state.attr,
+ &dev_attr_priv_sess_target_state.attr,
&dev_attr_priv_sess_creator.attr,
&dev_attr_sess_chap_out_idx.attr,
&dev_attr_sess_chap_in_idx.attr,
return S_IRUGO | S_IWUSR;
else if (attr == &dev_attr_priv_sess_state.attr)
return S_IRUGO;
+ else if (attr == &dev_attr_priv_sess_target_state.attr)
+ return S_IRUGO;
else if (attr == &dev_attr_priv_sess_creator.attr)
return S_IRUGO;
else if (attr == &dev_attr_priv_sess_target_id.attr)
ret = storvsc_do_io(dev, cmd_request, get_cpu());
put_cpu();
+ if (ret)
+ scsi_dma_unmap(scmnd);
+
if (ret == -EAGAIN) {
/* no more space */
ret = SCSI_MLQUEUE_DEVICE_BUSY;
return err;
}
-static int scsifront_remove(struct xenbus_device *dev)
+static void scsifront_remove(struct xenbus_device *dev)
{
struct vscsifrnt_info *info = dev_get_drvdata(&dev->dev);
scsifront_free_ring(info);
scsi_host_put(info->host);
-
- return 0;
}
static void scsifront_disconnect(struct vscsifrnt_info *info)
#define CDNS_XSPI_CMD_FLD_DSEQ_CMD_3(op) ( \
FIELD_PREP(CDNS_XSPI_CMD_DSEQ_R3_DCNT_H, \
((op)->data.nbytes >> 16) & 0xffff) | \
- FIELD_PREP(CDNS_XSPI_CMD_DSEQ_R3_NUM_OF_DUMMY, (op)->dummy.nbytes * 8))
+ FIELD_PREP(CDNS_XSPI_CMD_DSEQ_R3_NUM_OF_DUMMY, \
+ (op)->dummy.buswidth != 0 ? \
+ (((op)->dummy.nbytes * 8) / (op)->dummy.buswidth) : \
+ 0))
#define CDNS_XSPI_CMD_FLD_DSEQ_CMD_4(op, chipsel) ( \
FIELD_PREP(CDNS_XSPI_CMD_DSEQ_R4_BANK, chipsel) | \
dev_notice(dev, "SPI dma_set_mask(%d) failed, ret:%d\n",
addr_bits, ret);
+ ret = devm_request_irq(dev, irq, mtk_spi_interrupt,
+ IRQF_TRIGGER_NONE, dev_name(dev), master);
+ if (ret)
+ return dev_err_probe(dev, ret, "failed to register irq\n");
+
pm_runtime_enable(dev);
ret = devm_spi_register_master(dev, master);
return dev_err_probe(dev, ret, "failed to register master\n");
}
- ret = devm_request_irq(dev, irq, mtk_spi_interrupt,
- IRQF_TRIGGER_NONE, dev_name(dev), master);
- if (ret) {
- pm_runtime_disable(dev);
- return dev_err_probe(dev, ret, "failed to register irq\n");
- }
-
return 0;
}
if (!of_property_read_u32(nc, "spi-max-frequency", &value))
spi->max_speed_hz = value;
- if (!of_property_read_u16(nc, "spi-cs-setup-ns", &cs_setup)) {
+ if (!of_property_read_u16(nc, "spi-cs-setup-delay-ns", &cs_setup)) {
spi->cs_setup.value = cs_setup;
spi->cs_setup.unit = SPI_DELAY_UNIT_NSECS;
}
struct spidev_data {
dev_t devt;
- spinlock_t spi_lock;
+ struct mutex spi_lock;
struct spi_device *spi;
struct list_head device_entry;
int status;
struct spi_device *spi;
- spin_lock_irq(&spidev->spi_lock);
+ mutex_lock(&spidev->spi_lock);
spi = spidev->spi;
- spin_unlock_irq(&spidev->spi_lock);
if (spi == NULL)
status = -ESHUTDOWN;
if (status == 0)
status = message->actual_length;
+ mutex_unlock(&spidev->spi_lock);
return status;
}
* we issue this ioctl.
*/
spidev = filp->private_data;
- spin_lock_irq(&spidev->spi_lock);
+ mutex_lock(&spidev->spi_lock);
spi = spi_dev_get(spidev->spi);
- spin_unlock_irq(&spidev->spi_lock);
-
- if (spi == NULL)
+ if (spi == NULL) {
+ mutex_unlock(&spidev->spi_lock);
return -ESHUTDOWN;
+ }
/* use the buffer lock here for triple duty:
* - prevent I/O (from us) so calling spi_setup() is safe;
mutex_unlock(&spidev->buf_lock);
spi_dev_put(spi);
+ mutex_unlock(&spidev->spi_lock);
return retval;
}
* we issue this ioctl.
*/
spidev = filp->private_data;
- spin_lock_irq(&spidev->spi_lock);
+ mutex_lock(&spidev->spi_lock);
spi = spi_dev_get(spidev->spi);
- spin_unlock_irq(&spidev->spi_lock);
-
- if (spi == NULL)
+ if (spi == NULL) {
+ mutex_unlock(&spidev->spi_lock);
return -ESHUTDOWN;
+ }
/* SPI_IOC_MESSAGE needs the buffer locked "normally" */
mutex_lock(&spidev->buf_lock);
done:
mutex_unlock(&spidev->buf_lock);
spi_dev_put(spi);
+ mutex_unlock(&spidev->spi_lock);
return retval;
}
if (!spidev->tx_buffer) {
spidev->tx_buffer = kmalloc(bufsiz, GFP_KERNEL);
if (!spidev->tx_buffer) {
- dev_dbg(&spidev->spi->dev, "open/ENOMEM\n");
status = -ENOMEM;
goto err_find_dev;
}
if (!spidev->rx_buffer) {
spidev->rx_buffer = kmalloc(bufsiz, GFP_KERNEL);
if (!spidev->rx_buffer) {
- dev_dbg(&spidev->spi->dev, "open/ENOMEM\n");
status = -ENOMEM;
goto err_alloc_rx_buf;
}
spidev = filp->private_data;
filp->private_data = NULL;
- spin_lock_irq(&spidev->spi_lock);
+ mutex_lock(&spidev->spi_lock);
/* ... after we unbound from the underlying device? */
dofree = (spidev->spi == NULL);
- spin_unlock_irq(&spidev->spi_lock);
+ mutex_unlock(&spidev->spi_lock);
/* last close? */
spidev->users--;
/* Initialize the driver data */
spidev->spi = spi;
- spin_lock_init(&spidev->spi_lock);
+ mutex_init(&spidev->spi_lock);
mutex_init(&spidev->buf_lock);
INIT_LIST_HEAD(&spidev->device_entry);
/* prevent new opens */
mutex_lock(&device_list_lock);
/* make sure ops on existing fds can abort cleanly */
- spin_lock_irq(&spidev->spi_lock);
+ mutex_lock(&spidev->spi_lock);
spidev->spi = NULL;
- spin_unlock_irq(&spidev->spi_lock);
+ mutex_unlock(&spidev->spi_lock);
list_del(&spidev->device_entry);
device_destroy(spidev_class, spidev->devt);
RFIM_SHOW(rfi_restriction_run_busy, 1)
RFIM_SHOW(rfi_restriction_err_code, 1)
RFIM_SHOW(rfi_restriction_data_rate, 1)
+RFIM_SHOW(rfi_restriction_data_rate_base, 1)
RFIM_SHOW(ddr_data_rate_point_0, 1)
RFIM_SHOW(ddr_data_rate_point_1, 1)
RFIM_SHOW(ddr_data_rate_point_2, 1)
RFIM_STORE(rfi_restriction_run_busy, 1)
RFIM_STORE(rfi_restriction_err_code, 1)
RFIM_STORE(rfi_restriction_data_rate, 1)
+RFIM_STORE(rfi_restriction_data_rate_base, 1)
RFIM_STORE(rfi_disable, 1)
static DEVICE_ATTR_RW(rfi_restriction_run_busy);
static DEVICE_ATTR_RW(rfi_restriction_err_code);
static DEVICE_ATTR_RW(rfi_restriction_data_rate);
+static DEVICE_ATTR_RW(rfi_restriction_data_rate_base);
static DEVICE_ATTR_RO(ddr_data_rate_point_0);
static DEVICE_ATTR_RO(ddr_data_rate_point_1);
static DEVICE_ATTR_RO(ddr_data_rate_point_2);
&dev_attr_rfi_restriction_run_busy.attr,
&dev_attr_rfi_restriction_err_code.attr,
&dev_attr_rfi_restriction_data_rate.attr,
+ &dev_attr_rfi_restriction_data_rate_base.attr,
&dev_attr_ddr_data_rate_point_0.attr,
&dev_attr_ddr_data_rate_point_1.attr,
&dev_attr_ddr_data_rate_point_2.attr,
static struct xencons_info *vtermno_to_xencons(int vtermno)
{
- struct xencons_info *entry, *n, *ret = NULL;
+ struct xencons_info *entry, *ret = NULL;
+ unsigned long flags;
- if (list_empty(&xenconsoles))
- return NULL;
+ spin_lock_irqsave(&xencons_lock, flags);
+ if (list_empty(&xenconsoles)) {
+ spin_unlock_irqrestore(&xencons_lock, flags);
+ return NULL;
+ }
- list_for_each_entry_safe(entry, n, &xenconsoles, list) {
+ list_for_each_entry(entry, &xenconsoles, list) {
if (entry->vtermno == vtermno) {
ret = entry;
break;
}
}
+ spin_unlock_irqrestore(&xencons_lock, flags);
return ret;
}
{
int r;
uint64_t v = 0;
- unsigned long gfn;
+ unsigned long gfn, flags;
struct xencons_info *info;
if (!xen_hvm_domain())
goto err;
info->vtermno = HVC_COOKIE;
- spin_lock(&xencons_lock);
+ spin_lock_irqsave(&xencons_lock, flags);
list_add_tail(&info->list, &xenconsoles);
- spin_unlock(&xencons_lock);
+ spin_unlock_irqrestore(&xencons_lock, flags);
return 0;
err:
static int xen_pv_console_init(void)
{
struct xencons_info *info;
+ unsigned long flags;
if (!xen_pv_domain())
return -ENODEV;
/* already configured */
return 0;
}
- spin_lock(&xencons_lock);
+ spin_lock_irqsave(&xencons_lock, flags);
xencons_info_pv_init(info, HVC_COOKIE);
- spin_unlock(&xencons_lock);
+ spin_unlock_irqrestore(&xencons_lock, flags);
return 0;
}
static int xen_initial_domain_console_init(void)
{
struct xencons_info *info;
+ unsigned long flags;
if (!xen_initial_domain())
return -ENODEV;
info->irq = bind_virq_to_irq(VIRQ_CONSOLE, 0, false);
info->vtermno = HVC_COOKIE;
- spin_lock(&xencons_lock);
+ spin_lock_irqsave(&xencons_lock, flags);
list_add_tail(&info->list, &xenconsoles);
- spin_unlock(&xencons_lock);
+ spin_unlock_irqrestore(&xencons_lock, flags);
return 0;
}
static int xen_console_remove(struct xencons_info *info)
{
+ unsigned long flags;
+
xencons_disconnect_backend(info);
- spin_lock(&xencons_lock);
+ spin_lock_irqsave(&xencons_lock, flags);
list_del(&info->list);
- spin_unlock(&xencons_lock);
+ spin_unlock_irqrestore(&xencons_lock, flags);
if (info->xbdev != NULL)
xencons_free(info);
else {
return 0;
}
-static int xencons_remove(struct xenbus_device *dev)
+static void xencons_remove(struct xenbus_device *dev)
{
- return xen_console_remove(dev_get_drvdata(&dev->dev));
+ xen_console_remove(dev_get_drvdata(&dev->dev));
}
static int xencons_connect_backend(struct xenbus_device *dev,
{
int ret, devid;
struct xencons_info *info;
+ unsigned long flags;
devid = dev->nodename[strlen(dev->nodename) - 1] - '0';
if (devid == 0)
ret = xencons_connect_backend(dev, info);
if (ret < 0)
goto error;
- spin_lock(&xencons_lock);
+ spin_lock_irqsave(&xencons_lock, flags);
list_add_tail(&info->list, &xenconsoles);
- spin_unlock(&xencons_lock);
+ spin_unlock_irqrestore(&xencons_lock, flags);
return 0;
info->hvc = hvc_alloc(HVC_COOKIE, info->irq, ops, 256);
if (IS_ERR(info->hvc)) {
+ unsigned long flags;
+
r = PTR_ERR(info->hvc);
- spin_lock(&xencons_lock);
+ spin_lock_irqsave(&xencons_lock, flags);
list_del(&info->list);
- spin_unlock(&xencons_lock);
+ spin_unlock_irqrestore(&xencons_lock, flags);
if (info->irq)
unbind_from_irqhandler(info->irq, NULL);
kfree(info);
}
}
+static void ufshcd_force_error_recovery(struct ufs_hba *hba)
+{
+ spin_lock_irq(hba->host->host_lock);
+ hba->force_reset = true;
+ ufshcd_schedule_eh_work(hba);
+ spin_unlock_irq(hba->host->host_lock);
+}
+
static void ufshcd_clk_scaling_allow(struct ufs_hba *hba, bool allow)
{
down_write(&hba->clk_scaling_lock);
if (!hba->dev_info.b_rpm_dev_flush_capable) {
ret = ufshcd_set_dev_pwr_mode(hba, req_dev_pwr_mode);
+ if (ret && pm_op != UFS_SHUTDOWN_PM) {
+ /*
+ * If return err in suspend flow, IO will hang.
+ * Trigger error handler and break suspend for
+ * error recovery.
+ */
+ ufshcd_force_error_recovery(hba);
+ ret = -EBUSY;
+ }
if (ret)
goto enable_scaling;
}
*/
check_for_bkops = !ufshcd_is_ufs_dev_deepsleep(hba);
ret = ufshcd_link_state_transition(hba, req_link_state, check_for_bkops);
+ if (ret && pm_op != UFS_SHUTDOWN_PM) {
+ /*
+ * If return err in suspend flow, IO will hang.
+ * Trigger error handler and break suspend for
+ * error recovery.
+ */
+ ufshcd_force_error_recovery(hba);
+ ret = -EBUSY;
+ }
if (ret)
goto set_dev_active;
/* Test the interface */
ret = ulpi_write(ulpi, ULPI_SCRATCH, 0xaa);
if (ret < 0)
- return ret;
+ goto err;
ret = ulpi_read(ulpi, ULPI_SCRATCH);
if (ret < 0)
#include <linux/of.h>
#include <linux/platform_device.h>
#include <linux/dma-mapping.h>
+#include <linux/gpio/consumer.h>
#include <linux/of_gpio.h>
#include <linux/of_platform.h>
#include <linux/pm_runtime.h>
else if (!ret)
dep->flags |= DWC3_EP_END_TRANSFER_PENDING;
+ dep->flags &= ~DWC3_EP_DELAY_STOP;
return ret;
}
if (dep->number <= 1 && dwc->ep0state != EP0_DATA_PHASE)
return;
+ if (interrupt && (dep->flags & DWC3_EP_DELAY_STOP))
+ return;
+
if (!(dep->flags & DWC3_EP_TRANSFER_STARTED) ||
- (dep->flags & DWC3_EP_DELAY_STOP) ||
(dep->flags & DWC3_EP_END_TRANSFER_PENDING))
return;
static int __init fotg210_init(void)
{
- if (usb_disabled())
- return -ENODEV;
-
- if (IS_ENABLED(CONFIG_USB_FOTG210_HCD))
+ if (IS_ENABLED(CONFIG_USB_FOTG210_HCD) && !usb_disabled())
fotg210_hcd_init();
return platform_driver_register(&fotg210_driver);
}
dev_info(dev, "found and initialized PHY\n");
}
+ ret = -ENOMEM;
+
for (i = 0; i < FOTG210_MAX_NUM_EP; i++) {
fotg210->ep[i] = kzalloc(sizeof(struct fotg210_ep), GFP_KERNEL);
if (!fotg210->ep[i])
}
}
-static int xenhcd_remove(struct xenbus_device *dev)
+static void xenhcd_remove(struct xenbus_device *dev)
{
struct xenhcd_info *info = dev_get_drvdata(&dev->dev);
struct usb_hcd *hcd = xenhcd_info_to_hcd(info);
xenhcd_destroy_rings(info);
usb_put_hcd(hcd);
-
- return 0;
}
static int xenhcd_probe(struct xenbus_device *dev,
int inlen);
int mlx5_vdpa_destroy_mkey(struct mlx5_vdpa_dev *mvdev, u32 mkey);
int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
- bool *change_map);
-int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb);
+ bool *change_map, unsigned int asid);
+int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
+ unsigned int asid);
void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev);
#define mlx5_vdpa_warn(__dev, format, ...) \
u64 st;
u64 sz;
int err;
- int i = 0;
st = start;
while (size) {
mr->num_directs++;
mr->num_klms++;
st += sz;
- i++;
}
list_splice_tail(&tmp, &mr->head);
return 0;
mutex_unlock(&mr->mkey_mtx);
}
-static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
+static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev,
+ struct vhost_iotlb *iotlb, unsigned int asid)
{
struct mlx5_vdpa_mr *mr = &mvdev->mr;
int err;
if (mr->initialized)
return 0;
- if (iotlb)
- err = create_user_mr(mvdev, iotlb);
- else
- err = create_dma_mr(mvdev, mr);
+ if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid) {
+ if (iotlb)
+ err = create_user_mr(mvdev, iotlb);
+ else
+ err = create_dma_mr(mvdev, mr);
- if (err)
- return err;
+ if (err)
+ return err;
+ }
- err = dup_iotlb(mvdev, iotlb);
- if (err)
- goto out_err;
+ if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] == asid) {
+ err = dup_iotlb(mvdev, iotlb);
+ if (err)
+ goto out_err;
+ }
mr->initialized = true;
return 0;
out_err:
- if (iotlb)
- destroy_user_mr(mvdev, mr);
- else
- destroy_dma_mr(mvdev, mr);
+ if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid) {
+ if (iotlb)
+ destroy_user_mr(mvdev, mr);
+ else
+ destroy_dma_mr(mvdev, mr);
+ }
return err;
}
-int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
+int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
+ unsigned int asid)
{
int err;
mutex_lock(&mvdev->mr.mkey_mtx);
- err = _mlx5_vdpa_create_mr(mvdev, iotlb);
+ err = _mlx5_vdpa_create_mr(mvdev, iotlb, asid);
mutex_unlock(&mvdev->mr.mkey_mtx);
return err;
}
int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
- bool *change_map)
+ bool *change_map, unsigned int asid)
{
struct mlx5_vdpa_mr *mr = &mvdev->mr;
int err = 0;
*change_map = true;
}
if (!*change_map)
- err = _mlx5_vdpa_create_mr(mvdev, iotlb);
+ err = _mlx5_vdpa_create_mr(mvdev, iotlb, asid);
mutex_unlock(&mr->mkey_mtx);
return err;
dmac_v = MLX5_ADDR_OF(fte_match_param, headers_v, outer_headers.dmac_47_16);
eth_broadcast_addr(dmac_c);
ether_addr_copy(dmac_v, mac);
- MLX5_SET(fte_match_set_lyr_2_4, headers_c, cvlan_tag, 1);
+ if (ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VLAN)) {
+ MLX5_SET(fte_match_set_lyr_2_4, headers_c, cvlan_tag, 1);
+ MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, first_vid);
+ }
if (tagged) {
MLX5_SET(fte_match_set_lyr_2_4, headers_v, cvlan_tag, 1);
- MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, first_vid);
- MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_vid, vid);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_vid, vid);
}
flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR;
/* Need recreate the flow table entry, so that the packet could forward back
*/
- mac_vlan_del(ndev, ndev->config.mac, 0, false);
+ mac_vlan_del(ndev, mac_back, 0, false);
if (mac_vlan_add(ndev, ndev->config.mac, 0, false)) {
mlx5_vdpa_warn(mvdev, "failed to insert forward rules, try to restore\n");
size_t read;
u16 id;
+ if (!(ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VLAN)))
+ return status;
+
switch (cmd) {
case VIRTIO_NET_CTRL_VLAN_ADD:
read = vringh_iov_pull_iotlb(&cvq->vring, &cvq->riov, &vlan, sizeof(vlan));
}
}
-static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
+static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev,
+ struct vhost_iotlb *iotlb, unsigned int asid)
{
struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
int err;
teardown_driver(ndev);
mlx5_vdpa_destroy_mr(mvdev);
- err = mlx5_vdpa_create_mr(mvdev, iotlb);
+ err = mlx5_vdpa_create_mr(mvdev, iotlb, asid);
if (err)
goto err_mr;
++mvdev->generation;
if (MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) {
- if (mlx5_vdpa_create_mr(mvdev, NULL))
+ if (mlx5_vdpa_create_mr(mvdev, NULL, 0))
mlx5_vdpa_warn(mvdev, "create MR failed\n");
}
up_write(&ndev->reslock);
return mvdev->generation;
}
-static int set_map_control(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
-{
- u64 start = 0ULL, last = 0ULL - 1;
- struct vhost_iotlb_map *map;
- int err = 0;
-
- spin_lock(&mvdev->cvq.iommu_lock);
- vhost_iotlb_reset(mvdev->cvq.iotlb);
-
- for (map = vhost_iotlb_itree_first(iotlb, start, last); map;
- map = vhost_iotlb_itree_next(map, start, last)) {
- err = vhost_iotlb_add_range(mvdev->cvq.iotlb, map->start,
- map->last, map->addr, map->perm);
- if (err)
- goto out;
- }
-
-out:
- spin_unlock(&mvdev->cvq.iommu_lock);
- return err;
-}
-
-static int set_map_data(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
+static int set_map_data(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
+ unsigned int asid)
{
bool change_map;
int err;
- err = mlx5_vdpa_handle_set_map(mvdev, iotlb, &change_map);
+ err = mlx5_vdpa_handle_set_map(mvdev, iotlb, &change_map, asid);
if (err) {
mlx5_vdpa_warn(mvdev, "set map failed(%d)\n", err);
return err;
}
if (change_map)
- err = mlx5_vdpa_change_map(mvdev, iotlb);
+ err = mlx5_vdpa_change_map(mvdev, iotlb, asid);
return err;
}
int err = -EINVAL;
down_write(&ndev->reslock);
- if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid) {
- err = set_map_data(mvdev, iotlb);
- if (err)
- goto out;
- }
-
- if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] == asid)
- err = set_map_control(mvdev, iotlb);
-
-out:
+ err = set_map_data(mvdev, iotlb, asid);
up_write(&ndev->reslock);
return err;
}
int i;
down_write(&ndev->reslock);
- mlx5_notifier_unregister(mvdev->mdev, &ndev->nb);
ndev->nb_registered = false;
+ mlx5_notifier_unregister(mvdev->mdev, &ndev->nb);
flush_workqueue(ndev->mvdev.wq);
for (i = 0; i < ndev->cur_num_vqs; i++) {
mvq = &ndev->vqs[i];
else
ndev->config.status &= cpu_to_mlx5vdpa16(mvdev, ~VIRTIO_NET_S_LINK_UP);
- if (ndev->config_cb.callback)
+ if (ndev->nb_registered && ndev->config_cb.callback)
ndev->config_cb.callback(ndev->config_cb.private);
kfree(wqent);
switch (eqe->sub_type) {
case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
- down_read(&ndev->reslock);
- if (!ndev->nb_registered) {
- up_read(&ndev->reslock);
- return NOTIFY_DONE;
- }
wqent = kzalloc(sizeof(*wqent), GFP_ATOMIC);
- if (!wqent) {
- up_read(&ndev->reslock);
+ if (!wqent)
return NOTIFY_DONE;
- }
wqent->mvdev = &ndev->mvdev;
INIT_WORK(&wqent->work, update_carrier);
queue_work(ndev->mvdev.wq, &wqent->work);
- up_read(&ndev->reslock);
ret = NOTIFY_OK;
break;
default:
goto err_mpfs;
if (MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) {
- err = mlx5_vdpa_create_mr(mvdev, NULL);
+ err = mlx5_vdpa_create_mr(mvdev, NULL, 0);
if (err)
goto err_res;
}
struct workqueue_struct *wq;
if (ndev->nb_registered) {
- mlx5_notifier_unregister(mvdev->mdev, &ndev->nb);
ndev->nb_registered = false;
+ mlx5_notifier_unregister(mvdev->mdev, &ndev->nb);
}
wq = mvdev->wq;
mvdev->wq = NULL;
features_device = vdev->config->get_device_features(vdev);
- if (nla_put_u64_64bit(msg, VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES, features_device,
+ if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_FEATURES, features_device,
VDPA_ATTR_PAD))
return -EMSGSIZE;
{
struct virtio_net_config config = {};
u64 features;
- u16 max_vqp;
u8 status;
int err;
}
vdpa_get_config_unlocked(vdev, 0, &config, sizeof(config));
- max_vqp = __virtio16_to_cpu(true, config.max_virtqueue_pairs);
- if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MAX_VQP, max_vqp))
- return -EMSGSIZE;
-
features = vdev->config->get_driver_features(vdev);
if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_NEGOTIATED_FEATURES,
features, VDPA_ATTR_PAD))
return -EMSGSIZE;
+ err = vdpa_dev_net_mq_config_fill(msg, features, &config);
+ if (err)
+ return err;
+
if (nla_put_u32(msg, VDPA_ATTR_DEV_QUEUE_INDEX, index))
return -EMSGSIZE;
{
struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx];
- vringh_init_iotlb(&vq->vring, vdpasim->dev_attr.supported_features,
- VDPASIM_QUEUE_MAX, false,
+ vringh_init_iotlb(&vq->vring, vdpasim->features, vq->num, false,
(struct vring_desc *)(uintptr_t)vq->desc_addr,
(struct vring_avail *)
(uintptr_t)vq->driver_addr,
}
kvfree(vdpasim->buffer);
- vhost_iotlb_free(vdpasim->iommu);
+ for (i = 0; i < vdpasim->dev_attr.nas; i++)
+ vhost_iotlb_reset(&vdpasim->iommu[i]);
+ kfree(vdpasim->iommu);
kfree(vdpasim->vqs);
kfree(vdpasim->config);
}
int ret;
ret = device_register(&vdpasim_blk_mgmtdev);
- if (ret)
+ if (ret) {
+ put_device(&vdpasim_blk_mgmtdev);
return ret;
+ }
ret = vdpa_mgmtdev_register(&mgmt_dev);
if (ret)
if (len < ETH_ALEN + hdr_len)
return false;
+ if (is_broadcast_ether_addr(vdpasim->buffer + hdr_len) ||
+ is_multicast_ether_addr(vdpasim->buffer + hdr_len))
+ return true;
if (!strncmp(vdpasim->buffer + hdr_len, vio_config->mac, ETH_ALEN))
return true;
int ret;
ret = device_register(&vdpasim_net_mgmtdev);
- if (ret)
+ if (ret) {
+ put_device(&vdpasim_net_mgmtdev);
return ret;
+ }
ret = vdpa_mgmtdev_register(&mgmt_dev);
if (ret)
if (config->config_size > PAGE_SIZE)
return false;
+ if (config->vq_num > 0xffff)
+ return false;
+
if (!device_is_allowed(config->device_id))
return false;
mdev = vp_vdpa_mgtdev->mdev;
vp_modern_remove(mdev);
vdpa_mgmtdev_unregister(&vp_vdpa_mgtdev->mgtdev);
- kfree(&vp_vdpa_mgtdev->mgtdev.id_table);
+ kfree(vp_vdpa_mgtdev->mgtdev.id_table);
kfree(mdev);
kfree(vp_vdpa_mgtdev);
}
static dev_t vhost_vdpa_major;
+static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v,
+ struct vhost_iotlb *iotlb, u64 start,
+ u64 last, u32 asid);
+
static inline u32 iotlb_to_asid(struct vhost_iotlb *iotlb)
{
struct vhost_vdpa_as *as = container_of(iotlb, struct
return -EINVAL;
hlist_del(&as->hash_link);
- vhost_iotlb_reset(&as->iotlb);
+ vhost_vdpa_iotlb_unmap(v, &as->iotlb, 0ULL, 0ULL - 1, asid);
kfree(as);
return 0;
mutex_unlock(&d->mutex);
return r;
}
+static void vhost_vdpa_general_unmap(struct vhost_vdpa *v,
+ struct vhost_iotlb_map *map, u32 asid)
+{
+ struct vdpa_device *vdpa = v->vdpa;
+ const struct vdpa_config_ops *ops = vdpa->config;
+ if (ops->dma_map) {
+ ops->dma_unmap(vdpa, asid, map->start, map->size);
+ } else if (ops->set_map == NULL) {
+ iommu_unmap(v->domain, map->start, map->size);
+ }
+}
-static void vhost_vdpa_pa_unmap(struct vhost_vdpa *v,
- struct vhost_iotlb *iotlb,
- u64 start, u64 last)
+static void vhost_vdpa_pa_unmap(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,
+ u64 start, u64 last, u32 asid)
{
struct vhost_dev *dev = &v->vdev;
struct vhost_iotlb_map *map;
unpin_user_page(page);
}
atomic64_sub(PFN_DOWN(map->size), &dev->mm->pinned_vm);
+ vhost_vdpa_general_unmap(v, map, asid);
vhost_iotlb_map_free(iotlb, map);
}
}
-static void vhost_vdpa_va_unmap(struct vhost_vdpa *v,
- struct vhost_iotlb *iotlb,
- u64 start, u64 last)
+static void vhost_vdpa_va_unmap(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,
+ u64 start, u64 last, u32 asid)
{
struct vhost_iotlb_map *map;
struct vdpa_map_file *map_file;
map_file = (struct vdpa_map_file *)map->opaque;
fput(map_file->file);
kfree(map_file);
+ vhost_vdpa_general_unmap(v, map, asid);
vhost_iotlb_map_free(iotlb, map);
}
}
static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v,
- struct vhost_iotlb *iotlb,
- u64 start, u64 last)
+ struct vhost_iotlb *iotlb, u64 start,
+ u64 last, u32 asid)
{
struct vdpa_device *vdpa = v->vdpa;
if (vdpa->use_va)
- return vhost_vdpa_va_unmap(v, iotlb, start, last);
+ return vhost_vdpa_va_unmap(v, iotlb, start, last, asid);
- return vhost_vdpa_pa_unmap(v, iotlb, start, last);
+ return vhost_vdpa_pa_unmap(v, iotlb, start, last, asid);
}
static int perm_to_iommu_flags(u32 perm)
const struct vdpa_config_ops *ops = vdpa->config;
u32 asid = iotlb_to_asid(iotlb);
- vhost_vdpa_iotlb_unmap(v, iotlb, iova, iova + size - 1);
+ vhost_vdpa_iotlb_unmap(v, iotlb, iova, iova + size - 1, asid);
- if (ops->dma_map) {
- ops->dma_unmap(vdpa, asid, iova, size);
- } else if (ops->set_map) {
+ if (ops->set_map) {
if (!v->in_batch)
ops->set_map(vdpa, asid, iotlb);
- } else {
- iommu_unmap(v->domain, iova, size);
}
-
/* If we are in the middle of batch processing, delay the free
* of AS until BATCH_END.
*/
struct vhost_vdpa_as *as;
u32 asid;
- vhost_dev_cleanup(&v->vdev);
- kfree(v->vdev.vqs);
-
for (asid = 0; asid < v->vdpa->nas; asid++) {
as = asid_to_as(v, asid);
if (as)
vhost_vdpa_remove_as(v, asid);
}
+
+ vhost_dev_cleanup(&v->vdev);
+ kfree(v->vdev.vqs);
}
static int vhost_vdpa_open(struct inode *inode, struct file *filep)
struct vhost_dev *dev = vq->dev;
struct vhost_iotlb *umem = dev->iotlb ? dev->iotlb : dev->umem;
struct iovec *_iov;
- u64 s = 0;
+ u64 s = 0, last = addr + len - 1;
int ret = 0;
while ((u64)len > s) {
break;
}
- map = vhost_iotlb_itree_first(umem, addr, addr + len - 1);
+ map = vhost_iotlb_itree_first(umem, addr, last);
if (map == NULL || map->start > addr) {
if (umem != dev->iotlb) {
ret = -EFAULT;
struct vhost_iotlb_map *map;
struct vhost_iotlb *iotlb = vrh->iotlb;
int ret = 0;
- u64 s = 0;
+ u64 s = 0, last = addr + len - 1;
spin_lock(vrh->iotlb_lock);
break;
}
- map = vhost_iotlb_itree_first(iotlb, addr,
- addr + len - 1);
+ map = vhost_iotlb_itree_first(iotlb, addr, last);
if (!map || map->start > addr) {
ret = -EINVAL;
break;
VSOCK_TRANSPORT_F_H2G);
if (ret < 0)
return ret;
- return misc_register(&vhost_vsock_misc);
+
+ ret = misc_register(&vhost_vsock_misc);
+ if (ret) {
+ vsock_core_unregister(&vhost_transport.transport);
+ return ret;
+ }
+
+ return 0;
};
static void __exit vhost_vsock_exit(void)
chipset found in Ataris.
config FB_OF
- bool "Open Firmware frame buffer device support"
- depends on (FB = y) && PPC && (!PPC_PSERIES || PCI)
+ tristate "Open Firmware frame buffer device support"
+ depends on FB && PPC && (!PPC_PSERIES || PCI)
depends on !DRM_OFDRM
select APERTURE_HELPERS
select FB_CFB_FILLRECT
* which we print to the screen.
*/
id = *(u8 *)par->lcd_table;
- strncpy(model, (char *)par->lcd_table+1, 24);
- model[23] = 0;
+ strscpy(model, (char *)par->lcd_table+1, sizeof(model));
width = par->lcd_width = *(u16 *)(par->lcd_table+25);
height = par->lcd_height = *(u16 *)(par->lcd_table+27);
.lowlevel = &matrox_G100
};
static struct video_board vbG200eW = {
- .maxvram = 0x100000,
- .maxdisplayable = 0x800000,
+ .maxvram = 0x1000000,
+ .maxdisplayable = 0x0800000,
.accelID = FB_ACCEL_MATROX_MGAG200,
.lowlevel = &matrox_G100
};
info->fbops = &omapfb_ops;
info->flags = FBINFO_FLAG_DEFAULT;
- strncpy(fix->id, MODULE_NAME, sizeof(fix->id));
+ strscpy(fix->id, MODULE_NAME, sizeof(fix->id));
info->pseudo_palette = fbdev->pseudo_palette;
fbdev->ctrl = NULL;
- strncpy(name, conf->lcd.ctrl_name, sizeof(name) - 1);
- name[sizeof(name) - 1] = '\0';
+ strscpy(name, conf->lcd.ctrl_name, sizeof(name));
if (strcmp(name, "internal") == 0) {
fbdev->ctrl = fbdev->int_ctrl;
{
struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
unsigned long flags;
- struct dsi_irq_stats stats;
+ struct dsi_irq_stats *stats;
+
+ stats = kzalloc(sizeof(*stats), GFP_KERNEL);
+ if (!stats) {
+ seq_printf(s, "out of memory\n");
+ return;
+ }
spin_lock_irqsave(&dsi->irq_stats_lock, flags);
- stats = dsi->irq_stats;
+ *stats = dsi->irq_stats;
memset(&dsi->irq_stats, 0, sizeof(dsi->irq_stats));
dsi->irq_stats.last_reset = jiffies;
spin_unlock_irqrestore(&dsi->irq_stats_lock, flags);
seq_printf(s, "period %u ms\n",
- jiffies_to_msecs(jiffies - stats.last_reset));
+ jiffies_to_msecs(jiffies - stats->last_reset));
- seq_printf(s, "irqs %d\n", stats.irq_count);
+ seq_printf(s, "irqs %d\n", stats->irq_count);
#define PIS(x) \
- seq_printf(s, "%-20s %10d\n", #x, stats.dsi_irqs[ffs(DSI_IRQ_##x)-1])
+ seq_printf(s, "%-20s %10d\n", #x, stats->dsi_irqs[ffs(DSI_IRQ_##x)-1])
seq_printf(s, "-- DSI%d interrupts --\n", dsi->module_id + 1);
PIS(VC0);
#define PIS(x) \
seq_printf(s, "%-20s %10d %10d %10d %10d\n", #x, \
- stats.vc_irqs[0][ffs(DSI_VC_IRQ_##x)-1], \
- stats.vc_irqs[1][ffs(DSI_VC_IRQ_##x)-1], \
- stats.vc_irqs[2][ffs(DSI_VC_IRQ_##x)-1], \
- stats.vc_irqs[3][ffs(DSI_VC_IRQ_##x)-1]);
+ stats->vc_irqs[0][ffs(DSI_VC_IRQ_##x)-1], \
+ stats->vc_irqs[1][ffs(DSI_VC_IRQ_##x)-1], \
+ stats->vc_irqs[2][ffs(DSI_VC_IRQ_##x)-1], \
+ stats->vc_irqs[3][ffs(DSI_VC_IRQ_##x)-1]);
seq_printf(s, "-- VC interrupts --\n");
PIS(CS);
#define PIS(x) \
seq_printf(s, "%-20s %10d\n", #x, \
- stats.cio_irqs[ffs(DSI_CIO_IRQ_##x)-1]);
+ stats->cio_irqs[ffs(DSI_CIO_IRQ_##x)-1]);
seq_printf(s, "-- CIO interrupts --\n");
PIS(ERRSYNCESC1);
PIS(ULPSACTIVENOT_ALL0);
PIS(ULPSACTIVENOT_ALL1);
#undef PIS
+
+ kfree(stats);
}
static void dsi1_dump_irqs(struct seq_file *s)
"Video memory size in MB, width, height in pixels (default 2,800,600)");
static void xenfb_make_preferred_console(void);
-static int xenfb_remove(struct xenbus_device *);
+static void xenfb_remove(struct xenbus_device *);
static void xenfb_init_shared_page(struct xenfb_info *, struct fb_info *);
static int xenfb_connect_backend(struct xenbus_device *, struct xenfb_info *);
static void xenfb_disconnect_backend(struct xenfb_info *);
return xenfb_connect_backend(dev, info);
}
-static int xenfb_remove(struct xenbus_device *dev)
+static void xenfb_remove(struct xenbus_device *dev)
{
struct xenfb_info *info = dev_get_drvdata(&dev->dev);
vfree(info->gfns);
vfree(info->fb);
kfree(info);
-
- return 0;
}
static unsigned long vmalloc_to_gfn(void *address)
struct device_attribute *attr, char *buf)
{
struct virtio_device *dev = dev_to_virtio(_d);
- return sprintf(buf, "0x%04x\n", dev->id.device);
+ return sysfs_emit(buf, "0x%04x\n", dev->id.device);
}
static DEVICE_ATTR_RO(device);
struct device_attribute *attr, char *buf)
{
struct virtio_device *dev = dev_to_virtio(_d);
- return sprintf(buf, "0x%04x\n", dev->id.vendor);
+ return sysfs_emit(buf, "0x%04x\n", dev->id.vendor);
}
static DEVICE_ATTR_RO(vendor);
struct device_attribute *attr, char *buf)
{
struct virtio_device *dev = dev_to_virtio(_d);
- return sprintf(buf, "0x%08x\n", dev->config->get_status(dev));
+ return sysfs_emit(buf, "0x%08x\n", dev->config->get_status(dev));
}
static DEVICE_ATTR_RO(status);
struct device_attribute *attr, char *buf)
{
struct virtio_device *dev = dev_to_virtio(_d);
- return sprintf(buf, "virtio:d%08Xv%08X\n",
+ return sysfs_emit(buf, "virtio:d%08Xv%08X\n",
dev->id.device, dev->id.vendor);
}
static DEVICE_ATTR_RO(modalias);
/* We actually represent this as a bitstring, as it could be
* arbitrary length in future. */
for (i = 0; i < sizeof(dev->features)*8; i++)
- len += sprintf(buf+len, "%c",
+ len += sysfs_emit_at(buf, len, "%c",
__virtio_test_bit(dev, i) ? '1' : '0');
- len += sprintf(buf+len, "\n");
+ len += sysfs_emit_at(buf, len, "\n");
return len;
}
static DEVICE_ATTR_RO(features);
int err;
if (index >= vp_modern_get_num_queues(mdev))
- return ERR_PTR(-ENOENT);
+ return ERR_PTR(-EINVAL);
/* Check if queue is either not available or already active. */
num = vp_modern_get_queue_size(mdev, index);
if (!num || vp_modern_get_queue_enable(mdev, index))
return ERR_PTR(-ENOENT);
- if (num & (num - 1)) {
+ if (!is_power_of_2(num)) {
dev_warn(&vp_dev->pci_dev->dev, "bad queue size %u", num);
return ERR_PTR(-EINVAL);
}
dma_addr_t dma_addr;
/* We assume num is a power of 2. */
- if (num & (num - 1)) {
+ if (!is_power_of_2(num)) {
dev_warn(&vdev->dev, "Bad virtqueue length %u\n", num);
return -EINVAL;
}
}
}
-static int pvcalls_back_remove(struct xenbus_device *dev)
+static void pvcalls_back_remove(struct xenbus_device *dev)
{
- return 0;
}
static int pvcalls_back_uevent(struct xenbus_device *xdev,
return IRQ_HANDLED;
}
+static void free_active_ring(struct sock_mapping *map);
+
static void pvcalls_front_free_map(struct pvcalls_bedata *bedata,
struct sock_mapping *map)
{
for (i = 0; i < (1 << PVCALLS_RING_ORDER); i++)
gnttab_end_foreign_access(map->active.ring->ref[i], NULL);
gnttab_end_foreign_access(map->active.ref, NULL);
- free_page((unsigned long)map->active.ring);
+ free_active_ring(map);
kfree(map);
}
{ "" }
};
-static int pvcalls_front_remove(struct xenbus_device *dev)
+static void pvcalls_front_remove(struct xenbus_device *dev)
{
struct pvcalls_bedata *bedata;
struct sock_mapping *map = NULL, *n;
kfree(bedata->ring.sring);
kfree(bedata);
xenbus_switch_state(dev, XenbusStateClosed);
- return 0;
}
static int pvcalls_front_probe(struct xenbus_device *dev,
return err;
}
-static int xen_pcibk_xenbus_remove(struct xenbus_device *dev)
+static void xen_pcibk_xenbus_remove(struct xenbus_device *dev)
{
struct xen_pcibk_device *pdev = dev_get_drvdata(&dev->dev);
if (pdev != NULL)
free_pdev(pdev);
-
- return 0;
}
static const struct xenbus_device_id xen_pcibk_ids[] = {
spin_unlock_irqrestore(&info->v2p_lock, flags);
}
-static int scsiback_remove(struct xenbus_device *dev)
+static void scsiback_remove(struct xenbus_device *dev)
{
struct vscsibk_info *info = dev_get_drvdata(&dev->dev);
gnttab_page_cache_shrink(&info->free_pages, 0);
dev_set_drvdata(&dev->dev, NULL);
-
- return 0;
}
static int scsiback_probe(struct xenbus_device *dev,
if (inode->i_size > AFFS_I(inode)->mmu_private) {
struct address_space *mapping = inode->i_mapping;
struct page *page;
- void *fsdata;
+ void *fsdata = NULL;
loff_t isize = inode->i_size;
int res;
#include "internal.h"
#include "afs_cm.h"
#include "protocol_yfs.h"
+#define RXRPC_TRACE_ONLY_DEFINE_ENUMS
+#include <trace/events/rxrpc.h>
static int afs_deliver_cb_init_call_back_state(struct afs_call *);
static int afs_deliver_cb_init_call_back_state3(struct afs_call *);
* Abort a service call from within an action function.
*/
static void afs_abort_service_call(struct afs_call *call, u32 abort_code, int error,
- const char *why)
+ enum rxrpc_abort_reason why)
{
rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
abort_code, error, why);
if (memcmp(r, &call->net->uuid, sizeof(call->net->uuid)) == 0)
afs_send_empty_reply(call);
else
- afs_abort_service_call(call, 1, 1, "K-1");
+ afs_abort_service_call(call, 1, 1, afs_abort_probeuuid_negative);
afs_put_call(call);
_leave("");
#include "internal.h"
#include "afs_cm.h"
#include "protocol_yfs.h"
+#define RXRPC_TRACE_ONLY_DEFINE_ENUMS
+#include <trace/events/rxrpc.h>
struct workqueue_struct *afs_async_calls;
error_do_abort:
if (ret != -ECONNABORTED) {
rxrpc_kernel_abort_call(call->net->socket, rxcall,
- RX_USER_ABORT, ret, "KSD");
+ RX_USER_ABORT, ret,
+ afs_abort_send_data_error);
} else {
len = 0;
iov_iter_kvec(&msg.msg_iter, ITER_DEST, NULL, 0, 0);
case -ENOTSUPP:
abort_code = RXGEN_OPCODE;
rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
- abort_code, ret, "KIV");
+ abort_code, ret,
+ afs_abort_op_not_supported);
goto local_abort;
case -EIO:
pr_err("kAFS: Call %u in bad state %u\n",
if (state != AFS_CALL_CL_AWAIT_REPLY)
abort_code = RXGEN_SS_UNMARSHAL;
rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
- abort_code, ret, "KUM");
+ abort_code, ret,
+ afs_abort_unmarshal_error);
goto local_abort;
default:
abort_code = RX_CALL_DEAD;
rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
- abort_code, ret, "KER");
+ abort_code, ret,
+ afs_abort_general_error);
goto local_abort;
}
}
/* Kill off the call if it's still live. */
_debug("call interrupted");
if (rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
- RX_USER_ABORT, -EINTR, "KWI"))
+ RX_USER_ABORT, -EINTR,
+ afs_abort_interrupted))
afs_set_call_complete(call, -EINTR, 0);
}
}
case -ENOMEM:
_debug("oom");
rxrpc_kernel_abort_call(net->socket, call->rxcall,
- RXGEN_SS_MARSHAL, -ENOMEM, "KOO");
+ RXGEN_SS_MARSHAL, -ENOMEM,
+ afs_abort_oom);
fallthrough;
default:
_leave(" [error]");
if (n == -ENOMEM) {
_debug("oom");
rxrpc_kernel_abort_call(net->socket, call->rxcall,
- RXGEN_SS_MARSHAL, -ENOMEM, "KOO");
+ RXGEN_SS_MARSHAL, -ENOMEM,
+ afs_abort_oom);
}
_leave(" [error]");
}
ret = rxrpc_kernel_recv_data(net->socket, call->rxcall, iter,
&call->iov_len, want_more, &remote_abort,
&call->service_id);
+ trace_afs_receive_data(call, call->iter, want_more, ret);
if (ret == 0 || ret == -EAGAIN)
return ret;
* The number of segs are recored into ELF header as 16bit value.
* Please check DEFAULT_MAX_MAP_COUNT definition when you modify here.
*/
- segs = cprm->vma_count + elf_core_extra_phdrs();
+ segs = cprm->vma_count + elf_core_extra_phdrs(cprm);
/* for notes section */
segs++;
dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE);
offset += cprm->vma_data_size;
- offset += elf_core_extra_data_size();
+ offset += elf_core_extra_data_size(cprm);
e_shoff = offset;
if (e_phnum == PN_XNUM) {
tmp->next = thread_list;
thread_list = tmp;
- segs = cprm->vma_count + elf_core_extra_phdrs();
+ segs = cprm->vma_count + elf_core_extra_phdrs(cprm);
/* for notes section */
segs++;
dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE);
offset += cprm->vma_data_size;
- offset += elf_core_extra_data_size();
+ offset += elf_core_extra_data_size(cprm);
e_shoff = offset;
if (e_phnum == PN_XNUM) {
u64 wanted_disk_byte = ref->wanted_disk_byte;
u64 count = 0;
u64 data_offset;
+ u8 type;
if (level != 0) {
eb = path->nodes[level];
continue;
}
fi = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item);
+ type = btrfs_file_extent_type(eb, fi);
+ if (type == BTRFS_FILE_EXTENT_INLINE)
+ goto next;
disk_byte = btrfs_file_extent_disk_bytenr(eb, fi);
data_offset = btrfs_file_extent_offset(eb, fi);
&map_length, &bioc, mirror_num);
if (ret)
goto out_counter_dec;
- BUG_ON(mirror_num != bioc->mirror_num);
+ /*
+ * This happens when dev-replace is also running, and the
+ * mirror_num indicates the dev-replace target.
+ *
+ * In this case, we don't need to do anything, as the read
+ * error just means the replace progress hasn't reached our
+ * read range, and later replace routine would handle it well.
+ */
+ if (mirror_num != bioc->mirror_num)
+ goto out_counter_dec;
}
sector = bioc->stripes[bioc->mirror_num - 1].physical >> 9;
goto out;
path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
+ if (!path) {
+ ret = -ENOMEM;
+ goto out;
+ }
level = btrfs_header_level(root->node);
btrfs_print_tree(eb, 0);
btrfs_err(fs_info, "block=%llu write time tree block corruption detected",
eb->start);
- WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
+ /*
+ * Be noisy if this is an extent buffer from a log tree. We don't abort
+ * a transaction in case there's a bad log tree extent buffer, we just
+ * fallback to a transaction commit. Still we want to know when there is
+ * a bad log tree extent buffer, as that may signal a bug somewhere.
+ */
+ WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG) ||
+ btrfs_header_owner(eb) == BTRFS_TREE_LOG_OBJECTID);
return ret;
}
}
if (found_level != check->level) {
+ btrfs_err(fs_info,
+ "level verify failed on logical %llu mirror %u wanted %u found %u",
+ eb->start, eb->read_mirror, check->level, found_level);
ret = -EIO;
goto out;
}
/*
* Do various sanity and dependency checks of different features.
*
+ * @is_rw_mount: If the mount is read-write.
+ *
* This is the place for less strict checks (like for subpage or artificial
* feature dependencies).
*
* (space cache related) can modify on-disk format like free space tree and
* screw up certain feature dependencies.
*/
-int btrfs_check_features(struct btrfs_fs_info *fs_info, struct super_block *sb)
+int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount)
{
struct btrfs_super_block *disk_super = fs_info->super_copy;
u64 incompat = btrfs_super_incompat_flags(disk_super);
if (btrfs_super_nodesize(disk_super) > PAGE_SIZE)
incompat |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
- if (compat_ro_unsupp && !sb_rdonly(sb)) {
+ if (compat_ro_unsupp && is_rw_mount) {
btrfs_err(fs_info,
"cannot mount read-write because of unknown compat_ro features (0x%llx)",
compat_ro);
goto fail_alloc;
}
- ret = btrfs_check_features(fs_info, sb);
+ ret = btrfs_check_features(fs_info, !sb_rdonly(sb));
if (ret < 0) {
err = ret;
goto fail_alloc;
void __cold close_ctree(struct btrfs_fs_info *fs_info);
int btrfs_validate_super(struct btrfs_fs_info *fs_info,
struct btrfs_super_block *sb, int mirror_num);
-int btrfs_check_features(struct btrfs_fs_info *fs_info, struct super_block *sb);
+int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount);
int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors);
struct btrfs_super_block *btrfs_read_dev_super(struct block_device *bdev);
struct btrfs_super_block *btrfs_read_dev_one_super(struct block_device *bdev,
u64 last = 0;
int found = 0;
- if (WARN_ON(search_end <= cur_start))
+ if (WARN_ON(search_end < cur_start))
return 0;
spin_lock(&tree->lock);
BUG();
if (ret && insert_reserved)
btrfs_pin_extent(trans, node->bytenr, node->num_bytes, 1);
+ if (ret < 0)
+ btrfs_err(trans->fs_info,
+"failed to run delayed ref for logical %llu num_bytes %llu type %u action %u ref_mod %d: %d",
+ node->bytenr, node->num_bytes, node->type,
+ node->action, node->ref_mod, ret);
return ret;
}
if (ret) {
unselect_delayed_ref_head(delayed_refs, locked_ref);
btrfs_put_delayed_ref(ref);
- btrfs_debug(fs_info, "run_one_delayed_ref returned %d",
- ret);
return ret;
}
btrfs_bio_end_io_t end_io_func;
/*
+ * This is for metadata read, to provide the extra needed verification
+ * info. This has to be provided for submit_one_bio(), as
+ * submit_one_bio() can submit a bio if it ends at stripe boundary. If
+ * no such parent_check is provided, the metadata can hit false alert at
+ * endio time.
+ */
+ struct btrfs_tree_parent_check *parent_check;
+
+ /*
* Tell writepage not to lock the state bits for this range, it still
* does the unlocking.
*/
btrfs_bio(bio)->file_offset = page_offset(bv->bv_page) + bv->bv_offset;
- if (!is_data_inode(&inode->vfs_inode))
+ if (!is_data_inode(&inode->vfs_inode)) {
+ if (btrfs_op(bio) != BTRFS_MAP_WRITE) {
+ /*
+ * For metadata read, we should have the parent_check,
+ * and copy it to bbio for metadata verification.
+ */
+ ASSERT(bio_ctrl->parent_check);
+ memcpy(&btrfs_bio(bio)->parent_check,
+ bio_ctrl->parent_check,
+ sizeof(struct btrfs_tree_parent_check));
+ }
btrfs_submit_metadata_bio(inode, bio, mirror_num);
- else if (btrfs_op(bio) == BTRFS_MAP_WRITE)
+ } else if (btrfs_op(bio) == BTRFS_MAP_WRITE) {
btrfs_submit_data_write_bio(inode, bio, mirror_num);
- else
+ } else {
btrfs_submit_data_read_bio(inode, bio, mirror_num,
bio_ctrl->compress_type);
+ }
/* The bio is owned by the end_io handler now */
bio_ctrl->bio = NULL;
struct extent_state *cached_state = NULL;
struct btrfs_bio_ctrl bio_ctrl = {
.mirror_num = mirror_num,
+ .parent_check = check,
};
int ret = 0;
*/
atomic_dec(&eb->io_pages);
}
- memcpy(&btrfs_bio(bio_ctrl.bio)->parent_check, check, sizeof(*check));
submit_one_bio(&bio_ctrl);
if (ret || wait != WAIT_COMPLETE) {
free_extent_state(cached_state);
unsigned long num_reads = 0;
struct btrfs_bio_ctrl bio_ctrl = {
.mirror_num = mirror_num,
+ .parent_check = check,
};
if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))
}
}
- memcpy(&btrfs_bio(bio_ctrl.bio)->parent_check, check, sizeof(*check));
submit_one_bio(&bio_ctrl);
if (ret || wait != WAIT_COMPLETE)
bool search_io_tree = true;
bool ret = false;
- while (cur_offset < end) {
+ while (cur_offset <= end) {
u64 delalloc_start;
u64 delalloc_end;
bool delalloc;
/* Indicate that we want to commit the transaction. */
BTRFS_FS_NEED_TRANS_COMMIT,
+ /*
+ * Indicate metadata over-commit is disabled. This is set when active
+ * zone tracking is needed.
+ */
+ BTRFS_FS_NO_OVERCOMMIT,
+
#if BITS_PER_LONG == 32
/* Indicate if we have error/warn message printed on 32bit systems */
BTRFS_FS_32BIT_ERROR,
* Other members are not utilized for inline extents.
*/
ASSERT(em->block_start == EXTENT_MAP_INLINE);
- ASSERT(em->len = fs_info->sectorsize);
+ ASSERT(em->len == fs_info->sectorsize);
ret = read_inline_extent(inode, path, page);
if (ret < 0)
if (flags & RENAME_WHITEOUT) {
whiteout_args.inode = new_whiteout_inode(mnt_userns, old_dir);
- if (!whiteout_args.inode)
- return -ENOMEM;
+ if (!whiteout_args.inode) {
+ ret = -ENOMEM;
+ goto out_fscrypt_names;
+ }
ret = btrfs_new_inode_prepare(&whiteout_args, &trans_num_items);
if (ret)
goto out_whiteout_inode;
/*
* Old roots should be searched when inserting qgroup
- * extent record
+ * extent record.
+ *
+ * But for INCONSISTENT (NO_ACCOUNTING) -> rescan case,
+ * we may have some record inserted during
+ * NO_ACCOUNTING (thus no old_roots populated), but
+ * later we start rescan, which clears NO_ACCOUNTING,
+ * leaving some inserted records without old_roots
+ * populated.
+ *
+ * Those cases are rare and should not cause too much
+ * time spent during commit_transaction().
*/
- if (WARN_ON(!record->old_roots)) {
+ if (!record->old_roots) {
/* Search commit root to find old_roots */
ret = btrfs_find_all_roots(&ctx, false);
if (ret < 0)
* current root. It's safe inside commit_transaction().
*/
ctx.trans = trans;
+ ctx.time_seq = BTRFS_SEQ_LAST;
ret = btrfs_find_all_roots(&ctx, false);
if (ret < 0)
goto cleanup;
void **pointers = NULL;
void **unmap_array = NULL;
int sector_nr;
- int ret;
+ int ret = 0;
/*
* @pointers array stores the pointer for each sector.
return 0;
used = btrfs_space_info_used(space_info, true);
- if (btrfs_is_zoned(fs_info) && (space_info->flags & BTRFS_BLOCK_GROUP_METADATA))
+ if (test_bit(BTRFS_FS_NO_OVERCOMMIT, &fs_info->flags) &&
+ (space_info->flags & BTRFS_BLOCK_GROUP_METADATA))
avail = 0;
else
avail = calc_available_free_space(fs_info, space_info, flush);
if (ret)
goto restore;
- ret = btrfs_check_features(fs_info, sb);
+ ret = btrfs_check_features(fs_info, !(*flags & SB_RDONLY));
if (ret < 0)
goto restore;
static void __exit exit_btrfs_fs(void)
{
btrfs_exit_btrfs_fs();
+ btrfs_cleanup_fs_uuids();
}
static int __init init_btrfs_fs(void)
ret = 0;
if (ret) {
blk_finish_plug(&plug);
- btrfs_abort_transaction(trans, ret);
btrfs_set_log_full_commit(trans);
mutex_unlock(&root->log_mutex);
goto out;
blk_finish_plug(&plug);
btrfs_set_log_full_commit(trans);
-
- if (ret != -ENOSPC) {
- btrfs_abort_transaction(trans, ret);
- mutex_unlock(&log_root_tree->log_mutex);
- goto out;
- }
+ if (ret != -ENOSPC)
+ btrfs_err(fs_info,
+ "failed to update log for root %llu ret %d",
+ root->root_key.objectid, ret);
btrfs_wait_tree_log_extents(log, mark);
mutex_unlock(&log_root_tree->log_mutex);
- ret = BTRFS_LOG_FORCE_COMMIT;
goto out;
}
goto out_wake_log_root;
} else if (ret) {
btrfs_set_log_full_commit(trans);
- btrfs_abort_transaction(trans, ret);
mutex_unlock(&log_root_tree->log_mutex);
goto out_wake_log_root;
}
path->slots[0]);
if (tmp.type == BTRFS_DIR_INDEX_KEY)
last_old_dentry_offset = tmp.offset;
+ } else if (ret < 0) {
+ err = ret;
}
+
goto done;
}
*/
if (tmp.type == BTRFS_DIR_INDEX_KEY)
last_old_dentry_offset = tmp.offset;
+ } else if (ret < 0) {
+ err = ret;
+ goto done;
}
+
btrfs_release_path(path);
/*
- * Find the first key from this transaction again. See the note for
- * log_new_dir_dentries, if we're logging a directory recursively we
- * won't be holding its i_mutex, which means we can modify the directory
- * while we're logging it. If we remove an entry between our first
- * search and this search we'll not find the key again and can just
- * bail.
+ * Find the first key from this transaction again or the one we were at
+ * in the loop below in case we had to reschedule. We may be logging the
+ * directory without holding its VFS lock, which happen when logging new
+ * dentries (through log_new_dir_dentries()) or in some cases when we
+ * need to log the parent directory of an inode. This means a dir index
+ * key might be deleted from the inode's root, and therefore we may not
+ * find it anymore. If we can't find it, just move to the next key. We
+ * can not bail out and ignore, because if we do that we will simply
+ * not log dir index keys that come after the one that was just deleted
+ * and we can end up logging a dir index range that ends at (u64)-1
+ * (@last_offset is initialized to that), resulting in removing dir
+ * entries we should not remove at log replay time.
*/
search:
ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0);
+ if (ret > 0)
+ ret = btrfs_next_item(root, path);
+ if (ret < 0)
+ err = ret;
+ /* If ret is 1, there are no more keys in the inode's root. */
if (ret != 0)
goto done;
* LOG_INODE_EXISTS mode) and slow down other fsyncs or transaction
* commits.
*/
- if (ctx->num_conflict_inodes >= MAX_CONFLICT_INODES)
+ if (ctx->num_conflict_inodes >= MAX_CONFLICT_INODES) {
+ btrfs_set_log_full_commit(trans);
return BTRFS_LOG_FORCE_COMMIT;
+ }
inode = btrfs_iget(root->fs_info->sb, ino, root);
/*
* not fail, but if it does, it's not serious, just bail out and
* mark the log for a full commit.
*/
- if (WARN_ON_ONCE(ret < 0))
+ if (WARN_ON_ONCE(ret < 0)) {
+ fscrypt_free_filename(&fname);
goto out;
+ }
+
log_pinned = true;
path = btrfs_alloc_path();
BTRFS_SUPER_FLAG_CHANGING_FSID_V2);
error = lookup_bdev(path, &path_devt);
- if (error)
+ if (error) {
+ btrfs_err(NULL, "failed to lookup block device for path %s: %d",
+ path, error);
return ERR_PTR(error);
+ }
if (fsid_change_in_progress) {
if (!has_metadata_uuid)
unsigned int nofs_flag;
if (fs_devices->opened) {
+ btrfs_err(NULL,
+ "device %s belongs to fsid %pU, and the fs is already mounted",
+ path, fs_devices->fsid);
mutex_unlock(&fs_devices->device_list_mutex);
return ERR_PTR(-EBUSY);
}
* generation are equal.
*/
mutex_unlock(&fs_devices->device_list_mutex);
+ btrfs_err(NULL,
+"device %s already registered with a higher generation, found %llu expect %llu",
+ path, found_transid, device->generation);
return ERR_PTR(-EEXIST);
}
}
atomic_set(&zone_info->active_zones_left,
max_active_zones - nactive);
+ /* Overcommit does not work well with active zone tacking. */
+ set_bit(BTRFS_FS_NO_OVERCOMMIT, &fs_info->flags);
}
/* Validate superblock log */
while (true) {
flags &= CEPH_FILE_MODE_MASK;
- if (atomic_read(&fi->num_locks))
+ if (vfs_inode_has_locks(inode))
flags |= CHECK_FILELOCK;
_got = 0;
ret = try_get_cap_refs(inode, need, want, endoff,
static void ceph_fl_copy_lock(struct file_lock *dst, struct file_lock *src)
{
- struct ceph_file_info *fi = dst->fl_file->private_data;
struct inode *inode = file_inode(dst->fl_file);
atomic_inc(&ceph_inode(inode)->i_filelock_ref);
- atomic_inc(&fi->num_locks);
+ dst->fl_u.ceph.inode = igrab(inode);
}
+/*
+ * Do not use the 'fl->fl_file' in release function, which
+ * is possibly already released by another thread.
+ */
static void ceph_fl_release_lock(struct file_lock *fl)
{
- struct ceph_file_info *fi = fl->fl_file->private_data;
- struct inode *inode = file_inode(fl->fl_file);
- struct ceph_inode_info *ci = ceph_inode(inode);
- atomic_dec(&fi->num_locks);
+ struct inode *inode = fl->fl_u.ceph.inode;
+ struct ceph_inode_info *ci;
+
+ /*
+ * If inode is NULL it should be a request file_lock,
+ * nothing we can do.
+ */
+ if (!inode)
+ return;
+
+ ci = ceph_inode(inode);
if (atomic_dec_and_test(&ci->i_filelock_ref)) {
/* clear error when all locks are released */
spin_lock(&ci->i_ceph_lock);
ci->i_ceph_flags &= ~CEPH_I_ERROR_FILELOCK;
spin_unlock(&ci->i_ceph_lock);
}
+ fl->fl_u.ceph.inode = NULL;
+ iput(inode);
}
static const struct file_lock_operations ceph_fl_lock_ops = {
struct list_head rw_contexts;
u32 filp_gen;
- atomic_t num_locks;
};
struct ceph_dir_file_info {
* ( for NTLMSSP_AV_NB_DOMAIN_NAME followed by NTLMSSP_AV_EOL ) +
* unicode length of a netbios domain name
*/
+ kfree_sensitive(ses->auth_key.response);
ses->auth_key.len = size + 2 * dlen;
ses->auth_key.response = kzalloc(ses->auth_key.len, GFP_KERNEL);
if (!ses->auth_key.response) {
INIT_LIST_HEAD(&tcon->pending_opens);
tcon->status = TID_GOOD;
- /* schedule query interfaces poll */
INIT_DELAYED_WORK(&tcon->query_interfaces,
smb2_query_server_interfaces);
- queue_delayed_work(cifsiod_wq, &tcon->query_interfaces,
- (SMB_INTERFACE_POLL_INTERVAL * HZ));
+ if (ses->server->dialect >= SMB30_PROT_ID &&
+ (ses->server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) {
+ /* schedule query interfaces poll */
+ queue_delayed_work(cifsiod_wq, &tcon->query_interfaces,
+ (SMB_INTERFACE_POLL_INTERVAL * HZ));
+ }
spin_lock(&cifs_tcp_ses_lock);
list_add(&tcon->tcon_list, &ses->tcon_list);
return rc;
}
-static int target_share_matches_server(struct TCP_Server_Info *server, const char *tcp_host,
- size_t tcp_host_len, char *share, bool *target_match)
+static int target_share_matches_server(struct TCP_Server_Info *server, char *share,
+ bool *target_match)
{
int rc = 0;
const char *dfs_host;
extract_unc_hostname(share, &dfs_host, &dfs_host_len);
/* Check if hostnames or addresses match */
- if (dfs_host_len != tcp_host_len || strncasecmp(dfs_host, tcp_host, dfs_host_len) != 0) {
- cifs_dbg(FYI, "%s: %.*s doesn't match %.*s\n", __func__, (int)dfs_host_len,
- dfs_host, (int)tcp_host_len, tcp_host);
+ cifs_server_lock(server);
+ if (dfs_host_len != strlen(server->hostname) ||
+ strncasecmp(dfs_host, server->hostname, dfs_host_len)) {
+ cifs_dbg(FYI, "%s: %.*s doesn't match %s\n", __func__,
+ (int)dfs_host_len, dfs_host, server->hostname);
rc = match_target_ip(server, dfs_host, dfs_host_len, target_match);
if (rc)
cifs_dbg(VFS, "%s: failed to match target ip: %d\n", __func__, rc);
}
+ cifs_server_unlock(server);
return rc;
}
struct cifs_ses *root_ses = CIFS_DFS_ROOT_SES(tcon->ses);
struct cifs_tcon *ipc = root_ses->tcon_ipc;
char *share = NULL, *prefix = NULL;
- const char *tcp_host;
- size_t tcp_host_len;
struct dfs_cache_tgt_iterator *tit;
bool target_match;
- extract_unc_hostname(server->hostname, &tcp_host, &tcp_host_len);
-
tit = dfs_cache_get_tgt_iterator(tl);
if (!tit) {
rc = -ENOENT;
break;
}
- rc = target_share_matches_server(server, tcp_host, tcp_host_len, share,
- &target_match);
+ rc = target_share_matches_server(server, share, &target_match);
if (rc)
break;
if (!target_match) {
if (ipc->need_reconnect) {
scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", server->hostname);
rc = ops->tree_connect(xid, ipc->ses, tree, ipc, cifs_sb->local_nls);
- if (rc)
- break;
+ cifs_dbg(FYI, "%s: reconnect ipc: %d\n", __func__, rc);
}
scnprintf(tree, MAX_TREE_SIZE, "\\%s", share);
}
if (tcon->ipc) {
+ cifs_server_lock(server);
scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", server->hostname);
+ cifs_server_unlock(server);
rc = ops->tree_connect(xid, tcon->ses, tree, tcon, nlsc);
goto out;
}
* Resolve share's hostname and check if server address matches. Otherwise just ignore it
* as we could not have upcall to resolve hostname or failed to convert ip address.
*/
- match = true;
extract_unc_hostname(s1, &host, &hostlen);
scnprintf(unc, sizeof(unc), "\\\\%.*s", (int)hostlen, host);
oparms.disposition = FILE_CREATE;
oparms.fid = &fid;
oparms.reconnect = false;
+ oparms.mode = 0644;
rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL,
NULL, NULL);
if (rc < 0)
return rc;
+ spin_lock(&server->srv_lock);
*result = cifs_match_ipaddr((struct sockaddr *)&server->dstaddr, (struct sockaddr *)&ss);
+ spin_unlock(&server->srv_lock);
cifs_dbg(FYI, "%s: ip addresses match: %u\n", __func__, *result);
return 0;
}
continue;
}
kref_get(&iface->refcount);
+ break;
}
- if (!list_entry_is_head(iface, &ses->iface_list, iface_head)) {
+ if (list_entry_is_head(iface, &ses->iface_list, iface_head)) {
rc = 1;
iface = NULL;
cifs_dbg(FYI, "unable to find a suitable iface\n");
return -EINVAL;
}
if (tilen) {
+ kfree_sensitive(ses->auth_key.response);
ses->auth_key.response = kmemdup(bcc_ptr + tioffset, tilen,
GFP_KERNEL);
if (!ses->auth_key.response) {
goto out_put_spnego_key;
}
+ kfree_sensitive(ses->auth_key.response);
ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len,
GFP_KERNEL);
if (!ses->auth_key.response) {
if ((rc == -EOPNOTSUPP) || (rc == -EINVAL)) {
rc = SMBQueryInformation(xid, tcon, full_path, &fi, cifs_sb->local_nls,
cifs_remap(cifs_sb));
- if (!rc)
- move_cifs_info_to_smb2(&data->fi, &fi);
*adjustTZ = true;
}
- if (!rc && (le32_to_cpu(fi.Attributes) & ATTR_REPARSE)) {
+ if (!rc) {
int tmprc;
int oplock = 0;
struct cifs_fid fid;
struct cifs_open_parms oparms;
+ move_cifs_info_to_smb2(&data->fi, &fi);
+
+ if (!(le32_to_cpu(fi.Attributes) & ATTR_REPARSE))
+ return 0;
+
oparms.tcon = tcon;
oparms.cifs_sb = cifs_sb;
oparms.desired_access = FILE_READ_ATTRIBUTES;
static int cifs_open_file(const unsigned int xid, struct cifs_open_parms *oparms, __u32 *oplock,
void *buf)
{
- FILE_ALL_INFO *fi = buf;
+ struct cifs_open_info_data *data = buf;
+ FILE_ALL_INFO fi = {};
+ int rc;
if (!(oparms->tcon->ses->capabilities & CAP_NT_SMBS))
- return SMBLegacyOpen(xid, oparms->tcon, oparms->path,
- oparms->disposition,
- oparms->desired_access,
- oparms->create_options,
- &oparms->fid->netfid, oplock, fi,
- oparms->cifs_sb->local_nls,
- cifs_remap(oparms->cifs_sb));
- return CIFS_open(xid, oparms, oplock, fi);
+ rc = SMBLegacyOpen(xid, oparms->tcon, oparms->path,
+ oparms->disposition,
+ oparms->desired_access,
+ oparms->create_options,
+ &oparms->fid->netfid, oplock, &fi,
+ oparms->cifs_sb->local_nls,
+ cifs_remap(oparms->cifs_sb));
+ else
+ rc = CIFS_open(xid, oparms, oplock, &fi);
+
+ if (!rc && data)
+ move_cifs_info_to_smb2(&data->fi, &fi);
+
+ return rc;
}
static void
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct inode *newinode = NULL;
int rc = -EPERM;
- FILE_ALL_INFO *buf = NULL;
+ struct cifs_open_info_data buf = {};
struct cifs_io_parms io_parms;
__u32 oplock = 0;
struct cifs_fid fid;
cifs_sb->local_nls,
cifs_remap(cifs_sb));
if (rc)
- goto out;
+ return rc;
rc = cifs_get_inode_info_unix(&newinode, full_path,
inode->i_sb, xid);
if (rc == 0)
d_instantiate(dentry, newinode);
- goto out;
+ return rc;
}
/*
* support block and char device (no socket & fifo)
*/
if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL))
- goto out;
+ return rc;
if (!S_ISCHR(mode) && !S_ISBLK(mode))
- goto out;
+ return rc;
cifs_dbg(FYI, "sfu compat create special file\n");
- buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL);
- if (buf == NULL) {
- rc = -ENOMEM;
- goto out;
- }
-
oparms.tcon = tcon;
oparms.cifs_sb = cifs_sb;
oparms.desired_access = GENERIC_WRITE;
oplock = REQ_OPLOCK;
else
oplock = 0;
- rc = tcon->ses->server->ops->open(xid, &oparms, &oplock, buf);
+ rc = tcon->ses->server->ops->open(xid, &oparms, &oplock, &buf);
if (rc)
- goto out;
+ return rc;
/*
* BB Do not bother to decode buf since no local inode yet to put
* timestamps in, but we can reuse it safely.
*/
- pdev = (struct win_dev *)buf;
+ pdev = (struct win_dev *)&buf.fi;
io_parms.pid = current->tgid;
io_parms.tcon = tcon;
io_parms.offset = 0;
io_parms.length = sizeof(struct win_dev);
- iov[1].iov_base = buf;
+ iov[1].iov_base = &buf.fi;
iov[1].iov_len = sizeof(struct win_dev);
if (S_ISCHR(mode)) {
memcpy(pdev->type, "IntxCHR", 8);
d_drop(dentry);
/* FIXME: add code here to set EAs */
-out:
- kfree(buf);
+
+ cifs_free_open_info(&buf);
return rc;
}
p = buf;
spin_lock(&ses->iface_lock);
- ses->iface_count = 0;
/*
* Go through iface_list and do kref_put to remove
* any unused ifaces. ifaces in use will be removed
iface_head) {
iface->is_active = 0;
kref_put(&iface->refcount, release_iface);
+ ses->iface_count--;
}
spin_unlock(&ses->iface_lock);
/* just get a ref so that it doesn't get picked/freed */
iface->is_active = 1;
kref_get(&iface->refcount);
+ ses->iface_count++;
spin_unlock(&ses->iface_lock);
goto next_iface;
} else if (ret < 0) {
/* copy pages form the old */
for (j = 0; j < npages; j++) {
- char *dst, *src;
unsigned int offset, len;
rqst_page_get_length(new, j, &len, &offset);
- dst = kmap_local_page(new->rq_pages[j]) + offset;
- src = kmap_local_page(old->rq_pages[j]) + offset;
-
- memcpy(dst, src, len);
- kunmap(new->rq_pages[j]);
- kunmap(old->rq_pages[j]);
+ memcpy_page(new->rq_pages[j], offset,
+ old->rq_pages[j], offset, len);
}
}
assemble_neg_contexts(struct smb2_negotiate_req *req,
struct TCP_Server_Info *server, unsigned int *total_len)
{
- char *pneg_ctxt;
- char *hostname = NULL;
unsigned int ctxt_len, neg_context_count;
+ struct TCP_Server_Info *pserver;
+ char *pneg_ctxt;
+ char *hostname;
if (*total_len > 200) {
/* In case length corrupted don't want to overrun smb buffer */
* secondary channels don't have the hostname field populated
* use the hostname field in the primary channel instead
*/
- hostname = CIFS_SERVER_IS_CHAN(server) ?
- server->primary_server->hostname : server->hostname;
+ pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server;
+ cifs_server_lock(pserver);
+ hostname = pserver->hostname;
if (hostname && (hostname[0] != 0)) {
ctxt_len = build_netname_ctxt((struct smb2_netname_neg_context *)pneg_ctxt,
hostname);
neg_context_count = 3;
} else
neg_context_count = 2;
+ cifs_server_unlock(pserver);
build_posix_ctxt((struct smb2_posix_neg_context *)pneg_ctxt);
*total_len += sizeof(struct smb2_posix_neg_context);
/* keep session key if binding */
if (!is_binding) {
+ kfree_sensitive(ses->auth_key.response);
ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len,
GFP_KERNEL);
if (!ses->auth_key.response) {
out_put_spnego_key:
key_invalidate(spnego_key);
key_put(spnego_key);
- if (rc)
+ if (rc) {
kfree_sensitive(ses->auth_key.response);
+ ses->auth_key.response = NULL;
+ ses->auth_key.len = 0;
+ }
out:
sess_data->result = rc;
sess_data->func = NULL;
}
++ctx->devs->extra_devices;
break;
- case Opt_fsid:
#ifdef CONFIG_EROFS_FS_ONDEMAND
+ case Opt_fsid:
kfree(ctx->fsid);
ctx->fsid = kstrdup(param->string, GFP_KERNEL);
if (!ctx->fsid)
return -ENOMEM;
-#else
- errorfc(fc, "fsid option not supported");
-#endif
break;
case Opt_domain_id:
-#ifdef CONFIG_EROFS_FS_ONDEMAND
kfree(ctx->domain_id);
ctx->domain_id = kstrdup(param->string, GFP_KERNEL);
if (!ctx->domain_id)
return -ENOMEM;
+ break;
#else
- errorfc(fc, "domain_id option not supported");
-#endif
+ case Opt_fsid:
+ case Opt_domain_id:
+ errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name);
break;
+#endif
default:
return -ENOPARAM;
}
if (!be->decompressed_pages)
be->decompressed_pages =
- kvcalloc(be->nr_pages, sizeof(struct page *),
- GFP_KERNEL | __GFP_NOFAIL);
+ kcalloc(be->nr_pages, sizeof(struct page *),
+ GFP_KERNEL | __GFP_NOFAIL);
if (!be->compressed_pages)
be->compressed_pages =
- kvcalloc(pclusterpages, sizeof(struct page *),
- GFP_KERNEL | __GFP_NOFAIL);
+ kcalloc(pclusterpages, sizeof(struct page *),
+ GFP_KERNEL | __GFP_NOFAIL);
z_erofs_parse_out_bvecs(be);
err2 = z_erofs_parse_in_bvecs(be, &overlapped);
}
if (be->compressed_pages < be->onstack_pages ||
be->compressed_pages >= be->onstack_pages + Z_EROFS_ONSTACK_PAGES)
- kvfree(be->compressed_pages);
+ kfree(be->compressed_pages);
z_erofs_fill_other_copies(be, err);
for (i = 0; i < be->nr_pages; ++i) {
}
if (be->decompressed_pages != be->onstack_pages)
- kvfree(be->decompressed_pages);
+ kfree(be->decompressed_pages);
pcl->length = 0;
pcl->partial = true;
iomap->type = IOMAP_HOLE;
iomap->addr = IOMAP_NULL_ADDR;
/*
- * No strict rule how to describe extents for post EOF, yet
- * we need do like below. Otherwise, iomap itself will get
+ * No strict rule on how to describe extents for post EOF, yet
+ * we need to do like below. Otherwise, iomap itself will get
* into an endless loop on post EOF.
+ *
+ * Calculate the effective offset by subtracting extent start
+ * (map.m_la) from the requested offset, and add it to length.
+ * (NB: offset >= map.m_la always)
*/
if (iomap->offset >= inode->i_size)
- iomap->length = length + map.m_la - offset;
+ iomap->length = length + offset - map.m_la;
}
iomap->flags = 0;
return 0;
sector_t last_block_in_file;
const unsigned blocksize = blks_to_bytes(inode, 1);
struct decompress_io_ctx *dic = NULL;
- struct extent_info ei = {0, };
+ struct extent_info ei = {};
bool from_dnode = true;
int i;
int ret = 0;
struct extent_node *en;
bool ret = false;
- f2fs_bug_on(sbi, !et);
+ if (!et)
+ return false;
trace_f2fs_lookup_extent_tree_start(inode, pgofs, type);
}
/* This returns a new age and allocated blocks in ei */
-static int __get_new_block_age(struct inode *inode, struct extent_info *ei)
+static int __get_new_block_age(struct inode *inode, struct extent_info *ei,
+ block_t blkaddr)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
loff_t f_size = i_size_read(inode);
unsigned long long cur_blocks =
atomic64_read(&sbi->allocated_data_blocks);
+ struct extent_info tei = *ei; /* only fofs and len are valid */
/*
* When I/O is not aligned to a PAGE_SIZE, update will happen to the last
* block here.
*/
if ((f_size >> PAGE_SHIFT) == ei->fofs && f_size & (PAGE_SIZE - 1) &&
- ei->blk == NEW_ADDR)
+ blkaddr == NEW_ADDR)
return -EINVAL;
- if (__lookup_extent_tree(inode, ei->fofs, ei, EX_BLOCK_AGE)) {
+ if (__lookup_extent_tree(inode, ei->fofs, &tei, EX_BLOCK_AGE)) {
unsigned long long cur_age;
- if (cur_blocks >= ei->last_blocks)
- cur_age = cur_blocks - ei->last_blocks;
+ if (cur_blocks >= tei.last_blocks)
+ cur_age = cur_blocks - tei.last_blocks;
else
/* allocated_data_blocks overflow */
- cur_age = ULLONG_MAX - ei->last_blocks + cur_blocks;
+ cur_age = ULLONG_MAX - tei.last_blocks + cur_blocks;
- if (ei->age)
- ei->age = __calculate_block_age(cur_age, ei->age);
+ if (tei.age)
+ ei->age = __calculate_block_age(cur_age, tei.age);
else
ei->age = cur_age;
ei->last_blocks = cur_blocks;
return 0;
}
- f2fs_bug_on(sbi, ei->blk == NULL_ADDR);
+ f2fs_bug_on(sbi, blkaddr == NULL_ADDR);
/* the data block was allocated for the first time */
- if (ei->blk == NEW_ADDR)
+ if (blkaddr == NEW_ADDR)
goto out;
- if (__is_valid_data_blkaddr(ei->blk) &&
- !f2fs_is_valid_blkaddr(sbi, ei->blk, DATA_GENERIC_ENHANCE)) {
+ if (__is_valid_data_blkaddr(blkaddr) &&
+ !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) {
f2fs_bug_on(sbi, 1);
return -EINVAL;
}
static void __update_extent_cache(struct dnode_of_data *dn, enum extent_type type)
{
- struct extent_info ei;
+ struct extent_info ei = {};
if (!__may_extent_tree(dn->inode, type))
return;
else
ei.blk = dn->data_blkaddr;
} else if (type == EX_BLOCK_AGE) {
- ei.blk = dn->data_blkaddr;
- if (__get_new_block_age(dn->inode, &ei))
+ if (__get_new_block_age(dn->inode, &ei, dn->data_blkaddr))
return;
}
__update_extent_tree_range(dn->inode, &ei, type);
struct f2fs_map_blocks map = { .m_next_extent = NULL,
.m_seg_type = NO_CHECK_TYPE,
.m_may_create = false };
- struct extent_info ei = {0, };
+ struct extent_info ei = {};
pgoff_t pg_start, pg_end, next_pgofs;
unsigned int blk_per_seg = sbi->blocks_per_seg;
unsigned int total = 0, sec_num;
if (IS_ERR(fcc->f2fs_issue_flush)) {
int err = PTR_ERR(fcc->f2fs_issue_flush);
- kfree(fcc);
- SM_I(sbi)->fcc_info = NULL;
+ fcc->f2fs_issue_flush = NULL;
return err;
}
static int __get_age_segment_type(struct inode *inode, pgoff_t pgofs)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct extent_info ei;
+ struct extent_info ei = {};
if (f2fs_lookup_age_extent_cache(inode, pgofs, &ei)) {
if (!ei.age)
init_f2fs_rwsem(&sm_info->curseg_lock);
- if (!f2fs_readonly(sbi->sb)) {
- err = f2fs_create_flush_cmd_control(sbi);
- if (err)
- return err;
- }
+ err = f2fs_create_flush_cmd_control(sbi);
+ if (err)
+ return err;
err = create_discard_cmd_control(sbi);
if (err)
/* panic? */
return -EIO;
+ res = -EIO;
if (HFS_I(main_inode)->cat_key.CName.len > HFS_NAMELEN)
- return -EIO;
+ goto out;
fd.search_key->cat = HFS_I(main_inode)->cat_key;
if (hfs_brec_find(&fd))
- /* panic? */
goto out;
if (S_ISDIR(main_inode->i_mode)) {
- WARN_ON(fd.entrylength < sizeof(struct hfs_cat_dir));
+ if (fd.entrylength < sizeof(struct hfs_cat_dir))
+ goto out;
hfs_bnode_read(fd.bnode, &rec, fd.entryoffset,
sizeof(struct hfs_cat_dir));
if (rec.type != HFS_CDR_DIR ||
hfs_bnode_write(fd.bnode, &rec, fd.entryoffset,
sizeof(struct hfs_cat_dir));
} else if (HFS_IS_RSRC(inode)) {
+ if (fd.entrylength < sizeof(struct hfs_cat_file))
+ goto out;
hfs_bnode_read(fd.bnode, &rec, fd.entryoffset,
sizeof(struct hfs_cat_file));
hfs_inode_write_fork(inode, rec.file.RExtRec,
hfs_bnode_write(fd.bnode, &rec, fd.entryoffset,
sizeof(struct hfs_cat_file));
} else {
- WARN_ON(fd.entrylength < sizeof(struct hfs_cat_file));
+ if (fd.entrylength < sizeof(struct hfs_cat_file))
+ goto out;
hfs_bnode_read(fd.bnode, &rec, fd.entryoffset,
sizeof(struct hfs_cat_file));
if (rec.type != HFS_CDR_FIL ||
hfs_bnode_write(fd.bnode, &rec, fd.entryoffset,
sizeof(struct hfs_cat_file));
}
+ res = 0;
out:
hfs_find_exit(&fd);
- return 0;
+ return res;
}
static struct dentry *hfs_file_lookup(struct inode *dir, struct dentry *dentry,
dn_off = le32_to_cpu(authblob->DomainName.BufferOffset);
dn_len = le16_to_cpu(authblob->DomainName.Length);
- if (blob_len < (u64)dn_off + dn_len || blob_len < (u64)nt_off + nt_len)
+ if (blob_len < (u64)dn_off + dn_len || blob_len < (u64)nt_off + nt_len ||
+ nt_len < CIFS_ENCPWD_SIZE)
return -EINVAL;
/* TODO : use domain name that imported from configuration file */
/* 4 for rfc1002 length field */
size = pdu_size + 4;
- conn->request_buf = kvmalloc(size, GFP_KERNEL);
+ conn->request_buf = kvmalloc(size,
+ GFP_KERNEL |
+ __GFP_NOWARN |
+ __GFP_NORETRY);
if (!conn->request_buf)
- continue;
+ break;
memcpy(conn->request_buf, hdr_buf, sizeof(hdr_buf));
if (!ksmbd_smb_request(conn))
if (conn->posix_ext_supported)
status.tree_conn->posix_extensions = true;
-out_err1:
rsp->StructureSize = cpu_to_le16(16);
+ inc_rfc1001_len(work->response_buf, 16);
+out_err1:
rsp->Capabilities = 0;
rsp->Reserved = 0;
/* default manual caching */
rsp->ShareFlags = SMB2_SHAREFLAG_MANUAL_CACHING;
- inc_rfc1001_len(work->response_buf, 16);
if (!IS_ERR(treename))
kfree(treename);
rsp->hdr.Status = STATUS_ACCESS_DENIED;
}
+ if (status.ret != KSMBD_TREE_CONN_STATUS_OK)
+ smb2_set_err_rsp(work);
+
return rc;
}
struct msghdr ksmbd_msg;
struct kvec *iov;
struct ksmbd_conn *conn = KSMBD_TRANS(t)->conn;
+ int max_retry = 2;
iov = get_conn_iovec(t, nr_segs);
if (!iov)
} else if (conn->status == KSMBD_SESS_NEED_RECONNECT) {
total_read = -EAGAIN;
break;
- } else if (length == -ERESTARTSYS || length == -EAGAIN) {
+ } else if ((length == -ERESTARTSYS || length == -EAGAIN) &&
+ max_retry) {
usleep_range(1000, 2000);
length = 0;
+ max_retry--;
continue;
} else if (length <= 0) {
total_read = -EAGAIN;
const struct cred *cred)
{
const struct task_struct *parent;
+ const struct cred *pcred;
u64 ret;
rcu_read_lock();
for (;;) {
parent = rcu_dereference(task->real_parent);
- if (parent == task || cred_fscmp(parent->cred, cred) != 0)
+ pcred = rcu_dereference(parent->cred);
+ if (parent == task || cred_fscmp(pcred, cred) != 0)
break;
task = parent;
}
* but do it without locking.
*/
struct nfs_inode *nfsi = NFS_I(inode);
+ u64 login_time = nfs_access_login_time(current, cred);
struct nfs_access_entry *cache;
int err = -ECHILD;
struct list_head *lh;
cache = NULL;
if (cache == NULL)
goto out;
+ if ((s64)(login_time - cache->timestamp) > 0)
+ goto out;
if (nfs_check_cache_invalid(inode, NFS_INO_INVALID_ACCESS))
goto out;
*mask = cache->mask;
return &fl->generic_hdr;
}
+static bool
+filelayout_lseg_is_striped(const struct nfs4_filelayout_segment *flseg)
+{
+ return flseg->num_fh > 1;
+}
+
/*
* filelayout_pg_test(). Called by nfs_can_coalesce_requests()
*
size = pnfs_generic_pg_test(pgio, prev, req);
if (!size)
return 0;
+ else if (!filelayout_lseg_is_striped(FILELAYOUT_LSEG(pgio->pg_lseg)))
+ return size;
/* see if req and prev are in the same stripe */
if (prev) {
static __be32
nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
- unsigned int may_flags, struct nfsd_file **pnf,
- bool open, bool want_gc)
+ unsigned int may_flags, struct file *file,
+ struct nfsd_file **pnf, bool want_gc)
{
struct nfsd_file_lookup_key key = {
.type = NFSD_FILE_KEY_FULL,
status = nfserrno(nfsd_open_break_lease(file_inode(nf->nf_file), may_flags));
out:
if (status == nfs_ok) {
- if (open)
- this_cpu_inc(nfsd_file_acquisitions);
+ this_cpu_inc(nfsd_file_acquisitions);
*pnf = nf;
} else {
if (refcount_dec_and_test(&nf->nf_ref))
out_status:
put_cred(key.cred);
- if (open)
- trace_nfsd_file_acquire(rqstp, key.inode, may_flags, nf, status);
+ trace_nfsd_file_acquire(rqstp, key.inode, may_flags, nf, status);
return status;
open_file:
trace_nfsd_file_alloc(nf);
nf->nf_mark = nfsd_file_mark_find_or_create(nf, key.inode);
if (nf->nf_mark) {
- if (open) {
+ if (file) {
+ get_file(file);
+ nf->nf_file = file;
+ status = nfs_ok;
+ trace_nfsd_file_opened(nf, status);
+ } else {
status = nfsd_open_verified(rqstp, fhp, may_flags,
&nf->nf_file);
trace_nfsd_file_open(nf, status);
- } else
- status = nfs_ok;
+ }
} else
status = nfserr_jukebox;
/*
nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp,
unsigned int may_flags, struct nfsd_file **pnf)
{
- return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, true, true);
+ return nfsd_file_do_acquire(rqstp, fhp, may_flags, NULL, pnf, true);
}
/**
nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
unsigned int may_flags, struct nfsd_file **pnf)
{
- return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, true, false);
+ return nfsd_file_do_acquire(rqstp, fhp, may_flags, NULL, pnf, false);
}
/**
- * nfsd_file_create - Get a struct nfsd_file, do not open
+ * nfsd_file_acquire_opened - Get a struct nfsd_file using existing open file
* @rqstp: the RPC transaction being executed
* @fhp: the NFS filehandle of the file just created
* @may_flags: NFSD_MAY_ settings for the file
+ * @file: cached, already-open file (may be NULL)
* @pnf: OUT: new or found "struct nfsd_file" object
*
- * The nfsd_file_object returned by this API is reference-counted
- * but not garbage-collected. The object is released immediately
- * one RCU grace period after the final nfsd_file_put().
+ * Acquire a nfsd_file object that is not GC'ed. If one doesn't already exist,
+ * and @file is non-NULL, use it to instantiate a new nfsd_file instead of
+ * opening a new one.
*
* Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in
* network byte order is returned.
*/
__be32
-nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
- unsigned int may_flags, struct nfsd_file **pnf)
+nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ unsigned int may_flags, struct file *file,
+ struct nfsd_file **pnf)
{
- return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, false, false);
+ return nfsd_file_do_acquire(rqstp, fhp, may_flags, file, pnf, false);
}
/*
unsigned int may_flags, struct nfsd_file **nfp);
__be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
unsigned int may_flags, struct nfsd_file **nfp);
-__be32 nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
- unsigned int may_flags, struct nfsd_file **nfp);
+__be32 nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ unsigned int may_flags, struct file *file,
+ struct nfsd_file **nfp);
int nfsd_file_cache_stats_show(struct seq_file *m, void *v);
#endif /* _FS_NFSD_FILECACHE_H */
atomic_t nfsd_courtesy_clients;
struct shrinker nfsd_client_shrinker;
- struct delayed_work nfsd_shrinker_work;
+ struct work_struct nfsd_shrinker_work;
};
/* Simple check to find out if a given net was properly initialized */
* the client wants us to do more in this compound:
*/
if (!nfsd4_last_compound_op(rqstp))
- __clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
+ clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
/* check stateid */
status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh,
/* allow 20secs for mount/unmount for now - revisit */
if (signal_pending(current) ||
(schedule_timeout(20*HZ) == 0)) {
+ finish_wait(&nn->nfsd_ssc_waitq, &wait);
kfree(work);
return nfserr_eagain;
}
cstate->minorversion = args->minorversion;
fh_init(current_fh, NFS4_FHSIZE);
fh_init(save_fh, NFS4_FHSIZE);
-
/*
* Don't use the deferral mechanism for NFSv4; compounds make it
* too hard to avoid non-idempotency problems.
*/
- __clear_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
+ clear_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
/*
* According to RFC3010, this takes precedence over all other errors.
out:
cstate->status = status;
/* Reset deferral mechanism for RPC deferrals */
- __set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
+ set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
return rpc_success;
}
if (!count)
count = atomic_long_read(&num_delegations);
if (count)
- mod_delayed_work(laundry_wq, &nn->nfsd_shrinker_work, 0);
+ queue_work(laundry_wq, &nn->nfsd_shrinker_work);
return (unsigned long)count;
}
return SHRINK_STOP;
}
-int
+void
nfsd4_init_leases_net(struct nfsd_net *nn)
{
struct sysinfo si;
nn->nfs4_max_clients = max_t(int, max_clients, NFS4_CLIENTS_PER_GB);
atomic_set(&nn->nfsd_courtesy_clients, 0);
- nn->nfsd_client_shrinker.scan_objects = nfsd4_state_shrinker_scan;
- nn->nfsd_client_shrinker.count_objects = nfsd4_state_shrinker_count;
- nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS;
- return register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client");
-}
-
-void
-nfsd4_leases_net_shutdown(struct nfsd_net *nn)
-{
- unregister_shrinker(&nn->nfsd_client_shrinker);
}
static void init_nfs4_replay(struct nfs4_replay *rp)
if (!fp->fi_fds[oflag]) {
spin_unlock(&fp->fi_lock);
- if (!open->op_filp) {
- status = nfsd_file_acquire(rqstp, cur_fh, access, &nf);
- if (status != nfs_ok)
- goto out_put_access;
- } else {
- status = nfsd_file_create(rqstp, cur_fh, access, &nf);
- if (status != nfs_ok)
- goto out_put_access;
- nf->nf_file = open->op_filp;
- open->op_filp = NULL;
- trace_nfsd_file_create(rqstp, access, nf);
- }
+ status = nfsd_file_acquire_opened(rqstp, cur_fh, access,
+ open->op_filp, &nf);
+ if (status != nfs_ok)
+ goto out_put_access;
spin_lock(&fp->fi_lock);
if (!fp->fi_fds[oflag]) {
static void
nfsd4_state_shrinker_worker(struct work_struct *work)
{
- struct delayed_work *dwork = to_delayed_work(work);
- struct nfsd_net *nn = container_of(dwork, struct nfsd_net,
+ struct nfsd_net *nn = container_of(work, struct nfsd_net,
nfsd_shrinker_work);
courtesy_client_reaper(nn);
INIT_LIST_HEAD(&nn->blocked_locks_lru);
INIT_DELAYED_WORK(&nn->laundromat_work, laundromat_main);
- INIT_DELAYED_WORK(&nn->nfsd_shrinker_work, nfsd4_state_shrinker_worker);
+ INIT_WORK(&nn->nfsd_shrinker_work, nfsd4_state_shrinker_worker);
get_net(net);
+ nn->nfsd_client_shrinker.scan_objects = nfsd4_state_shrinker_scan;
+ nn->nfsd_client_shrinker.count_objects = nfsd4_state_shrinker_count;
+ nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS;
+
+ if (register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client"))
+ goto err_shrinker;
return 0;
+err_shrinker:
+ put_net(net);
+ kfree(nn->sessionid_hashtbl);
err_sessionid:
kfree(nn->unconf_id_hashtbl);
err_unconf_id:
struct list_head *pos, *next, reaplist;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ unregister_shrinker(&nn->nfsd_client_shrinker);
+ cancel_work(&nn->nfsd_shrinker_work);
cancel_delayed_work_sync(&nn->laundromat_work);
locks_end_grace(&nn->nfsd4_manager);
argp->rqstp->rq_cachetype = cachethis ? RC_REPLBUFF : RC_NOCACHE;
if (readcount > 1 || max_reply > PAGE_SIZE - auth_slack)
- __clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags);
+ clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags);
return true;
}
case nfserr_noent:
xdr_truncate_encode(xdr, start_offset);
goto skip_entry;
+ case nfserr_jukebox:
+ /*
+ * The pseudoroot should only display dentries that lead to
+ * exports. If we get EJUKEBOX here, then we can't tell whether
+ * this entry should be included. Just fail the whole READDIR
+ * with NFS4ERR_DELAY in that case, and hope that the situation
+ * will resolve itself by the client's next attempt.
+ */
+ if (cd->rd_fhp->fh_export->ex_flags & NFSEXP_V4ROOT)
+ goto fail;
+ fallthrough;
default:
/*
* If the client requested the RDATTR_ERROR attribute,
goto out_idmap_error;
nn->nfsd_versions = NULL;
nn->nfsd4_minorversions = NULL;
- retval = nfsd4_init_leases_net(nn);
- if (retval)
- goto out_drc_error;
+ nfsd4_init_leases_net(nn);
retval = nfsd_reply_cache_init(nn);
if (retval)
goto out_cache_error;
return 0;
out_cache_error:
- nfsd4_leases_net_shutdown(nn);
-out_drc_error:
nfsd_idmap_shutdown(net);
out_idmap_error:
nfsd_export_shutdown(net);
nfsd_idmap_shutdown(net);
nfsd_export_shutdown(net);
nfsd_netns_free_versions(net_generic(net, nfsd_net_id));
- nfsd4_leases_net_shutdown(nn);
}
static struct pernet_operations nfsd_net_ops = {
extern void nfsd4_ssc_init_umount_work(struct nfsd_net *nn);
#endif
-extern int nfsd4_init_leases_net(struct nfsd_net *nn);
-extern void nfsd4_leases_net_shutdown(struct nfsd_net *nn);
+extern void nfsd4_init_leases_net(struct nfsd_net *nn);
#else /* CONFIG_NFSD_V4 */
static inline int nfsd4_is_junction(struct dentry *dentry)
return 0;
}
-static inline int nfsd4_init_leases_net(struct nfsd_net *nn) { return 0; };
-static inline void nfsd4_leases_net_shutdown(struct nfsd_net *nn) {};
+static inline void nfsd4_init_leases_net(struct nfsd_net *nn) { };
#define register_cld_notifier() 0
#define unregister_cld_notifier() do { } while(0)
if (resp->status == nfs_ok)
resp->status = fh_getattr(&resp->fh, &resp->stat);
else if (resp->status == nfserr_jukebox)
- __set_bit(RQ_DROPME, &rqstp->rq_flags);
+ set_bit(RQ_DROPME, &rqstp->rq_flags);
return rpc_success;
}
if (resp->status == nfs_ok)
resp->status = fh_getattr(&resp->fh, &resp->stat);
else if (resp->status == nfserr_jukebox)
- __set_bit(RQ_DROPME, &rqstp->rq_flags);
+ set_bit(RQ_DROPME, &rqstp->rq_flags);
return rpc_success;
}
{
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
- nfsd_file_cache_shutdown_net(net);
nfs4_state_shutdown_net(net);
+ nfsd_file_cache_shutdown_net(net);
if (nn->lockd_up) {
lockd_down(net);
nn->lockd_up = false;
)
);
-TRACE_EVENT(nfsd_file_create,
- TP_PROTO(
- const struct svc_rqst *rqstp,
- unsigned int may_flags,
- const struct nfsd_file *nf
- ),
-
- TP_ARGS(rqstp, may_flags, nf),
-
- TP_STRUCT__entry(
- __field(const void *, nf_inode)
- __field(const void *, nf_file)
- __field(unsigned long, may_flags)
- __field(unsigned long, nf_flags)
- __field(unsigned long, nf_may)
- __field(unsigned int, nf_ref)
- __field(u32, xid)
- ),
-
- TP_fast_assign(
- __entry->nf_inode = nf->nf_inode;
- __entry->nf_file = nf->nf_file;
- __entry->may_flags = may_flags;
- __entry->nf_flags = nf->nf_flags;
- __entry->nf_may = nf->nf_may;
- __entry->nf_ref = refcount_read(&nf->nf_ref);
- __entry->xid = be32_to_cpu(rqstp->rq_xid);
- ),
-
- TP_printk("xid=0x%x inode=%p may_flags=%s ref=%u nf_flags=%s nf_may=%s nf_file=%p",
- __entry->xid, __entry->nf_inode,
- show_nfsd_may_flags(__entry->may_flags),
- __entry->nf_ref, show_nf_flags(__entry->nf_flags),
- show_nfsd_may_flags(__entry->nf_may), __entry->nf_file
- )
-);
-
TRACE_EVENT(nfsd_file_insert_err,
TP_PROTO(
const struct svc_rqst *rqstp,
)
);
-TRACE_EVENT(nfsd_file_open,
- TP_PROTO(struct nfsd_file *nf, __be32 status),
+DECLARE_EVENT_CLASS(nfsd_file_open_class,
+ TP_PROTO(const struct nfsd_file *nf, __be32 status),
TP_ARGS(nf, status),
TP_STRUCT__entry(
__field(void *, nf_inode) /* cannot be dereferenced */
__entry->nf_file)
)
+#define DEFINE_NFSD_FILE_OPEN_EVENT(name) \
+DEFINE_EVENT(nfsd_file_open_class, name, \
+ TP_PROTO( \
+ const struct nfsd_file *nf, \
+ __be32 status \
+ ), \
+ TP_ARGS(nf, status))
+
+DEFINE_NFSD_FILE_OPEN_EVENT(nfsd_file_open);
+DEFINE_NFSD_FILE_OPEN_EVENT(nfsd_file_opened);
+
TRACE_EVENT(nfsd_file_is_cached,
TP_PROTO(
const struct inode *inode,
ret = nilfs_btnode_submit_block(btnc, ptr, 0, REQ_OP_READ, &bh,
&submit_ptr);
if (ret) {
- if (ret != -EEXIST)
- return ret;
- goto out_check;
+ if (likely(ret == -EEXIST))
+ goto out_check;
+ if (ret == -ENOENT) {
+ /*
+ * Block address translation failed due to invalid
+ * value of 'ptr'. In this case, return internal code
+ * -EINVAL (broken bmap) to notify bmap layer of fatal
+ * metadata corruption.
+ */
+ ret = -EINVAL;
+ }
+ return ret;
}
if (ra) {
new_valid = ntfs_up_block(sb, min_t(u64, ni->i_valid, new_size));
- ni_lock(ni);
-
truncate_setsize(inode, new_size);
+ ni_lock(ni);
+
down_write(&ni->file.run_lock);
err = attr_set_size(ni, ATTR_DATA, NULL, 0, &ni->file.run, new_size,
&new_valid, ni->mi.sbi->options->prealloc, NULL);
*/
if (new_elen <= (last_ext->extLength & UDF_EXTENT_LENGTH_MASK))
return;
- added_bytes = (last_ext->extLength & UDF_EXTENT_LENGTH_MASK) - new_elen;
+ added_bytes = new_elen - (last_ext->extLength & UDF_EXTENT_LENGTH_MASK);
last_ext->extLength += added_bytes;
UDF_I(inode)->i_lenExtents += added_bytes;
struct kernel_lb_addr eloc, tmpeloc;
int c = 1;
loff_t lbcount = 0, b_off = 0;
- udf_pblk_t newblocknum, newblock;
+ udf_pblk_t newblocknum, newblock = 0;
sector_t offset = 0;
int8_t etype;
struct udf_inode_info *iinfo = UDF_I(inode);
ret = udf_do_extend_file(inode, &prev_epos, laarr, hole_len);
if (ret < 0) {
*err = ret;
- newblock = 0;
goto out_free;
}
c = 0;
goal, err);
if (!newblocknum) {
*err = -ENOSPC;
- newblock = 0;
goto out_free;
}
if (isBeyondEOF)
return ctx->features & UFFD_FEATURE_INITIALIZED;
}
+static void userfaultfd_set_vm_flags(struct vm_area_struct *vma,
+ vm_flags_t flags)
+{
+ const bool uffd_wp_changed = (vma->vm_flags ^ flags) & VM_UFFD_WP;
+
+ vma->vm_flags = flags;
+ /*
+ * For shared mappings, we want to enable writenotify while
+ * userfaultfd-wp is enabled (see vma_wants_writenotify()). We'll simply
+ * recalculate vma->vm_page_prot whenever userfaultfd-wp changes.
+ */
+ if ((vma->vm_flags & VM_SHARED) && uffd_wp_changed)
+ vma_set_page_prot(vma);
+}
+
static int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode,
int wake_flags, void *key)
{
for_each_vma(vmi, vma) {
if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) {
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
- vma->vm_flags &= ~__VM_UFFD_FLAGS;
+ userfaultfd_set_vm_flags(vma,
+ vma->vm_flags & ~__VM_UFFD_FLAGS);
}
}
mmap_write_unlock(mm);
octx = vma->vm_userfaultfd_ctx.ctx;
if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) {
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
- vma->vm_flags &= ~__VM_UFFD_FLAGS;
+ userfaultfd_set_vm_flags(vma, vma->vm_flags & ~__VM_UFFD_FLAGS);
return 0;
}
} else {
/* Drop uffd context if remap feature not enabled */
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
- vma->vm_flags &= ~__VM_UFFD_FLAGS;
+ userfaultfd_set_vm_flags(vma, vma->vm_flags & ~__VM_UFFD_FLAGS);
}
}
prev = vma;
}
- vma->vm_flags = new_flags;
+ userfaultfd_set_vm_flags(vma, new_flags);
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
}
mmap_write_unlock(mm);
* the next vma was merged into the current one and
* the current one has not been updated yet.
*/
- vma->vm_flags = new_flags;
+ userfaultfd_set_vm_flags(vma, new_flags);
vma->vm_userfaultfd_ctx.ctx = ctx;
if (is_vm_hugetlb_page(vma) && uffd_disable_huge_pmd_share(vma))
* the next vma was merged into the current one and
* the current one has not been updated yet.
*/
- vma->vm_flags = new_flags;
+ userfaultfd_set_vm_flags(vma, new_flags);
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
skip:
const unsigned int *limits,
unsigned long long leaf_blocks)
{
- unsigned long long node_blocks = limits[1];
+ /*
+ * The root btree block can have fewer than minrecs pointers in it
+ * because the tree might not be big enough to require that amount of
+ * fanout. Hence it has a minimum size of 2 pointers, not limits[1].
+ */
+ unsigned long long node_blocks = 2;
unsigned long long blocks_left = leaf_blocks - 1;
unsigned int height = 1;
*
*/
busyp->bno = fend;
+ busyp->length = bend - fend;
} else if (bbno < fbno) {
/*
* Case 8:
struct xfs_inodegc, work);
struct llist_node *node = llist_del_all(&gc->list);
struct xfs_inode *ip, *n;
+ unsigned int nofs_flag;
WRITE_ONCE(gc->items, 0);
if (!node)
return;
+ /*
+ * We can allocate memory here while doing writeback on behalf of
+ * memory reclaim. To avoid memory allocation deadlocks set the
+ * task-wide nofs context for the following operations.
+ */
+ nofs_flag = memalloc_nofs_save();
+
ip = llist_entry(node, struct xfs_inode, i_gclist);
trace_xfs_inodegc_worker(ip->i_mount, READ_ONCE(gc->shrinker_hits));
xfs_iflags_set(ip, XFS_INACTIVATING);
xfs_inodegc_inactivate(ip);
}
+
+ memalloc_nofs_restore(nofs_flag);
}
/*
static int
xfs_bulk_ireq_setup(
struct xfs_mount *mp,
- struct xfs_bulk_ireq *hdr,
+ const struct xfs_bulk_ireq *hdr,
struct xfs_ibulk *breq,
void __user *ubuffer)
{
switch (hdr->ino) {
case XFS_BULK_IREQ_SPECIAL_ROOT:
- hdr->ino = mp->m_sb.sb_rootino;
+ breq->startino = mp->m_sb.sb_rootino;
break;
default:
return -EINVAL;
return true;
}
-const struct iomap_page_ops xfs_iomap_page_ops = {
+static const struct iomap_page_ops xfs_iomap_page_ops = {
.iomap_valid = xfs_iomap_valid,
};
while (1) {
struct xfs_dquot *batch[XFS_DQ_LOOKUP_BATCH];
- int error = 0;
+ int error;
int i;
mutex_lock(&qi->qi_tree_lock);
goto convert;
}
- ASSERT(cmap->br_startoff > imap->br_startoff);
-
/* Allocate the entire reservation as unwritten blocks. */
nimaps = 1;
error = xfs_bmapi_write(tp, ip, imap->br_startoff, imap->br_blockcount,
data_size = zonefs_check_zone_condition(inode, zone,
false, false);
}
+ } else if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_RO &&
+ data_size > isize) {
+ /* Do not expose garbage data */
+ data_size = isize;
}
/*
ret = submit_bio_wait(bio);
+ /*
+ * If the file zone was written underneath the file system, the zone
+ * write pointer may not be where we expect it to be, but the zone
+ * append write can still succeed. So check manually that we wrote where
+ * we intended to, that is, at zi->i_wpoffset.
+ */
+ if (!ret) {
+ sector_t wpsector =
+ zi->i_zsector + (zi->i_wpoffset >> SECTOR_SHIFT);
+
+ if (bio->bi_iter.bi_sector != wpsector) {
+ zonefs_warn(inode->i_sb,
+ "Corrupted write pointer %llu for zone at %llu\n",
+ wpsector, zi->i_zsector);
+ ret = -EIO;
+ }
+ }
+
zonefs_file_write_dio_end_io(iocb, size, ret, 0);
trace_zonefs_file_dio_append(inode, size, ret);
u32 hardware_id:1;
u32 bus_address:1;
u32 platform_id:1;
- u32 reserved:29;
+ u32 backlight:1;
+ u32 reserved:28;
};
struct acpi_device_pnp {
#include <linux/types.h>
+struct drm_atomic_state;
struct drm_crtc;
struct drm_framebuffer;
struct drm_modeset_acquire_ctx;
extern void bio_set_pages_dirty(struct bio *bio);
extern void bio_check_pages_dirty(struct bio *bio);
+extern void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter,
+ struct bio *src, struct bvec_iter *src_iter);
extern void bio_copy_data(struct bio *dst, struct bio *src);
extern void bio_free_pages(struct bio *bio);
void guard_bio_eod(struct bio *bio);
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);
/* returns the length of the identifier or a negative errno: */
int (*get_unique_id)(struct gendisk *disk, u8 id[16],
enum blk_unique_id id_type);
QCA_HDR_MGMT_COMMAND_LEN + \
QCA_HDR_MGMT_DATA1_LEN)
-#define QCA_HDR_MGMT_DATA2_LEN 12 /* Other 12 byte for the mdio data */
-#define QCA_HDR_MGMT_PADDING_LEN 34 /* Padding to reach the min Ethernet packet */
+#define QCA_HDR_MGMT_DATA2_LEN 28 /* Other 28 byte for the mdio data */
+#define QCA_HDR_MGMT_PADDING_LEN 18 /* Padding to reach the min Ethernet packet */
#define QCA_HDR_MGMT_PKT_LEN (QCA_HDR_MGMT_HEADER_LEN + \
QCA_HDR_LEN + \
* Dumping its extra ELF program headers includes all the other information
* a debugger needs to easily find how the gate DSO was being used.
*/
-extern Elf_Half elf_core_extra_phdrs(void);
+extern Elf_Half elf_core_extra_phdrs(struct coredump_params *cprm);
extern int
elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset);
extern int
elf_core_write_extra_data(struct coredump_params *cprm);
-extern size_t elf_core_extra_data_size(void);
+extern size_t elf_core_extra_data_size(struct coredump_params *cprm);
#else
-static inline Elf_Half elf_core_extra_phdrs(void)
+static inline Elf_Half elf_core_extra_phdrs(struct coredump_params *cprm)
{
return 0;
}
return 1;
}
-static inline size_t elf_core_extra_data_size(void)
+static inline size_t elf_core_extra_data_size(struct coredump_params *cprm)
{
return 0;
}
int state; /* state of grant or error if -ve */
unsigned int debug_id;
} afs;
+ struct {
+ struct inode *inode;
+ } ceph;
} fl_u;
} __randomize_layout;
struct {
spinlock_t completion_lock;
+ bool poll_multi_queue;
+
/*
* ->iopoll_list is protected by the ctx->uring_lock for
* io_uring instances that don't use IORING_SETUP_SQPOLL.
*/
struct io_wq_work_list iopoll_list;
struct io_hash_table cancel_table;
- bool poll_multi_queue;
struct llist_head work_llist;
};
enum {
+ MLX5_VPORT_CVLAN_INSERT_WHEN_NO_CVLAN = 0x1,
+ MLX5_VPORT_CVLAN_INSERT_ALWAYS = 0x3,
+};
+
+enum {
MLX5_L3_PROT_TYPE_IPV4 = 0,
MLX5_L3_PROT_TYPE_IPV6 = 1,
};
struct mlx5_cmd_debug dbg;
struct cmd_msg_cache cache[MLX5_NUM_COMMAND_CACHES];
int checksum_disabled;
- struct mlx5_cmd_stats *stats;
+ struct mlx5_cmd_stats stats[MLX5_CMD_OP_MAX];
};
struct mlx5_cmd_mailbox {
u8 vport_svlan_insert[0x1];
u8 vport_cvlan_insert_if_not_exist[0x1];
u8 vport_cvlan_insert_overwrite[0x1];
- u8 reserved_at_5[0x2];
+ u8 reserved_at_5[0x1];
+ u8 vport_cvlan_insert_always[0x1];
u8 esw_shared_ingress_acl[0x1];
u8 esw_uplink_ingress_acl[0x1];
u8 root_ft_on_other_esw[0x1];
__folio_put(folio);
}
-/**
- * release_pages - release an array of pages or folios
+/*
+ * union release_pages_arg - an array of pages or folios
*
- * This just releases a simple array of multiple pages, and
+ * release_pages() releases a simple array of multiple pages, and
* accepts various different forms of said page array: either
* a regular old boring array of pages, an array of folios, or
* an array of encoded page pointers.
* Not using anon_vma_name because it generates a warning if mmap_lock
* is not held, which might be the case here.
*/
- if (!vma->vm_file)
- anon_vma_name_put(vma->anon_name);
+ anon_vma_name_put(vma->anon_name);
}
static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1,
/*
* For private and shared anonymous mappings, a pointer to a null
* terminated string containing the name given to the vma, or NULL if
- * unnamed. Serialized by mmap_sem. Use anon_vma_name to access.
+ * unnamed. Serialized by mmap_lock. Use anon_vma_name to access.
*/
struct anon_vma_name *anon_name;
#endif
#define __LINUX_MTD_SPI_NOR_H
#include <linux/bitops.h>
-#include <linux/mtd/cfi.h>
#include <linux/mtd/mtd.h>
#include <linux/spi/spi-mem.h>
};
/* Max range where every element is added/deleted in one step */
-#define IPSET_MAX_RANGE (1<<20)
+#define IPSET_MAX_RANGE (1<<14)
/* The max revision number supported by any set type + 1 */
#define IPSET_REVISION_MAX 9
*
* You can also use this function if you're holding a lock that prevents
* pages being frozen & removed; eg the i_pages lock for the page cache
- * or the mmap_sem or page table lock for page tables. In this case,
+ * or the mmap_lock or page table lock for page tables. In this case,
* it will always succeed, and you could have used a plain folio_get(),
* but it's sometimes more convenient to have a common function called
* from both locked and RCU-protected contexts.
* whether to advertise lower-speed modes for that interface. It is
* assumed that if a rate matching mode is supported on an interface,
* then that interface's rate can be adapted to all slower link speeds
- * supported by the phy. If iface is %PHY_INTERFACE_MODE_NA, and the phy
- * supports any kind of rate matching for any interface, then it must
- * return that rate matching mode (preferring %RATE_MATCH_PAUSE to
- * %RATE_MATCH_CRS). If the interface is not supported, this should
+ * supported by the phy. If the interface is not supported, this should
* return %RATE_MATCH_NONE.
*/
int (*get_rate_matching)(struct phy_device *phydev,
--- /dev/null
+/*
+ * Copyright (C) 2000 Jens Axboe <axboe@suse.de>
+ * Copyright (C) 2001-2004 Peter Osterlund <petero2@telia.com>
+ *
+ * May be copied or modified under the terms of the GNU General Public
+ * License. See linux/COPYING for more information.
+ *
+ * Packet writing layer for ATAPI and SCSI CD-R, CD-RW, DVD-R, and
+ * DVD-RW devices.
+ *
+ */
+#ifndef __PKTCDVD_H
+#define __PKTCDVD_H
+
+#include <linux/blkdev.h>
+#include <linux/completion.h>
+#include <linux/cdrom.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
+#include <linux/mempool.h>
+#include <uapi/linux/pktcdvd.h>
+
+/* default bio write queue congestion marks */
+#define PKT_WRITE_CONGESTION_ON 10000
+#define PKT_WRITE_CONGESTION_OFF 9000
+
+
+struct packet_settings
+{
+ __u32 size; /* packet size in (512 byte) sectors */
+ __u8 fp; /* fixed packets */
+ __u8 link_loss; /* the rest is specified
+ * as per Mt Fuji */
+ __u8 write_type;
+ __u8 track_mode;
+ __u8 block_mode;
+};
+
+/*
+ * Very crude stats for now
+ */
+struct packet_stats
+{
+ unsigned long pkt_started;
+ unsigned long pkt_ended;
+ unsigned long secs_w;
+ unsigned long secs_rg;
+ unsigned long secs_r;
+};
+
+struct packet_cdrw
+{
+ struct list_head pkt_free_list;
+ struct list_head pkt_active_list;
+ spinlock_t active_list_lock; /* Serialize access to pkt_active_list */
+ struct task_struct *thread;
+ atomic_t pending_bios;
+};
+
+/*
+ * Switch to high speed reading after reading this many kilobytes
+ * with no interspersed writes.
+ */
+#define HI_SPEED_SWITCH 512
+
+struct packet_iosched
+{
+ atomic_t attention; /* Set to non-zero when queue processing is needed */
+ int writing; /* Non-zero when writing, zero when reading */
+ spinlock_t lock; /* Protecting read/write queue manipulations */
+ struct bio_list read_queue;
+ struct bio_list write_queue;
+ sector_t last_write; /* The sector where the last write ended */
+ int successive_reads;
+};
+
+/*
+ * 32 buffers of 2048 bytes
+ */
+#if (PAGE_SIZE % CD_FRAMESIZE) != 0
+#error "PAGE_SIZE must be a multiple of CD_FRAMESIZE"
+#endif
+#define PACKET_MAX_SIZE 128
+#define FRAMES_PER_PAGE (PAGE_SIZE / CD_FRAMESIZE)
+#define PACKET_MAX_SECTORS (PACKET_MAX_SIZE * CD_FRAMESIZE >> 9)
+
+enum packet_data_state {
+ PACKET_IDLE_STATE, /* Not used at the moment */
+ PACKET_WAITING_STATE, /* Waiting for more bios to arrive, so */
+ /* we don't have to do as much */
+ /* data gathering */
+ PACKET_READ_WAIT_STATE, /* Waiting for reads to fill in holes */
+ PACKET_WRITE_WAIT_STATE, /* Waiting for the write to complete */
+ PACKET_RECOVERY_STATE, /* Recover after read/write errors */
+ PACKET_FINISHED_STATE, /* After write has finished */
+
+ PACKET_NUM_STATES /* Number of possible states */
+};
+
+/*
+ * Information needed for writing a single packet
+ */
+struct pktcdvd_device;
+
+struct packet_data
+{
+ struct list_head list;
+
+ spinlock_t lock; /* Lock protecting state transitions and */
+ /* orig_bios list */
+
+ struct bio_list orig_bios; /* Original bios passed to pkt_make_request */
+ /* that will be handled by this packet */
+ int write_size; /* Total size of all bios in the orig_bios */
+ /* list, measured in number of frames */
+
+ struct bio *w_bio; /* The bio we will send to the real CD */
+ /* device once we have all data for the */
+ /* packet we are going to write */
+ sector_t sector; /* First sector in this packet */
+ int frames; /* Number of frames in this packet */
+
+ enum packet_data_state state; /* Current state */
+ atomic_t run_sm; /* Incremented whenever the state */
+ /* machine needs to be run */
+ long sleep_time; /* Set this to non-zero to make the state */
+ /* machine run after this many jiffies. */
+
+ atomic_t io_wait; /* Number of pending IO operations */
+ atomic_t io_errors; /* Number of read/write errors during IO */
+
+ struct bio *r_bios[PACKET_MAX_SIZE]; /* bios to use during data gathering */
+ struct page *pages[PACKET_MAX_SIZE / FRAMES_PER_PAGE];
+
+ int cache_valid; /* If non-zero, the data for the zone defined */
+ /* by the sector variable is completely cached */
+ /* in the pages[] vector. */
+
+ int id; /* ID number for debugging */
+ struct pktcdvd_device *pd;
+};
+
+struct pkt_rb_node {
+ struct rb_node rb_node;
+ struct bio *bio;
+};
+
+struct packet_stacked_data
+{
+ struct bio *bio; /* Original read request bio */
+ struct pktcdvd_device *pd;
+};
+#define PSD_POOL_SIZE 64
+
+struct pktcdvd_device
+{
+ struct block_device *bdev; /* dev attached */
+ dev_t pkt_dev; /* our dev */
+ char name[20];
+ struct packet_settings settings;
+ struct packet_stats stats;
+ int refcnt; /* Open count */
+ int write_speed; /* current write speed, kB/s */
+ int read_speed; /* current read speed, kB/s */
+ unsigned long offset; /* start offset */
+ __u8 mode_offset; /* 0 / 8 */
+ __u8 type;
+ unsigned long flags;
+ __u16 mmc3_profile;
+ __u32 nwa; /* next writable address */
+ __u32 lra; /* last recorded address */
+ struct packet_cdrw cdrw;
+ wait_queue_head_t wqueue;
+
+ spinlock_t lock; /* Serialize access to bio_queue */
+ struct rb_root bio_queue; /* Work queue of bios we need to handle */
+ int bio_queue_size; /* Number of nodes in bio_queue */
+ bool congested; /* Someone is waiting for bio_queue_size
+ * to drop. */
+ sector_t current_sector; /* Keep track of where the elevator is */
+ atomic_t scan_queue; /* Set to non-zero when pkt_handle_queue */
+ /* needs to be run. */
+ mempool_t rb_pool; /* mempool for pkt_rb_node allocations */
+
+ struct packet_iosched iosched;
+ struct gendisk *disk;
+
+ int write_congestion_off;
+ int write_congestion_on;
+
+ struct device *dev; /* sysfs pktcdvd[0-7] dev */
+
+ struct dentry *dfs_d_root; /* debugfs: devname directory */
+ struct dentry *dfs_f_info; /* debugfs: info file */
+};
+
+#endif /* __PKTCDVD_H */
SIMATIC_IPC_IPC477E = 0x00000A02,
SIMATIC_IPC_IPC127E = 0x00000D01,
SIMATIC_IPC_IPC227G = 0x00000F01,
- SIMATIC_IPC_IPC427G = 0x00001001,
+ SIMATIC_IPC_IPCBX_39A = 0x00001001,
+ SIMATIC_IPC_IPCPX_39A = 0x00001002,
};
static inline u32 simatic_ipc_get_station_id(u8 *data, int max_len)
char __user *, size_t);
extern int rpc_queue_upcall(struct rpc_pipe *, struct rpc_pipe_msg *);
+/* returns true if the msg is in-flight, i.e., already eaten by the peer */
+static inline bool rpc_msg_is_inflight(const struct rpc_pipe_msg *msg) {
+ return (msg->copied != 0 && list_empty(&msg->list));
+}
+
struct rpc_clnt;
extern struct dentry *rpc_create_client_dir(struct dentry *, const char *, struct rpc_clnt *);
extern int rpc_remove_client_dir(struct rpc_clnt *);
* The loop below will unmap these fields if the log is larger than
* one page, so save them here for reference:
*/
- count = READ_ONCE(event->count);
- event_type = READ_ONCE(event->event_type);
+ count = event->count;
+ event_type = event->event_type;
/* Verify that it's the log header */
if (event_header->pcr_idx != 0 ||
struct sock;
struct socket;
struct rxrpc_call;
+enum rxrpc_abort_reason;
enum rxrpc_interruptibility {
RXRPC_INTERRUPTIBLE, /* Call is interruptible */
int rxrpc_kernel_recv_data(struct socket *, struct rxrpc_call *,
struct iov_iter *, size_t *, bool, u32 *, u16 *);
bool rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *,
- u32, int, const char *);
+ u32, int, enum rxrpc_abort_reason);
void rxrpc_kernel_end_call(struct socket *, struct rxrpc_call *);
void rxrpc_kernel_get_peer(struct socket *, struct rxrpc_call *,
struct sockaddr_rxrpc *);
struct hlist_node node;
/* List of sockets hashed to this bucket */
struct hlist_head owners;
+ /* bhash has twsk in owners, but bhash2 has twsk in
+ * deathrow not to add a member in struct sock_common.
+ */
+ struct hlist_head deathrow;
};
static inline struct net *ib_net(const struct inet_bind_bucket *ib)
u32 tw_priority;
struct timer_list tw_timer;
struct inet_bind_bucket *tw_tb;
+ struct inet_bind2_bucket *tw_tb2;
+ struct hlist_node tw_bind2_node;
};
#define tw_tclass tw_tos
+#define twsk_for_each_bound_bhash2(__tw, list) \
+ hlist_for_each_entry(__tw, list, tw_bind2_node)
+
static inline struct inet_timewait_sock *inet_twsk(const struct sock *sk)
{
return (struct inet_timewait_sock *)sk;
/**
* struct nft_set_desc - description of set elements
*
+ * @ktype: key type
* @klen: key length
+ * @dtype: data type
* @dlen: data length
+ * @objtype: object type
+ * @flags: flags
* @size: number of set elements
+ * @policy: set policy
+ * @gc_int: garbage collector interval
* @field_len: length of each field in concatenation, bytes
* @field_count: number of concatenated fields in element
* @expr: set must support for expressions
*/
struct nft_set_desc {
+ u32 ktype;
unsigned int klen;
+ u32 dtype;
unsigned int dlen;
+ u32 objtype;
unsigned int size;
+ u32 policy;
+ u32 gc_int;
+ u64 timeout;
u8 field_len[NFT_REG32_COUNT];
u8 field_count;
bool expr;
static inline unsigned long nft_set_gc_interval(const struct nft_set *set)
{
- return set->gc_int ? msecs_to_jiffies(set->gc_int) : HZ;
+ u32 gc_int = READ_ONCE(set->gc_int);
+
+ return gc_int ? msecs_to_jiffies(gc_int) : HZ;
}
/**
struct nft_trans_set {
struct nft_set *set;
u32 set_id;
+ u32 gc_int;
+ u64 timeout;
+ bool update;
bool bound;
};
(((struct nft_trans_set *)trans->data)->set_id)
#define nft_trans_set_bound(trans) \
(((struct nft_trans_set *)trans->data)->bound)
+#define nft_trans_set_update(trans) \
+ (((struct nft_trans_set *)trans->data)->update)
+#define nft_trans_set_timeout(trans) \
+ (((struct nft_trans_set *)trans->data)->timeout)
+#define nft_trans_set_gc_int(trans) \
+ (((struct nft_trans_set *)trans->data)->gc_int)
struct nft_trans_chain {
bool update;
return tp->classify(skb, tp, res);
}
+#endif /* CONFIG_NET_CLS */
+
static inline void tc_wrapper_init(void)
{
#ifdef CONFIG_X86
#endif
}
-#endif /* CONFIG_NET_CLS */
-
#else
#define TC_INDIRECT_SCOPE static
ISCSI_SESSION_FREE,
};
+enum {
+ ISCSI_SESSION_TARGET_UNBOUND,
+ ISCSI_SESSION_TARGET_ALLOCATED,
+ ISCSI_SESSION_TARGET_SCANNED,
+ ISCSI_SESSION_TARGET_UNBINDING,
+ ISCSI_SESSION_TARGET_MAX,
+};
+
#define ISCSI_MAX_TARGET -1
struct iscsi_cls_session {
*/
pid_t creator;
int state;
+ int target_state; /* session target bind state */
int sid; /* session id */
void *dd_data; /* LLD private data */
struct device dev; /* sysfs transport/container device */
EM( FLUSH_DELALLOC_WAIT, "FLUSH_DELALLOC_WAIT") \
EM( FLUSH_DELALLOC_FULL, "FLUSH_DELALLOC_FULL") \
EM( FLUSH_DELAYED_REFS_NR, "FLUSH_DELAYED_REFS_NR") \
- EM( FLUSH_DELAYED_REFS, "FLUSH_ELAYED_REFS") \
+ EM( FLUSH_DELAYED_REFS, "FLUSH_DELAYED_REFS") \
EM( ALLOC_CHUNK, "ALLOC_CHUNK") \
EM( ALLOC_CHUNK_FORCE, "ALLOC_CHUNK_FORCE") \
EM( RUN_DELAYED_IPUTS, "RUN_DELAYED_IPUTS") \
/*
* Declare tracing information enums and their string mappings for display.
*/
+#define rxrpc_abort_reasons \
+ /* AFS errors */ \
+ EM(afs_abort_general_error, "afs-error") \
+ EM(afs_abort_interrupted, "afs-intr") \
+ EM(afs_abort_oom, "afs-oom") \
+ EM(afs_abort_op_not_supported, "afs-op-notsupp") \
+ EM(afs_abort_probeuuid_negative, "afs-probeuuid-neg") \
+ EM(afs_abort_send_data_error, "afs-send-data") \
+ EM(afs_abort_unmarshal_error, "afs-unmarshal") \
+ /* rxperf errors */ \
+ EM(rxperf_abort_general_error, "rxperf-error") \
+ EM(rxperf_abort_oom, "rxperf-oom") \
+ EM(rxperf_abort_op_not_supported, "rxperf-op-notsupp") \
+ EM(rxperf_abort_unmarshal_error, "rxperf-unmarshal") \
+ /* RxKAD security errors */ \
+ EM(rxkad_abort_1_short_check, "rxkad1-short-check") \
+ EM(rxkad_abort_1_short_data, "rxkad1-short-data") \
+ EM(rxkad_abort_1_short_encdata, "rxkad1-short-encdata") \
+ EM(rxkad_abort_1_short_header, "rxkad1-short-hdr") \
+ EM(rxkad_abort_2_short_check, "rxkad2-short-check") \
+ EM(rxkad_abort_2_short_data, "rxkad2-short-data") \
+ EM(rxkad_abort_2_short_header, "rxkad2-short-hdr") \
+ EM(rxkad_abort_2_short_len, "rxkad2-short-len") \
+ EM(rxkad_abort_bad_checksum, "rxkad2-bad-cksum") \
+ EM(rxkad_abort_chall_key_expired, "rxkad-chall-key-exp") \
+ EM(rxkad_abort_chall_level, "rxkad-chall-level") \
+ EM(rxkad_abort_chall_no_key, "rxkad-chall-nokey") \
+ EM(rxkad_abort_chall_short, "rxkad-chall-short") \
+ EM(rxkad_abort_chall_version, "rxkad-chall-version") \
+ EM(rxkad_abort_resp_bad_callid, "rxkad-resp-bad-callid") \
+ EM(rxkad_abort_resp_bad_checksum, "rxkad-resp-bad-cksum") \
+ EM(rxkad_abort_resp_bad_param, "rxkad-resp-bad-param") \
+ EM(rxkad_abort_resp_call_ctr, "rxkad-resp-call-ctr") \
+ EM(rxkad_abort_resp_call_state, "rxkad-resp-call-state") \
+ EM(rxkad_abort_resp_key_expired, "rxkad-resp-key-exp") \
+ EM(rxkad_abort_resp_key_rejected, "rxkad-resp-key-rej") \
+ EM(rxkad_abort_resp_level, "rxkad-resp-level") \
+ EM(rxkad_abort_resp_nokey, "rxkad-resp-nokey") \
+ EM(rxkad_abort_resp_ooseq, "rxkad-resp-ooseq") \
+ EM(rxkad_abort_resp_short, "rxkad-resp-short") \
+ EM(rxkad_abort_resp_short_tkt, "rxkad-resp-short-tkt") \
+ EM(rxkad_abort_resp_tkt_aname, "rxkad-resp-tk-aname") \
+ EM(rxkad_abort_resp_tkt_expired, "rxkad-resp-tk-exp") \
+ EM(rxkad_abort_resp_tkt_future, "rxkad-resp-tk-future") \
+ EM(rxkad_abort_resp_tkt_inst, "rxkad-resp-tk-inst") \
+ EM(rxkad_abort_resp_tkt_len, "rxkad-resp-tk-len") \
+ EM(rxkad_abort_resp_tkt_realm, "rxkad-resp-tk-realm") \
+ EM(rxkad_abort_resp_tkt_short, "rxkad-resp-tk-short") \
+ EM(rxkad_abort_resp_tkt_sinst, "rxkad-resp-tk-sinst") \
+ EM(rxkad_abort_resp_tkt_sname, "rxkad-resp-tk-sname") \
+ EM(rxkad_abort_resp_unknown_tkt, "rxkad-resp-unknown-tkt") \
+ EM(rxkad_abort_resp_version, "rxkad-resp-version") \
+ /* rxrpc errors */ \
+ EM(rxrpc_abort_call_improper_term, "call-improper-term") \
+ EM(rxrpc_abort_call_reset, "call-reset") \
+ EM(rxrpc_abort_call_sendmsg, "call-sendmsg") \
+ EM(rxrpc_abort_call_sock_release, "call-sock-rel") \
+ EM(rxrpc_abort_call_sock_release_tba, "call-sock-rel-tba") \
+ EM(rxrpc_abort_call_timeout, "call-timeout") \
+ EM(rxrpc_abort_no_service_key, "no-serv-key") \
+ EM(rxrpc_abort_nomem, "nomem") \
+ EM(rxrpc_abort_service_not_offered, "serv-not-offered") \
+ EM(rxrpc_abort_shut_down, "shut-down") \
+ EM(rxrpc_abort_unsupported_security, "unsup-sec") \
+ EM(rxrpc_badmsg_bad_abort, "bad-abort") \
+ EM(rxrpc_badmsg_bad_jumbo, "bad-jumbo") \
+ EM(rxrpc_badmsg_short_ack, "short-ack") \
+ EM(rxrpc_badmsg_short_ack_info, "short-ack-info") \
+ EM(rxrpc_badmsg_short_hdr, "short-hdr") \
+ EM(rxrpc_badmsg_unsupported_packet, "unsup-pkt") \
+ EM(rxrpc_badmsg_zero_call, "zero-call") \
+ EM(rxrpc_badmsg_zero_seq, "zero-seq") \
+ EM(rxrpc_badmsg_zero_service, "zero-service") \
+ EM(rxrpc_eproto_ackr_outside_window, "ackr-out-win") \
+ EM(rxrpc_eproto_ackr_sack_overflow, "ackr-sack-over") \
+ EM(rxrpc_eproto_ackr_short_sack, "ackr-short-sack") \
+ EM(rxrpc_eproto_ackr_zero, "ackr-zero") \
+ EM(rxrpc_eproto_bad_upgrade, "bad-upgrade") \
+ EM(rxrpc_eproto_data_after_last, "data-after-last") \
+ EM(rxrpc_eproto_different_last, "diff-last") \
+ EM(rxrpc_eproto_early_reply, "early-reply") \
+ EM(rxrpc_eproto_improper_term, "improper-term") \
+ EM(rxrpc_eproto_no_client_call, "no-cl-call") \
+ EM(rxrpc_eproto_no_client_conn, "no-cl-conn") \
+ EM(rxrpc_eproto_no_service_call, "no-sv-call") \
+ EM(rxrpc_eproto_reupgrade, "re-upgrade") \
+ EM(rxrpc_eproto_rxnull_challenge, "rxnull-chall") \
+ EM(rxrpc_eproto_rxnull_response, "rxnull-resp") \
+ EM(rxrpc_eproto_tx_rot_last, "tx-rot-last") \
+ EM(rxrpc_eproto_unexpected_ack, "unex-ack") \
+ EM(rxrpc_eproto_unexpected_ackall, "unex-ackall") \
+ EM(rxrpc_eproto_unexpected_implicit_end, "unex-impl-end") \
+ EM(rxrpc_eproto_unexpected_reply, "unex-reply") \
+ EM(rxrpc_eproto_wrong_security, "wrong-sec") \
+ EM(rxrpc_recvmsg_excess_data, "recvmsg-excess") \
+ EM(rxrpc_recvmsg_short_data, "recvmsg-short") \
+ E_(rxrpc_sendmsg_late_send, "sendmsg-late")
+
#define rxrpc_call_poke_traces \
+ EM(rxrpc_call_poke_abort, "Abort") \
+ EM(rxrpc_call_poke_complete, "Compl") \
EM(rxrpc_call_poke_error, "Error") \
EM(rxrpc_call_poke_idle, "Idle") \
EM(rxrpc_call_poke_start, "Start") \
#define rxrpc_skb_traces \
EM(rxrpc_skb_eaten_by_unshare, "ETN unshare ") \
EM(rxrpc_skb_eaten_by_unshare_nomem, "ETN unshar-nm") \
+ EM(rxrpc_skb_get_conn_secured, "GET conn-secd") \
EM(rxrpc_skb_get_conn_work, "GET conn-work") \
EM(rxrpc_skb_get_local_work, "GET locl-work") \
EM(rxrpc_skb_get_reject_work, "GET rej-work ") \
EM(rxrpc_skb_new_error_report, "NEW error-rpt") \
EM(rxrpc_skb_new_jumbo_subpacket, "NEW jumbo-sub") \
EM(rxrpc_skb_new_unshared, "NEW unshared ") \
+ EM(rxrpc_skb_put_conn_secured, "PUT conn-secd") \
EM(rxrpc_skb_put_conn_work, "PUT conn-work") \
EM(rxrpc_skb_put_error_report, "PUT error-rep") \
EM(rxrpc_skb_put_input, "PUT input ") \
#define rxrpc_peer_traces \
EM(rxrpc_peer_free, "FREE ") \
EM(rxrpc_peer_get_accept, "GET accept ") \
- EM(rxrpc_peer_get_activate_call, "GET act-call") \
EM(rxrpc_peer_get_bundle, "GET bundle ") \
EM(rxrpc_peer_get_client_conn, "GET cln-conn") \
EM(rxrpc_peer_get_input, "GET input ") \
EM(rxrpc_peer_put_bundle, "PUT bundle ") \
EM(rxrpc_peer_put_call, "PUT call ") \
EM(rxrpc_peer_put_conn, "PUT conn ") \
- EM(rxrpc_peer_put_discard_tmp, "PUT disc-tmp") \
EM(rxrpc_peer_put_input, "PUT input ") \
EM(rxrpc_peer_put_input_error, "PUT inpt-err") \
E_(rxrpc_peer_put_keepalive, "PUT keepaliv")
EM(rxrpc_bundle_get_client_call, "GET clt-call") \
EM(rxrpc_bundle_get_client_conn, "GET clt-conn") \
EM(rxrpc_bundle_get_service_conn, "GET svc-conn") \
+ EM(rxrpc_bundle_put_call, "PUT call ") \
EM(rxrpc_bundle_put_conn, "PUT conn ") \
EM(rxrpc_bundle_put_discard, "PUT discard ") \
E_(rxrpc_bundle_new, "NEW ")
EM(rxrpc_conn_get_call_input, "GET inp-call") \
EM(rxrpc_conn_get_conn_input, "GET inp-conn") \
EM(rxrpc_conn_get_idle, "GET idle ") \
- EM(rxrpc_conn_get_poke, "GET poke ") \
+ EM(rxrpc_conn_get_poke_abort, "GET pk-abort") \
+ EM(rxrpc_conn_get_poke_timer, "GET poke ") \
EM(rxrpc_conn_get_service_conn, "GET svc-conn") \
EM(rxrpc_conn_new_client, "NEW client ") \
EM(rxrpc_conn_new_service, "NEW service ") \
EM(rxrpc_conn_put_call, "PUT call ") \
EM(rxrpc_conn_put_call_input, "PUT inp-call") \
EM(rxrpc_conn_put_conn_input, "PUT inp-conn") \
- EM(rxrpc_conn_put_discard, "PUT discard ") \
EM(rxrpc_conn_put_discard_idle, "PUT disc-idl") \
EM(rxrpc_conn_put_local_dead, "PUT loc-dead") \
EM(rxrpc_conn_put_noreuse, "PUT noreuse ") \
EM(rxrpc_conn_put_service_reaped, "PUT svc-reap") \
EM(rxrpc_conn_put_unbundle, "PUT unbundle") \
EM(rxrpc_conn_put_unidle, "PUT unidle ") \
+ EM(rxrpc_conn_put_work, "PUT work ") \
EM(rxrpc_conn_queue_challenge, "QUE chall ") \
EM(rxrpc_conn_queue_retry_work, "QUE retry-wk") \
EM(rxrpc_conn_queue_rx_work, "QUE rx-work ") \
- EM(rxrpc_conn_queue_timer, "QUE timer ") \
EM(rxrpc_conn_see_new_service_conn, "SEE new-svc ") \
EM(rxrpc_conn_see_reap_service, "SEE reap-svc") \
E_(rxrpc_conn_see_work, "SEE work ")
EM(rxrpc_client_chan_activate, "ChActv") \
EM(rxrpc_client_chan_disconnect, "ChDisc") \
EM(rxrpc_client_chan_pass, "ChPass") \
- EM(rxrpc_client_chan_wait_failed, "ChWtFl") \
EM(rxrpc_client_cleanup, "Clean ") \
EM(rxrpc_client_discard, "Discar") \
- EM(rxrpc_client_duplicate, "Duplic") \
EM(rxrpc_client_exposed, "Expose") \
EM(rxrpc_client_replace, "Replac") \
+ EM(rxrpc_client_queue_new_call, "Q-Call") \
EM(rxrpc_client_to_active, "->Actv") \
E_(rxrpc_client_to_idle, "->Idle")
#define rxrpc_call_traces \
+ EM(rxrpc_call_get_io_thread, "GET iothread") \
EM(rxrpc_call_get_input, "GET input ") \
EM(rxrpc_call_get_kernel_service, "GET krnl-srv") \
EM(rxrpc_call_get_notify_socket, "GET notify ") \
EM(rxrpc_call_new_prealloc_service, "NEW prealloc") \
EM(rxrpc_call_put_discard_prealloc, "PUT disc-pre") \
EM(rxrpc_call_put_discard_error, "PUT disc-err") \
+ EM(rxrpc_call_put_io_thread, "PUT iothread") \
EM(rxrpc_call_put_input, "PUT input ") \
EM(rxrpc_call_put_kernel, "PUT kernel ") \
EM(rxrpc_call_put_poke, "PUT poke ") \
EM(rxrpc_call_put_sendmsg, "PUT sendmsg ") \
EM(rxrpc_call_put_unnotify, "PUT unnotify") \
EM(rxrpc_call_put_userid_exists, "PUT u-exists") \
+ EM(rxrpc_call_put_userid, "PUT user-id ") \
EM(rxrpc_call_see_accept, "SEE accept ") \
EM(rxrpc_call_see_activate_client, "SEE act-clnt") \
EM(rxrpc_call_see_connect_failed, "SEE con-fail") \
EM(rxrpc_call_see_connected, "SEE connect ") \
+ EM(rxrpc_call_see_disconnected, "SEE disconn ") \
EM(rxrpc_call_see_distribute_error, "SEE dist-err") \
EM(rxrpc_call_see_input, "SEE input ") \
EM(rxrpc_call_see_release, "SEE release ") \
#define EM(a, b) a,
#define E_(a, b) a
+enum rxrpc_abort_reason { rxrpc_abort_reasons } __mode(byte);
enum rxrpc_bundle_trace { rxrpc_bundle_traces } __mode(byte);
enum rxrpc_call_poke_trace { rxrpc_call_poke_traces } __mode(byte);
enum rxrpc_call_trace { rxrpc_call_traces } __mode(byte);
*/
#undef EM
#undef E_
+
+#ifndef RXRPC_TRACE_ONLY_DEFINE_ENUMS
+
#define EM(a, b) TRACE_DEFINE_ENUM(a);
#define E_(a, b) TRACE_DEFINE_ENUM(a);
+rxrpc_abort_reasons;
rxrpc_bundle_traces;
rxrpc_call_poke_traces;
rxrpc_call_traces;
);
TRACE_EVENT(rxrpc_abort,
- TP_PROTO(unsigned int call_nr, const char *why, u32 cid, u32 call_id,
- rxrpc_seq_t seq, int abort_code, int error),
+ TP_PROTO(unsigned int call_nr, enum rxrpc_abort_reason why,
+ u32 cid, u32 call_id, rxrpc_seq_t seq, int abort_code, int error),
TP_ARGS(call_nr, why, cid, call_id, seq, abort_code, error),
TP_STRUCT__entry(
__field(unsigned int, call_nr )
- __array(char, why, 4 )
+ __field(enum rxrpc_abort_reason, why )
__field(u32, cid )
__field(u32, call_id )
__field(rxrpc_seq_t, seq )
),
TP_fast_assign(
- memcpy(__entry->why, why, 4);
__entry->call_nr = call_nr;
+ __entry->why = why;
__entry->cid = cid;
__entry->call_id = call_id;
__entry->abort_code = abort_code;
TP_printk("c=%08x %08x:%08x s=%u a=%d e=%d %s",
__entry->call_nr,
__entry->cid, __entry->call_id, __entry->seq,
- __entry->abort_code, __entry->error, __entry->why)
+ __entry->abort_code, __entry->error,
+ __print_symbolic(__entry->why, rxrpc_abort_reasons))
);
TRACE_EVENT(rxrpc_call_complete,
);
TRACE_EVENT(rxrpc_recvmsg,
- TP_PROTO(struct rxrpc_call *call, enum rxrpc_recvmsg_trace why,
+ TP_PROTO(unsigned int call_debug_id, enum rxrpc_recvmsg_trace why,
int ret),
- TP_ARGS(call, why, ret),
+ TP_ARGS(call_debug_id, why, ret),
TP_STRUCT__entry(
__field(unsigned int, call )
),
TP_fast_assign(
- __entry->call = call ? call->debug_id : 0;
+ __entry->call = call_debug_id;
__entry->why = why;
__entry->ret = ret;
),
__entry->abort_code)
);
-TRACE_EVENT(rxrpc_rx_eproto,
- TP_PROTO(struct rxrpc_call *call, rxrpc_serial_t serial,
- const char *why),
-
- TP_ARGS(call, serial, why),
-
- TP_STRUCT__entry(
- __field(unsigned int, call )
- __field(rxrpc_serial_t, serial )
- __field(const char *, why )
- ),
-
- TP_fast_assign(
- __entry->call = call ? call->debug_id : 0;
- __entry->serial = serial;
- __entry->why = why;
- ),
-
- TP_printk("c=%08x EPROTO %08x %s",
- __entry->call,
- __entry->serial,
- __entry->why)
- );
-
TRACE_EVENT(rxrpc_connect_call,
TP_PROTO(struct rxrpc_call *call),
#undef EM
#undef E_
+
+#endif /* RXRPC_TRACE_ONLY_DEFINE_ENUMS */
#endif /* _TRACE_RXRPC_H */
/* This part must be outside protection */
*/
#define BR2684_ENCAPS_VC (0) /* VC-mux */
#define BR2684_ENCAPS_LLC (1)
-#define BR2684_ENCAPS_AUTODETECT (2) /* Unsuported */
+#define BR2684_ENCAPS_AUTODETECT (2) /* Unsupported */
/*
* Is this VC bridged or routed?
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2000 Jens Axboe <axboe@suse.de>
+ * Copyright (C) 2001-2004 Peter Osterlund <petero2@telia.com>
+ *
+ * May be copied or modified under the terms of the GNU General Public
+ * License. See linux/COPYING for more information.
+ *
+ * Packet writing layer for ATAPI and SCSI CD-R, CD-RW, DVD-R, and
+ * DVD-RW devices.
+ *
+ */
+#ifndef _UAPI__PKTCDVD_H
+#define _UAPI__PKTCDVD_H
+
+#include <linux/types.h>
+
+/*
+ * 1 for normal debug messages, 2 is very verbose. 0 to turn it off.
+ */
+#define PACKET_DEBUG 1
+
+#define MAX_WRITERS 8
+
+#define PKT_RB_POOL_SIZE 512
+
+/*
+ * How long we should hold a non-full packet before starting data gathering.
+ */
+#define PACKET_WAIT_TIME (HZ * 5 / 1000)
+
+/*
+ * use drive write caching -- we need deferred error handling to be
+ * able to successfully recover with this option (drive will return good
+ * status as soon as the cdb is validated).
+ */
+#if defined(CONFIG_CDROM_PKTCDVD_WCACHE)
+#define USE_WCACHING 1
+#else
+#define USE_WCACHING 0
+#endif
+
+/*
+ * No user-servicable parts beyond this point ->
+ */
+
+/*
+ * device types
+ */
+#define PACKET_CDR 1
+#define PACKET_CDRW 2
+#define PACKET_DVDR 3
+#define PACKET_DVDRW 4
+
+/*
+ * flags
+ */
+#define PACKET_WRITABLE 1 /* pd is writable */
+#define PACKET_NWA_VALID 2 /* next writable address valid */
+#define PACKET_LRA_VALID 3 /* last recorded address valid */
+#define PACKET_MERGE_SEGS 4 /* perform segment merging to keep */
+ /* underlying cdrom device happy */
+
+/*
+ * Disc status -- from READ_DISC_INFO
+ */
+#define PACKET_DISC_EMPTY 0
+#define PACKET_DISC_INCOMPLETE 1
+#define PACKET_DISC_COMPLETE 2
+#define PACKET_DISC_OTHER 3
+
+/*
+ * write type, and corresponding data block type
+ */
+#define PACKET_MODE1 1
+#define PACKET_MODE2 2
+#define PACKET_BLOCK_MODE1 8
+#define PACKET_BLOCK_MODE2 10
+
+/*
+ * Last session/border status
+ */
+#define PACKET_SESSION_EMPTY 0
+#define PACKET_SESSION_INCOMPLETE 1
+#define PACKET_SESSION_RESERVED 2
+#define PACKET_SESSION_COMPLETE 3
+
+#define PACKET_MCN "4a656e734178626f65323030300000"
+
+#undef PACKET_USE_LS
+
+#define PKT_CTRL_CMD_SETUP 0
+#define PKT_CTRL_CMD_TEARDOWN 1
+#define PKT_CTRL_CMD_STATUS 2
+
+struct pkt_ctrl_command {
+ __u32 command; /* in: Setup, teardown, status */
+ __u32 dev_index; /* in/out: Device index */
+ __u32 dev; /* in/out: Device nr for cdrw device */
+ __u32 pkt_dev; /* in/out: Device nr for packet device */
+ __u32 num_devices; /* out: Largest device index + 1 */
+ __u32 padding; /* Not used */
+};
+
+/*
+ * packet ioctls
+ */
+#define PACKET_IOCTL_MAGIC ('X')
+#define PACKET_CTRL_CMD _IOWR(PACKET_IOCTL_MAGIC, 1, struct pkt_ctrl_command)
+
+
+#endif /* _UAPI__PKTCDVD_H */
#define PSCI_1_1_FN_SYSTEM_RESET2 PSCI_0_2_FN(18)
#define PSCI_1_1_FN_MEM_PROTECT PSCI_0_2_FN(19)
-#define PSCI_1_1_FN_MEM_PROTECT_CHECK_RANGE PSCI_0_2_FN(19)
+#define PSCI_1_1_FN_MEM_PROTECT_CHECK_RANGE PSCI_0_2_FN(20)
#define PSCI_1_0_FN64_CPU_DEFAULT_SUSPEND PSCI_0_2_FN64(12)
#define PSCI_1_0_FN64_NODE_HW_STATE PSCI_0_2_FN64(13)
#define PSCI_1_0_FN64_STAT_COUNT PSCI_0_2_FN64(17)
#define PSCI_1_1_FN64_SYSTEM_RESET2 PSCI_0_2_FN64(18)
-#define PSCI_1_1_FN64_MEM_PROTECT_CHECK_RANGE PSCI_0_2_FN64(19)
+#define PSCI_1_1_FN64_MEM_PROTECT_CHECK_RANGE PSCI_0_2_FN64(20)
/* PSCI v0.2 power state encoding for CPU_SUSPEND function */
#define PSCI_0_2_POWER_STATE_ID_MASK 0xffff
VDPA_ATTR_DEV_VENDOR_ATTR_NAME, /* string */
VDPA_ATTR_DEV_VENDOR_ATTR_VALUE, /* u64 */
+ /* virtio features that are provisioned to the vDPA device */
VDPA_ATTR_DEV_FEATURES, /* u64 */
- /* virtio features that are supported by the vDPA device */
- VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES, /* u64 */
-
/* new attributes must be added above here */
VDPA_ATTR_MAX,
};
const struct xenbus_device_id *id);
void (*otherend_changed)(struct xenbus_device *dev,
enum xenbus_state backend_state);
- int (*remove)(struct xenbus_device *dev);
+ void (*remove)(struct xenbus_device *dev);
int (*suspend)(struct xenbus_device *dev);
int (*resume)(struct xenbus_device *dev);
int (*uevent)(struct xenbus_device *, struct kobj_uevent_env *);
depends on PRINTK
help
Select the size of an alternate printk per-CPU buffer where messages
- printed from usafe contexts are temporary stored. One example would
+ printed from unsafe contexts are temporary stored. One example would
be NMI messages, another one - printk recursion. The messages are
copied to the main log buffer in a safe context to avoid a deadlock.
The value defines the size as a power of 2.
default "-Wimplicit-fallthrough=5" if CC_IS_GCC && $(cc-option,-Wimplicit-fallthrough=5)
default "-Wimplicit-fallthrough" if CC_IS_CLANG && $(cc-option,-Wunreachable-code-fallthrough)
-# Currently, disable gcc-12 array-bounds globally.
+# Currently, disable gcc-11,12 array-bounds globally.
# We may want to target only particular configurations some day.
+config GCC11_NO_ARRAY_BOUNDS
+ def_bool y
+
config GCC12_NO_ARRAY_BOUNDS
def_bool y
config CC_NO_ARRAY_BOUNDS
bool
+ default y if CC_IS_GCC && GCC_VERSION >= 110000 && GCC_VERSION < 120000 && GCC11_NO_ARRAY_BOUNDS
default y if CC_IS_GCC && GCC_VERSION >= 120000 && GCC_VERSION < 130000 && GCC12_NO_ARRAY_BOUNDS
#
$(obj)/version-timestamp.o: include/generated/utsversion.h
CFLAGS_version-timestamp.o := -include include/generated/utsversion.h
+KASAN_SANITIZE_version-timestamp.o := n
xa_for_each(&ctx->personalities, index, cred)
io_uring_show_cred(m, index, cred);
}
- if (has_lock)
- mutex_unlock(&ctx->uring_lock);
seq_puts(m, "PollList:\n");
for (i = 0; i < (1U << ctx->cancel_table.hash_bits); i++) {
struct io_hash_bucket *hb = &ctx->cancel_table.hbs[i];
+ struct io_hash_bucket *hbl = &ctx->cancel_table_locked.hbs[i];
struct io_kiocb *req;
spin_lock(&hb->lock);
seq_printf(m, " op=%d, task_works=%d\n", req->opcode,
task_work_pending(req->task));
spin_unlock(&hb->lock);
+
+ if (!has_lock)
+ continue;
+ hlist_for_each_entry(req, &hbl->list, hash_node)
+ seq_printf(m, " op=%d, task_works=%d\n", req->opcode,
+ task_work_pending(req->task));
}
+ if (has_lock)
+ mutex_unlock(&ctx->uring_lock);
+
seq_puts(m, "CqOverflowList:\n");
spin_lock(&ctx->completion_lock);
list_for_each_entry(ocqe, &ctx->cq_overflow_list, list) {
worker = container_of(cb, struct io_worker, create_work);
io_worker_cancel_cb(worker);
+ /*
+ * Only the worker continuation helper has worker allocated and
+ * hence needs freeing.
+ */
+ if (cb->func == create_worker_cont)
+ kfree(worker);
}
}
size_t ocq_size = sizeof(struct io_overflow_cqe);
bool is_cqe32 = (ctx->flags & IORING_SETUP_CQE32);
+ lockdep_assert_held(&ctx->completion_lock);
+
if (is_cqe32)
ocq_size += sizeof(struct io_uring_cqe);
{
struct io_uring_cqe *cqe;
- if (!ctx->task_complete)
- lockdep_assert_held(&ctx->completion_lock);
-
ctx->cq_extra++;
/*
{
struct io_ring_ctx *ctx = req->ctx;
- if (!llist_add(&req->io_task_work.node, &ctx->work_llist))
+ percpu_ref_get(&ctx->refs);
+
+ if (!llist_add(&req->io_task_work.node, &ctx->work_llist)) {
+ percpu_ref_put(&ctx->refs);
return;
+ }
/* need it for the following io_cqring_wake() */
smp_mb__after_atomic();
if (unlikely(atomic_read(&req->task->io_uring->in_idle))) {
io_move_task_work_from_local(ctx);
+ percpu_ref_put(&ctx->refs);
return;
}
if (ctx->has_evfd)
io_eventfd_signal(ctx);
__io_cqring_wake(ctx);
+ percpu_ref_put(&ctx->refs);
}
void __io_req_task_work_add(struct io_kiocb *req, bool allow_local)
/* when returns >0, the caller should retry */
static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
struct io_wait_queue *iowq,
- ktime_t timeout)
+ ktime_t *timeout)
{
int ret;
unsigned long check_cq;
if (check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT))
return -EBADR;
}
- if (!schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS))
+ if (!schedule_hrtimeout(timeout, HRTIMER_MODE_ABS))
return -ETIME;
/*
}
prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq,
TASK_INTERRUPTIBLE);
- ret = io_cqring_wait_schedule(ctx, &iowq, timeout);
+ ret = io_cqring_wait_schedule(ctx, &iowq, &timeout);
if (__io_cqring_events_user(ctx) >= min_events)
break;
cond_resched();
bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task,
bool cancel_all);
+#define io_lockdep_assert_cq_locked(ctx) \
+ do { \
+ if (ctx->flags & IORING_SETUP_IOPOLL) { \
+ lockdep_assert_held(&ctx->uring_lock); \
+ } else if (!ctx->task_complete) { \
+ lockdep_assert_held(&ctx->completion_lock); \
+ } else if (ctx->submitter_task->flags & PF_EXITING) { \
+ lockdep_assert(current_work()); \
+ } else { \
+ lockdep_assert(current == ctx->submitter_task); \
+ } \
+ } while (0)
+
static inline void io_req_task_work_add(struct io_kiocb *req)
{
__io_req_task_work_add(req, true);
static inline struct io_uring_cqe *io_get_cqe_overflow(struct io_ring_ctx *ctx,
bool overflow)
{
+ io_lockdep_assert_cq_locked(ctx);
+
if (likely(ctx->cqe_cached < ctx->cqe_sentinel)) {
struct io_uring_cqe *cqe = ctx->cqe_cached;
IOU_POLL_DONE = 0,
IOU_POLL_NO_ACTION = 1,
IOU_POLL_REMOVE_POLL_USE_RES = 2,
+ IOU_POLL_REISSUE = 3,
};
/*
* All poll tw should go through this. Checks for poll events, manages
* references, does rewait, etc.
*
- * Returns a negative error on failure. IOU_POLL_NO_ACTION when no action require,
- * which is either spurious wakeup or multishot CQE is served.
- * IOU_POLL_DONE when it's done with the request, then the mask is stored in req->cqe.res.
- * IOU_POLL_REMOVE_POLL_USE_RES indicates to remove multishot poll and that the result
- * is stored in req->cqe.
+ * Returns a negative error on failure. IOU_POLL_NO_ACTION when no action
+ * require, which is either spurious wakeup or multishot CQE is served.
+ * IOU_POLL_DONE when it's done with the request, then the mask is stored in
+ * req->cqe.res. IOU_POLL_REMOVE_POLL_USE_RES indicates to remove multishot
+ * poll and that the result is stored in req->cqe.
*/
static int io_poll_check_events(struct io_kiocb *req, bool *locked)
{
- int v, ret;
+ int v;
/* req->task == current here, checking PF_EXITING is safe */
if (unlikely(req->task->flags & PF_EXITING))
if (!req->cqe.res) {
struct poll_table_struct pt = { ._key = req->apoll_events };
req->cqe.res = vfs_poll(req->file, &pt) & req->apoll_events;
+ /*
+ * We got woken with a mask, but someone else got to
+ * it first. The above vfs_poll() doesn't add us back
+ * to the waitqueue, so if we get nothing back, we
+ * should be safe and attempt a reissue.
+ */
+ if (unlikely(!req->cqe.res))
+ return IOU_POLL_REISSUE;
}
-
- if ((unlikely(!req->cqe.res)))
- continue;
if (req->apoll_events & EPOLLONESHOT)
return IOU_POLL_DONE;
return IOU_POLL_REMOVE_POLL_USE_RES;
}
} else {
- ret = io_poll_issue(req, locked);
+ int ret = io_poll_issue(req, locked);
if (ret == IOU_STOP_MULTISHOT)
return IOU_POLL_REMOVE_POLL_USE_RES;
if (ret < 0)
poll = io_kiocb_to_cmd(req, struct io_poll);
req->cqe.res = mangle_poll(req->cqe.res & poll->events);
+ } else if (ret == IOU_POLL_REISSUE) {
+ io_req_task_submit(req, locked);
+ return;
} else if (ret != IOU_POLL_REMOVE_POLL_USE_RES) {
req->cqe.res = ret;
req_set_fail(req);
if (ret == IOU_POLL_REMOVE_POLL_USE_RES)
io_req_task_complete(req, locked);
- else if (ret == IOU_POLL_DONE)
+ else if (ret == IOU_POLL_DONE || ret == IOU_POLL_REISSUE)
io_req_task_submit(req, locked);
else
io_req_defer_failed(req, ret);
return pt->owning || io_poll_get_ownership(req);
}
+static void io_poll_add_hash(struct io_kiocb *req)
+{
+ if (req->flags & REQ_F_HASH_LOCKED)
+ io_poll_req_insert_locked(req);
+ else
+ io_poll_req_insert(req);
+}
+
/*
* Returns 0 when it's handed over for polling. The caller owns the requests if
* it returns non-zero, but otherwise should not touch it. Negative values
if (mask &&
((poll->events & (EPOLLET|EPOLLONESHOT)) == (EPOLLET|EPOLLONESHOT))) {
- if (!io_poll_can_finish_inline(req, ipt))
+ if (!io_poll_can_finish_inline(req, ipt)) {
+ io_poll_add_hash(req);
return 0;
+ }
io_poll_remove_entries(req);
ipt->result_mask = mask;
/* no one else has access to the req, forget about the ref */
return 1;
}
- if (req->flags & REQ_F_HASH_LOCKED)
- io_poll_req_insert_locked(req);
- else
- io_poll_req_insert(req);
+ io_poll_add_hash(req);
if (mask && (poll->events & EPOLLET) &&
io_poll_can_finish_inline(req, ipt)) {
continue;
req->cqe.flags = io_put_kbuf(req, 0);
- io_fill_cqe_req(req->ctx, req);
+ if (unlikely(!__io_fill_cqe_req(ctx, req))) {
+ spin_lock(&ctx->completion_lock);
+ io_req_cqe_overflow(req);
+ spin_unlock(&ctx->completion_lock);
+ }
}
if (unlikely(!nr_events))
BTF_ID(func, bpf_lsm_bpf_prog_free_security)
BTF_ID(func, bpf_lsm_file_alloc_security)
BTF_ID(func, bpf_lsm_file_free_security)
+#ifdef CONFIG_SECURITY_NETWORK
BTF_ID(func, bpf_lsm_sk_alloc_security)
BTF_ID(func, bpf_lsm_sk_free_security)
+#endif /* CONFIG_SECURITY_NETWORK */
BTF_ID(func, bpf_lsm_task_free)
BTF_SET_END(untrusted_lsm_hooks)
*/
struct bpf_iter_seq_task_common common;
struct task_struct *task;
+ struct mm_struct *mm;
struct vm_area_struct *vma;
u32 tid;
unsigned long prev_vm_start;
enum bpf_task_vma_iter_find_op op;
struct vm_area_struct *curr_vma;
struct task_struct *curr_task;
+ struct mm_struct *curr_mm;
u32 saved_tid = info->tid;
/* If this function returns a non-NULL vma, it holds a reference to
- * the task_struct, and holds read lock on vma->mm->mmap_lock.
+ * the task_struct, holds a refcount on mm->mm_users, and holds
+ * read lock on vma->mm->mmap_lock.
* If this function returns NULL, it does not hold any reference or
* lock.
*/
if (info->task) {
curr_task = info->task;
curr_vma = info->vma;
+ curr_mm = info->mm;
/* In case of lock contention, drop mmap_lock to unblock
* the writer.
*
* 4.2) VMA2 and VMA2' covers different ranges, process
* VMA2'.
*/
- if (mmap_lock_is_contended(curr_task->mm)) {
+ if (mmap_lock_is_contended(curr_mm)) {
info->prev_vm_start = curr_vma->vm_start;
info->prev_vm_end = curr_vma->vm_end;
op = task_vma_iter_find_vma;
- mmap_read_unlock(curr_task->mm);
- if (mmap_read_lock_killable(curr_task->mm))
+ mmap_read_unlock(curr_mm);
+ if (mmap_read_lock_killable(curr_mm)) {
+ mmput(curr_mm);
goto finish;
+ }
} else {
op = task_vma_iter_next_vma;
}
op = task_vma_iter_find_vma;
}
- if (!curr_task->mm)
+ curr_mm = get_task_mm(curr_task);
+ if (!curr_mm)
goto next_task;
- if (mmap_read_lock_killable(curr_task->mm))
+ if (mmap_read_lock_killable(curr_mm)) {
+ mmput(curr_mm);
goto finish;
+ }
}
switch (op) {
case task_vma_iter_first_vma:
- curr_vma = find_vma(curr_task->mm, 0);
+ curr_vma = find_vma(curr_mm, 0);
break;
case task_vma_iter_next_vma:
- curr_vma = find_vma(curr_task->mm, curr_vma->vm_end);
+ curr_vma = find_vma(curr_mm, curr_vma->vm_end);
break;
case task_vma_iter_find_vma:
/* We dropped mmap_lock so it is necessary to use find_vma
* to find the next vma. This is similar to the mechanism
* in show_smaps_rollup().
*/
- curr_vma = find_vma(curr_task->mm, info->prev_vm_end - 1);
+ curr_vma = find_vma(curr_mm, info->prev_vm_end - 1);
/* case 1) and 4.2) above just use curr_vma */
/* check for case 2) or case 4.1) above */
if (curr_vma &&
curr_vma->vm_start == info->prev_vm_start &&
curr_vma->vm_end == info->prev_vm_end)
- curr_vma = find_vma(curr_task->mm, curr_vma->vm_end);
+ curr_vma = find_vma(curr_mm, curr_vma->vm_end);
break;
}
if (!curr_vma) {
/* case 3) above, or case 2) 4.1) with vma->next == NULL */
- mmap_read_unlock(curr_task->mm);
+ mmap_read_unlock(curr_mm);
+ mmput(curr_mm);
goto next_task;
}
info->task = curr_task;
info->vma = curr_vma;
+ info->mm = curr_mm;
return curr_vma;
next_task:
put_task_struct(curr_task);
info->task = NULL;
+ info->mm = NULL;
info->tid++;
goto again;
put_task_struct(curr_task);
info->task = NULL;
info->vma = NULL;
+ info->mm = NULL;
return NULL;
}
*/
info->prev_vm_start = ~0UL;
info->prev_vm_end = info->vma->vm_end;
- mmap_read_unlock(info->task->mm);
+ mmap_read_unlock(info->mm);
+ mmput(info->mm);
+ info->mm = NULL;
put_task_struct(info->task);
info->task = NULL;
}
/* reset fops->func and fops->trampoline for re-register */
tr->fops->func = NULL;
tr->fops->trampoline = 0;
+
+ /* reset im->image memory attr for arch_prepare_bpf_trampoline */
+ set_memory_nx((long)im->image, 1);
+ set_memory_rw((long)im->image, 1);
goto again;
}
#endif
*/
static void *copy_array(void *dst, const void *src, size_t n, size_t size, gfp_t flags)
{
+ size_t alloc_bytes;
+ void *orig = dst;
size_t bytes;
if (ZERO_OR_NULL_PTR(src))
if (unlikely(check_mul_overflow(n, size, &bytes)))
return NULL;
- if (ksize(dst) < ksize(src)) {
- kfree(dst);
- dst = kmalloc_track_caller(kmalloc_size_roundup(bytes), flags);
- if (!dst)
- return NULL;
+ alloc_bytes = max(ksize(orig), kmalloc_size_roundup(bytes));
+ dst = krealloc(orig, alloc_bytes, flags);
+ if (!dst) {
+ kfree(orig);
+ return NULL;
}
memcpy(dst, src, bytes);
* register B - not null
* for JNE A, B, ... - A is not null in the false branch;
* for JEQ A, B, ... - A is not null in the true branch.
+ *
+ * Since PTR_TO_BTF_ID points to a kernel struct that does
+ * not need to be null checked by the BPF program, i.e.,
+ * could be null even without PTR_MAYBE_NULL marking, so
+ * only propagate nullness when neither reg is that type.
*/
if (!is_jmp32 && BPF_SRC(insn->code) == BPF_X &&
__is_pointer_value(false, src_reg) && __is_pointer_value(false, dst_reg) &&
- type_may_be_null(src_reg->type) != type_may_be_null(dst_reg->type)) {
+ type_may_be_null(src_reg->type) != type_may_be_null(dst_reg->type) &&
+ base_type(src_reg->type) != PTR_TO_BTF_ID &&
+ base_type(dst_reg->type) != PTR_TO_BTF_ID) {
eq_branch_regs = NULL;
switch (opcode) {
case BPF_JEQ:
static int lookup_name(void *data, const char *name, struct module *mod, unsigned long addr)
{
u64 t0, t1, t;
- unsigned long flags;
struct test_stat *stat = (struct test_stat *)data;
- local_irq_save(flags);
- t0 = sched_clock();
+ t0 = ktime_get_ns();
(void)kallsyms_lookup_name(name);
- t1 = sched_clock();
- local_irq_restore(flags);
+ t1 = ktime_get_ns();
t = t1 - t0;
if (t < stat->min)
static void test_perf_kallsyms_on_each_symbol(void)
{
u64 t0, t1;
- unsigned long flags;
struct test_stat stat;
memset(&stat, 0, sizeof(stat));
stat.max = INT_MAX;
stat.name = stub_name;
stat.perf = 1;
- local_irq_save(flags);
- t0 = sched_clock();
+ t0 = ktime_get_ns();
kallsyms_on_each_symbol(find_symbol, &stat);
- t1 = sched_clock();
- local_irq_restore(flags);
+ t1 = ktime_get_ns();
pr_info("kallsyms_on_each_symbol() traverse all: %lld ns\n", t1 - t0);
}
static void test_perf_kallsyms_on_each_match_symbol(void)
{
u64 t0, t1;
- unsigned long flags;
struct test_stat stat;
memset(&stat, 0, sizeof(stat));
stat.max = INT_MAX;
stat.name = stub_name;
- local_irq_save(flags);
- t0 = sched_clock();
+ t0 = ktime_get_ns();
kallsyms_on_each_match_symbol(match_symbol, stat.name, &stat);
- t1 = sched_clock();
- local_irq_restore(flags);
+ t1 = ktime_get_ns();
pr_info("kallsyms_on_each_match_symbol() traverse all: %lld ns\n", t1 - t0);
}
const bool is_assert = (r->access[0].type | r->access[1].type) & KCSAN_ACCESS_ASSERT;
bool ret = false;
unsigned long flags;
- typeof(observed.lines) expect;
+ typeof(*observed.lines) *expect;
const char *end;
char *cur;
int i;
if (!report_available())
return false;
+ expect = kmalloc(sizeof(observed.lines), GFP_KERNEL);
+ if (WARN_ON(!expect))
+ return false;
+
/* Generate expected report contents. */
/* Title */
strstr(observed.lines[2], expect[1])));
out:
spin_unlock_irqrestore(&observed.lock, flags);
+ kfree(expect);
return ret;
}
.user_mask = NULL,
.flags = SCA_USER, /* clear the user requested mask */
};
+ union cpumask_rcuhead {
+ cpumask_t cpumask;
+ struct rcu_head rcu;
+ };
__do_set_cpus_allowed(p, &ac);
- kfree(ac.user_mask);
+
+ /*
+ * Because this is called with p->pi_lock held, it is not possible
+ * to use kfree() here (when PREEMPT_RT=y), therefore punt to using
+ * kfree_rcu().
+ */
+ kfree_rcu((union cpumask_rcuhead *)ac.user_mask, rcu);
+}
+
+static cpumask_t *alloc_user_cpus_ptr(int node)
+{
+ /*
+ * See do_set_cpus_allowed() above for the rcu_head usage.
+ */
+ int size = max_t(int, cpumask_size(), sizeof(struct rcu_head));
+
+ return kmalloc_node(size, GFP_KERNEL, node);
}
int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
int node)
{
+ cpumask_t *user_mask;
unsigned long flags;
- if (!src->user_cpus_ptr)
+ /*
+ * Always clear dst->user_cpus_ptr first as their user_cpus_ptr's
+ * may differ by now due to racing.
+ */
+ dst->user_cpus_ptr = NULL;
+
+ /*
+ * This check is racy and losing the race is a valid situation.
+ * It is not worth the extra overhead of taking the pi_lock on
+ * every fork/clone.
+ */
+ if (data_race(!src->user_cpus_ptr))
return 0;
- dst->user_cpus_ptr = kmalloc_node(cpumask_size(), GFP_KERNEL, node);
- if (!dst->user_cpus_ptr)
+ user_mask = alloc_user_cpus_ptr(node);
+ if (!user_mask)
return -ENOMEM;
- /* Use pi_lock to protect content of user_cpus_ptr */
+ /*
+ * Use pi_lock to protect content of user_cpus_ptr
+ *
+ * Though unlikely, user_cpus_ptr can be reset to NULL by a concurrent
+ * do_set_cpus_allowed().
+ */
raw_spin_lock_irqsave(&src->pi_lock, flags);
- cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr);
+ if (src->user_cpus_ptr) {
+ swap(dst->user_cpus_ptr, user_mask);
+ cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr);
+ }
raw_spin_unlock_irqrestore(&src->pi_lock, flags);
+
+ if (unlikely(user_mask))
+ kfree(user_mask);
+
return 0;
}
return false;
}
+static inline cpumask_t *alloc_user_cpus_ptr(int node)
+{
+ return NULL;
+}
+
#endif /* !CONFIG_SMP */
static void
unsigned long thermal_pressure;
u64 resched_latency;
- arch_scale_freq_tick();
+ if (housekeeping_cpu(cpu, HK_TYPE_TICK))
+ arch_scale_freq_tick();
+
sched_clock_tick();
rq_lock(rq, &rf);
if (retval)
goto out_put_task;
- user_mask = kmalloc(cpumask_size(), GFP_KERNEL);
- if (!user_mask) {
+ user_mask = alloc_user_cpus_ptr(NUMA_NO_NODE);
+ if (IS_ENABLED(CONFIG_SMP) && !user_mask) {
retval = -ENOMEM;
goto out_put_task;
}
#include "tick-internal.h"
/**
- * tick_program_event
+ * tick_program_event - program the CPU local timer device for the next event
*/
int tick_program_event(ktime_t expires, int force)
{
}
/**
- * tick_check_oneshot_mode - check whether the system is in oneshot mode
+ * tick_oneshot_mode_active - check whether the system is in oneshot mode
*
* returns 1 when either nohz or highres are enabled. otherwise 0.
*/
EXPORT_SYMBOL(ns_to_kernel_old_timeval);
/**
- * set_normalized_timespec - set timespec sec and nsec parts and normalize
+ * set_normalized_timespec64 - set timespec sec and nsec parts and normalize
*
* @ts: pointer to timespec variable to be set
* @sec: seconds to set
EXPORT_SYMBOL(ns_to_timespec64);
/**
- * msecs_to_jiffies: - convert milliseconds to jiffies
+ * __msecs_to_jiffies: - convert milliseconds to jiffies
* @m: time in milliseconds
*
* conversion is done as follows:
* handling any 32-bit overflows.
* for the details see __msecs_to_jiffies()
*
- * msecs_to_jiffies() checks for the passed in value being a constant
+ * __msecs_to_jiffies() checks for the passed in value being a constant
* via __builtin_constant_p() allowing gcc to eliminate most of the
* code, __msecs_to_jiffies() is called if the value passed does not
* allow constant folding and the actual conversion must be done at
* runtime.
- * the _msecs_to_jiffies helpers are the HZ dependent conversion
+ * The _msecs_to_jiffies helpers are the HZ dependent conversion
* routines found in include/linux/jiffies.h
*/
unsigned long __msecs_to_jiffies(const unsigned int m)
/**
* read_persistent_wall_and_boot_offset - Read persistent clock, and also offset
* from the boot.
+ * @wall_time: current time as returned by persistent clock
+ * @boot_offset: offset that is defined as wall_time - boot_time
*
* Weak dummy function for arches that do not yet support it.
- * @wall_time: - current time as returned by persistent clock
- * @boot_offset: - offset that is defined as wall_time - boot_time
*
* The default function calculates offset based on the current value of
* local_clock(). This way architectures that support sched_clock() but don't
}
#if defined(CONFIG_PM_SLEEP) && defined(CONFIG_RTC_HCTOSYS_DEVICE)
-/**
+/*
* We have three kinds of time sources to use for sleep time
* injection, the preference order is:
* 1) non-stop clocksource
return !suspend_timing_needed;
}
-/**
+/*
* 1) can be determined whether to use or not only when doing
* timekeeping_resume() which is invoked after rtc_suspend(),
* so we can't skip rtc_suspend() surely if system has 1).
} \
if (!--retry) \
break; \
- cpu_relax(); \
} \
} while (0)
/* Merge contiguous pages into the last SG */
prv_len = sgt_append->prv->length;
last_pg = sg_page(sgt_append->prv);
- while (n_pages && pages_are_mergeable(last_pg, pages[0])) {
+ while (n_pages && pages_are_mergeable(pages[0], last_pg)) {
if (sgt_append->prv->length + PAGE_SIZE > max_segment)
break;
sgt_append->prv->length += PAGE_SIZE;
// SPDX-License-Identifier: GPL-2.0
-/**
+/*
* lib/minmax.c: windowed min/max tracker
*
* Kathleen Nichols' algorithm for tracking the minimum (or maximum)
static void hugetlb_vma_lock_free(struct vm_area_struct *vma);
static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma);
static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma);
+static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end);
static inline bool subpool_is_free(struct hugepage_subpool *spool)
{
/*
* Reset and decrement one ref on hugepage private reservation.
- * Called with mm->mmap_sem writer semaphore held.
+ * Called with mm->mmap_lock writer semaphore held.
* This function should be only used by move_vma() and operate on
* same sized vma. It should never come here with last ref on the
* reservation.
{
if (addr & ~(huge_page_mask(hstate_vma(vma))))
return -EINVAL;
+
+ /*
+ * PMD sharing is only possible for PUD_SIZE-aligned address ranges
+ * in HugeTLB VMAs. If we will lose PUD_SIZE alignment due to this
+ * split, unshare PMDs in the PUD_SIZE interval surrounding addr now.
+ */
+ if (addr & ~PUD_MASK) {
+ /*
+ * hugetlb_vm_op_split is called right before we attempt to
+ * split the VMA. We will need to unshare PMDs in the old and
+ * new VMAs, so let's unshare before we split.
+ */
+ unsigned long floor = addr & PUD_MASK;
+ unsigned long ceil = floor + PUD_SIZE;
+
+ if (floor >= vma->vm_start && ceil <= vma->vm_end)
+ hugetlb_unshare_pmds(vma, floor, ceil);
+ }
+
return 0;
}
/*
* We don't have to worry about the ordering of src and dst ptlocks
- * because exclusive mmap_sem (or the i_mmap_lock) prevents deadlock.
+ * because exclusive mmap_lock (or the i_mmap_lock) prevents deadlock.
*/
if (src_ptl != dst_ptl)
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
spinlock_t *ptl;
ptep = huge_pte_offset(mm, address, psize);
if (!ptep) {
- address |= last_addr_mask;
- continue;
+ if (!uffd_wp) {
+ address |= last_addr_mask;
+ continue;
+ }
+ /*
+ * Userfaultfd wr-protect requires pgtable
+ * pre-allocations to install pte markers.
+ */
+ ptep = huge_pte_alloc(mm, vma, address, psize);
+ if (!ptep)
+ break;
}
ptl = huge_pte_lock(h, mm, ptep);
if (huge_pmd_unshare(mm, vma, address, ptep)) {
}
pte = huge_ptep_get(ptep);
if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) {
- spin_unlock(ptl);
- continue;
- }
- if (unlikely(is_hugetlb_entry_migration(pte))) {
+ /* Nothing to do. */
+ } else if (unlikely(is_hugetlb_entry_migration(pte))) {
swp_entry_t entry = pte_to_swp_entry(pte);
struct page *page = pfn_swap_entry_to_page(entry);
+ pte_t newpte = pte;
- if (!is_readable_migration_entry(entry)) {
- pte_t newpte;
-
+ if (is_writable_migration_entry(entry)) {
if (PageAnon(page))
entry = make_readable_exclusive_migration_entry(
swp_offset(entry));
entry = make_readable_migration_entry(
swp_offset(entry));
newpte = swp_entry_to_pte(entry);
- if (uffd_wp)
- newpte = pte_swp_mkuffd_wp(newpte);
- else if (uffd_wp_resolve)
- newpte = pte_swp_clear_uffd_wp(newpte);
- set_huge_pte_at(mm, address, ptep, newpte);
pages++;
}
- spin_unlock(ptl);
- continue;
- }
- if (unlikely(pte_marker_uffd_wp(pte))) {
- /*
- * This is changing a non-present pte into a none pte,
- * no need for huge_ptep_modify_prot_start/commit().
- */
+
+ if (uffd_wp)
+ newpte = pte_swp_mkuffd_wp(newpte);
+ else if (uffd_wp_resolve)
+ newpte = pte_swp_clear_uffd_wp(newpte);
+ if (!pte_same(pte, newpte))
+ set_huge_pte_at(mm, address, ptep, newpte);
+ } else if (unlikely(is_pte_marker(pte))) {
+ /* No other markers apply for now. */
+ WARN_ON_ONCE(!pte_marker_uffd_wp(pte));
if (uffd_wp_resolve)
+ /* Safe to modify directly (non-present->none). */
huge_pte_clear(mm, address, ptep, psize);
- }
- if (!huge_pte_none(pte)) {
+ } else if (!huge_pte_none(pte)) {
pte_t old_pte;
unsigned int shift = huge_page_shift(hstate_vma(vma));
}
}
-/*
- * This function will unconditionally remove all the shared pmd pgtable entries
- * within the specific vma for a hugetlbfs memory range.
- */
-void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
+static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
+ unsigned long start,
+ unsigned long end)
{
struct hstate *h = hstate_vma(vma);
unsigned long sz = huge_page_size(h);
struct mm_struct *mm = vma->vm_mm;
struct mmu_notifier_range range;
- unsigned long address, start, end;
+ unsigned long address;
spinlock_t *ptl;
pte_t *ptep;
if (!(vma->vm_flags & VM_MAYSHARE))
return;
- start = ALIGN(vma->vm_start, PUD_SIZE);
- end = ALIGN_DOWN(vma->vm_end, PUD_SIZE);
-
if (start >= end)
return;
mmu_notifier_invalidate_range_end(&range);
}
+/*
+ * This function will unconditionally remove all the shared pmd pgtable entries
+ * within the specific vma for a hugetlbfs memory range.
+ */
+void hugetlb_unshare_all_pmds(struct vm_area_struct *vma)
+{
+ hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE),
+ ALIGN_DOWN(vma->vm_end, PUD_SIZE));
+}
+
#ifdef CONFIG_CMA
static bool cma_reserve_called __initdata;
* Whether the KASAN KUnit test suite is currently being executed.
* Updated in kasan_test.c.
*/
-bool kasan_kunit_executing;
+static bool kasan_kunit_executing;
void kasan_kunit_test_suite_start(void)
{
if (!hugepage_vma_check(vma, vma->vm_flags, false, false, false))
return SCAN_VMA_CHECK;
- /*
- * Symmetry with retract_page_tables(): Exclude MAP_PRIVATE mappings
- * that got written to. Without this, we'd have to also lock the
- * anon_vma if one exists.
- */
- if (vma->anon_vma)
- return SCAN_VMA_CHECK;
-
/* Keep pmd pgtable for uffd-wp; see comment in retract_page_tables() */
if (userfaultfd_wp(vma))
return SCAN_PTE_UFFD_WP;
}
/* step 4: remove pte entries */
+ /* we make no change to anon, but protect concurrent anon page lookup */
+ if (vma->anon_vma)
+ anon_vma_lock_write(vma->anon_vma);
+
collapse_and_free_pmd(mm, vma, haddr, pmd);
+ if (vma->anon_vma)
+ anon_vma_unlock_write(vma->anon_vma);
i_mmap_unlock_write(vma->vm_file->f_mapping);
maybe_install_pmd:
goto out_nolock;
}
- hend = vma->vm_end & HPAGE_PMD_MASK;
+ hend = min(hend, vma->vm_end & HPAGE_PMD_MASK);
}
mmap_assert_locked(mm);
memset(cc->node_load, 0, sizeof(cc->node_load));
#endif /* CONFIG_ANON_VMA_NAME */
/*
* Update the vm_flags on region of a vma, splitting it or merging it as
- * necessary. Must be called with mmap_sem held for writing;
+ * necessary. Must be called with mmap_lock held for writing;
* Caller should ensure anon_name stability by raising its refcount even when
* anon_name belongs to a valid vma because this function might free that vma.
*/
* @base: phys starting address of the boot memory block
* @size: size of the boot memory block in bytes
*
- * Free boot memory block previously allocated by memblock_alloc_xx() API.
+ * Free boot memory block previously allocated by memblock_phys_alloc_xx() API.
* The freeing memory will not be released to the buddy allocator.
*/
int __init_memblock memblock_phys_free(phys_addr_t base, phys_addr_t size)
end = PFN_DOWN(base + size);
for (; cursor < end; cursor++) {
- memblock_free_pages(pfn_to_page(cursor), cursor, 0);
+ /*
+ * Reserved pages are always initialized by the end of
+ * memblock_free_all() (by memmap_init() and, if deferred
+ * initialization is enabled, memmap_init_reserved_pages()), so
+ * these pages can be released directly to the buddy allocator.
+ */
+ __free_pages_core(pfn_to_page(cursor), 0);
totalram_pages_inc();
}
}
if (vma_soft_dirty_enabled(vma) && !is_vm_hugetlb_page(vma))
return 1;
+ /* Do we need write faults for uffd-wp tracking? */
+ if (userfaultfd_wp(vma))
+ return 1;
+
/* Specialty mapping? */
if (vm_flags & VM_PFNMAP)
return 0;
* @start: The aligned start address to munmap.
* @end: The aligned end address to munmap.
* @uf: The userfaultfd list_head
- * @downgrade: Set to true to attempt a write downgrade of the mmap_sem
+ * @downgrade: Set to true to attempt a write downgrade of the mmap_lock
*
* If @downgrade is true, check return code for potential release of the lock.
*/
* @len: The length of the range to munmap
* @uf: The userfaultfd list_head
* @downgrade: set to true if the user wants to attempt to write_downgrade the
- * mmap_sem
+ * mmap_lock
*
* This function takes a @mas that is either pointing to the previous VMA or set
* to MA_START and sets it up to remove the mapping(s). The @len will be
static void setup_vma_to_mm(struct vm_area_struct *vma, struct mm_struct *mm)
{
- mm->map_count++;
vma->vm_mm = mm;
/* add the VMA to the mapping */
BUG_ON(!vma->vm_region);
setup_vma_to_mm(vma, mm);
+ mm->map_count++;
/* add the VMA to the tree */
vma_mas_store(vma, mas);
error_just_free:
up_write(&nommu_region_sem);
error:
+ mas_destroy(&mas);
if (region->vm_file)
fput(region->vm_file);
kmem_cache_free(vm_region_jar, region);
sharing_violation:
up_write(&nommu_region_sem);
- mas_destroy(&mas);
pr_warn("Attempt to share mismatched mappings\n");
ret = -EINVAL;
goto error;
if (vma->vm_file)
return -ENOMEM;
+ mm = vma->vm_mm;
if (mm->map_count >= sysctl_max_map_count)
return -ENOMEM;
mas_set_range(&mas, vma->vm_start, vma->vm_end - 1);
mas_store(&mas, vma);
vma_mas_store(new, &mas);
+ mm->map_count++;
return 0;
err_mas_preallocate:
erase_whole_vma:
if (delete_vma_from_mm(vma))
ret = -ENOMEM;
- delete_vma(mm, vma);
+ else
+ delete_vma(mm, vma);
return ret;
}
if (vma && ((vma->vm_flags & VM_NOHUGEPAGE) ||
test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)))
return false;
- if (shmem_huge_force)
- return true;
- if (shmem_huge == SHMEM_HUGE_FORCE)
- return true;
if (shmem_huge == SHMEM_HUGE_DENY)
return false;
+ if (shmem_huge_force || shmem_huge == SHMEM_HUGE_FORCE)
+ return true;
switch (SHMEM_SB(inode->i_sb)->huge) {
case SHMEM_HUGE_ALWAYS:
raw_spin_unlock_irq(&n->list_lock);
slab_destroy(cache, slab);
nr_freed++;
+
+ cond_resched();
}
out:
return nr_freed;
kfree(priv);
}
-static int xen_9pfs_front_remove(struct xenbus_device *dev)
+static void xen_9pfs_front_remove(struct xenbus_device *dev)
{
struct xen_9pfs_front_priv *priv = dev_get_drvdata(&dev->dev);
dev_set_drvdata(&dev->dev, NULL);
xen_9pfs_front_free(priv);
- return 0;
}
static int xen_9pfs_front_alloc_dataring(struct xenbus_device *dev,
default:
pr_warn("Request setup of bad link type = %d\n",
param->linktype);
+ cfpkt_destroy(pkt);
return -EINVAL;
}
req = kzalloc(sizeof(*req), GFP_KERNEL);
- if (!req)
+ if (!req) {
+ cfpkt_destroy(pkt);
return -ENOMEM;
+ }
+
req->client_layer = user_layer;
req->cmd = CFCTRL_CMD_LINK_SETUP;
req->param = *param;
static int bpf_skb_generic_pop(struct sk_buff *skb, u32 off, u32 len)
{
+ void *old_data;
+
/* skb_ensure_writable() is not needed here, as we're
* already working on an uncloned skb.
*/
if (unlikely(!pskb_may_pull(skb, off + len)))
return -ENOMEM;
- skb_postpull_rcsum(skb, skb->data + off, len);
- memmove(skb->data + len, skb->data, off);
+ old_data = skb->data;
__skb_pull(skb, len);
+ skb_postpull_rcsum(skb, old_data + off, len);
+ memmove(skb->data, old_data, off);
return 0;
}
NAPI_GRO_CB(skb)->count = 1;
if (unlikely(skb_is_gso(skb))) {
NAPI_GRO_CB(skb)->count = skb_shinfo(skb)->gso_segs;
- /* Only support TCP at the moment. */
- if (!skb_is_gso_tcp(skb))
+ /* Only support TCP and non DODGY users. */
+ if (!skb_is_gso_tcp(skb) ||
+ (skb_shinfo(skb)->gso_type & SKB_GSO_DODGY))
NAPI_GRO_CB(skb)->flush = 1;
}
return ret;
}
-static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr)
+static int ethtool_vzalloc_stats_array(int n_stats, u64 **data)
{
+ if (n_stats < 0)
+ return n_stats;
+ if (n_stats > S32_MAX / sizeof(u64))
+ return -ENOMEM;
+ if (WARN_ON_ONCE(!n_stats))
+ return -EOPNOTSUPP;
+
+ *data = vzalloc(array_size(n_stats, sizeof(u64)));
+ if (!*data)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static int ethtool_get_phy_stats_phydev(struct phy_device *phydev,
+ struct ethtool_stats *stats,
+ u64 **data)
+ {
const struct ethtool_phy_ops *phy_ops = ethtool_phy_ops;
+ int n_stats, ret;
+
+ if (!phy_ops || !phy_ops->get_sset_count || !phy_ops->get_stats)
+ return -EOPNOTSUPP;
+
+ n_stats = phy_ops->get_sset_count(phydev);
+
+ ret = ethtool_vzalloc_stats_array(n_stats, data);
+ if (ret)
+ return ret;
+
+ stats->n_stats = n_stats;
+ return phy_ops->get_stats(phydev, stats, *data);
+}
+
+static int ethtool_get_phy_stats_ethtool(struct net_device *dev,
+ struct ethtool_stats *stats,
+ u64 **data)
+{
const struct ethtool_ops *ops = dev->ethtool_ops;
- struct phy_device *phydev = dev->phydev;
- struct ethtool_stats stats;
- u64 *data;
- int ret, n_stats;
+ int n_stats, ret;
- if (!phydev && (!ops->get_ethtool_phy_stats || !ops->get_sset_count))
+ if (!ops || !ops->get_sset_count || ops->get_ethtool_phy_stats)
return -EOPNOTSUPP;
- if (phydev && !ops->get_ethtool_phy_stats &&
- phy_ops && phy_ops->get_sset_count)
- n_stats = phy_ops->get_sset_count(phydev);
- else
- n_stats = ops->get_sset_count(dev, ETH_SS_PHY_STATS);
- if (n_stats < 0)
- return n_stats;
- if (n_stats > S32_MAX / sizeof(u64))
- return -ENOMEM;
- WARN_ON_ONCE(!n_stats);
+ n_stats = ops->get_sset_count(dev, ETH_SS_PHY_STATS);
+
+ ret = ethtool_vzalloc_stats_array(n_stats, data);
+ if (ret)
+ return ret;
+
+ stats->n_stats = n_stats;
+ ops->get_ethtool_phy_stats(dev, stats, *data);
+
+ return 0;
+}
+
+static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr)
+{
+ struct phy_device *phydev = dev->phydev;
+ struct ethtool_stats stats;
+ u64 *data = NULL;
+ int ret = -EOPNOTSUPP;
if (copy_from_user(&stats, useraddr, sizeof(stats)))
return -EFAULT;
- stats.n_stats = n_stats;
+ if (phydev)
+ ret = ethtool_get_phy_stats_phydev(phydev, &stats, &data);
- if (n_stats) {
- data = vzalloc(array_size(n_stats, sizeof(u64)));
- if (!data)
- return -ENOMEM;
+ if (ret == -EOPNOTSUPP)
+ ret = ethtool_get_phy_stats_ethtool(dev, &stats, &data);
- if (phydev && !ops->get_ethtool_phy_stats &&
- phy_ops && phy_ops->get_stats) {
- ret = phy_ops->get_stats(phydev, &stats, data);
- if (ret < 0)
- goto out;
- } else {
- ops->get_ethtool_phy_stats(dev, &stats, data);
- }
- } else {
- data = NULL;
- }
+ if (ret)
+ goto out;
- ret = -EFAULT;
- if (copy_to_user(useraddr, &stats, sizeof(stats)))
+ if (copy_to_user(useraddr, &stats, sizeof(stats))) {
+ ret = -EFAULT;
goto out;
+ }
+
useraddr += sizeof(stats);
- if (n_stats && copy_to_user(useraddr, data, array_size(n_stats, sizeof(u64))))
- goto out;
- ret = 0;
+ if (copy_to_user(useraddr, data, array_size(stats.n_stats, sizeof(u64))))
+ ret = -EFAULT;
out:
vfree(data);
if (rc == 0) {
*sk = sock->sk;
(*sk)->sk_allocation = GFP_ATOMIC;
+ (*sk)->sk_use_task_frag = false;
/*
* Unhash it so that IP input processing does not even see it,
* we do not wish this socket to see incoming packets.
return false;
}
+static bool __inet_bhash2_conflict(const struct sock *sk, struct sock *sk2,
+ kuid_t sk_uid, bool relax,
+ bool reuseport_cb_ok, bool reuseport_ok)
+{
+ if (sk->sk_family == AF_INET && ipv6_only_sock(sk2))
+ return false;
+
+ return inet_bind_conflict(sk, sk2, sk_uid, relax,
+ reuseport_cb_ok, reuseport_ok);
+}
+
static bool inet_bhash2_conflict(const struct sock *sk,
const struct inet_bind2_bucket *tb2,
kuid_t sk_uid,
bool relax, bool reuseport_cb_ok,
bool reuseport_ok)
{
+ struct inet_timewait_sock *tw2;
struct sock *sk2;
sk_for_each_bound_bhash2(sk2, &tb2->owners) {
- if (sk->sk_family == AF_INET && ipv6_only_sock(sk2))
- continue;
+ if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax,
+ reuseport_cb_ok, reuseport_ok))
+ return true;
+ }
- if (inet_bind_conflict(sk, sk2, sk_uid, relax,
- reuseport_cb_ok, reuseport_ok))
+ twsk_for_each_bound_bhash2(tw2, &tb2->deathrow) {
+ sk2 = (struct sock *)tw2;
+
+ if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax,
+ reuseport_cb_ok, reuseport_ok))
return true;
}
+
return false;
}
}
EXPORT_SYMBOL(inet_csk_prepare_forced_close);
+static int inet_ulp_can_listen(const struct sock *sk)
+{
+ const struct inet_connection_sock *icsk = inet_csk(sk);
+
+ if (icsk->icsk_ulp_ops && !icsk->icsk_ulp_ops->clone)
+ return -EINVAL;
+
+ return 0;
+}
+
int inet_csk_listen_start(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_sock *inet = inet_sk(sk);
int err;
+ err = inet_ulp_can_listen(sk);
+ if (unlikely(err))
+ return err;
+
reqsk_queue_alloc(&icsk->icsk_accept_queue);
sk->sk_ack_backlog = 0;
#endif
tb->rcv_saddr = sk->sk_rcv_saddr;
INIT_HLIST_HEAD(&tb->owners);
+ INIT_HLIST_HEAD(&tb->deathrow);
hlist_add_head(&tb->node, &head->chain);
}
/* Caller must hold hashbucket lock for this tb with local BH disabled */
void inet_bind2_bucket_destroy(struct kmem_cache *cachep, struct inet_bind2_bucket *tb)
{
- if (hlist_empty(&tb->owners)) {
+ if (hlist_empty(&tb->owners) && hlist_empty(&tb->deathrow)) {
__hlist_del(&tb->node);
kmem_cache_free(cachep, tb);
}
/* Head lock still held and bh's disabled */
inet_bind_hash(sk, tb, tb2, port);
- spin_unlock(&head2->lock);
-
if (sk_unhashed(sk)) {
inet_sk(sk)->inet_sport = htons(port);
inet_ehash_nolisten(sk, (struct sock *)tw, NULL);
}
if (tw)
inet_twsk_bind_unhash(tw, hinfo);
+
+ spin_unlock(&head2->lock);
spin_unlock(&head->lock);
+
if (tw)
inet_twsk_deschedule_put(tw);
local_bh_enable();
void inet_twsk_bind_unhash(struct inet_timewait_sock *tw,
struct inet_hashinfo *hashinfo)
{
+ struct inet_bind2_bucket *tb2 = tw->tw_tb2;
struct inet_bind_bucket *tb = tw->tw_tb;
if (!tb)
__hlist_del(&tw->tw_bind_node);
tw->tw_tb = NULL;
inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
+
+ __hlist_del(&tw->tw_bind2_node);
+ tw->tw_tb2 = NULL;
+ inet_bind2_bucket_destroy(hashinfo->bind2_bucket_cachep, tb2);
+
__sock_put((struct sock *)tw);
}
{
struct inet_hashinfo *hashinfo = tw->tw_dr->hashinfo;
spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash);
- struct inet_bind_hashbucket *bhead;
+ struct inet_bind_hashbucket *bhead, *bhead2;
spin_lock(lock);
sk_nulls_del_node_init_rcu((struct sock *)tw);
/* Disassociate with bind bucket. */
bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), tw->tw_num,
hashinfo->bhash_size)];
+ bhead2 = inet_bhashfn_portaddr(hashinfo, (struct sock *)tw,
+ twsk_net(tw), tw->tw_num);
spin_lock(&bhead->lock);
+ spin_lock(&bhead2->lock);
inet_twsk_bind_unhash(tw, hashinfo);
+ spin_unlock(&bhead2->lock);
spin_unlock(&bhead->lock);
refcount_dec(&tw->tw_dr->tw_refcount);
hlist_add_head(&tw->tw_bind_node, list);
}
+static void inet_twsk_add_bind2_node(struct inet_timewait_sock *tw,
+ struct hlist_head *list)
+{
+ hlist_add_head(&tw->tw_bind2_node, list);
+}
+
/*
* Enter the time wait state. This is called with locally disabled BH.
* Essentially we whip up a timewait bucket, copy the relevant info into it
const struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_ehash_bucket *ehead = inet_ehash_bucket(hashinfo, sk->sk_hash);
spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
- struct inet_bind_hashbucket *bhead;
+ struct inet_bind_hashbucket *bhead, *bhead2;
+
/* Step 1: Put TW into bind hash. Original socket stays there too.
Note, that any socket with inet->num != 0 MUST be bound in
binding cache, even if it is closed.
*/
bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num,
hashinfo->bhash_size)];
+ bhead2 = inet_bhashfn_portaddr(hashinfo, sk, twsk_net(tw), inet->inet_num);
+
spin_lock(&bhead->lock);
+ spin_lock(&bhead2->lock);
+
tw->tw_tb = icsk->icsk_bind_hash;
WARN_ON(!icsk->icsk_bind_hash);
inet_twsk_add_bind_node(tw, &tw->tw_tb->owners);
+
+ tw->tw_tb2 = icsk->icsk_bind2_hash;
+ WARN_ON(!icsk->icsk_bind2_hash);
+ inet_twsk_add_bind2_node(tw, &tw->tw_tb2->deathrow);
+
+ spin_unlock(&bhead2->lock);
spin_unlock(&bhead->lock);
spin_lock(lock);
if (sk->sk_socket)
clear_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
+ err = -EINVAL;
+ if (!ulp_ops->clone && sk->sk_state == TCP_LISTEN)
+ goto out_err;
+
err = ulp_ops->init(sk);
if (err)
goto out_err;
static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
struct raw6_sock *rp)
{
+ struct ipv6_txoptions *opt;
struct sk_buff *skb;
int err = 0;
int offset;
offset = rp->offset;
total_len = inet_sk(sk)->cork.base.length;
+ opt = inet6_sk(sk)->cork.opt;
+ total_len -= opt ? opt->opt_flen : 0;
+
if (offset >= total_len - 1) {
err = -EINVAL;
ip6_flush_pending_frames(sk);
set_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags);
}
+static int mptcp_disconnect(struct sock *sk, int flags);
+
static int mptcp_sendmsg_fastopen(struct sock *sk, struct sock *ssk, struct msghdr *msg,
size_t len, int *copied_syn)
{
lock_sock(ssk);
msg->msg_flags |= MSG_DONTWAIT;
msk->connect_flags = O_NONBLOCK;
- msk->is_sendmsg = 1;
+ msk->fastopening = 1;
ret = tcp_sendmsg_fastopen(ssk, msg, copied_syn, len, NULL);
- msk->is_sendmsg = 0;
+ msk->fastopening = 0;
msg->msg_flags = saved_flags;
release_sock(ssk);
*/
if (ret && ret != -EINPROGRESS && ret != -ERESTARTSYS && ret != -EINTR)
*copied_syn = 0;
+ } else if (ret && ret != -EINPROGRESS) {
+ mptcp_disconnect(sk, 0);
}
return ret;
/* otherwise tcp will dispose of the ssk and subflow ctx */
if (ssk->sk_state == TCP_LISTEN) {
tcp_set_state(ssk, TCP_CLOSE);
- mptcp_subflow_queue_clean(ssk);
+ mptcp_subflow_queue_clean(sk, ssk);
inet_csk_listen_stop(ssk);
mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED);
}
{
struct mptcp_sock *msk = mptcp_sk(sk);
+ /* We are on the fastopen error path. We can't call straight into the
+ * subflows cleanup code due to lock nesting (we are already under
+ * msk->firstsocket lock). Do nothing and leave the cleanup to the
+ * caller.
+ */
+ if (msk->fastopening)
+ return 0;
+
inet_sk_state_store(sk, TCP_CLOSE);
mptcp_stop_timer(sk);
/* if reaching here via the fastopen/sendmsg path, the caller already
* acquired the subflow socket lock, too.
*/
- if (msk->is_sendmsg)
+ if (msk->fastopening)
err = __inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags, 1);
else
err = inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags);
u8 recvmsg_inq:1,
cork:1,
nodelay:1,
- is_sendmsg:1;
+ fastopening:1;
int connect_flags;
struct work_struct work;
struct sk_buff *ooo_last_skb;
struct mptcp_subflow_context *subflow);
void __mptcp_subflow_send_ack(struct sock *ssk);
void mptcp_subflow_reset(struct sock *ssk);
-void mptcp_subflow_queue_clean(struct sock *ssk);
+void mptcp_subflow_queue_clean(struct sock *sk, struct sock *ssk);
void mptcp_sock_graft(struct sock *sk, struct socket *parent);
struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk);
bool __mptcp_close(struct sock *sk, long timeout);
}
}
-void mptcp_subflow_queue_clean(struct sock *listener_ssk)
+void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk)
{
struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue;
struct mptcp_sock *msk, *next, *head = NULL;
do_cancel_work = __mptcp_close(sk, 0);
release_sock(sk);
- if (do_cancel_work)
+ if (do_cancel_work) {
+ /* lockdep will report a false positive ABBA deadlock
+ * between cancel_work_sync and the listener socket.
+ * The involved locks belong to different sockets WRT
+ * the existing AB chain.
+ * Using a per socket key is problematic as key
+ * deregistration requires process context and must be
+ * performed at socket disposal time, in atomic
+ * context.
+ * Just tell lockdep to consider the listener socket
+ * released here.
+ */
+ mutex_release(&listener_sk->sk_lock.dep_map, _RET_IP_);
mptcp_cancel_work(sk);
+ mutex_acquire(&listener_sk->sk_lock.dep_map,
+ SINGLE_DEPTH_NESTING, 0, _RET_IP_);
+ }
sock_put(sk);
}
ret = set->variant->uadt(set, tb, adt, &lineno, flags, retried);
ip_set_unlock(set);
retried = true;
- } while (ret == -EAGAIN &&
- set->variant->resize &&
- (ret = set->variant->resize(set, retried)) == 0);
+ } while (ret == -ERANGE ||
+ (ret == -EAGAIN &&
+ set->variant->resize &&
+ (ret = set->variant->resize(set, retried)) == 0));
if (!ret || (ret == -IPSET_ERR_EXIST && eexist))
return 0;
hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_ip4 *h = set->data;
+ struct hash_ip4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ip4_elem e = { 0 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
- u32 ip = 0, ip_to = 0, hosts;
+ u32 ip = 0, ip_to = 0, hosts, i = 0;
int ret = 0;
if (tb[IPSET_ATTR_LINENO])
hosts = h->netmask == 32 ? 1 : 2 << (32 - h->netmask - 1);
- /* 64bit division is not allowed on 32bit */
- if (((u64)ip_to - ip + 1) >> (32 - h->netmask) > IPSET_MAX_RANGE)
- return -ERANGE;
-
if (retried)
ip = ntohl(h->next.ip);
- for (; ip <= ip_to;) {
+ for (; ip <= ip_to; i++) {
e.ip = htonl(ip);
+ if (i > IPSET_MAX_RANGE) {
+ hash_ip4_data_next(&h->next, &e);
+ return -ERANGE;
+ }
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
return ret;
hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_ipmark4 *h = set->data;
+ struct hash_ipmark4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipmark4_elem e = { };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
- u32 ip, ip_to = 0;
+ u32 ip, ip_to = 0, i = 0;
int ret;
if (tb[IPSET_ATTR_LINENO])
ip_set_mask_from_to(ip, ip_to, cidr);
}
- if (((u64)ip_to - ip + 1) > IPSET_MAX_RANGE)
- return -ERANGE;
-
if (retried)
ip = ntohl(h->next.ip);
- for (; ip <= ip_to; ip++) {
+ for (; ip <= ip_to; ip++, i++) {
e.ip = htonl(ip);
+ if (i > IPSET_MAX_RANGE) {
+ hash_ipmark4_data_next(&h->next, &e);
+ return -ERANGE;
+ }
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_ipport4 *h = set->data;
+ struct hash_ipport4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipport4_elem e = { .ip = 0 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
- u32 ip, ip_to = 0, p = 0, port, port_to;
+ u32 ip, ip_to = 0, p = 0, port, port_to, i = 0;
bool with_ports = false;
int ret;
swap(port, port_to);
}
- if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE)
- return -ERANGE;
-
if (retried)
ip = ntohl(h->next.ip);
for (; ip <= ip_to; ip++) {
p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port)
: port;
- for (; p <= port_to; p++) {
+ for (; p <= port_to; p++, i++) {
e.ip = htonl(ip);
e.port = htons(p);
+ if (i > IPSET_MAX_RANGE) {
+ hash_ipport4_data_next(&h->next, &e);
+ return -ERANGE;
+ }
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_ipportip4 *h = set->data;
+ struct hash_ipportip4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipportip4_elem e = { .ip = 0 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
- u32 ip, ip_to = 0, p = 0, port, port_to;
+ u32 ip, ip_to = 0, p = 0, port, port_to, i = 0;
bool with_ports = false;
int ret;
swap(port, port_to);
}
- if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE)
- return -ERANGE;
-
if (retried)
ip = ntohl(h->next.ip);
for (; ip <= ip_to; ip++) {
p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port)
: port;
- for (; p <= port_to; p++) {
+ for (; p <= port_to; p++, i++) {
e.ip = htonl(ip);
e.port = htons(p);
+ if (i > IPSET_MAX_RANGE) {
+ hash_ipportip4_data_next(&h->next, &e);
+ return -ERANGE;
+ }
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_ipportnet4 *h = set->data;
+ struct hash_ipportnet4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_ipportnet4_elem e = { .cidr = HOST_MASK - 1 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
u32 ip = 0, ip_to = 0, p = 0, port, port_to;
- u32 ip2_from = 0, ip2_to = 0, ip2;
+ u32 ip2_from = 0, ip2_to = 0, ip2, i = 0;
bool with_ports = false;
u8 cidr;
int ret;
swap(port, port_to);
}
- if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE)
- return -ERANGE;
-
ip2_to = ip2_from;
if (tb[IPSET_ATTR_IP2_TO]) {
ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2_TO], &ip2_to);
for (; p <= port_to; p++) {
e.port = htons(p);
do {
+ i++;
e.ip2 = htonl(ip2);
ip2 = ip_set_range_to_cidr(ip2, ip2_to, &cidr);
e.cidr = cidr - 1;
+ if (i > IPSET_MAX_RANGE) {
+ hash_ipportnet4_data_next(&h->next,
+ &e);
+ return -ERANGE;
+ }
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
hash_net4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_net4 *h = set->data;
+ struct hash_net4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_net4_elem e = { .cidr = HOST_MASK };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
- u32 ip = 0, ip_to = 0, ipn, n = 0;
+ u32 ip = 0, ip_to = 0, i = 0;
int ret;
if (tb[IPSET_ATTR_LINENO])
if (ip + UINT_MAX == ip_to)
return -IPSET_ERR_HASH_RANGE;
}
- ipn = ip;
- do {
- ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr);
- n++;
- } while (ipn++ < ip_to);
-
- if (n > IPSET_MAX_RANGE)
- return -ERANGE;
if (retried)
ip = ntohl(h->next.ip);
do {
+ i++;
e.ip = htonl(ip);
+ if (i > IPSET_MAX_RANGE) {
+ hash_net4_data_next(&h->next, &e);
+ return -ERANGE;
+ }
ip = ip_set_range_to_cidr(ip, ip_to, &e.cidr);
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netiface4_elem e = { .cidr = HOST_MASK, .elem = 1 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
- u32 ip = 0, ip_to = 0, ipn, n = 0;
+ u32 ip = 0, ip_to = 0, i = 0;
int ret;
if (tb[IPSET_ATTR_LINENO])
} else {
ip_set_mask_from_to(ip, ip_to, e.cidr);
}
- ipn = ip;
- do {
- ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr);
- n++;
- } while (ipn++ < ip_to);
-
- if (n > IPSET_MAX_RANGE)
- return -ERANGE;
if (retried)
ip = ntohl(h->next.ip);
do {
+ i++;
e.ip = htonl(ip);
+ if (i > IPSET_MAX_RANGE) {
+ hash_netiface4_data_next(&h->next, &e);
+ return -ERANGE;
+ }
ip = ip_set_range_to_cidr(ip, ip_to, &e.cidr);
ret = adtfn(set, &e, &ext, &ext, flags);
hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_netnet4 *h = set->data;
+ struct hash_netnet4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netnet4_elem e = { };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
u32 ip = 0, ip_to = 0;
- u32 ip2 = 0, ip2_from = 0, ip2_to = 0, ipn;
- u64 n = 0, m = 0;
+ u32 ip2 = 0, ip2_from = 0, ip2_to = 0, i = 0;
int ret;
if (tb[IPSET_ATTR_LINENO])
} else {
ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]);
}
- ipn = ip;
- do {
- ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr[0]);
- n++;
- } while (ipn++ < ip_to);
- ipn = ip2_from;
- do {
- ipn = ip_set_range_to_cidr(ipn, ip2_to, &e.cidr[1]);
- m++;
- } while (ipn++ < ip2_to);
-
- if (n*m > IPSET_MAX_RANGE)
- return -ERANGE;
if (retried) {
ip = ntohl(h->next.ip[0]);
e.ip[0] = htonl(ip);
ip = ip_set_range_to_cidr(ip, ip_to, &e.cidr[0]);
do {
+ i++;
e.ip[1] = htonl(ip2);
+ if (i > IPSET_MAX_RANGE) {
+ hash_netnet4_data_next(&h->next, &e);
+ return -ERANGE;
+ }
ip2 = ip_set_range_to_cidr(ip2, ip2_to, &e.cidr[1]);
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_netport4 *h = set->data;
+ struct hash_netport4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netport4_elem e = { .cidr = HOST_MASK - 1 };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
- u32 port, port_to, p = 0, ip = 0, ip_to = 0, ipn;
- u64 n = 0;
+ u32 port, port_to, p = 0, ip = 0, ip_to = 0, i = 0;
bool with_ports = false;
u8 cidr;
int ret;
} else {
ip_set_mask_from_to(ip, ip_to, e.cidr + 1);
}
- ipn = ip;
- do {
- ipn = ip_set_range_to_cidr(ipn, ip_to, &cidr);
- n++;
- } while (ipn++ < ip_to);
-
- if (n*(port_to - port + 1) > IPSET_MAX_RANGE)
- return -ERANGE;
if (retried) {
ip = ntohl(h->next.ip);
e.ip = htonl(ip);
ip = ip_set_range_to_cidr(ip, ip_to, &cidr);
e.cidr = cidr - 1;
- for (; p <= port_to; p++) {
+ for (; p <= port_to; p++, i++) {
e.port = htons(p);
+ if (i > IPSET_MAX_RANGE) {
+ hash_netport4_data_next(&h->next, &e);
+ return -ERANGE;
+ }
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
return ret;
return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
}
+static u32
+hash_netportnet4_range_to_cidr(u32 from, u32 to, u8 *cidr)
+{
+ if (from == 0 && to == UINT_MAX) {
+ *cidr = 0;
+ return to;
+ }
+ return ip_set_range_to_cidr(from, to, cidr);
+}
+
static int
hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct hash_netportnet4 *h = set->data;
+ struct hash_netportnet4 *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
struct hash_netportnet4_elem e = { };
struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
u32 ip = 0, ip_to = 0, p = 0, port, port_to;
- u32 ip2_from = 0, ip2_to = 0, ip2, ipn;
- u64 n = 0, m = 0;
+ u32 ip2_from = 0, ip2_to = 0, ip2, i = 0;
bool with_ports = false;
int ret;
} else {
ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]);
}
- ipn = ip;
- do {
- ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr[0]);
- n++;
- } while (ipn++ < ip_to);
- ipn = ip2_from;
- do {
- ipn = ip_set_range_to_cidr(ipn, ip2_to, &e.cidr[1]);
- m++;
- } while (ipn++ < ip2_to);
-
- if (n*m*(port_to - port + 1) > IPSET_MAX_RANGE)
- return -ERANGE;
if (retried) {
ip = ntohl(h->next.ip[0]);
do {
e.ip[0] = htonl(ip);
- ip = ip_set_range_to_cidr(ip, ip_to, &e.cidr[0]);
+ ip = hash_netportnet4_range_to_cidr(ip, ip_to, &e.cidr[0]);
for (; p <= port_to; p++) {
e.port = htons(p);
do {
+ i++;
e.ip[1] = htonl(ip2);
- ip2 = ip_set_range_to_cidr(ip2, ip2_to,
- &e.cidr[1]);
+ if (i > IPSET_MAX_RANGE) {
+ hash_netportnet4_data_next(&h->next,
+ &e);
+ return -ERANGE;
+ }
+ ip2 = hash_netportnet4_range_to_cidr(ip2,
+ ip2_to, &e.cidr[1]);
ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
return ret;
struct nf_conn *ct;
bool seqadj_needed;
__be16 frag_off;
+ int start;
u8 pnum;
ct = nf_ct_get(skb, &ctinfo);
break;
case NFPROTO_IPV6:
pnum = ipv6_hdr(skb)->nexthdr;
- protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum, &frag_off);
- if (protoff < 0 || (frag_off & htons(~0x7)) != 0)
+ start = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum, &frag_off);
+ if (start < 0 || (frag_off & htons(~0x7)) != 0)
return nf_conntrack_confirm(skb);
+
+ protoff = start;
break;
default:
return nf_conntrack_confirm(skb);
return 0;
}
-static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type,
- struct nft_set *set)
+static int __nft_trans_set_add(const struct nft_ctx *ctx, int msg_type,
+ struct nft_set *set,
+ const struct nft_set_desc *desc)
{
struct nft_trans *trans;
if (trans == NULL)
return -ENOMEM;
- if (msg_type == NFT_MSG_NEWSET && ctx->nla[NFTA_SET_ID] != NULL) {
+ if (msg_type == NFT_MSG_NEWSET && ctx->nla[NFTA_SET_ID] && !desc) {
nft_trans_set_id(trans) =
ntohl(nla_get_be32(ctx->nla[NFTA_SET_ID]));
nft_activate_next(ctx->net, set);
}
nft_trans_set(trans) = set;
+ if (desc) {
+ nft_trans_set_update(trans) = true;
+ nft_trans_set_gc_int(trans) = desc->gc_int;
+ nft_trans_set_timeout(trans) = desc->timeout;
+ }
nft_trans_commit_list_add_tail(ctx->net, trans);
return 0;
}
+static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type,
+ struct nft_set *set)
+{
+ return __nft_trans_set_add(ctx, msg_type, set, NULL);
+}
+
static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set)
{
int err;
static const struct nft_set_ops *
nft_select_set_ops(const struct nft_ctx *ctx,
const struct nlattr * const nla[],
- const struct nft_set_desc *desc,
- enum nft_set_policies policy)
+ const struct nft_set_desc *desc)
{
struct nftables_pernet *nft_net = nft_pernet(ctx->net);
const struct nft_set_ops *ops, *bops;
if (!ops->estimate(desc, flags, &est))
continue;
- switch (policy) {
+ switch (desc->policy) {
case NFT_SET_POL_PERFORMANCE:
if (est.lookup < best.lookup)
break;
static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
const struct nft_set *set, u16 event, u16 flags)
{
- struct nlmsghdr *nlh;
+ u64 timeout = READ_ONCE(set->timeout);
+ u32 gc_int = READ_ONCE(set->gc_int);
u32 portid = ctx->portid;
+ struct nlmsghdr *nlh;
struct nlattr *nest;
u32 seq = ctx->seq;
int i;
nla_put_be32(skb, NFTA_SET_OBJ_TYPE, htonl(set->objtype)))
goto nla_put_failure;
- if (set->timeout &&
+ if (timeout &&
nla_put_be64(skb, NFTA_SET_TIMEOUT,
- nf_jiffies64_to_msecs(set->timeout),
+ nf_jiffies64_to_msecs(timeout),
NFTA_SET_PAD))
goto nla_put_failure;
- if (set->gc_int &&
- nla_put_be32(skb, NFTA_SET_GC_INTERVAL, htonl(set->gc_int)))
+ if (gc_int &&
+ nla_put_be32(skb, NFTA_SET_GC_INTERVAL, htonl(gc_int)))
goto nla_put_failure;
if (set->policy != NFT_SET_POL_PERFORMANCE) {
return err;
}
+static int nft_set_expr_alloc(struct nft_ctx *ctx, struct nft_set *set,
+ const struct nlattr * const *nla,
+ struct nft_expr **exprs, int *num_exprs,
+ u32 flags)
+{
+ struct nft_expr *expr;
+ int err, i;
+
+ if (nla[NFTA_SET_EXPR]) {
+ expr = nft_set_elem_expr_alloc(ctx, set, nla[NFTA_SET_EXPR]);
+ if (IS_ERR(expr)) {
+ err = PTR_ERR(expr);
+ goto err_set_expr_alloc;
+ }
+ exprs[0] = expr;
+ (*num_exprs)++;
+ } else if (nla[NFTA_SET_EXPRESSIONS]) {
+ struct nlattr *tmp;
+ int left;
+
+ if (!(flags & NFT_SET_EXPR)) {
+ err = -EINVAL;
+ goto err_set_expr_alloc;
+ }
+ i = 0;
+ nla_for_each_nested(tmp, nla[NFTA_SET_EXPRESSIONS], left) {
+ if (i == NFT_SET_EXPR_MAX) {
+ err = -E2BIG;
+ goto err_set_expr_alloc;
+ }
+ if (nla_type(tmp) != NFTA_LIST_ELEM) {
+ err = -EINVAL;
+ goto err_set_expr_alloc;
+ }
+ expr = nft_set_elem_expr_alloc(ctx, set, tmp);
+ if (IS_ERR(expr)) {
+ err = PTR_ERR(expr);
+ goto err_set_expr_alloc;
+ }
+ exprs[i++] = expr;
+ (*num_exprs)++;
+ }
+ }
+
+ return 0;
+
+err_set_expr_alloc:
+ for (i = 0; i < *num_exprs; i++)
+ nft_expr_destroy(ctx, exprs[i]);
+
+ return err;
+}
+
+static bool nft_set_is_same(const struct nft_set *set,
+ const struct nft_set_desc *desc,
+ struct nft_expr *exprs[], u32 num_exprs, u32 flags)
+{
+ int i;
+
+ if (set->ktype != desc->ktype ||
+ set->dtype != desc->dtype ||
+ set->flags != flags ||
+ set->klen != desc->klen ||
+ set->dlen != desc->dlen ||
+ set->field_count != desc->field_count ||
+ set->num_exprs != num_exprs)
+ return false;
+
+ for (i = 0; i < desc->field_count; i++) {
+ if (set->field_len[i] != desc->field_len[i])
+ return false;
+ }
+
+ for (i = 0; i < num_exprs; i++) {
+ if (set->exprs[i]->ops != exprs[i]->ops)
+ return false;
+ }
+
+ return true;
+}
+
static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
const struct nlattr * const nla[])
{
- u32 ktype, dtype, flags, policy, gc_int, objtype;
struct netlink_ext_ack *extack = info->extack;
u8 genmask = nft_genmask_next(info->net);
u8 family = info->nfmsg->nfgen_family;
const struct nft_set_ops *ops;
- struct nft_expr *expr = NULL;
struct net *net = info->net;
struct nft_set_desc desc;
struct nft_table *table;
struct nft_set *set;
struct nft_ctx ctx;
size_t alloc_size;
- u64 timeout;
+ int num_exprs = 0;
char *name;
int err, i;
u16 udlen;
+ u32 flags;
u64 size;
if (nla[NFTA_SET_TABLE] == NULL ||
memset(&desc, 0, sizeof(desc));
- ktype = NFT_DATA_VALUE;
+ desc.ktype = NFT_DATA_VALUE;
if (nla[NFTA_SET_KEY_TYPE] != NULL) {
- ktype = ntohl(nla_get_be32(nla[NFTA_SET_KEY_TYPE]));
- if ((ktype & NFT_DATA_RESERVED_MASK) == NFT_DATA_RESERVED_MASK)
+ desc.ktype = ntohl(nla_get_be32(nla[NFTA_SET_KEY_TYPE]));
+ if ((desc.ktype & NFT_DATA_RESERVED_MASK) == NFT_DATA_RESERVED_MASK)
return -EINVAL;
}
return -EOPNOTSUPP;
}
- dtype = 0;
+ desc.dtype = 0;
if (nla[NFTA_SET_DATA_TYPE] != NULL) {
if (!(flags & NFT_SET_MAP))
return -EINVAL;
- dtype = ntohl(nla_get_be32(nla[NFTA_SET_DATA_TYPE]));
- if ((dtype & NFT_DATA_RESERVED_MASK) == NFT_DATA_RESERVED_MASK &&
- dtype != NFT_DATA_VERDICT)
+ desc.dtype = ntohl(nla_get_be32(nla[NFTA_SET_DATA_TYPE]));
+ if ((desc.dtype & NFT_DATA_RESERVED_MASK) == NFT_DATA_RESERVED_MASK &&
+ desc.dtype != NFT_DATA_VERDICT)
return -EINVAL;
- if (dtype != NFT_DATA_VERDICT) {
+ if (desc.dtype != NFT_DATA_VERDICT) {
if (nla[NFTA_SET_DATA_LEN] == NULL)
return -EINVAL;
desc.dlen = ntohl(nla_get_be32(nla[NFTA_SET_DATA_LEN]));
if (!(flags & NFT_SET_OBJECT))
return -EINVAL;
- objtype = ntohl(nla_get_be32(nla[NFTA_SET_OBJ_TYPE]));
- if (objtype == NFT_OBJECT_UNSPEC ||
- objtype > NFT_OBJECT_MAX)
+ desc.objtype = ntohl(nla_get_be32(nla[NFTA_SET_OBJ_TYPE]));
+ if (desc.objtype == NFT_OBJECT_UNSPEC ||
+ desc.objtype > NFT_OBJECT_MAX)
return -EOPNOTSUPP;
} else if (flags & NFT_SET_OBJECT)
return -EINVAL;
else
- objtype = NFT_OBJECT_UNSPEC;
+ desc.objtype = NFT_OBJECT_UNSPEC;
- timeout = 0;
+ desc.timeout = 0;
if (nla[NFTA_SET_TIMEOUT] != NULL) {
if (!(flags & NFT_SET_TIMEOUT))
return -EINVAL;
- err = nf_msecs_to_jiffies64(nla[NFTA_SET_TIMEOUT], &timeout);
+ err = nf_msecs_to_jiffies64(nla[NFTA_SET_TIMEOUT], &desc.timeout);
if (err)
return err;
}
- gc_int = 0;
+ desc.gc_int = 0;
if (nla[NFTA_SET_GC_INTERVAL] != NULL) {
if (!(flags & NFT_SET_TIMEOUT))
return -EINVAL;
- gc_int = ntohl(nla_get_be32(nla[NFTA_SET_GC_INTERVAL]));
+ desc.gc_int = ntohl(nla_get_be32(nla[NFTA_SET_GC_INTERVAL]));
}
- policy = NFT_SET_POL_PERFORMANCE;
+ desc.policy = NFT_SET_POL_PERFORMANCE;
if (nla[NFTA_SET_POLICY] != NULL)
- policy = ntohl(nla_get_be32(nla[NFTA_SET_POLICY]));
+ desc.policy = ntohl(nla_get_be32(nla[NFTA_SET_POLICY]));
if (nla[NFTA_SET_DESC] != NULL) {
err = nf_tables_set_desc_parse(&desc, nla[NFTA_SET_DESC]);
return PTR_ERR(set);
}
} else {
+ struct nft_expr *exprs[NFT_SET_EXPR_MAX] = {};
+
if (info->nlh->nlmsg_flags & NLM_F_EXCL) {
NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]);
return -EEXIST;
if (info->nlh->nlmsg_flags & NLM_F_REPLACE)
return -EOPNOTSUPP;
- return 0;
+ err = nft_set_expr_alloc(&ctx, set, nla, exprs, &num_exprs, flags);
+ if (err < 0)
+ return err;
+
+ err = 0;
+ if (!nft_set_is_same(set, &desc, exprs, num_exprs, flags)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]);
+ err = -EEXIST;
+ }
+
+ for (i = 0; i < num_exprs; i++)
+ nft_expr_destroy(&ctx, exprs[i]);
+
+ if (err < 0)
+ return err;
+
+ return __nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set, &desc);
}
if (!(info->nlh->nlmsg_flags & NLM_F_CREATE))
return -ENOENT;
- ops = nft_select_set_ops(&ctx, nla, &desc, policy);
+ ops = nft_select_set_ops(&ctx, nla, &desc);
if (IS_ERR(ops))
return PTR_ERR(ops);
set->table = table;
write_pnet(&set->net, net);
set->ops = ops;
- set->ktype = ktype;
+ set->ktype = desc.ktype;
set->klen = desc.klen;
- set->dtype = dtype;
- set->objtype = objtype;
+ set->dtype = desc.dtype;
+ set->objtype = desc.objtype;
set->dlen = desc.dlen;
set->flags = flags;
set->size = desc.size;
- set->policy = policy;
+ set->policy = desc.policy;
set->udlen = udlen;
set->udata = udata;
- set->timeout = timeout;
- set->gc_int = gc_int;
+ set->timeout = desc.timeout;
+ set->gc_int = desc.gc_int;
set->field_count = desc.field_count;
for (i = 0; i < desc.field_count; i++)
if (err < 0)
goto err_set_init;
- if (nla[NFTA_SET_EXPR]) {
- expr = nft_set_elem_expr_alloc(&ctx, set, nla[NFTA_SET_EXPR]);
- if (IS_ERR(expr)) {
- err = PTR_ERR(expr);
- goto err_set_expr_alloc;
- }
- set->exprs[0] = expr;
- set->num_exprs++;
- } else if (nla[NFTA_SET_EXPRESSIONS]) {
- struct nft_expr *expr;
- struct nlattr *tmp;
- int left;
-
- if (!(flags & NFT_SET_EXPR)) {
- err = -EINVAL;
- goto err_set_expr_alloc;
- }
- i = 0;
- nla_for_each_nested(tmp, nla[NFTA_SET_EXPRESSIONS], left) {
- if (i == NFT_SET_EXPR_MAX) {
- err = -E2BIG;
- goto err_set_expr_alloc;
- }
- if (nla_type(tmp) != NFTA_LIST_ELEM) {
- err = -EINVAL;
- goto err_set_expr_alloc;
- }
- expr = nft_set_elem_expr_alloc(&ctx, set, tmp);
- if (IS_ERR(expr)) {
- err = PTR_ERR(expr);
- goto err_set_expr_alloc;
- }
- set->exprs[i++] = expr;
- set->num_exprs++;
- }
- }
+ err = nft_set_expr_alloc(&ctx, set, nla, set->exprs, &num_exprs, flags);
+ if (err < 0)
+ goto err_set_destroy;
+ set->num_exprs = num_exprs;
set->handle = nf_tables_alloc_handle(table);
err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set);
err_set_expr_alloc:
for (i = 0; i < set->num_exprs; i++)
nft_expr_destroy(&ctx, set->exprs[i]);
-
+err_set_destroy:
ops->destroy(set);
err_set_init:
kfree(set->name);
return err;
} else if (set->flags & NFT_SET_TIMEOUT &&
!(flags & NFT_SET_ELEM_INTERVAL_END)) {
- timeout = set->timeout;
+ timeout = READ_ONCE(set->timeout);
}
expiration = 0;
if (err < 0)
goto err_parse_key_end;
- if (timeout != set->timeout) {
+ if (timeout != READ_ONCE(set->timeout)) {
err = nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT);
if (err < 0)
goto err_parse_key_end;
nft_flow_rule_destroy(nft_trans_flow_rule(trans));
break;
case NFT_MSG_NEWSET:
- nft_clear(net, nft_trans_set(trans));
- /* This avoids hitting -EBUSY when deleting the table
- * from the transaction.
- */
- if (nft_set_is_anonymous(nft_trans_set(trans)) &&
- !list_empty(&nft_trans_set(trans)->bindings))
- trans->ctx.table->use--;
+ if (nft_trans_set_update(trans)) {
+ struct nft_set *set = nft_trans_set(trans);
+ WRITE_ONCE(set->timeout, nft_trans_set_timeout(trans));
+ WRITE_ONCE(set->gc_int, nft_trans_set_gc_int(trans));
+ } else {
+ nft_clear(net, nft_trans_set(trans));
+ /* This avoids hitting -EBUSY when deleting the table
+ * from the transaction.
+ */
+ if (nft_set_is_anonymous(nft_trans_set(trans)) &&
+ !list_empty(&nft_trans_set(trans)->bindings))
+ trans->ctx.table->use--;
+ }
nf_tables_set_notify(&trans->ctx, nft_trans_set(trans),
NFT_MSG_NEWSET, GFP_KERNEL);
nft_trans_destroy(trans);
nft_trans_destroy(trans);
break;
case NFT_MSG_NEWSET:
+ if (nft_trans_set_update(trans)) {
+ nft_trans_destroy(trans);
+ break;
+ }
trans->ctx.table->use--;
if (nft_trans_set_bound(trans)) {
nft_trans_destroy(trans);
u32 dev_idx, se_idx;
u8 *apdu;
size_t apdu_len;
+ int rc;
if (!info->attrs[NFC_ATTR_DEVICE_INDEX] ||
!info->attrs[NFC_ATTR_SE_INDEX] ||
if (!dev)
return -ENODEV;
- if (!dev->ops || !dev->ops->se_io)
- return -ENOTSUPP;
+ if (!dev->ops || !dev->ops->se_io) {
+ rc = -EOPNOTSUPP;
+ goto put_dev;
+ }
apdu_len = nla_len(info->attrs[NFC_ATTR_SE_APDU]);
- if (apdu_len == 0)
- return -EINVAL;
+ if (apdu_len == 0) {
+ rc = -EINVAL;
+ goto put_dev;
+ }
apdu = nla_data(info->attrs[NFC_ATTR_SE_APDU]);
- if (!apdu)
- return -EINVAL;
+ if (!apdu) {
+ rc = -EINVAL;
+ goto put_dev;
+ }
ctx = kzalloc(sizeof(struct se_io_ctx), GFP_KERNEL);
- if (!ctx)
- return -ENOMEM;
+ if (!ctx) {
+ rc = -ENOMEM;
+ goto put_dev;
+ }
ctx->dev_idx = dev_idx;
ctx->se_idx = se_idx;
- return nfc_se_io(dev, se_idx, apdu, apdu_len, se_io_cb, ctx);
+ rc = nfc_se_io(dev, se_idx, apdu, apdu_len, se_io_cb, ctx);
+
+put_dev:
+ nfc_put_device(dev);
+ return rc;
}
static int nfc_genl_vendor_cmd(struct sk_buff *skb,
subcmd = nla_get_u32(info->attrs[NFC_ATTR_VENDOR_SUBCMD]);
dev = nfc_get_device(dev_idx);
- if (!dev || !dev->vendor_cmds || !dev->n_vendor_cmds)
+ if (!dev)
return -ENODEV;
+ if (!dev->vendor_cmds || !dev->n_vendor_cmds) {
+ err = -ENODEV;
+ goto put_dev;
+ }
+
if (info->attrs[NFC_ATTR_VENDOR_DATA]) {
data = nla_data(info->attrs[NFC_ATTR_VENDOR_DATA]);
data_len = nla_len(info->attrs[NFC_ATTR_VENDOR_DATA]);
- if (data_len == 0)
- return -EINVAL;
+ if (data_len == 0) {
+ err = -EINVAL;
+ goto put_dev;
+ }
} else {
data = NULL;
data_len = 0;
dev->cur_cmd_info = info;
err = cmd->doit(dev, data, data_len);
dev->cur_cmd_info = NULL;
- return err;
+ goto put_dev;
}
- return -EOPNOTSUPP;
+ err = -EOPNOTSUPP;
+
+put_dev:
+ nfc_put_device(dev);
+ return err;
}
/* message building helper */
vport->upcall_stats = netdev_alloc_pcpu_stats(struct vport_upcall_stats_percpu);
if (!vport->upcall_stats) {
err = -ENOMEM;
- goto err_destroy_portids;
+ goto err_destroy_vport;
}
err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
ovs_notify(&dp_datapath_genl_family, reply, info);
return 0;
+err_destroy_vport:
+ ovs_dp_detach_port(vport);
err_destroy_portids:
kfree(rcu_dereference_raw(dp->upcall_portids));
err_unlock_and_destroy_meters:
vport->upcall_stats = netdev_alloc_pcpu_stats(struct vport_upcall_stats_percpu);
if (!vport->upcall_stats) {
err = -ENOMEM;
- goto exit_unlock_free;
+ goto exit_unlock_free_vport;
}
err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info),
ovs_notify(&dp_vport_genl_family, reply, info);
return 0;
+exit_unlock_free_vport:
+ ovs_dp_detach_port(vport);
exit_unlock_free:
ovs_unlock();
kfree_skb(reply);
call_accept.o \
call_event.o \
call_object.o \
+ call_state.o \
conn_client.o \
conn_event.o \
conn_object.o \
if (service_id) {
write_lock(&local->services_lock);
- if (rcu_access_pointer(local->service))
+ if (local->service)
goto service_in_use;
rx->local = local;
- rcu_assign_pointer(local->service, rx);
+ local->service = rx;
write_unlock(&local->services_lock);
rx->sk.sk_state = RXRPC_SERVER_BOUND;
mutex_unlock(&call->user_mutex);
}
- rxrpc_put_peer(cp.peer, rxrpc_peer_put_discard_tmp);
_leave(" = %p", call);
return call;
}
* @sock: The socket the call is on
* @call: The call to check
*
- * Allow a kernel service to find out whether a call is still alive -
- * ie. whether it has completed.
+ * Allow a kernel service to find out whether a call is still alive - whether
+ * it has completed successfully and all received data has been consumed.
*/
bool rxrpc_kernel_check_life(const struct socket *sock,
const struct rxrpc_call *call)
{
- return call->state != RXRPC_CALL_COMPLETE;
+ if (!rxrpc_call_is_complete(call))
+ return true;
+ if (call->completion != RXRPC_CALL_SUCCEEDED)
+ return false;
+ return !skb_queue_empty(&call->recvmsg_queue);
}
EXPORT_SYMBOL(rxrpc_kernel_check_life);
sk->sk_state = RXRPC_CLOSE;
- if (rx->local && rcu_access_pointer(rx->local->service) == rx) {
+ if (rx->local && rx->local->service == rx) {
write_lock(&rx->local->services_lock);
- rcu_assign_pointer(rx->local->service, NULL);
+ rx->local->service = NULL;
write_unlock(&rx->local->services_lock);
}
static int __init af_rxrpc_init(void)
{
int ret = -1;
- unsigned int tmp;
BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > sizeof_field(struct sk_buff, cb));
- get_random_bytes(&tmp, sizeof(tmp));
- tmp &= 0x3fffffff;
- if (tmp == 0)
- tmp = 1;
- idr_set_cursor(&rxrpc_client_conn_ids, tmp);
-
ret = -ENOMEM;
rxrpc_call_jar = kmem_cache_create(
"rxrpc_call_jar", sizeof(struct rxrpc_call), 0,
* are released.
*/
rcu_barrier();
- rxrpc_destroy_client_conn_ids();
destroy_workqueue(rxrpc_workqueue);
rxrpc_exit_security();
enum rxrpc_skb_mark {
RXRPC_SKB_MARK_PACKET, /* Received packet */
RXRPC_SKB_MARK_ERROR, /* Error notification */
+ RXRPC_SKB_MARK_SERVICE_CONN_SECURED, /* Service connection response has been verified */
RXRPC_SKB_MARK_REJECT_BUSY, /* Reject with BUSY */
RXRPC_SKB_MARK_REJECT_ABORT, /* Reject with ABORT (code in skb->priority) */
};
bool live;
- bool kill_all_client_conns;
atomic_t nr_client_conns;
- spinlock_t client_conn_cache_lock; /* Lock for ->*_client_conns */
- struct mutex client_conn_discard_lock; /* Prevent multiple discarders */
- struct list_head idle_client_conns;
- struct work_struct client_conn_reaper;
- struct timer_list client_conn_reap_timer;
struct hlist_head local_endpoints;
struct mutex local_mutex; /* Lock for ->local_endpoints */
* - max 48 bytes (struct sk_buff::cb)
*/
struct rxrpc_skb_priv {
+ struct rxrpc_connection *conn; /* Connection referred to (poke packet) */
u16 offset; /* Offset of data */
u16 len; /* Length of data */
u8 flags;
/* respond to a challenge */
int (*respond_to_challenge)(struct rxrpc_connection *,
- struct sk_buff *,
- u32 *);
+ struct sk_buff *);
/* verify a response */
int (*verify_response)(struct rxrpc_connection *,
- struct sk_buff *,
- u32 *);
+ struct sk_buff *);
/* clear connection security */
void (*clear)(struct rxrpc_connection *);
struct rcu_head rcu;
atomic_t active_users; /* Number of users of the local endpoint */
refcount_t ref; /* Number of references to the structure */
- struct rxrpc_net *rxnet; /* The network ns in which this resides */
+ struct net *net; /* The network namespace */
+ struct rxrpc_net *rxnet; /* Our bits in the network namespace */
struct hlist_node link;
struct socket *socket; /* my UDP socket */
struct task_struct *io_thread;
struct completion io_thread_ready; /* Indication that the I/O thread started */
- struct rxrpc_sock __rcu *service; /* Service(s) listening on this endpoint */
+ struct rxrpc_sock *service; /* Service(s) listening on this endpoint */
struct rw_semaphore defrag_sem; /* control re-enablement of IP DF bit */
struct sk_buff_head rx_queue; /* Received packets */
+ struct list_head conn_attend_q; /* Conns requiring immediate attention */
struct list_head call_attend_q; /* Calls requiring immediate attention */
+
struct rb_root client_bundles; /* Client connection bundles by socket params */
spinlock_t client_bundles_lock; /* Lock for client_bundles */
+ bool kill_all_client_conns;
+ struct list_head idle_client_conns;
+ struct timer_list client_conn_reap_timer;
+ unsigned long client_conn_flags;
+#define RXRPC_CLIENT_CONN_REAP_TIMER 0 /* The client conn reap timer expired */
+
spinlock_t lock; /* access lock */
rwlock_t services_lock; /* lock for services list */
int debug_id; /* debug ID for printks */
bool dead;
bool service_closed; /* Service socket closed */
+ struct idr conn_ids; /* List of connection IDs */
+ struct list_head new_client_calls; /* Newly created client calls need connection */
+ spinlock_t client_call_lock; /* Lock for ->new_client_calls */
struct sockaddr_rxrpc srx; /* local address */
};
struct rxrpc_conn_parameters {
struct rxrpc_local *local; /* Representation of local endpoint */
- struct rxrpc_peer *peer; /* Remote endpoint */
struct key *key; /* Security details */
bool exclusive; /* T if conn is exclusive */
bool upgrade; /* T if service ID can be upgraded */
};
/*
+ * Call completion condition (state == RXRPC_CALL_COMPLETE).
+ */
+enum rxrpc_call_completion {
+ RXRPC_CALL_SUCCEEDED, /* - Normal termination */
+ RXRPC_CALL_REMOTELY_ABORTED, /* - call aborted by peer */
+ RXRPC_CALL_LOCALLY_ABORTED, /* - call aborted locally on error or close */
+ RXRPC_CALL_LOCAL_ERROR, /* - call failed due to local error */
+ RXRPC_CALL_NETWORK_ERROR, /* - call terminated by network error */
+ NR__RXRPC_CALL_COMPLETIONS
+};
+
+/*
* Bits in the connection flags.
*/
enum rxrpc_conn_flag {
- RXRPC_CONN_HAS_IDR, /* Has a client conn ID assigned */
RXRPC_CONN_IN_SERVICE_CONNS, /* Conn is in peer->service_conns */
RXRPC_CONN_DONT_REUSE, /* Don't reuse this connection */
RXRPC_CONN_PROBING_FOR_UPGRADE, /* Probing for service upgrade */
*/
enum rxrpc_conn_event {
RXRPC_CONN_EV_CHALLENGE, /* Send challenge packet */
+ RXRPC_CONN_EV_ABORT_CALLS, /* Abort attached calls */
};
/*
*/
enum rxrpc_conn_proto_state {
RXRPC_CONN_UNUSED, /* Connection not yet attempted */
+ RXRPC_CONN_CLIENT_UNSECURED, /* Client connection needs security init */
RXRPC_CONN_CLIENT, /* Client connection */
RXRPC_CONN_SERVICE_PREALLOC, /* Service connection preallocation */
RXRPC_CONN_SERVICE_UNSECURED, /* Service unsecured connection */
RXRPC_CONN_SERVICE_CHALLENGING, /* Service challenging for security */
RXRPC_CONN_SERVICE, /* Service secured connection */
- RXRPC_CONN_REMOTELY_ABORTED, /* Conn aborted by peer */
- RXRPC_CONN_LOCALLY_ABORTED, /* Conn aborted locally */
+ RXRPC_CONN_ABORTED, /* Conn aborted */
RXRPC_CONN__NR_STATES
};
struct rxrpc_local *local; /* Representation of local endpoint */
struct rxrpc_peer *peer; /* Remote endpoint */
struct key *key; /* Security details */
+ const struct rxrpc_security *security; /* applied security module */
refcount_t ref;
atomic_t active; /* Number of active users */
unsigned int debug_id;
u32 security_level; /* Security level selected */
u16 service_id; /* Service ID for this connection */
bool try_upgrade; /* True if the bundle is attempting upgrade */
- bool alloc_conn; /* True if someone's getting a conn */
bool exclusive; /* T if conn is exclusive */
bool upgrade; /* T if service ID can be upgraded */
- short alloc_error; /* Error from last conn allocation */
- spinlock_t channel_lock;
+ unsigned short alloc_error; /* Error from last conn allocation */
struct rb_node local_node; /* Node in local->client_conns */
struct list_head waiting_calls; /* Calls waiting for channels */
unsigned long avail_chans; /* Mask of available channels */
struct rxrpc_peer *peer; /* Remote endpoint */
struct rxrpc_net *rxnet; /* Network namespace to which call belongs */
struct key *key; /* Security details */
+ struct list_head attend_link; /* Link in local->conn_attend_q */
refcount_t ref;
atomic_t active; /* Active count for service conns */
unsigned char act_chans; /* Mask of active channels */
struct rxrpc_channel {
unsigned long final_ack_at; /* Time at which to issue final ACK */
- struct rxrpc_call __rcu *call; /* Active call */
+ struct rxrpc_call *call; /* Active call */
unsigned int call_debug_id; /* call->debug_id */
u32 call_id; /* ID of current call */
u32 call_counter; /* Call ID counter */
struct list_head link; /* link in master connection list */
struct sk_buff_head rx_queue; /* received conn-level packets */
+ struct mutex security_lock; /* Lock for security management */
const struct rxrpc_security *security; /* applied security module */
union {
struct {
unsigned long idle_timestamp; /* Time at which last became idle */
spinlock_t state_lock; /* state-change lock */
enum rxrpc_conn_proto_state state; /* current state of connection */
- u32 abort_code; /* Abort code of connection abort */
+ enum rxrpc_call_completion completion; /* Completion condition */
+ s32 abort_code; /* Abort code of connection abort */
int debug_id; /* debug ID for printks */
atomic_t serial; /* packet serial number counter */
unsigned int hi_serial; /* highest serial number received */
RXRPC_CALL_KERNEL, /* The call was made by the kernel */
RXRPC_CALL_UPGRADE, /* Service upgrade was requested for the call */
RXRPC_CALL_EXCLUSIVE, /* The call uses a once-only connection */
- RXRPC_CALL_RX_IS_IDLE, /* Reception is idle - send an ACK */
+ RXRPC_CALL_RX_IS_IDLE, /* recvmsg() is idle - send an ACK */
+ RXRPC_CALL_RECVMSG_READ_ALL, /* recvmsg() read all of the received data */
};
/*
};
/*
- * Call completion condition (state == RXRPC_CALL_COMPLETE).
- */
-enum rxrpc_call_completion {
- RXRPC_CALL_SUCCEEDED, /* - Normal termination */
- RXRPC_CALL_REMOTELY_ABORTED, /* - call aborted by peer */
- RXRPC_CALL_LOCALLY_ABORTED, /* - call aborted locally on error or close */
- RXRPC_CALL_LOCAL_ERROR, /* - call failed due to local error */
- RXRPC_CALL_NETWORK_ERROR, /* - call terminated by network error */
- NR__RXRPC_CALL_COMPLETIONS
-};
-
-/*
* Call Tx congestion management modes.
*/
enum rxrpc_congest_mode {
struct rxrpc_call {
struct rcu_head rcu;
struct rxrpc_connection *conn; /* connection carrying call */
+ struct rxrpc_bundle *bundle; /* Connection bundle to use */
struct rxrpc_peer *peer; /* Peer record for remote address */
struct rxrpc_local *local; /* Representation of local endpoint */
struct rxrpc_sock __rcu *socket; /* socket responsible */
struct work_struct destroyer; /* In-process-context destroyer */
rxrpc_notify_rx_t notify_rx; /* kernel service Rx notification function */
struct list_head link; /* link in master call list */
- struct list_head chan_wait_link; /* Link in conn->bundle->waiting_calls */
+ struct list_head wait_link; /* Link in local->new_client_calls */
struct hlist_node error_link; /* link in error distribution list */
struct list_head accept_link; /* Link in rx->acceptq */
struct list_head recvmsg_link; /* Link in rx->recvmsg_q */
unsigned long flags;
unsigned long events;
spinlock_t notify_lock; /* Kernel notification lock */
- rwlock_t state_lock; /* lock for state transition */
- u32 abort_code; /* Local/remote abort code */
+ unsigned int send_abort_why; /* Why the abort [enum rxrpc_abort_reason] */
+ s32 send_abort; /* Abort code to be sent */
+ short send_abort_err; /* Error to be associated with the abort */
+ rxrpc_seq_t send_abort_seq; /* DATA packet that incurred the abort (or 0) */
+ s32 abort_code; /* Local/remote abort code */
int error; /* Local error incurred */
- enum rxrpc_call_state state; /* current state of call */
+ enum rxrpc_call_state _state; /* Current state of call (needs barrier) */
enum rxrpc_call_completion completion; /* Call completion condition */
refcount_t ref;
u8 security_ix; /* Security type */
*/
int rxrpc_service_prealloc(struct rxrpc_sock *, gfp_t);
void rxrpc_discard_prealloc(struct rxrpc_sock *);
-int rxrpc_new_incoming_call(struct rxrpc_local *, struct rxrpc_peer *,
- struct rxrpc_connection *, struct sockaddr_rxrpc *,
- struct sk_buff *);
+bool rxrpc_new_incoming_call(struct rxrpc_local *local,
+ struct rxrpc_peer *peer,
+ struct rxrpc_connection *conn,
+ struct sockaddr_rxrpc *peer_srx,
+ struct sk_buff *skb);
void rxrpc_accept_incoming_calls(struct rxrpc_local *);
int rxrpc_user_charge_accept(struct rxrpc_sock *, unsigned long);
unsigned long now,
enum rxrpc_timer_trace why);
-void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb);
+bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb);
/*
* call_object.c
struct sockaddr_rxrpc *,
struct rxrpc_call_params *, gfp_t,
unsigned int);
+void rxrpc_start_call_timer(struct rxrpc_call *call);
void rxrpc_incoming_call(struct rxrpc_sock *, struct rxrpc_call *,
struct sk_buff *);
void rxrpc_release_call(struct rxrpc_sock *, struct rxrpc_call *);
}
/*
+ * call_state.c
+ */
+bool rxrpc_set_call_completion(struct rxrpc_call *call,
+ enum rxrpc_call_completion compl,
+ u32 abort_code,
+ int error);
+bool rxrpc_call_completed(struct rxrpc_call *call);
+bool rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq,
+ u32 abort_code, int error, enum rxrpc_abort_reason why);
+void rxrpc_prefail_call(struct rxrpc_call *call, enum rxrpc_call_completion compl,
+ int error);
+
+static inline void rxrpc_set_call_state(struct rxrpc_call *call,
+ enum rxrpc_call_state state)
+{
+ /* Order write of completion info before write of ->state. */
+ smp_store_release(&call->_state, state);
+ wake_up(&call->waitq);
+}
+
+static inline enum rxrpc_call_state __rxrpc_call_state(const struct rxrpc_call *call)
+{
+ return call->_state; /* Only inside I/O thread */
+}
+
+static inline bool __rxrpc_call_is_complete(const struct rxrpc_call *call)
+{
+ return __rxrpc_call_state(call) == RXRPC_CALL_COMPLETE;
+}
+
+static inline enum rxrpc_call_state rxrpc_call_state(const struct rxrpc_call *call)
+{
+ /* Order read ->state before read of completion info. */
+ return smp_load_acquire(&call->_state);
+}
+
+static inline bool rxrpc_call_is_complete(const struct rxrpc_call *call)
+{
+ return rxrpc_call_state(call) == RXRPC_CALL_COMPLETE;
+}
+
+static inline bool rxrpc_call_has_failed(const struct rxrpc_call *call)
+{
+ return rxrpc_call_is_complete(call) && call->completion != RXRPC_CALL_SUCCEEDED;
+}
+
+/*
* conn_client.c
*/
extern unsigned int rxrpc_reap_client_connections;
extern unsigned long rxrpc_conn_idle_client_expiry;
extern unsigned long rxrpc_conn_idle_client_fast_expiry;
-extern struct idr rxrpc_client_conn_ids;
-void rxrpc_destroy_client_conn_ids(void);
+void rxrpc_purge_client_connections(struct rxrpc_local *local);
struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *, enum rxrpc_bundle_trace);
void rxrpc_put_bundle(struct rxrpc_bundle *, enum rxrpc_bundle_trace);
-int rxrpc_connect_call(struct rxrpc_sock *, struct rxrpc_call *,
- struct rxrpc_conn_parameters *, struct sockaddr_rxrpc *,
- gfp_t);
+int rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t gfp);
+void rxrpc_connect_client_calls(struct rxrpc_local *local);
void rxrpc_expose_client_call(struct rxrpc_call *);
void rxrpc_disconnect_client_call(struct rxrpc_bundle *, struct rxrpc_call *);
+void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle);
void rxrpc_put_client_conn(struct rxrpc_connection *, enum rxrpc_conn_trace);
-void rxrpc_discard_expired_client_conns(struct work_struct *);
-void rxrpc_destroy_all_client_connections(struct rxrpc_net *);
+void rxrpc_discard_expired_client_conns(struct rxrpc_local *local);
void rxrpc_clean_up_local_conns(struct rxrpc_local *);
/*
* conn_event.c
*/
+void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, struct sk_buff *skb,
+ unsigned int channel);
+int rxrpc_abort_conn(struct rxrpc_connection *conn, struct sk_buff *skb,
+ s32 abort_code, int err, enum rxrpc_abort_reason why);
void rxrpc_process_connection(struct work_struct *);
void rxrpc_process_delayed_final_acks(struct rxrpc_connection *, bool);
-int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb);
+bool rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb);
+void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb);
+
+static inline bool rxrpc_is_conn_aborted(const struct rxrpc_connection *conn)
+{
+ /* Order reading the abort info after the state check. */
+ return smp_load_acquire(&conn->state) == RXRPC_CONN_ABORTED;
+}
/*
* conn_object.c
extern unsigned int rxrpc_connection_expiry;
extern unsigned int rxrpc_closed_conn_expiry;
+void rxrpc_poke_conn(struct rxrpc_connection *conn, enum rxrpc_conn_trace why);
struct rxrpc_connection *rxrpc_alloc_connection(struct rxrpc_net *, gfp_t);
struct rxrpc_connection *rxrpc_find_client_connection_rcu(struct rxrpc_local *,
struct sockaddr_rxrpc *,
*/
int rxrpc_encap_rcv(struct sock *, struct sk_buff *);
void rxrpc_error_report(struct sock *);
+bool rxrpc_direct_abort(struct sk_buff *skb, enum rxrpc_abort_reason why,
+ s32 abort_code, int err);
int rxrpc_io_thread(void *data);
static inline void rxrpc_wake_up_io_thread(struct rxrpc_local *local)
{
wake_up_process(local->io_thread);
}
+static inline bool rxrpc_protocol_error(struct sk_buff *skb, enum rxrpc_abort_reason why)
+{
+ return rxrpc_direct_abort(skb, why, RX_PROTOCOL_ERROR, -EPROTO);
+}
+
/*
* insecure.c
*/
int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb);
int rxrpc_send_abort_packet(struct rxrpc_call *);
int rxrpc_send_data_packet(struct rxrpc_call *, struct rxrpc_txbuf *);
+void rxrpc_send_conn_abort(struct rxrpc_connection *conn);
void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb);
void rxrpc_send_keepalive(struct rxrpc_peer *);
void rxrpc_transmit_one(struct rxrpc_call *call, struct rxrpc_txbuf *txb);
*/
struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *,
const struct sockaddr_rxrpc *);
-struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *, struct rxrpc_local *,
- struct sockaddr_rxrpc *, gfp_t);
+struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local,
+ struct sockaddr_rxrpc *srx, gfp_t gfp);
struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t,
enum rxrpc_peer_trace);
-void rxrpc_new_incoming_peer(struct rxrpc_sock *, struct rxrpc_local *,
- struct rxrpc_peer *);
+void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer);
void rxrpc_destroy_all_peers(struct rxrpc_net *);
struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *, enum rxrpc_peer_trace);
struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *, enum rxrpc_peer_trace);
* recvmsg.c
*/
void rxrpc_notify_socket(struct rxrpc_call *);
-bool __rxrpc_set_call_completion(struct rxrpc_call *, enum rxrpc_call_completion, u32, int);
-bool rxrpc_set_call_completion(struct rxrpc_call *, enum rxrpc_call_completion, u32, int);
-bool __rxrpc_call_completed(struct rxrpc_call *);
-bool rxrpc_call_completed(struct rxrpc_call *);
-bool __rxrpc_abort_call(const char *, struct rxrpc_call *, rxrpc_seq_t, u32, int);
-bool rxrpc_abort_call(const char *, struct rxrpc_call *, rxrpc_seq_t, u32, int);
int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int);
/*
* Abort a call due to a protocol error.
*/
-static inline bool __rxrpc_abort_eproto(struct rxrpc_call *call,
- struct sk_buff *skb,
- const char *eproto_why,
- const char *why,
- u32 abort_code)
+static inline int rxrpc_abort_eproto(struct rxrpc_call *call,
+ struct sk_buff *skb,
+ s32 abort_code,
+ enum rxrpc_abort_reason why)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
- trace_rxrpc_rx_eproto(call, sp->hdr.serial, eproto_why);
- return rxrpc_abort_call(why, call, sp->hdr.seq, abort_code, -EPROTO);
+ rxrpc_abort_call(call, sp->hdr.seq, abort_code, -EPROTO, why);
+ return -EPROTO;
}
-#define rxrpc_abort_eproto(call, skb, eproto_why, abort_why, abort_code) \
- __rxrpc_abort_eproto((call), (skb), tracepoint_string(eproto_why), \
- (abort_why), (abort_code))
-
/*
* rtt.c
*/
/*
* sendmsg.c
*/
+bool rxrpc_propose_abort(struct rxrpc_call *call, s32 abort_code, int error,
+ enum rxrpc_abort_reason why);
int rxrpc_do_sendmsg(struct rxrpc_sock *, struct msghdr *, size_t);
/*
if (!call)
return -ENOMEM;
call->flags |= (1 << RXRPC_CALL_IS_SERVICE);
- call->state = RXRPC_CALL_SERVER_PREALLOC;
+ rxrpc_set_call_state(call, RXRPC_CALL_SERVER_PREALLOC);
__set_bit(RXRPC_CALL_EV_INITIAL_PING, &call->events);
trace_rxrpc_call(call->debug_id, refcount_read(&call->ref),
(peer_tail + 1) &
(RXRPC_BACKLOG_MAX - 1));
- rxrpc_new_incoming_peer(rx, local, peer);
+ rxrpc_new_incoming_peer(local, peer);
}
/* Now allocate and set up the connection */
* If we want to report an error, we mark the skb with the packet type and
* abort code and return false.
*/
-int rxrpc_new_incoming_call(struct rxrpc_local *local,
- struct rxrpc_peer *peer,
- struct rxrpc_connection *conn,
- struct sockaddr_rxrpc *peer_srx,
- struct sk_buff *skb)
+bool rxrpc_new_incoming_call(struct rxrpc_local *local,
+ struct rxrpc_peer *peer,
+ struct rxrpc_connection *conn,
+ struct sockaddr_rxrpc *peer_srx,
+ struct sk_buff *skb)
{
const struct rxrpc_security *sec = NULL;
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
_enter("");
- /* Don't set up a call for anything other than the first DATA packet. */
- if (sp->hdr.seq != 1 ||
- sp->hdr.type != RXRPC_PACKET_TYPE_DATA)
- return 0; /* Just discard */
+ /* Don't set up a call for anything other than a DATA packet. */
+ if (sp->hdr.type != RXRPC_PACKET_TYPE_DATA)
+ return rxrpc_protocol_error(skb, rxrpc_eproto_no_service_call);
- rcu_read_lock();
+ read_lock(&local->services_lock);
/* Weed out packets to services we're not offering. Packets that would
* begin a call are explicitly rejected and the rest are just
* discarded.
*/
- rx = rcu_dereference(local->service);
+ rx = local->service;
if (!rx || (sp->hdr.serviceId != rx->srx.srx_service &&
sp->hdr.serviceId != rx->second_service)
) {
if (!conn) {
sec = rxrpc_get_incoming_security(rx, skb);
if (!sec)
- goto reject;
+ goto unsupported_security;
}
spin_lock(&rx->incoming_lock);
if (rx->sk.sk_state == RXRPC_SERVER_LISTEN_DISABLED ||
rx->sk.sk_state == RXRPC_CLOSE) {
- trace_rxrpc_abort(0, "CLS", sp->hdr.cid, sp->hdr.callNumber,
- sp->hdr.seq, RX_INVALID_OPERATION, ESHUTDOWN);
- skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
- skb->priority = RX_INVALID_OPERATION;
+ rxrpc_direct_abort(skb, rxrpc_abort_shut_down,
+ RX_INVALID_OPERATION, -ESHUTDOWN);
goto no_call;
}
spin_unlock(&conn->state_lock);
spin_unlock(&rx->incoming_lock);
- rcu_read_unlock();
+ read_unlock(&local->services_lock);
if (hlist_unhashed(&call->error_link)) {
spin_lock(&call->peer->lock);
_leave(" = %p{%d}", call, call->debug_id);
rxrpc_input_call_event(call, skb);
rxrpc_put_call(call, rxrpc_call_put_input);
- return 0;
+ return true;
unsupported_service:
- trace_rxrpc_abort(0, "INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- RX_INVALID_OPERATION, EOPNOTSUPP);
- skb->priority = RX_INVALID_OPERATION;
- goto reject;
+ read_unlock(&local->services_lock);
+ return rxrpc_direct_abort(skb, rxrpc_abort_service_not_offered,
+ RX_INVALID_OPERATION, -EOPNOTSUPP);
+unsupported_security:
+ read_unlock(&local->services_lock);
+ return rxrpc_direct_abort(skb, rxrpc_abort_service_not_offered,
+ RX_INVALID_OPERATION, -EKEYREJECTED);
no_call:
spin_unlock(&rx->incoming_lock);
-reject:
- rcu_read_unlock();
+ read_unlock(&local->services_lock);
_leave(" = f [%u]", skb->mark);
- return -EPROTO;
+ return false;
discard:
- rcu_read_unlock();
- return 0;
+ read_unlock(&local->services_lock);
+ return true;
}
/*
_leave("");
}
+/*
+ * Start transmitting the reply to a service. This cancels the need to ACK the
+ * request if we haven't yet done so.
+ */
+static void rxrpc_begin_service_reply(struct rxrpc_call *call)
+{
+ unsigned long now = jiffies;
+
+ rxrpc_set_call_state(call, RXRPC_CALL_SERVER_SEND_REPLY);
+ WRITE_ONCE(call->delay_ack_at, now + MAX_JIFFY_OFFSET);
+ if (call->ackr_reason == RXRPC_ACK_DELAY)
+ call->ackr_reason = 0;
+ trace_rxrpc_timer(call, rxrpc_timer_init_for_send_reply, now);
+}
+
+/*
+ * Close the transmission phase. After this point there is no more data to be
+ * transmitted in the call.
+ */
+static void rxrpc_close_tx_phase(struct rxrpc_call *call)
+{
+ _debug("________awaiting reply/ACK__________");
+
+ switch (__rxrpc_call_state(call)) {
+ case RXRPC_CALL_CLIENT_SEND_REQUEST:
+ rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_AWAIT_REPLY);
+ break;
+ case RXRPC_CALL_SERVER_SEND_REPLY:
+ rxrpc_set_call_state(call, RXRPC_CALL_SERVER_AWAIT_ACK);
+ break;
+ default:
+ break;
+ }
+}
+
static bool rxrpc_tx_window_has_space(struct rxrpc_call *call)
{
unsigned int winsize = min_t(unsigned int, call->tx_winsize,
{
struct rxrpc_txbuf *txb;
- if (rxrpc_is_client_call(call) &&
- !test_bit(RXRPC_CALL_EXPOSED, &call->flags))
+ if (!test_bit(RXRPC_CALL_EXPOSED, &call->flags)) {
+ if (list_empty(&call->tx_sendmsg))
+ return;
rxrpc_expose_client_call(call);
+ }
while ((txb = list_first_entry_or_null(&call->tx_sendmsg,
struct rxrpc_txbuf, call_link))) {
call->tx_top = txb->seq;
list_add_tail(&txb->call_link, &call->tx_buffer);
+ if (txb->wire.flags & RXRPC_LAST_PACKET)
+ rxrpc_close_tx_phase(call);
+
rxrpc_transmit_one(call, txb);
if (!rxrpc_tx_window_has_space(call))
static void rxrpc_transmit_some_data(struct rxrpc_call *call)
{
- switch (call->state) {
+ switch (__rxrpc_call_state(call)) {
case RXRPC_CALL_SERVER_ACK_REQUEST:
if (list_empty(&call->tx_sendmsg))
return;
+ rxrpc_begin_service_reply(call);
fallthrough;
case RXRPC_CALL_SERVER_SEND_REPLY:
- case RXRPC_CALL_SERVER_AWAIT_ACK:
case RXRPC_CALL_CLIENT_SEND_REQUEST:
- case RXRPC_CALL_CLIENT_AWAIT_REPLY:
if (!rxrpc_tx_window_has_space(call))
return;
if (list_empty(&call->tx_sendmsg)) {
/*
* Handle retransmission and deferred ACK/abort generation.
*/
-void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
+bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb)
{
unsigned long now, next, t;
rxrpc_serial_t ackr_serial;
bool resend = false, expired = false;
+ s32 abort_code;
rxrpc_see_call(call, rxrpc_call_see_input);
//printk("\n--------------------\n");
_enter("{%d,%s,%lx}",
- call->debug_id, rxrpc_call_states[call->state], call->events);
+ call->debug_id, rxrpc_call_states[__rxrpc_call_state(call)],
+ call->events);
- if (call->state == RXRPC_CALL_COMPLETE)
+ if (__rxrpc_call_is_complete(call))
goto out;
+ /* Handle abort request locklessly, vs rxrpc_propose_abort(). */
+ abort_code = smp_load_acquire(&call->send_abort);
+ if (abort_code) {
+ rxrpc_abort_call(call, 0, call->send_abort, call->send_abort_err,
+ call->send_abort_why);
+ goto out;
+ }
+
if (skb && skb->mark == RXRPC_SKB_MARK_ERROR)
goto out;
}
t = READ_ONCE(call->expect_req_by);
- if (call->state == RXRPC_CALL_SERVER_RECV_REQUEST &&
+ if (__rxrpc_call_state(call) == RXRPC_CALL_SERVER_RECV_REQUEST &&
time_after_eq(now, t)) {
trace_rxrpc_timer(call, rxrpc_timer_exp_idle, now);
expired = true;
if (test_bit(RXRPC_CALL_RX_HEARD, &call->flags) &&
(int)call->conn->hi_serial - (int)call->rx_serial > 0) {
trace_rxrpc_call_reset(call);
- rxrpc_abort_call("EXP", call, 0, RX_CALL_DEAD, -ECONNRESET);
+ rxrpc_abort_call(call, 0, RX_CALL_DEAD, -ECONNRESET,
+ rxrpc_abort_call_reset);
} else {
- rxrpc_abort_call("EXP", call, 0, RX_CALL_TIMEOUT, -ETIME);
+ rxrpc_abort_call(call, 0, RX_CALL_TIMEOUT, -ETIME,
+ rxrpc_abort_call_timeout);
}
- rxrpc_send_abort_packet(call);
goto out;
}
rxrpc_send_ACK(call, RXRPC_ACK_PING, 0,
rxrpc_propose_ack_ping_for_lost_ack);
- if (resend && call->state != RXRPC_CALL_CLIENT_RECV_REPLY)
+ if (resend && __rxrpc_call_state(call) != RXRPC_CALL_CLIENT_RECV_REPLY)
rxrpc_resend(call, NULL);
if (test_and_clear_bit(RXRPC_CALL_RX_IS_IDLE, &call->flags))
rxrpc_propose_ack_input_data);
/* Make sure the timer is restarted */
- if (call->state != RXRPC_CALL_COMPLETE) {
+ if (!__rxrpc_call_is_complete(call)) {
next = call->expect_rx_by;
#define set(T) { t = READ_ONCE(T); if (time_before(t, next)) next = t; }
}
out:
- if (call->state == RXRPC_CALL_COMPLETE)
+ if (__rxrpc_call_is_complete(call)) {
del_timer_sync(&call->timer);
+ if (!test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
+ rxrpc_disconnect_call(call);
+ if (call->security)
+ call->security->free_call_crypto(call);
+ }
if (call->acks_hard_ack != call->tx_bottom)
rxrpc_shrink_call_tx_buffer(call);
_leave("");
+ return true;
}
struct rxrpc_local *local = call->local;
bool busy;
- if (call->state < RXRPC_CALL_COMPLETE) {
+ if (!test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) {
spin_lock_bh(&local->lock);
busy = !list_empty(&call->attend_link);
trace_rxrpc_poke_call(call, busy, what);
_enter("%d", call->debug_id);
- if (call->state < RXRPC_CALL_COMPLETE) {
+ if (!__rxrpc_call_is_complete(call)) {
trace_rxrpc_timer_expired(call, jiffies);
rxrpc_poke_call(call, rxrpc_call_poke_timer);
}
timer_setup(&call->timer, rxrpc_call_timer_expired, 0);
INIT_WORK(&call->destroyer, rxrpc_destroy_call);
INIT_LIST_HEAD(&call->link);
- INIT_LIST_HEAD(&call->chan_wait_link);
+ INIT_LIST_HEAD(&call->wait_link);
INIT_LIST_HEAD(&call->accept_link);
INIT_LIST_HEAD(&call->recvmsg_link);
INIT_LIST_HEAD(&call->sock_link);
init_waitqueue_head(&call->waitq);
spin_lock_init(&call->notify_lock);
spin_lock_init(&call->tx_lock);
- rwlock_init(&call->state_lock);
refcount_set(&call->ref, 1);
call->debug_id = debug_id;
call->tx_total_len = -1;
now = ktime_get_real();
call->acks_latest_ts = now;
call->cong_tstamp = now;
- call->state = RXRPC_CALL_CLIENT_AWAIT_CONN;
call->dest_srx = *srx;
call->interruptibility = p->interruptibility;
call->tx_total_len = p->tx_total_len;
ret = rxrpc_init_client_call_security(call);
if (ret < 0) {
- __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret);
+ rxrpc_prefail_call(call, RXRPC_CALL_LOCAL_ERROR, ret);
rxrpc_put_call(call, rxrpc_call_put_discard_error);
return ERR_PTR(ret);
}
+ rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_AWAIT_CONN);
+
trace_rxrpc_call(call->debug_id, refcount_read(&call->ref),
p->user_call_ID, rxrpc_call_new_client);
/*
* Initiate the call ack/resend/expiry timer.
*/
-static void rxrpc_start_call_timer(struct rxrpc_call *call)
+void rxrpc_start_call_timer(struct rxrpc_call *call)
{
unsigned long now = jiffies;
unsigned long j = now + MAX_JIFFY_OFFSET;
}
/*
+ * Start the process of connecting a call. We obtain a peer and a connection
+ * bundle, but the actual association of a call with a connection is offloaded
+ * to the I/O thread to simplify locking.
+ */
+static int rxrpc_connect_call(struct rxrpc_call *call, gfp_t gfp)
+{
+ struct rxrpc_local *local = call->local;
+ int ret = 0;
+
+ _enter("{%d,%lx},", call->debug_id, call->user_call_ID);
+
+ call->peer = rxrpc_lookup_peer(local, &call->dest_srx, gfp);
+ if (!call->peer)
+ goto error;
+
+ ret = rxrpc_look_up_bundle(call, gfp);
+ if (ret < 0)
+ goto error;
+
+ trace_rxrpc_client(NULL, -1, rxrpc_client_queue_new_call);
+ rxrpc_get_call(call, rxrpc_call_get_io_thread);
+ spin_lock(&local->client_call_lock);
+ list_add_tail(&call->wait_link, &local->new_client_calls);
+ spin_unlock(&local->client_call_lock);
+ rxrpc_wake_up_io_thread(local);
+ return 0;
+
+error:
+ __set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
+ return ret;
+}
+
+/*
* Set up a call for the given parameters.
* - Called with the socket lock held, which it must release.
* - If it returns a call, the call's lock will need releasing by the caller.
/* Set up or get a connection record and set the protocol parameters,
* including channel number and call ID.
*/
- ret = rxrpc_connect_call(rx, call, cp, srx, gfp);
+ ret = rxrpc_connect_call(call, gfp);
if (ret < 0)
goto error_attached_to_socket;
- rxrpc_see_call(call, rxrpc_call_see_connected);
-
- rxrpc_start_call_timer(call);
-
_leave(" = %p [new]", call);
return call;
error_dup_user_ID:
write_unlock(&rx->call_lock);
release_sock(&rx->sk);
- __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,
- RX_CALL_DEAD, -EEXIST);
+ rxrpc_prefail_call(call, RXRPC_CALL_LOCAL_ERROR, -EEXIST);
trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), 0,
rxrpc_call_see_userid_exists);
- rxrpc_release_call(rx, call);
mutex_unlock(&call->user_mutex);
rxrpc_put_call(call, rxrpc_call_put_userid_exists);
_leave(" = -EEXIST");
return ERR_PTR(-EEXIST);
/* We got an error, but the call is attached to the socket and is in
- * need of release. However, we might now race with recvmsg() when
- * completing the call queues it. Return 0 from sys_sendmsg() and
+ * need of release. However, we might now race with recvmsg() when it
+ * completion notifies the socket. Return 0 from sys_sendmsg() and
* leave the error to recvmsg() to deal with.
*/
error_attached_to_socket:
trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), ret,
rxrpc_call_see_connect_failed);
- set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
- __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,
- RX_CALL_DEAD, ret);
+ rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret);
_leave(" = c=%08x [err]", call->debug_id);
return call;
}
call->call_id = sp->hdr.callNumber;
call->dest_srx.srx_service = sp->hdr.serviceId;
call->cid = sp->hdr.cid;
- call->state = RXRPC_CALL_SERVER_SECURING;
call->cong_tstamp = skb->tstamp;
+ __set_bit(RXRPC_CALL_EXPOSED, &call->flags);
+ rxrpc_set_call_state(call, RXRPC_CALL_SERVER_SECURING);
+
spin_lock(&conn->state_lock);
switch (conn->state) {
case RXRPC_CONN_SERVICE_UNSECURED:
case RXRPC_CONN_SERVICE_CHALLENGING:
- call->state = RXRPC_CALL_SERVER_SECURING;
+ rxrpc_set_call_state(call, RXRPC_CALL_SERVER_SECURING);
break;
case RXRPC_CONN_SERVICE:
- call->state = RXRPC_CALL_SERVER_RECV_REQUEST;
+ rxrpc_set_call_state(call, RXRPC_CALL_SERVER_RECV_REQUEST);
break;
- case RXRPC_CONN_REMOTELY_ABORTED:
- __rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED,
- conn->abort_code, conn->error);
- break;
- case RXRPC_CONN_LOCALLY_ABORTED:
- __rxrpc_abort_call("CON", call, 1,
- conn->abort_code, conn->error);
+ case RXRPC_CONN_ABORTED:
+ rxrpc_set_call_completion(call, conn->completion,
+ conn->abort_code, conn->error);
break;
default:
BUG();
}
+ rxrpc_get_call(call, rxrpc_call_get_io_thread);
+
/* Set the channel for this call. We don't get channel_lock as we're
* only defending against the data_ready handler (which we're called
* from) and the RESPONSE packet parser (which is only really
chan = sp->hdr.cid & RXRPC_CHANNELMASK;
conn->channels[chan].call_counter = call->call_id;
conn->channels[chan].call_id = call->call_id;
- rcu_assign_pointer(conn->channels[chan].call, call);
+ conn->channels[chan].call = call;
spin_unlock(&conn->state_lock);
spin_lock(&conn->peer->lock);
void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call)
{
struct rxrpc_connection *conn = call->conn;
- bool put = false;
+ bool put = false, putu = false;
_enter("{%d,%d}", call->debug_id, refcount_read(&call->ref));
trace_rxrpc_call(call->debug_id, refcount_read(&call->ref),
call->flags, rxrpc_call_see_release);
- ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
-
if (test_and_set_bit(RXRPC_CALL_RELEASED, &call->flags))
BUG();
rxrpc_put_call_slot(call);
- del_timer_sync(&call->timer);
/* Make sure we don't get any more notifications */
write_lock(&rx->recvmsg_lock);
if (test_and_clear_bit(RXRPC_CALL_HAS_USERID, &call->flags)) {
rb_erase(&call->sock_node, &rx->calls);
memset(&call->sock_node, 0xdd, sizeof(call->sock_node));
- rxrpc_put_call(call, rxrpc_call_put_userid_exists);
+ putu = true;
}
list_del(&call->sock_link);
_debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, conn);
- if (conn && !test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
- rxrpc_disconnect_call(call);
- if (call->security)
- call->security->free_call_crypto(call);
+ if (putu)
+ rxrpc_put_call(call, rxrpc_call_put_userid);
+
_leave("");
}
call = list_entry(rx->to_be_accepted.next,
struct rxrpc_call, accept_link);
list_del(&call->accept_link);
- rxrpc_abort_call("SKR", call, 0, RX_CALL_DEAD, -ECONNRESET);
+ rxrpc_propose_abort(call, RX_CALL_DEAD, -ECONNRESET,
+ rxrpc_abort_call_sock_release_tba);
rxrpc_put_call(call, rxrpc_call_put_release_sock_tba);
}
call = list_entry(rx->sock_calls.next,
struct rxrpc_call, sock_link);
rxrpc_get_call(call, rxrpc_call_get_release_sock);
- rxrpc_abort_call("SKT", call, 0, RX_CALL_DEAD, -ECONNRESET);
- rxrpc_send_abort_packet(call);
+ rxrpc_propose_abort(call, RX_CALL_DEAD, -ECONNRESET,
+ rxrpc_abort_call_sock_release);
rxrpc_release_call(rx, call);
rxrpc_put_call(call, rxrpc_call_put_release_sock);
}
dead = __refcount_dec_and_test(&call->ref, &r);
trace_rxrpc_call(debug_id, r - 1, 0, why);
if (dead) {
- ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
+ ASSERTCMP(__rxrpc_call_state(call), ==, RXRPC_CALL_COMPLETE);
if (!list_empty(&call->link)) {
spin_lock(&rxnet->call_lock);
rxrpc_put_txbuf(call->tx_pending, rxrpc_txbuf_put_cleaned);
rxrpc_put_connection(call->conn, rxrpc_conn_put_call);
+ rxrpc_deactivate_bundle(call->bundle);
+ rxrpc_put_bundle(call->bundle, rxrpc_bundle_put_call);
rxrpc_put_peer(call->peer, rxrpc_peer_put_call);
rxrpc_put_local(call->local, rxrpc_local_put_call);
call_rcu(&call->rcu, rxrpc_rcu_free_call);
{
memset(&call->sock_node, 0xcd, sizeof(call->sock_node));
- ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
+ ASSERTCMP(__rxrpc_call_state(call), ==, RXRPC_CALL_COMPLETE);
ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags));
del_timer(&call->timer);
pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n",
call, refcount_read(&call->ref),
- rxrpc_call_states[call->state],
+ rxrpc_call_states[__rxrpc_call_state(call)],
call->flags, call->events);
spin_unlock(&rxnet->call_lock);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Call state changing functions.
+ *
+ * Copyright (C) 2022 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include "ar-internal.h"
+
+/*
+ * Transition a call to the complete state.
+ */
+bool rxrpc_set_call_completion(struct rxrpc_call *call,
+ enum rxrpc_call_completion compl,
+ u32 abort_code,
+ int error)
+{
+ if (__rxrpc_call_state(call) == RXRPC_CALL_COMPLETE)
+ return false;
+
+ call->abort_code = abort_code;
+ call->error = error;
+ call->completion = compl;
+ /* Allow reader of completion state to operate locklessly */
+ rxrpc_set_call_state(call, RXRPC_CALL_COMPLETE);
+ trace_rxrpc_call_complete(call);
+ wake_up(&call->waitq);
+ rxrpc_notify_socket(call);
+ return true;
+}
+
+/*
+ * Record that a call successfully completed.
+ */
+bool rxrpc_call_completed(struct rxrpc_call *call)
+{
+ return rxrpc_set_call_completion(call, RXRPC_CALL_SUCCEEDED, 0, 0);
+}
+
+/*
+ * Record that a call is locally aborted.
+ */
+bool rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq,
+ u32 abort_code, int error, enum rxrpc_abort_reason why)
+{
+ trace_rxrpc_abort(call->debug_id, why, call->cid, call->call_id, seq,
+ abort_code, error);
+ if (!rxrpc_set_call_completion(call, RXRPC_CALL_LOCALLY_ABORTED,
+ abort_code, error))
+ return false;
+ if (test_bit(RXRPC_CALL_EXPOSED, &call->flags))
+ rxrpc_send_abort_packet(call);
+ return true;
+}
+
+/*
+ * Record that a call errored out before even getting off the ground, thereby
+ * setting the state to allow it to be destroyed.
+ */
+void rxrpc_prefail_call(struct rxrpc_call *call, enum rxrpc_call_completion compl,
+ int error)
+{
+ call->abort_code = RX_CALL_DEAD;
+ call->error = error;
+ call->completion = compl;
+ call->_state = RXRPC_CALL_COMPLETE;
+ trace_rxrpc_call_complete(call);
+ WARN_ON_ONCE(__test_and_set_bit(RXRPC_CALL_RELEASED, &call->flags));
+}
__read_mostly unsigned long rxrpc_conn_idle_client_expiry = 2 * 60 * HZ;
__read_mostly unsigned long rxrpc_conn_idle_client_fast_expiry = 2 * HZ;
-/*
- * We use machine-unique IDs for our client connections.
- */
-DEFINE_IDR(rxrpc_client_conn_ids);
-static DEFINE_SPINLOCK(rxrpc_conn_id_lock);
-
-static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle);
-
-/*
- * Get a connection ID and epoch for a client connection from the global pool.
- * The connection struct pointer is then recorded in the idr radix tree. The
- * epoch doesn't change until the client is rebooted (or, at least, unless the
- * module is unloaded).
- */
-static int rxrpc_get_client_connection_id(struct rxrpc_connection *conn,
- gfp_t gfp)
+static void rxrpc_activate_bundle(struct rxrpc_bundle *bundle)
{
- struct rxrpc_net *rxnet = conn->rxnet;
- int id;
-
- _enter("");
-
- idr_preload(gfp);
- spin_lock(&rxrpc_conn_id_lock);
-
- id = idr_alloc_cyclic(&rxrpc_client_conn_ids, conn,
- 1, 0x40000000, GFP_NOWAIT);
- if (id < 0)
- goto error;
-
- spin_unlock(&rxrpc_conn_id_lock);
- idr_preload_end();
-
- conn->proto.epoch = rxnet->epoch;
- conn->proto.cid = id << RXRPC_CIDSHIFT;
- set_bit(RXRPC_CONN_HAS_IDR, &conn->flags);
- _leave(" [CID %x]", conn->proto.cid);
- return 0;
-
-error:
- spin_unlock(&rxrpc_conn_id_lock);
- idr_preload_end();
- _leave(" = %d", id);
- return id;
+ atomic_inc(&bundle->active);
}
/*
- * Release a connection ID for a client connection from the global pool.
+ * Release a connection ID for a client connection.
*/
-static void rxrpc_put_client_connection_id(struct rxrpc_connection *conn)
+static void rxrpc_put_client_connection_id(struct rxrpc_local *local,
+ struct rxrpc_connection *conn)
{
- if (test_bit(RXRPC_CONN_HAS_IDR, &conn->flags)) {
- spin_lock(&rxrpc_conn_id_lock);
- idr_remove(&rxrpc_client_conn_ids,
- conn->proto.cid >> RXRPC_CIDSHIFT);
- spin_unlock(&rxrpc_conn_id_lock);
- }
+ idr_remove(&local->conn_ids, conn->proto.cid >> RXRPC_CIDSHIFT);
}
/*
* Destroy the client connection ID tree.
*/
-void rxrpc_destroy_client_conn_ids(void)
+static void rxrpc_destroy_client_conn_ids(struct rxrpc_local *local)
{
struct rxrpc_connection *conn;
int id;
- if (!idr_is_empty(&rxrpc_client_conn_ids)) {
- idr_for_each_entry(&rxrpc_client_conn_ids, conn, id) {
+ if (!idr_is_empty(&local->conn_ids)) {
+ idr_for_each_entry(&local->conn_ids, conn, id) {
pr_err("AF_RXRPC: Leaked client conn %p {%d}\n",
conn, refcount_read(&conn->ref));
}
BUG();
}
- idr_destroy(&rxrpc_client_conn_ids);
+ idr_destroy(&local->conn_ids);
}
/*
* Allocate a connection bundle.
*/
-static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_conn_parameters *cp,
+static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_call *call,
gfp_t gfp)
{
struct rxrpc_bundle *bundle;
bundle = kzalloc(sizeof(*bundle), gfp);
if (bundle) {
- bundle->local = cp->local;
- bundle->peer = rxrpc_get_peer(cp->peer, rxrpc_peer_get_bundle);
- bundle->key = cp->key;
- bundle->exclusive = cp->exclusive;
- bundle->upgrade = cp->upgrade;
- bundle->service_id = cp->service_id;
- bundle->security_level = cp->security_level;
+ bundle->local = call->local;
+ bundle->peer = rxrpc_get_peer(call->peer, rxrpc_peer_get_bundle);
+ bundle->key = key_get(call->key);
+ bundle->security = call->security;
+ bundle->exclusive = test_bit(RXRPC_CALL_EXCLUSIVE, &call->flags);
+ bundle->upgrade = test_bit(RXRPC_CALL_UPGRADE, &call->flags);
+ bundle->service_id = call->dest_srx.srx_service;
+ bundle->security_level = call->security_level;
refcount_set(&bundle->ref, 1);
atomic_set(&bundle->active, 1);
- spin_lock_init(&bundle->channel_lock);
INIT_LIST_HEAD(&bundle->waiting_calls);
trace_rxrpc_bundle(bundle->debug_id, 1, rxrpc_bundle_new);
}
{
trace_rxrpc_bundle(bundle->debug_id, 1, rxrpc_bundle_free);
rxrpc_put_peer(bundle->peer, rxrpc_peer_put_bundle);
+ key_put(bundle->key);
kfree(bundle);
}
void rxrpc_put_bundle(struct rxrpc_bundle *bundle, enum rxrpc_bundle_trace why)
{
- unsigned int id = bundle->debug_id;
+ unsigned int id;
bool dead;
int r;
- dead = __refcount_dec_and_test(&bundle->ref, &r);
- trace_rxrpc_bundle(id, r - 1, why);
- if (dead)
- rxrpc_free_bundle(bundle);
+ if (bundle) {
+ id = bundle->debug_id;
+ dead = __refcount_dec_and_test(&bundle->ref, &r);
+ trace_rxrpc_bundle(id, r - 1, why);
+ if (dead)
+ rxrpc_free_bundle(bundle);
+ }
+}
+
+/*
+ * Get rid of outstanding client connection preallocations when a local
+ * endpoint is destroyed.
+ */
+void rxrpc_purge_client_connections(struct rxrpc_local *local)
+{
+ rxrpc_destroy_client_conn_ids(local);
}
/*
* Allocate a client connection.
*/
static struct rxrpc_connection *
-rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle, gfp_t gfp)
+rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle)
{
struct rxrpc_connection *conn;
- struct rxrpc_net *rxnet = bundle->local->rxnet;
- int ret;
+ struct rxrpc_local *local = bundle->local;
+ struct rxrpc_net *rxnet = local->rxnet;
+ int id;
_enter("");
- conn = rxrpc_alloc_connection(rxnet, gfp);
- if (!conn) {
- _leave(" = -ENOMEM");
+ conn = rxrpc_alloc_connection(rxnet, GFP_ATOMIC | __GFP_NOWARN);
+ if (!conn)
return ERR_PTR(-ENOMEM);
+
+ id = idr_alloc_cyclic(&local->conn_ids, conn, 1, 0x40000000,
+ GFP_ATOMIC | __GFP_NOWARN);
+ if (id < 0) {
+ kfree(conn);
+ return ERR_PTR(id);
}
refcount_set(&conn->ref, 1);
- conn->bundle = bundle;
- conn->local = bundle->local;
- conn->peer = bundle->peer;
- conn->key = bundle->key;
+ conn->proto.cid = id << RXRPC_CIDSHIFT;
+ conn->proto.epoch = local->rxnet->epoch;
+ conn->out_clientflag = RXRPC_CLIENT_INITIATED;
+ conn->bundle = rxrpc_get_bundle(bundle, rxrpc_bundle_get_client_conn);
+ conn->local = rxrpc_get_local(bundle->local, rxrpc_local_get_client_conn);
+ conn->peer = rxrpc_get_peer(bundle->peer, rxrpc_peer_get_client_conn);
+ conn->key = key_get(bundle->key);
+ conn->security = bundle->security;
conn->exclusive = bundle->exclusive;
conn->upgrade = bundle->upgrade;
conn->orig_service_id = bundle->service_id;
conn->security_level = bundle->security_level;
- conn->out_clientflag = RXRPC_CLIENT_INITIATED;
- conn->state = RXRPC_CONN_CLIENT;
+ conn->state = RXRPC_CONN_CLIENT_UNSECURED;
conn->service_id = conn->orig_service_id;
- ret = rxrpc_get_client_connection_id(conn, gfp);
- if (ret < 0)
- goto error_0;
-
- ret = rxrpc_init_client_conn_security(conn);
- if (ret < 0)
- goto error_1;
+ if (conn->security == &rxrpc_no_security)
+ conn->state = RXRPC_CONN_CLIENT;
atomic_inc(&rxnet->nr_conns);
write_lock(&rxnet->conn_lock);
list_add_tail(&conn->proc_link, &rxnet->conn_proc_list);
write_unlock(&rxnet->conn_lock);
- rxrpc_get_bundle(bundle, rxrpc_bundle_get_client_conn);
- rxrpc_get_peer(conn->peer, rxrpc_peer_get_client_conn);
- rxrpc_get_local(conn->local, rxrpc_local_get_client_conn);
- key_get(conn->key);
-
- trace_rxrpc_conn(conn->debug_id, refcount_read(&conn->ref),
- rxrpc_conn_new_client);
+ rxrpc_see_connection(conn, rxrpc_conn_new_client);
atomic_inc(&rxnet->nr_client_conns);
trace_rxrpc_client(conn, -1, rxrpc_client_alloc);
- _leave(" = %p", conn);
return conn;
-
-error_1:
- rxrpc_put_client_connection_id(conn);
-error_0:
- kfree(conn);
- _leave(" = %d", ret);
- return ERR_PTR(ret);
}
/*
if (test_bit(RXRPC_CONN_DONT_REUSE, &conn->flags))
goto dont_reuse;
- if (conn->state != RXRPC_CONN_CLIENT ||
+ if ((conn->state != RXRPC_CONN_CLIENT_UNSECURED &&
+ conn->state != RXRPC_CONN_CLIENT) ||
conn->proto.epoch != rxnet->epoch)
goto mark_dont_reuse;
* times the maximum number of client conns away from the current
* allocation point to try and keep the IDs concentrated.
*/
- id_cursor = idr_get_cursor(&rxrpc_client_conn_ids);
+ id_cursor = idr_get_cursor(&conn->local->conn_ids);
id = conn->proto.cid >> RXRPC_CIDSHIFT;
distance = id - id_cursor;
if (distance < 0)
* Look up the conn bundle that matches the connection parameters, adding it if
* it doesn't yet exist.
*/
-static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *cp,
- gfp_t gfp)
+int rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t gfp)
{
static atomic_t rxrpc_bundle_id;
struct rxrpc_bundle *bundle, *candidate;
- struct rxrpc_local *local = cp->local;
+ struct rxrpc_local *local = call->local;
struct rb_node *p, **pp, *parent;
long diff;
+ bool upgrade = test_bit(RXRPC_CALL_UPGRADE, &call->flags);
_enter("{%px,%x,%u,%u}",
- cp->peer, key_serial(cp->key), cp->security_level, cp->upgrade);
+ call->peer, key_serial(call->key), call->security_level,
+ upgrade);
- if (cp->exclusive)
- return rxrpc_alloc_bundle(cp, gfp);
+ if (test_bit(RXRPC_CALL_EXCLUSIVE, &call->flags)) {
+ call->bundle = rxrpc_alloc_bundle(call, gfp);
+ return call->bundle ? 0 : -ENOMEM;
+ }
/* First, see if the bundle is already there. */
_debug("search 1");
while (p) {
bundle = rb_entry(p, struct rxrpc_bundle, local_node);
-#define cmp(X) ((long)bundle->X - (long)cp->X)
- diff = (cmp(peer) ?:
- cmp(key) ?:
- cmp(security_level) ?:
- cmp(upgrade));
+#define cmp(X, Y) ((long)(X) - (long)(Y))
+ diff = (cmp(bundle->peer, call->peer) ?:
+ cmp(bundle->key, call->key) ?:
+ cmp(bundle->security_level, call->security_level) ?:
+ cmp(bundle->upgrade, upgrade));
#undef cmp
if (diff < 0)
p = p->rb_left;
_debug("not found");
/* It wasn't. We need to add one. */
- candidate = rxrpc_alloc_bundle(cp, gfp);
+ candidate = rxrpc_alloc_bundle(call, gfp);
if (!candidate)
- return NULL;
+ return -ENOMEM;
_debug("search 2");
spin_lock(&local->client_bundles_lock);
parent = *pp;
bundle = rb_entry(parent, struct rxrpc_bundle, local_node);
-#define cmp(X) ((long)bundle->X - (long)cp->X)
- diff = (cmp(peer) ?:
- cmp(key) ?:
- cmp(security_level) ?:
- cmp(upgrade));
+#define cmp(X, Y) ((long)(X) - (long)(Y))
+ diff = (cmp(bundle->peer, call->peer) ?:
+ cmp(bundle->key, call->key) ?:
+ cmp(bundle->security_level, call->security_level) ?:
+ cmp(bundle->upgrade, upgrade));
#undef cmp
if (diff < 0)
pp = &(*pp)->rb_left;
candidate->debug_id = atomic_inc_return(&rxrpc_bundle_id);
rb_link_node(&candidate->local_node, parent, pp);
rb_insert_color(&candidate->local_node, &local->client_bundles);
- rxrpc_get_bundle(candidate, rxrpc_bundle_get_client_call);
+ call->bundle = rxrpc_get_bundle(candidate, rxrpc_bundle_get_client_call);
spin_unlock(&local->client_bundles_lock);
- _leave(" = %u [new]", candidate->debug_id);
- return candidate;
+ _leave(" = B=%u [new]", call->bundle->debug_id);
+ return 0;
found_bundle_free:
rxrpc_free_bundle(candidate);
found_bundle:
- rxrpc_get_bundle(bundle, rxrpc_bundle_get_client_call);
- atomic_inc(&bundle->active);
+ call->bundle = rxrpc_get_bundle(bundle, rxrpc_bundle_get_client_call);
+ rxrpc_activate_bundle(bundle);
spin_unlock(&local->client_bundles_lock);
- _leave(" = %u [found]", bundle->debug_id);
- return bundle;
-}
-
-/*
- * Create or find a client bundle to use for a call.
- *
- * If we return with a connection, the call will be on its waiting list. It's
- * left to the caller to assign a channel and wake up the call.
- */
-static struct rxrpc_bundle *rxrpc_prep_call(struct rxrpc_sock *rx,
- struct rxrpc_call *call,
- struct rxrpc_conn_parameters *cp,
- struct sockaddr_rxrpc *srx,
- gfp_t gfp)
-{
- struct rxrpc_bundle *bundle;
-
- _enter("{%d,%lx},", call->debug_id, call->user_call_ID);
-
- cp->peer = rxrpc_lookup_peer(rx, cp->local, srx, gfp);
- if (!cp->peer)
- goto error;
-
- call->tx_last_sent = ktime_get_real();
- call->cong_ssthresh = cp->peer->cong_ssthresh;
- if (call->cong_cwnd >= call->cong_ssthresh)
- call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE;
- else
- call->cong_mode = RXRPC_CALL_SLOW_START;
- if (cp->upgrade)
- __set_bit(RXRPC_CALL_UPGRADE, &call->flags);
-
- /* Find the client connection bundle. */
- bundle = rxrpc_look_up_bundle(cp, gfp);
- if (!bundle)
- goto error;
-
- /* Get this call queued. Someone else may activate it whilst we're
- * lining up a new connection, but that's fine.
- */
- spin_lock(&bundle->channel_lock);
- list_add_tail(&call->chan_wait_link, &bundle->waiting_calls);
- spin_unlock(&bundle->channel_lock);
-
- _leave(" = [B=%x]", bundle->debug_id);
- return bundle;
-
-error:
- _leave(" = -ENOMEM");
- return ERR_PTR(-ENOMEM);
+ _leave(" = B=%u [found]", call->bundle->debug_id);
+ return 0;
}
/*
* Allocate a new connection and add it into a bundle.
*/
-static void rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle, gfp_t gfp)
- __releases(bundle->channel_lock)
+static bool rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle,
+ unsigned int slot)
{
- struct rxrpc_connection *candidate = NULL, *old = NULL;
- bool conflict;
- int i;
-
- _enter("");
-
- conflict = bundle->alloc_conn;
- if (!conflict)
- bundle->alloc_conn = true;
- spin_unlock(&bundle->channel_lock);
- if (conflict) {
- _leave(" [conf]");
- return;
- }
-
- candidate = rxrpc_alloc_client_connection(bundle, gfp);
-
- spin_lock(&bundle->channel_lock);
- bundle->alloc_conn = false;
-
- if (IS_ERR(candidate)) {
- bundle->alloc_error = PTR_ERR(candidate);
- spin_unlock(&bundle->channel_lock);
- _leave(" [err %ld]", PTR_ERR(candidate));
- return;
- }
-
- bundle->alloc_error = 0;
-
- for (i = 0; i < ARRAY_SIZE(bundle->conns); i++) {
- unsigned int shift = i * RXRPC_MAXCALLS;
- int j;
-
- old = bundle->conns[i];
- if (!rxrpc_may_reuse_conn(old)) {
- if (old)
- trace_rxrpc_client(old, -1, rxrpc_client_replace);
- candidate->bundle_shift = shift;
- atomic_inc(&bundle->active);
- bundle->conns[i] = candidate;
- for (j = 0; j < RXRPC_MAXCALLS; j++)
- set_bit(shift + j, &bundle->avail_chans);
- candidate = NULL;
- break;
- }
+ struct rxrpc_connection *conn, *old;
+ unsigned int shift = slot * RXRPC_MAXCALLS;
+ unsigned int i;
- old = NULL;
+ old = bundle->conns[slot];
+ if (old) {
+ bundle->conns[slot] = NULL;
+ trace_rxrpc_client(old, -1, rxrpc_client_replace);
+ rxrpc_put_connection(old, rxrpc_conn_put_noreuse);
}
- spin_unlock(&bundle->channel_lock);
-
- if (candidate) {
- _debug("discard C=%x", candidate->debug_id);
- trace_rxrpc_client(candidate, -1, rxrpc_client_duplicate);
- rxrpc_put_connection(candidate, rxrpc_conn_put_discard);
+ conn = rxrpc_alloc_client_connection(bundle);
+ if (IS_ERR(conn)) {
+ bundle->alloc_error = PTR_ERR(conn);
+ return false;
}
- rxrpc_put_connection(old, rxrpc_conn_put_noreuse);
- _leave("");
+ rxrpc_activate_bundle(bundle);
+ conn->bundle_shift = shift;
+ bundle->conns[slot] = conn;
+ for (i = 0; i < RXRPC_MAXCALLS; i++)
+ set_bit(shift + i, &bundle->avail_chans);
+ return true;
}
/*
* Add a connection to a bundle if there are no usable connections or we have
* connections waiting for extra capacity.
*/
-static void rxrpc_maybe_add_conn(struct rxrpc_bundle *bundle, gfp_t gfp)
+static bool rxrpc_bundle_has_space(struct rxrpc_bundle *bundle)
{
- struct rxrpc_call *call;
- int i, usable;
+ int slot = -1, i, usable;
_enter("");
- spin_lock(&bundle->channel_lock);
+ bundle->alloc_error = 0;
/* See if there are any usable connections. */
usable = 0;
- for (i = 0; i < ARRAY_SIZE(bundle->conns); i++)
+ for (i = 0; i < ARRAY_SIZE(bundle->conns); i++) {
if (rxrpc_may_reuse_conn(bundle->conns[i]))
usable++;
-
- if (!usable && !list_empty(&bundle->waiting_calls)) {
- call = list_first_entry(&bundle->waiting_calls,
- struct rxrpc_call, chan_wait_link);
- if (test_bit(RXRPC_CALL_UPGRADE, &call->flags))
- bundle->try_upgrade = true;
+ else if (slot == -1)
+ slot = i;
}
+ if (!usable && bundle->upgrade)
+ bundle->try_upgrade = true;
+
if (!usable)
goto alloc_conn;
if (!bundle->avail_chans &&
!bundle->try_upgrade &&
- !list_empty(&bundle->waiting_calls) &&
usable < ARRAY_SIZE(bundle->conns))
goto alloc_conn;
- spin_unlock(&bundle->channel_lock);
_leave("");
- return;
+ return usable;
alloc_conn:
- return rxrpc_add_conn_to_bundle(bundle, gfp);
+ return slot >= 0 ? rxrpc_add_conn_to_bundle(bundle, slot) : false;
}
/*
struct rxrpc_channel *chan = &conn->channels[channel];
struct rxrpc_bundle *bundle = conn->bundle;
struct rxrpc_call *call = list_entry(bundle->waiting_calls.next,
- struct rxrpc_call, chan_wait_link);
+ struct rxrpc_call, wait_link);
u32 call_id = chan->call_counter + 1;
_enter("C=%x,%u", conn->debug_id, channel);
+ list_del_init(&call->wait_link);
+
trace_rxrpc_client(conn, channel, rxrpc_client_chan_activate);
/* Cancel the final ACK on the previous call if it hasn't been sent yet
clear_bit(conn->bundle_shift + channel, &bundle->avail_chans);
rxrpc_see_call(call, rxrpc_call_see_activate_client);
- list_del_init(&call->chan_wait_link);
- call->peer = rxrpc_get_peer(conn->peer, rxrpc_peer_get_activate_call);
call->conn = rxrpc_get_connection(conn, rxrpc_conn_get_activate_call);
call->cid = conn->proto.cid | channel;
call->call_id = call_id;
call->dest_srx.srx_service = conn->service_id;
-
- trace_rxrpc_connect_call(call);
-
- write_lock(&call->state_lock);
- call->state = RXRPC_CALL_CLIENT_SEND_REQUEST;
- write_unlock(&call->state_lock);
-
- /* Paired with the read barrier in rxrpc_connect_call(). This orders
- * cid and epoch in the connection wrt to call_id without the need to
- * take the channel_lock.
- *
- * We provisionally assign a callNumber at this point, but we don't
- * confirm it until the call is about to be exposed.
- *
- * TODO: Pair with a barrier in the data_ready handler when that looks
- * at the call ID through a connection channel.
- */
- smp_wmb();
+ call->cong_ssthresh = call->peer->cong_ssthresh;
+ if (call->cong_cwnd >= call->cong_ssthresh)
+ call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE;
+ else
+ call->cong_mode = RXRPC_CALL_SLOW_START;
chan->call_id = call_id;
chan->call_debug_id = call->debug_id;
- rcu_assign_pointer(chan->call, call);
+ chan->call = call;
+
+ rxrpc_see_call(call, rxrpc_call_see_connected);
+ trace_rxrpc_connect_call(call);
+ call->tx_last_sent = ktime_get_real();
+ rxrpc_start_call_timer(call);
+ rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_SEND_REQUEST);
wake_up(&call->waitq);
}
/*
* Remove a connection from the idle list if it's on it.
*/
-static void rxrpc_unidle_conn(struct rxrpc_bundle *bundle, struct rxrpc_connection *conn)
+static void rxrpc_unidle_conn(struct rxrpc_connection *conn)
{
- struct rxrpc_net *rxnet = bundle->local->rxnet;
- bool drop_ref;
-
if (!list_empty(&conn->cache_link)) {
- drop_ref = false;
- spin_lock(&rxnet->client_conn_cache_lock);
- if (!list_empty(&conn->cache_link)) {
- list_del_init(&conn->cache_link);
- drop_ref = true;
- }
- spin_unlock(&rxnet->client_conn_cache_lock);
- if (drop_ref)
- rxrpc_put_connection(conn, rxrpc_conn_put_unidle);
+ list_del_init(&conn->cache_link);
+ rxrpc_put_connection(conn, rxrpc_conn_put_unidle);
}
}
/*
- * Assign channels and callNumbers to waiting calls with channel_lock
- * held by caller.
+ * Assign channels and callNumbers to waiting calls.
*/
-static void rxrpc_activate_channels_locked(struct rxrpc_bundle *bundle)
+static void rxrpc_activate_channels(struct rxrpc_bundle *bundle)
{
struct rxrpc_connection *conn;
unsigned long avail, mask;
unsigned int channel, slot;
+ trace_rxrpc_client(NULL, -1, rxrpc_client_activate_chans);
+
if (bundle->try_upgrade)
mask = 1;
else
if (bundle->try_upgrade)
set_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags);
- rxrpc_unidle_conn(bundle, conn);
+ rxrpc_unidle_conn(conn);
channel &= (RXRPC_MAXCALLS - 1);
conn->act_chans |= 1 << channel;
}
/*
- * Assign channels and callNumbers to waiting calls.
- */
-static void rxrpc_activate_channels(struct rxrpc_bundle *bundle)
-{
- _enter("B=%x", bundle->debug_id);
-
- trace_rxrpc_client(NULL, -1, rxrpc_client_activate_chans);
-
- if (!bundle->avail_chans)
- return;
-
- spin_lock(&bundle->channel_lock);
- rxrpc_activate_channels_locked(bundle);
- spin_unlock(&bundle->channel_lock);
- _leave("");
-}
-
-/*
- * Wait for a callNumber and a channel to be granted to a call.
- */
-static int rxrpc_wait_for_channel(struct rxrpc_bundle *bundle,
- struct rxrpc_call *call, gfp_t gfp)
-{
- DECLARE_WAITQUEUE(myself, current);
- int ret = 0;
-
- _enter("%d", call->debug_id);
-
- if (!gfpflags_allow_blocking(gfp)) {
- rxrpc_maybe_add_conn(bundle, gfp);
- rxrpc_activate_channels(bundle);
- ret = bundle->alloc_error ?: -EAGAIN;
- goto out;
- }
-
- add_wait_queue_exclusive(&call->waitq, &myself);
- for (;;) {
- rxrpc_maybe_add_conn(bundle, gfp);
- rxrpc_activate_channels(bundle);
- ret = bundle->alloc_error;
- if (ret < 0)
- break;
-
- switch (call->interruptibility) {
- case RXRPC_INTERRUPTIBLE:
- case RXRPC_PREINTERRUPTIBLE:
- set_current_state(TASK_INTERRUPTIBLE);
- break;
- case RXRPC_UNINTERRUPTIBLE:
- default:
- set_current_state(TASK_UNINTERRUPTIBLE);
- break;
- }
- if (READ_ONCE(call->state) != RXRPC_CALL_CLIENT_AWAIT_CONN)
- break;
- if ((call->interruptibility == RXRPC_INTERRUPTIBLE ||
- call->interruptibility == RXRPC_PREINTERRUPTIBLE) &&
- signal_pending(current)) {
- ret = -ERESTARTSYS;
- break;
- }
- schedule();
- }
- remove_wait_queue(&call->waitq, &myself);
- __set_current_state(TASK_RUNNING);
-
-out:
- _leave(" = %d", ret);
- return ret;
-}
-
-/*
- * find a connection for a call
- * - called in process context with IRQs enabled
+ * Connect waiting channels (called from the I/O thread).
*/
-int rxrpc_connect_call(struct rxrpc_sock *rx,
- struct rxrpc_call *call,
- struct rxrpc_conn_parameters *cp,
- struct sockaddr_rxrpc *srx,
- gfp_t gfp)
+void rxrpc_connect_client_calls(struct rxrpc_local *local)
{
- struct rxrpc_bundle *bundle;
- struct rxrpc_net *rxnet = cp->local->rxnet;
- int ret = 0;
-
- _enter("{%d,%lx},", call->debug_id, call->user_call_ID);
-
- rxrpc_discard_expired_client_conns(&rxnet->client_conn_reaper);
+ struct rxrpc_call *call;
- bundle = rxrpc_prep_call(rx, call, cp, srx, gfp);
- if (IS_ERR(bundle)) {
- ret = PTR_ERR(bundle);
- goto out;
- }
+ while ((call = list_first_entry_or_null(&local->new_client_calls,
+ struct rxrpc_call, wait_link))
+ ) {
+ struct rxrpc_bundle *bundle = call->bundle;
- if (call->state == RXRPC_CALL_CLIENT_AWAIT_CONN) {
- ret = rxrpc_wait_for_channel(bundle, call, gfp);
- if (ret < 0)
- goto wait_failed;
- }
+ spin_lock(&local->client_call_lock);
+ list_move_tail(&call->wait_link, &bundle->waiting_calls);
+ spin_unlock(&local->client_call_lock);
-granted_channel:
- /* Paired with the write barrier in rxrpc_activate_one_channel(). */
- smp_rmb();
-
-out_put_bundle:
- rxrpc_deactivate_bundle(bundle);
- rxrpc_put_bundle(bundle, rxrpc_bundle_get_client_call);
-out:
- _leave(" = %d", ret);
- return ret;
-
-wait_failed:
- spin_lock(&bundle->channel_lock);
- list_del_init(&call->chan_wait_link);
- spin_unlock(&bundle->channel_lock);
-
- if (call->state != RXRPC_CALL_CLIENT_AWAIT_CONN) {
- ret = 0;
- goto granted_channel;
+ if (rxrpc_bundle_has_space(bundle))
+ rxrpc_activate_channels(bundle);
}
-
- trace_rxrpc_client(call->conn, ret, rxrpc_client_chan_wait_failed);
- rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret);
- rxrpc_disconnect_client_call(bundle, call);
- goto out_put_bundle;
}
/*
/*
* Set the reap timer.
*/
-static void rxrpc_set_client_reap_timer(struct rxrpc_net *rxnet)
+static void rxrpc_set_client_reap_timer(struct rxrpc_local *local)
{
- if (!rxnet->kill_all_client_conns) {
+ if (!local->kill_all_client_conns) {
unsigned long now = jiffies;
unsigned long reap_at = now + rxrpc_conn_idle_client_expiry;
- if (rxnet->live)
- timer_reduce(&rxnet->client_conn_reap_timer, reap_at);
+ if (local->rxnet->live)
+ timer_reduce(&local->client_conn_reap_timer, reap_at);
}
}
{
struct rxrpc_connection *conn;
struct rxrpc_channel *chan = NULL;
- struct rxrpc_net *rxnet = bundle->local->rxnet;
+ struct rxrpc_local *local = bundle->local;
unsigned int channel;
bool may_reuse;
u32 cid;
_enter("c=%x", call->debug_id);
- spin_lock(&bundle->channel_lock);
- set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
-
/* Calls that have never actually been assigned a channel can simply be
* discarded.
*/
_debug("call is waiting");
ASSERTCMP(call->call_id, ==, 0);
ASSERT(!test_bit(RXRPC_CALL_EXPOSED, &call->flags));
- list_del_init(&call->chan_wait_link);
- goto out;
+ list_del_init(&call->wait_link);
+ return;
}
cid = call->cid;
chan = &conn->channels[channel];
trace_rxrpc_client(conn, channel, rxrpc_client_chan_disconnect);
- if (rcu_access_pointer(chan->call) != call) {
- spin_unlock(&bundle->channel_lock);
- BUG();
- }
+ if (WARN_ON(chan->call != call))
+ return;
may_reuse = rxrpc_may_reuse_conn(conn);
trace_rxrpc_client(conn, channel, rxrpc_client_to_active);
bundle->try_upgrade = false;
if (may_reuse)
- rxrpc_activate_channels_locked(bundle);
+ rxrpc_activate_channels(bundle);
}
-
}
/* See if we can pass the channel directly to another call. */
if (may_reuse && !list_empty(&bundle->waiting_calls)) {
trace_rxrpc_client(conn, channel, rxrpc_client_chan_pass);
rxrpc_activate_one_channel(conn, channel);
- goto out;
+ return;
}
/* Schedule the final ACK to be transmitted in a short while so that it
}
/* Deactivate the channel. */
- rcu_assign_pointer(chan->call, NULL);
+ chan->call = NULL;
set_bit(conn->bundle_shift + channel, &conn->bundle->avail_chans);
conn->act_chans &= ~(1 << channel);
conn->idle_timestamp = jiffies;
rxrpc_get_connection(conn, rxrpc_conn_get_idle);
- spin_lock(&rxnet->client_conn_cache_lock);
- list_move_tail(&conn->cache_link, &rxnet->idle_client_conns);
- spin_unlock(&rxnet->client_conn_cache_lock);
+ list_move_tail(&conn->cache_link, &local->idle_client_conns);
- rxrpc_set_client_reap_timer(rxnet);
+ rxrpc_set_client_reap_timer(local);
}
-
-out:
- spin_unlock(&bundle->channel_lock);
- _leave("");
- return;
}
/*
{
struct rxrpc_bundle *bundle = conn->bundle;
unsigned int bindex;
- bool need_drop = false;
int i;
_enter("C=%x", conn->debug_id);
if (conn->flags & RXRPC_CONN_FINAL_ACK_MASK)
rxrpc_process_delayed_final_acks(conn, true);
- spin_lock(&bundle->channel_lock);
bindex = conn->bundle_shift / RXRPC_MAXCALLS;
if (bundle->conns[bindex] == conn) {
_debug("clear slot %u", bindex);
bundle->conns[bindex] = NULL;
for (i = 0; i < RXRPC_MAXCALLS; i++)
clear_bit(conn->bundle_shift + i, &bundle->avail_chans);
- need_drop = true;
- }
- spin_unlock(&bundle->channel_lock);
-
- if (need_drop) {
+ rxrpc_put_client_connection_id(bundle->local, conn);
rxrpc_deactivate_bundle(bundle);
rxrpc_put_connection(conn, rxrpc_conn_put_unbundle);
}
/*
* Drop the active count on a bundle.
*/
-static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle)
+void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle)
{
- struct rxrpc_local *local = bundle->local;
+ struct rxrpc_local *local;
bool need_put = false;
+ if (!bundle)
+ return;
+
+ local = bundle->local;
if (atomic_dec_and_lock(&bundle->active, &local->client_bundles_lock)) {
if (!bundle->exclusive) {
_debug("erase bundle");
trace_rxrpc_client(conn, -1, rxrpc_client_cleanup);
atomic_dec(&rxnet->nr_client_conns);
- rxrpc_put_client_connection_id(conn);
+ rxrpc_put_client_connection_id(local, conn);
}
/*
* This may be called from conn setup or from a work item so cannot be
* considered non-reentrant.
*/
-void rxrpc_discard_expired_client_conns(struct work_struct *work)
+void rxrpc_discard_expired_client_conns(struct rxrpc_local *local)
{
struct rxrpc_connection *conn;
- struct rxrpc_net *rxnet =
- container_of(work, struct rxrpc_net, client_conn_reaper);
unsigned long expiry, conn_expires_at, now;
unsigned int nr_conns;
_enter("");
- if (list_empty(&rxnet->idle_client_conns)) {
- _leave(" [empty]");
- return;
- }
-
- /* Don't double up on the discarding */
- if (!mutex_trylock(&rxnet->client_conn_discard_lock)) {
- _leave(" [already]");
- return;
- }
-
/* We keep an estimate of what the number of conns ought to be after
* we've discarded some so that we don't overdo the discarding.
*/
- nr_conns = atomic_read(&rxnet->nr_client_conns);
+ nr_conns = atomic_read(&local->rxnet->nr_client_conns);
next:
- spin_lock(&rxnet->client_conn_cache_lock);
-
- if (list_empty(&rxnet->idle_client_conns))
- goto out;
-
- conn = list_entry(rxnet->idle_client_conns.next,
- struct rxrpc_connection, cache_link);
+ conn = list_first_entry_or_null(&local->idle_client_conns,
+ struct rxrpc_connection, cache_link);
+ if (!conn)
+ return;
- if (!rxnet->kill_all_client_conns) {
+ if (!local->kill_all_client_conns) {
/* If the number of connections is over the reap limit, we
* expedite discard by reducing the expiry timeout. We must,
* however, have at least a short grace period to be able to do
trace_rxrpc_client(conn, -1, rxrpc_client_discard);
list_del_init(&conn->cache_link);
- spin_unlock(&rxnet->client_conn_cache_lock);
-
rxrpc_unbundle_conn(conn);
/* Drop the ->cache_link ref */
rxrpc_put_connection(conn, rxrpc_conn_put_discard_idle);
* then things get messier.
*/
_debug("not yet");
- if (!rxnet->kill_all_client_conns)
- timer_reduce(&rxnet->client_conn_reap_timer, conn_expires_at);
-
-out:
- spin_unlock(&rxnet->client_conn_cache_lock);
- mutex_unlock(&rxnet->client_conn_discard_lock);
- _leave("");
-}
-
-/*
- * Preemptively destroy all the client connection records rather than waiting
- * for them to time out
- */
-void rxrpc_destroy_all_client_connections(struct rxrpc_net *rxnet)
-{
- _enter("");
-
- spin_lock(&rxnet->client_conn_cache_lock);
- rxnet->kill_all_client_conns = true;
- spin_unlock(&rxnet->client_conn_cache_lock);
-
- del_timer_sync(&rxnet->client_conn_reap_timer);
-
- if (!rxrpc_queue_work(&rxnet->client_conn_reaper))
- _debug("destroy: queue failed");
+ if (!local->kill_all_client_conns)
+ timer_reduce(&local->client_conn_reap_timer, conn_expires_at);
_leave("");
}
*/
void rxrpc_clean_up_local_conns(struct rxrpc_local *local)
{
- struct rxrpc_connection *conn, *tmp;
- struct rxrpc_net *rxnet = local->rxnet;
- LIST_HEAD(graveyard);
+ struct rxrpc_connection *conn;
_enter("");
- spin_lock(&rxnet->client_conn_cache_lock);
-
- list_for_each_entry_safe(conn, tmp, &rxnet->idle_client_conns,
- cache_link) {
- if (conn->local == local) {
- atomic_dec(&conn->active);
- trace_rxrpc_client(conn, -1, rxrpc_client_discard);
- list_move(&conn->cache_link, &graveyard);
- }
- }
+ local->kill_all_client_conns = true;
- spin_unlock(&rxnet->client_conn_cache_lock);
+ del_timer_sync(&local->client_conn_reap_timer);
- while (!list_empty(&graveyard)) {
- conn = list_entry(graveyard.next,
- struct rxrpc_connection, cache_link);
+ while ((conn = list_first_entry_or_null(&local->idle_client_conns,
+ struct rxrpc_connection, cache_link))) {
list_del_init(&conn->cache_link);
+ atomic_dec(&conn->active);
+ trace_rxrpc_client(conn, -1, rxrpc_client_discard);
rxrpc_unbundle_conn(conn);
rxrpc_put_connection(conn, rxrpc_conn_put_local_dead);
}
#include "ar-internal.h"
/*
+ * Set the completion state on an aborted connection.
+ */
+static bool rxrpc_set_conn_aborted(struct rxrpc_connection *conn, struct sk_buff *skb,
+ s32 abort_code, int err,
+ enum rxrpc_call_completion compl)
+{
+ bool aborted = false;
+
+ if (conn->state != RXRPC_CONN_ABORTED) {
+ spin_lock(&conn->state_lock);
+ if (conn->state != RXRPC_CONN_ABORTED) {
+ conn->abort_code = abort_code;
+ conn->error = err;
+ conn->completion = compl;
+ /* Order the abort info before the state change. */
+ smp_store_release(&conn->state, RXRPC_CONN_ABORTED);
+ set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags);
+ set_bit(RXRPC_CONN_EV_ABORT_CALLS, &conn->events);
+ aborted = true;
+ }
+ spin_unlock(&conn->state_lock);
+ }
+
+ return aborted;
+}
+
+/*
+ * Mark a socket buffer to indicate that the connection it's on should be aborted.
+ */
+int rxrpc_abort_conn(struct rxrpc_connection *conn, struct sk_buff *skb,
+ s32 abort_code, int err, enum rxrpc_abort_reason why)
+{
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+
+ if (rxrpc_set_conn_aborted(conn, skb, abort_code, err,
+ RXRPC_CALL_LOCALLY_ABORTED)) {
+ trace_rxrpc_abort(0, why, sp->hdr.cid, sp->hdr.callNumber,
+ sp->hdr.seq, abort_code, err);
+ rxrpc_poke_conn(conn, rxrpc_conn_get_poke_abort);
+ }
+ return -EPROTO;
+}
+
+/*
+ * Mark a connection as being remotely aborted.
+ */
+static bool rxrpc_input_conn_abort(struct rxrpc_connection *conn,
+ struct sk_buff *skb)
+{
+ return rxrpc_set_conn_aborted(conn, skb, skb->priority, -ECONNABORTED,
+ RXRPC_CALL_REMOTELY_ABORTED);
+}
+
+/*
* Retransmit terminal ACK or ABORT of the previous call.
*/
-static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
- struct sk_buff *skb,
- unsigned int channel)
+void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
+ struct sk_buff *skb,
+ unsigned int channel)
{
struct rxrpc_skb_priv *sp = skb ? rxrpc_skb(skb) : NULL;
struct rxrpc_channel *chan;
/* If the last call got moved on whilst we were waiting to run, just
* ignore this packet.
*/
- call_id = READ_ONCE(chan->last_call);
- /* Sync with __rxrpc_disconnect_call() */
- smp_rmb();
+ call_id = chan->last_call;
if (skb && call_id != sp->hdr.callNumber)
return;
iov[2].iov_base = &ack_info;
iov[2].iov_len = sizeof(ack_info);
+ serial = atomic_inc_return(&conn->serial);
+
pkt.whdr.epoch = htonl(conn->proto.epoch);
pkt.whdr.cid = htonl(conn->proto.cid | channel);
pkt.whdr.callNumber = htonl(call_id);
+ pkt.whdr.serial = htonl(serial);
pkt.whdr.seq = 0;
pkt.whdr.type = chan->last_type;
pkt.whdr.flags = conn->out_clientflag;
iov[0].iov_len += sizeof(pkt.ack);
len += sizeof(pkt.ack) + 3 + sizeof(ack_info);
ioc = 3;
- break;
-
- default:
- return;
- }
-
- /* Resync with __rxrpc_disconnect_call() and check that the last call
- * didn't get advanced whilst we were filling out the packets.
- */
- smp_rmb();
- if (READ_ONCE(chan->last_call) != call_id)
- return;
-
- serial = atomic_inc_return(&conn->serial);
- pkt.whdr.serial = htonl(serial);
- switch (chan->last_type) {
- case RXRPC_PACKET_TYPE_ABORT:
- break;
- case RXRPC_PACKET_TYPE_ACK:
trace_rxrpc_tx_ack(chan->call_debug_id, serial,
ntohl(pkt.ack.firstPacket),
ntohl(pkt.ack.serial),
pkt.ack.reason, 0);
break;
+
+ default:
+ return;
}
ret = kernel_sendmsg(conn->local->socket, &msg, iov, ioc, len);
/*
* pass a connection-level abort onto all calls on that connection
*/
-static void rxrpc_abort_calls(struct rxrpc_connection *conn,
- enum rxrpc_call_completion compl,
- rxrpc_serial_t serial)
+static void rxrpc_abort_calls(struct rxrpc_connection *conn)
{
struct rxrpc_call *call;
int i;
_enter("{%d},%x", conn->debug_id, conn->abort_code);
- spin_lock(&conn->bundle->channel_lock);
-
for (i = 0; i < RXRPC_MAXCALLS; i++) {
- call = rcu_dereference_protected(
- conn->channels[i].call,
- lockdep_is_held(&conn->bundle->channel_lock));
- if (call) {
- if (compl == RXRPC_CALL_LOCALLY_ABORTED)
- trace_rxrpc_abort(call->debug_id,
- "CON", call->cid,
- call->call_id, 0,
+ call = conn->channels[i].call;
+ if (call)
+ rxrpc_set_call_completion(call,
+ conn->completion,
conn->abort_code,
conn->error);
- else
- trace_rxrpc_rx_abort(call, serial,
- conn->abort_code);
- rxrpc_set_call_completion(call, compl,
- conn->abort_code,
- conn->error);
- }
}
- spin_unlock(&conn->bundle->channel_lock);
_leave("");
}
/*
- * generate a connection-level abort
- */
-static int rxrpc_abort_connection(struct rxrpc_connection *conn,
- int error, u32 abort_code)
-{
- struct rxrpc_wire_header whdr;
- struct msghdr msg;
- struct kvec iov[2];
- __be32 word;
- size_t len;
- u32 serial;
- int ret;
-
- _enter("%d,,%u,%u", conn->debug_id, error, abort_code);
-
- /* generate a connection-level abort */
- spin_lock(&conn->state_lock);
- if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) {
- spin_unlock(&conn->state_lock);
- _leave(" = 0 [already dead]");
- return 0;
- }
-
- conn->error = error;
- conn->abort_code = abort_code;
- conn->state = RXRPC_CONN_LOCALLY_ABORTED;
- set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags);
- spin_unlock(&conn->state_lock);
-
- msg.msg_name = &conn->peer->srx.transport;
- msg.msg_namelen = conn->peer->srx.transport_len;
- msg.msg_control = NULL;
- msg.msg_controllen = 0;
- msg.msg_flags = 0;
-
- whdr.epoch = htonl(conn->proto.epoch);
- whdr.cid = htonl(conn->proto.cid);
- whdr.callNumber = 0;
- whdr.seq = 0;
- whdr.type = RXRPC_PACKET_TYPE_ABORT;
- whdr.flags = conn->out_clientflag;
- whdr.userStatus = 0;
- whdr.securityIndex = conn->security_ix;
- whdr._rsvd = 0;
- whdr.serviceId = htons(conn->service_id);
-
- word = htonl(conn->abort_code);
-
- iov[0].iov_base = &whdr;
- iov[0].iov_len = sizeof(whdr);
- iov[1].iov_base = &word;
- iov[1].iov_len = sizeof(word);
-
- len = iov[0].iov_len + iov[1].iov_len;
-
- serial = atomic_inc_return(&conn->serial);
- rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED, serial);
- whdr.serial = htonl(serial);
-
- ret = kernel_sendmsg(conn->local->socket, &msg, iov, 2, len);
- if (ret < 0) {
- trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
- rxrpc_tx_point_conn_abort);
- _debug("sendmsg failed: %d", ret);
- return -EAGAIN;
- }
-
- trace_rxrpc_tx_packet(conn->debug_id, &whdr, rxrpc_tx_point_conn_abort);
-
- conn->peer->last_tx_at = ktime_get_seconds();
-
- _leave(" = 0");
- return 0;
-}
-
-/*
* mark a call as being on a now-secured channel
* - must be called with BH's disabled.
*/
static void rxrpc_call_is_secure(struct rxrpc_call *call)
{
- _enter("%p", call);
- if (call) {
- write_lock(&call->state_lock);
- if (call->state == RXRPC_CALL_SERVER_SECURING) {
- call->state = RXRPC_CALL_SERVER_RECV_REQUEST;
- rxrpc_notify_socket(call);
- }
- write_unlock(&call->state_lock);
+ if (call && __rxrpc_call_state(call) == RXRPC_CALL_SERVER_SECURING) {
+ rxrpc_set_call_state(call, RXRPC_CALL_SERVER_RECV_REQUEST);
+ rxrpc_notify_socket(call);
}
}
* connection-level Rx packet processor
*/
static int rxrpc_process_event(struct rxrpc_connection *conn,
- struct sk_buff *skb,
- u32 *_abort_code)
+ struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
- int loop, ret;
+ int ret;
- if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) {
- _leave(" = -ECONNABORTED [%u]", conn->state);
+ if (conn->state == RXRPC_CONN_ABORTED)
return -ECONNABORTED;
- }
_enter("{%d},{%u,%%%u},", conn->debug_id, sp->hdr.type, sp->hdr.serial);
switch (sp->hdr.type) {
- case RXRPC_PACKET_TYPE_DATA:
- case RXRPC_PACKET_TYPE_ACK:
- rxrpc_conn_retransmit_call(conn, skb,
- sp->hdr.cid & RXRPC_CHANNELMASK);
- return 0;
-
- case RXRPC_PACKET_TYPE_BUSY:
- /* Just ignore BUSY packets for now. */
- return 0;
-
- case RXRPC_PACKET_TYPE_ABORT:
- conn->error = -ECONNABORTED;
- conn->abort_code = skb->priority;
- conn->state = RXRPC_CONN_REMOTELY_ABORTED;
- set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags);
- rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, sp->hdr.serial);
- return -ECONNABORTED;
-
case RXRPC_PACKET_TYPE_CHALLENGE:
- return conn->security->respond_to_challenge(conn, skb,
- _abort_code);
+ return conn->security->respond_to_challenge(conn, skb);
case RXRPC_PACKET_TYPE_RESPONSE:
- ret = conn->security->verify_response(conn, skb, _abort_code);
+ ret = conn->security->verify_response(conn, skb);
if (ret < 0)
return ret;
if (ret < 0)
return ret;
- spin_lock(&conn->bundle->channel_lock);
spin_lock(&conn->state_lock);
-
- if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING) {
+ if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING)
conn->state = RXRPC_CONN_SERVICE;
- spin_unlock(&conn->state_lock);
- for (loop = 0; loop < RXRPC_MAXCALLS; loop++)
- rxrpc_call_is_secure(
- rcu_dereference_protected(
- conn->channels[loop].call,
- lockdep_is_held(&conn->bundle->channel_lock)));
- } else {
- spin_unlock(&conn->state_lock);
- }
+ spin_unlock(&conn->state_lock);
- spin_unlock(&conn->bundle->channel_lock);
+ if (conn->state == RXRPC_CONN_SERVICE) {
+ /* Offload call state flipping to the I/O thread. As
+ * we've already received the packet, put it on the
+ * front of the queue.
+ */
+ skb->mark = RXRPC_SKB_MARK_SERVICE_CONN_SECURED;
+ rxrpc_get_skb(skb, rxrpc_skb_get_conn_secured);
+ skb_queue_head(&conn->local->rx_queue, skb);
+ rxrpc_wake_up_io_thread(conn->local);
+ }
return 0;
default:
- trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
- tracepoint_string("bad_conn_pkt"));
+ WARN_ON_ONCE(1);
return -EPROTO;
}
}
*/
static void rxrpc_secure_connection(struct rxrpc_connection *conn)
{
- u32 abort_code;
- int ret;
-
- _enter("{%d}", conn->debug_id);
-
- ASSERT(conn->security_ix != 0);
-
- if (conn->security->issue_challenge(conn) < 0) {
- abort_code = RX_CALL_DEAD;
- ret = -ENOMEM;
- goto abort;
- }
-
- _leave("");
- return;
-
-abort:
- _debug("abort %d, %d", ret, abort_code);
- rxrpc_abort_connection(conn, ret, abort_code);
- _leave(" [aborted]");
+ if (conn->security->issue_challenge(conn) < 0)
+ rxrpc_abort_conn(conn, NULL, RX_CALL_DEAD, -ENOMEM,
+ rxrpc_abort_nomem);
}
/*
if (!test_bit(RXRPC_CONN_FINAL_ACK_0 + channel, &conn->flags))
continue;
- smp_rmb(); /* vs rxrpc_disconnect_client_call */
- ack_at = READ_ONCE(chan->final_ack_at);
-
+ ack_at = chan->final_ack_at;
if (time_before(j, ack_at) && !force) {
if (time_before(ack_at, next_j)) {
next_j = ack_at;
static void rxrpc_do_process_connection(struct rxrpc_connection *conn)
{
struct sk_buff *skb;
- u32 abort_code = RX_PROTOCOL_ERROR;
int ret;
if (test_and_clear_bit(RXRPC_CONN_EV_CHALLENGE, &conn->events))
rxrpc_secure_connection(conn);
- /* Process delayed ACKs whose time has come. */
- if (conn->flags & RXRPC_CONN_FINAL_ACK_MASK)
- rxrpc_process_delayed_final_acks(conn, false);
-
/* go through the conn-level event packets, releasing the ref on this
* connection that each one has when we've finished with it */
while ((skb = skb_dequeue(&conn->rx_queue))) {
rxrpc_see_skb(skb, rxrpc_skb_see_conn_work);
- ret = rxrpc_process_event(conn, skb, &abort_code);
+ ret = rxrpc_process_event(conn, skb);
switch (ret) {
- case -EPROTO:
- case -EKEYEXPIRED:
- case -EKEYREJECTED:
- goto protocol_error;
case -ENOMEM:
case -EAGAIN:
- goto requeue_and_leave;
- case -ECONNABORTED:
+ skb_queue_head(&conn->rx_queue, skb);
+ rxrpc_queue_conn(conn, rxrpc_conn_queue_retry_work);
+ break;
default:
rxrpc_free_skb(skb, rxrpc_skb_put_conn_work);
break;
}
}
-
- return;
-
-requeue_and_leave:
- skb_queue_head(&conn->rx_queue, skb);
- return;
-
-protocol_error:
- if (rxrpc_abort_connection(conn, ret, abort_code) < 0)
- goto requeue_and_leave;
- rxrpc_free_skb(skb, rxrpc_skb_put_conn_work);
- return;
}
void rxrpc_process_connection(struct work_struct *work)
/*
* Input a connection-level packet.
*/
-int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb)
+bool rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
- if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) {
- _leave(" = -ECONNABORTED [%u]", conn->state);
- return -ECONNABORTED;
- }
-
- _enter("{%d},{%u,%%%u},", conn->debug_id, sp->hdr.type, sp->hdr.serial);
-
switch (sp->hdr.type) {
- case RXRPC_PACKET_TYPE_DATA:
- case RXRPC_PACKET_TYPE_ACK:
- rxrpc_conn_retransmit_call(conn, skb,
- sp->hdr.cid & RXRPC_CHANNELMASK);
- return 0;
-
case RXRPC_PACKET_TYPE_BUSY:
/* Just ignore BUSY packets for now. */
- return 0;
+ return true;
case RXRPC_PACKET_TYPE_ABORT:
- conn->error = -ECONNABORTED;
- conn->abort_code = skb->priority;
- conn->state = RXRPC_CONN_REMOTELY_ABORTED;
- set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags);
- rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, sp->hdr.serial);
- return -ECONNABORTED;
+ if (rxrpc_is_conn_aborted(conn))
+ return true;
+ rxrpc_input_conn_abort(conn, skb);
+ rxrpc_abort_calls(conn);
+ return true;
case RXRPC_PACKET_TYPE_CHALLENGE:
case RXRPC_PACKET_TYPE_RESPONSE:
+ if (rxrpc_is_conn_aborted(conn)) {
+ if (conn->completion == RXRPC_CALL_LOCALLY_ABORTED)
+ rxrpc_send_conn_abort(conn);
+ return true;
+ }
rxrpc_post_packet_to_conn(conn, skb);
- return 0;
+ return true;
default:
- trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
- tracepoint_string("bad_conn_pkt"));
- return -EPROTO;
+ WARN_ON_ONCE(1);
+ return true;
}
}
+
+/*
+ * Input a connection event.
+ */
+void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb)
+{
+ unsigned int loop;
+
+ if (test_and_clear_bit(RXRPC_CONN_EV_ABORT_CALLS, &conn->events))
+ rxrpc_abort_calls(conn);
+
+ switch (skb->mark) {
+ case RXRPC_SKB_MARK_SERVICE_CONN_SECURED:
+ if (conn->state != RXRPC_CONN_SERVICE)
+ break;
+
+ for (loop = 0; loop < RXRPC_MAXCALLS; loop++)
+ rxrpc_call_is_secure(conn->channels[loop].call);
+ break;
+ }
+
+ /* Process delayed ACKs whose time has come. */
+ if (conn->flags & RXRPC_CONN_FINAL_ACK_MASK)
+ rxrpc_process_delayed_final_acks(conn, false);
+}
static void rxrpc_set_service_reap_timer(struct rxrpc_net *rxnet,
unsigned long reap_at);
+void rxrpc_poke_conn(struct rxrpc_connection *conn, enum rxrpc_conn_trace why)
+{
+ struct rxrpc_local *local = conn->local;
+ bool busy;
+
+ if (WARN_ON_ONCE(!local))
+ return;
+
+ spin_lock_bh(&local->lock);
+ busy = !list_empty(&conn->attend_link);
+ if (!busy) {
+ rxrpc_get_connection(conn, why);
+ list_add_tail(&conn->attend_link, &local->conn_attend_q);
+ }
+ spin_unlock_bh(&local->lock);
+ rxrpc_wake_up_io_thread(local);
+}
+
static void rxrpc_connection_timer(struct timer_list *timer)
{
struct rxrpc_connection *conn =
container_of(timer, struct rxrpc_connection, timer);
- rxrpc_queue_conn(conn, rxrpc_conn_queue_timer);
+ rxrpc_poke_conn(conn, rxrpc_conn_get_poke_timer);
}
/*
INIT_WORK(&conn->destructor, rxrpc_clean_up_connection);
INIT_LIST_HEAD(&conn->proc_link);
INIT_LIST_HEAD(&conn->link);
+ mutex_init(&conn->security_lock);
skb_queue_head_init(&conn->rx_queue);
conn->rxnet = rxnet;
conn->security = &rxrpc_no_security;
_enter(",%x", sp->hdr.cid & RXRPC_CIDMASK);
- /* Look up client connections by connection ID alone as their IDs are
- * unique for this machine.
+ /* Look up client connections by connection ID alone as their
+ * IDs are unique for this machine.
*/
- conn = idr_find(&rxrpc_client_conn_ids, sp->hdr.cid >> RXRPC_CIDSHIFT);
+ conn = idr_find(&local->conn_ids, sp->hdr.cid >> RXRPC_CIDSHIFT);
if (!conn || refcount_read(&conn->ref) == 0) {
_debug("no conn");
goto not_found;
_enter("%d,%x", conn->debug_id, call->cid);
- if (rcu_access_pointer(chan->call) == call) {
+ if (chan->call == call) {
/* Save the result of the call so that we can repeat it if necessary
* through the channel, whilst disposing of the actual call record.
*/
break;
}
- /* Sync with rxrpc_conn_retransmit(). */
- smp_wmb();
chan->last_call = chan->call_id;
chan->call_id = chan->call_counter;
-
- rcu_assign_pointer(chan->call, NULL);
+ chan->call = NULL;
}
_leave("");
{
struct rxrpc_connection *conn = call->conn;
+ set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
+ rxrpc_see_call(call, rxrpc_call_see_disconnected);
+
call->peer->cong_ssthresh = call->cong_ssthresh;
if (!hlist_unhashed(&call->error_link)) {
spin_unlock(&call->peer->lock);
}
- if (rxrpc_is_client_call(call))
- return rxrpc_disconnect_client_call(conn->bundle, call);
-
- spin_lock(&conn->bundle->channel_lock);
- __rxrpc_disconnect_call(conn, call);
- spin_unlock(&conn->bundle->channel_lock);
+ if (rxrpc_is_client_call(call)) {
+ rxrpc_disconnect_client_call(call->bundle, call);
+ } else {
+ __rxrpc_disconnect_call(conn, call);
+ conn->idle_timestamp = jiffies;
+ if (atomic_dec_and_test(&conn->active))
+ rxrpc_set_service_reap_timer(conn->rxnet,
+ jiffies + rxrpc_connection_expiry);
+ }
- set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
- conn->idle_timestamp = jiffies;
- if (atomic_dec_and_test(&conn->active))
- rxrpc_set_service_reap_timer(conn->rxnet,
- jiffies + rxrpc_connection_expiry);
+ rxrpc_put_call(call, rxrpc_call_put_io_thread);
}
/*
container_of(work, struct rxrpc_connection, destructor);
struct rxrpc_net *rxnet = conn->rxnet;
- ASSERT(!rcu_access_pointer(conn->channels[0].call) &&
- !rcu_access_pointer(conn->channels[1].call) &&
- !rcu_access_pointer(conn->channels[2].call) &&
- !rcu_access_pointer(conn->channels[3].call));
+ ASSERT(!conn->channels[0].call &&
+ !conn->channels[1].call &&
+ !conn->channels[2].call &&
+ !conn->channels[3].call);
ASSERT(list_empty(&conn->cache_link));
del_timer_sync(&conn->timer);
_enter("");
atomic_dec(&rxnet->nr_conns);
- rxrpc_destroy_all_client_connections(rxnet);
del_timer_sync(&rxnet->service_conn_reap_timer);
rxrpc_queue_work(&rxnet->service_conn_reaper);
static struct rxrpc_bundle rxrpc_service_dummy_bundle = {
.ref = REFCOUNT_INIT(1),
.debug_id = UINT_MAX,
- .channel_lock = __SPIN_LOCK_UNLOCKED(&rxrpc_service_dummy_bundle.channel_lock),
};
/*
#include "ar-internal.h"
-static void rxrpc_proto_abort(const char *why,
- struct rxrpc_call *call, rxrpc_seq_t seq)
+static void rxrpc_proto_abort(struct rxrpc_call *call, rxrpc_seq_t seq,
+ enum rxrpc_abort_reason why)
{
- if (rxrpc_abort_call(why, call, seq, RX_PROTOCOL_ERROR, -EBADMSG))
- rxrpc_send_abort_packet(call);
+ rxrpc_abort_call(call, seq, RX_PROTOCOL_ERROR, -EBADMSG, why);
}
/*
if (call->cong_mode != RXRPC_CALL_SLOW_START &&
call->cong_mode != RXRPC_CALL_CONGEST_AVOIDANCE)
return;
- if (call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY)
+ if (__rxrpc_call_state(call) == RXRPC_CALL_CLIENT_AWAIT_REPLY)
return;
rtt = ns_to_ktime(call->peer->srtt_us * (1000 / 8));
* This occurs when we get an ACKALL packet, the first DATA packet of a reply,
* or a final ACK packet.
*/
-static bool rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun,
- const char *abort_why)
+static void rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun,
+ enum rxrpc_abort_reason abort_why)
{
- unsigned int state;
-
ASSERT(test_bit(RXRPC_CALL_TX_LAST, &call->flags));
- write_lock(&call->state_lock);
-
- state = call->state;
- switch (state) {
+ switch (__rxrpc_call_state(call)) {
case RXRPC_CALL_CLIENT_SEND_REQUEST:
case RXRPC_CALL_CLIENT_AWAIT_REPLY:
- if (reply_begun)
- call->state = state = RXRPC_CALL_CLIENT_RECV_REPLY;
- else
- call->state = state = RXRPC_CALL_CLIENT_AWAIT_REPLY;
+ if (reply_begun) {
+ rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_RECV_REPLY);
+ trace_rxrpc_txqueue(call, rxrpc_txqueue_end);
+ break;
+ }
+
+ rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_AWAIT_REPLY);
+ trace_rxrpc_txqueue(call, rxrpc_txqueue_await_reply);
break;
case RXRPC_CALL_SERVER_AWAIT_ACK:
- __rxrpc_call_completed(call);
- state = call->state;
+ rxrpc_call_completed(call);
+ trace_rxrpc_txqueue(call, rxrpc_txqueue_end);
break;
default:
- goto bad_state;
+ kdebug("end_tx %s", rxrpc_call_states[__rxrpc_call_state(call)]);
+ rxrpc_proto_abort(call, call->tx_top, abort_why);
+ break;
}
-
- write_unlock(&call->state_lock);
- if (state == RXRPC_CALL_CLIENT_AWAIT_REPLY)
- trace_rxrpc_txqueue(call, rxrpc_txqueue_await_reply);
- else
- trace_rxrpc_txqueue(call, rxrpc_txqueue_end);
- _leave(" = ok");
- return true;
-
-bad_state:
- write_unlock(&call->state_lock);
- kdebug("end_tx %s", rxrpc_call_states[call->state]);
- rxrpc_proto_abort(abort_why, call, call->tx_top);
- return false;
}
/*
if (call->ackr_reason) {
now = jiffies;
timo = now + MAX_JIFFY_OFFSET;
- WRITE_ONCE(call->resend_at, timo);
+
WRITE_ONCE(call->delay_ack_at, timo);
trace_rxrpc_timer(call, rxrpc_timer_init_for_reply, now);
}
if (!test_bit(RXRPC_CALL_TX_LAST, &call->flags)) {
if (!rxrpc_rotate_tx_window(call, top, &summary)) {
- rxrpc_proto_abort("TXL", call, top);
+ rxrpc_proto_abort(call, top, rxrpc_eproto_early_reply);
return false;
}
}
- return rxrpc_end_tx_phase(call, true, "ETD");
+
+ rxrpc_end_tx_phase(call, true, rxrpc_eproto_unexpected_reply);
+ return true;
+}
+
+/*
+ * End the packet reception phase.
+ */
+static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial)
+{
+ rxrpc_seq_t whigh = READ_ONCE(call->rx_highest_seq);
+
+ _enter("%d,%s", call->debug_id, rxrpc_call_states[__rxrpc_call_state(call)]);
+
+ trace_rxrpc_receive(call, rxrpc_receive_end, 0, whigh);
+
+ switch (__rxrpc_call_state(call)) {
+ case RXRPC_CALL_CLIENT_RECV_REPLY:
+ rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_terminal_ack);
+ rxrpc_call_completed(call);
+ break;
+
+ case RXRPC_CALL_SERVER_RECV_REQUEST:
+ rxrpc_set_call_state(call, RXRPC_CALL_SERVER_ACK_REQUEST);
+ call->expect_req_by = jiffies + MAX_JIFFY_OFFSET;
+ rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_processing_op);
+ break;
+
+ default:
+ break;
+ }
}
static void rxrpc_input_update_ack_window(struct rxrpc_call *call,
__skb_queue_tail(&call->recvmsg_queue, skb);
rxrpc_input_update_ack_window(call, window, wtop);
-
trace_rxrpc_receive(call, last ? why + 1 : why, sp->hdr.serial, sp->hdr.seq);
+ if (last)
+ rxrpc_end_rx_phase(call, sp->hdr.serial);
}
/*
if (last) {
if (test_and_set_bit(RXRPC_CALL_RX_LAST, &call->flags) &&
- seq + 1 != wtop) {
- rxrpc_proto_abort("LSN", call, seq);
- return;
- }
+ seq + 1 != wtop)
+ return rxrpc_proto_abort(call, seq, rxrpc_eproto_different_last);
} else {
if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) &&
after_eq(seq, wtop)) {
pr_warn("Packet beyond last: c=%x q=%x window=%x-%x wlimit=%x\n",
call->debug_id, seq, window, wtop, wlimit);
- rxrpc_proto_abort("LSA", call, seq);
- return;
+ return rxrpc_proto_abort(call, seq, rxrpc_eproto_data_after_last);
}
}
static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
- enum rxrpc_call_state state;
rxrpc_serial_t serial = sp->hdr.serial;
rxrpc_seq_t seq0 = sp->hdr.seq;
atomic64_read(&call->ackr_window), call->rx_highest_seq,
skb->len, seq0);
- state = READ_ONCE(call->state);
- if (state >= RXRPC_CALL_COMPLETE)
+ if (__rxrpc_call_is_complete(call))
return;
- if (state == RXRPC_CALL_SERVER_RECV_REQUEST) {
+ switch (__rxrpc_call_state(call)) {
+ case RXRPC_CALL_CLIENT_SEND_REQUEST:
+ case RXRPC_CALL_CLIENT_AWAIT_REPLY:
+ /* Received data implicitly ACKs all of the request
+ * packets we sent when we're acting as a client.
+ */
+ if (!rxrpc_receiving_reply(call))
+ goto out_notify;
+ break;
+
+ case RXRPC_CALL_SERVER_RECV_REQUEST: {
unsigned long timo = READ_ONCE(call->next_req_timo);
unsigned long now, expect_req_by;
rxrpc_reduce_call_timer(call, expect_req_by, now,
rxrpc_timer_set_for_idle);
}
+ break;
}
- /* Received data implicitly ACKs all of the request packets we sent
- * when we're acting as a client.
- */
- if ((state == RXRPC_CALL_CLIENT_SEND_REQUEST ||
- state == RXRPC_CALL_CLIENT_AWAIT_REPLY) &&
- !rxrpc_receiving_reply(call))
- goto out_notify;
+ default:
+ break;
+ }
if (!rxrpc_input_split_jumbo(call, skb)) {
- rxrpc_proto_abort("VLD", call, sp->hdr.seq);
+ rxrpc_proto_abort(call, sp->hdr.seq, rxrpc_badmsg_bad_jumbo);
goto out_notify;
}
skb = NULL;
offset = sizeof(struct rxrpc_wire_header);
if (skb_copy_bits(skb, offset, &ack, sizeof(ack)) < 0)
- return rxrpc_proto_abort("XAK", call, 0);
+ return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack);
offset += sizeof(ack);
ack_serial = sp->hdr.serial;
ioffset = offset + nr_acks + 3;
if (skb->len >= ioffset + sizeof(info) &&
skb_copy_bits(skb, ioffset, &info, sizeof(info)) < 0)
- return rxrpc_proto_abort("XAI", call, 0);
+ return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack_info);
if (nr_acks > 0)
skb_condense(skb);
rxrpc_input_ackinfo(call, skb, &info);
if (first_soft_ack == 0)
- return rxrpc_proto_abort("AK0", call, 0);
+ return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_zero);
/* Ignore ACKs unless we are or have just been transmitting. */
- switch (READ_ONCE(call->state)) {
+ switch (__rxrpc_call_state(call)) {
case RXRPC_CALL_CLIENT_SEND_REQUEST:
case RXRPC_CALL_CLIENT_AWAIT_REPLY:
case RXRPC_CALL_SERVER_SEND_REPLY:
if (before(hard_ack, call->acks_hard_ack) ||
after(hard_ack, call->tx_top))
- return rxrpc_proto_abort("AKW", call, 0);
+ return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_outside_window);
if (nr_acks > call->tx_top - hard_ack)
- return rxrpc_proto_abort("AKN", call, 0);
+ return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_sack_overflow);
if (after(hard_ack, call->acks_hard_ack)) {
if (rxrpc_rotate_tx_window(call, hard_ack, &summary)) {
- rxrpc_end_tx_phase(call, false, "ETA");
+ rxrpc_end_tx_phase(call, false, rxrpc_eproto_unexpected_ack);
return;
}
}
if (nr_acks > 0) {
if (offset > (int)skb->len - nr_acks)
- return rxrpc_proto_abort("XSA", call, 0);
+ return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_short_sack);
rxrpc_input_soft_acks(call, skb->data + offset, first_soft_ack,
nr_acks, &summary);
}
struct rxrpc_ack_summary summary = { 0 };
if (rxrpc_rotate_tx_window(call, call->tx_top, &summary))
- rxrpc_end_tx_phase(call, false, "ETL");
+ rxrpc_end_tx_phase(call, false, rxrpc_eproto_unexpected_ackall);
}
/*
switch (sp->hdr.type) {
case RXRPC_PACKET_TYPE_DATA:
- rxrpc_input_data(call, skb);
- break;
+ return rxrpc_input_data(call, skb);
case RXRPC_PACKET_TYPE_ACK:
- rxrpc_input_ack(call, skb);
- break;
+ return rxrpc_input_ack(call, skb);
case RXRPC_PACKET_TYPE_BUSY:
/* Just ignore BUSY packets from the server; the retry and
* lifespan timers will take care of business. BUSY packets
* from the client don't make sense.
*/
- break;
+ return;
case RXRPC_PACKET_TYPE_ABORT:
- rxrpc_input_abort(call, skb);
- break;
+ return rxrpc_input_abort(call, skb);
case RXRPC_PACKET_TYPE_ACKALL:
- rxrpc_input_ackall(call, skb);
- break;
+ return rxrpc_input_ackall(call, skb);
default:
break;
*/
void rxrpc_implicit_end_call(struct rxrpc_call *call, struct sk_buff *skb)
{
- struct rxrpc_connection *conn = call->conn;
-
- switch (READ_ONCE(call->state)) {
+ switch (__rxrpc_call_state(call)) {
case RXRPC_CALL_SERVER_AWAIT_ACK:
rxrpc_call_completed(call);
fallthrough;
case RXRPC_CALL_COMPLETE:
break;
default:
- if (rxrpc_abort_call("IMP", call, 0, RX_CALL_DEAD, -ESHUTDOWN))
- rxrpc_send_abort_packet(call);
+ rxrpc_abort_call(call, 0, RX_CALL_DEAD, -ESHUTDOWN,
+ rxrpc_eproto_improper_term);
trace_rxrpc_improper_term(call);
break;
}
rxrpc_input_call_event(call, skb);
-
- spin_lock(&conn->bundle->channel_lock);
- __rxrpc_disconnect_call(conn, call);
- spin_unlock(&conn->bundle->channel_lock);
}
}
static int none_respond_to_challenge(struct rxrpc_connection *conn,
- struct sk_buff *skb,
- u32 *_abort_code)
+ struct sk_buff *skb)
{
- struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
-
- trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
- tracepoint_string("chall_none"));
- return -EPROTO;
+ return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO,
+ rxrpc_eproto_rxnull_challenge);
}
static int none_verify_response(struct rxrpc_connection *conn,
- struct sk_buff *skb,
- u32 *_abort_code)
+ struct sk_buff *skb)
{
- struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
-
- trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
- tracepoint_string("resp_none"));
- return -EPROTO;
+ return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO,
+ rxrpc_eproto_rxnull_response);
}
static void none_clear(struct rxrpc_connection *conn)
}
/*
+ * Directly produce an abort from a packet.
+ */
+bool rxrpc_direct_abort(struct sk_buff *skb, enum rxrpc_abort_reason why,
+ s32 abort_code, int err)
+{
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+
+ trace_rxrpc_abort(0, why, sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
+ abort_code, err);
+ skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
+ skb->priority = abort_code;
+ return false;
+}
+
+static bool rxrpc_bad_message(struct sk_buff *skb, enum rxrpc_abort_reason why)
+{
+ return rxrpc_direct_abort(skb, why, RX_PROTOCOL_ERROR, -EBADMSG);
+}
+
+#define just_discard true
+
+/*
* Process event packets targeted at a local endpoint.
*/
-static void rxrpc_input_version(struct rxrpc_local *local, struct sk_buff *skb)
+static bool rxrpc_input_version(struct rxrpc_local *local, struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
char v;
if (v == 0)
rxrpc_send_version_request(local, &sp->hdr, skb);
}
+
+ return true;
}
/*
* Extract the wire header from a packet and translate the byte order.
*/
-static noinline
-int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb)
+static bool rxrpc_extract_header(struct rxrpc_skb_priv *sp,
+ struct sk_buff *skb)
{
struct rxrpc_wire_header whdr;
/* dig out the RxRPC connection details */
- if (skb_copy_bits(skb, 0, &whdr, sizeof(whdr)) < 0) {
- trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
- tracepoint_string("bad_hdr"));
- return -EBADMSG;
- }
+ if (skb_copy_bits(skb, 0, &whdr, sizeof(whdr)) < 0)
+ return rxrpc_bad_message(skb, rxrpc_badmsg_short_hdr);
memset(sp, 0, sizeof(*sp));
sp->hdr.epoch = ntohl(whdr.epoch);
sp->hdr.securityIndex = whdr.securityIndex;
sp->hdr._rsvd = ntohs(whdr._rsvd);
sp->hdr.serviceId = ntohs(whdr.serviceId);
- return 0;
+ return true;
}
/*
/*
* Process packets received on the local endpoint
*/
-static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb)
+static bool rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb)
{
struct rxrpc_connection *conn;
struct sockaddr_rxrpc peer_srx;
struct rxrpc_skb_priv *sp;
struct rxrpc_peer *peer = NULL;
struct sk_buff *skb = *_skb;
- int ret = 0;
+ bool ret = false;
skb_pull(skb, sizeof(struct udphdr));
sp = rxrpc_skb(skb);
/* dig out the RxRPC connection details */
- if (rxrpc_extract_header(sp, skb) < 0)
- goto bad_message;
+ if (!rxrpc_extract_header(sp, skb))
+ return just_discard;
if (IS_ENABLED(CONFIG_AF_RXRPC_INJECT_LOSS)) {
static int lose;
if ((lose++ & 7) == 7) {
trace_rxrpc_rx_lose(sp);
- return 0;
+ return just_discard;
}
}
switch (sp->hdr.type) {
case RXRPC_PACKET_TYPE_VERSION:
if (rxrpc_to_client(sp))
- return 0;
- rxrpc_input_version(local, skb);
- return 0;
+ return just_discard;
+ return rxrpc_input_version(local, skb);
case RXRPC_PACKET_TYPE_BUSY:
if (rxrpc_to_server(sp))
- return 0;
+ return just_discard;
fallthrough;
case RXRPC_PACKET_TYPE_ACK:
case RXRPC_PACKET_TYPE_ACKALL:
if (sp->hdr.callNumber == 0)
- goto bad_message;
+ return rxrpc_bad_message(skb, rxrpc_badmsg_zero_call);
break;
case RXRPC_PACKET_TYPE_ABORT:
if (!rxrpc_extract_abort(skb))
- return 0; /* Just discard if malformed */
+ return just_discard; /* Just discard if malformed */
break;
case RXRPC_PACKET_TYPE_DATA:
- if (sp->hdr.callNumber == 0 ||
- sp->hdr.seq == 0)
- goto bad_message;
+ if (sp->hdr.callNumber == 0)
+ return rxrpc_bad_message(skb, rxrpc_badmsg_zero_call);
+ if (sp->hdr.seq == 0)
+ return rxrpc_bad_message(skb, rxrpc_badmsg_zero_seq);
/* Unshare the packet so that it can be modified for in-place
* decryption.
if (!skb) {
rxrpc_eaten_skb(*_skb, rxrpc_skb_eaten_by_unshare_nomem);
*_skb = NULL;
- return 0;
+ return just_discard;
}
if (skb != *_skb) {
case RXRPC_PACKET_TYPE_CHALLENGE:
if (rxrpc_to_server(sp))
- return 0;
+ return just_discard;
break;
case RXRPC_PACKET_TYPE_RESPONSE:
if (rxrpc_to_client(sp))
- return 0;
+ return just_discard;
break;
/* Packet types 9-11 should just be ignored. */
case RXRPC_PACKET_TYPE_PARAMS:
case RXRPC_PACKET_TYPE_10:
case RXRPC_PACKET_TYPE_11:
- return 0;
+ return just_discard;
default:
- goto bad_message;
+ return rxrpc_bad_message(skb, rxrpc_badmsg_unsupported_packet);
}
if (sp->hdr.serviceId == 0)
- goto bad_message;
+ return rxrpc_bad_message(skb, rxrpc_badmsg_zero_service);
if (WARN_ON_ONCE(rxrpc_extract_addr_from_skb(&peer_srx, skb) < 0))
- return true; /* Unsupported address type - discard. */
+ return just_discard; /* Unsupported address type. */
if (peer_srx.transport.family != local->srx.transport.family &&
(peer_srx.transport.family == AF_INET &&
pr_warn_ratelimited("AF_RXRPC: Protocol mismatch %u not %u\n",
peer_srx.transport.family,
local->srx.transport.family);
- return true; /* Wrong address type - discard. */
+ return just_discard; /* Wrong address type. */
}
if (rxrpc_to_client(sp)) {
conn = rxrpc_find_client_connection_rcu(local, &peer_srx, skb);
conn = rxrpc_get_connection_maybe(conn, rxrpc_conn_get_call_input);
rcu_read_unlock();
- if (!conn) {
- trace_rxrpc_abort(0, "NCC", sp->hdr.cid,
- sp->hdr.callNumber, sp->hdr.seq,
- RXKADINCONSISTENCY, EBADMSG);
- goto protocol_error;
- }
+ if (!conn)
+ return rxrpc_protocol_error(skb, rxrpc_eproto_no_client_conn);
ret = rxrpc_input_packet_on_conn(conn, &peer_srx, skb);
rxrpc_put_connection(conn, rxrpc_conn_put_call_input);
ret = rxrpc_new_incoming_call(local, peer, NULL, &peer_srx, skb);
rxrpc_put_peer(peer, rxrpc_peer_put_input);
- if (ret < 0)
- goto reject_packet;
- return 0;
-
-bad_message:
- trace_rxrpc_abort(0, "BAD", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- RX_PROTOCOL_ERROR, EBADMSG);
-protocol_error:
- skb->priority = RX_PROTOCOL_ERROR;
- skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
-reject_packet:
- rxrpc_reject_packet(local, skb);
- return 0;
+ return ret;
}
/*
struct rxrpc_channel *chan;
struct rxrpc_call *call = NULL;
unsigned int channel;
+ bool ret;
if (sp->hdr.securityIndex != conn->security_ix)
- goto wrong_security;
+ return rxrpc_direct_abort(skb, rxrpc_eproto_wrong_security,
+ RXKADINCONSISTENCY, -EBADMSG);
if (sp->hdr.serviceId != conn->service_id) {
int old_id;
if (!test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags))
- goto reupgrade;
+ return rxrpc_protocol_error(skb, rxrpc_eproto_reupgrade);
+
old_id = cmpxchg(&conn->service_id, conn->orig_service_id,
sp->hdr.serviceId);
-
if (old_id != conn->orig_service_id &&
old_id != sp->hdr.serviceId)
- goto reupgrade;
+ return rxrpc_protocol_error(skb, rxrpc_eproto_bad_upgrade);
}
if (after(sp->hdr.serial, conn->hi_serial))
/* Ignore really old calls */
if (sp->hdr.callNumber < chan->last_call)
- return 0;
+ return just_discard;
if (sp->hdr.callNumber == chan->last_call) {
if (chan->call ||
sp->hdr.type == RXRPC_PACKET_TYPE_ABORT)
- return 0;
+ return just_discard;
/* For the previous service call, if completed successfully, we
* discard all further packets.
*/
if (rxrpc_conn_is_service(conn) &&
chan->last_type == RXRPC_PACKET_TYPE_ACK)
- return 0;
+ return just_discard;
/* But otherwise we need to retransmit the final packet from
* data cached in the connection record.
sp->hdr.seq,
sp->hdr.serial,
sp->hdr.flags);
- rxrpc_input_conn_packet(conn, skb);
- return 0;
+ rxrpc_conn_retransmit_call(conn, skb, channel);
+ return just_discard;
}
- rcu_read_lock();
- call = rxrpc_try_get_call(rcu_dereference(chan->call),
- rxrpc_call_get_input);
- rcu_read_unlock();
+ call = rxrpc_try_get_call(chan->call, rxrpc_call_get_input);
if (sp->hdr.callNumber > chan->call_id) {
if (rxrpc_to_client(sp)) {
rxrpc_put_call(call, rxrpc_call_put_input);
- goto reject_packet;
+ return rxrpc_protocol_error(skb,
+ rxrpc_eproto_unexpected_implicit_end);
}
if (call) {
if (!call) {
if (rxrpc_to_client(sp))
- goto bad_message;
- if (rxrpc_new_incoming_call(conn->local, conn->peer, conn,
- peer_srx, skb) == 0)
- return 0;
- goto reject_packet;
+ return rxrpc_protocol_error(skb, rxrpc_eproto_no_client_call);
+ return rxrpc_new_incoming_call(conn->local, conn->peer, conn,
+ peer_srx, skb);
}
- rxrpc_input_call_event(call, skb);
+ ret = rxrpc_input_call_event(call, skb);
rxrpc_put_call(call, rxrpc_call_put_input);
- return 0;
-
-wrong_security:
- trace_rxrpc_abort(0, "SEC", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- RXKADINCONSISTENCY, EBADMSG);
- skb->priority = RXKADINCONSISTENCY;
- goto post_abort;
-
-reupgrade:
- trace_rxrpc_abort(0, "UPG", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- RX_PROTOCOL_ERROR, EBADMSG);
- goto protocol_error;
-
-bad_message:
- trace_rxrpc_abort(0, "BAD", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- RX_PROTOCOL_ERROR, EBADMSG);
-protocol_error:
- skb->priority = RX_PROTOCOL_ERROR;
-post_abort:
- skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
-reject_packet:
- rxrpc_reject_packet(conn->local, skb);
- return 0;
+ return ret;
}
/*
*/
int rxrpc_io_thread(void *data)
{
+ struct rxrpc_connection *conn;
struct sk_buff_head rx_queue;
struct rxrpc_local *local = data;
struct rxrpc_call *call;
for (;;) {
rxrpc_inc_stat(local->rxnet, stat_io_loop);
+ /* Deal with connections that want immediate attention. */
+ conn = list_first_entry_or_null(&local->conn_attend_q,
+ struct rxrpc_connection,
+ attend_link);
+ if (conn) {
+ spin_lock_bh(&local->lock);
+ list_del_init(&conn->attend_link);
+ spin_unlock_bh(&local->lock);
+
+ rxrpc_input_conn_event(conn, NULL);
+ rxrpc_put_connection(conn, rxrpc_conn_put_poke);
+ continue;
+ }
+
+ if (test_and_clear_bit(RXRPC_CLIENT_CONN_REAP_TIMER,
+ &local->client_conn_flags))
+ rxrpc_discard_expired_client_conns(local);
+
/* Deal with calls that want immediate attention. */
if ((call = list_first_entry_or_null(&local->call_attend_q,
struct rxrpc_call,
continue;
}
+ if (!list_empty(&local->new_client_calls))
+ rxrpc_connect_client_calls(local);
+
/* Process received packets and errors. */
if ((skb = __skb_dequeue(&rx_queue))) {
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
switch (skb->mark) {
case RXRPC_SKB_MARK_PACKET:
skb->priority = 0;
- rxrpc_input_packet(local, &skb);
+ if (!rxrpc_input_packet(local, &skb))
+ rxrpc_reject_packet(local, skb);
trace_rxrpc_rx_done(skb->mark, skb->priority);
rxrpc_free_skb(skb, rxrpc_skb_put_input);
break;
rxrpc_input_error(local, skb);
rxrpc_free_skb(skb, rxrpc_skb_put_error_report);
break;
+ case RXRPC_SKB_MARK_SERVICE_CONN_SECURED:
+ rxrpc_input_conn_event(sp->conn, skb);
+ rxrpc_put_connection(sp->conn, rxrpc_conn_put_poke);
+ rxrpc_free_skb(skb, rxrpc_skb_put_conn_secured);
+ break;
default:
WARN_ON_ONCE(1);
rxrpc_free_skb(skb, rxrpc_skb_put_unknown);
set_current_state(TASK_INTERRUPTIBLE);
should_stop = kthread_should_stop();
if (!skb_queue_empty(&local->rx_queue) ||
- !list_empty(&local->call_attend_q)) {
+ !list_empty(&local->call_attend_q) ||
+ !list_empty(&local->conn_attend_q) ||
+ !list_empty(&local->new_client_calls) ||
+ test_bit(RXRPC_CLIENT_CONN_REAP_TIMER,
+ &local->client_conn_flags)) {
__set_current_state(TASK_RUNNING);
continue;
}
}
}
+static void rxrpc_client_conn_reap_timeout(struct timer_list *timer)
+{
+ struct rxrpc_local *local =
+ container_of(timer, struct rxrpc_local, client_conn_reap_timer);
+
+ if (local->kill_all_client_conns &&
+ test_and_set_bit(RXRPC_CLIENT_CONN_REAP_TIMER, &local->client_conn_flags))
+ rxrpc_wake_up_io_thread(local);
+}
+
/*
* Allocate a new local endpoint.
*/
-static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet,
+static struct rxrpc_local *rxrpc_alloc_local(struct net *net,
const struct sockaddr_rxrpc *srx)
{
struct rxrpc_local *local;
+ u32 tmp;
local = kzalloc(sizeof(struct rxrpc_local), GFP_KERNEL);
if (local) {
refcount_set(&local->ref, 1);
atomic_set(&local->active_users, 1);
- local->rxnet = rxnet;
+ local->net = net;
+ local->rxnet = rxrpc_net(net);
INIT_HLIST_NODE(&local->link);
init_rwsem(&local->defrag_sem);
init_completion(&local->io_thread_ready);
skb_queue_head_init(&local->rx_queue);
+ INIT_LIST_HEAD(&local->conn_attend_q);
INIT_LIST_HEAD(&local->call_attend_q);
+
local->client_bundles = RB_ROOT;
spin_lock_init(&local->client_bundles_lock);
+ local->kill_all_client_conns = false;
+ INIT_LIST_HEAD(&local->idle_client_conns);
+ timer_setup(&local->client_conn_reap_timer,
+ rxrpc_client_conn_reap_timeout, 0);
+
spin_lock_init(&local->lock);
rwlock_init(&local->services_lock);
local->debug_id = atomic_inc_return(&rxrpc_debug_id);
memcpy(&local->srx, srx, sizeof(*srx));
local->srx.srx_service = 0;
+ idr_init(&local->conn_ids);
+ get_random_bytes(&tmp, sizeof(tmp));
+ tmp &= 0x3fffffff;
+ if (tmp == 0)
+ tmp = 1;
+ idr_set_cursor(&local->conn_ids, tmp);
+ INIT_LIST_HEAD(&local->new_client_calls);
+ spin_lock_init(&local->client_call_lock);
+
trace_rxrpc_local(local->debug_id, rxrpc_local_new, 1, 1);
}
goto found;
}
- local = rxrpc_alloc_local(rxnet, srx);
+ local = rxrpc_alloc_local(net, srx);
if (!local)
goto nomem;
* local endpoint.
*/
rxrpc_purge_queue(&local->rx_queue);
+ rxrpc_purge_client_connections(local);
}
/*
unsigned int rxrpc_net_id;
-static void rxrpc_client_conn_reap_timeout(struct timer_list *timer)
-{
- struct rxrpc_net *rxnet =
- container_of(timer, struct rxrpc_net, client_conn_reap_timer);
-
- if (rxnet->live)
- rxrpc_queue_work(&rxnet->client_conn_reaper);
-}
-
static void rxrpc_service_conn_reap_timeout(struct timer_list *timer)
{
struct rxrpc_net *rxnet =
rxrpc_service_conn_reap_timeout, 0);
atomic_set(&rxnet->nr_client_conns, 0);
- rxnet->kill_all_client_conns = false;
- spin_lock_init(&rxnet->client_conn_cache_lock);
- mutex_init(&rxnet->client_conn_discard_lock);
- INIT_LIST_HEAD(&rxnet->idle_client_conns);
- INIT_WORK(&rxnet->client_conn_reaper,
- rxrpc_discard_expired_client_conns);
- timer_setup(&rxnet->client_conn_reap_timer,
- rxrpc_client_conn_reap_timeout, 0);
INIT_HLIST_HEAD(&rxnet->local_endpoints);
mutex_init(&rxnet->local_mutex);
rxrpc_tx_point_call_ack);
rxrpc_tx_backoff(call, ret);
- if (call->state < RXRPC_CALL_COMPLETE) {
+ if (!__rxrpc_call_is_complete(call)) {
if (ret < 0)
rxrpc_cancel_rtt_probe(call, serial, rtt_slot);
rxrpc_set_keepalive(call);
}
/*
+ * Transmit a connection-level abort.
+ */
+void rxrpc_send_conn_abort(struct rxrpc_connection *conn)
+{
+ struct rxrpc_wire_header whdr;
+ struct msghdr msg;
+ struct kvec iov[2];
+ __be32 word;
+ size_t len;
+ u32 serial;
+ int ret;
+
+ msg.msg_name = &conn->peer->srx.transport;
+ msg.msg_namelen = conn->peer->srx.transport_len;
+ msg.msg_control = NULL;
+ msg.msg_controllen = 0;
+ msg.msg_flags = 0;
+
+ whdr.epoch = htonl(conn->proto.epoch);
+ whdr.cid = htonl(conn->proto.cid);
+ whdr.callNumber = 0;
+ whdr.seq = 0;
+ whdr.type = RXRPC_PACKET_TYPE_ABORT;
+ whdr.flags = conn->out_clientflag;
+ whdr.userStatus = 0;
+ whdr.securityIndex = conn->security_ix;
+ whdr._rsvd = 0;
+ whdr.serviceId = htons(conn->service_id);
+
+ word = htonl(conn->abort_code);
+
+ iov[0].iov_base = &whdr;
+ iov[0].iov_len = sizeof(whdr);
+ iov[1].iov_base = &word;
+ iov[1].iov_len = sizeof(word);
+
+ len = iov[0].iov_len + iov[1].iov_len;
+
+ serial = atomic_inc_return(&conn->serial);
+ whdr.serial = htonl(serial);
+
+ iov_iter_kvec(&msg.msg_iter, WRITE, iov, 2, len);
+ ret = do_udp_sendmsg(conn->local->socket, &msg, len);
+ if (ret < 0) {
+ trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
+ rxrpc_tx_point_conn_abort);
+ _debug("sendmsg failed: %d", ret);
+ return;
+ }
+
+ trace_rxrpc_tx_packet(conn->debug_id, &whdr, rxrpc_tx_point_conn_abort);
+
+ conn->peer->last_tx_at = ktime_get_seconds();
+}
+
+/*
* Reject a packet through the local endpoint.
*/
void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb)
static inline void rxrpc_instant_resend(struct rxrpc_call *call,
struct rxrpc_txbuf *txb)
{
- if (call->state < RXRPC_CALL_COMPLETE)
+ if (!__rxrpc_call_is_complete(call))
kdebug("resend");
}
* assess the MTU size for the network interface through which this peer is
* reached
*/
-static void rxrpc_assess_MTU_size(struct rxrpc_sock *rx,
+static void rxrpc_assess_MTU_size(struct rxrpc_local *local,
struct rxrpc_peer *peer)
{
- struct net *net = sock_net(&rx->sk);
+ struct net *net = local->net;
struct dst_entry *dst;
struct rtable *rt;
struct flowi fl;
/*
* Initialise peer record.
*/
-static void rxrpc_init_peer(struct rxrpc_sock *rx, struct rxrpc_peer *peer,
+static void rxrpc_init_peer(struct rxrpc_local *local, struct rxrpc_peer *peer,
unsigned long hash_key)
{
peer->hash_key = hash_key;
- rxrpc_assess_MTU_size(rx, peer);
+ rxrpc_assess_MTU_size(local, peer);
peer->mtu = peer->if_mtu;
peer->rtt_last_req = ktime_get_real();
/*
* Set up a new peer.
*/
-static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_sock *rx,
- struct rxrpc_local *local,
+static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local,
struct sockaddr_rxrpc *srx,
unsigned long hash_key,
gfp_t gfp)
peer = rxrpc_alloc_peer(local, gfp, rxrpc_peer_new_client);
if (peer) {
memcpy(&peer->srx, srx, sizeof(*srx));
- rxrpc_init_peer(rx, peer, hash_key);
+ rxrpc_init_peer(local, peer, hash_key);
}
_leave(" = %p", peer);
* since we've already done a search in the list from the non-reentrant context
* (the data_ready handler) that is the only place we can add new peers.
*/
-void rxrpc_new_incoming_peer(struct rxrpc_sock *rx, struct rxrpc_local *local,
- struct rxrpc_peer *peer)
+void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer)
{
struct rxrpc_net *rxnet = local->rxnet;
unsigned long hash_key;
hash_key = rxrpc_peer_hash_key(local, &peer->srx);
- rxrpc_init_peer(rx, peer, hash_key);
+ rxrpc_init_peer(local, peer, hash_key);
spin_lock(&rxnet->peer_hash_lock);
hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key);
/*
* obtain a remote transport endpoint for the specified address
*/
-struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *rx,
- struct rxrpc_local *local,
+struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local,
struct sockaddr_rxrpc *srx, gfp_t gfp)
{
struct rxrpc_peer *peer, *candidate;
/* The peer is not yet present in hash - create a candidate
* for a new record and then redo the search.
*/
- candidate = rxrpc_create_peer(rx, local, srx, hash_key, gfp);
+ candidate = rxrpc_create_peer(local, srx, hash_key, gfp);
if (!candidate) {
_leave(" = NULL [nomem]");
return NULL;
static const char *const rxrpc_conn_states[RXRPC_CONN__NR_STATES] = {
[RXRPC_CONN_UNUSED] = "Unused ",
+ [RXRPC_CONN_CLIENT_UNSECURED] = "ClUnsec ",
[RXRPC_CONN_CLIENT] = "Client ",
[RXRPC_CONN_SERVICE_PREALLOC] = "SvPrealc",
[RXRPC_CONN_SERVICE_UNSECURED] = "SvUnsec ",
[RXRPC_CONN_SERVICE_CHALLENGING] = "SvChall ",
[RXRPC_CONN_SERVICE] = "SvSecure",
- [RXRPC_CONN_REMOTELY_ABORTED] = "RmtAbort",
- [RXRPC_CONN_LOCALLY_ABORTED] = "LocAbort",
+ [RXRPC_CONN_ABORTED] = "Aborted ",
};
/*
struct rxrpc_local *local;
struct rxrpc_call *call;
struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
+ enum rxrpc_call_state state;
unsigned long timeout = 0;
rxrpc_seq_t acks_hard_ack;
char lbuff[50], rbuff[50];
sprintf(rbuff, "%pISpc", &call->dest_srx.transport);
- if (call->state != RXRPC_CALL_SERVER_PREALLOC) {
+ state = rxrpc_call_state(call);
+ if (state != RXRPC_CALL_SERVER_PREALLOC) {
timeout = READ_ONCE(call->expect_rx_by);
timeout -= jiffies;
}
call->call_id,
rxrpc_is_service_call(call) ? "Svc" : "Clt",
refcount_read(&call->ref),
- rxrpc_call_states[call->state],
+ rxrpc_call_states[state],
call->abort_code,
call->debug_id,
acks_hard_ack, READ_ONCE(call->tx_top) - acks_hard_ack,
{
struct rxrpc_connection *conn;
struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
+ const char *state;
char lbuff[50], rbuff[50];
if (v == &rxnet->conn_proc_list) {
}
sprintf(lbuff, "%pISpc", &conn->local->srx.transport);
-
sprintf(rbuff, "%pISpc", &conn->peer->srx.transport);
print:
+ state = rxrpc_is_conn_aborted(conn) ?
+ rxrpc_call_completions[conn->completion] :
+ rxrpc_conn_states[conn->state];
seq_printf(seq,
"UDP %-47.47s %-47.47s %4x %08x %s %3u %3d"
" %s %08x %08x %08x %08x %08x %08x %08x\n",
rxrpc_conn_is_service(conn) ? "Svc" : "Clt",
refcount_read(&conn->ref),
atomic_read(&conn->active),
- rxrpc_conn_states[conn->state],
+ state,
key_serial(conn->key),
atomic_read(&conn->serial),
conn->hi_serial,
}
/*
- * Transition a call to the complete state.
- */
-bool __rxrpc_set_call_completion(struct rxrpc_call *call,
- enum rxrpc_call_completion compl,
- u32 abort_code,
- int error)
-{
- if (call->state < RXRPC_CALL_COMPLETE) {
- call->abort_code = abort_code;
- call->error = error;
- call->completion = compl;
- call->state = RXRPC_CALL_COMPLETE;
- trace_rxrpc_call_complete(call);
- wake_up(&call->waitq);
- rxrpc_notify_socket(call);
- return true;
- }
- return false;
-}
-
-bool rxrpc_set_call_completion(struct rxrpc_call *call,
- enum rxrpc_call_completion compl,
- u32 abort_code,
- int error)
-{
- bool ret = false;
-
- if (call->state < RXRPC_CALL_COMPLETE) {
- write_lock(&call->state_lock);
- ret = __rxrpc_set_call_completion(call, compl, abort_code, error);
- write_unlock(&call->state_lock);
- }
- return ret;
-}
-
-/*
- * Record that a call successfully completed.
- */
-bool __rxrpc_call_completed(struct rxrpc_call *call)
-{
- return __rxrpc_set_call_completion(call, RXRPC_CALL_SUCCEEDED, 0, 0);
-}
-
-bool rxrpc_call_completed(struct rxrpc_call *call)
-{
- bool ret = false;
-
- if (call->state < RXRPC_CALL_COMPLETE) {
- write_lock(&call->state_lock);
- ret = __rxrpc_call_completed(call);
- write_unlock(&call->state_lock);
- }
- return ret;
-}
-
-/*
- * Record that a call is locally aborted.
- */
-bool __rxrpc_abort_call(const char *why, struct rxrpc_call *call,
- rxrpc_seq_t seq, u32 abort_code, int error)
-{
- trace_rxrpc_abort(call->debug_id, why, call->cid, call->call_id, seq,
- abort_code, error);
- return __rxrpc_set_call_completion(call, RXRPC_CALL_LOCALLY_ABORTED,
- abort_code, error);
-}
-
-bool rxrpc_abort_call(const char *why, struct rxrpc_call *call,
- rxrpc_seq_t seq, u32 abort_code, int error)
-{
- bool ret;
-
- write_lock(&call->state_lock);
- ret = __rxrpc_abort_call(why, call, seq, abort_code, error);
- write_unlock(&call->state_lock);
- return ret;
-}
-
-/*
* Pass a call terminating message to userspace.
*/
static int rxrpc_recvmsg_term(struct rxrpc_call *call, struct msghdr *msg)
ret = put_cmsg(msg, SOL_RXRPC, RXRPC_LOCAL_ERROR, 4, &tmp);
break;
default:
- pr_err("Invalid terminal call state %u\n", call->state);
+ pr_err("Invalid terminal call state %u\n", call->completion);
BUG();
break;
}
}
/*
- * End the packet reception phase.
- */
-static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial)
-{
- rxrpc_seq_t whigh = READ_ONCE(call->rx_highest_seq);
-
- _enter("%d,%s", call->debug_id, rxrpc_call_states[call->state]);
-
- trace_rxrpc_receive(call, rxrpc_receive_end, 0, whigh);
-
- if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY)
- rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_terminal_ack);
-
- write_lock(&call->state_lock);
-
- switch (call->state) {
- case RXRPC_CALL_CLIENT_RECV_REPLY:
- __rxrpc_call_completed(call);
- write_unlock(&call->state_lock);
- break;
-
- case RXRPC_CALL_SERVER_RECV_REQUEST:
- call->state = RXRPC_CALL_SERVER_ACK_REQUEST;
- call->expect_req_by = jiffies + MAX_JIFFY_OFFSET;
- write_unlock(&call->state_lock);
- rxrpc_propose_delay_ACK(call, serial,
- rxrpc_propose_ack_processing_op);
- break;
- default:
- write_unlock(&call->state_lock);
- break;
- }
-}
-
-/*
* Discard a packet we've used up and advance the Rx window by one.
*/
static void rxrpc_rotate_rx_window(struct rxrpc_call *call)
trace_rxrpc_receive(call, last ? rxrpc_receive_rotate_last : rxrpc_receive_rotate,
serial, call->rx_consumed);
- if (last) {
- rxrpc_end_rx_phase(call, serial);
- return;
- }
+
+ if (last)
+ set_bit(RXRPC_CALL_RECVMSG_READ_ALL, &call->flags);
/* Check to see if there's an ACK that needs sending. */
acked = atomic_add_return(call->rx_consumed - old_consumed,
/*
* Deliver messages to a call. This keeps processing packets until the buffer
* is filled and we find either more DATA (returns 0) or the end of the DATA
- * (returns 1). If more packets are required, it returns -EAGAIN.
+ * (returns 1). If more packets are required, it returns -EAGAIN and if the
+ * call has failed it returns -EIO.
*/
static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call,
struct msghdr *msg, struct iov_iter *iter,
rx_pkt_offset = call->rx_pkt_offset;
rx_pkt_len = call->rx_pkt_len;
- if (call->state >= RXRPC_CALL_SERVER_ACK_REQUEST) {
+ if (rxrpc_call_has_failed(call)) {
+ seq = lower_32_bits(atomic64_read(&call->ackr_window)) - 1;
+ ret = -EIO;
+ goto done;
+ }
+
+ if (test_bit(RXRPC_CALL_RECVMSG_READ_ALL, &call->flags)) {
seq = lower_32_bits(atomic64_read(&call->ackr_window)) - 1;
ret = 1;
goto done;
if (rx_pkt_offset == 0) {
ret2 = rxrpc_verify_data(call, skb);
- rx_pkt_offset = sp->offset;
- rx_pkt_len = sp->len;
trace_rxrpc_recvdata(call, rxrpc_recvmsg_next, seq,
- rx_pkt_offset, rx_pkt_len, ret2);
+ sp->offset, sp->len, ret2);
if (ret2 < 0) {
+ kdebug("verify = %d", ret2);
ret = ret2;
goto out;
}
+ rx_pkt_offset = sp->offset;
+ rx_pkt_len = sp->len;
} else {
trace_rxrpc_recvdata(call, rxrpc_recvmsg_cont, seq,
rx_pkt_offset, rx_pkt_len, 0);
struct rxrpc_call *call;
struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
struct list_head *l;
+ unsigned int call_debug_id = 0;
size_t copied = 0;
long timeo;
int ret;
DEFINE_WAIT(wait);
- trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_enter, 0);
+ trace_rxrpc_recvmsg(0, rxrpc_recvmsg_enter, 0);
if (flags & (MSG_OOB | MSG_TRUNC))
return -EOPNOTSUPP;
if (list_empty(&rx->recvmsg_q)) {
if (signal_pending(current))
goto wait_interrupted;
- trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_wait, 0);
+ trace_rxrpc_recvmsg(0, rxrpc_recvmsg_wait, 0);
timeo = schedule_timeout(timeo);
}
finish_wait(sk_sleep(&rx->sk), &wait);
rxrpc_get_call(call, rxrpc_call_get_recvmsg);
write_unlock(&rx->recvmsg_lock);
- trace_rxrpc_recvmsg(call, rxrpc_recvmsg_dequeue, 0);
+ call_debug_id = call->debug_id;
+ trace_rxrpc_recvmsg(call_debug_id, rxrpc_recvmsg_dequeue, 0);
/* We're going to drop the socket lock, so we need to lock the call
* against interference by sendmsg.
msg->msg_namelen = len;
}
- switch (READ_ONCE(call->state)) {
- case RXRPC_CALL_CLIENT_RECV_REPLY:
- case RXRPC_CALL_SERVER_RECV_REQUEST:
- case RXRPC_CALL_SERVER_ACK_REQUEST:
- ret = rxrpc_recvmsg_data(sock, call, msg, &msg->msg_iter, len,
- flags, &copied);
- if (ret == -EAGAIN)
- ret = 0;
-
- if (!skb_queue_empty(&call->recvmsg_queue))
- rxrpc_notify_socket(call);
- break;
- default:
+ ret = rxrpc_recvmsg_data(sock, call, msg, &msg->msg_iter, len,
+ flags, &copied);
+ if (ret == -EAGAIN)
ret = 0;
- break;
- }
-
+ if (ret == -EIO)
+ goto call_failed;
if (ret < 0)
goto error_unlock_call;
- if (call->state == RXRPC_CALL_COMPLETE) {
- ret = rxrpc_recvmsg_term(call, msg);
- if (ret < 0)
- goto error_unlock_call;
- if (!(flags & MSG_PEEK))
- rxrpc_release_call(rx, call);
- msg->msg_flags |= MSG_EOR;
- ret = 1;
- }
+ if (rxrpc_call_is_complete(call) &&
+ skb_queue_empty(&call->recvmsg_queue))
+ goto call_complete;
+ if (rxrpc_call_has_failed(call))
+ goto call_failed;
+ rxrpc_notify_socket(call);
+ goto not_yet_complete;
+
+call_failed:
+ rxrpc_purge_queue(&call->recvmsg_queue);
+call_complete:
+ ret = rxrpc_recvmsg_term(call, msg);
+ if (ret < 0)
+ goto error_unlock_call;
+ if (!(flags & MSG_PEEK))
+ rxrpc_release_call(rx, call);
+ msg->msg_flags |= MSG_EOR;
+ ret = 1;
+
+not_yet_complete:
if (ret == 0)
msg->msg_flags |= MSG_MORE;
else
error_unlock_call:
mutex_unlock(&call->user_mutex);
rxrpc_put_call(call, rxrpc_call_put_recvmsg);
- trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, ret);
+ trace_rxrpc_recvmsg(call_debug_id, rxrpc_recvmsg_return, ret);
return ret;
error_requeue_call:
write_lock(&rx->recvmsg_lock);
list_add(&call->recvmsg_link, &rx->recvmsg_q);
write_unlock(&rx->recvmsg_lock);
- trace_rxrpc_recvmsg(call, rxrpc_recvmsg_requeue, 0);
+ trace_rxrpc_recvmsg(call_debug_id, rxrpc_recvmsg_requeue, 0);
} else {
rxrpc_put_call(call, rxrpc_call_put_recvmsg);
}
error_no_call:
release_sock(&rx->sk);
error_trace:
- trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, ret);
+ trace_rxrpc_recvmsg(call_debug_id, rxrpc_recvmsg_return, ret);
return ret;
wait_interrupted:
size_t offset = 0;
int ret;
- _enter("{%d,%s},%zu,%d",
- call->debug_id, rxrpc_call_states[call->state],
- *_len, want_more);
-
- ASSERTCMP(call->state, !=, RXRPC_CALL_SERVER_SECURING);
+ _enter("{%d},%zu,%d", call->debug_id, *_len, want_more);
mutex_lock(&call->user_mutex);
- switch (READ_ONCE(call->state)) {
- case RXRPC_CALL_CLIENT_RECV_REPLY:
- case RXRPC_CALL_SERVER_RECV_REQUEST:
- case RXRPC_CALL_SERVER_ACK_REQUEST:
- ret = rxrpc_recvmsg_data(sock, call, NULL, iter,
- *_len, 0, &offset);
- *_len -= offset;
- if (ret < 0)
- goto out;
-
- /* We can only reach here with a partially full buffer if we
- * have reached the end of the data. We must otherwise have a
- * full buffer or have been given -EAGAIN.
- */
- if (ret == 1) {
- if (iov_iter_count(iter) > 0)
- goto short_data;
- if (!want_more)
- goto read_phase_complete;
- ret = 0;
- goto out;
- }
-
- if (!want_more)
- goto excess_data;
+ ret = rxrpc_recvmsg_data(sock, call, NULL, iter, *_len, 0, &offset);
+ *_len -= offset;
+ if (ret == -EIO)
+ goto call_failed;
+ if (ret < 0)
goto out;
- case RXRPC_CALL_COMPLETE:
- goto call_complete;
-
- default:
- ret = -EINPROGRESS;
+ /* We can only reach here with a partially full buffer if we have
+ * reached the end of the data. We must otherwise have a full buffer
+ * or have been given -EAGAIN.
+ */
+ if (ret == 1) {
+ if (iov_iter_count(iter) > 0)
+ goto short_data;
+ if (!want_more)
+ goto read_phase_complete;
+ ret = 0;
goto out;
}
+ if (!want_more)
+ goto excess_data;
+ goto out;
+
read_phase_complete:
ret = 1;
out:
return ret;
short_data:
- trace_rxrpc_rx_eproto(call, 0, tracepoint_string("short_data"));
+ trace_rxrpc_abort(call->debug_id, rxrpc_recvmsg_short_data,
+ call->cid, call->call_id, call->rx_consumed,
+ 0, -EBADMSG);
ret = -EBADMSG;
goto out;
excess_data:
- trace_rxrpc_rx_eproto(call, 0, tracepoint_string("excess_data"));
+ trace_rxrpc_abort(call->debug_id, rxrpc_recvmsg_excess_data,
+ call->cid, call->call_id, call->rx_consumed,
+ 0, -EMSGSIZE);
ret = -EMSGSIZE;
goto out;
-call_complete:
+call_failed:
*_abort = call->abort_code;
ret = call->error;
if (call->completion == RXRPC_CALL_SUCCEEDED) {
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
struct rxrpc_crypt iv;
struct scatterlist sg[16];
- bool aborted;
u32 data_size, buf;
u16 check;
int ret;
_enter("");
- if (sp->len < 8) {
- aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_hdr", "V1H",
- RXKADSEALEDINCON);
- goto protocol_error;
- }
+ if (sp->len < 8)
+ return rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON,
+ rxkad_abort_1_short_header);
/* Decrypt the skbuff in-place. TODO: We really want to decrypt
* directly into the target buffer.
skcipher_request_zero(req);
/* Extract the decrypted packet length */
- if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0) {
- aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_len", "XV1",
- RXKADDATALEN);
- goto protocol_error;
- }
+ if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0)
+ return rxrpc_abort_eproto(call, skb, RXKADDATALEN,
+ rxkad_abort_1_short_encdata);
sp->offset += sizeof(sechdr);
sp->len -= sizeof(sechdr);
check = buf >> 16;
check ^= seq ^ call->call_id;
check &= 0xffff;
- if (check != 0) {
- aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_check", "V1C",
- RXKADSEALEDINCON);
- goto protocol_error;
- }
-
- if (data_size > sp->len) {
- aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_datalen", "V1L",
- RXKADDATALEN);
- goto protocol_error;
- }
+ if (check != 0)
+ return rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON,
+ rxkad_abort_1_short_check);
+ if (data_size > sp->len)
+ return rxrpc_abort_eproto(call, skb, RXKADDATALEN,
+ rxkad_abort_1_short_data);
sp->len = data_size;
_leave(" = 0 [dlen=%x]", data_size);
return 0;
-
-protocol_error:
- if (aborted)
- rxrpc_send_abort_packet(call);
- return -EPROTO;
}
/*
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
struct rxrpc_crypt iv;
struct scatterlist _sg[4], *sg;
- bool aborted;
u32 data_size, buf;
u16 check;
int nsg, ret;
_enter(",{%d}", sp->len);
- if (sp->len < 8) {
- aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_hdr", "V2H",
- RXKADSEALEDINCON);
- goto protocol_error;
- }
+ if (sp->len < 8)
+ return rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON,
+ rxkad_abort_2_short_header);
/* Decrypt the skbuff in-place. TODO: We really want to decrypt
* directly into the target buffer.
} else {
sg = kmalloc_array(nsg, sizeof(*sg), GFP_NOIO);
if (!sg)
- goto nomem;
+ return -ENOMEM;
}
sg_init_table(sg, nsg);
kfree(sg);
/* Extract the decrypted packet length */
- if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0) {
- aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_len", "XV2",
- RXKADDATALEN);
- goto protocol_error;
- }
+ if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0)
+ return rxrpc_abort_eproto(call, skb, RXKADDATALEN,
+ rxkad_abort_2_short_len);
sp->offset += sizeof(sechdr);
sp->len -= sizeof(sechdr);
check = buf >> 16;
check ^= seq ^ call->call_id;
check &= 0xffff;
- if (check != 0) {
- aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_check", "V2C",
- RXKADSEALEDINCON);
- goto protocol_error;
- }
+ if (check != 0)
+ return rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON,
+ rxkad_abort_2_short_check);
- if (data_size > sp->len) {
- aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_datalen", "V2L",
- RXKADDATALEN);
- goto protocol_error;
- }
+ if (data_size > sp->len)
+ return rxrpc_abort_eproto(call, skb, RXKADDATALEN,
+ rxkad_abort_2_short_data);
sp->len = data_size;
_leave(" = 0 [dlen=%x]", data_size);
return 0;
-
-protocol_error:
- if (aborted)
- rxrpc_send_abort_packet(call);
- return -EPROTO;
-
-nomem:
- _leave(" = -ENOMEM");
- return -ENOMEM;
}
/*
__be32 buf[2];
} crypto __aligned(8);
rxrpc_seq_t seq = sp->hdr.seq;
- bool aborted;
int ret;
u16 cksum;
u32 x, y;
cksum = 1; /* zero checksums are not permitted */
if (cksum != sp->hdr.cksum) {
- aborted = rxrpc_abort_eproto(call, skb, "rxkad_csum", "VCK",
- RXKADSEALEDINCON);
- goto protocol_error;
+ ret = rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON,
+ rxkad_abort_bad_checksum);
+ goto out;
}
switch (call->conn->security_level) {
break;
}
+out:
skcipher_request_free(req);
return ret;
-
-protocol_error:
- if (aborted)
- rxrpc_send_abort_packet(call);
- return -EPROTO;
}
/*
* respond to a challenge packet
*/
static int rxkad_respond_to_challenge(struct rxrpc_connection *conn,
- struct sk_buff *skb,
- u32 *_abort_code)
+ struct sk_buff *skb)
{
const struct rxrpc_key_token *token;
struct rxkad_challenge challenge;
struct rxkad_response *resp;
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
- const char *eproto;
- u32 version, nonce, min_level, abort_code;
- int ret;
+ u32 version, nonce, min_level;
+ int ret = -EPROTO;
_enter("{%d,%x}", conn->debug_id, key_serial(conn->key));
- eproto = tracepoint_string("chall_no_key");
- abort_code = RX_PROTOCOL_ERROR;
if (!conn->key)
- goto protocol_error;
+ return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO,
+ rxkad_abort_chall_no_key);
- abort_code = RXKADEXPIRED;
ret = key_validate(conn->key);
if (ret < 0)
- goto other_error;
+ return rxrpc_abort_conn(conn, skb, RXKADEXPIRED, ret,
+ rxkad_abort_chall_key_expired);
- eproto = tracepoint_string("chall_short");
- abort_code = RXKADPACKETSHORT;
if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
&challenge, sizeof(challenge)) < 0)
- goto protocol_error;
+ return rxrpc_abort_conn(conn, skb, RXKADPACKETSHORT, -EPROTO,
+ rxkad_abort_chall_short);
version = ntohl(challenge.version);
nonce = ntohl(challenge.nonce);
trace_rxrpc_rx_challenge(conn, sp->hdr.serial, version, nonce, min_level);
- eproto = tracepoint_string("chall_ver");
- abort_code = RXKADINCONSISTENCY;
if (version != RXKAD_VERSION)
- goto protocol_error;
+ return rxrpc_abort_conn(conn, skb, RXKADINCONSISTENCY, -EPROTO,
+ rxkad_abort_chall_version);
- abort_code = RXKADLEVELFAIL;
- ret = -EACCES;
if (conn->security_level < min_level)
- goto other_error;
+ return rxrpc_abort_conn(conn, skb, RXKADLEVELFAIL, -EACCES,
+ rxkad_abort_chall_level);
token = conn->key->payload.data[0];
ret = rxkad_send_response(conn, &sp->hdr, resp, token->kad);
kfree(resp);
return ret;
-
-protocol_error:
- trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto);
- ret = -EPROTO;
-other_error:
- *_abort_code = abort_code;
- return ret;
}
/*
struct sk_buff *skb,
void *ticket, size_t ticket_len,
struct rxrpc_crypt *_session_key,
- time64_t *_expiry,
- u32 *_abort_code)
+ time64_t *_expiry)
{
struct skcipher_request *req;
- struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
struct rxrpc_crypt iv, key;
struct scatterlist sg[1];
struct in_addr addr;
unsigned int life;
- const char *eproto;
time64_t issue, now;
bool little_endian;
- int ret;
- u32 abort_code;
u8 *p, *q, *name, *end;
_enter("{%d},{%x}", conn->debug_id, key_serial(server_key));
memcpy(&iv, &server_key->payload.data[2], sizeof(iv));
- ret = -ENOMEM;
req = skcipher_request_alloc(server_key->payload.data[0], GFP_NOFS);
if (!req)
- goto temporary_error;
+ return -ENOMEM;
sg_init_one(&sg[0], ticket, ticket_len);
skcipher_request_set_callback(req, 0, NULL, NULL);
p = ticket;
end = p + ticket_len;
-#define Z(field) \
- ({ \
- u8 *__str = p; \
- eproto = tracepoint_string("rxkad_bad_"#field); \
- q = memchr(p, 0, end - p); \
- if (!q || q - p > (field##_SZ)) \
- goto bad_ticket; \
- for (; p < q; p++) \
- if (!isprint(*p)) \
- goto bad_ticket; \
- p++; \
- __str; \
+#define Z(field, fieldl) \
+ ({ \
+ u8 *__str = p; \
+ q = memchr(p, 0, end - p); \
+ if (!q || q - p > field##_SZ) \
+ return rxrpc_abort_conn( \
+ conn, skb, RXKADBADTICKET, -EPROTO, \
+ rxkad_abort_resp_tkt_##fieldl); \
+ for (; p < q; p++) \
+ if (!isprint(*p)) \
+ return rxrpc_abort_conn( \
+ conn, skb, RXKADBADTICKET, -EPROTO, \
+ rxkad_abort_resp_tkt_##fieldl); \
+ p++; \
+ __str; \
})
/* extract the ticket flags */
p++;
/* extract the authentication name */
- name = Z(ANAME);
+ name = Z(ANAME, aname);
_debug("KIV ANAME: %s", name);
/* extract the principal's instance */
- name = Z(INST);
+ name = Z(INST, inst);
_debug("KIV INST : %s", name);
/* extract the principal's authentication domain */
- name = Z(REALM);
+ name = Z(REALM, realm);
_debug("KIV REALM: %s", name);
- eproto = tracepoint_string("rxkad_bad_len");
if (end - p < 4 + 8 + 4 + 2)
- goto bad_ticket;
+ return rxrpc_abort_conn(conn, skb, RXKADBADTICKET, -EPROTO,
+ rxkad_abort_resp_tkt_short);
/* get the IPv4 address of the entity that requested the ticket */
memcpy(&addr, p, sizeof(addr));
_debug("KIV ISSUE: %llx [%llx]", issue, now);
/* check the ticket is in date */
- if (issue > now) {
- abort_code = RXKADNOAUTH;
- ret = -EKEYREJECTED;
- goto other_error;
- }
-
- if (issue < now - life) {
- abort_code = RXKADEXPIRED;
- ret = -EKEYEXPIRED;
- goto other_error;
- }
+ if (issue > now)
+ return rxrpc_abort_conn(conn, skb, RXKADNOAUTH, -EKEYREJECTED,
+ rxkad_abort_resp_tkt_future);
+ if (issue < now - life)
+ return rxrpc_abort_conn(conn, skb, RXKADEXPIRED, -EKEYEXPIRED,
+ rxkad_abort_resp_tkt_expired);
*_expiry = issue + life;
/* get the service name */
- name = Z(SNAME);
+ name = Z(SNAME, sname);
_debug("KIV SNAME: %s", name);
/* get the service instance name */
- name = Z(INST);
+ name = Z(INST, sinst);
_debug("KIV SINST: %s", name);
return 0;
-
-bad_ticket:
- trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto);
- abort_code = RXKADBADTICKET;
- ret = -EPROTO;
-other_error:
- *_abort_code = abort_code;
- return ret;
-temporary_error:
- return ret;
}
/*
* verify a response
*/
static int rxkad_verify_response(struct rxrpc_connection *conn,
- struct sk_buff *skb,
- u32 *_abort_code)
+ struct sk_buff *skb)
{
struct rxkad_response *response;
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
struct rxrpc_crypt session_key;
struct key *server_key;
- const char *eproto;
time64_t expiry;
void *ticket;
- u32 abort_code, version, kvno, ticket_len, level;
+ u32 version, kvno, ticket_len, level;
__be32 csum;
int ret, i;
server_key = rxrpc_look_up_server_security(conn, skb, 0, 0);
if (IS_ERR(server_key)) {
- switch (PTR_ERR(server_key)) {
+ ret = PTR_ERR(server_key);
+ switch (ret) {
case -ENOKEY:
- abort_code = RXKADUNKNOWNKEY;
- break;
+ return rxrpc_abort_conn(conn, skb, RXKADUNKNOWNKEY, ret,
+ rxkad_abort_resp_nokey);
case -EKEYEXPIRED:
- abort_code = RXKADEXPIRED;
- break;
+ return rxrpc_abort_conn(conn, skb, RXKADEXPIRED, ret,
+ rxkad_abort_resp_key_expired);
default:
- abort_code = RXKADNOAUTH;
- break;
+ return rxrpc_abort_conn(conn, skb, RXKADNOAUTH, ret,
+ rxkad_abort_resp_key_rejected);
}
- trace_rxrpc_abort(0, "SVK",
- sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- abort_code, PTR_ERR(server_key));
- *_abort_code = abort_code;
- return -EPROTO;
}
ret = -ENOMEM;
if (!response)
goto temporary_error;
- eproto = tracepoint_string("rxkad_rsp_short");
- abort_code = RXKADPACKETSHORT;
if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
- response, sizeof(*response)) < 0)
+ response, sizeof(*response)) < 0) {
+ rxrpc_abort_conn(conn, skb, RXKADPACKETSHORT, -EPROTO,
+ rxkad_abort_resp_short);
goto protocol_error;
+ }
version = ntohl(response->version);
ticket_len = ntohl(response->ticket_len);
trace_rxrpc_rx_response(conn, sp->hdr.serial, version, kvno, ticket_len);
- eproto = tracepoint_string("rxkad_rsp_ver");
- abort_code = RXKADINCONSISTENCY;
- if (version != RXKAD_VERSION)
+ if (version != RXKAD_VERSION) {
+ rxrpc_abort_conn(conn, skb, RXKADINCONSISTENCY, -EPROTO,
+ rxkad_abort_resp_version);
goto protocol_error;
+ }
- eproto = tracepoint_string("rxkad_rsp_tktlen");
- abort_code = RXKADTICKETLEN;
- if (ticket_len < 4 || ticket_len > MAXKRB5TICKETLEN)
+ if (ticket_len < 4 || ticket_len > MAXKRB5TICKETLEN) {
+ rxrpc_abort_conn(conn, skb, RXKADTICKETLEN, -EPROTO,
+ rxkad_abort_resp_tkt_len);
goto protocol_error;
+ }
- eproto = tracepoint_string("rxkad_rsp_unkkey");
- abort_code = RXKADUNKNOWNKEY;
- if (kvno >= RXKAD_TKT_TYPE_KERBEROS_V5)
+ if (kvno >= RXKAD_TKT_TYPE_KERBEROS_V5) {
+ rxrpc_abort_conn(conn, skb, RXKADUNKNOWNKEY, -EPROTO,
+ rxkad_abort_resp_unknown_tkt);
goto protocol_error;
+ }
/* extract the kerberos ticket and decrypt and decode it */
ret = -ENOMEM;
if (!ticket)
goto temporary_error_free_resp;
- eproto = tracepoint_string("rxkad_tkt_short");
- abort_code = RXKADPACKETSHORT;
- ret = skb_copy_bits(skb, sizeof(struct rxrpc_wire_header) + sizeof(*response),
- ticket, ticket_len);
- if (ret < 0)
- goto temporary_error_free_ticket;
+ if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header) + sizeof(*response),
+ ticket, ticket_len) < 0) {
+ rxrpc_abort_conn(conn, skb, RXKADPACKETSHORT, -EPROTO,
+ rxkad_abort_resp_short_tkt);
+ goto protocol_error;
+ }
ret = rxkad_decrypt_ticket(conn, server_key, skb, ticket, ticket_len,
- &session_key, &expiry, _abort_code);
+ &session_key, &expiry);
if (ret < 0)
goto temporary_error_free_ticket;
* response */
rxkad_decrypt_response(conn, response, &session_key);
- eproto = tracepoint_string("rxkad_rsp_param");
- abort_code = RXKADSEALEDINCON;
- if (ntohl(response->encrypted.epoch) != conn->proto.epoch)
- goto protocol_error_free;
- if (ntohl(response->encrypted.cid) != conn->proto.cid)
- goto protocol_error_free;
- if (ntohl(response->encrypted.securityIndex) != conn->security_ix)
+ if (ntohl(response->encrypted.epoch) != conn->proto.epoch ||
+ ntohl(response->encrypted.cid) != conn->proto.cid ||
+ ntohl(response->encrypted.securityIndex) != conn->security_ix) {
+ rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO,
+ rxkad_abort_resp_bad_param);
goto protocol_error_free;
+ }
+
csum = response->encrypted.checksum;
response->encrypted.checksum = 0;
rxkad_calc_response_checksum(response);
- eproto = tracepoint_string("rxkad_rsp_csum");
- if (response->encrypted.checksum != csum)
+ if (response->encrypted.checksum != csum) {
+ rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO,
+ rxkad_abort_resp_bad_checksum);
goto protocol_error_free;
+ }
- spin_lock(&conn->bundle->channel_lock);
for (i = 0; i < RXRPC_MAXCALLS; i++) {
- struct rxrpc_call *call;
u32 call_id = ntohl(response->encrypted.call_id[i]);
+ u32 counter = READ_ONCE(conn->channels[i].call_counter);
+
+ if (call_id > INT_MAX) {
+ rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO,
+ rxkad_abort_resp_bad_callid);
+ goto protocol_error_free;
+ }
- eproto = tracepoint_string("rxkad_rsp_callid");
- if (call_id > INT_MAX)
- goto protocol_error_unlock;
-
- eproto = tracepoint_string("rxkad_rsp_callctr");
- if (call_id < conn->channels[i].call_counter)
- goto protocol_error_unlock;
-
- eproto = tracepoint_string("rxkad_rsp_callst");
- if (call_id > conn->channels[i].call_counter) {
- call = rcu_dereference_protected(
- conn->channels[i].call,
- lockdep_is_held(&conn->bundle->channel_lock));
- if (call && call->state < RXRPC_CALL_COMPLETE)
- goto protocol_error_unlock;
+ if (call_id < counter) {
+ rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO,
+ rxkad_abort_resp_call_ctr);
+ goto protocol_error_free;
+ }
+
+ if (call_id > counter) {
+ if (conn->channels[i].call) {
+ rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO,
+ rxkad_abort_resp_call_state);
+ goto protocol_error_free;
+ }
conn->channels[i].call_counter = call_id;
}
}
- spin_unlock(&conn->bundle->channel_lock);
- eproto = tracepoint_string("rxkad_rsp_seq");
- abort_code = RXKADOUTOFSEQUENCE;
- if (ntohl(response->encrypted.inc_nonce) != conn->rxkad.nonce + 1)
+ if (ntohl(response->encrypted.inc_nonce) != conn->rxkad.nonce + 1) {
+ rxrpc_abort_conn(conn, skb, RXKADOUTOFSEQUENCE, -EPROTO,
+ rxkad_abort_resp_ooseq);
goto protocol_error_free;
+ }
- eproto = tracepoint_string("rxkad_rsp_level");
- abort_code = RXKADLEVELFAIL;
level = ntohl(response->encrypted.level);
- if (level > RXRPC_SECURITY_ENCRYPT)
+ if (level > RXRPC_SECURITY_ENCRYPT) {
+ rxrpc_abort_conn(conn, skb, RXKADLEVELFAIL, -EPROTO,
+ rxkad_abort_resp_level);
goto protocol_error_free;
+ }
conn->security_level = level;
/* create a key to hold the security data and expiration time - after
_leave(" = 0");
return 0;
-protocol_error_unlock:
- spin_unlock(&conn->bundle->channel_lock);
protocol_error_free:
kfree(ticket);
protocol_error:
kfree(response);
- trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto);
key_put(server_key);
- *_abort_code = abort_code;
return -EPROTO;
temporary_error_free_ticket:
#include <linux/slab.h>
#include <net/sock.h>
#include <net/af_rxrpc.h>
+#define RXRPC_TRACE_ONLY_DEFINE_ENUMS
+#include <trace/events/rxrpc.h>
MODULE_DESCRIPTION("rxperf test server (afs)");
MODULE_AUTHOR("Red Hat, Inc.");
case -EOPNOTSUPP:
abort_code = RXGEN_OPCODE;
rxrpc_kernel_abort_call(rxperf_socket, call->rxcall,
- abort_code, ret, "GOP");
+ abort_code, ret,
+ rxperf_abort_op_not_supported);
goto call_complete;
case -ENOTSUPP:
abort_code = RX_USER_ABORT;
rxrpc_kernel_abort_call(rxperf_socket, call->rxcall,
- abort_code, ret, "GUA");
+ abort_code, ret,
+ rxperf_abort_op_not_supported);
goto call_complete;
case -EIO:
pr_err("Call %u in bad state %u\n",
case -ENOMEM:
case -EFAULT:
rxrpc_kernel_abort_call(rxperf_socket, call->rxcall,
- RXGEN_SS_UNMARSHAL, ret, "GUM");
+ RXGEN_SS_UNMARSHAL, ret,
+ rxperf_abort_unmarshal_error);
goto call_complete;
default:
rxrpc_kernel_abort_call(rxperf_socket, call->rxcall,
- RX_CALL_DEAD, ret, "GER");
+ RX_CALL_DEAD, ret,
+ rxperf_abort_general_error);
goto call_complete;
}
}
if (n == -ENOMEM)
rxrpc_kernel_abort_call(rxperf_socket, call->rxcall,
- RXGEN_SS_MARSHAL, -ENOMEM, "GOM");
+ RXGEN_SS_MARSHAL, -ENOMEM,
+ rxperf_abort_oom);
return n;
}
*/
int rxrpc_init_client_conn_security(struct rxrpc_connection *conn)
{
- const struct rxrpc_security *sec;
struct rxrpc_key_token *token;
struct key *key = conn->key;
- int ret;
+ int ret = 0;
_enter("{%d},{%x}", conn->debug_id, key_serial(key));
- if (!key)
- return 0;
-
- ret = key_validate(key);
- if (ret < 0)
- return ret;
-
for (token = key->payload.data[0]; token; token = token->next) {
- sec = rxrpc_security_lookup(token->security_index);
- if (sec)
+ if (token->security_index == conn->security->security_index)
goto found;
}
return -EKEYREJECTED;
found:
- conn->security = sec;
-
- ret = conn->security->init_connection_security(conn, token);
- if (ret < 0) {
- conn->security = &rxrpc_no_security;
- return ret;
+ mutex_lock(&conn->security_lock);
+ if (conn->state == RXRPC_CONN_CLIENT_UNSECURED) {
+ ret = conn->security->init_connection_security(conn, token);
+ if (ret == 0) {
+ spin_lock(&conn->state_lock);
+ if (conn->state == RXRPC_CONN_CLIENT_UNSECURED)
+ conn->state = RXRPC_CONN_CLIENT;
+ spin_unlock(&conn->state_lock);
+ }
}
-
- _leave(" = 0");
- return 0;
+ mutex_unlock(&conn->security_lock);
+ return ret;
}
/*
sec = rxrpc_security_lookup(sp->hdr.securityIndex);
if (!sec) {
- trace_rxrpc_abort(0, "SVS",
- sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- RX_INVALID_OPERATION, EKEYREJECTED);
- skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
- skb->priority = RX_INVALID_OPERATION;
+ rxrpc_direct_abort(skb, rxrpc_abort_unsupported_security,
+ RX_INVALID_OPERATION, -EKEYREJECTED);
return NULL;
}
if (sp->hdr.securityIndex != RXRPC_SECURITY_NONE &&
!rx->securities) {
- trace_rxrpc_abort(0, "SVR",
- sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- RX_INVALID_OPERATION, EKEYREJECTED);
- skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
- skb->priority = sec->no_key_abort;
+ rxrpc_direct_abort(skb, rxrpc_abort_no_service_key,
+ sec->no_key_abort, -EKEYREJECTED);
return NULL;
}
sprintf(kdesc, "%u:%u",
sp->hdr.serviceId, sp->hdr.securityIndex);
- rcu_read_lock();
+ read_lock(&conn->local->services_lock);
- rx = rcu_dereference(conn->local->service);
+ rx = conn->local->service;
if (!rx)
goto out;
}
out:
- rcu_read_unlock();
+ read_unlock(&conn->local->services_lock);
return key;
}
#include "ar-internal.h"
/*
+ * Propose an abort to be made in the I/O thread.
+ */
+bool rxrpc_propose_abort(struct rxrpc_call *call, s32 abort_code, int error,
+ enum rxrpc_abort_reason why)
+{
+ _enter("{%d},%d,%d,%u", call->debug_id, abort_code, error, why);
+
+ if (!call->send_abort && !rxrpc_call_is_complete(call)) {
+ call->send_abort_why = why;
+ call->send_abort_err = error;
+ call->send_abort_seq = 0;
+ /* Request abort locklessly vs rxrpc_input_call_event(). */
+ smp_store_release(&call->send_abort, abort_code);
+ rxrpc_poke_call(call, rxrpc_call_poke_abort);
+ return true;
+ }
+
+ return false;
+}
+
+/*
+ * Wait for a call to become connected. Interruption here doesn't cause the
+ * call to be aborted.
+ */
+static int rxrpc_wait_to_be_connected(struct rxrpc_call *call, long *timeo)
+{
+ DECLARE_WAITQUEUE(myself, current);
+ int ret = 0;
+
+ _enter("%d", call->debug_id);
+
+ if (rxrpc_call_state(call) != RXRPC_CALL_CLIENT_AWAIT_CONN)
+ return call->error;
+
+ add_wait_queue_exclusive(&call->waitq, &myself);
+
+ for (;;) {
+ ret = call->error;
+ if (ret < 0)
+ break;
+
+ switch (call->interruptibility) {
+ case RXRPC_INTERRUPTIBLE:
+ case RXRPC_PREINTERRUPTIBLE:
+ set_current_state(TASK_INTERRUPTIBLE);
+ break;
+ case RXRPC_UNINTERRUPTIBLE:
+ default:
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ break;
+ }
+ if (rxrpc_call_state(call) != RXRPC_CALL_CLIENT_AWAIT_CONN) {
+ ret = call->error;
+ break;
+ }
+ if ((call->interruptibility == RXRPC_INTERRUPTIBLE ||
+ call->interruptibility == RXRPC_PREINTERRUPTIBLE) &&
+ signal_pending(current)) {
+ ret = sock_intr_errno(*timeo);
+ break;
+ }
+ *timeo = schedule_timeout(*timeo);
+ }
+
+ remove_wait_queue(&call->waitq, &myself);
+ __set_current_state(TASK_RUNNING);
+
+ if (ret == 0 && rxrpc_call_is_complete(call))
+ ret = call->error;
+
+ _leave(" = %d", ret);
+ return ret;
+}
+
+/*
* Return true if there's sufficient Tx queue space.
*/
static bool rxrpc_check_tx_space(struct rxrpc_call *call, rxrpc_seq_t *_tx_win)
if (rxrpc_check_tx_space(call, NULL))
return 0;
- if (call->state >= RXRPC_CALL_COMPLETE)
+ if (rxrpc_call_is_complete(call))
return call->error;
if (signal_pending(current))
if (rxrpc_check_tx_space(call, &tx_win))
return 0;
- if (call->state >= RXRPC_CALL_COMPLETE)
+ if (rxrpc_call_is_complete(call))
return call->error;
if (timeout == 0 &&
if (rxrpc_check_tx_space(call, NULL))
return 0;
- if (call->state >= RXRPC_CALL_COMPLETE)
+ if (rxrpc_call_is_complete(call))
return call->error;
trace_rxrpc_txqueue(call, rxrpc_txqueue_wait);
struct rxrpc_txbuf *txb,
rxrpc_notify_end_tx_t notify_end_tx)
{
- unsigned long now;
rxrpc_seq_t seq = txb->seq;
bool last = test_bit(RXRPC_TXBUF_LAST, &txb->flags), poke;
poke = list_empty(&call->tx_sendmsg);
list_add_tail(&txb->call_link, &call->tx_sendmsg);
call->tx_prepared = seq;
+ if (last)
+ rxrpc_notify_end_tx(rx, call, notify_end_tx);
spin_unlock(&call->tx_lock);
- if (last || call->state == RXRPC_CALL_SERVER_ACK_REQUEST) {
- _debug("________awaiting reply/ACK__________");
- write_lock(&call->state_lock);
- switch (call->state) {
- case RXRPC_CALL_CLIENT_SEND_REQUEST:
- call->state = RXRPC_CALL_CLIENT_AWAIT_REPLY;
- rxrpc_notify_end_tx(rx, call, notify_end_tx);
- break;
- case RXRPC_CALL_SERVER_ACK_REQUEST:
- call->state = RXRPC_CALL_SERVER_SEND_REPLY;
- now = jiffies;
- WRITE_ONCE(call->delay_ack_at, now + MAX_JIFFY_OFFSET);
- if (call->ackr_reason == RXRPC_ACK_DELAY)
- call->ackr_reason = 0;
- trace_rxrpc_timer(call, rxrpc_timer_init_for_send_reply, now);
- if (!last)
- break;
- fallthrough;
- case RXRPC_CALL_SERVER_SEND_REPLY:
- call->state = RXRPC_CALL_SERVER_AWAIT_ACK;
- rxrpc_notify_end_tx(rx, call, notify_end_tx);
- break;
- default:
- break;
- }
- write_unlock(&call->state_lock);
- }
-
if (poke)
rxrpc_poke_call(call, rxrpc_call_poke_start);
}
timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
+ ret = rxrpc_wait_to_be_connected(call, &timeo);
+ if (ret < 0)
+ return ret;
+
+ if (call->conn->state == RXRPC_CONN_CLIENT_UNSECURED) {
+ ret = rxrpc_init_client_conn_security(call->conn);
+ if (ret < 0)
+ return ret;
+ }
+
/* this should be in poll */
sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
ret = -EPIPE;
if (sk->sk_shutdown & SEND_SHUTDOWN)
goto maybe_error;
- state = READ_ONCE(call->state);
+ state = rxrpc_call_state(call);
ret = -ESHUTDOWN;
if (state >= RXRPC_CALL_COMPLETE)
goto maybe_error;
ret = -EPROTO;
if (state != RXRPC_CALL_CLIENT_SEND_REQUEST &&
state != RXRPC_CALL_SERVER_ACK_REQUEST &&
- state != RXRPC_CALL_SERVER_SEND_REPLY)
+ state != RXRPC_CALL_SERVER_SEND_REPLY) {
+ /* Request phase complete for this client call */
+ trace_rxrpc_abort(call->debug_id, rxrpc_sendmsg_late_send,
+ call->cid, call->call_id, call->rx_consumed,
+ 0, -EPROTO);
goto maybe_error;
+ }
ret = -EMSGSIZE;
if (call->tx_total_len != -1) {
/* check for the far side aborting the call or a network error
* occurring */
- if (call->state == RXRPC_CALL_COMPLETE)
+ if (rxrpc_call_is_complete(call))
goto call_terminated;
/* add the packet to the send queue if it's now full */
success:
ret = copied;
- if (READ_ONCE(call->state) == RXRPC_CALL_COMPLETE) {
- read_lock(&call->state_lock);
- if (call->error < 0)
- ret = call->error;
- read_unlock(&call->state_lock);
- }
+ if (rxrpc_call_is_complete(call) &&
+ call->error < 0)
+ ret = call->error;
out:
call->tx_pending = txb;
_leave(" = %d", ret);
atomic_inc_return(&rxrpc_debug_id));
/* The socket is now unlocked */
- rxrpc_put_peer(cp.peer, rxrpc_peer_put_discard_tmp);
_leave(" = %p\n", call);
return call;
}
int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
__releases(&rx->sk.sk_lock.slock)
{
- enum rxrpc_call_state state;
struct rxrpc_call *call;
unsigned long now, j;
bool dropped_lock = false;
return PTR_ERR(call);
/* ... and we have the call lock. */
ret = 0;
- if (READ_ONCE(call->state) == RXRPC_CALL_COMPLETE)
+ if (rxrpc_call_is_complete(call))
goto out_put_unlock;
} else {
- switch (READ_ONCE(call->state)) {
+ switch (rxrpc_call_state(call)) {
case RXRPC_CALL_UNINITIALISED:
case RXRPC_CALL_CLIENT_AWAIT_CONN:
case RXRPC_CALL_SERVER_PREALLOC:
break;
}
- state = READ_ONCE(call->state);
- _debug("CALL %d USR %lx ST %d on CONN %p",
- call->debug_id, call->user_call_ID, state, call->conn);
-
- if (state >= RXRPC_CALL_COMPLETE) {
+ if (rxrpc_call_is_complete(call)) {
/* it's too late for this call */
ret = -ESHUTDOWN;
} else if (p.command == RXRPC_CMD_SEND_ABORT) {
+ rxrpc_propose_abort(call, p.abort_code, -ECONNABORTED,
+ rxrpc_abort_call_sendmsg);
ret = 0;
- if (rxrpc_abort_call("CMD", call, 0, p.abort_code, -ECONNABORTED))
- ret = rxrpc_send_abort_packet(call);
} else if (p.command != RXRPC_CMD_SEND_DATA) {
ret = -EINVAL;
} else {
bool dropped_lock = false;
int ret;
- _enter("{%d,%s},", call->debug_id, rxrpc_call_states[call->state]);
+ _enter("{%d},", call->debug_id);
ASSERTCMP(msg->msg_name, ==, NULL);
ASSERTCMP(msg->msg_control, ==, NULL);
mutex_lock(&call->user_mutex);
- _debug("CALL %d USR %lx ST %d on CONN %p",
- call->debug_id, call->user_call_ID, call->state, call->conn);
-
- switch (READ_ONCE(call->state)) {
- case RXRPC_CALL_CLIENT_SEND_REQUEST:
- case RXRPC_CALL_SERVER_ACK_REQUEST:
- case RXRPC_CALL_SERVER_SEND_REPLY:
- ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len,
- notify_end_tx, &dropped_lock);
- break;
- case RXRPC_CALL_COMPLETE:
- read_lock(&call->state_lock);
+ ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len,
+ notify_end_tx, &dropped_lock);
+ if (ret == -ESHUTDOWN)
ret = call->error;
- read_unlock(&call->state_lock);
- break;
- default:
- /* Request phase complete for this client call */
- trace_rxrpc_rx_eproto(call, 0, tracepoint_string("late_send"));
- ret = -EPROTO;
- break;
- }
if (!dropped_lock)
mutex_unlock(&call->user_mutex);
* @call: The call to be aborted
* @abort_code: The abort code to stick into the ABORT packet
* @error: Local error value
- * @why: 3-char string indicating why.
+ * @why: Indication as to why.
*
* Allow a kernel service to abort a call, if it's still in an abortable state
* and return true if the call was aborted, false if it was already complete.
*/
bool rxrpc_kernel_abort_call(struct socket *sock, struct rxrpc_call *call,
- u32 abort_code, int error, const char *why)
+ u32 abort_code, int error, enum rxrpc_abort_reason why)
{
bool aborted;
- _enter("{%d},%d,%d,%s", call->debug_id, abort_code, error, why);
+ _enter("{%d},%d,%d,%u", call->debug_id, abort_code, error, why);
mutex_lock(&call->user_mutex);
-
- aborted = rxrpc_abort_call(why, call, 0, abort_code, error);
- if (aborted)
- rxrpc_send_abort_packet(call);
-
+ aborted = rxrpc_propose_abort(call, abort_code, error, why);
mutex_unlock(&call->user_mutex);
return aborted;
}
{
const u32 *label = nla_data(attr);
+ if (nla_len(attr) != sizeof(*label)) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid MPLS label length");
+ return -EINVAL;
+ }
+
if (*label & ~MPLS_LABEL_MASK || *label == MPLS_LABEL_IMPLNULL) {
NL_SET_ERR_MSG_MOD(extack, "MPLS label out of range");
return -EINVAL;
static const struct nla_policy mpls_policy[TCA_MPLS_MAX + 1] = {
[TCA_MPLS_PARMS] = NLA_POLICY_EXACT_LEN(sizeof(struct tc_mpls)),
[TCA_MPLS_PROTO] = { .type = NLA_U16 },
- [TCA_MPLS_LABEL] = NLA_POLICY_VALIDATE_FN(NLA_U32, valid_label),
+ [TCA_MPLS_LABEL] = NLA_POLICY_VALIDATE_FN(NLA_BINARY,
+ valid_label),
[TCA_MPLS_TC] = NLA_POLICY_RANGE(NLA_U8, 0, 7),
[TCA_MPLS_TTL] = NLA_POLICY_MIN(NLA_U8, 1),
[TCA_MPLS_BOS] = NLA_POLICY_RANGE(NLA_U8, 0, 1),
struct tcindex_filter_result *r, struct nlattr **tb,
struct nlattr *est, u32 flags, struct netlink_ext_ack *extack)
{
- struct tcindex_filter_result new_filter_result, *old_r = r;
+ struct tcindex_filter_result new_filter_result;
struct tcindex_data *cp = NULL, *oldp;
struct tcindex_filter *f = NULL; /* make gcc behave */
struct tcf_result cr = {};
err = tcindex_filter_result_init(&new_filter_result, cp, net);
if (err < 0)
goto errout_alloc;
- if (old_r)
+ if (r)
cr = r->res;
err = -EBUSY;
tcf_bind_filter(tp, &cr, base);
}
- if (old_r && old_r != r) {
- err = tcindex_filter_result_init(old_r, cp, net);
- if (err < 0) {
- kfree(f);
- goto errout_alloc;
- }
- }
-
oldp = p;
r->res = cr;
tcf_exts_change(&r->exts, &e);
return -ENOENT;
}
+ if (new && new->ops == &noqueue_qdisc_ops) {
+ NL_SET_ERR_MSG(extack, "Cannot assign noqueue to a class");
+ return -EINVAL;
+ }
+
err = cops->graft(parent, cl, new, &old, extack);
if (err)
return err;
result = tcf_classify(skb, NULL, fl, &res, true);
if (result < 0)
continue;
+ if (result == TC_ACT_SHOT)
+ goto done;
+
flow = (struct atm_flow_data *)res.class;
if (!flow)
flow = lookup_flow(sch, res.classid);
- goto done;
+ goto drop;
}
}
flow = NULL;
result = tcf_classify(skb, NULL, fl, &res, true);
if (!fl || result < 0)
goto fallback;
+ if (result == TC_ACT_SHOT)
+ return NULL;
cl = (void *)res.class;
if (!cl) {
case TC_ACT_TRAP:
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
fallthrough;
- case TC_ACT_SHOT:
- return NULL;
case TC_ACT_RECLASSIFY:
return cbq_reclassify(skb, cl);
}
{
return (unsigned long)htb_find(handle, sch);
}
+
+#define HTB_DIRECT ((struct htb_class *)-1L)
+
/**
* htb_classify - classify a packet into class
+ * @skb: the socket buffer
+ * @sch: the active queue discipline
+ * @qerr: pointer for returned status code
*
* It returns NULL if the packet should be dropped or -1 if the packet
* should be passed directly thru. In all other cases leaf class is returned.
* have no valid leaf we try to use MAJOR:default leaf. It still unsuccessful
* then finish and return direct queue.
*/
-#define HTB_DIRECT ((struct htb_class *)-1L)
-
static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch,
int *qerr)
{
list_for_each_entry(pos, &pipe->in_downcall, list) {
if (!uid_eq(pos->uid, uid))
continue;
- if (auth && pos->auth->service != auth->service)
+ if (pos->auth->service != auth->service)
continue;
refcount_inc(&pos->count);
return pos;
return err;
}
+static struct gss_upcall_msg *
+gss_find_downcall(struct rpc_pipe *pipe, kuid_t uid)
+{
+ struct gss_upcall_msg *pos;
+ list_for_each_entry(pos, &pipe->in_downcall, list) {
+ if (!uid_eq(pos->uid, uid))
+ continue;
+ if (!rpc_msg_is_inflight(&pos->msg))
+ continue;
+ refcount_inc(&pos->count);
+ return pos;
+ }
+ return NULL;
+}
+
#define MSG_BUF_MAXSIZE 1024
static ssize_t
err = -ENOENT;
/* Find a matching upcall */
spin_lock(&pipe->lock);
- gss_msg = __gss_find_upcall(pipe, uid, NULL);
+ gss_msg = gss_find_downcall(pipe, uid);
if (gss_msg == NULL) {
spin_unlock(&pipe->lock);
goto err_put_ctx;
* rejecting the server-computed MIC in this somewhat rare case,
* do not use splice with the GSS integrity service.
*/
- __clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
+ clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
/* Did we already verify the signature on the original pass through? */
if (rqstp->rq_deferred)
int pad, remaining_len, offset;
u32 rseqno;
- __clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
+ clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
priv_len = svc_getnl(&buf->head[0]);
if (rqstp->rq_deferred) {
goto err_short_len;
/* Will be turned off by GSS integrity and privacy services */
- __set_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
+ set_bit(RQ_SPLICE_OK, &rqstp->rq_flags);
/* Will be turned off only when NFSv4 Sessions are used */
- __set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
- __clear_bit(RQ_DROPME, &rqstp->rq_flags);
+ set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags);
+ clear_bit(RQ_DROPME, &rqstp->rq_flags);
svc_putu32(resv, rqstp->rq_xid);
trace_svc_defer(rqstp);
svc_xprt_get(rqstp->rq_xprt);
dr->xprt = rqstp->rq_xprt;
- __set_bit(RQ_DROPME, &rqstp->rq_flags);
+ set_bit(RQ_DROPME, &rqstp->rq_flags);
dr->handle.revisit = svc_revisit;
return &dr->handle;
static void svc_sock_secure_port(struct svc_rqst *rqstp)
{
if (svc_port_is_privileged(svc_addr(rqstp)))
- __set_bit(RQ_SECURE, &rqstp->rq_flags);
+ set_bit(RQ_SECURE, &rqstp->rq_flags);
else
- __clear_bit(RQ_SECURE, &rqstp->rq_flags);
+ clear_bit(RQ_SECURE, &rqstp->rq_flags);
}
/*
rqstp->rq_xprt_ctxt = NULL;
rqstp->rq_prot = IPPROTO_TCP;
if (test_bit(XPT_LOCAL, &svsk->sk_xprt.xpt_flags))
- __set_bit(RQ_LOCAL, &rqstp->rq_flags);
+ set_bit(RQ_LOCAL, &rqstp->rq_flags);
else
- __clear_bit(RQ_LOCAL, &rqstp->rq_flags);
+ clear_bit(RQ_LOCAL, &rqstp->rq_flags);
p = (__be32 *)rqstp->rq_arg.head[0].iov_base;
calldir = p[1];
static void svc_rdma_secure_port(struct svc_rqst *rqstp)
{
- __set_bit(RQ_SECURE, &rqstp->rq_flags);
+ set_bit(RQ_SECURE, &rqstp->rq_flags);
}
static void svc_rdma_kill_temp_xprt(struct svc_xprt *xprt)
bool addr_match = false;
bool sign_match = false;
bool link_up = false;
+ bool link_is_reset = false;
bool accept_addr = false;
- bool reset = true;
+ bool reset = false;
char *if_name;
unsigned long intv;
u16 session;
/* Prepare to validate requesting node's signature and media address */
l = le->link;
link_up = l && tipc_link_is_up(l);
+ link_is_reset = l && tipc_link_is_reset(l);
addr_match = l && !memcmp(&le->maddr, maddr, sizeof(*maddr));
sign_match = (signature == n->signature);
/* These three flags give us eight permutations: */
if (sign_match && addr_match && link_up) {
- /* All is fine. Do nothing. */
- reset = false;
+ /* All is fine. Ignore requests. */
/* Peer node is not a container/local namespace */
if (!n->peer_hash_mix)
n->peer_hash_mix = hash_mixes;
*/
accept_addr = true;
*respond = true;
+ reset = true;
} else if (!sign_match && addr_match && link_up) {
/* Peer node rebooted. Two possibilities:
* - Delayed re-discovery; this link endpoint has already
n->signature = signature;
accept_addr = true;
*respond = true;
+ reset = true;
}
if (!accept_addr)
tipc_link_fsm_evt(l, LINK_RESET_EVT);
if (n->state == NODE_FAILINGOVER)
tipc_link_fsm_evt(l, LINK_FAILOVER_BEGIN_EVT);
+ link_is_reset = tipc_link_is_reset(l);
le->link = l;
n->link_cnt++;
tipc_node_calculate_timer(n, l);
memcpy(&le->maddr, maddr, sizeof(*maddr));
exit:
tipc_node_write_unlock(n);
- if (reset && l && !tipc_link_is_reset(l))
+ if (reset && !link_is_reset)
tipc_node_link_down(n, b->identity, false);
tipc_node_put(n);
}
$(if $(CONFIG_MODVERSIONS),-m) \
$(if $(CONFIG_MODULE_SRCVERSION_ALL),-a) \
$(if $(CONFIG_SECTION_MISMATCH_WARN_ONLY),,-E) \
+ $(if $(KBUILD_MODPOST_WARN),-w) \
$(if $(KBUILD_NSDEPS),-d $(MODULES_NSDEPS)) \
$(if $(CONFIG_MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS)$(KBUILD_NSDEPS),-N) \
-o $@
modpost-args += -n
endif
-ifneq ($(KBUILD_MODPOST_WARN)$(missing-input),)
-modpost-args += -w
-endif
-
# Read out modules.order to pass in modpost.
# Otherwise, allmodconfig would fail with "Argument list too long".
ifdef KBUILD_MODULES
endif # ($(KBUILD_EXTMOD),)
+ifneq ($(missing-input),)
+modpost-args += -w
+endif
+
quiet_cmd_modpost = MODPOST $@
cmd_modpost = \
$(if $(missing-input), \
$(call if_changed_dep,cc_o_c)
ifdef CONFIG_MODULES
+KASAN_SANITIZE_.vmlinux.export.o := n
targets += .vmlinux.export.o
vmlinux: .vmlinux.export.o
endif
select SECURITYFS
select SECURITY_PATH
select SECURITY_NETWORK
- select SRCU
- select BUILD_BIN2C
default n
help
This selects TOMOYO Linux, pathname-based access control.
Required userspace tools and further information may be
- found at <http://tomoyo.sourceforge.jp/>.
+ found at <https://tomoyo.osdn.jp/>.
If you are unsure how to answer this question, answer N.
config SECURITY_TOMOYO_MAX_ACCEPT_ENTRY
obj-y = audit.o common.o condition.o domain.o environ.o file.o gc.o group.o load_policy.o memory.o mount.o network.o realpath.o securityfs_if.o tomoyo.o util.o
targets += builtin-policy.h
-define do_policy
-echo "static char tomoyo_builtin_$(1)[] __initdata ="; \
-$(objtree)/scripts/bin2c <$(firstword $(wildcard $(obj)/policy/$(1).conf $(srctree)/$(src)/policy/$(1).conf.default) /dev/null); \
-echo ";"
-endef
-quiet_cmd_policy = POLICY $@
- cmd_policy = ($(call do_policy,profile); $(call do_policy,exception_policy); $(call do_policy,domain_policy); $(call do_policy,manager); $(call do_policy,stat)) >$@
-$(obj)/builtin-policy.h: $(wildcard $(obj)/policy/*.conf $(src)/policy/*.conf.default) FORCE
+quiet_cmd_policy = POLICY $@
+ cmd_policy = { \
+ $(foreach x, profile exception_policy domain_policy manager stat, \
+ printf 'static char tomoyo_builtin_$x[] __initdata =\n'; \
+ sed -e 's/\\/\\\\/g' -e 's/\"/\\"/g' -e 's/\(.*\)/\t"\1\\n"/' -- $(firstword $(filter %/$x.conf %/$x.conf.default, $^) /dev/null); \
+ printf '\t"";\n';) \
+ } > $@
+
+$(obj)/builtin-policy.h: $(wildcard $(obj)/policy/*.conf $(srctree)/$(src)/policy/*.conf.default) FORCE
$(call if_changed,policy)
+ifndef CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING
$(obj)/common.o: $(obj)/builtin-policy.h
+endif
const u32 pattern = 0xdeadbeef;
int ret;
+ down_read(&card->controls_rwsem);
kctl = snd_ctl_find_id(card, &control->id);
- if (kctl == NULL)
- return -ENOENT;
+ if (kctl == NULL) {
+ ret = -ENOENT;
+ goto unlock;
+ }
index_offset = snd_ctl_get_ioff(kctl, &control->id);
vd = &kctl->vd[index_offset];
- if (!(vd->access & SNDRV_CTL_ELEM_ACCESS_READ) || kctl->get == NULL)
- return -EPERM;
+ if (!(vd->access & SNDRV_CTL_ELEM_ACCESS_READ) || kctl->get == NULL) {
+ ret = -EPERM;
+ goto unlock;
+ }
snd_ctl_build_ioff(&control->id, kctl, index_offset);
info.id = control->id;
ret = __snd_ctl_elem_info(card, kctl, &info, NULL);
if (ret < 0)
- return ret;
+ goto unlock;
#endif
if (!snd_ctl_skip_validation(&info))
ret = kctl->get(kctl, control);
snd_power_unref(card);
if (ret < 0)
- return ret;
+ goto unlock;
if (!snd_ctl_skip_validation(&info) &&
sanity_check_elem_value(card, control, &info, pattern) < 0) {
dev_err(card->dev,
control->id.iface, control->id.device,
control->id.subdevice, control->id.name,
control->id.index);
- return -EINVAL;
+ ret = -EINVAL;
+ goto unlock;
}
+unlock:
+ up_read(&card->controls_rwsem);
return ret;
}
if (IS_ERR(control))
return PTR_ERR(control);
- down_read(&card->controls_rwsem);
result = snd_ctl_elem_read(card, control);
- up_read(&card->controls_rwsem);
if (result < 0)
goto error;
bool attach)
{
char buf2[256], *s, *os;
- size_t len = max(sizeof(s) - 1, count);
struct snd_ctl_elem_id id;
int err;
- strncpy(buf2, buf, len);
- buf2[len] = '\0';
+ if (strscpy(buf2, buf, sizeof(buf2)) < 0)
+ return -E2BIG;
memset(&id, 0, sizeof(id));
id.iface = SNDRV_CTL_ELEM_IFACE_MIXER;
s = buf2;
dev_dbg(cs35l41->dev, "System Suspend\n");
if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST_NO_VSPK_SWITCH) {
- dev_err(cs35l41->dev, "System Suspend not supported\n");
- return -EINVAL;
+ dev_err_once(cs35l41->dev, "System Suspend not supported\n");
+ return 0; /* don't block the whole system suspend */
}
ret = pm_runtime_force_suspend(dev);
dev_dbg(cs35l41->dev, "System Resume\n");
if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST_NO_VSPK_SWITCH) {
- dev_err(cs35l41->dev, "System Resume not supported\n");
- return -EINVAL;
+ dev_err_once(cs35l41->dev, "System Resume not supported\n");
+ return 0; /* don't block the whole system resume */
}
if (cs35l41->reset_gpio) {
return ret;
}
+static int cs35l41_runtime_idle(struct device *dev)
+{
+ struct cs35l41_hda *cs35l41 = dev_get_drvdata(dev);
+
+ if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST_NO_VSPK_SWITCH)
+ return -EBUSY; /* suspend not supported yet on this model */
+ return 0;
+}
+
static int cs35l41_runtime_suspend(struct device *dev)
{
struct cs35l41_hda *cs35l41 = dev_get_drvdata(dev);
EXPORT_SYMBOL_NS_GPL(cs35l41_hda_remove, SND_HDA_SCODEC_CS35L41);
const struct dev_pm_ops cs35l41_hda_pm_ops = {
- RUNTIME_PM_OPS(cs35l41_runtime_suspend, cs35l41_runtime_resume, NULL)
+ RUNTIME_PM_OPS(cs35l41_runtime_suspend, cs35l41_runtime_resume,
+ cs35l41_runtime_idle)
SYSTEM_SLEEP_PM_OPS(cs35l41_system_suspend, cs35l41_system_resume)
};
EXPORT_SYMBOL_NS_GPL(cs35l41_hda_pm_ops, SND_HDA_SCODEC_CS35L41);
SND_PCI_QUIRK(0x103c, 0x870f, "HP", 1),
SND_PCI_QUIRK(0x103c, 0x871a, "HP", 1),
SND_PCI_QUIRK(0x103c, 0x8711, "HP", 1),
+ SND_PCI_QUIRK(0x103c, 0x8715, "HP", 1),
SND_PCI_QUIRK(0x1462, 0xec94, "MS-7C94", 1),
SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", 1),
{}
hda_nid_t hp_pin = alc_get_hp_pin(spec);
bool hp_pin_sense;
+ if (spec->ultra_low_power) {
+ alc_update_coef_idx(codec, 0x03, 1<<1, 1<<1);
+ alc_update_coef_idx(codec, 0x08, 3<<2, 3<<2);
+ alc_update_coef_idx(codec, 0x08, 7<<4, 0);
+ alc_update_coef_idx(codec, 0x3b, 1<<15, 0);
+ alc_update_coef_idx(codec, 0x0e, 7<<6, 7<<6);
+ msleep(30);
+ }
+
if (!hp_pin)
hp_pin = 0x21;
msleep(2);
alc_update_coefex_idx(codec, 0x57, 0x04, 0x0007, 0x1); /* Low power */
- if (spec->ultra_low_power) {
- alc_update_coef_idx(codec, 0x03, 1<<1, 1<<1);
- alc_update_coef_idx(codec, 0x08, 3<<2, 3<<2);
- alc_update_coef_idx(codec, 0x08, 7<<4, 0);
- alc_update_coef_idx(codec, 0x3b, 1<<15, 0);
- alc_update_coef_idx(codec, 0x0e, 7<<6, 7<<6);
- msleep(30);
- }
snd_hda_codec_write(codec, hp_pin, 0,
AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE);
hda_nid_t hp_pin = alc_get_hp_pin(spec);
bool hp1_pin_sense, hp2_pin_sense;
+ if (spec->ultra_low_power) {
+ alc_update_coef_idx(codec, 0x08, 0x0f << 2, 3<<2);
+ alc_update_coef_idx(codec, 0x0e, 7<<6, 7<<6);
+ alc_update_coef_idx(codec, 0x33, 1<<11, 0);
+ msleep(30);
+ }
+
if (spec->codec_variant != ALC269_TYPE_ALC287 &&
spec->codec_variant != ALC269_TYPE_ALC245)
/* required only at boot or S3 and S4 resume time */
msleep(2);
alc_update_coefex_idx(codec, 0x57, 0x04, 0x0007, 0x1); /* Low power */
- if (spec->ultra_low_power) {
- alc_update_coef_idx(codec, 0x08, 0x0f << 2, 3<<2);
- alc_update_coef_idx(codec, 0x0e, 7<<6, 7<<6);
- alc_update_coef_idx(codec, 0x33, 1<<11, 0);
- msleep(30);
- }
if (hp1_pin_sense || spec->ultra_low_power)
snd_hda_codec_write(codec, hp_pin, 0,
}
}
+static void alc285_fixup_hp_gpio_micmute_led(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ struct alc_spec *spec = codec->spec;
+
+ if (action == HDA_FIXUP_ACT_PRE_PROBE)
+ spec->micmute_led_polarity = 1;
+ alc_fixup_hp_gpio_led(codec, action, 0, 0x04);
+}
+
static void alc236_fixup_hp_coef_micmute_led(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
{
alc285_fixup_hp_coef_micmute_led(codec, fix, action);
}
+static void alc285_fixup_hp_spectre_x360_mute_led(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ alc285_fixup_hp_mute_led_coefbit(codec, fix, action);
+ alc285_fixup_hp_gpio_micmute_led(codec, fix, action);
+}
+
static void alc236_fixup_hp_mute_led(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
{
ALC285_FIXUP_ASUS_G533Z_PINS,
ALC285_FIXUP_HP_GPIO_LED,
ALC285_FIXUP_HP_MUTE_LED,
+ ALC285_FIXUP_HP_SPECTRE_X360_MUTE_LED,
ALC236_FIXUP_HP_GPIO_LED,
ALC236_FIXUP_HP_MUTE_LED,
ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF,
.type = HDA_FIXUP_FUNC,
.v.func = alc285_fixup_hp_mute_led,
},
+ [ALC285_FIXUP_HP_SPECTRE_X360_MUTE_LED] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc285_fixup_hp_spectre_x360_mute_led,
+ },
[ALC236_FIXUP_HP_GPIO_LED] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc236_fixup_hp_gpio_led,
SND_PCI_QUIRK(0x1028, 0x0b1a, "Dell Precision 5570", ALC289_FIXUP_DUAL_SPK),
SND_PCI_QUIRK(0x1028, 0x0b37, "Dell Inspiron 16 Plus 7620 2-in-1", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS),
SND_PCI_QUIRK(0x1028, 0x0b71, "Dell Inspiron 16 Plus 7620", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS),
+ SND_PCI_QUIRK(0x1028, 0x0c03, "Dell Precision 5340", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x0c19, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS),
SND_PCI_QUIRK(0x1028, 0x0c1a, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS),
SND_PCI_QUIRK(0x1028, 0x0c1b, "Dell Precision 3440", ALC236_FIXUP_DELL_DUAL_CODECS),
SND_PCI_QUIRK(0x103c, 0x86c7, "HP Envy AiO 32", ALC274_FIXUP_HP_ENVY_GPIO),
SND_PCI_QUIRK(0x103c, 0x86e7, "HP Spectre x360 15-eb0xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1),
SND_PCI_QUIRK(0x103c, 0x86e8, "HP Spectre x360 15-eb0xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1),
+ SND_PCI_QUIRK(0x103c, 0x86f9, "HP Spectre x360 13-aw0xxx", ALC285_FIXUP_HP_SPECTRE_X360_MUTE_LED),
SND_PCI_QUIRK(0x103c, 0x8716, "HP Elite Dragonfly G2 Notebook PC", ALC285_FIXUP_HP_GPIO_AMP_INIT),
SND_PCI_QUIRK(0x103c, 0x8720, "HP EliteBook x360 1040 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_AMP_INIT),
SND_PCI_QUIRK(0x103c, 0x8724, "HP EliteBook 850 G7", ALC285_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8ad2, "HP EliteBook 860 16 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8b5d, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
SND_PCI_QUIRK(0x103c, 0x8b5e, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
+ SND_PCI_QUIRK(0x103c, 0x8bf0, "HP", ALC236_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
{
.driver_data = &acp6x_card,
.matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "M5402RA"),
+ }
+ },
+ {
+ .driver_data = &acp6x_card,
+ .matches = {
DMI_MATCH(DMI_BOARD_VENDOR, "Alienware"),
DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m17 R5 AMD"),
}
DMI_MATCH(DMI_PRODUCT_NAME, "Redmi Book Pro 14 2022"),
}
},
+ {
+ .driver_data = &acp6x_card,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Razer"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Blade 14 (2022) - RZ09-0427"),
+ }
+ },
{}
};
return 0;
}
+static int rt9120_codec_suspend(struct snd_soc_component *comp)
+{
+ return pm_runtime_force_suspend(comp->dev);
+}
+
+static int rt9120_codec_resume(struct snd_soc_component *comp)
+{
+ return pm_runtime_force_resume(comp->dev);
+}
+
static const struct snd_soc_component_driver rt9120_component_driver = {
.probe = rt9120_codec_probe,
+ .suspend = rt9120_codec_suspend,
+ .resume = rt9120_codec_resume,
.controls = rt9120_snd_controls,
.num_controls = ARRAY_SIZE(rt9120_snd_controls),
.dapm_widgets = rt9120_dapm_widgets,
int dcs_mask;
int dcs_l, dcs_r;
int dcs_l_reg, dcs_r_reg;
+ int an_out_reg;
int timeout;
int pwr_reg;
dcs_mask = WM8904_DCS_ENA_CHAN_0 | WM8904_DCS_ENA_CHAN_1;
dcs_r_reg = WM8904_DC_SERVO_8;
dcs_l_reg = WM8904_DC_SERVO_9;
+ an_out_reg = WM8904_ANALOGUE_OUT1_LEFT;
dcs_l = 0;
dcs_r = 1;
break;
dcs_mask = WM8904_DCS_ENA_CHAN_2 | WM8904_DCS_ENA_CHAN_3;
dcs_r_reg = WM8904_DC_SERVO_6;
dcs_l_reg = WM8904_DC_SERVO_7;
+ an_out_reg = WM8904_ANALOGUE_OUT2_LEFT;
dcs_l = 2;
dcs_r = 3;
break;
snd_soc_component_update_bits(component, reg,
WM8904_HPL_ENA_OUTP | WM8904_HPR_ENA_OUTP,
WM8904_HPL_ENA_OUTP | WM8904_HPR_ENA_OUTP);
+
+ /* Update volume, requires PGA to be powered */
+ val = snd_soc_component_read(component, an_out_reg);
+ snd_soc_component_write(component, an_out_reg, val);
break;
case SND_SOC_DAPM_POST_PMU:
static const struct snd_soc_dapm_route audio_map_ac97[] = {
/* 1st half -- Normal DAPM routes */
- {"Playback", NULL, "AC97 Playback"},
- {"AC97 Capture", NULL, "Capture"},
+ {"AC97 Playback", NULL, "CPU AC97 Playback"},
+ {"CPU AC97 Capture", NULL, "AC97 Capture"},
/* 2nd half -- ASRC DAPM routes */
- {"AC97 Playback", NULL, "ASRC-Playback"},
- {"ASRC-Capture", NULL, "AC97 Capture"},
+ {"CPU AC97 Playback", NULL, "ASRC-Playback"},
+ {"ASRC-Capture", NULL, "CPU AC97 Capture"},
};
static const struct snd_soc_dapm_route audio_map_tx[] = {
static const struct snd_kcontrol_new fsl_micfil_snd_controls[] = {
SOC_SINGLE_SX_TLV("CH0 Volume", REG_MICFIL_OUT_CTRL,
- MICFIL_OUTGAIN_CHX_SHIFT(0), 0xF, 0x7, gain_tlv),
+ MICFIL_OUTGAIN_CHX_SHIFT(0), 0x8, 0xF, gain_tlv),
SOC_SINGLE_SX_TLV("CH1 Volume", REG_MICFIL_OUT_CTRL,
- MICFIL_OUTGAIN_CHX_SHIFT(1), 0xF, 0x7, gain_tlv),
+ MICFIL_OUTGAIN_CHX_SHIFT(1), 0x8, 0xF, gain_tlv),
SOC_SINGLE_SX_TLV("CH2 Volume", REG_MICFIL_OUT_CTRL,
- MICFIL_OUTGAIN_CHX_SHIFT(2), 0xF, 0x7, gain_tlv),
+ MICFIL_OUTGAIN_CHX_SHIFT(2), 0x8, 0xF, gain_tlv),
SOC_SINGLE_SX_TLV("CH3 Volume", REG_MICFIL_OUT_CTRL,
- MICFIL_OUTGAIN_CHX_SHIFT(3), 0xF, 0x7, gain_tlv),
+ MICFIL_OUTGAIN_CHX_SHIFT(3), 0x8, 0xF, gain_tlv),
SOC_SINGLE_SX_TLV("CH4 Volume", REG_MICFIL_OUT_CTRL,
- MICFIL_OUTGAIN_CHX_SHIFT(4), 0xF, 0x7, gain_tlv),
+ MICFIL_OUTGAIN_CHX_SHIFT(4), 0x8, 0xF, gain_tlv),
SOC_SINGLE_SX_TLV("CH5 Volume", REG_MICFIL_OUT_CTRL,
- MICFIL_OUTGAIN_CHX_SHIFT(5), 0xF, 0x7, gain_tlv),
+ MICFIL_OUTGAIN_CHX_SHIFT(5), 0x8, 0xF, gain_tlv),
SOC_SINGLE_SX_TLV("CH6 Volume", REG_MICFIL_OUT_CTRL,
- MICFIL_OUTGAIN_CHX_SHIFT(6), 0xF, 0x7, gain_tlv),
+ MICFIL_OUTGAIN_CHX_SHIFT(6), 0x8, 0xF, gain_tlv),
SOC_SINGLE_SX_TLV("CH7 Volume", REG_MICFIL_OUT_CTRL,
- MICFIL_OUTGAIN_CHX_SHIFT(7), 0xF, 0x7, gain_tlv),
+ MICFIL_OUTGAIN_CHX_SHIFT(7), 0x8, 0xF, gain_tlv),
SOC_ENUM_EXT("MICFIL Quality Select",
fsl_micfil_quality_enum,
micfil_quality_get, micfil_quality_set),
.symmetric_channels = 1,
.probe = fsl_ssi_dai_probe,
.playback = {
- .stream_name = "AC97 Playback",
+ .stream_name = "CPU AC97 Playback",
.channels_min = 2,
.channels_max = 2,
.rates = SNDRV_PCM_RATE_8000_48000,
.formats = SNDRV_PCM_FMTBIT_S16 | SNDRV_PCM_FMTBIT_S20,
},
.capture = {
- .stream_name = "AC97 Capture",
+ .stream_name = "CPU AC97 Capture",
.channels_min = 2,
.channels_max = 2,
.rates = SNDRV_PCM_RATE_48000,
select SND_SOC_RT1015P
select SND_SOC_MAX98373_I2C
select SND_SOC_MAX98357A
+ select SND_SOC_NAU8315
select SND_SOC_DMIC
select SND_SOC_HDAC_HDMI
select SND_SOC_INTEL_HDA_DSP_COMMON
select SND_SOC_INTEL_SOF_MAXIM_COMMON
+ select SND_SOC_INTEL_SOF_REALTEK_COMMON
help
This adds support for ASoC machine driver for SOF platforms
with nau8825 codec.
#define SOF_MAX98373_SPEAKER_AMP_PRESENT BIT(15)
#define SOF_MAX98360A_SPEAKER_AMP_PRESENT BIT(16)
#define SOF_RT1015P_SPEAKER_AMP_PRESENT BIT(17)
+#define SOF_NAU8318_SPEAKER_AMP_PRESENT BIT(18)
static unsigned long sof_nau8825_quirk = SOF_NAU8825_SSP_CODEC(0);
}
};
+static struct snd_soc_dai_link_component nau8318_components[] = {
+ {
+ .name = "NVTN2012:00",
+ .dai_name = "nau8315-hifi",
+ }
+};
+
static struct snd_soc_dai_link_component dummy_component[] = {
{
.name = "snd-soc-dummy",
max_98360a_dai_link(&links[id]);
} else if (sof_nau8825_quirk & SOF_RT1015P_SPEAKER_AMP_PRESENT) {
sof_rt1015p_dai_link(&links[id]);
+ } else if (sof_nau8825_quirk &
+ SOF_NAU8318_SPEAKER_AMP_PRESENT) {
+ links[id].codecs = nau8318_components;
+ links[id].num_codecs = ARRAY_SIZE(nau8318_components);
+ links[id].init = speaker_codec_init;
} else {
goto devm_err;
}
},
{
- .name = "adl_rt1019p_nau8825",
+ .name = "adl_rt1019p_8825",
.driver_data = (kernel_ulong_t)(SOF_NAU8825_SSP_CODEC(0) |
SOF_SPEAKER_AMP_PRESENT |
SOF_RT1019P_SPEAKER_AMP_PRESENT |
SOF_NAU8825_NUM_HDMIDEV(4)),
},
{
- .name = "adl_max98373_nau8825",
+ .name = "adl_max98373_8825",
.driver_data = (kernel_ulong_t)(SOF_NAU8825_SSP_CODEC(0) |
SOF_SPEAKER_AMP_PRESENT |
SOF_MAX98373_SPEAKER_AMP_PRESENT |
},
{
/* The limitation of length of char array, shorten the name */
- .name = "adl_mx98360a_nau8825",
+ .name = "adl_mx98360a_8825",
.driver_data = (kernel_ulong_t)(SOF_NAU8825_SSP_CODEC(0) |
SOF_SPEAKER_AMP_PRESENT |
SOF_MAX98360A_SPEAKER_AMP_PRESENT |
},
{
- .name = "adl_rt1015p_nau8825",
+ .name = "adl_rt1015p_8825",
.driver_data = (kernel_ulong_t)(SOF_NAU8825_SSP_CODEC(0) |
SOF_SPEAKER_AMP_PRESENT |
SOF_RT1015P_SPEAKER_AMP_PRESENT |
SOF_BT_OFFLOAD_SSP(2) |
SOF_SSP_BT_OFFLOAD_PRESENT),
},
+ {
+ .name = "adl_nau8318_8825",
+ .driver_data = (kernel_ulong_t)(SOF_NAU8825_SSP_CODEC(0) |
+ SOF_SPEAKER_AMP_PRESENT |
+ SOF_NAU8318_SPEAKER_AMP_PRESENT |
+ SOF_NAU8825_SSP_AMP(1) |
+ SOF_NAU8825_NUM_HDMIDEV(4) |
+ SOF_BT_OFFLOAD_SSP(2) |
+ SOF_SSP_BT_OFFLOAD_PRESENT),
+ },
{ }
};
MODULE_DEVICE_TABLE(platform, board_ids);
.codecs = {"INTC10B0"}
};
+static const struct snd_soc_acpi_codecs adl_nau8318_amp = {
+ .num_codecs = 1,
+ .codecs = {"NVTN2012"}
+};
+
struct snd_soc_acpi_mach snd_soc_acpi_intel_adl_machines[] = {
{
.comp_ids = &adl_rt5682_rt5682s_hp,
},
{
.id = "10508825",
- .drv_name = "adl_rt1019p_nau8825",
+ .drv_name = "adl_rt1019p_8825",
.machine_quirk = snd_soc_acpi_codec_list,
.quirk_data = &adl_rt1019p_amp,
.sof_tplg_filename = "sof-adl-rt1019-nau8825.tplg",
},
{
.id = "10508825",
- .drv_name = "adl_max98373_nau8825",
+ .drv_name = "adl_max98373_8825",
.machine_quirk = snd_soc_acpi_codec_list,
.quirk_data = &adl_max98373_amp,
.sof_tplg_filename = "sof-adl-max98373-nau8825.tplg",
},
{
.id = "10508825",
- .drv_name = "adl_mx98360a_nau8825",
+ .drv_name = "adl_mx98360a_8825",
.machine_quirk = snd_soc_acpi_codec_list,
.quirk_data = &adl_max98360a_amp,
.sof_tplg_filename = "sof-adl-max98360a-nau8825.tplg",
},
{
.id = "10508825",
- .drv_name = "adl_rt1015p_nau8825",
+ .drv_name = "adl_rt1015p_8825",
.machine_quirk = snd_soc_acpi_codec_list,
.quirk_data = &adl_rt1015p_amp,
.sof_tplg_filename = "sof-adl-rt1015-nau8825.tplg",
},
{
.id = "10508825",
+ .drv_name = "adl_nau8318_8825",
+ .machine_quirk = snd_soc_acpi_codec_list,
+ .quirk_data = &adl_nau8318_amp,
+ .sof_tplg_filename = "sof-adl-nau8318-nau8825.tplg",
+ },
+ {
+ .id = "10508825",
.drv_name = "sof_nau8825",
.sof_tplg_filename = "sof-adl-nau8825.tplg",
},
{}
};
+static const struct snd_soc_acpi_link_adr rpl_sdw_rt711_link2_rt1316_link01[] = {
+ {
+ .mask = BIT(2),
+ .num_adr = ARRAY_SIZE(rt711_sdca_2_adr),
+ .adr_d = rt711_sdca_2_adr,
+ },
+ {
+ .mask = BIT(0),
+ .num_adr = ARRAY_SIZE(rt1316_0_group2_adr),
+ .adr_d = rt1316_0_group2_adr,
+ },
+ {
+ .mask = BIT(1),
+ .num_adr = ARRAY_SIZE(rt1316_1_group2_adr),
+ .adr_d = rt1316_1_group2_adr,
+ },
+ {}
+};
+
static const struct snd_soc_acpi_link_adr rpl_sdw_rt711_link0_rt1318_link12_rt714_link3[] = {
{
.mask = BIT(0),
{}
};
+static const struct snd_soc_acpi_link_adr rpl_sdw_rt711_link0_rt1318_link12[] = {
+ {
+ .mask = BIT(0),
+ .num_adr = ARRAY_SIZE(rt711_sdca_0_adr),
+ .adr_d = rt711_sdca_0_adr,
+ },
+ {
+ .mask = BIT(1),
+ .num_adr = ARRAY_SIZE(rt1318_1_group1_adr),
+ .adr_d = rt1318_1_group1_adr,
+ },
+ {
+ .mask = BIT(2),
+ .num_adr = ARRAY_SIZE(rt1318_2_group1_adr),
+ .adr_d = rt1318_2_group1_adr,
+ },
+ {}
+};
+
static const struct snd_soc_acpi_link_adr rpl_sdw_rt1316_link12_rt714_link0[] = {
{
.mask = BIT(1),
.sof_tplg_filename = "sof-rpl-rt711-l0-rt1318-l12-rt714-l3.tplg",
},
{
+ .link_mask = 0x7, /* rt711 on link0 & two rt1318s on link1 and link2 */
+ .links = rpl_sdw_rt711_link0_rt1318_link12,
+ .drv_name = "sof_sdw",
+ .sof_tplg_filename = "sof-rpl-rt711-l0-rt1318-l12.tplg",
+ },
+ {
.link_mask = 0x7, /* rt714 on link0 & two rt1316s on link1 and link2 */
.links = rpl_sdw_rt1316_link12_rt714_link0,
.drv_name = "sof_sdw",
.sof_tplg_filename = "sof-rpl-rt1316-l12-rt714-l0.tplg",
},
{
+ .link_mask = 0x7, /* rt711 on link2 & two rt1316s on link0 and link1 */
+ .links = rpl_sdw_rt711_link2_rt1316_link01,
+ .drv_name = "sof_sdw",
+ .sof_tplg_filename = "sof-rpl-rt711-l2-rt1316-l01.tplg",
+ },
+ {
.link_mask = 0x1, /* link0 required */
.links = rpl_rvp,
.drv_name = "sof_sdw",
If unsure select "N".
config SND_SOC_MT8186_MT6366_RT1019_RT5682S
- tristate "ASoC Audio driver for MT8186 with RT1019 RT5682S codec"
+ tristate "ASoC Audio driver for MT8186 with RT1019 RT5682S MAX98357A/MAX98360 codec"
depends on I2C && GPIOLIB
depends on SND_SOC_MT8186 && MTK_PMIC_WRAP
+ select SND_SOC_MAX98357A
select SND_SOC_MT6358
+ select SND_SOC_MAX98357A
select SND_SOC_RT1015P
select SND_SOC_RT5682S
select SND_SOC_BT_SCO
.num_configs = ARRAY_SIZE(mt8186_mt6366_rt1019_rt5682s_codec_conf),
};
+static struct snd_soc_card mt8186_mt6366_rt5682s_max98360_soc_card = {
+ .name = "mt8186_rt5682s_max98360",
+ .owner = THIS_MODULE,
+ .dai_link = mt8186_mt6366_rt1019_rt5682s_dai_links,
+ .num_links = ARRAY_SIZE(mt8186_mt6366_rt1019_rt5682s_dai_links),
+ .controls = mt8186_mt6366_rt1019_rt5682s_controls,
+ .num_controls = ARRAY_SIZE(mt8186_mt6366_rt1019_rt5682s_controls),
+ .dapm_widgets = mt8186_mt6366_rt1019_rt5682s_widgets,
+ .num_dapm_widgets = ARRAY_SIZE(mt8186_mt6366_rt1019_rt5682s_widgets),
+ .dapm_routes = mt8186_mt6366_rt1019_rt5682s_routes,
+ .num_dapm_routes = ARRAY_SIZE(mt8186_mt6366_rt1019_rt5682s_routes),
+ .codec_conf = mt8186_mt6366_rt1019_rt5682s_codec_conf,
+ .num_configs = ARRAY_SIZE(mt8186_mt6366_rt1019_rt5682s_codec_conf),
+};
+
static int mt8186_mt6366_rt1019_rt5682s_dev_probe(struct platform_device *pdev)
{
struct snd_soc_card *card;
#if IS_ENABLED(CONFIG_OF)
static const struct of_device_id mt8186_mt6366_rt1019_rt5682s_dt_match[] = {
- { .compatible = "mediatek,mt8186-mt6366-rt1019-rt5682s-sound",
+ {
+ .compatible = "mediatek,mt8186-mt6366-rt1019-rt5682s-sound",
.data = &mt8186_mt6366_rt1019_rt5682s_soc_card,
},
+ {
+ .compatible = "mediatek,mt8186-mt6366-rt5682s-max98360-sound",
+ .data = &mt8186_mt6366_rt5682s_max98360_soc_card,
+ },
{}
};
MODULE_DEVICE_TABLE(of, mt8186_mt6366_rt1019_rt5682s_dt_match);
menuconfig SND_SOC_QCOM
tristate "ASoC support for QCOM platforms"
depends on ARCH_QCOM || COMPILE_TEST
- imply SND_SOC_QCOM_COMMON
help
Say Y or M if you want to add support to use audio devices
in Qualcomm Technologies SOC-based platforms.
config SND_SOC_APQ8016_SBC
tristate "SoC Audio support for APQ8016 SBC platforms"
select SND_SOC_LPASS_APQ8016
- depends on SND_SOC_QCOM_COMMON
+ select SND_SOC_QCOM_COMMON
help
Support for Qualcomm Technologies LPASS audio block in
APQ8016 SOC-based systems.
Say Y if you want to use audio devices on MI2S.
config SND_SOC_QCOM_COMMON
- depends on SOUNDWIRE
+ tristate
+
+config SND_SOC_QCOM_SDW
tristate
config SND_SOC_QDSP6_COMMON
depends on QCOM_APR
depends on COMMON_CLK
select SND_SOC_QDSP6
- depends on SND_SOC_QCOM_COMMON
+ select SND_SOC_QCOM_COMMON
help
Support for Qualcomm Technologies LPASS audio block in
APQ8096 SoC-based systems.
depends on QCOM_APR && I2C && SOUNDWIRE
depends on COMMON_CLK
select SND_SOC_QDSP6
- depends on SND_SOC_QCOM_COMMON
+ select SND_SOC_QCOM_COMMON
select SND_SOC_RT5663
select SND_SOC_MAX98927
imply SND_SOC_CROS_EC_CODEC
depends on QCOM_APR && SOUNDWIRE
depends on COMMON_CLK
select SND_SOC_QDSP6
- depends on SND_SOC_QCOM_COMMON
+ select SND_SOC_QCOM_COMMON
+ select SND_SOC_QCOM_SDW
help
To add support for audio on Qualcomm Technologies Inc.
SM8250 SoC-based systems.
depends on QCOM_APR && SOUNDWIRE
depends on COMMON_CLK
select SND_SOC_QDSP6
- depends on SND_SOC_QCOM_COMMON
+ select SND_SOC_QCOM_COMMON
+ select SND_SOC_QCOM_SDW
help
To add support for audio on Qualcomm Technologies Inc.
SC8280XP SoC-based systems.
tristate "SoC Machine driver for SC7180 boards"
depends on I2C && GPIOLIB
depends on SOUNDWIRE || SOUNDWIRE=n
- depends on SND_SOC_QCOM_COMMON
+ select SND_SOC_QCOM_COMMON
select SND_SOC_LPASS_SC7180
select SND_SOC_MAX98357A
select SND_SOC_RT5682_I2C
config SND_SOC_SC7280
tristate "SoC Machine driver for SC7280 boards"
depends on I2C && SOUNDWIRE
- depends on SND_SOC_QCOM_COMMON
+ select SND_SOC_QCOM_COMMON
select SND_SOC_LPASS_SC7280
select SND_SOC_MAX98357A
select SND_SOC_WCD938X_SDW
snd-soc-sm8250-objs := sm8250.o
snd-soc-sc8280xp-objs := sc8280xp.o
snd-soc-qcom-common-objs := common.o
+snd-soc-qcom-sdw-objs := sdw.o
obj-$(CONFIG_SND_SOC_STORM) += snd-soc-storm.o
obj-$(CONFIG_SND_SOC_APQ8016_SBC) += snd-soc-apq8016-sbc.o
obj-$(CONFIG_SND_SOC_SDM845) += snd-soc-sdm845.o
obj-$(CONFIG_SND_SOC_SM8250) += snd-soc-sm8250.o
obj-$(CONFIG_SND_SOC_QCOM_COMMON) += snd-soc-qcom-common.o
+obj-$(CONFIG_SND_SOC_QCOM_SDW) += snd-soc-qcom-sdw.o
#DSP lib
obj-$(CONFIG_SND_SOC_QDSP6) += qdsp6/
}
EXPORT_SYMBOL_GPL(qcom_snd_parse_of);
-int qcom_snd_sdw_prepare(struct snd_pcm_substream *substream,
- struct sdw_stream_runtime *sruntime,
- bool *stream_prepared)
-{
- struct snd_soc_pcm_runtime *rtd = substream->private_data;
- struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0);
- int ret;
-
- if (!sruntime)
- return 0;
-
- switch (cpu_dai->id) {
- case WSA_CODEC_DMA_RX_0:
- case WSA_CODEC_DMA_RX_1:
- case RX_CODEC_DMA_RX_0:
- case RX_CODEC_DMA_RX_1:
- case TX_CODEC_DMA_TX_0:
- case TX_CODEC_DMA_TX_1:
- case TX_CODEC_DMA_TX_2:
- case TX_CODEC_DMA_TX_3:
- break;
- default:
- return 0;
- }
-
- if (*stream_prepared) {
- sdw_disable_stream(sruntime);
- sdw_deprepare_stream(sruntime);
- *stream_prepared = false;
- }
-
- ret = sdw_prepare_stream(sruntime);
- if (ret)
- return ret;
-
- /**
- * NOTE: there is a strict hw requirement about the ordering of port
- * enables and actual WSA881x PA enable. PA enable should only happen
- * after soundwire ports are enabled if not DC on the line is
- * accumulated resulting in Click/Pop Noise
- * PA enable/mute are handled as part of codec DAPM and digital mute.
- */
-
- ret = sdw_enable_stream(sruntime);
- if (ret) {
- sdw_deprepare_stream(sruntime);
- return ret;
- }
- *stream_prepared = true;
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(qcom_snd_sdw_prepare);
-
-int qcom_snd_sdw_hw_params(struct snd_pcm_substream *substream,
- struct snd_pcm_hw_params *params,
- struct sdw_stream_runtime **psruntime)
-{
- struct snd_soc_pcm_runtime *rtd = substream->private_data;
- struct snd_soc_dai *codec_dai;
- struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0);
- struct sdw_stream_runtime *sruntime;
- int i;
-
- switch (cpu_dai->id) {
- case WSA_CODEC_DMA_RX_0:
- case RX_CODEC_DMA_RX_0:
- case RX_CODEC_DMA_RX_1:
- case TX_CODEC_DMA_TX_0:
- case TX_CODEC_DMA_TX_1:
- case TX_CODEC_DMA_TX_2:
- case TX_CODEC_DMA_TX_3:
- for_each_rtd_codec_dais(rtd, i, codec_dai) {
- sruntime = snd_soc_dai_get_stream(codec_dai, substream->stream);
- if (sruntime != ERR_PTR(-ENOTSUPP))
- *psruntime = sruntime;
- }
- break;
- }
-
- return 0;
-
-}
-EXPORT_SYMBOL_GPL(qcom_snd_sdw_hw_params);
-
-int qcom_snd_sdw_hw_free(struct snd_pcm_substream *substream,
- struct sdw_stream_runtime *sruntime, bool *stream_prepared)
-{
- struct snd_soc_pcm_runtime *rtd = substream->private_data;
- struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0);
-
- switch (cpu_dai->id) {
- case WSA_CODEC_DMA_RX_0:
- case WSA_CODEC_DMA_RX_1:
- case RX_CODEC_DMA_RX_0:
- case RX_CODEC_DMA_RX_1:
- case TX_CODEC_DMA_TX_0:
- case TX_CODEC_DMA_TX_1:
- case TX_CODEC_DMA_TX_2:
- case TX_CODEC_DMA_TX_3:
- if (sruntime && *stream_prepared) {
- sdw_disable_stream(sruntime);
- sdw_deprepare_stream(sruntime);
- *stream_prepared = false;
- }
- break;
- default:
- break;
- }
-
- return 0;
-}
-EXPORT_SYMBOL_GPL(qcom_snd_sdw_hw_free);
-
int qcom_snd_wcd_jack_setup(struct snd_soc_pcm_runtime *rtd,
struct snd_soc_jack *jack, bool *jack_setup)
{
#define __QCOM_SND_COMMON_H__
#include <sound/soc.h>
-#include <linux/soundwire/sdw.h>
int qcom_snd_parse_of(struct snd_soc_card *card);
int qcom_snd_wcd_jack_setup(struct snd_soc_pcm_runtime *rtd,
struct snd_soc_jack *jack, bool *jack_setup);
-int qcom_snd_sdw_prepare(struct snd_pcm_substream *substream,
- struct sdw_stream_runtime *runtime,
- bool *stream_prepared);
-int qcom_snd_sdw_hw_params(struct snd_pcm_substream *substream,
- struct snd_pcm_hw_params *params,
- struct sdw_stream_runtime **psruntime);
-int qcom_snd_sdw_hw_free(struct snd_pcm_substream *substream,
- struct sdw_stream_runtime *sruntime,
- bool *stream_prepared);
#endif
struct lpass_data *data)
{
struct device_node *node;
- int ret, id;
+ int ret, i, id;
/* Allow all channels by default for backwards compatibility */
- for (id = 0; id < data->variant->num_dai; id++) {
+ for (i = 0; i < data->variant->num_dai; i++) {
+ id = data->variant->dai_driver[i].id;
data->mi2s_playback_sd_mode[id] = LPAIF_I2SCTL_MODE_8CH;
data->mi2s_capture_sd_mode[id] = LPAIF_I2SCTL_MODE_8CH;
}
#include <linux/input-event-codes.h>
#include "qdsp6/q6afe.h"
#include "common.h"
+#include "sdw.h"
#define DRIVER_NAME "sc8280xp"
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018, Linaro Limited.
+// Copyright (c) 2018, The Linux Foundation. All rights reserved.
+
+#include <linux/module.h>
+#include <sound/soc.h>
+#include "qdsp6/q6afe.h"
+#include "sdw.h"
+
+int qcom_snd_sdw_prepare(struct snd_pcm_substream *substream,
+ struct sdw_stream_runtime *sruntime,
+ bool *stream_prepared)
+{
+ struct snd_soc_pcm_runtime *rtd = substream->private_data;
+ struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0);
+ int ret;
+
+ if (!sruntime)
+ return 0;
+
+ switch (cpu_dai->id) {
+ case WSA_CODEC_DMA_RX_0:
+ case WSA_CODEC_DMA_RX_1:
+ case RX_CODEC_DMA_RX_0:
+ case RX_CODEC_DMA_RX_1:
+ case TX_CODEC_DMA_TX_0:
+ case TX_CODEC_DMA_TX_1:
+ case TX_CODEC_DMA_TX_2:
+ case TX_CODEC_DMA_TX_3:
+ break;
+ default:
+ return 0;
+ }
+
+ if (*stream_prepared) {
+ sdw_disable_stream(sruntime);
+ sdw_deprepare_stream(sruntime);
+ *stream_prepared = false;
+ }
+
+ ret = sdw_prepare_stream(sruntime);
+ if (ret)
+ return ret;
+
+ /**
+ * NOTE: there is a strict hw requirement about the ordering of port
+ * enables and actual WSA881x PA enable. PA enable should only happen
+ * after soundwire ports are enabled if not DC on the line is
+ * accumulated resulting in Click/Pop Noise
+ * PA enable/mute are handled as part of codec DAPM and digital mute.
+ */
+
+ ret = sdw_enable_stream(sruntime);
+ if (ret) {
+ sdw_deprepare_stream(sruntime);
+ return ret;
+ }
+ *stream_prepared = true;
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(qcom_snd_sdw_prepare);
+
+int qcom_snd_sdw_hw_params(struct snd_pcm_substream *substream,
+ struct snd_pcm_hw_params *params,
+ struct sdw_stream_runtime **psruntime)
+{
+ struct snd_soc_pcm_runtime *rtd = substream->private_data;
+ struct snd_soc_dai *codec_dai;
+ struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0);
+ struct sdw_stream_runtime *sruntime;
+ int i;
+
+ switch (cpu_dai->id) {
+ case WSA_CODEC_DMA_RX_0:
+ case RX_CODEC_DMA_RX_0:
+ case RX_CODEC_DMA_RX_1:
+ case TX_CODEC_DMA_TX_0:
+ case TX_CODEC_DMA_TX_1:
+ case TX_CODEC_DMA_TX_2:
+ case TX_CODEC_DMA_TX_3:
+ for_each_rtd_codec_dais(rtd, i, codec_dai) {
+ sruntime = snd_soc_dai_get_stream(codec_dai, substream->stream);
+ if (sruntime != ERR_PTR(-ENOTSUPP))
+ *psruntime = sruntime;
+ }
+ break;
+ }
+
+ return 0;
+
+}
+EXPORT_SYMBOL_GPL(qcom_snd_sdw_hw_params);
+
+int qcom_snd_sdw_hw_free(struct snd_pcm_substream *substream,
+ struct sdw_stream_runtime *sruntime, bool *stream_prepared)
+{
+ struct snd_soc_pcm_runtime *rtd = substream->private_data;
+ struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0);
+
+ switch (cpu_dai->id) {
+ case WSA_CODEC_DMA_RX_0:
+ case WSA_CODEC_DMA_RX_1:
+ case RX_CODEC_DMA_RX_0:
+ case RX_CODEC_DMA_RX_1:
+ case TX_CODEC_DMA_TX_0:
+ case TX_CODEC_DMA_TX_1:
+ case TX_CODEC_DMA_TX_2:
+ case TX_CODEC_DMA_TX_3:
+ if (sruntime && *stream_prepared) {
+ sdw_disable_stream(sruntime);
+ sdw_deprepare_stream(sruntime);
+ *stream_prepared = false;
+ }
+ break;
+ default:
+ break;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(qcom_snd_sdw_hw_free);
+MODULE_LICENSE("GPL v2");
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (c) 2018, The Linux Foundation. All rights reserved.
+
+#ifndef __QCOM_SND_SDW_H__
+#define __QCOM_SND_SDW_H__
+
+#include <linux/soundwire/sdw.h>
+
+int qcom_snd_sdw_prepare(struct snd_pcm_substream *substream,
+ struct sdw_stream_runtime *runtime,
+ bool *stream_prepared);
+int qcom_snd_sdw_hw_params(struct snd_pcm_substream *substream,
+ struct snd_pcm_hw_params *params,
+ struct sdw_stream_runtime **psruntime);
+int qcom_snd_sdw_hw_free(struct snd_pcm_substream *substream,
+ struct sdw_stream_runtime *sruntime,
+ bool *stream_prepared);
+#endif
#include <linux/input-event-codes.h>
#include "qdsp6/q6afe.h"
#include "common.h"
+#include "sdw.h"
#define DRIVER_NAME "sm8250"
#define MI2S_BCLK_RATE 1536000
return err;
}
- return 0;
+ return snd_sof_debugfs_buf_item(sdev, &sdev->fw_state,
+ sizeof(sdev->fw_state),
+ "fw_state", 0444);
}
EXPORT_SYMBOL_GPL(snd_sof_dbg_init);
const struct sof_ipc_pm_ops *pm_ops = sdev->ipc->ops->pm;
const struct sof_ipc_tplg_ops *tplg_ops = sdev->ipc->ops->tplg;
pm_message_t pm_state;
- u32 target_state = 0;
+ u32 target_state = snd_sof_dsp_power_target(sdev);
int ret;
/* do nothing if dsp suspend callback is not set */
if (runtime_suspend && !sof_ops(sdev)->runtime_suspend)
return 0;
+ if (tplg_ops && tplg_ops->tear_down_all_pipelines)
+ tplg_ops->tear_down_all_pipelines(sdev, false);
+
if (sdev->fw_state != SOF_FW_BOOT_COMPLETE)
goto suspend;
}
}
- target_state = snd_sof_dsp_power_target(sdev);
pm_state.event = target_state;
/* Skip to platform-specific suspend if DSP is entering D0 */
goto suspend;
}
- if (tplg_ops->tear_down_all_pipelines)
- tplg_ops->tear_down_all_pipelines(sdev, false);
-
/* suspend DMA trace */
sof_fw_trace_suspend(sdev, pm_state);
subs = find_matching_substream(chip, stream, target->sync_ep,
target->fmt_type);
if (!subs)
- return sync_fmt;
+ goto end;
high_score = 0;
list_for_each_entry(fp, &subs->fmt_list, list) {
}
}
+ end:
if (fixed_rate)
*fixed_rate = snd_usb_pcm_has_fixed_rate(subs);
return sync_fmt;
bool snd_usb_pcm_has_fixed_rate(struct snd_usb_substream *subs)
{
const struct audioformat *fp;
- struct snd_usb_audio *chip = subs->stream->chip;
+ struct snd_usb_audio *chip;
int rate = -1;
+ if (!subs)
+ return false;
+ chip = subs->stream->chip;
if (!(chip->quirk_flags & QUIRK_FLAG_FIXED_RATE))
return false;
list_for_each_entry(fp, &subs->fmt_list, list) {
if (snd_usb_endpoint_compatible(chip, subs->data_endpoint,
fmt, hw_params))
goto unlock;
+ if (stop_endpoints(subs, false))
+ sync_pending_stops(subs);
close_endpoints(chip, subs);
}
return changed;
}
+/* get the specified endpoint object that is being used by other streams
+ * (i.e. the parameter is locked)
+ */
+static const struct snd_usb_endpoint *
+get_endpoint_in_use(struct snd_usb_audio *chip, int endpoint,
+ const struct snd_usb_endpoint *ref_ep)
+{
+ const struct snd_usb_endpoint *ep;
+
+ ep = snd_usb_get_endpoint(chip, endpoint);
+ if (ep && ep->cur_audiofmt && (ep != ref_ep || ep->opened > 1))
+ return ep;
+ return NULL;
+}
+
static int hw_rule_rate(struct snd_pcm_hw_params *params,
struct snd_pcm_hw_rule *rule)
{
struct snd_usb_substream *subs = rule->private;
struct snd_usb_audio *chip = subs->stream->chip;
+ const struct snd_usb_endpoint *ep;
const struct audioformat *fp;
struct snd_interval *it = hw_param_interval(params, SNDRV_PCM_HW_PARAM_RATE);
unsigned int rmin, rmax, r;
list_for_each_entry(fp, &subs->fmt_list, list) {
if (!hw_check_valid_format(subs, params, fp))
continue;
+
+ ep = get_endpoint_in_use(chip, fp->endpoint,
+ subs->data_endpoint);
+ if (ep) {
+ hwc_debug("rate limit %d for ep#%x\n",
+ ep->cur_rate, fp->endpoint);
+ rmin = min(rmin, ep->cur_rate);
+ rmax = max(rmax, ep->cur_rate);
+ continue;
+ }
+
+ if (fp->implicit_fb) {
+ ep = get_endpoint_in_use(chip, fp->sync_ep,
+ subs->sync_endpoint);
+ if (ep) {
+ hwc_debug("rate limit %d for sync_ep#%x\n",
+ ep->cur_rate, fp->sync_ep);
+ rmin = min(rmin, ep->cur_rate);
+ rmax = max(rmax, ep->cur_rate);
+ continue;
+ }
+ }
+
r = snd_usb_endpoint_get_clock_rate(chip, fp->clock);
if (r > 0) {
if (!snd_interval_test(it, r))
struct snd_pcm_hw_rule *rule)
{
struct snd_usb_substream *subs = rule->private;
+ struct snd_usb_audio *chip = subs->stream->chip;
+ const struct snd_usb_endpoint *ep;
const struct audioformat *fp;
struct snd_mask *fmt = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT);
u64 fbits;
list_for_each_entry(fp, &subs->fmt_list, list) {
if (!hw_check_valid_format(subs, params, fp))
continue;
+
+ ep = get_endpoint_in_use(chip, fp->endpoint,
+ subs->data_endpoint);
+ if (ep) {
+ hwc_debug("format limit %d for ep#%x\n",
+ ep->cur_format, fp->endpoint);
+ fbits |= pcm_format_to_bits(ep->cur_format);
+ continue;
+ }
+
+ if (fp->implicit_fb) {
+ ep = get_endpoint_in_use(chip, fp->sync_ep,
+ subs->sync_endpoint);
+ if (ep) {
+ hwc_debug("format limit %d for sync_ep#%x\n",
+ ep->cur_format, fp->sync_ep);
+ fbits |= pcm_format_to_bits(ep->cur_format);
+ continue;
+ }
+ }
+
fbits |= fp->formats;
}
return apply_hw_params_format_bits(fmt, fbits);
return apply_hw_params_minmax(it, pmin, UINT_MAX);
}
-/* get the EP or the sync EP for implicit fb when it's already set up */
-static const struct snd_usb_endpoint *
-get_sync_ep_from_substream(struct snd_usb_substream *subs)
-{
- struct snd_usb_audio *chip = subs->stream->chip;
- const struct audioformat *fp;
- const struct snd_usb_endpoint *ep;
-
- list_for_each_entry(fp, &subs->fmt_list, list) {
- ep = snd_usb_get_endpoint(chip, fp->endpoint);
- if (ep && ep->cur_audiofmt) {
- /* if EP is already opened solely for this substream,
- * we still allow us to change the parameter; otherwise
- * this substream has to follow the existing parameter
- */
- if (ep->cur_audiofmt != subs->cur_audiofmt || ep->opened > 1)
- return ep;
- }
- if (!fp->implicit_fb)
- continue;
- /* for the implicit fb, check the sync ep as well */
- ep = snd_usb_get_endpoint(chip, fp->sync_ep);
- if (ep && ep->cur_audiofmt)
- return ep;
- }
- return NULL;
-}
-
/* additional hw constraints for implicit feedback mode */
-static int hw_rule_format_implicit_fb(struct snd_pcm_hw_params *params,
- struct snd_pcm_hw_rule *rule)
-{
- struct snd_usb_substream *subs = rule->private;
- const struct snd_usb_endpoint *ep;
- struct snd_mask *fmt = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT);
-
- ep = get_sync_ep_from_substream(subs);
- if (!ep)
- return 0;
-
- hwc_debug("applying %s\n", __func__);
- return apply_hw_params_format_bits(fmt, pcm_format_to_bits(ep->cur_format));
-}
-
-static int hw_rule_rate_implicit_fb(struct snd_pcm_hw_params *params,
- struct snd_pcm_hw_rule *rule)
-{
- struct snd_usb_substream *subs = rule->private;
- const struct snd_usb_endpoint *ep;
- struct snd_interval *it;
-
- ep = get_sync_ep_from_substream(subs);
- if (!ep)
- return 0;
-
- hwc_debug("applying %s\n", __func__);
- it = hw_param_interval(params, SNDRV_PCM_HW_PARAM_RATE);
- return apply_hw_params_minmax(it, ep->cur_rate, ep->cur_rate);
-}
-
static int hw_rule_period_size_implicit_fb(struct snd_pcm_hw_params *params,
struct snd_pcm_hw_rule *rule)
{
struct snd_usb_substream *subs = rule->private;
+ struct snd_usb_audio *chip = subs->stream->chip;
+ const struct audioformat *fp;
const struct snd_usb_endpoint *ep;
struct snd_interval *it;
+ unsigned int rmin, rmax;
- ep = get_sync_ep_from_substream(subs);
- if (!ep)
- return 0;
-
- hwc_debug("applying %s\n", __func__);
it = hw_param_interval(params, SNDRV_PCM_HW_PARAM_PERIOD_SIZE);
- return apply_hw_params_minmax(it, ep->cur_period_frames,
- ep->cur_period_frames);
+ hwc_debug("hw_rule_period_size: (%u,%u)\n", it->min, it->max);
+ rmin = UINT_MAX;
+ rmax = 0;
+ list_for_each_entry(fp, &subs->fmt_list, list) {
+ if (!hw_check_valid_format(subs, params, fp))
+ continue;
+ ep = get_endpoint_in_use(chip, fp->endpoint,
+ subs->data_endpoint);
+ if (ep) {
+ hwc_debug("period size limit %d for ep#%x\n",
+ ep->cur_period_frames, fp->endpoint);
+ rmin = min(rmin, ep->cur_period_frames);
+ rmax = max(rmax, ep->cur_period_frames);
+ continue;
+ }
+
+ if (fp->implicit_fb) {
+ ep = get_endpoint_in_use(chip, fp->sync_ep,
+ subs->sync_endpoint);
+ if (ep) {
+ hwc_debug("period size limit %d for sync_ep#%x\n",
+ ep->cur_period_frames, fp->sync_ep);
+ rmin = min(rmin, ep->cur_period_frames);
+ rmax = max(rmax, ep->cur_period_frames);
+ continue;
+ }
+ }
+ }
+
+ if (!rmax)
+ return 0; /* no limit by implicit fb */
+ return apply_hw_params_minmax(it, rmin, rmax);
}
static int hw_rule_periods_implicit_fb(struct snd_pcm_hw_params *params,
struct snd_pcm_hw_rule *rule)
{
struct snd_usb_substream *subs = rule->private;
+ struct snd_usb_audio *chip = subs->stream->chip;
+ const struct audioformat *fp;
const struct snd_usb_endpoint *ep;
struct snd_interval *it;
+ unsigned int rmin, rmax;
- ep = get_sync_ep_from_substream(subs);
- if (!ep)
- return 0;
-
- hwc_debug("applying %s\n", __func__);
it = hw_param_interval(params, SNDRV_PCM_HW_PARAM_PERIODS);
- return apply_hw_params_minmax(it, ep->cur_buffer_periods,
- ep->cur_buffer_periods);
+ hwc_debug("hw_rule_periods: (%u,%u)\n", it->min, it->max);
+ rmin = UINT_MAX;
+ rmax = 0;
+ list_for_each_entry(fp, &subs->fmt_list, list) {
+ if (!hw_check_valid_format(subs, params, fp))
+ continue;
+ ep = get_endpoint_in_use(chip, fp->endpoint,
+ subs->data_endpoint);
+ if (ep) {
+ hwc_debug("periods limit %d for ep#%x\n",
+ ep->cur_buffer_periods, fp->endpoint);
+ rmin = min(rmin, ep->cur_buffer_periods);
+ rmax = max(rmax, ep->cur_buffer_periods);
+ continue;
+ }
+
+ if (fp->implicit_fb) {
+ ep = get_endpoint_in_use(chip, fp->sync_ep,
+ subs->sync_endpoint);
+ if (ep) {
+ hwc_debug("periods limit %d for sync_ep#%x\n",
+ ep->cur_buffer_periods, fp->sync_ep);
+ rmin = min(rmin, ep->cur_buffer_periods);
+ rmax = max(rmax, ep->cur_buffer_periods);
+ continue;
+ }
+ }
+ }
+
+ if (!rmax)
+ return 0; /* no limit by implicit fb */
+ return apply_hw_params_minmax(it, rmin, rmax);
}
/*
return err;
/* additional hw constraints for implicit fb */
- err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_FORMAT,
- hw_rule_format_implicit_fb, subs,
- SNDRV_PCM_HW_PARAM_FORMAT, -1);
- if (err < 0)
- return err;
- err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_RATE,
- hw_rule_rate_implicit_fb, subs,
- SNDRV_PCM_HW_PARAM_RATE, -1);
- if (err < 0)
- return err;
err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_PERIOD_SIZE,
hw_rule_period_size_implicit_fb, subs,
SNDRV_PCM_HW_PARAM_PERIOD_SIZE, -1);
if (err < 0)
return err;
}
+
+ /* try to set the interface... */
+ usb_set_interface(chip->dev, iface_no, 0);
+ snd_usb_init_pitch(chip, fp);
+ snd_usb_init_sample_rate(chip, fp, fp->rate_max);
+ usb_set_interface(chip->dev, iface_no, altno);
}
return 0;
}
return xenbus_switch_state(xb_dev, XenbusStateInitialising);
}
-static int xen_drv_remove(struct xenbus_device *dev)
+static void xen_drv_remove(struct xenbus_device *dev)
{
struct xen_snd_front_info *front_info = dev_get_drvdata(&dev->dev);
int to = 100;
xen_snd_drv_fini(front_info);
xenbus_frontend_closed(dev);
- return 0;
}
static const struct xenbus_device_id xen_drv_ids[] = {
LLVM_CONFIG_LIB_COMPONENTS := mcdisassembler all-targets
CFLAGS += $(shell $(LLVM_CONFIG) --cflags --libs $(LLVM_CONFIG_LIB_COMPONENTS))
LIBS += $(shell $(LLVM_CONFIG) --libs $(LLVM_CONFIG_LIB_COMPONENTS))
+ ifeq ($(shell $(LLVM_CONFIG) --shared-mode),static)
+ LIBS += $(shell $(LLVM_CONFIG) --system-libs $(LLVM_CONFIG_LIB_COMPONENTS))
+ LIBS += -lstdc++
+ endif
LDFLAGS += $(shell $(LLVM_CONFIG) --ldflags)
else
# Fall back on libbfd
__asm__ (".section .text\n"
".weak __start\n"
".set nomips16\n"
+ ".set push\n"
".set noreorder\n"
".option pic0\n"
".ent __start\n"
"li $v0, 4001\n" // NR_exit == 4001
"syscall\n"
".end __start\n"
+ ".set pop\n"
"");
#endif // _NOLIBC_ARCH_MIPS_H
#define O_RDONLY 0
#define O_WRONLY 1
#define O_RDWR 2
-#define O_CREAT 0x100
-#define O_EXCL 0x200
-#define O_NOCTTY 0x400
-#define O_TRUNC 0x1000
-#define O_APPEND 0x2000
-#define O_NONBLOCK 0x4000
-#define O_DIRECTORY 0x200000
+#define O_CREAT 0x40
+#define O_EXCL 0x80
+#define O_NOCTTY 0x100
+#define O_TRUNC 0x200
+#define O_APPEND 0x400
+#define O_NONBLOCK 0x800
+#define O_DIRECTORY 0x10000
struct sys_stat_struct {
unsigned long st_dev; /* Device. */
return isgraph(c) && !isalnum(c);
}
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
#endif /* _NOLIBC_CTYPE_H */
*/
#define MAX_ERRNO 4095
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
#endif /* _NOLIBC_ERRNO_H */
return sys_kill(sys_getpid(), signal);
}
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
#endif /* _NOLIBC_SIGNAL_H */
fprintf(stderr, "%s%serrno=%d\n", (msg && *msg) ? msg : "", (msg && *msg) ? ": " : "", errno);
}
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
#endif /* _NOLIBC_STDIO_H */
return itoa_buffer;
}
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
#endif /* _NOLIBC_STDLIB_H */
{
char *p = dst;
- while (len--)
+ while (len--) {
+ /* prevent gcc from recognizing memset() here */
+ asm volatile("");
*(p++) = b;
+ }
return dst;
}
return (char *)ret;
}
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
#endif /* _NOLIBC_STRING_H */
return ret;
}
+/* make sure to include all global symbols */
+#include "nolibc.h"
#endif /* _NOLIBC_SYS_H */
return tv.tv_sec;
}
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
#endif /* _NOLIBC_TIME_H */
#define S_IFSOCK 0140000
#define S_IFMT 0170000
-#define S_ISDIR(mode) (((mode) & S_IFDIR) == S_IFDIR)
-#define S_ISCHR(mode) (((mode) & S_IFCHR) == S_IFCHR)
-#define S_ISBLK(mode) (((mode) & S_IFBLK) == S_IFBLK)
-#define S_ISREG(mode) (((mode) & S_IFREG) == S_IFREG)
-#define S_ISFIFO(mode) (((mode) & S_IFIFO) == S_IFIFO)
-#define S_ISLNK(mode) (((mode) & S_IFLNK) == S_IFLNK)
-#define S_ISSOCK(mode) (((mode) & S_IFSOCK) == S_IFSOCK)
+#define S_ISDIR(mode) (((mode) & S_IFMT) == S_IFDIR)
+#define S_ISCHR(mode) (((mode) & S_IFMT) == S_IFCHR)
+#define S_ISBLK(mode) (((mode) & S_IFMT) == S_IFBLK)
+#define S_ISREG(mode) (((mode) & S_IFMT) == S_IFREG)
+#define S_ISFIFO(mode) (((mode) & S_IFMT) == S_IFIFO)
+#define S_ISLNK(mode) (((mode) & S_IFMT) == S_IFLNK)
+#define S_ISSOCK(mode) (((mode) & S_IFMT) == S_IFSOCK)
/* dirent types */
#define DT_UNKNOWN 0x0
#define EXIT_SUCCESS 0
#define EXIT_FAILURE 1
+#define FD_SETIDXMASK (8 * sizeof(unsigned long))
+#define FD_SETBITMASK (8 * sizeof(unsigned long)-1)
+
/* for select() */
typedef struct {
- uint32_t fd32[(FD_SETSIZE + 31) / 32];
+ unsigned long fds[(FD_SETSIZE + FD_SETBITMASK) / FD_SETIDXMASK];
} fd_set;
-#define FD_CLR(fd, set) do { \
- fd_set *__set = (set); \
- int __fd = (fd); \
- if (__fd >= 0) \
- __set->fd32[__fd / 32] &= ~(1U << (__fd & 31)); \
+#define FD_CLR(fd, set) do { \
+ fd_set *__set = (set); \
+ int __fd = (fd); \
+ if (__fd >= 0) \
+ __set->fds[__fd / FD_SETIDXMASK] &= \
+ ~(1U << (__fd & FX_SETBITMASK)); \
} while (0)
-#define FD_SET(fd, set) do { \
- fd_set *__set = (set); \
- int __fd = (fd); \
- if (__fd >= 0) \
- __set->fd32[__fd / 32] |= 1U << (__fd & 31); \
+#define FD_SET(fd, set) do { \
+ fd_set *__set = (set); \
+ int __fd = (fd); \
+ if (__fd >= 0) \
+ __set->fds[__fd / FD_SETIDXMASK] |= \
+ 1 << (__fd & FD_SETBITMASK); \
} while (0)
-#define FD_ISSET(fd, set) ({ \
- fd_set *__set = (set); \
- int __fd = (fd); \
- int __r = 0; \
- if (__fd >= 0) \
- __r = !!(__set->fd32[__fd / 32] & 1U << (__fd & 31)); \
- __r; \
+#define FD_ISSET(fd, set) ({ \
+ fd_set *__set = (set); \
+ int __fd = (fd); \
+ int __r = 0; \
+ if (__fd >= 0) \
+ __r = !!(__set->fds[__fd / FD_SETIDXMASK] & \
+1U << (__fd & FD_SET_BITMASK)); \
+ __r; \
})
-#define FD_ZERO(set) do { \
- fd_set *__set = (set); \
- int __idx; \
- for (__idx = 0; __idx < (FD_SETSIZE+31) / 32; __idx ++) \
- __set->fd32[__idx] = 0; \
+#define FD_ZERO(set) do { \
+ fd_set *__set = (set); \
+ int __idx; \
+ int __size = (FD_SETSIZE+FD_SETBITMASK) / FD_SETIDXMASK;\
+ for (__idx = 0; __idx < __size; __idx++) \
+ __set->fds[__idx] = 0; \
} while (0)
/* for poll() */
})
#endif
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
#endif /* _NOLIBC_TYPES_H */
return ioctl(fd, TIOCSPGRP, &pid);
}
+/* make sure to include all global symbols */
+#include "nolibc.h"
+
#endif /* _NOLIBC_UNISTD_H */
if (func->type != STT_NOTYPE && func->type != STT_FUNC)
continue;
+ if (func->offset == sec->sh.sh_size) {
+ /* Heuristic: likely an "end" symbol */
+ if (func->type == STT_NOTYPE)
+ continue;
+ WARN("%s(): STT_FUNC at end of section",
+ func->name);
+ return -1;
+ }
+
if (func->return_thunk || func->alias != func)
continue;
$(ASCIIDOC) -b docbook -d manpage \
$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) \
-aperf_date=$(shell git log -1 --pretty="format:%cd" \
- --date=short $<) \
+ --date=short --no-show-signature $<) \
-o $@+ $< && \
mv $@+ $@
$(call feature_check,libbpf-bpf_program__set_insns)
ifeq ($(feature-libbpf-bpf_program__set_insns), 1)
CFLAGS += -DHAVE_LIBBPF_BPF_PROGRAM__SET_INSNS
+ else
+ dummy := $(error Error: libbpf devel library needs to be >= 0.8.0 to build with LIBBPF_DYNAMIC, update or build statically with the version that comes with the kernel sources);
endif
$(call feature_check,libbpf-btf__raw_data)
ifeq ($(feature-libbpf-btf__raw_data), 1)
dummy := $(error Error: No libbpf devel library found, please install libbpf-devel);
endif
else
+ # Libbpf will be built as a static library from tools/lib/bpf.
+ LIBBPF_STATIC := 1
CFLAGS += -DHAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID
CFLAGS += -DHAVE_LIBBPF_BPF_PROG_LOAD
CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_PROGRAM
export perfexec_instdir_SQ
-# If we install to $(HOME) we keep the traceevent default:
-# $(HOME)/.traceevent/plugins
-# Otherwise we install plugins into the global $(libdir).
-ifdef DESTDIR
-plugindir=$(libdir)/traceevent/plugins
-plugindir_SQ= $(subst ','\'',$(plugindir))
-endif
-
print_var = $(eval $(print_var_code)) $(info $(MSG))
define print_var_code
MSG = $(shell printf '...%40s: %s' $(1) $($(1)))
else
LIBBPF_OUTPUT = $(CURDIR)/libbpf
endif
-LIBBPF_DESTDIR = $(LIBBPF_OUTPUT)
-LIBBPF_INCLUDE = $(LIBBPF_DESTDIR)/include
-LIBBPF = $(LIBBPF_OUTPUT)/libbpf.a
-CFLAGS += -I$(LIBBPF_OUTPUT)/include
+ifdef LIBBPF_STATIC
+ LIBBPF_DESTDIR = $(LIBBPF_OUTPUT)
+ LIBBPF_INCLUDE = $(LIBBPF_DESTDIR)/include
+ LIBBPF = $(LIBBPF_OUTPUT)/libbpf.a
+ CFLAGS += -I$(LIBBPF_OUTPUT)/include
+endif
ifneq ($(OUTPUT),)
LIBSUBCMD_OUTPUT = $(abspath $(OUTPUT))/libsubcmd
export PERL_PATH
PERFLIBS = $(LIBAPI) $(LIBPERF) $(LIBSUBCMD) $(LIBSYMBOL)
-ifndef NO_LIBBPF
- ifndef LIBBPF_DYNAMIC
- PERFLIBS += $(LIBBPF)
- endif
+ifdef LIBBPF_STATIC
+ PERFLIBS += $(LIBBPF)
endif
# We choose to avoid "if .. else if .. else .. endif endif"
$(arch_errno_name_array) \
$(sync_file_range_arrays) \
$(LIBAPI) \
- $(LIBBPF) \
$(LIBPERF) \
$(LIBSUBCMD) \
$(LIBSYMBOL) \
bpf-skel
+ifdef LIBBPF_STATIC
+prepare: $(LIBBPF)
+endif
+
$(OUTPUT)%.o: %.c prepare FORCE
$(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@
$(LIBAPI): FORCE | $(LIBAPI_OUTPUT)
$(Q)$(MAKE) -C $(LIBAPI_DIR) O=$(LIBAPI_OUTPUT) \
- DESTDIR=$(LIBAPI_DESTDIR) prefix= \
+ DESTDIR=$(LIBAPI_DESTDIR) prefix= subdir= \
$@ install_headers
$(LIBAPI)-clean:
$(LIBBPF): FORCE | $(LIBBPF_OUTPUT)
$(Q)$(MAKE) -C $(LIBBPF_DIR) FEATURES_DUMP=$(FEATURE_DUMP_EXPORT) \
- O= OUTPUT=$(LIBBPF_OUTPUT)/ DESTDIR=$(LIBBPF_DESTDIR) prefix= \
+ O= OUTPUT=$(LIBBPF_OUTPUT)/ DESTDIR=$(LIBBPF_DESTDIR) prefix= subdir= \
$@ install_headers
$(LIBBPF)-clean:
$(LIBPERF): FORCE | $(LIBPERF_OUTPUT)
$(Q)$(MAKE) -C $(LIBPERF_DIR) O=$(LIBPERF_OUTPUT) \
- DESTDIR=$(LIBPERF_DESTDIR) prefix= \
+ DESTDIR=$(LIBPERF_DESTDIR) prefix= subdir= \
$@ install_headers
$(LIBPERF)-clean:
$(LIBSUBCMD): FORCE | $(LIBSUBCMD_OUTPUT)
$(Q)$(MAKE) -C $(LIBSUBCMD_DIR) O=$(LIBSUBCMD_OUTPUT) \
- DESTDIR=$(LIBSUBCMD_DESTDIR) prefix= \
+ DESTDIR=$(LIBSUBCMD_DESTDIR) prefix= subdir= \
$@ install_headers
$(LIBSUBCMD)-clean:
$(LIBSYMBOL): FORCE | $(LIBSYMBOL_OUTPUT)
$(Q)$(MAKE) -C $(LIBSYMBOL_DIR) O=$(LIBSYMBOL_OUTPUT) \
- DESTDIR=$(LIBSYMBOL_DESTDIR) prefix= \
+ DESTDIR=$(LIBSYMBOL_DESTDIR) prefix= subdir= \
$@ install_headers
$(LIBSYMBOL)-clean:
#include <elfutils/libdwfl.h>
#include "../../util/unwind-libdw.h"
#include "../../util/perf_regs.h"
-#include "../../util/event.h"
+#include "../../util/sample.h"
bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
{
#include "util/string2.h"
#include <linux/kernel.h>
+#include <linux/numa.h>
#include <linux/rbtree.h>
#include <linux/string.h>
#include <linux/zalloc.h>
total_allocated += bytes_alloc;
nr_allocs++;
- return 0;
-}
-static int evsel__process_alloc_node_event(struct evsel *evsel, struct perf_sample *sample)
-{
- int ret = evsel__process_alloc_event(evsel, sample);
+ /*
+ * Commit 11e9734bcb6a ("mm/slab_common: unify NUMA and UMA
+ * version of tracepoints") adds the field "node" into the
+ * tracepoints 'kmalloc' and 'kmem_cache_alloc'.
+ *
+ * The legacy tracepoints 'kmalloc_node' and 'kmem_cache_alloc_node'
+ * also contain the field "node".
+ *
+ * If the tracepoint contains the field "node" the tool stats the
+ * cross allocation.
+ */
+ if (evsel__field(evsel, "node")) {
+ int node1, node2;
- if (!ret) {
- int node1 = cpu__get_node((struct perf_cpu){.cpu = sample->cpu}),
- node2 = evsel__intval(evsel, sample, "node");
+ node1 = cpu__get_node((struct perf_cpu){.cpu = sample->cpu});
+ node2 = evsel__intval(evsel, sample, "node");
- if (node1 != node2)
+ /*
+ * If the field "node" is NUMA_NO_NODE (-1), we don't take it
+ * as a cross allocation.
+ */
+ if ((node2 != NUMA_NO_NODE) && (node1 != node2))
nr_cross_allocs++;
}
- return ret;
+ return 0;
}
static int ptr_cmp(void *, void *);
/* slab allocator */
{ "kmem:kmalloc", evsel__process_alloc_event, },
{ "kmem:kmem_cache_alloc", evsel__process_alloc_event, },
- { "kmem:kmalloc_node", evsel__process_alloc_node_event, },
- { "kmem:kmem_cache_alloc_node", evsel__process_alloc_node_event, },
+ { "kmem:kmalloc_node", evsel__process_alloc_event, },
+ { "kmem:kmem_cache_alloc_node", evsel__process_alloc_event, },
{ "kmem:kfree", evsel__process_free_event, },
{ "kmem:kmem_cache_free", evsel__process_free_event, },
/* page allocator */
return 0;
}
+static bool slab_legacy_tp_is_exposed(void)
+{
+ /*
+ * The tracepoints "kmem:kmalloc_node" and
+ * "kmem:kmem_cache_alloc_node" have been removed on the latest
+ * kernel, if the tracepoint "kmem:kmalloc_node" is existed it
+ * means the tool is running on an old kernel, we need to
+ * rollback to support these legacy tracepoints.
+ */
+ return IS_ERR(trace_event__tp_format("kmem", "kmalloc_node")) ?
+ false : true;
+}
+
static int __cmd_record(int argc, const char **argv)
{
const char * const record_args[] = {
};
const char * const slab_events[] = {
"-e", "kmem:kmalloc",
- "-e", "kmem:kmalloc_node",
"-e", "kmem:kfree",
"-e", "kmem:kmem_cache_alloc",
- "-e", "kmem:kmem_cache_alloc_node",
"-e", "kmem:kmem_cache_free",
};
+ const char * const slab_legacy_events[] = {
+ "-e", "kmem:kmalloc_node",
+ "-e", "kmem:kmem_cache_alloc_node",
+ };
const char * const page_events[] = {
"-e", "kmem:mm_page_alloc",
"-e", "kmem:mm_page_free",
};
unsigned int rec_argc, i, j;
const char **rec_argv;
+ unsigned int slab_legacy_tp_exposed = slab_legacy_tp_is_exposed();
rec_argc = ARRAY_SIZE(record_args) + argc - 1;
- if (kmem_slab)
+ if (kmem_slab) {
rec_argc += ARRAY_SIZE(slab_events);
+ if (slab_legacy_tp_exposed)
+ rec_argc += ARRAY_SIZE(slab_legacy_events);
+ }
if (kmem_page)
rec_argc += ARRAY_SIZE(page_events) + 1; /* for -g */
if (kmem_slab) {
for (j = 0; j < ARRAY_SIZE(slab_events); j++, i++)
rec_argv[i] = strdup(slab_events[j]);
+ if (slab_legacy_tp_exposed) {
+ for (j = 0; j < ARRAY_SIZE(slab_legacy_events); j++, i++)
+ rec_argv[i] = strdup(slab_legacy_events[j]);
+ }
}
if (kmem_page) {
rec_argv[i++] = strdup("-g");
/* for lock function check */
symbol_conf.sort_by_name = true;
+ symbol_conf.allow_aliases = true;
symbol__init(&session->header.env);
if (!data.is_pipe) {
/* for lock function check */
symbol_conf.sort_by_name = true;
+ symbol_conf.allow_aliases = true;
symbol__init(&session->header.env);
if (use_bpf) {
#include "util/record.h"
#include <api/fs/tracing_path.h>
+#ifdef HAVE_LIBBPF_SUPPORT
#include <bpf/bpf.h>
+#endif
#include "util/bpf_map.h"
#include "util/rlimit.h"
#include "builtin.h"
perf-inject mainporcelain common
perf-iostat mainporcelain common
perf-kallsyms mainporcelain common
-perf-kmem mainporcelain common
+perf-kmem mainporcelain traceevent
perf-kvm mainporcelain common
-perf-kwork mainporcelain common
+perf-kwork mainporcelain traceevent
perf-list mainporcelain common
-perf-lock mainporcelain common
+perf-lock mainporcelain traceevent
perf-mem mainporcelain common
perf-probe mainporcelain full
perf-record mainporcelain common
perf-report mainporcelain common
-perf-sched mainporcelain common
+perf-sched mainporcelain traceevent
perf-script mainporcelain common
perf-stat mainporcelain common
perf-test mainporcelain common
-perf-timechart mainporcelain common
+perf-timechart mainporcelain traceevent
perf-top mainporcelain common
perf-trace mainporcelain audit
perf-version mainporcelain common
# undef if
#endif
+typedef unsigned int __bitwise fmode_t;
+
#define FMODE_READ 0x1
#define FMODE_WRITE 0x2
installed_files_bin += etc/bash_completion.d/perf
installed_files_bin += libexec/perf-core/perf-archive
-installed_files_plugins := $(lib)/traceevent/plugins/plugin_cfg80211.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_scsi.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_xen.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_function.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_sched_switch.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_mac80211.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_kvm.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_kmem.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_hrtimer.so
-installed_files_plugins += $(lib)/traceevent/plugins/plugin_jbd2.so
-
installed_files_all := $(installed_files_bin)
-installed_files_all += $(installed_files_plugins)
test_make_install := $(call test_dest_files,$(installed_files_all))
test_make_install_O := $(call test_dest_files,$(installed_files_all))
case "$(uname -m)" in
s390x)
eventattr='call-graph=dwarf,max-stack=4'
+ echo "text_to_binary_address.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
echo "(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
echo "main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
perf_data=`mktemp -u /tmp/perf.data.XXX`
perf_script=`mktemp -u /tmp/perf.script.XXX`
perf record -e $event_name/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1
- perf script -i $perf_data > $perf_script
+ perf script -i $perf_data | tac | grep -m1 ^ping -B9 | tac > $perf_script
exec 3<$perf_script
exec 4<$expected
if test -d ../../.git -o -f ../../.git
then
TAG=$(MAKEFLAGS= make -sC ../.. kernelversion)
- CID=$(git log -1 --abbrev=12 --pretty=format:"%h" 2>/dev/null) && CID="-g$CID"
+ CID=$(git log -1 --abbrev=12 --pretty=format:"%h" --no-show-signature 2>/dev/null) && CID="-g$CID"
elif test -f ../../PERF-VERSION-FILE
then
TAG=$(cut -d' ' -f3 ../../PERF-VERSION-FILE | sed -e 's/\"//g')
*size = sym->start - *start;
if (idx > 0) {
if (*size)
- return 1;
+ return 0;
} else if (dso_sym_match(sym, sym_name, &cnt, idx)) {
print_duplicate_syms(dso, sym_name);
return -EINVAL;
#include <linux/list.h>
#include <sys/resource.h>
+
+#ifdef HAVE_LIBBPF_SUPPORT
#include <bpf/bpf.h>
#include <bpf/btf.h>
#include <bpf/libbpf.h>
+#endif
struct evsel;
struct target;
setrlimit(RLIMIT_MEMLOCK, &rinf);
}
+#ifdef HAVE_BPF_SKEL
+
static inline __u32 bpf_link_get_id(int fd)
{
struct bpf_link_info link_info = { .id = 0, };
return bpf_prog_test_run_opts(prog_fd, &opts);
}
+#endif /* HAVE_BPF_SKEL */
#endif /* __PERF_BPF_COUNTER_H */
/* open single copy of the events w/o cgroup */
err = evsel__open_per_cpu(evsel, evsel->core.cpus, -1);
- if (err) {
- pr_err("Failed to open first cgroup events\n");
- goto out;
- }
+ if (err == 0)
+ evsel->supported = true;
map_fd = bpf_map__fd(skel->maps.events);
perf_cpu_map__for_each_cpu(cpu, j, evsel->core.cpus) {
int fd = FD(evsel, j);
__u32 idx = evsel->core.idx * total_cpus + cpu.cpu;
- err = bpf_map_update_elem(map_fd, &idx, &fd,
- BPF_ANY);
- if (err < 0) {
- pr_err("Failed to update perf_event fd\n");
- goto out;
- }
+ bpf_map_update_elem(map_fd, &idx, &fd, BPF_ANY);
}
evsel->cgrp = leader_cgrp;
}
- evsel->supported = true;
if (evsel->cgrp == cgrp)
continue;
return 0;
}
+static int check_and_add_cgroup_name(const char *fpath)
+{
+ struct cgroup_name *cn;
+
+ list_for_each_entry(cn, &cgroup_list, list) {
+ if (!strcmp(cn->name, fpath))
+ return 0;
+ }
+
+ /* pretend if it's added by ftw() */
+ return add_cgroup_name(fpath, NULL, FTW_D, NULL);
+}
+
static void release_cgroup_list(void)
{
struct cgroup_name *cn;
struct cgroup_name *cn;
char *s;
- /* use given name as is - for testing purpose */
+ /* use given name as is when no regex is given */
for (;;) {
p = strchr(str, ',');
e = p ? p : eos;
s = strndup(str, e - str);
if (!s)
return -1;
- /* pretend if it's added by ftw() */
- ret = add_cgroup_name(s, NULL, FTW_D, NULL);
+
+ ret = check_and_add_cgroup_name(s);
free(s);
- if (ret)
+ if (ret < 0)
return -1;
} else {
- if (add_cgroup_name("", NULL, FTW_D, NULL) < 0)
+ if (check_and_add_cgroup_name("/") < 0)
return -1;
}
file->size = st.st_size;
}
+ closedir(dir);
if (!files)
return -EINVAL;
return 0;
out_err:
+ closedir(dir);
close_dir(files, nr);
return ret;
}
done
echo "#endif /* HAVE_LIBELF_SUPPORT */"
-echo "#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT)"
+echo "#if defined(HAVE_LIBTRACEEVENT) && (defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT))"
sed -n -e 's/^perf-\([^ ]*\)[ ].* audit*/\1/p' command-list.txt |
sort |
while read cmd
p
}' "Documentation/perf-$cmd.txt"
done
-echo "#endif /* HAVE_LIBELF_SUPPORT */"
+echo "#endif /* HAVE_LIBTRACEEVENT && (HAVE_LIBAUDIT_SUPPORT || HAVE_SYSCALL_TABLE_SUPPORT) */"
+
+echo "#ifdef HAVE_LIBTRACEEVENT"
+sed -n -e 's/^perf-\([^ ]*\)[ ].* traceevent.*/\1/p' command-list.txt |
+sort |
+while read cmd
+do
+ sed -n '
+ /^NAME/,/perf-'"$cmd"'/H
+ ${
+ x
+ s/.*perf-'"$cmd"' - \(.*\)/ {"'"$cmd"'", "\1"},/
+ p
+ }' "Documentation/perf-$cmd.txt"
+done
+echo "#endif /* HAVE_LIBTRACEEVENT */"
echo "};"
ret = add_all_matching_fields(evlist, field_name, raw_trace, level);
goto out;
}
+#else
+ evlist__for_each_entry(evlist, evsel) {
+ if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT) {
+ pr_err("%s %s", ret ? "," : "This perf binary isn't linked with libtraceevent, can't process", evsel__name(evsel));
+ ret = -ENOTSUP;
+ }
+ }
+
+ if (ret) {
+ pr_err("\n");
+ goto out;
+ }
#endif
evsel = find_evsel(evlist, event_name);
#include <stdbool.h>
#include <stdio.h>
+#include <sys/types.h>
#include <linux/types.h>
struct evlist;
main
memblock.c
linux/memblock.h
+asm/asm.h
asm/cmpxchg.h
@mkdir -p linux
test -L linux/memblock.h || ln -s ../../../../include/linux/memblock.h linux/memblock.h
+ test -L asm/asm.h || ln -s ../../../arch/x86/include/asm/asm.h asm/asm.h
test -L asm/cmpxchg.h || ln -s ../../../arch/x86/include/asm/cmpxchg.h asm/cmpxchg.h
memblock.c: $(EXTR_SRC)
test -L memblock.c || ln -s $(EXTR_SRC) memblock.c
clean:
- $(RM) $(TARGETS) $(OFILES) linux/memblock.h memblock.c asm/cmpxchg.h
+ $(RM) $(TARGETS) $(OFILES) linux/memblock.h memblock.c asm/asm.h asm/cmpxchg.h
help:
@echo 'Memblock simulator'
struct page {};
+void __free_pages_core(struct page *page, unsigned int order)
+{
+}
+
void memblock_free_pages(struct page *page, unsigned long pfn,
unsigned int order)
{
*.lskel.h
/no_alu32
/bpf_gcc
+/host-tools
/tools
/runqslower
/bench
cgrp_local_storage # prog_attach unexpected error: -524 (trampoline)
core_read_macros # unknown func bpf_probe_read#4 (overlapping)
d_path # failed to auto-attach program 'prog_stat': -524 (trampoline)
+decap_sanity # JIT does not support calling kernel function (kfunc)
deny_namespace # failed to attach: ERROR: strerror_r(-524)=22 (trampoline)
dummy_st_ops # test_run unexpected error: -524 (errno 524) (trampoline)
fentry_fexit # fentry attach failed: -524 (trampoline)
bpf_iter_task_vma__destroy(skel);
}
+static void test_task_vma_dead_task(void)
+{
+ struct bpf_iter_task_vma *skel;
+ int wstatus, child_pid = -1;
+ time_t start_tm, cur_tm;
+ int err, iter_fd = -1;
+ int wait_sec = 3;
+
+ skel = bpf_iter_task_vma__open();
+ if (!ASSERT_OK_PTR(skel, "bpf_iter_task_vma__open"))
+ return;
+
+ skel->bss->pid = getpid();
+
+ err = bpf_iter_task_vma__load(skel);
+ if (!ASSERT_OK(err, "bpf_iter_task_vma__load"))
+ goto out;
+
+ skel->links.proc_maps = bpf_program__attach_iter(
+ skel->progs.proc_maps, NULL);
+
+ if (!ASSERT_OK_PTR(skel->links.proc_maps, "bpf_program__attach_iter")) {
+ skel->links.proc_maps = NULL;
+ goto out;
+ }
+
+ start_tm = time(NULL);
+ cur_tm = start_tm;
+
+ child_pid = fork();
+ if (child_pid == 0) {
+ /* Fork short-lived processes in the background. */
+ while (cur_tm < start_tm + wait_sec) {
+ system("echo > /dev/null");
+ cur_tm = time(NULL);
+ }
+ exit(0);
+ }
+
+ if (!ASSERT_GE(child_pid, 0, "fork_child"))
+ goto out;
+
+ while (cur_tm < start_tm + wait_sec) {
+ iter_fd = bpf_iter_create(bpf_link__fd(skel->links.proc_maps));
+ if (!ASSERT_GE(iter_fd, 0, "create_iter"))
+ goto out;
+
+ /* Drain all data from iter_fd. */
+ while (cur_tm < start_tm + wait_sec) {
+ err = read_fd_into_buffer(iter_fd, task_vma_output, CMP_BUFFER_SIZE);
+ if (!ASSERT_GE(err, 0, "read_iter_fd"))
+ goto out;
+
+ cur_tm = time(NULL);
+
+ if (err == 0)
+ break;
+ }
+
+ close(iter_fd);
+ iter_fd = -1;
+ }
+
+ check_bpf_link_info(skel->progs.proc_maps);
+
+out:
+ waitpid(child_pid, &wstatus, 0);
+ close(iter_fd);
+ bpf_iter_task_vma__destroy(skel);
+}
+
void test_bpf_sockmap_map_iter_fd(void)
{
struct bpf_iter_sockmap *skel;
test_task_file();
if (test__start_subtest("task_vma"))
test_task_vma();
+ if (test__start_subtest("task_vma_dead_task"))
+ test_task_vma_dead_task();
if (test__start_subtest("task_btf"))
test_task_btf();
if (test__start_subtest("tcp4"))
static void test_btf_dump_var_data(struct btf *btf, struct btf_dump *d,
char *str)
{
-#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__)
+#if 0
TEST_BTF_DUMP_VAR(btf, d, NULL, str, "cpu_number", int, BTF_F_COMPACT,
"int cpu_number = (int)100", 100);
#endif
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <net/if.h>
+#include <linux/in6.h>
+
+#include "test_progs.h"
+#include "network_helpers.h"
+#include "decap_sanity.skel.h"
+
+#define SYS(fmt, ...) \
+ ({ \
+ char cmd[1024]; \
+ snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__); \
+ if (!ASSERT_OK(system(cmd), cmd)) \
+ goto fail; \
+ })
+
+#define NS_TEST "decap_sanity_ns"
+#define IPV6_IFACE_ADDR "face::1"
+#define UDP_TEST_PORT 7777
+
+void test_decap_sanity(void)
+{
+ LIBBPF_OPTS(bpf_tc_hook, qdisc_hook, .attach_point = BPF_TC_EGRESS);
+ LIBBPF_OPTS(bpf_tc_opts, tc_attach);
+ struct nstoken *nstoken = NULL;
+ struct decap_sanity *skel;
+ struct sockaddr_in6 addr;
+ socklen_t addrlen;
+ char buf[128] = {};
+ int sockfd, err;
+
+ skel = decap_sanity__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel open_and_load"))
+ return;
+
+ SYS("ip netns add %s", NS_TEST);
+ SYS("ip -net %s -6 addr add %s/128 dev lo nodad", NS_TEST, IPV6_IFACE_ADDR);
+ SYS("ip -net %s link set dev lo up", NS_TEST);
+
+ nstoken = open_netns(NS_TEST);
+ if (!ASSERT_OK_PTR(nstoken, "open_netns"))
+ goto fail;
+
+ qdisc_hook.ifindex = if_nametoindex("lo");
+ if (!ASSERT_GT(qdisc_hook.ifindex, 0, "if_nametoindex lo"))
+ goto fail;
+
+ err = bpf_tc_hook_create(&qdisc_hook);
+ if (!ASSERT_OK(err, "create qdisc hook"))
+ goto fail;
+
+ tc_attach.prog_fd = bpf_program__fd(skel->progs.decap_sanity);
+ err = bpf_tc_attach(&qdisc_hook, &tc_attach);
+ if (!ASSERT_OK(err, "attach filter"))
+ goto fail;
+
+ addrlen = sizeof(addr);
+ err = make_sockaddr(AF_INET6, IPV6_IFACE_ADDR, UDP_TEST_PORT,
+ (void *)&addr, &addrlen);
+ if (!ASSERT_OK(err, "make_sockaddr"))
+ goto fail;
+ sockfd = socket(AF_INET6, SOCK_DGRAM, 0);
+ if (!ASSERT_NEQ(sockfd, -1, "socket"))
+ goto fail;
+ err = sendto(sockfd, buf, sizeof(buf), 0, (void *)&addr, addrlen);
+ close(sockfd);
+ if (!ASSERT_EQ(err, sizeof(buf), "send"))
+ goto fail;
+
+ ASSERT_TRUE(skel->bss->init_csum_partial, "init_csum_partial");
+ ASSERT_TRUE(skel->bss->final_csum_none, "final_csum_none");
+ ASSERT_FALSE(skel->bss->broken_csum_start, "broken_csum_start");
+
+fail:
+ if (nstoken) {
+ bpf_tc_hook_destroy(&qdisc_hook);
+ close_netns(nstoken);
+ }
+ system("ip netns del " NS_TEST " >& /dev/null");
+ decap_sanity__destroy(skel);
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "jeq_infer_not_null_fail.skel.h"
+
+void test_jeq_infer_not_null(void)
+{
+ RUN_TESTS(jeq_infer_not_null_fail);
+}
#define ICSK_TIME_LOSS_PROBE 5
#define ICSK_TIME_REO_TIMEOUT 6
+#define ETH_HLEN 14
+#define ETH_P_IPV6 0x86DD
+
+#define CHECKSUM_NONE 0
+#define CHECKSUM_PARTIAL 3
+
#define IFNAMSIZ 16
#define RTF_GATEWAY 0x0002
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include "bpf_tracing_net.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define UDP_TEST_PORT 7777
+
+void *bpf_cast_to_kern_ctx(void *) __ksym;
+bool init_csum_partial = false;
+bool final_csum_none = false;
+bool broken_csum_start = false;
+
+static unsigned int skb_headlen(const struct sk_buff *skb)
+{
+ return skb->len - skb->data_len;
+}
+
+static unsigned int skb_headroom(const struct sk_buff *skb)
+{
+ return skb->data - skb->head;
+}
+
+static int skb_checksum_start_offset(const struct sk_buff *skb)
+{
+ return skb->csum_start - skb_headroom(skb);
+}
+
+SEC("tc")
+int decap_sanity(struct __sk_buff *skb)
+{
+ struct sk_buff *kskb;
+ struct ipv6hdr ip6h;
+ struct udphdr udph;
+ int err;
+
+ if (skb->protocol != __bpf_constant_htons(ETH_P_IPV6))
+ return TC_ACT_SHOT;
+
+ if (bpf_skb_load_bytes(skb, ETH_HLEN, &ip6h, sizeof(ip6h)))
+ return TC_ACT_SHOT;
+
+ if (ip6h.nexthdr != IPPROTO_UDP)
+ return TC_ACT_SHOT;
+
+ if (bpf_skb_load_bytes(skb, ETH_HLEN + sizeof(ip6h), &udph, sizeof(udph)))
+ return TC_ACT_SHOT;
+
+ if (udph.dest != __bpf_constant_htons(UDP_TEST_PORT))
+ return TC_ACT_SHOT;
+
+ kskb = bpf_cast_to_kern_ctx(skb);
+ init_csum_partial = (kskb->ip_summed == CHECKSUM_PARTIAL);
+ err = bpf_skb_adjust_room(skb, -(s32)(ETH_HLEN + sizeof(ip6h) + sizeof(udph)),
+ 1, BPF_F_ADJ_ROOM_FIXED_GSO);
+ if (err)
+ return TC_ACT_SHOT;
+ final_csum_none = (kskb->ip_summed == CHECKSUM_NONE);
+ if (kskb->ip_summed == CHECKSUM_PARTIAL &&
+ (unsigned int)skb_checksum_start_offset(kskb) >= skb_headlen(kskb))
+ broken_csum_start = true;
+
+ return TC_ACT_SHOT;
+}
+
+char __license[] SEC("license") = "GPL";
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(max_entries, 1);
+ __type(key, u64);
+ __type(value, u64);
+} m_hash SEC(".maps");
+
+SEC("?raw_tp")
+__failure __msg("R8 invalid mem access 'map_value_or_null")
+int jeq_infer_not_null_ptr_to_btfid(void *ctx)
+{
+ struct bpf_map *map = (struct bpf_map *)&m_hash;
+ struct bpf_map *inner_map = map->inner_map_meta;
+ u64 key = 0, ret = 0, *val;
+
+ val = bpf_map_lookup_elem(map, &key);
+ /* Do not mark ptr as non-null if one of them is
+ * PTR_TO_BTF_ID (R9), reject because of invalid
+ * access to map value (R8).
+ *
+ * Here, we need to inline those insns to access
+ * R8 directly, since compiler may use other reg
+ * once it figures out val==inner_map.
+ */
+ asm volatile("r8 = %[val];\n"
+ "r9 = %[inner_map];\n"
+ "if r8 != r9 goto +1;\n"
+ "%[ret] = *(u64 *)(r8 +0);\n"
+ : [ret] "+r"(ret)
+ : [inner_map] "r"(inner_map), [val] "r"(val)
+ : "r8", "r9");
+
+ return ret;
+}
# SPDX-License-Identifier: GPL-2.0-only
bind_bhash
+bind_timewait
csum
cmsg_sender
diag_uid
wait_for_signal(pipefd[0]);
if (connect(cfd, (struct sockaddr *)consumer_addr,
- sizeof(struct sockaddr)) != 0) {
+ sizeof(*consumer_addr)) != 0) {
perror("Connect failed");
kill(0, SIGTERM);
exit(1);
readonly V6_ADDR0=2001:db8:91::1
readonly V6_ADDR1=2001:db8:91::2
nsid=100
+ret=0
cleanup_v6()
{
ip netns del me
ip netns del peer
- sysctl -w net.ipv4.conf.veth0.ndisc_evict_nocarrier=1 >/dev/null 2>&1
- sysctl -w net.ipv4.conf.all.ndisc_evict_nocarrier=1 >/dev/null 2>&1
+ sysctl -w net.ipv6.conf.veth1.ndisc_evict_nocarrier=1 >/dev/null 2>&1
+ sysctl -w net.ipv6.conf.all.ndisc_evict_nocarrier=1 >/dev/null 2>&1
}
create_ns()
if [ $? -ne 0 ]; then
cleanup_v6
echo "failed"
- exit
+ exit 1
fi
# Set veth2 down, which will put veth1 in NOCARRIER state
if [ $? -ne 0 ]; then
cleanup_v4
echo "failed"
- exit
+ exit 1
fi
# Set veth1 down, which will put veth0 in NOCARRIER state
if [ $? -eq 0 ];then
echo "failed"
+ ret=1
else
echo "ok"
fi
echo "ok"
else
echo "failed"
+ ret=1
fi
cleanup_v4
if [ $? -eq 0 ];then
echo "failed"
+ ret=1
else
echo "ok"
fi
echo "ok"
else
echo "failed"
+ ret=1
fi
cleanup_v6
echo "ok"
else
echo "failed"
+ ret=1
fi
cleanup_v6
fi
run_all_tests
+exit $ret
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Amazon.com Inc. or its affiliates. */
+
+#include <sys/socket.h>
+#include <netinet/in.h>
+
+#include "../kselftest_harness.h"
+
+FIXTURE(bind_timewait)
+{
+ struct sockaddr_in addr;
+ socklen_t addrlen;
+};
+
+FIXTURE_VARIANT(bind_timewait)
+{
+ __u32 addr_const;
+};
+
+FIXTURE_VARIANT_ADD(bind_timewait, localhost)
+{
+ .addr_const = INADDR_LOOPBACK
+};
+
+FIXTURE_VARIANT_ADD(bind_timewait, addrany)
+{
+ .addr_const = INADDR_ANY
+};
+
+FIXTURE_SETUP(bind_timewait)
+{
+ self->addr.sin_family = AF_INET;
+ self->addr.sin_port = 0;
+ self->addr.sin_addr.s_addr = htonl(variant->addr_const);
+ self->addrlen = sizeof(self->addr);
+}
+
+FIXTURE_TEARDOWN(bind_timewait)
+{
+}
+
+void create_timewait_socket(struct __test_metadata *_metadata,
+ FIXTURE_DATA(bind_timewait) *self)
+{
+ int server_fd, client_fd, child_fd, ret;
+ struct sockaddr_in addr;
+ socklen_t addrlen;
+
+ server_fd = socket(AF_INET, SOCK_STREAM, 0);
+ ASSERT_GT(server_fd, 0);
+
+ ret = bind(server_fd, (struct sockaddr *)&self->addr, self->addrlen);
+ ASSERT_EQ(ret, 0);
+
+ ret = listen(server_fd, 1);
+ ASSERT_EQ(ret, 0);
+
+ ret = getsockname(server_fd, (struct sockaddr *)&self->addr, &self->addrlen);
+ ASSERT_EQ(ret, 0);
+
+ client_fd = socket(AF_INET, SOCK_STREAM, 0);
+ ASSERT_GT(client_fd, 0);
+
+ ret = connect(client_fd, (struct sockaddr *)&self->addr, self->addrlen);
+ ASSERT_EQ(ret, 0);
+
+ addrlen = sizeof(addr);
+ child_fd = accept(server_fd, (struct sockaddr *)&addr, &addrlen);
+ ASSERT_GT(child_fd, 0);
+
+ close(child_fd);
+ close(client_fd);
+ close(server_fd);
+}
+
+TEST_F(bind_timewait, 1)
+{
+ int fd, ret;
+
+ create_timewait_socket(_metadata, self);
+
+ fd = socket(AF_INET, SOCK_STREAM, 0);
+ ASSERT_GT(fd, 0);
+
+ ret = bind(fd, (struct sockaddr *)&self->addr, self->addrlen);
+ ASSERT_EQ(ret, -1);
+ ASSERT_EQ(errno, EADDRINUSE);
+
+ close(fd);
+}
+
+TEST_HARNESS_MAIN
static void cs_parse_args(int argc, char *argv[])
{
- char o;
+ int o;
while ((o = getopt(argc, argv, "46sS:p:m:M:d:tf:F:c:C:l:L:H:")) != -1) {
switch (o) {
# In addition this script also checks if forcing a specific field in the
# outer header is working.
+# Return 4 by default (Kselftest SKIP code)
+ERR=4
+
if [ "$(id -u)" != "0" ]; then
echo "Please run as root."
- exit 0
+ exit $ERR
fi
if ! which tcpdump > /dev/null 2>&1; then
echo "No tcpdump found. Required for this test."
- exit 0
+ exit $ERR
fi
expected_tos="0x00"
expected_ttl="0"
failed=false
+readonly NS0=$(mktemp -u ns0-XXXXXXXX)
+readonly NS1=$(mktemp -u ns1-XXXXXXXX)
+
+RUN_NS0="ip netns exec ${NS0}"
+
get_random_tos() {
# Get a random hex tos value between 0x00 and 0xfc, a multiple of 4
echo "0x$(tr -dc '0-9a-f' < /dev/urandom | head -c 1)\
local vlan="$5"
local test_tos="0x00"
local test_ttl="0"
- local ns="ip netns exec testing"
# We don't want a test-tos of 0x00,
# because this is the value that we get when no tos is set.
printf "│%7s │%6s │%6s │%13s │%13s │%6s │" \
"$type" "$outer" "$inner" "$tos" "$ttl" "$vlan"
- # Create 'testing' netns, veth pair and connect main ns with testing ns
- ip netns add testing
- ip link add type veth
- ip link set veth1 netns testing
- ip link set veth0 up
- $ns ip link set veth1 up
- ip addr flush dev veth0
- $ns ip addr flush dev veth1
+ # Create netns NS0 and NS1 and connect them with a veth pair
+ ip netns add "${NS0}"
+ ip netns add "${NS1}"
+ ip link add name veth0 netns "${NS0}" type veth \
+ peer name veth1 netns "${NS1}"
+ ip -netns "${NS0}" link set dev veth0 up
+ ip -netns "${NS1}" link set dev veth1 up
+ ip -netns "${NS0}" address flush dev veth0
+ ip -netns "${NS1}" address flush dev veth1
local local_addr1=""
local local_addr2=""
if [ "$type" = "gre" ]; then
type="gretap"
fi
- ip addr add 198.18.0.1/24 dev veth0
- $ns ip addr add 198.18.0.2/24 dev veth1
- ip link add name tep0 type $type $local_addr1 remote \
- 198.18.0.2 tos $test_tos ttl $test_ttl $vxlan $geneve
- $ns ip link add name tep1 type $type $local_addr2 remote \
- 198.18.0.1 tos $test_tos ttl $test_ttl $vxlan $geneve
+ ip -netns "${NS0}" address add 198.18.0.1/24 dev veth0
+ ip -netns "${NS1}" address add 198.18.0.2/24 dev veth1
+ ip -netns "${NS0}" link add name tep0 type $type $local_addr1 \
+ remote 198.18.0.2 tos $test_tos ttl $test_ttl \
+ $vxlan $geneve
+ ip -netns "${NS1}" link add name tep1 type $type $local_addr2 \
+ remote 198.18.0.1 tos $test_tos ttl $test_ttl \
+ $vxlan $geneve
elif [ "$outer" = "6" ]; then
if [ "$type" = "gre" ]; then
type="ip6gretap"
fi
- ip addr add fdd1:ced0:5d88:3fce::1/64 dev veth0
- $ns ip addr add fdd1:ced0:5d88:3fce::2/64 dev veth1
- ip link add name tep0 type $type $local_addr1 \
- remote fdd1:ced0:5d88:3fce::2 tos $test_tos ttl $test_ttl \
- $vxlan $geneve
- $ns ip link add name tep1 type $type $local_addr2 \
- remote fdd1:ced0:5d88:3fce::1 tos $test_tos ttl $test_ttl \
- $vxlan $geneve
+ ip -netns "${NS0}" address add fdd1:ced0:5d88:3fce::1/64 \
+ dev veth0 nodad
+ ip -netns "${NS1}" address add fdd1:ced0:5d88:3fce::2/64 \
+ dev veth1 nodad
+ ip -netns "${NS0}" link add name tep0 type $type $local_addr1 \
+ remote fdd1:ced0:5d88:3fce::2 tos $test_tos \
+ ttl $test_ttl $vxlan $geneve
+ ip -netns "${NS1}" link add name tep1 type $type $local_addr2 \
+ remote fdd1:ced0:5d88:3fce::1 tos $test_tos \
+ ttl $test_ttl $vxlan $geneve
fi
# Bring L2-tunnel link up and create VLAN on top
- ip link set tep0 up
- $ns ip link set tep1 up
- ip addr flush dev tep0
- $ns ip addr flush dev tep1
+ ip -netns "${NS0}" link set tep0 up
+ ip -netns "${NS1}" link set tep1 up
+ ip -netns "${NS0}" address flush dev tep0
+ ip -netns "${NS1}" address flush dev tep1
local parent
if $vlan; then
parent="vlan99-"
- ip link add link tep0 name ${parent}0 type vlan id 99
- $ns ip link add link tep1 name ${parent}1 type vlan id 99
- ip link set ${parent}0 up
- $ns ip link set ${parent}1 up
- ip addr flush dev ${parent}0
- $ns ip addr flush dev ${parent}1
+ ip -netns "${NS0}" link add link tep0 name ${parent}0 \
+ type vlan id 99
+ ip -netns "${NS1}" link add link tep1 name ${parent}1 \
+ type vlan id 99
+ ip -netns "${NS0}" link set dev ${parent}0 up
+ ip -netns "${NS1}" link set dev ${parent}1 up
+ ip -netns "${NS0}" address flush dev ${parent}0
+ ip -netns "${NS1}" address flush dev ${parent}1
else
parent="tep"
fi
# Assign inner IPv4/IPv6 addresses
if [ "$inner" = "4" ] || [ "$inner" = "other" ]; then
- ip addr add 198.19.0.1/24 brd + dev ${parent}0
- $ns ip addr add 198.19.0.2/24 brd + dev ${parent}1
+ ip -netns "${NS0}" address add 198.19.0.1/24 brd + dev ${parent}0
+ ip -netns "${NS1}" address add 198.19.0.2/24 brd + dev ${parent}1
elif [ "$inner" = "6" ]; then
- ip addr add fdd4:96cf:4eae:443b::1/64 dev ${parent}0
- $ns ip addr add fdd4:96cf:4eae:443b::2/64 dev ${parent}1
+ ip -netns "${NS0}" address add fdd4:96cf:4eae:443b::1/64 \
+ dev ${parent}0 nodad
+ ip -netns "${NS1}" address add fdd4:96cf:4eae:443b::2/64 \
+ dev ${parent}1 nodad
fi
}
ping_dst="198.19.0.3" # Generates ARPs which are not IPv4/IPv6
fi
if [ "$tos_ttl" = "inherit" ]; then
- ping -i 0.1 $ping_dst -Q "$expected_tos" -t "$expected_ttl" \
- 2>/dev/null 1>&2 & ping_pid="$!"
+ ${RUN_NS0} ping -i 0.1 $ping_dst -Q "$expected_tos" \
+ -t "$expected_ttl" 2>/dev/null 1>&2 & ping_pid="$!"
else
- ping -i 0.1 $ping_dst 2>/dev/null 1>&2 & ping_pid="$!"
+ ${RUN_NS0} ping -i 0.1 $ping_dst 2>/dev/null 1>&2 & ping_pid="$!"
fi
local tunnel_type_offset tunnel_type_proto req_proto_offset req_offset
if [ "$type" = "gre" ]; then
req_proto_offset="$((req_proto_offset + 4))"
req_offset="$((req_offset + 4))"
fi
- out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \
- ip[$tunnel_type_offset] = $tunnel_type_proto and \
- ip[$req_proto_offset] = 0x01 and \
- ip[$req_offset] = 0x08 2>/dev/null | head -n 1)"
+ out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \
+ -i veth0 -n \
+ ip[$tunnel_type_offset] = $tunnel_type_proto and \
+ ip[$req_proto_offset] = 0x01 and \
+ ip[$req_offset] = 0x08 2>/dev/null \
+ | head -n 1)"
elif [ "$inner" = "6" ]; then
req_proto_offset="44"
req_offset="78"
req_proto_offset="$((req_proto_offset + 4))"
req_offset="$((req_offset + 4))"
fi
- out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \
- ip[$tunnel_type_offset] = $tunnel_type_proto and \
- ip[$req_proto_offset] = 0x3a and \
- ip[$req_offset] = 0x80 2>/dev/null | head -n 1)"
+ out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \
+ -i veth0 -n \
+ ip[$tunnel_type_offset] = $tunnel_type_proto and \
+ ip[$req_proto_offset] = 0x3a and \
+ ip[$req_offset] = 0x80 2>/dev/null \
+ | head -n 1)"
elif [ "$inner" = "other" ]; then
req_proto_offset="36"
req_offset="45"
expected_tos="0x00"
expected_ttl="64"
fi
- out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \
- ip[$tunnel_type_offset] = $tunnel_type_proto and \
- ip[$req_proto_offset] = 0x08 and \
- ip[$((req_proto_offset + 1))] = 0x06 and \
- ip[$req_offset] = 0x01 2>/dev/null | head -n 1)"
+ out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \
+ -i veth0 -n \
+ ip[$tunnel_type_offset] = $tunnel_type_proto and \
+ ip[$req_proto_offset] = 0x08 and \
+ ip[$((req_proto_offset + 1))] = 0x06 and \
+ ip[$req_offset] = 0x01 2>/dev/null \
+ | head -n 1)"
fi
elif [ "$outer" = "6" ]; then
if [ "$type" = "gre" ]; then
req_proto_offset="$((req_proto_offset + 4))"
req_offset="$((req_offset + 4))"
fi
- out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \
- ip6[$tunnel_type_offset] = $tunnel_type_proto and \
- ip6[$req_proto_offset] = 0x01 and \
- ip6[$req_offset] = 0x08 2>/dev/null | head -n 1)"
+ out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \
+ -i veth0 -n \
+ ip6[$tunnel_type_offset] = $tunnel_type_proto and \
+ ip6[$req_proto_offset] = 0x01 and \
+ ip6[$req_offset] = 0x08 2>/dev/null \
+ | head -n 1)"
elif [ "$inner" = "6" ]; then
local req_proto_offset="72"
local req_offset="106"
req_proto_offset="$((req_proto_offset + 4))"
req_offset="$((req_offset + 4))"
fi
- out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \
- ip6[$tunnel_type_offset] = $tunnel_type_proto and \
- ip6[$req_proto_offset] = 0x3a and \
- ip6[$req_offset] = 0x80 2>/dev/null | head -n 1)"
+ out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \
+ -i veth0 -n \
+ ip6[$tunnel_type_offset] = $tunnel_type_proto and \
+ ip6[$req_proto_offset] = 0x3a and \
+ ip6[$req_offset] = 0x80 2>/dev/null \
+ | head -n 1)"
elif [ "$inner" = "other" ]; then
local req_proto_offset="64"
local req_offset="73"
expected_tos="0x00"
expected_ttl="64"
fi
- out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \
- ip6[$tunnel_type_offset] = $tunnel_type_proto and \
- ip6[$req_proto_offset] = 0x08 and \
- ip6[$((req_proto_offset + 1))] = 0x06 and \
- ip6[$req_offset] = 0x01 2>/dev/null | head -n 1)"
+ out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \
+ -i veth0 -n \
+ ip6[$tunnel_type_offset] = $tunnel_type_proto and \
+ ip6[$req_proto_offset] = 0x08 and \
+ ip6[$((req_proto_offset + 1))] = 0x06 and \
+ ip6[$req_offset] = 0x01 2>/dev/null \
+ | head -n 1)"
fi
fi
kill -9 $ping_pid
- wait $ping_pid 2>/dev/null
+ wait $ping_pid 2>/dev/null || true
result="FAIL"
if [ "$outer" = "4" ]; then
captured_ttl="$(get_field "ttl" "$out")"
}
cleanup() {
- ip link del veth0 2>/dev/null
- ip netns del testing 2>/dev/null
- ip link del tep0 2>/dev/null
+ ip netns del "${NS0}" 2>/dev/null
+ ip netns del "${NS1}" 2>/dev/null
}
+exit_handler() {
+ # Don't exit immediately if one of the intermediate commands fails.
+ # We might be called at the end of the script, when the network
+ # namespaces have already been deleted. So cleanup() may fail, but we
+ # still need to run until 'exit $ERR' or the script won't return the
+ # correct error code.
+ set +e
+
+ cleanup
+
+ exit $ERR
+}
+
+# Restore the default SIGINT handler (just in case) and exit.
+# The exit handler will take care of cleaning everything up.
+interrupted() {
+ trap - INT
+
+ exit $ERR
+}
+
+set -e
+trap exit_handler EXIT
+trap interrupted INT
+
printf "┌────────┬───────┬───────┬──────────────┬"
printf "──────────────┬───────┬────────┐\n"
for type in gre vxlan geneve; do
printf "└────────┴───────┴───────┴──────────────┴"
printf "──────────────┴───────┴────────┘\n"
+# All tests done.
+# Set ERR appropriately: it will be returned by the exit handler.
if $failed; then
- exit 1
+ ERR=1
+else
+ ERR=0
fi
#undef NDEBUG
#include <assert.h>
#include <errno.h>
+#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
* 1: vsyscall VMA is --xp vsyscall=xonly
* 2: vsyscall VMA is r-xp vsyscall=emulate
*/
-static int g_vsyscall;
+static volatile int g_vsyscall;
static const char *g_proc_pid_maps_vsyscall;
static const char *g_proc_pid_smaps_vsyscall;
g_vsyscall = 0;
/* gettimeofday(NULL, NULL); */
+ uint64_t rax = 0xffffffffff600000;
asm volatile (
- "call %P0"
- :
- : "i" (0xffffffffff600000), "D" (NULL), "S" (NULL)
- : "rax", "rcx", "r11"
+ "call *%[rax]"
+ : [rax] "+a" (rax)
+ : "D" (NULL), "S" (NULL)
+ : "rcx", "r11"
);
g_vsyscall = 1;
g_vsyscall = 0;
/* gettimeofday(NULL, NULL); */
+ uint64_t rax = 0xffffffffff600000;
asm volatile (
- "call %P0"
- :
- : "i" (0xffffffffff600000), "D" (NULL), "S" (NULL)
- : "rax", "rcx", "r11"
+ "call *%[rax]"
+ : [rax] "+a" (rax)
+ : "D" (NULL), "S" (NULL)
+ : "rcx", "r11"
);
g_vsyscall = 1;
#define smp_wmb() smp_release()
#endif
-#ifdef __alpha__
-#define smp_read_barrier_depends() smp_acquire()
-#else
-#define smp_read_barrier_depends() do {} while(0)
-#endif
-
static __always_inline
void __read_once_size(const volatile void *p, void *res, int size)
{
- switch (size) { \
- case 1: *(unsigned char *)res = *(volatile unsigned char *)p; break; \
- case 2: *(unsigned short *)res = *(volatile unsigned short *)p; break; \
- case 4: *(unsigned int *)res = *(volatile unsigned int *)p; break; \
- case 8: *(unsigned long long *)res = *(volatile unsigned long long *)p; break; \
- default: \
- barrier(); \
- __builtin_memcpy((void *)res, (const void *)p, size); \
- barrier(); \
- } \
+ switch (size) {
+ case 1: *(unsigned char *)res = *(volatile unsigned char *)p; break;
+ case 2: *(unsigned short *)res = *(volatile unsigned short *)p; break;
+ case 4: *(unsigned int *)res = *(volatile unsigned int *)p; break;
+ case 8: *(unsigned long long *)res = *(volatile unsigned long long *)p; break;
+ default:
+ barrier();
+ __builtin_memcpy((void *)res, (const void *)p, size);
+ barrier();
+ }
}
static __always_inline void __write_once_size(volatile void *p, void *res, int size)
}
}
+#ifdef __alpha__
#define READ_ONCE(x) \
({ \
union { typeof(x) __val; char __c[1]; } __u; \
__read_once_size(&(x), __u.__c, sizeof(x)); \
- smp_read_barrier_depends(); /* Enforce dependency ordering from x */ \
+ smp_mb(); /* Enforce dependency ordering from x */ \
+ __u.__val; \
+})
+#else
+#define READ_ONCE(x) \
+({ \
+ union { typeof(x) __val; char __c[1]; } __u; \
+ __read_once_size(&(x), __u.__c, sizeof(x)); \
__u.__val; \
})
+#endif
#define WRITE_ONCE(x, val) \
({ \
if (ret)
break;
- };
+ }
return ret;
long started = 0, completed = 0, next_reset = reset_n;
long completed_before, started_before;
int r, test = 1;
- unsigned len;
+ unsigned int len;
long long spurious = 0;
const bool random_batch = batch == RANDOM_BATCH;
gvdev.vdev.features = features;
INIT_LIST_HEAD(&gvdev.vdev.vqs);
+ spin_lock_init(&gvdev.vdev.vqs_list_lock);
gvdev.to_host_fd = to_host[1];
gvdev.notifies = 0;
getrange = getrange_iov;
vdev.features = 0;
INIT_LIST_HEAD(&vdev.vqs);
+ spin_lock_init(&vdev.vqs_list_lock);
while (argv[1]) {
if (strcmp(argv[1], "--indirect") == 0)
}
mutex_lock(&kvm->lock);
+
+#ifdef CONFIG_LOCKDEP
+ /* Ensure that lockdep knows vcpu->mutex is taken *inside* kvm->lock */
+ mutex_lock(&vcpu->mutex);
+ mutex_unlock(&vcpu->mutex);
+#endif
+
if (kvm_get_vcpu_by_id(kvm, id)) {
r = -EEXIST;
goto unlock_vcpu_destroy;